fix __aggregate_redistribute_shares() related lockup reported by
David S. Miller.
The problem this code tries to solve is 'accurately' calculating the 'fair'
share of the group weight for each cpu. The current code falls back to a global
group rebalance in case the sched_domain's span it looks at has no shares, but
does have tasks.
The reason it gets stuck here, is because its inherently racy - if someone
steals the last task after we compute the agg->rq_weight, but before we
rebalance, we'll never get out of the loop.
We could of course go fix that, but while looking at this issue I found that
this 'fallback' wasn't nearly as rare as I'd hoped it to be. In fact its quite
common - and given it walks the whole machine, thats very bad.
The new approach is simple (why didn't I think of it before?), we set the
aggregate shares to the full task group weight, and each larger sched domain
that encounters an aggregate shares larger than the weight, clips it (it
already re-distributes anyway).
This nicely converges to the desired global picture where the sum of all
shares equals the task group weight.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
David Miller reported:
|--------------->
the following commit:
| commit 27ec440779
| Author: Ingo Molnar <mingo@elte.hu>
| Date: Thu Feb 28 21:00:21 2008 +0100
|
| sched: make cpu_clock() globally synchronous
|
| Alexey Zaytsev reported (and bisected) that the introduction of
| cpu_clock() in printk made the timestamps jump back and forth.
|
| Make cpu_clock() more reliable while still keeping it fast when it's
| called frequently.
|
| Signed-off-by: Ingo Molnar <mingo@elte.hu>
causes watchdog triggers when a cpu exits NOHZ state when it has been
there for >= the soft lockup threshold, for example here are some
messages from a 128 cpu Niagara2 box:
[ 168.106406] BUG: soft lockup - CPU#11 stuck for 128s! [dd:3239]
[ 168.989592] BUG: soft lockup - CPU#21 stuck for 86s! [swapper:0]
[ 168.999587] BUG: soft lockup - CPU#29 stuck for 91s! [make:4511]
[ 168.999615] BUG: soft lockup - CPU#2 stuck for 85s! [swapper:0]
[ 169.020514] BUG: soft lockup - CPU#37 stuck for 91s! [swapper:0]
[ 169.020514] BUG: soft lockup - CPU#45 stuck for 91s! [sh:4515]
[ 169.020515] BUG: soft lockup - CPU#69 stuck for 92s! [swapper:0]
[ 169.020515] BUG: soft lockup - CPU#77 stuck for 92s! [swapper:0]
[ 169.020515] BUG: soft lockup - CPU#61 stuck for 92s! [swapper:0]
[ 169.112554] BUG: soft lockup - CPU#85 stuck for 92s! [swapper:0]
[ 169.112554] BUG: soft lockup - CPU#101 stuck for 92s! [swapper:0]
[ 169.112554] BUG: soft lockup - CPU#109 stuck for 92s! [swapper:0]
[ 169.112554] BUG: soft lockup - CPU#117 stuck for 92s! [swapper:0]
[ 169.171483] BUG: soft lockup - CPU#40 stuck for 80s! [dd:3239]
[ 169.331483] BUG: soft lockup - CPU#13 stuck for 86s! [swapper:0]
[ 169.351500] BUG: soft lockup - CPU#43 stuck for 101s! [dd:3239]
[ 169.531482] BUG: soft lockup - CPU#9 stuck for 129s! [mkdir:4565]
[ 169.595754] BUG: soft lockup - CPU#20 stuck for 93s! [swapper:0]
[ 169.626787] BUG: soft lockup - CPU#52 stuck for 93s! [swapper:0]
[ 169.626787] BUG: soft lockup - CPU#84 stuck for 92s! [swapper:0]
[ 169.636812] BUG: soft lockup - CPU#116 stuck for 94s! [swapper:0]
It's simple enough to trigger this by doing a 10 minute sleep after a
fresh bootup then starting a parallel kernel build.
I suspect this might be reintroducing a problem we've had and fixed
before, see the thread:
http://marc.info/?l=linux-kernel&m=119546414004065&w=2
<---------------|
touch the softlockup watchdog when exiting NOHZ state - we are
obviously not locked up.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
A recent change prevents SGI Altix from booting.
This patch fixes the problem.
The regresson was introduced in commit 434d53b00d
Signed-off-by: Russ Anderson <rja@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
iwlwifi: Fix built-in compilation of iwlcore
net: Unexport move_addr_to_{kernel,user}
rt2x00: Select LEDS_CLASS.
iwlwifi: Select LEDS_CLASS.
leds: Do not guard NEW_LEDS with HAS_IOMEM
[IPSEC]: Fix catch-22 with algorithm IDs above 31
time: Export set_normalized_timespec.
tcp: Make use of before macro in tcp_input.c
hamradio: Remove unneeded and deprecated cli()/sti() calls in dmascc.c
[NETNS]: Remove empty ->init callback.
[DCCP]: Convert do_gettimeofday() to getnstimeofday().
[NETNS]: Don't initialize err variable twice.
[NETNS]: The ip6_fib_timer can work with garbage on net namespace stop.
[IPV4]: Convert do_gettimeofday() to getnstimeofday().
[IPV4]: Make icmp_sk_init() static.
[IPV6]: Make struct ip6_prohibit_entry_template static.
tcp: Trivial fix to correct function name in a comment in net/ipv4/tcp.c
[NET]: Expose netdevice dev_id through sysfs
skbuff: fix missing kernel-doc notation
[ROSE]: Fix soft lockup wrt. rose_node_list_lock
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
[PATCH] get rid of __exit_files(), __exit_fs() and __put_fs_struct()
[PATCH] proc_readfd_common() race fix
[PATCH] double-free of inode on alloc_file() failure exit in create_write_pipe()
[PATCH] teach seq_file to discard entries
[PATCH] umount_tree() will unhash everything itself
[PATCH] get rid of more nameidata passing in namespace.c
[PATCH] switch a bunch of LSM hooks from nameidata to path
[PATCH] lock exclusively in collect_mounts() and drop_collected_mounts()
[PATCH] move a bunch of declarations to fs/internal.h
The only reason to have separated __...() for those was to keep them inlined
for local users in exit.c. Since Alexey removed the inline on those, there's
no reason whatsoever to keep them around; just collapse with normal variants.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Add missing kernel-doc in kernel/sched.c:
Warning(linux-2.6.25-git3//kernel/sched.c:7044): No description found for parameter 'span'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Sorry I have just realized set_normalized_timespec() (used in
timespec_sub()) is not exported, and link will fail because of it...
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/juhl/trivial: (24 commits)
DOC: A couple corrections and clarifications in USB doc.
Generate a slightly more informative error msg for bad HZ
fix typo "is" -> "if" in Makefile
ext*: spelling fix prefered -> preferred
DOCUMENTATION: Use newer DEFINE_SPINLOCK macro in docs.
KEYS: Fix the comment to match the file name in rxrpc-type.h.
RAID: remove trailing space from printk line
DMA engine: typo fixes
Remove unused MAX_NODES_SHIFT
MAINTAINERS: Clarify access to OCFS2 development mailing list.
V4L: Storage class should be before const qualifier (sn9c102)
V4L: Storage class should be before const qualifier
sonypi: Storage class should be before const qualifier
intel_menlow: Storage class should be before const qualifier
DVB: Storage class should be before const qualifier
arm: Storage class should be before const qualifier
ALSA: Storage class should be before const qualifier
acpi: Storage class should be before const qualifier
firmware_sample_driver.c: fix coding style
MAINTAINERS: Add ati_remote2 driver
...
Fixed up trivial conflicts in firmware_sample_driver.c
This adds support for PTRACE_GETSIGINFO and PTRACE_SETSIGINFO in
compat_ptrace_request. It relies on existing arch definitions for
copy_siginfo_to_user32 and copy_siginfo_from_user32.
On powerpc, this fixes a longstanding regression of 32-bit ptrace
calls on 64-bit kernels vs native calls (64-bit calls or 32-bit
kernels). This can be seen in a 32-bit call using PTRACE_GETSIGINFO
to examine e.g. siginfo_t.si_addr from a signal that sets it.
(This was broken as of 2.6.24 and, I presume, many or all prior versions.)
Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/tglx/linux-2.6-hrt:
hrtimer: optimize the softirq time optimization
hrtimer: reduce calls to hrtimer_get_softirq_time()
clockevents: fix typo in tick-broadcast.c
jiffies: add time_is_after_jiffies and others which compare with jiffies
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel: (62 commits)
sched: build fix
sched: better rt-group documentation
sched: features fix
sched: /debug/sched_features
sched: add SCHED_FEAT_DEADLINE
sched: debug: show a weight tree
sched: fair: weight calculations
sched: fair-group: de-couple load-balancing from the rb-trees
sched: fair-group scheduling vs latency
sched: rt-group: optimize dequeue_rt_stack
sched: debug: add some debug code to handle the full hierarchy
sched: fair-group: SMP-nice for group scheduling
sched, cpuset: customize sched domains, core
sched, cpuset: customize sched domains, docs
sched: prepatory code movement
sched: rt: multi level group constraints
sched: task_group hierarchy
sched: fix the task_group hierarchy for UID grouping
sched: allow the group scheduler to have multiple levels
sched: mix tasks and groups
...
These are small cleanups all over the tree.
Trivial style and comment changes to
fs/select.c, kernel/signal.c, kernel/stop_machine.c & mm/pdflush.c
Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Jesper Juhl <jesper.juhl@gmail.com>
The previous optimization did not take the case into account where a
clock provides its own softirq_get_time() function.
Check for the availablitiy of the clock get time function first and
then check if we need to retrieve the time for both clocks via
hrtimer_softirq_gettime() to avoid a double evaluation of time in that
case as well.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
It seems that hrtimer_run_queues() is calling hrtimer_get_softirq_time() more
often than it needs to. This can cause frequent contention on systems with
large numbers of processors/cores.
With this patch, hrtimer_run_queues only calls hrtimer_get_softirq_time() if
there is a pending timer in one of the hrtimer bases, and only once.
This also combines hrtimer_run_queues() and the inline run_hrtimer_queue()
into one function.
[ tglx@linutronix.de: coding style ]
Signed-off-by: Dimitri Sivanich <sivanich@sgi.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
braodcast -> broadcast
Signed-off-by: Glauber Costa <gcosta@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Done per Linus' request and suggestions. Linus has explained that
better than I'll be able to explain:
On Thu, Mar 27, 2008 at 10:12:10AM -0700, Linus Torvalds wrote:
> Actually, before we go any further, there might be a less intrusive
> alternative: add just a couple of flags to the resource flags field (we
> still have something like 8 unused bits on 32-bit), and use those to
> implement a generic "resource_alignment()" routine.
>
> Two flags would do it:
>
> - IORESOURCE_SIZEALIGN: size indicates alignment (regular PCI device
> resources)
>
> - IORESOURCE_STARTALIGN: start field is alignment (PCI bus resources
> during probing)
>
> and then the case of both flags zero (or both bits set) would actually be
> "invalid", and we would also clear the IORESOURCE_STARTALIGN flag when we
> actually allocate the resource (so that we don't use the "start" field as
> alignment incorrectly when it no longer indicates alignment).
>
> That wouldn't be totally generic, but it would have the nice property of
> automatically at least add sanity checking for that whole "res->start has
> the odd meaning of 'alignment' during probing" and remove the need for a
> new field, and it would allow us to have a generic "resource_alignment()"
> routine that just gets a resource pointer.
Besides, I removed IORESOURCE_BUS_HAS_VGA flag which was unused for ages.
Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Gary Hade <garyhade@us.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
provide a text based interface to the scheduler features; this saves the
'user' from setting bits using decimal arithmetic.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In order to level the hierarchy, we need to calculate load based on the
root view. That is, each task's load is in the same unit.
A
/ \
B 1
/ \
2 3
To compute 1's load we do:
weight(1)
--------------
rq_weight(A)
To compute 2's load we do:
weight(2) weight(B)
------------ * -----------
rq_weight(B) rw_weight(A)
This yields load fractions in comparable units.
The consequence is that it changes virtual time. We used to have:
time_{i}
vtime_{i} = ------------
weight_{i}
vtime = \Sum vtime_{i} = time / rq_weight.
But with the new way of load calculation we get that vtime equals time.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
De-couple load-balancing from the rb-trees, so that I can change their
organization.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently FAIR_GROUP sched grows the scheduler latency outside of
sysctl_sched_latency, invert this so it stays within.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that the group hierarchy can have an arbitrary depth the O(n^2) nature
of RT task dequeues will really hurt. Optimize this by providing space to
store the tree path, so we can walk it the other way.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add some extra debug output so we can get a better overview of the
full hierarchy.
We print the cgroup path after each cfs_rq, so we can see what group
we're looking at.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Implement SMP nice support for the full group hierarchy.
On each load-balance action, compile a sched_domain wide view of the full
task_group tree. We compute the domain wide view when walking down the
hierarchy, and readjust the weights when walking back up.
After collecting and readjusting the domain wide view, we try to balance the
tasks within the task_groups. The current approach is a naively balance each
task group until we've moved the targeted amount of load.
Inspired by Srivatsa Vaddsgiri's previous code and Abhishek Chandra's H-SMP
paper.
XXX: there will be some numerical issues due to the limited nature of
SCHED_LOAD_SCALE wrt to representing a task_groups influence on the
total weight. When the tree is deep enough, or the task weight small
enough, we'll run out of bits.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
CC: Abhishek Chandra <chandra@cs.umn.edu>
CC: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
[rebased for sched-devel/latest]
- Add a new cpuset file, having levels:
sched_relax_domain_level
- Modify partition_sched_domains() and build_sched_domains()
to take attributes parameter passed from cpuset.
- Fill newidle_idx for node domains which currently unused but
might be required if sched_relax_domain_level become higher.
- We can change the default level by boot option 'relax_domain_level='.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add the full parent<->child relation thing into task_groups as well.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
UID grouping doesn't actually have a task_group representing the root of
the task_group tree. Add one.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch makes the group scheduler multi hierarchy aware.
[a.p.zijlstra@chello.nl: rt-parts and assorted fixes]
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch allows tasks and groups to exist in the same cfs_rq. With this
change the CFS group scheduling follows a 1/(M+N) model from a 1/(1+N)
fairness model where M tasks and N groups exist at the cfs_rq level.
[a.p.zijlstra@chello.nl: rt bits and assorted fixes]
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add a new function that accepts a pointer to the "newly allowed cpus"
cpumask argument.
int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask)
The current set_cpus_allowed() function is modified to use the above
but this does not result in an ABI change. And with some compiler
optimization help, it may not introduce any additional overhead.
Additionally, to enforce the read only nature of the new_mask arg, the
"const" property is migrated to sub-functions called by set_cpus_allowed.
This silences compiler warnings.
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Move the setting of nr_cpu_ids from sched_init() to start_kernel()
so that it's available as early as possible.
Note that an arch has the option of setting it even earlier if need be,
but it should not result in a different value than the setup_nr_cpu_ids()
function.
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Remove another cpumask_t variable from stack that was missed in the
last kernel_sched_c updates.
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Cleaned up references to cpumask_scnprintf() and added new
cpulist_scnprintf() interfaces where appropriate.
* Fix some small bugs (or code efficiency improvments) for various uses
of cpumask_scnprintf.
* Clean up some checkpatch errors.
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Remove empty cpumask_t (and all non-zero/non-null) variables
in SD_*_INIT macros. Use memset(0) to clear. Also, don't
inline the initializer functions to save on stack space in
build_sched_domains().
* Merge change to include/linux/topology.h that uses the new
node_to_cpumask_ptr function in the nr_cpus_node macro into
this patch.
Depends on:
[mm-patch]: asm-generic-add-node_to_cpumask_ptr-macro.patch
[sched-devel]: sched: add new set_cpus_allowed_ptr function
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Use new node_to_cpumask_ptr. This creates a pointer to the
cpumask for a given node. This definition is in mm patch:
asm-generic-add-node_to_cpumask_ptr-macro.patch
* Use new set_cpus_allowed_ptr function.
Depends on:
[mm-patch]: asm-generic-add-node_to_cpumask_ptr-macro.patch
[sched-devel]: sched: add new set_cpus_allowed_ptr function
[x86/latest]: x86: add cpus_scnprintf function
Cc: Greg Kroah-Hartman <gregkh@suse.de>
Cc: Greg Banks <gnb@melbourne.sgi.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Modify sched_affinity functions to pass cpumask_t variables by reference
instead of by value.
* Use new set_cpus_allowed_ptr function.
Depends on:
[sched-devel]: sched: add new set_cpus_allowed_ptr function
Cc: Paul Jackson <pj@sgi.com>
Cc: Cliff Wickman <cpw@sgi.com>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Modify cpuset_cpus_allowed to return the currently allowed cpuset
via a pointer argument instead of as the function return value.
* Use new set_cpus_allowed_ptr function.
* Cleanup CPU_MASK_ALL and NODE_MASK_ALL uses.
Depends on:
[sched-devel]: sched: add new set_cpus_allowed_ptr function
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Use new set_cpus_allowed_ptr() function added by previous patch,
which instead of passing the "newly allowed cpus" cpumask_t arg
by value, pass it by pointer:
-int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
+int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask)
* Modify CPU_MASK_ALL
Depends on:
[sched-devel]: sched: add new set_cpus_allowed_ptr function
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Change fixed size arrays to per_cpu variables or dynamically allocated
arrays in sched_init() and sched_init_smp().
(1) static struct sched_entity *init_sched_entity_p[NR_CPUS];
(1) static struct cfs_rq *init_cfs_rq_p[NR_CPUS];
(1) static struct sched_rt_entity *init_sched_rt_entity_p[NR_CPUS];
(1) static struct rt_rq *init_rt_rq_p[NR_CPUS];
static struct sched_group **sched_group_nodes_bycpu[NR_CPUS];
(1) - these arrays are allocated via alloc_bootmem_low()
* Change sched_domain_debug_one() to use cpulist_scnprintf instead of
cpumask_scnprintf. This reduces the output buffer required and improves
readability when large NR_CPU count machines arrive.
* In sched_create_group() we allocate new arrays based on nr_cpu_ids.
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Replace usages of CPU_MASK_NONE, CPU_MASK_ALL, NODE_MASK_NONE,
NODE_MASK_ALL to reduce stack requirements for large NR_CPUS
and MAXNODES counts.
* In some cases, the cpumask variable was initialized but then overwritten
with another value. This is the case for changes like this:
- cpumask_t oldmask = CPU_MASK_ALL;
+ cpumask_t oldmask;
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently the schedstats implementation does not allow the statistics
to be reset. This patch aims to allow that.
echo 0 > cpuacct.usage
resets the usage. Any other value is not allowed and returns -EINVAL.
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Change the variable names to the common convention for the cpuacct
subsystem.
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
I noticed this when looking at an openswan issue. Openswan (ab?)uses the
tasklet API to defer processing of packets in some situations, with one
packet per tasklet_action(). I started noticing sequences of
backwards-ordered sequence numbers coming over the wire, since new tasklets
are always queued at the head of the list but processed sequentially.
Convert it to instead append new entries to the tail of the list. As an
extra bonus, the splicing code in takeover_tasklets() no longer has to
iterate over the list.
Signed-off-by: Olof Johansson <olof@lixom.net>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently the rt group scheduling does a per cpu runtime limit, however
the rt load balancer makes no guarantees about an equal spread of real-
time tasks, just that at any one time, the highest priority tasks run.
Solve this by making the runtime limit a global property by borrowing
excessive runtime from the other cpus once the local limit runs out.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Various SMP balancing algorithms require that the bandwidth period
run in sync.
Possible improvements are moving the rt_bandwidth thing into root_domain
and keeping a span per rt_bandwidth which marks throttled cpus.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Balbir Singh reported:
> 1:mon> t
> [c0000000e7677da0] c000000000067de0 .sys_sched_yield+0x6c/0xbc
> [c0000000e7677e30] c000000000008748 syscall_exit+0x0/0x40
> --- Exception: c01 (System Call) at 00000400001d09e4
> SP (4000664cb10) is in userspace
> 1:mon> r
> cpu 0x1: Vector: 300 (Data Access) at [c0000000e7677aa0]
> pc: c000000000068e50: .yield_task_fair+0x94/0xc4
> lr: c000000000067de0: .sys_sched_yield+0x6c/0xbc
the check that should have avoided that is:
/*
* Are we the only task in the tree?
*/
if (unlikely(rq->load.weight == curr->se.load.weight))
return;
But I guess that overlooks rt tasks, they also increase the load.
So I guess something like this ought to fix it..
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There is no need to loop any longer when 'same == 0'.
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
turn off sync wakeups by default. They are not needed anymore - the
buddy logic should be smart enough to keep the system from
overscheduling.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The wakeup buddy logic didn't use the same wakeup granularity logic as the
wakeup preemption did, this might cause the ->next buddy to be selected past
the point where we would have preempted had the task been a single running
instance.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When using CONFIG_NO_HZ, rq->tick_timestamp is not updated every TICK_NSEC.
We check that the number of skipped ticks matches the clock jump seen in
__update_rq_clock().
Signed-off-by: Guillaume Chazarain <guichaz@yahoo.fr>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
kernel/sched.c:506: erreur: implicit declaration of function tick_get_tick_sched
kernel/sched.c:506: erreur: invalid type argument of ->
kernel/sched.c:506: erreur: NOHZ_MODE_INACTIVE undeclared (first use in this function)
kernel/sched.c:506: erreur: (Each undeclared identifier is reported only once
kernel/sched.c:506: erreur: for each function it appears in.)
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Alexey Zaytsev reported (and bisected) that the introduction of
cpu_clock() in printk made the timestamps jump back and forth.
Make cpu_clock() more reliable while still keeping it fast when it's
called frequently.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Split the FPU save area from the task struct. This allows easy migration
of FPU context, and it's generally cleaner. It also allows the following
two optimizations:
1) only allocate when the application actually uses FPU, so in the first
lazy FPU trap. This could save memory for non-fpu using apps. Next patch
does this lazy allocation.
2) allocate the right size for the actual cpu rather than 512 bytes always.
Patches enabling xsave/xrstor support (coming shortly) will take advantage
of this.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We already catch most of the TSC problems by sanity checks, but there
is a subtle bug which has been in the code forever. This can cause
time jumps in the range of hours.
This was reported in:
http://lkml.org/lkml/2007/8/23/96
and
http://lkml.org/lkml/2008/3/31/23
I was able to reproduce the problem with a gettimeofday loop test on a
dual core and a quad core machine which both have sychronized
TSCs. The TSCs seems not to be perfectly in sync though, but the
kernel is not able to detect the slight delta in the sync check. Still
there exists an extremly small window where this delta can be observed
with a real big time jump. So far I was only able to reproduce this
with the vsyscall gettimeofday implementation, but in theory this
might be observable with the syscall based version as well.
CPU 0 updates the clock source variables under xtime/vyscall lock and
CPU1, where the TSC is slighty behind CPU0, is reading the time right
after the seqlock was unlocked.
The clocksource reference data was updated with the TSC from CPU0 and
the value which is read from TSC on CPU1 is less than the reference
data. This results in a huge delta value due to the unsigned
subtraction of the TSC value and the reference value. This algorithm
can not be changed due to the support of wrapping clock sources like
pm timer.
The huge delta is converted to nanoseconds and added to xtime, which
is then observable by the caller. The next gettimeofday call on CPU1
will show the correct time again as now the TSC has advanced above the
reference value.
To prevent this TSC specific wreckage we need to compare the TSC value
against the reference value and return the latter when it is larger
than the actual TSC value.
I pondered to mark the TSC unstable when the readout is smaller than
the reference value, but this would render an otherwise good and fast
clocksource unusable without a real good reason.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds prctl commands that make it possible
to deny the execution of timestamp counters in userspace.
If this is not implemented on a specific architecture,
prctl will return -EINVAL.
ned-off-by: Erik Bosman <ejbosman@cs.vu.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Rename the se_str and se_rule audit fields elements to
lsm_str and lsm_rule to avoid confusion.
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Ahmed S. Darwish <darwish.07@gmail.com>
Acked-by: James Morris <jmorris@namei.org>
Setup the new Audit LSM hooks for SELinux.
Remove the now redundant exported SELinux Audit interface.
Audit: Export 'audit_krule' and 'audit_field' to the public
since their internals are needed by the implementation of the
new LSM hook 'audit_rule_known'.
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Ahmed S. Darwish <darwish.07@gmail.com>
Acked-by: James Morris <jmorris@namei.org>
Convert Audit to use the new LSM Audit hooks instead of
the exported SELinux interface.
Basically, use:
security_audit_rule_init
secuirty_audit_rule_free
security_audit_rule_known
security_audit_rule_match
instad of (respectively) :
selinux_audit_rule_init
selinux_audit_rule_free
audit_rule_has_selinux
selinux_audit_rule_match
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Ahmed S. Darwish <darwish.07@gmail.com>
Acked-by: James Morris <jmorris@namei.org>
Stop using the following exported SELinux interfaces:
selinux_get_inode_sid(inode, sid)
selinux_get_ipc_sid(ipcp, sid)
selinux_get_task_sid(tsk, sid)
selinux_sid_to_string(sid, ctx, len)
kfree(ctx)
and use following generic LSM equivalents respectively:
security_inode_getsecid(inode, secid)
security_ipc_getsecid*(ipcp, secid)
security_task_getsecid(tsk, secid)
security_sid_to_secctx(sid, ctx, len)
security_release_secctx(ctx, len)
Call security_release_secctx only if security_secid_to_secctx
succeeded.
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Ahmed S. Darwish <darwish.07@gmail.com>
Acked-by: James Morris <jmorris@namei.org>
Reviewed-by: Paul Moore <paul.moore@hp.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/tglx/linux-2.6-hrt:
clocksource: make clocksource watchdog cycle through online CPUs
Documentation: move timer related documentation to a single place
clockevents: optimise tick_nohz_stop_sched_tick() a bit
locking: remove unused double_spin_lock()
hrtimers: simplify lockdep handling
timers: simplify lockdep handling
posix-timers: fix shadowed variables
timer_list: add annotations to workqueue.c
hrtimer: use nanosleep specific restart_block fields
hrtimer: add nanosleep specific restart_block member
* 'semaphore' of git://git.kernel.org/pub/scm/linux/kernel/git/willy/misc:
Remove DEBUG_SEMAPHORE from Kconfig
Improve semaphore documentation
Simplify semaphore implementation
Add down_timeout and change ACPI to use it
Introduce down_killable()
Generic semaphore implementation
Add semaphore.h to kernel_lock.c
Fix quota.h includes
* 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6: (36 commits)
[S390] Remove code duplication from monreader / dcssblk.
[S390] kernel: show last breaking-event-address on oops
[S390] lowcore: Change type of lowcores softirq_pending to __u32.
[S390] zcrypt: Comments and kernel-doc cleanup
[S390] uaccess: Always access the correct address space.
[S390] Fix a lot of sparse warnings.
[S390] Convert s390 to GENERIC_CLOCKEVENTS.
[S390] genirq/clockevents: move irq affinity prototypes/inlines to interrupt.h
[S390] Convert monitor calls to function calls.
[S390] qdio (new feature): enhancing info-retrieval from QDIO-adapters
[S390] replace remaining __FUNCTION__ occurrences
[S390] remove redundant display of free swap space in show_mem()
[S390] qdio: remove outdated developerworks link.
[S390] Add debug_register_mode() function to debug feature API
[S390] crypto: use more descriptive function names for init/exit routines.
[S390] switch sched_clock to store-clock-extended.
[S390] zcrypt: add support for large random numbers
[S390] hw_random: allow rng_dev_read() to return hardware errors.
[S390] Vertical cpu management.
[S390] cpu topology support for s390.
...
This breaks out the ptrace handling from get_signal_to_deliver into a
new subroutine. The actual code there doesn't change, and it gets
inlined into nearly identical compiled code. This makes the function
substantially shorter and thus easier to read, and it nicely isolates
the ptrace magic.
Signed-off-by: Roland McGrath <roland@redhat.com>
Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When I ran a test program to fork mass processes and at the same time
'cat /cgroup/tasks', I got the following oops:
------------[ cut here ]------------
kernel BUG at lib/list_debug.c:72!
invalid opcode: 0000 [#1] SMP
Pid: 4178, comm: a.out Not tainted (2.6.25-rc9 #72)
...
Call Trace:
[<c044a5f9>] ? cgroup_exit+0x55/0x94
[<c0427acf>] ? do_exit+0x217/0x5ba
[<c0427ed7>] ? do_group_exit+0.65/0x7c
[<c0427efd>] ? sys_exit_group+0xf/0x11
[<c0404842>] ? syscall_call+0x7/0xb
[<c05e0000>] ? init_cyrix+0x2fa/0x479
...
EIP: [<c04df671>] list_del+0x35/0x53 SS:ESP 0068:ebc7df4
---[ end trace caffb7332252612b ]---
Fixing recursive fault but reboot is needed!
After digging into the code and debugging, I finlly found out a race
situation:
do_exit()
->cgroup_exit()
->if (!list_empty(&tsk->cg_list))
list_del(&tsk->cg_list);
cgroup_iter_start()
->cgroup_enable_task_cg_list()
->list_add(&tsk->cg_list, ..);
In this case the list won't be deleted though the process has exited.
We got two bug reports in the past, which seem to be the same bug as
this one:
http://lkml.org/lkml/2008/3/5/332http://lkml.org/lkml/2007/10/17/224
Actually sometimes I got oops on list_del, sometimes oops on list_add.
And I can change my test program a bit to trigger other oops.
The patch has been tested both on x86_32 and x86_64.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: Paul Menage <menage@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On the ppc 4xx architecture the instruction cache must be flushed as
well as the data cache. This patch just makes it generic for all
architectures where CACHE_FLUSH_IS_SAFE is set to 1.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix the problem of protecting the kgdb handle_exception exit
which had an NMI race condition, while trying to restore
normal system operation.
There was a small window after the master processor sets cpu_in_debug
to zero but before it has set kgdb_active to zero where a
non-master processor in an SMP system could receive an NMI and
re-enter the kgdb_wait() loop.
As long as the master processor sets the cpu_in_debug before sending
the cpu roundup the cpu_in_debug variable can also be used to guard
against the race condition.
The kgdb_wait() function no longer needs to check
kgdb_active because it is done in the arch specific code
and handled along with the nmi traps at the low level.
This also allows kgdb_wait() to exit correctly if it was
entered for some unknown reason due to a spurious NMI that
could not be handled by the arch specific code.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
kgdb core fixes:
- Check to see that mm->mmap_cache is not null before calling
flush_cache_range(), else on arch=ARM it will cause a fatal
fault.
- Breakpoints should only be restored if they are in the BP_ACTIVE
state.
- Fix a typo in comments to "kgdb_register_io_module"
x86 kgdb fixes:
- Fix the x86 arch handler such that on a kill or detach that the
appropriate cleanup on the single stepping flags gets run.
- Add in the DIE_NMIWATCHDOG call for x86_64
- Touch the nmi watchdog before returning the system to normal
operation after performing any kind of kgdb operation, else
the possibility exists to trigger the watchdog.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix two regressions dealing with the kgdb core.
1) kgdb_skipexception and kgdb_post_primary_code are optional
functions that are only required on archs that need special exception
fixups.
2) The kernel address space scope must be set on any probe_kernel_*
function or archs such as ARCH=arm will not allow access to the kernel
memory space. As an example, it is required to allow the full kernel
address space is when you the kernel debugger to inspect a system
call.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add HW breakpoints into the arch specific portion of x86 kgdb. In the
current x86 kernel.org kernels HW breakpoints are changed out in lazy
fashion because there is no infrastructure around changing them when
changing to a kernel task or entering the kernel mode via a system
call. This lazy approach means that if a user process uses HW
breakpoints the kgdb will loose out. This is an acceptable trade off
because the developer debugging the kernel is assumed to know what is
going on system wide and would be aware of this trade off.
There is a minor bug fix to the kgdb core so as to correctly call the
hw breakpoint functions with a valid value from the enum.
There is also a minor change to the x86_64 startup code when using
early HW breakpoints. When the debugger is connected, the cpu startup
code must not zero out the HW breakpoint registers or you cannot hit
the breakpoints you are interested in, in the first place.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If kgdb does remove a breakpoint that had a problem on the recursion
check, it should also print the address of the breakpoint.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In order to not trip the clocksource watchdog, kgdb must touch the
clocksource watchdog on the return to normal system run state.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
kgdb core code. Handles the protocol and the arch details.
[ mingo@elte.hu: heavily modified, simplified and cleaned up. ]
[ xemul@openvz.org: use find_task_by_pid_ns ]
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jan Kiszka <jan.kiszka@web.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Move documentation from semaphore.h to semaphore.c as requested by
Andrew Morton. Also reformat to kernel-doc style and add some more
notes about the implementation.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
By removing the negative values of 'count' and relying on the wait_list to
indicate whether we have any waiters, we can simplify the implementation
by removing the protection against an unlikely race condition. Thanks to
David Howells for his suggestions.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
ACPI currently emulates a timeout for semaphores with calls to
down_trylock and sleep. This produces horrible behaviour in terms of
fairness and excessive wakeups. Now that we have a unified semaphore
implementation, adding a real down_trylock is almost trivial.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Semaphores are no longer performance-critical, so a generic C
implementation is better for maintainability, debuggability and
extensibility. Thanks to Peter Zijlstra for fixing the lockdep
warning. Thanks to Harvey Harrison for pointing out that the
unlikely() was unnecessary.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
This way it checks if the clocks are synchronized between CPUs too.
This might be able to detect slowly drifting TSCs which only
go wrong over longer time.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Call
ts = &per_cpu(tick_cpu_sched, cpu);
and
cpu = smp_processor_id();
once instead of twice.
No functional change done, as changed code runs with local irq off.
Reduces source lines and text size (20bytes on x86_64).
[ akpm@linux-foundation.org: Build fix ]
Signed-off-by: Karsten Wiese <fzu@wemgehoertderstaat.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
In order to avoid the false positive from lockdep, each per-cpu base->lock has
the separate lock class and migrate_hrtimers() uses double_spin_lock().
This is overcomplicated: except for migrate_hrtimers() we never take 2 locks
at once, and migrate_hrtimers() can use spin_lock_nested().
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>