To finally fix the infamous leap second issue and other race windows
caused by functions which change the offsets between the various time
bases (CLOCK_MONOTONIC, CLOCK_REALTIME and CLOCK_BOOTTIME) we need a
function which atomically gets the current monotonic time and updates
the offsets of CLOCK_REALTIME and CLOCK_BOOTTIME with minimalistic
overhead. The previous patch which provides ktime_t offsets allows us
to make this function almost as cheap as ktime_get() which is going to
be replaced in hrtimer_interrupt().
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Prarit Bhargava <prarit@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Link: http://lkml.kernel.org/r/1341960205-56738-7-git-send-email-johnstul@us.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
clock_was_set() cannot be called from hard interrupt context because
it calls on_each_cpu().
For fixing the widely reported leap seconds issue it is necessary to
call it from hard interrupt context, i.e. the timer tick code, which
does the timekeeping updates.
Provide a new function which denotes it in the hrtimer cpu base
structure of the cpu on which it is called and raise the hrtimer
softirq. We then execute the clock_was_set() notificiation from
softirq context in run_hrtimer_softirq(). The hrtimer softirq is
rarely used, so polling the flag there is not a performance issue.
[ tglx: Made it depend on CONFIG_HIGH_RES_TIMERS. We really should get
rid of all this ifdeffery ASAP ]
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Reported-by: Jan Engelhardt <jengelh@inai.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Prarit Bhargava <prarit@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1341960205-56738-2-git-send-email-johnstul@us.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Fix 'make htmldocs' warnings:
Warning(/include/linux/hrtimer.h:153): No description found for parameter 'clockid'
Warning(/include/linux/device.h:604): Excess struct/union/enum/typedef member 'of_match' description in 'device'
Warning(/include/net/sock.h:349): Excess struct/union/enum/typedef member 'sk_rmem_alloc' description in 'sock'
Signed-off-by: Vitaliy Ivanov <vitalivanov@gmail.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The ordering of the clock bases is historical due to the
CLOCK_REALTIME and CLOCK_MONOTONIC constants. Now the hrtimer bases
have their own enumeration due to the gap between CLOCK_MONOTONIC and
CLOCK_BOOTTIME. So we can be more clever as most timers end up on the
CLOCK_MONOTONIC base due to the virtue of POSIX declaring that
relative CLOCK_REALTIME timers are not affected by time changes. In
desktop environments this is slowly changing as applications switch to
absolute timers, but I've observed empty CLOCK_REALTIME bases often
enough. There is no performance penalty or overhead when
CLOCK_REALTIME timers are active, but in case they are not we don't
skip over a full cache line.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Instead of iterating over all possible timer bases avoid it by marking
the active bases in the cpu base.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
In the HIGHRES=y case we access the members at the end of struct
hrtimer_cpu_base first and then the one at the beginning. Move the
hrtimer data to front, so we have linear progressing access.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Peter is concerned about the extra scan of CLOCK_REALTIME_COS in the
timer interrupt. Yes, I did not think about it, because the solution
was so elegant. I didn't like the extra list in timerfd when it was
proposed some time ago, but with a rcu based list the list walk it's
less horrible than the original global lock, which was held over the
list iteration.
Requested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Some applications must be aware of clock realtime being set
backward. A simple example is a clock applet which arms a timer for
the next minute display. If clock realtime is set backward then the
applet displays a stale time for the amount of time which the clock
was set backwards. Due to that applications poll the time because we
don't have an interface.
Extend the timerfd interface by adding a flag which puts the timer
onto a different internal realtime clock. All timers on this clock are
expired whenever the clock was set.
The timerfd core records the monotonic offset when the timer is
created. When the timer is armed, then the current offset is compared
to the previous recorded offset. When it has changed, then
timerfd_settime returns -ECANCELED. When a timer is read the offset is
compared and if it changed -ECANCELED returned to user space. Periodic
timers are not rearmed in the cancelation case.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <johnstul@us.ibm.com>
Cc: Chris Friesen <chris.friesen@genband.com>
Tested-by: Kay Sievers <kay.sievers@vrfy.org>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Davide Libenzi <davidel@xmailserver.org>
Reviewed-by: Alexander Shishkin <virtuoso@slind.org>
Link: http://lkml.kernel.org/r/%3Calpine.LFD.2.02.1104271359580.3323%40ionos%3E
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Make clock_was_set() unconditional and rename hres_timers_resume to
hrtimers_resume. This is a preparatory patch for hrtimers which are
cancelled when clock realtime was set.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We changed some of the state bits and combinations thereof over time,
but never updated the documentation.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
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>
Fix new kernel-doc notation warning in hrtimer.h:
Warning(include/linux/hrtimer.h:150): Excess struct/union/enum/typedef member 'first' description in 'hrtimer_clock_base'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Converts the hrtimer code to use the new timerlist infrastructure
Signed-off-by: John Stultz <john.stultz@linaro.org>
LKML Reference: <1290136329-18291-3-git-send-email-john.stultz@linaro.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
CC: Alessandro Zummo <a.zummo@towertech.it>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Richard Cochran <richardcochran@gmail.com>
The current version of schedule_hrtimeout() always uses the
monotonic clock. Some system calls such as mq_timedsend()
and mq_timedreceive(), however, require the use of the wall
clock due to the definition of the system call.
This patch provides the infrastructure to use schedule_hrtimeout()
with a CLOCK_REALTIME timer.
Signed-off-by: Carsten Emde <C.Emde@osadl.org>
Tested-by: Pradyumna Sampath <pradysam@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arjan van de Veen <arjan@infradead.org>
LKML-Reference: <20100402204331.167439615@osadl.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Convert locks which cannot be sleeping locks in preempt-rt to
raw_spinlocks.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
There is no reason to make timer_stats_hrtimer_set_start_info and
friends visible to the rest of the kernel. So move all of them to
hrtimer.c. Also make timer_stats_hrtimer_set_start_info a static
inline function so it gets inlined and we avoid another function call.
Based on a patch by Thomas Gleixner.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
LKML-Reference: <20091210095629.GC4144@osiris.boeblingen.de.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The hrtimer_interrupt hang logic adjusts min_delta_ns based on the
execution time of the hrtimer callbacks.
This is error-prone for virtual machines, where a guest vcpu can be
scheduled out during the execution of the callbacks (and the callbacks
themselves can do operations that translate to blocking operations in
the hypervisor), which in can lead to large min_delta_ns rendering the
system unusable.
Replace the current heuristics with something more reliable. Allow the
interrupt code to try 3 times to catch up with the lost time. If that
fails use the total time spent in the interrupt handler to defer the
next timer interrupt so the system can catch up with other things
which got delayed. Limit that deferment to 100ms.
The retry events and the maximum time spent in the interrupt handler
are recorded and exposed via /proc/timer_list
Inspired by a patch from Marcelo.
Reported-by: Michael Tokarev <mjt@tls.msk.ru>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Marcelo Tosatti <mtosatti@redhat.com>
Cc: kvm@vger.kernel.org
commit 507e1231 (timer stats: Optimize by adding quick check to avoid
function calls) introduced a regression in /proc/timer_list.
/proc/timer_list shows now
#0: <c27d46b0>, tick_sched_timer, S:01, <(null)>, /-1
instead of
#0: <c27d46b0>, tick_sched_timer, S:01, hrtimer_start, swapper/0
Revert the hrtimer quick check for now. The optimization needs more
thought, but this is neither 2.6.32-rc7 nor stable material.
[ tglx: - Removed unrelated changes from the original patch
- Prevent unneccesary call to timer_stats_update_stats
- massaged the changelog ]
Signed-off-by: Feng Tang <feng.tang@intel.com>
LKML-Reference: <alpine.LFD.2.00.0911181933540.24119@localhost.localdomain>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: stable@kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
It's unused, remove it.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <new-submission>
git commit 507e1231 "timer stats: Optimize by adding quick check to
avoid function calls" added one wrong check so that one unnecessary
function call isn't elimated.
time_stats_account_hrtimer() checks if timer->start_pid isn't
initialized in order to find out if timer_stats_update_stats() should
be called. However start_pid is initialized with -1 instead of 0, so
that the function call always happens.
Check timer->start_site like in timer_stats_account_timer() to fix
this.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
When the kernel is configured with CONFIG_TIMER_STATS but timer
stats are runtime disabled we still get calls to
__timer_stats_timer_set_start_info which initializes some
fields in the corresponding struct timer_list.
So add some quick checks in the the timer stats setup functions
to avoid function calls to __timer_stats_timer_set_start_info
when timer stats are disabled.
In an artificial workload that does nothing but playing ping
pong with a single tcp packet via loopback this decreases cpu
consumption by 1 - 1.5%.
This is part of a modified function trace output on SLES11:
perl-2497 [00] 28630647177732388 [+ 125]: sk_reset_timer <-tcp_v4_rcv
perl-2497 [00] 28630647177732513 [+ 125]: mod_timer <-sk_reset_timer
perl-2497 [00] 28630647177732638 [+ 125]: __timer_stats_timer_set_start_info <-mod_timer
perl-2497 [00] 28630647177732763 [+ 125]: __mod_timer <-mod_timer
perl-2497 [00] 28630647177732888 [+ 125]: __timer_stats_timer_set_start_info <-__mod_timer
perl-2497 [00] 28630647177733013 [+ 93]: lock_timer_base <-__mod_timer
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mustafa Mesanovic <mustafa.mesanovic@de.ibm.com>
Cc: Arjan van de Ven <arjan@infradead.org>
LKML-Reference: <20090623153811.GA4641@osiris.boeblingen.de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Arun R Bharadwaj <arun@linux.vnet.ibm.com> [2009-04-16 12:11:36]:
This patch creates a new framework for identifying cpu-pinned timers
and hrtimers.
This framework is needed because pinned timers are expected to fire on
the same CPU on which they are queued. So it is essential to identify
these and not migrate them, in case there are any.
For regular timers, the currently existing add_timer_on() can be used
queue pinned timers and subsequently mod_timer_pinned() can be used
to modify the 'expires' field.
For hrtimers, new modes HRTIMER_ABS_PINNED and HRTIMER_REL_PINNED are
added to queue cpu-pinned hrtimer.
[ tglx: use .._PINNED mode argument instead of creating tons of new
functions ]
Signed-off-by: Arun R Bharadwaj <arun@linux.vnet.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
It appears I inadvertly introduced rq->lock recursion to the
hrtimer_start() path when I delegated running already expired
timers to softirq context.
This patch fixes it by introducing a __hrtimer_start_range_ns()
method that will not use raise_softirq_irqoff() but
__raise_softirq_irqoff() which avoids the wakeup.
It then also changes schedule() to check for pending softirqs and
do the wakeup then, I'm not quite sure I like this last bit, nor
am I convinced its really needed.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
LKML-Reference: <20090313112301.096138802@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: cleanup, move all hrtimer processing into hardirq context
This is an attempt at removing some of the hrtimer complexity by
reducing the number of callback modes to 1.
This means that all hrtimer callback functions will be ran from HARD-irq
context.
I went through all the 30 odd hrtimer callback functions in the kernel
and saw only one that I'm not quite sure of, which is the one in
net/can/bcm.c - hence I'm CC-ing the folks responsible for that code.
Furthermore, the hrtimer core now calls callbacks directly with IRQs
disabled in case you try to enqueue an expired timer. If this timer is a
periodic timer (which should use hrtimer_forward() to advance its time)
then it might be possible to end up in an inf. recursive loop due to the
fact that hrtimer_forward() doesn't round up to the next timer
granularity, and therefore keeps on calling the callback - obviously
this needs a fix.
Aside from that, this seems to compile and actually boot on my dual core
test box - although I'm sure there are some bugs in, me not hitting any
makes me certain :-)
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix the hrtimer_add_expires_ns() function. It should take a 'u64 ns' argument,
but rather takes an 'unsigned long ns' argument - which might only be 32-bits.
On FRV, this results in the kernel locking up because hrtimer_forward() passes
the result of a 64-bit multiplication to this function, for which the compiler
discards the top 32-bits - something that didn't happen when ktime_add_ns() was
called directly.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
the timer peek function was on the wrong side of an ifdef,
breaking for the !HRTIMERs case. Just provide an empty inline
for that case since it doesn't make sense in that scenario.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Impact: per CPU hrtimers can be migrated from a dead CPU
The hrtimer code has no knowledge about per CPU timers, but we need to
prevent the migration of such timers and warn when such a timer is
active at migration time.
Explicitely mark the timers as per CPU and use a more understandable
mode descriptor for the interrupts safe unlocked callback mode, which
is used by hrtimer_sleeper and the scheduler code.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Impact: during migration active hrtimers can be seen as inactive
The migration code removes the hrtimers from the queues of the dead
CPU and sets the state temporary to INACTIVE. The enqueue code sets it
to ACTIVE/PENDING again.
Prevent that the wrong state can be seen by using a separate migration
state bit.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
reorder struct hrtimer to save 8 bytes on 64 bit builds when
CONFIG_TIMER_STATS selected. (also removes 8 bytes from signal_struct)
Signed-off-by: Richard Kennedy <richard@rsk.demon.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
hrtimer_clock_base::reprogram() also appears to never
have been used, so remove it.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra noticed this 8 months ago and I just noticed
it again.
hrtimer_clock_base::get_softirq_time() is currently unused
in the entire tree. In fact, looking at the logs, it appears
as if it was never used. Remove it.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
As part of going idle, we already look at the time of the next timer event to determine
which C-state to select etc.
This patch adds functionality that causes the timers that are past their
soft expire time, to fire at this time, before we calculate the next wakeup
time. This functionality will thus avoid wakeups by running timers before
going idle rather than specially waking up for it.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
this patch adds a _range version of hrtimer_start() so that range timers
can be created; the hrtimer_start() function is just a wrapper around this.
In addition, hrtimer_start_expires() will now preserve existing ranges.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
in some randconfig configurations, hrtimers are used even though
the hrtimer config if off; and it broke the build due to some of
the new functions being on the wrong side of the ifdef.
This patch moves the functions to the other side of the ifdef, fixing
the build bug.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
this patch turns hrtimers into range timers; they have 2 expire points
1) the soft expire point
2) the hard expire point
the kernel will do it's regular best effort attempt to get the timer run
at the hard expire point. However, if some other time fires after the soft
expire point, the kernel now has the freedom to fire this timer at this point,
and thus grouping the events and preventing a power-expensive wakeup in the
future.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
To catch code that still touches the "expires" memory directly, rename it
to have the compiler complain rather than get nasty, hard to explain,
runtime behavior
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
In order to be able to turn hrtimers into range based, we need to provide
accessor functions for getting to the "expires" ktime_t member of the
struct hrtimer.
This patch adds a set of accessors for this purpose:
* hrtimer_set_expires
* hrtimer_set_expires_tv64
* hrtimer_add_expires
* hrtimer_add_expires_ns
* hrtimer_get_expires
* hrtimer_get_expires_tv64
* hrtimer_get_expires_ns
* hrtimer_expires_remaining
* hrtimer_start_expires
No users of these new accessors are added yet; these follow in later patches.
Hopefully this patch can even go into 2.6.27-rc so that the conversions will
not have a bottleneck in -next
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
This patch adds a schedule_hrtimeout() function, to be used by select() and
poll() in a later patch. This function works similar to schedule_timeout()
in most ways, but takes a timespec rather than jiffies.
With a lot of contributions/fixes from Thomas
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Thomas Gleixner