linux-toradex.git/kernel/trace/trace.c, branch v2.6.30.8

tracing: Fix missing function_graph events when we splice_read from trace_pipe

2009-08-16T21:18:36+00:00

commit 74e7ff8c50b6b022e6ffaa736b16a4dc161d3eaf upstream.

About a half events are missing when we splice_read
from trace_pipe. They are unexpectedly consumed because we ignore
the TRACE_TYPE_NO_CONSUME return value used by the function graph
tracer when it needs to consume the events by itself to walk on
the ring buffer.

The same problem appears with ftrace_dump()

Example of an output before this patch:

1)               |      ktime_get_real() {
1)   2.846 us    |          read_hpet();
1)   4.558 us    |        }
1)   6.195 us    |      }

After this patch:

0)               |      ktime_get_real() {
0)               |        getnstimeofday() {
0)   1.960 us    |          read_hpet();
0)   3.597 us    |        }
0)   5.196 us    |      }

The fix also applies on 2.6.30

Signed-off-by: Lai Jiangshan 
Cc: Steven Rostedt 
LKML-Reference: <4A6EEC52.90704@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker 
Signed-off-by: Greg Kroah-Hartman

tracing: Append prompt in /debug/tracing/README file

2009-05-15T17:43:22+00:00

append prompt in /debug/tracing/README file.

This is trivial issue. Fix typo Mini Howto file(README) for ftrace.

[ Impact: cleanup ]

Signed-off-by: GeunSik Lim 
Acked-by: Steven Rostedt 
Cc: williams 
LKML-Reference: <1242289418.31161.45.camel@centos51>
Signed-off-by: Ingo Molnar

tracing: fix ref count in splice pages

2009-04-29T06:02:44+00:00

The pages allocated for the splice binary buffer did not initialize
the ref count correctly. This caused pages not to be freed and causes
a drastic memory leak.

Thanks to logdev I was able to trace the tracer to find where the leak
was.

[ Impact: stop memory leak when using splice ]

Signed-off-by: Steven Rostedt 
Signed-off-by: Ingo Molnar

tracing: fix splice return too large

2009-04-10T10:44:46+00:00

I got these from strace:

 splice(0x3, 0, 0x5, 0, 0x1000, 0x1) = 12288
 splice(0x3, 0, 0x5, 0, 0x1000, 0x1) = 12288
 splice(0x3, 0, 0x5, 0, 0x1000, 0x1) = 12288
 splice(0x3, 0, 0x5, 0, 0x1000, 0x1) = 16384
 splice(0x3, 0, 0x5, 0, 0x1000, 0x1) = 8192
 splice(0x3, 0, 0x5, 0, 0x1000, 0x1) = 8192
 splice(0x3, 0, 0x5, 0, 0x1000, 0x1) = 8192

I wanted to splice_read 4096 bytes, but it returns 8192 or larger.

It is because the return value of tracing_buffers_splice_read()
does not include "zero out any left over data" bytes.

But tracing_buffers_read() includes these bytes, we make them
consistent.

Signed-off-by: Lai Jiangshan 
Cc: Frederic Weisbecker 
Cc: Steven Rostedt 
LKML-Reference: <49D46674.9030804@cn.fujitsu.com>
Signed-off-by: Ingo Molnar

tracing: update file->f_pos when splice(2) it

2009-04-10T10:44:44+00:00

Impact: Cleanup

These two lines:

	if (unlikely(*ppos))
		return -ESPIPE;

in tracing_buffers_splice_read() are not needed, VFS layer
has disabled seek(2).

We remove these two lines, and then we can update file->f_pos.

And tracing_buffers_read() updates file->f_pos, this fix
make tracing_buffers_splice_read() updates file->f_pos too.

Signed-off-by: Lai Jiangshan 
Cc: Frederic Weisbecker 
Cc: Steven Rostedt 
LKML-Reference: <49D46670.4010503@cn.fujitsu.com>
Signed-off-by: Ingo Molnar

tracing: allocate page when needed

2009-04-10T10:44:43+00:00

Impact: Cleanup

Sometimes, we open trace_pipe_raw, but we don't read(2) it,
we just splice(2) it, thus, the page is not used.

Signed-off-by: Lai Jiangshan 
Cc: Frederic Weisbecker 
Cc: Steven Rostedt 
LKML-Reference: <49D4666B.4010608@cn.fujitsu.com>
Signed-off-by: Ingo Molnar

tracing: disable seeking for trace_pipe_raw

2009-04-10T10:44:42+00:00

Impact: disable pread()

We set tracing_buffers_fops.llseek to no_llseek,
but we can still perform pread() to read this file.

That is not expected.

This fix uses nonseekable_open() to disable it.

tracing_buffers_fops.llseek is still set to no_llseek,
it mark this file is a "non-seekable device" and is used by
sys_splice(). See also do_splice() or manual of splice(2):

ERRORS
       EINVAL Target file system doesn't support  splicing;
              neither  of the descriptors refers to a pipe;
              or offset given for non-seekable device.

Signed-off-by: Lai Jiangshan 
Cc: Frederic Weisbecker 
Cc: Steven Rostedt 
LKML-Reference: <49D46668.8030806@cn.fujitsu.com>
Signed-off-by: Ingo Molnar

Update /debug/tracing/README

2009-04-07T12:02:36+00:00

Some of the tracers have been renamed, which was not updated in the in-kernel
run-time README file. Update it.

Signed-off-by: Nikanth Karthikesan 
LKML-Reference: <200903231158.32151.knikanth@suse.de>
Signed-off-by: Steven Rostedt 
Signed-off-by: Ingo Molnar

tracing/ftrace: alloc the started cpumask for the trace file

2009-04-07T12:02:03+00:00

Impact: fix a crash while cat trace file

Currently we are using a cpumask to remind each cpu where a
trace occured. It lets us notice the user that a cpu just had
its first trace.

But on latest -tip we have the following crash once we cat the trace
file:

IP: [] print_trace_fmt+0x45/0xe7
*pde = 00000000
Oops: 0000 [#1] PREEMPT SMP
last sysfs file: /sys/class/net/eth0/carrier
Pid: 3897, comm: cat Not tainted (2.6.29-tip-02825-g0f22972-dirty #81)
EIP: 0060:[] EFLAGS: 00010297 CPU: 0
EIP is at print_trace_fmt+0x45/0xe7
EAX: 00000000 EBX: 00000000 ECX: c12d9e98 EDX: ccdb7010
ESI: d31f4000 EDI: 00322401 EBP: d31f3f10 ESP: d31f3efc
DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
Process cat (pid: 3897, ti=d31f2000 task=d3b3cf20 task.ti=d31f2000)
Stack:
d31f4080 ccdb7010 d31f4000 d691fe70 ccdb7010 d31f3f24 c0270e5c d31f4000
d691fe70 d31f4000 d31f3f34 c02718e8 c12d9e98 d691fe70 d31f3f70 c02bfc33
00001000 09130000 d3b46e00 d691fe98 00000000 00000079 00000001 00000000
Call Trace:
[] ? print_trace_line+0x170/0x17c
[] ? s_show+0xa7/0xbd
[] ? seq_read+0x24a/0x327
[] ? seq_read+0x0/0x327
[] ? vfs_read+0x86/0xe1
[] ? sys_read+0x40/0x65
[] ? sysenter_do_call+0x12/0x3c
Code: 00 00 00 89 45 ec f7 c7 00 20 00 00 89 55 f0 74 4e f6 86 98 10 00 00 02 74 45 8b 86 8c 10 00 00 8b 9e a8 10 00 00 e8 52 f3 ff ff <0f> a3 03 19 c0 85 c0 75 2b 8b 86 8c 10 00 00 8b 9e a8 10 00 00
EIP: [] print_trace_fmt+0x45/0xe7 SS:ESP 0068:d31f3efc
CR2: 0000000000000000
---[ end trace aa9cf38e5ebed9dd ]---

This is because we alloc the iter->started cpumask on tracing_pipe_open but
not on tracing_open.

It hadn't been noticed until now because we need to have ring buffer overruns
to activate the starting of cpu buffer detection.

Also, we need a check to not print the messagge for the first trace on the file.

Signed-off-by: Frederic Weisbecker 
LKML-Reference: <1238619188-6109-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Steven Rostedt 
Signed-off-by: Ingo Molnar

tracing/ftrace: fix missing include string.h

2009-04-07T12:00:18+00:00

Building a kernel with tracing can raise the following warning on
tip/master:

kernel/trace/trace.c:1249: error: implicit declaration of function 'vbin_printf'

We are missing an include to string.h

Reported-by: Ingo Molnar 
Signed-off-by: Frederic Weisbecker 
LKML-Reference: <1238160130-7437-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Steven Rostedt 
Signed-off-by: Ingo Molnar