Merge tag 'for-4.20/block-20181021' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the main pull request for block changes for 4.20. This
  contains:

   - Series enabling runtime PM for blk-mq (Bart).

   - Two pull requests from Christoph for NVMe, with items such as;
      - Better AEN tracking
      - Multipath improvements
      - RDMA fixes
      - Rework of FC for target removal
      - Fixes for issues identified by static checkers
      - Fabric cleanups, as prep for TCP transport
      - Various cleanups and bug fixes

   - Block merging cleanups (Christoph)

   - Conversion of drivers to generic DMA mapping API (Christoph)

   - Series fixing ref count issues with blkcg (Dennis)

   - Series improving BFQ heuristics (Paolo, et al)

   - Series improving heuristics for the Kyber IO scheduler (Omar)

   - Removal of dangerous bio_rewind_iter() API (Ming)

   - Apply single queue IPI redirection logic to blk-mq (Ming)

   - Set of fixes and improvements for bcache (Coly et al)

   - Series closing a hotplug race with sysfs group attributes (Hannes)

   - Set of patches for lightnvm:
      - pblk trace support (Hans)
      - SPDX license header update (Javier)
      - Tons of refactoring patches to cleanly abstract the 1.2 and 2.0
        specs behind a common core interface. (Javier, Matias)
      - Enable pblk to use a common interface to retrieve chunk metadata
        (Matias)
      - Bug fixes (Various)

   - Set of fixes and updates to the blk IO latency target (Josef)

   - blk-mq queue number updates fixes (Jianchao)

   - Convert a bunch of drivers from the old legacy IO interface to
     blk-mq. This will conclude with the removal of the legacy IO
     interface itself in 4.21, with the rest of the drivers (me, Omar)

   - Removal of the DAC960 driver. The SCSI tree will introduce two
     replacement drivers for this (Hannes)"

* tag 'for-4.20/block-20181021' of git://git.kernel.dk/linux-block: (204 commits)
  block: setup bounce bio_sets properly
  blkcg: reassociate bios when make_request() is called recursively
  blkcg: fix edge case for blk_get_rl() under memory pressure
  nvme-fabrics: move controller options matching to fabrics
  nvme-rdma: always have a valid trsvcid
  mtip32xx: fully switch to the generic DMA API
  rsxx: switch to the generic DMA API
  umem: switch to the generic DMA API
  sx8: switch to the generic DMA API
  sx8: remove dead IF_64BIT_DMA_IS_POSSIBLE code
  skd: switch to the generic DMA API
  ubd: remove use of blk_rq_map_sg
  nvme-pci: remove duplicate check
  drivers/block: Remove DAC960 driver
  nvme-pci: fix hot removal during error handling
  nvmet-fcloop: suppress a compiler warning
  nvme-core: make implicit seed truncation explicit
  nvmet-fc: fix kernel-doc headers
  nvme-fc: rework the request initialization code
  nvme-fc: introduce struct nvme_fcp_op_w_sgl
  ...

12 files changed, 104 insertions, 269 deletions

diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 2cfbc531f63b..6b51826ab3d1 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -28,7 +28,6 @@
 #include <asm/byteorder.h>
 #include <asm/memory.h>
 #include <asm-generic/pci_iomap.h>
-#include <xen/xen.h>
 
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
@@ -459,20 +458,6 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
 
 #include <asm-generic/io.h>
 
-/*
- * can the hardware map this into one segment or not, given no other
- * constraints.
- */
-#define BIOVEC_MERGEABLE(vec1, vec2)	\
-	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
-
-struct bio_vec;
-extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
-				      const struct bio_vec *vec2);
-#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
-	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
-	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
-
 #ifdef CONFIG_MMU
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
 extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 35b2e50f17fb..9f8b915af3a7 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -31,8 +31,6 @@
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
 
-#include <xen/xen.h>
-
 /*
  * Generic IO read/write.  These perform native-endian accesses.
  */
@@ -205,12 +203,5 @@ extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
 
 extern int devmem_is_allowed(unsigned long pfn);
 
-struct bio_vec;
-extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
-				      const struct bio_vec *vec2);
-#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
-	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
-	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
-
 #endif	/* __KERNEL__ */
 #endif	/* __ASM_IO_H */
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index e9110b9b8bcd..38049357d6d3 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -73,7 +73,7 @@ static blk_qc_t nfhd_make_request(struct request_queue *queue, struct bio *bio)
 		len = bvec.bv_len;
 		len >>= 9;
 		nfhd_read_write(dev->id, 0, dir, sec >> shift, len >> shift,
-				bvec_to_phys(&bvec));
+				page_to_phys(bvec.bv_page) + bvec.bv_offset);
 		sec += len;
 	}
 	bio_endio(bio);
diff --git a/arch/m68k/include/asm/atafd.h b/arch/m68k/include/asm/atafd.h
deleted file mode 100644
index ad7014cad633..000000000000
--- a/arch/m68k/include/asm/atafd.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_M68K_FD_H
-#define _ASM_M68K_FD_H
-
-/* Definitions for the Atari Floppy driver */
-
-struct atari_format_descr {
-    int track;			/* to be formatted */
-    int head;			/*   ""     ""     */
-    int sect_offset;		/* offset of first sector */
-};
-
-#endif
diff --git a/arch/m68k/include/asm/atafdreg.h b/arch/m68k/include/asm/atafdreg.h
deleted file mode 100644
index c31b4919ed2d..000000000000
--- a/arch/m68k/include/asm/atafdreg.h
+++ /dev/null
@@ -1,80 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_FDREG_H
-#define _LINUX_FDREG_H
-
-/*
-** WD1772 stuff
- */
-
-/* register codes */
-
-#define FDCSELREG_STP   (0x80)   /* command/status register */
-#define FDCSELREG_TRA   (0x82)   /* track register */
-#define FDCSELREG_SEC   (0x84)   /* sector register */
-#define FDCSELREG_DTA   (0x86)   /* data register */
-
-/* register names for FDC_READ/WRITE macros */
-
-#define FDCREG_CMD		0
-#define FDCREG_STATUS	0
-#define FDCREG_TRACK	2
-#define FDCREG_SECTOR	4
-#define FDCREG_DATA		6
-
-/* command opcodes */
-
-#define FDCCMD_RESTORE  (0x00)   /*  -                   */
-#define FDCCMD_SEEK     (0x10)   /*   |                  */
-#define FDCCMD_STEP     (0x20)   /*   |  TYP 1 Commands  */
-#define FDCCMD_STIN     (0x40)   /*   |                  */
-#define FDCCMD_STOT     (0x60)   /*  -                   */
-#define FDCCMD_RDSEC    (0x80)   /*  -   TYP 2 Commands  */
-#define FDCCMD_WRSEC    (0xa0)   /*  -          "        */
-#define FDCCMD_RDADR    (0xc0)   /*  -                   */
-#define FDCCMD_RDTRA    (0xe0)   /*   |  TYP 3 Commands  */
-#define FDCCMD_WRTRA    (0xf0)   /*  -                   */
-#define FDCCMD_FORCI    (0xd0)   /*  -   TYP 4 Command   */
-
-/* command modifier bits */
-
-#define FDCCMDADD_SR6   (0x00)   /* step rate settings */
-#define FDCCMDADD_SR12  (0x01)
-#define FDCCMDADD_SR2   (0x02)
-#define FDCCMDADD_SR3   (0x03)
-#define FDCCMDADD_V     (0x04)   /* verify */
-#define FDCCMDADD_H     (0x08)   /* wait for spin-up */
-#define FDCCMDADD_U     (0x10)   /* update track register */
-#define FDCCMDADD_M     (0x10)   /* multiple sector access */
-#define FDCCMDADD_E     (0x04)   /* head settling flag */
-#define FDCCMDADD_P     (0x02)   /* precompensation off */
-#define FDCCMDADD_A0    (0x01)   /* DAM flag */
-
-/* status register bits */
-
-#define	FDCSTAT_MOTORON	(0x80)   /* motor on */
-#define	FDCSTAT_WPROT	(0x40)   /* write protected (FDCCMD_WR*) */
-#define	FDCSTAT_SPINUP	(0x20)   /* motor speed stable (Type I) */
-#define	FDCSTAT_DELDAM	(0x20)   /* sector has deleted DAM (Type II+III) */
-#define	FDCSTAT_RECNF	(0x10)   /* record not found */
-#define	FDCSTAT_CRC		(0x08)   /* CRC error */
-#define	FDCSTAT_TR00	(0x04)   /* Track 00 flag (Type I) */
-#define	FDCSTAT_LOST	(0x04)   /* Lost Data (Type II+III) */
-#define	FDCSTAT_IDX		(0x02)   /* Index status (Type I) */
-#define	FDCSTAT_DRQ		(0x02)   /* DRQ status (Type II+III) */
-#define	FDCSTAT_BUSY	(0x01)   /* FDC is busy */
-
-
-/* PSG Port A Bit Nr 0 .. Side Sel .. 0 -> Side 1  1 -> Side 2 */
-#define DSKSIDE     (0x01)
-
-#define DSKDRVNONE  (0x06)
-#define DSKDRV0     (0x02)
-#define DSKDRV1     (0x04)
-
-/* step rates */
-#define	FDCSTEP_6	0x00
-#define	FDCSTEP_12	0x01
-#define	FDCSTEP_2	0x02
-#define	FDCSTEP_3	0x03
-
-#endif
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 83c470364dfb..74c002ddc0ce 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -23,6 +23,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/ata.h>
 #include <linux/hdreg.h>
 #include <linux/cdrom.h>
@@ -142,7 +143,6 @@ struct cow {
 #define MAX_SG 64
 
 struct ubd {
-	struct list_head restart;
 	/* name (and fd, below) of the file opened for writing, either the
 	 * backing or the cow file. */
 	char *file;
@@ -156,11 +156,8 @@ struct ubd {
 	struct cow cow;
 	struct platform_device pdev;
 	struct request_queue *queue;
+	struct blk_mq_tag_set tag_set;
 	spinlock_t lock;
-	struct scatterlist sg[MAX_SG];
-	struct request *request;
-	int start_sg, end_sg;
-	sector_t rq_pos;
 };
 
 #define DEFAULT_COW { \
@@ -182,10 +179,6 @@ struct ubd {
 	.shared =		0, \
 	.cow =			DEFAULT_COW, \
 	.lock =			__SPIN_LOCK_UNLOCKED(ubd_devs.lock), \
-	.request =		NULL, \
-	.start_sg =		0, \
-	.end_sg =		0, \
-	.rq_pos =		0, \
 }
 
 /* Protected by ubd_lock */
@@ -196,6 +189,9 @@ static int fake_ide = 0;
 static struct proc_dir_entry *proc_ide_root = NULL;
 static struct proc_dir_entry *proc_ide = NULL;
 
+static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx,
+				 const struct blk_mq_queue_data *bd);
+
 static void make_proc_ide(void)
 {
 	proc_ide_root = proc_mkdir("ide", NULL);
@@ -436,11 +432,8 @@ __uml_help(udb_setup,
 "    in the boot output.\n\n"
 );
 
-static void do_ubd_request(struct request_queue * q);
-
 /* Only changed by ubd_init, which is an initcall. */
 static int thread_fd = -1;
-static LIST_HEAD(restart);
 
 /* Function to read several request pointers at a time
 * handling fractional reads if (and as) needed
@@ -498,9 +491,6 @@ static int bulk_req_safe_read(
 /* Called without dev->lock held, and only in interrupt context. */
 static void ubd_handler(void)
 {
-	struct ubd *ubd;
-	struct list_head *list, *next_ele;
-	unsigned long flags;
 	int n;
 	int count;
 
@@ -520,23 +510,17 @@ static void ubd_handler(void)
 			return;
 		}
 		for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
-			blk_end_request(
-				(*irq_req_buffer)[count]->req,
-				BLK_STS_OK,
-				(*irq_req_buffer)[count]->length
-			);
-			kfree((*irq_req_buffer)[count]);
+			struct io_thread_req *io_req = (*irq_req_buffer)[count];
+			int err = io_req->error ? BLK_STS_IOERR : BLK_STS_OK;
+
+			if (!blk_update_request(io_req->req, err, io_req->length))
+				__blk_mq_end_request(io_req->req, err);
+
+			kfree(io_req);
 		}
 	}
-	reactivate_fd(thread_fd, UBD_IRQ);
 
-	list_for_each_safe(list, next_ele, &restart){
-		ubd = container_of(list, struct ubd, restart);
-		list_del_init(&ubd->restart);
-		spin_lock_irqsave(&ubd->lock, flags);
-		do_ubd_request(ubd->queue);
-		spin_unlock_irqrestore(&ubd->lock, flags);
-	}
+	reactivate_fd(thread_fd, UBD_IRQ);
 }
 
 static irqreturn_t ubd_intr(int irq, void *dev)
@@ -857,6 +841,7 @@ static void ubd_device_release(struct device *dev)
 	struct ubd *ubd_dev = dev_get_drvdata(dev);
 
 	blk_cleanup_queue(ubd_dev->queue);
+	blk_mq_free_tag_set(&ubd_dev->tag_set);
 	*ubd_dev = ((struct ubd) DEFAULT_UBD);
 }
 
@@ -891,7 +876,7 @@ static int ubd_disk_register(int major, u64 size, int unit,
 
 	disk->private_data = &ubd_devs[unit];
 	disk->queue = ubd_devs[unit].queue;
-	device_add_disk(parent, disk);
+	device_add_disk(parent, disk, NULL);
 
 	*disk_out = disk;
 	return 0;
@@ -899,6 +884,10 @@ static int ubd_disk_register(int major, u64 size, int unit,
 
 #define ROUND_BLOCK(n) ((n + ((1 << 9) - 1)) & (-1 << 9))
 
+static const struct blk_mq_ops ubd_mq_ops = {
+	.queue_rq = ubd_queue_rq,
+};
+
 static int ubd_add(int n, char **error_out)
 {
 	struct ubd *ubd_dev = &ubd_devs[n];
@@ -915,15 +904,23 @@ static int ubd_add(int n, char **error_out)
 
 	ubd_dev->size = ROUND_BLOCK(ubd_dev->size);
 
-	INIT_LIST_HEAD(&ubd_dev->restart);
-	sg_init_table(ubd_dev->sg, MAX_SG);
+	ubd_dev->tag_set.ops = &ubd_mq_ops;
+	ubd_dev->tag_set.queue_depth = 64;
+	ubd_dev->tag_set.numa_node = NUMA_NO_NODE;
+	ubd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	ubd_dev->tag_set.driver_data = ubd_dev;
+	ubd_dev->tag_set.nr_hw_queues = 1;
 
-	err = -ENOMEM;
-	ubd_dev->queue = blk_init_queue(do_ubd_request, &ubd_dev->lock);
-	if (ubd_dev->queue == NULL) {
-		*error_out = "Failed to initialize device queue";
+	err = blk_mq_alloc_tag_set(&ubd_dev->tag_set);
+	if (err)
 		goto out;
+
+	ubd_dev->queue = blk_mq_init_queue(&ubd_dev->tag_set);
+	if (IS_ERR(ubd_dev->queue)) {
+		err = PTR_ERR(ubd_dev->queue);
+		goto out_cleanup;
 	}
+
 	ubd_dev->queue->queuedata = ubd_dev;
 	blk_queue_write_cache(ubd_dev->queue, true, false);
 
@@ -931,7 +928,7 @@ static int ubd_add(int n, char **error_out)
 	err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, &ubd_gendisk[n]);
 	if(err){
 		*error_out = "Failed to register device";
-		goto out_cleanup;
+		goto out_cleanup_tags;
 	}
 
 	if (fake_major != UBD_MAJOR)
@@ -949,6 +946,8 @@ static int ubd_add(int n, char **error_out)
 out:
 	return err;
 
+out_cleanup_tags:
+	blk_mq_free_tag_set(&ubd_dev->tag_set);
 out_cleanup:
 	blk_cleanup_queue(ubd_dev->queue);
 	goto out;
@@ -1290,123 +1289,82 @@ static void cowify_req(struct io_thread_req *req, unsigned long *bitmap,
 			   req->bitmap_words, bitmap_len);
 }
 
-/* Called with dev->lock held */
-static void prepare_request(struct request *req, struct io_thread_req *io_req,
-			    unsigned long long offset, int page_offset,
-			    int len, struct page *page)
+static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req,
+		u64 off, struct bio_vec *bvec)
 {
-	struct gendisk *disk = req->rq_disk;
-	struct ubd *ubd_dev = disk->private_data;
-
-	io_req->req = req;
-	io_req->fds[0] = (ubd_dev->cow.file != NULL) ? ubd_dev->cow.fd :
-		ubd_dev->fd;
-	io_req->fds[1] = ubd_dev->fd;
-	io_req->cow_offset = -1;
-	io_req->offset = offset;
-	io_req->length = len;
-	io_req->error = 0;
-	io_req->sector_mask = 0;
-
-	io_req->op = (rq_data_dir(req) == READ) ? UBD_READ : UBD_WRITE;
-	io_req->offsets[0] = 0;
-	io_req->offsets[1] = ubd_dev->cow.data_offset;
-	io_req->buffer = page_address(page) + page_offset;
-	io_req->sectorsize = 1 << 9;
-
-	if(ubd_dev->cow.file != NULL)
-		cowify_req(io_req, ubd_dev->cow.bitmap,
-			   ubd_dev->cow.bitmap_offset, ubd_dev->cow.bitmap_len);
-
-}
+	struct ubd *dev = hctx->queue->queuedata;
+	struct io_thread_req *io_req;
+	int ret;
 
-/* Called with dev->lock held */
-static void prepare_flush_request(struct request *req,
-				  struct io_thread_req *io_req)
-{
-	struct gendisk *disk = req->rq_disk;
-	struct ubd *ubd_dev = disk->private_data;
+	io_req = kmalloc(sizeof(struct io_thread_req), GFP_ATOMIC);
+	if (!io_req)
+		return -ENOMEM;
 
 	io_req->req = req;
-	io_req->fds[0] = (ubd_dev->cow.file != NULL) ? ubd_dev->cow.fd :
-		ubd_dev->fd;
-	io_req->op = UBD_FLUSH;
-}
+	if (dev->cow.file)
+		io_req->fds[0] = dev->cow.fd;
+	else
+		io_req->fds[0] = dev->fd;
 
-static bool submit_request(struct io_thread_req *io_req, struct ubd *dev)
-{
-	int n = os_write_file(thread_fd, &io_req,
-			     sizeof(io_req));
-	if (n != sizeof(io_req)) {
-		if (n != -EAGAIN)
-			printk("write to io thread failed, "
-			       "errno = %d\n", -n);
-		else if (list_empty(&dev->restart))
-			list_add(&dev->restart, &restart);
+	if (req_op(req) == REQ_OP_FLUSH) {
+		io_req->op = UBD_FLUSH;
+	} else {
+		io_req->fds[1] = dev->fd;
+		io_req->cow_offset = -1;
+		io_req->offset = off;
+		io_req->length = bvec->bv_len;
+		io_req->error = 0;
+		io_req->sector_mask = 0;
+
+		io_req->op = rq_data_dir(req) == READ ? UBD_READ : UBD_WRITE;
+		io_req->offsets[0] = 0;
+		io_req->offsets[1] = dev->cow.data_offset;
+		io_req->buffer = page_address(bvec->bv_page) + bvec->bv_offset;
+		io_req->sectorsize = 1 << 9;
+
+		if (dev->cow.file) {
+			cowify_req(io_req, dev->cow.bitmap,
+				   dev->cow.bitmap_offset, dev->cow.bitmap_len);
+		}
+	}
 
+	ret = os_write_file(thread_fd, &io_req, sizeof(io_req));
+	if (ret != sizeof(io_req)) {
+		if (ret != -EAGAIN)
+			pr_err("write to io thread failed: %d\n", -ret);
 		kfree(io_req);
-		return false;
 	}
-	return true;
+
+	return ret;
 }
 
-/* Called with dev->lock held */
-static void do_ubd_request(struct request_queue *q)
+static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx,
+				 const struct blk_mq_queue_data *bd)
 {
-	struct io_thread_req *io_req;
-	struct request *req;
-
-	while(1){
-		struct ubd *dev = q->queuedata;
-		if(dev->request == NULL){
-			struct request *req = blk_fetch_request(q);
-			if(req == NULL)
-				return;
-
-			dev->request = req;
-			dev->rq_pos = blk_rq_pos(req);
-			dev->start_sg = 0;
-			dev->end_sg = blk_rq_map_sg(q, req, dev->sg);
-		}
-
-		req = dev->request;
+	struct request *req = bd->rq;
+	int ret = 0;
 
-		if (req_op(req) == REQ_OP_FLUSH) {
-			io_req = kmalloc(sizeof(struct io_thread_req),
-					 GFP_ATOMIC);
-			if (io_req == NULL) {
-				if (list_empty(&dev->restart))
-					list_add(&dev->restart, &restart);
-				return;
-			}
-			prepare_flush_request(req, io_req);
-			if (submit_request(io_req, dev) == false)
-				return;
-		}
+	blk_mq_start_request(req);
 
-		while(dev->start_sg < dev->end_sg){
-			struct scatterlist *sg = &dev->sg[dev->start_sg];
-
-			io_req = kmalloc(sizeof(struct io_thread_req),
-					 GFP_ATOMIC);
-			if(io_req == NULL){
-				if(list_empty(&dev->restart))
-					list_add(&dev->restart, &restart);
-				return;
-			}
-			prepare_request(req, io_req,
-					(unsigned long long)dev->rq_pos << 9,
-					sg->offset, sg->length, sg_page(sg));
-
-			if (submit_request(io_req, dev) == false)
-				return;
-
-			dev->rq_pos += sg->length >> 9;
-			dev->start_sg++;
+	if (req_op(req) == REQ_OP_FLUSH) {
+		ret = ubd_queue_one_vec(hctx, req, 0, NULL);
+	} else {
+		struct req_iterator iter;
+		struct bio_vec bvec;
+		u64 off = (u64)blk_rq_pos(req) << 9;
+
+		rq_for_each_segment(bvec, req, iter) {
+			ret = ubd_queue_one_vec(hctx, req, off, &bvec);
+			if (ret < 0)
+				goto out;
+			off += bvec.bv_len;
 		}
-		dev->end_sg = 0;
-		dev->request = NULL;
 	}
+out:
+	if (ret < 0) {
+		blk_mq_requeue_request(req, true);
+	}
+	return BLK_STS_OK;
 }
 
 static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 6de64840dd22..9a92a3ac2ac5 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -369,18 +369,6 @@ extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
 
 extern bool is_early_ioremap_ptep(pte_t *ptep);
 
-#ifdef CONFIG_XEN
-#include <xen/xen.h>
-struct bio_vec;
-
-extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
-				      const struct bio_vec *vec2);
-
-#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
-	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
-	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
-#endif	/* CONFIG_XEN */
-
 #define IO_SPACE_LIMIT 0xffff
 
 #include <asm-generic/io.h>
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index d383140e1dc8..068d9b067c83 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_XEN_EVENTS_H
 #define _ASM_X86_XEN_EVENTS_H
 
+#include <xen/xen.h>
+
 enum ipi_vector {
 	XEN_RESCHEDULE_VECTOR,
 	XEN_CALL_FUNCTION_VECTOR,
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2eeddd814653..0ca46e03b830 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -5,6 +5,7 @@
 #include <linux/kexec.h>
 #include <linux/slab.h>
 
+#include <xen/xen.h>
 #include <xen/features.h>
 #include <xen/page.h>
 #include <xen/interface/memory.h>
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index c85d1a88f476..2a9025343534 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -11,6 +11,7 @@
 #include <asm/xen/interface.h>
 #include <asm/xen/hypercall.h>
 
+#include <xen/xen.h>
 #include <xen/interface/memory.h>
 #include <xen/interface/hvm/start_info.h>
 
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 33a783c77d96..b99585034dd2 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/export.h>
 
+#include <xen/xen.h>
 #include <xen/platform_pci.h>
 #include "xen-ops.h"
 
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 95997e6c0696..0972184f3f19 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -3,6 +3,7 @@
 #include <linux/interrupt.h>
 
 #include <asm/xen/hypercall.h>
+#include <xen/xen.h>
 #include <xen/page.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/vcpu.h>