Merge tag 'for-5.2/block-20190507' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Nothing major in this series, just fixes and improvements all over the
  map. This contains:

   - Series of fixes for sed-opal (David, Jonas)

   - Fixes and performance tweaks for BFQ (via Paolo)

   - Set of fixes for bcache (via Coly)

   - Set of fixes for md (via Song)

   - Enabling multi-page for passthrough requests (Ming)

   - Queue release fix series (Ming)

   - Device notification improvements (Martin)

   - Propagate underlying device rotational status in loop (Holger)

   - Removal of mtip32xx trim support, which has been disabled for years
     (Christoph)

   - Improvement and cleanup of nvme command handling (Christoph)

   - Add block SPDX tags (Christoph)

   - Cleanup/hardening of bio/bvec iteration (Christoph)

   - A few NVMe pull requests (Christoph)

   - Removal of CONFIG_LBDAF (Christoph)

   - Various little fixes here and there"

* tag 'for-5.2/block-20190507' of git://git.kernel.dk/linux-block: (164 commits)
  block: fix mismerge in bvec_advance
  block: don't drain in-progress dispatch in blk_cleanup_queue()
  blk-mq: move cancel of hctx->run_work into blk_mq_hw_sysfs_release
  blk-mq: always free hctx after request queue is freed
  blk-mq: split blk_mq_alloc_and_init_hctx into two parts
  blk-mq: free hw queue's resource in hctx's release handler
  blk-mq: move cancel of requeue_work into blk_mq_release
  blk-mq: grab .q_usage_counter when queuing request from plug code path
  block: fix function name in comment
  nvmet: protect discovery change log event list iteration
  nvme: mark nvme_core_init and nvme_core_exit static
  nvme: move command size checks to the core
  nvme-fabrics: check more command sizes
  nvme-pci: check more command sizes
  nvme-pci: remove an unneeded variable initialization
  nvme-pci: unquiesce admin queue on shutdown
  nvme-pci: shutdown on timeout during deletion
  nvme-pci: fix psdt field for single segment sgls
  nvme-multipath: don't print ANA group state by default
  nvme-multipath: split bios with the ns_head bio_set before submitting
  ...

14 files changed, 92 insertions, 120 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index e584673c1881..ea73df36529a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -1,19 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2001 Jens Axboe <axboe@suse.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- *
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public Licens
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
  */
 #ifndef __LINUX_BIO_H
 #define __LINUX_BIO_H
@@ -134,9 +121,8 @@ static inline bool bio_next_segment(const struct bio *bio,
  * drivers should _never_ use the all version - the bio may have been split
  * before it got to the driver and the driver won't own all of it
  */
-#define bio_for_each_segment_all(bvl, bio, i, iter)			\
-	for (i = 0, bvl = bvec_init_iter_all(&iter);			\
-	     bio_next_segment((bio), &iter); i++)
+#define bio_for_each_segment_all(bvl, bio, iter) \
+	for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); )
 
 static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
 				    unsigned bytes)
diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h
index 7b6ecf9ac4c3..5cc5f0f36218 100644
--- a/include/linux/blk-mq-rdma.h
+++ b/include/linux/blk-mq-rdma.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_BLK_MQ_RDMA_H
 #define _LINUX_BLK_MQ_RDMA_H
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index db29928de467..15d1aa53d96c 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -70,6 +70,8 @@ struct blk_mq_hw_ctx {
 	struct dentry		*sched_debugfs_dir;
 #endif
 
+	struct list_head	hctx_list;
+
 	/* Must be the last member - see also blk_mq_hw_ctx_size(). */
 	struct srcu_struct	srcu[0];
 };
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 791fee35df88..be418275763c 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -215,21 +215,24 @@ struct bio {
 /*
  * bio flags
  */
-#define BIO_NO_PAGE_REF	0	/* don't put release vec pages */
-#define BIO_SEG_VALID	1	/* bi_phys_segments valid */
-#define BIO_CLONED	2	/* doesn't own data */
-#define BIO_BOUNCED	3	/* bio is a bounce bio */
-#define BIO_USER_MAPPED 4	/* contains user pages */
-#define BIO_NULL_MAPPED 5	/* contains invalid user pages */
-#define BIO_QUIET	6	/* Make BIO Quiet */
-#define BIO_CHAIN	7	/* chained bio, ->bi_remaining in effect */
-#define BIO_REFFED	8	/* bio has elevated ->bi_cnt */
-#define BIO_THROTTLED	9	/* This bio has already been subjected to
+enum {
+	BIO_NO_PAGE_REF,	/* don't put release vec pages */
+	BIO_SEG_VALID,		/* bi_phys_segments valid */
+	BIO_CLONED,		/* doesn't own data */
+	BIO_BOUNCED,		/* bio is a bounce bio */
+	BIO_USER_MAPPED,	/* contains user pages */
+	BIO_NULL_MAPPED,	/* contains invalid user pages */
+	BIO_QUIET,		/* Make BIO Quiet */
+	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
+	BIO_REFFED,		/* bio has elevated ->bi_cnt */
+	BIO_THROTTLED,		/* This bio has already been subjected to
 				 * throttling rules. Don't do it again. */
-#define BIO_TRACE_COMPLETION 10	/* bio_endio() should trace the final completion
+	BIO_TRACE_COMPLETION,	/* bio_endio() should trace the final completion
 				 * of this bio. */
-#define BIO_QUEUE_ENTERED 11	/* can use blk_queue_enter_live() */
-#define BIO_TRACKED 12		/* set if bio goes through the rq_qos path */
+	BIO_QUEUE_ENTERED,	/* can use blk_queue_enter_live() */
+	BIO_TRACKED,		/* set if bio goes through the rq_qos path */
+	BIO_FLAG_LAST
+};
 
 /* See BVEC_POOL_OFFSET below before adding new flags */
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 317ab30d2904..1aafeb923e7b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -535,6 +535,13 @@ struct request_queue {
 
 	struct mutex		sysfs_lock;
 
+	/*
+	 * for reusing dead hctx instance in case of updating
+	 * nr_hw_queues
+	 */
+	struct list_head	unused_hctx_list;
+	spinlock_t		unused_hctx_lock;
+
 	atomic_t		mq_freeze_depth;
 
 #if defined(CONFIG_BLK_DEV_BSG)
@@ -640,6 +647,13 @@ static inline bool blk_account_rq(struct request *rq)
 
 #define rq_data_dir(rq)		(op_is_write(req_op(rq)) ? WRITE : READ)
 
+#define rq_dma_dir(rq) \
+	(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
+
+#define dma_map_bvec(dev, bv, dir, attrs) \
+	dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \
+	(dir), (attrs))
+
 static inline bool queue_is_mq(struct request_queue *q)
 {
 	return q->mq_ops;
@@ -931,6 +945,17 @@ static inline unsigned int blk_rq_payload_bytes(struct request *rq)
 	return blk_rq_bytes(rq);
 }
 
+/*
+ * Return the first full biovec in the request.  The caller needs to check that
+ * there are any bvecs before calling this helper.
+ */
+static inline struct bio_vec req_bvec(struct request *rq)
+{
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		return rq->special_vec;
+	return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
+}
+
 static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     int op)
 {
@@ -1051,7 +1076,6 @@ extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
 extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 			      sector_t offset);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
-extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern int blk_queue_dma_drain(struct request_queue *q,
 			       dma_drain_needed_fn *dma_drain_needed,
@@ -1547,6 +1571,17 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
 }
 
+/*
+ * Return the first bvec that contains integrity data.  Only drivers that are
+ * limited to a single integrity segment should use this helper.
+ */
+static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+{
+	if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
+		return NULL;
+	return rq->bio->bi_integrity->bip_vec;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct bio;
@@ -1621,6 +1656,11 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 	return 0;
 }
 
+static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct block_device_operations {
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index 7f14517a559b..960988d42f77 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -1,24 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  BSG helper library
  *
  *  Copyright (C) 2008   James Smart, Emulex Corporation
  *  Copyright (C) 2011   Red Hat, Inc.  All rights reserved.
  *  Copyright (C) 2011   Mike Christie
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
  */
 #ifndef _BLK_BSG_
 #define _BLK_BSG_
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index ff13cbc1887d..a032f01e928c 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -1,21 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * bvec iterator
  *
  * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- *
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public Licens
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
  */
 #ifndef __LINUX_BVEC_ITER_H
 #define __LINUX_BVEC_ITER_H
@@ -51,11 +38,6 @@ struct bvec_iter_all {
 	unsigned	done;
 };
 
-static inline struct page *bvec_nth_page(struct page *page, int idx)
-{
-	return idx == 0 ? page : nth_page(page, idx);
-}
-
 /*
  * various member access, note that bio_data should of course not be used
  * on highmem page vectors
@@ -92,8 +74,8 @@ static inline struct page *bvec_nth_page(struct page *page, int idx)
 	      PAGE_SIZE - bvec_iter_offset((bvec), (iter)))
 
 #define bvec_iter_page(bvec, iter)				\
-	bvec_nth_page(mp_bvec_iter_page((bvec), (iter)),		\
-		      mp_bvec_iter_page_idx((bvec), (iter)))
+	(mp_bvec_iter_page((bvec), (iter)) +			\
+	 mp_bvec_iter_page_idx((bvec), (iter)))
 
 #define bvec_iter_bvec(bvec, iter)				\
 ((struct bio_vec) {						\
@@ -157,11 +139,10 @@ static inline void bvec_advance(const struct bio_vec *bvec,
 	struct bio_vec *bv = &iter_all->bv;
 
 	if (iter_all->done) {
-		bv->bv_page = nth_page(bv->bv_page, 1);
+		bv->bv_page++;
 		bv->bv_offset = 0;
 	} else {
-		bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset /
-					    PAGE_SIZE);
+		bv->bv_page = bvec->bv_page + (bvec->bv_offset >> PAGE_SHIFT);
 		bv->bv_offset = bvec->bv_offset & ~PAGE_MASK;
 	}
 	bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset,
@@ -184,7 +165,7 @@ static inline void mp_bvec_last_segment(const struct bio_vec *bvec,
 	unsigned total = bvec->bv_offset + bvec->bv_len;
 	unsigned last_page = (total - 1) / PAGE_SIZE;
 
-	seg->bv_page = bvec_nth_page(bvec->bv_page, last_page);
+	seg->bv_page = bvec->bv_page + last_page;
 
 	/* the whole segment is inside the last page */
 	if (bvec->bv_offset >= last_page * PAGE_SIZE) {
@@ -196,9 +177,4 @@ static inline void mp_bvec_last_segment(const struct bio_vec *bvec,
 	}
 }
 
-#define mp_bvec_for_each_page(pg, bv, i)				\
-	for (i = (bv)->bv_offset / PAGE_SIZE;				\
-		(i <= (((bv)->bv_offset + (bv)->bv_len - 1) / PAGE_SIZE)) && \
-		(pg = bvec_nth_page((bv)->bv_page, i)); i += 1)
-
 #endif /* __LINUX_BVEC_ITER_H */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 06c0fd594097..8b5330dd5ac0 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -150,6 +150,13 @@ enum {
 	DISK_EVENT_EJECT_REQUEST		= 1 << 1, /* eject requested */
 };
 
+enum {
+	/* Poll even if events_poll_msecs is unset */
+	DISK_EVENT_FLAG_POLL			= 1 << 0,
+	/* Forward events to udev */
+	DISK_EVENT_FLAG_UEVENT			= 1 << 1,
+};
+
 struct disk_part_tbl {
 	struct rcu_head rcu_head;
 	int len;
@@ -184,8 +191,8 @@ struct gendisk {
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 	char *(*devnode)(struct gendisk *gd, umode_t *mode);
 
-	unsigned int events;		/* supported events */
-	unsigned int async_events;	/* async events, subset of all */
+	unsigned short events;		/* supported events */
+	unsigned short event_flags;	/* flags related to event processing */
 
 	/* Array of pointers to partitions indexed by partno.
 	 * Protected with matching bdev lock but stat and other
@@ -610,6 +617,7 @@ struct unixware_disklabel {
 
 extern int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
 extern void blk_free_devt(dev_t devt);
+extern void blk_invalidate_devt(dev_t devt);
 extern dev_t blk_lookup_devt(const char *name, int partno);
 extern char *disk_name (struct gendisk *hd, int partno, char *buf);
 
@@ -714,7 +722,7 @@ static inline void hd_free_part(struct hd_struct *part)
  */
 static inline sector_t part_nr_sects_read(struct hd_struct *part)
 {
-#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	sector_t nr_sects;
 	unsigned seq;
 	do {
@@ -722,7 +730,7 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part)
 		nr_sects = part->nr_sects;
 	} while (read_seqcount_retry(&part->nr_sects_seq, seq));
 	return nr_sects;
-#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
 	sector_t nr_sects;
 
 	preempt_disable();
@@ -741,11 +749,11 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part)
  */
 static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 {
-#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	write_seqcount_begin(&part->nr_sects_seq);
 	part->nr_sects = size;
 	write_seqcount_end(&part->nr_sects_seq);
-#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
 	preempt_disable();
 	part->nr_sects = size;
 	preempt_enable();
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2d14e21c16c0..a3b59d143afb 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -17,6 +17,7 @@
 #include <asm/byteorder.h>
 #include <asm/div64.h>
 #include <uapi/linux/kernel.h>
+#include <asm/div64.h>
 
 #define STACK_MAGIC	0xdeadbeef
 
@@ -175,18 +176,7 @@
 #define _RET_IP_		(unsigned long)__builtin_return_address(0)
 #define _THIS_IP_  ({ __label__ __here; __here: (unsigned long)&&__here; })
 
-#ifdef CONFIG_LBDAF
-# define sector_div(a, b) do_div(a, b)
-#else
-# define sector_div(n, b)( \
-{ \
-	int _res; \
-	_res = (n) % (b); \
-	(n) /= (b); \
-	_res; \
-} \
-)
-#endif
+#define sector_div(a, b) do_div(a, b)
 
 /**
  * upper_32_bits - return bits 32-63 of a number
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 3aa97b98dc89..3ec8e50efa16 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -77,7 +77,7 @@ struct nvme_rdma_cm_rep {
  * struct nvme_rdma_cm_rej - rdma connect reject
  *
  * @recfmt:        format of the RDMA Private Data
- * @fsts:          error status for the associated connect request
+ * @sts:           error status for the associated connect request
  */
 struct nvme_rdma_cm_rej {
 	__le16		recfmt;
diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h
index 04b124fca51e..3e76b6d7d97f 100644
--- a/include/linux/sed-opal.h
+++ b/include/linux/sed-opal.h
@@ -1,18 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright © 2016 Intel Corporation
  *
  * Authors:
  *    Rafael Antognolli <rafael.antognolli@intel.com>
  *    Scott  Bauer      <scott.bauer@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #ifndef LINUX_OPAL_H
diff --git a/include/linux/types.h b/include/linux/types.h
index cc0dbbe551d5..231114ae38f4 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -127,13 +127,8 @@ typedef s64			int64_t;
  *
  * blkcnt_t is the type of the inode's block count.
  */
-#ifdef CONFIG_LBDAF
 typedef u64 sector_t;
 typedef u64 blkcnt_t;
-#else
-typedef unsigned long sector_t;
-typedef unsigned long blkcnt_t;
-#endif
 
 /*
  * The type of an index into the pagecache.
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
index 627624d35030..33e53b80cd1f 100644
--- a/include/uapi/linux/sed-opal.h
+++ b/include/uapi/linux/sed-opal.h
@@ -5,15 +5,6 @@
  * Authors:
  *    Rafael Antognolli <rafael.antognolli@intel.com>
  *    Scott  Bauer      <scott.bauer@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #ifndef _UAPI_SED_OPAL_H
@@ -58,7 +49,7 @@ struct opal_key {
 struct opal_lr_act {
 	struct opal_key key;
 	__u32 sum;
-	__u8    num_lrs;
+	__u8 num_lrs;
 	__u8 lr[OPAL_MAX_LRS];
 	__u8 align[2]; /* Align to 8 byte boundary */
 };
diff --git a/include/xen/xen.h b/include/xen/xen.h
index 19d032373de5..19a72f591e2b 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -43,8 +43,10 @@ extern struct hvm_start_info pvh_start_info;
 #endif	/* CONFIG_XEN_DOM0 */
 
 struct bio_vec;
+struct page;
+
 bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
-		const struct bio_vec *vec2);
+		const struct page *page);
 
 #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_XEN_BALLOON)
 extern u64 xen_saved_max_mem_size;