4 files changed, 188 insertions, 126 deletions

diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index e82ec9f9a5d8..d1221731c7cf 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -522,89 +522,6 @@ rcu_scale_print_module_parms(struct rcu_scale_ops *cur_ops, const char *tag)
 		 scale_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
 }
 
-static void
-rcu_scale_cleanup(void)
-{
-	int i;
-	int j;
-	int ngps = 0;
-	u64 *wdp;
-	u64 *wdpp;
-
-	/*
-	 * Would like warning at start, but everything is expedited
-	 * during the mid-boot phase, so have to wait till the end.
-	 */
-	if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp)
-		SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
-	if (rcu_gp_is_normal() && gp_exp)
-		SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
-	if (gp_exp && gp_async)
-		SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
-
-	if (torture_cleanup_begin())
-		return;
-	if (!cur_ops) {
-		torture_cleanup_end();
-		return;
-	}
-
-	if (reader_tasks) {
-		for (i = 0; i < nrealreaders; i++)
-			torture_stop_kthread(rcu_scale_reader,
-					     reader_tasks[i]);
-		kfree(reader_tasks);
-	}
-
-	if (writer_tasks) {
-		for (i = 0; i < nrealwriters; i++) {
-			torture_stop_kthread(rcu_scale_writer,
-					     writer_tasks[i]);
-			if (!writer_n_durations)
-				continue;
-			j = writer_n_durations[i];
-			pr_alert("%s%s writer %d gps: %d\n",
-				 scale_type, SCALE_FLAG, i, j);
-			ngps += j;
-		}
-		pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n",
-			 scale_type, SCALE_FLAG,
-			 t_rcu_scale_writer_started, t_rcu_scale_writer_finished,
-			 t_rcu_scale_writer_finished -
-			 t_rcu_scale_writer_started,
-			 ngps,
-			 rcuscale_seq_diff(b_rcu_gp_test_finished,
-					   b_rcu_gp_test_started));
-		for (i = 0; i < nrealwriters; i++) {
-			if (!writer_durations)
-				break;
-			if (!writer_n_durations)
-				continue;
-			wdpp = writer_durations[i];
-			if (!wdpp)
-				continue;
-			for (j = 0; j < writer_n_durations[i]; j++) {
-				wdp = &wdpp[j];
-				pr_alert("%s%s %4d writer-duration: %5d %llu\n",
-					scale_type, SCALE_FLAG,
-					i, j, *wdp);
-				if (j % 100 == 0)
-					schedule_timeout_uninterruptible(1);
-			}
-			kfree(writer_durations[i]);
-		}
-		kfree(writer_tasks);
-		kfree(writer_durations);
-		kfree(writer_n_durations);
-	}
-
-	/* Do torture-type-specific cleanup operations.  */
-	if (cur_ops->cleanup != NULL)
-		cur_ops->cleanup();
-
-	torture_cleanup_end();
-}
-
 /*
  * Return the number if non-negative.  If -1, the number of CPUs.
  * If less than -1, that much less than the number of CPUs, but
@@ -625,20 +542,6 @@ static int compute_real(int n)
 }
 
 /*
- * RCU scalability shutdown kthread.  Just waits to be awakened, then shuts
- * down system.
- */
-static int
-rcu_scale_shutdown(void *arg)
-{
-	wait_event_idle(shutdown_wq, atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters);
-	smp_mb(); /* Wake before output. */
-	rcu_scale_cleanup();
-	kernel_power_off();
-	return -EINVAL;
-}
-
-/*
  * kfree_rcu() scalability tests: Start a kfree_rcu() loop on all CPUs for number
  * of iterations and measure total time and number of GP for all iterations to complete.
  */
@@ -874,6 +777,108 @@ unwind:
 	return firsterr;
 }
 
+static void
+rcu_scale_cleanup(void)
+{
+	int i;
+	int j;
+	int ngps = 0;
+	u64 *wdp;
+	u64 *wdpp;
+
+	/*
+	 * Would like warning at start, but everything is expedited
+	 * during the mid-boot phase, so have to wait till the end.
+	 */
+	if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp)
+		SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
+	if (rcu_gp_is_normal() && gp_exp)
+		SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
+	if (gp_exp && gp_async)
+		SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
+
+	if (kfree_rcu_test) {
+		kfree_scale_cleanup();
+		return;
+	}
+
+	if (torture_cleanup_begin())
+		return;
+	if (!cur_ops) {
+		torture_cleanup_end();
+		return;
+	}
+
+	if (reader_tasks) {
+		for (i = 0; i < nrealreaders; i++)
+			torture_stop_kthread(rcu_scale_reader,
+					     reader_tasks[i]);
+		kfree(reader_tasks);
+	}
+
+	if (writer_tasks) {
+		for (i = 0; i < nrealwriters; i++) {
+			torture_stop_kthread(rcu_scale_writer,
+					     writer_tasks[i]);
+			if (!writer_n_durations)
+				continue;
+			j = writer_n_durations[i];
+			pr_alert("%s%s writer %d gps: %d\n",
+				 scale_type, SCALE_FLAG, i, j);
+			ngps += j;
+		}
+		pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n",
+			 scale_type, SCALE_FLAG,
+			 t_rcu_scale_writer_started, t_rcu_scale_writer_finished,
+			 t_rcu_scale_writer_finished -
+			 t_rcu_scale_writer_started,
+			 ngps,
+			 rcuscale_seq_diff(b_rcu_gp_test_finished,
+					   b_rcu_gp_test_started));
+		for (i = 0; i < nrealwriters; i++) {
+			if (!writer_durations)
+				break;
+			if (!writer_n_durations)
+				continue;
+			wdpp = writer_durations[i];
+			if (!wdpp)
+				continue;
+			for (j = 0; j < writer_n_durations[i]; j++) {
+				wdp = &wdpp[j];
+				pr_alert("%s%s %4d writer-duration: %5d %llu\n",
+					scale_type, SCALE_FLAG,
+					i, j, *wdp);
+				if (j % 100 == 0)
+					schedule_timeout_uninterruptible(1);
+			}
+			kfree(writer_durations[i]);
+		}
+		kfree(writer_tasks);
+		kfree(writer_durations);
+		kfree(writer_n_durations);
+	}
+
+	/* Do torture-type-specific cleanup operations.  */
+	if (cur_ops->cleanup != NULL)
+		cur_ops->cleanup();
+
+	torture_cleanup_end();
+}
+
+/*
+ * RCU scalability shutdown kthread.  Just waits to be awakened, then shuts
+ * down system.
+ */
+static int
+rcu_scale_shutdown(void *arg)
+{
+	wait_event_idle(shutdown_wq, atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters);
+	smp_mb(); /* Wake before output. */
+	rcu_scale_cleanup();
+	kernel_power_off();
+	return -EINVAL;
+}
+
 static int __init
 rcu_scale_init(void)
 {
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 8f08c087142b..b770add3f843 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -241,7 +241,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 	if (rcu_task_enqueue_lim < 0) {
 		rcu_task_enqueue_lim = 1;
 		rcu_task_cb_adjust = true;
-		pr_info("%s: Setting adjustable number of callback queues.\n", __func__);
 	} else if (rcu_task_enqueue_lim == 0) {
 		rcu_task_enqueue_lim = 1;
 	}
@@ -272,7 +271,9 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 		raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
 	}
 	raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
-	pr_info("%s: Setting shift to %d and lim to %d.\n", __func__, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim));
+
+	pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name,
+			data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim), rcu_task_cb_adjust);
 }
 
 // IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic().
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 54963f8c244c..1449cb69a0e0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2778,7 +2778,7 @@ EXPORT_SYMBOL_GPL(call_rcu);
  */
 struct kvfree_rcu_bulk_data {
 	struct list_head list;
-	unsigned long gp_snap;
+	struct rcu_gp_oldstate gp_snap;
 	unsigned long nr_records;
 	void *records[];
 };
@@ -2795,6 +2795,7 @@ struct kvfree_rcu_bulk_data {
  * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests
  * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period
  * @head_free: List of kfree_rcu() objects waiting for a grace period
+ * @head_free_gp_snap: Grace-period snapshot to check for attempted premature frees.
  * @bulk_head_free: Bulk-List of kvfree_rcu() objects waiting for a grace period
  * @krcp: Pointer to @kfree_rcu_cpu structure
  */
@@ -2802,6 +2803,7 @@ struct kvfree_rcu_bulk_data {
 struct kfree_rcu_cpu_work {
 	struct rcu_work rcu_work;
 	struct rcu_head *head_free;
+	struct rcu_gp_oldstate head_free_gp_snap;
 	struct list_head bulk_head_free[FREE_N_CHANNELS];
 	struct kfree_rcu_cpu *krcp;
 };
@@ -2922,6 +2924,9 @@ drain_page_cache(struct kfree_rcu_cpu *krcp)
 	struct llist_node *page_list, *pos, *n;
 	int freed = 0;
 
+	if (!rcu_min_cached_objs)
+		return 0;
+
 	raw_spin_lock_irqsave(&krcp->lock, flags);
 	page_list = llist_del_all(&krcp->bkvcache);
 	WRITE_ONCE(krcp->nr_bkv_objs, 0);
@@ -2942,24 +2947,25 @@ kvfree_rcu_bulk(struct kfree_rcu_cpu *krcp,
 	unsigned long flags;
 	int i;
 
-	debug_rcu_bhead_unqueue(bnode);
-
-	rcu_lock_acquire(&rcu_callback_map);
-	if (idx == 0) { // kmalloc() / kfree().
-		trace_rcu_invoke_kfree_bulk_callback(
-			rcu_state.name, bnode->nr_records,
-			bnode->records);
-
-		kfree_bulk(bnode->nr_records, bnode->records);
-	} else { // vmalloc() / vfree().
-		for (i = 0; i < bnode->nr_records; i++) {
-			trace_rcu_invoke_kvfree_callback(
-				rcu_state.name, bnode->records[i], 0);
-
-			vfree(bnode->records[i]);
+	if (!WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&bnode->gp_snap))) {
+		debug_rcu_bhead_unqueue(bnode);
+		rcu_lock_acquire(&rcu_callback_map);
+		if (idx == 0) { // kmalloc() / kfree().
+			trace_rcu_invoke_kfree_bulk_callback(
+				rcu_state.name, bnode->nr_records,
+				bnode->records);
+
+			kfree_bulk(bnode->nr_records, bnode->records);
+		} else { // vmalloc() / vfree().
+			for (i = 0; i < bnode->nr_records; i++) {
+				trace_rcu_invoke_kvfree_callback(
+					rcu_state.name, bnode->records[i], 0);
+
+				vfree(bnode->records[i]);
+			}
 		}
+		rcu_lock_release(&rcu_callback_map);
 	}
-	rcu_lock_release(&rcu_callback_map);
 
 	raw_spin_lock_irqsave(&krcp->lock, flags);
 	if (put_cached_bnode(krcp, bnode))
@@ -3006,6 +3012,7 @@ static void kfree_rcu_work(struct work_struct *work)
 	struct rcu_head *head;
 	struct kfree_rcu_cpu *krcp;
 	struct kfree_rcu_cpu_work *krwp;
+	struct rcu_gp_oldstate head_gp_snap;
 	int i;
 
 	krwp = container_of(to_rcu_work(work),
@@ -3020,6 +3027,7 @@ static void kfree_rcu_work(struct work_struct *work)
 	// Channel 3.
 	head = krwp->head_free;
 	krwp->head_free = NULL;
+	head_gp_snap = krwp->head_free_gp_snap;
 	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 
 	// Handle the first two channels.
@@ -3036,7 +3044,8 @@ static void kfree_rcu_work(struct work_struct *work)
 	 * queued on a linked list through their rcu_head structures.
 	 * This list is named "Channel 3".
 	 */
-	kvfree_rcu_list(head);
+	if (head && !WARN_ON_ONCE(!poll_state_synchronize_rcu_full(&head_gp_snap)))
+		kvfree_rcu_list(head);
 }
 
 static bool
@@ -3103,7 +3112,7 @@ kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp)
 		INIT_LIST_HEAD(&bulk_ready[i]);
 
 		list_for_each_entry_safe_reverse(bnode, n, &krcp->bulk_head[i], list) {
-			if (!poll_state_synchronize_rcu(bnode->gp_snap))
+			if (!poll_state_synchronize_rcu_full(&bnode->gp_snap))
 				break;
 
 			atomic_sub(bnode->nr_records, &krcp->bulk_count[i]);
@@ -3168,6 +3177,7 @@ static void kfree_rcu_monitor(struct work_struct *work)
 			// objects queued on the linked list.
 			if (!krwp->head_free) {
 				krwp->head_free = krcp->head;
+				get_state_synchronize_rcu_full(&krwp->head_free_gp_snap);
 				atomic_set(&krcp->head_count, 0);
 				WRITE_ONCE(krcp->head, NULL);
 			}
@@ -3216,7 +3226,7 @@ static void fill_page_cache_func(struct work_struct *work)
 	nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
 		1 : rcu_min_cached_objs;
 
-	for (i = 0; i < nr_pages; i++) {
+	for (i = READ_ONCE(krcp->nr_bkv_objs); i < nr_pages; i++) {
 		bnode = (struct kvfree_rcu_bulk_data *)
 			__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
@@ -3240,6 +3250,10 @@ static void fill_page_cache_func(struct work_struct *work)
 static void
 run_page_cache_worker(struct kfree_rcu_cpu *krcp)
 {
+	// If cache disabled, bail out.
+	if (!rcu_min_cached_objs)
+		return;
+
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
 			!atomic_xchg(&krcp->work_in_progress, 1)) {
 		if (atomic_read(&krcp->backoff_page_cache_fill)) {
@@ -3294,7 +3308,7 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
 			// scenarios.
 			bnode = (struct kvfree_rcu_bulk_data *)
 				__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
-			*krcp = krc_this_cpu_lock(flags);
+			raw_spin_lock_irqsave(&(*krcp)->lock, *flags);
 		}
 
 		if (!bnode)
@@ -3307,7 +3321,7 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
 
 	// Finally insert and update the GP for this page.
 	bnode->records[bnode->nr_records++] = ptr;
-	bnode->gp_snap = get_state_synchronize_rcu();
+	get_state_synchronize_rcu_full(&bnode->gp_snap);
 	atomic_inc(&(*krcp)->bulk_count[idx]);
 
 	return true;
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index f2280616f9d5..43229d2b0c44 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1319,13 +1319,22 @@ lazy_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 	int cpu;
 	unsigned long count = 0;
 
+	if (WARN_ON_ONCE(!cpumask_available(rcu_nocb_mask)))
+		return 0;
+
+	/*  Protect rcu_nocb_mask against concurrent (de-)offloading. */
+	if (!mutex_trylock(&rcu_state.barrier_mutex))
+		return 0;
+
 	/* Snapshot count of all CPUs */
-	for_each_possible_cpu(cpu) {
+	for_each_cpu(cpu, rcu_nocb_mask) {
 		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 
 		count +=  READ_ONCE(rdp->lazy_len);
 	}
 
+	mutex_unlock(&rcu_state.barrier_mutex);
+
 	return count ? count : SHRINK_EMPTY;
 }
 
@@ -1336,15 +1345,45 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	unsigned long flags;
 	unsigned long count = 0;
 
+	if (WARN_ON_ONCE(!cpumask_available(rcu_nocb_mask)))
+		return 0;
+	/*
+	 * Protect against concurrent (de-)offloading. Otherwise nocb locking
+	 * may be ignored or imbalanced.
+	 */
+	if (!mutex_trylock(&rcu_state.barrier_mutex)) {
+		/*
+		 * But really don't insist if barrier_mutex is contended since we
+		 * can't guarantee that it will never engage in a dependency
+		 * chain involving memory allocation. The lock is seldom contended
+		 * anyway.
+		 */
+		return 0;
+	}
+
 	/* Snapshot count of all CPUs */
-	for_each_possible_cpu(cpu) {
+	for_each_cpu(cpu, rcu_nocb_mask) {
 		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-		int _count = READ_ONCE(rdp->lazy_len);
+		int _count;
+
+		if (WARN_ON_ONCE(!rcu_rdp_is_offloaded(rdp)))
+			continue;
 
-		if (_count == 0)
+		if (!READ_ONCE(rdp->lazy_len))
 			continue;
+
 		rcu_nocb_lock_irqsave(rdp, flags);
-		WRITE_ONCE(rdp->lazy_len, 0);
+		/*
+		 * Recheck under the nocb lock. Since we are not holding the bypass
+		 * lock we may still race with increments from the enqueuer but still
+		 * we know for sure if there is at least one lazy callback.
+		 */
+		_count = READ_ONCE(rdp->lazy_len);
+		if (!_count) {
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+			continue;
+		}
+		WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false));
 		rcu_nocb_unlock_irqrestore(rdp, flags);
 		wake_nocb_gp(rdp, false);
 		sc->nr_to_scan -= _count;
@@ -1352,6 +1391,9 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		if (sc->nr_to_scan <= 0)
 			break;
 	}
+
+	mutex_unlock(&rcu_state.barrier_mutex);
+
 	return count ? count : SHRINK_STOP;
 }