[tip:perf/core] perf tools: Fix compile error with libunwind x86

2018-01-10 Thread tip-bot for Wang Nan 
Commit-ID:  44df1afdb174fd6038e419f80efd914c0b5f2f85
Gitweb: https://git.kernel.org/tip/44df1afdb174fd6038e419f80efd914c0b5f2f85
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Wed, 6 Dec 2017 01:50:40 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Mon, 8 Jan 2018 11:11:57 -0300

perf tools: Fix compile error with libunwind x86

Fix a compile error:

 ...
   CC   util/libunwind/x86_32.o
 In file included from util/libunwind/x86_32.c:33:0:
 util/libunwind/../../arch/x86/util/unwind-libunwind.c: In function 
'libunwind__x86_reg_id':
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: error: 'EINVAL' 
undeclared (first use in this function)
return -EINVAL;
^
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: note: each 
undeclared identifier is reported only once for each function it appears in
 mv: cannot stat 'util/libunwind/.x86_32.o.tmp': No such file or directory
 make[4]: *** [util/libunwind/x86_32.o] Error 1
 make[3]: *** [util] Error 2
 make[2]: *** [libperf-in.o] Error 2
 make[1]: *** [sub-make] Error 2
 make: *** [all] Error 2

It happens when libunwind-x86 feature is detected.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Link: http://lkml.kernel.org/r/20171206015040.114574-1-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/arch/x86/util/unwind-libunwind.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c 
b/tools/perf/arch/x86/util/unwind-libunwind.c
index 9c917f8..05920e3 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
 #include "perf_regs.h"
 #include "../../util/unwind.h"

[tip:perf/core] perf tools: Fix compile error with libunwind x86

2018-01-10 Thread tip-bot for Wang Nan 
Commit-ID:  44df1afdb174fd6038e419f80efd914c0b5f2f85
Gitweb: https://git.kernel.org/tip/44df1afdb174fd6038e419f80efd914c0b5f2f85
Author: Wang Nan 
AuthorDate: Wed, 6 Dec 2017 01:50:40 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Mon, 8 Jan 2018 11:11:57 -0300

perf tools: Fix compile error with libunwind x86

Fix a compile error:

 ...
   CC   util/libunwind/x86_32.o
 In file included from util/libunwind/x86_32.c:33:0:
 util/libunwind/../../arch/x86/util/unwind-libunwind.c: In function 
'libunwind__x86_reg_id':
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: error: 'EINVAL' 
undeclared (first use in this function)
return -EINVAL;
^
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: note: each 
undeclared identifier is reported only once for each function it appears in
 mv: cannot stat 'util/libunwind/.x86_32.o.tmp': No such file or directory
 make[4]: *** [util/libunwind/x86_32.o] Error 1
 make[3]: *** [util] Error 2
 make[2]: *** [libperf-in.o] Error 2
 make[1]: *** [sub-make] Error 2
 make: *** [all] Error 2

It happens when libunwind-x86 feature is detected.

Signed-off-by: Wang Nan 
Link: http://lkml.kernel.org/r/20171206015040.114574-1-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/arch/x86/util/unwind-libunwind.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c 
b/tools/perf/arch/x86/util/unwind-libunwind.c
index 9c917f8..05920e3 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
 #include "perf_regs.h"
 #include "../../util/unwind.h"

[RESEND PATCH] perf tools: Fix compiling error in libunwind x86

2017-12-17 Thread Wang Nan 
Fix a compiling error:

 ...
   CC   util/libunwind/x86_32.o
 In file included from util/libunwind/x86_32.c:33:0:
 util/libunwind/../../arch/x86/util/unwind-libunwind.c: In function 
'libunwind__x86_reg_id':
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: error: 'EINVAL' 
undeclared (first use in this function)
return -EINVAL;
^
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: note: each 
undeclared identifier is reported only once for each function it appears in
 mv: cannot stat 'util/libunwind/.x86_32.o.tmp': No such file or directory
 make[4]: *** [util/libunwind/x86_32.o] Error 1
 make[3]: *** [util] Error 2
 make[2]: *** [libperf-in.o] Error 2
 make[1]: *** [sub-make] Error 2
 make: *** [all] Error 2

It happens when libunwind-x86 feature is detected.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Arnaldo Carvalho de Melo <a...@redhat.com>
Cc: Jiri Olsa <jo...@redhat.com>
---
 tools/perf/arch/x86/util/unwind-libunwind.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c 
b/tools/perf/arch/x86/util/unwind-libunwind.c
index 9c917f8..05920e3 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-- 
2.10.1

[RESEND PATCH] perf tools: Fix compiling error in libunwind x86

2017-12-17 Thread Wang Nan 
Fix a compiling error:

 ...
   CC   util/libunwind/x86_32.o
 In file included from util/libunwind/x86_32.c:33:0:
 util/libunwind/../../arch/x86/util/unwind-libunwind.c: In function 
'libunwind__x86_reg_id':
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: error: 'EINVAL' 
undeclared (first use in this function)
return -EINVAL;
^
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: note: each 
undeclared identifier is reported only once for each function it appears in
 mv: cannot stat 'util/libunwind/.x86_32.o.tmp': No such file or directory
 make[4]: *** [util/libunwind/x86_32.o] Error 1
 make[3]: *** [util] Error 2
 make[2]: *** [libperf-in.o] Error 2
 make[1]: *** [sub-make] Error 2
 make: *** [all] Error 2

It happens when libunwind-x86 feature is detected.

Signed-off-by: Wang Nan 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
---
 tools/perf/arch/x86/util/unwind-libunwind.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c 
b/tools/perf/arch/x86/util/unwind-libunwind.c
index 9c917f8..05920e3 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-- 
2.10.1

[tip:perf/core] perf mmap: Don't discard prev in backward mode

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  7fb4b407a1242dbc85ea3ed1be065dca8f9a6f5b
Gitweb: https://git.kernel.org/tip/7fb4b407a1242dbc85ea3ed1be065dca8f9a6f5b
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Mon, 4 Dec 2017 16:51:06 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Tue, 5 Dec 2017 15:59:37 -0300

perf mmap: Don't discard prev in backward mode

'perf record' can switch its output data file. The new output should
only store the data after switching. However, in overwrite backward
mode, the new output still can have data from before switching. That
also brings extra overhead.

At the end of mmap_read(), the position of the processed ring buffer is
saved in md->prev. Next mmap_read should be end in md->prev if it is not
overwriten. That avoids processing duplicate data.  However, md->prev is
discarded. So next the mmap_read() has to process whole valid ring
buffer, which probably includes old processed data.

Avoid calling backward_rb_find_range() when md->prev is still
available.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Tested-by: Kan Liang <kan.li...@intel.com>
Acked-by: Namhyung Kim <namhy...@kernel.org>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Mengting Zhang <zhangmengt...@huawei.com>
Link: http://lkml.kernel.org/r/20171204165107.95327-3-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/util/mmap.c | 33 +++--
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3f262e7..5f8cb15 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -267,18 +267,6 @@ static int backward_rb_find_range(void *buf, int mask, u64 
head, u64 *start, u64
return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-u64 *start, u64 *end, bool backward)
-{
-   if (!backward) {
-   *start = old;
-   *end = head;
-   return 0;
-   }
-
-   return backward_rb_find_range(data, mask, head, start, end);
-}
-
 int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
@@ -290,19 +278,28 @@ int perf_mmap__push(struct perf_mmap *md, bool backward,
void *buf;
int rc = 0;
 
-   if (rb_find_range(data, md->mask, head, old, , , backward))
-   return -1;
+   start = backward ? head : old;
+   end = backward ? old : head;
 
if (start == end)
return 0;
 
size = end - start;
if (size > (unsigned long)(md->mask) + 1) {
-   WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
+   if (!backward) {
+   WARN_ONCE(1, "failed to keep up with mmap data. (warn 
only once)\n");
 
-   md->prev = head;
-   perf_mmap__consume(md, backward);
-   return 0;
+   md->prev = head;
+   perf_mmap__consume(md, backward);
+   return 0;
+   }
+
+   /*
+* Backward ring buffer is full. We still have a chance to read
+* most of data from it.
+*/
+   if (backward_rb_find_range(data, md->mask, head, , ))
+   return -1;
}
 
if ((start & md->mask) + size != (end & md->mask)) {

[tip:perf/core] perf mmap: Don't discard prev in backward mode

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  7fb4b407a1242dbc85ea3ed1be065dca8f9a6f5b
Gitweb: https://git.kernel.org/tip/7fb4b407a1242dbc85ea3ed1be065dca8f9a6f5b
Author: Wang Nan 
AuthorDate: Mon, 4 Dec 2017 16:51:06 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Tue, 5 Dec 2017 15:59:37 -0300

perf mmap: Don't discard prev in backward mode

'perf record' can switch its output data file. The new output should
only store the data after switching. However, in overwrite backward
mode, the new output still can have data from before switching. That
also brings extra overhead.

At the end of mmap_read(), the position of the processed ring buffer is
saved in md->prev. Next mmap_read should be end in md->prev if it is not
overwriten. That avoids processing duplicate data.  However, md->prev is
discarded. So next the mmap_read() has to process whole valid ring
buffer, which probably includes old processed data.

Avoid calling backward_rb_find_range() when md->prev is still
available.

Signed-off-by: Wang Nan 
Tested-by: Kan Liang 
Acked-by: Namhyung Kim 
Cc: Jiri Olsa 
Cc: Mengting Zhang 
Link: http://lkml.kernel.org/r/20171204165107.95327-3-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/util/mmap.c | 33 +++--
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3f262e7..5f8cb15 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -267,18 +267,6 @@ static int backward_rb_find_range(void *buf, int mask, u64 
head, u64 *start, u64
return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-u64 *start, u64 *end, bool backward)
-{
-   if (!backward) {
-   *start = old;
-   *end = head;
-   return 0;
-   }
-
-   return backward_rb_find_range(data, mask, head, start, end);
-}
-
 int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
@@ -290,19 +278,28 @@ int perf_mmap__push(struct perf_mmap *md, bool backward,
void *buf;
int rc = 0;
 
-   if (rb_find_range(data, md->mask, head, old, , , backward))
-   return -1;
+   start = backward ? head : old;
+   end = backward ? old : head;
 
if (start == end)
return 0;
 
size = end - start;
if (size > (unsigned long)(md->mask) + 1) {
-   WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
+   if (!backward) {
+   WARN_ONCE(1, "failed to keep up with mmap data. (warn 
only once)\n");
 
-   md->prev = head;
-   perf_mmap__consume(md, backward);
-   return 0;
+   md->prev = head;
+   perf_mmap__consume(md, backward);
+   return 0;
+   }
+
+   /*
+* Backward ring buffer is full. We still have a chance to read
+* most of data from it.
+*/
+   if (backward_rb_find_range(data, md->mask, head, , ))
+   return -1;
}
 
if ((start & md->mask) + size != (end & md->mask)) {

[tip:perf/core] perf tools: Rename 'backward' to 'overwrite' in evlist, mmap and record

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  0b72d69a542873ee098867deeb37d27ad4629c64
Gitweb: https://git.kernel.org/tip/0b72d69a542873ee098867deeb37d27ad4629c64
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Mon, 4 Dec 2017 16:51:07 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Tue, 5 Dec 2017 16:02:39 -0300

perf tools: Rename 'backward' to 'overwrite' in evlist, mmap and record

Remove the backward/forward concept to make it uniform with user
interface (the '--overwrite' option).

Signed-off-by: Wang Nan <wangn...@huawei.com>
Acked-by: Namhyung Kim <namhy...@kernel.org>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Cc: Mengting Zhang <zhangmengt...@huawei.com>
Link: http://lkml.kernel.org/r/20171204165107.95327-4-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/builtin-record.c | 14 +++---
 tools/perf/tests/backward-ring-buffer.c |  4 ++--
 tools/perf/util/evlist.c| 30 +++---
 tools/perf/util/evlist.h|  2 +-
 tools/perf/util/mmap.c  | 22 +++---
 5 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 26b8571..0a5749e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -479,7 +479,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist 
*evlist,
-   bool backward)
+   bool overwrite)
 {
u64 bytes_written = rec->bytes_written;
int i;
@@ -489,18 +489,18 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (!evlist)
return 0;
 
-   maps = backward ? evlist->backward_mmap : evlist->mmap;
+   maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
if (!maps)
return 0;
 
-   if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+   if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], overwrite, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
@@ -520,7 +520,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (bytes_written != rec->bytes_written)
rc = record__write(rec, _round_event, 
sizeof(finished_round_event));
 
-   if (backward)
+   if (overwrite)
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
return rc;
@@ -692,8 +692,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
if (evlist) {
if (evlist->mmap && evlist->mmap[0].base)
return evlist->mmap[0].base;
-   if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-   return evlist->backward_mmap[0].base;
+   if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+   return evlist->overwrite_mmap[0].base;
}
return NULL;
 }
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index cf37e43..4035d43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,8 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int 
*sample_count,
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
 
-   perf_mmap__read_catchup(>backward_mmap[i]);
-   while ((event = 
perf_mmap__read_backward(>backward_mmap[i])) != NULL) {
+   perf_mmap__read_catchup(>overwrite_mmap[i]);
+   while ((event = 
perf_mmap__read_backward(>overwrite_mmap[i])) != NULL) {
const u32 type = event->header.type;
 
switch (type) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b1cea71..3570355 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -125,7 +125,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
zfree(>mmap);
-   zfree(>backward_mmap);
+   zfree(>overwrite_mmap);
fdarray__exit(>pollfd);
 }
 
@@ -675,11 +675,11 @@ static int perf_evlist__set_paused(struc

[tip:perf/core] perf tools: Rename 'backward' to 'overwrite' in evlist, mmap and record

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  0b72d69a542873ee098867deeb37d27ad4629c64
Gitweb: https://git.kernel.org/tip/0b72d69a542873ee098867deeb37d27ad4629c64
Author: Wang Nan 
AuthorDate: Mon, 4 Dec 2017 16:51:07 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Tue, 5 Dec 2017 16:02:39 -0300

perf tools: Rename 'backward' to 'overwrite' in evlist, mmap and record

Remove the backward/forward concept to make it uniform with user
interface (the '--overwrite' option).

Signed-off-by: Wang Nan 
Acked-by: Namhyung Kim 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Mengting Zhang 
Link: http://lkml.kernel.org/r/20171204165107.95327-4-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/builtin-record.c | 14 +++---
 tools/perf/tests/backward-ring-buffer.c |  4 ++--
 tools/perf/util/evlist.c| 30 +++---
 tools/perf/util/evlist.h|  2 +-
 tools/perf/util/mmap.c  | 22 +++---
 5 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 26b8571..0a5749e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -479,7 +479,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist 
*evlist,
-   bool backward)
+   bool overwrite)
 {
u64 bytes_written = rec->bytes_written;
int i;
@@ -489,18 +489,18 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (!evlist)
return 0;
 
-   maps = backward ? evlist->backward_mmap : evlist->mmap;
+   maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
if (!maps)
return 0;
 
-   if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+   if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], overwrite, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
@@ -520,7 +520,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (bytes_written != rec->bytes_written)
rc = record__write(rec, _round_event, 
sizeof(finished_round_event));
 
-   if (backward)
+   if (overwrite)
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
return rc;
@@ -692,8 +692,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
if (evlist) {
if (evlist->mmap && evlist->mmap[0].base)
return evlist->mmap[0].base;
-   if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-   return evlist->backward_mmap[0].base;
+   if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+   return evlist->overwrite_mmap[0].base;
}
return NULL;
 }
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index cf37e43..4035d43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,8 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int 
*sample_count,
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
 
-   perf_mmap__read_catchup(>backward_mmap[i]);
-   while ((event = 
perf_mmap__read_backward(>backward_mmap[i])) != NULL) {
+   perf_mmap__read_catchup(>overwrite_mmap[i]);
+   while ((event = 
perf_mmap__read_backward(>overwrite_mmap[i])) != NULL) {
const u32 type = event->header.type;
 
switch (type) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b1cea71..3570355 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -125,7 +125,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
zfree(>mmap);
-   zfree(>backward_mmap);
+   zfree(>overwrite_mmap);
fdarray__exit(>pollfd);
 }
 
@@ -675,11 +675,11 @@ static int perf_evlist__set_paused(struct perf_evlist 
*evlist, bool value)
 {
int i;
 
-   if (!evlist->backward_mmap)
+   if (!evlist->overwrite_mmap)
return 0;
 
for (i = 0; i < evlist->nr_mmap

[tip:perf/core] perf mmap: Fix perf backward recording

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  71f566a34986f4a86a8c546c7a36f70f0132b8a9
Gitweb: https://git.kernel.org/tip/71f566a34986f4a86a8c546c7a36f70f0132b8a9
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Mon, 4 Dec 2017 16:51:05 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Tue, 5 Dec 2017 15:45:36 -0300

perf mmap: Fix perf backward recording

'perf record' backward recording doesn't work as we expected: it never
overwrites when ring buffer gets full.

Test:

Run a busy python printing task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot, then:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps never change, but my background task is a dead loop, can
easily overwhelm the ring buffer.

This patch fixes it by forcing unsetting PROT_WRITE for a backward ring
buffer, so all backward ring buffers become overwrite ring buffers.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan <wangn...@huawei.com>
Acked-by: Namhyung Kim <namhy...@kernel.org>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Cc: Mengting Zhang <zhangmengt...@huawei.com>
Link: http://lkml.kernel.org/r/20171204165107.95327-2-

[tip:perf/core] perf mmap: Fix perf backward recording

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  71f566a34986f4a86a8c546c7a36f70f0132b8a9
Gitweb: https://git.kernel.org/tip/71f566a34986f4a86a8c546c7a36f70f0132b8a9
Author: Wang Nan 
AuthorDate: Mon, 4 Dec 2017 16:51:05 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Tue, 5 Dec 2017 15:45:36 -0300

perf mmap: Fix perf backward recording

'perf record' backward recording doesn't work as we expected: it never
overwrites when ring buffer gets full.

Test:

Run a busy python printing task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot, then:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps never change, but my background task is a dead loop, can
easily overwhelm the ring buffer.

This patch fixes it by forcing unsetting PROT_WRITE for a backward ring
buffer, so all backward ring buffers become overwrite ring buffers.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan 
Acked-by: Namhyung Kim 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Mengting Zhang 
Link: http://lkml.kernel.org/r/20171204165107.95327-2-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/util/evlist.c | 11 ---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util

[tip:perf/core] perf mmap: Remove overwrite and check_messup from mmap read

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  8eb7a1fe31612fd3e8ae8042dd2ebaf7575504cb
Gitweb: https://git.kernel.org/tip/8eb7a1fe31612fd3e8ae8042dd2ebaf7575504cb
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Sun, 3 Dec 2017 02:00:41 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Tue, 5 Dec 2017 15:43:54 -0300

perf mmap: Remove overwrite and check_messup from mmap read

All perf_mmap__read_forward() read from read-write ring buffer, so no
need check_messup. Reading from backward ring buffer doesn't require
check_messup because it never mess up. Cleanup arguments lists.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Acked-by: Namhyung Kim <namhy...@kernel.org>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Link: http://lkml.kernel.org/r/20171203020044.81680-6-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/util/evlist.c |  2 +-
 tools/perf/util/mmap.c   | 28 
 tools/perf/util/mmap.h   |  2 +-
 3 files changed, 6 insertions(+), 26 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a59134f..68c1f95 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct 
perf_evlist *evlist, int
 * No need for read-write ring buffer: kernel stop outputting when
 * it hit md->prev (perf_mmap__consume()).
 */
-   return perf_mmap__read_forward(md, false);
+   return perf_mmap__read_forward(md);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, 
int idx)
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 703ed41..3f262e7 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -21,33 +21,13 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 }
 
 /* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *perf_mmap__read(struct perf_mmap *map, bool 
check_messup,
+static union perf_event *perf_mmap__read(struct perf_mmap *map,
 u64 start, u64 end, u64 *prev)
 {
unsigned char *data = map->base + page_size;
union perf_event *event = NULL;
int diff = end - start;
 
-   if (check_messup) {
-   /*
-* If we're further behind than half the buffer, there's a 
chance
-* the writer will bite our tail and mess up the samples under 
us.
-*
-* If we somehow ended up ahead of the 'end', we got messed up.
-*
-* In either case, truncate and restart at 'end'.
-*/
-   if (diff > map->mask / 2 || diff < 0) {
-   fprintf(stderr, "WARNING: failed to keep up with mmap 
data.\n");
-
-   /*
-* 'end' points to a known good entry, start there.
-*/
-   start = end;
-   diff = 0;
-   }
-   }
-
if (diff >= (int)sizeof(event->header)) {
size_t size;
 
@@ -89,7 +69,7 @@ broken_event:
return event;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 {
u64 head;
u64 old = map->prev;
@@ -102,7 +82,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap 
*map, bool check_mess
 
head = perf_mmap__read_head(map);
 
-   return perf_mmap__read(map, check_messup, old, head, >prev);
+   return perf_mmap__read(map, old, head, >prev);
 }
 
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
@@ -138,7 +118,7 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap 
*map)
else
end = head + map->mask + 1;
 
-   return perf_mmap__read(map, false, start, end, >prev);
+   return perf_mmap__read(map, start, end, >prev);
 }
 
 void perf_mmap__read_catchup(struct perf_mmap *map)
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 2c3d291..d640273 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -86,7 +86,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap 
*md, u64 tail)
pc->data_tail = tail;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup);
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, bool backward,

[tip:perf/core] perf mmap: Remove overwrite and check_messup from mmap read

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  8eb7a1fe31612fd3e8ae8042dd2ebaf7575504cb
Gitweb: https://git.kernel.org/tip/8eb7a1fe31612fd3e8ae8042dd2ebaf7575504cb
Author: Wang Nan 
AuthorDate: Sun, 3 Dec 2017 02:00:41 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Tue, 5 Dec 2017 15:43:54 -0300

perf mmap: Remove overwrite and check_messup from mmap read

All perf_mmap__read_forward() read from read-write ring buffer, so no
need check_messup. Reading from backward ring buffer doesn't require
check_messup because it never mess up. Cleanup arguments lists.

Signed-off-by: Wang Nan 
Acked-by: Namhyung Kim 
Cc: Jiri Olsa 
Cc: Kan Liang 
Link: http://lkml.kernel.org/r/20171203020044.81680-6-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/util/evlist.c |  2 +-
 tools/perf/util/mmap.c   | 28 
 tools/perf/util/mmap.h   |  2 +-
 3 files changed, 6 insertions(+), 26 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a59134f..68c1f95 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct 
perf_evlist *evlist, int
 * No need for read-write ring buffer: kernel stop outputting when
 * it hit md->prev (perf_mmap__consume()).
 */
-   return perf_mmap__read_forward(md, false);
+   return perf_mmap__read_forward(md);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, 
int idx)
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 703ed41..3f262e7 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -21,33 +21,13 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 }
 
 /* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *perf_mmap__read(struct perf_mmap *map, bool 
check_messup,
+static union perf_event *perf_mmap__read(struct perf_mmap *map,
 u64 start, u64 end, u64 *prev)
 {
unsigned char *data = map->base + page_size;
union perf_event *event = NULL;
int diff = end - start;
 
-   if (check_messup) {
-   /*
-* If we're further behind than half the buffer, there's a 
chance
-* the writer will bite our tail and mess up the samples under 
us.
-*
-* If we somehow ended up ahead of the 'end', we got messed up.
-*
-* In either case, truncate and restart at 'end'.
-*/
-   if (diff > map->mask / 2 || diff < 0) {
-   fprintf(stderr, "WARNING: failed to keep up with mmap 
data.\n");
-
-   /*
-* 'end' points to a known good entry, start there.
-*/
-   start = end;
-   diff = 0;
-   }
-   }
-
if (diff >= (int)sizeof(event->header)) {
size_t size;
 
@@ -89,7 +69,7 @@ broken_event:
return event;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 {
u64 head;
u64 old = map->prev;
@@ -102,7 +82,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap 
*map, bool check_mess
 
head = perf_mmap__read_head(map);
 
-   return perf_mmap__read(map, check_messup, old, head, >prev);
+   return perf_mmap__read(map, old, head, >prev);
 }
 
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
@@ -138,7 +118,7 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap 
*map)
else
end = head + map->mask + 1;
 
-   return perf_mmap__read(map, false, start, end, >prev);
+   return perf_mmap__read(map, start, end, >prev);
 }
 
 void perf_mmap__read_catchup(struct perf_mmap *map)
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 2c3d291..d640273 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -86,7 +86,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap 
*md, u64 tail)
pc->data_tail = tail;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup);
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, bool backward,

[tip:perf/core] perf mmap: Remove overwrite from arguments list of perf_mmap__push

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  ca6a9a05391960be5e8161a59a9854b32325d901
Gitweb: https://git.kernel.org/tip/ca6a9a05391960be5e8161a59a9854b32325d901
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Sun, 3 Dec 2017 02:00:40 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Tue, 5 Dec 2017 15:43:54 -0300

perf mmap: Remove overwrite from arguments list of perf_mmap__push

'overwrite' argument is always 'false'. Remove it from arguments list of
perf_mmap__push().

Signed-off-by: Wang Nan <wangn...@huawei.com>
Acked-by: Namhyung Kim <namhy...@kernel.org>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Link: http://lkml.kernel.org/r/20171203020044.81680-5-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/mmap.c  | 6 +++---
 tools/perf/util/mmap.h  | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3bc6cee..26b8571 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -500,7 +500,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], false, backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 9fe5f9c..703ed41 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -299,7 +299,7 @@ static int rb_find_range(void *data, int mask, u64 head, 
u64 old,
return backward_rb_find_range(data, mask, head, start, end);
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
u64 head = perf_mmap__read_head(md);
@@ -321,7 +321,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
 
md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
+   perf_mmap__consume(md, backward);
return 0;
}
 
@@ -346,7 +346,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
}
 
md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
+   perf_mmap__consume(md, backward);
 out:
return rc;
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index efd78b8..2c3d291 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -89,7 +89,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap 
*md, u64 tail)
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);

[tip:perf/core] perf mmap: Remove overwrite from arguments list of perf_mmap__push

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  ca6a9a05391960be5e8161a59a9854b32325d901
Gitweb: https://git.kernel.org/tip/ca6a9a05391960be5e8161a59a9854b32325d901
Author: Wang Nan 
AuthorDate: Sun, 3 Dec 2017 02:00:40 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Tue, 5 Dec 2017 15:43:54 -0300

perf mmap: Remove overwrite from arguments list of perf_mmap__push

'overwrite' argument is always 'false'. Remove it from arguments list of
perf_mmap__push().

Signed-off-by: Wang Nan 
Acked-by: Namhyung Kim 
Cc: Jiri Olsa 
Cc: Kan Liang 
Link: http://lkml.kernel.org/r/20171203020044.81680-5-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/mmap.c  | 6 +++---
 tools/perf/util/mmap.h  | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3bc6cee..26b8571 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -500,7 +500,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], false, backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 9fe5f9c..703ed41 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -299,7 +299,7 @@ static int rb_find_range(void *data, int mask, u64 head, 
u64 old,
return backward_rb_find_range(data, mask, head, start, end);
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
u64 head = perf_mmap__read_head(md);
@@ -321,7 +321,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
 
md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
+   perf_mmap__consume(md, backward);
return 0;
}
 
@@ -346,7 +346,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
}
 
md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
+   perf_mmap__consume(md, backward);
 out:
return rc;
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index efd78b8..2c3d291 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -89,7 +89,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap 
*md, u64 tail)
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);

[tip:perf/core] perf evlist: Remove evlist->overwrite

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  144b9a4fc53039c09007b71a06640560a6e62140
Gitweb: https://git.kernel.org/tip/144b9a4fc53039c09007b71a06640560a6e62140
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Sun, 3 Dec 2017 02:00:39 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Tue, 5 Dec 2017 15:43:54 -0300

perf evlist: Remove evlist->overwrite

evlist->overwrite is set to false in all users. It can be removed.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Acked-by: Namhyung Kim <namhy...@kernel.org>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Link: http://lkml.kernel.org/r/20171203020044.81680-4-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/evlist.c| 5 ++---
 tools/perf/util/evlist.h| 1 -
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 08070f8..3bc6cee 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -500,7 +500,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], evlist->overwrite, 
backward, rec, record__pushfn) != 0) {
+   if (perf_mmap__push([i], false, backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 93272d9..a59134f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct 
perf_evlist *evlist, int
 * No need for read-write ring buffer: kernel stop outputting when
 * it hit md->prev (perf_mmap__consume()).
 */
-   return perf_mmap__read_forward(md, evlist->overwrite);
+   return perf_mmap__read_forward(md, false);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, 
int idx)
@@ -738,7 +738,7 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist 
*evlist, int idx)
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
-   perf_mmap__consume(>mmap[idx], evlist->overwrite);
+   perf_mmap__consume(>mmap[idx], false);
 }
 
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
@@ -1070,7 +1070,6 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) 
< 0)
return -ENOMEM;
 
-   evlist->overwrite = false;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 424a3d6..eec3377 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -31,7 +31,6 @@ struct perf_evlist {
int  nr_entries;
int  nr_groups;
int  nr_mmaps;
-   bool overwrite;
bool enabled;
bool has_user_cpus;
size_t   mmap_len;

[tip:perf/core] perf evlist: Remove evlist->overwrite

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  144b9a4fc53039c09007b71a06640560a6e62140
Gitweb: https://git.kernel.org/tip/144b9a4fc53039c09007b71a06640560a6e62140
Author: Wang Nan 
AuthorDate: Sun, 3 Dec 2017 02:00:39 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Tue, 5 Dec 2017 15:43:54 -0300

perf evlist: Remove evlist->overwrite

evlist->overwrite is set to false in all users. It can be removed.

Signed-off-by: Wang Nan 
Acked-by: Namhyung Kim 
Cc: Jiri Olsa 
Cc: Kan Liang 
Link: http://lkml.kernel.org/r/20171203020044.81680-4-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/evlist.c| 5 ++---
 tools/perf/util/evlist.h| 1 -
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 08070f8..3bc6cee 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -500,7 +500,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], evlist->overwrite, 
backward, rec, record__pushfn) != 0) {
+   if (perf_mmap__push([i], false, backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 93272d9..a59134f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct 
perf_evlist *evlist, int
 * No need for read-write ring buffer: kernel stop outputting when
 * it hit md->prev (perf_mmap__consume()).
 */
-   return perf_mmap__read_forward(md, evlist->overwrite);
+   return perf_mmap__read_forward(md, false);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, 
int idx)
@@ -738,7 +738,7 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist 
*evlist, int idx)
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
-   perf_mmap__consume(>mmap[idx], evlist->overwrite);
+   perf_mmap__consume(>mmap[idx], false);
 }
 
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
@@ -1070,7 +1070,6 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) 
< 0)
return -ENOMEM;
 
-   evlist->overwrite = false;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 424a3d6..eec3377 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -31,7 +31,6 @@ struct perf_evlist {
int  nr_entries;
int  nr_groups;
int  nr_mmaps;
-   bool overwrite;
bool enabled;
bool has_user_cpus;
size_t   mmap_len;

[tip:perf/core] perf evlist: Remove 'overwrite' parameter from perf_evlist__mmap_ex

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  7a276ff6c3202697c3c15cad757dec3bb07d14bf
Gitweb: https://git.kernel.org/tip/7a276ff6c3202697c3c15cad757dec3bb07d14bf
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Sun, 3 Dec 2017 02:00:38 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Tue, 5 Dec 2017 15:43:53 -0300

perf evlist: Remove 'overwrite' parameter from perf_evlist__mmap_ex

All users of perf_evlist__mmap_ex set !overwrite. Remove it from its
arguments list.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Acked-by: Namhyung Kim <namhy...@kernel.org>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Link: http://lkml.kernel.org/r/20171203020044.81680-3-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/evlist.c| 8 
 tools/perf/util/evlist.h| 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e304bc4..08070f8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -301,7 +301,7 @@ static int record__mmap_evlist(struct record *rec,
struct record_opts *opts = >opts;
char msg[512];
 
-   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 opts->auxtrace_mmap_pages,
 opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3c1778b..93272d9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1052,14 +1052,14 @@ int perf_evlist__parse_mmap_pages(const struct option 
*opt, const char *str,
  * Return: %0 on success, negative error code otherwise.
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-bool overwrite, unsigned int auxtrace_pages,
+unsigned int auxtrace_pages,
 bool auxtrace_overwrite)
 {
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
struct mmap_params mp = {
-   .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
+   .prot = PROT_READ | PROT_WRITE,
};
 
if (!evlist->mmap)
@@ -1070,7 +1070,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) 
< 0)
return -ENOMEM;
 
-   evlist->overwrite = overwrite;
+   evlist->overwrite = false;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
@@ -1093,7 +1093,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-   return perf_evlist__mmap_ex(evlist, pages, false, 0, false);
+   return perf_evlist__mmap_ex(evlist, pages, 0, false);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f0f2c8b..424a3d6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -169,7 +169,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
 unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-bool overwrite, unsigned int auxtrace_pages,
+unsigned int auxtrace_pages,
 bool auxtrace_overwrite);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);

[tip:perf/core] perf evlist: Remove 'overwrite' parameter from perf_evlist__mmap_ex

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  7a276ff6c3202697c3c15cad757dec3bb07d14bf
Gitweb: https://git.kernel.org/tip/7a276ff6c3202697c3c15cad757dec3bb07d14bf
Author: Wang Nan 
AuthorDate: Sun, 3 Dec 2017 02:00:38 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Tue, 5 Dec 2017 15:43:53 -0300

perf evlist: Remove 'overwrite' parameter from perf_evlist__mmap_ex

All users of perf_evlist__mmap_ex set !overwrite. Remove it from its
arguments list.

Signed-off-by: Wang Nan 
Acked-by: Namhyung Kim 
Cc: Jiri Olsa 
Cc: Kan Liang 
Link: http://lkml.kernel.org/r/20171203020044.81680-3-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/evlist.c| 8 
 tools/perf/util/evlist.h| 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e304bc4..08070f8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -301,7 +301,7 @@ static int record__mmap_evlist(struct record *rec,
struct record_opts *opts = >opts;
char msg[512];
 
-   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 opts->auxtrace_mmap_pages,
 opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3c1778b..93272d9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1052,14 +1052,14 @@ int perf_evlist__parse_mmap_pages(const struct option 
*opt, const char *str,
  * Return: %0 on success, negative error code otherwise.
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-bool overwrite, unsigned int auxtrace_pages,
+unsigned int auxtrace_pages,
 bool auxtrace_overwrite)
 {
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
struct mmap_params mp = {
-   .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
+   .prot = PROT_READ | PROT_WRITE,
};
 
if (!evlist->mmap)
@@ -1070,7 +1070,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) 
< 0)
return -ENOMEM;
 
-   evlist->overwrite = overwrite;
+   evlist->overwrite = false;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
@@ -1093,7 +1093,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-   return perf_evlist__mmap_ex(evlist, pages, false, 0, false);
+   return perf_evlist__mmap_ex(evlist, pages, 0, false);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f0f2c8b..424a3d6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -169,7 +169,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
 unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-bool overwrite, unsigned int auxtrace_pages,
+unsigned int auxtrace_pages,
 bool auxtrace_overwrite);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);

[tip:perf/core] perf evlist: Remove 'overwrite' parameter from perf_evlist__mmap

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  f74b9d3a1ac2b9c3ae1475f474ca0e6644746fbf
Gitweb: https://git.kernel.org/tip/f74b9d3a1ac2b9c3ae1475f474ca0e6644746fbf
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Sun, 3 Dec 2017 02:00:37 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Tue, 5 Dec 2017 15:43:53 -0300

perf evlist: Remove 'overwrite' parameter from perf_evlist__mmap

Now all perf_evlist__mmap's users doesn't set 'overwrite'. Remove it
from arguments list.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Acked-by: Namhyung Kim <namhy...@kernel.org>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Link: http://lkml.kernel.org/r/20171203020044.81680-2-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c | 2 +-
 tools/perf/builtin-kvm.c | 2 +-
 tools/perf/builtin-top.c | 2 +-
 tools/perf/builtin-trace.c   | 2 +-
 tools/perf/tests/backward-ring-buffer.c  | 2 +-
 tools/perf/tests/bpf.c   | 2 +-
 tools/perf/tests/code-reading.c  | 2 +-
 tools/perf/tests/keep-tracking.c | 2 +-
 tools/perf/tests/mmap-basic.c| 2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  | 2 +-
 tools/perf/tests/perf-record.c   | 2 +-
 tools/perf/tests/sw-clock.c  | 2 +-
 tools/perf/tests/switch-tracking.c   | 2 +-
 tools/perf/tests/task-exit.c | 2 +-
 tools/perf/util/evlist.c | 5 ++---
 tools/perf/util/evlist.h | 3 +--
 tools/perf/util/python.c | 2 +-
 17 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c 
b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index b59678e..06abe81 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -84,7 +84,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, 
int subtest __maybe
 
CHECK__(perf_evlist__open(evlist));
 
-   CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+   CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
pc = evlist->mmap[0].base;
ret = perf_read_tsc_conversion(pc, );
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 597c7de..9885316 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1044,7 +1044,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
goto out;
}
 
-   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
ui__error("Failed to mmap the events: %s\n",
  str_error_r(errno, sbuf, sizeof(sbuf)));
perf_evlist__close(evlist);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0077724..540461f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -907,7 +907,7 @@ try_again:
}
}
 
-   if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
ui__error("Failed to mmap with %d (%s)\n",
errno, str_error_r(errno, msg, sizeof(msg)));
goto out_err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 84debdb..7c57898 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2437,7 +2437,7 @@ static int trace__run(struct trace *trace, int argc, 
const char **argv)
if (err < 0)
goto out_error_apply_filters;
 
-   err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
+   err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
if (err < 0)
goto out_error_mmap;
 
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index 43a8c6a..cf37e43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -59,7 +59,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
int err;
char sbuf[STRERR_BUFSIZE];
 
-   err = perf_evlist__mmap(evlist, mmap_pages, false);
+   err = perf_evlist__mmap(evlist, mmap_pages);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 34c22cd..c433dd3 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -167,7 +167,7 @@ static int do_test(struct bpf_object *obj, int 
(*func)(void),
goto out_delete_evlist;
}
 
-   err = perf_evlist__m

[tip:perf/core] perf evlist: Remove 'overwrite' parameter from perf_evlist__mmap

2017-12-06 Thread tip-bot for Wang Nan 
Commit-ID:  f74b9d3a1ac2b9c3ae1475f474ca0e6644746fbf
Gitweb: https://git.kernel.org/tip/f74b9d3a1ac2b9c3ae1475f474ca0e6644746fbf
Author: Wang Nan 
AuthorDate: Sun, 3 Dec 2017 02:00:37 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Tue, 5 Dec 2017 15:43:53 -0300

perf evlist: Remove 'overwrite' parameter from perf_evlist__mmap

Now all perf_evlist__mmap's users doesn't set 'overwrite'. Remove it
from arguments list.

Signed-off-by: Wang Nan 
Acked-by: Namhyung Kim 
Cc: Jiri Olsa 
Cc: Kan Liang 
Link: http://lkml.kernel.org/r/20171203020044.81680-2-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c | 2 +-
 tools/perf/builtin-kvm.c | 2 +-
 tools/perf/builtin-top.c | 2 +-
 tools/perf/builtin-trace.c   | 2 +-
 tools/perf/tests/backward-ring-buffer.c  | 2 +-
 tools/perf/tests/bpf.c   | 2 +-
 tools/perf/tests/code-reading.c  | 2 +-
 tools/perf/tests/keep-tracking.c | 2 +-
 tools/perf/tests/mmap-basic.c| 2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  | 2 +-
 tools/perf/tests/perf-record.c   | 2 +-
 tools/perf/tests/sw-clock.c  | 2 +-
 tools/perf/tests/switch-tracking.c   | 2 +-
 tools/perf/tests/task-exit.c | 2 +-
 tools/perf/util/evlist.c | 5 ++---
 tools/perf/util/evlist.h | 3 +--
 tools/perf/util/python.c | 2 +-
 17 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c 
b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index b59678e..06abe81 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -84,7 +84,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, 
int subtest __maybe
 
CHECK__(perf_evlist__open(evlist));
 
-   CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+   CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
pc = evlist->mmap[0].base;
ret = perf_read_tsc_conversion(pc, );
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 597c7de..9885316 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1044,7 +1044,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
goto out;
}
 
-   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
ui__error("Failed to mmap the events: %s\n",
  str_error_r(errno, sbuf, sizeof(sbuf)));
perf_evlist__close(evlist);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0077724..540461f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -907,7 +907,7 @@ try_again:
}
}
 
-   if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
ui__error("Failed to mmap with %d (%s)\n",
errno, str_error_r(errno, msg, sizeof(msg)));
goto out_err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 84debdb..7c57898 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2437,7 +2437,7 @@ static int trace__run(struct trace *trace, int argc, 
const char **argv)
if (err < 0)
goto out_error_apply_filters;
 
-   err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
+   err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
if (err < 0)
goto out_error_mmap;
 
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index 43a8c6a..cf37e43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -59,7 +59,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
int err;
char sbuf[STRERR_BUFSIZE];
 
-   err = perf_evlist__mmap(evlist, mmap_pages, false);
+   err = perf_evlist__mmap(evlist, mmap_pages);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 34c22cd..c433dd3 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -167,7 +167,7 @@ static int do_test(struct bpf_object *obj, int 
(*func)(void),
goto out_delete_evlist;
}
 
-   err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+   err = perf_evlist__mmap(evlist, opts.mmap_pages);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",

[PATCH] perf tools: Fix compiling error in libunwind x86

2017-12-05 Thread Wang Nan 
Fix a compiling error:

 ...
   CC   util/libunwind/x86_32.o
 In file included from util/libunwind/x86_32.c:33:0:
 util/libunwind/../../arch/x86/util/unwind-libunwind.c: In function 
'libunwind__x86_reg_id':
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: error: 'EINVAL' 
undeclared (first use in this function)
return -EINVAL;
^
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: note: each 
undeclared identifier is reported only once for each function it appears in
 mv: cannot stat 'util/libunwind/.x86_32.o.tmp': No such file or directory
 make[4]: *** [util/libunwind/x86_32.o] Error 1
 make[3]: *** [util] Error 2
 make[2]: *** [libperf-in.o] Error 2
 make[1]: *** [sub-make] Error 2
 make: *** [all] Error 2

It happens when libunwind-x86 feature is detected.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/arch/x86/util/unwind-libunwind.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c 
b/tools/perf/arch/x86/util/unwind-libunwind.c
index 9c917f8..05920e3 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-- 
2.10.1

[PATCH] perf tools: Fix compiling error in libunwind x86

2017-12-05 Thread Wang Nan 
Fix a compiling error:

 ...
   CC   util/libunwind/x86_32.o
 In file included from util/libunwind/x86_32.c:33:0:
 util/libunwind/../../arch/x86/util/unwind-libunwind.c: In function 
'libunwind__x86_reg_id':
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: error: 'EINVAL' 
undeclared (first use in this function)
return -EINVAL;
^
 util/libunwind/../../arch/x86/util/unwind-libunwind.c:110:11: note: each 
undeclared identifier is reported only once for each function it appears in
 mv: cannot stat 'util/libunwind/.x86_32.o.tmp': No such file or directory
 make[4]: *** [util/libunwind/x86_32.o] Error 1
 make[3]: *** [util] Error 2
 make[2]: *** [libperf-in.o] Error 2
 make[1]: *** [sub-make] Error 2
 make: *** [all] Error 2

It happens when libunwind-x86 feature is detected.

Signed-off-by: Wang Nan 
---
 tools/perf/arch/x86/util/unwind-libunwind.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c 
b/tools/perf/arch/x86/util/unwind-libunwind.c
index 9c917f8..05920e3 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include 
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-- 
2.10.1

[PATCH v3 2/3] perf tools: Don't discard prev in backward mode

2017-12-04 Thread Wang Nan 
Perf record can switch output. The new output should only store the
data after switching. However, in overwrite backward mode, the new
output still have the data from old output. That also brings extra
overhead.

At the end of mmap_read, the position of processed ring buffer is
saved in md->prev. Next mmap_read should be end in md->prev if it is
not overwriten. That avoids to process duplicate data.
However, the md->prev is discarded. So next mmap_read has to process
whole valid ring buffer, which probably include the old processed
data.

Avoid calling backward_rb_find_range() when md->prev is still
available.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Tested-by: Kan Liang <kan.li...@intel.com>
---
 tools/perf/util/mmap.c | 33 +++--
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3f262e7..5f8cb15 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -267,18 +267,6 @@ static int backward_rb_find_range(void *buf, int mask, u64 
head, u64 *start, u64
return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-u64 *start, u64 *end, bool backward)
-{
-   if (!backward) {
-   *start = old;
-   *end = head;
-   return 0;
-   }
-
-   return backward_rb_find_range(data, mask, head, start, end);
-}
-
 int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
@@ -290,19 +278,28 @@ int perf_mmap__push(struct perf_mmap *md, bool backward,
void *buf;
int rc = 0;
 
-   if (rb_find_range(data, md->mask, head, old, , , backward))
-   return -1;
+   start = backward ? head : old;
+   end = backward ? old : head;
 
if (start == end)
return 0;
 
size = end - start;
if (size > (unsigned long)(md->mask) + 1) {
-   WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
+   if (!backward) {
+   WARN_ONCE(1, "failed to keep up with mmap data. (warn 
only once)\n");
 
-   md->prev = head;
-   perf_mmap__consume(md, backward);
-   return 0;
+   md->prev = head;
+   perf_mmap__consume(md, backward);
+   return 0;
+   }
+
+   /*
+* Backward ring buffer is full. We still have a chance to read
+* most of data from it.
+*/
+   if (backward_rb_find_range(data, md->mask, head, , ))
+   return -1;
}
 
if ((start & md->mask) + size != (end & md->mask)) {
-- 
2.10.1

[PATCH v3 3/3] perf tools: Replace 'backward' to 'overwrite' in evlist. mmap and record

2017-12-04 Thread Wang Nan 
Remove the backward/forward concept to make it uniform with user
interface (the '--overwrite' option).

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/builtin-record.c | 14 +++---
 tools/perf/tests/backward-ring-buffer.c |  4 ++--
 tools/perf/util/evlist.c| 30 +++---
 tools/perf/util/evlist.h|  2 +-
 tools/perf/util/mmap.c  | 22 +++---
 5 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 26b8571..0a5749e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -479,7 +479,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist 
*evlist,
-   bool backward)
+   bool overwrite)
 {
u64 bytes_written = rec->bytes_written;
int i;
@@ -489,18 +489,18 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (!evlist)
return 0;
 
-   maps = backward ? evlist->backward_mmap : evlist->mmap;
+   maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
if (!maps)
return 0;
 
-   if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+   if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], overwrite, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
@@ -520,7 +520,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (bytes_written != rec->bytes_written)
rc = record__write(rec, _round_event, 
sizeof(finished_round_event));
 
-   if (backward)
+   if (overwrite)
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
return rc;
@@ -692,8 +692,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
if (evlist) {
if (evlist->mmap && evlist->mmap[0].base)
return evlist->mmap[0].base;
-   if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-   return evlist->backward_mmap[0].base;
+   if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+   return evlist->overwrite_mmap[0].base;
}
return NULL;
 }
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index cf37e43..4035d43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,8 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int 
*sample_count,
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
 
-   perf_mmap__read_catchup(>backward_mmap[i]);
-   while ((event = 
perf_mmap__read_backward(>backward_mmap[i])) != NULL) {
+   perf_mmap__read_catchup(>overwrite_mmap[i]);
+   while ((event = 
perf_mmap__read_backward(>overwrite_mmap[i])) != NULL) {
const u32 type = event->header.type;
 
switch (type) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b1cea71..3570355 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -125,7 +125,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
zfree(>mmap);
-   zfree(>backward_mmap);
+   zfree(>overwrite_mmap);
fdarray__exit(>pollfd);
 }
 
@@ -675,11 +675,11 @@ static int perf_evlist__set_paused(struct perf_evlist 
*evlist, bool value)
 {
int i;
 
-   if (!evlist->backward_mmap)
+   if (!evlist->overwrite_mmap)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
-   int fd = evlist->backward_mmap[i].fd;
+   int fd = evlist->overwrite_mmap[i].fd;
int err;
 
if (fd < 0)
@@ -749,16 +749,16 @@ static void perf_evlist__munmap_nofree(struct perf_evlist 
*evlist)
for (i = 0; i < evlist->nr_mmaps; i++)
perf_mmap__munmap(>mmap[i]);
 
-   if (evlist->backward_mmap)
+   if (evlist->overwrite_mmap)
for (i = 0; i < evlist->

[PATCH v3 2/3] perf tools: Don't discard prev in backward mode

2017-12-04 Thread Wang Nan 
Perf record can switch output. The new output should only store the
data after switching. However, in overwrite backward mode, the new
output still have the data from old output. That also brings extra
overhead.

At the end of mmap_read, the position of processed ring buffer is
saved in md->prev. Next mmap_read should be end in md->prev if it is
not overwriten. That avoids to process duplicate data.
However, the md->prev is discarded. So next mmap_read has to process
whole valid ring buffer, which probably include the old processed
data.

Avoid calling backward_rb_find_range() when md->prev is still
available.

Signed-off-by: Wang Nan 
Tested-by: Kan Liang 
---
 tools/perf/util/mmap.c | 33 +++--
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3f262e7..5f8cb15 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -267,18 +267,6 @@ static int backward_rb_find_range(void *buf, int mask, u64 
head, u64 *start, u64
return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-u64 *start, u64 *end, bool backward)
-{
-   if (!backward) {
-   *start = old;
-   *end = head;
-   return 0;
-   }
-
-   return backward_rb_find_range(data, mask, head, start, end);
-}
-
 int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
@@ -290,19 +278,28 @@ int perf_mmap__push(struct perf_mmap *md, bool backward,
void *buf;
int rc = 0;
 
-   if (rb_find_range(data, md->mask, head, old, , , backward))
-   return -1;
+   start = backward ? head : old;
+   end = backward ? old : head;
 
if (start == end)
return 0;
 
size = end - start;
if (size > (unsigned long)(md->mask) + 1) {
-   WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
+   if (!backward) {
+   WARN_ONCE(1, "failed to keep up with mmap data. (warn 
only once)\n");
 
-   md->prev = head;
-   perf_mmap__consume(md, backward);
-   return 0;
+   md->prev = head;
+   perf_mmap__consume(md, backward);
+   return 0;
+   }
+
+   /*
+* Backward ring buffer is full. We still have a chance to read
+* most of data from it.
+*/
+   if (backward_rb_find_range(data, md->mask, head, , ))
+   return -1;
}
 
if ((start & md->mask) + size != (end & md->mask)) {
-- 
2.10.1

[PATCH v3 3/3] perf tools: Replace 'backward' to 'overwrite' in evlist. mmap and record

2017-12-04 Thread Wang Nan 
Remove the backward/forward concept to make it uniform with user
interface (the '--overwrite' option).

Signed-off-by: Wang Nan 
---
 tools/perf/builtin-record.c | 14 +++---
 tools/perf/tests/backward-ring-buffer.c |  4 ++--
 tools/perf/util/evlist.c| 30 +++---
 tools/perf/util/evlist.h|  2 +-
 tools/perf/util/mmap.c  | 22 +++---
 5 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 26b8571..0a5749e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -479,7 +479,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist 
*evlist,
-   bool backward)
+   bool overwrite)
 {
u64 bytes_written = rec->bytes_written;
int i;
@@ -489,18 +489,18 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (!evlist)
return 0;
 
-   maps = backward ? evlist->backward_mmap : evlist->mmap;
+   maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
if (!maps)
return 0;
 
-   if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+   if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], overwrite, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
@@ -520,7 +520,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (bytes_written != rec->bytes_written)
rc = record__write(rec, _round_event, 
sizeof(finished_round_event));
 
-   if (backward)
+   if (overwrite)
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
return rc;
@@ -692,8 +692,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
if (evlist) {
if (evlist->mmap && evlist->mmap[0].base)
return evlist->mmap[0].base;
-   if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-   return evlist->backward_mmap[0].base;
+   if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+   return evlist->overwrite_mmap[0].base;
}
return NULL;
 }
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index cf37e43..4035d43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,8 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int 
*sample_count,
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
 
-   perf_mmap__read_catchup(>backward_mmap[i]);
-   while ((event = 
perf_mmap__read_backward(>backward_mmap[i])) != NULL) {
+   perf_mmap__read_catchup(>overwrite_mmap[i]);
+   while ((event = 
perf_mmap__read_backward(>overwrite_mmap[i])) != NULL) {
const u32 type = event->header.type;
 
switch (type) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b1cea71..3570355 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -125,7 +125,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
zfree(>mmap);
-   zfree(>backward_mmap);
+   zfree(>overwrite_mmap);
fdarray__exit(>pollfd);
 }
 
@@ -675,11 +675,11 @@ static int perf_evlist__set_paused(struct perf_evlist 
*evlist, bool value)
 {
int i;
 
-   if (!evlist->backward_mmap)
+   if (!evlist->overwrite_mmap)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
-   int fd = evlist->backward_mmap[i].fd;
+   int fd = evlist->overwrite_mmap[i].fd;
int err;
 
if (fd < 0)
@@ -749,16 +749,16 @@ static void perf_evlist__munmap_nofree(struct perf_evlist 
*evlist)
for (i = 0; i < evlist->nr_mmaps; i++)
perf_mmap__munmap(>mmap[i]);
 
-   if (evlist->backward_mmap)
+   if (evlist->overwrite_mmap)
for (i = 0; i < evlist->nr_mmaps; i++)
-

[PATCH v3 1/3] perf mmap: Fix perf backward recording

2017-12-04 Thread Wang Nan 
perf record backward recording doesn't work as we expected: it never
overwrite when ring buffer full.

Test:

(Run a busy python printing task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot.)

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps are never change, but my background task is a dead loop, can
easily overwhelme the ring buffer.

This patch fix it by force unsetting PROT_WRITE for backward ring
buffer, so all backward ring buffer become overwrite ring buffer.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/util/evlist.c | 11 ---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 68c1f95..b1cea71 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -812,6 +812,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist 
*evlist, int idx,
int fd;
int cpu;
 
+   mp->prot = PROT_READ | PROT_WRITE;
if (evsel->attr.write_backward) {
output = _output_backward;
maps = evlist->backward_mmap;
@@ -824,6 +

[PATCH v3 1/3] perf mmap: Fix perf backward recording

2017-12-04 Thread Wang Nan 
perf record backward recording doesn't work as we expected: it never
overwrite when ring buffer full.

Test:

(Run a busy python printing task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot.)

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps are never change, but my background task is a dead loop, can
easily overwhelme the ring buffer.

This patch fix it by force unsetting PROT_WRITE for backward ring
buffer, so all backward ring buffer become overwrite ring buffer.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan 
---
 tools/perf/util/evlist.c | 11 ---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 68c1f95..b1cea71 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -812,6 +812,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist 
*evlist, int idx,
int fd;
int cpu;
 
+   mp->prot = PROT_READ | PROT_WRITE;
if (evsel->attr.write_backward) {
output = _output_backward;
maps = evlist->backward_mmap;
@@ -824,6 +825,7 @@ s

[PATCH v3 0/3] perf tools: perf tools: Clarify overwrite and backward, bugfix

2017-12-04 Thread Wang Nan 
Simplify patch 1/3 following Namhyung's suggestion.

Context adjustment for patch 2 and 3.

Wang Nan (3):
  perf mmap: Fix perf backward recording
  perf tools: Don't discard prev in backward mode
  perf tools: Replace 'backward' to 'overwrite' in evlist. mmap and
record

 tools/perf/builtin-record.c | 14 +-
 tools/perf/tests/backward-ring-buffer.c |  4 +--
 tools/perf/util/evlist.c| 41 +-
 tools/perf/util/evlist.h|  2 +-
 tools/perf/util/mmap.c  | 45 +++--
 5 files changed, 54 insertions(+), 52 deletions(-)

-- 
2.10.1

[PATCH v3 0/3] perf tools: perf tools: Clarify overwrite and backward, bugfix

2017-12-04 Thread Wang Nan 
Simplify patch 1/3 following Namhyung's suggestion.

Context adjustment for patch 2 and 3.

Wang Nan (3):
  perf mmap: Fix perf backward recording
  perf tools: Don't discard prev in backward mode
  perf tools: Replace 'backward' to 'overwrite' in evlist. mmap and
record

 tools/perf/builtin-record.c | 14 +-
 tools/perf/tests/backward-ring-buffer.c |  4 +--
 tools/perf/util/evlist.c| 41 +-
 tools/perf/util/evlist.h|  2 +-
 tools/perf/util/mmap.c  | 45 +++--
 5 files changed, 54 insertions(+), 52 deletions(-)

-- 
2.10.1

[PATCH v2 0/8] perf tools: perf tools: Clarify overwrite and backward, bugfix

2017-12-02 Thread Wang Nan 
THe final result of this patchset is removing the concept of
'forward/backward', merge them into the concept of 'overwrite'.

Patch 1 to 5 clear arguments lists of many functions, remove the
'overwrite'. Because all callers of these functions doesn't need
the overwrite be set, we can simply remove them from arguments
lists and adjust code as if a 'false' is given.

Patch 6 fix a bug that forget to setting readonly for overwrite
ring buffers.

Patch 7 is suggested by Liang Kan, prevent dumpping duplicated
data if there's no so many events between two dumpping commands.

Patch 8 is 's/backward/overwrite'. After patch 8, the concept of
'backward' is removed from most of the code, make it uniform with
user interface ('--overwrite').

Cc: Kan Liang <kan.li...@intel.com>
Cc: Arnaldo Carvalho de Melo <a...@redhat.com>
Cc: Jiri Olsa <jo...@kernel.org>
Cc: Namhyung Kim <namhy...@kernel.org>
Cc: Zhang Mengting <zhangmengt...@huawei.com>

Wang Nan (8):
  perf tools: Remove 'overwrite' parameter from perf_evlist__mmap
  perf tools: Remove 'overwrite' parameter from perf_evlist__mmap_ex
  perf tools: Remove evlist->overwrite
  perf tools: Remove overwrite from arguments list of perf_mmap__push
  perf tools: Remove overwrite and check_messup from mmap read
  perf mmap: Fix perf backward recording
  perf tool: Don't discard prev in backward mode
  perf tools: Replace 'backward' to 'overwrite' in evlist, mmap and
record

 tools/perf/arch/x86/tests/perf-time-to-tsc.c |  2 +-
 tools/perf/builtin-kvm.c |  2 +-
 tools/perf/builtin-record.c  | 16 +++---
 tools/perf/builtin-top.c |  2 +-
 tools/perf/builtin-trace.c   |  2 +-
 tools/perf/tests/backward-ring-buffer.c  |  6 +--
 tools/perf/tests/bpf.c   |  2 +-
 tools/perf/tests/code-reading.c  |  2 +-
 tools/perf/tests/keep-tracking.c |  2 +-
 tools/perf/tests/mmap-basic.c|  2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  |  2 +-
 tools/perf/tests/perf-record.c   |  2 +-
 tools/perf/tests/sw-clock.c  |  2 +-
 tools/perf/tests/switch-tracking.c   |  2 +-
 tools/perf/tests/task-exit.c |  2 +-
 tools/perf/util/evlist.c | 53 ++--
 tools/perf/util/evlist.h |  8 ++-
 tools/perf/util/mmap.c   | 73 ++--
 tools/perf/util/mmap.h   |  4 +-
 tools/perf/util/python.c |  2 +-
 20 files changed, 81 insertions(+), 107 deletions(-)

-- 
2.10.1

[PATCH v2 0/8] perf tools: perf tools: Clarify overwrite and backward, bugfix

2017-12-02 Thread Wang Nan 
THe final result of this patchset is removing the concept of
'forward/backward', merge them into the concept of 'overwrite'.

Patch 1 to 5 clear arguments lists of many functions, remove the
'overwrite'. Because all callers of these functions doesn't need
the overwrite be set, we can simply remove them from arguments
lists and adjust code as if a 'false' is given.

Patch 6 fix a bug that forget to setting readonly for overwrite
ring buffers.

Patch 7 is suggested by Liang Kan, prevent dumpping duplicated
data if there's no so many events between two dumpping commands.

Patch 8 is 's/backward/overwrite'. After patch 8, the concept of
'backward' is removed from most of the code, make it uniform with
user interface ('--overwrite').

Cc: Kan Liang 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Zhang Mengting 

Wang Nan (8):
  perf tools: Remove 'overwrite' parameter from perf_evlist__mmap
  perf tools: Remove 'overwrite' parameter from perf_evlist__mmap_ex
  perf tools: Remove evlist->overwrite
  perf tools: Remove overwrite from arguments list of perf_mmap__push
  perf tools: Remove overwrite and check_messup from mmap read
  perf mmap: Fix perf backward recording
  perf tool: Don't discard prev in backward mode
  perf tools: Replace 'backward' to 'overwrite' in evlist, mmap and
record

 tools/perf/arch/x86/tests/perf-time-to-tsc.c |  2 +-
 tools/perf/builtin-kvm.c |  2 +-
 tools/perf/builtin-record.c  | 16 +++---
 tools/perf/builtin-top.c |  2 +-
 tools/perf/builtin-trace.c   |  2 +-
 tools/perf/tests/backward-ring-buffer.c  |  6 +--
 tools/perf/tests/bpf.c   |  2 +-
 tools/perf/tests/code-reading.c  |  2 +-
 tools/perf/tests/keep-tracking.c |  2 +-
 tools/perf/tests/mmap-basic.c|  2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  |  2 +-
 tools/perf/tests/perf-record.c   |  2 +-
 tools/perf/tests/sw-clock.c  |  2 +-
 tools/perf/tests/switch-tracking.c   |  2 +-
 tools/perf/tests/task-exit.c |  2 +-
 tools/perf/util/evlist.c | 53 ++--
 tools/perf/util/evlist.h |  8 ++-
 tools/perf/util/mmap.c   | 73 ++--
 tools/perf/util/mmap.h   |  4 +-
 tools/perf/util/python.c |  2 +-
 20 files changed, 81 insertions(+), 107 deletions(-)

-- 
2.10.1

[PATCH v2 6/8] perf mmap: Fix perf backward recording

2017-12-02 Thread Wang Nan 
perf record backward recording doesn't work as we expected: it never
overwrite when ring buffer full.

Test:

(Run a busy printing task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot.)

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps are never change, but my background task is a dead loop, can
easily overwhelme the ring buffer.

This patch fix it by force unsetting PROT_WRITE for backward ring
buffer, so all backward ring buffer become overwrite ring buffer.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/util/evlist.c | 9 +
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 68c1f95..bb70aef 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,7 +799,7 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *mp, int cpu_idx,
+  struct mmap_params mp, int cpu_idx,
   int thread, int *_outpu

[PATCH v2 7/8] perf tools: Don't discard prev in backward mode

2017-12-02 Thread Wang Nan 
Perf record can switch output. The new output should only store the
data after switching. However, in overwrite backward mode, the new
output still have the data from old output. That also brings extra
overhead.

At the end of mmap_read, the position of processed ring buffer is
saved in md->prev. Next mmap_read should be end in md->prev if it is
not overwriten. That avoids to process duplicate data.
However, the md->prev is discarded. So next mmap_read has to process
whole valid ring buffer, which probably include the old processed
data.

Avoid calling backward_rb_find_range() when md->prev is still
available.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Tested-by: Kan Liang <kan.li...@intel.com>
---
 tools/perf/util/mmap.c | 33 +++--
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3f262e7..5f8cb15 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -267,18 +267,6 @@ static int backward_rb_find_range(void *buf, int mask, u64 
head, u64 *start, u64
return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-u64 *start, u64 *end, bool backward)
-{
-   if (!backward) {
-   *start = old;
-   *end = head;
-   return 0;
-   }
-
-   return backward_rb_find_range(data, mask, head, start, end);
-}
-
 int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
@@ -290,19 +278,28 @@ int perf_mmap__push(struct perf_mmap *md, bool backward,
void *buf;
int rc = 0;
 
-   if (rb_find_range(data, md->mask, head, old, , , backward))
-   return -1;
+   start = backward ? head : old;
+   end = backward ? old : head;
 
if (start == end)
return 0;
 
size = end - start;
if (size > (unsigned long)(md->mask) + 1) {
-   WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
+   if (!backward) {
+   WARN_ONCE(1, "failed to keep up with mmap data. (warn 
only once)\n");
 
-   md->prev = head;
-   perf_mmap__consume(md, backward);
-   return 0;
+   md->prev = head;
+   perf_mmap__consume(md, backward);
+   return 0;
+   }
+
+   /*
+* Backward ring buffer is full. We still have a chance to read
+* most of data from it.
+*/
+   if (backward_rb_find_range(data, md->mask, head, , ))
+   return -1;
}
 
if ((start & md->mask) + size != (end & md->mask)) {
-- 
2.10.1

[PATCH v2 6/8] perf mmap: Fix perf backward recording

2017-12-02 Thread Wang Nan 
perf record backward recording doesn't work as we expected: it never
overwrite when ring buffer full.

Test:

(Run a busy printing task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot.)

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps are never change, but my background task is a dead loop, can
easily overwhelme the ring buffer.

This patch fix it by force unsetting PROT_WRITE for backward ring
buffer, so all backward ring buffer become overwrite ring buffer.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan 
---
 tools/perf/util/evlist.c | 9 +
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 68c1f95..bb70aef 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,7 +799,7 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *mp, int cpu_idx,
+  struct mmap_params mp, int cpu_idx,
   int thread, int *_output, int 
*_output_backward

[PATCH v2 7/8] perf tools: Don't discard prev in backward mode

2017-12-02 Thread Wang Nan 
Perf record can switch output. The new output should only store the
data after switching. However, in overwrite backward mode, the new
output still have the data from old output. That also brings extra
overhead.

At the end of mmap_read, the position of processed ring buffer is
saved in md->prev. Next mmap_read should be end in md->prev if it is
not overwriten. That avoids to process duplicate data.
However, the md->prev is discarded. So next mmap_read has to process
whole valid ring buffer, which probably include the old processed
data.

Avoid calling backward_rb_find_range() when md->prev is still
available.

Signed-off-by: Wang Nan 
Tested-by: Kan Liang 
---
 tools/perf/util/mmap.c | 33 +++--
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3f262e7..5f8cb15 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -267,18 +267,6 @@ static int backward_rb_find_range(void *buf, int mask, u64 
head, u64 *start, u64
return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-u64 *start, u64 *end, bool backward)
-{
-   if (!backward) {
-   *start = old;
-   *end = head;
-   return 0;
-   }
-
-   return backward_rb_find_range(data, mask, head, start, end);
-}
-
 int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
@@ -290,19 +278,28 @@ int perf_mmap__push(struct perf_mmap *md, bool backward,
void *buf;
int rc = 0;
 
-   if (rb_find_range(data, md->mask, head, old, , , backward))
-   return -1;
+   start = backward ? head : old;
+   end = backward ? old : head;
 
if (start == end)
return 0;
 
size = end - start;
if (size > (unsigned long)(md->mask) + 1) {
-   WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
+   if (!backward) {
+   WARN_ONCE(1, "failed to keep up with mmap data. (warn 
only once)\n");
 
-   md->prev = head;
-   perf_mmap__consume(md, backward);
-   return 0;
+   md->prev = head;
+   perf_mmap__consume(md, backward);
+   return 0;
+   }
+
+   /*
+* Backward ring buffer is full. We still have a chance to read
+* most of data from it.
+*/
+   if (backward_rb_find_range(data, md->mask, head, , ))
+   return -1;
}
 
if ((start & md->mask) + size != (end & md->mask)) {
-- 
2.10.1

[PATCH v2 5/8] perf tools: Remove overwrite and check_messup from mmap read

2017-12-02 Thread Wang Nan 
All perf_mmap__read_forward() read from read-write ring buffer,
so no need check_messup. Reading from backward ring buffer doesn't
require check_messup because it never mess up. Cleanup arguments
lists.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/util/evlist.c |  2 +-
 tools/perf/util/mmap.c   | 28 
 tools/perf/util/mmap.h   |  2 +-
 3 files changed, 6 insertions(+), 26 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a59134f..68c1f95 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct 
perf_evlist *evlist, int
 * No need for read-write ring buffer: kernel stop outputting when
 * it hit md->prev (perf_mmap__consume()).
 */
-   return perf_mmap__read_forward(md, false);
+   return perf_mmap__read_forward(md);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, 
int idx)
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 703ed41..3f262e7 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -21,33 +21,13 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 }
 
 /* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *perf_mmap__read(struct perf_mmap *map, bool 
check_messup,
+static union perf_event *perf_mmap__read(struct perf_mmap *map,
 u64 start, u64 end, u64 *prev)
 {
unsigned char *data = map->base + page_size;
union perf_event *event = NULL;
int diff = end - start;
 
-   if (check_messup) {
-   /*
-* If we're further behind than half the buffer, there's a 
chance
-* the writer will bite our tail and mess up the samples under 
us.
-*
-* If we somehow ended up ahead of the 'end', we got messed up.
-*
-* In either case, truncate and restart at 'end'.
-*/
-   if (diff > map->mask / 2 || diff < 0) {
-   fprintf(stderr, "WARNING: failed to keep up with mmap 
data.\n");
-
-   /*
-* 'end' points to a known good entry, start there.
-*/
-   start = end;
-   diff = 0;
-   }
-   }
-
if (diff >= (int)sizeof(event->header)) {
size_t size;
 
@@ -89,7 +69,7 @@ static union perf_event *perf_mmap__read(struct perf_mmap 
*map, bool check_messu
return event;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 {
u64 head;
u64 old = map->prev;
@@ -102,7 +82,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap 
*map, bool check_mess
 
head = perf_mmap__read_head(map);
 
-   return perf_mmap__read(map, check_messup, old, head, >prev);
+   return perf_mmap__read(map, old, head, >prev);
 }
 
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
@@ -138,7 +118,7 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap 
*map)
else
end = head + map->mask + 1;
 
-   return perf_mmap__read(map, false, start, end, >prev);
+   return perf_mmap__read(map, start, end, >prev);
 }
 
 void perf_mmap__read_catchup(struct perf_mmap *map)
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 2c3d291..d640273 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -86,7 +86,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap 
*md, u64 tail)
pc->data_tail = tail;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup);
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, bool backward,
-- 
2.10.1

[PATCH v2 5/8] perf tools: Remove overwrite and check_messup from mmap read

2017-12-02 Thread Wang Nan 
All perf_mmap__read_forward() read from read-write ring buffer,
so no need check_messup. Reading from backward ring buffer doesn't
require check_messup because it never mess up. Cleanup arguments
lists.

Signed-off-by: Wang Nan 
---
 tools/perf/util/evlist.c |  2 +-
 tools/perf/util/mmap.c   | 28 
 tools/perf/util/mmap.h   |  2 +-
 3 files changed, 6 insertions(+), 26 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a59134f..68c1f95 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct 
perf_evlist *evlist, int
 * No need for read-write ring buffer: kernel stop outputting when
 * it hit md->prev (perf_mmap__consume()).
 */
-   return perf_mmap__read_forward(md, false);
+   return perf_mmap__read_forward(md);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, 
int idx)
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 703ed41..3f262e7 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -21,33 +21,13 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 }
 
 /* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *perf_mmap__read(struct perf_mmap *map, bool 
check_messup,
+static union perf_event *perf_mmap__read(struct perf_mmap *map,
 u64 start, u64 end, u64 *prev)
 {
unsigned char *data = map->base + page_size;
union perf_event *event = NULL;
int diff = end - start;
 
-   if (check_messup) {
-   /*
-* If we're further behind than half the buffer, there's a 
chance
-* the writer will bite our tail and mess up the samples under 
us.
-*
-* If we somehow ended up ahead of the 'end', we got messed up.
-*
-* In either case, truncate and restart at 'end'.
-*/
-   if (diff > map->mask / 2 || diff < 0) {
-   fprintf(stderr, "WARNING: failed to keep up with mmap 
data.\n");
-
-   /*
-* 'end' points to a known good entry, start there.
-*/
-   start = end;
-   diff = 0;
-   }
-   }
-
if (diff >= (int)sizeof(event->header)) {
size_t size;
 
@@ -89,7 +69,7 @@ static union perf_event *perf_mmap__read(struct perf_mmap 
*map, bool check_messu
return event;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 {
u64 head;
u64 old = map->prev;
@@ -102,7 +82,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap 
*map, bool check_mess
 
head = perf_mmap__read_head(map);
 
-   return perf_mmap__read(map, check_messup, old, head, >prev);
+   return perf_mmap__read(map, old, head, >prev);
 }
 
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
@@ -138,7 +118,7 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap 
*map)
else
end = head + map->mask + 1;
 
-   return perf_mmap__read(map, false, start, end, >prev);
+   return perf_mmap__read(map, start, end, >prev);
 }
 
 void perf_mmap__read_catchup(struct perf_mmap *map)
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 2c3d291..d640273 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -86,7 +86,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap 
*md, u64 tail)
pc->data_tail = tail;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup);
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, bool backward,
-- 
2.10.1

[PATCH v2 4/8] perf tools: Remove overwrite from arguments list of perf_mmap__push

2017-12-02 Thread Wang Nan 
'overwrite' argument is always 'false'. Revmove it from arguments
list of perf_mmap__push.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/mmap.c  | 6 +++---
 tools/perf/util/mmap.h  | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3bc6cee..26b8571 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -500,7 +500,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], false, backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 9fe5f9c..703ed41 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -299,7 +299,7 @@ static int rb_find_range(void *data, int mask, u64 head, 
u64 old,
return backward_rb_find_range(data, mask, head, start, end);
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
u64 head = perf_mmap__read_head(md);
@@ -321,7 +321,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
 
md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
+   perf_mmap__consume(md, backward);
return 0;
}
 
@@ -346,7 +346,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
}
 
md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
+   perf_mmap__consume(md, backward);
 out:
return rc;
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index efd78b8..2c3d291 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -89,7 +89,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap 
*md, u64 tail)
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
-- 
2.10.1

[PATCH v2 4/8] perf tools: Remove overwrite from arguments list of perf_mmap__push

2017-12-02 Thread Wang Nan 
'overwrite' argument is always 'false'. Revmove it from arguments
list of perf_mmap__push.

Signed-off-by: Wang Nan 
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/mmap.c  | 6 +++---
 tools/perf/util/mmap.h  | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3bc6cee..26b8571 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -500,7 +500,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], false, backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 9fe5f9c..703ed41 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -299,7 +299,7 @@ static int rb_find_range(void *data, int mask, u64 head, 
u64 old,
return backward_rb_find_range(data, mask, head, start, end);
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
u64 head = perf_mmap__read_head(md);
@@ -321,7 +321,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
 
md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
+   perf_mmap__consume(md, backward);
return 0;
}
 
@@ -346,7 +346,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
}
 
md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
+   perf_mmap__consume(md, backward);
 out:
return rc;
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index efd78b8..2c3d291 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -89,7 +89,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap 
*md, u64 tail)
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool 
check_messup);
 union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
+int perf_mmap__push(struct perf_mmap *md, bool backward,
void *to, int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
-- 
2.10.1

[PATCH v2 2/8] perf tools: Remove 'overwrite' parameter from perf_evlist__mmap_ex

2017-12-02 Thread Wang Nan 
All users of perf_evlist__mmap_ex set !overwrite. Remove it from its
arguments list.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/evlist.c| 8 
 tools/perf/util/evlist.h| 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e304bc4..08070f8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -301,7 +301,7 @@ static int record__mmap_evlist(struct record *rec,
struct record_opts *opts = >opts;
char msg[512];
 
-   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 opts->auxtrace_mmap_pages,
 opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3c1778b..93272d9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1052,14 +1052,14 @@ int perf_evlist__parse_mmap_pages(const struct option 
*opt, const char *str,
  * Return: %0 on success, negative error code otherwise.
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-bool overwrite, unsigned int auxtrace_pages,
+unsigned int auxtrace_pages,
 bool auxtrace_overwrite)
 {
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
struct mmap_params mp = {
-   .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
+   .prot = PROT_READ | PROT_WRITE,
};
 
if (!evlist->mmap)
@@ -1070,7 +1070,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) 
< 0)
return -ENOMEM;
 
-   evlist->overwrite = overwrite;
+   evlist->overwrite = false;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
@@ -1093,7 +1093,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-   return perf_evlist__mmap_ex(evlist, pages, false, 0, false);
+   return perf_evlist__mmap_ex(evlist, pages, 0, false);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f0f2c8b..424a3d6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -169,7 +169,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
 unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-bool overwrite, unsigned int auxtrace_pages,
+unsigned int auxtrace_pages,
 bool auxtrace_overwrite);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
-- 
2.10.1

[PATCH v2 2/8] perf tools: Remove 'overwrite' parameter from perf_evlist__mmap_ex

2017-12-02 Thread Wang Nan 
All users of perf_evlist__mmap_ex set !overwrite. Remove it from its
arguments list.

Signed-off-by: Wang Nan 
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/evlist.c| 8 
 tools/perf/util/evlist.h| 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e304bc4..08070f8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -301,7 +301,7 @@ static int record__mmap_evlist(struct record *rec,
struct record_opts *opts = >opts;
char msg[512];
 
-   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 opts->auxtrace_mmap_pages,
 opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3c1778b..93272d9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1052,14 +1052,14 @@ int perf_evlist__parse_mmap_pages(const struct option 
*opt, const char *str,
  * Return: %0 on success, negative error code otherwise.
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-bool overwrite, unsigned int auxtrace_pages,
+unsigned int auxtrace_pages,
 bool auxtrace_overwrite)
 {
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
struct mmap_params mp = {
-   .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
+   .prot = PROT_READ | PROT_WRITE,
};
 
if (!evlist->mmap)
@@ -1070,7 +1070,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) 
< 0)
return -ENOMEM;
 
-   evlist->overwrite = overwrite;
+   evlist->overwrite = false;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
@@ -1093,7 +1093,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-   return perf_evlist__mmap_ex(evlist, pages, false, 0, false);
+   return perf_evlist__mmap_ex(evlist, pages, 0, false);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f0f2c8b..424a3d6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -169,7 +169,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
 unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-bool overwrite, unsigned int auxtrace_pages,
+unsigned int auxtrace_pages,
 bool auxtrace_overwrite);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
-- 
2.10.1

[PATCH v2 8/8] perf tools: Replace 'backward' to 'overwrite' in evlist, mmap and record

2017-12-02 Thread Wang Nan 
Remove the backward/forward concept to make it uniform with user
interface (the '--overwrite' option).

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/builtin-record.c | 14 +++---
 tools/perf/tests/backward-ring-buffer.c |  4 ++--
 tools/perf/util/evlist.c| 30 +++---
 tools/perf/util/evlist.h|  2 +-
 tools/perf/util/mmap.c  | 22 +++---
 5 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 26b8571..0a5749e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -479,7 +479,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist 
*evlist,
-   bool backward)
+   bool overwrite)
 {
u64 bytes_written = rec->bytes_written;
int i;
@@ -489,18 +489,18 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (!evlist)
return 0;
 
-   maps = backward ? evlist->backward_mmap : evlist->mmap;
+   maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
if (!maps)
return 0;
 
-   if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+   if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], overwrite, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
@@ -520,7 +520,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (bytes_written != rec->bytes_written)
rc = record__write(rec, _round_event, 
sizeof(finished_round_event));
 
-   if (backward)
+   if (overwrite)
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
return rc;
@@ -692,8 +692,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
if (evlist) {
if (evlist->mmap && evlist->mmap[0].base)
return evlist->mmap[0].base;
-   if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-   return evlist->backward_mmap[0].base;
+   if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+   return evlist->overwrite_mmap[0].base;
}
return NULL;
 }
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index cf37e43..4035d43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,8 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int 
*sample_count,
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
 
-   perf_mmap__read_catchup(>backward_mmap[i]);
-   while ((event = 
perf_mmap__read_backward(>backward_mmap[i])) != NULL) {
+   perf_mmap__read_catchup(>overwrite_mmap[i]);
+   while ((event = 
perf_mmap__read_backward(>overwrite_mmap[i])) != NULL) {
const u32 type = event->header.type;
 
switch (type) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bb70aef..2774528a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -125,7 +125,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
zfree(>mmap);
-   zfree(>backward_mmap);
+   zfree(>overwrite_mmap);
fdarray__exit(>pollfd);
 }
 
@@ -675,11 +675,11 @@ static int perf_evlist__set_paused(struct perf_evlist 
*evlist, bool value)
 {
int i;
 
-   if (!evlist->backward_mmap)
+   if (!evlist->overwrite_mmap)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
-   int fd = evlist->backward_mmap[i].fd;
+   int fd = evlist->overwrite_mmap[i].fd;
int err;
 
if (fd < 0)
@@ -749,16 +749,16 @@ static void perf_evlist__munmap_nofree(struct perf_evlist 
*evlist)
for (i = 0; i < evlist->nr_mmaps; i++)
perf_mmap__munmap(>mmap[i]);
 
-   if (evlist->backward_mmap)
+   if (evlist->overwrite_mmap)
for (i = 0; i < evlist->

[PATCH v2 8/8] perf tools: Replace 'backward' to 'overwrite' in evlist, mmap and record

2017-12-02 Thread Wang Nan 
Remove the backward/forward concept to make it uniform with user
interface (the '--overwrite' option).

Signed-off-by: Wang Nan 
---
 tools/perf/builtin-record.c | 14 +++---
 tools/perf/tests/backward-ring-buffer.c |  4 ++--
 tools/perf/util/evlist.c| 30 +++---
 tools/perf/util/evlist.h|  2 +-
 tools/perf/util/mmap.c  | 22 +++---
 5 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 26b8571..0a5749e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -479,7 +479,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist 
*evlist,
-   bool backward)
+   bool overwrite)
 {
u64 bytes_written = rec->bytes_written;
int i;
@@ -489,18 +489,18 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (!evlist)
return 0;
 
-   maps = backward ? evlist->backward_mmap : evlist->mmap;
+   maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
if (!maps)
return 0;
 
-   if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+   if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
+   if (perf_mmap__push([i], overwrite, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
@@ -520,7 +520,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
if (bytes_written != rec->bytes_written)
rc = record__write(rec, _round_event, 
sizeof(finished_round_event));
 
-   if (backward)
+   if (overwrite)
perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
return rc;
@@ -692,8 +692,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
if (evlist) {
if (evlist->mmap && evlist->mmap[0].base)
return evlist->mmap[0].base;
-   if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-   return evlist->backward_mmap[0].base;
+   if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+   return evlist->overwrite_mmap[0].base;
}
return NULL;
 }
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index cf37e43..4035d43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,8 +33,8 @@ static int count_samples(struct perf_evlist *evlist, int 
*sample_count,
for (i = 0; i < evlist->nr_mmaps; i++) {
union perf_event *event;
 
-   perf_mmap__read_catchup(>backward_mmap[i]);
-   while ((event = 
perf_mmap__read_backward(>backward_mmap[i])) != NULL) {
+   perf_mmap__read_catchup(>overwrite_mmap[i]);
+   while ((event = 
perf_mmap__read_backward(>overwrite_mmap[i])) != NULL) {
const u32 type = event->header.type;
 
switch (type) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bb70aef..2774528a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -125,7 +125,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
zfree(>mmap);
-   zfree(>backward_mmap);
+   zfree(>overwrite_mmap);
fdarray__exit(>pollfd);
 }
 
@@ -675,11 +675,11 @@ static int perf_evlist__set_paused(struct perf_evlist 
*evlist, bool value)
 {
int i;
 
-   if (!evlist->backward_mmap)
+   if (!evlist->overwrite_mmap)
return 0;
 
for (i = 0; i < evlist->nr_mmaps; i++) {
-   int fd = evlist->backward_mmap[i].fd;
+   int fd = evlist->overwrite_mmap[i].fd;
int err;
 
if (fd < 0)
@@ -749,16 +749,16 @@ static void perf_evlist__munmap_nofree(struct perf_evlist 
*evlist)
for (i = 0; i < evlist->nr_mmaps; i++)
perf_mmap__munmap(>mmap[i]);
 
-   if (evlist->backward_mmap)
+   if (evlist->overwrite_mmap)
for (i = 0; i < evlist->nr_mmaps; i++)
-

[PATCH v2 1/8] perf tools: Remove 'overwrite' parameter from perf_evlist__mmap

2017-12-02 Thread Wang Nan 
Now all perf_evlist__mmap's users doesn't set 'overwrite'. Remove it from
arguments list.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c | 2 +-
 tools/perf/builtin-kvm.c | 2 +-
 tools/perf/builtin-top.c | 2 +-
 tools/perf/builtin-trace.c   | 2 +-
 tools/perf/tests/backward-ring-buffer.c  | 2 +-
 tools/perf/tests/bpf.c   | 2 +-
 tools/perf/tests/code-reading.c  | 2 +-
 tools/perf/tests/keep-tracking.c | 2 +-
 tools/perf/tests/mmap-basic.c| 2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  | 2 +-
 tools/perf/tests/perf-record.c   | 2 +-
 tools/perf/tests/sw-clock.c  | 2 +-
 tools/perf/tests/switch-tracking.c   | 2 +-
 tools/perf/tests/task-exit.c | 2 +-
 tools/perf/util/evlist.c | 5 ++---
 tools/perf/util/evlist.h | 3 +--
 tools/perf/util/python.c | 2 +-
 17 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c 
b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index b59678e..06abe81 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -84,7 +84,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, 
int subtest __maybe
 
CHECK__(perf_evlist__open(evlist));
 
-   CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+   CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
pc = evlist->mmap[0].base;
ret = perf_read_tsc_conversion(pc, );
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 597c7de..9885316 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1044,7 +1044,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
goto out;
}
 
-   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
ui__error("Failed to mmap the events: %s\n",
  str_error_r(errno, sbuf, sizeof(sbuf)));
perf_evlist__close(evlist);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0077724..540461f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -907,7 +907,7 @@ static int perf_top__start_counters(struct perf_top *top)
}
}
 
-   if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
ui__error("Failed to mmap with %d (%s)\n",
errno, str_error_r(errno, msg, sizeof(msg)));
goto out_err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 84debdb..7c57898 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2437,7 +2437,7 @@ static int trace__run(struct trace *trace, int argc, 
const char **argv)
if (err < 0)
goto out_error_apply_filters;
 
-   err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
+   err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
if (err < 0)
goto out_error_mmap;
 
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index 43a8c6a..cf37e43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -59,7 +59,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
int err;
char sbuf[STRERR_BUFSIZE];
 
-   err = perf_evlist__mmap(evlist, mmap_pages, false);
+   err = perf_evlist__mmap(evlist, mmap_pages);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 34c22cd..c433dd3 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -167,7 +167,7 @@ static int do_test(struct bpf_object *obj, int 
(*func)(void),
goto out_delete_evlist;
}
 
-   err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+   err = perf_evlist__mmap(evlist, opts.mmap_pages);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index fcc8984..3bf7b14 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -639,7 +639,7 @@ static int do_test_code_reading(bool try_kcore)
break;
}
 
-   ret = perf_evlist__mmap(evlist, UINT_MAX, false);
+   ret = perf_evlist__mmap(evl

[PATCH v2 3/8] perf tools: Remove evlist->overwrite

2017-12-02 Thread Wang Nan 
evlist->overwrite is set to false in all users. It can be removed.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/evlist.c| 5 ++---
 tools/perf/util/evlist.h| 1 -
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 08070f8..3bc6cee 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -500,7 +500,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], evlist->overwrite, 
backward, rec, record__pushfn) != 0) {
+   if (perf_mmap__push([i], false, backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 93272d9..a59134f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct 
perf_evlist *evlist, int
 * No need for read-write ring buffer: kernel stop outputting when
 * it hit md->prev (perf_mmap__consume()).
 */
-   return perf_mmap__read_forward(md, evlist->overwrite);
+   return perf_mmap__read_forward(md, false);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, 
int idx)
@@ -738,7 +738,7 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist 
*evlist, int idx)
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
-   perf_mmap__consume(>mmap[idx], evlist->overwrite);
+   perf_mmap__consume(>mmap[idx], false);
 }
 
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
@@ -1070,7 +1070,6 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) 
< 0)
return -ENOMEM;
 
-   evlist->overwrite = false;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 424a3d6..eec3377 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -31,7 +31,6 @@ struct perf_evlist {
int  nr_entries;
int  nr_groups;
int  nr_mmaps;
-   bool overwrite;
bool enabled;
bool has_user_cpus;
size_t   mmap_len;
-- 
2.10.1

[PATCH v2 1/8] perf tools: Remove 'overwrite' parameter from perf_evlist__mmap

2017-12-02 Thread Wang Nan 
Now all perf_evlist__mmap's users doesn't set 'overwrite'. Remove it from
arguments list.

Signed-off-by: Wang Nan 
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c | 2 +-
 tools/perf/builtin-kvm.c | 2 +-
 tools/perf/builtin-top.c | 2 +-
 tools/perf/builtin-trace.c   | 2 +-
 tools/perf/tests/backward-ring-buffer.c  | 2 +-
 tools/perf/tests/bpf.c   | 2 +-
 tools/perf/tests/code-reading.c  | 2 +-
 tools/perf/tests/keep-tracking.c | 2 +-
 tools/perf/tests/mmap-basic.c| 2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  | 2 +-
 tools/perf/tests/perf-record.c   | 2 +-
 tools/perf/tests/sw-clock.c  | 2 +-
 tools/perf/tests/switch-tracking.c   | 2 +-
 tools/perf/tests/task-exit.c | 2 +-
 tools/perf/util/evlist.c | 5 ++---
 tools/perf/util/evlist.h | 3 +--
 tools/perf/util/python.c | 2 +-
 17 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c 
b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index b59678e..06abe81 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -84,7 +84,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, 
int subtest __maybe
 
CHECK__(perf_evlist__open(evlist));
 
-   CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+   CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
pc = evlist->mmap[0].base;
ret = perf_read_tsc_conversion(pc, );
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 597c7de..9885316 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1044,7 +1044,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
goto out;
}
 
-   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
ui__error("Failed to mmap the events: %s\n",
  str_error_r(errno, sbuf, sizeof(sbuf)));
perf_evlist__close(evlist);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0077724..540461f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -907,7 +907,7 @@ static int perf_top__start_counters(struct perf_top *top)
}
}
 
-   if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
ui__error("Failed to mmap with %d (%s)\n",
errno, str_error_r(errno, msg, sizeof(msg)));
goto out_err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 84debdb..7c57898 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2437,7 +2437,7 @@ static int trace__run(struct trace *trace, int argc, 
const char **argv)
if (err < 0)
goto out_error_apply_filters;
 
-   err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
+   err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
if (err < 0)
goto out_error_mmap;
 
diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index 43a8c6a..cf37e43 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -59,7 +59,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
int err;
char sbuf[STRERR_BUFSIZE];
 
-   err = perf_evlist__mmap(evlist, mmap_pages, false);
+   err = perf_evlist__mmap(evlist, mmap_pages);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 34c22cd..c433dd3 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -167,7 +167,7 @@ static int do_test(struct bpf_object *obj, int 
(*func)(void),
goto out_delete_evlist;
}
 
-   err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+   err = perf_evlist__mmap(evlist, opts.mmap_pages);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index fcc8984..3bf7b14 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -639,7 +639,7 @@ static int do_test_code_reading(bool try_kcore)
break;
}
 
-   ret = perf_evlist__mmap(evlist, UINT_MAX, false);
+   ret = perf_evlist__mmap(evlist, UINT_MAX);
if (ret < 0

[PATCH v2 3/8] perf tools: Remove evlist->overwrite

2017-12-02 Thread Wang Nan 
evlist->overwrite is set to false in all users. It can be removed.

Signed-off-by: Wang Nan 
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/util/evlist.c| 5 ++---
 tools/perf/util/evlist.h| 1 -
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 08070f8..3bc6cee 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -500,7 +500,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], evlist->overwrite, 
backward, rec, record__pushfn) != 0) {
+   if (perf_mmap__push([i], false, backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 93272d9..a59134f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -711,7 +711,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct 
perf_evlist *evlist, int
 * No need for read-write ring buffer: kernel stop outputting when
 * it hit md->prev (perf_mmap__consume()).
 */
-   return perf_mmap__read_forward(md, evlist->overwrite);
+   return perf_mmap__read_forward(md, false);
 }
 
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, 
int idx)
@@ -738,7 +738,7 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist 
*evlist, int idx)
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
-   perf_mmap__consume(>mmap[idx], evlist->overwrite);
+   perf_mmap__consume(>mmap[idx], false);
 }
 
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
@@ -1070,7 +1070,6 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) 
< 0)
return -ENOMEM;
 
-   evlist->overwrite = false;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
mp.mask = evlist->mmap_len - page_size - 1;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 424a3d6..eec3377 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -31,7 +31,6 @@ struct perf_evlist {
int  nr_entries;
int  nr_groups;
int  nr_mmaps;
-   bool overwrite;
bool enabled;
bool has_user_cpus;
size_t   mmap_len;
-- 
2.10.1

[tip:perf/core] perf tests: Set evlist of test__task_exit() to !overwrite

2017-11-18 Thread tip-bot for Wang Nan 
Commit-ID:  a0e3dd79cdd8ad838cbcefeff530a15193f8336e
Gitweb: https://git.kernel.org/tip/a0e3dd79cdd8ad838cbcefeff530a15193f8336e
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Mon, 13 Nov 2017 01:38:07 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Thu, 16 Nov 2017 14:49:58 -0300

perf tests: Set evlist of test__task_exit() to !overwrite

Changing ringbuffer to !overwrite in this task is harmless because
this test uses a very low frequency (1) and using a very simple program
(true). There should have only 3 events in the whole test.  Overwriting
is impossible to happen.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Cc: Namhyung Kim <namhy...@kernel.org>
Link: http://lkml.kernel.org/r/20171113013809.212417-6-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/tests/task-exit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bc4a734..98c0984 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -97,7 +97,7 @@ int test__task_exit(struct test *test __maybe_unused, int 
subtest __maybe_unused
goto out_delete_evlist;
}
 
-   if (perf_evlist__mmap(evlist, 128, true) < 0) {
+   if (perf_evlist__mmap(evlist, 128, false) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;

[tip:perf/core] perf tests: Set evlist of test__task_exit() to !overwrite

2017-11-18 Thread tip-bot for Wang Nan 
Commit-ID:  a0e3dd79cdd8ad838cbcefeff530a15193f8336e
Gitweb: https://git.kernel.org/tip/a0e3dd79cdd8ad838cbcefeff530a15193f8336e
Author: Wang Nan 
AuthorDate: Mon, 13 Nov 2017 01:38:07 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Thu, 16 Nov 2017 14:49:58 -0300

perf tests: Set evlist of test__task_exit() to !overwrite

Changing ringbuffer to !overwrite in this task is harmless because
this test uses a very low frequency (1) and using a very simple program
(true). There should have only 3 events in the whole test.  Overwriting
is impossible to happen.

Signed-off-by: Wang Nan 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Namhyung Kim 
Link: http://lkml.kernel.org/r/20171113013809.212417-6-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/tests/task-exit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bc4a734..98c0984 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -97,7 +97,7 @@ int test__task_exit(struct test *test __maybe_unused, int 
subtest __maybe_unused
goto out_delete_evlist;
}
 
-   if (perf_evlist__mmap(evlist, 128, true) < 0) {
+   if (perf_evlist__mmap(evlist, 128, false) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;

[tip:perf/core] perf tests: Set evlist of test__sw_clock_freq() to !overwrite

2017-11-18 Thread tip-bot for Wang Nan 
Commit-ID:  677b0601768881934f658bebb1713c3c843893fa
Gitweb: https://git.kernel.org/tip/677b0601768881934f658bebb1713c3c843893fa
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Mon, 13 Nov 2017 01:38:05 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Thu, 16 Nov 2017 14:49:57 -0300

perf tests: Set evlist of test__sw_clock_freq() to !overwrite

Unsetting overwrite when calling perf_evlist__mmap is harmless. This
commit passes false to it, makes following commits eliminate the
overwrite argument easier.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Cc: Namhyung Kim <namhy...@kernel.org>
Link: http://lkml.kernel.org/r/20171113013809.212417-4-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/tests/sw-clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 725a196..c6937ed 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
goto out_delete_evlist;
}
 
-   err = perf_evlist__mmap(evlist, 128, true);
+   err = perf_evlist__mmap(evlist, 128, false);
if (err < 0) {
pr_debug("failed to mmap event: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));

[tip:perf/core] perf tests: Set evlist of test__backward_ring_buffer() to !overwrite

2017-11-18 Thread tip-bot for Wang Nan 
Commit-ID:  d492326f160e44e08fcf132a63163b36dd8e8839
Gitweb: https://git.kernel.org/tip/d492326f160e44e08fcf132a63163b36dd8e8839
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Mon, 13 Nov 2017 01:38:04 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Thu, 16 Nov 2017 14:49:57 -0300

perf tests: Set evlist of test__backward_ring_buffer() to !overwrite

Setting overwrite in perf_evlist__mmap() is meaningless because the
event in this evlist is already have 'overwrite' postfix and goes to
backward ring buffer automatically. Pass 'false' to perf_evlist__mmap()
to make it similar to others.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Cc: Namhyung Kim <namhy...@kernel.org>
Link: http://lkml.kernel.org/r/20171113013809.212417-3-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/tests/backward-ring-buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index 71b9a0b..43a8c6a 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -59,7 +59,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
int err;
char sbuf[STRERR_BUFSIZE];
 
-   err = perf_evlist__mmap(evlist, mmap_pages, true);
+   err = perf_evlist__mmap(evlist, mmap_pages, false);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));

[tip:perf/core] perf tests: Set evlist of test__sw_clock_freq() to !overwrite

2017-11-18 Thread tip-bot for Wang Nan 
Commit-ID:  677b0601768881934f658bebb1713c3c843893fa
Gitweb: https://git.kernel.org/tip/677b0601768881934f658bebb1713c3c843893fa
Author: Wang Nan 
AuthorDate: Mon, 13 Nov 2017 01:38:05 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Thu, 16 Nov 2017 14:49:57 -0300

perf tests: Set evlist of test__sw_clock_freq() to !overwrite

Unsetting overwrite when calling perf_evlist__mmap is harmless. This
commit passes false to it, makes following commits eliminate the
overwrite argument easier.

Signed-off-by: Wang Nan 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Namhyung Kim 
Link: http://lkml.kernel.org/r/20171113013809.212417-4-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/tests/sw-clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 725a196..c6937ed 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
goto out_delete_evlist;
}
 
-   err = perf_evlist__mmap(evlist, 128, true);
+   err = perf_evlist__mmap(evlist, 128, false);
if (err < 0) {
pr_debug("failed to mmap event: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));

[tip:perf/core] perf tests: Set evlist of test__backward_ring_buffer() to !overwrite

2017-11-18 Thread tip-bot for Wang Nan 
Commit-ID:  d492326f160e44e08fcf132a63163b36dd8e8839
Gitweb: https://git.kernel.org/tip/d492326f160e44e08fcf132a63163b36dd8e8839
Author: Wang Nan 
AuthorDate: Mon, 13 Nov 2017 01:38:04 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Thu, 16 Nov 2017 14:49:57 -0300

perf tests: Set evlist of test__backward_ring_buffer() to !overwrite

Setting overwrite in perf_evlist__mmap() is meaningless because the
event in this evlist is already have 'overwrite' postfix and goes to
backward ring buffer automatically. Pass 'false' to perf_evlist__mmap()
to make it similar to others.

Signed-off-by: Wang Nan 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Namhyung Kim 
Link: http://lkml.kernel.org/r/20171113013809.212417-3-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/tests/backward-ring-buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index 71b9a0b..43a8c6a 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -59,7 +59,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
int err;
char sbuf[STRERR_BUFSIZE];
 
-   err = perf_evlist__mmap(evlist, mmap_pages, true);
+   err = perf_evlist__mmap(evlist, mmap_pages, false);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));

[tip:perf/core] perf tests: Set evlist of test__basic_mmap() to !overwrite

2017-11-18 Thread tip-bot for Wang Nan 
Commit-ID:  301d724aa19add1c0cf3ec8cad0d10151d30393f
Gitweb: https://git.kernel.org/tip/301d724aa19add1c0cf3ec8cad0d10151d30393f
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Mon, 13 Nov 2017 01:38:06 +
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Thu, 16 Nov 2017 14:49:58 -0300

perf tests: Set evlist of test__basic_mmap() to !overwrite

In this test, a large ring buffer is required so all events can feed
into, so overwrite or not is meaningless.

Change to !overwrite so following commits can remove this argument.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kan Liang <kan.li...@intel.com>
Cc: Namhyung Kim <namhy...@kernel.org>
Link: http://lkml.kernel.org/r/20171113013809.212417-5-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/tests/mmap-basic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5a8bf31..91f10d6 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -94,7 +94,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int 
subtest __maybe_unuse
expected_nr_events[i] = 1 + rand() % 127;
}
 
-   if (perf_evlist__mmap(evlist, 128, true) < 0) {
+   if (perf_evlist__mmap(evlist, 128, false) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;

[tip:perf/core] perf tests: Set evlist of test__basic_mmap() to !overwrite

2017-11-18 Thread tip-bot for Wang Nan 
Commit-ID:  301d724aa19add1c0cf3ec8cad0d10151d30393f
Gitweb: https://git.kernel.org/tip/301d724aa19add1c0cf3ec8cad0d10151d30393f
Author: Wang Nan 
AuthorDate: Mon, 13 Nov 2017 01:38:06 +
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Thu, 16 Nov 2017 14:49:58 -0300

perf tests: Set evlist of test__basic_mmap() to !overwrite

In this test, a large ring buffer is required so all events can feed
into, so overwrite or not is meaningless.

Change to !overwrite so following commits can remove this argument.

Signed-off-by: Wang Nan 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Namhyung Kim 
Link: http://lkml.kernel.org/r/20171113013809.212417-5-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/tests/mmap-basic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5a8bf31..91f10d6 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -94,7 +94,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int 
subtest __maybe_unuse
expected_nr_events[i] = 1 + rand() % 127;
}
 
-   if (perf_evlist__mmap(evlist, 128, true) < 0) {
+   if (perf_evlist__mmap(evlist, 128, false) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;

[PATCH 7/7] perf tools: Remove prot field in mmap param

2017-11-12 Thread Wang Nan 
After removing the concept of 'overwrite' in code level, now the
prot is determinated by write_backward. There's no need to pass
prot from perf_evlist__mmap_ex().

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/util/evlist.c | 17 ++---
 tools/perf/util/mmap.c   |  4 ++--
 tools/perf/util/mmap.h   |  4 ++--
 3 files changed, 10 insertions(+), 15 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4948d3d..0d713e0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,28 +799,23 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *_mp, int cpu_idx,
+  struct mmap_params *mp, int cpu_idx,
   int thread, int *_output, int 
*_output_backward)
 {
struct perf_evsel *evsel;
int revent;
int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx);
-   struct mmap_params *mp;
 
evlist__for_each_entry(evlist, evsel) {
struct perf_mmap *maps = evlist->mmap;
-   struct mmap_params rdonly_mp;
int *output = _output;
int fd;
int cpu;
+   int prot = PROT_READ;
 
-   mp = _mp;
if (evsel->attr.write_backward) {
output = _output_backward;
maps = evlist->backward_mmap;
-   rdonly_mp = *_mp;
-   rdonly_mp.prot &= ~PROT_WRITE;
-   mp = _mp;
 
if (!maps) {
maps = perf_evlist__alloc_mmap(evlist);
@@ -830,6 +825,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist 
*evlist, int idx,
if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
perf_evlist__toggle_bkw_mmap(evlist, 
BKW_MMAP_RUNNING);
}
+   } else {
+   prot |= PROT_WRITE;
}
 
if (evsel->system_wide && thread)
@@ -844,7 +841,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist 
*evlist, int idx,
if (*output == -1) {
*output = fd;
 
-   if (perf_mmap__mmap([idx], mp, *output)  < 0)
+   if (perf_mmap__mmap([idx], mp, prot, *output)  < 0)
return -1;
} else {
if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
@@ -1064,9 +1061,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
-   struct mmap_params mp = {
-   .prot = PROT_READ | PROT_WRITE,
-   };
+   struct mmap_params mp;
 
if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 703ed41..40e91a0 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -219,7 +219,7 @@ void perf_mmap__munmap(struct perf_mmap *map)
auxtrace_mmap__munmap(>auxtrace_mmap);
 }
 
-int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int prot, 
int fd)
 {
/*
 * The last one will be done at perf_evlist__mmap_consume(), so that we
@@ -237,7 +237,7 @@ int perf_mmap__mmap(struct perf_mmap *map, struct 
mmap_params *mp, int fd)
refcount_set(>refcnt, 2);
map->prev = 0;
map->mask = mp->mask;
-   map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+   map->base = mmap(NULL, perf_mmap__mmap_len(map), prot,
 MAP_SHARED, fd, 0);
if (map->base == MAP_FAILED) {
pr_debug2("failed to mmap perf event ring buffer, error %d\n",
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 2c3d291..1f6fcc6 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -53,11 +53,11 @@ enum bkw_mmap_state {
 };
 
 struct mmap_params {
-   int prot, mask;
+   int mask;
struct auxtrace_mmap_params auxtrace_mp;
 };
 
-int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd);
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int prot, 
int fd);
 void perf_mmap__munmap(struct perf_mmap *map);
 
 void perf_mmap__get(struct perf_mmap *map);
-- 
2.10.1

[PATCH 7/7] perf tools: Remove prot field in mmap param

2017-11-12 Thread Wang Nan 
After removing the concept of 'overwrite' in code level, now the
prot is determinated by write_backward. There's no need to pass
prot from perf_evlist__mmap_ex().

Signed-off-by: Wang Nan 
---
 tools/perf/util/evlist.c | 17 ++---
 tools/perf/util/mmap.c   |  4 ++--
 tools/perf/util/mmap.h   |  4 ++--
 3 files changed, 10 insertions(+), 15 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4948d3d..0d713e0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,28 +799,23 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *_mp, int cpu_idx,
+  struct mmap_params *mp, int cpu_idx,
   int thread, int *_output, int 
*_output_backward)
 {
struct perf_evsel *evsel;
int revent;
int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx);
-   struct mmap_params *mp;
 
evlist__for_each_entry(evlist, evsel) {
struct perf_mmap *maps = evlist->mmap;
-   struct mmap_params rdonly_mp;
int *output = _output;
int fd;
int cpu;
+   int prot = PROT_READ;
 
-   mp = _mp;
if (evsel->attr.write_backward) {
output = _output_backward;
maps = evlist->backward_mmap;
-   rdonly_mp = *_mp;
-   rdonly_mp.prot &= ~PROT_WRITE;
-   mp = _mp;
 
if (!maps) {
maps = perf_evlist__alloc_mmap(evlist);
@@ -830,6 +825,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist 
*evlist, int idx,
if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
perf_evlist__toggle_bkw_mmap(evlist, 
BKW_MMAP_RUNNING);
}
+   } else {
+   prot |= PROT_WRITE;
}
 
if (evsel->system_wide && thread)
@@ -844,7 +841,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist 
*evlist, int idx,
if (*output == -1) {
*output = fd;
 
-   if (perf_mmap__mmap([idx], mp, *output)  < 0)
+   if (perf_mmap__mmap([idx], mp, prot, *output)  < 0)
return -1;
} else {
if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
@@ -1064,9 +1061,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, 
unsigned int pages,
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
-   struct mmap_params mp = {
-   .prot = PROT_READ | PROT_WRITE,
-   };
+   struct mmap_params mp;
 
if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 703ed41..40e91a0 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -219,7 +219,7 @@ void perf_mmap__munmap(struct perf_mmap *map)
auxtrace_mmap__munmap(>auxtrace_mmap);
 }
 
-int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int prot, 
int fd)
 {
/*
 * The last one will be done at perf_evlist__mmap_consume(), so that we
@@ -237,7 +237,7 @@ int perf_mmap__mmap(struct perf_mmap *map, struct 
mmap_params *mp, int fd)
refcount_set(>refcnt, 2);
map->prev = 0;
map->mask = mp->mask;
-   map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+   map->base = mmap(NULL, perf_mmap__mmap_len(map), prot,
 MAP_SHARED, fd, 0);
if (map->base == MAP_FAILED) {
pr_debug2("failed to mmap perf event ring buffer, error %d\n",
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 2c3d291..1f6fcc6 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -53,11 +53,11 @@ enum bkw_mmap_state {
 };
 
 struct mmap_params {
-   int prot, mask;
+   int mask;
struct auxtrace_mmap_params auxtrace_mp;
 };
 
-int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd);
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int prot, 
int fd);
 void perf_mmap__munmap(struct perf_mmap *map);
 
 void perf_mmap__get(struct perf_mmap *map);
-- 
2.10.1

[PATCH 5/7] perf tests: Set evlist of test__task_exit() to !overwrite

2017-11-12 Thread Wang Nan 
Changing ringbuffer to !overwrite in this task is harmless because
this test uses a very low frequency (1) and using a very simple
program (true). There should have only 3 events in the whole test.
Overwriting is impossible to happen.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/tests/task-exit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index f0881d0..4fb6609 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -96,7 +96,7 @@ int test__task_exit(struct test *test __maybe_unused, int 
subtest __maybe_unused
goto out_delete_evlist;
}
 
-   if (perf_evlist__mmap(evlist, 128, true) < 0) {
+   if (perf_evlist__mmap(evlist, 128, false) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
-- 
2.10.1

[PATCH 1/7] perf mmap: Fix perf backward recording

2017-11-12 Thread Wang Nan 
perf record backward recording doesn't work as we expected: it never
overwrite when ring buffer full.

Test:

(Run a busy printing task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot.)

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps are never change, but my background task is a dead loop, can
easily overwhelme the ring buffer.

This patch fix it by force unsetting PROT_WRITE for backward ring
buffer, so all backward ring buffer become overwrite ring buffer.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/util/evlist.c | 8 +++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e..4c5daba 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,22 +799,28 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *mp, int cpu_idx,
+  struct mmap_params *_mp, int cpu_idx,
   int thread, int *_

[PATCH 0/7] perf tools: Clarify overwrite and backward, bugfix

2017-11-12 Thread Wang Nan 
Based on previous discussion, perf needs to support only two types
of ringbuffer: read-write + forward, readonly + backward. This patchset
completly removes the concept of 'overwrite' from code level, controls
mapping permission using write_backward instead.

Wang Nan (7):
  perf mmap: Fix perf backward recording
  perf tests: Set evlist of test__backward_ring_buffer() to !overwrite
  perf tests: Set evlist of test__sw_clock_freq() to !overwrite
  perf tests: Set evlist of test__basic_mmap() to !overwrite
  perf tests: Set evlist of test__task_exit() to !overwrite
  perf tools: Remove 'overwrite' concept from code level
  perf tools: Remove prot field in mmap param

 tools/perf/arch/x86/tests/perf-time-to-tsc.c |  2 +-
 tools/perf/builtin-kvm.c |  2 +-
 tools/perf/builtin-record.c  |  4 ++--
 tools/perf/builtin-top.c |  2 +-
 tools/perf/builtin-trace.c   |  2 +-
 tools/perf/tests/backward-ring-buffer.c  |  2 +-
 tools/perf/tests/bpf.c   |  2 +-
 tools/perf/tests/code-reading.c  |  2 +-
 tools/perf/tests/keep-tracking.c |  2 +-
 tools/perf/tests/mmap-basic.c|  2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  |  2 +-
 tools/perf/tests/perf-record.c   |  2 +-
 tools/perf/tests/sw-clock.c  |  2 +-
 tools/perf/tests/switch-tracking.c   |  2 +-
 tools/perf/tests/task-exit.c |  2 +-
 tools/perf/util/evlist.c | 21 ++---
 tools/perf/util/evlist.h |  6 ++
 tools/perf/util/mmap.c   | 10 +-
 tools/perf/util/mmap.h   |  6 +++---
 tools/perf/util/python.c | 10 +-
 20 files changed, 41 insertions(+), 44 deletions(-)

-- 
2.10.1

[PATCH 5/7] perf tests: Set evlist of test__task_exit() to !overwrite

2017-11-12 Thread Wang Nan 
Changing ringbuffer to !overwrite in this task is harmless because
this test uses a very low frequency (1) and using a very simple
program (true). There should have only 3 events in the whole test.
Overwriting is impossible to happen.

Signed-off-by: Wang Nan 
---
 tools/perf/tests/task-exit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index f0881d0..4fb6609 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -96,7 +96,7 @@ int test__task_exit(struct test *test __maybe_unused, int 
subtest __maybe_unused
goto out_delete_evlist;
}
 
-   if (perf_evlist__mmap(evlist, 128, true) < 0) {
+   if (perf_evlist__mmap(evlist, 128, false) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
-- 
2.10.1

[PATCH 1/7] perf mmap: Fix perf backward recording

2017-11-12 Thread Wang Nan 
perf record backward recording doesn't work as we expected: it never
overwrite when ring buffer full.

Test:

(Run a busy printing task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot.)

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps are never change, but my background task is a dead loop, can
easily overwhelme the ring buffer.

This patch fix it by force unsetting PROT_WRITE for backward ring
buffer, so all backward ring buffer become overwrite ring buffer.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan 
---
 tools/perf/util/evlist.c | 8 +++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e..4c5daba 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,22 +799,28 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *mp, int cpu_idx,
+  struct mmap_params *_mp, int cpu_idx,
   int thread, int *_output, int 
*_output_backward

[PATCH 0/7] perf tools: Clarify overwrite and backward, bugfix

2017-11-12 Thread Wang Nan 
Based on previous discussion, perf needs to support only two types
of ringbuffer: read-write + forward, readonly + backward. This patchset
completly removes the concept of 'overwrite' from code level, controls
mapping permission using write_backward instead.

Wang Nan (7):
  perf mmap: Fix perf backward recording
  perf tests: Set evlist of test__backward_ring_buffer() to !overwrite
  perf tests: Set evlist of test__sw_clock_freq() to !overwrite
  perf tests: Set evlist of test__basic_mmap() to !overwrite
  perf tests: Set evlist of test__task_exit() to !overwrite
  perf tools: Remove 'overwrite' concept from code level
  perf tools: Remove prot field in mmap param

 tools/perf/arch/x86/tests/perf-time-to-tsc.c |  2 +-
 tools/perf/builtin-kvm.c |  2 +-
 tools/perf/builtin-record.c  |  4 ++--
 tools/perf/builtin-top.c |  2 +-
 tools/perf/builtin-trace.c   |  2 +-
 tools/perf/tests/backward-ring-buffer.c  |  2 +-
 tools/perf/tests/bpf.c   |  2 +-
 tools/perf/tests/code-reading.c  |  2 +-
 tools/perf/tests/keep-tracking.c |  2 +-
 tools/perf/tests/mmap-basic.c|  2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  |  2 +-
 tools/perf/tests/perf-record.c   |  2 +-
 tools/perf/tests/sw-clock.c  |  2 +-
 tools/perf/tests/switch-tracking.c   |  2 +-
 tools/perf/tests/task-exit.c |  2 +-
 tools/perf/util/evlist.c | 21 ++---
 tools/perf/util/evlist.h |  6 ++
 tools/perf/util/mmap.c   | 10 +-
 tools/perf/util/mmap.h   |  6 +++---
 tools/perf/util/python.c | 10 +-
 20 files changed, 41 insertions(+), 44 deletions(-)

-- 
2.10.1

[PATCH 3/7] perf tests: Set evlist of test__sw_clock_freq() to !overwrite

2017-11-12 Thread Wang Nan 
Unsetting overwrite when calling perf_evlist__mmap is harmless. This commit
passes false to it, makes following commits eliminate the overwrite argument
easier.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/tests/sw-clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index d88511f..c468e6c 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -77,7 +77,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
goto out_delete_evlist;
}
 
-   err = perf_evlist__mmap(evlist, 128, true);
+   err = perf_evlist__mmap(evlist, 128, false);
if (err < 0) {
pr_debug("failed to mmap event: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
-- 
2.10.1

[PATCH 3/7] perf tests: Set evlist of test__sw_clock_freq() to !overwrite

2017-11-12 Thread Wang Nan 
Unsetting overwrite when calling perf_evlist__mmap is harmless. This commit
passes false to it, makes following commits eliminate the overwrite argument
easier.

Signed-off-by: Wang Nan 
---
 tools/perf/tests/sw-clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index d88511f..c468e6c 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -77,7 +77,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
goto out_delete_evlist;
}
 
-   err = perf_evlist__mmap(evlist, 128, true);
+   err = perf_evlist__mmap(evlist, 128, false);
if (err < 0) {
pr_debug("failed to mmap event: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
-- 
2.10.1

[PATCH 4/7] perf tests: Set evlist of test__basic_mmap() to !overwrite

2017-11-12 Thread Wang Nan 
In this test, a large ring buffer is required so all events can feed into,
so overwrite or not is meaningless.

Change to !overwrite so following commits can remove this argument.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/tests/mmap-basic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index bc8a70e..667d696 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -93,7 +93,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int 
subtest __maybe_unuse
expected_nr_events[i] = 1 + rand() % 127;
}
 
-   if (perf_evlist__mmap(evlist, 128, true) < 0) {
+   if (perf_evlist__mmap(evlist, 128, false) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
-- 
2.10.1

[PATCH 2/7] perf tests: Set evlist of test__backward_ring_buffer() to !overwrite

2017-11-12 Thread Wang Nan 
Setting overwrite in perf_evlist__mmap() is meaningless because the
event in this evlist is already have 'overwrite' postfix and goes to
backward ring buffer automatically. Pass 'false' to perf_evlist__mmap()
to make it similar to others.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/tests/backward-ring-buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index d233ad3..992c917 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -58,7 +58,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
int err;
char sbuf[STRERR_BUFSIZE];
 
-   err = perf_evlist__mmap(evlist, mmap_pages, true);
+   err = perf_evlist__mmap(evlist, mmap_pages, false);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));
-- 
2.10.1

[PATCH 4/7] perf tests: Set evlist of test__basic_mmap() to !overwrite

2017-11-12 Thread Wang Nan 
In this test, a large ring buffer is required so all events can feed into,
so overwrite or not is meaningless.

Change to !overwrite so following commits can remove this argument.

Signed-off-by: Wang Nan 
---
 tools/perf/tests/mmap-basic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index bc8a70e..667d696 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -93,7 +93,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int 
subtest __maybe_unuse
expected_nr_events[i] = 1 + rand() % 127;
}
 
-   if (perf_evlist__mmap(evlist, 128, true) < 0) {
+   if (perf_evlist__mmap(evlist, 128, false) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
 str_error_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
-- 
2.10.1

[PATCH 2/7] perf tests: Set evlist of test__backward_ring_buffer() to !overwrite

2017-11-12 Thread Wang Nan 
Setting overwrite in perf_evlist__mmap() is meaningless because the
event in this evlist is already have 'overwrite' postfix and goes to
backward ring buffer automatically. Pass 'false' to perf_evlist__mmap()
to make it similar to others.

Signed-off-by: Wang Nan 
---
 tools/perf/tests/backward-ring-buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/backward-ring-buffer.c 
b/tools/perf/tests/backward-ring-buffer.c
index d233ad3..992c917 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -58,7 +58,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
int err;
char sbuf[STRERR_BUFSIZE];
 
-   err = perf_evlist__mmap(evlist, mmap_pages, true);
+   err = perf_evlist__mmap(evlist, mmap_pages, false);
if (err < 0) {
pr_debug("perf_evlist__mmap: %s\n",
 str_error_r(errno, sbuf, sizeof(sbuf)));
-- 
2.10.1

[PATCH 6/7] perf tools: Remove 'overwrite' concept from code level

2017-11-12 Thread Wang Nan 
Since all 'overwrite' usage are cleaned and no one really use a readonly main
ringbuffer, remove 'overwrite' from function arguments and evlist. The concept
of 'overwrite' and 'write_backward' are cleanner than before:

  1. In code level, there's no 'overwrite' concept. Each evlist has two
 ringbuffer groups. One is read-write/forward, another is readonly/backward.
 Don't support read-write/backward and readonly/forward.

  2. In user interface, we keep '--overwrite' and translate it into 
write_backward
 in each event.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c |  2 +-
 tools/perf/builtin-kvm.c |  2 +-
 tools/perf/builtin-record.c  |  4 ++--
 tools/perf/builtin-top.c |  2 +-
 tools/perf/builtin-trace.c   |  2 +-
 tools/perf/tests/backward-ring-buffer.c  |  2 +-
 tools/perf/tests/bpf.c   |  2 +-
 tools/perf/tests/code-reading.c  |  2 +-
 tools/perf/tests/keep-tracking.c |  2 +-
 tools/perf/tests/mmap-basic.c|  2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  |  2 +-
 tools/perf/tests/perf-record.c   |  2 +-
 tools/perf/tests/sw-clock.c  |  2 +-
 tools/perf/tests/switch-tracking.c   |  2 +-
 tools/perf/tests/task-exit.c |  2 +-
 tools/perf/util/evlist.c | 14 ++
 tools/perf/util/evlist.h |  6 ++
 tools/perf/util/mmap.c   |  6 +++---
 tools/perf/util/mmap.h   |  2 +-
 tools/perf/util/python.c | 10 +-
 20 files changed, 33 insertions(+), 37 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c 
b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 5dd7efb..c7ea843 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -83,7 +83,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, 
int subtest __maybe
 
CHECK__(perf_evlist__open(evlist));
 
-   CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+   CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
pc = evlist->mmap[0].base;
ret = perf_read_tsc_conversion(pc, );
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0af4c09..e3e2a80 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1043,7 +1043,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
goto out;
}
 
-   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
ui__error("Failed to mmap the events: %s\n",
  str_error_r(errno, sbuf, sizeof(sbuf)));
perf_evlist__close(evlist);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f4d9fc5..b3ef33f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -300,7 +300,7 @@ static int record__mmap_evlist(struct record *rec,
struct record_opts *opts = >opts;
char msg[512];
 
-   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 opts->auxtrace_mmap_pages,
 opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
@@ -481,7 +481,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], evlist->overwrite, 
backward, rec, record__pushfn) != 0) {
+   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 477a869..83d2ae2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -902,7 +902,7 @@ static int perf_top__start_counters(struct perf_top *top)
}
}
 
-   if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
ui__error("Failed to mmap with %d (%s)\n",
errno, str_error_r(errno, msg, sizeof(msg)));
goto out_err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c373f9a..c3f2f98 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2404,7 +2404,7 @@ static int trace__run(struct trace *trace, int argc, 
const char **argv)
if (err < 0)
goto out_error_apply_fil

[PATCH 6/7] perf tools: Remove 'overwrite' concept from code level

2017-11-12 Thread Wang Nan 
Since all 'overwrite' usage are cleaned and no one really use a readonly main
ringbuffer, remove 'overwrite' from function arguments and evlist. The concept
of 'overwrite' and 'write_backward' are cleanner than before:

  1. In code level, there's no 'overwrite' concept. Each evlist has two
 ringbuffer groups. One is read-write/forward, another is readonly/backward.
 Don't support read-write/backward and readonly/forward.

  2. In user interface, we keep '--overwrite' and translate it into 
write_backward
 in each event.

Signed-off-by: Wang Nan 
---
 tools/perf/arch/x86/tests/perf-time-to-tsc.c |  2 +-
 tools/perf/builtin-kvm.c |  2 +-
 tools/perf/builtin-record.c  |  4 ++--
 tools/perf/builtin-top.c |  2 +-
 tools/perf/builtin-trace.c   |  2 +-
 tools/perf/tests/backward-ring-buffer.c  |  2 +-
 tools/perf/tests/bpf.c   |  2 +-
 tools/perf/tests/code-reading.c  |  2 +-
 tools/perf/tests/keep-tracking.c |  2 +-
 tools/perf/tests/mmap-basic.c|  2 +-
 tools/perf/tests/openat-syscall-tp-fields.c  |  2 +-
 tools/perf/tests/perf-record.c   |  2 +-
 tools/perf/tests/sw-clock.c  |  2 +-
 tools/perf/tests/switch-tracking.c   |  2 +-
 tools/perf/tests/task-exit.c |  2 +-
 tools/perf/util/evlist.c | 14 ++
 tools/perf/util/evlist.h |  6 ++
 tools/perf/util/mmap.c   |  6 +++---
 tools/perf/util/mmap.h   |  2 +-
 tools/perf/util/python.c | 10 +-
 20 files changed, 33 insertions(+), 37 deletions(-)

diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c 
b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 5dd7efb..c7ea843 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -83,7 +83,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, 
int subtest __maybe
 
CHECK__(perf_evlist__open(evlist));
 
-   CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+   CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
pc = evlist->mmap[0].base;
ret = perf_read_tsc_conversion(pc, );
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0af4c09..e3e2a80 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1043,7 +1043,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
goto out;
}
 
-   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
ui__error("Failed to mmap the events: %s\n",
  str_error_r(errno, sbuf, sizeof(sbuf)));
perf_evlist__close(evlist);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f4d9fc5..b3ef33f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -300,7 +300,7 @@ static int record__mmap_evlist(struct record *rec,
struct record_opts *opts = >opts;
char msg[512];
 
-   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+   if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 opts->auxtrace_mmap_pages,
 opts->auxtrace_snapshot_mode) < 0) {
if (errno == EPERM) {
@@ -481,7 +481,7 @@ static int record__mmap_read_evlist(struct record *rec, 
struct perf_evlist *evli
struct auxtrace_mmap *mm = [i].auxtrace_mmap;
 
if (maps[i].base) {
-   if (perf_mmap__push([i], evlist->overwrite, 
backward, rec, record__pushfn) != 0) {
+   if (perf_mmap__push([i], backward, rec, 
record__pushfn) != 0) {
rc = -1;
goto out;
}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 477a869..83d2ae2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -902,7 +902,7 @@ static int perf_top__start_counters(struct perf_top *top)
}
}
 
-   if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+   if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
ui__error("Failed to mmap with %d (%s)\n",
errno, str_error_r(errno, msg, sizeof(msg)));
goto out_err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c373f9a..c3f2f98 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2404,7 +2404,7 @@ static int trace__run(struct trace *trace, int argc, 
const char **argv)
if (err < 0)
goto out_error_apply_filters;
 
-   err

[RESEND PATCH] mm, oom_reaper: gather each vma to prevent leaking TLB entry

2017-11-07 Thread Wang Nan 
tlb_gather_mmu(, mm, 0, -1) means gathering the whole virtual memory
space. In this case, tlb->fullmm is true. Some archs like arm64 doesn't
flush TLB when tlb->fullmm is true:

  commit 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1").

Which makes leaking of tlb entries.

Will clarifies his patch:

> Basically, we tag each address space with an ASID (PCID on x86) which
> is resident in the TLB. This means we can elide TLB invalidation when
> pulling down a full mm because we won't ever assign that ASID to another mm
> without doing TLB invalidation elsewhere (which actually just nukes the
> whole TLB).
>
> I think that means that we could potentially not fault on a kernel uaccess,
> because we could hit in the TLB.

There could be a window between complete_signal() sending IPI to other
cores and all threads sharing this mm are really kicked off from cores.
In this window, the oom reaper may calls tlb_flush_mmu_tlbonly() to flush
TLB then frees pages. However, due to the above problem, the TLB entries
are not really flushed on arm64. Other threads are possible to access
these pages through TLB entries. Moreover, a copy_to_user() can also
write to these pages without generating page fault, causes use-after-free
bugs.

This patch gathers each vma instead of gathering full vm space.
In this case tlb->fullmm is not true. The behavior of oom reaper become
similar to munmapping before do_exit, which should be safe for all archs.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Bob Liu <liub...@huawei.com>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: Michal Hocko <mho...@suse.com>
Cc: David Rientjes <rient...@google.com>
Cc: Ingo Molnar <mi...@kernel.org>
Cc: Roman Gushchin <g...@fb.com>
Cc: Konstantin Khlebnikov <khlebni...@yandex-team.ru>
Cc: Andrea Arcangeli <aarca...@redhat.com>
---
 mm/oom_kill.c | 7 ---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dee0f75..18c5b35 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -532,7 +532,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, 
struct mm_struct *mm)
 */
set_bit(MMF_UNSTABLE, >flags);
 
-   tlb_gather_mmu(, mm, 0, -1);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
@@ -547,11 +546,13 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, 
struct mm_struct *mm)
 * we do not want to block exit_mmap by keeping mm ref
 * count elevated without a good reason.
 */
-   if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED))
+   if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+   tlb_gather_mmu(, mm, vma->vm_start, vma->vm_end);
unmap_page_range(, vma, vma->vm_start, vma->vm_end,
 NULL);
+   tlb_finish_mmu(, vma->vm_start, vma->vm_end);
+   }
}
-   tlb_finish_mmu(, 0, -1);
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, 
file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
-- 
2.10.1

[RESEND PATCH] mm, oom_reaper: gather each vma to prevent leaking TLB entry

2017-11-07 Thread Wang Nan 
tlb_gather_mmu(, mm, 0, -1) means gathering the whole virtual memory
space. In this case, tlb->fullmm is true. Some archs like arm64 doesn't
flush TLB when tlb->fullmm is true:

  commit 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1").

Which makes leaking of tlb entries.

Will clarifies his patch:

> Basically, we tag each address space with an ASID (PCID on x86) which
> is resident in the TLB. This means we can elide TLB invalidation when
> pulling down a full mm because we won't ever assign that ASID to another mm
> without doing TLB invalidation elsewhere (which actually just nukes the
> whole TLB).
>
> I think that means that we could potentially not fault on a kernel uaccess,
> because we could hit in the TLB.

There could be a window between complete_signal() sending IPI to other
cores and all threads sharing this mm are really kicked off from cores.
In this window, the oom reaper may calls tlb_flush_mmu_tlbonly() to flush
TLB then frees pages. However, due to the above problem, the TLB entries
are not really flushed on arm64. Other threads are possible to access
these pages through TLB entries. Moreover, a copy_to_user() can also
write to these pages without generating page fault, causes use-after-free
bugs.

This patch gathers each vma instead of gathering full vm space.
In this case tlb->fullmm is not true. The behavior of oom reaper become
similar to munmapping before do_exit, which should be safe for all archs.

Signed-off-by: Wang Nan 
Cc: Bob Liu 
Cc: Andrew Morton 
Cc: Michal Hocko 
Cc: David Rientjes 
Cc: Ingo Molnar 
Cc: Roman Gushchin 
Cc: Konstantin Khlebnikov 
Cc: Andrea Arcangeli 
---
 mm/oom_kill.c | 7 ---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dee0f75..18c5b35 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -532,7 +532,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, 
struct mm_struct *mm)
 */
set_bit(MMF_UNSTABLE, >flags);
 
-   tlb_gather_mmu(, mm, 0, -1);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
@@ -547,11 +546,13 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, 
struct mm_struct *mm)
 * we do not want to block exit_mmap by keeping mm ref
 * count elevated without a good reason.
 */
-   if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED))
+   if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+   tlb_gather_mmu(, mm, vma->vm_start, vma->vm_end);
unmap_page_range(, vma, vma->vm_start, vma->vm_end,
 NULL);
+   tlb_finish_mmu(, vma->vm_start, vma->vm_end);
+   }
}
-   tlb_finish_mmu(, 0, -1);
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, 
file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
-- 
2.10.1

[RFC PATCH] mm, oom_reaper: gather each vma to prevent leaking TLB entry

2017-11-05 Thread Wang Nan 
tlb_gather_mmu(, mm, 0, -1) means gathering all virtual memory space.
In this case, tlb->fullmm is true. Some archs like arm64 doesn't flush
TLB when tlb->fullmm is true:

  commit 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1").

Which makes leaking of tlb entries. For example, when oom_reaper
selects a task and reaps its virtual memory space, another thread
in this task group may still running on another core and access
these already freed memory through tlb entries.

This patch gather each vma instead of gathering full vm space,
tlb->fullmm is not true. The behavior of oom reaper become similar
to munmapping before do_exit, which should be safe for all archs.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Bob Liu <liub...@huawei.com>
Cc: Michal Hocko <mho...@suse.com>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: Michal Hocko <mho...@suse.com>
Cc: David Rientjes <rient...@google.com>
Cc: Ingo Molnar <mi...@kernel.org>
Cc: Roman Gushchin <g...@fb.com>
Cc: Konstantin Khlebnikov <khlebni...@yandex-team.ru>
Cc: Andrea Arcangeli <aarca...@redhat.com>
---
 mm/oom_kill.c | 7 ---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dee0f75..18c5b35 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -532,7 +532,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, 
struct mm_struct *mm)
 */
set_bit(MMF_UNSTABLE, >flags);
 
-   tlb_gather_mmu(, mm, 0, -1);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
@@ -547,11 +546,13 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, 
struct mm_struct *mm)
 * we do not want to block exit_mmap by keeping mm ref
 * count elevated without a good reason.
 */
-   if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED))
+   if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+   tlb_gather_mmu(, mm, vma->vm_start, vma->vm_end);
unmap_page_range(, vma, vma->vm_start, vma->vm_end,
 NULL);
+   tlb_finish_mmu(, vma->vm_start, vma->vm_end);
+   }
}
-   tlb_finish_mmu(, 0, -1);
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, 
file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
-- 
2.10.1

[RFC PATCH] mm, oom_reaper: gather each vma to prevent leaking TLB entry

2017-11-05 Thread Wang Nan 
tlb_gather_mmu(, mm, 0, -1) means gathering all virtual memory space.
In this case, tlb->fullmm is true. Some archs like arm64 doesn't flush
TLB when tlb->fullmm is true:

  commit 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1").

Which makes leaking of tlb entries. For example, when oom_reaper
selects a task and reaps its virtual memory space, another thread
in this task group may still running on another core and access
these already freed memory through tlb entries.

This patch gather each vma instead of gathering full vm space,
tlb->fullmm is not true. The behavior of oom reaper become similar
to munmapping before do_exit, which should be safe for all archs.

Signed-off-by: Wang Nan 
Cc: Bob Liu 
Cc: Michal Hocko 
Cc: Andrew Morton 
Cc: Michal Hocko 
Cc: David Rientjes 
Cc: Ingo Molnar 
Cc: Roman Gushchin 
Cc: Konstantin Khlebnikov 
Cc: Andrea Arcangeli 
---
 mm/oom_kill.c | 7 ---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dee0f75..18c5b35 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -532,7 +532,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, 
struct mm_struct *mm)
 */
set_bit(MMF_UNSTABLE, >flags);
 
-   tlb_gather_mmu(, mm, 0, -1);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
@@ -547,11 +546,13 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, 
struct mm_struct *mm)
 * we do not want to block exit_mmap by keeping mm ref
 * count elevated without a good reason.
 */
-   if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED))
+   if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+   tlb_gather_mmu(, mm, vma->vm_start, vma->vm_end);
unmap_page_range(, vma, vma->vm_start, vma->vm_end,
 NULL);
+   tlb_finish_mmu(, vma->vm_start, vma->vm_end);
+   }
}
-   tlb_finish_mmu(, 0, -1);
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, 
file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
-- 
2.10.1

[PATCH 2/2] perf record: Replace 'overwrite' by 'flightrecorder' for better naming

2017-10-31 Thread Wang Nan 
The meaning of perf record's "overwrite" option and many "overwrite" in
source code are not clear. In perf's code, the 'overwrite' has 2 meanings:
 1. Make ringbuffer readonly (perf_evlist__mmap_ex's argument).
 2. Set evsel's "backward" attribute (in apply_config_terms).

perf record doesn't use meaning 1 at all, but have a overwrite option, its
real meaning is setting backward.

This patch separates these two concepts, introduce 'flightrecorder' mode
which is what we really want. It combines these 2 concept together, wraps
them into a record mode. In flight recorder mode, perf only dumps data before
something happen.

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/Documentation/perf-record.txt |  8 
 tools/perf/builtin-record.c  |  4 ++--
 tools/perf/perf.h|  2 +-
 tools/perf/util/evsel.c  |  6 +++---
 tools/perf/util/evsel.h  |  4 ++--
 tools/perf/util/parse-events.c   | 20 ++--
 tools/perf/util/parse-events.h   |  4 ++--
 tools/perf/util/parse-events.l   |  4 ++--
 8 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt 
b/tools/perf/Documentation/perf-record.txt
index 5a626ef..463c2d3 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -467,19 +467,19 @@ the beginning of record, collect them during finalizing 
an output file.
 The collected non-sample events reflects the status of the system when
 record is finished.
 
---overwrite::
+--flight-recorder::
 Makes all events use an overwritable ring buffer. An overwritable ring
 buffer works like a flight recorder: when it gets full, the kernel will
 overwrite the oldest records, that thus will never make it to the
 perf.data file.
 
-When '--overwrite' and '--switch-output' are used perf records and drops
+When '--flight-recorder' and '--switch-output' are used perf records and drops
 events until it receives a signal, meaning that something unusual was
 detected that warrants taking a snapshot of the most current events,
 those fitting in the ring buffer at that moment.
 
-'overwrite' attribute can also be set or canceled for an event using
-config terms. For example: 'cycles/overwrite/' and 
'instructions/no-overwrite/'.
+'flightrecorder' attribute can also be set or canceled separately for an event 
using
+config terms. For example: 'cycles/flightrecorder/' and 
'instructions/no-flightrecorder/'.
 
 Implies --tail-synthesize.
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f4d9fc5..315ea09 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1489,7 +1489,7 @@ static struct option __record_options[] = {
"child tasks do not inherit counters"),
OPT_BOOLEAN(0, "tail-synthesize", _synthesize,
"synthesize non-sample events at the end of output"),
-   OPT_BOOLEAN(0, "overwrite", , "use overwrite 
mode"),
+   OPT_BOOLEAN(0, "flight-recoder", _recorder, "use 
flight recoder mode"),
OPT_UINTEGER('F', "freq", _freq, "profile at this 
frequency"),
OPT_CALLBACK('m', "mmap-pages", , "pages[,pages]",
 "number of mmap data pages and AUX area tracing mmap 
pages",
@@ -1733,7 +1733,7 @@ int cmd_record(int argc, const char **argv)
}
}
 
-   if (record.opts.overwrite)
+   if (record.opts.flight_recorder)
record.opts.tail_synthesize = true;
 
if (rec->evlist->nr_entries == 0 &&
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index fbb0a9c..a7f7618 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -57,7 +57,7 @@ struct record_opts {
bool all_kernel;
bool all_user;
bool tail_synthesize;
-   bool overwrite;
+   bool flight_recorder;
bool ignore_missing_thread;
unsigned int freq;
unsigned int mmap_pages;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f894893..0e1e8e8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -772,8 +772,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
 */
attr->inherit = term->val.inherit ? 1 : 0;
break;
-   case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
-   attr->write_backward = term->val.overwrite ? 1 : 0;
+   case PERF_EVSEL__CONFIG_TERM_FLIGHTRECORDER:
+   attr->write_backward = term->val.flightrecorder ? 1 : 0;
break;
default:
break;
@@ -856,7 +856,7 @@ void perf_evs

[PATCH 0/2] perf record: Fix --overwrite and clarify concepts

2017-10-31 Thread Wang Nan 
Kan reports that 'perf record --overwrite' not working as it should be.

Patch 1/2 fix a bug, map backward events to readonly ring buffer so kernel
can overwrite that ring buffer.

Patch 2/2 clarify concepts of 'overwrite' and 'backward' in the source code
by introducing the concept of 'flightrecorder' and convert many 'overwrite'
to it to clarify that what we really want is a perf record flightrecorder
mode, not only mapping the ring buffer overwritable.

Wang Nan (2):
  perf mmap: Fix perf backward recording
  perf record: Replace 'overwrite' by 'flightrecorder' for better naming

 tools/perf/Documentation/perf-record.txt |  8 
 tools/perf/builtin-record.c  |  4 ++--
 tools/perf/perf.h|  2 +-
 tools/perf/util/evlist.c |  8 +++-
 tools/perf/util/evsel.c  |  6 +++---
 tools/perf/util/evsel.h  |  4 ++--
 tools/perf/util/parse-events.c   | 20 ++--
 tools/perf/util/parse-events.h   |  4 ++--
 tools/perf/util/parse-events.l   |  4 ++--
 9 files changed, 33 insertions(+), 27 deletions(-)

-- 
2.10.1

[PATCH 2/2] perf record: Replace 'overwrite' by 'flightrecorder' for better naming

2017-10-31 Thread Wang Nan 
The meaning of perf record's "overwrite" option and many "overwrite" in
source code are not clear. In perf's code, the 'overwrite' has 2 meanings:
 1. Make ringbuffer readonly (perf_evlist__mmap_ex's argument).
 2. Set evsel's "backward" attribute (in apply_config_terms).

perf record doesn't use meaning 1 at all, but have a overwrite option, its
real meaning is setting backward.

This patch separates these two concepts, introduce 'flightrecorder' mode
which is what we really want. It combines these 2 concept together, wraps
them into a record mode. In flight recorder mode, perf only dumps data before
something happen.

Signed-off-by: Wang Nan 
---
 tools/perf/Documentation/perf-record.txt |  8 
 tools/perf/builtin-record.c  |  4 ++--
 tools/perf/perf.h|  2 +-
 tools/perf/util/evsel.c  |  6 +++---
 tools/perf/util/evsel.h  |  4 ++--
 tools/perf/util/parse-events.c   | 20 ++--
 tools/perf/util/parse-events.h   |  4 ++--
 tools/perf/util/parse-events.l   |  4 ++--
 8 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt 
b/tools/perf/Documentation/perf-record.txt
index 5a626ef..463c2d3 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -467,19 +467,19 @@ the beginning of record, collect them during finalizing 
an output file.
 The collected non-sample events reflects the status of the system when
 record is finished.
 
---overwrite::
+--flight-recorder::
 Makes all events use an overwritable ring buffer. An overwritable ring
 buffer works like a flight recorder: when it gets full, the kernel will
 overwrite the oldest records, that thus will never make it to the
 perf.data file.
 
-When '--overwrite' and '--switch-output' are used perf records and drops
+When '--flight-recorder' and '--switch-output' are used perf records and drops
 events until it receives a signal, meaning that something unusual was
 detected that warrants taking a snapshot of the most current events,
 those fitting in the ring buffer at that moment.
 
-'overwrite' attribute can also be set or canceled for an event using
-config terms. For example: 'cycles/overwrite/' and 
'instructions/no-overwrite/'.
+'flightrecorder' attribute can also be set or canceled separately for an event 
using
+config terms. For example: 'cycles/flightrecorder/' and 
'instructions/no-flightrecorder/'.
 
 Implies --tail-synthesize.
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f4d9fc5..315ea09 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1489,7 +1489,7 @@ static struct option __record_options[] = {
"child tasks do not inherit counters"),
OPT_BOOLEAN(0, "tail-synthesize", _synthesize,
"synthesize non-sample events at the end of output"),
-   OPT_BOOLEAN(0, "overwrite", , "use overwrite 
mode"),
+   OPT_BOOLEAN(0, "flight-recoder", _recorder, "use 
flight recoder mode"),
OPT_UINTEGER('F', "freq", _freq, "profile at this 
frequency"),
OPT_CALLBACK('m', "mmap-pages", , "pages[,pages]",
 "number of mmap data pages and AUX area tracing mmap 
pages",
@@ -1733,7 +1733,7 @@ int cmd_record(int argc, const char **argv)
}
}
 
-   if (record.opts.overwrite)
+   if (record.opts.flight_recorder)
record.opts.tail_synthesize = true;
 
if (rec->evlist->nr_entries == 0 &&
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index fbb0a9c..a7f7618 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -57,7 +57,7 @@ struct record_opts {
bool all_kernel;
bool all_user;
bool tail_synthesize;
-   bool overwrite;
+   bool flight_recorder;
bool ignore_missing_thread;
unsigned int freq;
unsigned int mmap_pages;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f894893..0e1e8e8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -772,8 +772,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
 */
attr->inherit = term->val.inherit ? 1 : 0;
break;
-   case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
-   attr->write_backward = term->val.overwrite ? 1 : 0;
+   case PERF_EVSEL__CONFIG_TERM_FLIGHTRECORDER:
+   attr->write_backward = term->val.flightrecorder ? 1 : 0;
break;
default:
break;
@@ -856,7 +856,7 @@ void perf_evsel__config(struct pe

[PATCH 0/2] perf record: Fix --overwrite and clarify concepts

2017-10-31 Thread Wang Nan 
Kan reports that 'perf record --overwrite' not working as it should be.

Patch 1/2 fix a bug, map backward events to readonly ring buffer so kernel
can overwrite that ring buffer.

Patch 2/2 clarify concepts of 'overwrite' and 'backward' in the source code
by introducing the concept of 'flightrecorder' and convert many 'overwrite'
to it to clarify that what we really want is a perf record flightrecorder
mode, not only mapping the ring buffer overwritable.

Wang Nan (2):
  perf mmap: Fix perf backward recording
  perf record: Replace 'overwrite' by 'flightrecorder' for better naming

 tools/perf/Documentation/perf-record.txt |  8 
 tools/perf/builtin-record.c  |  4 ++--
 tools/perf/perf.h|  2 +-
 tools/perf/util/evlist.c |  8 +++-
 tools/perf/util/evsel.c  |  6 +++---
 tools/perf/util/evsel.h  |  4 ++--
 tools/perf/util/parse-events.c   | 20 ++--
 tools/perf/util/parse-events.h   |  4 ++--
 tools/perf/util/parse-events.l   |  4 ++--
 9 files changed, 33 insertions(+), 27 deletions(-)

-- 
2.10.1

[PATCH 1/2] perf mmap: Fix perf backward recording

2017-10-31 Thread Wang Nan 
perf record backward recording doesn't work as we expected: it never
overwrite when ring buffer full.

Test:

(Run a busy printing python task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot.)

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps are never change, but my background task is a dead loop, can
easily overwhelme the ring buffer.

This patch fix it by force unsetting PROT_WRITE for backward ring
buffer, so all backward ring buffer become overwrite ring buffer.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 tools/perf/util/evlist.c | 8 +++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e..4c5daba 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,22 +799,28 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *mp, int cpu_idx,
+  struct mmap_params *_mp, int cpu_idx,
   int threa

[PATCH 1/2] perf mmap: Fix perf backward recording

2017-10-31 Thread Wang Nan 
perf record backward recording doesn't work as we expected: it never
overwrite when ring buffer full.

Test:

(Run a busy printing python task background like this:

 while True:
 print 123

send SIGUSR2 to perf to capture snapshot.)

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101520743 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521251 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101521692 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101521936 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]

 # ./perf script -i ./perf.data.2017110101520743 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521251 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101521692 | head -n3
 perf  2717 [000] 12449.310785: raw_syscalls:sys_enter: NR 16 (5, 
2400, 0, 59, 100, 0)
 perf  2717 [000] 12449.310790: raw_syscalls:sys_enter: NR 7 
(4112340, 2, , 3df, 100, 0)
   python  2545 [000] 12449.310800:  raw_syscalls:sys_exit: NR 1 = 4

Timestamps are never change, but my background task is a dead loop, can
easily overwhelme the ring buffer.

This patch fix it by force unsetting PROT_WRITE for backward ring
buffer, so all backward ring buffer become overwrite ring buffer.

Test result:

 # ./perf record --overwrite -e raw_syscalls:sys_enter -e raw_syscalls:sys_exit 
--exclude-perf -a --switch-output
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101285323 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290053 ]
 [ perf record: dump data: Woken up 1 times ]
 [ perf record: Dump perf.data.2017110101290446 ]
 ^C[ perf record: Woken up 1 times to write data ]
 [ perf record: Dump perf.data.2017110101290837 ]
 [ perf record: Captured and wrote 0.826 MB perf.data. ]
 # ./perf script -i ./perf.data.2017110101285323 | head -n3
   python  2545 [000] 11064.268083:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11064.268084: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11064.268086:  raw_syscalls:sys_exit: NR 1 = 4
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 failed to open ./perf.data.2017110101290: No such file or directory
 # ./perf script -i ./perf.data.2017110101290053 | head -n3
   python  2545 [000] 11071.564062: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11071.564064:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11071.564066: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
 # ./perf script -i ./perf.data.2017110101290 | head -n3
 perf.data.2017110101290053  perf.data.2017110101290446  
perf.data.2017110101290837
 # ./perf script -i ./perf.data.2017110101290446 | head -n3
 sshd  1321 [000] 11075.499473:  raw_syscalls:sys_exit: NR 14 = 0
 sshd  1321 [000] 11075.499474: raw_syscalls:sys_enter: NR 14 (2, 
7ffe98899490, 0, 8, 0, 3000)
 sshd  1321 [000] 11075.499474:  raw_syscalls:sys_exit: NR 14 = 0
 # ./perf script -i ./perf.data.2017110101290837 | head -n3
   python  2545 [000] 11079.280844:  raw_syscalls:sys_exit: NR 1 = 4
   python  2545 [000] 11079.280847: raw_syscalls:sys_enter: NR 1 (1, 
12cc330, 4, 7fc237280370, 7fc2373d0700, 2c7b0)
   python  2545 [000] 11079.280850:  raw_syscalls:sys_exit: NR 1 = 4

Signed-off-by: Wang Nan 
---
 tools/perf/util/evlist.c | 8 +++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e..4c5daba 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,22 +799,28 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *mp, int cpu_idx,
+  struct mmap_params *_mp, int cpu_idx,
   int thread, int *_output, int

[PATCH] perf tool: Don't discard prev in backward mode

2017-10-12 Thread Wang Nan 
Perf record can switch output. The new output should only store the
data after switching. However, in overwrite backward mode, the new
output still have the data from old output. That also brings extra overhead.

At the end of mmap_read, the position of processed ring buffer is
saved in md->prev. Next mmap_read should be end in md->prev if it is
not overwriten. That avoids to process duplicate data.
However, the md->prev is discarded. So next mmap_read has to process
whole valid ring buffer, which probably include the old processed
data.

Avoid calling backward_rb_find_range() when md->prev is still
available.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Liang Kan <kan.li...@intel.com>
---
 tools/perf/util/mmap.c | 33 +++--
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 9fe5f9c..df1de55 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -287,18 +287,6 @@ static int backward_rb_find_range(void *buf, int mask, u64 
head, u64 *start, u64
return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-u64 *start, u64 *end, bool backward)
-{
-   if (!backward) {
-   *start = old;
-   *end = head;
-   return 0;
-   }
-
-   return backward_rb_find_range(data, mask, head, start, end);
-}
-
 int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
@@ -310,19 +298,28 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
void *buf;
int rc = 0;
 
-   if (rb_find_range(data, md->mask, head, old, , , backward))
-   return -1;
+   start = backward ? head : old;
+   end = backward ? old : head;
 
if (start == end)
return 0;
 
size = end - start;
if (size > (unsigned long)(md->mask) + 1) {
-   WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
+   if (!backward) {
+   WARN_ONCE(1, "failed to keep up with mmap data. (warn 
only once)\n");
 
-   md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
-   return 0;
+   md->prev = head;
+   perf_mmap__consume(md, overwrite || backward);
+   return 0;
+   }
+
+   /*
+* Backward ring buffer is full. We still have a chance to read
+* most of data from it.
+*/
+   if (backward_rb_find_range(data, md->mask, head, , ))
+   return -1;
}
 
if ((start & md->mask) + size != (end & md->mask)) {
-- 
2.9.3

[PATCH] perf tool: Don't discard prev in backward mode

2017-10-12 Thread Wang Nan 
Perf record can switch output. The new output should only store the
data after switching. However, in overwrite backward mode, the new
output still have the data from old output. That also brings extra overhead.

At the end of mmap_read, the position of processed ring buffer is
saved in md->prev. Next mmap_read should be end in md->prev if it is
not overwriten. That avoids to process duplicate data.
However, the md->prev is discarded. So next mmap_read has to process
whole valid ring buffer, which probably include the old processed
data.

Avoid calling backward_rb_find_range() when md->prev is still
available.

Signed-off-by: Wang Nan 
Cc: Liang Kan 
---
 tools/perf/util/mmap.c | 33 +++--
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 9fe5f9c..df1de55 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -287,18 +287,6 @@ static int backward_rb_find_range(void *buf, int mask, u64 
head, u64 *start, u64
return -1;
 }
 
-static int rb_find_range(void *data, int mask, u64 head, u64 old,
-u64 *start, u64 *end, bool backward)
-{
-   if (!backward) {
-   *start = old;
-   *end = head;
-   return 0;
-   }
-
-   return backward_rb_find_range(data, mask, head, start, end);
-}
-
 int perf_mmap__push(struct perf_mmap *md, bool overwrite, bool backward,
void *to, int push(void *to, void *buf, size_t size))
 {
@@ -310,19 +298,28 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, 
bool backward,
void *buf;
int rc = 0;
 
-   if (rb_find_range(data, md->mask, head, old, , , backward))
-   return -1;
+   start = backward ? head : old;
+   end = backward ? old : head;
 
if (start == end)
return 0;
 
size = end - start;
if (size > (unsigned long)(md->mask) + 1) {
-   WARN_ONCE(1, "failed to keep up with mmap data. (warn only 
once)\n");
+   if (!backward) {
+   WARN_ONCE(1, "failed to keep up with mmap data. (warn 
only once)\n");
 
-   md->prev = head;
-   perf_mmap__consume(md, overwrite || backward);
-   return 0;
+   md->prev = head;
+   perf_mmap__consume(md, overwrite || backward);
+   return 0;
+   }
+
+   /*
+* Backward ring buffer is full. We still have a chance to read
+* most of data from it.
+*/
+   if (backward_rb_find_range(data, md->mask, head, , ))
+   return -1;
}
 
if ((start & md->mask) + size != (end & md->mask)) {
-- 
2.9.3

[PATCH] perf tools: fix: Force backward ring buffer mapped readonly

2017-10-11 Thread Wang Nan 
perf record's --overwrite option doesn't work as we expect.
For example:

$ ~/linux/tools/perf$ sudo rm ./perf.data*
rm: cannot remove './perf.data*': No such file or directory
: ~/linux/tools/perf$ sudo ./perf record -m 4 -e raw_syscalls:* -g 
--overwrite \
--switch-output=1s --tail-synthesize   
dd if=/dev/zero of=/dev/null
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221460002 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221460102 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221460202 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221460302 ]
^C[ perf record: Woken up 1 times to write data ]
2066346+0 records in
2066346+0 records out
1057969152 bytes (1.1 GB, 1009 MiB) copied, 4.25983 s, 248 MB/s
[ perf record: Dump perf.data.2017101221460332 ]
[ perf record: Captured and wrote 0.034 MB perf.data. ]

$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221460002 | 
head -n 1
dd  3918 [006] 182589.668954:  raw_syscalls:sys_exit: NR 59 = 0
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221460102 | 
head -n 1
dd  3918 [006] 182589.668954:  raw_syscalls:sys_exit: NR 59 = 0
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221460202 | 
head -n 1
dd  3918 [006] 182589.668954:  raw_syscalls:sys_exit: NR 59 = 0
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221460302 | 
head -n 1
dd  3918 [006] 182589.668954:  raw_syscalls:sys_exit: NR 59 = 0

In the above example we get same records from the backward ring buffer
all the time. Overwriting is not triggered.

This commit maps backward ring buffers readonly, make it overwritable.
It is safe because we assume backward ring buffer always overwritable
in other part of code.

After applying this patch:

$ ~/linux/tools/perf$ sudo ./perf record -m 4 -e raw_syscalls:* -g 
--overwrite \
   --switch-output=1s --tail-synthesize   dd 
if=/dev/zero of=/dev/null
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221540350 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221540451 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221540551 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221540651 ]
^C[ perf record: Woken up 1 times to write data ]
1604606+0 records in
1604605+0 records out
821557760 bytes (822 MB, 783 MiB) copied, 4.42736 s, 186 MB/s
[ perf record: Dump perf.data.2017101221540700 ]
[ perf record: Captured and wrote 0.034 MB perf.data. ]

$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221540350 | 
head -n 1
dd  5126 [003] 183074.104581:  raw_syscalls:sys_exit: NR 0 = 512
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221540451 | 
head -n 1
dd  5126 [003] 183075.106496:  raw_syscalls:sys_exit: NR 1 = 512
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221540551 | 
head -n 1
dd  5126 [003] 183076.108093: raw_syscalls:sys_enter: NR 1 (1, af8000, 200, 
871, 0, af8060)
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221540651 | 
head -n 1
dd  5126 [003] 183077.109676:  raw_syscalls:sys_exit: NR 1 = 512


Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Liang Kan <kan.li...@intel.com>
Cc: Arnaldo Carvalho de Melo <a...@kernel.org>
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Ingo Molnar <mi...@kernel.org>
Cc: Jiri Olsa <jo...@kernel.org>
Cc: Namhyung Kim <namhy...@kernel.org>
Cc: Alexander Shishkin <alexander.shish...@linux.intel.com>
Cc: Adrian Hunter <adrian.hun...@intel.com>
Cc: Andi Kleen <a...@linux.intel.com>
Cc: Li Zefan <lize...@huawei.com>
---
 tools/perf/util/evlist.c | 7 ++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e..a86b0d2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,12 +799,14 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *mp, int cpu_idx,
+  struct mmap_params *_mp, int cpu_idx,
   int thread, int *_output, int 
*_output_backward)
 {
struct perf_evsel *evsel;
int revent;
int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx);
+   struct mmap_params *mp = _mp;
+   struct mmap_params backward_mp;
 
evlist__for_each_entry(evlist, evse

[PATCH] perf tools: fix: Force backward ring buffer mapped readonly

2017-10-11 Thread Wang Nan 
perf record's --overwrite option doesn't work as we expect.
For example:

$ ~/linux/tools/perf$ sudo rm ./perf.data*
rm: cannot remove './perf.data*': No such file or directory
: ~/linux/tools/perf$ sudo ./perf record -m 4 -e raw_syscalls:* -g 
--overwrite \
--switch-output=1s --tail-synthesize   
dd if=/dev/zero of=/dev/null
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221460002 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221460102 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221460202 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221460302 ]
^C[ perf record: Woken up 1 times to write data ]
2066346+0 records in
2066346+0 records out
1057969152 bytes (1.1 GB, 1009 MiB) copied, 4.25983 s, 248 MB/s
[ perf record: Dump perf.data.2017101221460332 ]
[ perf record: Captured and wrote 0.034 MB perf.data. ]

$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221460002 | 
head -n 1
dd  3918 [006] 182589.668954:  raw_syscalls:sys_exit: NR 59 = 0
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221460102 | 
head -n 1
dd  3918 [006] 182589.668954:  raw_syscalls:sys_exit: NR 59 = 0
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221460202 | 
head -n 1
dd  3918 [006] 182589.668954:  raw_syscalls:sys_exit: NR 59 = 0
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221460302 | 
head -n 1
dd  3918 [006] 182589.668954:  raw_syscalls:sys_exit: NR 59 = 0

In the above example we get same records from the backward ring buffer
all the time. Overwriting is not triggered.

This commit maps backward ring buffers readonly, make it overwritable.
It is safe because we assume backward ring buffer always overwritable
in other part of code.

After applying this patch:

$ ~/linux/tools/perf$ sudo ./perf record -m 4 -e raw_syscalls:* -g 
--overwrite \
   --switch-output=1s --tail-synthesize   dd 
if=/dev/zero of=/dev/null
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221540350 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221540451 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221540551 ]
[ perf record: dump data: Woken up 1 times ]
[ perf record: Dump perf.data.2017101221540651 ]
^C[ perf record: Woken up 1 times to write data ]
1604606+0 records in
1604605+0 records out
821557760 bytes (822 MB, 783 MiB) copied, 4.42736 s, 186 MB/s
[ perf record: Dump perf.data.2017101221540700 ]
[ perf record: Captured and wrote 0.034 MB perf.data. ]

$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221540350 | 
head -n 1
dd  5126 [003] 183074.104581:  raw_syscalls:sys_exit: NR 0 = 512
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221540451 | 
head -n 1
dd  5126 [003] 183075.106496:  raw_syscalls:sys_exit: NR 1 = 512
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221540551 | 
head -n 1
dd  5126 [003] 183076.108093: raw_syscalls:sys_enter: NR 1 (1, af8000, 200, 
871, 0, af8060)
$ ~/linux/tools/perf$ sudo ./perf script -i ./perf.data.2017101221540651 | 
head -n 1
dd  5126 [003] 183077.109676:  raw_syscalls:sys_exit: NR 1 = 512


Signed-off-by: Wang Nan 
Cc: Liang Kan 
Cc: Arnaldo Carvalho de Melo 
Cc: Peter Zijlstra 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Alexander Shishkin 
Cc: Adrian Hunter 
Cc: Andi Kleen 
Cc: Li Zefan 
---
 tools/perf/util/evlist.c | 7 ++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c6c891e..a86b0d2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -799,12 +799,14 @@ perf_evlist__should_poll(struct perf_evlist *evlist 
__maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-  struct mmap_params *mp, int cpu_idx,
+  struct mmap_params *_mp, int cpu_idx,
   int thread, int *_output, int 
*_output_backward)
 {
struct perf_evsel *evsel;
int revent;
int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx);
+   struct mmap_params *mp = _mp;
+   struct mmap_params backward_mp;
 
evlist__for_each_entry(evlist, evsel) {
struct perf_mmap *maps = evlist->mmap;
@@ -815,6 +817,9 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist 
*evlist, int idx,
if (evsel->attr.write_backward) {
output = _output_backward;
maps = evlist->b

[tip:perf/core] perf bpf: Fix endianness problem when loading parameters in prologue

2017-08-17 Thread tip-bot for Wang Nan 
Commit-ID:  db26984a363e8b8e35783c402978e8acdf9041a5
Gitweb: http://git.kernel.org/tip/db26984a363e8b8e35783c402978e8acdf9041a5
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Tue, 15 Aug 2017 11:21:59 +0200
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Wed, 16 Aug 2017 10:31:11 -0300

perf bpf: Fix endianness problem when loading parameters in prologue

Perf's BPF prologue generator unconditionally fetches 8 bytes for
function parameters, which causes problems on big endian machines. Thomas
gives a detailed analysis for this problem:

 
http://lkml.kernel.org/r/968ebda5-abe4-8830-8d69-49f62529d...@linux.vnet.ibm.com

  8< 
  I investigated perf test BPF for s390x and have a question regarding
  the 38.3 subtest (bpf-prologue test) which fails on s390x.

  When I turn on trace_printk in tests/bpf-script-test-prologue.c
  I see this output in /sys/kernel/debug/tracing/trace:

  [root@s8360047 perf]# cat /sys/kernel/debug/tracing/trace
  perf-30229 [000] d..2 170161.535791: : f_mode 2001d offset:0 orig:0
  perf-30229 [000] d..2 170161.535809: : f_mode 6001f offset:0 orig:0
  perf-30229 [000] d..2 170161.535815: : f_mode 6001f offset:1 orig:0
  perf-30229 [000] d..2 170161.535819: : f_mode 2001d offset:1 orig:0
  perf-30229 [000] d..2 170161.535822: : f_mode 2001d offset:2 orig:1
  perf-30229 [000] d..2 170161.535825: : f_mode 6001f offset:2 orig:1
  perf-30229 [000] d..2 170161.535828: : f_mode 6001f offset:3 orig:1
  perf-30229 [000] d..2 170161.535832: : f_mode 2001d offset:3 orig:1
  perf-30229 [000] d..2 170161.535835: : f_mode 2001d offset:4 orig:0
  perf-30229 [000] d..2 170161.535841: : f_mode 6001f offset:4 orig:0

  [...]

  There are 3 parameters the eBPF program tests/bpf-script-test-prologue.c
  accesses: f_mode (member of struct file at offset 140) offset and orig.  They
  are parameters of the lseek() system call triggered in this test case in
  function llseek_loop().

  What is really strange is the value of f_mode. It is an 8 byte value, whereas
  in the probe event it is defined as a 4 byte value.  The lower 4 bytes are all
  zero and do not belong to member f_mode.  The correct value should be 2001d 
for
  read-only and 6001f for read-write open mode.

  Here is the output of the 'perf test -vv bpf' trace:
  Try to find probe point from debuginfo.
  Matched function: null_lseek [2d9310d]
   Probe point found: null_lseek+0
  Searching 'file' variable in context.
  Converting variable file into trace event.
  converting f_mode in file
  f_mode type is unsigned int.
  Opening /sys/kernel/debug/tracing//README write=0
  Searching 'offset' variable in context.
  Converting variable offset into trace event.
  offset type is long long int.
  Searching 'orig' variable in context.
  Converting variable orig into trace event.
  orig type is int.
  Found 1 probe_trace_events.
  Opening /sys/kernel/debug/tracing//kprobe_events write=1
  Writing event: p:perf_bpf_probe/func _text+8794224 f_mode=+140(%r2):x32
  8< 

This patch parses the type of each argument and converts data from memory to
expected type.

Now the test runs successfully on 4.13.0-rc5:

  [root@s8360046 perf]# ./perf test  bpf
  38: BPF filter :
  38.1: Basic BPF filtering  : Ok
  38.2: BPF pinning  : Ok
  38.3: BPF prologue generation  : Ok
  38.4: BPF relocation checker   : Ok
  [root@s8360046 perf]#

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Hendrik Brueckner <brueck...@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20170815092159.31912-1-tmri...@linux.vnet.ibm.com
Signed-off-by: Thomas-Mich Richter <tmri...@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/tests/bpf-script-test-prologue.c |  4 ++-
 tools/perf/util/bpf-prologue.c  | 49 +++--
 2 files changed, 50 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index b4ebc75..43f1e16 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int 
fmt_size, ...) =
(void *) 6;
 
 SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
 unsigned long offset, unsigned long orig)
 {
+   fmode_t f_mode = (fmode_t)_f_mode;
+
if (err)
return 0;
if (f_mode & FMODE_WRITE)
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 1356220..827f914 100644
--- a/tools/perf/util/bpf-prol

[tip:perf/core] perf bpf: Fix endianness problem when loading parameters in prologue

2017-08-17 Thread tip-bot for Wang Nan 
Commit-ID:  db26984a363e8b8e35783c402978e8acdf9041a5
Gitweb: http://git.kernel.org/tip/db26984a363e8b8e35783c402978e8acdf9041a5
Author: Wang Nan 
AuthorDate: Tue, 15 Aug 2017 11:21:59 +0200
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Wed, 16 Aug 2017 10:31:11 -0300

perf bpf: Fix endianness problem when loading parameters in prologue

Perf's BPF prologue generator unconditionally fetches 8 bytes for
function parameters, which causes problems on big endian machines. Thomas
gives a detailed analysis for this problem:

 
http://lkml.kernel.org/r/968ebda5-abe4-8830-8d69-49f62529d...@linux.vnet.ibm.com

  8< 
  I investigated perf test BPF for s390x and have a question regarding
  the 38.3 subtest (bpf-prologue test) which fails on s390x.

  When I turn on trace_printk in tests/bpf-script-test-prologue.c
  I see this output in /sys/kernel/debug/tracing/trace:

  [root@s8360047 perf]# cat /sys/kernel/debug/tracing/trace
  perf-30229 [000] d..2 170161.535791: : f_mode 2001d offset:0 orig:0
  perf-30229 [000] d..2 170161.535809: : f_mode 6001f offset:0 orig:0
  perf-30229 [000] d..2 170161.535815: : f_mode 6001f offset:1 orig:0
  perf-30229 [000] d..2 170161.535819: : f_mode 2001d offset:1 orig:0
  perf-30229 [000] d..2 170161.535822: : f_mode 2001d offset:2 orig:1
  perf-30229 [000] d..2 170161.535825: : f_mode 6001f offset:2 orig:1
  perf-30229 [000] d..2 170161.535828: : f_mode 6001f offset:3 orig:1
  perf-30229 [000] d..2 170161.535832: : f_mode 2001d offset:3 orig:1
  perf-30229 [000] d..2 170161.535835: : f_mode 2001d offset:4 orig:0
  perf-30229 [000] d..2 170161.535841: : f_mode 6001f offset:4 orig:0

  [...]

  There are 3 parameters the eBPF program tests/bpf-script-test-prologue.c
  accesses: f_mode (member of struct file at offset 140) offset and orig.  They
  are parameters of the lseek() system call triggered in this test case in
  function llseek_loop().

  What is really strange is the value of f_mode. It is an 8 byte value, whereas
  in the probe event it is defined as a 4 byte value.  The lower 4 bytes are all
  zero and do not belong to member f_mode.  The correct value should be 2001d 
for
  read-only and 6001f for read-write open mode.

  Here is the output of the 'perf test -vv bpf' trace:
  Try to find probe point from debuginfo.
  Matched function: null_lseek [2d9310d]
   Probe point found: null_lseek+0
  Searching 'file' variable in context.
  Converting variable file into trace event.
  converting f_mode in file
  f_mode type is unsigned int.
  Opening /sys/kernel/debug/tracing//README write=0
  Searching 'offset' variable in context.
  Converting variable offset into trace event.
  offset type is long long int.
  Searching 'orig' variable in context.
  Converting variable orig into trace event.
  orig type is int.
  Found 1 probe_trace_events.
  Opening /sys/kernel/debug/tracing//kprobe_events write=1
  Writing event: p:perf_bpf_probe/func _text+8794224 f_mode=+140(%r2):x32
  8< 

This patch parses the type of each argument and converts data from memory to
expected type.

Now the test runs successfully on 4.13.0-rc5:

  [root@s8360046 perf]# ./perf test  bpf
  38: BPF filter :
  38.1: Basic BPF filtering  : Ok
  38.2: BPF pinning  : Ok
  38.3: BPF prologue generation  : Ok
  38.4: BPF relocation checker   : Ok
  [root@s8360046 perf]#

Signed-off-by: Wang Nan 
Cc: Hendrik Brueckner 
Link: http://lkml.kernel.org/r/20170815092159.31912-1-tmri...@linux.vnet.ibm.com
Signed-off-by: Thomas-Mich Richter 
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/tests/bpf-script-test-prologue.c |  4 ++-
 tools/perf/util/bpf-prologue.c  | 49 +++--
 2 files changed, 50 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index b4ebc75..43f1e16 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int 
fmt_size, ...) =
(void *) 6;
 
 SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
 unsigned long offset, unsigned long orig)
 {
+   fmode_t f_mode = (fmode_t)_f_mode;
+
if (err)
return 0;
if (f_mode & FMODE_WRITE)
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 1356220..827f914 100644
--- a/tools/perf/util/bpf-prologue.c
+++ b/tools/perf/util/bpf-prologue.c
@@ -58,6 +58,46 @@ check_pos(struct bpf_insn_pos *pos)
return 0;
 }
 
+/*
+ * Convert type string (u8/u16/u32/u64/

[PATCH] perf bpf: Fix endianness problem when loading parameters in prologue

2017-08-11 Thread Wang Nan 
Perf BPF prologue generator unconditionally fetches 8 bytes for function
parameters, which causes problem on big endian machine. Thomas gives a
detail analysis for this problem:

 
http://lkml.kernel.org/r/968ebda5-abe4-8830-8d69-49f62529d...@linux.vnet.ibm.com

This patch parses the type of each argument and converts data from
memory to expected type.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Arnaldo Carvalho de Melo <a...@kernel.org>
Cc: Thomas Richter <tmri...@linux.vnet.ibm.com>
Cc: Alexei Starovoitov <alexei.starovoi...@gmail.com>
Cc: Hendrik Brueckner <brueck...@linux.vnet.ibm.com>
Cc: Li Zefan <lize...@huawei.com>
---
 tools/perf/tests/bpf-script-test-prologue.c |  4 ++-
 tools/perf/util/bpf-prologue.c  | 49 +++--
 2 files changed, 50 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index b4ebc75..43f1e16 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int 
fmt_size, ...) =
(void *) 6;
 
 SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
 unsigned long offset, unsigned long orig)
 {
+   fmode_t f_mode = (fmode_t)_f_mode;
+
if (err)
return 0;
if (f_mode & FMODE_WRITE)
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 6cdbee1..ce28993 100644
--- a/tools/perf/util/bpf-prologue.c
+++ b/tools/perf/util/bpf-prologue.c
@@ -57,6 +57,46 @@ check_pos(struct bpf_insn_pos *pos)
return 0;
 }
 
+/*
+ * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see
+ * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM
+ * instruction (BPF_{B,H,W,DW}).
+ */
+static int
+argtype_to_ldx_size(const char *type)
+{
+   int arg_size = type ? atoi([1]) : 64;
+
+   switch (arg_size) {
+   case 8:
+   return BPF_B;
+   case 16:
+   return BPF_H;
+   case 32:
+   return BPF_W;
+   case 64:
+   default:
+   return BPF_DW;
+   }
+}
+
+static const char *
+insn_sz_to_str(int insn_sz)
+{
+   switch (insn_sz) {
+   case BPF_B:
+   return "BPF_B";
+   case BPF_H:
+   return "BPF_H";
+   case BPF_W:
+   return "BPF_W";
+   case BPF_DW:
+   return "BPF_DW";
+   default:
+   return "UNKNOWN";
+   }
+}
+
 /* Give it a shorter name */
 #define ins(i, p) append_insn((i), (p))
 
@@ -257,9 +297,14 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos,
}
 
/* Final pass: read to registers */
-   for (i = 0; i < nargs; i++)
-   ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i,
+   for (i = 0; i < nargs; i++) {
+   int insn_sz = argtype_to_ldx_size(args[i].type);
+
+   pr_debug("prologue: load arg %d, insn_sz is %s\n",
+i, insn_sz_to_str(insn_sz));
+   ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i,
BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
+   }
 
ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
 
-- 
2.10.1

[PATCH] perf bpf: Fix endianness problem when loading parameters in prologue

2017-08-11 Thread Wang Nan 
Perf BPF prologue generator unconditionally fetches 8 bytes for function
parameters, which causes problem on big endian machine. Thomas gives a
detail analysis for this problem:

 
http://lkml.kernel.org/r/968ebda5-abe4-8830-8d69-49f62529d...@linux.vnet.ibm.com

This patch parses the type of each argument and converts data from
memory to expected type.

Signed-off-by: Wang Nan 
Cc: Arnaldo Carvalho de Melo 
Cc: Thomas Richter 
Cc: Alexei Starovoitov 
Cc: Hendrik Brueckner 
Cc: Li Zefan 
---
 tools/perf/tests/bpf-script-test-prologue.c |  4 ++-
 tools/perf/util/bpf-prologue.c  | 49 +++--
 2 files changed, 50 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index b4ebc75..43f1e16 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int 
fmt_size, ...) =
(void *) 6;
 
 SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
 unsigned long offset, unsigned long orig)
 {
+   fmode_t f_mode = (fmode_t)_f_mode;
+
if (err)
return 0;
if (f_mode & FMODE_WRITE)
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 6cdbee1..ce28993 100644
--- a/tools/perf/util/bpf-prologue.c
+++ b/tools/perf/util/bpf-prologue.c
@@ -57,6 +57,46 @@ check_pos(struct bpf_insn_pos *pos)
return 0;
 }
 
+/*
+ * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see
+ * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM
+ * instruction (BPF_{B,H,W,DW}).
+ */
+static int
+argtype_to_ldx_size(const char *type)
+{
+   int arg_size = type ? atoi([1]) : 64;
+
+   switch (arg_size) {
+   case 8:
+   return BPF_B;
+   case 16:
+   return BPF_H;
+   case 32:
+   return BPF_W;
+   case 64:
+   default:
+   return BPF_DW;
+   }
+}
+
+static const char *
+insn_sz_to_str(int insn_sz)
+{
+   switch (insn_sz) {
+   case BPF_B:
+   return "BPF_B";
+   case BPF_H:
+   return "BPF_H";
+   case BPF_W:
+   return "BPF_W";
+   case BPF_DW:
+   return "BPF_DW";
+   default:
+   return "UNKNOWN";
+   }
+}
+
 /* Give it a shorter name */
 #define ins(i, p) append_insn((i), (p))
 
@@ -257,9 +297,14 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos,
}
 
/* Final pass: read to registers */
-   for (i = 0; i < nargs; i++)
-   ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i,
+   for (i = 0; i < nargs; i++) {
+   int insn_sz = argtype_to_ldx_size(args[i].type);
+
+   pr_debug("prologue: load arg %d, insn_sz is %s\n",
+i, insn_sz_to_str(insn_sz));
+   ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i,
BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
+   }
 
ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
 
-- 
2.10.1

[PATCH] perf test llvm: Fix f_mode endianness problem

2017-08-10 Thread Wang Nan 
Perf BPF prologue generator unconditionally fetches 8 bytes for function
parameters. On big endian machine, a casting is resquired if the parameter
is not u64.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Arnaldo Carvalho de Melo <a...@kernel.org>
Cc: Thomas Richter <tmri...@linux.vnet.ibm.com>
Cc: Alexei Starovoitov <alexei.starovoi...@gmail.com>
Cc: Hendrik Brueckner <brueck...@linux.vnet.ibm.com>
Cc: Li Zefan <lize...@huawei.com>
---
 tools/perf/tests/bpf-script-test-prologue.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index b4ebc75..43f1e16 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int 
fmt_size, ...) =
(void *) 6;
 
 SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
 unsigned long offset, unsigned long orig)
 {
+   fmode_t f_mode = (fmode_t)_f_mode;
+
if (err)
return 0;
if (f_mode & FMODE_WRITE)
-- 
2.10.1

[PATCH] perf test llvm: Fix f_mode endianness problem

2017-08-10 Thread Wang Nan 
Perf BPF prologue generator unconditionally fetches 8 bytes for function
parameters. On big endian machine, a casting is resquired if the parameter
is not u64.

Signed-off-by: Wang Nan 
Cc: Arnaldo Carvalho de Melo 
Cc: Thomas Richter 
Cc: Alexei Starovoitov 
Cc: Hendrik Brueckner 
Cc: Li Zefan 
---
 tools/perf/tests/bpf-script-test-prologue.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index b4ebc75..43f1e16 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int 
fmt_size, ...) =
(void *) 6;
 
 SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
 unsigned long offset, unsigned long orig)
 {
+   fmode_t f_mode = (fmode_t)_f_mode;
+
if (err)
return 0;
if (f_mode & FMODE_WRITE)
-- 
2.10.1

[tip:perf/core] perf test llvm: Avoid error when PROFILE_ALL_BRANCHES is set

2017-06-20 Thread tip-bot for Wang Nan 
Commit-ID:  9b57fb7e35957c6838f89f4ed7e3f8433a4bbfc5
Gitweb: http://git.kernel.org/tip/9b57fb7e35957c6838f89f4ed7e3f8433a4bbfc5
Author: Wang Nan <wangn...@huawei.com>
AuthorDate: Wed, 21 Jun 2017 02:32:03 +0800
Committer:  Arnaldo Carvalho de Melo <a...@redhat.com>
CommitDate: Mon, 19 Jun 2017 16:11:26 -0300

perf test llvm: Avoid error when PROFILE_ALL_BRANCHES is set

The 'if' keyword is a define that expands to complex code when
CONFIG_PROFILE_ALL_BRANCHES is selected, which causes a 'perf test LLVM'
failure like:

  $ ./perf test LLVM
  35: LLVM search and compile:
  35.1: Basic BPF llvm compile: Ok
  35.2: kbuild searching  : Ok
  35.3: Compile source for BPF prologue generation: FAILED!
  35.4: Compile source for BPF relocation : Skip

The only affected test case is bpf-script-test-prologue.c
because it uses kernel headers and has 'if' inside.

This patch undefines 'if' to make it passes perf test.

More detailed analysis from a message in this thread, also by Wang:

The problem is caused by following relocation information:

  $ readelf -a ./llvmsubtest3
  ...
 [ 5] _ftrace_branchPROGBITS   0260
  00a0    WA   0 0 4
  ...
  Relocation section '.relfunc=null_lseek file->f_mode offset orig' at
  offset 0x490 contains 4 entries:
 Offset  Info   Type   Sym. ValueSym. Name
  0038  000b0001 unrecognized: 1    
_ftrace_branch
  00b0  000b0001 unrecognized: 1    
_ftrace_branch
  0128  000b0001 unrecognized: 1    
_ftrace_branch
  01c0  000b0001 unrecognized: 1    
_ftrace_branch

  Relocation section '.rel_ftrace_branch' at offset 0x4d0 contains 8 entries:
 Offset  Info   Type   Sym. ValueSym. Name
    00020001 unrecognized: 1    
.L__func__.bpf_func__n
  0008  00010001 unrecognized: 1   0015 .L.str
  0028  00020001 unrecognized: 1    
.L__func__.bpf_func__n
  0030  00010001 unrecognized: 1   0015 .L.str
  0050  00020001 unrecognized: 1    
.L__func__.bpf_func__n
  0058  00010001 unrecognized: 1   0015 .L.str
  0078  00020001 unrecognized: 1    
.L__func__.bpf_func__n
  0080  00010001 unrecognized: 1   0015 .L.str
  ...

So I think the failure is because you enabled CONFIG_PROFILE_ALL_BRANCHES.

I can reproduce your buggy result by selecting
CONFIG_PROFILE_ALL_BRANCHES in my kbuild:

  $ ./perf test LLVM
  35: LLVM search and compile:
  35.1: Basic BPF llvm compile: Ok
  35.2: kbuild searching  : Ok
  35.3: Compile source for BPF prologue generation: FAILED!
  35.4: Compile source for BPF relocation : Skip

Simply undef CONFIG_PROFILE_ALL_BRANCHES in clang opts not working
because it is introduced by "#include ", which override
cmdline options. So I think the best way is to undefine 'if' inside BPF
script.

Reported-and-Tested-by: Thomas-Mich Richter <tmri...@linux.vnet.ibm.com>
Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Alexei Starovoitov <alexei.starovoi...@gmail.com>
Cc: Hendrik Brueckner <brueck...@linux.vnet.ibm.com>
Cc: Zefan Li <lize...@huawei.com>
Link: http://lkml.kernel.org/r/20170620183203.2517-1-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com>
---
 tools/perf/tests/bpf-script-test-prologue.c | 9 +
 1 file changed, 9 insertions(+)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index 7230e62..b4ebc75 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -10,6 +10,15 @@
 
 #include 
 
+/*
+ * If CONFIG_PROFILE_ALL_BRANCHES is selected,
+ * 'if' is redefined after include kernel header.
+ * Recover 'if' for BPF object code.
+ */
+#ifdef if
+# undef if
+#endif
+
 #define FMODE_READ 0x1
 #define FMODE_WRITE0x2

[tip:perf/core] perf test llvm: Avoid error when PROFILE_ALL_BRANCHES is set

2017-06-20 Thread tip-bot for Wang Nan 
Commit-ID:  9b57fb7e35957c6838f89f4ed7e3f8433a4bbfc5
Gitweb: http://git.kernel.org/tip/9b57fb7e35957c6838f89f4ed7e3f8433a4bbfc5
Author: Wang Nan 
AuthorDate: Wed, 21 Jun 2017 02:32:03 +0800
Committer:  Arnaldo Carvalho de Melo 
CommitDate: Mon, 19 Jun 2017 16:11:26 -0300

perf test llvm: Avoid error when PROFILE_ALL_BRANCHES is set

The 'if' keyword is a define that expands to complex code when
CONFIG_PROFILE_ALL_BRANCHES is selected, which causes a 'perf test LLVM'
failure like:

  $ ./perf test LLVM
  35: LLVM search and compile:
  35.1: Basic BPF llvm compile: Ok
  35.2: kbuild searching  : Ok
  35.3: Compile source for BPF prologue generation: FAILED!
  35.4: Compile source for BPF relocation : Skip

The only affected test case is bpf-script-test-prologue.c
because it uses kernel headers and has 'if' inside.

This patch undefines 'if' to make it passes perf test.

More detailed analysis from a message in this thread, also by Wang:

The problem is caused by following relocation information:

  $ readelf -a ./llvmsubtest3
  ...
 [ 5] _ftrace_branchPROGBITS   0260
  00a0    WA   0 0 4
  ...
  Relocation section '.relfunc=null_lseek file->f_mode offset orig' at
  offset 0x490 contains 4 entries:
 Offset  Info   Type   Sym. ValueSym. Name
  0038  000b0001 unrecognized: 1    
_ftrace_branch
  00b0  000b0001 unrecognized: 1    
_ftrace_branch
  0128  000b0001 unrecognized: 1    
_ftrace_branch
  01c0  000b0001 unrecognized: 1    
_ftrace_branch

  Relocation section '.rel_ftrace_branch' at offset 0x4d0 contains 8 entries:
 Offset  Info   Type   Sym. ValueSym. Name
    00020001 unrecognized: 1    
.L__func__.bpf_func__n
  0008  00010001 unrecognized: 1   0015 .L.str
  0028  00020001 unrecognized: 1    
.L__func__.bpf_func__n
  0030  00010001 unrecognized: 1   0015 .L.str
  0050  00020001 unrecognized: 1    
.L__func__.bpf_func__n
  0058  00010001 unrecognized: 1   0015 .L.str
  0078  00020001 unrecognized: 1    
.L__func__.bpf_func__n
  0080  00010001 unrecognized: 1   0015 .L.str
  ...

So I think the failure is because you enabled CONFIG_PROFILE_ALL_BRANCHES.

I can reproduce your buggy result by selecting
CONFIG_PROFILE_ALL_BRANCHES in my kbuild:

  $ ./perf test LLVM
  35: LLVM search and compile:
  35.1: Basic BPF llvm compile: Ok
  35.2: kbuild searching  : Ok
  35.3: Compile source for BPF prologue generation: FAILED!
  35.4: Compile source for BPF relocation : Skip

Simply undef CONFIG_PROFILE_ALL_BRANCHES in clang opts not working
because it is introduced by "#include ", which override
cmdline options. So I think the best way is to undefine 'if' inside BPF
script.

Reported-and-Tested-by: Thomas-Mich Richter 
Signed-off-by: Wang Nan 
Cc: Alexei Starovoitov 
Cc: Hendrik Brueckner 
Cc: Zefan Li 
Link: http://lkml.kernel.org/r/20170620183203.2517-1-wangn...@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo 
---
 tools/perf/tests/bpf-script-test-prologue.c | 9 +
 1 file changed, 9 insertions(+)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index 7230e62..b4ebc75 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -10,6 +10,15 @@
 
 #include 
 
+/*
+ * If CONFIG_PROFILE_ALL_BRANCHES is selected,
+ * 'if' is redefined after include kernel header.
+ * Recover 'if' for BPF object code.
+ */
+#ifdef if
+# undef if
+#endif
+
 #define FMODE_READ 0x1
 #define FMODE_WRITE0x2

[PATCH] perf test llvm: Avoid error when PROFILE_ALL_BRANCHES is set

2017-06-19 Thread Wang Nan 
'if' is defined to complex code when CONFIG_PROFILE_ALL_BRANCHES is
selected, which cause a 'perf test LLVM' failure like:

 $ ./perf test LLVM
 35: LLVM search and compile:
 35.1: Basic BPF llvm compile: Ok
 35.2: kbuild searching  : Ok
 35.3: Compile source for BPF prologue generation: FAILED!
 35.4: Compile source for BPF relocation : Skip

The only affected test case is bpf-script-test-prologue.c
because it uses kernel headers and has 'if' inside.

This patch undefines 'if' to make it passes perf test.

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: Arnaldo Carvalho de Melo <a...@redhat.com>
Cc: Thomas-Mich Richter <tmri...@linux.vnet.ibm.com>
Cc: Hendrik Brueckner <brueck...@linux.vnet.ibm.com>
Cc: Alexei Starovoitov <alexei.starovoi...@gmail.com>
Cc: Li Zefan <lize...@huawei.com>
---
 tools/perf/tests/bpf-script-test-prologue.c | 9 +
 1 file changed, 9 insertions(+)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index 7230e62..b4ebc75 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -10,6 +10,15 @@
 
 #include 
 
+/*
+ * If CONFIG_PROFILE_ALL_BRANCHES is selected,
+ * 'if' is redefined after include kernel header.
+ * Recover 'if' for BPF object code.
+ */
+#ifdef if
+# undef if
+#endif
+
 #define FMODE_READ 0x1
 #define FMODE_WRITE0x2
 
-- 
2.9.3

[PATCH] perf test llvm: Avoid error when PROFILE_ALL_BRANCHES is set

2017-06-19 Thread Wang Nan 
'if' is defined to complex code when CONFIG_PROFILE_ALL_BRANCHES is
selected, which cause a 'perf test LLVM' failure like:

 $ ./perf test LLVM
 35: LLVM search and compile:
 35.1: Basic BPF llvm compile: Ok
 35.2: kbuild searching  : Ok
 35.3: Compile source for BPF prologue generation: FAILED!
 35.4: Compile source for BPF relocation : Skip

The only affected test case is bpf-script-test-prologue.c
because it uses kernel headers and has 'if' inside.

This patch undefines 'if' to make it passes perf test.

Signed-off-by: Wang Nan 
Cc: Arnaldo Carvalho de Melo 
Cc: Thomas-Mich Richter 
Cc: Hendrik Brueckner 
Cc: Alexei Starovoitov 
Cc: Li Zefan 
---
 tools/perf/tests/bpf-script-test-prologue.c | 9 +
 1 file changed, 9 insertions(+)

diff --git a/tools/perf/tests/bpf-script-test-prologue.c 
b/tools/perf/tests/bpf-script-test-prologue.c
index 7230e62..b4ebc75 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -10,6 +10,15 @@
 
 #include 
 
+/*
+ * If CONFIG_PROFILE_ALL_BRANCHES is selected,
+ * 'if' is redefined after include kernel header.
+ * Recover 'if' for BPF object code.
+ */
+#ifdef if
+# undef if
+#endif
+
 #define FMODE_READ 0x1
 #define FMODE_WRITE0x2
 
-- 
2.9.3

[PATCH -stable 4.1 2/2] perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race

2017-02-24 Thread Wang Nan 
From: Peter Zijlstra <pet...@infradead.org>

[ Upstream commit 321027c1fe77f892f4ea07846aeae08cefbbb290 ]

Di Shen reported a race between two concurrent sys_perf_event_open()
calls where both try and move the same pre-existing software group
into a hardware context.

The problem is exactly that described in commit:

  f63a8daa5812 ("perf: Fix event->ctx locking")

... where, while we wait for a ctx->mutex acquisition, the event->ctx
relation can have changed under us.

That very same commit failed to recognise sys_perf_event_context() as an
external access vector to the events and thereby didn't apply the
established locking rules correctly.

So while one sys_perf_event_open() call is stuck waiting on
mutex_lock_double(), the other (which owns said locks) moves the group
about. So by the time the former sys_perf_event_open() acquires the
locks, the context we've acquired is stale (and possibly dead).

Apply the established locking rules as per perf_event_ctx_lock_nested()
to the mutex_lock_double() for the 'move_group' case. This obviously means
we need to validate state after we acquire the locks.

CVE-2017-6001

Reported-by: Di Shen (Keen Lab)
Tested-by: John Dias <joaod...@google.com>
Signed-off-by: Peter Zijlstra (Intel) <pet...@infradead.org>
Cc: Alexander Shishkin <alexander.shish...@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <a...@kernel.org>
Cc: Arnaldo Carvalho de Melo <a...@redhat.com>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Kees Cook <keesc...@chromium.org>
Cc: Linus Torvalds <torva...@linux-foundation.org>
Cc: Min Chong <mch...@google.com>
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Stephane Eranian <eran...@google.com>
Cc: Thomas Gleixner <t...@linutronix.de>
Cc: Vince Weaver <vincent.wea...@maine.edu>
Fixes: f63a8daa5812 ("perf: Fix event->ctx locking")
Link: 
http://lkml.kernel.org/r/20170106131444.gz3...@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mi...@kernel.org>
Signed-off-by: Wang Nan <wangn...@huawei.com>
[ - Correct code context
  - Use group_flags instead of group_caps
]
---
 kernel/events/core.c | 57 
 1 file changed, 53 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 77be116..3973df8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7900,6 +7900,37 @@ static int perf_event_set_clock(struct perf_event 
*event, clockid_t clk_id)
return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+struct perf_event_context *ctx)
+{
+   struct perf_event_context *gctx;
+
+again:
+   rcu_read_lock();
+   gctx = READ_ONCE(group_leader->ctx);
+   if (!atomic_inc_not_zero(>refcount)) {
+   rcu_read_unlock();
+   goto again;
+   }
+   rcu_read_unlock();
+
+   mutex_lock_double(>mutex, >mutex);
+
+   if (group_leader->ctx != gctx) {
+   mutex_unlock(>mutex);
+   mutex_unlock(>mutex);
+   put_ctx(gctx);
+   goto again;
+   }
+
+   return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -8123,8 +8154,26 @@ SYSCALL_DEFINE5(perf_event_open,
}
 
if (move_group) {
-   gctx = group_leader->ctx;
-   mutex_lock_double(>mutex, >mutex);
+   gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
+   /*
+* Check if we raced against another sys_perf_event_open() call
+* moving the software group underneath us.
+*/
+   if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+   /*
+* If someone moved the group out from under us, check
+* if this new event wound up on the same ctx, if so
+* its the regular !move_group case, otherwise fail.
+*/
+   if (gctx != ctx) {
+   err = -EINVAL;
+   goto err_locked;
+   } else {
+   perf_event_ctx_unlock(group_leader, gctx);
+   move_group = 0;
+   }
+   }
} else {
mutex_lock(>mutex);
}
@@ -8200,7 +8249,7 @@ SYSCALL_DEFINE5(perf_event_open,
perf_unpin_context(ctx);
 
if (move_group)
-   mutex_unlock(>mutex);
+   perf_event_ctx_unlock(group_leader, gctx);
mutex_unlock(>mutex);
 
put_online_cpus();
@@ -8229,7 +82

[PATCH -stable 4.1 2/2] perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race

2017-02-24 Thread Wang Nan 
From: Peter Zijlstra 

[ Upstream commit 321027c1fe77f892f4ea07846aeae08cefbbb290 ]

Di Shen reported a race between two concurrent sys_perf_event_open()
calls where both try and move the same pre-existing software group
into a hardware context.

The problem is exactly that described in commit:

  f63a8daa5812 ("perf: Fix event->ctx locking")

... where, while we wait for a ctx->mutex acquisition, the event->ctx
relation can have changed under us.

That very same commit failed to recognise sys_perf_event_context() as an
external access vector to the events and thereby didn't apply the
established locking rules correctly.

So while one sys_perf_event_open() call is stuck waiting on
mutex_lock_double(), the other (which owns said locks) moves the group
about. So by the time the former sys_perf_event_open() acquires the
locks, the context we've acquired is stale (and possibly dead).

Apply the established locking rules as per perf_event_ctx_lock_nested()
to the mutex_lock_double() for the 'move_group' case. This obviously means
we need to validate state after we acquire the locks.

CVE-2017-6001

Reported-by: Di Shen (Keen Lab)
Tested-by: John Dias 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Alexander Shishkin 
Cc: Arnaldo Carvalho de Melo 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: Kees Cook 
Cc: Linus Torvalds 
Cc: Min Chong 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Cc: Thomas Gleixner 
Cc: Vince Weaver 
Fixes: f63a8daa5812 ("perf: Fix event->ctx locking")
Link: 
http://lkml.kernel.org/r/20170106131444.gz3...@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar 
Signed-off-by: Wang Nan 
[ - Correct code context
  - Use group_flags instead of group_caps
]
---
 kernel/events/core.c | 57 
 1 file changed, 53 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 77be116..3973df8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7900,6 +7900,37 @@ static int perf_event_set_clock(struct perf_event 
*event, clockid_t clk_id)
return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+struct perf_event_context *ctx)
+{
+   struct perf_event_context *gctx;
+
+again:
+   rcu_read_lock();
+   gctx = READ_ONCE(group_leader->ctx);
+   if (!atomic_inc_not_zero(>refcount)) {
+   rcu_read_unlock();
+   goto again;
+   }
+   rcu_read_unlock();
+
+   mutex_lock_double(>mutex, >mutex);
+
+   if (group_leader->ctx != gctx) {
+   mutex_unlock(>mutex);
+   mutex_unlock(>mutex);
+   put_ctx(gctx);
+   goto again;
+   }
+
+   return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -8123,8 +8154,26 @@ SYSCALL_DEFINE5(perf_event_open,
}
 
if (move_group) {
-   gctx = group_leader->ctx;
-   mutex_lock_double(>mutex, >mutex);
+   gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
+   /*
+* Check if we raced against another sys_perf_event_open() call
+* moving the software group underneath us.
+*/
+   if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+   /*
+* If someone moved the group out from under us, check
+* if this new event wound up on the same ctx, if so
+* its the regular !move_group case, otherwise fail.
+*/
+   if (gctx != ctx) {
+   err = -EINVAL;
+   goto err_locked;
+   } else {
+   perf_event_ctx_unlock(group_leader, gctx);
+   move_group = 0;
+   }
+   }
} else {
mutex_lock(>mutex);
}
@@ -8200,7 +8249,7 @@ SYSCALL_DEFINE5(perf_event_open,
perf_unpin_context(ctx);
 
if (move_group)
-   mutex_unlock(>mutex);
+   perf_event_ctx_unlock(group_leader, gctx);
mutex_unlock(>mutex);
 
put_online_cpus();
@@ -8229,7 +8278,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 err_locked:
if (move_group)
-   mutex_unlock(>mutex);
+   perf_event_ctx_unlock(group_leader, gctx);
mutex_unlock(>mutex);
 /* err_file: */
fput(event_file);
-- 
2.10.1

[PATCH -stable 4.1 1/2] perf: Restructure perf syscall point of no return

2017-02-24 Thread Wang Nan 
From: Peter Zijlstra <pet...@infradead.org>

[ Upstream commit f55fc2a57cc9ca3b1bb4fb8eb25b6e1989e5b993 ]

The exclusive_event_installable() stuff only works because its
exclusive with the grouping bits.

Rework the code such that there is a sane place to error out before we
go do things we cannot undo.

CVE 2017-6001

Signed-off-by: Peter Zijlstra (Intel) <pet...@infradead.org>
Cc: Alexander Shishkin <alexander.shish...@linux.intel.com>
Cc: Linus Torvalds <torva...@linux-foundation.org>
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Thomas Gleixner <t...@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mi...@kernel.org>
Signed-off-by: Wang Nan <wangn...@huawei.com>
---
 kernel/events/core.c | 49 -
 1 file changed, 32 insertions(+), 17 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6da64f0..77be116 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8124,13 +8124,30 @@ SYSCALL_DEFINE5(perf_event_open,
 
if (move_group) {
gctx = group_leader->ctx;
+   mutex_lock_double(>mutex, >mutex);
+   } else {
+   mutex_lock(>mutex);
+   }
+
+   /*
+* Must be under the same ctx::mutex as perf_install_in_context(),
+* because we need to serialize with concurrent event creation.
+*/
+   if (!exclusive_event_installable(event, ctx)) {
+   /* exclusive and group stuff are assumed mutually exclusive */
+   WARN_ON_ONCE(move_group);
+
+   err = -EBUSY;
+   goto err_locked;
+   }
 
+   WARN_ON_ONCE(ctx->parent_ctx);
+
+   if (move_group) {
/*
 * See perf_event_ctx_lock() for comments on the details
 * of swizzling perf_event::ctx.
 */
-   mutex_lock_double(>mutex, >mutex);
-
perf_remove_from_context(group_leader, false);
 
list_for_each_entry(sibling, _leader->sibling_list,
@@ -8138,13 +8155,7 @@ SYSCALL_DEFINE5(perf_event_open,
perf_remove_from_context(sibling, false);
put_ctx(gctx);
}
-   } else {
-   mutex_lock(>mutex);
-   }
-
-   WARN_ON_ONCE(ctx->parent_ctx);
 
-   if (move_group) {
/*
 * Wait for everybody to stop referencing the events through
 * the old lists, before installing it on new lists.
@@ -8176,22 +8187,20 @@ SYSCALL_DEFINE5(perf_event_open,
perf_event__state_init(group_leader);
perf_install_in_context(ctx, group_leader, group_leader->cpu);
get_ctx(ctx);
-   }
 
-   if (!exclusive_event_installable(event, ctx)) {
-   err = -EBUSY;
-   mutex_unlock(>mutex);
-   fput(event_file);
-   goto err_context;
+   /*
+* Now that all events are installed in @ctx, nothing
+* references @gctx anymore, so drop the last reference we have
+* on it.
+*/
+   put_ctx(gctx);
}
 
perf_install_in_context(ctx, event, event->cpu);
perf_unpin_context(ctx);
 
-   if (move_group) {
+   if (move_group)
mutex_unlock(>mutex);
-   put_ctx(gctx);
-   }
mutex_unlock(>mutex);
 
put_online_cpus();
@@ -8218,6 +8227,12 @@ SYSCALL_DEFINE5(perf_event_open,
fd_install(event_fd, event_file);
return event_fd;
 
+err_locked:
+   if (move_group)
+   mutex_unlock(>mutex);
+   mutex_unlock(>mutex);
+/* err_file: */
+   fput(event_file);
 err_context:
perf_unpin_context(ctx);
put_ctx(ctx);
-- 
2.10.1

[PATCH -stable 4.1 0/2] perf/core: Fix CVE-2017-6001

2017-02-24 Thread Wang Nan 
These two patch are needed for stable 4.1. They fix CVE-2017-6001.

Peter Zijlstra (2):
  perf: Restructure perf syscall point of no return
  perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race

 kernel/events/core.c | 102 +--
 1 file changed, 83 insertions(+), 19 deletions(-)

-- 
2.10.1

  1   2   3   4   5   6   7   8   9   10   >