This patch implements the kernel side support for ftrace event
record sampling.
A new counter sampling attribute is added:
PERF_SAMPLE_TP_RECORD
which requests ftrace events record sampling. In this case
if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint
fires, we emit the tracepoint binary record to the
perfcounter event buffer, as a sample.
Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf
record:
perf record -f -F 1 -a -e workqueue:workqueue_execution
perf report -D
0x21e18 [0x48]: event: 9
.
. ... raw event: size 72 bytes
. 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........
. 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!......
. 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve
. 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1...........
. 0040: e0 b1 31 81 ff ff ff ff .......
.
0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33
The raw ftrace binary record starts at offset 0020.
Translation:
struct trace_entry {
type = 0x2b = 43;
flags = 1;
preempt_count = 2;
pid = 0xa = 10;
tgid = 0xa = 10;
}
thread_comm = "events/1"
thread_pid = 0xa = 10;
func = 0xffffffff8131b1e0 = flush_to_ldisc()
What will come next?
- Userspace support ('perf trace'), 'flight data recorder' mode
for perf trace, etc.
- The unconditional copy from the profiling callback brings
some costs however if someone wants no such sampling to
occur, and needs to be fixed in the future. For that we need
to have an instant access to the perf counter attribute.
This is a matter of a flag to add in the struct ftrace_event.
- Take care of the events recursivity! Don't ever try to record
a lock event for example, it seems some locking is used in
the profiling fast path and lead to a tracing recursivity.
That will be fixed using raw spinlock or recursivity
protection.
- [...]
- Profit! :-)
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Merge reason: Merge up to almost-rc6 to pick up latest perfcounters
(on which we'll queue up a dependent fix)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If filter_add_subsystem_pred() fails due to ENOSPC or ENOMEM,
the pred doesn't get freed, while as a side effect it does for
other errors. Make it so the caller always frees the pred for
any error.
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1249746593.6453.32.camel@tropicana>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Dan Carpenter sent me a fix to prevent pred from being used if
it couldn't be allocated. I noticed the same problem also
existed for the create_pred() case and added a fix for that.
Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1249746549.6453.29.camel@tropicana>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When calling rb_buffer_peek() from ring_buffer_consume() and a
padding event is returned, the function rb_advance_reader() is
called twice. This may lead to missing samples or under high
workloads to the warning below. This patch fixes this. If a padding
event is returned by rb_buffer_peek() it will be consumed by the
calling function now.
Also, I simplified some code in ring_buffer_consume().
------------[ cut here ]------------
WARNING: at /dev/shm/.source/linux/kernel/trace/ring_buffer.c:2289 rb_advance_reader+0x2e/0xc5()
Hardware name: Anaheim
Modules linked in:
Pid: 29, comm: events/2 Tainted: G W 2.6.31-rc3-oprofile-x86_64-standard-00059-g5050dc2 #1
Call Trace:
[<ffffffff8106776f>] ? rb_advance_reader+0x2e/0xc5
[<ffffffff81039ffe>] warn_slowpath_common+0x77/0x8f
[<ffffffff8103a025>] warn_slowpath_null+0xf/0x11
[<ffffffff8106776f>] rb_advance_reader+0x2e/0xc5
[<ffffffff81068bda>] ring_buffer_consume+0xa0/0xd2
[<ffffffff81326933>] op_cpu_buffer_read_entry+0x21/0x9e
[<ffffffff810be3af>] ? __find_get_block+0x4b/0x165
[<ffffffff8132749b>] sync_buffer+0xa5/0x401
[<ffffffff810be3af>] ? __find_get_block+0x4b/0x165
[<ffffffff81326c1b>] ? wq_sync_buffer+0x0/0x78
[<ffffffff81326c76>] wq_sync_buffer+0x5b/0x78
[<ffffffff8104aa30>] worker_thread+0x113/0x1ac
[<ffffffff8104dd95>] ? autoremove_wake_function+0x0/0x38
[<ffffffff8104a91d>] ? worker_thread+0x0/0x1ac
[<ffffffff8104dc9a>] kthread+0x88/0x92
[<ffffffff8100bdba>] child_rip+0xa/0x20
[<ffffffff8104dc12>] ? kthread+0x0/0x92
[<ffffffff8100bdb0>] ? child_rip+0x0/0x20
---[ end trace f561c0a58fcc89bd ]---
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: <stable@kernel.org>
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Not all tracepoints are created equal, in specific the ftrace
tracepoints are created with TRACE_EVENT_FORMAT() which does
not generate the needed bits to tie them into perf counters.
For those events, don't create the 'id' file and fail
->profile_enable when their ID is specified through other
means.
Reported-by: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1249497664.5890.4.camel@laptop>
[ v2: fix build error in the !CONFIG_EVENT_PROFILE case ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The commit:
commit e0fdace10e
Author: David Miller <davem@davemloft.net>
Date: Fri Aug 1 01:11:22 2008 -0700
debug_locks: set oops_in_progress if we will log messages.
Otherwise lock debugging messages on runqueue locks can deadlock the
system due to the wakeups performed by printk().
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Will permanently set oops_in_progress on any lockdep failure.
When this triggers it will cause any read from the ring buffer to
permanently disable the ring buffer (not to mention no locking of
printk).
This patch removes the check. It keeps the print in NMI which makes
sense. This is probably OK, since the ring buffer should not cause
something to set oops_in_progress anyway.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The function ring_buffer_discard_commit inversed the code path
of the result of try_to_discard. It should skip incrementing the
entry counter if try_to_discard succeeded. But instead, it increments
the entry conder if it succeeded to discard, and does not increment
it if it fails.
The result of this bug is that filtering will make the stat counters
incorrect.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
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 <laijs@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: stable@kernel.org
LKML-Reference: <4A6EEC52.90704@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
When print_graph_entry() computes a function call entry event, it needs
to also check the next entry to guess if it matches the return event of
the current function entry.
In order to look at this next event, it needs to consume the current
entry before going ahead in the ring buffer.
However, if the current event that gets consumed is the last one in the
ring buffer head page, the ring_buffer may reuse the page for writers.
The consumed entry will then become invalid because of possible
racy overwriting.
Me must then handle this entry by making a copy of it.
The fix also applies on 2.6.30
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: stable@kernel.org
LKML-Reference: <4A6EEAEC.3050508@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
The current code will truncate the ftrace files contents if O_APPEND
is not set and the file is opened in write mode. This is incorrect.
It should only truncate the file if O_TRUNC is set. Otherwise
if one of these files is opened by a C program with fopen "r+",
it will incorrectly truncate the file.
Reported-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Since the trace_printk may use pointers to the format fields
in the buffer, they are exported via debugfs/tracing/printk_formats.
This is used by utilities that read the ring buffer in binary format.
It helps the utilities map the address of the format in the binary
buffer to what the printf format looks like.
Unfortunately, the way the output code works, it exports the address
of the pointer to the format address, and not the format address
itself. This makes the file totally useless in trying to figure
out what format string a binary address belongs to.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Every time we cat a trace_stat file, we leak memory allocated by
seq_open().
Also fix memory leak in a failure path in tracing_stat_open().
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4A67D92B.4060704@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
ftrace_trace_onoff_callback() will return an error even if we do the
right operation, for example:
# echo _spin_*:traceon:10 > set_ftrace_filter
-bash: echo: write error: Invalid argument
# cat set_ftrace_filter
#### all functions enabled ####
_spin_trylock_bh:traceon:count=10
_spin_unlock_irq:traceon:count=10
_spin_unlock_bh:traceon:count=10
_spin_lock_irq:traceon:count=10
_spin_unlock:traceon:count=10
_spin_trylock:traceon:count=10
_spin_unlock_irqrestore:traceon:count=10
_spin_lock_irqsave:traceon:count=10
_spin_lock_bh:traceon:count=10
_spin_lock:traceon:count=10
We want to set _spin_*:traceon:10 to set_ftrace_filter, it complains
with "Invalid argument", but the operation is successful.
This is because ftrace_process_regex() returns the number of functions that
matched the pattern. If the number is not 0, this value is returned
by ftrace_regex_write() whereas we want to return the number of bytes
virtually written.
Also the file offset pointer is not updated in this case.
If the number of matched functions is lower than the number of bytes written
by the user, this results to a reprocessing of the string given by the user with
a lower size, leading to a malformed ftrace regex and then a -EINVAL returned.
So, this patch fixes it by returning 0 if no error occured.
The fix also applies on 2.6.30
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Reviewed-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: stable@kernel.org
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
The per cpu variable stat is freeded if we fail to allocate a name
on start up. This was due to stat at first being allocated in the
initial design. But since then, it has become a static per cpu variable
but the free on error was not removed.
Also added __init annotation to the function that this is in.
[ Impact: prevent possible memory corruption on low mem at boot up ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Remove smp_lock.h from files which don't need it (including some headers!)
* Add smp_lock.h to files which do need it
* Make smp_lock.h include conditional in hardirq.h
It's needed only for one kernel_locked() usage which is under CONFIG_PREEMPT
This will make hardirq.h inclusion cheaper for every PREEMPT=n config
(which includes allmodconfig/allyesconfig, BTW)
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We will lose something if trace_seq->buffer[0] is 0, because the copy length
is calculated by strlen() in seq_puts(), so using seq_write() instead of
seq_puts().
There have a example:
after reboot:
# echo kmemtrace > current_tracer
# echo 0 > options/kmem_minimalistic
# cat trace
# tracer: kmemtrace
#
#
Nothing is exported, because the first byte of trace_seq->buffer[ ]
is KMEMTRACE_USER_ALLOC.
( the value of KMEMTRACE_USER_ALLOC is zero, seeing
kmemtrace_print_alloc_user() in kernel/trace/kmemtrace.c)
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Acked-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <4A4B2351.5010300@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This made my machine completely frozen:
# echo 1 > /proc/sys/kernel/stack_tracer_enabled
# echo 2 > /proc/sys/kernel/stack_tracer_enabled
The cause is register_ftrace_function() was called twice.
Also fix ftrace_enabled sysctl, though seems nothing bad happened
as I tested it.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4A448D17.9010305@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
