Merge branch 'for-4.4/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Here are the block driver changes for 4.4.  This pull request
  contains:

   - NVMe:
        - Refactor and moving of code to prepare for proper target
          support. From Christoph and Jay.

        - 32-bit nvme warning fix from Arnd.

        - Error initialization fix from me.

        - Proper namespace removal and reference counting support from
          Keith.

        - Device resume fix on IO failure, also from Keith.

        - Dependency fix from Keith, now that nvme isn't under the
          umbrella of the block anymore.

        - Target location and maintainers update from Jay.

   - From Ming Lei, the long awaited DIO/AIO support for loop.

   - Enable BD-RE writeable opens, from Georgios"

* 'for-4.4/drivers' of git://git.kernel.dk/linux-block: (24 commits)
  Update target repo for nvme patch contributions
  NVMe: initialize error to '0'
  nvme: use an integer value to Linux errno values
  nvme: fix 32-bit build warning
  NVMe: Add explicit block config dependency
  nvme: include <linux/types.ĥ> in <linux/nvme.h>
  nvme: move to a new drivers/nvme/host directory
  nvme.h: add missing nvme_id_ctrl endianess annotations
  nvme: move hardware structures out of the uapi version of nvme.h
  nvme: add a local nvme.h header
  nvme: properly handle partially initialized queues in nvme_create_io_queues
  nvme: merge nvme_dev_start, nvme_dev_resume and nvme_async_probe
  nvme: factor reset code into a common helper
  nvme: merge nvme_dev_reset into nvme_reset_failed_dev
  nvme: delete dev from dev_list in nvme_reset
  NVMe: Simplify device resume on io queue failure
  NVMe: Namespace removal simplifications
  NVMe: Reference count open namespaces
  cdrom: Random writing support for BD-RE media
  block: loop: support DIO & AIO
  ...

14 files changed, 467 insertions, 200 deletions

diff --git a/drivers/Kconfig b/drivers/Kconfig
index 46b4a8e..e69ec82a 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -18,6 +18,8 @@ source "drivers/pnp/Kconfig"
 
 source "drivers/block/Kconfig"
 
+source "drivers/nvme/Kconfig"
+
 # misc before ide - BLK_DEV_SGIIOC4 depends on SGI_IOC4
 
 source "drivers/misc/Kconfig"
diff --git a/drivers/Makefile b/drivers/Makefile
index b250b36..42f9dd5 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -70,6 +70,7 @@ obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
 obj-$(CONFIG_SCSI)		+= scsi/
+obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
 obj-$(CONFIG_MTD)		+= mtd/
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 1b8094d..29819e7 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -310,17 +310,6 @@ config BLK_DEV_NBD
 
 	  If unsure, say N.
 
-config BLK_DEV_NVME
-	tristate "NVM Express block device"
-	depends on PCI
-	---help---
-	  The NVM Express driver is for solid state drives directly
-	  connected to the PCI or PCI Express bus.  If you know you
-	  don't have one of these, it is safe to answer N.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called nvme.
-
 config BLK_DEV_SKD
 	tristate "STEC S1120 Block Driver"
 	depends on PCI
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 02b688d..6713290 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -22,7 +22,6 @@ obj-$(CONFIG_XILINX_SYSACE)	+= xsysace.o
 obj-$(CONFIG_CDROM_PKTCDVD)	+= pktcdvd.o
 obj-$(CONFIG_MG_DISK)		+= mg_disk.o
 obj-$(CONFIG_SUNVDC)		+= sunvdc.o
-obj-$(CONFIG_BLK_DEV_NVME)	+= nvme.o
 obj-$(CONFIG_BLK_DEV_SKD)	+= skd.o
 obj-$(CONFIG_BLK_DEV_OSD)	+= osdblk.o
 
@@ -44,6 +43,5 @@ obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
 obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
 obj-$(CONFIG_ZRAM) += zram/
 
-nvme-y		:= nvme-core.o nvme-scsi.o
 skd-y		:= skd_main.o
 swim_mod-y	:= swim.o swim_asm.o
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 674f800..423f4ca 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -164,6 +164,62 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
 	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
 }
 
+static void __loop_update_dio(struct loop_device *lo, bool dio)
+{
+	struct file *file = lo->lo_backing_file;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	unsigned short sb_bsize = 0;
+	unsigned dio_align = 0;
+	bool use_dio;
+
+	if (inode->i_sb->s_bdev) {
+		sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
+		dio_align = sb_bsize - 1;
+	}
+
+	/*
+	 * We support direct I/O only if lo_offset is aligned with the
+	 * logical I/O size of backing device, and the logical block
+	 * size of loop is bigger than the backing device's and the loop
+	 * needn't transform transfer.
+	 *
+	 * TODO: the above condition may be loosed in the future, and
+	 * direct I/O may be switched runtime at that time because most
+	 * of requests in sane appplications should be PAGE_SIZE algined
+	 */
+	if (dio) {
+		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
+				!(lo->lo_offset & dio_align) &&
+				mapping->a_ops->direct_IO &&
+				!lo->transfer)
+			use_dio = true;
+		else
+			use_dio = false;
+	} else {
+		use_dio = false;
+	}
+
+	if (lo->use_dio == use_dio)
+		return;
+
+	/* flush dirty pages before changing direct IO */
+	vfs_fsync(file, 0);
+
+	/*
+	 * The flag of LO_FLAGS_DIRECT_IO is handled similarly with
+	 * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
+	 * will get updated by ioctl(LOOP_GET_STATUS)
+	 */
+	blk_mq_freeze_queue(lo->lo_queue);
+	lo->use_dio = use_dio;
+	if (use_dio)
+		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
+	else
+		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
+	blk_mq_unfreeze_queue(lo->lo_queue);
+}
+
 static int
 figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
 {
@@ -389,6 +445,89 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq)
 	return ret;
 }
 
+static inline void handle_partial_read(struct loop_cmd *cmd, long bytes)
+{
+	if (bytes < 0 || (cmd->rq->cmd_flags & REQ_WRITE))
+		return;
+
+	if (unlikely(bytes < blk_rq_bytes(cmd->rq))) {
+		struct bio *bio = cmd->rq->bio;
+
+		bio_advance(bio, bytes);
+		zero_fill_bio(bio);
+	}
+}
+
+static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
+{
+	struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
+	struct request *rq = cmd->rq;
+
+	handle_partial_read(cmd, ret);
+
+	if (ret > 0)
+		ret = 0;
+	else if (ret < 0)
+		ret = -EIO;
+
+	blk_mq_complete_request(rq, ret);
+}
+
+static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
+		     loff_t pos, bool rw)
+{
+	struct iov_iter iter;
+	struct bio_vec *bvec;
+	struct bio *bio = cmd->rq->bio;
+	struct file *file = lo->lo_backing_file;
+	int ret;
+
+	/* nomerge for loop request queue */
+	WARN_ON(cmd->rq->bio != cmd->rq->biotail);
+
+	bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+	iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
+		      bio_segments(bio), blk_rq_bytes(cmd->rq));
+
+	cmd->iocb.ki_pos = pos;
+	cmd->iocb.ki_filp = file;
+	cmd->iocb.ki_complete = lo_rw_aio_complete;
+	cmd->iocb.ki_flags = IOCB_DIRECT;
+
+	if (rw == WRITE)
+		ret = file->f_op->write_iter(&cmd->iocb, &iter);
+	else
+		ret = file->f_op->read_iter(&cmd->iocb, &iter);
+
+	if (ret != -EIOCBQUEUED)
+		cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
+	return 0;
+}
+
+
+static inline int lo_rw_simple(struct loop_device *lo,
+		struct request *rq, loff_t pos, bool rw)
+{
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	if (cmd->use_aio)
+		return lo_rw_aio(lo, cmd, pos, rw);
+
+	/*
+	 * lo_write_simple and lo_read_simple should have been covered
+	 * by io submit style function like lo_rw_aio(), one blocker
+	 * is that lo_read_simple() need to call flush_dcache_page after
+	 * the page is written from kernel, and it isn't easy to handle
+	 * this in io submit style function which submits all segments
+	 * of the req at one time. And direct read IO doesn't need to
+	 * run flush_dcache_page().
+	 */
+	if (rw == WRITE)
+		return lo_write_simple(lo, rq, pos);
+	else
+		return lo_read_simple(lo, rq, pos);
+}
+
 static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 {
 	loff_t pos;
@@ -404,13 +543,13 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 		else if (lo->transfer)
 			ret = lo_write_transfer(lo, rq, pos);
 		else
-			ret = lo_write_simple(lo, rq, pos);
+			ret = lo_rw_simple(lo, rq, pos, WRITE);
 
 	} else {
 		if (lo->transfer)
 			ret = lo_read_transfer(lo, rq, pos);
 		else
-			ret = lo_read_simple(lo, rq, pos);
+			ret = lo_rw_simple(lo, rq, pos, READ);
 	}
 
 	return ret;
@@ -421,6 +560,12 @@ struct switch_request {
 	struct completion wait;
 };
 
+static inline void loop_update_dio(struct loop_device *lo)
+{
+	__loop_update_dio(lo, io_is_direct(lo->lo_backing_file) |
+			lo->use_dio);
+}
+
 /*
  * Do the actual switch; called from the BIO completion routine
  */
@@ -441,6 +586,7 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
 		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));
+	loop_update_dio(lo);
 }
 
 /*
@@ -627,11 +773,19 @@ static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
 	return sprintf(buf, "%s\n", partscan ? "1" : "0");
 }
 
+static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
+{
+	int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);
+
+	return sprintf(buf, "%s\n", dio ? "1" : "0");
+}
+
 LOOP_ATTR_RO(backing_file);
 LOOP_ATTR_RO(offset);
 LOOP_ATTR_RO(sizelimit);
 LOOP_ATTR_RO(autoclear);
 LOOP_ATTR_RO(partscan);
+LOOP_ATTR_RO(dio);
 
 static struct attribute *loop_attrs[] = {
 	&loop_attr_backing_file.attr,
@@ -639,6 +793,7 @@ static struct attribute *loop_attrs[] = {
 	&loop_attr_sizelimit.attr,
 	&loop_attr_autoclear.attr,
 	&loop_attr_partscan.attr,
+	&loop_attr_dio.attr,
 	NULL,
 };
 
@@ -688,6 +843,23 @@ static void loop_config_discard(struct loop_device *lo)
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
+static void loop_unprepare_queue(struct loop_device *lo)
+{
+	flush_kthread_worker(&lo->worker);
+	kthread_stop(lo->worker_task);
+}
+
+static int loop_prepare_queue(struct loop_device *lo)
+{
+	init_kthread_worker(&lo->worker);
+	lo->worker_task = kthread_run(kthread_worker_fn,
+			&lo->worker, "loop%d", lo->lo_number);
+	if (IS_ERR(lo->worker_task))
+		return -ENOMEM;
+	set_user_nice(lo->worker_task, MIN_NICE);
+	return 0;
+}
+
 static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 		       struct block_device *bdev, unsigned int arg)
 {
@@ -745,17 +917,15 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	size = get_loop_size(lo, file);
 	if ((loff_t)(sector_t)size != size)
 		goto out_putf;
-	error = -ENOMEM;
-	lo->wq = alloc_workqueue("kloopd%d",
-			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 16,
-			lo->lo_number);
-	if (!lo->wq)
+	error = loop_prepare_queue(lo);
+	if (error)
 		goto out_putf;
 
 	error = 0;
 
 	set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
 
+	lo->use_dio = false;
 	lo->lo_blocksize = lo_blocksize;
 	lo->lo_device = bdev;
 	lo->lo_flags = lo_flags;
@@ -769,6 +939,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
+	loop_update_dio(lo);
 	set_capacity(lo->lo_disk, size);
 	bd_set_size(bdev, size << 9);
 	loop_sysfs_init(lo);
@@ -903,8 +1074,7 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_flags = 0;
 	if (!part_shift)
 		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
-	destroy_workqueue(lo->wq);
-	lo->wq = NULL;
+	loop_unprepare_queue(lo);
 	mutex_unlock(&lo->lo_ctl_mutex);
 	/*
 	 * Need not hold lo_ctl_mutex to fput backing file.
@@ -988,6 +1158,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 		lo->lo_key_owner = uid;
 	}
 
+	/* update dio if lo_offset or transfer is changed */
+	__loop_update_dio(lo, lo->use_dio);
+
 	return 0;
 }
 
@@ -1138,6 +1311,20 @@ static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
 	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
 }
 
+static int loop_set_dio(struct loop_device *lo, unsigned long arg)
+{
+	int error = -ENXIO;
+	if (lo->lo_state != Lo_bound)
+		goto out;
+
+	__loop_update_dio(lo, !!arg);
+	if (lo->use_dio == !!arg)
+		return 0;
+	error = -EINVAL;
+ out:
+	return error;
+}
+
 static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
@@ -1181,6 +1368,11 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
 			err = loop_set_capacity(lo, bdev);
 		break;
+	case LOOP_SET_DIRECT_IO:
+		err = -EPERM;
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+			err = loop_set_dio(lo, arg);
+		break;
 	default:
 		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
 	}
@@ -1461,23 +1653,13 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (lo->lo_state != Lo_bound)
 		return -EIO;
 
-	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 (lo->use_dio && !(cmd->rq->cmd_flags & (REQ_FLUSH |
+					REQ_DISCARD)))
+		cmd->use_aio = true;
+	else
+		cmd->use_aio = false;
 
-		if (need_sched)
-			queue_work(lo->wq, &lo->write_work);
-	} else {
-		queue_work(lo->wq, &cmd->read_work);
-	}
+	queue_kthread_work(&lo->worker, &cmd->work);
 
 	return BLK_MQ_RQ_QUEUE_OK;
 }
@@ -1495,38 +1677,15 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 
 	ret = do_req_filebacked(lo, cmd->rq);
  failed:
-	blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
+	/* complete non-aio request */
+	if (!cmd->use_aio || ret)
+		blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
 }
 
-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)
+static void loop_queue_work(struct kthread_work *work)
 {
 	struct loop_cmd *cmd =
-		container_of(work, struct loop_cmd, read_work);
+		container_of(work, struct loop_cmd, work);
 
 	loop_handle_cmd(cmd);
 }
@@ -1538,7 +1697,7 @@ static int loop_init_request(void *data, struct request *rq,
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
 	cmd->rq = rq;
-	INIT_WORK(&cmd->read_work, loop_queue_read_work);
+	init_kthread_work(&cmd->work, loop_queue_work);
 
 	return 0;
 }
@@ -1594,8 +1753,11 @@ static int loop_add(struct loop_device **l, int i)
 	}
 	lo->lo_queue->queuedata = lo;
 
-	INIT_LIST_HEAD(&lo->write_cmd_head);
-	INIT_WORK(&lo->write_work, loop_queue_write_work);
+	/*
+	 * It doesn't make sense to enable merge because the I/O
+	 * submitted to backing file is handled page by page.
+	 */
+	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue);
 
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 25e8997..fb2237c 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -14,7 +14,7 @@
 #include <linux/blk-mq.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
+#include <linux/kthread.h>
 #include <uapi/linux/loop.h>
 
 /* Possible states of device */
@@ -54,12 +54,11 @@ struct loop_device {
 	gfp_t		old_gfp_mask;
 
 	spinlock_t		lo_lock;
-	struct workqueue_struct *wq;
-	struct list_head	write_cmd_head;
-	struct work_struct	write_work;
-	bool			write_started;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
+	struct kthread_worker	worker;
+	struct task_struct	*worker_task;
+	bool			use_dio;
 
 	struct request_queue	*lo_queue;
 	struct blk_mq_tag_set	tag_set;
@@ -67,9 +66,11 @@ struct loop_device {
 };
 
 struct loop_cmd {
-	struct work_struct read_work;
+	struct kthread_work work;
 	struct request *rq;
 	struct list_head list;
+	bool use_aio;           /* use AIO interface to handle I/O */
+	struct kiocb iocb;
 };
 
 /* Support for loadable transfer modules */
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 5d28a45..c206ccd 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -885,6 +885,7 @@ static int cdrom_is_dvd_rw(struct cdrom_device_info *cdi)
 	switch (cdi->mmc3_profile) {
 	case 0x12:	/* DVD-RAM	*/
 	case 0x1A:	/* DVD+RW	*/
+	case 0x43:	/* BD-RE	*/
 		return 0;
 	default:
 		return 1;
diff --git a/drivers/nvme/Kconfig b/drivers/nvme/Kconfig
new file mode 100644
index 0000000..a39d943
--- /dev/null
+++ b/drivers/nvme/Kconfig
@@ -0,0 +1 @@
+source "drivers/nvme/host/Kconfig"
diff --git a/drivers/nvme/Makefile b/drivers/nvme/Makefile
new file mode 100644
index 0000000..9421e82
--- /dev/null
+++ b/drivers/nvme/Makefile
@@ -0,0 +1,2 @@
+
+obj-y		+= host/
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
new file mode 100644
index 0000000..002a94a
--- /dev/null
+++ b/drivers/nvme/host/Kconfig
@@ -0,0 +1,10 @@
+config BLK_DEV_NVME
+	tristate "NVM Express block device"
+	depends on PCI && BLOCK
+	---help---
+	  The NVM Express driver is for solid state drives directly
+	  connected to the PCI or PCI Express bus.  If you know you
+	  don't have one of these, it is safe to answer N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called nvme.
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
new file mode 100644
index 0000000..cfb6679
--- /dev/null
+++ b/drivers/nvme/host/Makefile
@@ -0,0 +1,4 @@
+
+obj-$(CONFIG_BLK_DEV_NVME)     += nvme.o
+
+nvme-y		+= pci.o scsi.o
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
new file mode 100644
index 0000000..c1f41bf
--- /dev/null
+++ b/drivers/nvme/host/nvme.h
@@ -0,0 +1,133 @@
+/*
+ * Copyright (c) 2011-2014, Intel Corporation.
+ *
+ * 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 _NVME_H
+#define _NVME_H
+
+#include <linux/nvme.h>
+#include <linux/pci.h>
+#include <linux/kref.h>
+#include <linux/blk-mq.h>
+
+extern unsigned char nvme_io_timeout;
+#define NVME_IO_TIMEOUT	(nvme_io_timeout * HZ)
+
+/*
+ * Represents an NVM Express device.  Each nvme_dev is a PCI function.
+ */
+struct nvme_dev {
+	struct list_head node;
+	struct nvme_queue **queues;
+	struct request_queue *admin_q;
+	struct blk_mq_tag_set tagset;
+	struct blk_mq_tag_set admin_tagset;
+	u32 __iomem *dbs;
+	struct device *dev;
+	struct dma_pool *prp_page_pool;
+	struct dma_pool *prp_small_pool;
+	int instance;
+	unsigned queue_count;
+	unsigned online_queues;
+	unsigned max_qid;
+	int q_depth;
+	u32 db_stride;
+	u32 ctrl_config;
+	struct msix_entry *entry;
+	struct nvme_bar __iomem *bar;
+	struct list_head namespaces;
+	struct kref kref;
+	struct device *device;
+	struct work_struct reset_work;
+	struct work_struct probe_work;
+	struct work_struct scan_work;
+	char name[12];
+	char serial[20];
+	char model[40];
+	char firmware_rev[8];
+	bool subsystem;
+	u32 max_hw_sectors;
+	u32 stripe_size;
+	u32 page_size;
+	void __iomem *cmb;
+	dma_addr_t cmb_dma_addr;
+	u64 cmb_size;
+	u32 cmbsz;
+	u16 oncs;
+	u16 abort_limit;
+	u8 event_limit;
+	u8 vwc;
+};
+
+/*
+ * An NVM Express namespace is equivalent to a SCSI LUN
+ */
+struct nvme_ns {
+	struct list_head list;
+
+	struct nvme_dev *dev;
+	struct request_queue *queue;
+	struct gendisk *disk;
+	struct kref kref;
+
+	unsigned ns_id;
+	int lba_shift;
+	u16 ms;
+	bool ext;
+	u8 pi_type;
+	u64 mode_select_num_blocks;
+	u32 mode_select_block_len;
+};
+
+/*
+ * The nvme_iod describes the data in an I/O, including the list of PRP
+ * entries.  You can't see it in this data structure because C doesn't let
+ * me express that.  Use nvme_alloc_iod to ensure there's enough space
+ * allocated to store the PRP list.
+ */
+struct nvme_iod {
+	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 scatterlist meta_sg[1]; /* metadata requires single contiguous buffer */
+	struct scatterlist sg[0];
+};
+
+static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
+{
+	return (sector >> (ns->lba_shift - 9));
+}
+
+int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void *buf, unsigned bufflen);
+int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void *buffer, void __user *ubuffer, unsigned bufflen,
+		u32 *result, unsigned timeout);
+int nvme_identify_ctrl(struct nvme_dev *dev, struct nvme_id_ctrl **id);
+int nvme_identify_ns(struct nvme_dev *dev, unsigned nsid,
+		struct nvme_id_ns **id);
+int nvme_get_log_page(struct nvme_dev *dev, struct nvme_smart_log **log);
+int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid,
+			dma_addr_t dma_addr, u32 *result);
+int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
+			dma_addr_t dma_addr, u32 *result);
+
+struct sg_io_hdr;
+
+int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr);
+int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg);
+int nvme_sg_get_version_num(int __user *ip);
+
+#endif /* _NVME_H */
diff --git a/drivers/block/nvme-core.c b/drivers/nvme/host/pci.c
index ccc0c1f..0a179ed 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/nvme/host/pci.c
@@ -12,7 +12,6 @@
  * more details.
  */
 
-#include <linux/nvme.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
@@ -43,6 +42,9 @@
 #include <scsi/sg.h>
 #include <asm-generic/io-64-nonatomic-lo-hi.h>
 
+#include <uapi/linux/nvme_ioctl.h>
+#include "nvme.h"
+
 #define NVME_MINORS		(1U << MINORBITS)
 #define NVME_Q_DEPTH		1024
 #define NVME_AQ_DEPTH		256
@@ -84,9 +86,10 @@ static wait_queue_head_t nvme_kthread_wait;
 
 static struct class *nvme_class;
 
-static void nvme_reset_failed_dev(struct work_struct *ws);
+static int __nvme_reset(struct nvme_dev *dev);
 static int nvme_reset(struct nvme_dev *dev);
 static int nvme_process_cq(struct nvme_queue *nvmeq);
+static void nvme_dead_ctrl(struct nvme_dev *dev);
 
 struct async_cmd_info {
 	struct kthread_work work;
@@ -1283,18 +1286,13 @@ static void nvme_abort_req(struct request *req)
 	struct nvme_command cmd;
 
 	if (!nvmeq->qid || cmd_rq->aborted) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&dev_list_lock, flags);
-		if (work_busy(&dev->reset_work))
-			goto out;
-		list_del_init(&dev->node);
-		dev_warn(dev->dev, "I/O %d QID %d timeout, reset controller\n",
-							req->tag, nvmeq->qid);
-		dev->reset_workfn = nvme_reset_failed_dev;
-		queue_work(nvme_workq, &dev->reset_work);
- out:
-		spin_unlock_irqrestore(&dev_list_lock, flags);
+		spin_lock(&dev_list_lock);
+		if (!__nvme_reset(dev)) {
+			dev_warn(dev->dev,
+				 "I/O %d QID %d timeout, reset controller\n",
+				 req->tag, nvmeq->qid);
+		}
+		spin_unlock(&dev_list_lock);
 		return;
 	}
 
@@ -1949,6 +1947,20 @@ static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
 #define nvme_compat_ioctl	NULL
 #endif
 
+static void nvme_free_dev(struct kref *kref);
+static void nvme_free_ns(struct kref *kref)
+{
+	struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
+
+	spin_lock(&dev_list_lock);
+	ns->disk->private_data = NULL;
+	spin_unlock(&dev_list_lock);
+
+	kref_put(&ns->dev->kref, nvme_free_dev);
+	put_disk(ns->disk);
+	kfree(ns);
+}
+
 static int nvme_open(struct block_device *bdev, fmode_t mode)
 {
 	int ret = 0;
@@ -1958,21 +1970,17 @@ static int nvme_open(struct block_device *bdev, fmode_t mode)
 	ns = bdev->bd_disk->private_data;
 	if (!ns)
 		ret = -ENXIO;
-	else if (!kref_get_unless_zero(&ns->dev->kref))
+	else if (!kref_get_unless_zero(&ns->kref))
 		ret = -ENXIO;
 	spin_unlock(&dev_list_lock);
 
 	return ret;
 }
 
-static void nvme_free_dev(struct kref *kref);
-
 static void nvme_release(struct gendisk *disk, fmode_t mode)
 {
 	struct nvme_ns *ns = disk->private_data;
-	struct nvme_dev *dev = ns->dev;
-
-	kref_put(&dev->kref, nvme_free_dev);
+	kref_put(&ns->kref, nvme_free_ns);
 }
 
 static int nvme_getgeo(struct block_device *bd, struct hd_geometry *geo)
@@ -2079,14 +2087,11 @@ static int nvme_kthread(void *data)
 
 			if ((dev->subsystem && (csts & NVME_CSTS_NSSRO)) ||
 							csts & NVME_CSTS_CFS) {
-				if (work_busy(&dev->reset_work))
-					continue;
-				list_del_init(&dev->node);
-				dev_warn(dev->dev,
-					"Failed status: %x, reset controller\n",
-					readl(&dev->bar->csts));
-				dev->reset_workfn = nvme_reset_failed_dev;
-				queue_work(nvme_workq, &dev->reset_work);
+				if (!__nvme_reset(dev)) {
+					dev_warn(dev->dev,
+						"Failed status: %x, reset controller\n",
+						readl(&dev->bar->csts));
+				}
 				continue;
 			}
 			for (i = 0; i < dev->queue_count; i++) {
@@ -2132,6 +2137,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	if (!disk)
 		goto out_free_queue;
 
+	kref_init(&ns->kref);
 	ns->ns_id = nsid;
 	ns->disk = disk;
 	ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */
@@ -2168,6 +2174,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	if (nvme_revalidate_disk(ns->disk))
 		goto out_free_disk;
 
+	kref_get(&dev->kref);
 	add_disk(ns->disk);
 	if (ns->ms) {
 		struct block_device *bd = bdget_disk(ns->disk, 0);
@@ -2190,6 +2197,13 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	kfree(ns);
 }
 
+/*
+ * Create I/O queues.  Failing to create an I/O queue is not an issue,
+ * we can continue with less than the desired amount of queues, and
+ * even a controller without I/O queues an still be used to issue
+ * admin commands.  This might be useful to upgrade a buggy firmware
+ * for example.
+ */
 static void nvme_create_io_queues(struct nvme_dev *dev)
 {
 	unsigned i;
@@ -2199,8 +2213,10 @@ static void nvme_create_io_queues(struct nvme_dev *dev)
 			break;
 
 	for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
-		if (nvme_create_queue(dev->queues[i], i))
+		if (nvme_create_queue(dev->queues[i], i)) {
+			nvme_free_queues(dev, i);
 			break;
+		}
 }
 
 static int set_queue_count(struct nvme_dev *dev, int count)
@@ -2363,18 +2379,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	return result;
 }
 
-static void nvme_free_namespace(struct nvme_ns *ns)
-{
-	list_del(&ns->list);
-
-	spin_lock(&dev_list_lock);
-	ns->disk->private_data = NULL;
-	spin_unlock(&dev_list_lock);
-
-	put_disk(ns->disk);
-	kfree(ns);
-}
-
 static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
 	struct nvme_ns *nsa = container_of(a, struct nvme_ns, list);
@@ -2416,7 +2420,9 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	if (kill || !blk_queue_dying(ns->queue)) {
 		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);
-        }
+	}
+	list_del_init(&ns->list);
+	kref_put(&ns->kref, nvme_free_ns);
 }
 
 static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn)
@@ -2427,18 +2433,14 @@ static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn)
 	for (i = 1; i <= nn; i++) {
 		ns = nvme_find_ns(dev, i);
 		if (ns) {
-			if (revalidate_disk(ns->disk)) {
+			if (revalidate_disk(ns->disk))
 				nvme_ns_remove(ns);
-				nvme_free_namespace(ns);
-			}
 		} else
 			nvme_alloc_ns(dev, i);
 	}
 	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
-		if (ns->ns_id > nn) {
+		if (ns->ns_id > nn)
 			nvme_ns_remove(ns);
-			nvme_free_namespace(ns);
-		}
 	}
 	list_sort(NULL, &dev->namespaces, ns_cmp);
 }
@@ -2828,9 +2830,9 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 
 static void nvme_dev_remove(struct nvme_dev *dev)
 {
-	struct nvme_ns *ns;
+	struct nvme_ns *ns, *next;
 
-	list_for_each_entry(ns, &dev->namespaces, list)
+	list_for_each_entry_safe(ns, next, &dev->namespaces, list)
 		nvme_ns_remove(ns);
 }
 
@@ -2886,21 +2888,12 @@ static void nvme_release_instance(struct nvme_dev *dev)
 	spin_unlock(&dev_list_lock);
 }
 
-static void nvme_free_namespaces(struct nvme_dev *dev)
-{
-	struct nvme_ns *ns, *next;
-
-	list_for_each_entry_safe(ns, next, &dev->namespaces, list)
-		nvme_free_namespace(ns);
-}
-
 static void nvme_free_dev(struct kref *kref)
 {
 	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
 
 	put_device(dev->dev);
 	put_device(dev->device);
-	nvme_free_namespaces(dev);
 	nvme_release_instance(dev);
 	if (dev->tagset.tags)
 		blk_mq_free_tag_set(&dev->tagset);
@@ -2974,14 +2967,15 @@ static const struct file_operations nvme_dev_fops = {
 	.compat_ioctl	= nvme_dev_ioctl,
 };
 
-static int nvme_dev_start(struct nvme_dev *dev)
+static void nvme_probe_work(struct work_struct *work)
 {
-	int result;
+	struct nvme_dev *dev = container_of(work, struct nvme_dev, probe_work);
 	bool start_thread = false;
+	int result;
 
 	result = nvme_dev_map(dev);
 	if (result)
-		return result;
+		goto out;
 
 	result = nvme_configure_admin_queue(dev);
 	if (result)
@@ -3016,7 +3010,20 @@ static int nvme_dev_start(struct nvme_dev *dev)
 		goto free_tags;
 
 	dev->event_limit = 1;
-	return result;
+
+	/*
+	 * Keep the controller around but remove all namespaces if we don't have
+	 * any working I/O queue.
+	 */
+	if (dev->online_queues < 2) {
+		dev_warn(dev->dev, "IO queues not created\n");
+		nvme_dev_remove(dev);
+	} else {
+		nvme_unfreeze_queues(dev);
+		nvme_dev_add(dev);
+	}
+
+	return;
 
  free_tags:
 	nvme_dev_remove_admin(dev);
@@ -3028,7 +3035,9 @@ static int nvme_dev_start(struct nvme_dev *dev)
 	nvme_dev_list_remove(dev);
  unmap:
 	nvme_dev_unmap(dev);
-	return result;
+ out:
+	if (!work_busy(&dev->reset_work))
+		nvme_dead_ctrl(dev);
 }
 
 static int nvme_remove_dead_ctrl(void *arg)
@@ -3042,33 +3051,6 @@ static int nvme_remove_dead_ctrl(void *arg)
 	return 0;
 }
 
-static void nvme_remove_disks(struct work_struct *ws)
-{
-	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
-
-	nvme_free_queues(dev, 1);
-	nvme_dev_remove(dev);
-}
-
-static int nvme_dev_resume(struct nvme_dev *dev)
-{
-	int ret;
-
-	ret = nvme_dev_start(dev);
-	if (ret)
-		return ret;
-	if (dev->online_queues < 2) {
-		spin_lock(&dev_list_lock);
-		dev->reset_workfn = nvme_remove_disks;
-		queue_work(nvme_workq, &dev->reset_work);
-		spin_unlock(&dev_list_lock);
-	} else {
-		nvme_unfreeze_queues(dev);
-		nvme_dev_add(dev);
-	}
-	return 0;
-}
-
 static void nvme_dead_ctrl(struct nvme_dev *dev)
 {
 	dev_warn(dev->dev, "Device failed to resume\n");
@@ -3081,8 +3063,9 @@ static void nvme_dead_ctrl(struct nvme_dev *dev)
 	}
 }
 
-static void nvme_dev_reset(struct nvme_dev *dev)
+static void nvme_reset_work(struct work_struct *ws)
 {
+	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
 	bool in_probe = work_busy(&dev->probe_work);
 
 	nvme_dev_shutdown(dev);
@@ -3102,31 +3085,24 @@ static void nvme_dev_reset(struct nvme_dev *dev)
 	schedule_work(&dev->probe_work);
 }
 
-static void nvme_reset_failed_dev(struct work_struct *ws)
-{
-	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
-	nvme_dev_reset(dev);
-}
-
-static void nvme_reset_workfn(struct work_struct *work)
+static int __nvme_reset(struct nvme_dev *dev)
 {
-	struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
-	dev->reset_workfn(work);
+	if (work_pending(&dev->reset_work))
+		return -EBUSY;
+	list_del_init(&dev->node);
+	queue_work(nvme_workq, &dev->reset_work);
+	return 0;
 }
 
 static int nvme_reset(struct nvme_dev *dev)
 {
-	int ret = -EBUSY;
+	int ret;
 
 	if (!dev->admin_q || blk_queue_dying(dev->admin_q))
 		return -ENODEV;
 
 	spin_lock(&dev_list_lock);
-	if (!work_pending(&dev->reset_work)) {
-		dev->reset_workfn = nvme_reset_failed_dev;
-		queue_work(nvme_workq, &dev->reset_work);
-		ret = 0;
-	}
+	ret = __nvme_reset(dev);
 	spin_unlock(&dev_list_lock);
 
 	if (!ret) {
@@ -3153,7 +3129,6 @@ static ssize_t nvme_sysfs_reset(struct device *dev,
 }
 static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);
 
-static void nvme_async_probe(struct work_struct *work);
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int node, result = -ENOMEM;
@@ -3176,8 +3151,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto free;
 
 	INIT_LIST_HEAD(&dev->namespaces);
-	dev->reset_workfn = nvme_reset_failed_dev;
-	INIT_WORK(&dev->reset_work, nvme_reset_workfn);
+	INIT_WORK(&dev->reset_work, nvme_reset_work);
 	dev->dev = get_device(&pdev->dev);
 	pci_set_drvdata(pdev, dev);
 	result = nvme_set_instance(dev);
@@ -3205,7 +3179,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	INIT_LIST_HEAD(&dev->node);
 	INIT_WORK(&dev->scan_work, nvme_dev_scan);
-	INIT_WORK(&dev->probe_work, nvme_async_probe);
+	INIT_WORK(&dev->probe_work, nvme_probe_work);
 	schedule_work(&dev->probe_work);
 	return 0;
 
@@ -3225,14 +3199,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return result;
 }
 
-static void nvme_async_probe(struct work_struct *work)
-{
-	struct nvme_dev *dev = container_of(work, struct nvme_dev, probe_work);
-
-	if (nvme_dev_resume(dev) && !work_busy(&dev->reset_work))
-		nvme_dead_ctrl(dev);
-}
-
 static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
@@ -3240,7 +3206,7 @@ static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
 	if (prepare)
 		nvme_dev_shutdown(dev);
 	else
-		nvme_dev_resume(dev);
+		schedule_work(&dev->probe_work);
 }
 
 static void nvme_shutdown(struct pci_dev *pdev)
@@ -3294,10 +3260,7 @@ static int nvme_resume(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct nvme_dev *ndev = pci_get_drvdata(pdev);
 
-	if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
-		ndev->reset_workfn = nvme_reset_failed_dev;
-		queue_work(nvme_workq, &ndev->reset_work);
-	}
+	schedule_work(&ndev->probe_work);
 	return 0;
 }
 #endif
diff --git a/drivers/block/nvme-scsi.c b/drivers/nvme/host/scsi.c
index e5a63f0..c3d8d38 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/nvme/host/scsi.c
@@ -17,7 +17,6 @@
  * each command is translated.
  */
 
-#include <linux/nvme.h>
 #include <linux/bio.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
@@ -45,6 +44,7 @@
 #include <scsi/sg.h>
 #include <scsi/scsi.h>
 
+#include "nvme.h"
 
 static int sg_version_num = 30534;	/* 2 digits for each component */