linux-stable/kernel/rcu/tree_exp.h

1107 lines
34 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0+ */
/*
* RCU expedited grace periods
*
* Copyright IBM Corporation, 2016
*
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
*/
#include <linux/lockdep.h>
static void rcu_exp_handler(void *unused);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
/*
* Record the start of an expedited grace period.
*/
static void rcu_exp_gp_seq_start(void)
{
rcu_seq_start(&rcu_state.expedited_sequence);
rcu: Make polled grace-period API account for expedited grace periods Currently, this code could splat: oldstate = get_state_synchronize_rcu(); synchronize_rcu_expedited(); WARN_ON_ONCE(!poll_state_synchronize_rcu(oldstate)); This situation is counter-intuitive and user-unfriendly. After all, there really was a perfectly valid full grace period right after the call to get_state_synchronize_rcu(), so why shouldn't poll_state_synchronize_rcu() know about it? This commit therefore makes the polled grace-period API aware of expedited grace periods in addition to the normal grace periods that it is already aware of. With this change, the above code is guaranteed not to splat. Please note that the above code can still splat due to counter wrap on the one hand and situations involving partially overlapping normal/expedited grace periods on the other. On 64-bit systems, the second is of course much more likely than the first. It is possible to modify this approach to prevent overlapping grace periods from causing splats, but only at the expense of greatly increasing the probability of counter wrap, as in within milliseconds on 32-bit systems and within minutes on 64-bit systems. This commit is in preparation for polled expedited grace periods. Link: https://lore.kernel.org/all/20220121142454.1994916-1-bfoster@redhat.com/ Link: https://docs.google.com/document/d/1RNKWW9jQyfjxw2E8dsXVTdvZYh0HnYeSHDKog9jhdN8/edit?usp=sharing Cc: Brian Foster <bfoster@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ian Kent <raven@themaw.net> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-14 13:56:35 +00:00
rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_exp_snap);
}
/*
* Return the value that the expedited-grace-period counter will have
* at the end of the current grace period.
*/
static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void)
{
return rcu_seq_endval(&rcu_state.expedited_sequence);
}
/*
* Record the end of an expedited grace period.
*/
static void rcu_exp_gp_seq_end(void)
{
rcu: Make polled grace-period API account for expedited grace periods Currently, this code could splat: oldstate = get_state_synchronize_rcu(); synchronize_rcu_expedited(); WARN_ON_ONCE(!poll_state_synchronize_rcu(oldstate)); This situation is counter-intuitive and user-unfriendly. After all, there really was a perfectly valid full grace period right after the call to get_state_synchronize_rcu(), so why shouldn't poll_state_synchronize_rcu() know about it? This commit therefore makes the polled grace-period API aware of expedited grace periods in addition to the normal grace periods that it is already aware of. With this change, the above code is guaranteed not to splat. Please note that the above code can still splat due to counter wrap on the one hand and situations involving partially overlapping normal/expedited grace periods on the other. On 64-bit systems, the second is of course much more likely than the first. It is possible to modify this approach to prevent overlapping grace periods from causing splats, but only at the expense of greatly increasing the probability of counter wrap, as in within milliseconds on 32-bit systems and within minutes on 64-bit systems. This commit is in preparation for polled expedited grace periods. Link: https://lore.kernel.org/all/20220121142454.1994916-1-bfoster@redhat.com/ Link: https://docs.google.com/document/d/1RNKWW9jQyfjxw2E8dsXVTdvZYh0HnYeSHDKog9jhdN8/edit?usp=sharing Cc: Brian Foster <bfoster@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ian Kent <raven@themaw.net> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-14 13:56:35 +00:00
rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_exp_snap);
rcu_seq_end(&rcu_state.expedited_sequence);
smp_mb(); /* Ensure that consecutive grace periods serialize. */
}
/*
* Take a snapshot of the expedited-grace-period counter, which is the
* earliest value that will indicate that a full grace period has
* elapsed since the current time.
*/
static unsigned long rcu_exp_gp_seq_snap(void)
{
unsigned long s;
smp_mb(); /* Caller's modifications seen first by other CPUs. */
s = rcu_seq_snap(&rcu_state.expedited_sequence);
trace_rcu_exp_grace_period(rcu_state.name, s, TPS("snap"));
return s;
}
/*
* Given a counter snapshot from rcu_exp_gp_seq_snap(), return true
* if a full expedited grace period has elapsed since that snapshot
* was taken.
*/
static bool rcu_exp_gp_seq_done(unsigned long s)
{
return rcu_seq_done(&rcu_state.expedited_sequence, s);
}
/*
* Reset the ->expmaskinit values in the rcu_node tree to reflect any
* recent CPU-online activity. Note that these masks are not cleared
* when CPUs go offline, so they reflect the union of all CPUs that have
* ever been online. This means that this function normally takes its
* no-work-to-do fastpath.
*/
static void sync_exp_reset_tree_hotplug(void)
{
bool done;
unsigned long flags;
unsigned long mask;
unsigned long oldmask;
int ncpus = smp_load_acquire(&rcu_state.ncpus); /* Order vs. locking. */
struct rcu_node *rnp;
struct rcu_node *rnp_up;
/* If no new CPUs onlined since last time, nothing to do. */
if (likely(ncpus == rcu_state.ncpus_snap))
return;
rcu_state.ncpus_snap = ncpus;
/*
* Each pass through the following loop propagates newly onlined
* CPUs for the current rcu_node structure up the rcu_node tree.
*/
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->expmaskinit == rnp->expmaskinitnext) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
continue; /* No new CPUs, nothing to do. */
}
/* Update this node's mask, track old value for propagation. */
oldmask = rnp->expmaskinit;
rnp->expmaskinit = rnp->expmaskinitnext;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
/* If was already nonzero, nothing to propagate. */
if (oldmask)
continue;
/* Propagate the new CPU up the tree. */
mask = rnp->grpmask;
rnp_up = rnp->parent;
done = false;
while (rnp_up) {
raw_spin_lock_irqsave_rcu_node(rnp_up, flags);
if (rnp_up->expmaskinit)
done = true;
rnp_up->expmaskinit |= mask;
raw_spin_unlock_irqrestore_rcu_node(rnp_up, flags);
if (done)
break;
mask = rnp_up->grpmask;
rnp_up = rnp_up->parent;
}
}
}
/*
* Reset the ->expmask values in the rcu_node tree in preparation for
* a new expedited grace period.
*/
static void __maybe_unused sync_exp_reset_tree(void)
{
unsigned long flags;
struct rcu_node *rnp;
sync_exp_reset_tree_hotplug();
rcu_for_each_node_breadth_first(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
WARN_ON_ONCE(rnp->expmask);
WRITE_ONCE(rnp->expmask, rnp->expmaskinit);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}
/*
* Return non-zero if there is no RCU expedited grace period in progress
* for the specified rcu_node structure, in other words, if all CPUs and
* tasks covered by the specified rcu_node structure have done their bit
* for the current expedited grace period.
*/
static bool sync_rcu_exp_done(struct rcu_node *rnp)
{
raw_lockdep_assert_held_rcu_node(rnp);
return READ_ONCE(rnp->exp_tasks) == NULL &&
READ_ONCE(rnp->expmask) == 0;
}
/*
* Like sync_rcu_exp_done(), but where the caller does not hold the
* rcu_node's ->lock.
*/
static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp)
{
unsigned long flags;
bool ret;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
ret = sync_rcu_exp_done(rnp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return ret;
}
/*
* Report the exit from RCU read-side critical section for the last task
* that queued itself during or before the current expedited preemptible-RCU
* grace period. This event is reported either to the rcu_node structure on
* which the task was queued or to one of that rcu_node structure's ancestors,
* recursively up the tree. (Calm down, calm down, we do the recursion
* iteratively!)
*/
static void __rcu_report_exp_rnp(struct rcu_node *rnp,
bool wake, unsigned long flags)
__releases(rnp->lock)
{
unsigned long mask;
raw_lockdep_assert_held_rcu_node(rnp);
for (;;) {
if (!sync_rcu_exp_done(rnp)) {
if (!rnp->expmask)
rcu_initiate_boost(rnp, flags);
else
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
break;
}
if (rnp->parent == NULL) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (wake) {
smp_mb(); /* EGP done before wake_up(). */
swake_up_one(&rcu_state.expedited_wq);
}
break;
}
mask = rnp->grpmask;
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled */
rnp = rnp->parent;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
WARN_ON_ONCE(!(rnp->expmask & mask));
WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
}
}
/*
* Report expedited quiescent state for specified node. This is a
* lock-acquisition wrapper function for __rcu_report_exp_rnp().
*/
static void __maybe_unused rcu_report_exp_rnp(struct rcu_node *rnp, bool wake)
{
unsigned long flags;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
__rcu_report_exp_rnp(rnp, wake, flags);
}
/*
* Report expedited quiescent state for multiple CPUs, all covered by the
* specified leaf rcu_node structure.
*/
static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
unsigned long mask, bool wake)
{
int cpu;
unsigned long flags;
struct rcu_data *rdp;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (!(rnp->expmask & mask)) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
for_each_leaf_node_cpu_mask(rnp, cpu, mask) {
rdp = per_cpu_ptr(&rcu_data, cpu);
if (!IS_ENABLED(CONFIG_NO_HZ_FULL) || !rdp->rcu_forced_tick_exp)
continue;
rdp->rcu_forced_tick_exp = false;
tick_dep_clear_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
}
__rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */
}
/*
* Report expedited quiescent state for specified rcu_data (CPU).
*/
static void rcu_report_exp_rdp(struct rcu_data *rdp)
{
WRITE_ONCE(rdp->cpu_no_qs.b.exp, false);
rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true);
}
/* Common code for work-done checking. */
static bool sync_exp_work_done(unsigned long s)
{
if (rcu_exp_gp_seq_done(s)) {
trace_rcu_exp_grace_period(rcu_state.name, s, TPS("done"));
smp_mb(); /* Ensure test happens before caller kfree(). */
return true;
}
return false;
}
/*
* Funnel-lock acquisition for expedited grace periods. Returns true
* if some other task completed an expedited grace period that this task
* can piggy-back on, and with no mutex held. Otherwise, returns false
* with the mutex held, indicating that the caller must actually do the
* expedited grace period.
*/
static bool exp_funnel_lock(unsigned long s)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
struct rcu_node *rnp = rdp->mynode;
struct rcu_node *rnp_root = rcu_get_root();
/* Low-contention fastpath. */
if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) &&
(rnp == rnp_root ||
ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) &&
mutex_trylock(&rcu_state.exp_mutex))
goto fastpath;
/*
* Each pass through the following loop works its way up
* the rcu_node tree, returning if others have done the work or
* otherwise falls through to acquire ->exp_mutex. The mapping
* from CPU to rcu_node structure can be inexact, as it is just
* promoting locality and is not strictly needed for correctness.
*/
for (; rnp != NULL; rnp = rnp->parent) {
if (sync_exp_work_done(s))
return true;
/* Work not done, either wait here or go up. */
spin_lock(&rnp->exp_lock);
if (ULONG_CMP_GE(rnp->exp_seq_rq, s)) {
/* Someone else doing GP, so wait for them. */
spin_unlock(&rnp->exp_lock);
trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level,
rnp->grplo, rnp->grphi,
TPS("wait"));
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(s));
return true;
}
WRITE_ONCE(rnp->exp_seq_rq, s); /* Followers can wait on us. */
spin_unlock(&rnp->exp_lock);
trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level,
rnp->grplo, rnp->grphi, TPS("nxtlvl"));
}
mutex_lock(&rcu_state.exp_mutex);
fastpath:
if (sync_exp_work_done(s)) {
mutex_unlock(&rcu_state.exp_mutex);
return true;
}
rcu_exp_gp_seq_start();
trace_rcu_exp_grace_period(rcu_state.name, s, TPS("start"));
return false;
}
/*
* Select the CPUs within the specified rcu_node that the upcoming
* expedited grace period needs to wait for.
*/
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
static void __sync_rcu_exp_select_node_cpus(struct rcu_exp_work *rewp)
{
int cpu;
unsigned long flags;
unsigned long mask_ofl_test;
unsigned long mask_ofl_ipi;
int ret;
struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
/* Each pass checks a CPU for identity, offline, and idle. */
mask_ofl_test = 0;
for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
unsigned long mask = rdp->grpmask;
int snap;
if (raw_smp_processor_id() == cpu ||
!(rnp->qsmaskinitnext & mask)) {
mask_ofl_test |= mask;
} else {
snap = rcu_dynticks_snap(cpu);
if (rcu_dynticks_in_eqs(snap))
mask_ofl_test |= mask;
else
rdp->exp_dynticks_snap = snap;
}
}
mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
/*
* Need to wait for any blocked tasks as well. Note that
* additional blocking tasks will also block the expedited GP
* until such time as the ->expmask bits are cleared.
*/
if (rcu_preempt_has_tasks(rnp))
WRITE_ONCE(rnp->exp_tasks, rnp->blkd_tasks.next);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
/* IPI the remaining CPUs for expedited quiescent state. */
for_each_leaf_node_cpu_mask(rnp, cpu, mask_ofl_ipi) {
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
unsigned long mask = rdp->grpmask;
retry_ipi:
if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) {
mask_ofl_test |= mask;
continue;
}
if (get_cpu() == cpu) {
rcu/exp: Mark current CPU as exp-QS in IPI loop second pass Expedited RCU grace periods invoke sync_rcu_exp_select_node_cpus(), which takes two passes over the leaf rcu_node structure's CPUs. The first pass gathers up the current CPU and CPUs that are in dynticks idle mode. The workqueue will report a quiescent state on their behalf later. The second pass sends IPIs to the rest of the CPUs, but excludes the current CPU, incorrectly assuming it has been included in the first pass's list of CPUs. Unfortunately the current CPU may have changed between the first and second pass, due to the fact that the various rcu_node structures' ->lock fields have been dropped, thus momentarily enabling preemption. This means that if the second pass's CPU was not on the first pass's list, it will be ignored completely. There will be no IPI sent to it, and there will be no reporting of quiescent states on its behalf. Unfortunately, the expedited grace period will nevertheless be waiting for that CPU to report a quiescent state, but with that CPU having no reason to believe that such a report is needed. The result will be an expedited grace period stall. Fix this by no longer excluding the current CPU from consideration during the second pass. Fixes: b9ad4d6ed18e ("rcu: Avoid self-IPI in sync_rcu_exp_select_node_cpus()") Reviewed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com> Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Neeraj Upadhyay <quic_neeraju@quicinc.com> Cc: Boqun Feng <boqun.feng@gmail.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Joel Fernandes <joel@joelfernandes.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2021-11-30 16:21:08 +00:00
mask_ofl_test |= mask;
put_cpu();
continue;
}
ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
put_cpu();
/* The CPU will report the QS in response to the IPI. */
if (!ret)
continue;
/* Failed, raced with CPU hotplug operation. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if ((rnp->qsmaskinitnext & mask) &&
(rnp->expmask & mask)) {
/* Online, so delay for a bit and try again. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("selectofl"));
schedule_timeout_idle(1);
goto retry_ipi;
}
/* CPU really is offline, so we must report its QS. */
if (rnp->expmask & mask)
mask_ofl_test |= mask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
/* Report quiescent states for those that went offline. */
if (mask_ofl_test)
rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
}
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
static void rcu_exp_sel_wait_wake(unsigned long s);
#ifdef CONFIG_RCU_EXP_KTHREAD
static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp)
{
struct rcu_exp_work *rewp =
container_of(wp, struct rcu_exp_work, rew_work);
__sync_rcu_exp_select_node_cpus(rewp);
}
static inline bool rcu_gp_par_worker_started(void)
{
return !!READ_ONCE(rcu_exp_par_gp_kworker);
}
static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
{
kthread_init_work(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
/*
* Use rcu_exp_par_gp_kworker, because flushing a work item from
* another work item on the same kthread worker can result in
* deadlock.
*/
kthread_queue_work(rcu_exp_par_gp_kworker, &rnp->rew.rew_work);
}
static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
{
kthread_flush_work(&rnp->rew.rew_work);
}
/*
* Work-queue handler to drive an expedited grace period forward.
*/
static void wait_rcu_exp_gp(struct kthread_work *wp)
{
struct rcu_exp_work *rewp;
rewp = container_of(wp, struct rcu_exp_work, rew_work);
rcu_exp_sel_wait_wake(rewp->rew_s);
}
static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew)
{
kthread_init_work(&rew->rew_work, wait_rcu_exp_gp);
kthread_queue_work(rcu_exp_gp_kworker, &rew->rew_work);
}
static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew)
{
}
#else /* !CONFIG_RCU_EXP_KTHREAD */
static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
{
struct rcu_exp_work *rewp =
container_of(wp, struct rcu_exp_work, rew_work);
__sync_rcu_exp_select_node_cpus(rewp);
}
static inline bool rcu_gp_par_worker_started(void)
{
return !!READ_ONCE(rcu_par_gp_wq);
}
static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
{
int cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
/* If all offline, queue the work on an unbound CPU. */
if (unlikely(cpu > rnp->grphi - rnp->grplo))
cpu = WORK_CPU_UNBOUND;
else
cpu += rnp->grplo;
queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
}
static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
{
flush_work(&rnp->rew.rew_work);
}
/*
* Work-queue handler to drive an expedited grace period forward.
*/
static void wait_rcu_exp_gp(struct work_struct *wp)
{
struct rcu_exp_work *rewp;
rewp = container_of(wp, struct rcu_exp_work, rew_work);
rcu_exp_sel_wait_wake(rewp->rew_s);
}
static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew)
{
INIT_WORK_ONSTACK(&rew->rew_work, wait_rcu_exp_gp);
queue_work(rcu_gp_wq, &rew->rew_work);
}
static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew)
{
destroy_work_on_stack(&rew->rew_work);
}
#endif /* CONFIG_RCU_EXP_KTHREAD */
/*
* Select the nodes that the upcoming expedited grace period needs
* to wait for.
*/
static void sync_rcu_exp_select_cpus(void)
{
struct rcu_node *rnp;
trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("reset"));
sync_exp_reset_tree();
trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("select"));
/* Schedule work for each leaf rcu_node structure. */
rcu_for_each_leaf_node(rnp) {
rnp->exp_need_flush = false;
if (!READ_ONCE(rnp->expmask))
continue; /* Avoid early boot non-existent wq. */
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
if (!rcu_gp_par_worker_started() ||
rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
rcu_is_last_leaf_node(rnp)) {
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
/* No worker started yet or last leaf, do direct call. */
sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
continue;
}
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
sync_rcu_exp_select_cpus_queue_work(rnp);
rnp->exp_need_flush = true;
}
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
/* Wait for jobs (if any) to complete. */
rcu_for_each_leaf_node(rnp)
if (rnp->exp_need_flush)
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
sync_rcu_exp_select_cpus_flush_work(rnp);
}
/*
* Wait for the expedited grace period to elapse, within time limit.
* If the time limit is exceeded without the grace period elapsing,
* return false, otherwise return true.
*/
static bool synchronize_rcu_expedited_wait_once(long tlimit)
{
int t;
struct rcu_node *rnp_root = rcu_get_root();
t = swait_event_timeout_exclusive(rcu_state.expedited_wq,
sync_rcu_exp_done_unlocked(rnp_root),
tlimit);
// Workqueues should not be signaled.
if (t > 0 || sync_rcu_exp_done_unlocked(rnp_root))
return true;
WARN_ON(t < 0); /* workqueues should not be signaled. */
return false;
}
/*
* Wait for the expedited grace period to elapse, issuing any needed
* RCU CPU stall warnings along the way.
*/
static void synchronize_rcu_expedited_wait(void)
{
int cpu;
unsigned long j;
unsigned long jiffies_stall;
unsigned long jiffies_start;
unsigned long mask;
int ndetected;
struct rcu_data *rdp;
struct rcu_node *rnp;
struct rcu_node *rnp_root = rcu_get_root();
trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
jiffies_stall = rcu_exp_jiffies_till_stall_check();
jiffies_start = jiffies;
if (tick_nohz_full_enabled() && rcu_inkernel_boot_has_ended()) {
if (synchronize_rcu_expedited_wait_once(1))
return;
rcu_for_each_leaf_node(rnp) {
mask = READ_ONCE(rnp->expmask);
for_each_leaf_node_cpu_mask(rnp, cpu, mask) {
rdp = per_cpu_ptr(&rcu_data, cpu);
if (rdp->rcu_forced_tick_exp)
continue;
rdp->rcu_forced_tick_exp = true;
rcu: Prevent expedited GP from enabling tick on offline CPU If an RCU expedited grace period starts just when a CPU is in the process of going offline, so that the outgoing CPU has completed its pass through stop-machine but has not yet completed its final dive into the idle loop, RCU will attempt to enable that CPU's scheduling-clock tick via a call to tick_dep_set_cpu(). For this to happen, that CPU has to have been online when the expedited grace period completed its CPU-selection phase. This is pointless: The outgoing CPU has interrupts disabled, so it cannot take a scheduling-clock tick anyway. In addition, the tick_dep_set_cpu() function's eventual call to irq_work_queue_on() will splat as follows: smpboot: CPU 1 is now offline WARNING: CPU: 6 PID: 124 at kernel/irq_work.c:95 +irq_work_queue_on+0x57/0x60 Modules linked in: CPU: 6 PID: 124 Comm: kworker/6:2 Not tainted 5.15.0-rc1+ #3 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS +rel-1.14.0-0-g155821a-rebuilt.opensuse.org 04/01/2014 Workqueue: rcu_gp wait_rcu_exp_gp RIP: 0010:irq_work_queue_on+0x57/0x60 Code: 8b 05 1d c7 ea 62 a9 00 00 f0 00 75 21 4c 89 ce 44 89 c7 e8 +9b 37 fa ff ba 01 00 00 00 89 d0 c3 4c 89 cf e8 3b ff ff ff eb ee <0f> 0b eb b7 +0f 0b eb db 90 48 c7 c0 98 2a 02 00 65 48 03 05 91 6f RSP: 0000:ffffb12cc038fe48 EFLAGS: 00010282 RAX: 0000000000000001 RBX: 0000000000005208 RCX: 0000000000000020 RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff9ad01f45a680 RBP: 000000000004c990 R08: 0000000000000001 R09: ffff9ad01f45a680 R10: ffffb12cc0317db0 R11: 0000000000000001 R12: 00000000fffecee8 R13: 0000000000000001 R14: 0000000000026980 R15: ffffffff9e53ae00 FS: 0000000000000000(0000) GS:ffff9ad01f580000(0000) +knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000000de0c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tick_nohz_dep_set_cpu+0x59/0x70 rcu_exp_wait_wake+0x54e/0x870 ? sync_rcu_exp_select_cpus+0x1fc/0x390 process_one_work+0x1ef/0x3c0 ? process_one_work+0x3c0/0x3c0 worker_thread+0x28/0x3c0 ? process_one_work+0x3c0/0x3c0 kthread+0x115/0x140 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x22/0x30 ---[ end trace c5bf75eb6aa80bc6 ]--- This commit therefore avoids invoking tick_dep_set_cpu() on offlined CPUs to limit both futility and false-positive splats. Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2021-09-29 16:21:34 +00:00
preempt_disable();
if (cpu_online(cpu))
tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
preempt_enable();
}
}
j = READ_ONCE(jiffies_till_first_fqs);
if (synchronize_rcu_expedited_wait_once(j + HZ))
return;
}
for (;;) {
if (synchronize_rcu_expedited_wait_once(jiffies_stall))
return;
if (rcu_stall_is_suppressed())
continue;
trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
rcu_state.name);
ndetected = 0;
rcu_for_each_leaf_node(rnp) {
ndetected += rcu_print_task_exp_stall(rnp);
rcu: Correctly handle sparse possible cpus In many cases in the RCU tree code, we iterate over the set of cpus for a leaf node described by rcu_node::grplo and rcu_node::grphi, checking per-cpu data for each cpu in this range. However, if the set of possible cpus is sparse, some cpus described in this range are not possible, and thus no per-cpu region will have been allocated (or initialised) for them by the generic percpu code. Erroneous accesses to a per-cpu area for these !possible cpus may fault or may hit other data depending on the addressed generated when the erroneous per cpu offset is applied. In practice, both cases have been observed on arm64 hardware (the former being silent, but detectable with additional patches). To avoid issues resulting from this, we must iterate over the set of *possible* cpus for a given leaf node. This patch add a new helper, for_each_leaf_node_possible_cpu, to enable this. As iteration is often intertwined with rcu_node local bitmask manipulation, a new leaf_node_cpu_bit helper is added to make this simpler and more consistent. The RCU tree code is made to use both of these where appropriate. Without this patch, running reboot at a shell can result in an oops like: [ 3369.075979] Unable to handle kernel paging request at virtual address ffffff8008b21b4c [ 3369.083881] pgd = ffffffc3ecdda000 [ 3369.087270] [ffffff8008b21b4c] *pgd=00000083eca48003, *pud=00000083eca48003, *pmd=0000000000000000 [ 3369.096222] Internal error: Oops: 96000007 [#1] PREEMPT SMP [ 3369.101781] Modules linked in: [ 3369.104825] CPU: 2 PID: 1817 Comm: NetworkManager Tainted: G W 4.6.0+ #3 [ 3369.121239] task: ffffffc0fa13e000 ti: ffffffc3eb940000 task.ti: ffffffc3eb940000 [ 3369.128708] PC is at sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.134094] LR is at sync_rcu_exp_select_cpus+0x104/0x510 [ 3369.139479] pc : [<ffffff80081109a8>] lr : [<ffffff8008110924>] pstate: 200001c5 [ 3369.146860] sp : ffffffc3eb9435a0 [ 3369.150162] x29: ffffffc3eb9435a0 x28: ffffff8008be4f88 [ 3369.155465] x27: ffffff8008b66c80 x26: ffffffc3eceb2600 [ 3369.160767] x25: 0000000000000001 x24: ffffff8008be4f88 [ 3369.166070] x23: ffffff8008b51c3c x22: ffffff8008b66c80 [ 3369.171371] x21: 0000000000000001 x20: ffffff8008b21b40 [ 3369.176673] x19: ffffff8008b66c80 x18: 0000000000000000 [ 3369.181975] x17: 0000007fa951a010 x16: ffffff80086a30f0 [ 3369.187278] x15: 0000007fa9505590 x14: 0000000000000000 [ 3369.192580] x13: ffffff8008b51000 x12: ffffffc3eb940000 [ 3369.197882] x11: 0000000000000006 x10: ffffff8008b51b78 [ 3369.203184] x9 : 0000000000000001 x8 : ffffff8008be4000 [ 3369.208486] x7 : ffffff8008b21b40 x6 : 0000000000001003 [ 3369.213788] x5 : 0000000000000000 x4 : ffffff8008b27280 [ 3369.219090] x3 : ffffff8008b21b4c x2 : 0000000000000001 [ 3369.224406] x1 : 0000000000000001 x0 : 0000000000000140 ... [ 3369.972257] [<ffffff80081109a8>] sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.978685] [<ffffff80081128b4>] synchronize_rcu_expedited+0x64/0xa8 [ 3369.985026] [<ffffff80086b987c>] synchronize_net+0x24/0x30 [ 3369.990499] [<ffffff80086ddb54>] dev_deactivate_many+0x28c/0x298 [ 3369.996493] [<ffffff80086b6bb8>] __dev_close_many+0x60/0xd0 [ 3370.002052] [<ffffff80086b6d48>] __dev_close+0x28/0x40 [ 3370.007178] [<ffffff80086bf62c>] __dev_change_flags+0x8c/0x158 [ 3370.012999] [<ffffff80086bf718>] dev_change_flags+0x20/0x60 [ 3370.018558] [<ffffff80086cf7f0>] do_setlink+0x288/0x918 [ 3370.023771] [<ffffff80086d0798>] rtnl_newlink+0x398/0x6a8 [ 3370.029158] [<ffffff80086cee84>] rtnetlink_rcv_msg+0xe4/0x220 [ 3370.034891] [<ffffff80086e274c>] netlink_rcv_skb+0xc4/0xf8 [ 3370.040364] [<ffffff80086ced8c>] rtnetlink_rcv+0x2c/0x40 [ 3370.045663] [<ffffff80086e1fe8>] netlink_unicast+0x160/0x238 [ 3370.051309] [<ffffff80086e24b8>] netlink_sendmsg+0x2f0/0x358 [ 3370.056956] [<ffffff80086a0070>] sock_sendmsg+0x18/0x30 [ 3370.062168] [<ffffff80086a21cc>] ___sys_sendmsg+0x26c/0x280 [ 3370.067728] [<ffffff80086a30ac>] __sys_sendmsg+0x44/0x88 [ 3370.073027] [<ffffff80086a3100>] SyS_sendmsg+0x10/0x20 [ 3370.078153] [<ffffff8008085e70>] el0_svc_naked+0x24/0x28 Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reported-by: Dennis Chen <dennis.chen@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Steve Capper <steve.capper@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2016-06-03 14:20:04 +00:00
for_each_leaf_node_possible_cpu(rnp, cpu) {
struct rcu_data *rdp;
rcu: Correctly handle sparse possible cpus In many cases in the RCU tree code, we iterate over the set of cpus for a leaf node described by rcu_node::grplo and rcu_node::grphi, checking per-cpu data for each cpu in this range. However, if the set of possible cpus is sparse, some cpus described in this range are not possible, and thus no per-cpu region will have been allocated (or initialised) for them by the generic percpu code. Erroneous accesses to a per-cpu area for these !possible cpus may fault or may hit other data depending on the addressed generated when the erroneous per cpu offset is applied. In practice, both cases have been observed on arm64 hardware (the former being silent, but detectable with additional patches). To avoid issues resulting from this, we must iterate over the set of *possible* cpus for a given leaf node. This patch add a new helper, for_each_leaf_node_possible_cpu, to enable this. As iteration is often intertwined with rcu_node local bitmask manipulation, a new leaf_node_cpu_bit helper is added to make this simpler and more consistent. The RCU tree code is made to use both of these where appropriate. Without this patch, running reboot at a shell can result in an oops like: [ 3369.075979] Unable to handle kernel paging request at virtual address ffffff8008b21b4c [ 3369.083881] pgd = ffffffc3ecdda000 [ 3369.087270] [ffffff8008b21b4c] *pgd=00000083eca48003, *pud=00000083eca48003, *pmd=0000000000000000 [ 3369.096222] Internal error: Oops: 96000007 [#1] PREEMPT SMP [ 3369.101781] Modules linked in: [ 3369.104825] CPU: 2 PID: 1817 Comm: NetworkManager Tainted: G W 4.6.0+ #3 [ 3369.121239] task: ffffffc0fa13e000 ti: ffffffc3eb940000 task.ti: ffffffc3eb940000 [ 3369.128708] PC is at sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.134094] LR is at sync_rcu_exp_select_cpus+0x104/0x510 [ 3369.139479] pc : [<ffffff80081109a8>] lr : [<ffffff8008110924>] pstate: 200001c5 [ 3369.146860] sp : ffffffc3eb9435a0 [ 3369.150162] x29: ffffffc3eb9435a0 x28: ffffff8008be4f88 [ 3369.155465] x27: ffffff8008b66c80 x26: ffffffc3eceb2600 [ 3369.160767] x25: 0000000000000001 x24: ffffff8008be4f88 [ 3369.166070] x23: ffffff8008b51c3c x22: ffffff8008b66c80 [ 3369.171371] x21: 0000000000000001 x20: ffffff8008b21b40 [ 3369.176673] x19: ffffff8008b66c80 x18: 0000000000000000 [ 3369.181975] x17: 0000007fa951a010 x16: ffffff80086a30f0 [ 3369.187278] x15: 0000007fa9505590 x14: 0000000000000000 [ 3369.192580] x13: ffffff8008b51000 x12: ffffffc3eb940000 [ 3369.197882] x11: 0000000000000006 x10: ffffff8008b51b78 [ 3369.203184] x9 : 0000000000000001 x8 : ffffff8008be4000 [ 3369.208486] x7 : ffffff8008b21b40 x6 : 0000000000001003 [ 3369.213788] x5 : 0000000000000000 x4 : ffffff8008b27280 [ 3369.219090] x3 : ffffff8008b21b4c x2 : 0000000000000001 [ 3369.224406] x1 : 0000000000000001 x0 : 0000000000000140 ... [ 3369.972257] [<ffffff80081109a8>] sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.978685] [<ffffff80081128b4>] synchronize_rcu_expedited+0x64/0xa8 [ 3369.985026] [<ffffff80086b987c>] synchronize_net+0x24/0x30 [ 3369.990499] [<ffffff80086ddb54>] dev_deactivate_many+0x28c/0x298 [ 3369.996493] [<ffffff80086b6bb8>] __dev_close_many+0x60/0xd0 [ 3370.002052] [<ffffff80086b6d48>] __dev_close+0x28/0x40 [ 3370.007178] [<ffffff80086bf62c>] __dev_change_flags+0x8c/0x158 [ 3370.012999] [<ffffff80086bf718>] dev_change_flags+0x20/0x60 [ 3370.018558] [<ffffff80086cf7f0>] do_setlink+0x288/0x918 [ 3370.023771] [<ffffff80086d0798>] rtnl_newlink+0x398/0x6a8 [ 3370.029158] [<ffffff80086cee84>] rtnetlink_rcv_msg+0xe4/0x220 [ 3370.034891] [<ffffff80086e274c>] netlink_rcv_skb+0xc4/0xf8 [ 3370.040364] [<ffffff80086ced8c>] rtnetlink_rcv+0x2c/0x40 [ 3370.045663] [<ffffff80086e1fe8>] netlink_unicast+0x160/0x238 [ 3370.051309] [<ffffff80086e24b8>] netlink_sendmsg+0x2f0/0x358 [ 3370.056956] [<ffffff80086a0070>] sock_sendmsg+0x18/0x30 [ 3370.062168] [<ffffff80086a21cc>] ___sys_sendmsg+0x26c/0x280 [ 3370.067728] [<ffffff80086a30ac>] __sys_sendmsg+0x44/0x88 [ 3370.073027] [<ffffff80086a3100>] SyS_sendmsg+0x10/0x20 [ 3370.078153] [<ffffff8008085e70>] el0_svc_naked+0x24/0x28 Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reported-by: Dennis Chen <dennis.chen@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Steve Capper <steve.capper@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2016-06-03 14:20:04 +00:00
mask = leaf_node_cpu_bit(rnp, cpu);
if (!(READ_ONCE(rnp->expmask) & mask))
continue;
ndetected++;
rdp = per_cpu_ptr(&rcu_data, cpu);
rcu: Add irqs-disabled indicator to expedited RCU CPU stall warnings If a CPU has interrupts disabled continuously starting before the beginning of a given expedited RCU grace period, that CPU will not execute that grace period's IPI handler. This will in turn mean that the ->cpu_no_qs.b.exp field in that CPU's rcu_data structure will continue to contain the boolean value false. Knowing whether or not a CPU has had interrupts disabled can be helpful when debugging an expedited RCU CPU stall warning, so this commit adds a "D" indicator expedited RCU CPU stall warnings that signifies that the corresponding CPU has had interrupts disabled throughout. This capability was tested as follows: runqemu kvm slirp nographic qemuparams="-m 4096 -smp 4" bootparams= "isolcpus=2,3 nohz_full=2,3 rcu_nocbs=2,3 rcutree.dump_tree=1 rcutorture.stall_cpu_holdoff=30 rcutorture.stall_cpu=40 rcutorture.stall_cpu_irqsoff=1 rcutorture.stall_cpu_block=0 rcutorture.stall_no_softlockup=1" -d The rcu_torture_stall() function ran on CPU 1, which displays the "D" as expected given the rcutorture.stall_cpu_irqsoff=1 module parameter: ............ rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: { 1-...D } 26467 jiffies s: 13317 root: 0x1/. rcu: blocking rcu_node structures (internal RCU debug): l=1:0-1:0x2/. Task dump for CPU 1: task:rcu_torture_sta state:R running task stack: 0 pid: 76 ppid: 2 flags:0x00004008 Signed-off-by: Zqiang <qiang1.zhang@intel.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-05-18 11:43:10 +00:00
pr_cont(" %d-%c%c%c%c", cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rnp->expmaskinit)],
rcu: Add irqs-disabled indicator to expedited RCU CPU stall warnings If a CPU has interrupts disabled continuously starting before the beginning of a given expedited RCU grace period, that CPU will not execute that grace period's IPI handler. This will in turn mean that the ->cpu_no_qs.b.exp field in that CPU's rcu_data structure will continue to contain the boolean value false. Knowing whether or not a CPU has had interrupts disabled can be helpful when debugging an expedited RCU CPU stall warning, so this commit adds a "D" indicator expedited RCU CPU stall warnings that signifies that the corresponding CPU has had interrupts disabled throughout. This capability was tested as follows: runqemu kvm slirp nographic qemuparams="-m 4096 -smp 4" bootparams= "isolcpus=2,3 nohz_full=2,3 rcu_nocbs=2,3 rcutree.dump_tree=1 rcutorture.stall_cpu_holdoff=30 rcutorture.stall_cpu=40 rcutorture.stall_cpu_irqsoff=1 rcutorture.stall_cpu_block=0 rcutorture.stall_no_softlockup=1" -d The rcu_torture_stall() function ran on CPU 1, which displays the "D" as expected given the rcutorture.stall_cpu_irqsoff=1 module parameter: ............ rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: { 1-...D } 26467 jiffies s: 13317 root: 0x1/. rcu: blocking rcu_node structures (internal RCU debug): l=1:0-1:0x2/. Task dump for CPU 1: task:rcu_torture_sta state:R running task stack: 0 pid: 76 ppid: 2 flags:0x00004008 Signed-off-by: Zqiang <qiang1.zhang@intel.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-05-18 11:43:10 +00:00
"N."[!!(rdp->grpmask & rnp->expmaskinitnext)],
"D."[!!(rdp->cpu_no_qs.b.exp)]);
}
}
pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
jiffies - jiffies_start, rcu_state.expedited_sequence,
data_race(rnp_root->expmask),
".T"[!!data_race(rnp_root->exp_tasks)]);
if (ndetected) {
pr_err("blocking rcu_node structures (internal RCU debug):");
rcu_for_each_node_breadth_first(rnp) {
if (rnp == rnp_root)
continue; /* printed unconditionally */
if (sync_rcu_exp_done_unlocked(rnp))
continue;
pr_cont(" l=%u:%d-%d:%#lx/%c",
rnp->level, rnp->grplo, rnp->grphi,
data_race(rnp->expmask),
".T"[!!data_race(rnp->exp_tasks)]);
}
pr_cont("\n");
}
rcu_for_each_leaf_node(rnp) {
rcu: Correctly handle sparse possible cpus In many cases in the RCU tree code, we iterate over the set of cpus for a leaf node described by rcu_node::grplo and rcu_node::grphi, checking per-cpu data for each cpu in this range. However, if the set of possible cpus is sparse, some cpus described in this range are not possible, and thus no per-cpu region will have been allocated (or initialised) for them by the generic percpu code. Erroneous accesses to a per-cpu area for these !possible cpus may fault or may hit other data depending on the addressed generated when the erroneous per cpu offset is applied. In practice, both cases have been observed on arm64 hardware (the former being silent, but detectable with additional patches). To avoid issues resulting from this, we must iterate over the set of *possible* cpus for a given leaf node. This patch add a new helper, for_each_leaf_node_possible_cpu, to enable this. As iteration is often intertwined with rcu_node local bitmask manipulation, a new leaf_node_cpu_bit helper is added to make this simpler and more consistent. The RCU tree code is made to use both of these where appropriate. Without this patch, running reboot at a shell can result in an oops like: [ 3369.075979] Unable to handle kernel paging request at virtual address ffffff8008b21b4c [ 3369.083881] pgd = ffffffc3ecdda000 [ 3369.087270] [ffffff8008b21b4c] *pgd=00000083eca48003, *pud=00000083eca48003, *pmd=0000000000000000 [ 3369.096222] Internal error: Oops: 96000007 [#1] PREEMPT SMP [ 3369.101781] Modules linked in: [ 3369.104825] CPU: 2 PID: 1817 Comm: NetworkManager Tainted: G W 4.6.0+ #3 [ 3369.121239] task: ffffffc0fa13e000 ti: ffffffc3eb940000 task.ti: ffffffc3eb940000 [ 3369.128708] PC is at sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.134094] LR is at sync_rcu_exp_select_cpus+0x104/0x510 [ 3369.139479] pc : [<ffffff80081109a8>] lr : [<ffffff8008110924>] pstate: 200001c5 [ 3369.146860] sp : ffffffc3eb9435a0 [ 3369.150162] x29: ffffffc3eb9435a0 x28: ffffff8008be4f88 [ 3369.155465] x27: ffffff8008b66c80 x26: ffffffc3eceb2600 [ 3369.160767] x25: 0000000000000001 x24: ffffff8008be4f88 [ 3369.166070] x23: ffffff8008b51c3c x22: ffffff8008b66c80 [ 3369.171371] x21: 0000000000000001 x20: ffffff8008b21b40 [ 3369.176673] x19: ffffff8008b66c80 x18: 0000000000000000 [ 3369.181975] x17: 0000007fa951a010 x16: ffffff80086a30f0 [ 3369.187278] x15: 0000007fa9505590 x14: 0000000000000000 [ 3369.192580] x13: ffffff8008b51000 x12: ffffffc3eb940000 [ 3369.197882] x11: 0000000000000006 x10: ffffff8008b51b78 [ 3369.203184] x9 : 0000000000000001 x8 : ffffff8008be4000 [ 3369.208486] x7 : ffffff8008b21b40 x6 : 0000000000001003 [ 3369.213788] x5 : 0000000000000000 x4 : ffffff8008b27280 [ 3369.219090] x3 : ffffff8008b21b4c x2 : 0000000000000001 [ 3369.224406] x1 : 0000000000000001 x0 : 0000000000000140 ... [ 3369.972257] [<ffffff80081109a8>] sync_rcu_exp_select_cpus+0x188/0x510 [ 3369.978685] [<ffffff80081128b4>] synchronize_rcu_expedited+0x64/0xa8 [ 3369.985026] [<ffffff80086b987c>] synchronize_net+0x24/0x30 [ 3369.990499] [<ffffff80086ddb54>] dev_deactivate_many+0x28c/0x298 [ 3369.996493] [<ffffff80086b6bb8>] __dev_close_many+0x60/0xd0 [ 3370.002052] [<ffffff80086b6d48>] __dev_close+0x28/0x40 [ 3370.007178] [<ffffff80086bf62c>] __dev_change_flags+0x8c/0x158 [ 3370.012999] [<ffffff80086bf718>] dev_change_flags+0x20/0x60 [ 3370.018558] [<ffffff80086cf7f0>] do_setlink+0x288/0x918 [ 3370.023771] [<ffffff80086d0798>] rtnl_newlink+0x398/0x6a8 [ 3370.029158] [<ffffff80086cee84>] rtnetlink_rcv_msg+0xe4/0x220 [ 3370.034891] [<ffffff80086e274c>] netlink_rcv_skb+0xc4/0xf8 [ 3370.040364] [<ffffff80086ced8c>] rtnetlink_rcv+0x2c/0x40 [ 3370.045663] [<ffffff80086e1fe8>] netlink_unicast+0x160/0x238 [ 3370.051309] [<ffffff80086e24b8>] netlink_sendmsg+0x2f0/0x358 [ 3370.056956] [<ffffff80086a0070>] sock_sendmsg+0x18/0x30 [ 3370.062168] [<ffffff80086a21cc>] ___sys_sendmsg+0x26c/0x280 [ 3370.067728] [<ffffff80086a30ac>] __sys_sendmsg+0x44/0x88 [ 3370.073027] [<ffffff80086a3100>] SyS_sendmsg+0x10/0x20 [ 3370.078153] [<ffffff8008085e70>] el0_svc_naked+0x24/0x28 Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reported-by: Dennis Chen <dennis.chen@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Steve Capper <steve.capper@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2016-06-03 14:20:04 +00:00
for_each_leaf_node_possible_cpu(rnp, cpu) {
mask = leaf_node_cpu_bit(rnp, cpu);
if (!(READ_ONCE(rnp->expmask) & mask))
continue;
dump_cpu_task(cpu);
}
}
jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3;
panic_on_rcu_stall();
}
}
/*
* Wait for the current expedited grace period to complete, and then
* wake up everyone who piggybacked on the just-completed expedited
* grace period. Also update all the ->exp_seq_rq counters as needed
* in order to avoid counter-wrap problems.
*/
static void rcu_exp_wait_wake(unsigned long s)
{
struct rcu_node *rnp;
synchronize_rcu_expedited_wait();
rcu: Allow only one expedited GP to run concurrently with wakeups 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: 3b5f668e715b ("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>
2019-11-19 19:50:52 +00:00
// Switch over to wakeup mode, allowing the next GP to proceed.
// End the previous grace period only after acquiring the mutex
// to ensure that only one GP runs concurrently with wakeups.
mutex_lock(&rcu_state.exp_wake_mutex);
rcu: Allow only one expedited GP to run concurrently with wakeups 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: 3b5f668e715b ("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>
2019-11-19 19:50:52 +00:00
rcu_exp_gp_seq_end();
trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end"));
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) {
spin_lock(&rnp->exp_lock);
/* Recheck, avoid hang in case someone just arrived. */
if (ULONG_CMP_LT(rnp->exp_seq_rq, s))
WRITE_ONCE(rnp->exp_seq_rq, s);
spin_unlock(&rnp->exp_lock);
}
smp_mb(); /* All above changes before wakeup. */
rcu: Fix missed wakeup of exp_wq waiters 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: 3b5f668e715b ("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>
2019-11-19 03:17:07 +00:00
wake_up_all(&rnp->exp_wq[rcu_seq_ctr(s) & 0x3]);
}
trace_rcu_exp_grace_period(rcu_state.name, s, TPS("endwake"));
mutex_unlock(&rcu_state.exp_wake_mutex);
}
rcu: Narrow early boot window of illegal synchronous grace periods The current preemptible RCU implementation goes through three phases during bootup. In the first phase, there is only one CPU that is running with preemption disabled, so that a no-op is a synchronous grace period. In the second mid-boot phase, the scheduler is running, but RCU has not yet gotten its kthreads spawned (and, for expedited grace periods, workqueues are not yet running. During this time, any attempt to do a synchronous grace period will hang the system (or complain bitterly, depending). In the third and final phase, RCU is fully operational and everything works normally. This has been OK for some time, but there has recently been some synchronous grace periods showing up during the second mid-boot phase. This code worked "by accident" for awhile, but started failing as soon as expedited RCU grace periods switched over to workqueues in commit 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue"). Note that the code was buggy even before this commit, as it was subject to failure on real-time systems that forced all expedited grace periods to run as normal grace periods (for example, using the rcu_normal ksysfs parameter). The callchain from the failure case is as follows: early_amd_iommu_init() |-> acpi_put_table(ivrs_base); |-> acpi_tb_put_table(table_desc); |-> acpi_tb_invalidate_table(table_desc); |-> acpi_tb_release_table(...) |-> acpi_os_unmap_memory |-> acpi_os_unmap_iomem |-> acpi_os_map_cleanup |-> synchronize_rcu_expedited The kernel showing this callchain was built with CONFIG_PREEMPT_RCU=y, which caused the code to try using workqueues before they were initialized, which did not go well. This commit therefore reworks RCU to permit synchronous grace periods to proceed during this mid-boot phase. This commit is therefore a fix to a regression introduced in v4.9, and is therefore being put forward post-merge-window in v4.10. This commit sets a flag from the existing rcu_scheduler_starting() function which causes all synchronous grace periods to take the expedited path. The expedited path now checks this flag, using the requesting task to drive the expedited grace period forward during the mid-boot phase. Finally, this flag is updated by a core_initcall() function named rcu_exp_runtime_mode(), which causes the runtime codepaths to be used. Note that this arrangement assumes that tasks are not sent POSIX signals (or anything similar) from the time that the first task is spawned through core_initcall() time. Fixes: 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue") Reported-by: "Zheng, Lv" <lv.zheng@intel.com> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Stan Kain <stan.kain@gmail.com> Tested-by: Ivan <waffolz@hotmail.com> Tested-by: Emanuel Castelo <emanuel.castelo@gmail.com> Tested-by: Bruno Pesavento <bpesavento@infinito.it> Tested-by: Borislav Petkov <bp@suse.de> Tested-by: Frederic Bezies <fredbezies@gmail.com> Cc: <stable@vger.kernel.org> # 4.9.0-
2017-01-10 10:28:26 +00:00
/*
* Common code to drive an expedited grace period forward, used by
* workqueues and mid-boot-time tasks.
*/
static void rcu_exp_sel_wait_wake(unsigned long s)
rcu: Narrow early boot window of illegal synchronous grace periods The current preemptible RCU implementation goes through three phases during bootup. In the first phase, there is only one CPU that is running with preemption disabled, so that a no-op is a synchronous grace period. In the second mid-boot phase, the scheduler is running, but RCU has not yet gotten its kthreads spawned (and, for expedited grace periods, workqueues are not yet running. During this time, any attempt to do a synchronous grace period will hang the system (or complain bitterly, depending). In the third and final phase, RCU is fully operational and everything works normally. This has been OK for some time, but there has recently been some synchronous grace periods showing up during the second mid-boot phase. This code worked "by accident" for awhile, but started failing as soon as expedited RCU grace periods switched over to workqueues in commit 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue"). Note that the code was buggy even before this commit, as it was subject to failure on real-time systems that forced all expedited grace periods to run as normal grace periods (for example, using the rcu_normal ksysfs parameter). The callchain from the failure case is as follows: early_amd_iommu_init() |-> acpi_put_table(ivrs_base); |-> acpi_tb_put_table(table_desc); |-> acpi_tb_invalidate_table(table_desc); |-> acpi_tb_release_table(...) |-> acpi_os_unmap_memory |-> acpi_os_unmap_iomem |-> acpi_os_map_cleanup |-> synchronize_rcu_expedited The kernel showing this callchain was built with CONFIG_PREEMPT_RCU=y, which caused the code to try using workqueues before they were initialized, which did not go well. This commit therefore reworks RCU to permit synchronous grace periods to proceed during this mid-boot phase. This commit is therefore a fix to a regression introduced in v4.9, and is therefore being put forward post-merge-window in v4.10. This commit sets a flag from the existing rcu_scheduler_starting() function which causes all synchronous grace periods to take the expedited path. The expedited path now checks this flag, using the requesting task to drive the expedited grace period forward during the mid-boot phase. Finally, this flag is updated by a core_initcall() function named rcu_exp_runtime_mode(), which causes the runtime codepaths to be used. Note that this arrangement assumes that tasks are not sent POSIX signals (or anything similar) from the time that the first task is spawned through core_initcall() time. Fixes: 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue") Reported-by: "Zheng, Lv" <lv.zheng@intel.com> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Stan Kain <stan.kain@gmail.com> Tested-by: Ivan <waffolz@hotmail.com> Tested-by: Emanuel Castelo <emanuel.castelo@gmail.com> Tested-by: Bruno Pesavento <bpesavento@infinito.it> Tested-by: Borislav Petkov <bp@suse.de> Tested-by: Frederic Bezies <fredbezies@gmail.com> Cc: <stable@vger.kernel.org> # 4.9.0-
2017-01-10 10:28:26 +00:00
{
/* Initialize the rcu_node tree in preparation for the wait. */
sync_rcu_exp_select_cpus();
rcu: Narrow early boot window of illegal synchronous grace periods The current preemptible RCU implementation goes through three phases during bootup. In the first phase, there is only one CPU that is running with preemption disabled, so that a no-op is a synchronous grace period. In the second mid-boot phase, the scheduler is running, but RCU has not yet gotten its kthreads spawned (and, for expedited grace periods, workqueues are not yet running. During this time, any attempt to do a synchronous grace period will hang the system (or complain bitterly, depending). In the third and final phase, RCU is fully operational and everything works normally. This has been OK for some time, but there has recently been some synchronous grace periods showing up during the second mid-boot phase. This code worked "by accident" for awhile, but started failing as soon as expedited RCU grace periods switched over to workqueues in commit 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue"). Note that the code was buggy even before this commit, as it was subject to failure on real-time systems that forced all expedited grace periods to run as normal grace periods (for example, using the rcu_normal ksysfs parameter). The callchain from the failure case is as follows: early_amd_iommu_init() |-> acpi_put_table(ivrs_base); |-> acpi_tb_put_table(table_desc); |-> acpi_tb_invalidate_table(table_desc); |-> acpi_tb_release_table(...) |-> acpi_os_unmap_memory |-> acpi_os_unmap_iomem |-> acpi_os_map_cleanup |-> synchronize_rcu_expedited The kernel showing this callchain was built with CONFIG_PREEMPT_RCU=y, which caused the code to try using workqueues before they were initialized, which did not go well. This commit therefore reworks RCU to permit synchronous grace periods to proceed during this mid-boot phase. This commit is therefore a fix to a regression introduced in v4.9, and is therefore being put forward post-merge-window in v4.10. This commit sets a flag from the existing rcu_scheduler_starting() function which causes all synchronous grace periods to take the expedited path. The expedited path now checks this flag, using the requesting task to drive the expedited grace period forward during the mid-boot phase. Finally, this flag is updated by a core_initcall() function named rcu_exp_runtime_mode(), which causes the runtime codepaths to be used. Note that this arrangement assumes that tasks are not sent POSIX signals (or anything similar) from the time that the first task is spawned through core_initcall() time. Fixes: 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue") Reported-by: "Zheng, Lv" <lv.zheng@intel.com> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Stan Kain <stan.kain@gmail.com> Tested-by: Ivan <waffolz@hotmail.com> Tested-by: Emanuel Castelo <emanuel.castelo@gmail.com> Tested-by: Bruno Pesavento <bpesavento@infinito.it> Tested-by: Borislav Petkov <bp@suse.de> Tested-by: Frederic Bezies <fredbezies@gmail.com> Cc: <stable@vger.kernel.org> # 4.9.0-
2017-01-10 10:28:26 +00:00
/* Wait and clean up, including waking everyone. */
rcu_exp_wait_wake(s);
rcu: Narrow early boot window of illegal synchronous grace periods The current preemptible RCU implementation goes through three phases during bootup. In the first phase, there is only one CPU that is running with preemption disabled, so that a no-op is a synchronous grace period. In the second mid-boot phase, the scheduler is running, but RCU has not yet gotten its kthreads spawned (and, for expedited grace periods, workqueues are not yet running. During this time, any attempt to do a synchronous grace period will hang the system (or complain bitterly, depending). In the third and final phase, RCU is fully operational and everything works normally. This has been OK for some time, but there has recently been some synchronous grace periods showing up during the second mid-boot phase. This code worked "by accident" for awhile, but started failing as soon as expedited RCU grace periods switched over to workqueues in commit 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue"). Note that the code was buggy even before this commit, as it was subject to failure on real-time systems that forced all expedited grace periods to run as normal grace periods (for example, using the rcu_normal ksysfs parameter). The callchain from the failure case is as follows: early_amd_iommu_init() |-> acpi_put_table(ivrs_base); |-> acpi_tb_put_table(table_desc); |-> acpi_tb_invalidate_table(table_desc); |-> acpi_tb_release_table(...) |-> acpi_os_unmap_memory |-> acpi_os_unmap_iomem |-> acpi_os_map_cleanup |-> synchronize_rcu_expedited The kernel showing this callchain was built with CONFIG_PREEMPT_RCU=y, which caused the code to try using workqueues before they were initialized, which did not go well. This commit therefore reworks RCU to permit synchronous grace periods to proceed during this mid-boot phase. This commit is therefore a fix to a regression introduced in v4.9, and is therefore being put forward post-merge-window in v4.10. This commit sets a flag from the existing rcu_scheduler_starting() function which causes all synchronous grace periods to take the expedited path. The expedited path now checks this flag, using the requesting task to drive the expedited grace period forward during the mid-boot phase. Finally, this flag is updated by a core_initcall() function named rcu_exp_runtime_mode(), which causes the runtime codepaths to be used. Note that this arrangement assumes that tasks are not sent POSIX signals (or anything similar) from the time that the first task is spawned through core_initcall() time. Fixes: 8b355e3bc140 ("rcu: Drive expedited grace periods from workqueue") Reported-by: "Zheng, Lv" <lv.zheng@intel.com> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Stan Kain <stan.kain@gmail.com> Tested-by: Ivan <waffolz@hotmail.com> Tested-by: Emanuel Castelo <emanuel.castelo@gmail.com> Tested-by: Bruno Pesavento <bpesavento@infinito.it> Tested-by: Borislav Petkov <bp@suse.de> Tested-by: Frederic Bezies <fredbezies@gmail.com> Cc: <stable@vger.kernel.org> # 4.9.0-
2017-01-10 10:28:26 +00:00
}
#ifdef CONFIG_PREEMPT_RCU
/*
* Remote handler for smp_call_function_single(). If there is an
* RCU read-side critical section in effect, request that the
* next rcu_read_unlock() record the quiescent state up the
* ->expmask fields in the rcu_node tree. Otherwise, immediately
* report the quiescent state.
*/
static void rcu_exp_handler(void *unused)
{
int depth = rcu_preempt_depth();
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
unsigned long flags;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
struct rcu_node *rnp = rdp->mynode;
struct task_struct *t = current;
/*
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
* First, the common case of not being in an RCU read-side
* critical section. If also enabled or idle, immediately
* report the quiescent state, otherwise defer.
*/
if (!depth) {
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
rcu_is_cpu_rrupt_from_idle()) {
rcu_report_exp_rdp(rdp);
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
} else {
WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
set_tsk_need_resched(t);
set_preempt_need_resched();
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
}
return;
}
/*
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
* Second, the less-common case of being in an RCU read-side
* critical section. In this case we can count on a future
* rcu_read_unlock(). However, this rcu_read_unlock() might
* execute on some other CPU, but in that case there will be
* a future context switch. Either way, if the expedited
* grace period is still waiting on this CPU, set ->deferred_qs
* so that the eventual quiescent state will be reported.
* Note that there is a large group of race conditions that
* can have caused this quiescent state to already have been
* reported, so we really do need to check ->expmask.
*/
if (depth > 0) {
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rcu: Speed up expedited GPs when interrupting RCU reader In PREEMPT kernels, an expedited grace period might send an IPI to a CPU that is executing an RCU read-side critical section. In that case, it would be nice if the rcu_read_unlock() directly interacted with the RCU core code to immediately report the quiescent state. And this does happen in the case where the reader has been preempted. But it would also be a nice performance optimization if immediate reporting also happened in the preemption-free case. This commit therefore adds an ->exp_hint field to the task_struct structure's ->rcu_read_unlock_special field. The IPI handler sets this hint when it has interrupted an RCU read-side critical section, and this causes the outermost rcu_read_unlock() call to invoke rcu_read_unlock_special(), which, if preemption is enabled, reports the quiescent state immediately. If preemption is disabled, then the report is required to be deferred until preemption (or bottom halves or interrupts or whatever) is re-enabled. Because this is a hint, it does nothing for more complicated cases. For example, if the IPI interrupts an RCU reader, but interrupts are disabled across the rcu_read_unlock(), but another rcu_read_lock() is executed before interrupts are re-enabled, the hint will already have been cleared. If you do crazy things like this, reporting will be deferred until some later RCU_SOFTIRQ handler, context switch, cond_resched(), or similar. Reported-by: Joel Fernandes <joel@joelfernandes.org> Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> Acked-by: Joel Fernandes (Google) <joel@joelfernandes.org>
2018-10-16 11:12:58 +00:00
if (rnp->expmask & rdp->grpmask) {
WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
t->rcu_read_unlock_special.b.exp_hint = true;
rcu: Speed up expedited GPs when interrupting RCU reader In PREEMPT kernels, an expedited grace period might send an IPI to a CPU that is executing an RCU read-side critical section. In that case, it would be nice if the rcu_read_unlock() directly interacted with the RCU core code to immediately report the quiescent state. And this does happen in the case where the reader has been preempted. But it would also be a nice performance optimization if immediate reporting also happened in the preemption-free case. This commit therefore adds an ->exp_hint field to the task_struct structure's ->rcu_read_unlock_special field. The IPI handler sets this hint when it has interrupted an RCU read-side critical section, and this causes the outermost rcu_read_unlock() call to invoke rcu_read_unlock_special(), which, if preemption is enabled, reports the quiescent state immediately. If preemption is disabled, then the report is required to be deferred until preemption (or bottom halves or interrupts or whatever) is re-enabled. Because this is a hint, it does nothing for more complicated cases. For example, if the IPI interrupts an RCU reader, but interrupts are disabled across the rcu_read_unlock(), but another rcu_read_lock() is executed before interrupts are re-enabled, the hint will already have been cleared. If you do crazy things like this, reporting will be deferred until some later RCU_SOFTIRQ handler, context switch, cond_resched(), or similar. Reported-by: Joel Fernandes <joel@joelfernandes.org> Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> Acked-by: Joel Fernandes (Google) <joel@joelfernandes.org>
2018-10-16 11:12:58 +00:00
}
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ]
2018-06-21 19:50:01 +00:00
}
// Finally, negative nesting depth should not happen.
WARN_ON_ONCE(1);
}
/* PREEMPTION=y, so no PREEMPTION=n expedited grace period to clean up after. */
static void sync_sched_exp_online_cleanup(int cpu)
{
}
/*
* Scan the current list of tasks blocked within RCU read-side critical
* sections, printing out the tid of each that is blocking the current
* expedited grace period.
*/
static int rcu_print_task_exp_stall(struct rcu_node *rnp)
{
unsigned long flags;
int ndetected = 0;
struct task_struct *t;
if (!READ_ONCE(rnp->exp_tasks))
return 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
t = list_entry(rnp->exp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
ndetected++;
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return ndetected;
}
#else /* #ifdef CONFIG_PREEMPT_RCU */
/* Request an expedited quiescent state. */
static void rcu_exp_need_qs(void)
{
__this_cpu_write(rcu_data.cpu_no_qs.b.exp, true);
/* Store .exp before .rcu_urgent_qs. */
smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true);
set_tsk_need_resched(current);
set_preempt_need_resched();
}
/* Invoked on each online non-idle CPU for expedited quiescent state. */
static void rcu_exp_handler(void *unused)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
2022-07-05 19:09:51 +00:00
bool preempt_bh_enabled = !(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK));
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
__this_cpu_read(rcu_data.cpu_no_qs.b.exp))
return;
2022-07-05 19:09:51 +00:00
if (rcu_is_cpu_rrupt_from_idle() ||
(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preempt_bh_enabled)) {
rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
return;
}
rcu_exp_need_qs();
}
/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */
static void sync_sched_exp_online_cleanup(int cpu)
{
unsigned long flags;
int my_cpu;
struct rcu_data *rdp;
int ret;
struct rcu_node *rnp;
rdp = per_cpu_ptr(&rcu_data, cpu);
rnp = rdp->mynode;
my_cpu = get_cpu();
/* Quiescent state either not needed or already requested, leave. */
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
READ_ONCE(rdp->cpu_no_qs.b.exp)) {
put_cpu();
return;
}
/* Quiescent state needed on current CPU, so set it up locally. */
if (my_cpu == cpu) {
local_irq_save(flags);
rcu_exp_need_qs();
local_irq_restore(flags);
put_cpu();
return;
}
/* Quiescent state needed on some other CPU, send IPI. */
ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
put_cpu();
WARN_ON_ONCE(ret);
}
/*
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections that are
* blocking the current expedited grace period.
*/
static int rcu_print_task_exp_stall(struct rcu_node *rnp)
{
return 0;
}
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
/**
* synchronize_rcu_expedited - Brute-force RCU grace period
*
* Wait for an RCU grace period, but expedite it. The basic idea is to
* IPI all non-idle non-nohz online CPUs. The IPI handler checks whether
* the CPU is in an RCU critical section, and if so, it sets a flag that
* causes the outermost rcu_read_unlock() to report the quiescent state
* for RCU-preempt or asks the scheduler for help for RCU-sched. On the
* other hand, if the CPU is not in an RCU read-side critical section,
* the IPI handler reports the quiescent state immediately.
*
* Although this is a great improvement over previous expedited
* implementations, it is still unfriendly to real-time workloads, so is
* thus not recommended for any sort of common-case code. In fact, if
* you are using synchronize_rcu_expedited() in a loop, please restructure
* your code to batch your updates, and then use a single synchronize_rcu()
* instead.
*
* This has the same semantics as (but is more brutal than) synchronize_rcu().
*/
void synchronize_rcu_expedited(void)
{
bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT);
unsigned long flags;
struct rcu_exp_work rew;
struct rcu_node *rnp;
unsigned long s;
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu_expedited() in RCU read-side critical section");
/* Is the state is such that the call is a grace period? */
rcu: Make polled grace-period API account for expedited grace periods Currently, this code could splat: oldstate = get_state_synchronize_rcu(); synchronize_rcu_expedited(); WARN_ON_ONCE(!poll_state_synchronize_rcu(oldstate)); This situation is counter-intuitive and user-unfriendly. After all, there really was a perfectly valid full grace period right after the call to get_state_synchronize_rcu(), so why shouldn't poll_state_synchronize_rcu() know about it? This commit therefore makes the polled grace-period API aware of expedited grace periods in addition to the normal grace periods that it is already aware of. With this change, the above code is guaranteed not to splat. Please note that the above code can still splat due to counter wrap on the one hand and situations involving partially overlapping normal/expedited grace periods on the other. On 64-bit systems, the second is of course much more likely than the first. It is possible to modify this approach to prevent overlapping grace periods from causing splats, but only at the expense of greatly increasing the probability of counter wrap, as in within milliseconds on 32-bit systems and within minutes on 64-bit systems. This commit is in preparation for polled expedited grace periods. Link: https://lore.kernel.org/all/20220121142454.1994916-1-bfoster@redhat.com/ Link: https://docs.google.com/document/d/1RNKWW9jQyfjxw2E8dsXVTdvZYh0HnYeSHDKog9jhdN8/edit?usp=sharing Cc: Brian Foster <bfoster@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ian Kent <raven@themaw.net> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-14 13:56:35 +00:00
if (rcu_blocking_is_gp()) {
// Note well that this code runs with !PREEMPT && !SMP.
// In addition, all code that advances grace periods runs
// at process level. Therefore, this expedited GP overlaps
// with other expedited GPs only by being fully nested within
// them, which allows reuse of ->gp_seq_polled_exp_snap.
rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_exp_snap);
rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_exp_snap);
local_irq_save(flags);
WARN_ON_ONCE(num_online_cpus() > 1);
rcu_state.expedited_sequence += (1 << RCU_SEQ_CTR_SHIFT);
local_irq_restore(flags);
rcu: Make polled grace-period API account for expedited grace periods Currently, this code could splat: oldstate = get_state_synchronize_rcu(); synchronize_rcu_expedited(); WARN_ON_ONCE(!poll_state_synchronize_rcu(oldstate)); This situation is counter-intuitive and user-unfriendly. After all, there really was a perfectly valid full grace period right after the call to get_state_synchronize_rcu(), so why shouldn't poll_state_synchronize_rcu() know about it? This commit therefore makes the polled grace-period API aware of expedited grace periods in addition to the normal grace periods that it is already aware of. With this change, the above code is guaranteed not to splat. Please note that the above code can still splat due to counter wrap on the one hand and situations involving partially overlapping normal/expedited grace periods on the other. On 64-bit systems, the second is of course much more likely than the first. It is possible to modify this approach to prevent overlapping grace periods from causing splats, but only at the expense of greatly increasing the probability of counter wrap, as in within milliseconds on 32-bit systems and within minutes on 64-bit systems. This commit is in preparation for polled expedited grace periods. Link: https://lore.kernel.org/all/20220121142454.1994916-1-bfoster@redhat.com/ Link: https://docs.google.com/document/d/1RNKWW9jQyfjxw2E8dsXVTdvZYh0HnYeSHDKog9jhdN8/edit?usp=sharing Cc: Brian Foster <bfoster@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ian Kent <raven@themaw.net> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-14 13:56:35 +00:00
return; // Context allows vacuous grace periods.
}
/* If expedited grace periods are prohibited, fall back to normal. */
if (rcu_gp_is_normal()) {
wait_rcu_gp(call_rcu_hurry);
return;
}
/* Take a snapshot of the sequence number. */
s = rcu_exp_gp_seq_snap();
if (exp_funnel_lock(s))
return; /* Someone else did our work for us. */
/* Ensure that load happens before action based on it. */
if (unlikely(boottime)) {
/* Direct call during scheduler init and early_initcalls(). */
rcu_exp_sel_wait_wake(s);
} else {
/* Marshall arguments & schedule the expedited grace period. */
rew.rew_s = s;
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
synchronize_rcu_expedited_queue_work(&rew);
}
/* Wait for expedited grace period to complete. */
rnp = rcu_get_root();
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(s));
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
smp_mb(); /* Work actions happen before return. */
/* Let the next expedited grace period start. */
mutex_unlock(&rcu_state.exp_mutex);
if (likely(!boottime))
rcu: Move expedited grace period (GP) work to RT kthread_worker Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period latency because its workqueues run at SCHED_OTHER, and thus can be delayed by normal processes. This commit avoids these delays by moving the expedited GP work items to a real-time-priority kthread_worker. This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by default on PREEMPT_RT=y kernels which disable expedited grace periods after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1. The results were evaluated on arm64 Android devices (6GB ram) running 5.10 kernel, and capturing trace data in critical user-level code. The table below shows the resulting order-of-magnitude improvements in synchronize_rcu_expedited() latency: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Count | 725 | 688 | | ------------------------------------------------------------------------ | Min Duration (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Q1 (ns) | 39,428 | 38,971 | -1.16% | ------------------------------------------------------------------------ | Q2 - Median (ns) | 98,225 | 69,743 | -29.00% | ------------------------------------------------------------------------ | Q3 (ns) | 342,122 | 126,638 | -62.98% | ------------------------------------------------------------------------ | Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% | ------------------------------------------------------------------------ | Standard Deviation (ns) | 19,327,765 | 294,408 | | ------------------------------------------------------------------------ The below table show the range of maximums/minimums for synchronize_rcu_expedited() latency from all experiments: ------------------------------------------------------------------------ | | workqueues | kthread_worker | Diff | ------------------------------------------------------------------------ | Total No. of Experiments | 25 | 23 | | ------------------------------------------------------------------------ | Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% | ------------------------------------------------------------------------ | Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% | ------------------------------------------------------------------------ | Range of Maximums (ns) | 372,728,148 | 2,242,717 | | ------------------------------------------------------------------------ | Largest Minimum (ns) | 88,623 | 27,588 | -68.87% | ------------------------------------------------------------------------ | Smallest Minimum (ns) | 326 | 447 | 37.12% | ------------------------------------------------------------------------ | Range of Minimums (ns) | 88,297 | 27,141 | | ------------------------------------------------------------------------ Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Tejun Heo <tj@kernel.org> Reported-by: Tim Murray <timmurray@google.com> Reported-by: Wei Wang <wvw@google.com> Tested-by: Kyle Lin <kylelin@google.com> Tested-by: Chunwei Lu <chunweilu@google.com> Tested-by: Lulu Wang <luluw@google.com> Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2022-04-09 00:35:27 +00:00
synchronize_rcu_expedited_destroy_work(&rew);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
/*
* Ensure that start_poll_synchronize_rcu_expedited() has the expedited
* RCU grace periods that it needs.
*/
static void sync_rcu_do_polled_gp(struct work_struct *wp)
{
unsigned long flags;
int i = 0;
struct rcu_node *rnp = container_of(wp, struct rcu_node, exp_poll_wq);
unsigned long s;
raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
s = rnp->exp_seq_poll_rq;
rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
if (s == RCU_GET_STATE_COMPLETED)
return;
while (!poll_state_synchronize_rcu(s)) {
synchronize_rcu_expedited();
if (i == 10 || i == 20)
pr_info("%s: i = %d s = %lx gp_seq_polled = %lx\n", __func__, i, s, READ_ONCE(rcu_state.gp_seq_polled));
i++;
}
raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
s = rnp->exp_seq_poll_rq;
if (poll_state_synchronize_rcu(s))
rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
}
/**
* start_poll_synchronize_rcu_expedited - Snapshot current RCU state and start expedited grace period
*
* Returns a cookie to pass to a call to cond_synchronize_rcu(),
* cond_synchronize_rcu_expedited(), or poll_state_synchronize_rcu(),
* allowing them to determine whether or not any sort of grace period has
* elapsed in the meantime. If the needed expedited grace period is not
* already slated to start, initiates that grace period.
*/
unsigned long start_poll_synchronize_rcu_expedited(void)
{
unsigned long flags;
struct rcu_data *rdp;
struct rcu_node *rnp;
unsigned long s;
s = get_state_synchronize_rcu();
rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
rnp = rdp->mynode;
if (rcu_init_invoked())
raw_spin_lock_irqsave(&rnp->exp_poll_lock, flags);
if (!poll_state_synchronize_rcu(s)) {
rnp->exp_seq_poll_rq = s;
if (rcu_init_invoked())
queue_work(rcu_gp_wq, &rnp->exp_poll_wq);
}
if (rcu_init_invoked())
raw_spin_unlock_irqrestore(&rnp->exp_poll_lock, flags);
return s;
}
EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_expedited);
/**
* start_poll_synchronize_rcu_expedited_full - Take a full snapshot and start expedited grace period
* @rgosp: Place to put snapshot of grace-period state
*
* Places the normal and expedited grace-period states in rgosp. This
* state value can be passed to a later call to cond_synchronize_rcu_full()
* or poll_state_synchronize_rcu_full() to determine whether or not a
* grace period (whether normal or expedited) has elapsed in the meantime.
* If the needed expedited grace period is not already slated to start,
* initiates that grace period.
*/
void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
{
get_state_synchronize_rcu_full(rgosp);
(void)start_poll_synchronize_rcu_expedited();
}
EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_expedited_full);
/**
* cond_synchronize_rcu_expedited - Conditionally wait for an expedited RCU grace period
*
* @oldstate: value from get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or start_poll_synchronize_rcu_expedited()
*
* If any type of full RCU grace period has elapsed since the earlier
* call to get_state_synchronize_rcu(), start_poll_synchronize_rcu(),
* or start_poll_synchronize_rcu_expedited(), just return. Otherwise,
* invoke synchronize_rcu_expedited() to wait for a full grace period.
*
* Yes, this function does not take counter wrap into account.
* But counter wrap is harmless. If the counter wraps, we have waited for
* more than 2 billion grace periods (and way more on a 64-bit system!),
* so waiting for a couple of additional grace periods should be just fine.
*
* This function provides the same memory-ordering guarantees that
* would be provided by a synchronize_rcu() that was invoked at the call
* to the function that provided @oldstate and that returned at the end
* of this function.
*/
void cond_synchronize_rcu_expedited(unsigned long oldstate)
{
if (!poll_state_synchronize_rcu(oldstate))
synchronize_rcu_expedited();
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu_expedited);
/**
* cond_synchronize_rcu_expedited_full - Conditionally wait for an expedited RCU grace period
* @rgosp: value from get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(), or start_poll_synchronize_rcu_expedited_full()
*
* If a full RCU grace period has elapsed since the call to
* get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(),
* or start_poll_synchronize_rcu_expedited_full() from which @rgosp was
* obtained, just return. Otherwise, invoke synchronize_rcu_expedited()
* to wait for a full grace period.
*
* Yes, this function does not take counter wrap into account.
* But counter wrap is harmless. If the counter wraps, we have waited for
* more than 2 billion grace periods (and way more on a 64-bit system!),
* so waiting for a couple of additional grace periods should be just fine.
*
* This function provides the same memory-ordering guarantees that
* would be provided by a synchronize_rcu() that was invoked at the call
* to the function that provided @rgosp and that returned at the end of
* this function.
*/
void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
{
if (!poll_state_synchronize_rcu_full(rgosp))
synchronize_rcu_expedited();
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu_expedited_full);