Merge branch 'stable/for-linus-3.3' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

* 'stable/for-linus-3.3' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen: (37 commits)
  xen/pciback: Expand the warning message to include domain id.
  xen/pciback: Fix "device has been assigned to X domain!" warning
  xen/pciback: Move the PCI_DEV_FLAGS_ASSIGNED ops to the "[un|]bind"
  xen/xenbus: don't reimplement kvasprintf via a fixed size buffer
  xenbus: maximum buffer size is XENSTORE_PAYLOAD_MAX
  xen/xenbus: Reject replies with payload > XENSTORE_PAYLOAD_MAX.
  Xen: consolidate and simplify struct xenbus_driver instantiation
  xen-gntalloc: introduce missing kfree
  xen/xenbus: Fix compile error - missing header for xen_initial_domain()
  xen/netback: Enable netback on HVM guests
  xen/grant-table: Support mappings required by blkback
  xenbus: Use grant-table wrapper functions
  xenbus: Support HVM backends
  xen/xenbus-frontend: Fix compile error with randconfig
  xen/xenbus-frontend: Make error message more clear
  xen/privcmd: Remove unused support for arch specific privcmp mmap
  xen: Add xenbus_backend device
  xen: Add xenbus device driver
  xen: Add privcmd device driver
  xen/gntalloc: fix reference counts on multi-page mappings
  ...

24 files changed, 1038 insertions, 183 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 8795480c2350..a1ced521cf74 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -86,6 +86,7 @@ config XEN_BACKEND
 
 config XENFS
 	tristate "Xen filesystem"
+	select XEN_PRIVCMD
 	default y
 	help
 	  The xen filesystem provides a way for domains to share
@@ -171,4 +172,10 @@ config XEN_PCIDEV_BACKEND
 	  xen-pciback.hide=(03:00.0)(04:00.0)
 
 	  If in doubt, say m.
+
+config XEN_PRIVCMD
+	tristate
+	depends on XEN
+	default m
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 974fffdf22b2..aa31337192cc 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -19,7 +19,9 @@ obj-$(CONFIG_XEN_TMEM)			+= tmem.o
 obj-$(CONFIG_SWIOTLB_XEN)		+= swiotlb-xen.o
 obj-$(CONFIG_XEN_DOM0)			+= pci.o
 obj-$(CONFIG_XEN_PCIDEV_BACKEND)	+= xen-pciback/
+obj-$(CONFIG_XEN_PRIVCMD)		+= xen-privcmd.o
 
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
 xen-gntalloc-y				:= gntalloc.o
+xen-privcmd-y				:= privcmd.o
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 6e075cdd0c6b..e5e5812a1014 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -87,6 +87,7 @@ enum xen_irq_type {
  */
 struct irq_info {
 	struct list_head list;
+	int refcnt;
 	enum xen_irq_type type;	/* type */
 	unsigned irq;
 	unsigned short evtchn;	/* event channel */
@@ -406,6 +407,7 @@ static void xen_irq_init(unsigned irq)
 		panic("Unable to allocate metadata for IRQ%d\n", irq);
 
 	info->type = IRQT_UNBOUND;
+	info->refcnt = -1;
 
 	irq_set_handler_data(irq, info);
 
@@ -469,6 +471,8 @@ static void xen_free_irq(unsigned irq)
 
 	irq_set_handler_data(irq, NULL);
 
+	WARN_ON(info->refcnt > 0);
+
 	kfree(info);
 
 	/* Legacy IRQ descriptors are managed by the arch. */
@@ -637,7 +641,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 	if (irq != -1) {
 		printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n",
 		       irq, gsi);
-		goto out;	/* XXX need refcount? */
+		goto out;
 	}
 
 	irq = xen_allocate_irq_gsi(gsi);
@@ -939,9 +943,16 @@ static void unbind_from_irq(unsigned int irq)
 {
 	struct evtchn_close close;
 	int evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = irq_get_handler_data(irq);
 
 	mutex_lock(&irq_mapping_update_lock);
 
+	if (info->refcnt > 0) {
+		info->refcnt--;
+		if (info->refcnt != 0)
+			goto done;
+	}
+
 	if (VALID_EVTCHN(evtchn)) {
 		close.port = evtchn;
 		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
@@ -970,6 +981,7 @@ static void unbind_from_irq(unsigned int irq)
 
 	xen_free_irq(irq);
 
+ done:
 	mutex_unlock(&irq_mapping_update_lock);
 }
 
@@ -1065,6 +1077,69 @@ void unbind_from_irqhandler(unsigned int irq, void *dev_id)
 }
 EXPORT_SYMBOL_GPL(unbind_from_irqhandler);
 
+int evtchn_make_refcounted(unsigned int evtchn)
+{
+	int irq = evtchn_to_irq[evtchn];
+	struct irq_info *info;
+
+	if (irq == -1)
+		return -ENOENT;
+
+	info = irq_get_handler_data(irq);
+
+	if (!info)
+		return -ENOENT;
+
+	WARN_ON(info->refcnt != -1);
+
+	info->refcnt = 1;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(evtchn_make_refcounted);
+
+int evtchn_get(unsigned int evtchn)
+{
+	int irq;
+	struct irq_info *info;
+	int err = -ENOENT;
+
+	if (evtchn >= NR_EVENT_CHANNELS)
+		return -EINVAL;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	irq = evtchn_to_irq[evtchn];
+	if (irq == -1)
+		goto done;
+
+	info = irq_get_handler_data(irq);
+
+	if (!info)
+		goto done;
+
+	err = -EINVAL;
+	if (info->refcnt <= 0)
+		goto done;
+
+	info->refcnt++;
+	err = 0;
+ done:
+	mutex_unlock(&irq_mapping_update_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(evtchn_get);
+
+void evtchn_put(unsigned int evtchn)
+{
+	int irq = evtchn_to_irq[evtchn];
+	if (WARN_ON(irq == -1))
+		return;
+	unbind_from_irq(irq);
+}
+EXPORT_SYMBOL_GPL(evtchn_put);
+
 void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
 {
 	int irq = per_cpu(ipi_to_irq, cpu)[vector];
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index dbc13e94b612..b1f60a0c0bea 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -268,7 +268,7 @@ static int evtchn_bind_to_user(struct per_user_data *u, int port)
 	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
 				       u->name, (void *)(unsigned long)port);
 	if (rc >= 0)
-		rc = 0;
+		rc = evtchn_make_refcounted(port);
 
 	return rc;
 }
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
index e1c4c6e5b469..934985d14c24 100644
--- a/drivers/xen/gntalloc.c
+++ b/drivers/xen/gntalloc.c
@@ -74,7 +74,7 @@ MODULE_PARM_DESC(limit, "Maximum number of grants that may be allocated by "
 		"the gntalloc device");
 
 static LIST_HEAD(gref_list);
-static DEFINE_SPINLOCK(gref_lock);
+static DEFINE_MUTEX(gref_mutex);
 static int gref_size;
 
 struct notify_info {
@@ -99,6 +99,12 @@ struct gntalloc_file_private_data {
 	uint64_t index;
 };
 
+struct gntalloc_vma_private_data {
+	struct gntalloc_gref *gref;
+	int users;
+	int count;
+};
+
 static void __del_gref(struct gntalloc_gref *gref);
 
 static void do_cleanup(void)
@@ -143,15 +149,15 @@ static int add_grefs(struct ioctl_gntalloc_alloc_gref *op,
 	}
 
 	/* Add to gref lists. */
-	spin_lock(&gref_lock);
+	mutex_lock(&gref_mutex);
 	list_splice_tail(&queue_gref, &gref_list);
 	list_splice_tail(&queue_file, &priv->list);
-	spin_unlock(&gref_lock);
+	mutex_unlock(&gref_mutex);
 
 	return 0;
 
 undo:
-	spin_lock(&gref_lock);
+	mutex_lock(&gref_mutex);
 	gref_size -= (op->count - i);
 
 	list_for_each_entry(gref, &queue_file, next_file) {
@@ -167,7 +173,7 @@ undo:
 	 */
 	if (unlikely(!list_empty(&queue_gref)))
 		list_splice_tail(&queue_gref, &gref_list);
-	spin_unlock(&gref_lock);
+	mutex_unlock(&gref_mutex);
 	return rc;
 }
 
@@ -178,8 +184,10 @@ static void __del_gref(struct gntalloc_gref *gref)
 		tmp[gref->notify.pgoff] = 0;
 		kunmap(gref->page);
 	}
-	if (gref->notify.flags & UNMAP_NOTIFY_SEND_EVENT)
+	if (gref->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
 		notify_remote_via_evtchn(gref->notify.event);
+		evtchn_put(gref->notify.event);
+	}
 
 	gref->notify.flags = 0;
 
@@ -189,6 +197,8 @@ static void __del_gref(struct gntalloc_gref *gref)
 
 		if (!gnttab_end_foreign_access_ref(gref->gref_id, 0))
 			return;
+
+		gnttab_free_grant_reference(gref->gref_id);
 	}
 
 	gref_size--;
@@ -251,7 +261,7 @@ static int gntalloc_release(struct inode *inode, struct file *filp)
 
 	pr_debug("%s: priv %p\n", __func__, priv);
 
-	spin_lock(&gref_lock);
+	mutex_lock(&gref_mutex);
 	while (!list_empty(&priv->list)) {
 		gref = list_entry(priv->list.next,
 			struct gntalloc_gref, next_file);
@@ -261,7 +271,7 @@ static int gntalloc_release(struct inode *inode, struct file *filp)
 			__del_gref(gref);
 	}
 	kfree(priv);
-	spin_unlock(&gref_lock);
+	mutex_unlock(&gref_mutex);
 
 	return 0;
 }
@@ -286,21 +296,21 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
 		goto out;
 	}
 
-	spin_lock(&gref_lock);
+	mutex_lock(&gref_mutex);
 	/* Clean up pages that were at zero (local) users but were still mapped
 	 * by remote domains. Since those pages count towards the limit that we
 	 * are about to enforce, removing them here is a good idea.
 	 */
 	do_cleanup();
 	if (gref_size + op.count > limit) {
-		spin_unlock(&gref_lock);
+		mutex_unlock(&gref_mutex);
 		rc = -ENOSPC;
 		goto out_free;
 	}
 	gref_size += op.count;
 	op.index = priv->index;
 	priv->index += op.count * PAGE_SIZE;
-	spin_unlock(&gref_lock);
+	mutex_unlock(&gref_mutex);
 
 	rc = add_grefs(&op, gref_ids, priv);
 	if (rc < 0)
@@ -343,7 +353,7 @@ static long gntalloc_ioctl_dealloc(struct gntalloc_file_private_data *priv,
 		goto dealloc_grant_out;
 	}
 
-	spin_lock(&gref_lock);
+	mutex_lock(&gref_mutex);
 	gref = find_grefs(priv, op.index, op.count);
 	if (gref) {
 		/* Remove from the file list only, and decrease reference count.
@@ -363,7 +373,7 @@ static long gntalloc_ioctl_dealloc(struct gntalloc_file_private_data *priv,
 
 	do_cleanup();
 
-	spin_unlock(&gref_lock);
+	mutex_unlock(&gref_mutex);
 dealloc_grant_out:
 	return rc;
 }
@@ -383,7 +393,7 @@ static long gntalloc_ioctl_unmap_notify(struct gntalloc_file_private_data *priv,
 	index = op.index & ~(PAGE_SIZE - 1);
 	pgoff = op.index & (PAGE_SIZE - 1);
 
-	spin_lock(&gref_lock);
+	mutex_lock(&gref_mutex);
 
 	gref = find_grefs(priv, index, 1);
 	if (!gref) {
@@ -396,12 +406,30 @@ static long gntalloc_ioctl_unmap_notify(struct gntalloc_file_private_data *priv,
 		goto unlock_out;
 	}
 
+	/* We need to grab a reference to the event channel we are going to use
+	 * to send the notify before releasing the reference we may already have
+	 * (if someone has called this ioctl twice). This is required so that
+	 * it is possible to change the clear_byte part of the notification
+	 * without disturbing the event channel part, which may now be the last
+	 * reference to that event channel.
+	 */
+	if (op.action & UNMAP_NOTIFY_SEND_EVENT) {
+		if (evtchn_get(op.event_channel_port)) {
+			rc = -EINVAL;
+			goto unlock_out;
+		}
+	}
+
+	if (gref->notify.flags & UNMAP_NOTIFY_SEND_EVENT)
+		evtchn_put(gref->notify.event);
+
 	gref->notify.flags = op.action;
 	gref->notify.pgoff = pgoff;
 	gref->notify.event = op.event_channel_port;
 	rc = 0;
+
  unlock_out:
-	spin_unlock(&gref_lock);
+	mutex_unlock(&gref_mutex);
 	return rc;
 }
 
@@ -429,26 +457,40 @@ static long gntalloc_ioctl(struct file *filp, unsigned int cmd,
 
 static void gntalloc_vma_open(struct vm_area_struct *vma)
 {
-	struct gntalloc_gref *gref = vma->vm_private_data;
-	if (!gref)
+	struct gntalloc_vma_private_data *priv = vma->vm_private_data;
+
+	if (!priv)
 		return;
 
-	spin_lock(&gref_lock);
-	gref->users++;
-	spin_unlock(&gref_lock);
+	mutex_lock(&gref_mutex);
+	priv->users++;
+	mutex_unlock(&gref_mutex);
 }
 
 static void gntalloc_vma_close(struct vm_area_struct *vma)
 {
-	struct gntalloc_gref *gref = vma->vm_private_data;
-	if (!gref)
+	struct gntalloc_vma_private_data *priv = vma->vm_private_data;
+	struct gntalloc_gref *gref, *next;
+	int i;
+
+	if (!priv)
 		return;
 
-	spin_lock(&gref_lock);
-	gref->users--;
-	if (gref->users == 0)
-		__del_gref(gref);
-	spin_unlock(&gref_lock);
+	mutex_lock(&gref_mutex);
+	priv->users--;
+	if (priv->users == 0) {
+		gref = priv->gref;
+		for (i = 0; i < priv->count; i++) {
+			gref->users--;
+			next = list_entry(gref->next_gref.next,
+					  struct gntalloc_gref, next_gref);
+			if (gref->users == 0)
+				__del_gref(gref);
+			gref = next;
+		}
+		kfree(priv);
+	}
+	mutex_unlock(&gref_mutex);
 }
 
 static struct vm_operations_struct gntalloc_vmops = {
@@ -459,30 +501,41 @@ static struct vm_operations_struct gntalloc_vmops = {
 static int gntalloc_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct gntalloc_file_private_data *priv = filp->private_data;
+	struct gntalloc_vma_private_data *vm_priv;
 	struct gntalloc_gref *gref;
 	int count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 	int rv, i;
 
-	pr_debug("%s: priv %p, page %lu+%d\n", __func__,
-		       priv, vma->vm_pgoff, count);
-
 	if (!(vma->vm_flags & VM_SHARED)) {
 		printk(KERN_ERR "%s: Mapping must be shared.\n", __func__);
 		return -EINVAL;
 	}
 
-	spin_lock(&gref_lock);
+	vm_priv = kmalloc(sizeof(*vm_priv), GFP_KERNEL);
+	if (!vm_priv)
+		return -ENOMEM;
+
+	mutex_lock(&gref_mutex);
+
+	pr_debug("%s: priv %p,%p, page %lu+%d\n", __func__,
+		       priv, vm_priv, vma->vm_pgoff, count);
+
 	gref = find_grefs(priv, vma->vm_pgoff << PAGE_SHIFT, count);
 	if (gref == NULL) {
 		rv = -ENOENT;
 		pr_debug("%s: Could not find grant reference",
 				__func__);
+		kfree(vm_priv);
 		goto out_unlock;
 	}
 
-	vma->vm_private_data = gref;
+	vm_priv->gref = gref;
+	vm_priv->users = 1;
+	vm_priv->count = count;
+
+	vma->vm_private_data = vm_priv;
 
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_RESERVED | VM_DONTEXPAND;
 
 	vma->vm_ops = &gntalloc_vmops;
 
@@ -499,7 +552,7 @@ static int gntalloc_mmap(struct file *filp, struct vm_area_struct *vma)
 	rv = 0;
 
 out_unlock:
-	spin_unlock(&gref_lock);
+	mutex_unlock(&gref_mutex);
 	return rv;
 }
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index afca14d9042e..99d8151c824a 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -193,8 +193,10 @@ static void gntdev_put_map(struct grant_map *map)
 
 	atomic_sub(map->count, &pages_mapped);
 
-	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT)
+	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
 		notify_remote_via_evtchn(map->notify.event);
+		evtchn_put(map->notify.event);
+	}
 
 	if (map->pages) {
 		if (!use_ptemod)
@@ -312,7 +314,8 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
 		}
 	}
 
-	err = gnttab_unmap_refs(map->unmap_ops + offset, map->pages + offset, pages);
+	err = gnttab_unmap_refs(map->unmap_ops + offset, map->pages + offset,
+				pages, true);
 	if (err)
 		return err;
 
@@ -599,6 +602,8 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 	struct ioctl_gntdev_unmap_notify op;
 	struct grant_map *map;
 	int rc;
+	int out_flags;
+	unsigned int out_event;
 
 	if (copy_from_user(&op, u, sizeof(op)))
 		return -EFAULT;
@@ -606,6 +611,21 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 	if (op.action & ~(UNMAP_NOTIFY_CLEAR_BYTE|UNMAP_NOTIFY_SEND_EVENT))
 		return -EINVAL;
 
+	/* We need to grab a reference to the event channel we are going to use
+	 * to send the notify before releasing the reference we may already have
+	 * (if someone has called this ioctl twice). This is required so that
+	 * it is possible to change the clear_byte part of the notification
+	 * without disturbing the event channel part, which may now be the last
+	 * reference to that event channel.
+	 */
+	if (op.action & UNMAP_NOTIFY_SEND_EVENT) {
+		if (evtchn_get(op.event_channel_port))
+			return -EINVAL;
+	}
+
+	out_flags = op.action;
+	out_event = op.event_channel_port;
+
 	spin_lock(&priv->lock);
 
 	list_for_each_entry(map, &priv->maps, next) {
@@ -624,12 +644,22 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 		goto unlock_out;
 	}
 
+	out_flags = map->notify.flags;
+	out_event = map->notify.event;
+
 	map->notify.flags = op.action;
 	map->notify.addr = op.index - (map->index << PAGE_SHIFT);
 	map->notify.event = op.event_channel_port;
+
 	rc = 0;
+
  unlock_out:
 	spin_unlock(&priv->lock);
+
+	/* Drop the reference to the event channel we did not save in the map */
+	if (out_flags & UNMAP_NOTIFY_SEND_EVENT)
+		evtchn_put(out_event);
+
 	return rc;
 }
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index bf1c094f4ebf..1cd94daa71db 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -44,16 +44,19 @@
 #include <xen/page.h>
 #include <xen/grant_table.h>
 #include <xen/interface/memory.h>
+#include <xen/hvc-console.h>
 #include <asm/xen/hypercall.h>
 
 #include <asm/pgtable.h>
 #include <asm/sync_bitops.h>
 
-
 /* External tools reserve first few grant table entries. */
 #define NR_RESERVED_ENTRIES 8
 #define GNTTAB_LIST_END 0xffffffff
-#define GREFS_PER_GRANT_FRAME (PAGE_SIZE / sizeof(struct grant_entry))
+#define GREFS_PER_GRANT_FRAME \
+(grant_table_version == 1 ?                      \
+(PAGE_SIZE / sizeof(struct grant_entry_v1)) :   \
+(PAGE_SIZE / sizeof(union grant_entry_v2)))
 
 static grant_ref_t **gnttab_list;
 static unsigned int nr_grant_frames;
@@ -64,13 +67,97 @@ static DEFINE_SPINLOCK(gnttab_list_lock);
 unsigned long xen_hvm_resume_frames;
 EXPORT_SYMBOL_GPL(xen_hvm_resume_frames);
 
-static struct grant_entry *shared;
+static union {
+	struct grant_entry_v1 *v1;
+	union grant_entry_v2 *v2;
+	void *addr;
+} gnttab_shared;
+
+/*This is a structure of function pointers for grant table*/
+struct gnttab_ops {
+	/*
+	 * Mapping a list of frames for storing grant entries. Frames parameter
+	 * is used to store grant table address when grant table being setup,
+	 * nr_gframes is the number of frames to map grant table. Returning
+	 * GNTST_okay means success and negative value means failure.
+	 */
+	int (*map_frames)(unsigned long *frames, unsigned int nr_gframes);
+	/*
+	 * Release a list of frames which are mapped in map_frames for grant
+	 * entry status.
+	 */
+	void (*unmap_frames)(void);
+	/*
+	 * Introducing a valid entry into the grant table, granting the frame of
+	 * this grant entry to domain for accessing or transfering. Ref
+	 * parameter is reference of this introduced grant entry, domid is id of
+	 * granted domain, frame is the page frame to be granted, and flags is
+	 * status of the grant entry to be updated.
+	 */
+	void (*update_entry)(grant_ref_t ref, domid_t domid,
+			     unsigned long frame, unsigned flags);
+	/*
+	 * Stop granting a grant entry to domain for accessing. Ref parameter is
+	 * reference of a grant entry whose grant access will be stopped,
+	 * readonly is not in use in this function. If the grant entry is
+	 * currently mapped for reading or writing, just return failure(==0)
+	 * directly and don't tear down the grant access. Otherwise, stop grant
+	 * access for this entry and return success(==1).
+	 */
+	int (*end_foreign_access_ref)(grant_ref_t ref, int readonly);
+	/*
+	 * Stop granting a grant entry to domain for transfer. Ref parameter is
+	 * reference of a grant entry whose grant transfer will be stopped. If
+	 * tranfer has not started, just reclaim the grant entry and return
+	 * failure(==0). Otherwise, wait for the transfer to complete and then
+	 * return the frame.
+	 */
+	unsigned long (*end_foreign_transfer_ref)(grant_ref_t ref);
+	/*
+	 * Query the status of a grant entry. Ref parameter is reference of
+	 * queried grant entry, return value is the status of queried entry.
+	 * Detailed status(writing/reading) can be gotten from the return value
+	 * by bit operations.
+	 */
+	int (*query_foreign_access)(grant_ref_t ref);
+	/*
+	 * Grant a domain to access a range of bytes within the page referred by
+	 * an available grant entry. Ref parameter is reference of a grant entry
+	 * which will be sub-page accessed, domid is id of grantee domain, frame
+	 * is frame address of subpage grant, flags is grant type and flag
+	 * information, page_off is offset of the range of bytes, and length is
+	 * length of bytes to be accessed.
+	 */
+	void (*update_subpage_entry)(grant_ref_t ref, domid_t domid,
+				     unsigned long frame, int flags,
+				     unsigned page_off, unsigned length);
+	/*
+	 * Redirect an available grant entry on domain A to another grant
+	 * reference of domain B, then allow domain C to use grant reference
+	 * of domain B transitively. Ref parameter is an available grant entry
+	 * reference on domain A, domid is id of domain C which accesses grant
+	 * entry transitively, flags is grant type and flag information,
+	 * trans_domid is id of domain B whose grant entry is finally accessed
+	 * transitively, trans_gref is grant entry transitive reference of
+	 * domain B.
+	 */
+	void (*update_trans_entry)(grant_ref_t ref, domid_t domid, int flags,
+				   domid_t trans_domid, grant_ref_t trans_gref);
+};
+
+static struct gnttab_ops *gnttab_interface;
+
+/*This reflects status of grant entries, so act as a global value*/
+static grant_status_t *grstatus;
+
+static int grant_table_version;
 
 static struct gnttab_free_callback *gnttab_free_callback_list;
 
 static int gnttab_expand(unsigned int req_entries);
 
 #define RPP (PAGE_SIZE / sizeof(grant_ref_t))
+#define SPP (PAGE_SIZE / sizeof(grant_status_t))
 
 static inline grant_ref_t *__gnttab_entry(grant_ref_t entry)
 {
@@ -142,23 +229,33 @@ static void put_free_entry(grant_ref_t ref)
 	spin_unlock_irqrestore(&gnttab_list_lock, flags);
 }
 
-static void update_grant_entry(grant_ref_t ref, domid_t domid,
-			       unsigned long frame, unsigned flags)
+/*
+ * Following applies to gnttab_update_entry_v1 and gnttab_update_entry_v2.
+ * Introducing a valid entry into the grant table:
+ *  1. Write ent->domid.
+ *  2. Write ent->frame:
+ *      GTF_permit_access:   Frame to which access is permitted.
+ *      GTF_accept_transfer: Pseudo-phys frame slot being filled by new
+ *                           frame, or zero if none.
+ *  3. Write memory barrier (WMB).
+ *  4. Write ent->flags, inc. valid type.
+ */
+static void gnttab_update_entry_v1(grant_ref_t ref, domid_t domid,
+				   unsigned long frame, unsigned flags)
+{
+	gnttab_shared.v1[ref].domid = domid;
+	gnttab_shared.v1[ref].frame = frame;
+	wmb();
+	gnttab_shared.v1[ref].flags = flags;
+}
+
+static void gnttab_update_entry_v2(grant_ref_t ref, domid_t domid,
+				   unsigned long frame, unsigned flags)
 {
-	/*
-	 * Introducing a valid entry into the grant table:
-	 *  1. Write ent->domid.
-	 *  2. Write ent->frame:
-	 *      GTF_permit_access:   Frame to which access is permitted.
-	 *      GTF_accept_transfer: Pseudo-phys frame slot being filled by new
-	 *                           frame, or zero if none.
-	 *  3. Write memory barrier (WMB).
-	 *  4. Write ent->flags, inc. valid type.
-	 */
-	shared[ref].frame = frame;
-	shared[ref].domid = domid;
+	gnttab_shared.v2[ref].hdr.domid = domid;
+	gnttab_shared.v2[ref].full_page.frame = frame;
 	wmb();
-	shared[ref].flags = flags;
+	gnttab_shared.v2[ref].hdr.flags = GTF_permit_access | flags;
 }
 
 /*
@@ -167,7 +264,7 @@ static void update_grant_entry(grant_ref_t ref, domid_t domid,
 void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid,
 				     unsigned long frame, int readonly)
 {
-	update_grant_entry(ref, domid, frame,
+	gnttab_interface->update_entry(ref, domid, frame,
 			   GTF_permit_access | (readonly ? GTF_readonly : 0));
 }
 EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_ref);
@@ -187,31 +284,184 @@ int gnttab_grant_foreign_access(domid_t domid, unsigned long frame,
 }
 EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access);
 
-int gnttab_query_foreign_access(grant_ref_t ref)
+void gnttab_update_subpage_entry_v2(grant_ref_t ref, domid_t domid,
+				    unsigned long frame, int flags,
+				    unsigned page_off,
+				    unsigned length)
+{
+	gnttab_shared.v2[ref].sub_page.frame = frame;
+	gnttab_shared.v2[ref].sub_page.page_off = page_off;
+	gnttab_shared.v2[ref].sub_page.length = length;
+	gnttab_shared.v2[ref].hdr.domid = domid;
+	wmb();
+	gnttab_shared.v2[ref].hdr.flags =
+				GTF_permit_access | GTF_sub_page | flags;
+}
+
+int gnttab_grant_foreign_access_subpage_ref(grant_ref_t ref, domid_t domid,
+					    unsigned long frame, int flags,
+					    unsigned page_off,
+					    unsigned length)
 {
-	u16 nflags;
+	if (flags & (GTF_accept_transfer | GTF_reading |
+		     GTF_writing | GTF_transitive))
+		return -EPERM;
 
-	nflags = shared[ref].flags;
+	if (gnttab_interface->update_subpage_entry == NULL)
+		return -ENOSYS;
 
-	return nflags & (GTF_reading|GTF_writing);
+	gnttab_interface->update_subpage_entry(ref, domid, frame, flags,
+					       page_off, length);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_subpage_ref);
+
+int gnttab_grant_foreign_access_subpage(domid_t domid, unsigned long frame,
+					int flags, unsigned page_off,
+					unsigned length)
+{
+	int ref, rc;
+
+	ref = get_free_entries(1);
+	if (unlikely(ref < 0))
+		return -ENOSPC;
+
+	rc = gnttab_grant_foreign_access_subpage_ref(ref, domid, frame, flags,
+						     page_off, length);
+	if (rc < 0) {
+		put_free_entry(ref);
+		return rc;
+	}
+
+	return ref;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_subpage);
+
+bool gnttab_subpage_grants_available(void)
+{
+	return gnttab_interface->update_subpage_entry != NULL;
+}
+EXPORT_SYMBOL_GPL(gnttab_subpage_grants_available);
+
+void gnttab_update_trans_entry_v2(grant_ref_t ref, domid_t domid,
+				  int flags, domid_t trans_domid,
+				  grant_ref_t trans_gref)
+{
+	gnttab_shared.v2[ref].transitive.trans_domid = trans_domid;
+	gnttab_shared.v2[ref].transitive.gref = trans_gref;
+	gnttab_shared.v2[ref].hdr.domid = domid;
+	wmb();
+	gnttab_shared.v2[ref].hdr.flags =
+				GTF_permit_access | GTF_transitive | flags;
+}
+
+int gnttab_grant_foreign_access_trans_ref(grant_ref_t ref, domid_t domid,
+					  int flags, domid_t trans_domid,
+					  grant_ref_t trans_gref)
+{
+	if (flags & (GTF_accept_transfer | GTF_reading |
+		     GTF_writing | GTF_sub_page))
+		return -EPERM;
+
+	if (gnttab_interface->update_trans_entry == NULL)
+		return -ENOSYS;
+
+	gnttab_interface->update_trans_entry(ref, domid, flags, trans_domid,
+					     trans_gref);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_trans_ref);
+
+int gnttab_grant_foreign_access_trans(domid_t domid, int flags,
+				      domid_t trans_domid,
+				      grant_ref_t trans_gref)
+{
+	int ref, rc;
+
+	ref = get_free_entries(1);
+	if (unlikely(ref < 0))
+		return -ENOSPC;
+
+	rc = gnttab_grant_foreign_access_trans_ref(ref, domid, flags,
+						   trans_domid, trans_gref);
+	if (rc < 0) {
+		put_free_entry(ref);
+		return rc;
+	}
+
+	return ref;
+}
+EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_trans);
+
+bool gnttab_trans_grants_available(void)
+{
+	return gnttab_interface->update_trans_entry != NULL;
+}
+EXPORT_SYMBOL_GPL(gnttab_trans_grants_available);
+
+static int gnttab_query_foreign_access_v1(grant_ref_t ref)
+{
+	return gnttab_shared.v1[ref].flags & (GTF_reading|GTF_writing);
+}
+
+static int gnttab_query_foreign_access_v2(grant_ref_t ref)
+{
+	return grstatus[ref] & (GTF_reading|GTF_writing);
+}
+
+int gnttab_query_foreign_access(grant_ref_t ref)
+{
+	return gnttab_interface->query_foreign_access(ref);
 }
 EXPORT_SYMBOL_GPL(gnttab_query_foreign_access);
 
-int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly)
+static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly)
 {
 	u16 flags, nflags;
+	u16 *pflags;
 
-	nflags = shared[ref].flags;
+	pflags = &gnttab_shared.v1[ref].flags;
+	nflags = *pflags;
 	do {
 		flags = nflags;
 		if (flags & (GTF_reading|GTF_writing)) {
 			printk(KERN_ALERT "WARNING: g.e. still in use!\n");
 			return 0;
 		}
-	} while ((nflags = sync_cmpxchg(&shared[ref].flags, flags, 0)) != flags);
+	} while ((nflags = sync_cmpxchg(pflags, flags, 0)) != flags);
+
+	return 1;
+}
+
+static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref, int readonly)
+{
+	gnttab_shared.v2[ref].hdr.flags = 0;
+	mb();
+	if (grstatus[ref] & (GTF_reading|GTF_writing)) {
+		return 0;
+	} else {
+		/* The read of grstatus needs to have acquire
+		semantics.  On x86, reads already have
+		that, and we just need to protect against
+		com