The commit "use softirq instead of kthreads except when RCU_BOOST=y"
just applied #ifdef in place. This commit is a cleanup that moves
the newly #ifdef'ed code to the header file kernel/rcutree_plugin.h.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This patch #ifdefs RCU kthreads out of the kernel unless RCU_BOOST=y,
thus eliminating context-switch overhead if RCU priority boosting has
not been configured.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Commit a26ac2455ffcf3(rcu: move TREE_RCU from softirq to kthread)
introduced performance regression. In an AIM7 test, this commit degraded
performance by about 40%.
The commit runs rcu callbacks in a kthread instead of softirq. We observed
high rate of context switch which is caused by this. Out test system has
64 CPUs and HZ is 1000, so we saw more than 64k context switch per second
which is caused by RCU's per-CPU kthread. A trace showed that most of
the time the RCU per-CPU kthread doesn't actually handle any callbacks,
but instead just does a very small amount of work handling grace periods.
This means that RCU's per-CPU kthreads are making the scheduler do quite
a bit of work in order to allow a very small amount of RCU-related
processing to be done.
Alex Shi's analysis determined that this slowdown is due to lock
contention within the scheduler. Unfortunately, as Peter Zijlstra points
out, the scheduler's real-time semantics require global action, which
means that this contention is inherent in real-time scheduling. (Yes,
perhaps someone will come up with a workaround -- otherwise, -rt is not
going to do well on large SMP systems -- but this patch will work around
this issue in the meantime. And "the meantime" might well be forever.)
This patch therefore re-introduces softirq processing to RCU, but only
for core RCU work. RCU callbacks are still executed in kthread context,
so that only a small amount of RCU work runs in softirq context in the
common case. This should minimize ksoftirqd execution, allowing us to
skip boosting of ksoftirqd for CONFIG_RCU_BOOST=y kernels.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Tested-by: "Alex,Shi" <alex.shi@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
It is not necessary to use waitqueues for the RCU kthreads because
we always know exactly which thread is to be awakened. In addition,
wake_up() only issues an actual wakeup when there is a thread waiting on
the queue, which was why there was an extra explicit wake_up_process()
to get the RCU kthreads started.
Eliminating the waitqueues (and wake_up()) in favor of wake_up_process()
eliminates the need for the initial wake_up_process() and also shrinks
the data structure size a bit. The wakeup logic is placed in a new
rcu_wait() macro.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
(Note: this was reverted, and is now being re-applied in pieces, with
this being the fifth and final piece. See below for the reason that
it is now felt to be safe to re-apply this.)
Commit d09b62d fixed grace-period synchronization, but left some smp_mb()
invocations in rcu_process_callbacks() that are no longer needed, but
sheer paranoia prevented them from being removed. This commit removes
them and provides a proof of correctness in their absence. It also adds
a memory barrier to rcu_report_qs_rsp() immediately before the update to
rsp->completed in order to handle the theoretical possibility that the
compiler or CPU might move massive quantities of code into a lock-based
critical section. This also proves that the sheer paranoia was not
entirely unjustified, at least from a theoretical point of view.
In addition, the old dyntick-idle synchronization depended on the fact
that grace periods were many milliseconds in duration, so that it could
be assumed that no dyntick-idle CPU could reorder a memory reference
across an entire grace period. Unfortunately for this design, the
addition of expedited grace periods breaks this assumption, which has
the unfortunate side-effect of requiring atomic operations in the
functions that track dyntick-idle state for RCU. (There is some hope
that the algorithms used in user-level RCU might be applied here, but
some work is required to handle the NMIs that user-space applications
can happily ignore. For the short term, better safe than sorry.)
This proof assumes that neither compiler nor CPU will allow a lock
acquisition and release to be reordered, as doing so can result in
deadlock. The proof is as follows:
1. A given CPU declares a quiescent state under the protection of
its leaf rcu_node's lock.
2. If there is more than one level of rcu_node hierarchy, the
last CPU to declare a quiescent state will also acquire the
->lock of the next rcu_node up in the hierarchy, but only
after releasing the lower level's lock. The acquisition of this
lock clearly cannot occur prior to the acquisition of the leaf
node's lock.
3. Step 2 repeats until we reach the root rcu_node structure.
Please note again that only one lock is held at a time through
this process. The acquisition of the root rcu_node's ->lock
must occur after the release of that of the leaf rcu_node.
4. At this point, we set the ->completed field in the rcu_state
structure in rcu_report_qs_rsp(). However, if the rcu_node
hierarchy contains only one rcu_node, then in theory the code
preceding the quiescent state could leak into the critical
section. We therefore precede the update of ->completed with a
memory barrier. All CPUs will therefore agree that any updates
preceding any report of a quiescent state will have happened
before the update of ->completed.
5. Regardless of whether a new grace period is needed, rcu_start_gp()
will propagate the new value of ->completed to all of the leaf
rcu_node structures, under the protection of each rcu_node's ->lock.
If a new grace period is needed immediately, this propagation
will occur in the same critical section that ->completed was
set in, but courtesy of the memory barrier in #4 above, is still
seen to follow any pre-quiescent-state activity.
6. When a given CPU invokes __rcu_process_gp_end(), it becomes
aware of the end of the old grace period and therefore makes
any RCU callbacks that were waiting on that grace period eligible
for invocation.
If this CPU is the same one that detected the end of the grace
period, and if there is but a single rcu_node in the hierarchy,
we will still be in the single critical section. In this case,
the memory barrier in step #4 guarantees that all callbacks will
be seen to execute after each CPU's quiescent state.
On the other hand, if this is a different CPU, it will acquire
the leaf rcu_node's ->lock, and will again be serialized after
each CPU's quiescent state for the old grace period.
On the strength of this proof, this commit therefore removes the memory
barriers from rcu_process_callbacks() and adds one to rcu_report_qs_rsp().
The effect is to reduce the number of memory barriers by one and to
reduce the frequency of execution from about once per scheduling tick
per CPU to once per grace period.
This was reverted do to hangs found during testing by Yinghai Lu and
Ingo Molnar. Frederic Weisbecker supplied Yinghai with tracing that
located the underlying problem, and Frederic also provided the fix.
The underlying problem was that the HARDIRQ_ENTER() macro from
lib/locking-selftest.c invoked irq_enter(), which in turn invokes
rcu_irq_enter(), but HARDIRQ_EXIT() invoked __irq_exit(), which
does not invoke rcu_irq_exit(). This situation resulted in calls
to rcu_irq_enter() that were not balanced by the required calls to
rcu_irq_exit(). Therefore, after these locking selftests completed,
RCU's dyntick-idle nesting count was a large number (for example,
72), which caused RCU to to conclude that the affected CPU was not in
dyntick-idle mode when in fact it was.
RCU would therefore incorrectly wait for this dyntick-idle CPU, resulting
in hangs.
In contrast, with Frederic's patch, which replaces the irq_enter()
in HARDIRQ_ENTER() with an __irq_enter(), these tests don't ever call
either rcu_irq_enter() or rcu_irq_exit(), which works because the CPU
running the test is already marked as not being in dyntick-idle mode.
This means that the rcu_irq_enter() and rcu_irq_exit() calls and RCU
then has no problem working out which CPUs are in dyntick-idle mode and
which are not.
The reason that the imbalance was not noticed before the barrier patch
was applied is that the old implementation of rcu_enter_nohz() ignored
the nesting depth. This could still result in delays, but much shorter
ones. Whenever there was a delay, RCU would IPI the CPU with the
unbalanced nesting level, which would eventually result in rcu_enter_nohz()
being called, which in turn would force RCU to see that the CPU was in
dyntick-idle mode.
The reason that very few people noticed the problem is that the mismatched
irq_enter() vs. __irq_exit() occured only when the kernel was built with
CONFIG_DEBUG_LOCKING_API_SELFTESTS.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This reverts commit e59fb3120b.
This reversion was due to (extreme) boot-time slowdowns on SPARC seen by
Yinghai Lu and on x86 by Ingo
.
This is a non-trivial reversion due to intervening commits.
Conflicts:
Documentation/RCU/trace.txt
kernel/rcutree.c
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Avoid calling into the scheduler while holding core RCU locks. This
allows rcu_read_unlock() to be called while holding the runqueue locks,
but only as long as there was no chance of the RCU read-side critical
section having been preempted. (Otherwise, if RCU priority boosting
is enabled, rcu_read_unlock() might call into the scheduler in order to
unboost itself, which might allows self-deadlock on the runqueue locks
within the scheduler.)
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The "preemptible" spelling is preferable. May as well fix it.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit adds the age in jiffies of the current grace period along
with the duration in jiffies of the longest grace period since boot
to the rcu/rcugp debugfs file. It also adds an additional "O" state
to kthread tracing to differentiate between the kthread waiting due to
having nothing to do on the one hand and waiting due to being on the
wrong CPU on the other hand.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Add tracing to help debugging situations when RCU's kthreads are not
running but are supposed to be.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Includes total number of tasks boosted, number boosted on behalf of each
of normal and expedited grace periods, and statistics on attempts to
initiate boosting that failed for various reasons.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Add priority boosting for TREE_PREEMPT_RCU, similar to that for
TINY_PREEMPT_RCU. This is enabled by the default-off RCU_BOOST
kernel parameter. The priority to which to boost preempted
RCU readers is controlled by the RCU_BOOST_PRIO kernel parameter
(defaulting to real-time priority 1) and the time to wait before
boosting the readers who are blocking a given grace period is
controlled by the RCU_BOOST_DELAY kernel parameter (defaulting to
500 milliseconds).
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
If RCU priority boosting is to be meaningful, callback invocation must
be boosted in addition to preempted RCU readers. Otherwise, in presence
of CPU real-time threads, the grace period ends, but the callbacks don't
get invoked. If the callbacks don't get invoked, the associated memory
doesn't get freed, so the system is still subject to OOM.
But it is not reasonable to priority-boost RCU_SOFTIRQ, so this commit
moves the callback invocations to a kthread, which can be boosted easily.
Also add comments and properly synchronized all accesses to
rcu_cpu_kthread_task, as suggested by Lai Jiangshan.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Combine the current TREE_PREEMPT_RCU ->blocked_tasks[] lists in the
rcu_node structure into a single ->blkd_tasks list with ->gp_tasks
and ->exp_tasks tail pointers. This is in preparation for RCU priority
boosting, which will add a third dimension to the combinatorial explosion
in the ->blocked_tasks[] case, but simply a third pointer in the new
->blkd_tasks case.
Also update documentation to reflect blocked_tasks[] merge
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Commit d09b62d fixed grace-period synchronization, but left some smp_mb()
invocations in rcu_process_callbacks() that are no longer needed, but
sheer paranoia prevented them from being removed. This commit removes
them and provides a proof of correctness in their absence. It also adds
a memory barrier to rcu_report_qs_rsp() immediately before the update to
rsp->completed in order to handle the theoretical possibility that the
compiler or CPU might move massive quantities of code into a lock-based
critical section. This also proves that the sheer paranoia was not
entirely unjustified, at least from a theoretical point of view.
In addition, the old dyntick-idle synchronization depended on the fact
that grace periods were many milliseconds in duration, so that it could
be assumed that no dyntick-idle CPU could reorder a memory reference
across an entire grace period. Unfortunately for this design, the
addition of expedited grace periods breaks this assumption, which has
the unfortunate side-effect of requiring atomic operations in the
functions that track dyntick-idle state for RCU. (There is some hope
that the algorithms used in user-level RCU might be applied here, but
some work is required to handle the NMIs that user-space applications
can happily ignore. For the short term, better safe than sorry.)
This proof assumes that neither compiler nor CPU will allow a lock
acquisition and release to be reordered, as doing so can result in
deadlock. The proof is as follows:
1. A given CPU declares a quiescent state under the protection of
its leaf rcu_node's lock.
2. If there is more than one level of rcu_node hierarchy, the
last CPU to declare a quiescent state will also acquire the
->lock of the next rcu_node up in the hierarchy, but only
after releasing the lower level's lock. The acquisition of this
lock clearly cannot occur prior to the acquisition of the leaf
node's lock.
3. Step 2 repeats until we reach the root rcu_node structure.
Please note again that only one lock is held at a time through
this process. The acquisition of the root rcu_node's ->lock
must occur after the release of that of the leaf rcu_node.
4. At this point, we set the ->completed field in the rcu_state
structure in rcu_report_qs_rsp(). However, if the rcu_node
hierarchy contains only one rcu_node, then in theory the code
preceding the quiescent state could leak into the critical
section. We therefore precede the update of ->completed with a
memory barrier. All CPUs will therefore agree that any updates
preceding any report of a quiescent state will have happened
before the update of ->completed.
5. Regardless of whether a new grace period is needed, rcu_start_gp()
will propagate the new value of ->completed to all of the leaf
rcu_node structures, under the protection of each rcu_node's ->lock.
If a new grace period is needed immediately, this propagation
will occur in the same critical section that ->completed was
set in, but courtesy of the memory barrier in #4 above, is still
seen to follow any pre-quiescent-state activity.
6. When a given CPU invokes __rcu_process_gp_end(), it becomes
aware of the end of the old grace period and therefore makes
any RCU callbacks that were waiting on that grace period eligible
for invocation.
If this CPU is the same one that detected the end of the grace
period, and if there is but a single rcu_node in the hierarchy,
we will still be in the single critical section. In this case,
the memory barrier in step #4 guarantees that all callbacks will
be seen to execute after each CPU's quiescent state.
On the other hand, if this is a different CPU, it will acquire
the leaf rcu_node's ->lock, and will again be serialized after
each CPU's quiescent state for the old grace period.
On the strength of this proof, this commit therefore removes the memory
barriers from rcu_process_callbacks() and adds one to rcu_report_qs_rsp().
The effect is to reduce the number of memory barriers by one and to
reduce the frequency of execution from about once per scheduling tick
per CPU to once per grace period.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The RCU CPU stall warnings can now be controlled using the
rcu_cpu_stall_suppress boot-time parameter or via the same parameter
from sysfs. There is therefore no longer any reason to have
kernel config parameters for this feature. This commit therefore
removes the RCU_CPU_STALL_DETECTOR and RCU_CPU_STALL_DETECTOR_RUNNABLE
kernel config parameters. The RCU_CPU_STALL_TIMEOUT parameter remains
to allow the timeout to be tuned and the RCU_CPU_STALL_VERBOSE parameter
remains to allow task-stall information to be suppressed if desired.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Some recent benchmarks have indicated possible lock contention on the
leaf-level rcu_node locks. This commit therefore limits the number of
CPUs per leaf-level rcu_node structure to 16, in other words, there
can be at most 16 rcu_data structures fanning into a given rcu_node
structure. Prior to this, the limit was 32 on 32-bit systems and 64 on
64-bit systems.
Note that the fanout of non-leaf rcu_node structures is unchanged. The
organization of accesses to the rcu_node tree is such that references
to non-leaf rcu_node structures are much less frequent than to the
leaf structures.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
When we handle the CPU_DYING notifier, the whole system is stopped except
for the current CPU. We therefore need no synchronization with the other
CPUs. This allows us to move any orphaned RCU callbacks directly to the
list of any online CPU without needing to run them through the global
orphan lists. These global orphan lists can therefore be dispensed with.
This commit makes thes changes, though currently victimizes CPU 0 @@@.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The current tracing data is not sufficient to deduce the average time
that a callback spends waiting for a grace period to end. Add three
per-CPU counters recording the number of callbacks invoked (ci), the
number of callbacks orphaned (co), and the number of callbacks adopted
(ca). Given the existing callback queue length (ql), the average wait
time in absence of CPU hotplug operations is ql/ci. The units of wait
time will be in terms of the duration over which ci was measured.
In the presence of CPU hotplug operations, there is room for argument,
but ql/(ci-co+ca) won't steer you too far wrong.
Also fixes a typo called out by Lucas De Marchi <lucas.de.marchi@gmail.com>.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Combine the duplicate definitions of ULONG_CMP_GE(), ULONG_CMP_LT(),
and rcu_preempt_depth() into include/linux/rcupdate.h.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
When using a kernel debugger, a long sojourn in the debugger can get
you lots of RCU CPU stall warnings once you resume. This might not be
helpful, especially if you are using the system console. This patch
therefore allows RCU CPU stall warnings to be suppressed, but only for
the duration of the current set of grace periods.
This differs from Jason's original patch in that it adds support for
tiny RCU and preemptible RCU, and uses a slightly different method for
suppressing the RCU CPU stall warning messages.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Jason Wessel <jason.wessel@windriver.com>
Currently, if RCU CPU stall warnings are enabled, they are enabled
immediately upon boot. They can be manually disabled via /sys (and
also re-enabled via /sys), and are automatically disabled upon panic.
However, some users need RCU CPU stalls to be disabled at boot time,
but to be enabled without rebuilding/rebooting. For example, someone
running a real-time application in production might not want the
additional latency of RCU CPU stall detection in normal operation, but
might need to enable it at any point for fault isolation purposes.
This commit therefore provides a new CONFIG_RCU_CPU_STALL_DETECTOR_RUNNABLE
kernel configuration parameter that maintains the current behavior
(enable at boot) by default, but allows a kernel to be configured
with RCU CPU stall detection built into the kernel, but disabled at
boot time.
Requested-by: Clark Williams <williams@redhat.com>
Requested-by: John Kacur <jkacur@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Also set the default to 60 seconds, up from the previous hard-coded timeout
of 10 seconds. This allows people who care to set short timeouts, while
avoiding people with unusual configurations (make randconfig!!!) from being
bothered with spurious CPU stall warnings.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
&percpu_data is compatible with allocated percpu data.
And we use it and remove the "->rda[NR_CPUS]" array, saving significant
storage on systems with large numbers of CPUs. This does add an additional
level of indirection and thus an additional cache line referenced, but
because ->rda is not used on the read side, this is OK.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Lai Jiangshan noted that up to 10% of the RCU_SOFTIRQ are spurious, and
traced this down to the fact that the current grace-period machinery
will uselessly raise RCU_SOFTIRQ when a given CPU needs to go through
a quiescent state, but has not yet done so. In this situation, there
might well be nothing that RCU_SOFTIRQ can do, and the overhead can be
worth worrying about in the ksoftirqd case. This patch therefore avoids
raising RCU_SOFTIRQ in this situation.
Changes since v1 (http://lkml.org/lkml/2010/3/30/122 from Lai Jiangshan):
o Omit the rcu_qs_pending() prechecks, as they aren't that
much less expensive than the quiescent-state checks.
o Merge with the set_need_resched() patch that reduces IPIs.
o Add the new n_rp_report_qs field to the rcu_pending tracing output.
o Update the tracing documentation accordingly.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The existing RCU CPU stall-warning messages can be confusing, especially
in the case where one CPU detects a single other stalled CPU. In addition,
the console messages did not say which flavor of RCU detected the stall,
which can make it difficult to work out exactly what is causing the stall.
This commit improves these messages.
Requested-by: Dhaval Giani <dhaval.giani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The C standard does not specify the result of an operation that
overflows a signed integer, so such operations need to be
avoided. This patch changes the type of several fields from
"long" to "unsigned long" and adjusts operations as needed.
ULONG_CMP_GE() and ULONG_CMP_LT() macros are introduced to do
the modular comparisons that are appropriate given that overflow
is an expected event.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1266887105-1528-17-git-send-email-paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The comparisons of rsp->gpnum nad rsp->completed in
rcu_process_dyntick() and force_quiescent_state() can be
replaced by the much more clear rcu_gp_in_progress() predicate
function. After doing this, it becomes clear that the
RCU_SAVE_COMPLETED leg of the force_quiescent_state() function's
switch statement is almost completely a no-op. A small change
to the RCU_SAVE_DYNTICK leg renders it a complete no-op, after
which it can be removed. Doing so also eliminates the forcenow
local variable from force_quiescent_state().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12626465501781-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reduce the number and variety of race conditions by prohibiting
the start of a new grace period while force_quiescent_state() is
active. A new fqs_active flag in the rcu_state structure is used
to trace whether or not force_quiescent_state() is active, and
this new flag is tested by rcu_start_gp(). If the CPU that
closed out the last grace period needs another grace period,
this new grace period may be delayed up to one scheduling-clock
tick, but it will eventually get started.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <126264655052-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Enable a fourth level of rcu_node hierarchy for TREE_RCU and
TREE_PREEMPT_RCU. This is for stress-testing and experiemental
purposes only, although in theory this would enable 16,777,216
CPUs on 64-bit systems, though only 1,048,576 CPUs on 32-bit
systems. Normal experimental use of this fourth level will
normally set CONFIG_RCU_FANOUT=2, requiring a 16-CPU system,
though the more adventurous (and more fortunate) experimenters
may wish to chose CONFIG_RCU_FANOUT=3 for 81-CPU systems or even
CONFIG_RCU_FANOUT=4 for 256-CPU systems.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Josh Triplett <josh@joshtriplett.org>
Acked-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12597846161257-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The number of "quiet" functions has grown recently, and the
names are no longer very descriptive. The point of all of these
functions is to do some portion of the task of reporting a
quiescent state, so rename them accordingly:
o cpu_quiet() becomes rcu_report_qs_rdp(), which reports a
quiescent state to the per-CPU rcu_data structure. If this
turns out to be a new quiescent state for this grace period,
then rcu_report_qs_rnp() will be invoked to propagate the
quiescent state up the rcu_node hierarchy.
o cpu_quiet_msk() becomes rcu_report_qs_rnp(), which reports
a quiescent state for a given CPU (or possibly a set of CPUs)
up the rcu_node hierarchy.
o cpu_quiet_msk_finish() becomes rcu_report_qs_rsp(), which
reports a full set of quiescent states to the global rcu_state
structure.
o task_quiet() becomes rcu_report_unblock_qs_rnp(), which reports
a quiescent state due to a task exiting an RCU read-side critical
section that had previously blocked in that same critical section.
As indicated by the new name, this type of quiescent state is
reported up the rcu_node hierarchy (using rcu_report_qs_rnp()
to do so).
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Josh Triplett <josh@joshtriplett.org>
Acked-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12597846163698-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When the last CPU of a given leaf rcu_node structure goes
offline, all of the tasks queued on that leaf rcu_node structure
(due to having blocked in their current RCU read-side critical
sections) are requeued onto the root rcu_node structure. This
requeuing is carried out by rcu_preempt_offline_tasks().
However, it is possible that these queued tasks are the only
thing preventing the leaf rcu_node structure from reporting a
quiescent state up the rcu_node hierarchy. Unfortunately, the
old code would fail to do this reporting, resulting in a
grace-period stall given the following sequence of events:
1. Kernel built for more than 32 CPUs on 32-bit systems or for more
than 64 CPUs on 64-bit systems, so that there is more than one
rcu_node structure. (Or CONFIG_RCU_FANOUT is artificially set
to a number smaller than CONFIG_NR_CPUS.)
2. The kernel is built with CONFIG_TREE_PREEMPT_RCU.
3. A task running on a CPU associated with a given leaf rcu_node
structure blocks while in an RCU read-side critical section
-and- that CPU has not yet passed through a quiescent state
for the current RCU grace period. This will cause the task
to be queued on the leaf rcu_node's blocked_tasks[] array, in
particular, on the element of this array corresponding to the
current grace period.
4. Each of the remaining CPUs corresponding to this same leaf rcu_node
structure pass through a quiescent state. However, the task is
still in its RCU read-side critical section, so these quiescent
states cannot be reported further up the rcu_node hierarchy.
Nevertheless, all bits in the leaf rcu_node structure's ->qsmask
field are now zero.
5. Each of the remaining CPUs go offline. (The events in step
#4 and #5 can happen in any order as long as each CPU passes
through a quiescent state before going offline.)
6. When the last CPU goes offline, __rcu_offline_cpu() will invoke
rcu_preempt_offline_tasks(), which will move the task to the
root rcu_node structure, but without reporting a quiescent state
up the rcu_node hierarchy (and this failure to report a quiescent
state is the bug).
But because this leaf rcu_node structure's ->qsmask field is
already zero and its ->block_tasks[] entries are all empty,
force_quiescent_state() will skip this rcu_node structure.
Therefore, grace periods are now hung.
This patch abstracts some code out of rcu_read_unlock_special(),
calling the result task_quiet() by analogy with cpu_quiet(), and
invokes task_quiet() from both rcu_read_lock_special() and
__rcu_offline_cpu(). Invoking task_quiet() from
__rcu_offline_cpu() reports the quiescent state up the rcu_node
hierarchy, fixing the bug. This ends up requiring a separate
lock_class_key per level of the rcu_node hierarchy, which this
patch also provides.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12589088301770-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impose a clear locking design on the rcu_process_gp_end()
function's use of the ->completed counter. This is done by
creating a ->completed field in the rcu_node structure, which
can safely be accessed under the protection of that structure's
lock. Performance and scalability are maintained by using a
form of double-checked locking, so that rcu_process_gp_end()
only acquires the leaf rcu_node structure's ->lock if a grace
period has recently ended.
This fix reduces rcutorture failure rate by at least two orders
of magnitude under heavy stress with force_quiescent_state()
being invoked artificially often. Without this fix,
unsynchronized access to the ->completed field can cause
rcu_process_gp_end() to advance callbacks whose grace period has
not yet expired. (Bad idea!)
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
Cc: <stable@kernel.org> # .32.x
LKML-Reference: <12571987494069-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Very long RCU read-side critical sections (50 milliseconds or
so) can cause a race between force_quiescent_state() and
rcu_start_gp() as follows on kernel builds with multi-level
rcu_node hierarchies:
1. CPU 0 calls force_quiescent_state(), sees that there is a
grace period in progress, and acquires ->fsqlock.
2. CPU 1 detects the end of the grace period, and so
cpu_quiet_msk_finish() sets rsp->completed to rsp->gpnum.
This operation is carried out under the root rnp->lock,
but CPU 0 has not yet acquired that lock. Note that
rsp->signaled is still RCU_SAVE_DYNTICK from the last
grace period.
3. CPU 1 calls rcu_start_gp(), but no one wants a new grace
period, so it drops the root rnp->lock and returns.
4. CPU 0 acquires the root rnp->lock and picks up rsp->completed
and rsp->signaled, then drops rnp->lock. It then enters the
RCU_SAVE_DYNTICK leg of the switch statement.
5. CPU 2 invokes call_rcu(), and now needs a new grace period.
It calls rcu_start_gp(), which acquires the root rnp->lock, sets
rsp->signaled to RCU_GP_INIT (too bad that CPU 0 is already in
the RCU_SAVE_DYNTICK leg of the switch statement!) and starts
initializing the rcu_node hierarchy. If there are multiple
levels to the hierarchy, it will drop the root rnp->lock and
initialize the lower levels of the hierarchy.
6. CPU 0 notes that rsp->completed has not changed, which permits
both CPU 2 and CPU 0 to try updating it concurrently. If CPU 0's
update prevails, later calls to force_quiescent_state() can
count old quiescent states against the new grace period, which
can in turn result in premature ending of grace periods.
Not good.
This patch adds an RCU_GP_IDLE state for rsp->signaled that is
set initially at boot time and any time a grace period ends.
This prevents CPU 0 from getting into the workings of
force_quiescent_state() in step 4. Additional locking and
checks prevent the concurrent update of rsp->signaled in step 6.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1256742889199-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If the following sequence of events occurs, then
TREE_PREEMPT_RCU will hang waiting for a grace period to
complete, eventually OOMing the system:
o A TREE_PREEMPT_RCU build of the kernel is booted on a system
with more than 64 physical CPUs present (32 on a 32-bit system).
Alternatively, a TREE_PREEMPT_RCU build of the kernel is booted
with RCU_FANOUT set to a sufficiently small value that the
physical CPUs populate two or more leaf rcu_node structures.
o A task is preempted in an RCU read-side critical section
while running on a CPU corresponding to a given leaf rcu_node
structure.
o All CPUs corresponding to this same leaf rcu_node structure
record quiescent states for the current grace period.
o All of these same CPUs go offline (hence the need for enough
physical CPUs to populate more than one leaf rcu_node structure).
This causes the preempted task to be moved to the root rcu_node
structure.
At this point, there is nothing left to cause the quiescent
state to be propagated up the rcu_node tree, so the current
grace period never completes.
The simplest fix, especially after considering the deadlock
possibilities, is to detect this situation when the last CPU is
offlined, and to set that CPU's ->qsmask bit in its leaf
rcu_node structure. This will cause the next invocation of
force_quiescent_state() to end the grace period.
Without this fix, this hang can be triggered in an hour or so on
some machines with rcutorture and random CPU onlining/offlining.
With this fix, these same machines pass a full 10 hours of this
sort of abuse.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <20091015162614.GA19131@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The current interaction between RCU and CPU hotplug requires that
RCU block in CPU notifiers waiting for callbacks to drain.
This can be greatly simplified by having each CPU relinquish its
own callbacks, and for both _rcu_barrier() and CPU_DEAD notifiers
to adopt all callbacks that were previously relinquished.
This change also eliminates the possibility of certain types of
hangs due to the previous practice of waiting for callbacks to be
invoked from within CPU notifiers. If you don't every wait, you
cannot hang.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <1254890898456-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
These issues identified during an old-fashioned face-to-face code
review extending over many hours. This group improves an existing
abstraction and introduces two new ones. It also fixes an RCU
stall-warning bug found while making the other changes.
o Make RCU_INIT_FLAVOR() declare its own variables, removing
the need to declare them at each call site.
o Create an rcu_for_each_leaf() macro that scans the leaf
nodes of the rcu_node tree.
o Create an rcu_for_each_node_breadth_first() macro that does
a breadth-first traversal of the rcu_node tree, AKA
stepping through the array in index-number order.
o If all CPUs corresponding to a given leaf rcu_node
structure go offline, then any tasks queued on that leaf
will be moved to the root rcu_node structure. Therefore,
the stall-warning code must dump out tasks queued on the
root rcu_node structure as well as those queued on the leaf
rcu_node structures.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: akpm@linux-foundation.org
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12541491934126-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Paul E. McKenney