linux-stable.git/kernel/rcu/tree.h, branch linux-5.17.y

rcu: Kill rnp->ofl_seq and use only rcu_state.ofl_lock for exclusion

2022-04-08T11:58:36+00:00

[ Upstream commit 82980b1622d97017053c6792382469d7dc26a486 ]

If we allow architectures to bring APs online in parallel, then we end
up requiring rcu_cpu_starting() to be reentrant. But currently, the
manipulation of rnp->ofl_seq is not thread-safe.

However, rnp->ofl_seq is also fairly much pointless anyway since both
rcu_cpu_starting() and rcu_report_dead() hold rcu_state.ofl_lock for
fairly much the whole time that rnp->ofl_seq is set to an odd number
to indicate that an operation is in progress.

So drop rnp->ofl_seq completely, and use only rcu_state.ofl_lock.

This has a couple of minor complexities: lockdep will complain when we
take rcu_state.ofl_lock, and currently accepts the 'excuse' of having
an odd value in rnp->ofl_seq. So switch it to an arch_spinlock_t to
avoid that false positive complaint. Since we're killing rnp->ofl_seq
of course that 'excuse' has to be changed too, so make it check for
arch_spin_is_locked(rcu_state.ofl_lock).

There's no arch_spin_lock_irqsave() so we have to manually save and
restore local interrupts around the locking.

At Paul's request based on Neeraj's analysis, make rcu_gp_init not just
wait but *exclude* any CPU online/offline activity, which was fairly
much true already by virtue of it holding rcu_state.ofl_lock.

Signed-off-by: David Woodhouse 
Signed-off-by: Paul E. McKenney 
Signed-off-by: Sasha Levin

Merge branches 'doc.2021.11.30c', 'exp.2021.12.07a', 'fastnohz.2021.11.30c', 'fixes.2021.11.30c', 'nocb.2021.12.09a', 'nolibc.2021.11.30c', 'tasks.2021.12.09a', 'torture.2021.12.07a' and 'torturescript.2021.11.30c' into HEAD

2021-12-09T19:38:09+00:00

doc.2021.11.30c: Documentation updates.
exp.2021.12.07a: Expedited-grace-period fixes.
fastnohz.2021.11.30c: Remove CONFIG_RCU_FAST_NO_HZ.
fixes.2021.11.30c: Miscellaneous fixes.
nocb.2021.12.09a: No-CB CPU updates.
nolibc.2021.11.30c: Tiny in-kernel library updates.
tasks.2021.12.09a: RCU-tasks updates, including update-side scalability.
torture.2021.12.07a: Torture-test in-kernel module updates.
torturescript.2021.11.30c: Torture-test scripting updates.

rcu/nocb: Remove rcu_node structure from nocb list when de-offloaded

2021-12-09T19:34:07+00:00

The nocb_gp_wait() function iterates over all CPUs in its group,
including even those CPUs that have been de-offloaded.  This is of
course suboptimal, especially if none of the CPUs within the group are
currently offloaded.  This will become even more of a problem once a
nocb kthread is created for all possible CPUs.

Therefore use a standard double linked list to link all the offloaded
rcu_data structures and safely add or delete these structure as we
offload or de-offload them, respectively.

Reviewed-by: Neeraj Upadhyay 
Signed-off-by: Frederic Weisbecker 
Cc: Boqun Feng 
Cc: Uladzislau Rezki 
Cc: Josh Triplett 
Cc: Joel Fernandes 
Tested-by: Juri Lelli 
Signed-off-by: Paul E. McKenney

rcu/nocb: Make local rcu_nocb_lock_irqsave() safe against concurrent deoffloading

2021-12-08T00:24:44+00:00

rcu_nocb_lock_irqsave() can be preempted between the call to
rcu_segcblist_is_offloaded() and the actual locking. This matters now
that rcu_core() is preemptible on PREEMPT_RT and the (de-)offloading
process can interrupt the softirq or the rcuc kthread.

As a result we may locklessly call into code that requires nocb locking.
In practice this is a problem while we accelerate callbacks on rcu_core().

Simply disabling interrupts before (instead of after) checking the NOCB
offload state fixes the issue.

Reported-and-tested-by: Valentin Schneider 
Tested-by: Sebastian Andrzej Siewior 
Signed-off-by: Frederic Weisbecker 
Cc: Valentin Schneider 
Cc: Peter Zijlstra 
Cc: Sebastian Andrzej Siewior 
Cc: Josh Triplett 
Cc: Joel Fernandes 
Cc: Boqun Feng 
Cc: Neeraj Upadhyay 
Cc: Uladzislau Rezki 
Cc: Thomas Gleixner 
Signed-off-by: Paul E. McKenney

rcu: Remove rcu_data.exp_deferred_qs and convert to rcu_data.cpu no_qs.b.exp

2021-12-08T00:22:21+00:00

Having two fields for the same purpose with subtle differences on
different RCU flavours is confusing, especially when both fields always
exist on both RCU flavours.

Fortunately, it is now safe for preemptible RCU to rely on the rcu_data
structure's ->cpu_no_qs.b.exp field, just like non-preemptible RCU.
This commit therefore removes the ad-hoc ->exp_deferred_qs field.

Signed-off-by: Frederic Weisbecker 
Signed-off-by: Paul E. McKenney

rcu: Remove the RCU_FAST_NO_HZ Kconfig option

2021-12-01T01:24:47+00:00

All of the uses of CONFIG_RCU_FAST_NO_HZ=y that I have seen involve
systems with RCU callbacks offloaded.  In this situation, all that this
Kconfig option does is slow down idle entry/exit with an additional
allways-taken early exit.  If this is the only use case, then this
Kconfig option nothing but an attractive nuisance that needs to go away.

This commit therefore removes the RCU_FAST_NO_HZ Kconfig option.

Signed-off-by: Paul E. McKenney

Merge branches 'bitmaprange.2021.05.10c', 'doc.2021.05.10c', 'fixes.2021.05.13a', 'kvfree_rcu.2021.05.10c', 'mmdumpobj.2021.05.10c', 'nocb.2021.05.12a', 'srcu.2021.05.12a', 'tasks.2021.05.18a' and 'torture.2021.05.10c' into HEAD

2021-05-18T17:56:19+00:00

bitmaprange.2021.05.10c: Allow "all" for bitmap ranges.
doc.2021.05.10c: Documentation updates.
fixes.2021.05.13a: Miscellaneous fixes.
kvfree_rcu.2021.05.10c: kvfree_rcu() updates.
mmdumpobj.2021.05.10c: mem_dump_obj() updates.
nocb.2021.05.12a: RCU NOCB CPU updates, including limited deoffloading.
srcu.2021.05.12a: SRCU updates.
tasks.2021.05.18a: Tasks-RCU updates.
torture.2021.05.10c: Torture-test updates.

rcu: Fix various typos in comments

2021-05-12T19:11:05+00:00

Fix ~12 single-word typos in RCU code comments.

[ paulmck: Apply feedback from Randy Dunlap. ]
Reviewed-by: Randy Dunlap 
Signed-off-by: Ingo Molnar 
Signed-off-by: Paul E. McKenney

rcu/nocb: Unify timers

2021-05-12T19:10:23+00:00

Now that ->nocb_timer and ->nocb_bypass_timer have become quite similar,
this commit merges them together.  A new RCU_NOCB_WAKE_BYPASS wake level
is introduced.  As a result, timers perform all kinds of deferred wake
ups but other deferred wakeup callsites only handle non-bypass wakeups
in order not to wake up rcuo too early.

The timer also unconditionally executes a full barrier so as to order
timer_pending() and callback enqueue although the path performing
RCU_NOCB_WAKE_FORCE that makes use of it is debatable. It should also
test against the rdp leader instead of the current rdp.

This unconditional full barrier shouldn't bring visible overhead since
these timers almost never fire.

Signed-off-by: Frederic Weisbecker 
Cc: Josh Triplett 
Cc: Lai Jiangshan 
Cc: Joel Fernandes 
Cc: Neeraj Upadhyay 
Cc: Boqun Feng 
Signed-off-by: Paul E. McKenney

rcu/nocb: Prepare for fine-grained deferred wakeup

2021-05-12T19:10:23+00:00

Tuning the deferred wakeup level must be done from a safe wakeup
point. Currently those sites are:

* ->nocb_timer
* user/idle/guest entry
* CPU down
* softirq/rcuc

All of these sites perform the wake up for both RCU_NOCB_WAKE and
RCU_NOCB_WAKE_FORCE.

In order to merge ->nocb_timer and ->nocb_bypass_timer together, we plan
to add a new RCU_NOCB_WAKE_BYPASS that really should be deferred until
a timer fires so that we don't wake up the NOCB-gp kthread too early.

To prepare for that, this commit specifies the per-callsite wakeup
level/limit.

Cc: Josh Triplett 
Cc: Lai Jiangshan 
Cc: Joel Fernandes 
Cc: Neeraj Upadhyay 
Cc: Boqun Feng 
Signed-off-by: Frederic Weisbecker 
[ paulmck: Fix non-NOCB rcu_nocb_need_deferred_wakeup() definition. ]
Signed-off-by: Paul E. McKenney