1 files changed, 127 insertions, 90 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4b00e4fbfa10..28f1093027b9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -186,6 +186,17 @@ module_param(rcu_unlock_delay, int, 0444);
 static int rcu_min_cached_objs = 5;
 module_param(rcu_min_cached_objs, int, 0444);
 
+// A page shrinker can ask for pages to be freed to make them
+// available for other parts of the system. This usually happens
+// under low memory conditions, and in that case we should also
+// defer page-cache filling for a short time period.
+//
+// The default value is 5 seconds, which is long enough to reduce
+// interference with the shrinker while it asks other systems to
+// drain their caches.
+static int rcu_delay_page_cache_fill_msec = 5000;
+module_param(rcu_delay_page_cache_fill_msec, int, 0444);
+
 /* Retrieve RCU kthreads priority for rcutorture */
 int rcu_get_gp_kthreads_prio(void)
 {
@@ -242,6 +253,7 @@ void rcu_softirq_qs(void)
 {
 	rcu_qs();
 	rcu_preempt_deferred_qs(current);
+	rcu_tasks_qs(current, false);
 }
 
 /*
@@ -2467,7 +2479,7 @@ int rcutree_dead_cpu(unsigned int cpu)
 
 /*
  * Invoke any RCU callbacks that have made it to the end of their grace
- * period.  Thottle as specified by rdp->blimit.
+ * period.  Throttle as specified by rdp->blimit.
  */
 static void rcu_do_batch(struct rcu_data *rdp)
 {
@@ -3153,6 +3165,7 @@ struct kfree_rcu_cpu_work {
  *	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
+ * @backoff_page_cache_fill: Delay cache refills
  * @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.
@@ -3172,7 +3185,8 @@ struct kfree_rcu_cpu {
 	bool initialized;
 	int count;
 
-	struct work_struct page_cache_work;
+	struct delayed_work page_cache_work;
+	atomic_t backoff_page_cache_fill;
 	atomic_t work_in_progress;
 	struct hrtimer hrtimer;
 
@@ -3219,7 +3233,7 @@ get_cached_bnode(struct kfree_rcu_cpu *krcp)
 	if (!krcp->nr_bkv_objs)
 		return NULL;
 
-	krcp->nr_bkv_objs--;
+	WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs - 1);
 	return (struct kvfree_rcu_bulk_data *)
 		llist_del_first(&krcp->bkvcache);
 }
@@ -3233,9 +3247,28 @@ put_cached_bnode(struct kfree_rcu_cpu *krcp,
 		return false;
 
 	llist_add((struct llist_node *) bnode, &krcp->bkvcache);
-	krcp->nr_bkv_objs++;
+	WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs + 1);
 	return true;
+}
+
+static int
+drain_page_cache(struct kfree_rcu_cpu *krcp)
+{
+	unsigned long flags;
+	struct llist_node *page_list, *pos, *n;
+	int freed = 0;
+
+	raw_spin_lock_irqsave(&krcp->lock, flags);
+	page_list = llist_del_all(&krcp->bkvcache);
+	WRITE_ONCE(krcp->nr_bkv_objs, 0);
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 
+	llist_for_each_safe(pos, n, page_list) {
+		free_page((unsigned long)pos);
+		freed++;
+	}
+
+	return freed;
 }
 
 /*
@@ -3305,9 +3338,11 @@ static void kfree_rcu_work(struct work_struct *work)
 	}
 
 	/*
-	 * Emergency case only. It can happen under low memory
-	 * condition when an allocation gets failed, so the "bulk"
-	 * path can not be temporary maintained.
+	 * This is used when the "bulk" path can not be used for the
+	 * double-argument of kvfree_rcu().  This happens when the
+	 * page-cache is empty, which means that objects are instead
+	 * queued on a linked list through their rcu_head structures.
+	 * This list is named "Channel 3".
 	 */
 	for (; head; head = next) {
 		unsigned long offset = (unsigned long)head->func;
@@ -3327,34 +3362,31 @@ static void kfree_rcu_work(struct work_struct *work)
 }
 
 /*
- * Schedule the kfree batch RCU work to run in workqueue context after a GP.
- *
- * This function is invoked by kfree_rcu_monitor() when the KFREE_DRAIN_JIFFIES
- * timeout has been reached.
+ * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
  */
-static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
+static void kfree_rcu_monitor(struct work_struct *work)
 {
-	struct kfree_rcu_cpu_work *krwp;
-	bool repeat = false;
+	struct kfree_rcu_cpu *krcp = container_of(work,
+		struct kfree_rcu_cpu, monitor_work.work);
+	unsigned long flags;
 	int i, j;
 
-	lockdep_assert_held(&krcp->lock);
+	raw_spin_lock_irqsave(&krcp->lock, flags);
 
+	// Attempt to start a new batch.
 	for (i = 0; i < KFREE_N_BATCHES; i++) {
-		krwp = &(krcp->krw_arr[i]);
+		struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]);
 
-		/*
-		 * Try to detach bkvhead or head and attach it over any
-		 * available corresponding free channel. It can be that
-		 * a previous RCU batch is in progress, it means that
-		 * immediately to queue another one is not possible so
-		 * return false to tell caller to retry.
-		 */
+		// Try to detach bkvhead or head and attach it over any
+		// available corresponding free channel. It can be that
+		// a previous RCU batch is in progress, it means that
+		// immediately to queue another one is not possible so
+		// in that case the monitor work is rearmed.
 		if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) ||
 			(krcp->bkvhead[1] && !krwp->bkvhead_free[1]) ||
 				(krcp->head && !krwp->head_free)) {
-			// Channel 1 corresponds to SLAB ptrs.
-			// Channel 2 corresponds to vmalloc ptrs.
+			// Channel 1 corresponds to the SLAB-pointer bulk path.
+			// Channel 2 corresponds to vmalloc-pointer bulk path.
 			for (j = 0; j < FREE_N_CHANNELS; j++) {
 				if (!krwp->bkvhead_free[j]) {
 					krwp->bkvhead_free[j] = krcp->bkvhead[j];
@@ -3362,7 +3394,8 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 				}
 			}
 
-			// Channel 3 corresponds to emergency path.
+			// Channel 3 corresponds to both SLAB and vmalloc
+			// objects queued on the linked list.
 			if (!krwp->head_free) {
 				krwp->head_free = krcp->head;
 				krcp->head = NULL;
@@ -3370,65 +3403,35 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 
 			WRITE_ONCE(krcp->count, 0);
 
-			/*
-			 * One work is per one batch, so there are three
-			 * "free channels", the batch can handle. It can
-			 * be that the work is in the pending state when
-			 * channels have been detached following by each
-			 * other.
-			 */
+			// One work is per one batch, so there are three
+			// "free channels", the batch can handle. It can
+			// be that the work is in the pending state when
+			// channels have been detached following by each
+			// other.
 			queue_rcu_work(system_wq, &krwp->rcu_work);
 		}
-
-		// Repeat if any "free" corresponding channel is still busy.
-		if (krcp->bkvhead[0] || krcp->bkvhead[1] || krcp->head)
-			repeat = true;
 	}
 
-	return !repeat;
-}
-
-static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
-					  unsigned long flags)
-{
-	// Attempt to start a new batch.
-	krcp->monitor_todo = false;
-	if (queue_kfree_rcu_work(krcp)) {
-		// Success! Our job is done here.
-		raw_spin_unlock_irqrestore(&krcp->lock, flags);
-		return;
-	}
+	// If there is nothing to detach, it means that our job is
+	// successfully done here. In case of having at least one
+	// of the channels that is still busy we should rearm the
+	// work to repeat an attempt. Because previous batches are
+	// still in progress.
+	if (!krcp->bkvhead[0] && !krcp->bkvhead[1] && !krcp->head)
+		krcp->monitor_todo = false;
+	else
+		schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
 
-	// Previous RCU batch still in progress, try again later.
-	krcp->monitor_todo = true;
-	schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
 	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
-/*
- * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
- * It invokes kfree_rcu_drain_unlock() to attempt to start another batch.
- */
-static void kfree_rcu_monitor(struct work_struct *work)
-{
-	unsigned long flags;
-	struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu,
-						 monitor_work.work);
-
-	raw_spin_lock_irqsave(&krcp->lock, flags);
-	if (krcp->monitor_todo)
-		kfree_rcu_drain_unlock(krcp, flags);
-	else
-		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);
+	queue_delayed_work(system_highpri_wq, &krcp->page_cache_work, 0);
 	return HRTIMER_NORESTART;
 }
 
@@ -3437,12 +3440,16 @@ 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);
+			page_cache_work.work);
 	unsigned long flags;
+	int nr_pages;
 	bool pushed;
 	int i;
 
-	for (i = 0; i < rcu_min_cached_objs; i++) {
+	nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
+		1 : rcu_min_cached_objs;
+
+	for (i = 0; i < nr_pages; i++) {
 		bnode = (struct kvfree_rcu_bulk_data *)
 			__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
@@ -3459,6 +3466,7 @@ static void fill_page_cache_func(struct work_struct *work)
 	}
 
 	atomic_set(&krcp->work_in_progress, 0);
+	atomic_set(&krcp->backoff_page_cache_fill, 0);
 }
 
 static void
@@ -3466,10 +3474,15 @@ 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);
+		if (atomic_read(&krcp->backoff_page_cache_fill)) {
+			queue_delayed_work(system_wq,
+				&krcp->page_cache_work,
+					msecs_to_jiffies(rcu_delay_page_cache_fill_msec));
+		} else {
+			hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+			krcp->hrtimer.function = schedule_page_work_fn;
+			hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
+		}
 	}
 }
 
@@ -3627,6 +3640,8 @@ kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
 		count += READ_ONCE(krcp->count);
+		count += READ_ONCE(krcp->nr_bkv_objs);
+		atomic_set(&krcp->backoff_page_cache_fill, 1);
 	}
 
 	return count;
@@ -3636,18 +3651,14 @@ static unsigned long
 kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
 	int cpu, freed = 0;
-	unsigned long flags;
 
 	for_each_possible_cpu(cpu) {
 		int count;
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
 		count = krcp->count;
-		raw_spin_lock_irqsave(&krcp->lock, flags);
-		if (krcp->monitor_todo)
-			kfree_rcu_drain_unlock(krcp, flags);
-		else
-			raw_spin_unlock_irqrestore(&krcp->lock, flags);
+		count += drain_page_cache(krcp);
+		kfree_rcu_monitor(&krcp->monitor_work.work);
 
 		sc->nr_to_scan -= count;
 		freed += count;
@@ -3675,7 +3686,8 @@ void __init kfree_rcu_scheduler_running(void)
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
 		raw_spin_lock_irqsave(&krcp->lock, flags);
-		if (!krcp->head || krcp->monitor_todo) {
+		if ((!krcp->bkvhead[0] && !krcp->bkvhead[1] && !krcp->head) ||
+				krcp->monitor_todo) {
 			raw_spin_unlock_irqrestore(&krcp->lock, flags);
 			continue;
 		}
@@ -3835,7 +3847,7 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
  *
  * If a full RCU grace period has elapsed since the earlier call from
  * which oldstate was obtained, return @true, otherwise return @false.
- * If @false is returned, it is the caller's responsibilty to invoke this
+ * If @false is returned, it is the caller's responsibility to invoke this
  * function later on until it does return @true.  Alternatively, the caller
  * can explicitly wait for a grace period, for example, by passing @oldstate
  * to cond_synchronize_rcu() or by directly invoking synchronize_rcu().
@@ -3908,7 +3920,7 @@ static int rcu_pending(int user)
 	check_cpu_stall(rdp);
 
 	/* Does this CPU need a deferred NOCB wakeup? */
-	if (rcu_nocb_need_deferred_wakeup(rdp))
+	if (rcu_nocb_need_deferred_wakeup(rdp, RCU_NOCB_WAKE))
 		return 1;
 
 	/* Is this a nohz_full CPU in userspace or idle?  (Ignore RCU if so.) */
@@ -4091,7 +4103,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier);
 /*
  * Propagate ->qsinitmask bits up the rcu_node tree to account for the
  * first CPU in a given leaf rcu_node structure coming online.  The caller
- * must hold the corresponding leaf rcu_node ->lock with interrrupts
+ * must hold the corresponding leaf rcu_node ->lock with interrupts
  * disabled.
  */
 static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
@@ -4580,11 +4592,25 @@ static void __init rcu_init_one(void)
  * replace the definitions in tree.h because those are needed to size
  * the ->node array in the rcu_state structure.
  */
-static void __init rcu_init_geometry(void)
+void rcu_init_geometry(void)
 {
 	ulong d;
 	int i;
+	static unsigned long old_nr_cpu_ids;
 	int rcu_capacity[RCU_NUM_LVLS];
+	static bool initialized;
+
+	if (initialized) {
+		/*
+		 * Warn if setup_nr_cpu_ids() had not yet been invoked,
+		 * unless nr_cpus_ids == NR_CPUS, in which case who cares?
+		 */
+		WARN_ON_ONCE(old_nr_cpu_ids != nr_cpu_ids);
+		return;
+	}
+
+	old_nr_cpu_ids = nr_cpu_ids;
+	initialized = true;
 
 	/*
 	 * Initialize any unspecified boot parameters.
@@ -4685,6 +4711,18 @@ static void __init kfree_rcu_batch_init(void)
 	int cpu;
 	int i;
 
+	/* Clamp it to [0:100] seconds interval. */
+	if (rcu_delay_page_cache_fill_msec < 0 ||
+		rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) {
+
+		rcu_delay_page_cache_fill_msec =
+			clamp(rcu_delay_page_cache_fill_msec, 0,
+				(int) (100 * MSEC_PER_SEC));
+
+		pr_info("Adjusting rcutree.rcu_delay_page_cache_fill_msec to %d ms.\n",
+			rcu_delay_page_cache_fill_msec);
+	}
+
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
@@ -4694,7 +4732,7 @@ static void __init kfree_rcu_batch_init(void)
 		}
 
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
-		INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
+		INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func);
 		krcp->initialized = true;
 	}
 	if (register_shrinker(&kfree_rcu_shrinker))
@@ -4733,7 +4771,6 @@ void __init rcu_init(void)
 	WARN_ON(!rcu_gp_wq);
 	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!rcu_par_gp_wq);
-	srcu_init();
 
 	/* Fill in default value for rcutree.qovld boot parameter. */
 	/* -After- the rcu_node ->lock fields are initialized! */