for-linus-20190715

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl0s1ZEQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpiCEEACE9H/pXoegTTWIVPVajMlsa19UHIeilk4N
 GI7oKSiirQEMZnAOmrEzgB4/0zyYQsVypys0gZlYUD3GJVsXDT3zzjNXL5NpVg/O
 nqwSGWMHBSjWkLbaM40Pb2QLXsYgveptNL+9PtxrgtoYPoT5/+TyrJMFrRfi72EK
 WFeNDKOu6aJxpJ26JSsckJ0gluKeeEpRoEqsgHGIwaMIGHQf+b+ikk7tel5FAIgA
 uDwwD+Oxsdgh/ChsXL0d90GkcbcSp6GQ7GybxVmw/tPijx6mpeIY72xY3Zx+t8zF
 b71UNk6NmCKjOPO/6fiuYKKTYw+KhzlyEKO0j675HKfx2AhchEwKw0irp4yUlydA
 zxWYmz4U7iRgktJtymv3J4FEQQ3S6d1EnuQkQNX1LwiOsEsfzhkWi+7jy7KFhZoJ
 AqtYzqnOXvLx92q0vloj06HtK6zo+I/MINldy0+qn9lq0N0VF+dctyztAHLsF7P6
 pUtS6i7l1JSFKAmMhC31sIj5TImaehM2e/TWMUPEDZaO96oKCmQwOF1oiloc6vlW
 h4xWsxP/9zOFcWNyPzy6Vo3JUXWRvFA7K+jV3Hsukw6rVHiNCGVYGSlTv8Roi5b7
 I4ggu9R2JOGyku7UIlL50IRxEyjAp11LaO8yHhcCnRB65rmyBuNMQNcfOsfxpZ5Y
 1mtSNhm5TQ==
 =g8xI
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-20190715' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:
 "A later pull request with some followup items. I had some vacation
  coming up to the merge window, so certain things items were delayed a
  bit. This pull request also contains fixes that came in within the
  last few days of the merge window, which I didn't want to push right
  before sending you a pull request.

  This contains:

   - NVMe pull request, mostly fixes, but also a few minor items on the
     feature side that were timing constrained (Christoph et al)

   - Report zones fixes (Damien)

   - Removal of dead code (Damien)

   - Turn on cgroup psi memstall (Josef)

   - block cgroup MAINTAINERS entry (Konstantin)

   - Flush init fix (Josef)

   - blk-throttle low iops timing fix (Konstantin)

   - nbd resize fixes (Mike)

   - nbd 0 blocksize crash fix (Xiubo)

   - block integrity error leak fix (Wenwen)

   - blk-cgroup writeback and priority inheritance fixes (Tejun)"

* tag 'for-linus-20190715' of git://git.kernel.dk/linux-block: (42 commits)
  MAINTAINERS: add entry for block io cgroup
  null_blk: fixup ->report_zones() for !CONFIG_BLK_DEV_ZONED
  block: Limit zone array allocation size
  sd_zbc: Fix report zones buffer allocation
  block: Kill gfp_t argument of blkdev_report_zones()
  block: Allow mapping of vmalloc-ed buffers
  block/bio-integrity: fix a memory leak bug
  nvme: fix NULL deref for fabrics options
  nbd: add netlink reconfigure resize support
  nbd: fix crash when the blksize is zero
  block: Disable write plugging for zoned block devices
  block: Fix elevator name declaration
  block: Remove unused definitions
  nvme: fix regression upon hot device removal and insertion
  blk-throttle: fix zero wait time for iops throttled group
  block: Fix potential overflow in blk_report_zones()
  blkcg: implement REQ_CGROUP_PUNT
  blkcg, writeback: Implement wbc_blkcg_css()
  blkcg, writeback: Add wbc->no_cgroup_owner
  blkcg, writeback: Rename wbc_account_io() to wbc_account_cgroup_owner()
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -2124,7 +2124,7 @@ following two functions.
 	a queue (device) has been associated with the bio and
 	before submission.
 
-  wbc_account_io(@wbc, @page, @bytes)
+  wbc_account_cgroup_owner(@wbc, @page, @bytes)
 	Should be called for each data segment being written out.
 	While this function doesn't care exactly when it's called
 	during the writeback session, it's the easiest and most

Documentation/block/biodoc.txt

@@ -843,11 +843,6 @@ elevator_latter_req_fn		These return the request before or after the
 
 elevator_completed_req_fn	called when a request is completed.
 
-elevator_may_queue_fn		returns true if the scheduler wants to allow the
-				current context to queue a new request even if
-				it is over the queue limit. This must be used
-				very carefully!!
-
 elevator_set_req_fn
 elevator_put_req_fn		Must be used to allocate and free any elevator
 				specific storage for a request.

MAINTAINERS

@@ -4183,6 +4183,19 @@ S:	Maintained
 F:	mm/memcontrol.c
 F:	mm/swap_cgroup.c
 
+CONTROL GROUP - BLOCK IO CONTROLLER (BLKIO)
+M:	Tejun Heo <tj@kernel.org>
+M:	Jens Axboe <axboe@kernel.dk>
+L:	cgroups@vger.kernel.org
+L:	linux-block@vger.kernel.org
+T:	git git://git.kernel.dk/linux-block
+F:	Documentation/cgroup-v1/blkio-controller.rst
+F:	block/blk-cgroup.c
+F:	include/linux/blk-cgroup.h
+F:	block/blk-throttle.c
+F:	block/blk-iolatency.c
+F:	block/bfq-cgroup.c
+
 CORETEMP HARDWARE MONITORING DRIVER
 M:	Fenghua Yu <fenghua.yu@intel.com>
 L:	linux-hwmon@vger.kernel.org

block/bio-integrity.c

@@ -276,8 +276,12 @@ bool bio_integrity_prep(struct bio *bio)
 		ret = bio_integrity_add_page(bio, virt_to_page(buf),
 					     bytes, offset);
 
-		if (ret == 0)
+		if (ret == 0) {
-			return false;
+			printk(KERN_ERR "could not attach integrity payload\n");
+			kfree(buf);
+			status = BLK_STS_RESOURCE;
+			goto err_end_io;
+		}
 
 		if (ret < bytes)
 			break;

block/bio.c

@@ -16,6 +16,7 @@
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <linux/blk-cgroup.h>
+#include <linux/highmem.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
@@ -1441,8 +1442,22 @@ void bio_unmap_user(struct bio *bio)
 	bio_put(bio);
 }
 
+static void bio_invalidate_vmalloc_pages(struct bio *bio)
+{
+#ifdef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+	if (bio->bi_private && !op_is_write(bio_op(bio))) {
+		unsigned long i, len = 0;
+
+		for (i = 0; i < bio->bi_vcnt; i++)
+			len += bio->bi_io_vec[i].bv_len;
+		invalidate_kernel_vmap_range(bio->bi_private, len);
+	}
+#endif
+}
+
 static void bio_map_kern_endio(struct bio *bio)
 {
+	bio_invalidate_vmalloc_pages(bio);
 	bio_put(bio);
 }
 
@@ -1463,6 +1478,8 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	unsigned long start = kaddr >> PAGE_SHIFT;
 	const int nr_pages = end - start;
+	bool is_vmalloc = is_vmalloc_addr(data);
+	struct page *page;
 	int offset, i;
 	struct bio *bio;
 
@@ -1470,6 +1487,11 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
 
+	if (is_vmalloc) {
+		flush_kernel_vmap_range(data, len);
+		bio->bi_private = data;
+	}
+
 	offset = offset_in_page(kaddr);
 	for (i = 0; i < nr_pages; i++) {
 		unsigned int bytes = PAGE_SIZE - offset;
@@ -1480,7 +1502,11 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 		if (bytes > len)
 			bytes = len;
 
-		if (bio_add_pc_page(q, bio, virt_to_page(data), bytes,
+		if (!is_vmalloc)
+			page = virt_to_page(data);
+		else
+			page = vmalloc_to_page(data);
+		if (bio_add_pc_page(q, bio, page, bytes,
 				    offset) < bytes) {
 			/* we don't support partial mappings */
 			bio_put(bio);

block/blk-cgroup.c

@@ -29,6 +29,7 @@
 #include <linux/ctype.h>
 #include <linux/blk-cgroup.h>
 #include <linux/tracehook.h>
+#include <linux/psi.h>
 #include "blk.h"
 
 #define MAX_KEY_LEN 100
@@ -47,12 +48,14 @@ struct blkcg blkcg_root;
 EXPORT_SYMBOL_GPL(blkcg_root);
 
 struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;
+EXPORT_SYMBOL_GPL(blkcg_root_css);
 
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
 static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
 
 static bool blkcg_debug_stats = false;
+static struct workqueue_struct *blkcg_punt_bio_wq;
 
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
@@ -87,6 +90,8 @@ static void __blkg_release(struct rcu_head *rcu)
 {
 	struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head);
 
+	WARN_ON(!bio_list_empty(&blkg->async_bios));
+
 	/* release the blkcg and parent blkg refs this blkg has been holding */
 	css_put(&blkg->blkcg->css);
 	if (blkg->parent)
@@ -112,6 +117,23 @@ static void blkg_release(struct percpu_ref *ref)
 	call_rcu(&blkg->rcu_head, __blkg_release);
 }
 
+static void blkg_async_bio_workfn(struct work_struct *work)
+{
+	struct blkcg_gq *blkg = container_of(work, struct blkcg_gq,
+					     async_bio_work);
+	struct bio_list bios = BIO_EMPTY_LIST;
+	struct bio *bio;
+
+	/* as long as there are pending bios, @blkg can't go away */
+	spin_lock_bh(&blkg->async_bio_lock);
+	bio_list_merge(&bios, &blkg->async_bios);
+	bio_list_init(&blkg->async_bios);
+	spin_unlock_bh(&blkg->async_bio_lock);
+
+	while ((bio = bio_list_pop(&bios)))
+		submit_bio(bio);
+}
+
 /**
  * blkg_alloc - allocate a blkg
  * @blkcg: block cgroup the new blkg is associated with
@@ -140,6 +162,9 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 
 	blkg->q = q;
 	INIT_LIST_HEAD(&blkg->q_node);
+	spin_lock_init(&blkg->async_bio_lock);
+	bio_list_init(&blkg->async_bios);
+	INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn);
 	blkg->blkcg = blkcg;
 
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
@@ -1526,6 +1551,25 @@ void blkcg_policy_unregister(struct blkcg_policy *pol)
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
 
+bool __blkcg_punt_bio_submit(struct bio *bio)
+{
+	struct blkcg_gq *blkg = bio->bi_blkg;
+
+	/* consume the flag first */
+	bio->bi_opf &= ~REQ_CGROUP_PUNT;
+
+	/* never bounce for the root cgroup */
+	if (!blkg->parent)
+		return false;
+
+	spin_lock_bh(&blkg->async_bio_lock);
+	bio_list_add(&blkg->async_bios, bio);
+	spin_unlock_bh(&blkg->async_bio_lock);
+
+	queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work);
+	return true;
+}
+
 /*
  * Scale the accumulated delay based on how long it has been since we updated
  * the delay.  We only call this when we are adding delay, in case it's been a
@@ -1587,6 +1631,7 @@ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
  */
 static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 {
+	unsigned long pflags;
 	u64 now = ktime_to_ns(ktime_get());
 	u64 exp;
 	u64 delay_nsec = 0;
@@ -1613,11 +1658,8 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 	 */
 	delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
 
-	/*
+	if (use_memdelay)
-	 * TODO: the use_memdelay flag is going to be for the upcoming psi stuff
+		psi_memstall_enter(&pflags);
-	 * that hasn't landed upstream yet.  Once that stuff is in place we need
-	 * to do a psi_memstall_enter/leave if memdelay is set.
-	 */
 
 	exp = ktime_add_ns(now, delay_nsec);
 	tok = io_schedule_prepare();
@@ -1627,6 +1669,9 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 			break;
 	} while (!fatal_signal_pending(current));
 	io_schedule_finish(tok);
+
+	if (use_memdelay)
+		psi_memstall_leave(&pflags);
 }
 
 /**
@@ -1726,5 +1771,16 @@ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
 	atomic64_add(delta, &blkg->delay_nsec);
 }
 
+static int __init blkcg_init(void)
+{
+	blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio",
+					    WQ_MEM_RECLAIM | WQ_FREEZABLE |
+					    WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!blkcg_punt_bio_wq)
+		return -ENOMEM;
+	return 0;
+}
+subsys_initcall(blkcg_init);
+
 module_param(blkcg_debug_stats, bool, 0644);
 MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");

block/blk-core.c

@@ -117,6 +117,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->internal_tag = -1;
 	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
+	refcount_set(&rq->ref, 1);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -687,7 +688,7 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	struct request *rq;
 	struct list_head *plug_list;
 
-	plug = current->plug;
+	plug = blk_mq_plug(q, bio);
 	if (!plug)
 		return false;
 
@@ -1127,6 +1128,9 @@ EXPORT_SYMBOL_GPL(direct_make_request);
  */
 blk_qc_t submit_bio(struct bio *bio)
 {
+	if (blkcg_punt_bio_submit(bio))
+		return BLK_QC_T_NONE;
+
 	/*
 	 * If it's a regular read/write or a barrier with data attached,
 	 * go through the normal accounting stuff before submission.

block/blk-mq.c

@@ -1973,7 +1973,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
-	plug = current->plug;
+	plug = blk_mq_plug(q, bio);
 	if (unlikely(is_flush_fua)) {
 		/* bypass scheduler for flush rq */
 		blk_insert_flush(rq);

block/blk-mq.h

@@ -233,4 +233,36 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
 		qmap->mq_map[cpu] = 0;
 }
 
+/*
+ * blk_mq_plug() - Get caller context plug
+ * @q: request queue
+ * @bio : the bio being submitted by the caller context
+ *
+ * Plugging, by design, may delay the insertion of BIOs into the elevator in
+ * order to increase BIO merging opportunities. This however can cause BIO
+ * insertion order to change from the order in which submit_bio() is being
+ * executed in the case of multiple contexts concurrently issuing BIOs to a
+ * device, even if these context are synchronized to tightly control BIO issuing
+ * order. While this is not a problem with regular block devices, this ordering
+ * change can cause write BIO failures with zoned block devices as these
+ * require sequential write patterns to zones. Prevent this from happening by
+ * ignoring the plug state of a BIO issuing context if the target request queue
+ * is for a zoned block device and the BIO to plug is a write operation.
+ *
+ * Return current->plug if the bio can be plugged and NULL otherwise
+ */
+static inline struct blk_plug *blk_mq_plug(struct request_queue *q,
+					   struct bio *bio)
+{
+	/*
+	 * For regular block devices or read operations, use the context plug
+	 * which may be NULL if blk_start_plug() was not executed.
+	 */
+	if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio)))
+		return current->plug;
+
+	/* Zoned block device write operation case: do not plug the BIO */
+	return NULL;
+}
+
 #endif

block/blk-throttle.c

@@ -881,13 +881,10 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 	u64 tmp;
 
-	jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
+	jiffy_elapsed = jiffies - tg->slice_start[rw];
 
-	/* Slice has just started. Consider one slice interval */
+	/* Round up to the next throttle slice, wait time must be nonzero */
-	if (!jiffy_elapsed)
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice);
-		jiffy_elapsed_rnd = tg->td->throtl_slice;
-
-	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
 
 	/*
 	 * jiffy_elapsed_rnd should not be a big value as minimum iops can be

block/blk-zoned.c

@@ -14,6 +14,9 @@
 #include <linux/rbtree.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/sched/mm.h>
 
 #include "blk.h"
 
@@ -70,7 +73,7 @@ EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
 static inline unsigned int __blkdev_nr_zones(struct request_queue *q,
 					     sector_t nr_sectors)
 {
-	unsigned long zone_sectors = blk_queue_zone_sectors(q);
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
 
 	return (nr_sectors + zone_sectors - 1) >> ilog2(zone_sectors);
 }
@@ -117,8 +120,7 @@ static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep)
 }
 
 static int blk_report_zones(struct gendisk *disk, sector_t sector,
-			    struct blk_zone *zones, unsigned int *nr_zones,
+			    struct blk_zone *zones, unsigned int *nr_zones)
-			    gfp_t gfp_mask)
 {
 	struct request_queue *q = disk->queue;
 	unsigned int z = 0, n, nrz = *nr_zones;
@@ -127,8 +129,7 @@ static int blk_report_zones(struct gendisk *disk, sector_t sector,
 
 	while (z < nrz && sector < capacity) {
 		n = nrz - z;
-		ret = disk->fops->report_zones(disk, sector, &zones[z], &n,
+		ret = disk->fops->report_zones(disk, sector, &zones[z], &n);
-					       gfp_mask);
 		if (ret)
 			return ret;
 		if (!n)
@@ -149,17 +150,18 @@ static int blk_report_zones(struct gendisk *disk, sector_t sector,
  * @sector:	Sector from which to report zones
  * @zones:	Array of zone structures where to return the zones information
  * @nr_zones:	Number of zone structures in the zone array
- * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
  *    Get zone information starting from the zone containing @sector.
  *    The number of zone information reported may be less than the number
  *    requested by @nr_zones. The number of zones actually reported is
  *    returned in @nr_zones.
+ *    The caller must use memalloc_noXX_save/restore() calls to control
+ *    memory allocations done within this function (zone array and command
+ *    buffer allocation by the device driver).
  */
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			struct blk_zone *zones, unsigned int *nr_zones,
+			struct blk_zone *zones, unsigned int *nr_zones)
-			gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	unsigned int i, nrz;
@@ -184,7 +186,7 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 	nrz = min(*nr_zones,
 		  __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector));
 	ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector,
-			       zones, &nrz, gfp_mask);
+			       zones, &nrz);
 	if (ret)
 		return ret;
 
@@ -305,9 +307,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!zones)
 		return -ENOMEM;
 
-	ret = blkdev_report_zones(bdev, rep.sector,
+	ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones);
-				  zones, &rep.nr_zones,
-				  GFP_KERNEL);
 	if (ret)
 		goto out;
 
@@ -373,22 +373,25 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node,
  * Allocate an array of struct blk_zone to get nr_zones zone information.
  * The allocated array may be smaller than nr_zones.
  */
-static struct blk_zone *blk_alloc_zones(int node, unsigned int *nr_zones)
+static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones)
 {
-	size_t size = *nr_zones * sizeof(struct blk_zone);
+	struct blk_zone *zones;
-	struct page *page;
+	size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES);
-	int order;
 
-	for (order = get_order(size); order >= 0; order--) {
+	/*
-		page = alloc_pages_node(node, GFP_NOIO | __GFP_ZERO, order);
+	 * GFP_KERNEL here is meaningless as the caller task context has
-		if (page) {
+	 * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones()
-			*nr_zones = min_t(unsigned int, *nr_zones,
+	 * with memalloc_noio_save().
-				(PAGE_SIZE << order) / sizeof(struct blk_zone));
+	 */
-			return page_address(page);
+	zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL);
-		}
+	if (!zones) {
+		*nr_zones = 0;
+		return NULL;
 	}
 
-	return NULL;
+	*nr_zones = nrz;
+
+	return zones;
 }
 
 void blk_queue_free_zone_bitmaps(struct request_queue *q)
@@ -415,6 +418,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 	unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
 	unsigned int i, rep_nr_zones = 0, z = 0, nrz;
 	struct blk_zone *zones = NULL;
+	unsigned int noio_flag;
 	sector_t sector = 0;
 	int ret = 0;
 
@@ -427,6 +431,12 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 		return 0;
 	}
 
+	/*
+	 * Ensure that all memory allocations in this context are done as
+	 * if GFP_NOIO was specified.
+	 */
+	noio_flag = memalloc_noio_save();
+
 	if (!blk_queue_is_zoned(q) || !nr_zones) {
 		nr_zones = 0;
 		goto update;
@@ -443,13 +453,13 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 
 	/* Get zone information and initialize seq_zones_bitmap */
 	rep_nr_zones = nr_zones;
-	zones = blk_alloc_zones(q->node, &rep_nr_zones);
+	zones = blk_alloc_zones(&rep_nr_zones);
 	if (!zones)
 		goto out;
 
 	while (z < nr_zones) {
 		nrz = min(nr_zones - z, rep_nr_zones);
-		ret = blk_report_zones(disk, sector, zones, &nrz, GFP_NOIO);
+		ret = blk_report_zones(disk, sector, zones, &nrz);
 		if (ret)
 			goto out;
 		if (!nrz)
@@ -480,8 +490,9 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 	blk_mq_unfreeze_queue(q);
 
 out:
-	free_pages((unsigned long)zones,
+	memalloc_noio_restore(noio_flag);
-		   get_order(rep_nr_zones * sizeof(struct blk_zone)));
+
+	kvfree(zones);
 	kfree(seq_zones_wlock);
 	kfree(seq_zones_bitmap);
 

drivers/block/nbd.c

@@ -134,6 +134,8 @@ static struct dentry *nbd_dbg_dir;
 
 #define NBD_MAGIC 0x68797548
 
+#define NBD_DEF_BLKSIZE 1024
+
 static unsigned int nbds_max = 16;
 static int max_part = 16;
 static struct workqueue_struct *recv_workqueue;
@@ -1236,6 +1238,14 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
 		nbd_config_put(nbd);
 }
 
+static bool nbd_is_valid_blksize(unsigned long blksize)
+{
+	if (!blksize || !is_power_of_2(blksize) || blksize < 512 ||
+	    blksize > PAGE_SIZE)
+		return false;
+	return true;
+}
+
 /* Must be called with config_lock held */
 static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		       unsigned int cmd, unsigned long arg)
@@ -1251,8 +1261,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	case NBD_SET_SOCK:
 		return nbd_add_socket(nbd, arg, false);
 	case NBD_SET_BLKSIZE:
-		if (!arg || !is_power_of_2(arg) || arg < 512 ||
+		if (!arg)
-		    arg > PAGE_SIZE)
+			arg = NBD_DEF_BLKSIZE;
+		if (!nbd_is_valid_blksize(arg))
 			return -EINVAL;
 		nbd_size_set(nbd, arg,
 			     div_s64(config->bytesize, arg));
@@ -1332,7 +1343,7 @@ static struct nbd_config *nbd_alloc_config(void)
 	atomic_set(&config->recv_threads, 0);
 	init_waitqueue_head(&config->recv_wq);
 	init_waitqueue_head(&config->conn_wait);
-	config->blksize = 1024;
+	config->blksize = NBD_DEF_BLKSIZE;
 	atomic_set(&config->live_connections, 0);
 	try_module_get(THIS_MODULE);
 	return config;
@@ -1673,6 +1684,30 @@ nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = {
 	[NBD_DEVICE_CONNECTED]		=	{ .type = NLA_U8 },
 };
 
+static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd)
+{
+	struct nbd_config *config = nbd->config;
+	u64 bsize = config->blksize;
+	u64 bytes = config->bytesize;
+
+	if (info->attrs[NBD_ATTR_SIZE_BYTES])
+		bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]);
+
+	if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) {
+		bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
+		if (!bsize)
+			bsize = NBD_DEF_BLKSIZE;
+		if (!nbd_is_valid_blksize(bsize)) {
+			printk(KERN_ERR "Invalid block size %llu\n", bsize);
+			return -EINVAL;
+		}
+	}
+
+	if (bytes != config->bytesize || bsize != config->blksize)
+		nbd_size_set(nbd, bsize, div64_u64(bytes, bsize));
+	return 0;
+}
+
 static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nbd_device *nbd = NULL;
@@ -1760,16 +1795,10 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 	refcount_set(&nbd->config_refs, 1);
 	set_bit(NBD_BOUND, &config->runtime_flags);
 
-	if (info->attrs[NBD_ATTR_SIZE_BYTES]) {
+	ret = nbd_genl_size_set(info, nbd);
-		u64 bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]);
+	if (ret)
-		nbd_size_set(nbd, config->blksize,
+		goto out;
-			     div64_u64(bytes, config->blksize));
+
-	}
-	if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) {
-		u64 bsize =
-			nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
-		nbd_size_set(nbd, bsize, div64_u64(config->bytesize, bsize));
-	}
 	if (info->attrs[NBD_ATTR_TIMEOUT]) {
 		u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
 		nbd->tag_set.timeout = timeout * HZ;
@@ -1938,6 +1967,10 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	}
 
+	ret = nbd_genl_size_set(info, nbd);
+	if (ret)
+		goto out;
+
 	if (info->attrs[NBD_ATTR_TIMEOUT]) {
 		u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
 		nbd->tag_set.timeout = timeout * HZ;

drivers/block/null_blk.h

@@ -89,8 +89,7 @@ struct nullb {
 int null_zone_init(struct nullb_device *dev);
 void null_zone_exit(struct nullb_device *dev);
 int null_zone_report(struct gendisk *disk, sector_t sector,
-		     struct blk_zone *zones, unsigned int *nr_zones,
+		     struct blk_zone *zones, unsigned int *nr_zones);
-		     gfp_t gfp_mask);
 void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 			unsigned int nr_sectors);
 void null_zone_reset(struct nullb_cmd *cmd, sector_t sector);
@@ -103,7 +102,7 @@ static inline int null_zone_init(struct nullb_device *dev)
 static inline void null_zone_exit(struct nullb_device *dev) {}
 static inline int null_zone_report(struct gendisk *disk, sector_t sector,
 				   struct blk_zone *zones,
-				   unsigned int *nr_zones, gfp_t gfp_mask)
+				   unsigned int *nr_zones)
 {
 	return -EOPNOTSUPP;
 }

drivers/block/null_blk_zoned.c

@@ -67,8 +67,7 @@ void null_zone_exit(struct nullb_device *dev)
 }
 
 int null_zone_report(struct gendisk *disk, sector_t sector,
-		     struct blk_zone *zones, unsigned int *nr_zones,
+		     struct blk_zone *zones, unsigned int *nr_zones)
-		     gfp_t gfp_mask)
 {
 	struct nullb *nullb = disk->private_data;
 	struct nullb_device *dev = nullb->dev;

drivers/md/dm-flakey.c

@@ -461,15 +461,14 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 
 #ifdef CONFIG_BLK_DEV_ZONED
 static int flakey_report_zones(struct dm_target *ti, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones,
+			       struct blk_zone *zones, unsigned int *nr_zones)
-			       gfp_t gfp_mask)
 {
 	struct flakey_c *fc = ti->private;
 	int ret;
 
 	/* Do report and remap it */
 	ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector),
-				  zones, nr_zones, gfp_mask);
+				  zones, nr_zones);
 	if (ret != 0)
 		return ret;
 

drivers/md/dm-linear.c

@@ -137,15 +137,14 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 
 #ifdef CONFIG_BLK_DEV_ZONED
 static int linear_report_zones(struct dm_target *ti, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones,
+			       struct blk_zone *zones, unsigned int *nr_zones)
-			       gfp_t gfp_mask)
 {
 	struct linear_c *lc = (struct linear_c *) ti->private;
 	int ret;
 
 	/* Do report and remap it */
 	ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector),
-				  zones, nr_zones, gfp_mask);
+				  zones, nr_zones);
 	if (ret != 0)
 		return ret;
 

drivers/md/dm-zoned-metadata.c

@@ -8,6 +8,7 @@
 
 #include <linux/module.h>
 #include <linux/crc32.h>
+#include <linux/sched/mm.h>
 
 #define	DM_MSG_PREFIX		"zoned metadata"
 
@@ -1162,8 +1163,7 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
 	while (sector < dev->capacity) {
 		/* Get zone information */
 		nr_blkz = DMZ_REPORT_NR_ZONES;
-		ret = blkdev_report_zones(dev->bdev, sector, blkz,
+		ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz);
-					  &nr_blkz, GFP_KERNEL);
 		if (ret) {
 			dmz_dev_err(dev, "Report zones failed %d", ret);
 			goto out;
@@ -1201,12 +1201,20 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
 static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 {
 	unsigned int nr_blkz = 1;
+	unsigned int noio_flag;
 	struct blk_zone blkz;
 	int ret;
 
-	/* Get zone information from disk */
+	/*
+	 * Get zone information from disk. Since blkdev_report_zones() uses
+	 * GFP_KERNEL by default for memory allocations, set the per-task
+	 * PF_MEMALLOC_NOIO flag so that all allocations are done as if
+	 * GFP_NOIO was specified.
+	 */
+	noio_flag = memalloc_noio_save();
 	ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone),
-				  &blkz, &nr_blkz, GFP_NOIO);
+				  &blkz, &nr_blkz);
+	memalloc_noio_restore(noio_flag);
 	if (!nr_blkz)
 		ret = -EIO;
 	if (ret) {

drivers/md/dm.c

@@ -441,8 +441,7 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones,
+			       struct blk_zone *zones, unsigned int *nr_zones)
-			       gfp_t gfp_mask)
 {
 #ifdef CONFIG_BLK_DEV_ZONED
 	struct mapped_device *md = disk->private_data;
@@ -480,8 +479,7 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 	 * So there is no need to loop here trying to fill the entire array
 	 * of zones.
 	 */
-	ret = tgt->type->report_zones(tgt, sector, zones,
+	ret = tgt->type->report_zones(tgt, sector, zones, nr_zones);
-				      nr_zones, gfp_mask);
 
 out:
 	dm_put_live_table(md, srcu_idx);

drivers/nvme/host/core.c

@@ -11,6 +11,7 @@
 #include <linux/hdreg.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/backing-dev.h>
 #include <linux/list_sort.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -1626,6 +1627,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 {
 	sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9);
 	unsigned short bs = 1 << ns->lba_shift;
+	u32 atomic_bs, phys_bs, io_opt;
 
 	if (ns->lba_shift > PAGE_SHIFT) {
 		/* unsupported block size, set capacity to 0 later */
@@ -1634,9 +1636,37 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_mq_freeze_queue(disk->queue);
 	blk_integrity_unregister(disk);
 
+	if (id->nabo == 0) {
+		/*
+		 * Bit 1 indicates whether NAWUPF is defined for this namespace
+		 * and whether it should be used instead of AWUPF. If NAWUPF ==
+		 * 0 then AWUPF must be used instead.
+		 */
+		if (id->nsfeat & (1 << 1) && id->nawupf)
+			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
+		else
+			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+	} else {
+		atomic_bs = bs;
+	}
+	phys_bs = bs;
+	io_opt = bs;
+	if (id->nsfeat & (1 << 4)) {
+		/* NPWG = Namespace Preferred Write Granularity */
+		phys_bs *= 1 + le16_to_cpu(id->npwg);
+		/* NOWS = Namespace Optimal Write Size */
+		io_opt *= 1 + le16_to_cpu(id->nows);
+	}
+
 	blk_queue_logical_block_size(disk->queue, bs);
-	blk_queue_physical_block_size(disk->queue, bs);
+	/*
-	blk_queue_io_min(disk->queue, bs);
+	 * Linux filesystems assume writing a single physical block is
+	 * an atomic operation. Hence limit the physical block size to the
+	 * value of the Atomic Write Unit Power Fail parameter.
+	 */
+	blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
+	blk_queue_io_min(disk->queue, phys_bs);
+	blk_queue_io_opt(disk->queue, io_opt);
 
 	if (ns->ms && !ns->ext &&
 	    (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
@@ -2386,8 +2416,8 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 	lockdep_assert_held(&nvme_subsystems_lock);
 
 	list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) {
-		if (ctrl->state == NVME_CTRL_DELETING ||
+		if (tmp->state == NVME_CTRL_DELETING ||
-		    ctrl->state == NVME_CTRL_DEAD)
+		    tmp->state == NVME_CTRL_DEAD)
 			continue;
 
 		if (tmp->cntlid == ctrl->cntlid) {
@@ -2433,6 +2463,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
+	subsys->awupf = le16_to_cpu(id->awupf);
 #ifdef CONFIG_NVME_MULTIPATH
 	subsys->iopolicy = NVME_IOPOLICY_NUMA;
 #endif
@@ -3274,6 +3305,10 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		goto out_free_ns;
 	}
 
+	if (ctrl->opts && ctrl->opts->data_digest)
+		ns->queue->backing_dev_info->capabilities
+			|= BDI_CAP_STABLE_WRITES;
+
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
 	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
 		blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);

drivers/nvme/host/fc.c

@@ -204,6 +204,9 @@ static DEFINE_IDA(nvme_fc_ctrl_cnt);
 
 static struct workqueue_struct *nvme_fc_wq;
 
+static bool nvme_fc_waiting_to_unload;
+static DECLARE_COMPLETION(nvme_fc_unload_proceed);
+
 /*
  * These items are short-term. They will eventually be moved into
  * a generic FC class. See comments in module init.
@@ -229,6 +232,8 @@ nvme_fc_free_lport(struct kref *ref)
 	/* remove from transport list */
 	spin_lock_irqsave(&nvme_fc_lock, flags);
 	list_del(&lport->port_list);
+	if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list))
+		complete(&nvme_fc_unload_proceed);
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
 	ida_simple_remove(&nvme_fc_local_port_cnt, lport->localport.port_num);
@@ -3457,11 +3462,51 @@ static int __init nvme_fc_init_module(void)
 	return ret;
 }
 
+static void
+nvme_fc_delete_controllers(struct nvme_fc_rport *rport)
+{
+	struct nvme_fc_ctrl *ctrl;
+
+	spin_lock(&rport->lock);
+	list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) {
+		dev_warn(ctrl->ctrl.device,
+			"NVME-FC{%d}: transport unloading: deleting ctrl\n",
+			ctrl->cnum);
+		nvme_delete_ctrl(&ctrl->ctrl);
+	}
+	spin_unlock(&rport->lock);
+}
+
+static void
+nvme_fc_cleanup_for_unload(void)
+{
+	struct nvme_fc_lport *lport;
+	struct nvme_fc_rport *rport;
+
+	list_for_each_entry(lport, &nvme_fc_lport_list, port_list) {
+		list_for_each_entry(rport, &lport->endp_list, endp_list) {
+			nvme_fc_delete_controllers(rport);
+		}
+	}
+}
+
 static void __exit nvme_fc_exit_module(void)
 {
-	/* sanity check - all lports should be removed */
+	unsigned long flags;
-	if (!list_empty(&nvme_fc_lport_list))
+	bool need_cleanup = false;
-		pr_warn("%s: localport list not empty\n", __func__);
+
+	spin_lock_irqsave(&nvme_fc_lock, flags);
+	nvme_fc_waiting_to_unload = true;
+	if (!list_empty(&nvme_fc_lport_list)) {
+		need_cleanup = true;
+		nvme_fc_cleanup_for_unload();
+	}
+	spin_unlock_irqrestore(&nvme_fc_lock, flags);
+	if (need_cleanup) {
+		pr_info("%s: waiting for ctlr deletes\n", __func__);
+		wait_for_completion(&nvme_fc_unload_proceed);
+		pr_info("%s: ctrl deletes complete\n", __func__);
+	}
 
 	nvmf_unregister_transport(&nvme_fc_transport);
 

drivers/nvme/host/multipath.c

@@ -123,14 +123,20 @@ void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 	}
 }
 
+static bool nvme_path_is_disabled(struct nvme_ns *ns)
+{
+	return ns->ctrl->state != NVME_CTRL_LIVE ||
+		test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
+		test_bit(NVME_NS_REMOVING, &ns->flags);
+}
+
 static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
 {
 	int found_distance = INT_MAX, fallback_distance = INT_MAX, distance;
 	struct nvme_ns *found = NULL, *fallback = NULL, *ns;
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
-		if (ns->ctrl->state != NVME_CTRL_LIVE ||
+		if (nvme_path_is_disabled(ns))
-		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
 			continue;
 
 		if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
@@ -178,14 +184,16 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 {
 	struct nvme_ns *ns, *found, *fallback = NULL;
 
-	if (list_is_singular(&head->list))
+	if (list_is_singular(&head->list)) {
+		if (nvme_path_is_disabled(old))
+			return NULL;
 		return old;
+	}
 
 	for (ns = nvme_next_ns(head, old);
 	     ns != old;
 	     ns = nvme_next_ns(head, ns)) {
-		if (ns->ctrl->state != NVME_CTRL_LIVE ||
+		if (nvme_path_is_disabled(ns))
-		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
 			continue;
 
 		if (ns->ana_state == NVME_ANA_OPTIMIZED) {

drivers/nvme/host/nvme.h

@@ -283,6 +283,7 @@ struct nvme_subsystem {
 	char			firmware_rev[8];
 	u8			cmic;
 	u16			vendor_id;
+	u16			awupf;	/* 0's based awupf value. */
 	struct ida		ns_ida;
 #ifdef CONFIG_NVME_MULTIPATH
 	enum nvme_iopolicy	iopolicy;

drivers/nvme/host/pci.c

@@ -1439,11 +1439,15 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 
 	if (qid && dev->cmb_use_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
 		nvmeq->sq_cmds = pci_alloc_p2pmem(pdev, SQ_SIZE(depth));
-		nvmeq->sq_dma_addr = pci_p2pmem_virt_to_bus(pdev,
+		if (nvmeq->sq_cmds) {
-						nvmeq->sq_cmds);
+			nvmeq->sq_dma_addr = pci_p2pmem_virt_to_bus(pdev,
-		if (nvmeq->sq_dma_addr) {
+							nvmeq->sq_cmds);
-			set_bit(NVMEQ_SQ_CMB, &nvmeq->flags);
+			if (nvmeq->sq_dma_addr) {
-			return 0; 
+				set_bit(NVMEQ_SQ_CMB, &nvmeq->flags);
+				return 0;
+			}
+
+			pci_free_p2pmem(pdev, nvmeq->sq_cmds, SQ_SIZE(depth));
 		}
 	}
 
@@ -2250,7 +2254,9 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	if (!dev->ctrl.tagset) {
 		dev->tagset.ops = &nvme_mq_ops;
 		dev->tagset.nr_hw_queues = dev->online_queues - 1;
-		dev->tagset.nr_maps = 2; /* default + read */
+		dev->tagset.nr_maps = 1; /* default */
+		if (dev->io_queues[HCTX_TYPE_READ])
+			dev->tagset.nr_maps++;
 		if (dev->io_queues[HCTX_TYPE_POLL])
 			dev->tagset.nr_maps++;
 		dev->tagset.timeout = NVME_IO_TIMEOUT;
@@ -2289,8 +2295,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 	pci_set_master(pdev);
 
-	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
+	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)))
-	    dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
 		goto disable;
 
 	if (readl(dev->bar + NVME_REG_CSTS) == -1) {
@@ -2498,7 +2503,8 @@ static void nvme_reset_work(struct work_struct *work)
 	 * Limit the max command size to prevent iod->sg allocations going
 	 * over a single page.
 	 */
-	dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
+	dev->ctrl.max_hw_sectors = min_t(u32,
+		NVME_MAX_KB_SZ << 1, dma_max_mapping_size(dev->dev) >> 9);
 	dev->ctrl.max_segments = NVME_MAX_SEGS;
 
 	/*
@@ -2923,7 +2929,7 @@ static int nvme_simple_resume(struct device *dev)
 	return 0;
 }
 
-const struct dev_pm_ops nvme_dev_pm_ops = {
+static const struct dev_pm_ops nvme_dev_pm_ops = {
 	.suspend	= nvme_suspend,
 	.resume		= nvme_resume,
 	.freeze		= nvme_simple_suspend,

drivers/nvme/host/tcp.c

@@ -860,7 +860,14 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 		else
 			flags |= MSG_MORE;
 
-		ret = kernel_sendpage(queue->sock, page, offset, len, flags);
+		/* can't zcopy slab pages */
+		if (unlikely(PageSlab(page))) {
+			ret = sock_no_sendpage(queue->sock, page, offset, len,
+					flags);
+		} else {
+			ret = kernel_sendpage(queue->sock, page, offset, len,
+					flags);
+		}
 		if (ret <= 0)
 			return ret;
 

drivers/nvme/host/trace.c

@@ -7,6 +7,17 @@
 #include <asm/unaligned.h>
 #include "trace.h"
 
+static const char *nvme_trace_delete_sq(struct trace_seq *p, u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u16 sqid = get_unaligned_le16(cdw10);
+
+	trace_seq_printf(p, "sqid=%u", sqid);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 static const char *nvme_trace_create_sq(struct trace_seq *p, u8 *cdw10)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
@@ -23,6 +34,17 @@ static const char *nvme_trace_create_sq(struct trace_seq *p, u8 *cdw10)
 	return ret;
 }
 
+static const char *nvme_trace_delete_cq(struct trace_seq *p, u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u16 cqid = get_unaligned_le16(cdw10);
+
+	trace_seq_printf(p, "cqid=%u", cqid);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 static const char *nvme_trace_create_cq(struct trace_seq *p, u8 *cdw10)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
@@ -107,8 +129,12 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p,
 				       u8 opcode, u8 *cdw10)
 {
 	switch (opcode) {
+	case nvme_admin_delete_sq:
+		return nvme_trace_delete_sq(p, cdw10);
 	case nvme_admin_create_sq:
 		return nvme_trace_create_sq(p, cdw10);
+	case nvme_admin_delete_cq:
+		return nvme_trace_delete_cq(p, cdw10);
 	case nvme_admin_create_cq:
 		return nvme_trace_create_cq(p, cdw10);
 	case nvme_admin_identify:
@@ -178,7 +204,7 @@ static const char *nvme_trace_fabrics_common(struct trace_seq *p, u8 *spc)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
 
-	trace_seq_printf(p, "spcecific=%*ph", 24, spc);
+	trace_seq_printf(p, "specific=%*ph", 24, spc);
 	trace_seq_putc(p, 0);
 	return ret;
 }

drivers/nvme/target/admin-cmd.c

@@ -442,6 +442,9 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 		break;
         }
 
+	if (ns->bdev)
+		nvmet_bdev_set_limits(ns->bdev, id);
+
 	/*
 	 * We just provide a single LBA format that matches what the
 	 * underlying device reports.

drivers/nvme/target/configfs.c

@@ -588,8 +588,10 @@ static struct config_group *nvmet_ns_make(struct config_group *group,
 		goto out;
 
 	ret = -EINVAL;
-	if (nsid == 0 || nsid == NVME_NSID_ALL)
+	if (nsid == 0 || nsid == NVME_NSID_ALL) {
+		pr_err("invalid nsid %#x", nsid);
 		goto out;
+	}
 
 	ret = -ENOMEM;
 	ns = nvmet_ns_alloc(subsys, nsid);

drivers/nvme/target/fcloop.c

@@ -434,7 +434,7 @@ fcloop_fcp_recv_work(struct work_struct *work)
 	int ret = 0;
 	bool aborted = false;
 
-	spin_lock(&tfcp_req->reqlock);
+	spin_lock_irq(&tfcp_req->reqlock);
 	switch (tfcp_req->inistate) {
 	case INI_IO_START:
 		tfcp_req->inistate = INI_IO_ACTIVE;
@@ -443,11 +443,11 @@ fcloop_fcp_recv_work(struct work_struct *work)
 		aborted = true;
 		break;
 	default:
-		spin_unlock(&tfcp_req->reqlock);
+		spin_unlock_irq(&tfcp_req->reqlock);
 		WARN_ON(1);
 		return;
 	}
-	spin_unlock(&tfcp_req->reqlock);
+	spin_unlock_irq(&tfcp_req->reqlock);
 
 	if (unlikely(aborted))
 		ret = -ECANCELED;
@@ -469,7 +469,7 @@ fcloop_fcp_abort_recv_work(struct work_struct *work)
 	struct nvmefc_fcp_req *fcpreq;
 	bool completed = false;
 
-	spin_lock(&tfcp_req->reqlock);
+	spin_lock_irq(&tfcp_req->reqlock);
 	fcpreq = tfcp_req->fcpreq;
 	switch (tfcp_req->inistate) {
 	case INI_IO_ABORTED:
@@ -478,11 +478,11 @@ fcloop_fcp_abort_recv_work(struct work_struct *work)
 		completed = true;
 		break;
 	default:
-		spin_unlock(&tfcp_req->reqlock);
+		spin_unlock_irq(&tfcp_req->reqlock);
 		WARN_ON(1);
 		return;
 	}
-	spin_unlock(&tfcp_req->reqlock);
+	spin_unlock_irq(&tfcp_req->reqlock);
 
 	if (unlikely(completed)) {
 		/* remove reference taken in original abort downcall */
@@ -494,9 +494,9 @@ fcloop_fcp_abort_recv_work(struct work_struct *work)
 		nvmet_fc_rcv_fcp_abort(tfcp_req->tport->targetport,
 					&tfcp_req->tgt_fcp_req);
 
-	spin_lock(&tfcp_req->reqlock);
+	spin_lock_irq(&tfcp_req->reqlock);
 	tfcp_req->fcpreq = NULL;
-	spin_unlock(&tfcp_req->reqlock);
+	spin_unlock_irq(&tfcp_req->reqlock);
 
 	fcloop_call_host_done(fcpreq, tfcp_req, -ECANCELED);
 	/* call_host_done releases reference for abort downcall */
@@ -513,10 +513,10 @@ fcloop_tgt_fcprqst_done_work(struct work_struct *work)
 		container_of(work, struct fcloop_fcpreq, tio_done_work);
 	struct nvmefc_fcp_req *fcpreq;
 
-	spin_lock(&tfcp_req->reqlock);
+	spin_lock_irq(&tfcp_req->reqlock);
 	fcpreq = tfcp_req->fcpreq;
 	tfcp_req->inistate = INI_IO_COMPLETED;
-	spin_unlock(&tfcp_req->reqlock);
+	spin_unlock_irq(&tfcp_req->reqlock);
 
 	fcloop_call_host_done(fcpreq, tfcp_req, tfcp_req->status);
 }
@@ -535,7 +535,7 @@ fcloop_fcp_req(struct nvme_fc_local_port *localport,
 	if (!rport->targetport)
 		return -ECONNREFUSED;
 
-	tfcp_req = kzalloc(sizeof(*tfcp_req), GFP_KERNEL);
+	tfcp_req = kzalloc(sizeof(*tfcp_req), GFP_ATOMIC);
 	if (!tfcp_req)
 		return -ENOMEM;
 
@@ -621,12 +621,12 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
 	int fcp_err = 0, active, aborted;
 	u8 op = tgt_fcpreq->op;
 
-	spin_lock(&tfcp_req->reqlock);
+	spin_lock_irq(&tfcp_req->reqlock);
 	fcpreq = tfcp_req->fcpreq;
 	active = tfcp_req->active;
 	aborted = tfcp_req->aborted;
 	tfcp_req->active = true;
-	spin_unlock(&tfcp_req->reqlock);
+	spin_unlock_irq(&tfcp_req->reqlock);
 
 	if (unlikely(active))
 		/* illegal - call while i/o active */
@@ -634,9 +634,9 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
 
 	if (unlikely(aborted)) {
 		/* target transport has aborted i/o prior */
-		spin_lock(&tfcp_req->reqlock);
+		spin_lock_irq(&tfcp_req->reqlock);
 		tfcp_req->active = false;
-		spin_unlock(&tfcp_req->reqlock);
+		spin_unlock_irq(&tfcp_req->reqlock);
 		tgt_fcpreq->transferred_length = 0;
 		tgt_fcpreq->fcp_error = -ECANCELED;
 		tgt_fcpreq->done(tgt_fcpreq);
@@ -693,9 +693,9 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
 		break;
 	}
 
-	spin_lock(&tfcp_req->reqlock);
+	spin_lock_irq(&tfcp_req->reqlock);
 	tfcp_req->active = false;
-	spin_unlock(&tfcp_req->reqlock);
+	spin_unlock_irq(&tfcp_req->reqlock);
 
 	tgt_fcpreq->transferred_length = xfrlen;
 	tgt_fcpreq->fcp_error = fcp_err;
@@ -715,9 +715,9 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport,
 	 * (one doing io, other doing abort) and only kills ops posted
 	 * after the abort request
 	 */
-	spin_lock(&tfcp_req->reqlock);
+	spin_lock_irq(&tfcp_req->reqlock);
 	tfcp_req->aborted = true;
-	spin_unlock(&tfcp_req->reqlock);
+	spin_unlock_irq(&tfcp_req->reqlock);
 
 	tfcp_req->status = NVME_SC_INTERNAL;
 
@@ -765,7 +765,7 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 		return;
 
 	/* break initiator/target relationship for io */
-	spin_lock(&tfcp_req->reqlock);
+	spin_lock_irq(&tfcp_req->reqlock);
 	switch (tfcp_req->inistate) {
 	case INI_IO_START:
 	case INI_IO_ACTIVE:
@@ -775,11 +775,11 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 		abortio = false;
 		break;
 	default:
-		spin_unlock(&tfcp_req->reqlock);
+		spin_unlock_irq(&tfcp_req->reqlock);
 		WARN_ON(1);
 		return;
 	}
-	spin_unlock(&tfcp_req->reqlock);
+	spin_unlock_irq(&tfcp_req->reqlock);
 
 	if (abortio)
 		/* leave the reference while the work item is scheduled */

drivers/nvme/target/io-cmd-bdev.c

@@ -8,6 +8,45 @@
 #include <linux/module.h>
 #include "nvmet.h"
 
+void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
+{
+	const struct queue_limits *ql = &bdev_get_queue(bdev)->limits;
+	/* Number of physical blocks per logical block. */
+	const u32 ppl = ql->physical_block_size / ql->logical_block_size;
+	/* Physical blocks per logical block, 0's based. */
+	const __le16 ppl0b = to0based(ppl);
+
+	/*
+	 * For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN,
+	 * NAWUPF, and NACWU are defined for this namespace and should be
+	 * used by the host for this namespace instead of the AWUN, AWUPF,
+	 * and ACWU fields in the Identify Controller data structure. If
+	 * any of these fields are zero that means that the corresponding
+	 * field from the identify controller data structure should be used.
+	 */
+	id->nsfeat |= 1 << 1;
+	id->nawun = ppl0b;
+	id->nawupf = ppl0b;
+	id->nacwu = ppl0b;
+
+	/*
+	 * Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and
+	 * NOWS are defined for this namespace and should be used by
+	 * the host for I/O optimization.
+	 */
+	id->nsfeat |= 1 << 4;
+	/* NPWG = Namespace Preferred Write Granularity. 0's based */
+	id->npwg = ppl0b;
+	/* NPWA = Namespace Preferred Write Alignment. 0's based */
+	id->npwa = id->npwg;
+	/* NPDG = Namespace Preferred Deallocate Granularity. 0's based */
+	id->npdg = to0based(ql->discard_granularity / ql->logical_block_size);
+	/* NPDG = Namespace Preferred Deallocate Alignment */
+	id->npda = id->npdg;
+	/* NOWS = Namespace Optimal Write Size */
+	id->nows = to0based(ql->io_opt / ql->logical_block_size);
+}
+
 int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
 {
 	int ret;

drivers/nvme/target/nvmet.h

@@ -365,6 +365,7 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask);
 void nvmet_execute_async_event(struct nvmet_req *req);
 
 u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
+void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id);
 u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req);
 u16 nvmet_file_parse_io_cmd(struct nvmet_req *req);
 u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
@@ -492,4 +493,11 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req)
 }
 
 u16 errno_to_nvme_status(struct nvmet_req *req, int errno);
+
+/* Convert a 32-bit number to a 16-bit 0's based number */
+static inline __le16 to0based(u32 a)
+{
+	return cpu_to_le16(max(1U, min(1U << 16, a)) - 1);
+}
+
 #endif /* _NVMET_H */

drivers/nvme/target/trace.c

@@ -146,7 +146,7 @@ static const char *nvmet_trace_fabrics_common(struct trace_seq *p, u8 *spc)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
 
-	trace_seq_printf(p, "spcecific=%*ph", 24, spc);
+	trace_seq_printf(p, "specific=%*ph", 24, spc);
 	trace_seq_putc(p, 0);
 	return ret;
 }

drivers/scsi/sd.h

@@ -213,8 +213,7 @@ extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd);
 extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 			    struct scsi_sense_hdr *sshdr);
 extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones,
+			       struct blk_zone *zones, unsigned int *nr_zones);
-			       gfp_t gfp_mask);
 
 #else /* CONFIG_BLK_DEV_ZONED */
 

drivers/scsi/sd_zbc.c

@@ -9,6 +9,8 @@
  */
 
 #include <linux/blkdev.h>
+#include <linux/vmalloc.h>
+#include <linux/sched/mm.h>
 
 #include <asm/unaligned.h>
 
@@ -50,7 +52,7 @@ static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
 /**
  * sd_zbc_do_report_zones - Issue a REPORT ZONES scsi command.
  * @sdkp: The target disk
- * @buf: Buffer to use for the reply
+ * @buf: vmalloc-ed buffer to use for the reply
  * @buflen: the buffer size
  * @lba: Start LBA of the report
  * @partial: Do partial report
@@ -79,7 +81,6 @@ static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 	put_unaligned_be32(buflen, &cmd[10]);
 	if (partial)
 		cmd[14] = ZBC_REPORT_ZONE_PARTIAL;
-	memset(buf, 0, buflen);
 
 	result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE,
 				  buf, buflen, &sshdr,
@@ -103,45 +104,83 @@ static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 	return 0;
 }
 
+/*
+ * Maximum number of zones to get with one report zones command.
+ */
+#define SD_ZBC_REPORT_MAX_ZONES		8192U
+
+/**
+ * Allocate a buffer for report zones reply.
+ * @sdkp: The target disk
+ * @nr_zones: Maximum number of zones to report
+ * @buflen: Size of the buffer allocated
+ *
+ * Try to allocate a reply buffer for the number of requested zones.
+ * The size of the buffer allocated may be smaller than requested to
+ * satify the device constraint (max_hw_sectors, max_segments, etc).
+ *
+ * Return the address of the allocated buffer and update @buflen with
+ * the size of the allocated buffer.
+ */
+static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
+					unsigned int nr_zones, size_t *buflen)
+{
+	struct request_queue *q = sdkp->disk->queue;
+	size_t bufsize;
+	void *buf;
+
+	/*
+	 * Report zone buffer size should be at most 64B times the number of
+	 * zones requested plus the 64B reply header, but should be at least
+	 * SECTOR_SIZE for ATA devices.
+	 * Make sure that this size does not exceed the hardware capabilities.
+	 * Furthermore, since the report zone command cannot be split, make
+	 * sure that the allocated buffer can always be mapped by limiting the
+	 * number of pages allocated to the HBA max segments limit.
+	 */
+	nr_zones = min(nr_zones, SD_ZBC_REPORT_MAX_ZONES);
+	bufsize = roundup((nr_zones + 1) * 64, 512);
+	bufsize = min_t(size_t, bufsize,
+			queue_max_hw_sectors(q) << SECTOR_SHIFT);
+	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
+
+	buf = vzalloc(bufsize);
+	if (buf)
+		*buflen = bufsize;
+
+	return buf;
+}
+
 /**
  * sd_zbc_report_zones - Disk report zones operation.
  * @disk: The target disk
  * @sector: Start 512B sector of the report
  * @zones: Array of zone descriptors
  * @nr_zones: Number of descriptors in the array
- * @gfp_mask: Memory allocation mask
  *
  * Execute a report zones command on the target disk.
  */
 int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
-			struct blk_zone *zones, unsigned int *nr_zones,
+			struct blk_zone *zones, unsigned int *nr_zones)
-			gfp_t gfp_mask)
 {
 	struct scsi_disk *sdkp = scsi_disk(disk);
-	unsigned int i, buflen, nrz = *nr_zones;
+	unsigned int i, nrz = *nr_zones;
 	unsigned char *buf;
-	size_t offset = 0;
+	size_t buflen = 0, offset = 0;
 	int ret = 0;
 
 	if (!sd_is_zoned(sdkp))
 		/* Not a zoned device */
 		return -EOPNOTSUPP;
 
-	/*
+	buf = sd_zbc_alloc_report_buffer(sdkp, nrz, &buflen);
-	 * Get a reply buffer for the number of requested zones plus a header,
-	 * without exceeding the device maximum command size. For ATA disks,
-	 * buffers must be aligned to 512B.
-	 */
-	buflen = min(queue_max_hw_sectors(disk->queue) << 9,
-		     roundup((nrz + 1) * 64, 512));
-	buf = kmalloc(buflen, gfp_mask);
 	if (!buf)
 		return -ENOMEM;
 
 	ret = sd_zbc_do_report_zones(sdkp, buf, buflen,
 			sectors_to_logical(sdkp->device, sector), true);
 	if (ret)
-		goto out_free_buf;
+		goto out;
 
 	nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64);
 	for (i = 0; i < nrz; i++) {
@@ -152,8 +191,8 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
 
 	*nr_zones = nrz;
 
-out_free_buf:
+out:
-	kfree(buf);
+	kvfree(buf);
 
 	return ret;
 }
@@ -287,8 +326,6 @@ static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp,
 	return 0;
 }
 
-#define SD_ZBC_BUF_SIZE 131072U
-
 /**
  * sd_zbc_check_zones - Check the device capacity and zone sizes
  * @sdkp: Target disk
@@ -304,22 +341,28 @@ static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp,
  */
 static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 {
+	size_t bufsize, buflen;
+	unsigned int noio_flag;
 	u64 zone_blocks = 0;
 	sector_t max_lba, block = 0;
 	unsigned char *buf;
 	unsigned char *rec;
-	unsigned int buf_len;
-	unsigned int list_length;
 	int ret;
 	u8 same;
 
+	/* Do all memory allocations as if GFP_NOIO was specified */
+	noio_flag = memalloc_noio_save();
+
 	/* Get a buffer */
-	buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
+	buf = sd_zbc_alloc_report_buffer(sdkp, SD_ZBC_REPORT_MAX_ZONES,
-	if (!buf)
+					 &bufsize);
-		return -ENOMEM;
+	if (!buf) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	/* Do a report zone to get max_lba and the same field */
-	ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0, false);
+	ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, 0, false);
 	if (ret)
 		goto out_free;
 
@@ -355,12 +398,12 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 	do {
 
 		/* Parse REPORT ZONES header */
-		list_length = get_unaligned_be32(&buf[0]) + 64;
+		buflen = min_t(size_t, get_unaligned_be32(&buf[0]) + 64,
+			       bufsize);
 		rec = buf + 64;
-		buf_len = min(list_length, SD_ZBC_BUF_SIZE);
 
 		/* Parse zone descriptors */
-		while (rec < buf + buf_len) {
+		while (rec < buf + buflen) {
 			u64 this_zone_blocks = get_unaligned_be64(&rec[8]);
 
 			if (zone_blocks == 0) {
@@ -376,8 +419,8 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 		}
 
 		if (block < sdkp->capacity) {
-			ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
+			ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, block,
-						     block, true);
+						     true);
 			if (ret)
 				goto out_free;
 		}
@@ -408,7 +451,8 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 	}
 
 out_free:
-	kfree(buf);
+	memalloc_noio_restore(noio_flag);
+	kvfree(buf);
 
 	return ret;
 }

fs/btrfs/extent_io.c

@@ -2911,7 +2911,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 			bio = NULL;
 		} else {
 			if (wbc)
-				wbc_account_io(wbc, page, page_size);
+				wbc_account_cgroup_owner(wbc, page, page_size);
 			return 0;
 		}
 	}
@@ -2924,7 +2924,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 	bio->bi_opf = opf;
 	if (wbc) {
 		wbc_init_bio(wbc, bio);
-		wbc_account_io(wbc, page, page_size);
+		wbc_account_cgroup_owner(wbc, page, page_size);
 	}
 
 	*bio_ret = bio;

fs/buffer.c

@@ -3089,7 +3089,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 
 	if (wbc) {
 		wbc_init_bio(wbc, bio);
-		wbc_account_io(wbc, bh->b_page, bh->b_size);
+		wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size);
 	}
 
 	submit_bio(bio);

fs/ext4/page-io.c

@@ -396,7 +396,7 @@ static int io_submit_add_bh(struct ext4_io_submit *io,
 	ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh));
 	if (ret != bh->b_size)
 		goto submit_and_retry;
-	wbc_account_io(io->io_wbc, page, bh->b_size);
+	wbc_account_cgroup_owner(io->io_wbc, page, bh->b_size);
 	io->io_next_block++;
 	return 0;
 }

fs/f2fs/data.c

@@ -470,7 +470,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	}
 
 	if (fio->io_wbc && !is_read_io(fio->op))
-		wbc_account_io(fio->io_wbc, page, PAGE_SIZE);
+		wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
 
 	bio_set_op_attrs(bio, fio->op, fio->op_flags);
 
@@ -513,7 +513,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
 	}
 
 	if (fio->io_wbc)
-		wbc_account_io(fio->io_wbc, page, PAGE_SIZE);
+		wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
 
 	inc_page_count(fio->sbi, WB_DATA_TYPE(page));
 
@@ -592,7 +592,7 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
 	}
 
 	if (fio->io_wbc)
-		wbc_account_io(fio->io_wbc, bio_page, PAGE_SIZE);
+		wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE);
 
 	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);

fs/f2fs/super.c

@@ -2818,9 +2818,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 	while (zones && sector < nr_sectors) {
 
 		nr_zones = F2FS_REPORT_NR_ZONES;
-		err = blkdev_report_zones(bdev, sector,
+		err = blkdev_report_zones(bdev, sector, zones, &nr_zones);
-					  zones, &nr_zones,
-					  GFP_KERNEL);
 		if (err)
 			break;
 		if (!nr_zones) {

fs/fs-writeback.c

@@ -270,6 +270,7 @@ void __inode_attach_wb(struct inode *inode, struct page *page)
 	if (unlikely(cmpxchg(&inode->i_wb, NULL, wb)))
 		wb_put(wb);
 }
+EXPORT_SYMBOL_GPL(__inode_attach_wb);
 
 /**
  * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it
@@ -582,6 +583,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
 	if (unlikely(wb_dying(wbc->wb)))
 		inode_switch_wbs(inode, wbc->wb_id);
 }
+EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode);
 
 /**
  * wbc_detach_inode - disassociate wbc from inode and perform foreign detection
@@ -701,9 +703,10 @@ void wbc_detach_inode(struct writeback_control *wbc)
 	wb_put(wbc->wb);
 	wbc->wb = NULL;
 }
+EXPORT_SYMBOL_GPL(wbc_detach_inode);
 
 /**
- * wbc_account_io - account IO issued during writeback
+ * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership
  * @wbc: writeback_control of the writeback in progress
  * @page: page being written out
  * @bytes: number of bytes being written out
@@ -712,8 +715,8 @@ void wbc_detach_inode(struct writeback_control *wbc)
  * controlled by @wbc.  Keep the book for foreign inode detection.  See
  * wbc_detach_inode().
  */
-void wbc_account_io(struct writeback_control *wbc, struct page *page,
+void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
-		    size_t bytes)
+			      size_t bytes)
 {
 	struct cgroup_subsys_state *css;
 	int id;
@@ -724,7 +727,7 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page,
 	 * behind a slow cgroup.  Ultimately, we want pageout() to kick off
 	 * regular writeback instead of writing things out itself.
 	 */
-	if (!wbc->wb)
+	if (!wbc->wb || wbc->no_cgroup_owner)
 		return;
 
 	css = mem_cgroup_css_from_page(page);
@@ -750,7 +753,7 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page,
 	else
 		wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes);
 }
-EXPORT_SYMBOL_GPL(wbc_account_io);
+EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner);
 
 /**
  * inode_congested - test whether an inode is congested

fs/mpage.c

@@ -647,7 +647,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	 * the confused fail path above (OOM) will be very confused when
 	 * it finds all bh marked clean (i.e. it will not write anything)
 	 */
-	wbc_account_io(wbc, page, PAGE_SIZE);
+	wbc_account_cgroup_owner(wbc, page, PAGE_SIZE);
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
 		bio = mpage_bio_submit(REQ_OP_WRITE, op_flags, bio);

fs/xfs/xfs_aops.c

@@ -796,7 +796,7 @@ xfs_add_to_ioend(
 	}
 
 	wpc->ioend->io_size += len;
-	wbc_account_io(wbc, page, len);
+	wbc_account_cgroup_owner(wbc, page, len);
 }
 
 STATIC void

include/linux/backing-dev.h

@@ -48,6 +48,7 @@ extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
 
 extern struct workqueue_struct *bdi_wq;
+extern struct workqueue_struct *bdi_async_bio_wq;
 
 static inline bool wb_has_dirty_io(struct bdi_writeback *wb)
 {

include/linux/blk-cgroup.h

@@ -132,13 +132,17 @@ struct blkcg_gq {
 
 	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
 
-	struct rcu_head			rcu_head;
+	spinlock_t			async_bio_lock;
+	struct bio_list			async_bios;
+	struct work_struct		async_bio_work;
 
 	atomic_t			use_delay;
 	atomic64_t			delay_nsec;
 	atomic64_t			delay_start;
 	u64				last_delay;
 	int				last_use;
+
+	struct rcu_head			rcu_head;
 };
 
 typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
@@ -701,6 +705,15 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg
 				  struct bio *bio) { return false; }
 #endif
 
+bool __blkcg_punt_bio_submit(struct bio *bio);
+
+static inline bool blkcg_punt_bio_submit(struct bio *bio)
+{
+	if (bio->bi_opf & REQ_CGROUP_PUNT)
+		return __blkcg_punt_bio_submit(bio);
+	else
+		return false;
+}
 
 static inline void blkcg_bio_issue_init(struct bio *bio)
 {
@@ -848,6 +861,7 @@ static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; }
 static inline void blkg_get(struct blkcg_gq *blkg) { }
 static inline void blkg_put(struct blkcg_gq *blkg) { }
 
+static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; }
 static inline void blkcg_bio_issue_init(struct bio *bio) { }
 static inline bool blkcg_bio_issue_check(struct request_queue *q,
 					 struct bio *bio) { return true; }

include/linux/blk_types.h

@@ -311,6 +311,14 @@ enum req_flag_bits {
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
 	__REQ_BACKGROUND,	/* background IO */
 	__REQ_NOWAIT,           /* Don't wait if request will block */
+	/*
+	 * When a shared kthread needs to issue a bio for a cgroup, doing
+	 * so synchronously can lead to priority inversions as the kthread
+	 * can be trapped waiting for that cgroup.  CGROUP_PUNT flag makes
+	 * submit_bio() punt the actual issuing to a dedicated per-blkcg
+	 * work item to avoid such priority inversions.
+	 */
+	__REQ_CGROUP_PUNT,
 
 	/* command specific flags for REQ_OP_WRITE_ZEROES: */
 	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
@@ -337,6 +345,8 @@ enum req_flag_bits {
 #define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
 #define REQ_BACKGROUND		(1ULL << __REQ_BACKGROUND)
 #define REQ_NOWAIT		(1ULL << __REQ_NOWAIT)
+#define REQ_CGROUP_PUNT		(1ULL << __REQ_CGROUP_PUNT)
+
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
 #define REQ_HIPRI		(1ULL << __REQ_HIPRI)
 

include/linux/blkdev.h

@@ -344,10 +344,15 @@ struct queue_limits {
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
+/*
+ * Maximum number of zones to report with a single report zones command.
+ */
+#define BLK_ZONED_REPORT_MAX_ZONES	8192U
+
 extern unsigned int blkdev_nr_zones(struct block_device *bdev);
 extern int blkdev_report_zones(struct block_device *bdev,
 			       sector_t sector, struct blk_zone *zones,
-			       unsigned int *nr_zones, gfp_t gfp_mask);
+			       unsigned int *nr_zones);
 extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
 			      sector_t nr_sectors, gfp_t gfp_mask);
 extern int blk_revalidate_disk_zones(struct gendisk *disk);
@@ -681,7 +686,7 @@ static inline bool blk_queue_is_zoned(struct request_queue *q)
 	}
 }
 
-static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
+static inline sector_t blk_queue_zone_sectors(struct request_queue *q)
 {
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
@@ -1418,7 +1423,7 @@ static inline bool bdev_is_zoned(struct block_device *bdev)
 	return false;
 }
 
-static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
+static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 
@@ -1673,8 +1678,7 @@ struct block_device_operations {
 	/* this callback is with swap_lock and sometimes page table lock held */
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 	int (*report_zones)(struct gendisk *, sector_t sector,
-			    struct blk_zone *zones, unsigned int *nr_zones,
+			    struct blk_zone *zones, unsigned int *nr_zones);
-			    gfp_t gfp_mask);
 	struct module *owner;
 	const struct pr_ops *pr_ops;
 };

include/linux/cgroup.h

@@ -699,6 +699,7 @@ void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
 struct cgroup_subsys_state;
 struct cgroup;
 
+static inline void css_get(struct cgroup_subsys_state *css) {}
 static inline void css_put(struct cgroup_subsys_state *css) {}
 static inline int cgroup_attach_task_all(struct task_struct *from,
 					 struct task_struct *t) { return 0; }

include/linux/device-mapper.h

@@ -95,8 +95,7 @@ typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **
 
 typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector,
 				   struct blk_zone *zones,
-				   unsigned int *nr_zones,
+				   unsigned int *nr_zones);
-				   gfp_t gfp_mask);
 
 /*
  * These iteration functions are typically used to check (and combine)

include/linux/elevator.h

@@ -75,7 +75,7 @@ struct elevator_type
 	size_t icq_size;	/* see iocontext.h */
 	size_t icq_align;	/* ditto */
 	struct elv_fs_entry *elevator_attrs;
-	char elevator_name[ELV_NAME_MAX];
+	const char *elevator_name;
 	const char *elevator_alias;
 	struct module *elevator_owner;
 #ifdef CONFIG_BLK_DEBUG_FS
@@ -160,15 +160,6 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t);
 #define ELEVATOR_INSERT_FLUSH	5
 #define ELEVATOR_INSERT_SORT_MERGE	6
 
-/*
- * return values from elevator_may_queue_fn
- */
-enum {
-	ELV_MQUEUE_MAY,
-	ELV_MQUEUE_NO,
-	ELV_MQUEUE_MUST,
-};
-
 #define rq_end_sector(rq)	(blk_rq_pos(rq) + blk_rq_sectors(rq))
 #define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
 

include/linux/nvme.h

@@ -315,7 +315,7 @@ struct nvme_id_ns {
 	__u8			nmic;
 	__u8			rescap;
 	__u8			fpi;
-	__u8			rsvd33;
+	__u8			dlfeat;
 	__le16			nawun;
 	__le16			nawupf;
 	__le16			nacwu;
@@ -324,11 +324,17 @@ struct nvme_id_ns {
 	__le16			nabspf;
 	__le16			noiob;
 	__u8			nvmcap[16];
-	__u8			rsvd64[28];
+	__le16			npwg;
+	__le16			npwa;
+	__le16			npdg;
+	__le16			npda;
+	__le16			nows;
+	__u8			rsvd74[18];
 	__le32			anagrpid;
 	__u8			rsvd96[3];
 	__u8			nsattr;
-	__u8			rsvd100[4];
+	__le16			nvmsetid;
+	__le16			endgid;
 	__u8			nguid[16];
 	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];

include/linux/writeback.h

@@ -11,6 +11,7 @@
 #include <linux/flex_proportions.h>
 #include <linux/backing-dev-defs.h>
 #include <linux/blk_types.h>
+#include <linux/blk-cgroup.h>
 
 struct bio;
 
@@ -68,6 +69,17 @@ struct writeback_control {
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned for_sync:1;		/* sync(2) WB_SYNC_ALL writeback */
+
+	/*
+	 * When writeback IOs are bounced through async layers, only the
+	 * initial synchronous phase should be accounted towards inode
+	 * cgroup ownership arbitration to avoid confusion.  Later stages
+	 * can set the following flag to disable the accounting.
+	 */
+	unsigned no_cgroup_owner:1;
+
+	unsigned punt_to_cgroup:1;	/* cgrp punting, see __REQ_CGROUP_PUNT */
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct bdi_writeback *wb;	/* wb this writeback is issued under */
 	struct inode *inode;		/* inode being written out */
@@ -84,12 +96,27 @@ struct writeback_control {
 
 static inline int wbc_to_write_flags(struct writeback_control *wbc)
 {
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	int flags = 0;
-		return REQ_SYNC;
-	else if (wbc->for_kupdate || wbc->for_background)
-		return REQ_BACKGROUND;
 
-	return 0;
+	if (wbc->punt_to_cgroup)
+		flags = REQ_CGROUP_PUNT;
+
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		flags |= REQ_SYNC;
+	else if (wbc->for_kupdate || wbc->for_background)
+		flags |= REQ_BACKGROUND;
+
+	return flags;
+}
+
+static inline struct cgroup_subsys_state *
+wbc_blkcg_css(struct writeback_control *wbc)
+{
+#ifdef CONFIG_CGROUP_WRITEBACK
+	if (wbc->wb)
+		return wbc->wb->blkcg_css;
+#endif
+	return blkcg_root_css;
 }
 
 /*
@@ -188,8 +215,8 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
 				 struct inode *inode)
 	__releases(&inode->i_lock);
 void wbc_detach_inode(struct writeback_control *wbc);
-void wbc_account_io(struct writeback_control *wbc, struct page *page,
+void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
-		    size_t bytes);
+			      size_t bytes);
 void cgroup_writeback_umount(void);
 
 /**
@@ -291,8 +318,8 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
 {
 }
 
-static inline void wbc_account_io(struct writeback_control *wbc,
+static inline void wbc_account_cgroup_owner(struct writeback_control *wbc,
-				  struct page *page, size_t bytes)
+					    struct page *page, size_t bytes)
 {
 }