Merge branch 'for-3.20/drivers' of git://git.kernel.dk/linux-block

Pull block driver changes from Jens Axboe:
 "This contains:

   - The 4k/partition fixes for brd from Boaz/Matthew.

   - A few xen front/back block fixes from David Vrabel and Roger Pau
     Monne.

   - Floppy changes from Takashi, cleaning the device file creation.

   - Switching libata to use the new blk-mq tagging policy, removing
     code (and a suboptimal implementation) from libata.  This will
     throw you a merge conflict, since a bug in the original libata
     tagging code was fixed since this code was branched.  Trivial.
     From Shaohua.

   - Conversion of loop to blk-mq, from Ming Lei.

   - Cleanup of the io_schedule() handling in bsg from Peter Zijlstra.
     He claims it improves on unreadable code, which will cost him a
     beer.

   - Maintainer update or NDB, now handled by Markus Pargmann.

   - NVMe:
        - Optimization from me that avoids a kmalloc/kfree per IO for
          smaller (<= 8KB) IO. This cuts about 1% of high IOPS CPU
          overhead.
        - Removal of (now) dead RCU code, a relic from before NVMe was
          converted to blk-mq"

* 'for-3.20/drivers' of git://git.kernel.dk/linux-block:
  xen-blkback: default to X86_32 ABI on x86
  xen-blkfront: fix accounting of reqs when migrating
  xen-blkback,xen-blkfront: add myself as maintainer
  block: Simplify bsg complete all
  floppy: Avoid manual call of device_create_file()
  NVMe: avoid kmalloc/kfree for smaller IO
  MAINTAINERS: Update NBD maintainer
  libata: make sata_sil24 use fifo tag allocator
  libata: move sas ata tag allocation to libata-scsi.c
  libata: use blk taging
  NVMe: within nvme_free_queues(), delete RCU sychro/deferred free
  null_blk: suppress invalid partition info
  brd: Request from fdisk 4k alignment
  brd: Fix all partitions BUGs
  axonram: Fix bug in direct_access
  loop: add blk-mq.h include
  block: loop: don't handle REQ_FUA explicitly
  block: loop: introduce lo_discard() and lo_req_flush()
  block: loop: say goodby to bio
  block: loop: improve performance via blk-mq

MAINTAINERS

@@ -6642,9 +6642,10 @@ F:	include/uapi/linux/netrom.h
 F:	net/netrom/
 
 NETWORK BLOCK DEVICE (NBD)
-M:	Paul Clements <Paul.Clements@steeleye.com>
+M:	Markus Pargmann <mpa@pengutronix.de>
 S:	Maintained
 L:	nbd-general@lists.sourceforge.net
+T:	git git://git.pengutronix.de/git/mpa/linux-nbd.git
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/linux/nbd.h
@@ -10690,6 +10691,7 @@ F:	drivers/pci/*xen*
 
 XEN BLOCK SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+M:	Roger Pau Monné <roger.pau@citrix.com>
 L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/block/xen-blkback/*

arch/powerpc/sysdev/axonram.c

@@ -147,7 +147,7 @@ axon_ram_direct_access(struct block_device *device, sector_t sector,
 	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
 
 	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
+	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
 	return bank->size - offset;
 }

block/bsg.c

@@ -136,42 +136,6 @@ static inline struct hlist_head *bsg_dev_idx_hash(int index)
 	return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)];
 }
 
-static int bsg_io_schedule(struct bsg_device *bd)
-{
-	DEFINE_WAIT(wait);
-	int ret = 0;
-
-	spin_lock_irq(&bd->lock);
-
-	BUG_ON(bd->done_cmds > bd->queued_cmds);
-
-	/*
-	 * -ENOSPC or -ENODATA?  I'm going for -ENODATA, meaning "I have no
-	 * work to do", even though we return -ENOSPC after this same test
-	 * during bsg_write() -- there, it means our buffer can't have more
-	 * bsg_commands added to it, thus has no space left.
-	 */
-	if (bd->done_cmds == bd->queued_cmds) {
-		ret = -ENODATA;
-		goto unlock;
-	}
-
-	if (!test_bit(BSG_F_BLOCK, &bd->flags)) {
-		ret = -EAGAIN;
-		goto unlock;
-	}
-
-	prepare_to_wait(&bd->wq_done, &wait, TASK_UNINTERRUPTIBLE);
-	spin_unlock_irq(&bd->lock);
-	io_schedule();
-	finish_wait(&bd->wq_done, &wait);
-
-	return ret;
-unlock:
-	spin_unlock_irq(&bd->lock);
-	return ret;
-}
-
 static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 				struct sg_io_v4 *hdr, struct bsg_device *bd,
 				fmode_t has_write_perm)
@@ -482,6 +446,30 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	return ret;
 }
 
+static bool bsg_complete(struct bsg_device *bd)
+{
+	bool ret = false;
+	bool spin;
+
+	do {
+		spin_lock_irq(&bd->lock);
+
+		BUG_ON(bd->done_cmds > bd->queued_cmds);
+
+		/*
+		 * All commands consumed.
+		 */
+		if (bd->done_cmds == bd->queued_cmds)
+			ret = true;
+
+		spin = !test_bit(BSG_F_BLOCK, &bd->flags);
+
+		spin_unlock_irq(&bd->lock);
+	} while (!ret && spin);
+
+	return ret;
+}
+
 static int bsg_complete_all_commands(struct bsg_device *bd)
 {
 	struct bsg_command *bc;
@@ -492,17 +480,7 @@ static int bsg_complete_all_commands(struct bsg_device *bd)
 	/*
 	 * wait for all commands to complete
 	 */
-	ret = 0;
-	do {
-		ret = bsg_io_schedule(bd);
-		/*
-		 * look for -ENODATA specifically -- we'll sometimes get
-		 * -ERESTARTSYS when we've taken a signal, but we can't
-		 * return until we're done freeing the queue, so ignore
-		 * it.  The signal will get handled when we're done freeing
-		 * the bsg_device.
-		 */
-	} while (ret != -ENODATA);
+	io_wait_event(bd->wq_done, bsg_complete(bd));
 
 	/*
 	 * discard done commands

drivers/ata/libata-core.c

@@ -1585,8 +1585,6 @@ unsigned ata_exec_internal_sg(struct ata_device *dev,
 	else
 		tag = 0;
 
-	if (test_and_set_bit(tag, &ap->qc_allocated))
-		BUG();
 	qc = __ata_qc_from_tag(ap, tag);
 
 	qc->tag = tag;
@@ -4722,69 +4720,36 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 }
 
 /**
- *	ata_qc_new - Request an available ATA command, for queueing
- *	@ap: target port
- *
- *	Some ATA host controllers may implement a queue depth which is less
- *	than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond
- *	the hardware limitation.
+ *	ata_qc_new_init - Request an available ATA command, and initialize it
+ *	@dev: Device from whom we request an available command structure
  *
  *	LOCKING:
  *	None.
  */
 
-static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
+struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag)
 {
-	struct ata_queued_cmd *qc = NULL;
-	unsigned int max_queue = ap->host->n_tags;
-	unsigned int i, tag;
+	struct ata_port *ap = dev->link->ap;
+	struct ata_queued_cmd *qc;
 
 	/* no command while frozen */
 	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
 		return NULL;
 
-	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
-		if (ap->flags & ATA_FLAG_LOWTAG)
-			tag = i;
-		else
-			tag = tag < max_queue ? tag : 0;
-
-		/* the last tag is reserved for internal command. */
-		if (tag == ATA_TAG_INTERNAL)
-			continue;
+	/* libsas case */
+	if (!ap->scsi_host) {
+		tag = ata_sas_allocate_tag(ap);
+		if (tag < 0)
+			return NULL;
+	}
 
-		if (!test_and_set_bit(tag, &ap->qc_allocated)) {
 	qc = __ata_qc_from_tag(ap, tag);
 	qc->tag = tag;
-			ap->last_tag = tag;
-			break;
-		}
-	}
-
-	return qc;
-}
-
-/**
- *	ata_qc_new_init - Request an available ATA command, and initialize it
- *	@dev: Device from whom we request an available command structure
- *
- *	LOCKING:
- *	None.
- */
-
-struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev)
-{
-	struct ata_port *ap = dev->link->ap;
-	struct ata_queued_cmd *qc;
-
-	qc = ata_qc_new(ap);
-	if (qc) {
 	qc->scsicmd = NULL;
 	qc->ap = ap;
 	qc->dev = dev;
 
 	ata_qc_reinit(qc);
-	}
 
 	return qc;
 }
@@ -4811,7 +4776,8 @@ void ata_qc_free(struct ata_queued_cmd *qc)
 	tag = qc->tag;
 	if (likely(ata_tag_valid(tag))) {
 		qc->tag = ATA_TAG_POISON;
-		clear_bit(tag, &ap->qc_allocated);
+		if (!ap->scsi_host)
+			ata_sas_free_tag(tag, ap);
 	}
 }
 

drivers/ata/libata-scsi.c

@@ -756,7 +756,7 @@ static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev,
 {
 	struct ata_queued_cmd *qc;
 
-	qc = ata_qc_new_init(dev);
+	qc = ata_qc_new_init(dev, cmd->request->tag);
 	if (qc) {
 		qc->scsicmd = cmd;
 		qc->scsidone = cmd->scsi_done;
@@ -3668,6 +3668,9 @@ int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht)
 		 */
 		shost->max_host_blocked = 1;
 
+		if (scsi_init_shared_tag_map(shost, host->n_tags))
+			goto err_add;
+
 		rc = scsi_add_host_with_dma(ap->scsi_host,
 						&ap->tdev, ap->host->dev);
 		if (rc)
@@ -4230,3 +4233,31 @@ int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap)
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ata_sas_queuecmd);
+
+int ata_sas_allocate_tag(struct ata_port *ap)
+{
+	unsigned int max_queue = ap->host->n_tags;
+	unsigned int i, tag;
+
+	for (i = 0, tag = ap->sas_last_tag + 1; i < max_queue; i++, tag++) {
+		if (ap->flags & ATA_FLAG_LOWTAG)
+			tag = 1;
+		else
+			tag = tag < max_queue ? tag : 0;
+
+		/* the last tag is reserved for internal command. */
+		if (tag == ATA_TAG_INTERNAL)
+			continue;
+
+		if (!test_and_set_bit(tag, &ap->sas_tag_allocated)) {
+			ap->sas_last_tag = tag;
+			return tag;
+		}
+	}
+	return -1;
+}
+
+void ata_sas_free_tag(unsigned int tag, struct ata_port *ap)
+{
+	clear_bit(tag, &ap->sas_tag_allocated);
+}

drivers/ata/libata.h

@@ -63,7 +63,7 @@ extern struct ata_link *ata_dev_phys_link(struct ata_device *dev);
 extern void ata_force_cbl(struct ata_port *ap);
 extern u64 ata_tf_to_lba(const struct ata_taskfile *tf);
 extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf);
-extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev);
+extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag);
 extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
 			   u64 block, u32 n_block, unsigned int tf_flags,
 			   unsigned int tag);
@@ -144,6 +144,8 @@ extern void ata_scsi_dev_rescan(struct work_struct *work);
 extern int ata_bus_probe(struct ata_port *ap);
 extern int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
 			      unsigned int id, u64 lun);
+int ata_sas_allocate_tag(struct ata_port *ap);
+void ata_sas_free_tag(unsigned int tag, struct ata_port *ap);
 
 
 /* libata-eh.c */

drivers/ata/sata_sil24.c

@@ -388,6 +388,7 @@ static struct scsi_host_template sil24_sht = {
 	.can_queue		= SIL24_MAX_CMDS,
 	.sg_tablesize		= SIL24_MAX_SGE,
 	.dma_boundary		= ATA_DMA_BOUNDARY,
+	.tag_alloc_policy	= BLK_TAG_ALLOC_FIFO,
 };
 
 static struct ata_port_operations sil24_ops = {

drivers/block/brd.c

@@ -438,19 +438,18 @@ static const struct block_device_operations brd_fops = {
 /*
  * And now the modules code and kernel interface.
  */
-static int rd_nr;
-int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
-static int max_part;
-static int part_shift;
-static int part_show = 0;
+static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT;
 module_param(rd_nr, int, S_IRUGO);
 MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
+
+int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
 module_param(rd_size, int, S_IRUGO);
 MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
+
+static int max_part = 1;
 module_param(max_part, int, S_IRUGO);
-MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");
-module_param(part_show, int, S_IRUGO);
-MODULE_PARM_DESC(part_show, "Control RAM disk visibility in /proc/partitions");
+MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
+
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
 MODULE_ALIAS("rd");
@@ -487,25 +486,33 @@ static struct brd_device *brd_alloc(int i)
 	brd->brd_queue = blk_alloc_queue(GFP_KERNEL);
 	if (!brd->brd_queue)
 		goto out_free_dev;
+
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
+	/* This is so fdisk will align partitions on 4k, because of
+	 * direct_access API needing 4k alignment, returning a PFN
+	 * (This is only a problem on very small devices <= 4M,
+	 *  otherwise fdisk will align on 1M. Regardless this call
+	 *  is harmless)
+	 */
+	blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
+
 	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
 	brd->brd_queue->limits.max_discard_sectors = UINT_MAX;
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
 
-	disk = brd->brd_disk = alloc_disk(1 << part_shift);
+	disk = brd->brd_disk = alloc_disk(max_part);
 	if (!disk)
 		goto out_free_queue;
 	disk->major		= RAMDISK_MAJOR;
-	disk->first_minor	= i << part_shift;
+	disk->first_minor	= i * max_part;
 	disk->fops		= &brd_fops;
 	disk->private_data	= brd;
 	disk->queue		= brd->brd_queue;
-	if (!part_show)
-		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
+	disk->flags		= GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "ram%d", i);
 	set_capacity(disk, rd_size * 2);
 
@@ -527,10 +534,11 @@ static void brd_free(struct brd_device *brd)
 	kfree(brd);
 }
 
-static struct brd_device *brd_init_one(int i)
+static struct brd_device *brd_init_one(int i, bool *new)
 {
 	struct brd_device *brd;
 
+	*new = false;
 	list_for_each_entry(brd, &brd_devices, brd_list) {
 		if (brd->brd_number == i)
 			goto out;
@@ -541,6 +549,7 @@ static struct brd_device *brd_init_one(int i)
 		add_disk(brd->brd_disk);
 		list_add_tail(&brd->brd_list, &brd_devices);
 	}
+	*new = true;
 out:
 	return brd;
 }
@@ -556,70 +565,46 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 {
 	struct brd_device *brd;
 	struct kobject *kobj;
+	bool new;
 
 	mutex_lock(&brd_devices_mutex);
-	brd = brd_init_one(MINOR(dev) >> part_shift);
+	brd = brd_init_one(MINOR(dev) / max_part, &new);
 	kobj = brd ? get_disk(brd->brd_disk) : NULL;
 	mutex_unlock(&brd_devices_mutex);
 
+	if (new)
 		*part = 0;
+
 	return kobj;
 }
 
 static int __init brd_init(void)
 {
-	int i, nr;
-	unsigned long range;
 	struct brd_device *brd, *next;
+	int i;
 
 	/*
 	 * brd module now has a feature to instantiate underlying device
 	 * structure on-demand, provided that there is an access dev node.
-	 * However, this will not work well with user space tool that doesn't
-	 * know about such "feature".  In order to not break any existing
-	 * tool, we do the following:
-	 *
-	 * (1) if rd_nr is specified, create that many upfront, and this
-	 *     also becomes a hard limit.
-	 * (2) if rd_nr is not specified, create CONFIG_BLK_DEV_RAM_COUNT
-	 *     (default 16) rd device on module load, user can further
-	 *     extend brd device by create dev node themselves and have
-	 *     kernel automatically instantiate actual device on-demand.
-	 */
-
-	part_shift = 0;
-	if (max_part > 0) {
-		part_shift = fls(max_part);
-
-		/*
-		 * Adjust max_part according to part_shift as it is exported
-		 * to user space so that user can decide correct minor number
-		 * if [s]he want to create more devices.
 	 *
-		 * Note that -1 is required because partition 0 is reserved
-		 * for the whole disk.
+	 * (1) if rd_nr is specified, create that many upfront. else
+	 *     it defaults to CONFIG_BLK_DEV_RAM_COUNT
+	 * (2) User can further extend brd devices by create dev node themselves
+	 *     and have kernel automatically instantiate actual device
+	 *     on-demand. Example:
+	 *		mknod /path/devnod_name b 1 X	# 1 is the rd major
+	 *		fdisk -l /path/devnod_name
+	 *	If (X / max_part) was not already created it will be created
+	 *	dynamically.
 	 */
-		max_part = (1UL << part_shift) - 1;
-	}
-
-	if ((1UL << part_shift) > DISK_MAX_PARTS)
-		return -EINVAL;
-
-	if (rd_nr > 1UL << (MINORBITS - part_shift))
-		return -EINVAL;
-
-	if (rd_nr) {
-		nr = rd_nr;
-		range = rd_nr << part_shift;
-	} else {
-		nr = CONFIG_BLK_DEV_RAM_COUNT;
-		range = 1UL << MINORBITS;
-	}
 
 	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
 		return -EIO;
 
-	for (i = 0; i < nr; i++) {
+	if (unlikely(!max_part))
+		max_part = 1;
+
+	for (i = 0; i < rd_nr; i++) {
 		brd = brd_alloc(i);
 		if (!brd)
 			goto out_free;
@@ -631,10 +616,10 @@ static int __init brd_init(void)
 	list_for_each_entry(brd, &brd_devices, brd_list)
 		add_disk(brd->brd_disk);
 
-	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), range,
+	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS,
 				  THIS_MODULE, brd_probe, NULL, NULL);
 
-	printk(KERN_INFO "brd: module loaded\n");
+	pr_info("brd: module loaded\n");
 	return 0;
 
 out_free:
@@ -644,21 +629,21 @@ static int __init brd_init(void)
 	}
 	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
 
+	pr_info("brd: module NOT loaded !!!\n");
 	return -ENOMEM;
 }
 
 static void __exit brd_exit(void)
 {
-	unsigned long range;
 	struct brd_device *brd, *next;
 
-	range = rd_nr ? rd_nr << part_shift : 1UL << MINORBITS;
-
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
 		brd_del_one(brd);
 
-	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), range);
+	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS);
 	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
+
+	pr_info("brd: module unloaded\n");
 }
 
 module_init(brd_init);

drivers/block/floppy.c

@@ -4112,6 +4112,13 @@ static ssize_t floppy_cmos_show(struct device *dev,
 
 static DEVICE_ATTR(cmos, S_IRUGO, floppy_cmos_show, NULL);
 
+static struct attribute *floppy_dev_attrs[] = {
+	&dev_attr_cmos.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(floppy_dev);
+
 static void floppy_device_release(struct device *dev)
 {
 }
@@ -4324,16 +4331,12 @@ static int __init do_floppy_init(void)
 		floppy_device[drive].name = floppy_device_name;
 		floppy_device[drive].id = drive;
 		floppy_device[drive].dev.release = floppy_device_release;
+		floppy_device[drive].dev.groups = floppy_dev_groups;
 
 		err = platform_device_register(&floppy_device[drive]);
 		if (err)
 			goto out_remove_drives;
 
-		err = device_create_file(&floppy_device[drive].dev,
-					 &dev_attr_cmos);
-		if (err)
-			goto out_unreg_platform_dev;
-
 		/* to be cleaned up... */
 		disks[drive]->private_data = (void *)(long)drive;
 		disks[drive]->flags |= GENHD_FL_REMOVABLE;
@@ -4343,13 +4346,10 @@ static int __init do_floppy_init(void)
 
 	return 0;
 
-out_unreg_platform_dev:
-	platform_device_unregister(&floppy_device[drive]);
 out_remove_drives:
 	while (drive--) {
 		if (floppy_available(drive)) {
 			del_gendisk(disks[drive]);
-			device_remove_file(&floppy_device[drive].dev, &dev_attr_cmos);
 			platform_device_unregister(&floppy_device[drive]);
 		}
 	}
@@ -4594,7 +4594,6 @@ static void __exit floppy_module_exit(void)
 
 		if (floppy_available(drive)) {
 			del_gendisk(disks[drive]);
-			device_remove_file(&floppy_device[drive].dev, &dev_attr_cmos);
 			platform_device_unregister(&floppy_device[drive]);
 		}
 		blk_cleanup_queue(disks[drive]->queue);

drivers/block/loop.c

@@ -85,6 +85,8 @@ static DEFINE_MUTEX(loop_index_mutex);
 static int max_part;
 static int part_shift;
 
+static struct workqueue_struct *loop_wq;
+
 /*
  * Transfer functions
  */
@@ -284,12 +286,12 @@ static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
 	return ret;
 }
 
-static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
+static int lo_send(struct loop_device *lo, struct request *rq, loff_t pos)
 {
 	int (*do_lo_send)(struct loop_device *, struct bio_vec *, loff_t,
 			struct page *page);
 	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct req_iterator iter;
 	struct page *page = NULL;
 	int ret = 0;
 
@@ -303,7 +305,7 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 		do_lo_send = do_lo_send_direct_write;
 	}
 
-	bio_for_each_segment(bvec, bio, iter) {
+	rq_for_each_segment(bvec, rq, iter) {
 		ret = do_lo_send(lo, &bvec, pos, page);
 		if (ret < 0)
 			break;
@@ -391,18 +393,21 @@ do_lo_receive(struct loop_device *lo,
 }
 
 static int
-lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
+lo_receive(struct loop_device *lo, struct request *rq, int bsize, loff_t pos)
 {
 	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct req_iterator iter;
 	ssize_t s;
 
-	bio_for_each_segment(bvec, bio, iter) {
+	rq_for_each_segment(bvec, rq, iter) {
 		s = do_lo_receive(lo, &bvec, bsize, pos);
 		if (s < 0)
 			return s;
 
 		if (s != bvec.bv_len) {
+			struct bio *bio;
+
+			__rq_for_each_bio(bio, rq)
 				zero_fill_bio(bio);
 			break;
 		}
@@ -411,106 +416,58 @@ lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
 	return 0;
 }
 
-static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
+static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
 {
-	loff_t pos;
-	int ret;
-
-	pos = ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset;
-
-	if (bio_rw(bio) == WRITE) {
-		struct file *file = lo->lo_backing_file;
-
-		if (bio->bi_rw & REQ_FLUSH) {
-			ret = vfs_fsync(file, 0);
-			if (unlikely(ret && ret != -EINVAL)) {
-				ret = -EIO;
-				goto out;
-			}
-		}
-
 	/*
 	 * We use punch hole to reclaim the free space used by the
 	 * image a.k.a. discard. However we do not support discard if
 	 * encryption is enabled, because it may give an attacker
 	 * useful information.
 	 */
-		if (bio->bi_rw & REQ_DISCARD) {
 	struct file *file = lo->lo_backing_file;
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
+	int ret;
 
-			if ((!file->f_op->fallocate) ||
-			    lo->lo_encrypt_key_size) {
+	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
-			ret = file->f_op->fallocate(file, mode, pos,
-						    bio->bi_iter.bi_size);
-			if (unlikely(ret && ret != -EINVAL &&
-				     ret != -EOPNOTSUPP))
-				ret = -EIO;
-			goto out;
-		}
-
-		ret = lo_send(lo, bio, pos);
 
-		if ((bio->bi_rw & REQ_FUA) && !ret) {
-			ret = vfs_fsync(file, 0);
-			if (unlikely(ret && ret != -EINVAL))
+	ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq));
+	if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP))
 		ret = -EIO;
-		}
-	} else
-		ret = lo_receive(lo, bio, lo->lo_blocksize, pos);
-
-out:
+ out:
 	return ret;
 }
 
-/*
- * Add bio to back of pending list
- */
-static void loop_add_bio(struct loop_device *lo, struct bio *bio)
+static int lo_req_flush(struct loop_device *lo, struct request *rq)
 {
-	lo->lo_bio_count++;
-	bio_list_add(&lo->lo_bio_list, bio);
-}
+	struct file *file = lo->lo_backing_file;
+	int ret = vfs_fsync(file, 0);
+	if (unlikely(ret && ret != -EINVAL))
+		ret = -EIO;
 
-/*
- * Grab first pending buffer
- */
-static struct bio *loop_get_bio(struct loop_device *lo)
-{
-	lo->lo_bio_count--;
-	return bio_list_pop(&lo->lo_bio_list);
+	return ret;
 }
 
-static void loop_make_request(struct request_queue *q, struct bio *old_bio)
+static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 {
-	struct loop_device *lo = q->queuedata;
-	int rw = bio_rw(old_bio);
-
-	if (rw == READA)
-		rw = READ;
+	loff_t pos;
+	int ret;
 
-	BUG_ON(!lo || (rw != READ && rw != WRITE));
+	pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
 
-	spin_lock_irq(&lo->lo_lock);
-	if (lo->lo_state != Lo_bound)
-		goto out;
-	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
-		goto out;
-	if (lo->lo_bio_count >= q->nr_congestion_on)
-		wait_event_lock_irq(lo->lo_req_wait,
-				    lo->lo_bio_count < q->nr_congestion_off,
-				    lo->lo_lock);
-	loop_add_bio(lo, old_bio);
-	wake_up(&lo->lo_event);
-	spin_unlock_irq(&lo->lo_lock);
-	return;
+	if (rq->cmd_flags & REQ_WRITE) {
+		if (rq->cmd_flags & REQ_FLUSH)
+			ret = lo_req_flush(lo, rq);
+		else if (rq->cmd_flags & REQ_DISCARD)
+			ret = lo_discard(lo, rq, pos);
+		else
+			ret = lo_send(lo, rq, pos);
+	} else
+		ret = lo_receive(lo, rq, lo->lo_blocksize, pos);
 
-out:
-	spin_unlock_irq(&lo->lo_lock);
-	bio_io_error(old_bio);
+	return ret;
 }
 
 struct switch_request {
@@ -518,57 +475,26 @@ struct switch_request {
 	struct completion wait;
 };
 
-static void do_loop_switch(struct loop_device *, struct switch_request *);
-
-static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio)
-{
-	if (unlikely(!bio->bi_bdev)) {
-		do_loop_switch(lo, bio->bi_private);
-		bio_put(bio);
-	} else {
-		int ret = do_bio_filebacked(lo, bio);
-		bio_endio(bio, ret);
-	}
-}
-
 /*
- * worker thread that handles reads/writes to file backed loop devices,
- * to avoid blocking in our make_request_fn. it also does loop decrypting
- * on reads for block backed loop, as that is too heavy to do from
- * b_end_io context where irqs may be disabled.
- *
- * Loop explanation:  loop_clr_fd() sets lo_state to Lo_rundown before
- * calling kthread_stop().  Therefore once kthread_should_stop() is
- * true, make_request will not place any more requests.  Therefore
- * once kthread_should_stop() is true and lo_bio is NULL, we are
- * done with the loop.
+ * Do the actual switch; called from the BIO completion routine
  */
-static int loop_thread(void *data)
+static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
 {
-	struct loop_device *lo = data;
-	struct bio *bio;
-
-	set_user_nice(current, MIN_NICE);
-
-	while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
-
-		wait_event_interruptible(lo->lo_event,
-				!bio_list_empty(&lo->lo_bio_list) ||
-				kthread_should_stop());
-
-		if (bio_list_empty(&lo->lo_bio_list))
-			continue;
-		spin_lock_irq(&lo->lo_lock);
-		bio = loop_get_bio(lo);
-		if (lo->lo_bio_count < lo->lo_queue->nr_congestion_off)
-			wake_up(&lo->lo_req_wait);
-		spin_unlock_irq(&lo->lo_lock);
+	struct file *file = p->file;
+	struct file *old_file = lo->lo_backing_file;
+	struct address_space *mapping;
 
-		BUG_ON(!bio);
-		loop_handle_bio(lo, bio);
-	}
+	/* if no new file, only flush of queued bios requested */
+	if (!file)
+		return;
 
-	return 0;
+	mapping = file->f_mapping;
+	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
+	lo->lo_backing_file = file;
+	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
+		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
+	lo->old_gfp_mask = mapping_gfp_mask(mapping);
+	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 }
 
 /*
@@ -579,15 +505,18 @@ static int loop_thread(void *data)
 static int loop_switch(struct loop_device *lo, struct file *file)
 {
 	struct switch_request w;
-	struct bio *bio = bio_alloc(GFP_KERNEL, 0);
-	if (!bio)
-		return -ENOMEM;
-	init_completion(&w.wait);
+
 	w.file = file;
-	bio->bi_private = &w;
-	bio->bi_bdev = NULL;
-	loop_make_request(lo->lo_queue, bio);
-	wait_for_completion(&w.wait);
+
+	/* freeze queue and wait for completion of scheduled requests */
+	blk_mq_freeze_queue(lo->lo_queue);
+
+	/* do the switch action */
+	do_loop_switch(lo, &w);
+
+	/* unfreeze */
+	blk_mq_unfreeze_queue(lo->lo_queue);
+
 	return 0;
 }
 
@@ -596,38 +525,9 @@ static int loop_switch(struct loop_device *lo, struct file *file)
  */
 static int loop_flush(struct loop_device *lo)
 {
-	/* loop not yet configured, no running thread, nothing to flush */
-	if (!lo->lo_thread)
-		return 0;
-
 	return loop_switch(lo, NULL);
 }
 
-/*
- * Do the actual switch; called from the BIO completion routine
- */
-static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
-{
-	struct file *file = p->file;
-	struct file *old_file = lo->lo_backing_file;
-	struct address_space *mapping;
-
-	/* if no new file, only flush of queued bios requested */
-	if (!file)
-		goto out;
-
-	mapping = file->f_mapping;
-	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
-	lo->lo_backing_file = file;
-	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
-		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
-	lo->old_gfp_mask = mapping_gfp_mask(mapping);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
-out:
-	complete(&p->wait);
-}
-
-
 /*
  * loop_change_fd switched the backing store of a loopback device to
  * a new file. This is useful for operating system installers to free up
@@ -889,12 +789,9 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->transfer = transfer_none;
 	lo->ioctl = NULL;
 	lo->lo_sizelimit = 0;
-	lo->lo_bio_count = 0;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
-	bio_list_init(&lo->lo_bio_list);
-
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
@@ -906,14 +803,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 
 	set_blocksize(bdev, lo_blocksize);
 
-	lo->lo_thread = kthread_create(loop_thread, lo, "loop%d",
-						lo->lo_number);
-	if (IS_ERR(lo->lo_thread)) {
-		error = PTR_ERR(lo->lo_thread);
-		goto out_clr;
-	}
 	lo->lo_state = Lo_bound;
-	wake_up_process(lo->lo_thread);
 	if (part_shift)
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
@@ -925,18 +815,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	bdgrab(bdev);
 	return 0;
 
-out_clr:
-	loop_sysfs_exit(lo);
-	lo->lo_thread = NULL;
-	lo->lo_device = NULL;
-	lo->lo_backing_file = NULL;
-	lo->lo_flags = 0;
-	set_capacity(lo->lo_disk, 0);
-	invalidate_bdev(bdev);
-	bd_set_size(bdev, 0);
-	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask);
-	lo->lo_state = Lo_unbound;
  out_putf:
 	fput(file);
  out:
@@ -1012,11 +890,6 @@ static int loop_clr_fd(struct loop_device *lo)
 
 	spin_lock_irq(&lo->lo_lock);
 	lo->lo_state = Lo_rundown;
-	spin_unlock_irq(&lo->lo_lock);
-
-	kthread_stop(lo->lo_thread);
-
-	spin_lock_irq(&lo->lo_lock);
 	lo->lo_backing_file = NULL;
 	spin_unlock_irq(&lo->lo_lock);
 
@@ -1028,7 +901,6 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_offset = 0;
 	lo->lo_sizelimit = 0;
 	lo->lo_encrypt_key_size = 0;
-	lo->lo_thread = NULL;
 	memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
 	memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
@@ -1601,6 +1473,105 @@ int loop_unregister_transfer(int number)
 EXPORT_SYMBOL(loop_register_transfer);
 EXPORT_SYMBOL(loop_unregister_transfer);
 
+static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
+{
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+
+	blk_mq_start_request(bd->rq);
+
+	if (cmd->rq->cmd_flags & REQ_WRITE) {
+		struct loop_device *lo = cmd->rq->q->queuedata;
+		bool need_sched = true;
+
+		spin_lock_irq(&lo->lo_lock);
+		if (lo->write_started)
+			need_sched = false;
+		else
+			lo->write_started = true;
+		list_add_tail(&cmd->list, &lo->write_cmd_head);
+		spin_unlock_irq(&lo->lo_lock);
+
+		if (need_sched)
+			queue_work(loop_wq, &lo->write_work);
+	} else {
+		queue_work(loop_wq, &cmd->read_work);
+	}
+
+	return BLK_MQ_RQ_QUEUE_OK;
+}
+
+static void loop_handle_cmd(struct loop_cmd *cmd)
+{
+	const bool write = cmd->rq->cmd_flags & REQ_WRITE;
+	struct loop_device *lo = cmd->rq->q->queuedata;
+	int ret = -EIO;
+
+	if (lo->lo_state != Lo_bound)
+		goto failed;
+
+	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY))
+		goto failed;
+
+	ret = do_req_filebacked(lo, cmd->rq);
+
+ failed:
+	if (ret)
+		cmd->rq->errors = -EIO;
+	blk_mq_complete_request(cmd->rq);
+}
+
+static void loop_queue_write_work(struct work_struct *work)
+{
+	struct loop_device *lo =
+		container_of(work, struct loop_device, write_work);
+	LIST_HEAD(cmd_list);
+
+	spin_lock_irq(&lo->lo_lock);
+ repeat:
+	list_splice_init(&lo->write_cmd_head, &cmd_list);
+	spin_unlock_irq(&lo->lo_lock);
+
+	while (!list_empty(&cmd_list)) {
+		struct loop_cmd *cmd = list_first_entry(&cmd_list,
+				struct loop_cmd, list);
+		list_del_init(&cmd->list);
+		loop_handle_cmd(cmd);
+	}
+
+	spin_lock_irq(&lo->lo_lock);
+	if (!list_empty(&lo->write_cmd_head))
+		goto repeat;
+	lo->write_started = false;
+	spin_unlock_irq(&lo->lo_lock);
+}
+
+static void loop_queue_read_work(struct work_struct *work)
+{
+	struct loop_cmd *cmd =
+		container_of(work, struct loop_cmd, read_work);
+
+	loop_handle_cmd(cmd);
+}
+
+static int loop_init_request(void *data, struct request *rq,
+		unsigned int hctx_idx, unsigned int request_idx,
+		unsigned int numa_node)
+{
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	cmd->rq = rq;
+	INIT_WORK(&cmd->read_work, loop_queue_read_work);
+
+	return 0;
+}
+
+static struct blk_mq_ops loop_mq_ops = {
+	.queue_rq       = loop_queue_rq,
+	.map_queue      = blk_mq_map_queue,
+	.init_request	= loop_init_request,
+};
+
 static int loop_add(struct loop_device **l, int i)
 {
 	struct loop_device *lo;
@@ -1627,16 +1598,28 @@ static int loop_add(struct loop_device **l, int i)
 	i = err;
 
 	err = -ENOMEM;
-	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
-	if (!lo->lo_queue)
+	lo->tag_set.ops = &loop_mq_ops;
+	lo->tag_set.nr_hw_queues = 1;
+	lo->tag_set.queue_depth = 128;
+	lo->tag_set.numa_node = NUMA_NO_NODE;
+	lo->tag_set.cmd_size = sizeof(struct loop_cmd);
+	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	lo->tag_set.driver_data = lo;
+
+	err = blk_mq_alloc_tag_set(&lo->tag_set);
+	if (err)
 		goto out_free_idr;
 
-	/*
-	 * set queue make_request_fn
-	 */
-	blk_queue_make_request(lo->lo_queue, loop_make_request);
+	lo->lo_queue = blk_mq_init_queue(&lo->tag_set);
+	if (IS_ERR_OR_NULL(lo->lo_queue)) {
+		err = PTR_ERR(lo->lo_queue);
+		goto out_cleanup_tags;
+	}
 	lo->lo_queue->queuedata = lo;
 
+	INIT_LIST_HEAD(&lo->write_cmd_head);
+	INIT_WORK(&lo->write_work, loop_queue_write_work);
+
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
 		goto out_free_queue;
@@ -1664,9 +1647,6 @@ static int loop_add(struct loop_device **l, int i)
 	disk->flags |= GENHD_FL_EXT_DEVT;
 	mutex_init(&lo->lo_ctl_mutex);
 	lo->lo_number		= i;
-	lo->lo_thread		= NULL;
-	init_waitqueue_head(&lo->lo_event);
-	init_waitqueue_head(&lo->lo_req_wait);
 	spin_lock_init(&lo->lo_lock);
 	disk->major		= LOOP_MAJOR;
 	disk->first_minor	= i << part_shift;
@@ -1680,6 +1660,8 @@ static int loop_add(struct loop_device **l, int i)
 
 out_free_queue:
 	blk_cleanup_queue(lo->lo_queue);
+out_cleanup_tags:
+	blk_mq_free_tag_set(&lo->tag_set);
 out_free_idr:
 	idr_remove(&loop_index_idr, i);
 out_free_dev:
@@ -1692,6 +1674,7 @@ static void loop_remove(struct loop_device *lo)
 {
 	del_gendisk(lo->lo_disk);
 	blk_cleanup_queue(lo->lo_queue);
+	blk_mq_free_tag_set(&lo->tag_set);
 	put_disk(lo->lo_disk);
 	kfree(lo);
 }
@@ -1875,6 +1858,13 @@ static int __init loop_init(void)
 		goto misc_out;
 	}
 
+	loop_wq = alloc_workqueue("kloopd",
+			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 0);
+	if (!loop_wq) {
+		err = -ENOMEM;
+		goto misc_out;
+	}
+
 	blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
 				  THIS_MODULE, loop_probe, NULL, NULL);
 
@@ -1912,6 +1902,8 @@ static void __exit loop_exit(void)
 	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
 	unregister_blkdev(LOOP_MAJOR, "loop");
 
+	destroy_workqueue(loop_wq);
+
 	misc_deregister(&loop_misc);
 }
 

drivers/block/loop.h

@@ -11,8 +11,10 @@
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/workqueue.h>
 #include <uapi/linux/loop.h>
 
 /* Possible states of device */
@@ -52,19 +54,23 @@ struct loop_device {
 	gfp_t		old_gfp_mask;
 
 	spinlock_t		lo_lock;
-	struct bio_list		lo_bio_list;
-	unsigned int		lo_bio_count;
+	struct list_head	write_cmd_head;
+	struct work_struct	write_work;
+	bool			write_started;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
-	struct task_struct	*lo_thread;
-	wait_queue_head_t	lo_event;
-	/* wait queue for incoming requests */
-	wait_queue_head_t	lo_req_wait;
 
 	struct request_queue	*lo_queue;
+	struct blk_mq_tag_set	tag_set;
 	struct gendisk		*lo_disk;
 };
 
+struct loop_cmd {
+	struct work_struct read_work;
+	struct request *rq;
+	struct list_head list;
+};
+
 /* Support for loadable transfer modules */
 struct loop_func_table {
 	int number;	/* filter type */ 

drivers/block/null_blk.c

@@ -579,7 +579,7 @@ static int null_add_dev(void)
 	sector_div(size, bs);
 	set_capacity(disk, size);
 
-	disk->flags |= GENHD_FL_EXT_DEVT;
+	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
 	disk->major		= null_major;
 	disk->first_minor	= nullb->index;
 	disk->fops		= &null_fops;

drivers/block/nvme-core.c

@@ -144,8 +144,37 @@ struct nvme_cmd_info {
 	void *ctx;
 	int aborted;
 	struct nvme_queue *nvmeq;
+	struct nvme_iod iod[0];
 };
 
+/*
+ * Max size of iod being embedded in the request payload
+ */
+#define NVME_INT_PAGES		2
+#define NVME_INT_BYTES(dev)	(NVME_INT_PAGES * (dev)->page_size)
+
+/*
+ * Will slightly overestimate the number of pages needed.  This is OK
+ * as it only leads to a small amount of wasted memory for the lifetime of
+ * the I/O.
+ */
+static int nvme_npages(unsigned size, struct nvme_dev *dev)
+{
+	unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
+	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+}
+
+static unsigned int nvme_cmd_size(struct nvme_dev *dev)
+{
+	unsigned int ret = sizeof(struct nvme_cmd_info);
+
+	ret += sizeof(struct nvme_iod);
+	ret += sizeof(__le64 *) * nvme_npages(NVME_INT_BYTES(dev), dev);
+	ret += sizeof(struct scatterlist) * NVME_INT_PAGES;
+
+	return ret;
+}
+
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 				unsigned int hctx_idx)
 {
@@ -218,6 +247,19 @@ static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
 	blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
 }
 
+static void *iod_get_private(struct nvme_iod *iod)
+{
+	return (void *) (iod->private & ~0x1UL);
+}
+
+/*
+ * If bit 0 is set, the iod is embedded in the request payload.
+ */
+static bool iod_should_kfree(struct nvme_iod *iod)
+{
+	return (iod->private & 0x01) == 0;
+}
+
 /* Special values must be less than 0x1000 */
 #define CMD_CTX_BASE		((void *)POISON_POINTER_DELTA)
 #define CMD_CTX_CANCELLED	(0x30C + CMD_CTX_BASE)
@@ -361,35 +403,53 @@ static __le64 **iod_list(struct nvme_iod *iod)
 	return ((void *)iod) + iod->offset;
 }
 
-/*
- * Will slightly overestimate the number of pages needed.  This is OK
- * as it only leads to a small amount of wasted memory for the lifetime of
- * the I/O.
- */
-static int nvme_npages(unsigned size, struct nvme_dev *dev)
+static inline void iod_init(struct nvme_iod *iod, unsigned nbytes,
+			    unsigned nseg, unsigned long private)
 {
-	unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
-	return DIV_ROUND_UP(8 * nprps, dev->page_size - 8);
+	iod->private = private;
+	iod->offset = offsetof(struct nvme_iod, sg[nseg]);
+	iod->npages = -1;
+	iod->length = nbytes;
+	iod->nents = 0;
 }
 
 static struct nvme_iod *
-nvme_alloc_iod(unsigned nseg, unsigned nbytes, struct nvme_dev *dev, gfp_t gfp)
+__nvme_alloc_iod(unsigned nseg, unsigned bytes, struct nvme_dev *dev,
+		 unsigned long priv, gfp_t gfp)
 {
 	struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
-				sizeof(__le64 *) * nvme_npages(nbytes, dev) +
+				sizeof(__le64 *) * nvme_npages(bytes, dev) +
 				sizeof(struct scatterlist) * nseg, gfp);
 
-	if (iod) {
-		iod->offset = offsetof(struct nvme_iod, sg[nseg]);
-		iod->npages = -1;
-		iod->length = nbytes;
-		iod->nents = 0;
-		iod->first_dma = 0ULL;
-	}
+	if (iod)
+		iod_init(iod, bytes, nseg, priv);
 
 	return iod;
 }
 
+static struct nvme_iod *nvme_alloc_iod(struct request *rq, struct nvme_dev *dev,
+			               gfp_t gfp)
+{
+	unsigned size = !(rq->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(rq) :
+                                                sizeof(struct nvme_dsm_range);
+	unsigned long mask = 0;
+	struct nvme_iod *iod;
+
+	if (rq->nr_phys_segments <= NVME_INT_PAGES &&
+	    size <= NVME_INT_BYTES(dev)) {
+		struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(rq);
+
+		iod = cmd->iod;
+		mask = 0x01;
+		iod_init(iod, size, rq->nr_phys_segments,
+				(unsigned long) rq | 0x01);
+		return iod;
+	}
+
+	return __nvme_alloc_iod(rq->nr_phys_segments, size, dev,
+				(unsigned long) rq, gfp);
+}
+
 void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 {
 	const int last_prp = dev->page_size / 8 - 1;
@@ -405,6 +465,8 @@ void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 		dma_pool_free(dev->prp_page_pool, prp_list, prp_dma);
 		prp_dma = next_prp_dma;
 	}
+
+	if (iod_should_kfree(iod))
 		kfree(iod);
 }
 
@@ -424,7 +486,7 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	struct nvme_iod *iod = ctx;
-	struct request *req = iod->private;
+	struct request *req = iod_get_private(iod);
 	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
 
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
@@ -585,7 +647,7 @@ static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 							struct nvme_ns *ns)
 {
-	struct request *req = iod->private;
+	struct request *req = iod_get_private(iod);
 	struct nvme_command *cmnd;
 	u16 control = 0;
 	u32 dsmgmt = 0;
@@ -626,17 +688,12 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_iod *iod;
-	int psegs = req->nr_phys_segments;
 	enum dma_data_direction dma_dir;
-	unsigned size = !(req->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(req) :
-						sizeof(struct nvme_dsm_range);
 
-	iod = nvme_alloc_iod(psegs, size, ns->dev, GFP_ATOMIC);
+	iod = nvme_alloc_iod(req, ns->dev, GFP_ATOMIC);
 	if (!iod)
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
-	iod->private = req;
-
 	if (req->cmd_flags & REQ_DISCARD) {
 		void *range;
 		/*
@@ -651,10 +708,10 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 			goto retry_cmd;
 		iod_list(iod)[0] = (__le64 *)range;
 		iod->npages = 0;
-	} else if (psegs) {
+	} else if (req->nr_phys_segments) {
 		dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 
-		sg_init_table(iod->sg, psegs);
+		sg_init_table(iod->sg, req->nr_phys_segments);
 		iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
 		if (!iod->nents)
 			goto error_cmd;
@@ -1137,21 +1194,14 @@ static void nvme_free_queue(struct nvme_queue *nvmeq)
 
 static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 {
-	LLIST_HEAD(q_list);
-	struct nvme_queue *nvmeq, *next;
-	struct llist_node *entry;
 	int i;
 
 	for (i = dev->queue_count - 1; i >= lowest; i--) {
 		struct nvme_queue *nvmeq = dev->queues[i];
-		llist_add(&nvmeq->node, &q_list);
 		dev->queue_count--;
 		dev->queues[i] = NULL;
-	}
-	synchronize_rcu();
-	entry = llist_del_all(&q_list);
-	llist_for_each_entry_safe(nvmeq, next, entry, node)
 		nvme_free_queue(nvmeq);
+	}
 }
 
 /**
@@ -1408,7 +1458,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
-		dev->admin_tagset.cmd_size = sizeof(struct nvme_cmd_info);
+		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
 		dev->admin_tagset.driver_data = dev;
 
 		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
@@ -1522,7 +1572,7 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 	}
 
 	err = -ENOMEM;
-	iod = nvme_alloc_iod(count, length, dev, GFP_KERNEL);
+	iod = __nvme_alloc_iod(count, length, dev, 0, GFP_KERNEL);
 	if (!iod)
 		goto put_pages;
 
@@ -2148,7 +2198,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	dev->tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
 	dev->tagset.queue_depth =
 				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
-	dev->tagset.cmd_size = sizeof(struct nvme_cmd_info);
+	dev->tagset.cmd_size = nvme_cmd_size(dev);
 	dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
 	dev->tagset.driver_data = dev;
 

drivers/block/xen-blkback/common.h

@@ -214,6 +214,15 @@ enum blkif_protocol {
 	BLKIF_PROTOCOL_X86_64 = 3,
 };
 
+/*
+ * Default protocol if the frontend doesn't specify one.
+ */
+#ifdef CONFIG_X86
+#  define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_X86_32
+#else
+#  define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_NATIVE
+#endif
+
 struct xen_vbd {
 	/* What the domain refers to this vbd as. */
 	blkif_vdev_t		handle;

drivers/block/xen-blkback/xenbus.c

@@ -868,11 +868,11 @@ static int connect_ring(struct backend_info *be)
 		return err;
 	}
 
-	be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
+	be->blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT;
 	err = xenbus_gather(XBT_NIL, dev->otherend, "protocol",
 			    "%63s", protocol, NULL);
 	if (err)
-		strcpy(protocol, "unspecified, assuming native");
+		strcpy(protocol, "unspecified, assuming default");
 	else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_NATIVE))
 		be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
 	else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_32))

drivers/block/xen-blkfront.c

@@ -1511,7 +1511,7 @@ static int blkif_recover(struct blkfront_info *info)
 		merge_bio.tail = copy[i].request->biotail;
 		bio_list_merge(&bio_list, &merge_bio);
 		copy[i].request->bio = NULL;
-		blk_put_request(copy[i].request);
+		blk_end_request_all(copy[i].request, 0);
 	}
 
 	kfree(copy);
@@ -1534,7 +1534,7 @@ static int blkif_recover(struct blkfront_info *info)
 		req->bio = NULL;
 		if (req->cmd_flags & (REQ_FLUSH | REQ_FUA))
 			pr_alert("diskcache flush request found!\n");
-		__blk_put_request(info->rq, req);
+		__blk_end_request_all(req, 0);
 	}
 	spin_unlock_irq(&info->io_lock);
 

include/linux/libata.h

@@ -823,10 +823,10 @@ struct ata_port {
 	unsigned int		cbl;	/* cable type; ATA_CBL_xxx */
 
 	struct ata_queued_cmd	qcmd[ATA_MAX_QUEUE];
-	unsigned long		qc_allocated;
+	unsigned long		sas_tag_allocated; /* for sas tag allocation only */
 	unsigned int		qc_active;
 	int			nr_active_links; /* #links with active qcs */
-	unsigned int		last_tag;	/* track next tag hw expects */
+	unsigned int		sas_last_tag;	/* track next tag hw expects */
 
 	struct ata_link		link;		/* host default link */
 	struct ata_link		*slave_link;	/* see ata_slave_link_init() */
@@ -1352,6 +1352,7 @@ extern struct device_attribute *ata_common_sdev_attrs[];
 	.ioctl			= ata_scsi_ioctl,		\
 	.queuecommand		= ata_scsi_queuecmd,		\
 	.can_queue		= ATA_DEF_QUEUE,		\
+	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
 	.this_id		= ATA_SHT_THIS_ID,		\
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,		\
 	.emulated		= ATA_SHT_EMULATED,		\

include/linux/nvme.h

@@ -132,13 +132,12 @@ struct nvme_ns {
  * allocated to store the PRP list.
  */
 struct nvme_iod {
-	void *private;		/* For the use of the submitter of the I/O */
+	unsigned long private;	/* For the use of the submitter of the I/O */
 	int npages;		/* In the PRP list. 0 means small pool in use */
 	int offset;		/* Of PRP list */
 	int nents;		/* Used in scatterlist */
 	int length;		/* Of data, in bytes */
 	dma_addr_t first_dma;
-	struct list_head node;
 	struct scatterlist sg[0];
 };
 

include/linux/wait.h

@@ -267,6 +267,21 @@ do {									\
 	__wait_event(wq, condition);					\
 } while (0)
 
+#define __io_wait_event(wq, condition)					\
+	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+			    io_schedule())
+
+/*
+ * io_wait_event() -- like wait_event() but with io_schedule()
+ */
+#define io_wait_event(wq, condition)					\
+do {									\
+	might_sleep();							\
+	if (condition)							\
+		break;							\
+	__io_wait_event(wq, condition);					\
+} while (0)
+
 #define __wait_event_freezable(wq, condition)				\
 	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 			    schedule(); try_to_freeze())