The cleanup_srcu_struct_quiesced() function was added because NVME
used WQ_MEM_RECLAIM workqueues and SRCU did not, which meant that
NVME workqueues waiting on SRCU workqueues could result in deadlocks
during low-memory conditions. However, SRCU now also has WQ_MEM_RECLAIM
workqueues, so there is no longer a potential for deadlock. Furthermore,
it turns out to be extremely hard to use cleanup_srcu_struct_quiesced()
correctly due to the fact that SRCU callback invocation accesses the
srcu_struct structure's per-CPU data area just after callbacks are
invoked. Therefore, the usual practice of using srcu_barrier() to wait
for callbacks to be invoked before invoking cleanup_srcu_struct_quiesced()
fails because SRCU's callback-invocation workqueue handler might be
delayed, which can result in cleanup_srcu_struct_quiesced() being invoked
(and thus freeing the per-CPU data) before the SRCU's callback-invocation
workqueue handler is finished using that per-CPU data. Nor is this a
theoretical problem: KASAN emitted use-after-free warnings because of
this problem on actual runs.
In short, NVME can now safely invoke cleanup_srcu_struct(), which
avoids the use-after-free scenario. And cleanup_srcu_struct_quiesced()
is quite difficult to use safely. This commit therefore removes
cleanup_srcu_struct_quiesced(), switching its sole user back to
cleanup_srcu_struct(). This effectively reverts the following pair
of commits:
f7194ac32c ("srcu: Add cleanup_srcu_struct_quiesced()")
4317228ad9 ("nvme: Avoid flush dependency in delete controller flow")
Reported-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Bart Van Assche <bvanassche@acm.org>
If someone fails to drain the corresponding SRCU callbacks (for
example, by failing to invoke srcu_barrier()) before invoking either
cleanup_srcu_struct() or cleanup_srcu_struct_quiesced(), the resulting
diagnostic is an ambiguous use-after-free diagnostic, and even then
only if you are running something like KASAN. This commit therefore
improves SRCU diagnostics by adding checks for in-flight callbacks at
_cleanup_srcu_struct() time.
Note that these diagnostics can still be defeated, for example, by
invoking call_srcu() concurrently with cleanup_srcu_struct(). Which is
a really bad idea, but sometimes all too easy to do. But even then,
these diagnostics have at least some probability of catching the problem.
Reported-by: Sagi Grimberg <sagi@grimberg.me>
Reported-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Tested-by: Bart Van Assche <bvanassche@acm.org>
Replace the license boiler plate with a SPDX license identifier.
While in the area, update an email address.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
srcu_queue_delayed_work_on() disables preemption (and therefore CPU
hotplug in RCU's case) and then checks based on its own accounting if a
CPU is online. If the CPU is online it uses queue_delayed_work_on()
otherwise it fallbacks to queue_delayed_work().
The problem here is that queue_work() on -RT does not work with disabled
preemption.
queue_work_on() works also on an offlined CPU. queue_delayed_work_on()
has the problem that it is possible to program a timer on an offlined
CPU. This timer will fire once the CPU is online again. But until then,
the timer remains programmed and nothing will happen.
Add a local timer which will fire (as requested per delay) on the local
CPU and then enqueue the work on the specific CPU.
RCUtorture testing with SRCU-P for 24h showed no problems.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
In RCU, the distinction between "rsp", "rnp", and "rdp" has served well
for a great many years, but in SRCU, "sp" vs. "sdp" has proven confusing.
This commit therefore renames SRCU's "sp" pointers to "ssp", so that there
is "ssp" for srcu_struct pointer, "snp" for srcu_node pointer, and "sdp"
for srcu_data pointer.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
The srcu_gp_start() function is called with the srcu_struct structure's
->lock held, but not with the srcu_data structure's ->lock. This is
problematic because this function accesses and updates the srcu_data
structure's ->srcu_cblist, which is protected by that lock. Failing to
hold this lock can result in corruption of the SRCU callback lists,
which in turn can result in arbitrarily bad results.
This commit therefore makes srcu_gp_start() acquire the srcu_data
structure's ->lock across the calls to rcu_segcblist_advance() and
rcu_segcblist_accelerate(), thus preventing this corruption.
Reported-by: Bart Van Assche <bvanassche@acm.org>
Reported-by: Christoph Hellwig <hch@infradead.org>
Reported-by: Sebastian Kuzminsky <seb.kuzminsky@gmail.com>
Signed-off-by: Dennis Krein <Dennis.Krein@netapp.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Tested-by: Dennis Krein <Dennis.Krein@netapp.com>
Cc: <stable@vger.kernel.org> # 4.16.x
Ever since cdf7abc461 ("srcu: Allow use of Tiny/Tree SRCU from
both process and interrupt context"), it has been permissible
to use SRCU read-side critical sections in interrupt context.
This allows __call_srcu() to use SRCU read-side critical sections to
prevent a new SRCU grace period from ending before the call to either
srcu_funnel_gp_start() or srcu_funnel_exp_start completes, thus preventing
SRCU grace-period counter overflow during that time.
Note that this does not permit removal of the counter-wrap checks in
srcu_gp_end(). These check are necessary to handle the case where
a given CPU does not interact at all with SRCU for an extended time
period.
This commit therefore adds an SRCU read-side critical section to
__call_srcu() in order to prevent grace period counter wrap during
the funnel-locking process.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Allocating a list_head structure that is almost never used, and, when
used, is used only during early boot (rcu_init() and earlier), is a bit
wasteful. This commit therefore eliminates that list_head in favor of
the one in the work_struct structure. This is safe because the work_struct
structure cannot be used until after rcu_init() returns.
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Event tracing is moving to SRCU in order to take advantage of the fact
that SRCU may be safely used from idle and even offline CPUs. However,
event tracing can invoke call_srcu() very early in the boot process,
even before workqueue_init_early() is invoked (let alone rcu_init()).
Therefore, call_srcu()'s attempts to queue work fail miserably.
This commit therefore detects this situation, and refrains from attempting
to queue work before rcu_init() time, but does everything else that it
would have done, and in addition, adds the srcu_struct to a global list.
The rcu_init() function now invokes a new srcu_init() function, which
is empty if CONFIG_SRCU=n. Otherwise, srcu_init() queues work for
each srcu_struct on the list. This all happens early enough in boot
that there is but a single CPU with interrupts disabled, which allows
synchronization to be dispensed with.
Of course, the queued work won't actually be invoked until after
workqueue_init() is invoked, which happens shortly after the scheduler
is up and running. This means that although call_srcu() may be invoked
any time after per-CPU variables have been set up, there is still a very
narrow window when synchronize_srcu() won't work, and this window
extends from the time that the scheduler starts until the time that
workqueue_init() returns. This can be fixed in a manner similar to
the fix for synchronize_rcu_expedited() and friends, but until someone
actually needs to use synchronize_srcu() during this window, this fix
is added churn for no benefit.
Finally, note that Tree SRCU's new srcu_init() function invokes
queue_work() rather than the queue_delayed_work() function that is
invoked post-boot. The reason is that queue_delayed_work() will (as you
would expect) post a timer, and timers have not yet been initialized.
So use of queue_work() avoids the complaints about use of uninitialized
spinlocks that would otherwise result. Besides, some delay is already
provide by the aforementioned fact that the queued work won't actually
be invoked until after the scheduler is up and running.
Requested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
There now is only one rcu_state structure in a given build of the Linux
kernel, so there is no need to pass it as a parameter to RCU's rcu_node
tree's accessor macros. This commit therefore removes the rsp parameter
from those macros in kernel/rcu/rcu.h, and removes some now-unused rsp
local variables while in the area.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit adds the SRCU grace-period number to the rcutorture statistics
printout, which allows it to be compared to the rcutorture "Writer stall
state" message.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit also adjusts some whitespace while in the area.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Revert string-breaking %s as requested by Andy Shevchenko. ]
SRCU has long used ->srcu_gp_seq, and now RCU uses ->gp_seq. This
commit therefore moves the rcutorture_get_gp_data() function from
a ->gpnum / ->completed pair to ->gp_seq.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit adds the address of the first callback to the per-CPU rcutorture
output in order to allow lost wakeups to be more efficiently tracked down.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit updates the header comment of srcu_funnel_gp_start() to
document the fact that srcu_funnel_gp_start() does the work of
srcu_funnel_exp_start(), in some cases by invoking it directly.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit simply changes some copy-pasta call_rcu() instances to
the correct call_srcu().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The current cleanup_srcu_struct() flushes work, which prevents it
from being invoked from some workqueue contexts, as well as from
atomic (non-blocking) contexts. This patch therefore introduced a
cleanup_srcu_struct_quiesced(), which can be invoked only after all
activity on the specified srcu_struct has completed. This restriction
allows cleanup_srcu_struct_quiesced() to be invoked from workqueue
contexts as well as from atomic contexts.
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Nitzan Carmi <nitzanc@mellanox.com>
Tested-by: Nicholas Piggin <npiggin@gmail.com>
RCU's expedited grace periods can participate in out-of-memory deadlocks
due to all available system_wq kthreads being blocked and there not being
memory available to create more. This commit prevents such deadlocks
by allocating an RCU-specific workqueue_struct at early boot time, and
providing it with a rescuer to ensure forward progress. This uses the
shiny new init_rescuer() function provided by Tejun (but indirectly).
This commit also causes SRCU to use this new RCU-specific
workqueue_struct. Note that SRCU's use of workqueues never blocks them
waiting for readers, so this should be safe from a forward-progress
viewpoint. Note that this moves SRCU from system_power_efficient_wq
to a normal workqueue. In the unlikely event that this results in
measurable degradation, a separate power-efficient workqueue will be
creates for SRCU.
Reported-by: Prateek Sood <prsood@codeaurora.org>
Reported-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Tejun Heo <tj@kernel.org>
The code in srcu_gp_end() inserts a delay every 0x3ff grace periods in
order to prevent SRCU grace-period work from consuming an entire CPU
when there is a long sequence of expedited SRCU grace-period requests.
However, all of SRCU's grace-period work is carried out in workqueues,
which are in turn within kthreads, which are automatically throttled as
needed by the scheduler. In particular, if there is plenty of idle time,
there is no point in throttling.
This commit therefore removes the expedited SRCU grace-period throttling.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Of course, compilers will optimize out a dead code. Anyway, remove
any dead code for better readibility.
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Currently, given a multi-level srcu_node tree, SRCU can scan the full
set of srcu_data structures at each level when cleaning up after a grace
period. This, though harmless otherwise, represents pointless overhead.
This commit therefore eliminates this overhead by scanning the srcu_data
structures only when traversing the leaf srcu_node structures.
Signed-off-by: Ildar Ismagilov <devix84@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
SRCU checks each srcu_data structure's grace-period number for counter
wrap four times per cycle by default. This frequency guarantees that
normal comparisons will detect potential wrap. However, the expedited
grace-period number is not checked. The consquences are not too horrible
(a failure to expedite a grace period when requested), but it would be
good to avoid such things. This commit therefore adds this check to
the expedited grace-period number.
Signed-off-by: Ildar Ismagilov <devix84@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit moves to __func__ for function names in the name of better
resilience to change.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The srcu_funnel_exp_start() function checks to see if the srcu_struct
structure's expedited grace period counter needs updating to reflect a
newly arrived request for an expedited SRCU grace period. Unfortunately,
the check is backwards, so this commit reverses the sense of the test.
Signed-off-by: Ildar Ismagilov <devix84@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Commits c0b334c5bf and ea9b0c8a26 introduced new sparse warnings
by accessing rcu_node->lock directly and ignoring the __private
marker. Introduce a new wrapper and use it. Also fix a similar problem
in srcutree.c introduced by a3883df393.
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Invoking queue_delayed_work() while holding a raw spinlock is forbidden
in -rt kernels, which is exactly what __call_srcu() does, indirectly via
srcu_funnel_gp_start(). This commit therefore downgrades Tree SRCU's
locking from raw to non-raw spinlocks, which works because call_srcu()
is not ever called while holding a raw spinlock.
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Because many of RCU's files have not been included into docbook, a
number of errors have accumulated. This commit fixes them.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Tree RCU guarantees that every online CPU has a memory barrier between
any given grace period and any of that CPU's RCU read-side sections that
must be ordered against that grace period. Since RCU doesn't always
know where read-side critical sections are, the actual implementation
guarantees order against prior and subsequent non-idle non-offline code,
whether in an RCU read-side critical section or not. As a result, there
does not need to be a memory barrier at the end of synchronize_rcu()
and friends because the ordering internal to the grace period has
ordered every CPU's post-grace-period execution against each CPU's
pre-grace-period execution, again for all non-idle online CPUs.
In contrast, SRCU can have non-idle online CPUs that are completely
uninvolved in a given SRCU grace period, for example, a CPU that
never runs any SRCU read-side critical sections and took no part in
the grace-period processing. It is in theory possible for a given
synchronize_srcu()'s wakeup to be delivered to a CPU that was completely
uninvolved in the prior SRCU grace period, which could mean that the
code following that synchronize_srcu() would end up being unordered with
respect to both the grace period and any pre-existing SRCU read-side
critical sections.
This commit therefore adds an smp_mb() to the end of __synchronize_srcu(),
which prevents this scenario from occurring.
Reported-by: Lance Roy <ldr709@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Lance Roy <ldr709@gmail.com>
Cc: <stable@vger.kernel.org> # 4.12.x
This commit adds printing of SRCU lock/unlock totals, which are just
the sums of the per-CPU counts. Saves a bit of mental arithmetic.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit gets rid of some ugly #ifdefs in rcutorture.c by moving
the SRCU status printing to the SRCU implementations.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The function process_srcu() is not invoked outside of srcutree.c, so
this commit makes it static and drops the EXPORT_SYMBOL_GPL().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit uses TREE RCU's rnp->lock wrappers to replace a few explicit
memory barriers. This change also has the advantage of making SRCU's
memory-ordering properties be implemented in roughly the same way as they
are in Tree RCU.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The call_srcu() docbook entry is currently in include/linux/srcu.h,
which causes needless processing for each include point. This commit
therefore moves this entry to kernel/rcu/srcutree.c, which the compiler
reads only once. In addition, the srcu_batches_completed() function is
used only within RCU and its torture-test suites. This commit therefore
also moves this function's declaration from include/linux/srcutiny.h,
include/linux/srcutree.h, and include/linux/srcuclassic.h to
kernel/rcu/rcu.h.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
If a given CPU never happens to ever start an SRCU grace period, the
grace-period sequence counter might wrap. If this CPU were to decide to
finally start a grace period, the state of its sdp->srcu_gp_seq_needed
might make it appear that it has already requested this grace period,
which would prevent starting the grace period. If no other CPU ever started
a grace period again, this would look like a grace-period hang. Even
if some other CPU took pity and started the needed grace period, the
leaf rcu_node structure's ->srcu_data_have_cbs field won't have record
of the fact that this CPU has a callback pending, which would look like
a very localized grace-period hang.
This might seem very unlikely, but SRCU grace periods can take less than
a microsecond on small systems, which means that overflow can happen
in much less than an hour on a 32-bit embedded system. And embedded
systems are especially likely to have long-term idle CPUs. Therefore,
it makes sense to prevent this scenario from happening.
This commit therefore scans each srcu_data structure occasionally,
with frequency controlled by the srcutree.counter_wrap_check kernel
boot parameter. This parameter can be set to something like 255
in order to exercise the counter-wrap-prevention code.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit adds DEBUG_OBJECTS_RCU_HEAD checking to detect call_srcu()
counterparts to double-free bugs.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit makes srcu_bootup_announce() check for non-default values
of the auto-expedite holdoff time exp_holdoff and print a message if so.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Because exp_holdoff is not used outside of srcutree.c, it can be static.
This commit therefore makes this change.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Currently, the only way to tell whether a given kernel is running
Classic, Tiny, or Tree SRCU is to look at the .config file, which
can easily be lost or associated with the wrong kernel. This commit
therefore has Classic and Tree SRCU identify themselves at boot time.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Earlier versions of Tree SRCU were subject to a counter overflow bug that
could theoretically result in too-short grace periods. This commit
eliminates this problem by adding an update-side memory barrier.
The short explanation is that if the updater sums the unlock counts
too late to see a given __srcu_read_unlock() increment, that CPU's
next __srcu_read_lock() must see the new value of ->srcu_idx, thus
incrementing the other bank of counters. This eliminates the possibility
of destructive counter overflow as long as the srcu_read_lock() nesting
level does not exceed floor(ULONG_MAX/NR_CPUS/2), which should be an
eminently reasonable nesting limit, especially on 64-bit systems.
Reported-by: Lance Roy <ldr709@gmail.com>
Suggested-by: Lance Roy <ldr709@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Linu Cherian reported a WARN in cleanup_srcu_struct() when shutting
down a guest running iperf on a VFIO assigned device. This happens
because irqfd_wakeup() calls srcu_read_lock(&kvm->irq_srcu) in interrupt
context, while a worker thread does the same inside kvm_set_irq(). If the
interrupt happens while the worker thread is executing __srcu_read_lock(),
updates to the Classic SRCU ->lock_count[] field or the Tree SRCU
->srcu_lock_count[] field can be lost.
The docs say you are not supposed to call srcu_read_lock() and
srcu_read_unlock() from irq context, but KVM interrupt injection happens
from (host) interrupt context and it would be nice if SRCU supported the
use case. KVM is using SRCU here not really for the "sleepable" part,
but rather due to its IPI-free fast detection of grace periods. It is
therefore not desirable to switch back to RCU, which would effectively
revert commit 719d93cd5f ("kvm/irqchip: Speed up KVM_SET_GSI_ROUTING",
2014-01-16).
However, the docs are overly conservative. You can have an SRCU instance
only has users in irq context, and you can mix process and irq context
as long as process context users disable interrupts. In addition,
__srcu_read_unlock() actually uses this_cpu_dec() on both Tree SRCU and
Classic SRCU. For those two implementations, only srcu_read_lock()
is unsafe.
When Classic SRCU's __srcu_read_unlock() was changed to use this_cpu_dec(),
in commit 5a41344a3d ("srcu: Simplify __srcu_read_unlock() via
this_cpu_dec()", 2012-11-29), __srcu_read_lock() did two increments.
Therefore it kept __this_cpu_inc(), with preempt_disable/enable in
the caller. Tree SRCU however only does one increment, so on most
architectures it is more efficient for __srcu_read_lock() to use
this_cpu_inc(), and any performance differences appear to be down in
the noise.
Unlike Classic and Tree SRCU, Tiny SRCU does increments and decrements on
a single variable. Therefore, as Peter Zijlstra pointed out, Tiny SRCU's
implementation already supports mixed-context use of srcu_read_lock()
and srcu_read_unlock(), at least as long as uses of srcu_read_lock()
and srcu_read_unlock() in each handler are nested and paired properly.
In other words, it is still illegal to (say) invoke srcu_read_lock()
in an interrupt handler and to invoke the matching srcu_read_unlock()
in a softirq handler. Therefore, the only change required for Tiny SRCU
is to its comments.
Fixes: 719d93cd5f ("kvm/irqchip: Speed up KVM_SET_GSI_ROUTING")
Reported-by: Linu Cherian <linuc.decode@gmail.com>
Suggested-by: Linu Cherian <linuc.decode@gmail.com>
Cc: kvm@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Paolo Bonzini <pbonzini@redhat.com>
Linus noticed that the <linux/rcu_segcblist.h> has huge inline functions
which should not be inline at all.
As a first step in cleaning this up, move them all to kernel/rcu/ and
only keep an absolute minimum of data type defines in the header:
before: -rw-r--r-- 1 mingo mingo 22284 May 2 10:25 include/linux/rcu_segcblist.h
after: -rw-r--r-- 1 mingo mingo 3180 May 2 10:22 include/linux/rcu_segcblist.h
More can be done, such as uninlining the large functions, which inlining
is unjustified even if it's an RCU internal matter.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The default value for the kernel boot parameter srcutree.exp_holdoff
is 50 microseconds, which is too long for good Tree SRCU performance
(compared to Classic SRCU) on the workloads tested by Mike Galbraith.
This commit therefore sets the default value to 25 microseconds, which
shows excellent results in Mike's testing.
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Mike Galbraith <efault@gmx.de>
On small systems, in the absence of readers, expedited SRCU grace
periods can complete in less than a microsecond. This means that an
eight-CPU system can have all CPUs doing synchronize_srcu() in a tight
loop and almost always expedite. This might actually be desirable in
some situations, but in general it is a good way to needlessly burn
CPU cycles. And in those situations where it is desirable, your friend
is the function synchronize_srcu_expedited().
For other situations, this commit adds a kernel parameter that specifies
a holdoff between completing the last SRCU grace period and auto-expediting
the next. If the next grace period starts before the holdoff expires,
auto-expediting is disabled. The holdoff is 50 microseconds by default,
and can be tuned to the desired number of nanoseconds. A value of zero
disables auto-expediting.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Mike Galbraith <efault@gmx.de>
Classic SRCU in effect expedites the first synchronize_srcu() when SRCU
is idle, and Mike Galbraith demonstrated that some use cases do in fact
rely on this behavior. In particular, Mike showed that Steven Rostedt's
hotplug stress script takes 55 seconds with Classic SRCU and more than
16 -minutes- when running Tree SRCU. Assuming that each Tree SRCU's call
to synchronize_srcu() takes four milliseconds, this implies that Steven's
test invokes synchronize_srcu() in isolation, but more than once per
200 microseconds. Mike used ftrace to demonstrate that the time between
successive calls to synchronize_srcu() ranged from 118 to 342 microseconds,
with one outlier at 80 milliseconds. This data clearly indicates that
Tree SRCU needs to expedite the first invocation of synchronize_srcu()
during an SRCU idle period.
This commit therefor introduces a srcu_might_be_idle() function that
probabilistically checks whether or not SRCU is idle. This function is
used by synchronize_rcu() as an additional criterion in deciding whether
or not to expedite.
(Hat trick to Peter Zijlstra for his earlier suggestion that this might
in fact be a problem. Which for all I know might have motivated Mike to
look into it.)
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Mike Galbraith <efault@gmx.de>
Commit f60d231a87 ("srcu: Crude control of expedited grace periods")
introduced a per-srcu_struct atomic counter to track outstanding
requests for grace periods. This works, but represents a memory-contention
bottleneck. This commit therefore uses the srcu_node combining tree
to remove this bottleneck.
This commit adds new ->srcu_gp_seq_needed_exp fields to the
srcu_data, srcu_node, and srcu_struct structures, which track the
farthest-in-the-future grace period that must be expedited, which in
turn requires that all nearer-term grace periods also be expedited.
Requests for expediting start with the srcu_data structure, run up
through the srcu_node tree, and end at the srcu_struct structure.
Note that it may be necessary to expedite a grace period that just
now started, and this is handled by a new srcu_funnel_exp_start()
function, which is invoked when the grace period itself is already
in its way, but when that grace period was not marked as expedited.
A new srcu_get_delay() function returns zero if there is at least one
expedited SRCU grace period in flight, or SRCU_INTERVAL otherwise.
This function is used to calculate delays: Normal grace periods
are allowed to extend in order to cover more requests with a given
grace-period computation, which decreases per-request overhead.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Mike Galbraith <efault@gmx.de>
Paul E. McKenney