Merge: blk-mq: fix scsi lockup

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1569

blk-mq: fix scsi lockup

JIRA: https://issues.redhat.com/browse/RHEL-120078

Signed-off-by: Ming Lei <ming.lei@redhat.com>

Approved-by: Jeff Moyer <jmoyer@redhat.com>
Approved-by: Ewan D. Milne <emilne@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Scott Weaver <scweaver@redhat.com>

Author: swvrrh

block/blk-mq-sysfs.c

@@ -34,7 +34,6 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj)
 	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
 						  kobj);
 
-	blk_free_flush_queue(hctx->fq);
 	sbitmap_free(&hctx->ctx_map);
 	free_cpumask_var(hctx->cpumask);
 	kfree(hctx->ctxs);

block/blk-mq-tag.c

@@ -8,6 +8,9 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 #include <linux/delay.h>
 #include "blk.h"
@@ -253,13 +256,10 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
 		unsigned int bitnr)
 {
 	struct request *rq;
-	unsigned long flags;
 
-	spin_lock_irqsave(&tags->lock, flags);
 	rq = tags->rqs[bitnr];
 	if (!rq || rq->tag != bitnr || !req_ref_inc_not_zero(rq))
 		rq = NULL;
-	spin_unlock_irqrestore(&tags->lock, flags);
 	return rq;
 }
 
@@ -437,7 +437,9 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv)
 {
 	unsigned int flags = tagset->flags;
-	int i, nr_tags;
+	int i, nr_tags, srcu_idx;
+
+	srcu_idx = srcu_read_lock(&tagset->tags_srcu);
 
 	nr_tags = blk_mq_is_shared_tags(flags) ? 1 : tagset->nr_hw_queues;
 
@@ -446,6 +448,7 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 			__blk_mq_all_tag_iter(tagset->tags[i], fn, priv,
 					      BT_TAG_ITER_STARTED);
 	}
+	srcu_read_unlock(&tagset->tags_srcu, srcu_idx);
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
@@ -496,6 +499,8 @@ EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 		void *priv)
 {
+	int srcu_idx;
+
 	/*
 	 * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and hctx_table
 	 * while the queue is frozen. So we can use q_usage_counter to avoid
@@ -504,6 +509,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
 
+	srcu_idx = srcu_read_lock(&q->tag_set->tags_srcu);
 	if (blk_mq_is_shared_tags(q->tag_set->flags)) {
 		struct blk_mq_tags *tags = q->tag_set->shared_tags;
 		struct sbitmap_queue *bresv = &tags->breserved_tags;
@@ -533,6 +539,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 			bt_for_each(hctx, q, btags, fn, priv, false);
 		}
 	}
+	srcu_read_unlock(&q->tag_set->tags_srcu, srcu_idx);
 	blk_queue_exit(q);
 }
 
@@ -562,6 +569,8 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 	spin_lock_init(&tags->lock);
+	INIT_LIST_HEAD(&tags->page_list);
+
 	if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node))
 		goto out_free_tags;
 	if (bt_alloc(&tags->breserved_tags, reserved_tags, round_robin, node))
@@ -576,11 +585,37 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	return NULL;
 }
 
-void blk_mq_free_tags(struct blk_mq_tags *tags)
+static void blk_mq_free_tags_callback(struct rcu_head *head)
+{
+	struct blk_mq_tags *tags = container_of(head, struct blk_mq_tags,
+						rcu_head);
+	struct page *page;
+
+	while (!list_empty(&tags->page_list)) {
+		page = list_first_entry(&tags->page_list, struct page, lru);
+		list_del_init(&page->lru);
+		/*
+		 * Remove kmemleak object previously allocated in
+		 * blk_mq_alloc_rqs().
+		 */
+		kmemleak_free(page_address(page));
+		__free_pages(page, page->private);
+	}
+	kfree(tags);
+}
+
+void blk_mq_free_tags(struct blk_mq_tag_set *set, struct blk_mq_tags *tags)
 {
 	sbitmap_queue_free(&tags->bitmap_tags);
 	sbitmap_queue_free(&tags->breserved_tags);
-	kfree(tags);
+
+	/* if tags pages is not allocated yet, free tags directly */
+	if (list_empty(&tags->page_list)) {
+		kfree(tags);
+		return;
+	}
+
+	call_srcu(&set->tags_srcu, &tags->rcu_head, blk_mq_free_tags_callback);
 }
 
 int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,

block/blk-mq.c

@@ -3413,7 +3413,6 @@ static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags,
 				    struct blk_mq_tags *tags)
 {
 	struct page *page;
-	unsigned long flags;
 
 	/*
 	 * There is no need to clear mapping if driver tags is not initialized
@@ -3437,22 +3436,12 @@ static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags,
 			}
 		}
 	}
-
-	/*
-	 * Wait until all pending iteration is done.
-	 *
-	 * Request reference is cleared and it is guaranteed to be observed
-	 * after the ->lock is released.
-	 */
-	spin_lock_irqsave(&drv_tags->lock, flags);
-	spin_unlock_irqrestore(&drv_tags->lock, flags);
 }
 
 void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx)
 {
 	struct blk_mq_tags *drv_tags;
-	struct page *page;
 
 	if (list_empty(&tags->page_list))
 		return;
@@ -3476,27 +3465,20 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 	}
 
 	blk_mq_clear_rq_mapping(drv_tags, tags);
-
-	while (!list_empty(&tags->page_list)) {
-		page = list_first_entry(&tags->page_list, struct page, lru);
-		list_del_init(&page->lru);
-		/*
-		 * Remove kmemleak object previously allocated in
-		 * blk_mq_alloc_rqs().
-		 */
-		kmemleak_free(page_address(page));
-		__free_pages(page, page->private);
-	}
+	/*
+	 * Free request pages in SRCU callback, which is called from
+	 * blk_mq_free_tags().
+	 */
 }
 
-void blk_mq_free_rq_map(struct blk_mq_tags *tags)
+void blk_mq_free_rq_map(struct blk_mq_tag_set *set, struct blk_mq_tags *tags)
 {
 	kfree(tags->rqs);
 	tags->rqs = NULL;
 	kfree(tags->static_rqs);
 	tags->static_rqs = NULL;
 
-	blk_mq_free_tags(tags);
+	blk_mq_free_tags(set, tags);
 }
 
 static enum hctx_type hctx_idx_to_type(struct blk_mq_tag_set *set,
@@ -3558,7 +3540,7 @@ static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 err_free_rqs:
 	kfree(tags->rqs);
 err_free_tags:
-	blk_mq_free_tags(tags);
+	blk_mq_free_tags(set, tags);
 	return NULL;
 }
 
@@ -3588,8 +3570,6 @@ static int blk_mq_alloc_rqs(struct blk_mq_tag_set *set,
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 
-	INIT_LIST_HEAD(&tags->page_list);
-
 	/*
 	 * rq_size is the size of the request plus driver payload, rounded
 	 * to the cacheline size
@@ -3676,8 +3656,12 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
 	struct rq_iter_data data = {
 		.hctx	= hctx,
 	};
+	int srcu_idx;
 
+	srcu_idx = srcu_read_lock(&hctx->queue->tag_set->tags_srcu);
 	blk_mq_all_tag_iter(tags, blk_mq_has_request, &data);
+	srcu_read_unlock(&hctx->queue->tag_set->tags_srcu, srcu_idx);
+
 	return data.has_rq;
 }
 
@@ -3897,7 +3881,6 @@ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
 		unsigned int queue_depth, struct request *flush_rq)
 {
 	int i;
-	unsigned long flags;
 
 	/* The hw queue may not be mapped yet */
 	if (!tags)
@@ -3907,15 +3890,14 @@ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
 
 	for (i = 0; i < queue_depth; i++)
 		cmpxchg(&tags->rqs[i], flush_rq, NULL);
+}
 
-	/*
-	 * Wait until all pending iteration is done.
-	 *
-	 * Request reference is cleared and it is guaranteed to be observed
-	 * after the ->lock is released.
-	 */
-	spin_lock_irqsave(&tags->lock, flags);
-	spin_unlock_irqrestore(&tags->lock, flags);
+static void blk_free_flush_queue_callback(struct rcu_head *head)
+{
+	struct blk_flush_queue *fq =
+		container_of(head, struct blk_flush_queue, rcu_head);
+
+	blk_free_flush_queue(fq);
 }
 
 /* hctx->ctxs will be freed in queue's release handler */
@@ -3937,6 +3919,10 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
+	call_srcu(&set->tags_srcu, &hctx->fq->rcu_head,
+			blk_free_flush_queue_callback);
+	hctx->fq = NULL;
+
 	xa_erase(&q->hctx_table, hctx_idx);
 
 	spin_lock(&q->unused_hctx_lock);
@@ -3962,13 +3948,19 @@ static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
 {
+	gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
+
+	hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
+	if (!hctx->fq)
+		goto fail;
+
 	hctx->queue_num = hctx_idx;
 
 	hctx->tags = set->tags[hctx_idx];
 
 	if (set->ops->init_hctx &&
 	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
-		goto fail;
+		goto fail_free_fq;
 
 	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
 				hctx->numa_node))
@@ -3985,6 +3977,9 @@ static int blk_mq_init_hctx(struct request_queue *q,
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
+ fail_free_fq:
+	blk_free_flush_queue(hctx->fq);
+	hctx->fq = NULL;
  fail:
 	return -1;
 }
@@ -4036,16 +4031,10 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
-	hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
-	if (!hctx->fq)
-		goto free_bitmap;
-
 	blk_mq_hctx_kobj_init(hctx);
 
 	return hctx;
 
- free_bitmap:
-	sbitmap_free(&hctx->ctx_map);
  free_ctxs:
 	kfree(hctx->ctxs);
  free_cpumask:
@@ -4099,7 +4088,7 @@ struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
 
 	ret = blk_mq_alloc_rqs(set, tags, hctx_idx, depth);
 	if (ret) {
-		blk_mq_free_rq_map(tags);
+		blk_mq_free_rq_map(set, tags);
 		return NULL;
 	}
 
@@ -4127,7 +4116,7 @@ void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
 {
 	if (tags) {
 		blk_mq_free_rqs(set, tags, hctx_idx);
-		blk_mq_free_rq_map(tags);
+		blk_mq_free_rq_map(set, tags);
 	}
 }
 
@@ -4826,6 +4815,9 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 		if (ret)
 			goto out_free_srcu;
 	}
+	ret = init_srcu_struct(&set->tags_srcu);
+	if (ret)
+		goto out_cleanup_srcu;
 
 	init_rwsem(&set->update_nr_hwq_lock);
 
@@ -4834,7 +4826,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 				 sizeof(struct blk_mq_tags *), GFP_KERNEL,
 				 set->numa_node);
 	if (!set->tags)
-		goto out_cleanup_srcu;
+		goto out_cleanup_tags_srcu;
 
 	for (i = 0; i < set->nr_maps; i++) {
 		set->map[i].mq_map = kcalloc_node(nr_cpu_ids,
@@ -4863,6 +4855,8 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	}
 	kfree(set->tags);
 	set->tags = NULL;
+out_cleanup_tags_srcu:
+	cleanup_srcu_struct(&set->tags_srcu);
 out_cleanup_srcu:
 	if (set->flags & BLK_MQ_F_BLOCKING)
 		cleanup_srcu_struct(set->srcu);
@@ -4908,6 +4902,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 
 	kfree(set->tags);
 	set->tags = NULL;
+
+	srcu_barrier(&set->tags_srcu);
+	cleanup_srcu_struct(&set->tags_srcu);
 	if (set->flags & BLK_MQ_F_BLOCKING) {
 		cleanup_srcu_struct(set->srcu);
 		kfree(set->srcu);

block/blk-mq.h

@@ -59,7 +59,7 @@ void blk_mq_put_rq_ref(struct request *rq);
  */
 void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx);
-void blk_mq_free_rq_map(struct blk_mq_tags *tags);
+void blk_mq_free_rq_map(struct blk_mq_tag_set *set, struct blk_mq_tags *tags);
 struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
 				unsigned int hctx_idx, unsigned int depth);
 void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
@@ -162,7 +162,7 @@ struct blk_mq_alloc_data {
 
 struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
 		unsigned int reserved_tags, unsigned int flags, int node);
-void blk_mq_free_tags(struct blk_mq_tags *tags);
+void blk_mq_free_tags(struct blk_mq_tag_set *set, struct blk_mq_tags *tags);
 
 unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
 unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags,

block/blk.h

@@ -32,6 +32,7 @@ struct blk_flush_queue {
 	struct list_head	flush_queue[2];
 	unsigned long		flush_data_in_flight;
 	struct request		*flush_rq;
+	struct rcu_head		rcu_head;
 };
 
 bool is_flush_rq(struct request *req);