Use for_each_leaf_cfs_rq() instead of list_for_each_entry_rcu(), this
achieves that load_balance_fair() only iterates those task_groups that
actually have tasks on busiest, and that we iterate bottom-up, trying to
move light groups before the heavier ones.
No idea if it will actually work out to be beneficial in practice, does
anybody have a cgroup workload that might show a difference one way or
the other?
[ Also move update_h_load to sched_fair.c, loosing #ifdef-ery ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Paul Turner <pjt@google.com>
Link: http://lkml.kernel.org/r/1310557009.2586.28.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In dequeue_task_fair() we bail on dequeue when we encounter a parenting entity
with additional weight. However, we perform a double shares update on this
entity as we continue the shares update traversal from this point, despite
dequeue_entity() having already updated its queuing cfs_rq.
Avoid this by starting from the parent when we resume.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110707053059.797714697@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
While looking at check_preempt_wakeup() I realized that we are
potentially updating the wrong entity in the fair-group scheduling
case. In this case the current task's cfs_rq may not be the same as
the one used for the comparison between the waking task and the
existing task's vruntime.
This potentially results in us using a stale vruntime in the
pre-emption decision, providing a small false preference for the
previous task. The effects of this are bounded since we always
perform a hierarchal update on the tick.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/CAPM31R+2Ke2urUZKao5W92_LupdR4AYEv-EZWiJ3tG=tEes2cw@mail.gmail.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Simple test-case,
int main(void)
{
int pid, status;
pid = fork();
if (!pid) {
pause();
assert(0);
return 0x23;
}
assert(ptrace(PTRACE_ATTACH, pid, 0,0) == 0);
assert(wait(&status) == pid);
assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP);
kill(pid, SIGCONT); // <--- also clears STOP_DEQUEUD
assert(ptrace(PTRACE_CONT, pid, 0,0) == 0);
assert(wait(&status) == pid);
assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGCONT);
assert(ptrace(PTRACE_CONT, pid, 0, SIGSTOP) == 0);
assert(wait(&status) == pid);
assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP);
kill(pid, SIGKILL);
return 0;
}
Without the patch it hangs. After the patch SIGSTOP "injected" by the
tracer is not ignored and stops the tracee.
Note also that if this test-case uses, say, SIGWINCH instead of SIGCONT,
everything works without the patch. This can't be right, and this is
confusing.
The problem is that SIGSTOP (or any other sig_kernel_stop() signal) has
no effect without JOBCTL_STOP_DEQUEUED. This means it is simply ignored
after PTRACE_CONT unless JOBCTL_STOP_DEQUEUED was set "by accident", say
it wasn't cleared after initial SIGSTOP sent by PTRACE_ATTACH.
At first glance we could change ptrace_signal() to add STOP_DEQUEUED
after return from ptrace_stop(), but this is not right in case when the
tracer does not change the reported SIGSTOP and SIGCONT comes in between.
This is even more wrong with PT_SEIZED, SIGCONT adds JOBCTL_TRAP_NOTIFY
which will be "lost" during the TRAP_STOP | TRAP_NOTIFY report.
So lets add STOP_DEQUEUED _before_ we report the signal. It has no effect
unless sig_kernel_stop() == T after the tracer resumes us, and in the
latter case the pending STOP_DEQUEUED means no SIGCONT in between, we
should stop.
Note also that if SIGCONT was sent, PT_SEIZED tracee will correctly
report PTRACE_EVENT_STOP/SIGTRAP and thus the tracer can notice the fact
SIGSTOP was cancelled.
Also, move the current->ptrace check from ptrace_signal() to its caller,
get_signal_to_deliver(), this looks more natural.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Terribly embarassing. Don't know how I committed this, but its
KERN_WARNING not KERN_WARN.
This fixes the following compile error:
kernel/time/timekeeping.c: In function ‘__timekeeping_inject_sleeptime’:
kernel/time/timekeeping.c:608: error: ‘KERN_WARN’ undeclared (first use in this function)
kernel/time/timekeeping.c:608: error: (Each undeclared identifier is reported only once
kernel/time/timekeeping.c:608: error: for each function it appears in.)
kernel/time/timekeeping.c:608: error: expected ‘)’ before string constant
make[2]: *** [kernel/time/timekeeping.o] Error 1
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: John Stultz <john.stultz@linaro.org>
The __lock_task_sighand() function calls rcu_read_lock() with interrupts
and preemption enabled, but later calls rcu_read_unlock() with interrupts
disabled. It is therefore possible that this RCU read-side critical
section will be preempted and later RCU priority boosted, which means that
rcu_read_unlock() will call rt_mutex_unlock() in order to deboost itself, but
with interrupts disabled. This results in lockdep splats, so this commit
nests the RCU read-side critical section within the interrupt-disabled
region of code. This prevents the RCU read-side critical section from
being preempted, and thus prevents the attempt to deboost with interrupts
disabled.
It is quite possible that a better long-term fix is to make rt_mutex_unlock()
disable irqs when acquiring the rt_mutex structure's ->wait_lock.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The rcu_read_unlock_special() function relies on in_irq() to exclude
scheduler activity from interrupt level. This fails because exit_irq()
can invoke the scheduler after clearing the preempt_count() bits that
in_irq() uses to determine that it is at interrupt level. This situation
can result in failures as follows:
$task IRQ SoftIRQ
rcu_read_lock()
/* do stuff */
<preempt> |= UNLOCK_BLOCKED
rcu_read_unlock()
--t->rcu_read_lock_nesting
irq_enter();
/* do stuff, don't use RCU */
irq_exit();
sub_preempt_count(IRQ_EXIT_OFFSET);
invoke_softirq()
ttwu();
spin_lock_irq(&pi->lock)
rcu_read_lock();
/* do stuff */
rcu_read_unlock();
rcu_read_unlock_special()
rcu_report_exp_rnp()
ttwu()
spin_lock_irq(&pi->lock) /* deadlock */
rcu_read_unlock_special(t);
Ed can simply trigger this 'easy' because invoke_softirq() immediately
does a ttwu() of ksoftirqd/# instead of doing the in-place softirq stuff
first, but even without that the above happens.
Cure this by also excluding softirqs from the
rcu_read_unlock_special() handler and ensuring the force_irqthreads
ksoftirqd/# wakeup is done from full softirq context.
[ Alternatively, delaying the ->rcu_read_lock_nesting decrement
until after the special handling would make the thing more robust
in the face of interrupts as well. And there is a separate patch
for that. ]
Cc: Thomas Gleixner <tglx@linutronix.de>
Reported-and-tested-by: Ed Tomlinson <edt@aei.ca>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Ensure scheduler_ipi() calls irq_{enter,exit} when it does some actual
work. Traditionally we never did any actual work from the resched IPI
and all magic happened in the return from interrupt path.
Now that we do do some work, we need to ensure irq_{enter,exit} are
called so that we don't confuse things.
This affects things like timekeeping, NO_HZ and RCU, basically
everything with a hook in irq_enter/exit.
Explicit examples of things going wrong are:
sched_clock_cpu() -- has a callback when leaving NO_HZ state to take
a new reading from GTOD and TSC. Without this
callback, time is stuck in the past.
RCU -- needs in_irq() to work in order to avoid some nasty deadlocks
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The addition of RCU read-side critical sections within runqueue and
priority-inheritance lock critical sections introduced some deadlock
cycles, for example, involving interrupts from __rcu_read_unlock()
where the interrupt handlers call wake_up(). This situation can cause
the instance of __rcu_read_unlock() invoked from interrupt to do some
of the processing that would otherwise have been carried out by the
task-level instance of __rcu_read_unlock(). When the interrupt-level
instance of __rcu_read_unlock() is called with a scheduler lock held
from interrupt-entry/exit situations where in_irq() returns false,
deadlock can result.
This commit resolves these deadlocks by using negative values of
the per-task ->rcu_read_lock_nesting counter to indicate that an
instance of __rcu_read_unlock() is in flight, which in turn prevents
instances from interrupt handlers from doing any special processing.
This patch is inspired by Steven Rostedt's earlier patch that similarly
made __rcu_read_unlock() guard against interrupt-mediated recursion
(see https://lkml.org/lkml/2011/7/15/326), but this commit refines
Steven's approach to avoid the need for preemption disabling on the
__rcu_read_unlock() fastpath and to also avoid the need for manipulating
a separate per-CPU variable.
This patch avoids need for preempt_disable() by instead using negative
values of the per-task ->rcu_read_lock_nesting counter. Note that nested
rcu_read_lock()/rcu_read_unlock() pairs are still permitted, but they will
never see ->rcu_read_lock_nesting go to zero, and will therefore never
invoke rcu_read_unlock_special(), thus preventing them from seeing the
RCU_READ_UNLOCK_BLOCKED bit should it be set in ->rcu_read_unlock_special.
This patch also adds a check for ->rcu_read_unlock_special being negative
in rcu_check_callbacks(), thus preventing the RCU_READ_UNLOCK_NEED_QS
bit from being set should a scheduling-clock interrupt occur while
__rcu_read_unlock() is exiting from an outermost RCU read-side critical
section.
Of course, __rcu_read_unlock() can be preempted during the time that
->rcu_read_lock_nesting is negative. This could result in the setting
of the RCU_READ_UNLOCK_BLOCKED bit after __rcu_read_unlock() checks it,
and would also result it this task being queued on the corresponding
rcu_node structure's blkd_tasks list. Therefore, some later RCU read-side
critical section would enter rcu_read_unlock_special() to clean up --
which could result in deadlock if that critical section happened to be in
the scheduler where the runqueue or priority-inheritance locks were held.
This situation is dealt with by making rcu_preempt_note_context_switch()
check for negative ->rcu_read_lock_nesting, thus refraining from
queuing the task (and from setting RCU_READ_UNLOCK_BLOCKED) if we are
already exiting from the outermost RCU read-side critical section (in
other words, we really are no longer actually in that RCU read-side
critical section). In addition, rcu_preempt_note_context_switch()
invokes rcu_read_unlock_special() to carry out the cleanup in this case,
which clears out the ->rcu_read_unlock_special bits and dequeues the task
(if necessary), in turn avoiding needless delay of the current RCU grace
period and needless RCU priority boosting.
It is still illegal to call rcu_read_unlock() while holding a scheduler
lock if the prior RCU read-side critical section has ever had either
preemption or irqs enabled. However, the common use case is legal,
namely where then entire RCU read-side critical section executes with
irqs disabled, for example, when the scheduler lock is held across the
entire lifetime of the RCU read-side critical section.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Allow for sched_domain spans that overlap by giving such domains their
own sched_group list instead of sharing the sched_groups amongst
each-other.
This is needed for machines with more than 16 nodes, because
sched_domain_node_span() will generate a node mask from the
16 nearest nodes without regard if these masks have any overlap.
Currently sched_domains have a sched_group that maps to their child
sched_domain span, and since there is no overlap we share the
sched_group between the sched_domains of the various CPUs. If however
there is overlap, we would need to link the sched_group list in
different ways for each cpu, and hence sharing isn't possible.
In order to solve this, allocate private sched_groups for each CPU's
sched_domain but have the sched_groups share a sched_group_power
structure such that we can uniquely track the power.
Reported-and-tested-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-08bxqw9wis3qti9u5inifh3y@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Given some common flag combinations, particularly -Os, gcc will inline
rcu_read_unlock_special() despite its being in an unlikely() clause.
Use noinline to prohibit this misoptimization.
In addition, move the second barrier() in __rcu_read_unlock() so that
it is not on the common-case code path. This will allow the compiler to
generate better code for the common-case path through __rcu_read_unlock().
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
The RCU_BOOST commits for TREE_PREEMPT_RCU introduced an other-task
write to a new RCU_READ_UNLOCK_BOOSTED bit in the task_struct structure's
->rcu_read_unlock_special field, but, as noted by Steven Rostedt, without
correctly synchronizing all accesses to ->rcu_read_unlock_special.
This could result in bits in ->rcu_read_unlock_special being spuriously
set and cleared due to conflicting accesses, which in turn could result
in deadlocks between the rcu_node structure's ->lock and the scheduler's
rq and pi locks. These deadlocks would result from RCU incorrectly
believing that the just-ended RCU read-side critical section had been
preempted and/or boosted. If that RCU read-side critical section was
executed with either rq or pi locks held, RCU's ensuing (incorrect)
calls to the scheduler would cause the scheduler to attempt to once
again acquire the rq and pi locks, resulting in deadlock. More complex
deadlock cycles are also possible, involving multiple rq and pi locks
as well as locks from multiple rcu_node structures.
This commit fixes synchronization by creating ->rcu_boosted field in
task_struct that is accessed and modified only when holding the ->lock
in the rcu_node structure on which the task is queued (on that rcu_node
structure's ->blkd_tasks list). This results in tasks accessing only
their own current->rcu_read_unlock_special fields, making unsynchronized
access once again legal, and keeping the rcu_read_unlock() fastpath free
of atomic instructions and memory barriers.
The reason that the rcu_read_unlock() fastpath does not need to access
the new current->rcu_boosted field is that this new field cannot
be non-zero unless the RCU_READ_UNLOCK_BLOCKED bit is set in the
current->rcu_read_unlock_special field. Therefore, rcu_read_unlock()
need only test current->rcu_read_unlock_special: if that is zero, then
current->rcu_boosted must also be zero.
This bug does not affect TINY_PREEMPT_RCU because this implementation
of RCU accesses current->rcu_read_unlock_special with irqs disabled,
thus preventing races on the !SMP systems that TINY_PREEMPT_RCU runs on.
Maybe-reported-by: Dave Jones <davej@redhat.com>
Maybe-reported-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
PREEMPT_RCU read-side critical sections blocking an expedited grace
period invoke rcu_report_exp_rnp(). When the last such critical section
has completed, rcu_report_exp_rnp() invokes the scheduler to wake up the
task that invoked synchronize_rcu_expedited() -- needlessly holding the
root rcu_node structure's lock while doing so, thus needlessly providing
a way for RCU and the scheduler to deadlock.
This commit therefore releases the root rcu_node structure's lock before
calling wake_up().
Reported-by: Ed Tomlinson <edt@aei.ca>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Peter Zijlstra
Paul Turner
Ingo Molnar
Oleg Nesterov
Christoph Hellwig
Linus Torvalds
John Stultz
Paul E. McKenney
Lai Jiangshan
Paul E. McKenney
Al Viro