perf ftrace: Fix the buffer size in __write_tracing_file
PATCH v2 1/1 perf ftrace: Fix the buffer size in __write_tracing_file
From: Changbin Du <[email protected]>
The terminal character '\0' should take into account into size of the string buffer. Without this fix, the '--graph-funcs', '--nograph-funcs' and '--trace-funcs' options didn't work as expected when the <func> doesn't exist. If usersapce writes a non-terminated string, the kernel side will always return success but actually no filter applied.
As discussed before, the kernel now support '\0' to mark the end of string:
https://lkml.org/lkml/2018/1/16/116
After this fix in userspace, the perf will report correct error state. Also let it print an error if reset_tracing_files() fails.
The problem:
$ sudo ./perf ftrace -a --graph-depth 1 --graph-funcs abcdefg 0) 0.140 us | rcu_all_qs(); 3) 0.304 us | mutex_unlock(); 0) 0.153 us | find_vma(); 3) 0.088 us | __fsnotify_parent(); 0) 6.145 us | handle_mm_fault(); 3) 0.089 us | fsnotify(); 3) 0.161 us | __sb_end_write(); 3) 0.710 us | SyS_close(); 3) 7.848 us | exit_to_usermode_loop();
On above example, I specified function filter 'abcdefg' but all functions are enabled. The expected error is hidden.
--- tools/perf/builtin-ftrace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
tools/perf/builtin-ftrace.c +4 -2
@@ -69,7 +69,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append) {char *file;int fd, ret =-1 ; -ssize_t size =strlen (val); +ssize_t size =strlen (val) +1 ;int flags =O_WRONLY ;char errbuf[512 ];
@@ -280,8 +280,10 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)signal (SIGCHLD , sig_handler);signal (SIGPIPE , sig_handler); -if (reset_tracing_files (ftrace) <0 ) +if (reset_tracing_files (ftrace) <0 ) { +pr_err ("failed to reset ftrace\n" ); goto out; + }/* reset ftrace buffer */ if (write_tracing_file ("trace" ,"0" ) <0 )
Signature · 1 line
2.7.4
Namhyung Kim
maintainerHello,
Quoted 8 lines · On Thu, Feb 08, 2018 at 04:13:20PM +0800, [email protected] wrote:
From: Changbin Du <[email protected]>
The terminal character '\0' should take into account into size of the string buffer. Without this fix, the '--graph-funcs', '--nograph-funcs' and '--trace-funcs' options didn't work as expected when the <func> doesn't exist. If usersapce writes a non-terminated string, the kernel side will always return success but actually no filter applied.
Quoted 5 lines
As discussed before, the kernel now support '\0' to mark the end of string:
https://lkml.org/lkml/2018/1/16/116After this fix in userspace, the perf will report correct error state. Also let it print an error if
reset_tracing_files()fails.
But what about old kernels? IIRC there was an error with this change.
Thanks,
Namhyung
Quoted 49 lines
The problem:
$ sudo ./perf ftrace -a --graph-depth 1 --graph-funcs abcdefg 0) 0.140 us | rcu_all_qs(); 3) 0.304 us | mutex_unlock(); 0) 0.153 us | find_vma(); 3) 0.088 us | __fsnotify_parent(); 0) 6.145 us | handle_mm_fault(); 3) 0.089 us | fsnotify(); 3) 0.161 us | __sb_end_write(); 3) 0.710 us | SyS_close(); 3) 7.848 us | exit_to_usermode_loop();On above example, I specified function filter 'abcdefg' but all functions are enabled. The expected error is hidden.
Signed-off-by Changbin Du <[email protected]>--- tools/perf/builtin-ftrace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)tools/perf/builtin-ftrace.c +4
-2@@ -69,7 +69,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append) {char *file;int fd, ret =-1 ; -ssize_t size =strlen (val); +ssize_t size =strlen (val) +1 ;int flags =O_WRONLY ;char errbuf[512 ];@@ -280,8 +280,10 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)signal (SIGCHLD , sig_handler);signal (SIGPIPE , sig_handler); -if (reset_tracing_files (ftrace) <0 ) +if (reset_tracing_files (ftrace) <0 ) { +pr_err ("failed to reset ftrace\n" ); goto out; + }/* reset ftrace buffer */ if (write_tracing_file ("trace" ,"0" ) <0 )Signature · 1 line
2.7.4
Hi,
Quoted 11 lines · Namhyung Kim
Hello,
Quoted 8 lines · On Thu, Feb 08, 2018 at 04:13:20PM +0800, [email protected] wrote:
From: Changbin Du <[email protected]>
The terminal character '\0' should take into account into size of the string buffer. Without this fix, the '--graph-funcs', '--nograph-funcs' and '--trace-funcs' options didn't work as expected when the <func> doesn't exist. If usersapce writes a non-terminated string, the kernel side will always return success but actually no filter applied.
Quoted 8 lines
Quoted 5 lines
As discussed before, the kernel now support '\0' to mark the end of string:
https://lkml.org/lkml/2018/1/16/116After this fix in userspace, the perf will report correct error state. Also let it print an error if
reset_tracing_files()fails.But what about old kernels? IIRC there was an error with this change.
Yes, you're right. I can't find a good compitable change. So what is the compatibilty policy for perf? If it must work with recent kernel, I think the only idea is leave as it was.
Quoted 53 lines
Thanks,
NamhyungQuoted 49 lines
The problem:
$ sudo ./perf ftrace -a --graph-depth 1 --graph-funcs abcdefg 0) 0.140 us | rcu_all_qs(); 3) 0.304 us | mutex_unlock(); 0) 0.153 us | find_vma(); 3) 0.088 us | __fsnotify_parent(); 0) 6.145 us | handle_mm_fault(); 3) 0.089 us | fsnotify(); 3) 0.161 us | __sb_end_write(); 3) 0.710 us | SyS_close(); 3) 7.848 us | exit_to_usermode_loop();On above example, I specified function filter 'abcdefg' but all functions are enabled. The expected error is hidden.
Signed-off-by Changbin Du <[email protected]>--- tools/perf/builtin-ftrace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)tools/perf/builtin-ftrace.c +4
-2@@ -69,7 +69,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append) {char *file;int fd, ret =-1 ; -ssize_t size =strlen (val); +ssize_t size =strlen (val) +1 ;int flags =O_WRONLY ;char errbuf[512 ];@@ -280,8 +280,10 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)signal (SIGCHLD , sig_handler);signal (SIGPIPE , sig_handler); -if (reset_tracing_files (ftrace) <0 ) +if (reset_tracing_files (ftrace) <0 ) { +pr_err ("failed to reset ftrace\n" ); goto out; + }/* reset ftrace buffer */ if (write_tracing_file ("trace" ,"0" ) <0 )Signature · 1 line
2.7.4
Signature · 2 lines
Thanks, Changbin Du
Namhyung Kim
maintainerQuoted 17 lines · Changbin
Hi,
Quoted 14 lines · Namhyung Kim
Hello,
Quoted 11 lines · On Thu, Feb 08, 2018 at 04:13:20PM +0800, [email protected] wrote:
From: Changbin Du <[email protected]>
The terminal character '\0' should take into account into size of the string buffer. Without this fix, the '--graph-funcs', '--nograph-funcs' and '--trace-funcs' options didn't work as expected when the <func> doesn't exist. If usersapce writes a non-terminated string, the kernel side will always return success but actually no filter applied.
As discussed before, the kernel now support '\0' to mark the end of string:
https://lkml.org/lkml/2018/1/16/116
Quoted 7 lines
Quoted 5 lines
Quoted 2 lines
After this fix in userspace, the perf will report correct error state. Also let it print an error if
reset_tracing_files()fails.But what about old kernels? IIRC there was an error with this change.
Yes, you're right. I can't find a good compitable change. So what is the compatibilty policy for perf? If it must work with recent kernel, I think the only idea is leave as it was.
It should support *both* of kernels. I suggest adding a space after function name. You can simply call write(fd, " ", 1) IMHO.
Thanks,
Namhyung
Quoted 55 lines
Quoted 51 lines
Quoted 51 lines
The problem:
$ sudo ./perf ftrace -a --graph-depth 1 --graph-funcs abcdefg 0) 0.140 us | rcu_all_qs(); 3) 0.304 us | mutex_unlock(); 0) 0.153 us | find_vma(); 3) 0.088 us | __fsnotify_parent(); 0) 6.145 us | handle_mm_fault(); 3) 0.089 us | fsnotify(); 3) 0.161 us | __sb_end_write(); 3) 0.710 us | SyS_close(); 3) 7.848 us | exit_to_usermode_loop();On above example, I specified function filter 'abcdefg' but all functions are enabled. The expected error is hidden.
Signed-off-by Changbin Du <[email protected]>--- tools/perf/builtin-ftrace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)tools/perf/builtin-ftrace.c +4
-2@@ -69,7 +69,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append) {char *file;int fd, ret =-1 ; -ssize_t size =strlen (val); +ssize_t size =strlen (val) +1 ;int flags =O_WRONLY ;char errbuf[512 ];@@ -280,8 +280,10 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)signal (SIGCHLD , sig_handler);signal (SIGPIPE , sig_handler); -if (reset_tracing_files (ftrace) <0 ) +if (reset_tracing_files (ftrace) <0 ) { +pr_err ("failed to reset ftrace\n" ); goto out; + }/* reset ftrace buffer */ if (write_tracing_file ("trace" ,"0" ) <0 )Signature · 1 line
2.7.4Signature · 2 lines
Thanks, Changbin Du
Quoted 21 lines · Namhyung Kim
Quoted 20 lines · Changbin
Hi,
Quoted 17 lines · Namhyung Kim
Hello,
Quoted 13 lines · On Thu, Feb 08, 2018 at 04:13:20PM +0800, [email protected] wrote:
From: Changbin Du <[email protected]>
The terminal character '\0' should take into account into size of the string buffer. Without this fix, the '--graph-funcs', '--nograph-funcs' and '--trace-funcs' options didn't work as expected when the <func> doesn't exist. If usersapce writes a non-terminated string, the kernel side will always return success but actually no filter applied.
As discussed before, the kernel now support '\0' to mark the end of string:
https://lkml.org/lkml/2018/1/16/116After this fix in userspace, the perf will report correct error state. Also let it print an error if
reset_tracing_files()fails.
Quoted 8 lines
Quoted 4 lines
Quoted 2 lines
But what about old kernels? IIRC there was an error with this change.
Yes, you're right. I can't find a good compitable change. So what is the compatibilty policy for perf? If it must work with recent kernel, I think the only idea is leave as it was.
It should support *both* of kernels. I suggest adding a space after function name. You can simply call
write(fd, " ", 1)IMHO.
hmm, I see. I will try it later mabye tommorow. Thanks!
Quoted 59 lines
Thanks,
NamhyungQuoted 55 lines
Quoted 51 lines
Quoted 51 lines
The problem:
$ sudo ./perf ftrace -a --graph-depth 1 --graph-funcs abcdefg 0) 0.140 us | rcu_all_qs(); 3) 0.304 us | mutex_unlock(); 0) 0.153 us | find_vma(); 3) 0.088 us | __fsnotify_parent(); 0) 6.145 us | handle_mm_fault(); 3) 0.089 us | fsnotify(); 3) 0.161 us | __sb_end_write(); 3) 0.710 us | SyS_close(); 3) 7.848 us | exit_to_usermode_loop();On above example, I specified function filter 'abcdefg' but all functions are enabled. The expected error is hidden.
Signed-off-by Changbin Du <[email protected]>--- tools/perf/builtin-ftrace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)tools/perf/builtin-ftrace.c +4
-2@@ -69,7 +69,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append) {char *file;int fd, ret =-1 ; -ssize_t size =strlen (val); +ssize_t size =strlen (val) +1 ;int flags =O_WRONLY ;char errbuf[512 ];@@ -280,8 +280,10 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)signal (SIGCHLD , sig_handler);signal (SIGPIPE , sig_handler); -if (reset_tracing_files (ftrace) <0 ) +if (reset_tracing_files (ftrace) <0 ) { +pr_err ("failed to reset ftrace\n" ); goto out; + }/* reset ftrace buffer */ if (write_tracing_file ("trace" ,"0" ) <0 )Signature · 1 line
2.7.4Signature · 2 lines
Thanks, Changbin Du
Signature · 2 lines
Thanks, Changbin Du