Introduce a core framework for run-time power management of I/O
devices. Add device run-time PM fields to 'struct dev_pm_info'
and device run-time PM callbacks to 'struct dev_pm_ops'. Introduce
a run-time PM workqueue and define some device run-time PM helper
functions at the core level. Document all these things.
Special thanks to Alan Stern for his help with the design and
multiple detailed reviews of the pereceding versions of this patch
and to Magnus Damm for testing feedback.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Magnus Damm <damm@igel.co.jp>
The commit 2ff05b2b (oom: move oom_adj value) moveed the oom_adj value to
the mm_struct. It was a very good first step for sanitize OOM.
However Paul Menage reported the commit makes regression to his job
scheduler. Current OOM logic can kill OOM_DISABLED process.
Why? His program has the code of similar to the following.
...
set_oom_adj(OOM_DISABLE); /* The job scheduler never killed by oom */
...
if (vfork() == 0) {
set_oom_adj(0); /* Invoked child can be killed */
execve("foo-bar-cmd");
}
....
vfork() parent and child are shared the same mm_struct. then above
set_oom_adj(0) doesn't only change oom_adj for vfork() child, it's also
change oom_adj for vfork() parent. Then, vfork() parent (job scheduler)
lost OOM immune and it was killed.
Actually, fork-setting-exec idiom is very frequently used in userland program.
We must not break this assumption.
Then, this patch revert commit 2ff05b2b and related commit.
Reverted commit list
---------------------
- commit 2ff05b2b4e (oom: move oom_adj value from task_struct to mm_struct)
- commit 4d8b9135c3 (oom: avoid unnecessary mm locking and scanning for OOM_DISABLE)
- commit 8123681022 (oom: only oom kill exiting tasks with attached memory)
- commit 933b787b57 (mm: copy over oom_adj value at fork time)
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The wake_up_process() of the new irq thread in __setup_irq() is too
early as the irqaction is not yet fully initialized especially
action->irq is not yet set. The interrupt thread might dereference the
wrong irq descriptor.
Move the wakeup after the action is installed and action->irq has been
set.
Reported-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Michael Buesch <mb@bu3sch.de>
PARISC does not build:
/home/mingo/tip/kernel/perf_counter.c: In function 'perf_counter_index':
/home/mingo/tip/kernel/perf_counter.c:2016: error: 'PERF_COUNTER_INDEX_OFFSET' undeclared (first use in this function)
/home/mingo/tip/kernel/perf_counter.c:2016: error: (Each undeclared identifier is reported only once
/home/mingo/tip/kernel/perf_counter.c:2016: error: for each function it appears in.)
As PERF_COUNTER_INDEX_OFFSET is not defined.
Now, we could define it in the architecture - but lets also provide
a core default of 0 (which happens to be what all but one
architecture uses at the moment).
Architectures that need a different index offset should set this
value in their asm/perf_counter.h files.
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Helge Deller <deller@gmx.de>
Cc: linux-parisc@vger.kernel.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In general, code in perf_counter.c that is called through an
IPI checks, for per-task counters, that the counter's task is
still the current task. This is to handle the race condition
where the cpu switches from the task we want to another task in
the interval between sending the IPI and the IPI arriving and
being handled on the target CPU.
For some reason, __perf_counter_read is missing this check, yet
there is no reason why the race condition can't occur. This
adds a check that the current task is the one we want. If it
isn't, we just return. In that case the counter->count value
should be up to date, since it will have been updated when the
counter was scheduled out, which must have happened since the
IPI was sent.
I don't have an example of an actual failure due to this race,
but it seems obvious that it could occur and we need to guard
against it.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <19076.63614.277861.368125@drongo.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently SELinux enforcement of controls on the ability to map low memory
is determined by the mmap_min_addr tunable. This patch causes SELinux to
ignore the tunable and instead use a seperate Kconfig option specific to how
much space the LSM should protect.
The tunable will now only control the need for CAP_SYS_RAWIO and SELinux
permissions will always protect the amount of low memory designated by
CONFIG_LSM_MMAP_MIN_ADDR.
This allows users who need to disable the mmap_min_addr controls (usual reason
being they run WINE as a non-root user) to do so and still have SELinux
controls preventing confined domains (like a web server) from being able to
map some area of low memory.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: James Morris <jmorris@namei.org>
free_irq() can remove an irqaction while the corresponding interrupt
is in progress, but free_irq() sets action->thread to NULL
unconditionally, which might lead to a NULL pointer dereference in
handle_IRQ_event() when the hard interrupt context tries to wake up
the handler thread.
Prevent this by moving the thread stop after synchronize_irq(). No
need to set action->thread to NULL either as action is going to be
freed anyway.
This fixes a boot crash reported against preempt-rt which uses the
mainline irq threads code to implement full irq threading.
[ tglx: removed local irqthread variable ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
perf_counter: Report the cloning task as parent on perf_counter_fork()
perf_counter: Fix an ipi-deadlock
perf: Rework/fix the whole read vs group stuff
perf_counter: Fix swcounter context invariance
perf report: Don't show unresolved DSOs and symbols when -S/-d is used
perf tools: Add a general option to enable raw sample records
perf tools: Add a per tracepoint counter attribute to get raw sample
perf_counter: Provide hw_perf_counter_setup_online() APIs
perf list: Fix large list output by using the pager
perf_counter, x86: Fix/improve apic fallback
perf record: Add missing -C option support for specifying profile cpu
perf tools: Fix dso__new handle() to handle deleted DSOs
perf tools: Fix fallback to cplus_demangle() when bfd_demangle() is not available
perf report: Show the tid too in -D
perf record: Fix .tid and .pid fill-in when synthesizing events
perf_counter, x86: Fix generic cache events on P6-mobile CPUs
perf_counter, x86: Fix lapic printk message
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
futex: Fix handling of bad requeue syscall pairing
futex: Fix compat_futex to be same as futex for REQUEUE_PI
locking, sched: Give waitqueue spinlocks their own lockdep classes
futex: Update futex_q lock_ptr on requeue proxy lock
A bug in (9f498cc: perf_counter: Full task tracing) makes
profiling multi-threaded apps it go belly up.
[ output as: (PID:TID):(PPID:PTID) ]
# ./perf report -D | grep FORK
0x4b0 [0x18]: PERF_EVENT_FORK: (3237:3237):(3236:3236)
0xa10 [0x18]: PERF_EVENT_FORK: (3237:3238):(3236:3236)
0xa70 [0x18]: PERF_EVENT_FORK: (3237:3239):(3236:3236)
0xad0 [0x18]: PERF_EVENT_FORK: (3237:3240):(3236:3236)
0xb18 [0x18]: PERF_EVENT_FORK: (3237:3241):(3236:3236)
Shows us that the test (27d028d perf report: Update for the new
FORK/EXIT events) in builtin-report.c:
/*
* A thread clone will have the same PID for both
* parent and child.
*/
if (thread == parent)
return 0;
Will clearly fail.
The problem is that perf_counter_fork() reports the actual
parent, instead of the cloning thread.
Fixing that (with the below patch), yields:
# ./perf report -D | grep FORK
0x4c8 [0x18]: PERF_EVENT_FORK: (1590:1590):(1589:1589)
0xbd8 [0x18]: PERF_EVENT_FORK: (1590:1591):(1590:1590)
0xc80 [0x18]: PERF_EVENT_FORK: (1590:1592):(1590:1590)
0x3338 [0x18]: PERF_EVENT_FORK: (1590:1593):(1590:1590)
0x66b0 [0x18]: PERF_EVENT_FORK: (1590:1594):(1590:1590)
Which both makes more sense and doesn't confuse perf report
anymore.
Reported-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: paulus@samba.org
Cc: Anton Blanchard <anton@samba.org>
Cc: Arjan van de Ven <arjan@infradead.org>
LKML-Reference: <1250172882.5241.62.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
perf_pending_counter() is called from IRQ context and will call
perf_counter_disable(), however perf_counter_disable() uses
smp_call_function_single() which doesn't fancy being used with
IRQs disabled due to IPI deadlocks.
Fix this by making it use the local __perf_counter_disable()
call and teaching the counter_sched_out() code about pending
disables as well.
This should cover the case where a counter migrates before the
pending queue gets processed.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Corey J Ashford <cjashfor@us.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
LKML-Reference: <20090813103655.244097721@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Replace PERF_SAMPLE_GROUP with PERF_SAMPLE_READ and introduce
PERF_FORMAT_GROUP to deal with group reads in a more generic
way.
This allows you to get group reads out of read() as well.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Corey J Ashford <cjashfor@us.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
LKML-Reference: <20090813103655.117411814@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
perf_swcounter_is_counting() uses a lock, which means we cannot
use swcounters from NMI or when holding that particular lock,
this is unintended.
The below removes the lock, this opens up race window, but not
worse than the swcounters already experience due to RCU
traversal of the context in perf_swcounter_ctx_event().
This also fixes the hard lockups while opening a lockdep
tracepoint counter.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Corey J Ashford <cjashfor@us.ibm.com>
LKML-Reference: <1250149915.10001.66.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Provide weak aliases for hw_perf_counter_setup_online(). This is
used by the BTS patches (for v2.6.32), but it interacts with
fixes so propagate this upstream. (it has no effect as of yet)
Also export perf_counter_output() to architecture code.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
commit fd51d251e4
Author: Stefan Raspl <raspl@linux.vnet.ibm.com>
Date: Tue May 19 09:59:08 2009 +0200
blktrace: remove debugfs entries on bad path
added in an explicit invocation of debugfs_remove for bt->dir, in
blk_remove_buf_file_callback we are also getting the directory removed. On
occasion I am seeing memory corruption that I have bisected down to
this commit. [The testing involves a (long) series of I/O benchmarks
with blktrace invoked around the actual runs.] I believe that this
committed patch is correct, but the problem actually lies in the code
in blk_remove_buf_file_callback.
With this patch I am able to consistently get complete runs whereas
previously I could not get a single run to complete.
The first part of the patch simply moves the debugfs_remove below the
relay_close: the relay_close call will remove files under bt->dir, and
so we should not remove the directory until all the files we created
have been removed. (Note: This is not sufficient to fix the problem -
the file system code has ref counts on the directoy, so our invocation
does not cause the directory to actually be removed. Nonetheless, we
should not rely upon that feature.)
Signed-off-by: Alan D. Brunelle <alan.brunelle@hp.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (27 commits)
perf_counter: Zero dead bytes from ftrace raw samples size alignment
perf_counter: Subtract the buffer size field from the event record size
perf_counter: Require CAP_SYS_ADMIN for raw tracepoint data
perf_counter: Correct PERF_SAMPLE_RAW output
perf tools: callchain: Fix bad rounding of minimum rate
perf_counter tools: Fix libbfd detection for systems with libz dependency
perf: "Longum est iter per praecepta, breve et efficax per exempla"
perf_counter: Fix a race on perf_counter_ctx
perf_counter: Fix tracepoint sampling to be part of generic sampling
perf_counter: Work around gcc warning by initializing tracepoint record unconditionally
perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode
perf tools: callchain: Fix 'perf report' display to be callchain by default
perf tools: callchain: Fix spurious 'perf report' warnings: ignore empty callchains
perf record: Fix the -A UI for empty or non-existent perf.data
perf util: Fix do_read() to fail on EOF instead of busy-looping
perf list: Fix the output to not include tracepoints without an id
perf_counter/powerpc: Fix oops on cpus without perf_counter hardware support
perf stat: Fix tool option consistency: rename -S/--scale to -c/--scale
perf report: Add debug help for the finding of symbol bugs - show the symtab origin (DSO, build-id, kernel, etc)
perf report: Fix per task mult-counter stat reporting
...
If futex_requeue(requeue_pi=1) finds a futex_q that was created by a call
other the futex_wait_requeue_pi(), the q.rt_waiter may be null. If so,
this will result in an oops from the following call graph:
futex_requeue()
rt_mutex_start_proxy_lock()
task_blocks_on_rt_mutex()
waiter->task dereference
OOPS
We currently WARN_ON() if this is detected, clearly this is inadequate.
If we detect a mispairing in futex_requeue(), bail out, seding -EINVAL to
user-space.
V2: Fix parenthesis warnings.
Signed-off-by: Darren Hart <dvhltc@us.ibm.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: John Kacur <jkacur@redhat.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Dinakar Guniguntala <dino@in.ibm.com>
Cc: John Stultz <johnstul@linux.vnet.ibm.com>
LKML-Reference: <4A7CA8C0.7010809@us.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Need to add the REQUEUE_PI checks to the compat_sys_futex API
as well to ensure 32 bit requeue's work fine on a 64 bit
system. Patch is against latest tip
Signed-off-by: Dinakar Guniguntala <dino@in.ibm.com>
Cc: Darren Hart <dvhltc@us.ibm.com>
LKML-Reference: <20090810130142.GA23619@in.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Give waitqueue spinlocks their own lockdep classes when they
are initialised from init_waitqueue_head(). This means that
struct wait_queue::func functions can operate other waitqueues.
This is used by CacheFiles to catch the page from a backing fs
being unlocked and to wake up another thread to take a copy of
it.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Takashi Iwai <tiwai@suse.de>
Cc: linux-cachefs@redhat.com
Cc: torvalds@osdl.org
Cc: akpm@linux-foundation.org
LKML-Reference: <20090810113305.17284.81508.stgit@warthog.procyon.org.uk>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Raw tracepoint data contains various kernel internals and
data from other users, so restrict this to CAP_SYS_ADMIN.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1249896452.17467.75.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
PERF_SAMPLE_* output switches should unconditionally output the
correct format, as they are the only way to unambiguously parse
the PERF_EVENT_SAMPLE data.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1249896447.17467.74.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
futex_requeue() can acquire the lock on behalf of a waiter
early on or during the requeue loop if it is uncontended or in
the event of a lock steal or owner died. On wakeup, the waiter
(in futex_wait_requeue_pi()) cleans up the pi_state owner using
the lock_ptr to protect against concurrent access to the
pi_state. The pi_state is hung off futex_q's on the requeue
target futex hash bucket so the lock_ptr needs to be updated
accordingly.
The problem manifested by triggering the WARN_ON in
lookup_pi_state() about the pid != pi_state->owner->pid. With
this patch, the pi_state is properly guarded against concurrent
access via the requeue target hb lock.
The astute reviewer may notice that there is a window of time
between when futex_requeue() unlocks the hb locks and when
futex_wait_requeue_pi() will acquire hb2->lock. During this
time the pi_state and uval are not in sync with the underlying
rtmutex owner (but the uval does indicate there are waiters, so
no atomic changes will occur in userspace). However, this is
not a problem. Should a contending thread enter
lookup_pi_state() and acquire hb2->lock before the ownership is
fixed up, it will find the pi_state hung off a waiter's
(possibly the pending owner's) futex_q and block on the
rtmutex. Once futex_wait_requeue_pi() fixes up the owner, it
will also move the pi_state from the old owner's
task->pi_state_list to its own.
v3: Fix plist lock name for application to mainline (rather
than -rt) Compile tested against tip/v2.6.31-rc5.
Signed-off-by: Darren Hart <dvhltc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Dinakar Guniguntala <dino@in.ibm.com>
Cc: John Stultz <johnstul@linux.vnet.ibm.com>
LKML-Reference: <4A7F4EFF.6090903@us.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
posix_cpu_timers_exit_group(): Do not use thread_group_cputimer()
* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
perf_counter: Fix/complete ftrace event records sampling
perf_counter, ftrace: Fix perf_counter integration
tracing/filters: Always free pred on filter_add_subsystem_pred() failure
tracing/filters: Don't use pred on alloc failure
ring-buffer: Fix memleak in ring_buffer_free()
tracing: Fix recordmcount.pl to handle sections with only weak functions
ring-buffer: Fix advance of reader in rb_buffer_peek()
tracing: do not use functions starting with .L in recordmcount.pl
ring-buffer: do not disable ring buffer on oops_in_progress
ring-buffer: fix check of try_to_discard result
* 'core-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
lockdep: Fix typos in documentation
lockdep: Fix file mode of lock_stat
rtmutex: Avoid deadlock in rt_mutex_start_proxy_lock()
While extending perfcounters with BTS hw-tracing, Markus
Metzger managed to trigger this warning:
[ 995.557128] WARNING: at kernel/perf_counter.c:1191 __perf_counter_task_sched_out+0x48/0x6b()
triggers because commit
9f498cc5be (perf_counter: Full
task tracing) removed clearing of tsk->perf_counter_ctxp out
from under ctx->lock which introduced a race (against
perf_lock_task_context).
Move it back and deal with the exit notification by explicitly
passing along the former task context.
Reported-by: Markus T Metzger <markus.t.metzger@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1249667341.17467.5.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Based on Peter's comments, make tracepoint sampling generic
just like all the other sampling bits are. This is a rename
with no code changes:
- PERF_SAMPLE_TP_RECORD to PERF_SAMPLE_RAW
- struct perf_tracepoint_record to perf_raw_record
We want the system in place that transport tracepoints raw
samples events into the perf ring buffer to be generalized and
usable by any type of counter.
Reported-by; Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1249698400-5441-4-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Despite that the tracepoint record is always present when the
PERF_SAMPLE_TP_RECORD flag is set, gcc raises a warning,
thinking it might not be initialized:
kernel/perf_counter.c: In function ‘perf_counter_output’:
kernel/perf_counter.c:2650: warning: ‘tp’ may be used uninitialized in this function
Then, initialize it to NULL and always check if it's not NULL
before dereference it.
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1249698400-5441-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reimplement the software counters to deal with fast moving
event sources (such as tracepoints). This means being able
to generate multiple overflows from a single 'event' as well
as support throttling.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
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>
Adds possible second part to the assign argument of TP_EVENT().
TP_perf_assign(
__perf_count(foo);
__perf_addr(bar);
)
Which, when specified make the swcounter increment with @foo instead
of the usual 1, and report @bar for PERF_SAMPLE_ADDR (data address
associated with the event) when this triggers a counter overflow.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
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>
When the process exits we don't have to run new cputimer nor
use running one (as it not accounts when tsk->exit_state != 0)
to get process CPU times. As there is only one thread we can
just use CPU times fields from task and signal structs.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Roland McGrath <roland@redhat.com>
Cc: Vitaly Mayatskikh <vmayatsk@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
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>
Don't move it if target node is -1.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4A785B5D.4070702@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
perf_counter: Fix double list iteration in per task precise stats
perf: Auto-detect libelf
perf symbol: Fix symbol parsing in certain cases: use the build-id as a symlink
perf_counter/powerpc: Check oprofile_cpu_type for NULL before using it
ftrace: Fix perf-tracepoint OOPS
perf report: Add missing command line options to man page
perf: Auto-detect libbfd
perf report: Make --sort comm,dso,symbol the default
While looking at Jens Rosenboom bug report
(http://lkml.org/lkml/2009/7/27/35) about strange sys_futex call done from
a dying "ps" program, we found following problem.
clone() syscall has special support for TID of created threads. This
support includes two features.
One (CLONE_CHILD_SETTID) is to set an integer into user memory with the
TID value.
One (CLONE_CHILD_CLEARTID) is to clear this same integer once the created
thread dies.
The integer location is a user provided pointer, provided at clone()
time.
kernel keeps this pointer value into current->clear_child_tid.
At execve() time, we should make sure kernel doesnt keep this user
provided pointer, as full user memory is replaced by a new one.
As glibc fork() actually uses clone() syscall with CLONE_CHILD_SETTID and
CLONE_CHILD_CLEARTID set, chances are high that we might corrupt user
memory in forked processes.
Following sequence could happen:
1) bash (or any program) starts a new process, by a fork() call that
glibc maps to a clone( ... CLONE_CHILD_SETTID | CLONE_CHILD_CLEARTID
...) syscall
2) When new process starts, its current->clear_child_tid is set to a
location that has a meaning only in bash (or initial program) context
(&THREAD_SELF->tid)
3) This new process does the execve() syscall to start a new program.
current->clear_child_tid is left unchanged (a non NULL value)
4) If this new program creates some threads, and initial thread exits,
kernel will attempt to clear the integer pointed by
current->clear_child_tid from mm_release() :
if (tsk->clear_child_tid
&& !(tsk->flags & PF_SIGNALED)
&& atomic_read(&mm->mm_users) > 1) {
u32 __user * tidptr = tsk->clear_child_tid;
tsk->clear_child_tid = NULL;
/*
* We don't check the error code - if userspace has
* not set up a proper pointer then tough luck.
*/
<< here >> put_user(0, tidptr);
sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0);
}
5) OR : if new program is not multi-threaded, but spied by /proc/pid
users (ps command for example), mm_users > 1, and the exiting program
could corrupt 4 bytes in a persistent memory area (shm or memory mapped
file)
If current->clear_child_tid points to a writeable portion of memory of the
new program, kernel happily and silently corrupts 4 bytes of memory, with
unexpected effects.
Fix is straightforward and should not break any sane program.
Reported-by: Jens Rosenboom <jens@mcbone.net>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sonny Rao <sonnyrao@us.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use CONFIG_HOTPLUG_CPU, not CONFIG_CPU_HOTPLUG
When hot-unpluging a cpu, it will leak memory allocated at cpu hotplug,
but only if CPUMASK_OFFSTACK=y, which is default to n.
The bug was introduced by 8969a5ede0
("generic-ipi: remove kmalloc()").
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I noticed oprofile memleaked in linux-2.6 current tree,
and tracked this ring-buffer leak.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
LKML-Reference: <4A7C06B9.2090302@gmail.com>
Cc: stable@kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Brice Goglin reported this crash with per task precise stats:
> I finally managed to test the threaded perfcounter statistics (thanks a
> lot for implementing it). I am running 2.6.31-rc5 (with the AMD
> magny-cours patches but I don't think they matter here). I am trying to
> measure local/remote memory accesses per thread during the well-known
> stream benchmark. It's compiled with OpenMP using 16 threads on a
> quad-socket quad-core barcelona machine.
>
> Command line is:
> /mnt/scratch/bgoglin/cpunode/linux-2.6.31/tools/perf/perf record -f -s
> -e r1000001e0 -e r1000002e0 -e r1000004e0 -e r1000008e0 ./stream
>
> It seems to work fine with a single -e <counter> on the command line
> while it crashes when there are at least 2 of them.
> It seems to work fine without -s as well.
A silly copy-paste resulted in a messed up iteration which would
cause the OOPS.
Reported-by: Brice Goglin <Brice.Goglin@inria.fr>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Brice Goglin <Brice.Goglin@inria.fr>
LKML-Reference: <1249574786.32113.550.camel@twins>
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>
In the event of a lock steal or owner died,
rt_mutex_start_proxy_lock() will give the rt_mutex to the
waiting task, but it fails to release the wait_lock. This leads
to subsequent deadlocks when other tasks try to acquire the
rt_mutex.
I also removed a few extra blank lines that really spaced this
routine out. I must have been high on the \n when I wrote this
originally...
Signed-off-by: Darren Hart <dvhltc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Dinakar Guniguntala <dino@in.ibm.com>
Cc: John Stultz <johnstul@linux.vnet.ibm.com>
LKML-Reference: <4A79D7F1.4000405@us.ibm.com>
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>
Rafael J. Wysocki
Linus Torvalds
KOSAKI Motohiro
Thomas Gleixner
Ingo Molnar
Paul Mackerras
Eric Paris
Peter Zijlstra
Peter Zijlstra
Alan D. Brunelle
Darren Hart
Dinakar Guniguntala
Frederic Weisbecker
Stanislaw Gruszka
Tom Zanussi
Yinghai Lu
Eric Dumazet
Xiao Guangrong
Li Zefan
Robert Richter
Steven Rostedt