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()
  ...

9 files changed, 81 insertions, 28 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f9b029180241..35b31d176f74 100644
--- a/include/linux/backing-dev.h
+++ b/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)
 {
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 33f23a858438..689a58231288 100644
--- a/include/linux/blk-cgroup.h
+++ b/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; }
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 6a53799c3fe2..feff3fe4467e 100644
--- a/include/linux/blk_types.h
+++ b/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)
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0c482371c8b3..1ef375dafb1c 100644
--- a/include/linux/blkdev.h
+++ b/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,
-			    gfp_t gfp_mask);
+			    struct blk_zone *zones, unsigned int *nr_zones);
 	struct module *owner;
 	const struct pr_ops *pr_ops;
 };
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 2af9b1b419f1..f6b048902d6c 100644
--- a/include/linux/cgroup.h
+++ b/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; }
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index e1f51d607cc5..3b470cb03b66 100644
--- a/include/linux/device-mapper.h
+++ b/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,
-				   gfp_t gfp_mask);
+				   unsigned int *nr_zones);
 
 /*
  * These iteration functions are typically used to check (and combine)
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 169bb2e02516..17cd0078377c 100644
--- a/include/linux/elevator.h
+++ b/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)
 
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index d98b2d8baf4e..01aa6a6c241d 100644
--- a/include/linux/nvme.h
+++ b/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];
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 738a0c24874f..8945aac31392 100644
--- a/include/linux/writeback.h
+++ b/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)
 {
+	int flags = 0;
+
+	if (wbc->punt_to_cgroup)
+		flags = REQ_CGROUP_PUNT;
+
 	if (wbc->sync_mode == WB_SYNC_ALL)
-		return REQ_SYNC;
+		flags |= REQ_SYNC;
 	else if (wbc->for_kupdate || wbc->for_background)
-		return REQ_BACKGROUND;
+		flags |= REQ_BACKGROUND;
 
-	return 0;
+	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,
-		    size_t bytes);
+void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
+			      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,
-				  struct page *page, size_t bytes)
+static inline void wbc_account_cgroup_owner(struct writeback_control *wbc,
+					    struct page *page, size_t bytes)
 {
 }