During suspend, we see failures to suspend 1 in 300-500 suspends.
Looking closer, it appears that asynchronous RCU callbacks are being
queued as lazy even though synchronous callbacks are expedited. These
delays appear to not be very welcome by the suspend/resume code as
evidenced by these occasional suspend failures.
This commit modifies call_rcu() to check if rcu_async_should_hurry(),
which will return true if we are in suspend or in-kernel boot.
[ paulmck: Alphabetize local variables. ]
Ignoring the lazy hint makes the 3000 suspend/resume cycles pass
reliably on a 12th gen 12-core Intel CPU, and there is some evidence
that it also slightly speeds up boot performance.
Fixes: 3cb278e73b ("rcu: Make call_rcu() lazy to save power")
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Boot and suspend/resume should not be slowed down in kernels built with
CONFIG_RCU_LAZY=y. In particular, suspend can sometimes fail in such
kernels.
This commit therefore adds rcu_async_hurry(), rcu_async_relax(), and
rcu_async_should_hurry() functions that track whether or not either
a boot or a suspend/resume operation is in progress. This will
enable a later commit to refrain from laziness during those times.
Export rcu_async_should_hurry(), rcu_async_hurry(), and rcu_async_relax()
for later use by rcutorture.
[ paulmck: Apply feedback from Steve Rostedt. ]
Fixes: 3cb278e73b ("rcu: Make call_rcu() lazy to save power")
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_boost_kthread_setaffinity() function is invoked at
rcutree_online_cpu() and rcutree_offline_cpu() time, early in the online
timeline and late in the offline timeline, respectively. It is also
invoked from rcutree_dead_cpu(), however, in the absence of userspace
manipulations (for which userspace must take responsibility), this call
is redundant with that from rcutree_offline_cpu(). This redundancy can
be demonstrated by printing out the relevant cpumasks
This commit therefore removes the call to rcu_boost_kthread_setaffinity()
from rcutree_dead_cpu().
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Because RCU CPU stall warnings are driven from the scheduling-clock
interrupt handler, a workload consisting of a very large number of
short-duration hardware interrupts can result in misleading stall-warning
messages. On systems supporting only a single level of interrupts,
that is, where interrupts handlers cannot be interrupted, this can
produce misleading diagnostics. The stack traces will show the
innocent-bystander interrupted task, not the interrupts that are
at the very least exacerbating the stall.
This situation can be improved by displaying the number of interrupts
and the CPU time that they have consumed. Diagnosing other types
of stalls can be eased by also providing the count of softirqs and
the CPU time that they consumed as well as the number of context
switches and the task-level CPU time consumed.
Consider the following output given this change:
rcu: INFO: rcu_preempt self-detected stall on CPU
rcu: 0-....: (1250 ticks this GP) <omitted>
rcu: hardirqs softirqs csw/system
rcu: number: 624 45 0
rcu: cputime: 69 1 2425 ==> 2500(ms)
This output shows that the number of hard and soft interrupts is small,
there are no context switches, and the system takes up a lot of time. This
indicates that the current task is looping with preemption disabled.
The impact on system performance is negligible because snapshot is
recorded only once for all continuous RCU stalls.
This added debugging information is suppressed by default and can be
enabled by building the kernel with CONFIG_RCU_CPU_STALL_CPUTIME=y or
by booting with rcupdate.rcu_cpu_stall_cputime=1.
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Reviewed-by: Mukesh Ojha <quic_mojha@quicinc.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This patch splits the lists of objects so as to avoid sending any
through RCU that have already been queued for more than one grace
period. These long-term-resident objects are immediately freed.
The remaining short-term-resident objects are queued for later freeing
using queue_rcu_work().
This change avoids delaying workqueue handlers with synchronize_rcu()
invocations. Yes, workqueue handlers are designed to handle blocking,
but avoiding blocking when unnecessary improves performance during
low-memory situations.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The schedule_delayed_monitor_work() function relies on the count of
objects queued into any given kfree_rcu_cpu structure. This count is
used to determine how quickly to schedule passing these objects to RCU.
There are three pipes where pointers can be placed. When any pipe is
offloaded, the kfree_rcu_cpu structure's ->count counter is set to zero,
which is wrong because the other pipes might still be non-empty.
This commit therefore maintains per-pipe counters, and introduces a
krc_count() helper to access the aggregate value of those counters.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The need_offload_krc() function is now lock-free, which gives the
compiler freedom to load old values from plain C-language loads from
the kfree_rcu_cpu struture's ->head pointer. This commit therefore
applied READ_ONCE() to these loads.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently all objects placed into a batch wait for a full grace period
to elapse after that batch is ready to send to RCU. However, this
can unnecessarily delay freeing of the first objects that were added
to the batch. After all, several RCU grace periods might have elapsed
since those objects were added, and if so, there is no point in further
deferring their freeing.
This commit therefore adds per-page grace-period snapshots which are
obtained from get_state_synchronize_rcu(). When the batch is ready
to be passed to call_rcu(), each page's snapshot is checked by passing
it to poll_state_synchronize_rcu(). If a given page's RCU grace period
has already elapsed, its objects are freed immediately by kvfree_rcu_bulk().
Otherwise, these objects are freed after a call to synchronize_rcu().
This approach requires that the pages be traversed in reverse order,
that is, the oldest ones first.
Test example:
kvm.sh --memory 10G --torture rcuscale --allcpus --duration 1 \
--kconfig CONFIG_NR_CPUS=64 \
--kconfig CONFIG_RCU_NOCB_CPU=y \
--kconfig CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y \
--kconfig CONFIG_RCU_LAZY=n \
--bootargs "rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 \
rcuscale.holdoff=20 rcuscale.kfree_loops=10000 \
torture.disable_onoff_at_boot" --trust-make
Before this commit:
Total time taken by all kfree'ers: 8535693700 ns, loops: 10000, batches: 1188, memory footprint: 2248MB
Total time taken by all kfree'ers: 8466933582 ns, loops: 10000, batches: 1157, memory footprint: 2820MB
Total time taken by all kfree'ers: 5375602446 ns, loops: 10000, batches: 1130, memory footprint: 6502MB
Total time taken by all kfree'ers: 7523283832 ns, loops: 10000, batches: 1006, memory footprint: 3343MB
Total time taken by all kfree'ers: 6459171956 ns, loops: 10000, batches: 1150, memory footprint: 6549MB
After this commit:
Total time taken by all kfree'ers: 8560060176 ns, loops: 10000, batches: 1787, memory footprint: 61MB
Total time taken by all kfree'ers: 8573885501 ns, loops: 10000, batches: 1777, memory footprint: 93MB
Total time taken by all kfree'ers: 8320000202 ns, loops: 10000, batches: 1727, memory footprint: 66MB
Total time taken by all kfree'ers: 8552718794 ns, loops: 10000, batches: 1790, memory footprint: 75MB
Total time taken by all kfree'ers: 8601368792 ns, loops: 10000, batches: 1724, memory footprint: 62MB
The reduction in memory footprint is well in excess of an order of
magnitude.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The need_offload_krc() function currently holds the krcp->lock in order
to safely check krcp->head. This commit removes the need for this lock
in that function by updating the krcp->head pointer using WRITE_ONCE()
macro so that readers can carry out lockless loads of that pointer.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The kvfree_rcu() code maintains lists of pages of pointers, but also a
singly linked list, with the latter being used when memory allocation
fails. Traversal of these two types of lists is currently open coded.
This commit simplifies the code by providing kvfree_rcu_bulk() and
kvfree_rcu_list() functions, respectively, to traverse these two types
of lists. This patch does not introduce any functional change.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit improves the readability and maintainability of the
kvfree_rcu() code by switching from an open-coded linked list to
the standard Linux-kernel circular doubly linked list. This patch
does not introduce any functional change.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently a kvfree_call_rcu() takes an offset within a structure as
a second parameter, so a helper such as a kvfree_rcu_arg_2() has to
convert rcu_head and a freed ptr to an offset in order to pass it. That
leads to an extra conversion on macro entry.
Instead of converting, refactor the code in way that a pointer that has
to be freed is passed directly to the kvfree_call_rcu().
This patch does not make any functional change and is transparent to
all kvfree_rcu() users.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit tests synchronize_rcu() and synchronize_rcu_expedited()
at the end of rcu_init(), in addition to the test already at the
beginning of that function. These tests are run only in kernels built
with CONFIG_PROVE_RCU=y.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, rcu_blocking_is_gp() invokes might_sleep() even during early
boot when interrupts are disabled and before the scheduler is scheduling.
This is at best an accident waiting to happen. Therefore, this commit
moves that might_sleep() under an rcu_scheduler_active check in order
to ensure that might_sleep() is not invoked unless sleeping might actually
happen.
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit emphasizes the possibility of concurrent calls to
synchronize_rcu() and synchronize_rcu_expedited() causing one or
the other of the two grace periods being lost from the viewpoint of
poll_state_synchronize_rcu().
If you cannot afford to lose grace periods this way, you should
instead use the _full() variants of the polled RCU API, for
example, poll_state_synchronize_rcu_full().
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, rcu_do_batch() sizes its batches based on the total number
of callbacks in the callback list. This can result in some strange
choices, for example, if there was 12,800 callbacks in the list, but
only 200 were ready to invoke, RCU would invoke 100 at a time (12,800
shifted down by seven bits).
A more measured approach would use the number that were actually ready
to invoke, an approach that has become feasible only recently given the
per-segment ->seglen counts in ->cblist.
This commit therefore bases the batch limit on the number of callbacks
ready to invoke instead of on the total number of callbacks.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit consolidates the initialization and CPU-hotplug code at
the end of kernel/rcu/tree.c. This is strictly a code-motion commit.
No functionality has changed.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit fixes a lockdep false positive in synchronize_rcu() that
can otherwise occur during early boot. Theis fix simply avoids invoking
lockdep if the scheduler has not yet been initialized, that is, during
that portion of boot when interrupts are disabled.
-----BEGIN PGP SIGNATURE-----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=UKUo
-----END PGP SIGNATURE-----
Merge tag 'rcu-urgent.2022.12.17a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu
Pull RCU fix from Paul McKenney:
"This fixes a lockdep false positive in synchronize_rcu() that can
otherwise occur during early boot.
The fix simply avoids invoking lockdep if the scheduler has not yet
been initialized, that is, during that portion of boot when interrupts
are disabled"
* tag 'rcu-urgent.2022.12.17a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu:
rcu: Don't assert interrupts enabled too early in boot
The rcu_poll_gp_seq_end() and rcu_poll_gp_seq_end_unlocked() both check
that interrupts are enabled, as they normally should be when waiting for
an RCU grace period. Except that it is legal to wait for grace periods
during early boot, before interrupts have been enabled for the first time,
and polling for grace periods is required to work during this time.
This can result in false-positive lockdep splats in the presence of
boot-time-initiated tracing.
This commit therefore conditions those interrupts-enabled checks on
rcu_scheduler_active having advanced past RCU_SCHEDULER_INACTIVE, by
which time interrupts have been enabled.
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Steven Rostedt (Google) <rostedt@goodmis.org>
This pull request contains the following branches:
doc.2022.10.20a: Documentation updates. This is the second
in a series from an ongoing review of the RCU documentation.
fixes.2022.10.21a: Miscellaneous fixes.
lazy.2022.11.30a: Introduces a default-off Kconfig option that depends
on RCU_NOCB_CPU that, on CPUs mentioned in the nohz_full or
rcu_nocbs boot-argument CPU lists, causes call_rcu() to introduce
delays. These delays result in significant power savings on
nearly idle Android and ChromeOS systems. These savings range
from a few percent to more than ten percent.
This series also includes several commits that change call_rcu()
to a new call_rcu_hurry() function that avoids these delays in
a few cases, for example, where timely wakeups are required.
Several of these are outside of RCU and thus have acks and
reviews from the relevant maintainers.
srcunmisafe.2022.11.09a: Creates an srcu_read_lock_nmisafe() and an
srcu_read_unlock_nmisafe() for architectures that support NMIs,
but which do not provide NMI-safe this_cpu_inc(). These NMI-safe
SRCU functions are required by the upcoming lockless printk()
work by John Ogness et al.
That printk() series depends on these commits, so if you pull
the printk() series before this one, you will have already
pulled in this branch, plus two more SRCU commits:
0cd7e350ab ("rcu: Make SRCU mandatory")
51f5f78a4f ("srcu: Make Tiny synchronize_srcu() check for readers")
These two commits appear to work well, but do not have
sufficient testing exposure over a long enough time for me to
feel comfortable pushing them unless something in mainline is
definitely going to use them immediately, and currently only
the new printk() work uses them.
torture.2022.10.18c: Changes providing minor but important increases
in test coverage for the new RCU polled-grace-period APIs.
torturescript.2022.10.20a: Changes that avoid redundant kernel builds,
thus providing about a 30% speedup for the torture.sh acceptance
test.
-----BEGIN PGP SIGNATURE-----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=eMOr
-----END PGP SIGNATURE-----
Merge tag 'rcu.2022.12.02a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu
Pull RCU updates from Paul McKenney:
- Documentation updates. This is the second in a series from an ongoing
review of the RCU documentation.
- Miscellaneous fixes.
- Introduce a default-off Kconfig option that depends on RCU_NOCB_CPU
that, on CPUs mentioned in the nohz_full or rcu_nocbs boot-argument
CPU lists, causes call_rcu() to introduce delays.
These delays result in significant power savings on nearly idle
Android and ChromeOS systems. These savings range from a few percent
to more than ten percent.
This series also includes several commits that change call_rcu() to a
new call_rcu_hurry() function that avoids these delays in a few
cases, for example, where timely wakeups are required. Several of
these are outside of RCU and thus have acks and reviews from the
relevant maintainers.
- Create an srcu_read_lock_nmisafe() and an srcu_read_unlock_nmisafe()
for architectures that support NMIs, but which do not provide
NMI-safe this_cpu_inc(). These NMI-safe SRCU functions are required
by the upcoming lockless printk() work by John Ogness et al.
- Changes providing minor but important increases in torture test
coverage for the new RCU polled-grace-period APIs.
- Changes to torturescript that avoid redundant kernel builds, thus
providing about a 30% speedup for the torture.sh acceptance test.
* tag 'rcu.2022.12.02a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (49 commits)
net: devinet: Reduce refcount before grace period
net: Use call_rcu_hurry() for dst_release()
workqueue: Make queue_rcu_work() use call_rcu_hurry()
percpu-refcount: Use call_rcu_hurry() for atomic switch
scsi/scsi_error: Use call_rcu_hurry() instead of call_rcu()
rcu/rcutorture: Use call_rcu_hurry() where needed
rcu/rcuscale: Use call_rcu_hurry() for async reader test
rcu/sync: Use call_rcu_hurry() instead of call_rcu
rcuscale: Add laziness and kfree tests
rcu: Shrinker for lazy rcu
rcu: Refactor code a bit in rcu_nocb_do_flush_bypass()
rcu: Make call_rcu() lazy to save power
rcu: Implement lockdep_rcu_enabled for !CONFIG_DEBUG_LOCK_ALLOC
srcu: Debug NMI safety even on archs that don't require it
srcu: Explain the reason behind the read side critical section on GP start
srcu: Warn when NMI-unsafe API is used in NMI
arch/s390: Add ARCH_HAS_NMI_SAFE_THIS_CPU_OPS Kconfig option
arch/loongarch: Add ARCH_HAS_NMI_SAFE_THIS_CPU_OPS Kconfig option
rcu: Fix __this_cpu_read() lockdep warning in rcu_force_quiescent_state()
rcu-tasks: Make grace-period-age message human-readable
...
Implement timer-based RCU callback batching (also known as lazy
callbacks). With this we save about 5-10% of power consumed due
to RCU requests that happen when system is lightly loaded or idle.
By default, all async callbacks (queued via call_rcu) are marked
lazy. An alternate API call_rcu_hurry() is provided for the few users,
for example synchronize_rcu(), that need the old behavior.
The batch is flushed whenever a certain amount of time has passed, or
the batch on a particular CPU grows too big. Also memory pressure will
flush it in a future patch.
To handle several corner cases automagically (such as rcu_barrier() and
hotplug), we re-use bypass lists which were originally introduced to
address lock contention, to handle lazy CBs as well. The bypass list
length has the lazy CB length included in it. A separate lazy CB length
counter is also introduced to keep track of the number of lazy CBs.
[ paulmck: Fix formatting of inline call_rcu_lazy() definition. ]
[ paulmck: Apply Zqiang feedback. ]
[ paulmck: Apply s/call_rcu_flush/call_rcu_hurry/ feedback from Tejun Heo. ]
Suggested-by: Paul McKenney <paulmck@kernel.org>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Running rcutorture with non-zero fqs_duration module parameter in a
kernel built with CONFIG_PREEMPTION=y results in the following splat:
BUG: using __this_cpu_read() in preemptible [00000000]
code: rcu_torture_fqs/398
caller is __this_cpu_preempt_check+0x13/0x20
CPU: 3 PID: 398 Comm: rcu_torture_fqs Not tainted 6.0.0-rc1-yoctodev-standard+
Call Trace:
<TASK>
dump_stack_lvl+0x5b/0x86
dump_stack+0x10/0x16
check_preemption_disabled+0xe5/0xf0
__this_cpu_preempt_check+0x13/0x20
rcu_force_quiescent_state.part.0+0x1c/0x170
rcu_force_quiescent_state+0x1e/0x30
rcu_torture_fqs+0xca/0x160
? rcu_torture_boost+0x430/0x430
kthread+0x192/0x1d0
? kthread_complete_and_exit+0x30/0x30
ret_from_fork+0x22/0x30
</TASK>
The problem is that rcu_force_quiescent_state() uses __this_cpu_read()
in preemptible code instead of the proper raw_cpu_read(). This commit
therefore changes __this_cpu_read() to raw_cpu_read().
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The commit 3fcd6a230f ("x86/cpu: Avoid cpuinfo-induced IPIing of
idle CPUs") introduced rcu_is_idle_cpu() in order to identify the
current CPU idle state. But commit f3eca381bd ("x86/aperfmperf:
Replace arch_freq_get_on_cpu()") switched to using MAX_SAMPLE_AGE,
so rcu_is_idle_cpu() is no longer used. This commit therefore removes it.
Fixes: f3eca381bd ("x86/aperfmperf: Replace arch_freq_get_on_cpu()")
Signed-off-by: Yipeng Zou <zouyipeng@huawei.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Making polled RCU grace periods account for expedited grace periods
required acquiring the leaf rcu_node structure's lock during early boot,
but after rcu_init() was called. This lock is irq-disabled, but the
code incorrectly assumes that irqs are always disabled when invoking
synchronize_rcu(). The exception is early boot before the scheduler has
started, which means that upon return from synchronize_rcu(), irqs will
be incorrectly enabled.
This commit fixes this bug by using irqsave/irqrestore locking primitives.
Fixes: bf95b2bc3e ("rcu: Switch polled grace-period APIs to ->gp_seq_polled")
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In preparation for RCU lazy changes, wake up the RCU nocb gp thread if
needed after an entrain. This change prevents the RCU barrier callback
from waiting in the queue for several seconds before the lazy callbacks
in front of it are serviced.
Reported-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rnp->qsmask is locklessly accessed from rcutree_dying_cpu(). This
may help avoid load tearing due to concurrent access, KCSAN
issues, and preserve sanity of people reading the mask in tracing.
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_report_dead() function invokes rcu_report_exp_rdp() in order
to force an immediate expedited quiescent state on the outgoing
CPU, and then it invokes rcu_preempt_deferred_qs() to provide any
required deferred quiescent state of either sort. Because the call to
rcu_preempt_deferred_qs() provides the expedited RCU quiescent state if
requested, the call to rcu_report_exp_rdp() is potentially redundant.
One possible issue is a concurrent start of a new expedited RCU
grace period, but this situation is already handled correctly
by __sync_rcu_exp_select_node_cpus(). This function will detect
that the CPU is going offline via the error return from its call
to smp_call_function_single(). In that case, it will retry, and
eventually stop retrying due to rcu_report_exp_rdp() clearing the
->qsmaskinitnext bit corresponding to the target CPU. As a result,
__sync_rcu_exp_select_node_cpus() will report the necessary quiescent
state after dealing with any remaining CPU.
This change assumes that control does not enter rcu_report_dead() within
an RCU read-side critical section, but then again, the surviving call
to rcu_preempt_deferred_qs() has always made this assumption.
This commit therefore removes the call to rcu_report_exp_rdp(), thus
relying on rcu_preempt_deferred_qs() to handle both normal and expedited
quiescent states.
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Userspace execution is a valid quiescent state for RCU Tasks Trace,
but the scheduling-clock interrupt does not currently report such
quiescent states.
Of course, the scheduling-clock interrupt is not strictly speaking
userspace execution. However, the only way that this code is not
in a quiescent state is if something invoked rcu_read_lock_trace(),
and that would be reflected in the ->trc_reader_nesting field in
the task_struct structure. Furthermore, this field is checked by
rcu_tasks_trace_qs(), which is invoked by rcu_tasks_qs() which is in
turn invoked by rcu_note_voluntary_context_switch() in kernels building
at least one of the RCU Tasks flavors. It is therefore safe to invoke
rcu_tasks_trace_qs() from the rcu_sched_clock_irq().
But rcu_tasks_qs() also invokes rcu_tasks_classic_qs() for RCU
Tasks, which lacks the read-side markers provided by RCU Tasks Trace.
This raises the possibility that an RCU Tasks grace period could start
after the interrupt from userspace execution, but before the call to
rcu_sched_clock_irq(). However, it turns out that this is safe because
the RCU Tasks grace period waits for an RCU grace period, which will
wait for the entire scheduling-clock interrupt handler, including any
RCU Tasks read-side critical section that this handler might contain.
This commit therefore updates the rcu_sched_clock_irq() function's
check for usermode execution and its call to rcu_tasks_classic_qs()
to instead check for both usermode execution and interrupt from idle,
and to instead call rcu_note_voluntary_context_switch(). This
consolidates code and provides more faster RCU Tasks Trace
reporting of quiescent states in kernels that do scheduling-clock
interrupts for userspace execution.
[ paulmck: Consolidate checks into rcu_sched_clock_irq(). ]
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Large systems can have hundreds of rcu_node structures, and updating
counters in each of them might slow down booting. This commit therefore
updates only the counters in those rcu_node structures corresponding
to the boot CPU, up to and including the root rcu_node structure.
The counters for the remaining rcu_node structures are updated by the
rcu_scheduler_starting() function, which executes just before the first
non-boot kthread is spawned.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Because both normal and expedited grace periods increment their respective
counters on their pre-scheduler early boot fastpaths, the rcu_gp_oldstate
structure no longer needs its ->rgos_polled field. This commit therefore
removes this field, shrinking this structure so that it is the same size
as an rcu_head structure.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit causes the early boot single-CPU synchronize_rcu() fastpath to
update the rcu_state and rcu_node structures' ->gp_seq and ->gp_seq_needed
counters. This will allow the full-state polled grace-period APIs to
detect all normal grace periods without the need to track the special
combined polling-only counter, which is a step towards removing the
->rgos_polled field from the rcu_gp_oldstate, thereby reducing its size
by one third.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Now that the grace-period fast path can only happen during the
pre-scheduler portion of early boot, this fast path can no longer block
run-time RCU Tasks and RCU Tasks Trace grace periods. This commit
therefore removes the conditional cond_resched_tasks_rcu_qs() invocation.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
It would be good do reduce the size of the rcu_gp_oldstate structure
from three unsigned long instances to two, but this requires that the
boot-time optimized grace periods update the various ->gp_seq fields.
Updating these fields in the rcu_state structure and in all of the
rcu_node structures is at least semi-reasonable, but updating them in
all of the rcu_data structures is a bridge too far. This means that if
there are too many early boot-time grace periods, the ->gp_seq field in
the rcu_data structure cannot be trusted. This commit therefore sets
each rcu_data structure's ->gpwrap field to provide the necessary impetus
for a suitable level of distrust.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The run-time single-CPU grace-period optimization applies only to
kernels built with CONFIG_SMP=y && CONFIG_PREEMPTION=y that are running
on a single-CPU system. But a kernel intended for a single-CPU system
should instead be built with CONFIG_SMP=n, and in any case, single-CPU
systems running Linux no longer appear to be the common case. Plus this
optimization results in the rcu_gp_oldstate structure being half again
larger than it needs to be.
This commit therefore disables the run-time single-CPU grace-period
optimization, so that this optimization applies only during the
pre-scheduler portion of the boot sequence.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The cond_synchronize_rcu() API compresses the combined expedited and
normal grace-period states into a single unsigned long, which conserves
storage, but can miss grace periods in certain cases involving overlapping
normal and expedited grace periods. Missing the occasional grace period
is usually not a problem, but there are use cases that care about each
and every grace period.
This commit therefore adds yet another member of the full-state RCU
grace-period polling API, which is the cond_synchronize_rcu_full()
function. This uses up to three times the storage (rcu_gp_oldstate
structure instead of unsigned long), but is guaranteed not to miss
grace periods.
[ paulmck: Apply feedback from kernel test robot and Julia Lawall. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit removes the blank line preceding the oldstate parameter to
the docbook header for the poll_state_synchronize_rcu() function and
marks uses of this parameter later in that header.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The start_poll_synchronize_rcu() API compresses the combined expedited and
normal grace-period states into a single unsigned long, which conserves
storage, but can miss grace periods in certain cases involving overlapping
normal and expedited grace periods. Missing the occasional grace period
is usually not a problem, but there are use cases that care about each
and every grace period.
This commit therefore adds the next member of the full-state RCU
grace-period polling API, namely the start_poll_synchronize_rcu_full()
function. This uses up to three times the storage (rcu_gp_oldstate
structure instead of unsigned long), but is guaranteed not to miss
grace periods.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The get_state_synchronize_rcu() API compresses the combined expedited and
normal grace-period states into a single unsigned long, which conserves
storage, but can miss grace periods in certain cases involving overlapping
normal and expedited grace periods. Missing the occasional grace period
is usually not a problem, but there are use cases that care about each
and every grace period.
This commit therefore adds the next member of the full-state RCU
grace-period polling API, namely the get_state_synchronize_rcu_full()
function. This uses up to three times the storage (rcu_gp_oldstate
structure instead of unsigned long), but is guaranteed not to miss
grace periods.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The get_completed_synchronize_rcu() and poll_state_synchronize_rcu()
APIs compress the combined expedited and normal grace-period states into a
single unsigned long, which conserves storage, but can miss grace periods
in certain cases involving overlapping normal and expedited grace periods.
Missing the occasional grace period is usually not a problem, but there
are use cases that care about each and every grace period.
This commit therefore adds the first members of the full-state RCU
grace-period polling API, namely the get_completed_synchronize_rcu_full()
and poll_state_synchronize_rcu_full() functions. These use up to three
times the storage (rcu_gp_oldstate structure instead of unsigned long),
but which are guaranteed not to miss grace periods, at least in situations
where the single-CPU grace-period optimization does not apply.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently the monitor work is scheduled with a fixed interval of HZ/20,
which is roughly 50 milliseconds. The drawback of this approach is
low utilization of the 512 page slots in scenarios with infrequence
kvfree_rcu() calls. For example on an Android system:
<snip>
kworker/3:3-507 [003] .... 470.286305: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d0f0dde5 nr_records=6
kworker/6:1-76 [006] .... 470.416613: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000ea0d6556 nr_records=1
kworker/6:1-76 [006] .... 470.416625: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000003e025849 nr_records=9
kworker/3:3-507 [003] .... 471.390000: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000815a8713 nr_records=48
kworker/1:1-73 [001] .... 471.725785: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000fda9bf20 nr_records=3
kworker/1:1-73 [001] .... 471.725833: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000a425b67b nr_records=76
kworker/0:4-1411 [000] .... 472.085673: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000007996be9d nr_records=1
kworker/0:4-1411 [000] .... 472.085728: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d0f0dde5 nr_records=5
kworker/6:1-76 [006] .... 472.260340: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000065630ee4 nr_records=102
<snip>
In many cases, out of 512 slots, fewer than 10 were actually used.
In order to improve batching and make utilization more efficient this
commit sets a drain interval to a fixed 5-seconds interval. Floods are
detected when a page fills quickly, and in that case, the reclaim work
is re-scheduled for the next scheduling-clock tick (jiffy).
After this change:
<snip>
kworker/7:1-371 [007] .... 5630.725708: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000005ab0ffb3 nr_records=121
kworker/7:1-371 [007] .... 5630.989702: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000060c84761 nr_records=47
kworker/7:1-371 [007] .... 5630.989714: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000000babf308 nr_records=510
kworker/7:1-371 [007] .... 5631.553790: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000bb7bd0ef nr_records=169
kworker/7:1-371 [007] .... 5631.553808: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000044c78753 nr_records=510
kworker/5:6-9428 [005] .... 5631.746102: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d98519aa nr_records=123
kworker/4:7-9434 [004] .... 5632.001758: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000526c9d44 nr_records=322
kworker/4:7-9434 [004] .... 5632.002073: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000002c6a8afa nr_records=185
kworker/7:1-371 [007] .... 5632.277515: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000007f4a962f nr_records=510
<snip>
Here, all but one of the cases, more than one hundreds slots were used,
representing an order-of-magnitude improvement.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
As per the comments in include/linux/shrinker.h, .count_objects callback
should return the number of freeable items, but if there are no objects
to free, SHRINK_EMPTY should be returned. The only time 0 is returned
should be when we are unable to determine the number of objects, or the
cache should be skipped for another reason.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The fill_page_cache_func() function allocates couple of pages to store
kvfree_rcu_bulk_data structures. This is a lightweight (GFP_NORETRY)
allocation which can fail under memory pressure. The function will,
however keep retrying even when the previous attempt has failed.
This retrying is in theory correct, but in practice the allocation is
invoked from workqueue context, which means that if the memory reclaim
gets stuck, these retries can hog the worker for quite some time.
Although the workqueues subsystem automatically adjusts concurrency, such
adjustment is not guaranteed to happen until the worker context sleeps.
And the fill_page_cache_func() function's retry loop is not guaranteed
to sleep (see the should_reclaim_retry() function).
And we have seen this function cause workqueue lockups:
kernel: BUG: workqueue lockup - pool cpus=93 node=1 flags=0x1 nice=0 stuck for 32s!
[...]
kernel: pool 74: cpus=37 node=0 flags=0x1 nice=0 hung=32s workers=2 manager: 2146
kernel: pwq 498: cpus=249 node=1 flags=0x1 nice=0 active=4/256 refcnt=5
kernel: in-flight: 1917:fill_page_cache_func
kernel: pending: dbs_work_handler, free_work, kfree_rcu_monitor
Originally, we thought that the root cause of this lockup was several
retries with direct reclaim, but this is not yet confirmed. Furthermore,
we have seen similar lockups without any heavy memory pressure. This
suggests that there are other factors contributing to these lockups.
However, it is not really clear that endless retries are desireable.
So let's make the fill_page_cache_func() function back off after
allocation failure.
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Lin, Yang Shi, Anshuman Khandual and Mike Rapoport
- Some kmemleak fixes from Patrick Wang and Waiman Long
- DAMON updates from SeongJae Park
- memcg debug/visibility work from Roman Gushchin
- vmalloc speedup from Uladzislau Rezki
- more folio conversion work from Matthew Wilcox
- enhancements for coherent device memory mapping from Alex Sierra
- addition of shared pages tracking and CoW support for fsdax, from
Shiyang Ruan
- hugetlb optimizations from Mike Kravetz
- Mel Gorman has contributed some pagealloc changes to improve latency
and realtime behaviour.
- mprotect soft-dirty checking has been improved by Peter Xu
- Many other singleton patches all over the place
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCYuravgAKCRDdBJ7gKXxA
jpqSAQDrXSdII+ht9kSHlaCVYjqRFQz/rRvURQrWQV74f6aeiAD+NHHeDPwZn11/
SPktqEUrF1pxnGQxqLh1kUFUhsVZQgE=
=w/UH
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
"Most of the MM queue. A few things are still pending.
Liam's maple tree rework didn't make it. This has resulted in a few
other minor patch series being held over for next time.
Multi-gen LRU still isn't merged as we were waiting for mapletree to
stabilize. The current plan is to merge MGLRU into -mm soon and to
later reintroduce mapletree, with a view to hopefully getting both
into 6.1-rc1.
Summary:
- The usual batches of cleanups from Baoquan He, Muchun Song, Miaohe
Lin, Yang Shi, Anshuman Khandual and Mike Rapoport
- Some kmemleak fixes from Patrick Wang and Waiman Long
- DAMON updates from SeongJae Park
- memcg debug/visibility work from Roman Gushchin
- vmalloc speedup from Uladzislau Rezki
- more folio conversion work from Matthew Wilcox
- enhancements for coherent device memory mapping from Alex Sierra
- addition of shared pages tracking and CoW support for fsdax, from
Shiyang Ruan
- hugetlb optimizations from Mike Kravetz
- Mel Gorman has contributed some pagealloc changes to improve
latency and realtime behaviour.
- mprotect soft-dirty checking has been improved by Peter Xu
- Many other singleton patches all over the place"
[ XFS merge from hell as per Darrick Wong in
https://lore.kernel.org/all/YshKnxb4VwXycPO8@magnolia/ ]
* tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (282 commits)
tools/testing/selftests/vm/hmm-tests.c: fix build
mm: Kconfig: fix typo
mm: memory-failure: convert to pr_fmt()
mm: use is_zone_movable_page() helper
hugetlbfs: fix inaccurate comment in hugetlbfs_statfs()
hugetlbfs: cleanup some comments in inode.c
hugetlbfs: remove unneeded header file
hugetlbfs: remove unneeded hugetlbfs_ops forward declaration
hugetlbfs: use helper macro SZ_1{K,M}
mm: cleanup is_highmem()
mm/hmm: add a test for cross device private faults
selftests: add soft-dirty into run_vmtests.sh
selftests: soft-dirty: add test for mprotect
mm/mprotect: fix soft-dirty check in can_change_pte_writable()
mm: memcontrol: fix potential oom_lock recursion deadlock
mm/gup.c: fix formatting in check_and_migrate_movable_page()
xfs: fail dax mount if reflink is enabled on a partition
mm/memcontrol.c: remove the redundant updating of stats_flush_threshold
userfaultfd: don't fail on unrecognized features
hugetlb_cgroup: fix wrong hugetlb cgroup numa stat
...
This commit adds expedited grace-period functionality to RCU's polled
grace-period API, adding start_poll_synchronize_rcu_expedited() and
cond_synchronize_rcu_expedited(), which are similar to the existing
start_poll_synchronize_rcu() and cond_synchronize_rcu() functions,
respectively.
Note that although start_poll_synchronize_rcu_expedited() can be invoked
very early, the resulting expedited grace periods are not guaranteed
to start until after workqueues are fully initialized. On the other
hand, both synchronize_rcu() and synchronize_rcu_expedited() can also
be invoked very early, and the resulting grace periods will be taken
into account as they occur.
[ paulmck: Apply feedback from Neeraj Upadhyay. ]
Link: https://lore.kernel.org/all/20220121142454.1994916-1-bfoster@redhat.com/
Link: https://docs.google.com/document/d/1RNKWW9jQyfjxw2E8dsXVTdvZYh0HnYeSHDKog9jhdN8/edit?usp=sharing
Cc: Brian Foster <bfoster@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Ian Kent <raven@themaw.net>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
