This patch exports CLOCK_BOOTTIME through the posix timers interface
CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
CLOCK_MONOTONIC stops while the system is in suspend. This is because
to applications system suspend is invisible. However, there is a
growing set of applications that are wanting to be suspend-aware,
but do not want to deal with the complications of CLOCK_REALTIME
(which might jump around if settimeofday is called).
For these applications, I propose a new clockid: CLOCK_BOOTTIME.
CLOCK_BOOTTIME is idential to CLOCK_MONOTONIC, except it also
includes any time spent in suspend.
This patch add hrtimer base for CLOCK_BOOTTIME, using
get_monotonic_boottime/ktime_get_boottime, to allow
in kernel users to set timers against.
CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
This adds new functions that return the monotonic time since boot
(in other words, CLOCK_MONOTONIC + suspend time).
CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
The hrtimer code is written mainly with CLOCK_REALTIME and CLOCK_MONOTONIC
in mind. These are clockids 0 and 1 resepctively. However, if we are
to introduce any new hrtimer bases, using new clockids, we have to skip
the cputimers (clockids 2,3) as well as other clockids that may not impelement
timers.
This patch adds a little bit of indirection between the clockid and
the base, so that we can extend the base by one when we add
a new clockid at number 7 or so.
CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
The switch case in __irq_set_trigger() lacks a break, which emits a
pr_err unconditionally on success.
Reported-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The runtime expansion of nr_irqs does not take into account that
bitmap_find_next_zero_area() returns "start" + size in case the search
for an matching zero area fails. That results in a start value which
can be completely off and is not covered by the following
expand_nr_irqs() and possibly outside of the absolute limit. But we
use it without further checking.
Use IRQ_BITMAP_BITS as the limit for the bitmap search and expand
nr_irqs when the start bit is beyond nr_irqs. So start is always
pointing to the correct area in the bitmap. nr_irqs is just the limit
for irq enumerations, not the real limit for the irq space.
[ tglx: Let irq_expand_nr_irqs() take the new upper end so we do not
expand nr_irqs more than necessary. Made changelog readable ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4D6014F9.8040605@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We lazy disable interrupt lines, so only mark the line masked, when
the chip provides an irq_disable callback.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
wq:fixes-2.6.38 does s/WQ_FREEZEABLE/WQ_FREEZABLE and wq:for-2.6.39
adds new usage of the flag. The combination of the two creates a
build failure after merge. Fix it by renaming all freezeables to
freezables.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
No need to lookup the irq descriptor when calling from a chip callback
function which has irq_data already handy.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Some chips want irq_eoi() only called when an interrupt is actually
handled. So they have checks for INPROGRESS and DISABLED in their
irq_eoi callbacks. Add a chip flag, which allows to handle that in the
generic code. No impact on the fastpath.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
sparc64 needs to call a preflow handler on certain interrupts befor
calling the action chain. Integrate it into handle_fasteoi_irq. Must
be enabled via CONFIG_IRQ_FASTEOI_PREFLOW. No impact when disabled.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: David S. Miller <davem@davemloft.net>
Most of the managing functions get the irq descriptor and lock it -
either with or without buslock. Instead of open coding this over and
over provide a common function to do that.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
If everything uses the right accessors, then enabling
GENERIC_HARDIRQS_NO_COMPAT should just work. If not it will tell you.
Don't be lazy and use the trick which I use in the core code!
git grep status_use_accessors
will unearth it in a split second. Offenders are tracked down and not
slapped with stinking trouts. This time we use frozen shark for a
better educational value.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Some irq_chips need to know the state of wakeup mode for
setting the trigger type etc. Reflect it in irq_data state.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
irq_chips, which require to mask the chip before changing the trigger
type should set this flag. So the core takes care of it and the
requirement for looking into desc->status in the chip goes away.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Walleij <linus.walleij@stericsson.com>
Cc: Lars-Peter Clausen <lars@metafoo.de>
That's the data structure chip functions get provided. Also allow them
to signal the core code that they updated the flags in irq_data.state
by returning IRQ_SET_MASK_OK_NOCOPY. The default is unchanged.
The type bits should be accessed via:
val = irqd_get_trigger_type(irqdata);
and
irqd_set_trigger_type(irqdata, val);
Coders who access them directly will be tracked down and slapped with
stinking trouts.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
That's the right data structure to look at for arch code.
Accessor functions are provided.
irqd_is_per_cpu(irqdata);
irqd_can_balance(irqdata);
Coders who access them directly will be tracked down and slapped with
stinking trouts.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The saving of this switch is minimal versus the ifdef mess it
creates. Simple enable PER_CPU unconditionally and remove the config
switch.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
chip implementations need to know about it. Keep status in sync until
all users are fixed.
Accessor function: irqd_is_setaffinity_pending(irqdata)
Coders who access them directly will be tracked down and slapped with
stinking trouts.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We need to maintain the flag for now in both fields status and istate.
Add a CONFIG_GENERIC_HARDIRQS_NO_COMPAT switch to allow testing w/o
the status one. Wrap the access to status IRQ_INPROGRESS in a inline
which can be turned of with CONFIG_GENERIC_HARDIRQS_NO_COMPAT along
with the define.
There is no reason that anything outside of core looks at this. That
needs some modifications, but we'll get there.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The irq_desc.status field will either go away or renamed to
settings. Anyway we need to maintain compatibility to avoid breaking
the world and some more. While moving bits into the core, I need to
avoid that I use any of the still existing IRQ_ bits in the core code
by typos. So that file will hold the inline wrappers and some nasty
CPP tricks to break the build when typoed.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
That field will contain internal state information which is not going
to be exposed to anything outside the core code - except via accessor
functions. I'm tired of everyone fiddling in irq_desc.status.
core_internal_state__do_not_mess_with_it is clear enough, annoying to
type and easy to grep for. Offenders will be tracked down and slapped
with stinking trouts.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
All archs implement show_interrupts() in more or less the same
way. That's tons of duplicated code with different bugs with no
value. Implement a generic version and deprecate show_interrupts()
Unfortunately we need some ifdeffery for !GENERIC_HARDIRQ archs.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
It's safe to drop the IRQ_INPROGRESS flag between action chain walks
as we are protected by desc->lock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Core code replacement for the ugly camel case. It contains all the
code which is shared in all handlers.
clear status flags
set INPROGRESS flag
unlock
call action chain
note_interrupt
lock
clr INPROGRESS flag
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
IRQ_MASKED is set in mask_ack_irq() anyway. Remove it from
handle_edge_irq() to allow simpler ab^HHreuse of that function.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110202212551.918484270@linutronix.de>
Now that everything uses the wrappers, we can remove the default
functions. None of those functions is performance critical.
That makes the IRQ_MASKED flag tracking fully consistent.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Aside of duplicated code some of the startup/shutdown sites do not
handle the MASKED/DISABLED flags and the depth field at all. Move that
to a helper function and take care of it there.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110202212551.787481468@linutronix.de>
The if (chip->irq_shutdown) check will always evaluate to true, as we
fill in chip->irq_shutdown with default_shutdown in
irq_chip_set_defaults() if the chip does not provide its own function.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110202212551.667607458@linutronix.de>
With the chip.end() function gone we might run into a situation where
a poll call runs and the real interrupt comes in, sees IRQ_INPROGRESS
and disables the line. That might be a perfect working one, which will
then be masked forever.
So mark them polled while the poll runs. When the real handler sees
IRQ_INPROGRESS it checks the poll flag and waits for the polling to
complete. Add the necessary amount of sanity checks to it to avoid
deadlocks.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
There is no point in polling disabled lines.
percpu does not make sense at all because we only poll on the cpu
we're currently running on. Also polling per_cpu interrupts is racy as
hell. The handler runs without locking so we might get a huge
surprise.
If the timer interrupt needs polling, then we wont get there anyway.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
try_one_irq() contains redundant code and lots of useless checks for
shared interrupts. Check for shared before setting IRQ_INPROGRESS and
then call handle_IRQ_event() while pending. Shorter version with the
same functionality.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We run all handlers with interrupts disabled and expect them not to
enable them. Warn when we catch one who does.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We cannot walk the action chain unlocked. Even if IRQ_INPROGRESS is
set an action can be removed and we follow a null pointer. It's safe
to take the lock there, because the code which removes the action will
call synchronize_irq() which waits unlocked for IRQ_INPROGRESS going
away.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
While rumaging through arch code I found that there are a few
workarounds which deal with the fact that the initial affinity setting
from request_irq() copies the mask into irq_data->affinity before the
chip code is called. In the normal path we unconditionally copy the
mask when the chip code returns 0.
Copy after the code is called and add a return code
IRQ_SET_MASK_OK_NOCOPY for the chip functions, which prevents the
copy. That way we see the real mask when the chip function decided to
truncate it further as some arches do. IRQ_SET_MASK_OK is 0, which is
the current behaviour.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
If the affinity had been set by the user, then a later request_irq()
will honour that setting. But online cpus can have changed. So apply
the online mask and for this case as well.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
There is lot of #ifdef CONFIG_GENERIC_PENDING_IRQ along with
duplicated code in the irq core. Move the #ifdeffery into one place
and cleanup the code so it's readable. No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The irq namespace has become quite convoluted. My bad. Clean it up
and deprecate the old functions. All new functions follow the scheme:
irq number based:
irq_set/get/xxx/_xxx(unsigned int irq, ...)
irq_data based:
irq_data_set/get/xxx/_xxx(struct irq_data *d, ....)
irq_desc based:
irq_desc_get_xxx(struct irq_desc *desc)
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
chips behind a slow bus cannot update the chip under desc->lock, but
we miss the chip_buslock/chip_bus_sync_unlock() calls around the set
type and set wake functions.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We face more and more the requirement to expand nr_irqs at
runtime. The reason are irq expanders which can not be detected in the
early boot stage. So we speculate nr_irqs to have enough room. Further
Xen needs extra irq numbers and we really want to avoid adding more
"detection" code into the early boot. There is no real good reason why
we need to limit nr_irqs at early boot.
Allow the allocation code to expand nr_irqs. We have already 8k extra
number space in the allocation bitmap, so lets use it.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
With CONFIG_SHIRQ_DEBUG=y we call a newly installed interrupt handler
in request_threaded_irq().
The original implementation (commit a304e1b8) called the handler
_BEFORE_ it was installed, but that caused problems with handlers
calling disable_irq_nosync(). See commit 377bf1e4.
It's braindead in the first place to call disable_irq_nosync in shared
handlers, but ....
Moving this call after we installed the handler looks innocent, but it
is very subtle broken on SMP.
Interrupt handlers rely on the fact, that the irq core prevents
reentrancy.
Now this debug call violates that promise because we run the handler
w/o the IRQ_INPROGRESS protection - which we cannot apply here because
that would result in a possibly forever masked interrupt line.
A concurrent real hardware interrupt on a different CPU results in
handler reentrancy and can lead to complete wreckage, which was
unfortunately observed in reality and took a fricking long time to
debug.
Leave the code here for now. We want this debug feature, but that's
not easy to fix. We really should get rid of those
disable_irq_nosync() abusers and remove that function completely.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Anton Vorontsov <avorontsov@ru.mvista.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: stable@kernel.org # .28 -> .37
Lars-Peter Clausen pointed out:
I stumbled upon this while looking through the existing archs using
SPARSE_IRQ. Even with SPARSE_IRQ the NR_IRQS is still the upper
limit for the number of IRQs.
Both PXA and MMP set NR_IRQS to IRQ_BOARD_START, with
IRQ_BOARD_START being the number of IRQs used by the core.
In various machine files the nr_irqs field of the ARM machine
defintion struct is then set to "IRQ_BOARD_START + NR_BOARD_IRQS".
As a result "nr_irqs" will greater then NR_IRQS which then again
causes the "allocated_irqs" bitmap in the core irq code to be
accessed beyond its size overwriting unrelated data.
The core code really misses a sanity check there.
This went unnoticed so far as by chance the compiler/linker places
data behind that bitmap which gets initialized later on those affected
platforms.
So the obvious fix would be to add a sanity check in early_irq_init()
and break all affected platforms. Though that check wants to be
backported to stable as well, which will require to fix all known
problematic platforms and probably some more yet not known ones as
well. Lots of churn.
A way simpler solution is to allocate a slightly larger bitmap and
avoid the whole churn w/o breaking anything. Add a few warnings when
an arch returns utter crap.
Reported-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org # .37
Cc: Haojian Zhuang <haojian.zhuang@marvell.com>
Cc: Eric Miao <eric.y.miao@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
* 'fixes-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
workqueue: make sure MAYDAY_INITIAL_TIMEOUT is at least 2 jiffies long
workqueue, freezer: unify spelling of 'freeze' + 'able' to 'freezable'
workqueue: wake up a worker when a rescuer is leaving a gcwq
The ADJ_SETOFFSET code redundantly checks the range of the nanoseconds
field of the time value. This field is checked again in the subsequent
call to timekeeping_inject_offset(). Also, as is, the check will not
detect whether the number of microseconds is out of range.
Let timekeeping_inject_offset() do the error checking.
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Cc: johnstul@us.ibm.com
LKML-Reference: <20110218090724.GA2924@riccoc20.at.omicron.at>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This reverts commit 5e38ca8f3e.
Breaks the build of several !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
architectures.
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Message-ID: <20110217171823.GB17058@elte.hu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently we return 0 in swsusp_alloc() when alloc_image_page() fails.
Fix that. Also remove unneeded "error" variable since the only
useful value of error is -ENOMEM.
[rjw: Fixed up the changelog and changed subject.]
Signed-off-by: Stanislaw Gruszka <stf_xl@wp.pl>
Cc: stable@kernel.org
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
MAYDAY_INITIAL_TIMEOUT is defined as HZ / 100 and depending on
configuration may end up 0 or 1. Even when it's 1, depending on when
the mayday timer is added in the current jiffy interval, it may expire
way before a jiffy has passed.
Make sure MAYDAY_INITIAL_TIMEOUT is at least two to guarantee that at
least a full jiffy has passed before calling rescuers.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Ray Jui <rjui@broadcom.com>
Cc: stable@kernel.org
There are two spellings in use for 'freeze' + 'able' - 'freezable' and
'freezeable'. The former is the more prominent one. The latter is
mostly used by workqueue and in a few other odd places. Unify the
spelling to 'freezable'.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
Acked-by: Dmitry Torokhov <dtor@mail.ru>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Alex Dubov <oakad@yahoo.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Twice I had to explain the output about why lockdep gives an error with
locks in IRQ context and with del_timer_sync(). Might as well write it
up and place it in the comments above the code in del_timer_sync().
Perhaps the next time this lockdep dump triggers people will understand
the issues.
It is a ticky issue and very subtle, explaining it in detail in the code
may help others understand the issue when they stumble upon the bug
again.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1297186794.23343.19.camel@gandalf.stny.rr.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
sd_idle logic was introduced way back in 2005 (commit 5969fe06),
as an HT optimization.
As per the discussion in the thread here:
lkml - sched: Resolve sd_idle and first_idle_cpu Catch-22 - v1
https://patchwork.kernel.org/patch/532501/
The capacity based logic in the load balancer right now handles this
in a much cleaner way, handling more than 2 SMT siblings etc, and sd_idle
does not seem to bring any additional benefits. sd_idle logic also has
some bugs that has performance impact. Here is the patch that removes
the sd_idle logic altogether.
Also, there was a dependency of sched_mc_power_savings == 2, with sd_idle
logic.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Acked-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1297723130-693-1-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There is no need to re-initialize the hrtimer every time we start it,
so don't do that (shaves a few cycles). Also, since we know hrtimers
run at a fixed rate (nanoseconds) we can pre-compute the desired
frequency at which they tick. This avoids us having to go through the
whole adaptive frequency feedback logic (shaves another few cycles).
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1297448589.5226.47.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
By pre-computing the maximum number of samples per tick we can avoid a
multiplication and a conditional since MAX_INTERRUPTS >
max_samples_per_tick.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This kernel patch adds the ability to filter monitoring based on
container groups (cgroups). This is for use in per-cpu mode only.
The cgroup to monitor is passed as a file descriptor in the pid
argument to the syscall. The file descriptor must be opened to
the cgroup name in the cgroup filesystem. For instance, if the
cgroup name is foo and cgroupfs is mounted in /cgroup, then the
file descriptor is opened to /cgroup/foo. Cgroup mode is
activated by passing PERF_FLAG_PID_CGROUP in the flags argument
to the syscall.
For instance to measure in cgroup foo on CPU1 assuming
cgroupfs is mounted under /cgroup:
struct perf_event_attr attr;
int cgroup_fd, fd;
cgroup_fd = open("/cgroup/foo", O_RDONLY);
fd = perf_event_open(&attr, cgroup_fd, 1, -1, PERF_FLAG_PID_CGROUP);
close(cgroup_fd);
Signed-off-by: Stephane Eranian <eranian@google.com>
[ added perf_cgroup_{exit,attach} ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590250.114ddf0a.689e.4482@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Make the ::exit method act like ::attach, it is after all very nearly
the same thing.
The bug had no effect on correctness - fixing it is an optimization for
the scheduler. Also, later perf-cgroups patches rely on it.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Menage <menage@google.com>
LKML-Reference: <1297160655.13327.92.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It was possible to call pmu::start() on an already running event. In
particular this lead so some wreckage as the hrtimer events would
re-initialize active timers.
This was due to throttled events being activated again by scheduling.
Scheduling in a context would add and force start events, resulting in
running events with a possible throttle status. The next tick to hit
that task will then try to unthrottle the event and call ->start() on
an already running event.
Reported-by: Jeff Moyer <jmoyer@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: Fix text_poke_smp_batch() deadlock
perf tools: Fix thread_map event synthesizing in top and record
watchdog, nmi: Lower the severity of error messages
ARM: oprofile: Fix backtraces in timer mode
oprofile: Fix usage of CONFIG_HW_PERF_EVENTS for oprofile_perf_init and friends
This patch enables gcov kernel profiling over the whole kernel for sh.
Profiling of specific files individually already worked. A handful of
files have to be explicitly excluded from the profiling to avoid
breaking things, notably pmb.c.
Signed-off-by: Chris Smith <chris.smith@st.com>
Signed-off-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
After executing the matching works, a rescuer leaves the gcwq whether
there are more pending works or not. This may decrease the
concurrency level to zero and stall execution until a new work item is
queued on the gcwq.
Make rescuer wake up a regular worker when it leaves a gcwq if there
are more works to execute, so that execution isn't stalled.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Ray Jui <rjui@broadcom.com>
Cc: stable@kernel.org
Add NULL check for avoiding NULL pointer deref.
This bug has been introduced by:
1ff511e35ed8: tracing/kprobes: Add bitfield type
which causes a null pointer dereference bug when kprobe-tracer
parses an argument without type.
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: 2nddept-manager@sdl.hitachi.co.jp
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110214054807.8919.69740.stgit@ltc236.sdl.hitachi.co.jp>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6:
pci: use security_capable() when checking capablities during config space read
security: add cred argument to security_capable()
tpm_tis: Use timeouts returned from TPM
The wake_up_process() call in ptrace_detach() is spurious and not
interlocked with the tracee state. IOW, the tracee could be running or
sleeping in any place in the kernel by the time wake_up_process() is
called. This can lead to the tracee waking up unexpectedly which can be
dangerous.
The wake_up is spurious and should be removed but for now reduce its
toxicity by only waking up if the tracee is in TRACED or STOPPED state.
This bug can possibly be used as an attack vector. I don't think it
will take too much effort to come up with an attack which triggers oops
somewhere. Most sleeps are wrapped in condition test loops and should
be safe but we have quite a number of places where sleep and wakeup
conditions are expected to be interlocked. Although the window of
opportunity is tiny, ptrace can be used by non-privileged users and with
some loading the window can definitely be extended and exploited.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Roland McGrath <roland@redhat.com>
Acked-by: 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>
When the fuction graph tracer starts, it needs to make a special
stack for each task to save the real return values of the tasks.
All running tasks have this stack created, as well as any new
tasks.
On CPU hot plug, the new idle task will allocate a stack as well
when init_idle() is called. The problem is that cpu hotplug does
not create a new idle_task. Instead it uses the idle task that
existed when the cpu went down.
ftrace_graph_init_task() will add a new ret_stack to the task
that is given to it. Because a clone will make the task
have a stack of its parent it does not check if the task's
ret_stack is already NULL or not. When the CPU hotplug code
starts a CPU up again, it will allocate a new stack even
though one already existed for it.
The solution is to treat the idle_task specially. In fact, the
function_graph code already does, just not at init_idle().
Instead of using the ftrace_graph_init_task() for the idle task,
which that function expects the task to be a clone, have a
separate ftrace_graph_init_idle_task(). Also, we will create a
per_cpu ret_stack that is used by the idle task. When we call
ftrace_graph_init_idle_task() it will check if the idle task's
ret_stack is NULL, if it is, then it will assign it the per_cpu
ret_stack.
Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stable Tree <stable@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Fixups due to rename of event_t routines from event__ to perf_event__
done in perf/core.
Conflicts:
tools/perf/builtin-record.c
tools/perf/builtin-top.c
tools/perf/util/event.c
tools/perf/util/event.h
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Expand security_capable() to include cred, so that it can be usable in a
wider range of call sites.
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: James Morris <jmorris@namei.org>
In commit ce6ada35bd ("security: Define CAP_SYSLOG") Serge Hallyn
introduced CAP_SYSLOG, but broke backwards compatibility by no longer
accepting CAP_SYS_ADMIN as an override (it would cause a warning and
then reject the operation).
Re-instate CAP_SYS_ADMIN - but keeping the warning - as an acceptable
capability until any legacy applications have been updated. There are
apparently applications out there that drop all capabilities except for
CAP_SYS_ADMIN in order to access the syslog.
(This is a re-implementation of a patch by Serge, cleaning the logic up
and making the code more readable)
Acked-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: James Morris <jmorris@namei.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Reason: irq/for-mips is provided for mips to make core independent
progress. Merge it into irq/core to avoid conflicts
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
irq_chips that supply .irq_bus_lock/.irq_bus_sync_unlock functions,
expect that the other chip methods will be called inside of calls to
the pair. If this expectation is not met, things tend to not work.
Make setup_irq() call chip_bus_lock()/chip_bus_sync_unlock() too.
For the vast majority of irq_chips, this will be a NOP as most don't
have these bus lock functions.
[ tglx: No we don't want to call that in __setup_irq(). Way too many
error exit pathes. ]
Signed-off-by: David Daney <ddaney@caviumnetworks.com>
LKML-Reference: <1297296265-18680-1-git-send-email-ddaney@caviumnetworks.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
During boot if the hardlockup detector fails to initialize, it
complains very loudly. Some failures should be expected under
certain situations, ie no lapics, or resource in-use. Tone
those error messages down a bit. Keep the rest at a high level.
Reported-by: Paul Bolle <pebolle@tiscali.nl>
Tested-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1297278153-21111-1-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
cdrom: support devices that have check_events but not media_changed
cfq-iosched: Don't wait if queue already has requests.
blkio-throttle: Avoid calling blkiocg_lookup_group() for root group
cfq: rename a function to give it more appropriate name
cciss: make cciss_revalidate not loop through CISS_MAX_LUNS volumes unnecessarily.
drivers/block/aoe/Makefile: replace the use of <module>-objs with <module>-y
loop: queue_lock NULL pointer derefence in blk_throtl_exit
drivers/block/Makefile: replace the use of <module>-objs with <module>-y
blktrace: Don't output messages if NOTIFY isn't set.
tracing_enabled should not be used, it is heavy weight and does not
do much in helping lower the overhead.
tracing_on should be used instead. Warn users to use tracing_on
when tracing_enabled is used as it will soon be removed from the
tracing directory.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The trace events sched_switch and sched_wakeup do the same thing
as the stand alone sched_switch tracer does. It is no longer needed.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
CONFIG_KSTAT_IRQS_ONDEMAND does not exist. It's not worth to implement
it. Use sparse irqs if you care about memory consumption of the
interrupt layer.
Found by undertaker: http://vamos.informatik.uni-erlangen.de/trac/undertaker
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
ksoftirqd() calls do_softirq() which switches stacks on several
architectures. That makes no sense at all. ksoftirqd's stack is
sufficient.
Call __do_softirq() directly.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: David Miller <davem@davemloft.net>
Cc: Paul Mundt <lethal@linux-sh.org>
Reviewed-by: Frank Rowand <frank.rowand@am.sony.com>
LKML-Reference: <alpine.LFD.2.00.1102021704530.31804@localhost6.localdomain6>
The warning "Delta way too big" warning might appear on a system with
unstable shed clock right after the system is resumed and tracing
was enabled during the suspend.
Since it's not realy bug, and the unstable sched clock is working
fast and reliable otherwise, Steven suggested to keep using the
sched clock in any case and just to make note in the warning itself.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
LKML-Reference: <1296649698-6003-1-git-send-email-jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
irq/for-xen contains new functionality to avoid Xen private irq
hackery. That branch has a single irq commit and is pulled by Xen to
base their new features on.
Merge it into irq/core as other patches modify the same code.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Xen needs to reenable interrupts which are marked IRQF_NO_SUSPEND in the
resume path. Add a flag to force the reenabling in the resume code.
Tested-and-acked-by: Ian Campbell <Ian.Campbell@eu.citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Both attempts at trying to allow softirq usage for
del_timer_sync() failed (produced bogus warnings),
so revert the commit for this release:
f266a5110d45: lockdep, timer: Fix del_timer_sync() annotation
and try again later.
Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Yong Zhang <yong.zhang0@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1297174680.13327.107.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Many system calls are unimplemented and mapped to sys_ni_syscall, but at
boot ftrace would still search through every syscall metadata entry for
a match which wouldn't be there.
This patch adds causes the search to terminate early if the system call
is not mapped.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
LKML-Reference: <1296703645-18718-7-git-send-email-imunsie@au1.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Some architectures have unusual symbol names and the generic code to
match the symbol name with the function name for the syscall metadata
will fail. For example, symbols on PPC64 start with a period and the
generic code will fail to match them.
This patch moves the match logic out into a separate function which an
arch can override by defining ARCH_HAS_SYSCALL_MATCH_SYM_NAME in
asm/ftrace.h and implementing arch_syscall_match_sym_name.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
LKML-Reference: <1296703645-18718-5-git-send-email-imunsie@au1.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Some architectures use non-trivial system call tables and will not work
with the generic arch_syscall_addr code. For example, PowerPC64 uses a
table of twin long longs.
This patch makes the generic arch_syscall_addr weak to allow
architectures with non-trivial system call tables to override it.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
LKML-Reference: <1296703645-18718-4-git-send-email-imunsie@au1.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
With the ftrace events now checking if the syscall_nr is valid upon
initialisation it should no longer be possible to register or unregister
a syscall event without a valid syscall_nr since they should not be
created. This adds a WARN_ON_ONCE in the register and unregister
functions to locate potential regressions in the future.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
LKML-Reference: <1296703645-18718-3-git-send-email-imunsie@au1.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
FTRACE_SYSCALLS would create events for each and every system call, even
if it had failed to map the system call's name with it's number. This
resulted in a number of events being created that would not behave as
expected.
This could happen, for example, on architectures who's symbol names are
unusual and will not match the system call name. It could also happen
with system calls which were mapped to sys_ni_syscall.
This patch changes the default system call number in the metadata to -1.
If the system call name from the metadata is not successfully mapped to
a system call number during boot, than the event initialisation routine
will now return an error, preventing the event from being created.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
LKML-Reference: <1296703645-18718-2-git-send-email-imunsie@au1.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Because the filters are processed first and then activated
(added to the call), we no longer need to worry about the preds
of the filter in __alloc_preds() being used. As the filter that
is allocating preds is not activated yet.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
When creating a new filter, instead of allocating the filter to the
event call first and then processing the filter, it is easier to
process a temporary filter and then just swap it with the call filter.
By doing this, it simplifies the code.
A filter is allocated and processed, when it is done, it is
swapped with the call filter, synchronize_sched() is called to make
sure all callers are done with the old filter (filters are called
with premption disabled), and then the old filter is freed.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Now that the filter logic does not require to save the pred results
on the stack, we can increase the max number of preds we allow.
As the preds are index by a short value, and we use the MSBs as flags
we can increase the max preds to 2^14 (16384) which should be way
more than enough.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The MAX_FILTER_PRED is only needed by the kernel/trace/*.c files.
Move it to kernel/trace/trace.h.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
There are many cases that a filter will contain multiple ORs or
ANDs together near the leafs. Walking up and down the tree to get
to the next compare can be a waste.
If there are several ORs or ANDs together, fold them into a single
pred and allocate an array of the conditions that they check.
This will speed up the filter by linearly walking an array
and can still break out if a short circuit condition is met.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Since the filter walks a tree to determine if a match is made or not,
if the tree was incorrectly created, it could cause an infinite loop.
Add a check to walk the entire tree before assigning it as a filter
to make sure the tree is correct.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The test if we should break out early for OR and AND operations
can be optimized by comparing the current result with
(pred->op == OP_OR)
That is if the result is true and the op is an OP_OR, or
if the result is false and the op is not an OP_OR (thus an OP_AND)
we can break out early in either case. Otherwise we continue
processing.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Currently the filter_match_preds() requires a stack to push
and pop the preds to determine if the filter matches the record or not.
This has two drawbacks:
1) It requires a stack to store state information. As this is done
in fast paths we can't allocate the storage for this stack, and
we can't use a global as it must be re-entrant. The stack is stored
on the kernel stack and this greatly limits how many preds we
may allow.
2) All conditions are calculated even when a short circuit exists.
a || b will always calculate a and b even though a was determined
to be true.
Using a tree we can walk a constant structure that will save
the state as we go. The algorithm is simply:
pred = root;
do {
switch (move) {
case MOVE_DOWN:
if (OR or AND) {
pred = left;
continue;
}
if (pred == root)
break;
match = pred->fn();
pred = pred->parent;
move = left child ? MOVE_UP_FROM_LEFT : MOVE_UP_FROM_RIGHT;
continue;
case MOVE_UP_FROM_LEFT:
/* Only OR or AND can be a parent */
if (match && OR || !match && AND) {
/* short circuit */
if (pred == root)
break;
pred = pred->parent;
move = left child ?
MOVE_UP_FROM_LEFT :
MOVE_UP_FROM_RIGHT;
continue;
}
pred = pred->right;
move = MOVE_DOWN;
continue;
case MOVE_UP_FROM_RIGHT:
if (pred == root)
break;
pred = pred->parent;
move = left child ? MOVE_UP_FROM_LEFT : MOVE_UP_FROM_RIGHT;
continue;
}
done = 1;
} while (!done);
This way there's no strict limit to how many preds we allow
and it also will short circuit the logical operations when possible.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Currently we allocate an array of pointers to filter_preds, and then
allocate a separate filter_pred for each item in the array.
This adds slight overhead in the filters as it needs to derefernce
twice to get to the op condition.
Allocating the preds themselves in a single array removes a dereference
as well as helps on the cache footprint.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
By separating out the reseting of the filter->n_preds to zero from
the reallocation of preds for the filter, we can reset groups of
filters first, call synchronize_sched() just once, and then reallocate
each of the filters in the system group.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
For every filter that is made, we create predicates to hold every
operation within the filter. We have a max of 32 predicates that we
can hold. Currently, we allocate all 32 even if we only need to
use one.
Part of the reason we do this is that the filter can be used at
any moment by any event. Fortunately, the filter is only used
with preemption disabled. By reseting the count of preds used "n_preds"
to zero, then performing a synchronize_sched(), we can safely
free and reallocate a new array of preds.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The ops OR and AND act different from the other ops, as they
are the only ones to take other ops as their arguements.
These ops als change the logic of the filter_match_preds.
By removing the OR and AND fn's we can also remove the val1 and val2
that is passed to all other fn's and are unused.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The n_preds field of a file can change at anytime, and even can become
zero, just as the filter is about to be processed by an event.
In the case that is zero on entering the filter, return 1, telling
the caller the event matchs and should be trace.
Also use a variable and assign it with ACCESS_ONCE() such that the
count stays consistent within the function.
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
In prepare_kernel_cred() since 2.6.29, put_cred(new) is called without
assigning new->usage when security_prepare_creds() returned an error. As a
result, memory for new and refcount for new->{user,group_info,tgcred} are
leaked because put_cred(new) won't call __put_cred() unless old->usage == 1.
Fix these leaks by assigning new->usage (and new->subscribers which was added
in 2.6.32) before calling security_prepare_creds().
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In cred_alloc_blank() since 2.6.32, abort_creds(new) is called with
new->security == NULL and new->magic == 0 when security_cred_alloc_blank()
returns an error. As a result, BUG() will be triggered if SELinux is enabled
or CONFIG_DEBUG_CREDENTIALS=y.
If CONFIG_DEBUG_CREDENTIALS=y, BUG() is called from __invalid_creds() because
cred->magic == 0. Failing that, BUG() is called from selinux_cred_free()
because selinux_cred_free() is not expecting cred->security == NULL. This does
not affect smack_cred_free(), tomoyo_cred_free() or apparmor_cred_free().
Fix these bugs by
(1) Set new->magic before calling security_cred_alloc_blank().
(2) Handle null cred->security in creds_are_invalid() and selinux_cred_free().
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add bitfield type for tracing arguments on kprobe-tracer. The syntax of
a bitfield type is:
b<bit-size>@<bit-offset>/<container-size>
e.g.
Accessing 2 bits-width field with 4 bits-offset in 32 bits-width data at
4 bytes offseted from the address pointed by AX register:
+4(%ax):b2@4/32
Since the width of container data depends on the arch, so I just added
the container-size at the end.
Cc: 2nddept-manager@sdl.hitachi.co.jp
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <20110204125205.9507.11363.stgit@ltc236.sdl.hitachi.co.jp>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Since strict_strtol() accepts minus digits started with '-', it doesn't
need to invert after converting.
Cc: 2nddept-manager@sdl.hitachi.co.jp
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <20110204125153.9507.49335.stgit@ltc236.sdl.hitachi.co.jp>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
lockdep, timer: Fix del_timer_sync() annotation
RTC: Prevents a division by zero in kernel code.
Calling local_bh_enable() will want to actually start processing
softirqs, which isn't a good idea since this can get called with IRQs
disabled.
Cure this by using _local_bh_enable() which doesn't start processing
softirqs, and use raw_local_irq_save() to avoid any softirqs from
happening without letting lockdep think IRQs are in fact disabled.
Reported-by: Nick Bowler <nbowler@elliptictech.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Yong Zhang <yong.zhang0@gmail.com>
LKML-Reference: <20110203141548.039540914@chello.nl>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched: Fix update_curr_rt()
sched, docs: Update schedstats documentation to version 15
Currently the syscall_meta structures for the syscall tracepoints are
placed in the __syscall_metadata section, and at link time, the linker
makes one large array of all these syscall metadata structures. On boot
up, this array is read (much like the initcall sections) and the syscall
data is processed.
The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.
A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).
Instead of packing the structures into an array, the structures' addresses
are now put into the __syscall_metadata section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).
By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.
The __syscall_metadata section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: David Miller <davem@davemloft.net>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Make the tracepoints more robust, making them solid enough to handle compiler
changes by not relying on anything based on compiler-specific behavior with
respect to structure alignment. Implement an approach proposed by David Miller:
use an array of const pointers to refer to the individual structures, and export
this pointer array through the linker script rather than the structures per se.
It will consume 32 extra bytes per tracepoint (24 for structure padding and 8
for the pointers), but are less likely to break due to compiler changes.
History:
commit 7e066fb8 tracepoints: add DECLARE_TRACE() and DEFINE_TRACE()
added the aligned(32) type and variable attribute to the tracepoint structures
to deal with gcc happily aligning statically defined structures on 32-byte
multiples.
One attempt was to use a 8-byte alignment for tracepoint structures by applying
both the variable and type attribute to tracepoint structures definitions and
declarations. It worked fine with gcc 4.5.1, but broke with gcc 4.4.4 and 4.4.5.
The reason is that the "aligned" attribute only specify the _minimum_ alignment
for a structure, leaving both the compiler and the linker free to align on
larger multiples. Because tracepoint.c expects the structures to be placed as an
array within each section, up-alignment cause NULL-pointer exceptions due to the
extra unexpected padding.
(this patch applies on top of -tip)
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: David S. Miller <davem@davemloft.net>
LKML-Reference: <20110126222622.GA10794@Krystal>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: Ingo Molnar <mingo@elte.hu>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Currently only implemented for fair class tasks.
Add a yield_to_task method() to the fair scheduling class. allowing the
caller of yield_to() to accelerate another thread in it's thread group,
task group.
Implemented via a scheduler hint, using cfs_rq->next to encourage the
target being selected. We can rely on pick_next_entity to keep things
fair, so noone can accelerate a thread that has already used its fair
share of CPU time.
This also means callers should only call yield_to when they really
mean it. Calling it too often can result in the scheduler just
ignoring the hint.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110201095051.4ddb7738@annuminas.surriel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use the buddy mechanism to implement yield_task_fair. This
allows us to skip onto the next highest priority se at every
level in the CFS tree, unless doing so would introduce gross
unfairness in CPU time distribution.
We order the buddy selection in pick_next_entity to check
yield first, then last, then next. We need next to be able
to override yield, because it is possible for the "next" and
"yield" task to be different processen in the same sub-tree
of the CFS tree. When they are, we need to go into that
sub-tree regardless of the "yield" hint, and pick the correct
entity once we get to the right level.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110201095103.3a79e92a@annuminas.surriel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The clear_buddies function does not seem to play well with the concept
of hierarchical runqueues. In the following tree, task groups are
represented by 'G', tasks by 'T', next by 'n' and last by 'l'.
(nl)
/ \
G(nl) G
/ \ \
T(l) T(n) T
This situation can arise when a task is woken up T(n), and the previously
running task T(l) is marked last.
When clear_buddies is called from either T(l) or T(n), the next and last
buddies of the group G(nl) will be cleared. This is not the desired
result, since we would like to be able to find the other type of buddy
in many cases.
This especially a worry when implementing yield_task_fair through the
buddy system.
The fix is simple: only clear the buddy type that the task itself
is indicated to be. As an added bonus, we stop walking up the tree
when the buddy has already been cleared or pointed elsewhere.
Signed-off-by: Rik van Riel <riel@redhat.coM>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110201094837.6b0962a9@annuminas.surriel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
With CONFIG_FAIR_GROUP_SCHED, each task_group has its own cfs_rq.
Yielding to a task from another cfs_rq may be worthwhile, since
a process calling yield typically cannot use the CPU right now.
Therefor, we want to check the per-cpu nr_running, not the
cgroup local one.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110201094715.798c4f86@annuminas.surriel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
cpu_stopper_thread()
migration_cpu_stop()
__migrate_task()
deactivate_task()
dequeue_task()
dequeue_task_rq()
update_curr_rt()
Will call update_curr_rt() on rq->curr, which at that time is
rq->stop. The problem is that rq->stop.prio matches an RT prio and
thus falsely assumes its a rt_sched_class task.
Reported-Debuged-Tested-Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Cc: stable@kernel.org # .37
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It is quite possible for the event to have been disabled between
perf_event_read() sending the IPI and the CPU servicing the IPI and
calling __perf_event_read(), hence revalidate the state.
Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Oleg reported that on architectures with
__ARCH_WANT_INTERRUPTS_ON_CTXSW the IPI from
task_oncpu_function_call() can land before perf_event_task_sched_in()
and cause interesting situations for eg. perf_install_in_context().
This patch reworks the task_oncpu_function_call() interface to give a
more usable primitive as well as rework all its users to hopefully be
more obvious as well as remove the races.
While looking at the code I also found a number of races against
perf_event_task_sched_out() which can flip contexts between tasks so
plug those too.
Reported-and-reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently the trace_event structures are placed in the _ftrace_events
section, and at link time, the linker makes one large array of all
the trace_event structures. On boot up, this array is read (much like
the initcall sections) and the events are processed.
The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.
A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).
Instead of packing the structures into an array, the structures' addresses
are now put into the _ftrace_event section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).
By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.
The _ftrace_event section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: David Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
move_native_irq() masks and unmasks the interrupt line
unconditionally, but the interrupt line might be masked due to a
threaded oneshot handler in progress. Unmasking the line in that case
can lead to interrupt storms. Observed on PREEMPT_RT.
Originally-from: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
This patch adds support for adding and removing posix clocks. The
clock lifetime cycle is patterned after usb devices. Each clock is
represented by a standard character device. In addition, the driver
may optionally implement custom character device operations.
The posix clock and timer system calls listed below now work with
dynamic posix clocks, as well as the traditional static clocks.
The following system calls are affected:
- clock_adjtime (brand new syscall)
- clock_gettime
- clock_getres
- clock_settime
- timer_create
- timer_delete
- timer_gettime
- timer_settime
[ tglx: Adapted to the posix-timer cleanup. Moved clock_posix_dynamic
to posix-clock.c and made all referenced functions static ]
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134420.164172635@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Rename register_posix_clock() to posix_timers_register_clock(). That's
what the function really does. As a side effect this cleans up the
posix_clock namespace for the upcoming dynamic posix_clock
infrastructure.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
Cc: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <alpine.LFD.2.00.1102021222240.31804@localhost6.localdomain6>
Extend the negative clockids which are currently used by posix cpu
timers to encode the PID with a file descriptor based type which
encodes the fd in the upper bits.
Originally-from: Richard Cochran <richard.cochran@omicron.at>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134420.062860200@linutronix.de>
A new syscall is introduced that allows tuning of a POSIX clock. The
new call, clock_adjtime, takes two parameters, the clock ID and a
pointer to a struct timex. Any ADJTIMEX(2) operation may be requested
via this system call, but various POSIX clocks may or may not support
tuning.
[ tglx: Adapted to the posix-timer cleanup series. Avoid copy_to_user
in the error case ]
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134419.869804645@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Split out the compat timex accessors into separate
functions. Preparatory patch for a new syscall.
[ tglx: Split that patch from Richards "posix-timers: Introduce a
syscall for clock tuning.". Keeps the changes strictly
separate ]
Originally-from: Richard Cochran <richardcochran@gmail.com>
Acked-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <20110201134419.772343089@linutronix.de>
This patch adds a new mode bit into the timex structure. When set, the bit
instructs the kernel to add the given time value to the current time.
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134320.688829863@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This adds a kernel-internal timekeeping interface to add or subtract
a fixed amount from CLOCK_REALTIME. This makes it so kernel users or
interfaces trying to do so do not have to read the time, then add an
offset and then call settimeofday(), which adds some extra error in
comparision to just simply adding the offset in the kernel timekeeping
core.
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.584311693@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Pick the cleanup to the comment in posix-timers.c from Richards all in
one conversion patch.
Originally-from: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134419.487708516@linutronix.de>
All functions are accessed via clock_posix_cpu now. So make them static.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.389755466@linutronix.de>
All users gone. Remove the cruft.
Huge thanks to Richard Cochran who tackled that maze first.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.294620613@linutronix.de>
Set the common function for CLOCK_MONOTONIC and CLOCK_REALTIME kclocks
and use the new decoding function.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.198999420@linutronix.de>
Set the common function for CLOCK_MONOTONIC and CLOCK_REALTIME kclocks
and use the new decoding function.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.101243181@linutronix.de>
Set the common function for CLOCK_MONOTONIC and CLOCK_REALTIME kclocks
and use the new decoding function.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.001863714@linutronix.de>
Setup timer_create for CLOCK_MONOTONIC and CLOCK_REALTIME kclocks and
remove the no_timer_create() implementation.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.903604289@linutronix.de>
The res member of kclock is only used by mmtimer.c, but even there it
contains redundant information. Remove the field and fixup mmtimer.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.808714587@linutronix.de>
Use the new kclock decoding. Fixup the fallout in mmtimer.c
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.709802797@linutronix.de>
Richard said: "I would think that we can require k_clocks to provide
the read function. This could be checked and enforced in
register_posix_clock()."
Add checks for clock_getres and clock_get in the register function.
Suggested-by: Richard Cochran <richardcochran@gmail.com>
Cc: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Use the new kclock decoding mechanism and rename the misnomed
common_clock_get() to posix_clock_realtime_get().
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.611097203@linutronix.de>
Use the new kclock decoding function in clock_settime and cleanup all
kclocks which use the default functions. Rename the misnomed
common_clock_set() to posix_clock_realtime_set().
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.518851246@linutronix.de>
CLOCK_THREAD_CPUTIME_ID implements stub functions for nanosleep and
nanosleep_restart, which return -EINVAL. That return value is
wrong. The correct return value is -ENOTSUP.
Remove the stubs and let the new dispatch code return the correct
error code.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.422446502@linutronix.de>
posix timers still use the legacy arg0-arg3 members of
restart_block. Use restart_block.nanosleep instead
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.232288779@linutronix.de>
Use the new kclock decoding function in clock_nanosleep_restart.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.131263211@linutronix.de>
Use the new kclock decoding function in clock_nanosleep and cleanup all
kclocks which use the default functions.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.034175556@linutronix.de>
New function to find the kclock for a given clockid.
Returns a pointer to clock_posix_cpu if clockid < 0. If clockid >=
MAXCLOCK or if the clock_getres pointer is not set it returns
NULL. For valid clocks it returns a pointer to the matching
posix_clock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <johnstul@us.ibm.com>
Acked-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.938447839@linutronix.de>
The CLOCK_DISPATCH() macro is a horrible magic. We call common
functions if a function pointer is not set. That's just backwards.
To support dynamic file decriptor based clocks we need to cleanup that
dispatch logic.
Create a k_clock struct clock_posix_cpu which has all the
posix-cpu-timer functions filled in. After the cleanup the functions
can be made static.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.841974553@linutronix.de>
Cosmetic. No functional change
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.745627057@linutronix.de>
Define the conditional nanosleep not supported error value outside of
do_posix_clock_nonanosleep(). Preparatory patch for further cleanups.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Richard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.643486574@linutronix.de>
Both settimeofday() and clock_settime() promise with a 'const'
attribute not to alter the arguments passed in. This patch adds the
missing 'const' attribute into the various kernel functions
implementing these calls.
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134417.545698637@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The only user for this hook was selinux. sysctl routes every call
through /proc/sys/. Selinux and other security modules use the file
system checks for sysctl too, so no need for this hook any more.
Signed-off-by: Lucian Adrian Grijincu <lucian.grijincu@gmail.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
The xtime/dotimer cleanup broke architectures which do not implement
clockevents. Time to send out another __do_IRQ threat.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Ingo Molnar <mingo@elte.hu>
Cc: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
LKML-Reference: <20110127145905.23248.30458.stgit@localhost>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
All callers of do_timer() are converted to xtime_update(). The only
users of xtime_lock are in kernel/time/. Make both local to
kernel/time/ and remove them from the global header files.
[ tglx: Reuse tick-internal.h instead of creating another local header
file. Massaged changelog ]
Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The hrtimer code accesses timekeeping variables under
xtime_lock. Provide a sensible accessor function and use it.
[ tglx: Removed the conditionals, unused variable, fixed codingstyle
and massaged changelog ]
Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
LKML-Reference: <20110127145905.23248.30458.stgit@localhost>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
do_timer() is primary timekeeping related. calc_global_load() is
called from do_timer() as well, but that's more for historical
reasons.
[ tglx: Fixed up the calc_global_load() reject andmassaged changelog ]
Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
LKML-Reference: <20110127145855.23248.56933.stgit@localhost>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
If it was not possible to enable watchdog for any cpu, switch
watchdog_enabled back to 0, because it's visible via
kernel.watchdog sysctl.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: <stable@kernel.org>
LKML-Reference: <1296230433-6261-2-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Passing nowatchdog to kernel disables 2 things: creation of
watchdog threads AND initialization of percpu watchdog_hrtimer.
As hrtimers are initialized only at boot it's not possible to
enable watchdog later - for me all watchdog threads started to
eat 100% of CPU time, but they could just crash.
Additionally, even if these threads would start properly,
watchdog_disable_all_cpus was guarded by no_watchdog check, so
you couldn't disable watchdog.
To fix this, remove no_watchdog variable and use already
existing watchdog_enabled variable.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
[ removed another no_watchdog instance ]
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: <stable@kernel.org>
LKML-Reference: <1296230433-6261-1-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The new code of commit cd7eab44e(genirq: Add IRQ affinity notifiers)
references irq_desc.affinity which fails to compile with
CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED=y.
Use irq_desc.irq_data.affinity instead.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Since check_prlimit_permission always fails in the case of SUID/GUID
processes, such processes are not able to read or set their own limits.
This commit changes this by assuming that process can always read/change
its own limits.
Signed-off-by: Kacper Kornet <kornet@camk.edu.pl>
Acked-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In current rtmutex, the pending owner may be boosted by the tasks
in the rtmutex's waitlist when the pending owner is deboosted
or a task in the waitlist is boosted. This boosting is unrelated,
because the pending owner does not really take the rtmutex.
It is not reasonable.
Example.
time1:
A(high prio) onwers the rtmutex.
B(mid prio) and C (low prio) in the waitlist.
time2
A release the lock, B becomes the pending owner
A(or other high prio task) continues to run. B's prio is lower
than A, so B is just queued at the runqueue.
time3
A or other high prio task sleeps, but we have passed some time
The B and C's prio are changed in the period (time2 ~ time3)
due to boosting or deboosting. Now C has the priority higher
than B. ***Is it reasonable that C has to boost B and help B to
get the rtmutex?
NO!! I think, it is unrelated/unneed boosting before B really
owns the rtmutex. We should give C a chance to beat B and
win the rtmutex.
This is the motivation of this patch. This patch *ensures*
only the top waiter or higher priority task can take the lock.
How?
1) we don't dequeue the top waiter when unlock, if the top waiter
is changed, the old top waiter will fail and go to sleep again.
2) when requiring lock, it will get the lock when the lock is not taken and:
there is no waiter OR higher priority than waiters OR it is top waiter.
3) In any time, the top waiter is changed, the top waiter will be woken up.
The algorithm is much simpler than before, no pending owner, no
boosting for pending owner.
Other advantage of this patch:
1) The states of a rtmutex are reduced a half, easier to read the code.
2) the codes become shorter.
3) top waiter is not dequeued until it really take the lock:
they will retain FIFO when it is stolen.
Not advantage nor disadvantage
1) Even we may wakeup multiple waiters(any time when top waiter changed),
we hardly cause "thundering herd",
the number of wokenup task is likely 1 or very little.
2) two APIs are changed.
rt_mutex_owner() will not return pending owner, it will return NULL when
the top waiter is going to take the lock.
rt_mutex_next_owner() always return the top waiter.
will not return NULL if we have waiters
because the top waiter is not dequeued.
I have fixed the code that use these APIs.
need updated after this patch is accepted
1) Document/*
2) the testcase scripts/rt-tester/t4-l2-pi-deboost.tst
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4D3012D5.4060709@cn.fujitsu.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Commit 927c7a9e92 ("perf: Fix race in callchains") introduced
a mismatch in the sizing of struct callchain_cpus_entries.
nr_cpu_ids must be used instead of num_possible_cpus(), or we
might get out of bound memory accesses on some machines.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Miller <davem@davemloft.net>
Cc: Stephane Eranian <eranian@google.com>
CC: stable@kernel.org
LKML-Reference: <1295980851.3588.351.camel@edumazet-laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix the build on UP.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Turner <pjt@google.com>
LKML-Reference: <20110122044852.102126037@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The BKL is going away, no need to test it any more.
I left the definitions of the test case numbers
in, so that the other tests do not get renumbered.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <1295993854-4971-19-git-send-email-arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
When a task is taken out of the fair class we must ensure the vruntime
is properly normalized because when we put it back in it will assume
to be normalized.
The case that goes wrong is when changing away from the fair class
while sleeping. Sleeping tasks have non-normalized vruntime in order
to make sleeper-fairness work. So treat the switch away from fair as a
wakeup and preserve the relative vruntime.
Also update sysrq-n to call the ->switch_{to,from} methods.
Reported-by: Onkalo Samu <samu.p.onkalo@nokia.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Since commit 48c5ccae88 (sched: Simplify cpu-hot-unplug task
migration) this should no longer happen, so remove the code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
softirq time in ksoftirqd context is not accounted in ns granularity
per cpu softirq stats, as we want that to be a part of ksoftirqd
exec_runtime.
Accounting them as softirq on /proc/stat separately.
Tested-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1292980144-28796-6-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
CONFIG_IRQ_TIME_ACCOUNTING adds ns granularity irq time on each CPU.
This info is already used in scheduler to do proper task chargeback
(earlier patches). This patch retro-fits this ns granularity
hardirq and softirq information to /proc/stat irq and softirq fields.
The update is still done on timer tick, where we look at accumulated
ns hardirq/softirq time and account the tick to user/system/irq/hardirq/guest
accordingly.
No new interface added.
Earlier versions looked at adding this as new fields in some /proc
files. This one seems to be the best in terms of impact to existing
apps, even though it has somewhat more kernel code than earlier versions.
Tested-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1292980144-28796-5-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Refactor account_system_time, to separate out the logic of
identifying the update needed and code that does actual update.
This is used by following patch for IRQ_TIME_ACCOUNTING,
which has different identification logic and same update logic.
Tested-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1292980144-28796-4-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add nsecs_to_cputime64 interface. This is used in following patches that
updates cpu irq stat based on ns granularity info in IRQ_TIME_ACCOUNTING.
Tested-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1292980144-28796-3-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cleanup patch, freeing up PF_KSOFTIRQD and use per_cpu ksoftirqd pointer
instead, as suggested by Eric Dumazet.
Tested-by: Shaun Ruffell <sruffell@digium.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1292980144-28796-2-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Since cfs->{load_stamp,load_last} are zero-initalized the initial load update
will consider the delta to be 'since the beginning of time'.
This results in a lot of pointless divisions to bring this large period to be
within the sysctl_sched_shares_window.
Fix this by initializing load_stamp to be 1 at cfs_rq initialization, this
allows for an initial load_stamp > load_last which then lets standard idle
truncation proceed.
We avoid spinning (and slightly improve consistency) by fixing delta to be
[period - 1] in this path resulting in a slightly more predictable shares ramp.
(Previously the amount of idle time preserved by the overflow would range between
[period/2,period-1].)
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110122044852.102126037@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Re-visiting this: Since update_cfs_shares will now only ever re-weight an
entity that is a relative parent of the current entity in enqueue_entity; we
can safely issue the account_entity_enqueue relative to that cfs_rq and avoid
the requirement for special handling of the enqueue case in update_cfs_shares.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110122044851.915214637@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The delta in clock_task is a more fair attribution of how much time a tg has
been contributing load to the current cpu.
While not really important it also means we're more in sync (by magnitude)
with respect to periodic updates (since __update_curr deltas are clock_task
based).
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110122044852.007092349@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Since updates are against an entity's queuing cfs_rq it's not possible to
enter update_cfs_{shares,load} with a NULL cfs_rq. (Indeed, update_cfs_load
would crash prior to the check if we did anyway since we load is examined
during the initializers).
Also, in the update_cfs_load case there's no point
in maintaining averages for rq->cfs_rq since we don't perform shares
distribution at that level -- NULL check is replaced accordingly.
Thanks to Dan Carpenter for pointing out the deference before NULL check.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110122044851.825284940@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
While care is taken around the zero-point in effective_load to not exceed
the instantaneous rq->weight, it's still possible (e.g. using wake_idx != 0)
for (load + effective_load) to underflow.
In this case the comparing the unsigned values can result in incorrect balanced
decisions.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110122044851.734245014@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
Input: wacom - pass touch resolution to clients through input_absinfo
Input: wacom - add 2 Bamboo Pen and touch models
Input: sysrq - ensure sysrq_enabled and __sysrq_enabled are consistent
Input: sparse-keymap - fix KEY_VSW handling in sparse_keymap_setup
Input: tegra-kbc - add tegra keyboard driver
Input: gpio_keys - switch to using request_any_context_irq
Input: serio - allow registered drivers to get status flag
Input: ct82710c - return proper error code for ct82c710_open
Input: bu21013_ts - added regulator support
Input: bu21013_ts - remove duplicate resolution parameters
Input: tnetv107x-ts - don't treat NULL clk as an error
Input: tnetv107x-keypad - don't treat NULL clk as an error
Fix up trivial conflicts in drivers/input/keyboard/Makefile due to
additions of tc3589x/Tegra drivers
The -rt patches change the console_semaphore to console_mutex. As a
result, a quite large chunk of the patches changes all
acquire/release_console_sem() to acquire/release_console_mutex()
This commit makes things use more neutral function names which dont make
implications about the underlying lock.
The only real change is the return value of console_trylock which is
inverted from try_acquire_console_sem()
This patch also paves the way to switching console_sem from a semaphore to
a mutex.
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: make console_trylock return 1 on success, per Geert]
Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Thomas Gleixner <tglx@tglx.de>
Cc: Greg KH <gregkh@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
perf tools: Fix time function double declaration with glibc
perf tools: Fix build by checking if extra warnings are supported
perf tools: Fix build when using gcc 3.4.6
perf tools: Add missing header, fixes build
perf tools: Fix 64 bit integer format strings
perf test: Fix build on older glibcs
perf: perf_event_exit_task_context: s/rcu_dereference/rcu_dereference_raw/
perf test: Use cpu_map->[cpu] when setting affinity
perf symbols: Fix annotation of thumb code
perf: Annotate cpuctx->ctx.mutex to avoid a lockdep splat
powerpc, perf: Fix frequency calculation for overflowing counters (FSL version)
perf: Fix perf_event_init_task()/perf_event_free_task() interaction
perf: Fix find_get_context() vs perf_event_exit_task() race
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched: Fix poor interactivity on UP systems due to group scheduler nice tune bug
Currently sysrq_enabled and __sysrq_enabled are initialised separately
and inconsistently, leading to sysrq being actually enabled by reported
as not enabled in sysfs. The first change to the sysfs configurable
synchronises these two:
static int __read_mostly sysrq_enabled = 1;
static int __sysrq_enabled;
Add a common define to carry the default for these preventing them becoming
out of sync again. Default this to 1 to mirror previous behaviour.
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Cc: stable@kernel.org
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
Michael Witten and Christian Kujau reported that the autogroup
scheduling feature hurts interactivity on their UP systems.
It turns out that this is an older bug in the group scheduling code,
and the wider appeal provided by the autogroup feature exposed it
more prominently.
When on UP with FAIR_GROUP_SCHED enabled, tune shares
only affect tg->shares, but is not reflected in
tg->se->load. The reason is that update_cfs_shares()
does nothing on UP.
So introduce update_cfs_shares() for UP && FAIR_GROUP_SCHED.
This issue was found when enable autogroup scheduling was enabled,
but it is an older bug that also exists on cgroup.cpu on UP.
Reported-and-Tested-by: Michael Witten <mfwitten@gmail.com>
Reported-and-Tested-by: Christian Kujau <christian@nerdbynature.de>
Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Acked-by: Pekka Enberg <penberg@kernel.org>
Acked-by: Mike Galbraith <efault@gmx.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <20110124073352.GA24186@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently only drivers that are built as modules have their versions
shown in /sys/module/<module_name>/version, but this information might
also be useful for built-in drivers as well. This especially important
for drivers that do not define any parameters - such drivers, if
built-in, are completely invisible from userspace.
This patch changes MODULE_VERSION() macro so that in case when we are
compiling built-in module, version information is stored in a separate
section. Kernel then uses this data to create 'version' sysfs attribute
in the same fashion it creates attributes for module parameters.
Signed-off-by: Dmitry Torokhov <dtor@vmware.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
When initiating I/O on a multiqueue and multi-IRQ device, we may want
to select a queue for which the response will be handled on the same
or a nearby CPU. This requires a reverse-map of IRQ affinity. Add a
notification mechanism to support this.
This is based closely on work by Thomas Gleixner <tglx@linutronix.de>.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Cc: linux-net-drivers@solarflare.com
Cc: Tom Herbert <therbert@google.com>
Cc: David Miller <davem@davemloft.net>
LKML-Reference: <1295470904.11126.84.camel@bwh-desktop>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* 'fixes-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
workqueue: note the nested NOT_RUNNING test in worker_clr_flags() isn't a noop
workqueue: relax lockdep annotation on flush_work()
In theory, almost every user of task->child->perf_event_ctxp[]
is wrong. find_get_context() can install the new context at any
moment, we need read_barrier_depends().
dbe08d82ce "perf: Fix
find_get_context() vs perf_event_exit_task() race" added
rcu_dereference() into perf_event_exit_task_context() to make
the precedent, but this makes __rcu_dereference_check() unhappy.
Use rcu_dereference_raw() to shut up the warning.
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: acme@redhat.com
Cc: paulus@samba.org
Cc: stern@rowland.harvard.edu
Cc: a.p.zijlstra@chello.nl
Cc: fweisbec@gmail.com
Cc: roland@redhat.com
Cc: prasad@linux.vnet.ibm.com
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
LKML-Reference: <20110121174547.GA8796@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Lockdep spotted:
loop_1b_instruc/1899 is trying to acquire lock:
(event_mutex){+.+.+.}, at: [<ffffffff810e1908>] perf_trace_init+0x3b/0x2f7
but task is already holding lock:
(&ctx->mutex){+.+.+.}, at: [<ffffffff810eb45b>] perf_event_init_context+0xc0/0x218
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #3 (&ctx->mutex){+.+.+.}:
-> #2 (cpu_hotplug.lock){+.+.+.}:
-> #1 (module_mutex){+.+...}:
-> #0 (event_mutex){+.+.+.}:
But because the deadlock would be cpuhotplug (cpu-event) vs fork
(task-event) it cannot, in fact, happen. We can annotate this by giving the
perf_event_context used for the cpuctx a different lock class from those
used by tasks.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
All architectures are finally converted. Remove the cruft.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Greg Ungerer <gerg@uclinux.org>
Cc: Michal Simek <monstr@monstr.eu>
Acked-by: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Chen Liqin <liqin.chen@sunplusct.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jeff Dike <jdike@addtoit.com>
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
smp: Allow on_each_cpu() to be called while early_boot_irqs_disabled status to init/main.c
lockdep: Move early boot local IRQ enable/disable status to init/main.c
* akpm:
kernel/smp.c: consolidate writes in smp_call_function_interrupt()
kernel/smp.c: fix smp_call_function_many() SMP race
memcg: correctly order reading PCG_USED and pc->mem_cgroup
backlight: fix 88pm860x_bl macro collision
drivers/leds/ledtrig-gpio.c: make output match input, tighten input checking
MAINTAINERS: update Atmel AT91 entry
mm: fix truncate_setsize() comment
memcg: fix rmdir, force_empty with THP
memcg: fix LRU accounting with THP
memcg: fix USED bit handling at uncharge in THP
memcg: modify accounting function for supporting THP better
fs/direct-io.c: don't try to allocate more than BIO_MAX_PAGES in a bio
mm: compaction: prevent division-by-zero during user-requested compaction
mm/vmscan.c: remove duplicate include of compaction.h
memblock: fix memblock_is_region_memory()
thp: keep highpte mapped until it is no longer needed
kconfig: rename CONFIG_EMBEDDED to CONFIG_EXPERT
We have to test the cpu mask in the interrupt handler before checking the
refs, otherwise we can start to follow an entry before its deleted and
find it partially initailzed for the next trip. Presently we also clear
the cpumask bit before executing the called function, which implies
getting write access to the line. After the function is called we then
decrement refs, and if they go to zero we then unlock the structure.
However, this implies getting write access to the call function data
before and after another the function is called. If we can assert that no
smp_call_function execution function is allowed to enable interrupts, then
we can move both writes to after the function is called, hopfully allowing
both writes with one cache line bounce.
On a 256 thread system with a kernel compiled for 1024 threads, the time
to execute testcase in the "smp_call_function_many race" changelog was
reduced by about 30-40ms out of about 545 ms.
I decided to keep this as WARN because its now a buggy function, even
though the stack trace is of no value -- a simple printk would give us the
information needed.
Raw data:
Without patch:
ipi_test startup took 1219366ns complete 539819014ns total 541038380ns
ipi_test startup took 1695754ns complete 543439872ns total 545135626ns
ipi_test startup took 7513568ns complete 539606362ns total 547119930ns
ipi_test startup took 13304064ns complete 533898562ns total 547202626ns
ipi_test startup took 8668192ns complete 544264074ns total 552932266ns
ipi_test startup took 4977626ns complete 548862684ns total 553840310ns
ipi_test startup took 2144486ns complete 541292318ns total 543436804ns
ipi_test startup took 21245824ns complete 530280180ns total 551526004ns
With patch:
ipi_test startup took 5961748ns complete 500859628ns total 506821376ns
ipi_test startup took 8975996ns complete 495098924ns total 504074920ns
ipi_test startup took 19797750ns complete 492204740ns total 512002490ns
ipi_test startup took 14824796ns complete 487495878ns total 502320674ns
ipi_test startup took 11514882ns complete 494439372ns total 505954254ns
ipi_test startup took 8288084ns complete 502570774ns total 510858858ns
ipi_test startup took 6789954ns complete 493388112ns total 500178066ns
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h> /* sched clock */
#define ITERATIONS 100
static void do_nothing_ipi(void *dummy)
{
}
static void do_ipis(struct work_struct *dummy)
{
int i;
for (i = 0; i < ITERATIONS; i++)
smp_call_function(do_nothing_ipi, NULL, 1);
printk(KERN_DEBUG "cpu %d finished\n", smp_processor_id());
}
static struct work_struct work[NR_CPUS];
static int __init testcase_init(void)
{
int cpu;
u64 start, started, done;
start = local_clock();
for_each_online_cpu(cpu) {
INIT_WORK(&work[cpu], do_ipis);
schedule_work_on(cpu, &work[cpu]);
}
started = local_clock();
for_each_online_cpu(cpu)
flush_work(&work[cpu]);
done = local_clock();
pr_info("ipi_test startup took %lldns complete %lldns total %lldns\n",
started-start, done-started, done-start);
return 0;
}
static void __exit testcase_exit(void)
{
}
module_init(testcase_init)
module_exit(testcase_exit)
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Anton Blanchard");
Signed-off-by: Milton Miller <miltonm@bga.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I noticed a failure where we hit the following WARN_ON in
generic_smp_call_function_interrupt:
if (!cpumask_test_and_clear_cpu(cpu, data->cpumask))
continue;
data->csd.func(data->csd.info);
refs = atomic_dec_return(&data->refs);
WARN_ON(refs < 0); <-------------------------
We atomically tested and cleared our bit in the cpumask, and yet the
number of cpus left (ie refs) was 0. How can this be?
It turns out commit 54fdade1c3
("generic-ipi: make struct call_function_data lockless") is at fault. It
removes locking from smp_call_function_many and in doing so creates a
rather complicated race.
The problem comes about because:
- The smp_call_function_many interrupt handler walks call_function.queue
without any locking.
- We reuse a percpu data structure in smp_call_function_many.
- We do not wait for any RCU grace period before starting the next
smp_call_function_many.
Imagine a scenario where CPU A does two smp_call_functions back to back,
and CPU B does an smp_call_function in between. We concentrate on how CPU
C handles the calls:
CPU A CPU B CPU C CPU D
smp_call_function
smp_call_function_interrupt
walks
call_function.queue sees
data from CPU A on list
smp_call_function
smp_call_function_interrupt
walks
call_function.queue sees
(stale) CPU A on list
smp_call_function int
clears last ref on A
list_del_rcu, unlock
smp_call_function reuses
percpu *data A
data->cpumask sees and
clears bit in cpumask
might be using old or new fn!
decrements refs below 0
set data->refs (too late!)
The important thing to note is since the interrupt handler walks a
potentially stale call_function.queue without any locking, then another
cpu can view the percpu *data structure at any time, even when the owner
is in the process of initialising it.
The following test case hits the WARN_ON 100% of the time on my PowerPC
box (having 128 threads does help :)
#include <linux/module.h>
#include <linux/init.h>
#define ITERATIONS 100
static void do_nothing_ipi(void *dummy)
{
}
static void do_ipis(struct work_struct *dummy)
{
int i;
for (i = 0; i < ITERATIONS; i++)
smp_call_function(do_nothing_ipi, NULL, 1);
printk(KERN_DEBUG "cpu %d finished\n", smp_processor_id());
}
static struct work_struct work[NR_CPUS];
static int __init testcase_init(void)
{
int cpu;
for_each_online_cpu(cpu) {
INIT_WORK(&work[cpu], do_ipis);
schedule_work_on(cpu, &work[cpu]);
}
return 0;
}
static void __exit testcase_exit(void)
{
}
module_init(testcase_init)
module_exit(testcase_exit)
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Anton Blanchard");
I tried to fix it by ordering the read and the write of ->cpumask and
->refs. In doing so I missed a critical case but Paul McKenney was able
to spot my bug thankfully :) To ensure we arent viewing previous
iterations the interrupt handler needs to read ->refs then ->cpumask then
->refs _again_.
Thanks to Milton Miller and Paul McKenney for helping to debug this issue.
[miltonm@bga.com: add WARN_ON and BUG_ON, remove extra read of refs before initial read of mask that doesn't help (also noted by Peter Zijlstra), adjust comments, hopefully clarify scenario ]
[miltonm@bga.com: remove excess tests]
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Milton Miller <miltonm@bga.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: <stable@kernel.org> [2.6.32+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched, cgroup: Use exit hook to avoid use-after-free crash
sched: Fix signed unsigned comparison in check_preempt_tick()
sched: Replace rq->bkl_count with rq->rq_sched_info.bkl_count
sched, autogroup: Fix CONFIG_RT_GROUP_SCHED sched_setscheduler() failure
sched: Display autogroup names in /proc/sched_debug
sched: Reinstate group names in /proc/sched_debug
sched: Update effective_load() to use global share weights
percpu may end up calling vfree() during early boot which in
turn may call on_each_cpu() for TLB flushes. The function of
on_each_cpu() can be done safely while IRQ is disabled during
early boot but it assumed that the function is always called
with local IRQ enabled which ended up enabling local IRQ
prematurely during boot and triggering a couple of warnings.
This patch updates on_each_cpu() and smp_call_function_many()
such on_each_cpu() can be used safely while
early_boot_irqs_disabled is set.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Pekka Enberg <penberg@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <20110120110713.GC6036@htj.dyndns.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reported-by: Ingo Molnar <mingo@elte.hu>
John Stultz