The srcu_struct structure's ->srcu_idx field is accessed locklessly,
so reads must use READ_ONCE(). This commit therefore adds the needed
READ_ONCE() invocation where it was missed.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The srcu_struct structure's ->srcu_gp_seq_needed_exp field is accessed
locklessly, so updates must use WRITE_ONCE(). This commit therefore
adds the needed WRITE_ONCE() invocations.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The srcu_node structure's ->srcu_gp_seq_needed_exp field is accessed
locklessly, so updates must use WRITE_ONCE(). This commit therefore
adds the needed WRITE_ONCE() invocations.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Sparse reports a warning at exit_tasks_rcu_finish(void)
|warning: context imbalance in exit_tasks_rcu_finish()
|- wrong count at exit
To fix this, this commit adds a __releases(&tasks_rcu_exit_srcu).
Given that exit_tasks_rcu_finish() does actually call __srcu_read_lock(),
this not only fixes the warning but also improves on the readability of
the code.
Signed-off-by: Jules Irenge <jbi.octave@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Sparse reports a warning at exit_tasks_rcu_start(void)
|warning: context imbalance in exit_tasks_rcu_start() - wrong count at exit
To fix this, this commit adds an __acquires(&tasks_rcu_exit_srcu).
Given that exit_tasks_rcu_start() does actually call __srcu_read_lock(),
this not only fixes the warning but also improves on the readability of
the code.
Signed-off-by: Jules Irenge <jbi.octave@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
The RCU tasks list of callbacks, rcu_tasks_cbs_head, is sampled locklessly
by rcu_tasks_kthread() when waiting for work to do. This commit therefore
applies READ_ONCE() to that lockless sampling and WRITE_ONCE() to the
single potential store outside of rcu_tasks_kthread.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The __call_rcu() function's header comment refers to a cpu argument
that no longer exists, and the comment of the return path from
rcu_nocb_try_bypass() ignores the non-no-CBs CPU case. This commit
therefore update both comments.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit fixes a spelling mistake in a pr_info() message.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
RCU priority boosting currently is not applied until the grace period
is at least 250 milliseconds old (or the number of milliseconds specified
by the CONFIG_RCU_BOOST_DELAY Kconfig option). Although this has worked
well, it can result in OOM under conditions of RCU callback flooding.
One can argue that the real-time systems using RCU priority boosting
should carefully avoid RCU callback flooding, but one can just as well
argue that an OOM is a rather obnoxious error message.
This commit therefore disables the RCU priority boosting delay when
there are excessive numbers of callbacks queued.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In default configutions, RCU currently waits at least 100 milliseconds
before asking cond_resched() and/or resched_rcu() for help seeking
quiescent states to end a grace period. But 100 milliseconds can be
one good long time during an RCU callback flood, for example, as can
happen when user processes repeatedly open and close files in a tight
loop. These 100-millisecond gaps in successive grace periods during a
callback flood can result in excessive numbers of callbacks piling up,
unnecessarily increasing memory footprint.
This commit therefore asks cond_resched() and/or resched_rcu() for help
as early as the first FQS scan when at least one of the CPUs has more
than 20,000 callbacks queued, a number that can be changed using the new
rcutree.qovld kernel boot parameter. An auxiliary qovld_calc variable
is used to avoid acquisition of locks that have not yet been initialized.
Early tests indicate that this reduces the RCU-callback memory footprint
during rcutorture floods by from 50% to 4x, depending on configuration.
Reported-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reported-by: Tejun Heo <tj@kernel.org>
[ paulmck: Fix bug located by Qian Cai. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Dexuan Cui <decui@microsoft.com>
Tested-by: Qian Cai <cai@lca.pw>
The rcu_data structure's ->core_needs_qs field does not necessarily get
cleared in a timely fashion after the corresponding CPUs' quiescent state
has been reported. From a functional viewpoint, no harm done, but this
can result in excessive invocation of RCU core processing, as witnessed
by the kernel test robot, which saw greatly increased softirq overhead.
This commit therefore restores the rcu_report_qs_rdp() function's
clearing of this field, but only when running on the corresponding CPU.
Cases where some other CPU reports the quiescent state (for example, on
behalf of an idle CPU) are handled by setting this field appropriately
within the __note_gp_changes() function's end-of-grace-period checks.
This handling is carried out regardless of whether the end of a grace
period actually happened, thus handling the case where a CPU goes non-idle
after a quiescent state is reported on its behalf, but before the grace
period ends. This fix also avoids cross-CPU updates to ->core_needs_qs,
While in the area, this commit changes the __note_gp_changes() need_gp
variable's name to need_qs because it is a quiescent state that is needed
from the CPU in question.
Fixes: ed93dfc6bc ("rcu: Confine ->core_needs_qs accesses to the corresponding CPU")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The event is given three parameters, first one is the name
of RCU flavour, second one is the number of elements in array
for free and last one is an address of the array holding
pointers to be freed by the kfree_bulk() function.
To enable the trace event your kernel has to be build with
CONFIG_RCU_TRACE=y, after that it is possible to track the
events using ftrace subsystem.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The kfree_rcu() logic can be improved further by using kfree_bulk()
interface along with "basic batching support" introduced earlier.
The are at least two advantages of using "bulk" interface:
- in case of large number of kfree_rcu() requests kfree_bulk()
reduces the per-object overhead caused by calling kfree()
per-object.
- reduces the number of cache-misses due to "pointer chasing"
between objects which can be far spread between each other.
This approach defines a new kfree_rcu_bulk_data structure that
stores pointers in an array with a specific size. Number of entries
in that array depends on PAGE_SIZE making kfree_rcu_bulk_data
structure to be exactly one page.
Since it deals with "block-chain" technique there is an extra
need in dynamic allocation when a new block is required. Memory
is allocated with GFP_NOWAIT | __GFP_NOWARN flags, i.e. that
allows to skip direct reclaim under low memory condition to
prevent stalling and fails silently under high memory pressure.
The "emergency path" gets maintained when a system is run out of
memory. In that case objects are linked into regular list.
The "rcuperf" was run to analyze this change in terms of memory
consumption and kfree_bulk() throughput.
1) Testing on the Intel(R) Xeon(R) W-2135 CPU @ 3.70GHz, 12xCPUs
with following parameters:
kfree_loops=200000 kfree_alloc_num=1000 kfree_rcu_test=1 kfree_vary_obj_size=1
dev.2020.01.10a branch
Default / CONFIG_SLAB
53607352517 ns, loops: 200000, batches: 1885, memory footprint: 1248MB
53529637912 ns, loops: 200000, batches: 1921, memory footprint: 1193MB
53570175705 ns, loops: 200000, batches: 1929, memory footprint: 1250MB
Patch / CONFIG_SLAB
23981587315 ns, loops: 200000, batches: 810, memory footprint: 1219MB
23879375281 ns, loops: 200000, batches: 822, memory footprint: 1190MB
24086841707 ns, loops: 200000, batches: 794, memory footprint: 1380MB
Default / CONFIG_SLUB
51291025022 ns, loops: 200000, batches: 1713, memory footprint: 741MB
51278911477 ns, loops: 200000, batches: 1671, memory footprint: 719MB
51256183045 ns, loops: 200000, batches: 1719, memory footprint: 647MB
Patch / CONFIG_SLUB
50709919132 ns, loops: 200000, batches: 1618, memory footprint: 456MB
50736297452 ns, loops: 200000, batches: 1633, memory footprint: 507MB
50660403893 ns, loops: 200000, batches: 1628, memory footprint: 429MB
in case of CONFIG_SLAB there is double increase in performance and
slightly higher memory usage. As for CONFIG_SLUB, the performance
figures are better together with lower memory usage.
2) Testing on the HiKey-960, arm64, 8xCPUs with below parameters:
CONFIG_SLAB=y
kfree_loops=200000 kfree_alloc_num=1000 kfree_rcu_test=1
102898760401 ns, loops: 200000, batches: 5822, memory footprint: 158MB
89947009882 ns, loops: 200000, batches: 6715, memory footprint: 115MB
rcuperf shows approximately ~12% better throughput in case of
using "bulk" interface. The "drain logic" or its RCU callback
does the work faster that leads to better throughput.
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Tested-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, nocb_gp_wait() unconditionally complains if there is a
callback not already associated with a grace period. This assumes that
either there was no such callback initially on the one hand, or that
the rcu_advance_cbs() function assigned all such callbacks to a grace
period on the other. However, in theory there are some situations that
would prevent rcu_advance_cbs() from assigning all of the callbacks.
This commit therefore checks for unassociated callbacks immediately after
rcu_advance_cbs() returns, while the corresponding rcu_node structure's
->lock is still held. If there are unassociated callbacks at that point,
the subsequent WARN_ON_ONCE() is disabled.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The ->nocb_lock lockdep assertion is currently guarded by cpu_online(),
which is incorrect for no-CBs CPUs, whose callback lists must be
protected by ->nocb_lock regardless of whether or not the corresponding
CPU is online. This situation could result in failure to detect bugs
resulting from failing to hold ->nocb_lock for offline CPUs.
This commit therefore removes the cpu_online() guard.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit reworks the atomic_cmpxchg() loop in rcu_eqs_special_set()
to do only the initial read from the current CPU's rcu_data structure's
->dynticks field explicitly. On subsequent passes, this value is instead
retained from the failing atomic_cmpxchg() operation.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Sparse reports warning at rcu_nocb_bypass_unlock()
warning: context imbalance in rcu_nocb_bypass_unlock() - unexpected unlock
The root cause is a missing annotation of rcu_nocb_bypass_unlock()
which causes the warning.
This commit therefore adds the missing __releases(&rdp->nocb_bypass_lock)
annotation.
Signed-off-by: Jules Irenge <jbi.octave@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Boqun Feng <boqun.feng@gmail.com>
Sparse reports warning at rcu_nocb_bypass_lock()
|warning: context imbalance in rcu_nocb_bypass_lock() - wrong count at exit
To fix this, this commit adds an __acquires(&rdp->nocb_bypass_lock).
Given that rcu_nocb_bypass_lock() does actually call raw_spin_lock()
when raw_spin_trylock() fails, this not only fixes the warning but also
improves on the readability of the code.
Signed-off-by: Jules Irenge <jbi.octave@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently rcu_check_gp_start_stall() complains if a grace period takes
too long to start, where "too long" is roughly one RCU CPU stall-warning
interval. This has worked well, but there are some debugging Kconfig
options (such as CONFIG_EFI_PGT_DUMP=y) that can make booting take a
very long time, so much so that the stall-warning interval has expired
before RCU's grace-period kthread has even been spawned.
This commit therefore resets the rcu_state.gp_req_activity and
rcu_state.gp_activity timestamps just before the grace-period kthread
is spawned, and modifies the checks and adds ordering to ensure that
if rcu_check_gp_start_stall() sees that the grace-period kthread
has been spawned, that it will also see the resets applied to the
rcu_state.gp_req_activity and rcu_state.gp_activity timestamps.
Reported-by: Qian Cai <cai@lca.pw>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
[ paulmck: Fix whitespace issues reported by Qian Cai. ]
Tested-by: Qian Cai <cai@lca.pw>
[ paulmck: Simplify grace-period wakeup check per Steve Rostedt feedback. ]
The rcu_barrier_callback() function does an atomic_dec_and_test(), and
if it is the last CPU to check in, does the required wakeup. Either way,
it does an event trace. Unfortunately, this is susceptible to the
following sequence of events:
o CPU 0 invokes rcu_barrier_callback(), but atomic_dec_and_test()
says that it is not last. But at this point, CPU 0 is delayed,
perhaps due to an NMI, SMI, or vCPU preemption.
o CPU 1 invokes rcu_barrier_callback(), and atomic_dec_and_test()
says that it is last. So CPU 1 traces completion and does
the needed wakeup.
o The awakened rcu_barrier() function does cleanup and releases
rcu_state.barrier_mutex.
o Another CPU now acquires rcu_state.barrier_mutex and starts
another round of rcu_barrier() processing, including updating
rcu_state.barrier_sequence.
o CPU 0 gets its act back together and does its tracing. Except
that rcu_state.barrier_sequence has already been updated, so
its tracing is incorrect and probably quite confusing.
(Wait! Why did this CPU check in twice for one rcu_barrier()
invocation???)
This commit therefore causes rcu_barrier_callback() to take a
snapshot of the value of rcu_state.barrier_sequence before invoking
atomic_dec_and_test(), thus guaranteeing that the event-trace output
is sensible, even if the timing of the event-trace output might still
be confusing. (Wait! Why did the old rcu_barrier() complete before
all of its CPUs checked in???) But being that this is RCU, only so much
confusion can reasonably be eliminated.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely and due to the mild consequences of the
failure, namely a confusing event trace.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_state structure's ->gp_start field is read locklessly, so this
commit adds the WRITE_ONCE() to an update in order to provide proper
documentation and READ_ONCE()/WRITE_ONCE() pairing.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_segcblist_insert_pend_cbs() function currently (partially)
initializes the rcu_cblist that it pulls callbacks from. However, all
the resulting stores are dead because all callers pass in the address of
an on-stack cblist that is not used afterwards. This commit therefore
removes this pointless initialization.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_node structure's ->boost_kthread_status field is accessed
locklessly, so this commit causes all updates to use WRITE_ONCE() and
all reads to use READ_ONCE().
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_data structure's ->rcu_forced_tick field is read locklessly, so
this commit adds WRITE_ONCE() to all updates and READ_ONCE() to all
lockless reads.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_data structure's ->gpwrap field is read locklessly, and so
this commit adds the required READ_ONCE() to a pair of laods in order
to avoid destructive compiler optimizations.
This data race was reported by KCSAN.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Convert to plural and add a note that this is for Tree RCU.
Signed-off-by: SeongJae Park <sjpark@amazon.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The various RCU structures' ->gp_seq, ->gp_seq_needed, ->gp_req_activity,
and ->gp_activity fields are read locklessly, so they must be updated with
WRITE_ONCE() and, when read locklessly, with READ_ONCE(). This commit makes
these changes.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_segcblist structure's ->tails[] array entries are read
locklessly, so this commit adds the READ_ONCE() to a load in order to
avoid destructive compiler optimizations.
This data race was reported by KCSAN.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_state structure's ->qsmaskinitnext field is read locklessly,
so this commit adds the WRITE_ONCE() to an update in order to provide
proper documentation and READ_ONCE()/WRITE_ONCE() pairing.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely for systems not doing incessant CPU-hotplug
operations.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_state structure's ->gp_req_activity field is read locklessly,
so this commit adds the WRITE_ONCE() to an update in order to provide
proper documentation and READ_ONCE()/WRITE_ONCE() pairing.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_node structure's ->gp_seq field is read locklessly, so this
commit adds the READ_ONCE() to several loads in order to avoid
destructive compiler optimizations.
This data race was reported by KCSAN. Not appropriate for backporting
because this affects only tracing and warnings.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_node structure's ->exp_seq_rq field is read locklessly, so
this commit adds the WRITE_ONCE() to a load in order to provide proper
documentation and READ_ONCE()/WRITE_ONCE() pairing.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_node structure's ->qsmask field is read locklessly, so this
commit adds the WRITE_ONCE() to an update in order to provide proper
documentation and READ_ONCE()/WRITE_ONCE() pairing.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit adds "-g -fno-omit-frame-pointer" to ease interpretation
of KCSAN output, but only for CONFIG_KCSAN=y kerrnels.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_node structure's ->exp_seq_rq field is accessed locklessly, so
updates must use WRITE_ONCE(). This commit therefore adds the needed
WRITE_ONCE() invocation where it was missed.
This data race was reported by KCSAN. Not appropriate for backporting
due to failure being unlikely.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The for_each_leaf_node_cpu_mask() and for_each_leaf_node_possible_cpu()
macros must be invoked only on leaf rcu_node structures. Failing to
abide by this restriction can result in infinite loops on systems with
more than 64 CPUs (or for more than 32 CPUs on 32-bit systems). This
commit therefore adds WARN_ON_ONCE() calls to make misuse of these two
macros easier to debug.
Reported-by: Qian Cai <cai@lca.pw>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Boot-time processing often loops in the kernel longer than one might
prefer, which can prevent expedited grace periods from completing in
a timely manner. This in turn triggers a splat In nohz_full CPUs One
could argue that long-looping code should be fixed, but on the other hand,
boot time is a bit special.
This commit therefore removes the splat. Later commits will add the
splat back in, but in a way that removes false positives.
Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Long ago, RCU used the stop-machine mechanism to implement expedited
grace periods, but no longer does so. This commit therefore removes
the no-longer-needed #includes of linux/stop_machine.h.
Link: https://lwn.net/Articles/805317/
Reported-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The ->srcu_last_gp_end field is accessed from any CPU at any time
by synchronize_srcu(), so non-initialization references need to use
READ_ONCE() and WRITE_ONCE(). This commit therefore makes that change.
Reported-by: syzbot+08f3e9d26e5541e1ecf2@syzkaller.appspotmail.com
Acked-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, force_qs_rnp() uses a for_each_leaf_node_possible_cpu()
loop containing a check of the current CPU's bit in ->qsmask.
This works, but this commit saves three lines by instead using
for_each_leaf_node_cpu_mask(), which combines the functionality of
for_each_leaf_node_possible_cpu() and leaf_node_cpu_bit(). This commit
also replaces the use of the local variable "bit" with rdp->grpmask.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit moves the rcu_{expedited,normal} definitions from
kernel/rcu/update.c to include/linux/rcupdate.h to make sure they are
in sync, and also to avoid the following warning from sparse:
kernel/ksysfs.c:150:5: warning: symbol 'rcu_expedited' was not declared. Should it be static?
kernel/ksysfs.c:167:5: warning: symbol 'rcu_normal' was not declared. Should it be static?
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Only tree_stall.h needs to get name from GP state, so this commit
moves the gp_state_names[] array and the gp_state_getname()
from kernel/rcu/tree.h and kernel/rcu/tree.c, respectively, to
kernel/rcu/tree_stall.h. While moving gp_state_names[], this commit
uses the GCC syntax to ensure that the right string is associated with
the right CPP macro.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The call_rcu() function is an external RCU API that is declared in
include/linux/rcupdate.h. There is thus no point in redeclaring it
in kernel/rcu/tree.h, so this commit removes that redundant declaration.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In the call to trace_rcu_utilization() at the start of the loop in
rcu_cpu_kthread(), "rcu_wait" is incorrect, plus this trace event needs
to be hoisted above the loop to balance with either the "rcu_wait" or
"rcu_yield", depending on how the loop exits. This commit therefore
makes these changes.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The C preprocessor macros SRCU and TINY_RCU should instead be CONFIG_SRCU
and CONFIG_TINY_RCU, respectively in the #f in kernel/rcu/rcu.h. But
there is no harm when "TINY_RCU" is wrongly used, which are always
non-defined, which makes "!defined(TINY_RCU)" always true, which means
the code block is always included, and the included code block doesn't
cause any compilation error so far in CONFIG_TINY_RCU builds. It is
also the reason this change should not be taken in -stable.
This commit adds the needed "CONFIG_" prefix to both macros.
Not for -stable.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In the current code, rcu_nmi_enter_common() might decide to turn on
the tick using tick_dep_set_cpu(), but be delayed just before doing so.
Then the grace-period kthread might notice that the CPU in question had
in fact gone through a quiescent state, thus turning off the tick using
tick_dep_clear_cpu(). The later invocation of tick_dep_set_cpu() would
then incorrectly leave the tick on.
This commit therefore enlists the aid of the leaf rcu_node structure's
->lock to ensure that decisions to enable or disable the tick are
carried out before they can be reversed.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit provides wrapper functions for uses of ->rcu_read_lock_nesting
to improve readability and to ease future changes to support inlining
of __rcu_read_lock() and __rcu_read_unlock().
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_node structure's ->expmask field is updated only when holding the
->lock, but is also accessed locklessly. This means that all ->expmask
updates must use WRITE_ONCE() and all reads carried out without holding
->lock must use READ_ONCE(). This commit therefore changes the lockless
->expmask read in rcu_read_unlock_special() to use READ_ONCE().
Reported-by: syzbot+99f4ddade3c22ab0cf23@syzkaller.appspotmail.com
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Marco Elver <elver@google.com>
In rcu_preempt_deferred_qs_irqrestore(), ->rcu_read_unlock_special is
cleared one piece at a time. Given that the "if" statements in this
function use the copy in "special", this commit removes the clearing
of the individual pieces in favor of clearing ->rcu_read_unlock_special
in one go just after it has been determined to be non-zero.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, the .exp_hint flag is cleared in rcu_read_unlock_special(),
which works, but which can also prevent subsequent rcu_read_unlock() calls
from helping expedite the quiescent state needed by an ongoing expedited
RCU grace period. This commit therefore defers clearing of .exp_hint
from rcu_read_unlock_special() to rcu_preempt_deferred_qs_irqrestore(),
thus ensuring that intervening calls to rcu_read_unlock() have a chance
to help end the expedited grace period.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
CONFIG_PREEMPTION and CONFIG_PREEMPT_RCU are always identical,
but some code depends on CONFIG_PREEMPTION to access to
rcu_preempt functionality. This patch changes CONFIG_PREEMPTION
to CONFIG_PREEMPT_RCU in these cases.
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Now that the kfree_rcu() special-casing has been removed from tree RCU,
this commit removes kfree_call_rcu_nobatch() since it is no longer needed.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit removes kfree_rcu() special-casing and the lazy-callback
handling from Tree RCU. It moves some of this special casing to Tiny RCU,
the removal of which will be the subject of later commits.
This results in a nice negative delta.
Suggested-by: Paul E. McKenney <paulmck@linux.ibm.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Add slab.h #include, thanks to kbuild test robot <lkp@intel.com>. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit applies RCU's debug_objects debugging to the new batched
kfree_rcu() implementations. The object is queued at the kfree_rcu()
call and dequeued during reclaim.
Tested that enabling CONFIG_DEBUG_OBJECTS_RCU_HEAD successfully detects
double kfree_rcu() calls.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Fix IRQ per kbuild test robot <lkp@intel.com> feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
During testing, it was observed that amount of memory consumed due
kfree_rcu() batching is 300-400MB. Previously we had only a single
head_free pointer pointing to the list of rcu_head(s) that are to be
freed after a grace period. Until this list is drained, we cannot queue
any more objects on it since such objects may not be ready to be
reclaimed when the worker thread eventually gets to drainin g the
head_free list.
We can do better by maintaining multiple lists as done by this patch.
Testing shows that memory consumption came down by around 100-150MB with
just adding another list. Adding more than 1 additional list did not
show any improvement.
Suggested-by: Paul E. McKenney <paulmck@linux.ibm.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Code style and initialization handling. ]
[ paulmck: Fix field name, reported by kbuild test robot <lkp@intel.com>. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Because the ->monitor_todo field is always protected by krcp->lock,
this commit downgrades from xchg() to non-atomic unmarked assignment
statements.
Signed-off-by: Joel Fernandes <joel@joelfernandes.org>
[ paulmck: Update to include early-boot kick code. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This test runs kfree_rcu() in a loop to measure performance of the new
kfree_rcu() batching functionality.
The following table shows results when booting with arguments:
rcuperf.kfree_loops=20000 rcuperf.kfree_alloc_num=8000
rcuperf.kfree_rcu_test=1 rcuperf.kfree_no_batch=X
rcuperf.kfree_no_batch=X # Grace Periods Test Duration (s)
X=1 (old behavior) 9133 11.5
X=0 (new behavior) 1732 12.5
On a 16 CPU system with the above boot parameters, we see that the total
number of grace periods that elapse during the test drops from 9133 when
not batching to 1732 when batching (a 5X improvement). The kfree_rcu()
flood itself slows down a bit when batching, though, as shown.
Note that the active memory consumption during the kfree_rcu() flood
does increase to around 200-250MB due to the batching (from around 50MB
without batching). However, this memory consumption is relatively
constant. In other words, the system is able to keep up with the
kfree_rcu() load. The memory consumption comes down considerably if
KFREE_DRAIN_JIFFIES is increased from HZ/50 to HZ/80. A later patch will
reduce memory consumption further by using multiple lists.
Also, when running the test, please disable CONFIG_DEBUG_PREEMPT and
CONFIG_PROVE_RCU for realistic comparisons with/without batching.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Recently a discussion about stability and performance of a system
involving a high rate of kfree_rcu() calls surfaced on the list [1]
which led to another discussion how to prepare for this situation.
This patch adds basic batching support for kfree_rcu(). It is "basic"
because we do none of the slab management, dynamic allocation, code
moving or any of the other things, some of which previous attempts did
[2]. These fancier improvements can be follow-up patches and there are
different ideas being discussed in those regards. This is an effort to
start simple, and build up from there. In the future, an extension to
use kfree_bulk and possibly per-slab batching could be done to further
improve performance due to cache-locality and slab-specific bulk free
optimizations. By using an array of pointers, the worker thread
processing the work would need to read lesser data since it does not
need to deal with large rcu_head(s) any longer.
Torture tests follow in the next patch and show improvements of around
5x reduction in number of grace periods on a 16 CPU system. More
details and test data are in that patch.
There is an implication with rcu_barrier() with this patch. Since the
kfree_rcu() calls can be batched, and may not be handed yet to the RCU
machinery in fact, the monitor may not have even run yet to do the
queue_rcu_work(), there seems no easy way of implementing rcu_barrier()
to wait for those kfree_rcu()s that are already made. So this means a
kfree_rcu() followed by an rcu_barrier() does not imply that memory will
be freed once rcu_barrier() returns.
Another implication is higher active memory usage (although not
run-away..) until the kfree_rcu() flooding ends, in comparison to
without batching. More details about this are in the second patch which
adds an rcuperf test.
Finally, in the near future we will get rid of kfree_rcu() special casing
within RCU such as in rcu_do_batch and switch everything to just
batching. Currently we don't do that since timer subsystem is not yet up
and we cannot schedule the kfree_rcu() monitor as the timer subsystem's
lock are not initialized. That would also mean getting rid of
kfree_call_rcu_nobatch() entirely.
[1] http://lore.kernel.org/lkml/20190723035725-mutt-send-email-mst@kernel.org
[2] https://lkml.org/lkml/2017/12/19/824
Cc: kernel-team@android.com
Cc: kernel-team@lge.com
Co-developed-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
[ paulmck: Applied 0day and Paul Walmsley feedback on ->monitor_todo. ]
[ paulmck: Make it work during early boot. ]
[ paulmck: Add a crude early boot self-test. ]
[ paulmck: Style adjustments and experimental docbook structure header. ]
Link: https://lore.kernel.org/lkml/alpine.DEB.2.21.9999.1908161931110.32497@viisi.sifive.com/T/#me9956f66cb611b95d26ae92700e1d901f46e8c59
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Each of rcu_state, rcu_rnp_online_cpus(), rcu_dynticks_curr_cpu_in_eqs(),
and rcu_dynticks_snap() are used only in the kernel/rcu/tree.o translation
unit, and may thus be marked static. This commit therefore makes this
change.
Reported-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
This commit switches from static structure to dynamic allocation
for rcu_fwds as another step towards providing multiple call_rcu()
forward-progress kthreads.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit threads pointers to rcu_fwd structures through the remaining
functions using rcu_fwds directly, namely rcu_torture_fwd_prog_cbfree(),
rcutorture_oom_notify() and rcu_torture_fwd_prog_init().
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In order to add multiple call_rcu() forward-progress kthreads, it will
be necessary to dynamically allocate and initialize. This commit
therefore moves the initialization from compile time to instead
immediately precede thread-creation time.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In order to add multiple kthreads, it will be necessary to allow
the various functions to operate on a pointer to their kthread's
rcu_fwd structure. This commit therefore starts the process of
adding the needed "struct rcu_fwd" parameters and arguments to the
various callback forward-progress functions.
Note that rcutorture_oom_notify() and rcu_torture_fwd_cb_hist() will
eventually need to iterate over all kthreads' rcu_fwd structures.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Now that RCU behaves reasonably well with the current single-kthread
call_rcu() forward-progress testing, it is time to add more kthreads.
This commit takes a first step towards that goal by wrapping what
will be the per-kthread data into a new rcu_fwd structure.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The config option `CONFIG_PREEMPT' is used for the preemption model
"Low-Latency Desktop". The config option `CONFIG_PREEMPTION' is enabled
when kernel preemption is enabled which is true for the preemption model
`CONFIG_PREEMPT' and `CONFIG_PREEMPT_RT'.
Use `CONFIG_PREEMPTION' if it applies to both preemption models and not
just to `CONFIG_PREEMPT'.
Cc: "Paul E. McKenney" <paulmck@kernel.org>
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>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: rcu@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently PREEMPT_RCU and TREE_RCU are mutually exclusive Kconfig
options. But PREEMPT_RCU actually specifies a kind of TREE_RCU,
namely a preemptible TREE_RCU. This commit therefore makes PREEMPT_RCU
be a modifer to the TREE_RCU Kconfig option. This has the benefit of
simplifying several of the #if expressions that formerly needed to
check both, but now need only check one or the other.
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Lai Jiangshan <jiangshanlai@gmail.com>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_preempt_check_blocked_tasks() function has a comment
that states that the rcu_node structure's ->lock must be held,
which might be informative, but which carries little weight if
not read. This commit therefore removes this comment in favor of
raw_lockdep_assert_held_rcu_node(), which will complain quite
visibly if the required lock is not held.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_gp_fqs_check_wake() function uses rcu_preempt_blocked_readers_cgp()
to read ->gp_tasks while other cpus might overwrite this field.
We need READ_ONCE()/WRITE_ONCE() pairs to avoid compiler
tricks and KCSAN splats like the following :
BUG: KCSAN: data-race in rcu_gp_fqs_check_wake / rcu_preempt_deferred_qs_irqrestore
write to 0xffffffff85a7f190 of 8 bytes by task 7317 on cpu 0:
rcu_preempt_deferred_qs_irqrestore+0x43d/0x580 kernel/rcu/tree_plugin.h:507
rcu_read_unlock_special+0xec/0x370 kernel/rcu/tree_plugin.h:659
__rcu_read_unlock+0xcf/0xe0 kernel/rcu/tree_plugin.h:394
rcu_read_unlock include/linux/rcupdate.h:645 [inline]
__ip_queue_xmit+0x3b0/0xa40 net/ipv4/ip_output.c:533
ip_queue_xmit+0x45/0x60 include/net/ip.h:236
__tcp_transmit_skb+0xdeb/0x1cd0 net/ipv4/tcp_output.c:1158
__tcp_send_ack+0x246/0x300 net/ipv4/tcp_output.c:3685
tcp_send_ack+0x34/0x40 net/ipv4/tcp_output.c:3691
tcp_cleanup_rbuf+0x130/0x360 net/ipv4/tcp.c:1575
tcp_recvmsg+0x633/0x1a30 net/ipv4/tcp.c:2179
inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838
sock_recvmsg_nosec net/socket.c:871 [inline]
sock_recvmsg net/socket.c:889 [inline]
sock_recvmsg+0x92/0xb0 net/socket.c:885
sock_read_iter+0x15f/0x1e0 net/socket.c:967
call_read_iter include/linux/fs.h:1864 [inline]
new_sync_read+0x389/0x4f0 fs/read_write.c:414
read to 0xffffffff85a7f190 of 8 bytes by task 10 on cpu 1:
rcu_gp_fqs_check_wake kernel/rcu/tree.c:1556 [inline]
rcu_gp_fqs_check_wake+0x93/0xd0 kernel/rcu/tree.c:1546
rcu_gp_fqs_loop+0x36c/0x580 kernel/rcu/tree.c:1611
rcu_gp_kthread+0x143/0x220 kernel/rcu/tree.c:1768
kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253
ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 10 Comm: rcu_preempt Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
[ paulmck: Added another READ_ONCE() for RCU CPU stall warnings. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Commit 18cd8c93e6 ("rcu/nocb: Print gp/cb kthread hierarchy if
dump_tree") added print statements to rcu_organize_nocb_kthreads for
debugging, but incorrectly guarded them, causing the function to always
spew out its message.
This patch fixes it by guarding both pr_alert statements with dump_tree,
while also changing the second pr_alert to a pr_cont, to print the
hierarchy in a single line (assuming that's how it was supposed to
work).
Fixes: 18cd8c93e6 ("rcu/nocb: Print gp/cb kthread hierarchy if dump_tree")
Signed-off-by: Stefan Reiter <stefan@pimaker.at>
[ paulmck: Make single-nocbs-CPU GP kthreads look less erroneous. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
An expedited grace period can be stalled by a nohz_full CPU looping
in kernel context. This possibility is currently handled by some
carefully crafted checks in rcu_read_unlock_special() that enlist help
from ksoftirqd when permitted by the scheduler. However, it is exactly
these checks that require the scheduler avoid holding any of its rq or
pi locks across rcu_read_unlock() without also having held them across
the entire RCU read-side critical section.
It would therefore be very nice if expedited grace periods could
handle nohz_full CPUs looping in kernel context without such checks.
This commit therefore adds code to the expedited grace period's wait
and cleanup code that forces the scheduler-clock interrupt on for CPUs
that fail to quickly supply a quiescent state. "Quickly" is currently
a hard-coded single-jiffy delay.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
After RCU flavor consolidation, synchronize_sched_expedited_wait() does
both RCU-preempt and RCU-sched, whichever happens to have been built into
the running kernel. This commit therefore changes this function's name
to synchronize_rcu_expedited_wait() to reflect its new generic nature.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The function-header comments in kernel/rcu/tree_exp.h have gotten a bit
out of date, so this commit updates a number of them.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Now that the RCU flavors have been consolidated, there is one common
function for checking to see if an expedited RCU grace period has
completed, namely sync_rcu_preempt_exp_done(). Because this function is
no longer specific to RCU-preempt, this commit removes the "_preempt" from
its name. This commit also changes sync_rcu_preempt_exp_done_unlocked()
to sync_rcu_exp_done_unlocked() for the same reason.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The current expedited RCU grace-period code expects that a task
requesting an expedited grace period cannot awaken until that grace
period has reached the wakeup phase. However, it is possible for a long
preemption to result in the waiting task never sleeping. For example,
consider the following sequence of events:
1. Task A starts an expedited grace period by invoking
synchronize_rcu_expedited(). It proceeds normally up to the
wait_event() near the end of that function, and is then preempted
(or interrupted or whatever).
2. The expedited grace period completes, and a kworker task starts
the awaken phase, having incremented the counter and acquired
the rcu_state structure's .exp_wake_mutex. This kworker task
is then preempted or interrupted or whatever.
3. Task A resumes and enters wait_event(), which notes that the
expedited grace period has completed, and thus doesn't sleep.
4. Task B starts an expedited grace period exactly as did Task A,
complete with the preemption (or whatever delay) just before
the call to wait_event().
5. The expedited grace period completes, and another kworker
task starts the awaken phase, having incremented the counter.
However, it blocks when attempting to acquire the rcu_state
structure's .exp_wake_mutex because step 2's kworker task has
not yet released it.
6. Steps 4 and 5 repeat, resulting in overflow of the rcu_node
structure's ->exp_wq[] array.
In theory, this is harmless. Tasks waiting on the various ->exp_wq[]
array will just be spuriously awakened, but they will just sleep again
on noting that the rcu_state structure's ->expedited_sequence value has
not advanced far enough.
In practice, this wastes CPU time and is an accident waiting to happen.
This commit therefore moves the rcu_exp_gp_seq_end() call that officially
ends the expedited grace period (along with associate tracing) until
after the ->exp_wake_mutex has been acquired. This prevents Task A from
awakening prematurely, thus preventing more than one expedited grace
period from being in flight during a previous expedited grace period's
wakeup phase.
Fixes: 3b5f668e71 ("rcu: Overlap wakeups with next expedited grace period")
Signed-off-by: Neeraj Upadhyay <neeraju@codeaurora.org>
[ paulmck: Added updated comment. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Tasks waiting within exp_funnel_lock() for an expedited grace period to
elapse can be starved due to the following sequence of events:
1. Tasks A and B both attempt to start an expedited grace
period at about the same time. This grace period will have
completed when the lower four bits of the rcu_state structure's
->expedited_sequence field are 0b'0100', for example, when the
initial value of this counter is zero. Task A wins, and thus
does the actual work of starting the grace period, including
acquiring the rcu_state structure's .exp_mutex and sets the
counter to 0b'0001'.
2. Because task B lost the race to start the grace period, it
waits on ->expedited_sequence to reach 0b'0100' inside of
exp_funnel_lock(). This task therefore blocks on the rcu_node
structure's ->exp_wq[1] field, keeping in mind that the
end-of-grace-period value of ->expedited_sequence (0b'0100')
is shifted down two bits before indexing the ->exp_wq[] field.
3. Task C attempts to start another expedited grace period,
but blocks on ->exp_mutex, which is still held by Task A.
4. The aforementioned expedited grace period completes, so that
->expedited_sequence now has the value 0b'0100'. A kworker task
therefore acquires the rcu_state structure's ->exp_wake_mutex
and starts awakening any tasks waiting for this grace period.
5. One of the first tasks awakened happens to be Task A. Task A
therefore releases the rcu_state structure's ->exp_mutex,
which allows Task C to start the next expedited grace period,
which causes the lower four bits of the rcu_state structure's
->expedited_sequence field to become 0b'0101'.
6. Task C's expedited grace period completes, so that the lower four
bits of the rcu_state structure's ->expedited_sequence field now
become 0b'1000'.
7. The kworker task from step 4 above continues its wakeups.
Unfortunately, the wake_up_all() refetches the rcu_state
structure's .expedited_sequence field:
wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rcu_state.expedited_sequence) & 0x3]);
This results in the wakeup being applied to the rcu_node
structure's ->exp_wq[2] field, which is unfortunate given that
Task B is instead waiting on ->exp_wq[1].
On a busy system, no harm is done (or at least no permanent harm is done).
Some later expedited grace period will redo the wakeup. But on a quiet
system, such as many embedded systems, it might be a good long time before
there was another expedited grace period. On such embedded systems,
this situation could therefore result in a system hang.
This issue manifested as DPM device timeout during suspend (which
usually qualifies as a quiet time) due to a SCSI device being stuck in
_synchronize_rcu_expedited(), with the following stack trace:
schedule()
synchronize_rcu_expedited()
synchronize_rcu()
scsi_device_quiesce()
scsi_bus_suspend()
dpm_run_callback()
__device_suspend()
This commit therefore prevents such delays, timeouts, and hangs by
making rcu_exp_wait_wake() use its "s" argument consistently instead of
refetching from rcu_state.expedited_sequence.
Fixes: 3b5f668e71 ("rcu: Overlap wakeups with next expedited grace period")
Signed-off-by: Neeraj Upadhyay <neeraju@codeaurora.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The code in sync_rcu_exp_select_node_cpus() calculates the current
CPU's mask within its rcu_node structure's bitmasks, but this has
already been computed in the ->grpmask field of that CPU's rcu_data
structure. This commit therefore just uses this ->grpmask field.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This fixes a data-race where `atomic_t dynticks` is copied by value. The
copy is performed non-atomically, resulting in a data-race if `dynticks`
is updated concurrently.
This data-race was found with KCSAN:
==================================================================
BUG: KCSAN: data-race in dyntick_save_progress_counter / rcu_irq_enter
write to 0xffff989dbdbe98e0 of 4 bytes by task 10 on cpu 3:
atomic_add_return include/asm-generic/atomic-instrumented.h:78 [inline]
rcu_dynticks_snap kernel/rcu/tree.c:310 [inline]
dyntick_save_progress_counter+0x43/0x1b0 kernel/rcu/tree.c:984
force_qs_rnp+0x183/0x200 kernel/rcu/tree.c:2286
rcu_gp_fqs kernel/rcu/tree.c:1601 [inline]
rcu_gp_fqs_loop+0x71/0x880 kernel/rcu/tree.c:1653
rcu_gp_kthread+0x22c/0x3b0 kernel/rcu/tree.c:1799
kthread+0x1b5/0x200 kernel/kthread.c:255
<snip>
read to 0xffff989dbdbe98e0 of 4 bytes by task 154 on cpu 7:
rcu_nmi_enter_common kernel/rcu/tree.c:828 [inline]
rcu_irq_enter+0xda/0x240 kernel/rcu/tree.c:870
irq_enter+0x5/0x50 kernel/softirq.c:347
<snip>
Reported by Kernel Concurrency Sanitizer on:
CPU: 7 PID: 154 Comm: kworker/7:1H Not tainted 5.3.0+ #5
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
Workqueue: kblockd blk_mq_run_work_fn
==================================================================
Signed-off-by: Marco Elver <elver@google.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: rcu@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The "mask_ofl_ipi" is used to track which CPUs get IPIed, however
in the IPI sending loop, "mask_ofl_ipi" along with another variable
"mask_ofl_test" might also get modified to record which CPUs' quiesent
states must be reported by the sync_rcu_exp_select_node_cpus() at
the end of sync_rcu_exp_select_node_cpus(). This overlap of roles
can be confusing, so this patch cleans things a little by using
"mask_ofl_ipi" solely for determining which CPUs must be IPIed and
"mask_ofl_test" for solely determining on behalf of which CPUs
sync_rcu_exp_select_node_cpus() must report a quiscent state.
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Acked-by: Marco Elver <elver@google.com>
The rcu_node structure's ->expmask field is accessed locklessly when
starting a new expedited grace period and when reporting an expedited
RCU CPU stall warning. This commit therefore handles the former by
taking a snapshot of ->expmask while the lock is held and the latter
by applying READ_ONCE() to lockless reads and WRITE_ONCE() to the
corresponding updates.
Link: https://lore.kernel.org/lkml/CANpmjNNmSOagbTpffHr4=Yedckx9Rm2NuGqC9UqE+AOz5f1-ZQ@mail.gmail.com
Reported-by: syzbot+134336b86f728d6e55a0@syzkaller.appspotmail.com
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Acked-by: Marco Elver <elver@google.com>
New tools bring new warnings, and with v5.3 comes:
kernel/rcu/srcutree.c: warning: 'levelspread[<U aa0>]' may be used uninitialized in this function [-Wuninitialized]: => 121:34
This commit suppresses this warning by initializing the full array
to INT_MIN, which will result in failures should any out-of-bounds
references appear.
Reported-by: Michael Ellerman <mpe@ellerman.id.au>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
We never set this to false. This probably doesn't affect most people's
runtime because GCC will automatically initialize it to false at certain
common optimization levels. But that behavior is related to a bug in
GCC and obviously should not be relied on.
Fixes: 5d6742b377 ("rcu/nocb: Use rcu_segcblist for no-CBs CPUs")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The RCU-specific resched_cpu() function sends a resched IPI to the
specified CPU, which can be used to force the tick on for a given
nohz_full CPU. This is needed when this nohz_full CPU is looping in the
kernel while blocking the current grace period. However, for the tick
to actually be forced on in all cases, that CPU's rcu_data structure's
->rcu_urgent_qs flag must be set beforehand. This commit therefore
causes rcu_implicit_dynticks_qs() to set this flag prior to invoking
resched_cpu() on a holdout nohz_full CPU.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
None of rcu_segcblist_set_len(), rcu_segcblist_add_len(), or
rcu_segcblist_xchg_len() are used outside of kernel/rcu/rcu_segcblist.c.
This commit therefore makes them static.
Fixes: eda669a6a2 ("rcu/nocb: Atomic ->len field in rcu_segcblist structure")
Signed-off-by: kbuild test robot <lkp@intel.com>
[ paulmck: "Fixes:" updated per Stephen Rothwell feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
If a nohz_full CPU is idle or executing in userspace, it makes good sense
to keep it out of RCU core processing. After all, the RCU grace-period
kthread can see its quiescent states and all of its callbacks are
offloaded, so there is nothing for RCU core processing to do.
However, if a nohz_full CPU is executing in kernel space, the RCU
grace-period kthread cannot do anything for it, so such a CPU must report
its own quiescent states. This commit therefore makes nohz_full CPUs
skip RCU core processing only if the scheduler-clock interrupt caught
them in idle or in userspace.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Commit 671a63517c ("rcu: Avoid unnecessary softirq when system
is idle") fixed a bug that could result in an indefinite number of
unnecessary invocations of the RCU_SOFTIRQ handler at the trailing edge
of a scheduler-clock interrupt. However, the fix introduced off-CPU
stores to ->core_needs_qs. These writes did not conflict with the
on-CPU stores because the CPU's leaf rcu_node structure's ->lock was
held across all such stores. However, the loads from ->core_needs_qs
were not promoted to READ_ONCE() and, worse yet, the code loading from
->core_needs_qs was written assuming that it was only ever updated by
the corresponding CPU. So operation has been robust, but only by luck.
This situation is therefore an accident waiting to happen.
This commit therefore takes a different approach. Instead of clearing
->core_needs_qs from the grace-period kthread's force-quiescent-state
processing, it modifies the rcu_pending() function to suppress the
rcu_sched_clock_irq() function's call to invoke_rcu_core() if there is no
grace period in progress. This avoids the infinite needless RCU_SOFTIRQ
handlers while still keeping all accesses to ->core_needs_qs local to
the corresponding CPU.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
In some cases, tracing shows that need_heavy_qs is still set even though
urgent_qs was cleared upon reporting of a quiescent state. One such
case is when the softirq reports that a CPU has passed quiescent state.
Commit 671a63517c ("rcu: Avoid unnecessary softirq when system is
idle") fixed a bug where core_needs_qs was not being cleared. In order
to avoid running into similar situations with the urgent-grace-period
flags, this commit causes rcu_disable_urgency_upon_qs(), previously
rcu_disable_tick_upon_qs(), to clear the urgency hints, ->rcu_urgent_qs
and ->rcu_need_heavy_qs. Note that it is possible for CPUs to go
offline with these urgency hints still set. This is handled because
rcu_disable_urgency_upon_qs() is also invoked during the online process.
Because these hints can be cleared both by the corresponding CPU and by
the grace-period kthread, this commit also adds a number of READ_ONCE()
and WRITE_ONCE() calls.
Tested overnight with rcutorture running for 60 minutes on all
configurations of RCU.
Signed-off-by: "Joel Fernandes (Google)" <joel@joelfernandes.org>
[ paulmck: Clear urgency flags in rcu_disable_urgency_upon_qs(). ]
[ paulmck: Remove ->core_needs_qs from the set cleared at quiescent state. ]
[ paulmck: Make rcu_disable_urgency_upon_qs static per kbuild test robot. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
There is interrupt-exit code that forces on the tick for nohz_full CPUs
failing to respond to the current grace period in a timely fashion.
However, this code must compare ->dynticks_nmi_nesting to the value 2
in the interrupt-exit fastpath. This commit therefore moves this code
to the interrupt-entry fastpath, where a lighter-weight comparison to
zero may be used.
Reported-by: Joel Fernandes <joel@joelfernandes.org>
[ paulmck: Apply Joel Fernandes TICK_DEP_MASK_RCU->TICK_DEP_BIT_RCU fix. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
CPUs running for long time periods in the kernel in nohz_full mode
might leave the scheduling-clock interrupt disabled for then full
duration of their in-kernel execution. This can (among other things)
delay grace periods. This commit therefore forces the tick back on
for any nohz_full CPU that is failing to pass through a quiescent state
upon return from interrupt, which the resched_cpu() will induce.
Reported-by: Joel Fernandes <joel@joelfernandes.org>
[ paulmck: Clear ->rcu_forced_tick as reported by Joel Fernandes testing. ]
[ paulmck: Apply Joel Fernandes TICK_DEP_MASK_RCU->TICK_DEP_BIT_RCU fix. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The rcu_torture_fwd_prog_nr() tests the ability of RCU to tolerate
in-kernel busy loops. It invokes rcu_torture_fwd_prog_cond_resched()
within its delay loop, which, in PREEMPT && NO_HZ_FULL kernels results
in the occasional direct call to schedule(). Now, this direct call to
schedule() is appropriate for call_rcu() flood testing, in which either
the kernel should restrain itself or userspace transitions will supply
the needed restraint. But in pure in-kernel loops, the occasional
cond_resched() should do the job.
This commit therefore makes rcu_torture_fwd_prog_nr() use cond_resched()
instead of rcu_torture_fwd_prog_cond_resched() in order to increase the
brutality of this aspect of rcutorture testing.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Currently, each of six different types of failure triggers a
single WARN_ON_ONCE(), and it is then necessary to stare at the
rcu_torture_stats(), Reader Pipe, and Reader Batch lines looking for
inappropriately non-zero values. This can be annoying and error-prone,
so this commit provides a separate WARN_ON_ONCE() for each of the
six error conditions and adds short comments to each to ease error
identification.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The variable rcu_perf_writer_state is declared and initialized,
but is never actually referenced. Remove it to clean code.
Signed-off-by: Ethan Hansen <1ethanhansen@gmail.com>
[ paulmck: Also removed unused macros assigned to that variable. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The function rcutorture_record_progress() is declared in rcu.h, but is
never used. This commit therefore removes rcutorture_record_progress()
to clean code.
Signed-off-by: Ethan Hansen <1ethanhansen@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
During an actual call_rcu() flood, there would be frequent trips to
userspace (in-kernel call_rcu() floods must be otherwise housebroken).
Userspace execution on nohz_full CPUs implies an RCU dyntick idle/not-idle
transition pair, so this commit adds emulation of that pair.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
CPU-hotplug removal operations run the multi_cpu_stop() function, which
relies on the scheduler to gain control from whatever is running on the
various online CPUs, including any nohz_full CPUs running long loops in
kernel-mode code. Lack of the scheduler-clock interrupt on such CPUs
can delay multi_cpu_stop() for several minutes and can also result in
RCU CPU stall warnings. This commit therefore causes CPU-hotplug removal
operations to enable the scheduler-clock interrupt on all online CPUs.
[ paulmck: Apply Joel Fernandes TICK_DEP_MASK_RCU->TICK_DEP_BIT_RCU fix. ]
[ paulmck: Apply simplifications suggested by Frederic Weisbecker. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
When multi_cpu_stop() loops waiting for other tasks, it can trigger an RCU
CPU stall warning. This can be misleading because what is instead needed
is information on whatever task is blocking multi_cpu_stop(). This commit
therefore inserts an RCU quiescent state into the multi_cpu_stop()
function's waitloop.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Readers and callback flooders in the rcutorture stress-test suite run for
extended time periods by design. They do take pains to relinquish the
CPU from time to time, but in some cases this relies on the scheduler
being active, which in turn relies on the scheduler-clock interrupt
firing from time to time.
This commit therefore forces scheduling-clock interrupts within
these loops. While in the area, this commit also prevents
rcu_torture_reader()'s occasional timed sleeps from delaying shutdown.
[ paulmck: Apply Joel Fernandes TICK_DEP_MASK_RCU->TICK_DEP_BIT_RCU fix. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Callback invocation can run for a significant time period, and within
CONFIG_NO_HZ_FULL=y kernels, this period will be devoid of scheduler-clock
interrupts. In-kernel execution without such interrupts can cause all
manner of malfunction, with RCU CPU stall warnings being but one result.
This commit therefore forces scheduling-clock interrupts on whenever more
than a few RCU callbacks are invoked. Because offloaded callback invocation
can be preempted, this forcing is withdrawn on each context switch. This
in turn requires that the loop invoking RCU callbacks reiterate the forcing
periodically.
[ paulmck: Apply Joel Fernandes TICK_DEP_MASK_RCU->TICK_DEP_BIT_RCU fix. ]
[ paulmck: Remove NO_HZ_FULL check per Frederic Weisbecker feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Pull scheduler updates from Ingo Molnar:
- MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and
Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann,
Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers.
As perf and the scheduler is getting bigger and more complex,
document the status quo of current responsibilities and interests,
and spread the review pain^H^H^H^H fun via an increase in the Cc:
linecount generated by scripts/get_maintainer.pl. :-)
- Add another series of patches that brings the -rt (PREEMPT_RT) tree
closer to mainline: split the monolithic CONFIG_PREEMPT dependencies
into a new CONFIG_PREEMPTION category that will allow the eventual
introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches
to go though.
- Extend the CPU cgroup controller with uclamp.min and uclamp.max to
allow the finer shaping of CPU bandwidth usage.
- Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS).
- Improve the behavior of high CPU count, high thread count
applications running under cpu.cfs_quota_us constraints.
- Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present.
- Improve CPU isolation housekeeping CPU allocation NUMA locality.
- Fix deadline scheduler bandwidth calculations and logic when cpusets
rebuilds the topology, or when it gets deadline-throttled while it's
being offlined.
- Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from
setscheduler() system calls without creating global serialization.
Add new synchronization between cpuset topology-changing events and
the deadline acceptance tests in setscheduler(), which were broken
before.
- Rework the active_mm state machine to be less confusing and more
optimal.
- Rework (simplify) the pick_next_task() slowpath.
- Improve load-balancing on AMD EPYC systems.
- ... and misc cleanups, smaller fixes and improvements - please see
the Git log for more details.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
sched/psi: Correct overly pessimistic size calculation
sched/fair: Speed-up energy-aware wake-ups
sched/uclamp: Always use 'enum uclamp_id' for clamp_id values
sched/uclamp: Update CPU's refcount on TG's clamp changes
sched/uclamp: Use TG's clamps to restrict TASK's clamps
sched/uclamp: Propagate system defaults to the root group
sched/uclamp: Propagate parent clamps
sched/uclamp: Extend CPU's cgroup controller
sched/topology: Improve load balancing on AMD EPYC systems
arch, ia64: Make NUMA select SMP
sched, perf: MAINTAINERS update, add submaintainers and reviewers
sched/fair: Use rq_lock/unlock in online_fair_sched_group
cpufreq: schedutil: fix equation in comment
sched: Rework pick_next_task() slow-path
sched: Allow put_prev_task() to drop rq->lock
sched/fair: Expose newidle_balance()
sched: Add task_struct pointer to sched_class::set_curr_task
sched: Rework CPU hotplug task selection
sched/{rt,deadline}: Fix set_next_task vs pick_next_task
sched: Fix kerneldoc comment for ia64_set_curr_task
...
Bimodal behavior of rcu_do_batch() is not really suited to Google
applications like gfe servers.
When a process with millions of sockets exits, closing all files
queues two rcu callbacks per socket.
This eventually reaches the point where RCU enters an emergency
mode, where rcu_do_batch() do not return until whole queue is flushed.
Each rcu callback lasts at least 70 nsec, so with millions of
elements, we easily spend more than 100 msec without rescheduling.
Goal of this patch is to avoid the infamous message like following
"need_resched set for > 51999388 ns (52 ticks) without schedule"
We dynamically adjust the number of elements we process, instead
of 10 / INFINITE choices, we use a floor of ~1 % of current entries.
If the number is above 1000, we switch to a time based limit of 3 msec
per batch, adjustable with /sys/module/rcutree/parameters/rcu_resched_ns
Signed-off-by: Eric Dumazet <edumazet@google.com>
[ paulmck: Forward-port and remove debug statements. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
When under overload conditions, __call_rcu_nocb_wake() will wake the
no-CBs GP kthread any time the no-CBs CB kthread is asleep or there
are no ready-to-invoke callbacks, but only after a timer delay. If the
no-CBs GP kthread has a ->nocb_bypass_timer pending, the deferred wakeup
from __call_rcu_nocb_wake() is redundant. This commit therefore makes
__call_rcu_nocb_wake() avoid posting the redundant deferred wakeup if
->nocb_bypass_timer is pending. This requires adding a bit of ordering
of timer actions.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, __call_rcu_nocb_wake() advances callbacks each time that it
detects excessive numbers of callbacks, though only if it succeeds in
conditionally acquiring its leaf rcu_node structure's ->lock. Despite
the conditional acquisition of ->lock, this does increase contention.
This commit therefore avoids advancing callbacks unless there are
callbacks in ->cblist whose grace period has completed and advancing
has not yet been done during this jiffy.
Note that this decision does not take the presence of new callbacks
into account. That is because on this code path, there will always be
at least one new callback, namely the one we just enqueued.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, nocb_cb_wait() advances callbacks on each pass through its
loop, though only if it succeeds in conditionally acquiring its leaf
rcu_node structure's ->lock. Despite the conditional acquisition of
->lock, this does increase contention. This commit therefore avoids
advancing callbacks unless there are callbacks in ->cblist whose grace
period has completed.
Note that nocb_cb_wait() doesn't worry about callbacks that have not
yet been assigned a grace period. The idea is that the only reason for
nocb_cb_wait() to advance callbacks is to allow it to continue invoking
callbacks. Time will tell whether this is the correct choice.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
The rcutree_migrate_callbacks() invokes rcu_advance_cbs() on both the
offlined CPU's ->cblist and that of the surviving CPU, then merges
them. However, after the merge, and of the offlined CPU's callbacks
that were not ready to be invoked will no longer be associated with a
grace-period number. This commit therefore invokes rcu_advance_cbs()
one more time on the merged ->cblist in order to assign a grace-period
number to these callbacks.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
When callbacks are in full flow, the common case is waiting for a
grace period, and this grace period will normally take a few jiffies to
complete. It therefore isn't all that helpful for __call_rcu_nocb_wake()
to do a synchronous wakeup in this case. This commit therefore turns this
into a timer-based deferred wakeup of the no-CBs grace-period kthread.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit causes locking, sleeping, and callback state to be printed
for no-CBs CPUs when the rcutorture writer is delayed sufficiently for
rcutorture to complain.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Use of the rcu_data structure's segmented ->cblist for no-CBs CPUs
takes advantage of unrelated grace periods, thus reducing the memory
footprint in the face of floods of call_rcu() invocations. However,
the ->cblist field is a more-complex rcu_segcblist structure which must
be protected via locking. Even though there are only three entities
which can acquire this lock (the CPU invoking call_rcu(), the no-CBs
grace-period kthread, and the no-CBs callbacks kthread), the contention
on this lock is excessive under heavy stress.
This commit therefore greatly reduces contention by provisioning
an rcu_cblist structure field named ->nocb_bypass within the
rcu_data structure. Each no-CBs CPU is permitted only a limited
number of enqueues onto the ->cblist per jiffy, controlled by a new
nocb_nobypass_lim_per_jiffy kernel boot parameter that defaults to
about 16 enqueues per millisecond (16 * 1000 / HZ). When that limit is
exceeded, the CPU instead enqueues onto the new ->nocb_bypass.
The ->nocb_bypass is flushed into the ->cblist every jiffy or when
the number of callbacks on ->nocb_bypass exceeds qhimark, whichever
happens first. During call_rcu() floods, this flushing is carried out
by the CPU during the course of its call_rcu() invocations. However,
a CPU could simply stop invoking call_rcu() at any time. The no-CBs
grace-period kthread therefore carries out less-aggressive flushing
(every few jiffies or when the number of callbacks on ->nocb_bypass
exceeds (2 * qhimark), whichever comes first). This means that the
no-CBs grace-period kthread cannot be permitted to do unbounded waits
while there are callbacks on ->nocb_bypass. A ->nocb_bypass_timer is
used to provide the needed wakeups.
[ paulmck: Apply Coverity feedback reported by Colin Ian King. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Upcoming ->nocb_lock contention-reduction work requires that the
rcu_segcblist structure's ->len field be concurrently manipulated,
but only if there are no-CBs CPUs in the kernel. This commit
therefore makes this ->len field be an atomic_long_t, but only
in CONFIG_RCU_NOCB_CPU=y kernels.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
When there are excessive numbers of callbacks, and when either the
corresponding no-CBs callback kthread is asleep or there is no more
ready-to-invoke callbacks, and when least one callback is pending,
__call_rcu_nocb_wake() will advance the callbacks, but refrain from
awakening the corresponding no-CBs grace-period kthread. However,
because rcu_advance_cbs_nowake() is used, it is possible (if a bit
unlikely) that the needed advancement could not happen due to a grace
period not being in progress. Plus there will always be at least one
pending callback due to one having just now been enqueued.
This commit therefore attempts to advance callbacks and awakens the
no-CBs grace-period kthread when there are excessive numbers of callbacks
posted and when the no-CBs callback kthread is not in a position to do
anything helpful.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
The sleep/wakeup of the no-CBs grace-period kthreads is synchronized
using the ->nocb_lock of the first CPU corresponding to that kthread.
This commit provides a separate ->nocb_gp_lock for this purpose, thus
reducing contention on ->nocb_lock.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, nocb_cb_wait() unconditionally acquires the leaf rcu_node
->lock to advance callbacks when done invoking the previous batch.
It does this while holding ->nocb_lock, which means that contention on
the leaf rcu_node ->lock visits itself on the ->nocb_lock. This commit
therefore makes this lock acquisition conditional, forgoing callback
advancement when the leaf rcu_node ->lock is not immediately available.
(In this case, the no-CBs grace-period kthread will eventually do any
needed callback advancement.)
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, __call_rcu_nocb_wake() conditionally acquires the leaf rcu_node
structure's ->lock, and only afterwards does rcu_advance_cbs_nowake()
check to see if it is possible to advance callbacks without potentially
needing to awaken the grace-period kthread. Given that the no-awaken
check can be done locklessly, this commit reverses the order, so that
rcu_advance_cbs_nowake() is invoked without holding the leaf rcu_node
structure's ->lock and rcu_advance_cbs_nowake() checks the grace-period
state before conditionally acquiring that lock, thus reducing the number
of needless acquistions of the leaf rcu_node structure's ->lock.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, when the square root of the number of CPUs is rounded down
by int_sqrt(), this round-down is applied to the number of callback
kthreads per grace-period kthreads. This makes almost no difference
for large systems, but results in oddities such as three no-CBs
grace-period kthreads for a five-CPU system, which is a bit excessive.
This commit therefore causes the round-down to apply to the number of
no-CBs grace-period kthreads, so that systems with from four to eight
CPUs have only two no-CBs grace period kthreads.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
A given rcu_data structure's ->nocb_lock can be acquired very frequently
by the corresponding CPU and occasionally by the corresponding no-CBs
grace-period and callbacks kthreads. In particular, these two kthreads
will have frequent gaps between ->nocb_lock acquisitions that are roughly
a grace period in duration. This means that any excessive ->nocb_lock
contention will be due to the CPU's acquisitions, and this in turn
enables a very naive contention-avoidance strategy to be quite effective.
This commit therefore modifies rcu_nocb_lock() to first
attempt a raw_spin_trylock(), and to atomically increment a
separate ->nocb_lock_contended across a raw_spin_lock(). This new
->nocb_lock_contended field is checked in __call_rcu_nocb_wake() when
interrupts are enabled, with a spin-wait for contending acquisitions
to complete, thus allowing the kthreads a chance to acquire the lock.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, the code provides an extra wakeup for the no-CBs grace-period
kthread if one of its CPUs is generating excessive numbers of callbacks.
But satisfying though it is to wake something up when things are going
south, unless the thing being awakened can actually help solve the
problem, that extra wakeup does nothing but consume additional CPU time,
which is exactly what you don't want during a call_rcu() flood.
This commit therefore avoids doing anything if the corresponding
no-CBs callback kthread is going full tilt. Otherwise, if advancing
callbacks immediately might help and if the leaf rcu_node structure's
lock is immediately available, this commit invokes a new variant of
rcu_advance_cbs() that advances callbacks only if doing so won't require
awakening the grace-period kthread (not to be confused with any of the
no-CBs grace-period kthreads).
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
It might be hard to imagine having more than two billion callbacks
queued on a single CPU's ->cblist, but someone will do it sometime.
This commit therefore makes __call_rcu_nocb_wake() handle this situation
by upgrading local variable "len" from "int" to "long".
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, wake_nocb_gp_defer() simply stores whatever waketype was
passed in, which can result in a RCU_NOCB_WAKE_FORCE being downgraded
to RCU_NOCB_WAKE, which could in turn delay callback processing.
This commit therefore adds a check so that wake_nocb_gp_defer() only
updates ->nocb_defer_wakeup when the update increases the forcefulness,
thus avoiding downgrades.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
The __call_rcu_nocb_wake() function and its predecessors set
->qlen_last_fqs_check to zero for the first callback and to LONG_MAX / 2
for forced reawakenings. The former can result in a too-quick reawakening
when there are many callbacks ready to invoke and the latter prevents a
second reawakening. This commit therefore sets ->qlen_last_fqs_check
to the current number of callbacks in both cases. While in the area,
this commit also moves both assignments under ->nocb_lock.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Historically, no-CBs CPUs allowed the scheduler-clock tick to be
unconditionally disabled on any transition to idle or nohz_full userspace
execution (see the rcu_needs_cpu() implementations). Unfortunately,
the checks used by rcu_needs_cpu() are defeated now that no-CBs CPUs
use ->cblist, which might make users of battery-powered devices rather
unhappy. This commit therefore adds explicit rcu_segcblist_is_offloaded()
checks to return to the historical energy-efficient semantics.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Some compilers complain that wait_gp_seq might be used uninitialized
in nocb_gp_wait(). This cannot actually happen because when wait_gp_seq
is uninitialized, needwait_gp must be false, which prevents wait_gp_seq
from being used. But this analysis is apparently beyond some compilers,
so this commit adds a bogus initialization of wait_gp_seq for the sole
purpose of suppressing the false-positive warning.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, rcu_pending() invokes rcu_segcblist_is_offloaded() even
in CONFIG_RCU_NOCB_CPU=n kernels, which cannot possibly be offloaded.
Given that rcu_pending() is on a fastpath, it makes sense to check for
CONFIG_RCU_NOCB_CPU=y before invoking rcu_segcblist_is_offloaded().
This commit therefore makes this change.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, rcu_core() invokes rcu_segcblist_is_offloaded() each time it
needs to know whether the current CPU is a no-CBs CPU. Given that it is
not possible to change the no-CBs status of a CPU after boot, and given
that it is not possible to even have no-CBs CPUs in CONFIG_RCU_NOCB_CPU=n
kernels, this repeated runtime invocation wastes CPU. This commit
therefore created a const on-stack variable to allow this check to be
done only once per rcu_core() invocation.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, rcu_do_batch() invokes rcu_segcblist_is_offloaded() each time
it needs to know whether the current CPU is a no-CBs CPU. Given that it
is not possible to change the no-CBs status of a CPU after boot, and given
that it is not possible to even have no-CBs CPUs in CONFIG_RCU_NOCB_CPU=n
kernels, this per-callback invocation wastes CPU. This commit therefore
created a const on-stack variable to allow this check to be done only
once per rcu_do_batch() invocation.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit removes the obsolete nocb_q_count and nocb_q_count_lazy
fields, also removing rcu_get_n_cbs_nocb_cpu(), adjusting
rcu_get_n_cbs_cpu(), and making rcutree_migrate_callbacks() once again
disable the ->cblist fields of offline CPUs.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently the RCU callbacks for no-CBs CPUs are queued on a series of
ad-hoc linked lists, which means that these callbacks cannot benefit
from "drive-by" grace periods, thus suffering needless delays prior
to invocation. In addition, the no-CBs grace-period kthreads first
wait for callbacks to appear and later wait for a new grace period,
which means that callbacks appearing during a grace-period wait can
be delayed. These delays increase memory footprint, and could even
result in an out-of-memory condition.
This commit therefore enqueues RCU callbacks from no-CBs CPUs on the
rcu_segcblist structure that is already used by non-no-CBs CPUs. It also
restructures the no-CBs grace-period kthread to be checking for incoming
callbacks while waiting for grace periods. Also, instead of waiting
for a new grace period, it waits for the closest grace period that will
cause some of the callbacks to be safe to invoke. All of these changes
reduce callback latency and thus the number of outstanding callbacks,
in turn reducing the probability of an out-of-memory condition.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
As a first step towards making no-CBs CPUs use the ->cblist, this commit
leaves the ->cblist enabled for these CPUs. The main reason to make
no-CBs CPUs use ->cblist is to take advantage of callback numbering,
which will reduce the effects of missed grace periods which in turn will
reduce forward-progress problems for no-CBs CPUs.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, rcu_segcblist_empty() assumes that the callback list is not
being changed by other CPUs, but upcoming changes will require it to
operate locklessly. This commit therefore adds the needed READ_ONCE()
call, along with the WRITE_ONCE() calls when updating the callback list's
->head field.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, rcu_segcblist_restempty() assumes that the callback list
is not being changed by other CPUs, but upcoming changes will require
it to operate locklessly. This commit therefore adds the needed
READ_ONCE() calls, along with the WRITE_ONCE() calls when updating
the callback list.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
The idea behind the checks for extended quiescent states at the end of
__call_rcu_nocb() is to handle cases where call_rcu() is invoked directly
from within an extended quiescent state, for example, from the idle loop.
However, this will result in a timer-mediated deferred wakeup, which
will cause the needed wakeup to happen within a jiffy or thereabouts.
There should be no forward-progress concerns, and if there are, the proper
response is to exit the extended quiescent state while executing the
endless blast of call_rcu() invocations, for example, using RCU_NONIDLE().
Given the more realistic case of an isolated call_rcu() invocation, there
should be no problem.
This commit therefore removes the checks for invoking call_rcu() within
an extended quiescent state for on no-CBs CPUs.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
In theory, a timer is used to defer wakeups of no-CBs grace-period
kthreads when the wakeup cannot be done safely directly from the
call_rcu(). In practice, the one-jiffy delay is not always consistent
with timely callback invocation under heavy call_rcu() loads. Therefore,
there are a number of checks for a pending deferred wakeup, including
from the scheduling-clock interrupt. Unfortunately, this check follows
the rcu_nohz_full_cpu() early exit, which renders it useless on such CPUs.
This commit therefore moves the check for the pending deferred no-CB
wakeup to precede the rcu_nohz_full_cpu() early exit.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Because rcutree_migrate_callbacks() is invoked infrequently and because
an exact snapshot of the grace-period state might save some callbacks a
second trip through a grace period, this function has used the root
rcu_node structure. However, this safe-second-trip optimization
happens only if rcutree_migrate_callbacks() races with grace-period
initialization, so it is not worth the added mental load. This commit
therefore makes rcutree_migrate_callbacks() start with the leaf rcu_node
structures, as is done elsewhere.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit is a preparatory patch for offloaded callbacks using the
same ->cblist structure used by non-offloaded callbacks. It therefore
adds rcu_segcblist_is_offloaded() calls where they will be needed when
!rcu_segcblist_is_enabled() no longer flags the offloaded case. It also
adds checks in rcu_do_batch() to ensure that there are no missed checks:
Currently, it should not be possible for offloaded execution to reach
rcu_do_batch(), though this will change later in this series.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
RCU callback processing currently uses rcu_is_nocb_cpu() to determine
whether or not the current CPU's callbacks are to be offloaded.
This works, but it is not so good for cache locality. Plus use of
->cblist for offloaded callbacks will greatly increase the frequency
of these checks. This commit therefore adds a ->offloaded flag to the
rcu_segcblist structure to provide a more flexible and cache-friendly
means of checking for callback offloading.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
NULLing the RCU_NEXT_TAIL pointer was a clever way to save a byte, but
forward-progress considerations would require that this pointer be both
NULL and non-NULL, which, absent a quantum-computer port of the Linux
kernel, simply won't happen. This commit therefore creates as separate
->enabled flag to replace the current NULL checks.
[ paulmck: Add include files per 0day test robot and -next. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit causes the no-CBs grace-period/callback hierarchy to be
printed to the console when the dump_tree kernel boot parameter is set.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit changes the name of the rcu_nocb_leader_stride kernel
boot parameter to rcu_nocb_gp_stride in order to account for the new
distinction between callback and grace-period no-CBs kthreads.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
The nocb_cb_wait() function traces a "FollowerSleep" trace_rcu_nocb_wake()
event, which never was documented and is now misleading. This commit
therefore changes "FollowerSleep" to "CBSleep", documents this, and
updates the documentation for "Sleep" as well.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit renames rdp_leader to rdp_gp in order to account for the
new distinction between callback and grace-period no-CBs kthreads.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit adjusts naming to account for the new distinction between
callback and grace-period no-CBs kthreads.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit adjusts naming to account for the new distinction between
callback and grace-period no-CBs kthreads. While in the area, it also
updates local variables.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit adjusts naming to account for the new distinction between
callback and grace-period no-CBs kthreads.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit adjusts naming to account for the new distinction between
callback and grace-period no-CBs kthreads.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Currently, there is one no-CBs rcuo kthread per CPU, and these kthreads
are divided into groups. The first rcuo kthread to come online in a
given group is that group's leader, and the leader both waits for grace
periods and invokes its CPU's callbacks. The non-leader rcuo kthreads
only invoke callbacks.
This works well in the real-time/embedded environments for which it was
intended because such environments tend not to generate all that many
callbacks. However, given huge floods of callbacks, it is possible for
the leader kthread to be stuck invoking callbacks while its followers
wait helplessly while their callbacks pile up. This is a good recipe
for an OOM, and rcutorture's new callback-flood capability does generate
such OOMs.
One strategy would be to wait until such OOMs start happening in
production, but similar OOMs have in fact happened starting in 2018.
It would therefore be wise to take a more proactive approach.
This commit therefore features per-CPU rcuo kthreads that do nothing
but invoke callbacks. Instead of having one of these kthreads act as
leader, each group has a separate rcog kthread that handles grace periods
for its group. Because these rcuog kthreads do not invoke callbacks,
callback floods on one CPU no longer block callbacks from reaching the
rcuc callback-invocation kthreads on other CPUs.
This change does introduce additional kthreads, however:
1. The number of additional kthreads is about the square root of
the number of CPUs, so that a 4096-CPU system would have only
about 64 additional kthreads. Note that recent changes
decreased the number of rcuo kthreads by a factor of two
(CONFIG_PREEMPT=n) or even three (CONFIG_PREEMPT=y), so
this still represents a significant improvement on most systems.
2. The leading "rcuo" of the rcuog kthreads should allow existing
scripting to affinity these additional kthreads as needed, the
same as for the rcuop and rcuos kthreads. (There are no longer
any rcuob kthreads.)
3. A state-machine approach was considered and rejected. Although
this would allow the rcuo kthreads to continue their dual
leader/follower roles, it complicates callback invocation
and makes it more difficult to consolidate rcuo callback
invocation with existing softirq callback invocation.
The introduction of rcuog kthreads should thus be acceptable.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
This commit simply rewords comments to prepare for leader nocb kthreads
doing only grace-period work and callback shuffling. This will mean
the addition of replacement kthreads to invoke callbacks. The "leader"
and "follower" thus become less meaningful, so the commit changes no-CB
comments with these strings to "GP" and "CB", respectively. (Give or
take the usual grammatical transformations.)
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
