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

Pull more block layer patches from Jens Axboe:
 "A few later arrivers that I didn't fold into the first pull request,
  so we had a chance to run some testing.  This contains:

   - NVMe:
        - Set of fixes from Keith
        - 4.4 and earlier gcc build fix from Andrew

   - small set of xen-blk{back,front} fixes from Bob Liu.

   - warnings fix for bogus inline statement in I_BDEV() from Geert.

   - error code fixup for SG_IO ioctl from Paolo Bonzini"

* 'for-linus' of git://git.kernel.dk/linux-block:
  drivers/block/nvme-core.c: fix build with gcc-4.4.4
  bdi: Remove "inline" keyword from exported I_BDEV() implementation
  block: fix bogus EFAULT error from SG_IO ioctl
  NVMe: Fix filesystem deadlock on removal
  NVMe: Failed controller initialization fixes
  NVMe: Unify controller probe and resume
  NVMe: Don't use fake status on cancelled command
  NVMe: Fix device cleanup on initialization failure
  drivers: xen-blkfront: only talk_to_blkback() when in XenbusStateInitialising
  xen/block: add multi-page ring support
  driver: xen-blkfront: move talk_to_blkback to a more suitable place
  drivers: xen-blkback: delay pending_req allocation to connect_ring

7 files changed, 308 insertions, 171 deletions

diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 55b6f15dac90..dda653ce7b24 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -326,8 +326,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 			goto out_put_request;
 	}
 
-	ret = -EFAULT;
-	if (blk_fill_sghdr_rq(q, rq, hdr, mode))
+	ret = blk_fill_sghdr_rq(q, rq, hdr, mode);
+	if (ret < 0)
 		goto out_free_cdb;
 
 	ret = 0;
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index e5112714188f..34338d7438f5 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -193,6 +193,13 @@ static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 	return 0;
 }
 
+static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+	struct nvme_queue *nvmeq = hctx->driver_data;
+
+	nvmeq->tags = NULL;
+}
+
 static int nvme_admin_init_request(void *data, struct request *req,
 				unsigned int hctx_idx, unsigned int rq_idx,
 				unsigned int numa_node)
@@ -606,7 +613,10 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 			return;
 		}
 		if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
-			req->errors = status;
+			if (cmd_rq->ctx == CMD_CTX_CANCELLED)
+				req->errors = -EINTR;
+			else
+				req->errors = status;
 		} else {
 			req->errors = nvme_error_status(status);
 		}
@@ -1161,12 +1171,13 @@ static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid)
 
 int nvme_identify_ctrl(struct nvme_dev *dev, struct nvme_id_ctrl **id)
 {
-	struct nvme_command c = {
-		.identify.opcode = nvme_admin_identify,
-		.identify.cns = cpu_to_le32(1),
-	};
+	struct nvme_command c = { };
 	int error;
 
+	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.cns = cpu_to_le32(1);
+
 	*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
 	if (!*id)
 		return -ENOMEM;
@@ -1181,12 +1192,13 @@ 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)
 {
-	struct nvme_command c = {
-		.identify.opcode = nvme_admin_identify,
-		.identify.nsid = cpu_to_le32(nsid),
-	};
+	struct nvme_command c = { };
 	int error;
 
+	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
+	c.identify.opcode = nvme_admin_identify,
+	c.identify.nsid = cpu_to_le32(nsid),
+
 	*id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL);
 	if (!*id)
 		return -ENOMEM;
@@ -1230,14 +1242,14 @@ int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
 
 int nvme_get_log_page(struct nvme_dev *dev, struct nvme_smart_log **log)
 {
-	struct nvme_command c = {
-		.common.opcode = nvme_admin_get_log_page,
-		.common.nsid = cpu_to_le32(0xFFFFFFFF),
-		.common.cdw10[0] = cpu_to_le32(
+	struct nvme_command c = { };
+	int error;
+
+	c.common.opcode = nvme_admin_get_log_page,
+	c.common.nsid = cpu_to_le32(0xFFFFFFFF),
+	c.common.cdw10[0] = cpu_to_le32(
 			(((sizeof(struct nvme_smart_log) / 4) - 1) << 16) |
 			 NVME_LOG_SMART),
-	};
-	int error;
 
 	*log = kmalloc(sizeof(struct nvme_smart_log), GFP_KERNEL);
 	if (!*log)
@@ -1606,6 +1618,7 @@ static struct blk_mq_ops nvme_mq_admin_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_admin_init_hctx,
+	.exit_hctx      = nvme_admin_exit_hctx,
 	.init_request	= nvme_admin_init_request,
 	.timeout	= nvme_timeout,
 };
@@ -1648,6 +1661,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		}
 		if (!blk_get_queue(dev->admin_q)) {
 			nvme_dev_remove_admin(dev);
+			dev->admin_q = NULL;
 			return -ENODEV;
 		}
 	} else
@@ -2349,19 +2363,20 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	}
 	kfree(ctrl);
 
-	dev->tagset.ops = &nvme_mq_ops;
-	dev->tagset.nr_hw_queues = dev->online_queues - 1;
-	dev->tagset.timeout = NVME_IO_TIMEOUT;
-	dev->tagset.numa_node = dev_to_node(dev->dev);
-	dev->tagset.queue_depth =
+	if (!dev->tagset.tags) {
+		dev->tagset.ops = &nvme_mq_ops;
+		dev->tagset.nr_hw_queues = dev->online_queues - 1;
+		dev->tagset.timeout = NVME_IO_TIMEOUT;
+		dev->tagset.numa_node = dev_to_node(dev->dev);
+		dev->tagset.queue_depth =
 				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
-	dev->tagset.cmd_size = nvme_cmd_size(dev);
-	dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
-	dev->tagset.driver_data = dev;
-
-	if (blk_mq_alloc_tag_set(&dev->tagset))
-		return 0;
+		dev->tagset.cmd_size = nvme_cmd_size(dev);
+		dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
+		dev->tagset.driver_data = dev;
 
+		if (blk_mq_alloc_tag_set(&dev->tagset))
+			return 0;
+	}
 	schedule_work(&dev->scan_work);
 	return 0;
 }
@@ -2734,8 +2749,10 @@ static void nvme_free_dev(struct kref *kref)
 	put_device(dev->device);
 	nvme_free_namespaces(dev);
 	nvme_release_instance(dev);
-	blk_mq_free_tag_set(&dev->tagset);
-	blk_put_queue(dev->admin_q);
+	if (dev->tagset.tags)
+		blk_mq_free_tag_set(&dev->tagset);
+	if (dev->admin_q)
+		blk_put_queue(dev->admin_q);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2866,6 +2883,9 @@ static int nvme_dev_start(struct nvme_dev *dev)
 
  free_tags:
 	nvme_dev_remove_admin(dev);
+	blk_put_queue(dev->admin_q);
+	dev->admin_q = NULL;
+	dev->queues[0]->tags = NULL;
  disable:
 	nvme_disable_queue(dev, 0);
 	nvme_dev_list_remove(dev);
@@ -2907,25 +2927,43 @@ static int nvme_dev_resume(struct nvme_dev *dev)
 		spin_unlock(&dev_list_lock);
 	} else {
 		nvme_unfreeze_queues(dev);
-		schedule_work(&dev->scan_work);
+		nvme_dev_add(dev);
 		nvme_set_irq_hints(dev);
 	}
 	return 0;
 }
 
+static void nvme_dead_ctrl(struct nvme_dev *dev)
+{
+	dev_warn(dev->dev, "Device failed to resume\n");
+	kref_get(&dev->kref);
+	if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
+						dev->instance))) {
+		dev_err(dev->dev,
+			"Failed to start controller remove task\n");
+		kref_put(&dev->kref, nvme_free_dev);
+	}
+}
+
 static void nvme_dev_reset(struct nvme_dev *dev)
 {
+	bool in_probe = work_busy(&dev->probe_work);
+
 	nvme_dev_shutdown(dev);
-	if (nvme_dev_resume(dev)) {
-		dev_warn(dev->dev, "Device failed to resume\n");
-		kref_get(&dev->kref);
-		if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
-							dev->instance))) {
-			dev_err(dev->dev,
-				"Failed to start controller remove task\n");
-			kref_put(&dev->kref, nvme_free_dev);
-		}
+
+	/* Synchronize with device probe so that work will see failure status
+	 * and exit gracefully without trying to schedule another reset */
+	flush_work(&dev->probe_work);
+
+	/* Fail this device if reset occured during probe to avoid
+	 * infinite initialization loops. */
+	if (in_probe) {
+		nvme_dead_ctrl(dev);
+		return;
 	}
+	/* Schedule device resume asynchronously so the reset work is available
+	 * to cleanup errors that may occur during reinitialization */
+	schedule_work(&dev->probe_work);
 }
 
 static void nvme_reset_failed_dev(struct work_struct *ws)
@@ -2957,6 +2995,7 @@ static int nvme_reset(struct nvme_dev *dev)
 
 	if (!ret) {
 		flush_work(&dev->reset_work);
+		flush_work(&dev->probe_work);
 		return 0;
 	}
 
@@ -3053,26 +3092,9 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 static void nvme_async_probe(struct work_struct *work)
 {
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, probe_work);
-	int result;
 
-	result = nvme_dev_start(dev);
-	if (result)
-		goto reset;
-
-	if (dev->online_queues > 1)
-		result = nvme_dev_add(dev);
-	if (result)
-		goto reset;
-
-	nvme_set_irq_hints(dev);
-	return;
- reset:
-	spin_lock(&dev_list_lock);
-	if (!work_busy(&dev->reset_work)) {
-		dev->reset_workfn = nvme_reset_failed_dev;
-		queue_work(nvme_workq, &dev->reset_work);
-	}
-	spin_unlock(&dev_list_lock);
+	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)
@@ -3104,8 +3126,8 @@ static void nvme_remove(struct pci_dev *pdev)
 	flush_work(&dev->reset_work);
 	flush_work(&dev->scan_work);
 	device_remove_file(dev->device, &dev_attr_reset_controller);
-	nvme_dev_shutdown(dev);
 	nvme_dev_remove(dev);
+	nvme_dev_shutdown(dev);
 	nvme_dev_remove_admin(dev);
 	device_destroy(nvme_class, MKDEV(nvme_char_major, dev->instance));
 	nvme_free_queues(dev, 0);
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 713fc9ff1149..2126842fb6e8 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -84,6 +84,13 @@ MODULE_PARM_DESC(max_persistent_grants,
                  "Maximum number of grants to map persistently");
 
 /*
+ * Maximum order of pages to be used for the shared ring between front and
+ * backend, 4KB page granularity is used.
+ */
+unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_PAGE_ORDER;
+module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
+MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
+/*
  * The LRU mechanism to clean the lists of persistent grants needs to
  * be executed periodically. The time interval between consecutive executions
  * of the purge mechanism is set in ms.
@@ -1438,6 +1445,12 @@ static int __init xen_blkif_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	if (xen_blkif_max_ring_order > XENBUS_MAX_RING_PAGE_ORDER) {
+		pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
+			xen_blkif_max_ring_order, XENBUS_MAX_RING_PAGE_ORDER);
+		xen_blkif_max_ring_order = XENBUS_MAX_RING_PAGE_ORDER;
+	}
+
 	rc = xen_blkif_interface_init();
 	if (rc)
 		goto failed_init;
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index f620b5d3f77c..8ccc49d01c8e 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -44,6 +44,7 @@
 #include <xen/interface/io/blkif.h>
 #include <xen/interface/io/protocols.h>
 
+extern unsigned int xen_blkif_max_ring_order;
 /*
  * This is the maximum number of segments that would be allowed in indirect
  * requests. This value will also be passed to the frontend.
@@ -248,7 +249,7 @@ struct backend_info;
 #define PERSISTENT_GNT_WAS_ACTIVE	1
 
 /* Number of requests that we can fit in a ring */
-#define XEN_BLKIF_REQS			32
+#define XEN_BLKIF_REQS_PER_PAGE		32
 
 struct persistent_gnt {
 	struct page *page;
@@ -320,6 +321,7 @@ struct xen_blkif {
 	struct work_struct	free_work;
 	/* Thread shutdown wait queue. */
 	wait_queue_head_t	shutdown_wq;
+	unsigned int nr_ring_pages;
 };
 
 struct seg_buf {
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 6ab69ad61ee1..deb3f001791f 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -25,6 +25,7 @@
 
 /* Enlarge the array size in order to fully show blkback name. */
 #define BLKBACK_NAME_LEN (20)
+#define RINGREF_NAME_LEN (20)
 
 struct backend_info {
 	struct xenbus_device	*dev;
@@ -124,8 +125,6 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
 static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 {
 	struct xen_blkif *blkif;
-	struct pending_req *req, *n;
-	int i, j;
 
 	BUILD_BUG_ON(MAX_INDIRECT_PAGES > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST);
 
@@ -151,55 +150,15 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 
 	INIT_LIST_HEAD(&blkif->pending_free);
 	INIT_WORK(&blkif->free_work, xen_blkif_deferred_free);
-
-	for (i = 0; i < XEN_BLKIF_REQS; i++) {
-		req = kzalloc(sizeof(*req), GFP_KERNEL);
-		if (!req)
-			goto fail;
-		list_add_tail(&req->free_list,
-		              &blkif->pending_free);
-		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
-			req->segments[j] = kzalloc(sizeof(*req->segments[0]),
-			                           GFP_KERNEL);
-			if (!req->segments[j])
-				goto fail;
-		}
-		for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
-			req->indirect_pages[j] = kzalloc(sizeof(*req->indirect_pages[0]),
-			                                 GFP_KERNEL);
-			if (!req->indirect_pages[j])
-				goto fail;
-		}
-	}
 	spin_lock_init(&blkif->pending_free_lock);
 	init_waitqueue_head(&blkif->pending_free_wq);
 	init_waitqueue_head(&blkif->shutdown_wq);
 
 	return blkif;
-
-fail:
-	list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
-		list_del(&req->free_list);
-		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
-			if (!req->segments[j])
-				break;
-			kfree(req->segments[j]);
-		}
-		for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
-			if (!req->indirect_pages[j])
-				break;
-			kfree(req->indirect_pages[j]);
-		}
-		kfree(req);
-	}
-
-	kmem_cache_free(xen_blkif_cachep, blkif);
-
-	return ERR_PTR(-ENOMEM);
 }
 
-static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t gref,
-			 unsigned int evtchn)
+static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref,
+			 unsigned int nr_grefs, unsigned int evtchn)
 {
 	int err;
 
@@ -207,7 +166,7 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t gref,
 	if (blkif->irq)
 		return 0;
 
-	err = xenbus_map_ring_valloc(blkif->be->dev, &gref, 1,
+	err = xenbus_map_ring_valloc(blkif->be->dev, gref, nr_grefs,
 				     &blkif->blk_ring);
 	if (err < 0)
 		return err;
@@ -217,21 +176,21 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t gref,
 	{
 		struct blkif_sring *sring;
 		sring = (struct blkif_sring *)blkif->blk_ring;
-		BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE);
+		BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE * nr_grefs);
 		break;
 	}
 	case BLKIF_PROTOCOL_X86_32:
 	{
 		struct blkif_x86_32_sring *sring_x86_32;
 		sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring;
-		BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE);
+		BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE * nr_grefs);
 		break;
 	}
 	case BLKIF_PROTOCOL_X86_64:
 	{
 		struct blkif_x86_64_sring *sring_x86_64;
 		sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring;
-		BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE);
+		BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE * nr_grefs);
 		break;
 	}
 	default:
@@ -312,7 +271,7 @@ static void xen_blkif_free(struct xen_blkif *blkif)
 		i++;
 	}
 
-	WARN_ON(i != XEN_BLKIF_REQS);
+	WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
 
 	kmem_cache_free(xen_blkif_cachep, blkif);
 }
@@ -597,6 +556,11 @@ static int xen_blkbk_probe(struct xenbus_device *dev,
 	if (err)
 		goto fail;
 
+	err = xenbus_printf(XBT_NIL, dev->nodename, "max-ring-page-order", "%u",
+			    xen_blkif_max_ring_order);
+	if (err)
+		pr_warn("%s write out 'max-ring-page-order' failed\n", __func__);
+
 	err = xenbus_switch_state(dev, XenbusStateInitWait);
 	if (err)
 		goto fail;
@@ -860,22 +824,66 @@ again:
 static int connect_ring(struct backend_info *be)
 {
 	struct xenbus_device *dev = be->dev;
-	unsigned long ring_ref;
-	unsigned int evtchn;
+	unsigned int ring_ref[XENBUS_MAX_RING_PAGES];
+	unsigned int evtchn, nr_grefs, ring_page_order;
 	unsigned int pers_grants;
 	char protocol[64] = "";
-	int err;
+	struct pending_req *req, *n;
+	int err, i, j;
 
 	pr_debug("%s %s\n", __func__, dev->otherend);
 
-	err = xenbus_gather(XBT_NIL, dev->otherend, "ring-ref", "%lu",
-			    &ring_ref, "event-channel", "%u", &evtchn, NULL);
-	if (err) {
-		xenbus_dev_fatal(dev, err,
-				 "reading %s/ring-ref and event-channel",
+	err = xenbus_scanf(XBT_NIL, dev->otherend, "event-channel", "%u",
+			  &evtchn);
+	if (err != 1) {
+		err = -EINVAL;
+		xenbus_dev_fatal(dev, err, "reading %s/event-channel",
 				 dev->otherend);
 		return err;
 	}
+	pr_info("event-channel %u\n", evtchn);
+
+	err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-page-order", "%u",
+			  &ring_page_order);
+	if (err != 1) {
+		err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-ref",
+				  "%u", &ring_ref[0]);
+		if (err != 1) {
+			err = -EINVAL;
+			xenbus_dev_fatal(dev, err, "reading %s/ring-ref",
+					 dev->otherend);
+			return err;
+		}
+		nr_grefs = 1;
+		pr_info("%s:using single page: ring-ref %d\n", dev->otherend,
+			ring_ref[0]);
+	} else {
+		unsigned int i;
+
+		if (ring_page_order > xen_blkif_max_ring_order) {
+			err = -EINVAL;
+			xenbus_dev_fatal(dev, err, "%s/request %d ring page order exceed max:%d",
+					 dev->otherend, ring_page_order,
+					 xen_blkif_max_ring_order);
+			return err;
+		}
+
+		nr_grefs = 1 << ring_page_order;
+		for (i = 0; i < nr_grefs; i++) {
+			char ring_ref_name[RINGREF_NAME_LEN];
+
+			snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
+			err = xenbus_scanf(XBT_NIL, dev->otherend, ring_ref_name,
+					   "%u", &ring_ref[i]);
+			if (err != 1) {
+				err = -EINVAL;
+				xenbus_dev_fatal(dev, err, "reading %s/%s",
+						 dev->otherend, ring_ref_name);
+				return err;
+			}
+			pr_info("ring-ref%u: %u\n", i, ring_ref[i]);
+		}
+	}
 
 	be->blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT;
 	err = xenbus_gather(XBT_NIL, dev->otherend, "protocol",
@@ -900,20 +908,55 @@ static int connect_ring(struct backend_info *be)
 
 	be->blkif->vbd.feature_gnt_persistent = pers_grants;
 	be->blkif->vbd.overflow_max_grants = 0;
+	be->blkif->nr_ring_pages = nr_grefs;
 
-	pr_info("ring-ref %ld, event-channel %d, protocol %d (%s) %s\n",
-		ring_ref, evtchn, be->blkif->blk_protocol, protocol,
+	pr_info("ring-pages:%d, event-channel %d, protocol %d (%s) %s\n",
+		nr_grefs, evtchn, be->blkif->blk_protocol, protocol,
 		pers_grants ? "persistent grants" : "");
 
+	for (i = 0; i < nr_grefs * XEN_BLKIF_REQS_PER_PAGE; i++) {
+		req = kzalloc(sizeof(*req), GFP_KERNEL);
+		if (!req)
+			goto fail;
+		list_add_tail(&req->free_list, &be->blkif->pending_free);
+		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
+			req->segments[j] = kzalloc(sizeof(*req->segments[0]), GFP_KERNEL);
+			if (!req->segments[j])
+				goto fail;
+		}
+		for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
+			req->indirect_pages[j] = kzalloc(sizeof(*req->indirect_pages[0]),
+							 GFP_KERNEL);
+			if (!req->indirect_pages[j])
+				goto fail;
+		}
+	}
+
 	/* Map the shared frame, irq etc. */
-	err = xen_blkif_map(be->blkif, ring_ref, evtchn);
+	err = xen_blkif_map(be->blkif, ring_ref, nr_grefs, evtchn);
 	if (err) {
-		xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u",
-				 ring_ref, evtchn);
+		xenbus_dev_fatal(dev, err, "mapping ring-ref port %u", evtchn);
 		return err;
 	}
 
 	return 0;
+
+fail:
+	list_for_each_entry_safe(req, n, &be->blkif->pending_free, free_list) {
+		list_del(&req->free_list);
+		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
+			if (!req->segments[j])
+				break;
+			kfree(req->segments[j]);
+		}
+		for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
+			if (!req->indirect_pages[j])
+				break;
+			kfree(req->indirect_pages[j]);
+		}
+		kfree(req);
+	}
+	return -ENOMEM;
 }
 
 static const struct xenbus_device_id xen_blkbk_ids[] = {
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 2c61cf8c6f61..fc770b7d3beb 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -98,7 +98,21 @@ static unsigned int xen_blkif_max_segments = 32;
 module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
 MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests (default is 32)");
 
-#define BLK_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE)
+/*
+ * Maximum order of pages to be used for the shared ring between front and
+ * backend, 4KB page granularity is used.
+ */
+static unsigned int xen_blkif_max_ring_order;
+module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
+MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
+
+#define BLK_RING_SIZE(info) __CONST_RING_SIZE(blkif, PAGE_SIZE * (info)->nr_ring_pages)
+#define BLK_MAX_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE * XENBUS_MAX_RING_PAGES)
+/*
+ * ring-ref%i i=(-1UL) would take 11 characters + 'ring-ref' is 8, so 19
+ * characters are enough. Define to 20 to keep consist with backend.
+ */
+#define RINGREF_NAME_LEN (20)
 
 /*
  * We have one of these per vbd, whether ide, scsi or 'other'.  They
@@ -114,13 +128,14 @@ struct blkfront_info
 	int vdevice;
 	blkif_vdev_t handle;
 	enum blkif_state connected;
-	int ring_ref;
+	int ring_ref[XENBUS_MAX_RING_PAGES];
+	unsigned int nr_ring_pages;
 	struct blkif_front_ring ring;
 	unsigned int evtchn, irq;
 	struct request_queue *rq;
 	struct work_struct work;
 	struct gnttab_free_callback callback;
-	struct blk_shadow shadow[BLK_RING_SIZE];
+	struct blk_shadow shadow[BLK_MAX_RING_SIZE];
 	struct list_head grants;
 	struct list_head indirect_pages;
 	unsigned int persistent_gnts_c;
@@ -139,8 +154,6 @@ static unsigned int nr_minors;
 static unsigned long *minors;
 static DEFINE_SPINLOCK(minor_lock);
 
-#define MAXIMUM_OUTSTANDING_BLOCK_REQS \
-	(BLKIF_MAX_SEGMENTS_PER_REQUEST * BLK_RING_SIZE)
 #define GRANT_INVALID_REF	0
 
 #define PARTS_PER_DISK		16
@@ -170,7 +183,7 @@ static int blkfront_setup_indirect(struct blkfront_info *info);
 static int get_id_from_freelist(struct blkfront_info *info)
 {
 	unsigned long free = info->shadow_free;
-	BUG_ON(free >= BLK_RING_SIZE);
+	BUG_ON(free >= BLK_RING_SIZE(info));
 	info->shadow_free = info->shadow[free].req.u.rw.id;
 	info->shadow[free].req.u.rw.id = 0x0fffffee; /* debug */
 	return free;
@@ -983,7 +996,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 		}
 	}
 
-	for (i = 0; i < BLK_RING_SIZE; i++) {
+	for (i = 0; i < BLK_RING_SIZE(info); i++) {
 		/*
 		 * Clear persistent grants present in requests already
 		 * on the shared ring
@@ -1033,12 +1046,15 @@ free_shadow:
 	flush_work(&info->work);
 
 	/* Free resources associated with old device channel. */
-	if (info->ring_ref != GRANT_INVALID_REF) {
-		gnttab_end_foreign_access(info->ring_ref, 0,
-					  (unsigned long)info->ring.sring);
-		info->ring_ref = GRANT_INVALID_REF;
-		info->ring.sring = NULL;
+	for (i = 0; i < info->nr_ring_pages; i++) {
+		if (info->ring_ref[i] != GRANT_INVALID_REF) {
+			gnttab_end_foreign_access(info->ring_ref[i], 0, 0);
+			info->ring_ref[i] = GRANT_INVALID_REF;
+		}
 	}
+	free_pages((unsigned long)info->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE));
+	info->ring.sring = NULL;
+
 	if (info->irq)
 		unbind_from_irqhandler(info->irq, info);
 	info->evtchn = info->irq = 0;
@@ -1157,7 +1173,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 		 * never have given to it (we stamp it up to BLK_RING_SIZE -
 		 * look in get_id_from_freelist.
 		 */
-		if (id >= BLK_RING_SIZE) {
+		if (id >= BLK_RING_SIZE(info)) {
 			WARN(1, "%s: response to %s has incorrect id (%ld)\n",
 			     info->gd->disk_name, op_name(bret->operation), id);
 			/* We can't safely get the 'struct request' as
@@ -1245,26 +1261,30 @@ static int setup_blkring(struct xenbus_device *dev,
 			 struct blkfront_info *info)
 {
 	struct blkif_sring *sring;
-	grant_ref_t gref;
-	int err;
+	int err, i;
+	unsigned long ring_size = info->nr_ring_pages * PAGE_SIZE;
+	grant_ref_t gref[XENBUS_MAX_RING_PAGES];
 
-	info->ring_ref = GRANT_INVALID_REF;
+	for (i = 0; i < info->nr_ring_pages; i++)
+		info->ring_ref[i] = GRANT_INVALID_REF;
 
-	sring = (struct blkif_sring *)__get_free_page(GFP_NOIO | __GFP_HIGH);
+	sring = (struct blkif_sring *)__get_free_pages(GFP_NOIO | __GFP_HIGH,
+						       get_order(ring_size));
 	if (!sring) {
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
 		return -ENOMEM;
 	}
 	SHARED_RING_INIT(sring);
-	FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE);
+	FRONT_RING_INIT(&info->ring, sring, ring_size);
 
-	err = xenbus_grant_ring(dev, info->ring.sring, 1, &gref);
+	err = xenbus_grant_ring(dev, info->ring.sring, info->nr_ring_pages, gref);
 	if (err < 0) {
-		free_page((unsigned long)sring);
+		free_pages((unsigned long)sring, get_order(ring_size));
 		info->ring.sring = NULL;
 		goto fail;
 	}
-	info->ring_ref = gref;
+	for (i = 0; i < info->nr_ring_pages; i++)
+		info->ring_ref[i] = gref[i];
 
 	err = xenbus_alloc_evtchn(dev, &info->evtchn);
 	if (err)
@@ -1292,7 +1312,18 @@ static int talk_to_blkback(struct xenbus_device *dev,
 {
 	const char *message = NULL;
 	struct xenbus_transaction xbt;
-	int err;
+	int err, i;
+	unsigned int max_page_order = 0;
+	unsigned int ring_page_order = 0;
+
+	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+			   "max-ring-page-order", "%u", &max_page_order);
+	if (err != 1)
+		info->nr_ring_pages = 1;
+	else {
+		ring_page_order = min(xen_blkif_max_ring_order, max_page_order);
+		info->nr_ring_pages = 1 << ring_page_order;
+	}
 
 	/* Create shared ring, alloc event channel. */
 	err = setup_blkring(dev, info);
@@ -1306,11 +1337,32 @@ again:
 		goto destroy_blkring;
 	}
 
-	err = xenbus_printf(xbt, dev->nodename,
-			    "ring-ref", "%u", info->ring_ref);
-	if (err) {
-		message = "writing ring-ref";
-		goto abort_transaction;
+	if (info->nr_ring_pages == 1) {
+		err = xenbus_printf(xbt, dev->nodename,
+				    "ring-ref", "%u", info->ring_ref[0]);
+		if (err) {
+			message = "writing ring-ref";
+			goto abort_transaction;
+		}
+	} else {
+		err = xenbus_printf(xbt, dev->nodename,
+				    "ring-page-order", "%u", ring_page_order);
+		if (err) {
+			message = "writing ring-page-order";
+			goto abort_transaction;
+		}
+
+		for (i = 0; i < info->nr_ring_pages; i++) {
+			char ring_ref_name[RINGREF_NAME_LEN];
+
+			snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
+			err = xenbus_printf(xbt, dev->nodename, ring_ref_name,
+					    "%u", info->ring_ref[i]);
+			if (err) {
+				message = "writing ring-ref";
+				goto abort_transaction;
+			}
+		}
 	}
 	err = xenbus_printf(xbt, dev->nodename,
 			    "event-channel", "%u", info->evtchn);
@@ -1338,6 +1390,9 @@ again:
 		goto destroy_blkring;
 	}
 
+	for (i = 0; i < BLK_RING_SIZE(info); i++)
+		info->shadow[i].req.u.rw.id = i+1;
+	info->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
 	xenbus_switch_state(dev, XenbusStateInitialised);
 
 	return 0;
@@ -1361,7 +1416,7 @@ again:
 static int blkfront_probe(struct xenbus_device *dev,
 			  const struct xenbus_device_id *id)
 {
-	int err, vdevice, i;
+	int err, vdevice;
 	struct blkfront_info *info;
 
 	/* FIXME: Use dynamic device id if this is not set. */
@@ -1422,21 +1477,10 @@ static int blkfront_probe(struct xenbus_device *dev,
 	info->connected = BLKIF_STATE_DISCONNECTED;
 	INIT_WORK(&info->work, blkif_restart_queue);
 
-	for (i = 0; i < BLK_RING_SIZE; i++)
-		info->shadow[i].req.u.rw.id = i+1;
-	info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
-
 	/* Front end dir is a number, which is used as the id. */
 	info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0);
 	dev_set_drvdata(&dev->dev, info);
 
-	err = talk_to_blkback(dev, info);
-	if (err) {
-		kfree(info);
-		dev_set_drvdata(&dev->dev, NULL);
-		return err;
-	}
-
 	return 0;
 }
 
@@ -1476,10 +1520,10 @@ static int blkif_recover(struct blkfront_info *info)
 
 	/* Stage 2: Set up free list. */
 	memset(&info->shadow, 0, sizeof(info->shadow));
-	for (i = 0; i < BLK_RING_SIZE; i++)
+	for (i = 0; i < BLK_RING_SIZE(info); i++)
 		info->shadow[i].req.u.rw.id = i+1;
 	info->shadow_free = info->ring.req_prod_pvt;
-	info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
+	info->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
 
 	rc = blkfront_setup_indirect(info);
 	if (rc) {
@@ -1491,7 +1535,7 @@ static int blkif_recover(struct blkfront_info *info)
 	blk_queue_max_segments(info->rq, segs);
 	bio_list_init(&bio_list);
 	INIT_LIST_HEAD(&requests);
-	for (i = 0; i < BLK_RING_SIZE; i++) {
+	for (i = 0; i < BLK_RING_SIZE(info); i++) {
 		/* Not in use? */
 		if (!copy[i].request)
 			continue;
@@ -1697,7 +1741,7 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
 		segs = info->max_indirect_segments;
 	}
 
-	err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE);
+	err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE(info));
 	if (err)
 		goto out_of_memory;
 
@@ -1707,7 +1751,7 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
 		 * grants, we need to allocate a set of pages that can be
 		 * used for mapping indirect grefs
 		 */
-		int num = INDIRECT_GREFS(segs) * BLK_RING_SIZE;
+		int num = INDIRECT_GREFS(segs) * BLK_RING_SIZE(info);
 
 		BUG_ON(!list_empty(&info->indirect_pages));
 		for (i = 0; i < num; i++) {
@@ -1718,7 +1762,7 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
 		}
 	}
 
-	for (i = 0; i < BLK_RING_SIZE; i++) {
+	for (i = 0; i < BLK_RING_SIZE(info); i++) {
 		info->shadow[i].grants_used = kzalloc(
 			sizeof(info->shadow[i].grants_used[0]) * segs,
 			GFP_NOIO);
@@ -1740,7 +1784,7 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
 	return 0;
 
 out_of_memory:
-	for (i = 0; i < BLK_RING_SIZE; i++) {
+	for (i = 0; i < BLK_RING_SIZE(info); i++) {
 		kfree(info->shadow[i].grants_used);
 		info->shadow[i].grants_used = NULL;
 		kfree(info->shadow[i].sg);
@@ -1906,8 +1950,15 @@ static void blkback_changed(struct xenbus_device *dev,
 	dev_dbg(&dev->dev, "blkfront:blkback_changed to state %d.\n", backend_state);
 
 	switch (backend_state) {
-	case XenbusStateInitialising:
 	case XenbusStateInitWait:
+		if (dev->state != XenbusStateInitialising)
+			break;
+		if (talk_to_blkback(dev, info)) {
+			kfree(info);
+			dev_set_drvdata(&dev->dev, NULL);
+			break;
+		}
+	case XenbusStateInitialising:
 	case XenbusStateInitialised:
 	case XenbusStateReconfiguring:
 	case XenbusStateReconfigured:
@@ -2091,6 +2142,12 @@ static int __init xlblk_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	if (xen_blkif_max_ring_order > XENBUS_MAX_RING_PAGE_ORDER) {
+		pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
+			xen_blkif_max_ring_order, XENBUS_MAX_RING_PAGE_ORDER);
+		xen_blkif_max_ring_order = 0;
+	}
+
 	if (!xen_has_pv_disk_devices())
 		return -ENODEV;
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b155d32db766..4fe10f93db8a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -43,7 +43,7 @@ static inline struct bdev_inode *BDEV_I(struct inode *inode)
 	return container_of(inode, struct bdev_inode, vfs_inode);
 }
 
-inline struct block_device *I_BDEV(struct inode *inode)
+struct block_device *I_BDEV(struct inode *inode)
 {
 	return &BDEV_I(inode)->bdev;
 }