Merge tag 'block-6.10-20240523' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:
 "Followup block updates, mostly due to NVMe being a bit late to the
  party. But nothing major in there, so not a big deal.

  In detail, this contains:

   - NVMe pull request via Keith:
       - Fabrics connection retries (Daniel, Hannes)
       - Fabrics logging enhancements (Tokunori)
       - RDMA delete optimization (Sagi)

   - ublk DMA alignment fix (me)

   - null_blk sparse warning fixes (Bart)

   - Discard support for brd (Keith)

   - blk-cgroup list corruption fixes (Ming)

   - blk-cgroup stat propagation fix (Waiman)

   - Regression fix for plugging stall with md (Yu)

   - Misc fixes or cleanups (David, Jeff, Justin)"

* tag 'block-6.10-20240523' of git://git.kernel.dk/linux: (24 commits)
  null_blk: fix null-ptr-dereference while configuring 'power' and 'submit_queues'
  blk-throttle: remove unused struct 'avg_latency_bucket'
  block: fix lost bio for plug enabled bio based device
  block: t10-pi: add MODULE_DESCRIPTION()
  blk-mq: add helper for checking if one CPU is mapped to specified hctx
  blk-cgroup: Properly propagate the iostat update up the hierarchy
  blk-cgroup: fix list corruption from reorder of WRITE ->lqueued
  blk-cgroup: fix list corruption from resetting io stat
  cdrom: rearrange last_media_change check to avoid unintentional overflow
  nbd: Fix signal handling
  nbd: Remove a local variable from nbd_send_cmd()
  nbd: Improve the documentation of the locking assumptions
  nbd: Remove superfluous casts
  nbd: Use NULL to represent a pointer
  brd: implement discard support
  null_blk: Fix two sparse warnings
  ublk_drv: set DMA alignment mask to 3
  nvme-rdma, nvme-tcp: include max reconnects for reconnect logging
  nvmet-rdma: Avoid o(n^2) loop in delete_ctrl
  nvme: do not retry authentication failures
  ...

Author: torvalds

block/blk-cgroup.c

@@ -322,6 +322,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	blkg->q = disk->queue;
 	INIT_LIST_HEAD(&blkg->q_node);
 	blkg->blkcg = blkcg;
+	blkg->iostat.blkg = blkg;
 #ifdef CONFIG_BLK_CGROUP_PUNT_BIO
 	spin_lock_init(&blkg->async_bio_lock);
 	bio_list_init(&blkg->async_bios);
@@ -618,12 +619,45 @@ static void blkg_destroy_all(struct gendisk *disk)
 	spin_unlock_irq(&q->queue_lock);
 }
 
+static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] = src->bytes[i];
+		dst->ios[i] = src->ios[i];
+	}
+}
+
+static void __blkg_clear_stat(struct blkg_iostat_set *bis)
+{
+	struct blkg_iostat cur = {0};
+	unsigned long flags;
+
+	flags = u64_stats_update_begin_irqsave(&bis->sync);
+	blkg_iostat_set(&bis->cur, &cur);
+	blkg_iostat_set(&bis->last, &cur);
+	u64_stats_update_end_irqrestore(&bis->sync, flags);
+}
+
+static void blkg_clear_stat(struct blkcg_gq *blkg)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu);
+
+		__blkg_clear_stat(s);
+	}
+	__blkg_clear_stat(&blkg->iostat);
+}
+
 static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 			     struct cftype *cftype, u64 val)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
-	int i, cpu;
+	int i;
 
 	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
@@ -634,18 +668,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	 * anyway.  If you get hit by a race, retry.
 	 */
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
-		for_each_possible_cpu(cpu) {
-			struct blkg_iostat_set *bis =
-				per_cpu_ptr(blkg->iostat_cpu, cpu);
-			memset(bis, 0, sizeof(*bis));
-
-			/* Re-initialize the cleared blkg_iostat_set */
-			u64_stats_init(&bis->sync);
-			bis->blkg = blkg;
-		}
-		memset(&blkg->iostat, 0, sizeof(blkg->iostat));
-		u64_stats_init(&blkg->iostat.sync);
-
+		blkg_clear_stat(blkg);
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
 
@@ -948,16 +971,6 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx)
 }
 EXPORT_SYMBOL_GPL(blkg_conf_exit);
 
-static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
-{
-	int i;
-
-	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
-		dst->bytes[i] = src->bytes[i];
-		dst->ios[i] = src->ios[i];
-	}
-}
-
 static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
 {
 	int i;
@@ -1023,7 +1036,19 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu)
 		struct blkg_iostat cur;
 		unsigned int seq;
 
+		/*
+		 * Order assignment of `next_bisc` from `bisc->lnode.next` in
+		 * llist_for_each_entry_safe and clearing `bisc->lqueued` for
+		 * avoiding to assign `next_bisc` with new next pointer added
+		 * in blk_cgroup_bio_start() in case of re-ordering.
+		 *
+		 * The pair barrier is implied in llist_add() in blk_cgroup_bio_start().
+		 */
+		smp_mb();
+
 		WRITE_ONCE(bisc->lqueued, false);
+		if (bisc == &blkg->iostat)
+			goto propagate_up; /* propagate up to parent only */
 
 		/* fetch the current per-cpu values */
 		do {
@@ -1033,10 +1058,24 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu)
 
 		blkcg_iostat_update(blkg, &cur, &bisc->last);
 
+propagate_up:
 		/* propagate global delta to parent (unless that's root) */
-		if (parent && parent->parent)
+		if (parent && parent->parent) {
 			blkcg_iostat_update(parent, &blkg->iostat.cur,
 					    &blkg->iostat.last);
+			/*
+			 * Queue parent->iostat to its blkcg's lockless
+			 * list to propagate up to the grandparent if the
+			 * iostat hasn't been queued yet.
+			 */
+			if (!parent->iostat.lqueued) {
+				struct llist_head *plhead;
+
+				plhead = per_cpu_ptr(parent->blkcg->lhead, cpu);
+				llist_add(&parent->iostat.lnode, plhead);
+				parent->iostat.lqueued = true;
+			}
+		}
 	}
 	raw_spin_unlock_irqrestore(&blkg_stat_lock, flags);
 out:

block/blk-core.c

@@ -615,9 +615,14 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 
 static void __submit_bio(struct bio *bio)
 {
+	/* If plug is not used, add new plug here to cache nsecs time. */
+	struct blk_plug plug;
+
 	if (unlikely(!blk_crypto_bio_prep(&bio)))
 		return;
 
+	blk_start_plug(&plug);
+
 	if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) {
 		blk_mq_submit_bio(bio);
 	} else if (likely(bio_queue_enter(bio) == 0)) {
@@ -626,6 +631,8 @@ static void __submit_bio(struct bio *bio)
 		disk->fops->submit_bio(bio);
 		blk_queue_exit(disk->queue);
 	}
+
+	blk_finish_plug(&plug);
 }
 
 /*
@@ -650,13 +657,11 @@ static void __submit_bio(struct bio *bio)
 static void __submit_bio_noacct(struct bio *bio)
 {
 	struct bio_list bio_list_on_stack[2];
-	struct blk_plug plug;
 
 	BUG_ON(bio->bi_next);
 
 	bio_list_init(&bio_list_on_stack[0]);
 	current->bio_list = bio_list_on_stack;
-	blk_start_plug(&plug);
 
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
@@ -690,23 +695,19 @@ static void __submit_bio_noacct(struct bio *bio)
 		bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 	} while ((bio = bio_list_pop(&bio_list_on_stack[0])));
 
-	blk_finish_plug(&plug);
 	current->bio_list = NULL;
 }
 
 static void __submit_bio_noacct_mq(struct bio *bio)
 {
 	struct bio_list bio_list[2] = { };
-	struct blk_plug plug;
 
 	current->bio_list = bio_list;
-	blk_start_plug(&plug);
 
 	do {
 		__submit_bio(bio);
 	} while ((bio = bio_list_pop(&bio_list[0])));
 
-	blk_finish_plug(&plug);
 	current->bio_list = NULL;
 }
 

block/blk-mq.c

@@ -3545,12 +3545,28 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
+/*
+ * Check if one CPU is mapped to the specified hctx
+ *
+ * Isolated CPUs have been ruled out from hctx->cpumask, which is supposed
+ * to be used for scheduling kworker only. For other usage, please call this
+ * helper for checking if one CPU belongs to the specified hctx
+ */
+static bool blk_mq_cpu_mapped_to_hctx(unsigned int cpu,
+		const struct blk_mq_hw_ctx *hctx)
+{
+	struct blk_mq_hw_ctx *mapped_hctx = blk_mq_map_queue_type(hctx->queue,
+			hctx->type, cpu);
+
+	return mapped_hctx == hctx;
+}
+
 static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
 {
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
 
-	if (cpumask_test_cpu(cpu, hctx->cpumask))
+	if (blk_mq_cpu_mapped_to_hctx(cpu, hctx))
 		clear_bit(BLK_MQ_S_INACTIVE, &hctx->state);
 	return 0;
 }
@@ -3568,7 +3584,7 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	enum hctx_type type;
 
 	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
-	if (!cpumask_test_cpu(cpu, hctx->cpumask))
+	if (!blk_mq_cpu_mapped_to_hctx(cpu, hctx))
 		return 0;
 
 	ctx = __blk_mq_get_ctx(hctx->queue, cpu);

block/blk-throttle.c

@@ -39,11 +39,6 @@ struct latency_bucket {
 	int samples;
 };
 
-struct avg_latency_bucket {
-	unsigned long latency; /* ns / 1024 */
-	bool valid;
-};
-
 struct throtl_data
 {
 	/* service tree for active throtl groups */

block/t10-pi.c

@@ -495,5 +495,5 @@ const struct blk_integrity_profile ext_pi_type3_crc64 = {
 };
 EXPORT_SYMBOL_GPL(ext_pi_type3_crc64);
 
-MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("T10 Protection Information module");
 MODULE_LICENSE("GPL");

drivers/block/brd.c

@@ -222,13 +222,36 @@ static int brd_do_bvec(struct brd_device *brd, struct page *page,
 	return err;
 }
 
+static void brd_do_discard(struct brd_device *brd, sector_t sector, u32 size)
+{
+	sector_t aligned_sector = (sector + PAGE_SECTORS) & ~PAGE_SECTORS;
+	struct page *page;
+
+	size -= (aligned_sector - sector) * SECTOR_SIZE;
+	xa_lock(&brd->brd_pages);
+	while (size >= PAGE_SIZE && aligned_sector < rd_size * 2) {
+		page = __xa_erase(&brd->brd_pages, aligned_sector >> PAGE_SECTORS_SHIFT);
+		if (page)
+			__free_page(page);
+		aligned_sector += PAGE_SECTORS;
+		size -= PAGE_SIZE;
+	}
+	xa_unlock(&brd->brd_pages);
+}
+
 static void brd_submit_bio(struct bio *bio)
 {
 	struct brd_device *brd = bio->bi_bdev->bd_disk->private_data;
 	sector_t sector = bio->bi_iter.bi_sector;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 
+	if (unlikely(op_is_discard(bio->bi_opf))) {
+		brd_do_discard(brd, sector, bio->bi_iter.bi_size);
+		bio_endio(bio);
+		return;
+	}
+
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 		int err;
@@ -309,6 +332,9 @@ static int brd_alloc(int i)
 		 *  is harmless)
 		 */
 		.physical_block_size	= PAGE_SIZE,
+		.max_hw_discard_sectors	= UINT_MAX,
+		.max_discard_segments	= 1,
+		.discard_granularity	= PAGE_SIZE,
 	};
 
 	list_for_each_entry(brd, &brd_devices, brd_list)