Vince Weaver reports that, on all architectures apart from ARM,
PERF_EVENT_IOC_PERIOD doesn't actually update the period until the next
event fires. This is counter-intuitive behaviour and is better dealt
with in the core code.
This patch ensures that the period is forcefully reset when dealing with
such a request in the core code. A subsequent patch removes the
equivalent hack from the ARM back-end.
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1385560479-11014-1-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch touches the RT group scheduling case.
Functions inc_rt_prio_smp() and dec_rt_prio_smp() change (global) rq's
priority, while rt_rq passed to them may be not the top-level rt_rq.
This is wrong, because changing of priority on a child level does not
guarantee that the priority is the highest all over the rq. So, this
leak makes RT balancing unusable.
The short example: the task having the highest priority among all rq's
RT tasks (no one other task has the same priority) are waking on a
throttle rt_rq. The rq's cpupri is set to the task's priority
equivalent, but real rq->rt.highest_prio.curr is less.
The patch below fixes the problem.
Signed-off-by: Kirill Tkhai <tkhai@yandex.ru>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/49231385567953@web4m.yandex.ru
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 42eb088e (sched: Avoid NULL dereference on sd_busy) corrected a NULL
dereference on sd_busy but the fix also altered what scheduling domain it
used for the 'sd_llc' percpu variable.
One impact of this is that a task selecting a runqueue may consider
idle CPUs that are not cache siblings as candidates for running.
Tasks are then running on CPUs that are not cache hot.
This was found through bisection where ebizzy threads were not seeing equal
performance and it looked like a scheduling fairness issue. This patch
mitigates but does not completely fix the problem on all machines tested
implying there may be an additional bug or a common root cause. Here are
the average range of performance seen by individual ebizzy threads. It
was tested on top of candidate patches related to x86 TLB range flushing.
4-core machine
3.13.0-rc3 3.13.0-rc3
vanilla fixsd-v3r3
Mean 1 0.00 ( 0.00%) 0.00 ( 0.00%)
Mean 2 0.34 ( 0.00%) 0.10 ( 70.59%)
Mean 3 1.29 ( 0.00%) 0.93 ( 27.91%)
Mean 4 7.08 ( 0.00%) 0.77 ( 89.12%)
Mean 5 193.54 ( 0.00%) 2.14 ( 98.89%)
Mean 6 151.12 ( 0.00%) 2.06 ( 98.64%)
Mean 7 115.38 ( 0.00%) 2.04 ( 98.23%)
Mean 8 108.65 ( 0.00%) 1.92 ( 98.23%)
8-core machine
Mean 1 0.00 ( 0.00%) 0.00 ( 0.00%)
Mean 2 0.40 ( 0.00%) 0.21 ( 47.50%)
Mean 3 23.73 ( 0.00%) 0.89 ( 96.25%)
Mean 4 12.79 ( 0.00%) 1.04 ( 91.87%)
Mean 5 13.08 ( 0.00%) 2.42 ( 81.50%)
Mean 6 23.21 ( 0.00%) 69.46 (-199.27%)
Mean 7 15.85 ( 0.00%) 101.72 (-541.77%)
Mean 8 109.37 ( 0.00%) 19.13 ( 82.51%)
Mean 12 124.84 ( 0.00%) 28.62 ( 77.07%)
Mean 16 113.50 ( 0.00%) 24.16 ( 78.71%)
It's eliminated for one machine and reduced for another.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Alex Shi <alex.shi@linaro.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: H Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131217092124.GV11295@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently, only one PMU in a context gets disabled during unthrottling
and event_sched_{out,in}(), however, events in one context may belong to
different pmus, which results in PMUs being reprogrammed while they are
still enabled.
This means that mixed PMU use [which is rare in itself] resulted in
potentially completely unreliable results: corrupted events, bogus
results, etc.
This patch temporarily disables PMUs that correspond to
each event in the context while these events are being modified.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: http://lkml.kernel.org/r/1387196256-8030-1-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Hugh reported this bug:
> CONFIG_MEMCG_SWAP is broken in 3.13-rc. Try something like this:
>
> mkdir -p /tmp/tmpfs /tmp/memcg
> mount -t tmpfs -o size=1G tmpfs /tmp/tmpfs
> mount -t cgroup -o memory memcg /tmp/memcg
> mkdir /tmp/memcg/old
> echo 512M >/tmp/memcg/old/memory.limit_in_bytes
> echo $$ >/tmp/memcg/old/tasks
> cp /dev/zero /tmp/tmpfs/zero 2>/dev/null
> echo $$ >/tmp/memcg/tasks
> rmdir /tmp/memcg/old
> sleep 1 # let rmdir work complete
> mkdir /tmp/memcg/new
> umount /tmp/tmpfs
> dmesg | grep WARNING
> rmdir /tmp/memcg/new
> umount /tmp/memcg
>
> Shows lots of WARNING: CPU: 1 PID: 1006 at kernel/res_counter.c:91
> res_counter_uncharge_locked+0x1f/0x2f()
>
> Breakage comes from 34c00c319c ("memcg: convert to use cgroup id").
>
> The lifetime of a cgroup id is different from the lifetime of the
> css id it replaced: memsw's css_get()s do nothing to hold on to the
> old cgroup id, it soon gets recycled to a new cgroup, which then
> mysteriously inherits the old's swap, without any charge for it.
Instead of removing cgroup id right after all the csses have been
offlined, we should do that after csses have been destroyed.
To make sure an invalid css pointer won't be returned after the css
is destroyed, make sure css_from_id() returns NULL in this case.
tj: Updated comment to note planned changes for cgrp->id.
Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Li Zefan <lizefan@huawei.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Tejun Heo <tj@kernel.org>
Ftrace currently initializes only the online CPUs. This implementation has
two problems:
- If we online a CPU after we enable the function profile, and then run the
test, we will lose the trace information on that CPU.
Steps to reproduce:
# echo 0 > /sys/devices/system/cpu/cpu1/online
# cd <debugfs>/tracing/
# echo <some function name> >> set_ftrace_filter
# echo 1 > function_profile_enabled
# echo 1 > /sys/devices/system/cpu/cpu1/online
# run test
- If we offline a CPU before we enable the function profile, we will not clear
the trace information when we enable the function profile. It will trouble
the users.
Steps to reproduce:
# cd <debugfs>/tracing/
# echo <some function name> >> set_ftrace_filter
# echo 1 > function_profile_enabled
# run test
# cat trace_stat/function*
# echo 0 > /sys/devices/system/cpu/cpu1/online
# echo 0 > function_profile_enabled
# echo 1 > function_profile_enabled
# cat trace_stat/function*
# run test
# cat trace_stat/function*
So it is better that we initialize the ftrace profiler for each possible cpu
every time we enable the function profile instead of just the online ones.
Link: http://lkml.kernel.org/r/1387178401-10619-1-git-send-email-miaox@cn.fujitsu.com
Cc: stable@vger.kernel.org # 2.6.31+
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
RCU must ensure that there is the equivalent of a full memory
barrier between any memory access preceding grace period and any
memory access following that same grace period, regardless of
which CPU(s) happen to execute the two memory accesses.
Therefore, downgrading UNLOCK+LOCK to no longer imply a full
memory barrier requires some adjustments to RCU.
This commit therefore adds smp_mb__after_unlock_lock()
invocations as needed after the RCU lock acquisitions that need
to be part of a full-memory-barrier UNLOCK+LOCK.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-7-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Calling cgroup_unload_subsys() from cgroup_load_subsys() after
online_css() failure will result in a NULL ptr dereference on attempt to
offline_css(), because online_css() only assigns css to cgroup on
success. Let's fix that by skipping calls to offline_css() and
css_free() in cgroup_unload_subsys() if there is no css, and freeing css
in cgroup_load_subsys() on online_css() failure.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Fix the gathering of certificates from both the source tree and the build tree
to correctly calculate the pathnames of all the certificates.
The problem was that if the default generated cert, signing_key.x509, didn't
exist then it would not have a path attached and if it did, it would have a
path attached.
This means that the contents of kernel/.x509.list would change between the
first compilation in a directory and the second. After the second it would
remain stable because the signing_key.x509 file exists.
The consequence was that the kernel would get relinked unconditionally on the
second recompilation. The second recompilation would also show something like
this:
X.509 certificate list changed
CERTS kernel/x509_certificate_list
- Including cert /home/torvalds/v2.6/linux/signing_key.x509
AS kernel/system_certificates.o
LD kernel/built-in.o
which is why the relink would happen.
Unfortunately, it isn't a simple matter of just sticking a path on the front
of the filename of the certificate in the build directory as make can't then
work out how to build it.
So the path has to be prepended to the name for sorting and duplicate
elimination and then removed for the make rule if it is in the build tree.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Function prototypes don't need to have the "extern" keyword since this
is the default behavior. Its explicit use is redundant. This commit
therefore removes them.
Signed-off-by: Teodora Baluta <teobaluta@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
If the rcutorture SRCU output exceeds 4096 bytes, for example, if you
have more than about 75 CPUs, it will overflow the current statically
allocated buffer. This commit therefore replaces this static buffer
with a dynamically buffer whose size is based on the number of CPUs.
Benefits:
- Avoids both buffer overflow and output truncation.
- Handles an arbitrarily large number of CPUs.
- Straightforward implementation.
Shortcomings:
- Some memory is wasted:
1 cpu now comsumes 50 - 60 bytes, and this patch provides 200 bytes.
Therefore, for 1K CPUs, roughly 100KB of memory will be wasted.
However, the memory is freed immediately after printing, so this
wastage should not be a problem in practice.
Testing (Fedora16 2 CPUs, 2GB RAM x86_64):
- as module, with/without "torture_type=srcu".
- build-in not boot runnable, with/without "torture_type=srcu".
- build-in let boot runnable, with/without "torture_type=srcu".
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Whenever a CPU receives a scheduling-clock interrupt, RCU checks to see
if the RCU core needs anything from this CPU. If so, RCU raises
RCU_SOFTIRQ to carry out any needed processing.
This approach has worked well historically, but it is undesirable on
NO_HZ_FULL CPUs. Such CPUs are expected to spend almost all of their time
in userspace, so that scheduling-clock interrupts can be disabled while
there is only one runnable task on the CPU in question. Unfortunately,
raising any softirq has the potential to wake up ksoftirqd, which would
provide the second runnable task on that CPU, preventing disabling of
scheduling-clock interrupts.
What is needed instead is for RCU to leave NO_HZ_FULL CPUs alone,
relying on the grace-period kthreads' quiescent-state forcing to
do any needed RCU work on behalf of those CPUs.
This commit therefore refrains from raising RCU_SOFTIRQ on any
NO_HZ_FULL CPUs during any grace periods that have been in effect
for less than one second. The one-second limit handles the case
where an inappropriate workload is running on a NO_HZ_FULL CPU
that features lots of scheduling-clock interrupts, but no idle
or userspace time.
Reported-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Mike Galbraith <bitbucket@online.de>
Toasted-by: Frederic Weisbecker <fweisbec@gmail.com>
After commit #10f39bb1b2c1 (rcu: protect __rcu_read_unlock() against
scheduler-using irq handlers), it is no longer possible to enter
the main body of rcu_read_lock_special() from an NMI, interrupt, or
softirq handler. In theory, this implies that the check for "in_irq()
|| in_serving_softirq()" must always fail, so that in theory this check
could be removed entirely.
In practice, this commit wraps this condition with a WARN_ON_ONCE().
If this warning never triggers, then the condition will be removed
entirely.
[ paulmck: And one way of triggering the WARN_ON() is if a scheduling
clock interrupt occurs in an RCU read-side critical section, setting
RCU_READ_UNLOCK_NEED_QS, which is handled by rcu_read_unlock_special().
Updated this commit to return if only that bit was set. ]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.15 (GNU/Linux)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=/AdA
-----END PGP SIGNATURE-----
Merge tag 'keys-devel-20131210' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
Pull misc keyrings fixes from David Howells:
"These break down into five sets:
- A patch to error handling in the big_key type for huge payloads.
If the payload is larger than the "low limit" and the backing store
allocation fails, then big_key_instantiate() doesn't clear the
payload pointers in the key, assuming them to have been previously
cleared - but only one of them is.
Unfortunately, the garbage collector still calls big_key_destroy()
when sees one of the pointers with a weird value in it (and not
NULL) which it then tries to clean up.
- Three patches to fix the keyring type:
* A patch to fix the hash function to correctly divide keyrings off
from keys in the topology of the tree inside the associative
array. This is only a problem if searching through nested
keyrings - and only if the hash function incorrectly puts the a
keyring outside of the 0 branch of the root node.
* A patch to fix keyrings' use of the associative array. The
__key_link_begin() function initially passes a NULL key pointer
to assoc_array_insert() on the basis that it's holding a place in
the tree whilst it does more allocation and stuff.
This is only a problem when a node contains 16 keys that match at
that level and we want to add an also matching 17th. This should
easily be manufactured with a keyring full of keyrings (without
chucking any other sort of key into the mix) - except for (a)
above which makes it on average adding the 65th keyring.
* A patch to fix searching down through nested keyrings, where any
keyring in the set has more than 16 keyrings and none of the
first keyrings we look through has a match (before the tree
iteration needs to step to a more distal node).
Test in keyutils test suite:
http://git.kernel.org/cgit/linux/kernel/git/dhowells/keyutils.git/commit/?id=8b4ae963ed92523aea18dfbb8cab3f4979e13bd1
- A patch to fix the big_key type's use of a shmem file as its
backing store causing audit messages and LSM check failures. This
is done by setting S_PRIVATE on the file to avoid LSM checks on the
file (access to the shmem file goes through the keyctl() interface
and so is gated by the LSM that way).
This isn't normally a problem if a key is used by the context that
generated it - and it's currently only used by libkrb5.
Test in keyutils test suite:
http://git.kernel.org/cgit/linux/kernel/git/dhowells/keyutils.git/commit/?id=d9a53cbab42c293962f2f78f7190253fc73bd32e
- A patch to add a generated file to .gitignore.
- A patch to fix the alignment of the system certificate data such
that it it works on s390. As I understand it, on the S390 arch,
symbols must be 2-byte aligned because loading the address discards
the least-significant bit"
* tag 'keys-devel-20131210' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs:
KEYS: correct alignment of system_certificate_list content in assembly file
Ignore generated file kernel/x509_certificate_list
security: shmem: implement kernel private shmem inodes
KEYS: Fix searching of nested keyrings
KEYS: Fix multiple key add into associative array
KEYS: Fix the keyring hash function
KEYS: Pre-clear struct key on allocation
When debugging the read-only hugepage case, I was confused by the fact
that get_futex_key() did an access_ok() only for the non-shared futex
case, since the user address checking really isn't in any way specific
to the private key handling.
Now, it turns out that the shared key handling does effectively do the
equivalent checks inside get_user_pages_fast() (it doesn't actually
check the address range on x86, but does check the page protections for
being a user page). So it wasn't actually a bug, but the fact that we
treat the address differently for private and shared futexes threw me
for a loop.
Just move the check up, so that it gets done for both cases. Also, use
the 'rw' parameter for the type, even if it doesn't actually matter any
more (it's a historical artifact of the old racy i386 "page faults from
kernel space don't check write protections").
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The hugepage code had the exact same bug that regular pages had in
commit 7485d0d375 ("futexes: Remove rw parameter from
get_futex_key()").
The regular page case was fixed by commit 9ea71503a8 ("futex: Fix
regression with read only mappings"), but the transparent hugepage case
(added in a5b338f2b0: "thp: update futex compound knowledge") case
remained broken.
Found by Dave Jones and his trinity tool.
Reported-and-tested-by: Dave Jones <davej@fedoraproject.org>
Cc: stable@kernel.org # v2.6.38+
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Darren Hart <dvhart@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add the missing unlock before return from function cgroup_load_subsys()
in the error handling case.
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Remove a full barrier from the ring-buffer write path by relying on
a control dependency to order a LOAD -> STORE scenario.
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-8alv40z6ikk57jzbaobnxrjl@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This
results in him occasionally seeing time going backwards - which
crashes the scheduler ...
Most of our time accounting can actually handle that except the most
common one; the tick time update of sched_fair.
There is a further problem with that code; previously we assumed that
because we get a tick every TICK_NSEC our time delta could never
exceed 32bits and math was simpler.
However, ever since Frederic managed to get NO_HZ_FULL merged; this is
no longer the case since now a task can run for a long time indeed
without getting a tick. It only takes about ~4.2 seconds to overflow
our u32 in nanoseconds.
This means we not only need to better deal with time going backwards;
but also means we need to be able to deal with large deltas.
This patch reworks the entire code and uses mul_u64_u32_shr() as
proposed by Andy a long while ago.
We express our virtual time scale factor in a u32 multiplier and shift
right and the 32bit mul_u64_u32_shr() implementation reduces to a
single 32x32->64 multiply if the time delta is still short (common
case).
For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128.
Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: fweisbec@gmail.com
Cc: Paul Turner <pjt@google.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Yinghai reported that he saw a /0 in sg_capacity on his EX parts.
Make sure to always initialize power_orig now that we actually use it.
Ideally build_sched_domains() -> init_sched_groups_power() would also
initialize this; but for some yet unexplained reason some setups seem
to miss updates there.
Reported-by: Yinghai Lu <yinghai@kernel.org>
Tested-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-l8ng2m9uml6fhibln8wqpom7@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Apart from data-type specific alignment constraints, there are also
architecture-specific alignment requirements.
For example, on s390 symbols must be on even addresses implying a 2-byte
alignment. If the system_certificate_list_end symbol is on an odd address
and if this address is loaded, the least-significant bit is ignored. As a
result, the load_system_certificate_list() fails to load the certificates
because of a wrong certificate length calculation.
To be safe, align system_certificate_list on an 8-byte boundary. Also improve
the length calculation of the system_certificate_list content. Introduce a
system_certificate_list_size (8-byte aligned because of unsigned long) variable
that stores the length. Let the linker calculate this size by introducing
a start and end label for the certificate content.
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: David Howells <dhowells@redhat.com>
$ git status
# On branch pending-rebases
# Untracked files:
# (use "git add <file>..." to include in what will be committed)
#
# kernel/x509_certificate_list
nothing added to commit but untracked files present (use "git add" to track)
$
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: David Howells <dhowells@redhat.com>
Currently blocking in an RCU callback function will result in
"scheduling while atomic", which could be triggered for any number
of reasons. To aid debugging, this patch introduces a rcu_callback_map
that is used to tie the inappropriate voluntary context switch back
to the fact that the function is being invoked from within a callback.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit documents the memory-barrier guarantees provided by
synchronize_srcu() and call_srcu().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Each element of the rcu_state structure's ->levelspread[] array
is intended to contain the per-level fanout, where the zero-th
element corresponds to the root of the rcu_node tree, and the last
element corresponds to the leaves. In the CONFIG_RCU_FANOUT_EXACT
case, this means that the last element should be filled in
from CONFIG_RCU_FANOUT_LEAF (or from the rcu_fanout_leaf boot
parameter, if provided) and that the remaining elements should
be filled in from CONFIG_RCU_FANOUT. Unfortunately, the current
code in rcu_init_levelspread() takes the opposite approach, placing
CONFIG_RCU_FANOUT_LEAF in the zero-th element and CONFIG_RCU_FANOUT in
the remaining elements.
For typical power-of-two values, this generates odd but functional
rcu_node trees. However, other values, for example CONFIG_RCU_FANOUT=3
and CONFIG_RCU_FANOUT_LEAF=2, generate trees that can leave some CPUs
out of the grace-period computation, resulting in too-short grace periods
and therefore a broken RCU implementation.
This commit therefore fixes rcu_init_levelspread() to set the last
->levelspread[] array element from CONFIG_RCU_FANOUT_LEAF and the
remaining elements from CONFIG_RCU_FANOUT, thus generating the
intended rcu_node trees.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit fixes the following coccinelle warning:
kernel/rcu/tree.c:712:9-10: WARNING: return of 0/1 in function
'rcu_lockdep_current_cpu_online' with return type bool
Return statements in functions returning bool should use
true/false instead of 1/0.
Generated by: coccinelle/misc/boolreturn.cocci
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The posix cpu timers code makes a heavy use of BUG_ON()
but none of these concern fatal issues that require
to stop the machine. So let's just warn the user when
some internal state slips out of our hands.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
The remaining uses of tasklist_lock were mostly about synchronizing
against sighand modifications, getting coherent and safe group samples
and also thread/process wide timers list handling.
All of this is already safely synchronizable with the target's
sighand lock. Let's use it on these places instead.
Also update the comments about locking.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Timer deletion doesn't need the tasklist lock.
We need to protect against:
* concurrent access to the lists p->cputime_expires and
p->sighand->cputime_expires
* task reaping that may also delete the timer list entry
* timer firing
We already hold the timer lock which protects us against concurrent
timer firing.
The rest only need the targets sighand to be locked.
So hold it and drop the use of tasklist_lock there.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
There is no need for the tasklist_lock just to take a process
wide clock sample.
All we need is to get a coherent sample that doesn't race with
exit() and exec():
* exit() may be concurrently reaping a task and flushing its time
* sighand is unstable under exit() and exec(), and the latter also
result in group leader that can change
To protect against these, locking the target's sighand is enough.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Consolidate the clock sampling common code used for both local
and remote targets.
Note that this introduces a tiny user ABI change: if a
PID is passed to clock_gettime() along the clockid,
we used to forbid a process wide clock sample when that
PID doesn't belong to a group leader. Now after this patch
we allow process wide clock samples if that PID belongs to
the current task, even if the current task is not the
group leader.
But local process wide clock samples are allowed if PID == 0
(current task) even if the current task is not the group leader.
So in the end this should be no big deal as this actually harmonize
the behaviour when the remote sample is actually a local one.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Now that we've removed all the optimizations that could
result in NULL timer's targets, we can remove all the
associated special case handling.
Also add some warnings on NULL targets to spot any possible
leftover.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
When a timer's target is seen to be buried, for example on calls
to timer_gettime(), the posix cpu timers code behaves a bit
like a garbage collector and releases early the reference to the
task.
Then again, this optimization complicates the code for no much
value: it's up to the user to release the timer and its associated
ressources by calling timer_delete() after it buries the target
tasks.
Remove this to simplify the code.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Now that we removed dead thread posix cpu timers caching,
lets remove the dead process wide version. This caching
is similar to the per thread version but it should be even
more rare:
* If the process id dead, we are not reading its timers
status from a thread belonging to its group since they
are all dead. So this caching only concern remote process
timers reads. Now posix cpu timers using itimers or timer_settime()
can't do remote process timers anyway so it's not even clear if there
is actually a user for this caching.
* Unlike per thread timers caching, this only applies to
zombies targets. Buried targets' process wide timers return
0 values. But then again, timer_gettime() can't read remote
process timers, so if the process is dead, there can't be
any reader left anyway.
Then again this caching seem to complicate the code for
corner cases that are probably not worth it. So lets get
rid of it.
Also remove the sample snapshot on dying process timer
that is now useless, as suggested by Kosaki.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
When a task is exiting or has exited, its posix cpu timers
don't tick anymore and won't elapse further. It's too late
for them to expire.
So any further call to timer_gettime() on these timers will
return the same remaining expiry time.
The current code optimize this by caching the remaining delta
and storing it where we use to save the absolute expiration time.
This way, the future calls to timer_gettime() won't need to
compute the difference between the absolute expiration time and
the current time anymore.
Now this optimization doesn't seem to bring much value. Computing
the timer remaining delta is not very costly. Fetching the timer
value OTOH can be costly in two ways:
* CPUCLOCK_SCHED read requires to lock the target's rq. But some
optimizations are on the way to make task_sched_runtime() not holding
the rq lock of a non-running target.
* CPUCLOCK_VIRT/CPUCLOCK_PROF read simply consist in fetching
current->utime/current->stime except when the system uses full
dynticks cputime accounting. The latter requires a per task lock
in order to correctly compute user and system time. But once the
target is dead, this lock shouldn't be contended anyway.
All in one this caching doesn't seem to be justified.
Given that it complicates the code significantly for
few wins, let's remove it on single thread timers.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Add a flag to tell the PCI subsystem that kernel is shutting down in
preparation to kexec a kernel. Add code in PCI subsystem to use this flag
to clear Bus Master bit on PCI devices only in case of kexec reboot.
This fixes a power-off problem on Acer Aspire V5-573G and likely other
machines and avoids any other issues caused by clearing Bus Master bit on
PCI devices in normal shutdown path. The problem was introduced by
b566a22c23 ("PCI: disable Bus Master on PCI device shutdown").
This patch is based on discussion at
http://marc.info/?l=linux-pci&m=138425645204355&w=2
Link: https://bugzilla.kernel.org/show_bug.cgi?id=63861
Reported-by: Chang Liu <cl91tp@gmail.com>
Signed-off-by: Khalid Aziz <khalid.aziz@oracle.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: stable@vger.kernel.org # v3.5+
After the previous patch which introduced for_each_css(),
for_each_root_subsys() only has two users left. This patch replaces
it with for_each_subsys() + explicit subsys_mask testing and remove
for_each_root_subsys() along with cgroupfs_root->subsys_list handling.
This patch doesn't introduce any behavior changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
There are enough places where css's of a cgroup are iterated, which
currently uses for_each_root_subsys() + explicit cgroup_css(). This
patch implements for_each_css() and replaces the above combination
with it.
This patch doesn't introduce any behavior changes.
v2: Updated to apply cleanly on top of v2 of "cgroup: fix css leaks on
online_css() failure"
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Now that all opertations to create a css (cgroup_subsys_state) are
collected into a single loop in cgroup_create(), it's easy to factor
it out into its own function. Factor out css creation into
create_css(). This makes the code easier to follow and will enable
decoupling css creation from cgroup creation which is necessary for
the planned unified hierarchy.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Now that css operations in cgroup_create() are back-to-back, there
isn't much point in allocating css's in one loop and onlining them in
another. Merge the two loops so that a css is allocated and onlined
on each iteration.
css_ar[] is no longer necessary and replaced with a single pointer.
This also simplifies the error handling path.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
cgroup_create() currently does the followings.
1. alloc cgroup
2. alloc css's
3. create the directory and commit to cgroup creation
4. online css's
5. create cgroup and css files
The sequence performs allocations before other operations but it
doesn't buy anything because each of the above steps may fail and
should be unrollable. Reorganize the sequence such that cgroup
operations are done before css operations.
1. alloc cgroup
2. create the directory and files and commit to cgroup creation
3. alloc css's
4. create files for and online css's
This simplifies the code a bit and enables further simplification and
separating out css creation from cgroup creation which is necessary
for the planned unified hierarchy where css's will be created and
destroyed dynamically across the lifetime of a cgroup.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
We want to use for_each_subsys() in cgroupfs_root handling where only
cgroup_root_mutex is held. The only way cgroup_subsys[] can change is
through module load/unload, make cgroup_[un]load_subsys() grab
cgroup_root_mutex too and update the lockdep annotation in
for_each_subsys() to allow either cgroup_mutex or cgroup_root_mutex.
* Lockdep annotation is moved from inner 'if' condition to outer 'for'
init caluse. There's no reason to execute the assertion every loop.
* Loop index @i is renamed to @ssid. Indices iterating through subsys
will be [re]named to @ssid gradually.
v2: cgroup_assert_mutex_or_root_locked() caused build failure if
!CONFIG_LOCKEDP. Conditionalize its definition. The build failure
was reported by kbuild test bot.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: kbuild test robot <fengguang.wu@intel.com>
Currently, all css iterations and css_from_dir() require RCU read lock
whether the caller is holding cgroup_mutex or not, which is
unnecessarily restrictive. They are all safe to use under
cgroup_mutex without holding RCU read lock.
Factor out cgroup_assert_mutex_or_rcu_locked() from css_from_id() and
apply it to all css iteration functions and css_from_dir().
v2: cgroup_assert_mutex_or_rcu_locked() definition doesn't need to be
inside CONFIG_PROVE_RCU ifdef as rcu_lockdep_assert() is always
defined and conditionalized. Move it outside of the ifdef block.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
