1 files changed, 122 insertions, 77 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d626d32f6e57..1978eef95dca 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -23,6 +23,7 @@
 #include <linux/cache.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/signal.h>
+#include <linux/suspend.h>
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
 #include <linux/prefetch.h>
@@ -335,12 +336,12 @@ void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set)
 {
 	struct request_queue *q;
 
-	mutex_lock(&set->tag_list_lock);
-	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(q, &set->tag_list, tag_set_list) {
 		if (!blk_queue_skip_tagset_quiesce(q))
 			blk_mq_quiesce_queue_nowait(q);
 	}
-	mutex_unlock(&set->tag_list_lock);
+	rcu_read_unlock();
 
 	blk_mq_wait_quiesce_done(set);
 }
@@ -350,12 +351,12 @@ void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set)
 {
 	struct request_queue *q;
 
-	mutex_lock(&set->tag_list_lock);
-	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(q, &set->tag_list, tag_set_list) {
 		if (!blk_queue_skip_tagset_quiesce(q))
 			blk_mq_unquiesce_queue(q);
 	}
-	mutex_unlock(&set->tag_list_lock);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset);
 
@@ -376,6 +377,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	INIT_LIST_HEAD(&rq->queuelist);
 	rq->q = q;
 	rq->__sector = (sector_t) -1;
+	rq->phys_gap_bit = 0;
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->tag = BLK_MQ_NO_TAG;
@@ -467,21 +469,26 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 	unsigned long tag_mask;
 	int i, nr = 0;
 
-	tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
-	if (unlikely(!tag_mask))
-		return NULL;
+	do {
+		tag_mask = blk_mq_get_tags(data, data->nr_tags - nr, &tag_offset);
+		if (unlikely(!tag_mask)) {
+			if (nr == 0)
+				return NULL;
+			break;
+		}
+		tags = blk_mq_tags_from_data(data);
+		for (i = 0; tag_mask; i++) {
+			if (!(tag_mask & (1UL << i)))
+				continue;
+			tag = tag_offset + i;
+			prefetch(tags->static_rqs[tag]);
+			tag_mask &= ~(1UL << i);
+			rq = blk_mq_rq_ctx_init(data, tags, tag);
+			rq_list_add_head(data->cached_rqs, rq);
+			nr++;
+		}
+	} while (data->nr_tags > nr);
 
-	tags = blk_mq_tags_from_data(data);
-	for (i = 0; tag_mask; i++) {
-		if (!(tag_mask & (1UL << i)))
-			continue;
-		tag = tag_offset + i;
-		prefetch(tags->static_rqs[tag]);
-		tag_mask &= ~(1UL << i);
-		rq = blk_mq_rq_ctx_init(data, tags, tag);
-		rq_list_add_head(data->cached_rqs, rq);
-		nr++;
-	}
 	if (!(data->rq_flags & RQF_SCHED_TAGS))
 		blk_mq_add_active_requests(data->hctx, nr);
 	/* caller already holds a reference, add for remainder */
@@ -668,6 +675,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
 			goto out_queue_exit;
 	}
 	rq->__data_len = 0;
+	rq->phys_gap_bit = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
 	return rq;
@@ -723,7 +731,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	 * If not tell the caller that it should skip this queue.
 	 */
 	ret = -EXDEV;
-	data.hctx = xa_load(&q->hctx_table, hctx_idx);
+	data.hctx = q->queue_hw_ctx[hctx_idx];
 	if (!blk_mq_hw_queue_mapped(data.hctx))
 		goto out_queue_exit;
 	cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
@@ -748,6 +756,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag);
 	blk_mq_rq_time_init(rq, alloc_time_ns);
 	rq->__data_len = 0;
+	rq->phys_gap_bit = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
 	return rq;
@@ -2674,6 +2683,8 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 	rq->bio = rq->biotail = bio;
 	rq->__sector = bio->bi_iter.bi_sector;
 	rq->__data_len = bio->bi_iter.bi_size;
+	rq->phys_gap_bit = bio->bi_bvec_gap_bit;
+
 	rq->nr_phys_segments = nr_segs;
 	if (bio_integrity(bio))
 		rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q,
@@ -3380,6 +3391,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	}
 	rq->nr_phys_segments = rq_src->nr_phys_segments;
 	rq->nr_integrity_segments = rq_src->nr_integrity_segments;
+	rq->phys_gap_bit = rq_src->phys_gap_bit;
 
 	if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0)
 		goto free_and_out;
@@ -3707,6 +3719,7 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 {
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
+	int ret = 0;
 
 	if (blk_mq_hctx_has_online_cpu(hctx, cpu))
 		return 0;
@@ -3727,12 +3740,24 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 	 * frozen and there are no requests.
 	 */
 	if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) {
-		while (blk_mq_hctx_has_requests(hctx))
+		while (blk_mq_hctx_has_requests(hctx)) {
+			/*
+			 * The wakeup capable IRQ handler of block device is
+			 * not called during suspend. Skip the loop by checking
+			 * pm_wakeup_pending to prevent the deadlock and improve
+			 * suspend latency.
+			 */
+			if (pm_wakeup_pending()) {
+				clear_bit(BLK_MQ_S_INACTIVE, &hctx->state);
+				ret = -EBUSY;
+				break;
+			}
 			msleep(5);
+		}
 		percpu_ref_put(&hctx->queue->q_usage_counter);
 	}
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -3935,8 +3960,6 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 			blk_free_flush_queue_callback);
 	hctx->fq = NULL;
 
-	xa_erase(&q->hctx_table, hctx_idx);
-
 	spin_lock(&q->unused_hctx_lock);
 	list_add(&hctx->hctx_list, &q->unused_hctx_list);
 	spin_unlock(&q->unused_hctx_lock);
@@ -3978,14 +4001,8 @@ static int blk_mq_init_hctx(struct request_queue *q,
 				hctx->numa_node))
 		goto exit_hctx;
 
-	if (xa_insert(&q->hctx_table, hctx_idx, hctx, GFP_KERNEL))
-		goto exit_flush_rq;
-
 	return 0;
 
- exit_flush_rq:
-	if (set->ops->exit_request)
-		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
@@ -4294,7 +4311,7 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 	struct blk_mq_tag_set *set = q->tag_set;
 
 	mutex_lock(&set->tag_list_lock);
-	list_del(&q->tag_set_list);
+	list_del_rcu(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
 		set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
@@ -4302,7 +4319,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 		blk_mq_update_tag_set_shared(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
-	INIT_LIST_HEAD(&q->tag_set_list);
 }
 
 static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
@@ -4321,7 +4337,7 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	}
 	if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
 		queue_set_hctx_shared(q, true);
-	list_add_tail(&q->tag_set_list, &set->tag_list);
+	list_add_tail_rcu(&q->tag_set_list, &set->tag_list);
 
 	mutex_unlock(&set->tag_list_lock);
 }
@@ -4374,7 +4390,7 @@ void blk_mq_release(struct request_queue *q)
 		kobject_put(&hctx->kobj);
 	}
 
-	xa_destroy(&q->hctx_table);
+	kfree(q->queue_hw_ctx);
 
 	/*
 	 * release .mq_kobj and sw queue's kobject now because
@@ -4518,26 +4534,49 @@ static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
 static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 				     struct request_queue *q)
 {
-	struct blk_mq_hw_ctx *hctx;
-	unsigned long i, j;
+	int i, j, end;
+	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
+
+	if (q->nr_hw_queues < set->nr_hw_queues) {
+		struct blk_mq_hw_ctx **new_hctxs;
+
+		new_hctxs = kcalloc_node(set->nr_hw_queues,
+				       sizeof(*new_hctxs), GFP_KERNEL,
+				       set->numa_node);
+		if (!new_hctxs)
+			return;
+		if (hctxs)
+			memcpy(new_hctxs, hctxs, q->nr_hw_queues *
+			       sizeof(*hctxs));
+		rcu_assign_pointer(q->queue_hw_ctx, new_hctxs);
+		/*
+		 * Make sure reading the old queue_hw_ctx from other
+		 * context concurrently won't trigger uaf.
+		 */
+		synchronize_rcu_expedited();
+		kfree(hctxs);
+		hctxs = new_hctxs;
+	}
 
 	for (i = 0; i < set->nr_hw_queues; i++) {
 		int old_node;
 		int node = blk_mq_get_hctx_node(set, i);
-		struct blk_mq_hw_ctx *old_hctx = xa_load(&q->hctx_table, i);
+		struct blk_mq_hw_ctx *old_hctx = hctxs[i];
 
 		if (old_hctx) {
 			old_node = old_hctx->numa_node;
 			blk_mq_exit_hctx(q, set, old_hctx, i);
 		}
 
-		if (!blk_mq_alloc_and_init_hctx(set, q, i, node)) {
+		hctxs[i] = blk_mq_alloc_and_init_hctx(set, q, i, node);
+		if (!hctxs[i]) {
 			if (!old_hctx)
 				break;
 			pr_warn("Allocate new hctx on node %d fails, fallback to previous one on node %d\n",
 					node, old_node);
-			hctx = blk_mq_alloc_and_init_hctx(set, q, i, old_node);
-			WARN_ON_ONCE(!hctx);
+			hctxs[i] = blk_mq_alloc_and_init_hctx(set, q, i,
+					old_node);
+			WARN_ON_ONCE(!hctxs[i]);
 		}
 	}
 	/*
@@ -4546,13 +4585,21 @@ static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	 */
 	if (i != set->nr_hw_queues) {
 		j = q->nr_hw_queues;
+		end = i;
 	} else {
 		j = i;
+		end = q->nr_hw_queues;
 		q->nr_hw_queues = set->nr_hw_queues;
 	}
 
-	xa_for_each_start(&q->hctx_table, j, hctx, j)
-		blk_mq_exit_hctx(q, set, hctx, j);
+	for (; j < end; j++) {
+		struct blk_mq_hw_ctx *hctx = hctxs[j];
+
+		if (hctx) {
+			blk_mq_exit_hctx(q, set, hctx, j);
+			hctxs[j] = NULL;
+		}
+	}
 }
 
 static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
@@ -4588,8 +4635,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&q->unused_hctx_list);
 	spin_lock_init(&q->unused_hctx_lock);
 
-	xa_init(&q->hctx_table);
-
 	blk_mq_realloc_hw_ctxs(set, q);
 	if (!q->nr_hw_queues)
 		goto err_hctxs;
@@ -4983,27 +5028,28 @@ struct elevator_tags *blk_mq_update_nr_requests(struct request_queue *q,
  * Switch back to the elevator type stored in the xarray.
  */
 static void blk_mq_elv_switch_back(struct request_queue *q,
-		struct xarray *elv_tbl, struct xarray *et_tbl)
+		struct xarray *elv_tbl)
 {
-	struct elevator_type *e = xa_load(elv_tbl, q->id);
-	struct elevator_tags *t = xa_load(et_tbl, q->id);
+	struct elv_change_ctx *ctx = xa_load(elv_tbl, q->id);
+
+	if (WARN_ON_ONCE(!ctx))
+		return;
 
 	/* The elv_update_nr_hw_queues unfreezes the queue. */
-	elv_update_nr_hw_queues(q, e, t);
+	elv_update_nr_hw_queues(q, ctx);
 
 	/* Drop the reference acquired in blk_mq_elv_switch_none. */
-	if (e)
-		elevator_put(e);
+	if (ctx->type)
+		elevator_put(ctx->type);
 }
 
 /*
- * Stores elevator type in xarray and set current elevator to none. It uses
- * q->id as an index to store the elevator type into the xarray.
+ * Stores elevator name and type in ctx and set current elevator to none.
  */
 static int blk_mq_elv_switch_none(struct request_queue *q,
 		struct xarray *elv_tbl)
 {
-	int ret = 0;
+	struct elv_change_ctx *ctx;
 
 	lockdep_assert_held_write(&q->tag_set->update_nr_hwq_lock);
 
@@ -5015,10 +5061,11 @@ static int blk_mq_elv_switch_none(struct request_queue *q,
 	 * can't run concurrently.
 	 */
 	if (q->elevator) {
+		ctx = xa_load(elv_tbl, q->id);
+		if (WARN_ON_ONCE(!ctx))
+			return -ENOENT;
 
-		ret = xa_insert(elv_tbl, q->id, q->elevator->type, GFP_KERNEL);
-		if (WARN_ON_ONCE(ret))
-			return ret;
+		ctx->name = q->elevator->type->elevator_name;
 
 		/*
 		 * Before we switch elevator to 'none', take a reference to
@@ -5029,9 +5076,14 @@ static int blk_mq_elv_switch_none(struct request_queue *q,
 		 */
 		__elevator_get(q->elevator->type);
 
+		/*
+		 * Store elevator type so that we can release the reference
+		 * taken above later.
+		 */
+		ctx->type = q->elevator->type;
 		elevator_set_none(q);
 	}
-	return ret;
+	return 0;
 }
 
 static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
@@ -5041,7 +5093,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	int prev_nr_hw_queues = set->nr_hw_queues;
 	unsigned int memflags;
 	int i;
-	struct xarray elv_tbl, et_tbl;
+	struct xarray elv_tbl;
 	bool queues_frozen = false;
 
 	lockdep_assert_held(&set->tag_list_lock);
@@ -5055,11 +5107,12 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	memflags = memalloc_noio_save();
 
-	xa_init(&et_tbl);
-	if (blk_mq_alloc_sched_tags_batch(&et_tbl, set, nr_hw_queues) < 0)
-		goto out_memalloc_restore;
-
 	xa_init(&elv_tbl);
+	if (blk_mq_alloc_sched_ctx_batch(&elv_tbl, set) < 0)
+		goto out_free_ctx;
+
+	if (blk_mq_alloc_sched_res_batch(&elv_tbl, set, nr_hw_queues) < 0)
+		goto out_free_ctx;
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_debugfs_unregister_hctxs(q);
@@ -5105,7 +5158,7 @@ switch_back:
 		/* switch_back expects queue to be frozen */
 		if (!queues_frozen)
 			blk_mq_freeze_queue_nomemsave(q);
-		blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl);
+		blk_mq_elv_switch_back(q, &elv_tbl);
 	}
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
@@ -5116,9 +5169,9 @@ switch_back:
 		blk_mq_add_hw_queues_cpuhp(q);
 	}
 
+out_free_ctx:
+	blk_mq_free_sched_ctx_batch(&elv_tbl);
 	xa_destroy(&elv_tbl);
-	xa_destroy(&et_tbl);
-out_memalloc_restore:
 	memalloc_noio_restore(memflags);
 
 	/* Free the excess tags when nr_hw_queues shrink. */
@@ -5139,27 +5192,19 @@ EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 			 struct io_comp_batch *iob, unsigned int flags)
 {
-	long state = get_current_state();
 	int ret;
 
 	do {
 		ret = q->mq_ops->poll(hctx, iob);
-		if (ret > 0) {
-			__set_current_state(TASK_RUNNING);
+		if (ret > 0)
 			return ret;
-		}
-
-		if (signal_pending_state(state, current))
-			__set_current_state(TASK_RUNNING);
-		if (task_is_running(current))
+		if (task_sigpending(current))
 			return 1;
-
 		if (ret < 0 || (flags & BLK_POLL_ONESHOT))
 			break;
 		cpu_relax();
 	} while (!need_resched());
 
-	__set_current_state(TASK_RUNNING);
 	return 0;
 }
 
@@ -5168,7 +5213,7 @@ int blk_mq_poll(struct request_queue *q, blk_qc_t cookie,
 {
 	if (!blk_mq_can_poll(q))
 		return 0;
-	return blk_hctx_poll(q, xa_load(&q->hctx_table, cookie), iob, flags);
+	return blk_hctx_poll(q, q->queue_hw_ctx[cookie], iob, flags);
 }
 
 int blk_rq_poll(struct request *rq, struct io_comp_batch *iob,