This commit annotates rcu_initiate_boost() fixes the following sparse
warning:
kernel/rcu/tree_plugin.h:1494:13: warning: context imbalance in 'rcu_initiate_boost' - unexpected unlock
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
The __rcu_reclaim() function returned 0/1, which is not proper for a
function of type bool. This commit therefore converts to false/true.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
The CONFIG_PROVE_RCU_DELAY Kconfig parameter doesn't appear to be very
effective at finding race conditions, so this commit removes it.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
[ paulmck: Remove definition and uses as noted by Paul Bolle. ]
Although NMI-based stack dumps are in principle more accurate, they are
also more likely to trigger deadlocks. This commit therefore replaces
all uses of trigger_all_cpu_backtrace() with rcu_dump_cpu_stacks(), so
that the CPU detecting an RCU CPU stall does the stack dumping.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Binding the grace-period kthreads to the timekeeping CPU resulted in
significant performance decreases for some workloads. For more detail,
see:
https://lkml.org/lkml/2014/6/3/395 for benchmark numbers
https://lkml.org/lkml/2014/6/4/218 for CPU statistics
It turns out that it is necessary to bind the grace-period kthreads
to the timekeeping CPU only when all but CPU 0 is a nohz_full CPU
on the one hand or if CONFIG_NO_HZ_FULL_SYSIDLE=y on the other.
In other cases, it suffices to bind the grace-period kthreads to the
set of non-nohz_full CPUs.
This commit therefore creates a tick_nohz_not_full_mask that is the
complement of tick_nohz_full_mask, and then binds the grace-period
kthread to the set of CPUs indicated by this new mask, which covers
the CONFIG_NO_HZ_FULL_SYSIDLE=n case. The CONFIG_NO_HZ_FULL_SYSIDLE=y
case still binds the grace-period kthreads to the timekeeping CPU.
This commit also includes the tick_nohz_full_enabled() check suggested
by Frederic Weisbecker.
Reported-by: Jet Chen <jet.chen@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Created housekeeping_affine() and housekeeping_mask per
fweisbec feedback. ]
RCU priority boosting currently checks for boosting via a pointer in
task_struct. However, this is not needed: As Oleg noted, if the
rt_mutex is placed in the rcu_node instead of on the booster's stack,
the boostee can simply check it see if it owns the lock. This commit
makes this change, shrinking task_struct by one pointer and the kernel
by thirteen lines.
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The rcu_start_future_gp() function checks the current rcu_node's ->gpnum
and ->completed twice, once without ACCESS_ONCE() and once with it.
Which is pointless because we hold that rcu_node's ->lock at that point.
The intent was to check the current rcu_node structure and the root
rcu_node structure, the latter locklessly with ACCESS_ONCE(). This
commit therefore makes that change.
The reason that it is safe to locklessly check the root rcu_nodes's
->gpnum and ->completed fields is that we hold the current rcu_node's
->lock, which constrains the root rcu_node's ability to change its
->gpnum and ->completed fields. Of course, if there is a single rcu_node
structure, then rnp_root==rnp, and holding the lock prevents all changes.
If there is more than one rcu_node structure, then the code updates the
fields in the following order:
1. Increment rnp_root->gpnum to start new grace period.
2. Increment rnp->gpnum to initialize the current rcu_node,
continuing initialization for the new grace period.
3. Increment rnp_root->completed to end the current grace period.
4. Increment rnp->completed to continue cleaning up after the
old grace period.
So there are four possible combinations of relative values of these
four fields:
N N N N: RCU idle, new grace period must be initiated.
Although rnp_root->gpnum might be incremented immediately
after we check, that will just result in unnecessary work.
The grace period already started, and we try to start it.
N+1 N N N: RCU grace period just started. No further change is
possible because we hold rnp->lock, so the checks of
rnp_root->gpnum and rnp_root->completed are stable.
We know that our request for a future grace period will
be seen during grace-period cleanup.
N+1 N N+1 N: RCU grace period is ongoing. Because rnp->gpnum is
different than rnp->completed, we won't even look at
rnp_root->gpnum and rnp_root->completed, so the possible
concurrent change to rnp_root->completed does not matter.
We know that our request for a future grace period will
be seen during grace-period cleanup, which cannot pass
this rcu_node because we hold its ->lock.
N+1 N+1 N+1 N: RCU grace period has ended, but not yet been cleaned up.
Because rnp->gpnum is different than rnp->completed, we
won't look at rnp_root->gpnum and rnp_root->completed, so
the possible concurrent change to rnp_root->completed does
not matter. We know that our request for a future grace
period will be seen during grace-period cleanup, which
cannot pass this rcu_node because we hold its ->lock.
Therefore, despite initial appearances, the lockless check is safe.
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
[ paulmck: Update comment to say why the lockless check is safe. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The current approach to RCU priority boosting uses an rt_mutex strictly
for its priority-boosting side effects. The rt_mutex_init_proxy_locked()
function is used by the booster to initialize the lock as held by the
boostee. The booster then uses rt_mutex_lock() to acquire this rt_mutex,
which priority-boosts the boostee. When the boostee reaches the end
of its outermost RCU read-side critical section, it checks a field in
its task structure to see whether it has been boosted, and, if so, uses
rt_mutex_unlock() to release the rt_mutex. The booster can then go on
to boost the next task that is blocking the current RCU grace period.
But reasonable implementations of rt_mutex_unlock() might result in the
boostee referencing the rt_mutex's data after releasing it. But the
booster might have re-initialized the rt_mutex between the time that the
boostee released it and the time that it later referenced it. This is
clearly asking for trouble, so this commit introduces a completion that
forces the booster to wait until the boostee has completely finished with
the rt_mutex, thus avoiding the case where the booster is re-initializing
the rt_mutex before the last boostee's last reference to that rt_mutex.
This of course does introduce some overhead, but the priority-boosting
code paths are miles from any possible fastpath, and the overhead of
executing the completion will normally be quite small compared to the
overhead of priority boosting and deboosting, so this should be OK.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The m68k architecture aligns only to 16-bit boundaries, which can cause
the align-to-32-bits check in __call_rcu() to trigger. Because there is
currently no known potential need for more than one low-order bit, this
commit loosens the check to 16-bit boundaries.
Reported-by: Greg Ungerer <gerg@uclinux.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
RCU contains code of the following forms:
ACCESS_ONCE(x)++;
ACCESS_ONCE(x) += y;
ACCESS_ONCE(x) -= y;
Now these constructs do operate correctly, but they really result in a
pair of volatile accesses, one to do the load and another to do the store.
This can be confusing, as the casual reader might well assume that (for
example) gcc might generate a memory-to-memory add instruction for each
of these three cases. In fact, gcc will do no such thing. Also, there
is a good chance that the kernel will move to separate load and store
variants of ACCESS_ONCE(), and constructs like the above could easily
confuse both people and scripts attempting to make that sort of change.
Finally, most of RCU's read-modify-write uses of ACCESS_ONCE() really
only need the store to be volatile, so that the read-modify-write form
might be misleading.
This commit therefore changes the above forms in RCU so that each instance
of ACCESS_ONCE() either does a load or a store, but not both. In a few
cases, ACCESS_ONCE() was not critical, for example, for maintaining
statisitics. In these cases, ACCESS_ONCE() has been dispensed with
entirely.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
In kernels built with CONFIG_NO_HZ_FULL, tick_do_timer_cpu is constant
once boot completes. Thus, there is no need to wrap it in ACCESS_ONCE()
in code that is built only when CONFIG_NO_HZ_FULL. This commit therefore
removes the redundant ACCESS_ONCE().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Those two arrays are being passed to lockdep_init_map(), which expects
const char *, and are stored in lockdep_map the same way.
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The explicit local_irq_save() in __lock_task_sighand() is needed to avoid
a potential deadlock condition, as noted in a841796f11c90d53 (signal:
align __lock_task_sighand() irq disabling and RCU). However, someone
reading the code might be forgiven for concluding that this separate
local_irq_save() was completely unnecessary. This commit therefore adds
a comment referencing the shiny new block comment on rcu_read_unlock().
Reported-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
After the previous patch to remove sane_behavior support from
non-default hierarchies, CGRP_ROOT_SANE_BEHAVIOR is used only to
indicate the default hierarchy while parsing mount options. This
patch makes the following cleanups around it.
* Don't show it in the mount option. Eventually the default hierarchy
will be assigned a different filesystem type.
* As sane_behavior is no longer effective on non-default hierarchies
and the default hierarchy doesn't accept any mount options,
parse_cgroupfs_options() can consider sane_behavior mount option as
indicating the default hierarchy and fail if any other options are
specified with it. While at it, remove one of the double blank
lines in the function.
* cgroup_mount() can now simply test CGRP_ROOT_SANE_BEHAVIOR to tell
whether to mount the default hierarchy or not.
* As CGROUP_ROOT_SANE_BEHAVIOR's only role now is indicating whether
to select the default hierarchy or not during mount, it doesn't need
to be set in the default hierarchy itself. cgroup_init_early()
updated accordingly.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
sane_behavior has been used as a development vehicle for the default
unified hierarchy. Now that the default hierarchy is in place, the
flag became redundant and confusing as its usage is allowed on all
hierarchies. There are gonna be either the default hierarchy or
legacy ones. Let's make that clear by removing sane_behavior support
on non-default hierarchies.
This patch replaces cgroup_sane_behavior() with cgroup_on_dfl(). The
comment on top of CGRP_ROOT_SANE_BEHAVIOR is moved to on top of
cgroup_on_dfl() with sane_behavior specific part dropped.
On the default and legacy hierarchies w/o sane_behavior, this
shouldn't cause any behavior differences.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
"cgroup.sane_behavior" is added to help distinguishing whether
sane_behavior is in effect or not. We now have the default hierarchy
where the flag is always in effect and are planning to remove
supporting sane behavior on the legacy hierarchies making this file on
the default hierarchy rather pointless. Let's make it legacy only and
thus always zero.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
cgroup_root->flags only contains CGRP_ROOT_* flags and there's no
reason to mask the flags. Remove CGRP_ROOT_OPTION_MASK.
This doesn't cause any behavior differences.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Currently, the blkio subsystem attributes all of writeback IOs to the
root. One of the issues is that there's no way to tell who originated
a writeback IO from block layer. Those IOs are usually issued
asynchronously from a task which didn't have anything to do with
actually generating the dirty pages. The memory subsystem, when
enabled, already keeps track of the ownership of each dirty page and
it's desirable for blkio to piggyback instead of adding its own
per-page tag.
blkio piggybacking on memory is an implementation detail which
preferably should be handled automatically without requiring explicit
userland action. To achieve that, this patch implements
cgroup_subsys->depends_on which contains the mask of subsystems which
should be enabled together when the subsystem is enabled.
The previous patches already implemented the support for enabled but
invisible subsystems and cgroup_subsys->depends_on can be easily
implemented by updating cgroup_refresh_child_subsys_mask() so that it
calculates cgroup->child_subsys_mask considering
cgroup_subsys->depends_on of the explicitly enabled subsystems.
Documentation/cgroups/unified-hierarchy.txt is updated to explain that
subsystems may not become immediately available after being unused
from userland and that dependency could be a factor in it. As
subsystems may already keep residual references, this doesn't
significantly change how subsystem rebinding can be used.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
cgroup is implementing support for subsystem dependency which would
require a way to enable a subsystem even when it's not directly
configured through "cgroup.subtree_control".
The previous patches added support for explicitly and implicitly
enabled subsystems and showing/hiding their interface files. An
explicitly enabled subsystem may become implicitly enabled if it's
turned off through "cgroup.subtree_control" but there are subsystems
depending on it. In such cases, the subsystem, as it's turned off
when seen from userland, shouldn't enforce any resource control.
Also, the subsystem may be explicitly turned on later again and its
interface files should be as close to the intial state as possible.
This patch adds cgroup_subsys->css_reset() which is invoked when a css
is hidden. The callback should disable resource control and reset the
state to the vanilla state.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
cgroup is implementing support for subsystem dependency which would
require a way to enable a subsystem even when it's not directly
configured through "cgroup.subtree_control".
The preceding patch distinguished cgroup->subtree_control and
->child_subsys_mask where the former is the subsystems explicitly
configured by the userland and the latter is all enabled subsystems
currently is equal to the former but will include subsystems
implicitly enabled through dependency.
Subsystems which are enabled due to dependency shouldn't be visible to
userland. This patch updates cgroup_subtree_control_write() and
create_css() such that interface files are not created for implicitly
enabled subsytems.
* @visible paramter is added to create_css(). Interface files are
created only when true.
* If an already implicitly enabled subsystem is turned on through
"cgroup.subtree_control", the existing css should be used. css
draining is skipped.
* cgroup_subtree_control_write() computes the new target
cgroup->child_subsys_mask and create/kill or show/hide csses
accordingly.
As the two subsystem masks are still kept identical, this patch
doesn't introduce any behavior changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
cgroup is implementing support for subsystem dependency which would
require a way to enable a subsystem even when it's not directly
configured through "cgroup.subtree_control".
Previously, cgroup->child_subsys_mask directly reflected
"cgroup.subtree_control" and the enabled subsystems in the child
cgroups. This patch adds cgroup->subtree_control which
"cgroup.subtree_control" operates on. cgroup->child_subsys_mask is
now calculated from cgroup->subtree_control by
cgroup_refresh_child_subsys_mask(), which sets it identical to
cgroup->subtree_control for now.
This will allow using cgroup->child_subsys_mask for all the enabled
subsystems including the implicit ones and ->subtree_control for
tracking the explicitly requested ones. This patch keeps the two
masks identical and doesn't introduce any behavior changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Make the following two reorganizations to
cgroup_subtree_control_write(). These are to prepare for future
changes and shouldn't cause any functional difference.
* Move availability above css offlining wait.
* Move cgrp->child_subsys_mask update above new css creation.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Sharvil noticed with the posix timer_settime interface, using the
CLOCK_REALTIME_ALARM or CLOCK_BOOTTIME_ALARM clockid, if the users
tried to specify a relative time timer, it would incorrectly be
treated as absolute regardless of the state of the flags argument.
This patch corrects this, properly checking the absolute/relative flag,
as well as adds further error checking that no invalid flag bits are set.
Reported-by: Sharvil Nanavati <sharvil@google.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Sharvil Nanavati <sharvil@google.com>
Cc: stable <stable@vger.kernel.org> #3.0+
Link: http://lkml.kernel.org/r/1404767171-6902-1-git-send-email-john.stultz@linaro.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Enabling NO_HZ_FULL currently has the side effect of enabling callback
offloading on all CPUs. This results in lots of additional rcuo kthreads,
and can also increase context switching and wakeups, even in cases where
callback offloading is neither needed nor particularly desirable. This
commit therefore enables callback offloading on a given CPU only if
specifically requested at build time or boot time, or if that CPU has
been specifically designated (again, either at build time or boot time)
as a nohz_full CPU.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
An 80-CPU system with a context-switch-heavy workload can require so
many NOCB kthread wakeups that the RCU grace-period kthreads spend several
tens of percent of a CPU just awakening things. This clearly will not
scale well: If you add enough CPUs, the RCU grace-period kthreads would
get behind, increasing grace-period latency.
To avoid this problem, this commit divides the NOCB kthreads into leaders
and followers, where the grace-period kthreads awaken the leaders each of
whom in turn awakens its followers. By default, the number of groups of
kthreads is the square root of the number of CPUs, but this default may
be overridden using the rcutree.rcu_nocb_leader_stride boot parameter.
This reduces the number of wakeups done per grace period by the RCU
grace-period kthread by the square root of the number of CPUs, but of
course by shifting those wakeups to the leaders. In addition, because
the leaders do grace periods on behalf of their respective followers,
the number of wakeups of the followers decreases by up to a factor of two.
Instead of being awakened once when new callbacks arrive and again
at the end of the grace period, the followers are awakened only at
the end of the grace period.
For a numerical example, in a 4096-CPU system, the grace-period kthread
would awaken 64 leaders, each of which would awaken its 63 followers
at the end of the grace period. This compares favorably with the 79
wakeups for the grace-period kthread on an 80-CPU system.
Reported-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Since the torture-test thread creation interface does not include
format string arguments, this commit makes sure the name can never be
accidentally processed as a format string.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
When hot-adding and onlining CPU, kernel panic occurs, showing following
call trace.
BUG: unable to handle kernel paging request at 0000000000001d08
IP: [<ffffffff8114acfd>] __alloc_pages_nodemask+0x9d/0xb10
PGD 0
Oops: 0000 [#1] SMP
...
Call Trace:
[<ffffffff812b8745>] ? cpumask_next_and+0x35/0x50
[<ffffffff810a3283>] ? find_busiest_group+0x113/0x8f0
[<ffffffff81193bc9>] ? deactivate_slab+0x349/0x3c0
[<ffffffff811926f1>] new_slab+0x91/0x300
[<ffffffff815de95a>] __slab_alloc+0x2bb/0x482
[<ffffffff8105bc1c>] ? copy_process.part.25+0xfc/0x14c0
[<ffffffff810a3c78>] ? load_balance+0x218/0x890
[<ffffffff8101a679>] ? sched_clock+0x9/0x10
[<ffffffff81105ba9>] ? trace_clock_local+0x9/0x10
[<ffffffff81193d1c>] kmem_cache_alloc_node+0x8c/0x200
[<ffffffff8105bc1c>] copy_process.part.25+0xfc/0x14c0
[<ffffffff81114d0d>] ? trace_buffer_unlock_commit+0x4d/0x60
[<ffffffff81085a80>] ? kthread_create_on_node+0x140/0x140
[<ffffffff8105d0ec>] do_fork+0xbc/0x360
[<ffffffff8105d3b6>] kernel_thread+0x26/0x30
[<ffffffff81086652>] kthreadd+0x2c2/0x300
[<ffffffff81086390>] ? kthread_create_on_cpu+0x60/0x60
[<ffffffff815f20ec>] ret_from_fork+0x7c/0xb0
[<ffffffff81086390>] ? kthread_create_on_cpu+0x60/0x60
In my investigation, I found the root cause is wq_numa_possible_cpumask.
All entries of wq_numa_possible_cpumask is allocated by
alloc_cpumask_var_node(). And these entries are used without initializing.
So these entries have wrong value.
When hot-adding and onlining CPU, wq_update_unbound_numa() is called.
wq_update_unbound_numa() calls alloc_unbound_pwq(). And alloc_unbound_pwq()
calls get_unbound_pool(). In get_unbound_pool(), worker_pool->node is set
as follow:
3592 /* if cpumask is contained inside a NUMA node, we belong to that node */
3593 if (wq_numa_enabled) {
3594 for_each_node(node) {
3595 if (cpumask_subset(pool->attrs->cpumask,
3596 wq_numa_possible_cpumask[node])) {
3597 pool->node = node;
3598 break;
3599 }
3600 }
3601 }
But wq_numa_possible_cpumask[node] does not have correct cpumask. So, wrong
node is selected. As a result, kernel panic occurs.
By this patch, all entries of wq_numa_possible_cpumask are allocated by
zalloc_cpumask_var_node to initialize them. And the panic disappeared.
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org
Fixes: bce903809ab3 ("workqueue: add wq_numa_tbl_len and wq_numa_possible_cpumask[]")
Pull irq fixes from Thomas Gleixner:
"A few minor fixlets in ARM SoC irq drivers and a fix for a memory leak
which I introduced in the last round of cleanups :("
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq: Fix memory leak when calling irq_free_hwirqs()
irqchip: spear_shirq: Fix interrupt offset
irqchip: brcmstb-l2: Level-2 interrupts are edge sensitive
irqchip: armada-370-xp: Mask all interrupts during initialization.
irq_free_hwirqs() always calls irq_free_descs() with a cnt == 0
which makes it a no-op since the interrupt count to free is
decremented in itself.
Fixes: 7b6ef1262549f6afc5c881aaef80beb8fd15f908
Signed-off-by: Keith Busch <keith.busch@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Link: http://lkml.kernel.org/r/1404167084-8070-1-git-send-email-keith.busch@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The mutex_trylock() function calls into __mutex_trylock_fastpath() when
trying to obtain the mutex. On 32 bit x86, in the !__HAVE_ARCH_CMPXCHG
case, __mutex_trylock_fastpath() calls directly into __mutex_trylock_slowpath()
regardless of whether or not the mutex is locked.
In __mutex_trylock_slowpath(), we then acquire the wait_lock spinlock, xchg()
lock->count with -1, then set lock->count back to 0 if there are no waiters,
and return true if the prev lock count was 1.
However, if the mutex is already locked, then there isn't much point
in attempting all of the above expensive operations. In this patch, we only
attempt the above trylock operations if the mutex is unlocked.
Signed-off-by: Jason Low <jason.low2@hp.com>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: akpm@linux-foundation.org
Cc: tim.c.chen@linux.intel.com
Cc: paulmck@linux.vnet.ibm.com
Cc: rostedt@goodmis.org
Cc: Waiman.Long@hp.com
Cc: scott.norton@hp.com
Cc: aswin@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1402511843-4721-5-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Upon entering the slowpath in __mutex_lock_common(), we try once more to
acquire the mutex. We only try to acquire if (lock->count >= 0). However,
what we actually want here is to try to acquire if the mutex is unlocked
(lock->count == 1).
This patch changes it so that we only try-acquire the mutex upon entering
the slowpath if it is unlocked, rather than if the lock count is non-negative.
This helps further reduce unnecessary atomic xchg() operations.
Furthermore, this patch uses !mutex_is_locked(lock) to do the initial
checks for if the lock is free rather than directly calling atomic_read()
on the lock->count, in order to improve readability.
Signed-off-by: Jason Low <jason.low2@hp.com>
Acked-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: akpm@linux-foundation.org
Cc: tim.c.chen@linux.intel.com
Cc: paulmck@linux.vnet.ibm.com
Cc: rostedt@goodmis.org
Cc: davidlohr@hp.com
Cc: scott.norton@hp.com
Cc: aswin@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1402511843-4721-4-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
MUTEX_SHOW_NO_WAITER() is a macro which checks for if there are
"no waiters" on a mutex by checking if the lock count is non-negative.
Based on feedback from the discussion in the earlier version of this
patchset, the macro is not very readable.
Furthermore, checking lock->count isn't always the correct way to
determine if there are "no waiters" on a mutex. For example, a negative
count on a mutex really only means that there "potentially" are
waiters. Likewise, there can be waiters on the mutex even if the count is
non-negative. Thus, "MUTEX_SHOW_NO_WAITER" doesn't always do what the name
of the macro suggests.
So this patch deletes the MUTEX_SHOW_NO_WAITERS() macro, directly
use atomic_read() instead of the macro, and adds comments which
elaborate on how the extra atomic_read() checks can help reduce
unnecessary xchg() operations.
Signed-off-by: Jason Low <jason.low2@hp.com>
Acked-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: akpm@linux-foundation.org
Cc: tim.c.chen@linux.intel.com
Cc: paulmck@linux.vnet.ibm.com
Cc: rostedt@goodmis.org
Cc: davidlohr@hp.com
Cc: scott.norton@hp.com
Cc: aswin@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1402511843-4721-3-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
1) Iterate thru all of threads in the system.
Check for all threads, not only for group leaders.
2) Check for p->on_rq instead of p->state and cputime.
Preempted task in !TASK_RUNNING state OR just
created task may be queued, that we want to be
reported too.
3) Use read_lock() instead of write_lock().
This function does not change any structures, and
read_lock() is enough.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Fabian Frederick <fabf@skynet.be>
Cc: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Cc: Konstantin Khorenko <khorenko@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael wang <wangyun@linux.vnet.ibm.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul Turner <pjt@google.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Todd E Brandt <todd.e.brandt@linux.intel.com>
Cc: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403684395.3462.44.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Make rt_rq available for pick_next_task(). Otherwise, their tasks
stay prisoned long time till dead cpu becomes alive again.
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
CC: Konstantin Khorenko <khorenko@parallels.com>
CC: Ben Segall <bsegall@google.com>
CC: Paul Turner <pjt@google.com>
CC: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403684388.3462.43.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We kill rq->rd on the CPU_DOWN_PREPARE stage:
cpuset_cpu_inactive -> cpuset_update_active_cpus -> partition_sched_domains ->
-> cpu_attach_domain -> rq_attach_root -> set_rq_offline
This unthrottles all throttled cfs_rqs.
But the cpu is still able to call schedule() till
take_cpu_down->__cpu_disable()
is called from stop_machine.
This case the tasks from just unthrottled cfs_rqs are pickable
in a standard scheduler way, and they are picked by dying cpu.
The cfs_rqs becomes throttled again, and migrate_tasks()
in migration_call skips their tasks (one more unthrottle
in migrate_tasks()->CPU_DYING does not happen, because rq->rd
is already NULL).
Patch sets runtime_enabled to zero. This guarantees, the runtime
is not accounted, and the cfs_rqs won't exceed given
cfs_rq->runtime_remaining = 1, and tasks will be pickable
in migrate_tasks(). runtime_enabled is recalculated again
when rq becomes online again.
Ben Segall also noticed, we always enable runtime in
tg_set_cfs_bandwidth(). Actually, we should do that for online
cpus only. To prevent races with unthrottle_offline_cfs_rqs()
we take get_online_cpus() lock.
Reviewed-by: Ben Segall <bsegall@google.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
CC: Konstantin Khorenko <khorenko@parallels.com>
CC: Paul Turner <pjt@google.com>
CC: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403684382.3462.42.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reading through the scan period code and comment, it appears the
intent was to slow down NUMA scanning when a majority of accesses
are on the local node, specifically a local:remote ratio of 3:1.
However, the code actually tests local / (local + remote), and
the actual cut-off point was around 30% local accesses, well before
a task has actually converged on a node.
Changing the threshold to 7 means scanning slows down when a task
has around 70% of its accesses local, which appears to match the
intent of the code more closely.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403538095-31256-8-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fix up the best node setting in task_numa_migrate() to deal with a task
in a pseudo-interleaved NUMA group, which is already running in the
best location.
Set the task's preferred nid to the current nid, so task migration is
not retried at a high rate.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403538095-31256-7-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Running "perf bench numa mem -0 -m -P 1000 -p 8 -t 20" on a 4
node system results in 160 runnable threads on a system with 80
CPU threads.
Once a process has nearly converged, with 39 threads on one node
and 1 thread on another node, the remaining thread will be unable
to migrate to its preferred node through a task swap.
However, a simple task move would make the workload converge,
witout causing an imbalance.
Test for this unlikely occurrence, and attempt a task move to
the preferred nid when it happens.
# Running main, "perf bench numa mem -p 8 -t 20 -0 -m -P 1000"
###
# 160 tasks will execute (on 4 nodes, 80 CPUs):
# -1x 0MB global shared mem operations
# -1x 1000MB process shared mem operations
# -1x 0MB thread local mem operations
###
###
#
# 0.0% [0.2 mins] 0/0 1/1 36/2 0/0 [36/3 ] l: 0-0 ( 0) {0-2}
# 0.0% [0.3 mins] 43/3 37/2 39/2 41/3 [ 6/10] l: 0-1 ( 1) {1-2}
# 0.0% [0.4 mins] 42/3 38/2 40/2 40/2 [ 4/9 ] l: 1-2 ( 1) [50.0%] {1-2}
# 0.0% [0.6 mins] 41/3 39/2 40/2 40/2 [ 2/9 ] l: 2-4 ( 2) [50.0%] {1-2}
# 0.0% [0.7 mins] 40/2 40/2 40/2 40/2 [ 0/8 ] l: 3-5 ( 2) [40.0%] ( 41.8s converged)
Without this patch, this same perf bench numa mem run had to
rely on the scheduler load balancer to first balance out the
load (moving a random task), before a task swap could complete
the NUMA convergence.
The load balancer does not normally take action unless the load
difference exceeds 25%. Convergence times of over half an hour
have been observed without this patch.
With this patch, the NUMA balancing code will simply migrate the
task, if that does not cause an imbalance.
Also skip examining a CPU in detail if the improvement on that CPU
is no more than the best we already have.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: chegu_vinod@hp.com
Cc: mgorman@suse.de
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-ggthh0rnh0yua6o5o3p6cr1o@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a task is part of a numa_group, the comparison should always use
the group weight, in order to make workloads converge.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: chegu_vinod@hp.com
Cc: mgorman@suse.de
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403538378-31571-4-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When CONFIG_FAIR_GROUP_SCHED is enabled, the load that a task places
on a CPU is determined by the group the task is in. The active groups
on the source and destination CPU can be different, resulting in a
different load contribution by the same task at its source and at its
destination. As a result, the load needs to be calculated separately
for each CPU, instead of estimated once with task_h_load().
Getting this calculation right allows some workloads to converge,
where previously the last thread could get stuck on another node,
without being able to migrate to its final destination.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403538378-31571-3-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently the NUMA code scales the load on each node with the
amount of CPU power available on that node, but it does not
apply any adjustment to the load of the task that is being
moved over.
On systems with SMT/HT, this results in a task being weighed
much more heavily than a CPU core, and a task move that would
even out the load between nodes being disallowed.
The correct thing is to apply the power correction to the
numbers after we have first applied the move of the tasks'
loads to them.
This also allows us to do the power correction with a multiplication,
rather than a division.
Also drop two function arguments for load_too_unbalanced, since it
takes various factors from env already.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: chegu_vinod@hp.com
Cc: mgorman@suse.de
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403538378-31571-2-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
From task_numa_placement, always try to consolidate the tasks
in a group on the group's top nid.
In case this task is part of a group that is interleaved over
multiple nodes, task_numa_migrate will set the task's preferred
nid to the best node it could find for the task, so this patch
will cause at most one run through task_numa_migrate.
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403538095-31256-2-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a system is lightly loaded (i.e. no more than 1 job per cpu),
attempt to pull job to a cpu before putting it to idle is unnecessary and
can be skipped. This patch adds an indicator so the scheduler can know
when there's no more than 1 active job is on any CPU in the system to
skip needless job pulls.
On a 4 socket machine with a request/response kind of workload from
clients, we saw about 0.13 msec delay when we go through a full load
balance to try pull job from all the other cpus. While 0.1 msec was
spent on processing the request and generating a response, the 0.13 msec
load balance overhead was actually more than the actual work being done.
This overhead can be skipped much of the time for lightly loaded systems.
With this patch, we tested with a netperf request/response workload that
has the server busy with half the cpus in a 4 socket system. We found
the patch eliminated 75% of the load balance attempts before idling a cpu.
The overhead of setting/clearing the indicator is low as we already gather
the necessary info while we call add_nr_running() and update_sd_lb_stats.()
We switch to full load balance load immediately if any cpu got more than
one job on its run queue in add_nr_running. We'll clear the indicator
to avoid load balance when we detect no cpu's have more than one job
when we scan the work queues in update_sg_lb_stats(). We are aggressive
in turning on the load balance and opportunistic in skipping the load
balance.
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Jason Low <jason.low2@hp.com>
Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Alex Shi <alex.shi@linaro.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403551009.2970.613.camel@schen9-DESK
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We don't need 'broadcast' to be set to 'zero or one', but to 'zero or non-zero'
and so the extra operation to convert it to 'zero or one' can be skipped.
Also change type of 'broadcast' to unsigned int, i.e. type of
drv->states[*].flags.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: linaro-kernel@lists.linaro.org
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/0dfbe2976aa108c53e08d3477ea90f6360c1f54c.1403584026.git.viresh.kumar@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If a task has been dequeued, it has been accounted. Do not project
cycles that may or may not ever be accounted to a dequeued task, as
that may make clock_gettime() both inaccurate and non-monotonic.
Protect update_rq_clock() from slight TSC skew while at it.
Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: kosaki.motohiro@jp.fujitsu.com
Cc: pjt@google.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403588980.29711.11.camel@marge.simpson.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
