Merge tag 'for-5.8/block-2020-06-01' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Core block changes that have been queued up for this release:

   - Remove dead blk-throttle and blk-wbt code (Guoqing)

   - Include pid in blktrace note traces (Jan)

   - Don't spew I/O errors on wouldblock termination (me)

   - Zone append addition (Johannes, Keith, Damien)

   - IO accounting improvements (Konstantin, Christoph)

   - blk-mq hardware map update improvements (Ming)

   - Scheduler dispatch improvement (Salman)

   - Inline block encryption support (Satya)

   - Request map fixes and improvements (Weiping)

   - blk-iocost tweaks (Tejun)

   - Fix for timeout failing with error injection (Keith)

   - Queue re-run fixes (Douglas)

   - CPU hotplug improvements (Christoph)

   - Queue entry/exit improvements (Christoph)

   - Move DMA drain handling to the few drivers that use it (Christoph)

   - Partition handling cleanups (Christoph)"

* tag 'for-5.8/block-2020-06-01' of git://git.kernel.dk/linux-block: (127 commits)
  block: mark bio_wouldblock_error() bio with BIO_QUIET
  blk-wbt: rename __wbt_update_limits to wbt_update_limits
  blk-wbt: remove wbt_update_limits
  blk-throttle: remove tg_drain_bios
  blk-throttle: remove blk_throtl_drain
  null_blk: force complete for timeout request
  blk-mq: drain I/O when all CPUs in a hctx are offline
  blk-mq: add blk_mq_all_tag_iter
  blk-mq: open code __blk_mq_alloc_request in blk_mq_alloc_request_hctx
  blk-mq: use BLK_MQ_NO_TAG in more places
  blk-mq: rename BLK_MQ_TAG_FAIL to BLK_MQ_NO_TAG
  blk-mq: move more request initialization to blk_mq_rq_ctx_init
  blk-mq: simplify the blk_mq_get_request calling convention
  blk-mq: remove the bio argument to ->prepare_request
  nvme: force complete cancelled requests
  blk-mq: blk-mq: provide forced completion method
  block: fix a warning when blkdev.h is included for !CONFIG_BLOCK builds
  block: blk-crypto-fallback: remove redundant initialization of variable err
  block: reduce part_stat_lock() scope
  block: use __this_cpu_add() instead of access by smp_processor_id()
  ...

36 files changed, 2879 insertions, 859 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 3bc76bb113a0..9382a4acefc3 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -146,6 +146,7 @@ config BLK_CGROUP_IOLATENCY
 config BLK_CGROUP_IOCOST
 	bool "Enable support for cost model based cgroup IO controller"
 	depends on BLK_CGROUP=y
+	select BLK_RQ_IO_DATA_LEN
 	select BLK_RQ_ALLOC_TIME
 	---help---
 	Enabling this option enables the .weight interface for cost
@@ -185,6 +186,23 @@ config BLK_SED_OPAL
 	Enabling this option enables users to setup/unlock/lock
 	Locking ranges for SED devices using the Opal protocol.
 
+config BLK_INLINE_ENCRYPTION
+	bool "Enable inline encryption support in block layer"
+	help
+	  Build the blk-crypto subsystem. Enabling this lets the
+	  block layer handle encryption, so users can take
+	  advantage of inline encryption hardware if present.
+
+config BLK_INLINE_ENCRYPTION_FALLBACK
+	bool "Enable crypto API fallback for blk-crypto"
+	depends on BLK_INLINE_ENCRYPTION
+	select CRYPTO
+	select CRYPTO_SKCIPHER
+	help
+	  Enabling this lets the block layer handle inline encryption
+	  by falling back to the kernel crypto API when inline
+	  encryption hardware is not present.
+
 menu "Partition Types"
 
 source "block/partitions/Kconfig"
diff --git a/block/Makefile b/block/Makefile
index 206b96e9387f..78719169fb2a 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -36,3 +36,5 @@ obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
 obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
 obj-$(CONFIG_BLK_PM)		+= blk-pm.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= keyslot-manager.o blk-crypto.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK)	+= blk-crypto-fallback.o
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 3d411716d7ee..50c8f034c01c 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6073,7 +6073,7 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
  * comments on bfq_init_rq for the reason behind this delayed
  * preparation.
  */
-static void bfq_prepare_request(struct request *rq, struct bio *bio)
+static void bfq_prepare_request(struct request *rq)
 {
 	/*
 	 * Regardless of whether we have an icq attached, we have to
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index bf62c25cde8f..3579ac0f6ec1 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -42,6 +42,9 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	struct bio_set *bs = bio->bi_pool;
 	unsigned inline_vecs;
 
+	if (WARN_ON_ONCE(bio_has_crypt_ctx(bio)))
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) {
 		bip = kmalloc(struct_size(bip, bip_inline_vecs, nr_vecs), gfp_mask);
 		inline_vecs = nr_vecs;
diff --git a/block/bio.c b/block/bio.c
index 21cbaa6a1c20..5235da6434aa 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -18,6 +18,7 @@
 #include <linux/blk-cgroup.h>
 #include <linux/highmem.h>
 #include <linux/sched/sysctl.h>
+#include <linux/blk-crypto.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
@@ -237,6 +238,8 @@ void bio_uninit(struct bio *bio)
 
 	if (bio_integrity(bio))
 		bio_integrity_free(bio);
+
+	bio_crypt_free_ctx(bio);
 }
 EXPORT_SYMBOL(bio_uninit);
 
@@ -708,6 +711,8 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 
 	__bio_clone_fast(b, bio);
 
+	bio_crypt_clone(b, bio, gfp_mask);
+
 	if (bio_integrity(bio)) {
 		int ret;
 
@@ -748,9 +753,14 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 	return true;
 }
 
-static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
-		struct page *page, unsigned len, unsigned offset,
-		bool *same_page)
+/*
+ * Try to merge a page into a segment, while obeying the hardware segment
+ * size limit.  This is not for normal read/write bios, but for passthrough
+ * or Zone Append operations that we can't split.
+ */
+static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
+				 struct page *page, unsigned len,
+				 unsigned offset, bool *same_page)
 {
 	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 	unsigned long mask = queue_segment_boundary(q);
@@ -765,38 +775,32 @@ static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
 }
 
 /**
- *	__bio_add_pc_page	- attempt to add page to passthrough bio
- *	@q: the target queue
- *	@bio: destination bio
- *	@page: page to add
- *	@len: vec entry length
- *	@offset: vec entry offset
- *	@same_page: return if the merge happen inside the same page
- *
- *	Attempt to add a page to the bio_vec maplist. This can fail for a
- *	number of reasons, such as the bio being full or target block device
- *	limitations. The target block device must allow bio's up to PAGE_SIZE,
- *	so it is always possible to add a single page to an empty bio.
+ * bio_add_hw_page - attempt to add a page to a bio with hw constraints
+ * @q: the target queue
+ * @bio: destination bio
+ * @page: page to add
+ * @len: vec entry length
+ * @offset: vec entry offset
+ * @max_sectors: maximum number of sectors that can be added
+ * @same_page: return if the segment has been merged inside the same page
  *
- *	This should only be used by passthrough bios.
+ * Add a page to a bio while respecting the hardware max_sectors, max_segment
+ * and gap limitations.
  */
-int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
+int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
-		bool *same_page)
+		unsigned int max_sectors, bool *same_page)
 {
 	struct bio_vec *bvec;
 
-	/*
-	 * cloned bio must not modify vec list
-	 */
-	if (unlikely(bio_flagged(bio, BIO_CLONED)))
+	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return 0;
 
-	if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q))
+	if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
 		return 0;
 
 	if (bio->bi_vcnt > 0) {
-		if (bio_try_merge_pc_page(q, bio, page, len, offset, same_page))
+		if (bio_try_merge_hw_seg(q, bio, page, len, offset, same_page))
 			return len;
 
 		/*
@@ -823,11 +827,27 @@ int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 	return len;
 }
 
+/**
+ * bio_add_pc_page	- attempt to add page to passthrough bio
+ * @q: the target queue
+ * @bio: destination bio
+ * @page: page to add
+ * @len: vec entry length
+ * @offset: vec entry offset
+ *
+ * Attempt to add a page to the bio_vec maplist. This can fail for a
+ * number of reasons, such as the bio being full or target block device
+ * limitations. The target block device must allow bio's up to PAGE_SIZE,
+ * so it is always possible to add a single page to an empty bio.
+ *
+ * This should only be used by passthrough bios.
+ */
 int bio_add_pc_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset)
 {
 	bool same_page = false;
-	return __bio_add_pc_page(q, bio, page, len, offset, &same_page);
+	return bio_add_hw_page(q, bio, page, len, offset,
+			queue_max_hw_sectors(q), &same_page);
 }
 EXPORT_SYMBOL(bio_add_pc_page);
 
@@ -936,6 +956,7 @@ void bio_release_pages(struct bio *bio, bool mark_dirty)
 		put_page(bvec->bv_page);
 	}
 }
+EXPORT_SYMBOL_GPL(bio_release_pages);
 
 static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
 {
@@ -1010,6 +1031,50 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	return 0;
 }
 
+static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
+	struct request_queue *q = bio->bi_disk->queue;
+	unsigned int max_append_sectors = queue_max_zone_append_sectors(q);
+	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
+	struct page **pages = (struct page **)bv;
+	ssize_t size, left;
+	unsigned len, i;
+	size_t offset;
+
+	if (WARN_ON_ONCE(!max_append_sectors))
+		return 0;
+
+	/*
+	 * Move page array up in the allocated memory for the bio vecs as far as
+	 * possible so that we can start filling biovecs from the beginning
+	 * without overwriting the temporary page array.
+	 */
+	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
+	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
+
+	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+	if (unlikely(size <= 0))
+		return size ? size : -EFAULT;
+
+	for (left = size, i = 0; left > 0; left -= len, i++) {
+		struct page *page = pages[i];
+		bool same_page = false;
+
+		len = min_t(size_t, PAGE_SIZE - offset, left);
+		if (bio_add_hw_page(q, bio, page, len, offset,
+				max_append_sectors, &same_page) != len)
+			return -EINVAL;
+		if (same_page)
+			put_page(page);
+		offset = 0;
+	}
+
+	iov_iter_advance(iter, size);
+	return 0;
+}
+
 /**
  * bio_iov_iter_get_pages - add user or kernel pages to a bio
  * @bio: bio to add pages to
@@ -1039,16 +1104,23 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		return -EINVAL;
 
 	do {
-		if (is_bvec)
-			ret = __bio_iov_bvec_add_pages(bio, iter);
-		else
-			ret = __bio_iov_iter_get_pages(bio, iter);
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+			if (WARN_ON_ONCE(is_bvec))
+				return -EINVAL;
+			ret = __bio_iov_append_get_pages(bio, iter);
+		} else {
+			if (is_bvec)
+				ret = __bio_iov_bvec_add_pages(bio, iter);
+			else
+				ret = __bio_iov_iter_get_pages(bio, iter);
+		}
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
 
 	if (is_bvec)
 		bio_set_flag(bio, BIO_NO_PAGE_REF);
 	return bio->bi_vcnt ? 0 : ret;
 }
+EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
 {
@@ -1105,6 +1177,7 @@ void bio_advance(struct bio *bio, unsigned bytes)
 	if (bio_integrity(bio))
 		bio_integrity_advance(bio, bytes);
 
+	bio_crypt_advance(bio, bytes);
 	bio_advance_iter(bio, &bio->bi_iter, bytes);
 }
 EXPORT_SYMBOL(bio_advance);
@@ -1303,55 +1376,6 @@ defer:
 	schedule_work(&bio_dirty_work);
 }
 
-void update_io_ticks(struct hd_struct *part, unsigned long now, bool end)
-{
-	unsigned long stamp;
-again:
-	stamp = READ_ONCE(part->stamp);
-	if (unlikely(stamp != now)) {
-		if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) {
-			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
-		}
-	}
-	if (part->partno) {
-		part = &part_to_disk(part)->part0;
-		goto again;
-	}
-}
-
-void generic_start_io_acct(struct request_queue *q, int op,
-			   unsigned long sectors, struct hd_struct *part)
-{
-	const int sgrp = op_stat_group(op);
-
-	part_stat_lock();
-
-	update_io_ticks(part, jiffies, false);
-	part_stat_inc(part, ios[sgrp]);
-	part_stat_add(part, sectors[sgrp], sectors);
-	part_inc_in_flight(q, part, op_is_write(op));
-
-	part_stat_unlock();
-}
-EXPORT_SYMBOL(generic_start_io_acct);
-
-void generic_end_io_acct(struct request_queue *q, int req_op,
-			 struct hd_struct *part, unsigned long start_time)
-{
-	unsigned long now = jiffies;
-	unsigned long duration = now - start_time;
-	const int sgrp = op_stat_group(req_op);
-
-	part_stat_lock();
-
-	update_io_ticks(part, now, true);
-	part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration));
-	part_dec_in_flight(q, part, op_is_write(req_op));
-
-	part_stat_unlock();
-}
-EXPORT_SYMBOL(generic_end_io_acct);
-
 static inline bool bio_remaining_done(struct bio *bio)
 {
 	/*
@@ -1445,6 +1469,10 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	BUG_ON(sectors <= 0);
 	BUG_ON(sectors >= bio_sectors(bio));
 
+	/* Zone append commands cannot be split */
+	if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
+		return NULL;
+
 	split = bio_clone_fast(bio, gfp, bs);
 	if (!split)
 		return NULL;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 930212c1a512..0ecc897b225c 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1530,6 +1530,10 @@ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
 {
 	u64 old = atomic64_read(&blkg->delay_start);
 
+	/* negative use_delay means no scaling, see blkcg_set_delay() */
+	if (atomic_read(&blkg->use_delay) < 0)
+		return;
+
 	/*
 	 * We only want to scale down every second.  The idea here is that we
 	 * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain
@@ -1717,6 +1721,8 @@ void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay)
  */
 void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
 {
+	if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
+		return;
 	blkcg_scale_delay(blkg, now);
 	atomic64_add(delta, &blkg->delay_nsec);
 }
diff --git a/block/blk-core.c b/block/blk-core.c
index 38d7b1f16067..03252af8c82c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -39,6 +39,8 @@
 #include <linux/debugfs.h>
 #include <linux/bpf.h>
 #include <linux/psi.h>
+#include <linux/sched/sysctl.h>
+#include <linux/blk-crypto.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -121,6 +123,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
 	refcount_set(&rq->ref, 1);
+	blk_crypto_rq_set_defaults(rq);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -136,6 +139,7 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(ZONE_OPEN),
 	REQ_OP_NAME(ZONE_CLOSE),
 	REQ_OP_NAME(ZONE_FINISH),
+	REQ_OP_NAME(ZONE_APPEND),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(SCSI_IN),
@@ -241,6 +245,17 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 
 	bio_advance(bio, nbytes);
 
+	if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) {
+		/*
+		 * Partial zone append completions cannot be supported as the
+		 * BIO fragments may end up not being written sequentially.
+		 */
+		if (bio->bi_iter.bi_size)
+			bio->bi_status = BLK_STS_IOERR;
+		else
+			bio->bi_iter.bi_sector = rq->__sector;
+	}
+
 	/* don't actually finish bio if it's part of flush sequence */
 	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
 		bio_endio(bio);
@@ -441,6 +456,23 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 	}
 }
 
+static inline int bio_queue_enter(struct bio *bio)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+	bool nowait = bio->bi_opf & REQ_NOWAIT;
+	int ret;
+
+	ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0);
+	if (unlikely(ret)) {
+		if (nowait && !blk_queue_dying(q))
+			bio_wouldblock_error(bio);
+		else
+			bio_io_error(bio);
+	}
+
+	return ret;
+}
+
 void blk_queue_exit(struct request_queue *q)
 {
 	percpu_ref_put(&q->q_usage_counter);
@@ -485,7 +517,7 @@ struct request_queue *__blk_alloc_queue(int node_id)
 	if (ret)
 		goto fail_id;
 
-	q->backing_dev_info = bdi_alloc_node(GFP_KERNEL, node_id);
+	q->backing_dev_info = bdi_alloc(node_id);
 	if (!q->backing_dev_info)
 		goto fail_split;
 
@@ -495,7 +527,6 @@ struct request_queue *__blk_alloc_queue(int node_id)
 
 	q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES;
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
-	q->backing_dev_info->name = "block";
 	q->node = node_id;
 
 	timer_setup(&q->backing_dev_info->laptop_mode_wb_timer,
@@ -606,6 +637,16 @@ void blk_put_request(struct request *req)
 }
 EXPORT_SYMBOL(blk_put_request);
 
+static void blk_account_io_merge_bio(struct request *req)
+{
+	if (!blk_do_io_stat(req))
+		return;
+
+	part_stat_lock();
+	part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+	part_stat_unlock();
+}
+
 bool bio_attempt_back_merge(struct request *req, struct bio *bio,
 		unsigned int nr_segs)
 {
@@ -624,7 +665,9 @@ bool bio_attempt_back_merge(struct request *req, struct bio *bio,
 	req->biotail = bio;
 	req->__data_len += bio->bi_iter.bi_size;
 
-	blk_account_io_start(req, false);
+	bio_crypt_free_ctx(bio);
+
+	blk_account_io_merge_bio(req);
 	return true;
 }
 
@@ -648,7 +691,9 @@ bool bio_attempt_front_merge(struct request *req, struct bio *bio,
 	req->__sector = bio->bi_iter.bi_sector;
 	req->__data_len += bio->bi_iter.bi_size;
 
-	blk_account_io_start(req, false);
+	bio_crypt_do_front_merge(req, bio);
+
+	blk_account_io_merge_bio(req);
 	return true;
 }
 
@@ -670,7 +715,7 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
 	req->__data_len += bio->bi_iter.bi_size;
 	req->nr_phys_segments = segments + 1;
 
-	blk_account_io_start(req, false);
+	blk_account_io_merge_bio(req);
 	return true;
 no_merge:
 	req_set_nomerge(q, req);
@@ -872,6 +917,41 @@ out:
 	return ret;
 }
 
+/*
+ * Check write append to a zoned block device.
+ */
+static inline blk_status_t blk_check_zone_append(struct request_queue *q,
+						 struct bio *bio)
+{
+	sector_t pos = bio->bi_iter.bi_sector;
+	int nr_sectors = bio_sectors(bio);
+
+	/* Only applicable to zoned block devices */
+	if (!blk_queue_is_zoned(q))
+		return BLK_STS_NOTSUPP;
+
+	/* The bio sector must point to the start of a sequential zone */
+	if (pos & (blk_queue_zone_sectors(q) - 1) ||
+	    !blk_queue_zone_is_seq(q, pos))
+		return BLK_STS_IOERR;
+
+	/*
+	 * Not allowed to cross zone boundaries. Otherwise, the BIO will be
+	 * split and could result in non-contiguous sectors being written in
+	 * different zones.
+	 */
+	if (nr_sectors > q->limits.chunk_sectors)
+		return BLK_STS_IOERR;
+
+	/* Make sure the BIO is small enough and will not get split */
+	if (nr_sectors > q->limits.max_zone_append_sectors)
+		return BLK_STS_IOERR;
+
+	bio->bi_opf |= REQ_NOMERGE;
+
+	return BLK_STS_OK;
+}
+
 static noinline_for_stack bool
 generic_make_request_checks(struct bio *bio)
 {
@@ -941,6 +1021,11 @@ generic_make_request_checks(struct bio *bio)
 		if (!q->limits.max_write_same_sectors)
 			goto not_supported;
 		break;
+	case REQ_OP_ZONE_APPEND:
+		status = blk_check_zone_append(q, bio);
+		if (status != BLK_STS_OK)
+			goto end_io;
+		break;
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
@@ -961,12 +1046,13 @@ generic_make_request_checks(struct bio *bio)
 	}
 
 	/*
-	 * Various block parts want %current->io_context and lazy ioc
-	 * allocation ends up trading a lot of pain for a small amount of
-	 * memory.  Just allocate it upfront.  This may fail and block
-	 * layer knows how to live with it.
+	 * Various block parts want %current->io_context, so allocate it up
+	 * front rather than dealing with lots of pain to allocate it only
+	 * where needed. This may fail and the block layer knows how to live
+	 * with it.
 	 */
-	create_io_context(GFP_ATOMIC, q->node);
+	if (unlikely(!current->io_context))
+		create_task_io_context(current, GFP_ATOMIC, q->node);
 
 	if (!blkcg_bio_issue_check(q, bio))
 		return false;
@@ -988,29 +1074,28 @@ end_io:
 	return false;
 }
 
+static blk_qc_t do_make_request(struct bio *bio)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+	blk_qc_t ret = BLK_QC_T_NONE;
+
+	if (blk_crypto_bio_prep(&bio)) {
+		if (!q->make_request_fn)
+			return blk_mq_make_request(q, bio);
+		ret = q->make_request_fn(q, bio);
+	}
+	blk_queue_exit(q);
+	return ret;
+}
+
 /**
- * generic_make_request - hand a buffer to its device driver for I/O
+ * generic_make_request - re-submit a bio to the block device layer for I/O
  * @bio:  The bio describing the location in memory and on the device.
  *
- * generic_make_request() is used to make I/O requests of block
- * devices. It is passed a &struct bio, which describes the I/O that needs
- * to be done.
- *
- * generic_make_request() does not return any status.  The
- * success/failure status of the request, along with notification of
- * completion, is delivered asynchronously through the bio->bi_end_io
- * function described (one day) else where.
- *
- * The caller of generic_make_request must make sure that bi_io_vec
- * are set to describe the memory buffer, and that bi_dev and bi_sector are
- * set to describe the device address, and the
- * bi_end_io and optionally bi_private are set to describe how
- * completion notification should be signaled.
- *
- * generic_make_request and the drivers it calls may use bi_next if this
- * bio happens to be merged with someone else, and may resubmit the bio to
- * a lower device by calling into generic_make_request recursively, which
- * means the bio should NOT be touched after the call to ->make_request_fn.
+ * This is a version of submit_bio() that shall only be used for I/O that is
+ * resubmitted to lower level drivers by stacking block drivers.  All file
+ * systems and other upper level users of the block layer should use
+ * submit_bio() instead.
  */
 blk_qc_t generic_make_request(struct bio *bio)
 {
@@ -1061,18 +1146,14 @@ blk_qc_t generic_make_request(struct bio *bio)
 	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bio->bi_disk->queue;
-		blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ?
-			BLK_MQ_REQ_NOWAIT : 0;
 
-		if (likely(blk_queue_enter(q, flags) == 0)) {
+		if (likely(bio_queue_enter(bio) == 0)) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
 			bio_list_on_stack[1] = bio_list_on_stack[0];
 			bio_list_init(&bio_list_on_stack[0]);
-			ret = q->make_request_fn(q, bio);
-
-			blk_queue_exit(q);
+			ret = do_make_request(bio);
 
 			/* sort new bios into those for a lower level
 			 * and those for the same level
@@ -1088,12 +1169,6 @@ blk_qc_t generic_make_request(struct bio *bio)
 			bio_list_merge(&bio_list_on_stack[0], &lower);
 			bio_list_merge(&bio_list_on_stack[0], &same);
 			bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
-		} else {
-			if (unlikely(!blk_queue_dying(q) &&
-					(bio->bi_opf & REQ_NOWAIT)))
-				bio_wouldblock_error(bio);
-			else
-				bio_io_error(bio);
 		}
 		bio = bio_list_pop(&bio_list_on_stack[0]);
 	} while (bio);
@@ -1110,30 +1185,25 @@ EXPORT_SYMBOL(generic_make_request);
  *
  * This function behaves like generic_make_request(), but does not protect
  * against recursion.  Must only be used if the called driver is known
- * to not call generic_make_request (or direct_make_request) again from
- * its make_request function.  (Calling direct_make_request again from
- * a workqueue is perfectly fine as that doesn't recurse).
+ * to be blk-mq based.
  */
 blk_qc_t direct_make_request(struct bio *bio)
 {
 	struct request_queue *q = bio->bi_disk->queue;
-	bool nowait = bio->bi_opf & REQ_NOWAIT;
-	blk_qc_t ret;
 
+	if (WARN_ON_ONCE(q->make_request_fn)) {
+		bio_io_error(bio);
+		return BLK_QC_T_NONE;
+	}
 	if (!generic_make_request_checks(bio))
 		return BLK_QC_T_NONE;
-
-	if (unlikely(blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0))) {
-		if (nowait && !blk_queue_dying(q))
-			bio_wouldblock_error(bio);
-		else
-			bio_io_error(bio);
+	if (unlikely(bio_queue_enter(bio)))
+		return BLK_QC_T_NONE;
+	if (!blk_crypto_bio_prep(&bio)) {
+		blk_queue_exit(q);
 		return BLK_QC_T_NONE;
 	}
-
-	ret = q->make_request_fn(q, bio);