17 files changed, 614 insertions, 155 deletions

diff --git a/block/Makefile b/block/Makefile
index 602f7f47b7b6..44df57e562bf 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -9,7 +9,7 @@ obj-y		:= bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \
-			disk-events.o
+			disk-events.o blk-ia-ranges.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o
diff --git a/block/bio.c b/block/bio.c
index 46a87c72d2b4..15ab0d6d1c06 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1046,36 +1046,27 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
 
-static void __bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 {
+	size_t size = iov_iter_count(iter);
+
 	WARN_ON_ONCE(bio->bi_max_vecs);
 
+	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+		size_t max_sectors = queue_max_zone_append_sectors(q);
+
+		size = min(size, max_sectors << SECTOR_SHIFT);
+	}
+
 	bio->bi_vcnt = iter->nr_segs;
 	bio->bi_io_vec = (struct bio_vec *)iter->bvec;
 	bio->bi_iter.bi_bvec_done = iter->iov_offset;
-	bio->bi_iter.bi_size = iter->count;
+	bio->bi_iter.bi_size = size;
 	bio_set_flag(bio, BIO_NO_PAGE_REF);
 	bio_set_flag(bio, BIO_CLONED);
 }
 
-static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
-{
-	__bio_iov_bvec_set(bio, iter);
-	iov_iter_advance(iter, iter->count);
-	return 0;
-}
-
-static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter)
-{
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	struct iov_iter i = *iter;
-
-	iov_iter_truncate(&i, queue_max_zone_append_sectors(q) << 9);
-	__bio_iov_bvec_set(bio, &i);
-	iov_iter_advance(iter, i.count);
-	return 0;
-}
-
 static void bio_put_pages(struct page **pages, size_t size, size_t off)
 {
 	size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE);
@@ -1217,9 +1208,9 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	int ret = 0;
 
 	if (iov_iter_is_bvec(iter)) {
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
-			return bio_iov_bvec_set_append(bio, iter);
-		return bio_iov_bvec_set(bio, iter);
+		bio_iov_bvec_set(bio, iter);
+		iov_iter_advance(iter, bio->bi_iter.bi_size);
+		return 0;
 	}
 
 	do {
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 8908298d6ad3..88b1fce90520 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -634,6 +634,14 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 
 	q = bdev_get_queue(bdev);
 
+	/*
+	 * blkcg_deactivate_policy() requires queue to be frozen, we can grab
+	 * q_usage_counter to prevent concurrent with blkcg_deactivate_policy().
+	 */
+	ret = blk_queue_enter(q, 0);
+	if (ret)
+		return ret;
+
 	rcu_read_lock();
 	spin_lock_irq(&q->queue_lock);
 
@@ -703,6 +711,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 			goto success;
 	}
 success:
+	blk_queue_exit(q);
 	ctx->bdev = bdev;
 	ctx->blkg = blkg;
 	ctx->body = input;
@@ -715,6 +724,7 @@ fail_unlock:
 	rcu_read_unlock();
 fail:
 	blkdev_put_no_open(bdev);
+	blk_queue_exit(q);
 	/*
 	 * If queue was bypassing, we should retry.  Do so after a
 	 * short msleep().  It isn't strictly necessary but queue
diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c
new file mode 100644
index 000000000000..c246c425d0d7
--- /dev/null
+++ b/block/blk-ia-ranges.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Block device concurrent positioning ranges.
+ *
+ *  Copyright (C) 2021 Western Digital Corporation or its Affiliates.
+ */
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+
+#include "blk.h"
+
+static ssize_t
+blk_ia_range_sector_show(struct blk_independent_access_range *iar,
+			 char *buf)
+{
+	return sprintf(buf, "%llu\n", iar->sector);
+}
+
+static ssize_t
+blk_ia_range_nr_sectors_show(struct blk_independent_access_range *iar,
+			     char *buf)
+{
+	return sprintf(buf, "%llu\n", iar->nr_sectors);
+}
+
+struct blk_ia_range_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct blk_independent_access_range *iar, char *buf);
+};
+
+static struct blk_ia_range_sysfs_entry blk_ia_range_sector_entry = {
+	.attr = { .name = "sector", .mode = 0444 },
+	.show = blk_ia_range_sector_show,
+};
+
+static struct blk_ia_range_sysfs_entry blk_ia_range_nr_sectors_entry = {
+	.attr = { .name = "nr_sectors", .mode = 0444 },
+	.show = blk_ia_range_nr_sectors_show,
+};
+
+static struct attribute *blk_ia_range_attrs[] = {
+	&blk_ia_range_sector_entry.attr,
+	&blk_ia_range_nr_sectors_entry.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(blk_ia_range);
+
+static ssize_t blk_ia_range_sysfs_show(struct kobject *kobj,
+				      struct attribute *attr, char *buf)
+{
+	struct blk_ia_range_sysfs_entry *entry =
+		container_of(attr, struct blk_ia_range_sysfs_entry, attr);
+	struct blk_independent_access_range *iar =
+		container_of(kobj, struct blk_independent_access_range, kobj);
+	ssize_t ret;
+
+	mutex_lock(&iar->queue->sysfs_lock);
+	ret = entry->show(iar, buf);
+	mutex_unlock(&iar->queue->sysfs_lock);
+
+	return ret;
+}
+
+static const struct sysfs_ops blk_ia_range_sysfs_ops = {
+	.show	= blk_ia_range_sysfs_show,
+};
+
+/*
+ * Independent access range entries are not freed individually, but alltogether
+ * with struct blk_independent_access_ranges and its array of ranges. Since
+ * kobject_add() takes a reference on the parent kobject contained in
+ * struct blk_independent_access_ranges, the array of independent access range
+ * entries cannot be freed until kobject_del() is called for all entries.
+ * So we do not need to do anything here, but still need this no-op release
+ * operation to avoid complaints from the kobject code.
+ */
+static void blk_ia_range_sysfs_nop_release(struct kobject *kobj)
+{
+}
+
+static struct kobj_type blk_ia_range_ktype = {
+	.sysfs_ops	= &blk_ia_range_sysfs_ops,
+	.default_groups	= blk_ia_range_groups,
+	.release	= blk_ia_range_sysfs_nop_release,
+};
+
+/*
+ * This will be executed only after all independent access range entries are
+ * removed with kobject_del(), at which point, it is safe to free everything,
+ * including the array of ranges.
+ */
+static void blk_ia_ranges_sysfs_release(struct kobject *kobj)
+{
+	struct blk_independent_access_ranges *iars =
+		container_of(kobj, struct blk_independent_access_ranges, kobj);
+
+	kfree(iars);
+}
+
+static struct kobj_type blk_ia_ranges_ktype = {
+	.release	= blk_ia_ranges_sysfs_release,
+};
+
+/**
+ * disk_register_ia_ranges - register with sysfs a set of independent
+ *			    access ranges
+ * @disk:	Target disk
+ * @new_iars:	New set of independent access ranges
+ *
+ * Register with sysfs a set of independent access ranges for @disk.
+ * If @new_iars is not NULL, this set of ranges is registered and the old set
+ * specified by q->ia_ranges is unregistered. Otherwise, q->ia_ranges is
+ * registered if it is not already.
+ */
+int disk_register_independent_access_ranges(struct gendisk *disk,
+				struct blk_independent_access_ranges *new_iars)
+{
+	struct request_queue *q = disk->queue;
+	struct blk_independent_access_ranges *iars;
+	int i, ret;
+
+	lockdep_assert_held(&q->sysfs_dir_lock);
+	lockdep_assert_held(&q->sysfs_lock);
+
+	/* If a new range set is specified, unregister the old one */
+	if (new_iars) {
+		if (q->ia_ranges)
+			disk_unregister_independent_access_ranges(disk);
+		q->ia_ranges = new_iars;
+	}
+
+	iars = q->ia_ranges;
+	if (!iars)
+		return 0;
+
+	/*
+	 * At this point, iars is the new set of sector access ranges that needs
+	 * to be registered with sysfs.
+	 */
+	WARN_ON(iars->sysfs_registered);
+	ret = kobject_init_and_add(&iars->kobj, &blk_ia_ranges_ktype,
+				   &q->kobj, "%s", "independent_access_ranges");
+	if (ret) {
+		q->ia_ranges = NULL;
+		kfree(iars);
+		return ret;
+	}
+
+	for (i = 0; i < iars->nr_ia_ranges; i++) {
+		iars->ia_range[i].queue = q;
+		ret = kobject_init_and_add(&iars->ia_range[i].kobj,
+					   &blk_ia_range_ktype, &iars->kobj,
+					   "%d", i);
+		if (ret) {
+			while (--i >= 0)
+				kobject_del(&iars->ia_range[i].kobj);
+			kobject_del(&iars->kobj);
+			kobject_put(&iars->kobj);
+			return ret;
+		}
+	}
+
+	iars->sysfs_registered = true;
+
+	return 0;
+}
+
+void disk_unregister_independent_access_ranges(struct gendisk *disk)
+{
+	struct request_queue *q = disk->queue;
+	struct blk_independent_access_ranges *iars = q->ia_ranges;
+	int i;
+
+	lockdep_assert_held(&q->sysfs_dir_lock);
+	lockdep_assert_held(&q->sysfs_lock);
+
+	if (!iars)
+		return;
+
+	if (iars->sysfs_registered) {
+		for (i = 0; i < iars->nr_ia_ranges; i++)
+			kobject_del(&iars->ia_range[i].kobj);
+		kobject_del(&iars->kobj);
+		kobject_put(&iars->kobj);
+	} else {
+		kfree(iars);
+	}
+
+	q->ia_ranges = NULL;
+}
+
+static struct blk_independent_access_range *
+disk_find_ia_range(struct blk_independent_access_ranges *iars,
+		  sector_t sector)
+{
+	struct blk_independent_access_range *iar;
+	int i;
+
+	for (i = 0; i < iars->nr_ia_ranges; i++) {
+		iar = &iars->ia_range[i];
+		if (sector >= iar->sector &&
+		    sector < iar->sector + iar->nr_sectors)
+			return iar;
+	}
+
+	return NULL;
+}
+
+static bool disk_check_ia_ranges(struct gendisk *disk,
+				struct blk_independent_access_ranges *iars)
+{
+	struct blk_independent_access_range *iar, *tmp;
+	sector_t capacity = get_capacity(disk);
+	sector_t sector = 0;
+	int i;
+
+	/*
+	 * While sorting the ranges in increasing LBA order, check that the
+	 * ranges do not overlap, that there are no sector holes and that all
+	 * sectors belong to one range.
+	 */
+	for (i = 0; i < iars->nr_ia_ranges; i++) {
+		tmp = disk_find_ia_range(iars, sector);
+		if (!tmp || tmp->sector != sector) {
+			pr_warn("Invalid non-contiguous independent access ranges\n");
+			return false;
+		}
+
+		iar = &iars->ia_range[i];
+		if (tmp != iar) {
+			swap(iar->sector, tmp->sector);
+			swap(iar->nr_sectors, tmp->nr_sectors);
+		}
+
+		sector += iar->nr_sectors;
+	}
+
+	if (sector != capacity) {
+		pr_warn("Independent access ranges do not match disk capacity\n");
+		return false;
+	}
+
+	return true;
+}
+
+static bool disk_ia_ranges_changed(struct gendisk *disk,
+				   struct blk_independent_access_ranges *new)
+{
+	struct blk_independent_access_ranges *old = disk->queue->ia_ranges;
+	int i;
+
+	if (!old)
+		return true;
+
+	if (old->nr_ia_ranges != new->nr_ia_ranges)
+		return true;
+
+	for (i = 0; i < old->nr_ia_ranges; i++) {
+		if (new->ia_range[i].sector != old->ia_range[i].sector ||
+		    new->ia_range[i].nr_sectors != old->ia_range[i].nr_sectors)
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * disk_alloc_independent_access_ranges - Allocate an independent access ranges
+ *                                        data structure
+ * @disk:		target disk
+ * @nr_ia_ranges:	Number of independent access ranges
+ *
+ * Allocate a struct blk_independent_access_ranges structure with @nr_ia_ranges
+ * access range descriptors.
+ */
+struct blk_independent_access_ranges *
+disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges)
+{
+	struct blk_independent_access_ranges *iars;
+
+	iars = kzalloc_node(struct_size(iars, ia_range, nr_ia_ranges),
+			    GFP_KERNEL, disk->queue->node);
+	if (iars)
+		iars->nr_ia_ranges = nr_ia_ranges;
+	return iars;
+}
+EXPORT_SYMBOL_GPL(disk_alloc_independent_access_ranges);
+
+/**
+ * disk_set_independent_access_ranges - Set a disk independent access ranges
+ * @disk:	target disk
+ * @iars:	independent access ranges structure
+ *
+ * Set the independent access ranges information of the request queue
+ * of @disk to @iars. If @iars is NULL and the independent access ranges
+ * structure already set is cleared. If there are no differences between
+ * @iars and the independent access ranges structure already set, @iars
+ * is freed.
+ */
+void disk_set_independent_access_ranges(struct gendisk *disk,
+				struct blk_independent_access_ranges *iars)
+{
+	struct request_queue *q = disk->queue;
+
+	if (WARN_ON_ONCE(iars && !iars->nr_ia_ranges)) {
+		kfree(iars);
+		iars = NULL;
+	}
+
+	mutex_lock(&q->sysfs_dir_lock);
+	mutex_lock(&q->sysfs_lock);
+
+	if (iars) {
+		if (!disk_check_ia_ranges(disk, iars)) {
+			kfree(iars);
+			iars = NULL;
+			goto reg;
+		}
+
+		if (!disk_ia_ranges_changed(disk, iars)) {
+			kfree(iars);
+			goto unlock;
+		}
+	}
+
+	/*
+	 * This may be called for a registered queue. E.g. during a device
+	 * revalidation. If that is the case, we need to unregister the old
+	 * set of independent access ranges and register the new set. If the
+	 * queue is not registered, registration of the device request queue
+	 * will register the independent access ranges, so only swap in the
+	 * new set and free the old one.
+	 */
+reg:
+	if (blk_queue_registered(q)) {
+		disk_register_independent_access_ranges(disk, iars);
+	} else {
+		swap(q->ia_ranges, iars);
+		kfree(iars);
+	}
+
+unlock:
+	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->sysfs_dir_lock);
+}
+EXPORT_SYMBOL_GPL(disk_set_independent_access_ranges);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index a317f05de466..f5076c173477 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -549,7 +549,7 @@ static int hctx_active_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
 
-	seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
+	seq_printf(m, "%d\n", __blk_mq_active_requests(hctx));
 	return 0;
 }
 
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 5b259fdea794..c62b966dfaba 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -541,7 +541,7 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int fla
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (hctx->sched_tags) {
-			if (!blk_mq_is_shared_tags(q->tag_set->flags))
+			if (!blk_mq_is_shared_tags(flags))
 				blk_mq_free_rq_map(hctx->sched_tags);
 			hctx->sched_tags = NULL;
 		}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d04ee72ba125..07eb1412760b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -316,40 +316,37 @@ void blk_mq_wake_waiters(struct request_queue *q)
 }
 
 static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
-		unsigned int tag, u64 alloc_time_ns)
+		struct blk_mq_tags *tags, unsigned int tag, u64 alloc_time_ns)
 {
 	struct blk_mq_ctx *ctx = data->ctx;
 	struct blk_mq_hw_ctx *hctx = data->hctx;
 	struct request_queue *q = data->q;
-	struct elevator_queue *e = q->elevator;
-	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 	struct request *rq = tags->static_rqs[tag];
-	unsigned int rq_flags = 0;
 
-	if (e) {
-		rq_flags = RQF_ELV;
-		rq->tag = BLK_MQ_NO_TAG;
-		rq->internal_tag = tag;
-	} else {
-		rq->tag = tag;
-		rq->internal_tag = BLK_MQ_NO_TAG;
-	}
+	rq->q = q;
+	rq->mq_ctx = ctx;
+	rq->mq_hctx = hctx;
+	rq->cmd_flags = data->cmd_flags;
 
 	if (data->flags & BLK_MQ_REQ_PM)
-		rq_flags |= RQF_PM;
+		data->rq_flags |= RQF_PM;
 	if (blk_queue_io_stat(q))
-		rq_flags |= RQF_IO_STAT;
-	rq->rq_flags = rq_flags;
+		data->rq_flags |= RQF_IO_STAT;
+	rq->rq_flags = data->rq_flags;
+
+	if (!(data->rq_flags & RQF_ELV)) {
+		rq->tag = tag;
+		rq->internal_tag = BLK_MQ_NO_TAG;
+	} else {
+		rq->tag = BLK_MQ_NO_TAG;
+		rq->internal_tag = tag;
+	}
+	rq->timeout = 0;
 
 	if (blk_mq_need_time_stamp(rq))
 		rq->start_time_ns = ktime_get_ns();
 	else
 		rq->start_time_ns = 0;
-	/* csd/requeue_work/fifo_time is initialized before use */
-	rq->q = q;
-	rq->mq_ctx = ctx;
-	rq->mq_hctx = hctx;
-	rq->cmd_flags = data->cmd_flags;
 	rq->rq_disk = NULL;
 	rq->part = NULL;
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
@@ -361,7 +358,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
 #endif
-	rq->timeout = 0;
 	rq->end_io = NULL;
 	rq->end_io_data = NULL;
 
@@ -396,20 +392,23 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
 		u64 alloc_time_ns)
 {
 	unsigned int tag, tag_offset;
+	struct blk_mq_tags *tags;
 	struct request *rq;
-	unsigned long tags;
+	unsigned long tag_mask;
 	int i, nr = 0;
 
-	tags = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
-	if (unlikely(!tags))
+	tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
+	if (unlikely(!tag_mask))
 		return NULL;
 
-	for (i = 0; tags; i++) {
-		if (!(tags & (1UL << i)))
+	tags = blk_mq_tags_from_data(data);
+	for (i = 0; tag_mask; i++) {
+		if (!(tag_mask & (1UL << i)))
 			continue;
+		prefetch(tags->static_rqs[tag]);
 		tag = tag_offset + i;
-		tags &= ~(1UL << i);
-		rq = blk_mq_rq_ctx_init(data, tag, alloc_time_ns);
+		tag_mask &= ~(1UL << i);
+		rq = blk_mq_rq_ctx_init(data, tags, tag, alloc_time_ns);
 		rq_list_add(data->cached_rq, rq);
 	}
 	data->nr_tags -= nr;
@@ -480,7 +479,8 @@ retry:
 		goto retry;
 	}
 
-	return blk_mq_rq_ctx_init(data, tag, alloc_time_ns);
+	return blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag,
+					alloc_time_ns);
 }
 
 struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
@@ -490,6 +490,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 		.q		= q,
 		.flags		= flags,
 		.cmd_flags	= op,
+		.rq_flags	= q->elevator ? RQF_ELV : 0,
 		.nr_tags	= 1,
 	};
 	struct request *rq;
@@ -519,6 +520,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 		.q		= q,
 		.flags		= flags,
 		.cmd_flags	= op,
+		.rq_flags	= q->elevator ? RQF_ELV : 0,
 		.nr_tags	= 1,
 	};
 	u64 alloc_time_ns = 0;
@@ -564,7 +566,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	tag = blk_mq_get_tag(&data);
 	if (tag == BLK_MQ_NO_TAG)
 		goto out_queue_exit;
-	return blk_mq_rq_ctx_init(&data, tag, alloc_time_ns);
+	return blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
+					alloc_time_ns);
 
 out_queue_exit:
 	blk_queue_exit(q);
@@ -640,7 +643,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		 * Partial zone append completions cannot be supported as the
 		 * BIO fragments may end up not being written sequentially.
 		 */
-		if (bio->bi_iter.bi_size == nbytes)
+		if (bio->bi_iter.bi_size != nbytes)
 			bio->bi_status = BLK_STS_IOERR;
 		else
 			bio->bi_iter.bi_sector = rq->__sector;
@@ -819,7 +822,7 @@ static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx,
 void blk_mq_end_request_batch(struct io_comp_batch *iob)
 {
 	int tags[TAG_COMP_BATCH], nr_tags = 0;
-	struct blk_mq_hw_ctx *last_hctx = NULL;
+	struct blk_mq_hw_ctx *cur_hctx = NULL;
 	struct request *rq;
 	u64 now = 0;
 
@@ -842,17 +845,17 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob)
 		blk_pm_mark_last_busy(rq);
 		rq_qos_done(rq->q, rq);
 
-		if (nr_tags == TAG_COMP_BATCH ||
-		    (last_hctx && last_hctx != rq->mq_hctx)) {
-			blk_mq_flush_tag_batch(last_hctx, tags, nr_tags);
+		if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) {
+			if (cur_hctx)
+				blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags);
 			nr_tags = 0;
+			cur_hctx = rq->mq_hctx;
 		}
 		tags[nr_tags++] = rq->tag;
-		last_hctx = rq->mq_hctx;
 	}
 
 	if (nr_tags)
-		blk_mq_flush_tag_batch(last_hctx, tags, nr_tags);
+		blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags);
 }
 EXPORT_SYMBOL_GPL(blk_mq_end_request_batch);
 
@@ -1593,6 +1596,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 	int errors, queued;
 	blk_status_t ret = BLK_STS_OK;
 	LIST_HEAD(zone_list);
+	bool needs_resource = false;
 
 	if (list_empty(list))
 		return false;
@@ -1638,6 +1642,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 			queued++;
 			break;
 		case BLK_STS_RESOURCE:
+			needs_resource = true;
+			fallthrough;
 		case BLK_STS_DEV_RESOURCE:
 			blk_mq_handle_dev_resource(rq, list);
 			goto out;
@@ -1648,6 +1654,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 			 * accept.
 			 */
 			blk_mq_handle_zone_resource(rq, &zone_list);
+			needs_resource = true;
 			break;
 		default:
 			errors++;
@@ -1672,7 +1679,6 @@ out:
 		/* For non-shared tags, the RESTART check will suffice */
 		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
 			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
-		bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
 
 		if (nr_budgets)
 			blk_mq_release_budgets(q, list);
@@ -1713,14 +1719,16 @@ out:
 		 * If driver returns BLK_STS_RESOURCE and SCHED_RESTART
 		 * bit is set, run queue after a delay to avoid IO stalls
 		 * that could otherwise occur if the queue is idle.  We'll do
-		 * similar if we couldn't get budget and SCHED_RESTART is set.
+		 * similar if we couldn't get budget or couldn't lock a zone
+		 * and SCHED_RESTART is set.
 		 */
 		needs_restart = blk_mq_sched_needs_restart(hctx);
+		if (prep == PREP_DISPATCH_NO_BUDGET)
+			needs_resource = true;
 		if (!needs_restart ||
 		    (no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
 			blk_mq_run_hw_queue(hctx, true);
-		else if (needs_restart && (ret == BLK_STS_RESOURCE ||
-					   no_budget_avail))
+		else if (needs_restart && needs_resource)
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
 
 		blk_mq_update_dispatch_busy(hctx, true);
@@ -2223,7 +2231,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		return;
 	plug->rq_count = 0;
 
-	if (!plug->multiple_queues && !plug->has_elevator) {
+	if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) {
 		blk_mq_plug_issue_direct(plug, from_schedule);
 		if (rq_list_empty(plug->mq_list))
 			return;
@@ -2512,6 +2520,7 @@ void blk_mq_submit_bio(struct bio *bio)
 			.q		= q,
 			.nr_tags	= 1,
 			.cmd_flags	= bio->bi_opf,
+			.rq_flags	= q->elevator ? RQF_ELV : 0,
 		};
 
 		if (plug) {
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 08fb5922e611..28859fc5faee 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -149,6 +149,7 @@ struct blk_mq_alloc_data {
 	blk_mq_req_flags_t flags;
 	unsigned int shallow_depth;
 	unsigned int cmd_flags;
+	unsigned int rq_flags;
 
 	/* allocate multiple requests/tags in one go */
 	unsigned int nr_tags;
@@ -166,10 +167,9 @@ static inline bool blk_mq_is_shared_tags(unsigned int flags)
 
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
-	if (data->q->elevator)
-		return data->hctx->sched_tags;
-
-	return data->hctx->tags;
+	if (!(data->rq_flags & RQF_ELV))
+		return data->hctx->tags;
+	return data->hctx->sched_tags;
 }
 
 static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
diff --git a/block/blk-settings.c b/block/blk-settings.c
index a7c857ad7d10..b880c70e22e4 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -842,6 +842,24 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
 
+static bool disk_has_partitions(struct gendisk *disk)
+{
+	unsigned long idx;
+	struct block_device *part;
+	bool ret = false;
+
+	rcu_read_lock();
+	xa_for_each(&disk->part_tbl, idx, part) {
+		if (bdev_is_partition(part)) {
+			ret = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /**
  * blk_queue_set_zoned - configure a disk queue zoned model.
  * @disk:	the gendisk of the queue to configure
@@ -876,7 +894,7 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
 		 * we do nothing special as far as the block layer is concerned.
 		 */
 		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
-		    !xa_empty(&disk->part_tbl))
+		    disk_has_partitions(disk))
 			model = BLK_ZONED_NONE;
 		break;
 	case BLK_ZONED_NONE:
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 36f14d658e81..cef1f713370b 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -873,16 +873,15 @@ int blk_register_queue(struct gendisk *disk)
 	}
 
 	mutex_lock(&q->sysfs_lock);
+
+	ret = disk_register_independent_access_ranges(disk, NULL);
+	if (ret)
+		goto put_dev;
+
 	if (q->elevator) {
 		ret = elv_register_queue(q, false);
-		if (ret) {
-			mutex_unlock(&q->sysfs_lock);
-			mutex_unlock(&q->sysfs_dir_lock);
-			kobject_del(&q->kobj);
-			blk_trace_remove_sysfs(dev);
-			kobject_put(&dev->kobj);
-			return ret;
-		}
+		if (ret)
+			goto put_dev;
 	}
 
 	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
@@ -914,6 +913,16 @@ unlock:
 	}
 
 	return ret;
+
+put_dev:
+	disk_unregister_independent_access_ranges(disk);
+	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->sysfs_dir_lock);
+	kobject_del(&q->kobj);
+	blk_trace_remove_sysfs(dev);
+	kobject_put(&dev->kobj);
+
+	return ret;
 }
 
 /**
@@ -958,6 +967,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	mutex_lock(&q->sysfs_lock);
 	if (q->elevator)
 		elv_unregister_queue(q);
+	disk_unregister_independent_access_ranges(disk);
 	mutex_unlock(&q->sysfs_lock);
 	mutex_unlock(&q->sysfs_dir_lock);
 
diff --git a/block/blk.h b/block/blk.h
index 6a039e6c7d07..7afffd548daf 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -454,4 +454,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 
 extern const struct address_space_operations def_blk_aops;
 
+int disk_register_independent_access_ranges(struct gendisk *disk,
+				struct blk_independent_access_ranges *new_iars);
+void disk_unregister_independent_access_ranges(struct gendisk *disk);
+
 #endif /* BLK_INTERNAL_H */
diff --git a/block/fops.c b/block/fops.c
index 396537598e3e..3777c7b76eae 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -124,9 +124,8 @@ out:
 }
 
 enum {
-	DIO_MULTI_BIO		= 1,
-	DIO_SHOULD_DIRTY	= 2,
-	DIO_IS_SYNC		= 4,
+	DIO_SHOULD_DIRTY	= 1,
+	DIO_IS_SYNC		= 2,
 };
 
 struct blkdev_dio {
@@ -150,7 +149,7 @@ static void blkdev_bio_end_io(struct bio *bio)
 	if (bio->bi_status && !dio->bio.bi_status)
 		dio->bio.bi_status = bio->bi_status;
 
-	if (!(dio->flags & DIO_MULTI_BIO) || atomic_dec_and_test(&dio->ref)) {
+	if (atomic_dec_and_test(&dio->ref)) {
 		if (!(dio->flags & DIO_IS_SYNC)) {
 			struct kiocb *iocb = dio->iocb;
 			ssize_t ret;
@@ -165,8 +164,7 @@ static void blkdev_bio_end_io(struct bio *bio)
 			}
 
 			dio->iocb->ki_complete(iocb, ret, 0);
-			if (dio->flags & DIO_MULTI_BIO)
-				bio_put(&dio->bio);
+			bio_put(&dio->bio);
 		} else {
 			struct task_struct *waiter = dio->waiter;
 
@@ -190,7 +188,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
-	bool do_poll = (iocb->ki_flags & IOCB_HIPRI);
 	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
 	loff_t pos = iocb->ki_pos;
 	int ret = 0;
@@ -202,11 +199,17 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
 
 	dio = container_of(bio, struct blkdev_dio, bio);
+	atomic_set(&dio->ref, 1);
+	/*
+	 * Grab an extra reference to ensure the dio structure which is embedded
+	 * into the first bio stays around.
+	 */
+	bio_get(bio);
+
 	is_sync = is_sync_kiocb(iocb);
 	if (is_sync) {
 		dio->flags = DIO_IS_SYNC;
 		dio->waiter = current;
-		bio_get(bio);
 	} else {
 		dio->flags = 0;
 		dio->iocb = iocb;
@@ -216,12 +219,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	if (is_read && iter_is_iovec(iter))
 		dio->flags |= DIO_SHOULD_DIRTY;
 
-	/*
-	 * Don't plug for HIPRI/polled IO, as those should go straight
-	 * to issue
-	 */
-	if (!(iocb->ki_flags & IOCB_HIPRI))
-		blk_start_plug(&plug);
+	blk_start_plug(&plug);
 
 	for (;;) {
 		bio_set_dev(bio, bdev);
@@ -254,34 +252,15 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 		nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
 		if (!nr_pages) {
-			if (do_poll)
-				bio_set_polled(bio, iocb);
 			submit_bio(bio);
-			if (do_poll)
-				WRITE_ONCE(iocb->private, bio);
 			break;
 		}
-		if (!(dio->flags & DIO_MULTI_BIO)) {
-			/*
-			 * AIO needs an extra reference to ensure the dio
-			 * structure which is embedded into the first bio
-			 * stays around.
-			 */
-			if (!is_sync)
-				bio_get(bio);
-			dio->flags |= DIO_MULTI_BIO;
-			atomic_set(&dio->ref, 2);
-			do_poll = false;
-		} else {
-			atomic_inc(&dio->ref);
-		}
-
+		atomic_inc(&dio->ref);
 		submit_bio(bio);
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 	}
 
-	if (!(iocb->ki_flags & IOCB_HIPRI))
-		blk_finish_plug(&plug);
+	blk_finish_plug(&plug);
 
 	if (!is_sync)
 		return -EIOCBQUEUED;
@@ -290,9 +269,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		if (!READ_ONCE(dio->waiter))
 			break;
-
-		if (!do_poll || !bio_poll(bio, NULL, 0))
-			blk_io_schedule();
+		blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
 
@@ -305,6 +282,94 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	return ret;
 }
 
+static void blkdev_bio_end_io_async(struct bio *bio)
+{
+	struct blkdev_dio *dio = container_of(bio, struct blkdev_dio, bio);
+	struct kiocb *iocb = dio->iocb;
+	ssize_t ret;
+
+	if (likely(!bio->bi_status)) {
+		ret = dio->size;
+		iocb->ki_pos += ret;
+	} else {
+		ret = blk_status_to_errno(bio->bi_status);
+	}
+
+	iocb->ki_complete(iocb, ret, 0);
+
+	if (dio->flags & DIO_SHOULD_DIRTY) {
+		bio_check_pages_dirty(bio);
+	} else {
+		bio_release_pages(bio, false);
+		bio_put(bio);
+	}
+}
+
+static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
+					struct iov_iter *iter,
+					unsigned int nr_pages)
+{
+	struct block_device *bdev = iocb->ki_filp->private_data;
+	struct blkdev_dio *dio;
+	struct bio *bio;
+	loff_t pos = iocb->ki_pos;
+	int ret = 0;
+
+	if ((pos | iov_iter_alignment(iter)) &
+	    (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
+	dio = container_of(bio, struct blkdev_dio, bio);
+	dio->flags = 0;
+	dio->iocb = iocb;
+	bio_set_dev(bio, bdev);
+	bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+	bio->bi_write_hint = iocb->ki_hint;
+	bio->bi_end_io = blkdev_bio_end_io_async;
+	bio->bi_ioprio = iocb->ki_ioprio;
+
+	if (iov_iter_is_bvec(iter)) {
+		/*
+		 * Users don't rely on the iterator being in any particular
+		 * state for async I/O returning -EIOCBQUEUED, hence we can
+		 * avoid expensive iov_iter_advance(). Bypass
+		 * bio_iov_iter_get_pages() and set the bvec directly.
+		 */
+		bio_iov_bvec_set(bio, iter);
+	} else {
+		ret = bio_iov_iter_get_pages(bio, iter);
+		if (unlikely(ret)) {
+			bio->bi_status = BLK_STS_IOERR;
+			bio_endio(bio);
+			return ret;
+		}
+	}
+	dio->size = bio->bi_iter.bi_size;
+
+	if (iov_iter_rw(iter) == READ) {
+		bio->bi_opf = REQ_OP_READ;
+		if (iter_is_iovec(iter)) {
+			dio->flags |= DIO_SHOULD_DIRTY;
+			bio_set_pages_dirty(bio);
+		}
+	} else {
+		bio->bi_opf = dio_bio_write_op(iocb);
+		task_io_account_write(bio->bi_iter.bi_size);
+	}
+
+	if (iocb->ki_flags & IOCB_HIPRI) {
+		bio->bi_opf |= REQ_POLLED | REQ_NOWAIT;
+		submit_bio(bio);
+		WRITE_ONCE(iocb->private, bio);
+	} else {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			bio->bi_opf |= REQ_NOWAIT;
+		submit_bio(bio);
+	}
+	return -EIOCBQUEUED;
+}
+
 static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	unsigned int nr_pages;
@@ -313,9 +378,11 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		return 0;
 
 	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
-	if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
-		return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
-
+	if (likely(nr_pages <= BIO_MAX_VECS)) {
+		if (is_sync_kiocb(iocb))
+			return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
+		return __blkdev_direct_IO_async(iocb, iter, nr_pages);
+	}
 	return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
 }
 
@@ -538,7 +605,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 		return -EOPNOTSUPP;
 
 	/* Don't go off the end of the device. */
-	isize = i_size_read(bdev->bd_inode);
+	isize = bdev_nr_bytes(bdev);
 	if (start >= isize)
 		return -EINVAL;
 	if (end >= isize) {
diff --git a/block/genhd.c b/block/genhd.c
index 64f83c4aee99..febaaa55125a 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -58,6 +58,7 @@ void set_capacity(struct gendisk *disk, sector_t sectors)
 
 	spin_lock(&bdev->bd_size_lock);
 	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	bdev->bd_nr_sectors = sectors;
 	spin_unlock(&bdev->bd_size_lock);
 }
 EXPORT_SYMBOL(set_capacity);
@@ -589,16 +590,6 @@ void del_gendisk(struct gendisk *disk)
 	 * Prevent new I/O from crossing bio_queue_enter().
 	 */
 	blk_queue_start_drain(q);
-	blk_mq_freeze_queue_wait(q);
-
-	rq_qos_exit(q);
-	blk_sync_queue(q);
-	blk_flush_integrity();
-	/*
-	 * Allow using passthrough request again after the queue is torn down.
-	 */
-	blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
-	__blk_mq_unfreeze_queue(q, true);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -621,6 +612,18 @@ void del_gendisk(struct gendisk *disk)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
+
+	blk_mq_freeze_queue_wait(q);
+
+	rq_qos_exit(q);
+	blk_sync_queue(q);
+	blk_flush_integrity();
+	/*
+	 * Allow using passthrough request again after the queue is torn down.
+	 */
+	blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+	__blk_mq_unfreeze_queue(q, true);
+
 }
 EXPORT_SYMBOL(del_gendisk);
 
diff --git a/block/ioctl.c b/block/ioctl.c
index 77b1b2453f39..d6af0ac97e57 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -132,7 +132,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	if (len & 511)
 		return -EINVAL;
 
-	if (start + len > i_size_read(bdev->bd_inode))
+	if (start + len > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
@@ -164,7 +164,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		return -EINVAL;
 	if (len & 511)
 		return -EINVAL;
-	if (end >= (uint64_t)i_size_read(bdev->bd_inode))
+	if (end >= (uint64_t)bdev_nr_bytes(bdev))
 		return -EINVAL;
 	if (end < start)
 		return -EINVAL;
@@ -543,7 +543,6 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	void __user *argp = (void __user *)arg;
 	fmode_t mode = file->f_mode;
-	loff_t size;
 	int ret;
 
 	/*
@@ -570,10 +569,9 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		return put_long(argp,
 			(bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512);
 	case BLKGETSIZE:
-		size = i_size_read(bdev->bd_inode);
-		if ((size >> 9) > ~0UL)
+		if (bdev_nr_sectors(bdev) > ~0UL)
 			return -EFBIG;
-		return put_ulong(argp, size >> 9);
+		return put_ulong(argp, bdev_nr_sectors(bdev));
 
 	/* The data is compatible, but the command number is different */
 	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
@@ -581,7 +579,7 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKBSZSET:
 		return blkdev_bszset(bdev, mode, argp);
 	case BLKGETSIZE64:
-		return put_u64(argp, i_size_read(bdev->bd_inode));
+		return put_u64(argp, bdev_nr_bytes(bdev));
 
 	/* Incompatible alignment on i386 */
 	case BLKTRACESETUP:
@@ -615,7 +613,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	struct gendisk *disk = bdev->bd_disk;
 	fmode_t mode = file->f_mode;
-	loff_t size;
 
 	/*
 	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
@@ -641,10 +638,9 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		return compat_put_long(argp,
 			(bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512);
 	case BLKGETSIZE:
-		size = i_size_read(bdev->bd_inode);
-		if ((size >> 9) > ~0UL)
+		if (bdev_nr_sectors(bdev) > ~0UL)
 			return -EFBIG;
-		return compat_put_ulong(argp, size >> 9);
+		return compat_put_ulong(argp, bdev_nr_sectors(bdev));
 
 	/* The data is compatible, but the command number is different */
 	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
@@ -652,7 +648,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKBSZSET_32:
 		return blkdev_bszset(bdev, mode, argp);
 	case BLKGETSIZE64_32:
-		return put_u64(argp, i_size_read(bdev->bd_inode));
+		return put_u64(argp, bdev_nr_bytes(bdev));
 
 	/* Incompatible alignment on i386 */
 	case BLKTRACESETUP32:
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 9dbddc355b40..334b72ef1d73 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -91,6 +91,7 @@ static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
 	spin_lock(&bdev->bd_size_lock);
 	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	bdev->bd_nr_sectors = sectors;
 	spin_unlock(&bdev->bd_size_lock);
 }
 
@@ -424,6 +425,7 @@ out_del:
 	device_del(pdev);
 out_put:
 	put_device(pdev);
+	return ERR_PTR(err);
 out_put_disk:
 	put_disk(disk);
 	return ERR_PTR(err);
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index 7ca5c4c374d4..5e9be13a56a8 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -133,7 +133,7 @@ efi_crc32(const void *buf, unsigned long len)
  */
 static u64 last_lba(struct gendisk *disk)
 {
-	return div_u64(disk->part0->bd_inode->i_size,
+	return div_u64(bdev_nr_bytes(disk->part0),
 		       queue_logical_block_size(disk->queue)) - 1ULL;
 }
 
diff --git a/block/partitions/ibm.c b/block/partitions/ibm.c
index 9bca396aef4a..403756dbd50d 100644
--- a/block/partitions/ibm.c
+++ b/block/partitions/ibm.c
@@ -198,7 +198,7 @@ static int find_lnx1_partitions(struct parsed_partitions *state,
 				char name[],
 				union label_t *label,
 				sector_t labelsect,
-				loff_t i_size,
+				sector_t nr_sectors,
 				dasd_information2_t *info)
 {
 	loff_t offset, geo_size, size;
@@ -213,14 +213,14 @@ static int find_lnx1_partitions(struct parsed_partitions *state,
 	} else {
 		/*
 		 * Formated w/o large volume support. If the sanity check
-		 * 'size based on geo == size based on i_size' is true, then
+		 * 'size based on geo == size based on nr_sectors' is true, then
 		 * we can safely assume that we know the formatted size of
 		 * the disk, otherwise we need additional information
 		 * that we can only get from a real DASD device.
 		 */
 		geo_size = geo->cylinders * geo->heads
 			* geo->sectors * secperblk;
-		size = i_size >> 9;
+		size = nr_sectors;
 		if (size != geo_size) {
 			if (!info) {
 				strlcat(state->pp_buf, "\n", PAGE_SIZE);
@@ -229,7 +229,7 @@ static int find_lnx1_partitions(struct parsed_partitions *state,
 			if (!strcmp(info->type, "ECKD"))
 				if (geo_size < size)
 					size = geo_size;
-			/* else keep size based on i_size */
+			/* else keep size based on nr_sectors */
 		}
 	}
 	/* first and only partition starts in the first block after the label */
@@ -293,7 +293,8 @@ int ibm_partition(struct parsed_partitions *state)
 	struct gendisk *disk = state->disk;
 	struct block_device *bdev = disk->part0;
 	int blocksize, res;
-	loff_t i_size, offset, size;
+	loff_t offset, size;
+	sector_t nr_sectors;
 	dasd_information2_t *info;
 	struct hd_geometry *geo;
 	char type[5] = {0,};
@@ -308,8 +309,8 @@ int ibm_partition(struct parsed_partitions *state)
 	blocksize = bdev_logical_block_size(bdev);
 	if (blocksize <= 0)
 		goto out_symbol;
-	i_size = i_size_read(bdev->bd_inode);
-	if (i_size == 0)
+	nr_sectors = bdev_nr_sectors(bdev);
+	if (nr_sectors == 0)
 		goto out_symbol;
 	info = kmalloc(sizeof(dasd_information2_t), GFP_KERNEL);
 	if (info == NULL)
@@ -336,7 +337,7 @@ int ibm_partition(struct parsed_partitions *state)
 						   label);
 		} else if (!strncmp(type, "LNX1", 4)) {
 			res = find_lnx1_partitions(state, geo, blocksize, name,
-						   label, labelsect, i_size,
+						   label, labelsect, nr_sectors,
 						   info);
 		} else if (!strncmp(type, "CMS1", 4)) {
 			res = find_cms1_partitions(state, geo, blocksize, name,
@@ -353,7 +354,7 @@ int ibm_partition(struct parsed_partitions *state)
 		res = 1;
 		if (info->format == DASD_FORMAT_LDL) {
 			strlcat(state->pp_buf, "(nonl)", PAGE_SIZE);
-			size = i_size >> 9;
+			size = nr_sectors;
 			offset = (info->label_block + 1) * (blocksize >> 9);
 			put_partition(state, 1, offset, size-offset);
 			strlcat(state->pp_buf, "\n", PAGE_SIZE);