Merge branch 'for-3.13/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "This is the block driver pull request for 3.13.  As with the core pull
  request just sent out, this was rebased on top of the core branch
  again after the immutable series was pulled.  This also means that
  bcache gets to sit the initial pull over.  I will send a second driver
  pull request in the merge window to get those fixes in, once they have
  been rebased and tested on top of the non-immutable stack.

  This pull request contains:

   - Add support for the sTec Kronos pci-e flash card from sTec.  Also
     has various cleanups for this driver, from myself, Bart, Mike
     Snizter, and Wei Yongjun.

   - Add surprise removal support for the micron mtip32xx driver from
     Micron.

   - Floppy documentation fix from Ben Harris.

   - debugfs bug fix for pktcdvd from Dan Carpenter.

   - Fix for the mtip32xx driver stack usage in the debugfs path,
     dynamically allocating those buffers instead.  From David Milburn.

   - Disable cpqarray in Kconfig.  The plan is to remove it on request
     of HP, but lets disable it for a few revisions just to see if
     anyone yells.

   - drbd fixes from Lars Ellenberg and Philipp Reisner.

   - Elevator switch fix for the s390 block driver from Heiko Carstens.

   - loop crash fix on IO to unassigned device from Mikulas Patocka.

   - A series of bug fixes for the IBM rsxx pci-e flash driver from
     Philip J Kelleher.

   - cciss probe fix from Stephen Cameron.

   - Xen block front/back fixes from Roger Pau Monne and Vegard Nossum"

* 'for-3.13/drivers' of git://git.kernel.dk/linux-block: (41 commits)
  floppy: Correct documentation of driver options when used as a module.
  pktcdvd: debugfs functions return NULL on error
  xen-blkfront: restore the non-persistent data path
  skd: fix formatting in skd_s1120.h
  skd: reorder construct/destruct code
  skd: cleanup skd_do_inq_page_da()
  skd: remove SKD_OMIT_FROM_SRC_DIST ifdefs
  skd: remove redundant skdev->pdev assignment from skd_pci_probe()
  skd: use <asm/unaligned.h>
  skd: remove SCSI subsystem specific includes
  skd: register block device only if some devices are present
  skd: fix error messages in skd_init()
  skd: fix error paths in skd_init()
  skd: fix unregister_blkdev() placement
  skd: more removal of bio-based code
  skd: cleanup the skd_*() function block wrapping
  skd: rip out bio path
  skd: fix error return code in skd_pci_probe()
  s390/dasd: hold request queue sysfs lock when calling elevator_init()
  cciss: return 0 from driver probe function on success, not 1
  ...

23 files changed, 6369 insertions, 364 deletions

diff --git a/Documentation/blockdev/floppy.txt b/Documentation/blockdev/floppy.txt
index 470fe4b5e379..e2240f5ab64d 100644
--- a/Documentation/blockdev/floppy.txt
+++ b/Documentation/blockdev/floppy.txt
@@ -39,15 +39,15 @@ Module configuration options
 ============================
 
  If you use the floppy driver as a module, use the following syntax:
-modprobe floppy <options>
+modprobe floppy floppy="<options>"
 
 Example:
- modprobe floppy omnibook messages
+ modprobe floppy floppy="omnibook messages"
 
  If you need certain options enabled every time you load the floppy driver,
 you can put:
 
- options floppy omnibook messages
+ options floppy floppy="omnibook messages"
 
 in a configuration file in /etc/modprobe.d/.
 
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 5902bd006a9c..86b9f37d102e 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -110,7 +110,7 @@ source "drivers/block/mtip32xx/Kconfig"
 
 config BLK_CPQ_DA
 	tristate "Compaq SMART2 support"
-	depends on PCI && VIRT_TO_BUS
+	depends on PCI && VIRT_TO_BUS && 0
 	help
 	  This is the driver for Compaq Smart Array controllers.  Everyone
 	  using these boards should say Y here.  See the file
@@ -319,6 +319,16 @@ config BLK_DEV_NVME
 	  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
+	depends on 64BIT
+	---help---
+	Saying Y or M here will enable support for the
+	STEC, Inc. S1120 PCIe SSD.
+
+	Use device /dev/skd$N amd /dev/skd$Np$M.
+
 config BLK_DEV_OSD
 	tristate "OSD object-as-blkdev support"
 	depends on SCSI_OSD_ULD
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 03b3b4a2bd8a..8cc98cd0d4a8 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -23,6 +23,7 @@ obj-$(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
 
 obj-$(CONFIG_BLK_DEV_UMEM)	+= umem.o
@@ -44,4 +45,5 @@ obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
 obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
 
 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/cciss.c b/drivers/block/cciss.c
index edfa2515bc86..0c004ac05811 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -5183,7 +5183,7 @@ reinit_after_soft_reset:
 	rebuild_lun_table(h, 1, 0);
 	cciss_engage_scsi(h);
 	h->busy_initializing = 0;
-	return 1;
+	return 0;
 
 clean4:
 	cciss_free_cmd_pool(h);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 2d7f608d181c..0e06f0c5dd1e 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1474,7 +1474,8 @@ enum determine_dev_size {
 	DS_ERROR = -1,
 	DS_UNCHANGED = 0,
 	DS_SHRUNK = 1,
-	DS_GREW = 2
+	DS_GREW = 2,
+	DS_GREW_FROM_ZERO = 3,
 };
 extern enum determine_dev_size
 drbd_determine_dev_size(struct drbd_conf *, enum dds_flags, struct resize_parms *) __must_hold(local);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 55635edf563b..9e3818b1bc83 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2750,13 +2750,6 @@ int __init drbd_init(void)
 		return err;
 	}
 
-	err = drbd_genl_register();
-	if (err) {
-		printk(KERN_ERR "drbd: unable to register generic netlink family\n");
-		goto fail;
-	}
-
-
 	register_reboot_notifier(&drbd_notifier);
 
 	/*
@@ -2767,6 +2760,15 @@ int __init drbd_init(void)
 	drbd_proc = NULL; /* play safe for drbd_cleanup */
 	idr_init(&minors);
 
+	rwlock_init(&global_state_lock);
+	INIT_LIST_HEAD(&drbd_tconns);
+
+	err = drbd_genl_register();
+	if (err) {
+		printk(KERN_ERR "drbd: unable to register generic netlink family\n");
+		goto fail;
+	}
+
 	err = drbd_create_mempools();
 	if (err)
 		goto fail;
@@ -2778,9 +2780,6 @@ int __init drbd_init(void)
 		goto fail;
 	}
 
-	rwlock_init(&global_state_lock);
-	INIT_LIST_HEAD(&drbd_tconns);
-
 	retry.wq = create_singlethread_workqueue("drbd-reissue");
 	if (!retry.wq) {
 		printk(KERN_ERR "drbd: unable to create retry workqueue\n");
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 8cc1e640f485..c706d50a8b06 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -955,7 +955,7 @@ drbd_determine_dev_size(struct drbd_conf *mdev, enum dds_flags flags, struct res
 	}
 
 	if (size > la_size_sect)
-		rv = DS_GREW;
+		rv = la_size_sect ? DS_GREW : DS_GREW_FROM_ZERO;
 	if (size < la_size_sect)
 		rv = DS_SHRUNK;
 
@@ -1132,9 +1132,9 @@ void drbd_reconsider_max_bio_size(struct drbd_conf *mdev)
 	/* We may ignore peer limits if the peer is modern enough.
 	   Because new from 8.3.8 onwards the peer can use multiple
 	   BIOs for a single peer_request */
-	if (mdev->state.conn >= C_CONNECTED) {
+	if (mdev->state.conn >= C_WF_REPORT_PARAMS) {
 		if (mdev->tconn->agreed_pro_version < 94)
-			peer = min( mdev->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
+			peer = min(mdev->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
 			/* Correct old drbd (up to 8.3.7) if it believes it can do more than 32KiB */
 		else if (mdev->tconn->agreed_pro_version == 94)
 			peer = DRBD_MAX_SIZE_H80_PACKET;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index cc29cd3bf78b..6fa6673b36b3 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1890,29 +1890,11 @@ static u32 seq_max(u32 a, u32 b)
 	return seq_greater(a, b) ? a : b;
 }
 
-static bool need_peer_seq(struct drbd_conf *mdev)
-{
-	struct drbd_tconn *tconn = mdev->tconn;
-	int tp;
-
-	/*
-	 * We only need to keep track of the last packet_seq number of our peer
-	 * if we are in dual-primary mode and we have the resolve-conflicts flag set; see
-	 * handle_write_conflicts().
-	 */
-
-	rcu_read_lock();
-	tp = rcu_dereference(mdev->tconn->net_conf)->two_primaries;
-	rcu_read_unlock();
-
-	return tp && test_bit(RESOLVE_CONFLICTS, &tconn->flags);
-}
-
 static void update_peer_seq(struct drbd_conf *mdev, unsigned int peer_seq)
 {
 	unsigned int newest_peer_seq;
 
-	if (need_peer_seq(mdev)) {
+	if (test_bit(RESOLVE_CONFLICTS, &mdev->tconn->flags)) {
 		spin_lock(&mdev->peer_seq_lock);
 		newest_peer_seq = seq_max(mdev->peer_seq, peer_seq);
 		mdev->peer_seq = newest_peer_seq;
@@ -1972,22 +1954,31 @@ static int wait_for_and_update_peer_seq(struct drbd_conf *mdev, const u32 peer_s
 {
 	DEFINE_WAIT(wait);
 	long timeout;
-	int ret;
+	int ret = 0, tp;
 
-	if (!need_peer_seq(mdev))
+	if (!test_bit(RESOLVE_CONFLICTS, &mdev->tconn->flags))
 		return 0;
 
 	spin_lock(&mdev->peer_seq_lock);
 	for (;;) {
 		if (!seq_greater(peer_seq - 1, mdev->peer_seq)) {
 			mdev->peer_seq = seq_max(mdev->peer_seq, peer_seq);
-			ret = 0;
 			break;
 		}
+
 		if (signal_pending(current)) {
 			ret = -ERESTARTSYS;
 			break;
 		}
+
+		rcu_read_lock();
+		tp = rcu_dereference(mdev->tconn->net_conf)->two_primaries;
+		rcu_read_unlock();
+
+		if (!tp)
+			break;
+
+		/* Only need to wait if two_primaries is enabled */
 		prepare_to_wait(&mdev->seq_wait, &wait, TASK_INTERRUPTIBLE);
 		spin_unlock(&mdev->peer_seq_lock);
 		rcu_read_lock();
@@ -2228,8 +2219,10 @@ static int receive_Data(struct drbd_tconn *tconn, struct packet_info *pi)
 			}
 			goto out_interrupted;
 		}
-	} else
+	} else {
+		update_peer_seq(mdev, peer_seq);
 		spin_lock_irq(&mdev->tconn->req_lock);
+	}
 	list_add(&peer_req->w.list, &mdev->active_ee);
 	spin_unlock_irq(&mdev->tconn->req_lock);
 
@@ -4132,7 +4125,11 @@ recv_bm_rle_bits(struct drbd_conf *mdev,
 				(unsigned int)bs.buf_len);
 			return -EIO;
 		}
-		look_ahead >>= bits;
+		/* if we consumed all 64 bits, assign 0; >> 64 is "undefined"; */
+		if (likely(bits < 64))
+			look_ahead >>= bits;
+		else
+			look_ahead = 0;
 		have -= bits;
 
 		bits = bitstream_get_bits(&bs, &tmp, 64 - have);
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c24379ffd4e3..fec7bef44994 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1306,6 +1306,7 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct
 	int backing_limit;
 
 	if (bio_size && get_ldev(mdev)) {
+		unsigned int max_hw_sectors = queue_max_hw_sectors(q);
 		struct request_queue * const b =
 			mdev->ldev->backing_bdev->bd_disk->queue;
 		if (b->merge_bvec_fn) {
@@ -1313,6 +1314,8 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct
 			limit = min(limit, backing_limit);
 		}
 		put_ldev(mdev);
+		if ((limit >> 9) > max_hw_sectors)
+			limit = max_hw_sectors << 9;
 	}
 	return limit;
 }
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index dbdb88a4976c..c8dac7305244 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -894,13 +894,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 
 	bio_list_init(&lo->lo_bio_list);
 
-	/*
-	 * set queue make_request_fn, and add limits based on lower level
-	 * device
-	 */
-	blk_queue_make_request(lo->lo_queue, loop_make_request);
-	lo->lo_queue->queuedata = lo;
-
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
@@ -1618,6 +1611,8 @@ static int loop_add(struct loop_device **l, int i)
 	if (!lo)
 		goto out;
 
+	lo->lo_state = Lo_unbound;
+
 	/* allocate id, if @id >= 0, we're requesting that specific id */
 	if (i >= 0) {
 		err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL);
@@ -1635,6 +1630,12 @@ static int loop_add(struct loop_device **l, int i)
 	if (!lo->lo_queue)
 		goto out_free_idr;
 
+	/*
+	 * set queue make_request_fn
+	 */
+	blk_queue_make_request(lo->lo_queue, loop_make_request);
+	lo->lo_queue->queuedata = lo;
+
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
 		goto out_free_queue;
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
index 77a60bedd7a3..7bc363f1ee82 100644
--- a/drivers/block/mg_disk.c
+++ b/drivers/block/mg_disk.c
@@ -936,7 +936,7 @@ static int mg_probe(struct platform_device *plat_dev)
 			goto probe_err_3b;
 		}
 		err = request_irq(host->irq, mg_irq,
-				IRQF_DISABLED | IRQF_TRIGGER_RISING,
+				IRQF_TRIGGER_RISING,
 				MG_DEV_NAME, host);
 		if (err) {
 			printk(KERN_ERR "%s:%d fail (request_irq err=%d)\n",
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 952dbfe22126..050c71267f14 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -126,64 +126,30 @@ struct mtip_compat_ide_task_request_s {
 static bool mtip_check_surprise_removal(struct pci_dev *pdev)
 {
 	u16 vendor_id = 0;
+	struct driver_data *dd = pci_get_drvdata(pdev);
+
+	if (dd->sr)
+		return true;
 
        /* Read the vendorID from the configuration space */
 	pci_read_config_word(pdev, 0x00, &vendor_id);
-	if (vendor_id == 0xFFFF)
+	if (vendor_id == 0xFFFF) {
+		dd->sr = true;
+		if (dd->queue)
+			set_bit(QUEUE_FLAG_DEAD, &dd->queue->queue_flags);
+		else
+			dev_warn(&dd->pdev->dev,
+				"%s: dd->queue is NULL\n", __func__);
+		if (dd->port) {
+			set_bit(MTIP_PF_SR_CLEANUP_BIT, &dd->port->flags);
+			wake_up_interruptible(&dd->port->svc_wait);
+		} else
+			dev_warn(&dd->pdev->dev,
+				"%s: dd->port is NULL\n", __func__);
 		return true; /* device removed */
-
-	return false; /* device present */
-}
-
-/*
- * This function is called for clean the pending command in the
- * command slot during the surprise removal of device and return
- * error to the upper layer.
- *
- * @dd Pointer to the DRIVER_DATA structure.
- *
- * return value
- *	None
- */
-static void mtip_command_cleanup(struct driver_data *dd)
-{
-	int group = 0, commandslot = 0, commandindex = 0;
-	struct mtip_cmd *command;
-	struct mtip_port *port = dd->port;
-	static int in_progress;
-
-	if (in_progress)
-		return;
-
-	in_progress = 1;
-
-	for (group = 0; group < 4; group++) {
-		for (commandslot = 0; commandslot < 32; commandslot++) {
-			if (!(port->allocated[group] & (1 << commandslot)))
-				continue;
-
-			commandindex = group << 5 | commandslot;
-			command = &port->commands[commandindex];
-
-			if (atomic_read(&command->active)
-			    && (command->async_callback)) {
-				command->async_callback(command->async_data,
-					-ENODEV);
-				command->async_callback = NULL;
-				command->async_data = NULL;
-			}
-
-			dma_unmap_sg(&port->dd->pdev->dev,
-				command->sg,
-				command->scatter_ents,
-				command->direction);
-		}
 	}
 
-	up(&port->cmd_slot);
-
-	set_bit(MTIP_DDF_CLEANUP_BIT, &dd->dd_flag);
-	in_progress = 0;
+	return false; /* device present */
 }
 
 /*
@@ -222,10 +188,7 @@ static int get_slot(struct mtip_port *port)
 	}
 	dev_warn(&port->dd->pdev->dev, "Failed to get a tag.\n");
 
-	if (mtip_check_surprise_removal(port->dd->pdev)) {
-		/* Device not present, clean outstanding commands */
-		mtip_command_cleanup(port->dd);
-	}
+	mtip_check_surprise_removal(port->dd->pdev);
 	return -1;
 }
 
@@ -246,6 +209,107 @@ static inline void release_slot(struct mtip_port *port, int tag)
 }
 
 /*
+ * IO completion function.
+ *
+ * This completion function is called by the driver ISR when a
+ * command that was issued by the kernel completes. It first calls the
+ * asynchronous completion function which normally calls back into the block
+ * layer passing the asynchronous callback data, then unmaps the
+ * scatter list associated with the completed command, and finally
+ * clears the allocated bit associated with the completed command.
+ *
+ * @port   Pointer to the port data structure.
+ * @tag    Tag of the command.
+ * @data   Pointer to driver_data.
+ * @status Completion status.
+ *
+ * return value
+ *	None
+ */
+static void mtip_async_complete(struct mtip_port *port,
+				int tag,
+				void *data,
+				int status)
+{
+	struct mtip_cmd *command;
+	struct driver_data *dd = data;
+	int cb_status = status ? -EIO : 0;
+
+	if (unlikely(!dd) || unlikely(!port))
+		return;
+
+	command = &port->commands[tag];
+
+	if (unlikely(status == PORT_IRQ_TF_ERR)) {
+		dev_warn(&port->dd->pdev->dev,
+			"Command tag %d failed due to TFE\n", tag);
+	}
+
+	/* Upper layer callback */
+	if (likely(command->async_callback))
+		command->async_callback(command->async_data, cb_status);
+
+	command->async_callback = NULL;
+	command->comp_func = NULL;
+
+	/* Unmap the DMA scatter list entries */
+	dma_unmap_sg(&dd->pdev->dev,
+		command->sg,
+		command->scatter_ents,
+		command->direction);
+
+	/* Clear the allocated and active bits for the command */
+	atomic_set(&port->commands[tag].active, 0);
+	release_slot(port, tag);
+
+	up(&port->cmd_slot);
+}
+
+/*
+ * This function is called for clean the pending command in the
+ * command slot during the surprise removal of device and return
+ * error to the upper layer.
+ *
+ * @dd Pointer to the DRIVER_DATA structure.
+ *
+ * return value
+ *	None
+ */
+static void mtip_command_cleanup(struct driver_data *dd)
+{
+	int tag = 0;
+	struct mtip_cmd *cmd;
+	struct mtip_port *port = dd->port;
+	unsigned int num_cmd_slots = dd->slot_groups * 32;
+
+	if (!test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
+		return;
+
+	if (!port)
+		return;
+
+	cmd = &port->commands[MTIP_TAG_INTERNAL];
+	if (atomic_read(&cmd->active))
+		if (readl(port->cmd_issue[MTIP_TAG_INTERNAL]) &
+					(1 << MTIP_TAG_INTERNAL))
+			if (cmd->comp_func)
+				cmd->comp_func(port, MTIP_TAG_INTERNAL,
+					 cmd->comp_data, -ENODEV);
+
+	while (1) {
+		tag = find_next_bit(port->allocated, num_cmd_slots, tag);
+		if (tag >= num_cmd_slots)
+			break;
+
+		cmd = &port->commands[tag];
+		if (atomic_read(&cmd->active))
+			mtip_async_complete(port, tag, dd, -ENODEV);
+	}
+
+	set_bit(MTIP_DDF_CLEANUP_BIT, &dd->dd_flag);
+}
+
+/*
  * Reset the HBA (without sleeping)
  *
  * @dd Pointer to the driver data structure.
@@ -584,6 +648,9 @@ static void mtip_timeout_function(unsigned long int data)
 	if (unlikely(!port))
 		return;
 
+	if (unlikely(port->dd->sr))
+		return;
+
 	if (test_bit(MTIP_DDF_RESUME_BIT, &port->dd->dd_flag)) {
 		mod_timer(&port->cmd_timer,
 			jiffies + msecs_to_jiffies(30000));
@@ -675,66 +742,6 @@ static void mtip_timeout_function(unsigned long int data)
 }
 
 /*
- * IO completion function.
- *
- * This completion function is called by the driver ISR when a
- * command that was issued by the kernel completes. It first calls the
- * asynchronous completion function which normally calls back into the block
- * layer passing the asynchronous callback data, then unmaps the
- * scatter list associated with the completed command, and finally
- * clears the allocated bit associated with the completed command.
- *
- * @port   Pointer to the port data structure.
- * @tag    Tag of the command.
- * @data   Pointer to driver_data.
- * @status Completion status.
- *
- * return value
- *	None
- */
-static void mtip_async_complete(struct mtip_port *port,
-				int tag,
-				void *data,
-				int status)
-{
-	struct mtip_cmd *command;
-	struct driver_data *dd = data;
-	int cb_status = status ? -EIO : 0;
-
-	if (unlikely(!dd) || unlikely(!port))
-		return;
-
-	command = &port->commands[tag];
-
-	if (unlikely(status == PORT_IRQ_TF_ERR)) {
-		dev_warn(&port->dd->pdev->dev,
-			"Command tag %d failed due to TFE\n", tag);
-	}
-
-	/* Upper layer callback */
-	if (likely(command->async_callback))
-		command->async_callback(command->async_data, cb_status);
-
-	command->async_callback = NULL;
-	command->comp_func = NULL;
-
-	/* Unmap the DMA scatter list entries */
-	dma_unmap_sg(&dd->pdev->dev,
-		command->sg,
-		command->scatter_ents,
-		command->direction);
-
-	/* Clear the allocated and active bits for the command */
-	atomic_set(&port->commands[tag].active, 0);
-	release_slot(port, tag);
-
-	if (unlikely(command->unaligned))
-		up(&port->cmd_slot_unal);
-	else
-		up(&port->cmd_slot);
-}
-
-/*
  * Internal command completion callback function.
  *
  * This function is normally called by the driver ISR when an internal
@@ -854,7 +861,6 @@ static void mtip_handle_tfe(struct driver_data *dd)
 					"Missing completion func for tag %d",
 					tag);
 				if (mtip_check_surprise_removal(dd->pdev)) {
-					mtip_command_cleanup(dd);
 					/* don't proceed further */
 					return;
 				}
@@ -1018,14 +1024,12 @@ static inline void mtip_workq_sdbfx(struct mtip_port *port, int group,
 					command->comp_data,
 					0);
 			} else {
-				dev_warn(&dd->pdev->dev,
-					"Null completion "
-					"for tag %d",
+				dev_dbg(&dd->pdev->dev,
+					"Null completion for tag %d",
 					tag);
 
 				if (mtip_check_surprise_removal(
 					dd->pdev)) {
-					mtip_command_cleanup(dd);
 					return;
 				}
 			}
@@ -1145,7 +1149,6 @@ static inline irqreturn_t mtip_handle_irq(struct driver_data *data)
 
 		if (unlikely(port_stat & PORT_IRQ_ERR)) {
 			if (unlikely(mtip_check_surprise_removal(dd->pdev))) {
-				mtip_command_cleanup(dd);
 				/* don't proceed further */
 				return IRQ_HANDLED;
 			}
@@ -2806,34 +2809,51 @@ static ssize_t show_device_status(struct device_driver *drv, char *buf)
 static ssize_t mtip_hw_read_device_status(struct file *f, char __user *ubuf,
 						size_t len, loff_t *offset)
 {
+	struct driver_data *dd =  (struct driver_data *)f->private_data;
 	int size = *offset;
-	char buf[MTIP_DFS_MAX_BUF_SIZE];
+	char *buf;
+	int rv = 0;
 
 	if (!len || *offset)
 		return 0;
 
+	buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL);
+	if (!buf) {
+		dev_err(&dd->pdev->dev,
+			"Memory allocation: status buffer\n");
+		return -ENOMEM;
+	}
+
 	size += show_device_status(NULL, buf);
 
 	*offset = size <= len ? size : len;
 	size = copy_to_user(ubuf, buf, *offset);
 	if (size)
-		return -EFAULT;
+		rv = -EFAULT;
 
-	return *offset;
+	kfree(buf);
+	return rv ? rv : *offset;
 }
 
 static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf,
 				  size_t len, loff_t *offset)
 {
 	struct driver_data *dd =  (struct driver_data *)f->private_data;
-	char buf[MTIP_DFS_MAX_BUF_SIZE];
+	char *buf;
 	u32 group_allocated;
 	int size = *offset;
-	int n;
+	int n, rv = 0;
 
 	if (!len || size)
 		return 0;
 
+	buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL);
+	if (!buf) {
+		dev_err(&dd->pdev->dev,
+			"Memory allocation: register buffer\n");
+		return -ENOMEM;
+	}
+
 	size += sprintf(&buf[size], "H/ S ACTive      : [ 0x");
 
 	for (n = dd->slot_groups-1; n >= 0; n--)
@@ -2888,21 +2908,30 @@ static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf,
 	*offset = size <= len ? size : len;
 	size = copy_to_user(ubuf, buf, *offset);
 	if (size)
-		return -EFAULT;
+		rv = -EFAULT;
 
-	return *offset;
+	kfree(buf);
+	return rv ? rv : *offset;
 }
 
 static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf,
 				  size_t len, loff_t *offset)
 {
 	struct driver_data *dd =  (struct driver_data *)f->private_data;
-	char buf[MTIP_DFS_MAX_BUF_SIZE];
+	char *buf;
 	int size = *offset;
+	int rv = 0;
 
 	if (!len || size)
 		return 0;
 
+	buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL);
+	if (!buf) {
+		dev_err(&dd->pdev->dev,
+			"Memory allocation: flag buffer\n");
+		return -ENOMEM;
+	}
+
 	size += sprintf(&buf[size], "Flag-port : [ %08lX ]\n",
 							dd->port->flags);
 	size += sprintf(&buf[size], "Flag-dd   : [ %08lX ]\n",
@@ -2911,9 +2940,10 @@ static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf,
 	*offset = size <= len ? size : len;
 	size = copy_to_user(ubuf, buf, *offset);
 	if (size)
-		return -EFAULT;
+		rv = -EFAULT;
 
-	return *offset;
+	kfree(buf);
+	return rv ? rv : *offset;
 }
 
 static const struct file_operations mtip_device_status_fops = {
@@ -3006,6 +3036,46 @@ static void mtip_hw_debugfs_exit(struct driver_data *dd)
 		debugfs_remove_recursive(dd->dfs_node);
 }
 
+static int mtip_free_orphan(struct driver_data *dd)
+{
+	struct kobject *kobj;
+
+	if (dd->bdev) {
+		if (dd->bdev->bd_holders >= 1)
+			return -2;
+
+		bdput(dd->bdev);
+		dd->bdev = NULL;
+	}
+
+	mtip_hw_debugfs_exit(dd);
+
+	spin_lock(&rssd_index_lock);
+	ida_remove(&rssd_index_ida, dd->index);
+	spin_unlock(&rssd_index_lock);
+
+	if (!test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag) &&
+			test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag)) {
+		put_disk(dd->disk);
+	} else {
+		if (dd->disk) {
+			kobj = kobject_get(&disk_to_dev(dd->disk)->kobj);
+			if (kobj) {
+				mtip_hw_sysfs_exit(dd, kobj);
+				kobject_put(kobj);
+			}
+			del_gendisk(dd->disk);
+			dd->disk = NULL;
+		}
+		if (dd->queue) {
+			dd->queue->queuedata = NULL;
+			blk_cleanup_queue(dd->queue);
+			dd->queue = NULL;
+		}
+	}
+	kfree(dd);
+	return 0;
+}
 
 /*
  * Perform any init/resume time hardware setup
@@ -3154,6 +3224,7 @@ static int mtip_service_thread(void *data)
 	unsigned long slot, slot_start, slot_wrap;
 	unsigned int num_cmd_slots = dd->slot_groups * 32;
 	struct mtip_port *port = dd->port;
+	int ret;
 
 	while (1) {
 		/*
@@ -3164,13 +3235,18 @@ static int mtip_service_thread(void *data)
 			!(port->flags & MTIP_PF_PAUSE_IO));
 
 		if (kthread_should_stop())
+			goto st_out;
+
+		set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
+
+		/* If I am an orphan, start self cleanup */
+		if (test_bit(MTIP_PF_SR_CLEANUP_BIT, &port->flags))
 			break;
 
 		if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
 				&dd->dd_flag)))
-			break;
+			goto st_out;
 
-		set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
 		if (test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) {
 			slot = 1;
 			/* used to restrict the loop to one iteration */
@@ -3201,7 +3277,7 @@ static int mtip_service_thread(void *data)
 
 			clear_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags);
 		} else if (test_bit(MTIP_PF_REBUILD_BIT, &port->flags)) {
-			if (!mtip_ftl_rebuild_poll(dd))
+			if (mtip_ftl_rebuild_poll(dd) < 0)
 				set_bit(MTIP_DDF_REBUILD_FAILED_BIT,
 							&dd->dd_flag);
 			clear_bit(MTIP_PF_REBUILD_BIT, &port->flags);
@@ -3209,8 +3285,30 @@ static int mtip_service_thread(void *data)
 		clear_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
 
 		if (test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags))
+			goto st_out;
+	}
+
+	/* wait for pci remove to exit */
+	while (1) {
+		if (test_bit(MTIP_DDF_REMOVE_DONE_BIT, &dd->dd_flag))
 			break;
+		msleep_interruptible(1000);
+		if (kthread_should_stop())
+			goto st_out;
+	}
+
+	while (1) {
+		ret = mtip_free_orphan(dd);
+		if (!ret) {
+			/* NOTE: All data structures are invalid, do not
+			 * access any here */
+			return 0;
+		}
+		msleep_interruptible(1000);
+		if (kthread_should_stop())
+			goto st_out;
 	}
+st_out:
 	return 0;
 }
 
@@ -3437,13 +3535,13 @@ static int mtip_hw_init(struct driver_data *dd)
 		rv = -EFAULT;
 		goto out3;
 	}
+	mtip_dump_identify(dd->port);
 
 	if (*(dd->port->identify + MTIP_FTL_REBUILD_OFFSET) ==
 		MTIP_FTL_REBUILD_MAGIC) {
 		set_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags);
 		return MTIP_FTL_REBUILD_MAGIC;
 	}
-	mtip_dump_identify(dd->port);
 
 	/* check write protect, over temp and rebuild statuses */
 	rv = mtip_read_log_page(dd->port, ATA_LOG_SATA_NCQ,
@@ -3467,8 +3565,8 @@ static int mtip_hw_init(struct driver_data *dd)
 		}
 		if (buf[288] == 0xBF) {
 			dev_info(&dd->pdev->dev,
-				"Drive indicate