* per-CPU. Object size is equal to one page. This value
* can be changed at boot time.
*/
-static int rcu_min_cached_objs = 2;
+static int rcu_min_cached_objs = 5;
module_param(rcu_min_cached_objs, int, 0444);
/* Retrieve RCU kthreads priority for rcutorture */
return !(snap & RCU_DYNTICK_CTRL_CTR);
}
+/* Return true if the specified CPU is currently idle from an RCU viewpoint. */
+bool rcu_is_idle_cpu(int cpu)
+{
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+ return rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
+}
+
/*
* Return true if the CPU corresponding to the specified rcu_data
* structure has spent some time in an extended quiescent state since
preempt_disable_notrace();
rdp = this_cpu_ptr(&rcu_data);
rnp = rdp->mynode;
- if (rdp->grpmask & rcu_rnp_online_cpus(rnp))
+ if (rdp->grpmask & rcu_rnp_online_cpus(rnp) || READ_ONCE(rnp->ofl_seq) & 0x1)
ret = true;
preempt_enable_notrace();
return ret;
*/
static bool rcu_gp_init(void)
{
+ unsigned long firstseq;
unsigned long flags;
unsigned long oldmask;
unsigned long mask;
*/
rcu_state.gp_state = RCU_GP_ONOFF;
rcu_for_each_leaf_node(rnp) {
+ smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values.
+ firstseq = READ_ONCE(rnp->ofl_seq);
+ if (firstseq & 0x1)
+ while (firstseq == READ_ONCE(rnp->ofl_seq))
+ schedule_timeout_idle(1); // Can't wake unless RCU is watching.
+ smp_mb(); // Pair with barriers used when updating ->ofl_seq to even values.
raw_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irq_rcu_node(rnp);
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
* In order to save some per-cpu space the list is singular.
* Even though it is lockless an access has to be protected by the
* per-cpu lock.
+ * @page_cache_work: A work to refill the cache when it is empty
+ * @work_in_progress: Indicates that page_cache_work is running
+ * @hrtimer: A hrtimer for scheduling a page_cache_work
* @nr_bkv_objs: number of allocated objects at @bkvcache.
*
* This is a per-CPU structure. The reason that it is not included in
bool monitor_todo;
bool initialized;
int count;
+
+ struct work_struct page_cache_work;
+ atomic_t work_in_progress;
+ struct hrtimer hrtimer;
+
struct llist_head bkvcache;
int nr_bkv_objs;
};
}
rcu_lock_release(&rcu_callback_map);
- krcp = krc_this_cpu_lock(&flags);
+ raw_spin_lock_irqsave(&krcp->lock, flags);
if (put_cached_bnode(krcp, bkvhead[i]))
bkvhead[i] = NULL;
- krc_this_cpu_unlock(krcp, flags);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
if (bkvhead[i])
free_page((unsigned long) bkvhead[i]);
raw_spin_unlock_irqrestore(&krcp->lock, flags);
}
+static enum hrtimer_restart
+schedule_page_work_fn(struct hrtimer *t)
+{
+ struct kfree_rcu_cpu *krcp =
+ container_of(t, struct kfree_rcu_cpu, hrtimer);
+
+ queue_work(system_highpri_wq, &krcp->page_cache_work);
+ return HRTIMER_NORESTART;
+}
+
+static void fill_page_cache_func(struct work_struct *work)
+{
+ struct kvfree_rcu_bulk_data *bnode;
+ struct kfree_rcu_cpu *krcp =
+ container_of(work, struct kfree_rcu_cpu,
+ page_cache_work);
+ unsigned long flags;
+ bool pushed;
+ int i;
+
+ for (i = 0; i < rcu_min_cached_objs; i++) {
+ bnode = (struct kvfree_rcu_bulk_data *)
+ __get_free_page(GFP_KERNEL | __GFP_NOWARN);
+
+ if (bnode) {
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ pushed = put_cached_bnode(krcp, bnode);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ if (!pushed) {
+ free_page((unsigned long) bnode);
+ break;
+ }
+ }
+ }
+
+ atomic_set(&krcp->work_in_progress, 0);
+}
+
+static void
+run_page_cache_worker(struct kfree_rcu_cpu *krcp)
+{
+ if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
+ !atomic_xchg(&krcp->work_in_progress, 1)) {
+ hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL);
+ krcp->hrtimer.function = schedule_page_work_fn;
+ hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
+ }
+}
+
static inline bool
kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
{
if (!krcp->bkvhead[idx] ||
krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
bnode = get_cached_bnode(krcp);
- if (!bnode) {
- /*
- * To keep this path working on raw non-preemptible
- * sections, prevent the optional entry into the
- * allocator as it uses sleeping locks. In fact, even
- * if the caller of kfree_rcu() is preemptible, this
- * path still is not, as krcp->lock is a raw spinlock.
- * With additional page pre-allocation in the works,
- * hitting this return is going to be much less likely.
- */
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- return false;
-
- /*
- * NOTE: For one argument of kvfree_rcu() we can
- * drop the lock and get the page in sleepable
- * context. That would allow to maintain an array
- * for the CONFIG_PREEMPT_RT as well if no cached
- * pages are available.
- */
- bnode = (struct kvfree_rcu_bulk_data *)
- __get_free_page(GFP_NOWAIT | __GFP_NOWARN);
- }
-
/* Switch to emergency path. */
- if (unlikely(!bnode))
+ if (!bnode)
return false;
/* Initialize the new block. */
goto unlock_return;
}
- /*
- * Under high memory pressure GFP_NOWAIT can fail,
- * in that case the emergency path is maintained.
- */
success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
if (!success) {
+ run_page_cache_worker(krcp);
+
if (head == NULL)
// Inline if kvfree_rcu(one_arg) call.
goto unlock_return;
* During early boot, any blocking grace-period wait automatically
* implies a grace period. Later on, this is never the case for PREEMPTION.
*
- * Howevr, because a context switch is a grace period for !PREEMPTION, any
+ * However, because a context switch is a grace period for !PREEMPTION, any
* blocking grace-period wait automatically implies a grace period if
* there is only one CPU online at any point time during execution of
* either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to
rnp = rdp->mynode;
mask = rdp->grpmask;
+ WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+ WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+ smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
raw_spin_lock_irqsave_rcu_node(rnp, flags);
WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
newcpu = !(rnp->expmaskinitnext & mask);
} else {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
+ smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
+ WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+ WARN_ON_ONCE(rnp->ofl_seq & 0x1);
smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
}
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
+ WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+ WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+ smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
raw_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
raw_spin_unlock(&rcu_state.ofl_lock);
+ smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
+ WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+ WARN_ON_ONCE(rnp->ofl_seq & 0x1);
rdp->cpu_started = false;
}
for_each_possible_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
- struct kvfree_rcu_bulk_data *bnode;
for (i = 0; i < KFREE_N_BATCHES; i++) {
INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
krcp->krw_arr[i].krcp = krcp;
}
- for (i = 0; i < rcu_min_cached_objs; i++) {
- bnode = (struct kvfree_rcu_bulk_data *)
- __get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-
- if (bnode)
- put_cached_bnode(krcp, bnode);
- else
- pr_err("Failed to preallocate for %d CPU!\n", cpu);
- }
-
INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
+ INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
krcp->initialized = true;
}
if (register_shrinker(&kfree_rcu_shrinker))