12 files changed, 533 insertions, 148 deletions

diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 5dfd8f8ff07f..5876e1ae6c2d 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -501,20 +501,24 @@ EXPORT_SYMBOL_GPL(balloon_set_new_target);
  * alloc_xenballooned_pages - get pages that have been ballooned out
  * @nr_pages: Number of pages to get
  * @pages: pages returned
+ * @highmem: highmem or lowmem pages
  * @return 0 on success, error otherwise
  */
-int alloc_xenballooned_pages(int nr_pages, struct page** pages)
+int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
 {
         int pgno = 0;
         struct page* page;
         mutex_lock(&balloon_mutex);
         while (pgno < nr_pages) {
-                page = balloon_retrieve(true);
-                if (page) {
+                page = balloon_retrieve(highmem);
+                if (page && PageHighMem(page) == highmem) {
                         pages[pgno++] = page;
                 } else {
                         enum bp_state st;
-                        st = decrease_reservation(nr_pages - pgno, GFP_HIGHUSER);
+                        if (page)
+                                balloon_append(page);
+                        st = decrease_reservation(nr_pages - pgno,
+                                        highmem ? GFP_HIGHUSER : GFP_USER);
                         if (st != BP_DONE)
                                 goto out_undo;
                 }
@@ -555,17 +559,40 @@ void free_xenballooned_pages(int nr_pages, struct page** pages)
 }
 EXPORT_SYMBOL(free_xenballooned_pages);
 
-static int __init balloon_init(void)
+static void __init balloon_add_region(unsigned long start_pfn,
+                                      unsigned long pages)
 {
         unsigned long pfn, extra_pfn_end;
         struct page *page;
 
+        /*
+         * If the amount of usable memory has been limited (e.g., with
+         * the 'mem' command line parameter), don't add pages beyond
+         * this limit.
+         */
+        extra_pfn_end = min(max_pfn, start_pfn + pages);
+
+        for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) {
+                page = pfn_to_page(pfn);
+                /* totalram_pages and totalhigh_pages do not
+                   include the boot-time balloon extension, so
+                   don't subtract from it. */
+                __balloon_append(page);
+        }
+}
+
+static int __init balloon_init(void)
+{
+        int i;
+
         if (!xen_domain())
                 return -ENODEV;
 
         pr_info("xen/balloon: Initialising balloon driver.\n");
 
-        balloon_stats.current_pages = xen_pv_domain() ? min(xen_start_info->nr_pages, max_pfn) : max_pfn;
+        balloon_stats.current_pages = xen_pv_domain()
+                ? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
+                : max_pfn;
         balloon_stats.target_pages  = balloon_stats.current_pages;
         balloon_stats.balloon_low   = 0;
         balloon_stats.balloon_high  = 0;
@@ -584,24 +611,13 @@ static int __init balloon_init(void)
 #endif
 
         /*
-         * Initialise the balloon with excess memory space.  We need
-         * to make sure we don't add memory which doesn't exist or
-         * logically exist.  The E820 map can be trimmed to be smaller
-         * than the amount of physical memory due to the mem= command
-         * line parameter.  And if this is a 32-bit non-HIGHMEM kernel
-         * on a system with memory which requires highmem to access,
-         * don't try to use it.
+         * Initialize the balloon with pages from the extra memory
+         * regions (see arch/x86/xen/setup.c).
          */
-        extra_pfn_end = min(min(max_pfn, e820_end_of_ram_pfn()),
-                            (unsigned long)PFN_DOWN(xen_extra_mem_start + xen_extra_mem_size));
-        for (pfn = PFN_UP(xen_extra_mem_start);
-             pfn < extra_pfn_end;
-             pfn++) {
-                page = pfn_to_page(pfn);
-                /* totalram_pages and totalhigh_pages do not include the boot-time
-                   balloon extension, so don't subtract from it. */
-                __balloon_append(page);
-        }
+        for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++)
+                if (xen_extra_mem[i].size)
+                        balloon_add_region(PFN_UP(xen_extra_mem[i].start),
+                                           PFN_DOWN(xen_extra_mem[i].size));
 
         return 0;
 }
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index da70f5c32eb9..7a55b292bf39 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -54,7 +54,7 @@
  * This lock protects updates to the following mapping and reference-count
  * arrays. The lock does not need to be acquired to read the mapping tables.
  */
-static DEFINE_SPINLOCK(irq_mapping_update_lock);
+static DEFINE_MUTEX(irq_mapping_update_lock);
 
 static LIST_HEAD(xen_irq_list_head);
 
@@ -432,7 +432,8 @@ static int __must_check xen_allocate_irq_dynamic(void)
 
         irq = irq_alloc_desc_from(first, -1);
 
-        xen_irq_init(irq);
+        if (irq >= 0)
+                xen_irq_init(irq);
 
         return irq;
 }
@@ -631,7 +632,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
         int irq = -1;
         struct physdev_irq irq_op;
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         irq = find_irq_by_gsi(gsi);
         if (irq != -1) {
@@ -684,7 +685,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
                                 handle_edge_irq, name);
 
 out:
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
 
         return irq;
 }
@@ -710,10 +711,10 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 {
         int irq, ret;
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         irq = xen_allocate_irq_dynamic();
-        if (irq == -1)
+        if (irq < 0)
                 goto out;
 
         irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
@@ -724,12 +725,12 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
         if (ret < 0)
                 goto error_irq;
 out:
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
         return irq;
 error_irq:
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
         xen_free_irq(irq);
-        return -1;
+        return ret;
 }
 #endif
 
@@ -740,7 +741,7 @@ int xen_destroy_irq(int irq)
         struct irq_info *info = info_for_irq(irq);
         int rc = -ENOENT;
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         desc = irq_to_desc(irq);
         if (!desc)
@@ -766,7 +767,7 @@ int xen_destroy_irq(int irq)
         xen_free_irq(irq);
 
 out:
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
         return rc;
 }
 
@@ -776,10 +777,10 @@ int xen_irq_from_pirq(unsigned pirq)
 
         struct irq_info *info;
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         list_for_each_entry(info, &xen_irq_list_head, list) {
-                if (info == NULL || info->type != IRQT_PIRQ)
+                if (info->type != IRQT_PIRQ)
                         continue;
                 irq = info->irq;
                 if (info->u.pirq.pirq == pirq)
@@ -787,7 +788,7 @@ int xen_irq_from_pirq(unsigned pirq)
         }
         irq = -1;
 out:
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
 
         return irq;
 }
@@ -802,7 +803,7 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 {
         int irq;
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         irq = evtchn_to_irq[evtchn];
 
@@ -818,7 +819,7 @@ int bind_evtchn_to_irq(unsigned int evtchn)
         }
 
 out:
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
 
         return irq;
 }
@@ -829,7 +830,7 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
         struct evtchn_bind_ipi bind_ipi;
         int evtchn, irq;
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         irq = per_cpu(ipi_to_irq, cpu)[ipi];
 
@@ -853,7 +854,7 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
         }
 
  out:
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
         return irq;
 }
 
@@ -872,13 +873,34 @@ static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
         return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
 }
 
+static int find_virq(unsigned int virq, unsigned int cpu)
+{
+        struct evtchn_status status;
+        int port, rc = -ENOENT;
+
+        memset(&status, 0, sizeof(status));
+        for (port = 0; port <= NR_EVENT_CHANNELS; port++) {
+                status.dom = DOMID_SELF;
+                status.port = port;
+                rc = HYPERVISOR_event_channel_op(EVTCHNOP_status, &status);
+                if (rc < 0)
+                        continue;
+                if (status.status != EVTCHNSTAT_virq)
+                        continue;
+                if (status.u.virq == virq && status.vcpu == cpu) {
+                        rc = port;
+                        break;
+                }
+        }
+        return rc;
+}
 
 int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 {
         struct evtchn_bind_virq bind_virq;
-        int evtchn, irq;
+        int evtchn, irq, ret;
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         irq = per_cpu(virq_to_irq, cpu)[virq];
 
@@ -892,10 +914,16 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 
                 bind_virq.virq = virq;
                 bind_virq.vcpu = cpu;
-                if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
-                                                &bind_virq) != 0)
-                        BUG();
-                evtchn = bind_virq.port;
+                ret = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+                                                &bind_virq);
+                if (ret == 0)
+                        evtchn = bind_virq.port;
+                else {
+                        if (ret == -EEXIST)
+                                ret = find_virq(virq, cpu);
+                        BUG_ON(ret < 0);
+                        evtchn = ret;
+                }
 
                 xen_irq_info_virq_init(cpu, irq, evtchn, virq);
 
@@ -903,7 +931,7 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
         }
 
 out:
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
 
         return irq;
 }
@@ -913,7 +941,7 @@ static void unbind_from_irq(unsigned int irq)
         struct evtchn_close close;
         int evtchn = evtchn_from_irq(irq);
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         if (VALID_EVTCHN(evtchn)) {
                 close.port = evtchn;
@@ -943,7 +971,7 @@ static void unbind_from_irq(unsigned int irq)
 
         xen_free_irq(irq);
 
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
 }
 
 int bind_evtchn_to_irqhandler(unsigned int evtchn,
@@ -1279,7 +1307,7 @@ void rebind_evtchn_irq(int evtchn, int irq)
            will also be masked. */
         disable_irq(irq);
 
-        spin_lock(&irq_mapping_update_lock);
+        mutex_lock(&irq_mapping_update_lock);
 
         /* After resume the irq<->evtchn mappings are all cleared out */
         BUG_ON(evtchn_to_irq[evtchn] != -1);
@@ -1289,7 +1317,7 @@ void rebind_evtchn_irq(int evtchn, int irq)
 
         xen_irq_info_evtchn_init(irq, evtchn);
 
-        spin_unlock(&irq_mapping_update_lock);
+        mutex_unlock(&irq_mapping_update_lock);
 
         /* new event channels are always bound to cpu 0 */
         irq_set_affinity(irq, cpumask_of(0));
@@ -1670,6 +1698,7 @@ void __init xen_init_IRQ(void)
 
         evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
                                     GFP_KERNEL);
+        BUG_ON(!evtchn_to_irq);
         for (i = 0; i < NR_EVENT_CHANNELS; i++)
                 evtchn_to_irq[i] = -1;
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index f914b26cf0c2..880798aae2f2 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -83,6 +83,7 @@ struct grant_map {
         struct ioctl_gntdev_grant_ref *grants;
         struct gnttab_map_grant_ref   *map_ops;
         struct gnttab_unmap_grant_ref *unmap_ops;
+        struct gnttab_map_grant_ref   *kmap_ops;
         struct page **pages;
 };
 
@@ -116,19 +117,22 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
         add->grants    = kzalloc(sizeof(add->grants[0])    * count, GFP_KERNEL);
         add->map_ops   = kzalloc(sizeof(add->map_ops[0])   * count, GFP_KERNEL);
         add->unmap_ops = kzalloc(sizeof(add->unmap_ops[0]) * count, GFP_KERNEL);
+        add->kmap_ops  = kzalloc(sizeof(add->kmap_ops[0])  * count, GFP_KERNEL);
         add->pages     = kzalloc(sizeof(add->pages[0])     * count, GFP_KERNEL);
         if (NULL == add->grants    ||
             NULL == add->map_ops   ||
             NULL == add->unmap_ops ||
+            NULL == add->kmap_ops  ||
             NULL == add->pages)
                 goto err;
 
-        if (alloc_xenballooned_pages(count, add->pages))
+        if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */))
                 goto err;
 
         for (i = 0; i < count; i++) {
                 add->map_ops[i].handle = -1;
                 add->unmap_ops[i].handle = -1;
+                add->kmap_ops[i].handle = -1;
         }
 
         add->index = 0;
@@ -142,6 +146,7 @@ err:
         kfree(add->grants);
         kfree(add->map_ops);
         kfree(add->unmap_ops);
+        kfree(add->kmap_ops);
         kfree(add);
         return NULL;
 }
@@ -243,10 +248,35 @@ static int map_grant_pages(struct grant_map *map)
                         gnttab_set_unmap_op(&map->unmap_ops[i], addr,
                                 map->flags, -1 /* handle */);
                 }
+        } else {
+                /*
+                 * Setup the map_ops corresponding to the pte entries pointing
+                 * to the kernel linear addresses of the struct pages.
+                 * These ptes are completely different from the user ptes dealt
+                 * with find_grant_ptes.
+                 */
+                for (i = 0; i < map->count; i++) {
+                        unsigned level;
+                        unsigned long address = (unsigned long)
+                                pfn_to_kaddr(page_to_pfn(map->pages[i]));
+                        pte_t *ptep;
+                        u64 pte_maddr = 0;
+                        BUG_ON(PageHighMem(map->pages[i]));
+
+                        ptep = lookup_address(address, &level);
+                        pte_maddr = arbitrary_virt_to_machine(ptep).maddr;
+                        gnttab_set_map_op(&map->kmap_ops[i], pte_maddr,
+                                map->flags |
+                                GNTMAP_host_map |
+                                GNTMAP_contains_pte,
+                                map->grants[i].ref,
+                                map->grants[i].domid);
+                }
         }
 
         pr_debug("map %d+%d\n", map->index, map->count);
-        err = gnttab_map_refs(map->map_ops, map->pages, map->count);
+        err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
+                        map->pages, map->count);
         if (err)
                 return err;
 
@@ -462,13 +492,11 @@ static int gntdev_release(struct inode *inode, struct file *flip)
 
         pr_debug("priv %p\n", priv);
 
-        spin_lock(&priv->lock);
         while (!list_empty(&priv->maps)) {
                 map = list_entry(priv->maps.next, struct grant_map, next);
                 list_del(&map->next);
                 gntdev_put_map(map);
         }
-        spin_unlock(&priv->lock);
 
         if (use_ptemod)
                 mmu_notifier_unregister(&priv->mn, priv->mm);
@@ -532,10 +560,11 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
         map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
         if (map) {
                 list_del(&map->next);
-                gntdev_put_map(map);
                 err = 0;
         }
         spin_unlock(&priv->lock);
+        if (map)
+                gntdev_put_map(map);
         return err;
 }
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 4f44b347b24a..8c71ab801756 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -448,7 +448,8 @@ unsigned int gnttab_max_grant_frames(void)
 EXPORT_SYMBOL_GPL(gnttab_max_grant_frames);
 
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
-                    struct page **pages, unsigned int count)
+                        struct gnttab_map_grant_ref *kmap_ops,
+                        struct page **pages, unsigned int count)
 {
         int i, ret;
         pte_t *pte;
@@ -488,8 +489,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
                          */
                         return -EOPNOTSUPP;
                 }
-                ret = m2p_add_override(mfn, pages[i],
-                                       map_ops[i].flags & GNTMAP_contains_pte);
+                ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
                 if (ret)
                         return ret;
         }
diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
index cef4bafc07dc..66057075d6e2 100644
--- a/drivers/xen/pci.c
+++ b/drivers/xen/pci.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/pci.h>
+#include <linux/acpi.h>
 #include <xen/xen.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/xen.h>
@@ -26,26 +27,85 @@
 #include <asm/xen/hypercall.h>
 #include "../pci/pci.h"
 
+static bool __read_mostly pci_seg_supported = true;
+
 static int xen_add_device(struct device *dev)
 {
         int r;
         struct pci_dev *pci_dev = to_pci_dev(dev);
+#ifdef CONFIG_PCI_IOV
+        struct pci_dev *physfn = pci_dev->physfn;
+#endif
+
+        if (pci_seg_supported) {
+                struct physdev_pci_device_add add = {
+                        .seg = pci_domain_nr(pci_dev->bus),
+                        .bus = pci_dev->bus->number,
+                        .devfn = pci_dev->devfn
+                };
+#ifdef CONFIG_ACPI
+                acpi_handle handle;
+#endif
+
+#ifdef CONFIG_PCI_IOV
+                if (pci_dev->is_virtfn) {
+                        add.flags = XEN_PCI_DEV_VIRTFN;
+                        add.physfn.bus = physfn->bus->number;
+                        add.physfn.devfn = physfn->devfn;
+                } else
+#endif
+                if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn))
+                        add.flags = XEN_PCI_DEV_EXTFN;
+
+#ifdef CONFIG_ACPI
+                handle = DEVICE_ACPI_HANDLE(&pci_dev->dev);
+                if (!handle)
+                        handle = DEVICE_ACPI_HANDLE(pci_dev->bus->bridge);
+#ifdef CONFIG_PCI_IOV
+                if (!handle && pci_dev->is_virtfn)
+                        handle = DEVICE_ACPI_HANDLE(physfn->bus->bridge);
+#endif
+                if (handle) {
+                        acpi_status status;
+
+                        do {
+                                unsigned long long pxm;
+
+                                status = acpi_evaluate_integer(handle, "_PXM",
+                                                               NULL, &pxm);
+                                if (ACPI_SUCCESS(status)) {
+                                        add.optarr[0] = pxm;
+                                        add.flags |= XEN_PCI_DEV_PXM;
+                                        break;
+                                }
+                                status = acpi_get_parent(handle, &handle);
+                        } while (ACPI_SUCCESS(status));
+                }
+#endif /* CONFIG_ACPI */
+
+                r = HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_add, &add);
+                if (r != -ENOSYS)
+                        return r;
+                pci_seg_supported = false;
+        }
 
+        if (pci_domain_nr(pci_dev->bus))
+                r = -ENOSYS;
 #ifdef CONFIG_PCI_IOV
-        if (pci_dev->is_virtfn) {
+        else if (pci_dev->is_virtfn) {
                 struct physdev_manage_pci_ext manage_pci_ext = {
                         .bus            = pci_dev->bus->number,
                         .devfn          = pci_dev->devfn,
                         .is_virtfn      = 1,
-                        .physfn.bus     = pci_dev->physfn->bus->number,
-                        .physfn.devfn   = pci_dev->physfn->devfn,
+                        .physfn.bus     = physfn->bus->number,
+                        .physfn.devfn   = physfn->devfn,
                 };
 
                 r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add_ext,
                         &manage_pci_ext);
-        } else
+        }
 #endif
-        if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn)) {
+        else if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn)) {
                 struct physdev_manage_pci_ext manage_pci_ext = {
                         .bus            = pci_dev->bus->number,
                         .devfn          = pci_dev->devfn,
@@ -71,13 +131,27 @@ static int xen_remove_device(struct device *dev)
 {
         int r;
         struct pci_dev *pci_dev = to_pci_dev(dev);
-        struct physdev_manage_pci manage_pci;
 
-        manage_pci.bus = pci_dev->bus->number;
-        manage_pci.devfn = pci_dev->devfn;
+        if (pci_seg_supported) {
+                struct physdev_pci_device device = {
+                        .seg = pci_domain_nr(pci_dev->bus),
+                        .bus = pci_dev->bus->number,
+                        .devfn = pci_dev->devfn
+                };
 
-        r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_remove,
-                &manage_pci);
+                r = HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_remove,
+                                          &device);
+        } else if (pci_domain_nr(pci_dev->bus))
+                r = -ENOSYS;
+        else {
+                struct physdev_manage_pci manage_pci = {
+                        .bus = pci_dev->bus->number,
+                        .devfn = pci_dev->devfn
+                };
+
+                r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_remove,
+                                          &manage_pci);
+        }
 
         return r;
 }
@@ -96,13 +170,16 @@ static int xen_pci_notifier(struct notifier_block *nb,
                 r = xen_remove_device(dev);
                 break;
         default:
-                break;
+                return NOTIFY_DONE;
         }
-
-        return r;
+        if (r)
+                dev_err(dev, "Failed to %s - passthrough or MSI/MSI-X might fail!\n",
+                        action == BUS_NOTIFY_ADD_DEVICE ? "add" :
+                        (action == BUS_NOTIFY_DEL_DEVICE ? "delete" : "?"));
+        return NOTIFY_OK;
 }
 
-struct notifier_block device_nb = {
+static struct notifier_block device_nb = {
         .notifier_call = xen_pci_notifier,
 };
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 6e8c15a23201..c984768d98ca 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -38,6 +38,7 @@
 #include <xen/swiotlb-xen.h>
 #include <xen/page.h>
 #include <xen/xen-ops.h>
+#include <xen/hvc-console.h>
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
  * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
@@ -146,8 +147,10 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 void __init xen_swiotlb_init(int verbose)
 {
         unsigned long bytes;
-        int rc;
+        int rc = -ENOMEM;
         unsigned long nr_tbl;
+        char *m = NULL;
+        unsigned int repeat = 3;
 
         nr_tbl = swioltb_nr_tbl();
         if (nr_tbl)
@@ -156,16 +159,17 @@ void __init xen_swiotlb_init(int verbose)
                 xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
                 xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
         }
-
+retry:
         bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
 
         /*
          * Get IO TLB memory from any location.
          */
         xen_io_tlb_start = alloc_bootmem(bytes);
-        if (!xen_io_tlb_start)
-                panic("Cannot allocate SWIOTLB buffer");
-
+        if (!xen_io_tlb_start) {
+                m = "Cannot allocate Xen-SWIOTLB buffer!\n";
+                goto error;
+        }
         xen_io_tlb_end = xen_io_tlb_start + bytes;
         /*
          * And replace that memory with pages under 4GB.
@@ -173,17 +177,28 @@ void __init xen_swiotlb_init(int verbose)
         rc = xen_swiotlb_fixup(xen_io_tlb_start,
                                bytes,
                                xen_io_tlb_nslabs);
-        if (rc)
+        if (rc) {
+                free_bootmem(__pa(xen_io_tlb_start), bytes);
+                m = "Failed to get contiguous memory for DMA from Xen!\n"\
+                    "You either: don't have the permissions, do not have"\
+                    " enough free memory under 4GB, or the hypervisor memory"\
+                    "is too fragmented!";
                 goto error;
-
+        }
         start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
         swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
 
         return;
 error:
-        panic("DMA(%d): Failed to exchange pages allocated for DMA with Xen! "\
-              "We either don't have the permission or you do not have enough"\
-              "free memory under 4GB!\n", rc);
+        if (repeat--) {
+                xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
+                                        (xen_io_tlb_nslabs >> 1));
+                printk(KERN_INFO "Xen-SWIOTLB: Lowering to %luMB\n",
+                      (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
+                goto retry;
+        }
+        xen_raw_printk("%s (rc:%d)", m, rc);
+        panic("%s (rc:%d)", m, rc);
 }
 
 void *
@@ -194,6 +209,8 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         int order = get_order(size);
         u64 dma_mask = DMA_BIT_MASK(32);
         unsigned long vstart;
+        phys_addr_t phys;
+        dma_addr_t dev_addr;
 
         /*
         * Ignore region specifiers - the kernel's ideas of
@@ -209,18 +226,26 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         vstart = __get_free_pages(flags, order);
         ret = (void *)vstart;
 
+        if (!ret)
+                return ret;
+
         if (hwdev && hwdev->coherent_dma_mask)
-                dma_mask = dma_alloc_coherent_mask(hwdev, flags);
+                dma_mask = hwdev->coherent_dma_mask;
 
-        if (ret) {
+        phys = virt_to_phys(ret);
+        dev_addr = xen_phys_to_bus(phys);
+        if (((dev_addr + size - 1 <= dma_mask)) &&
+            !range_straddles_page_boundary(phys, size))
+                *dma_handle = dev_addr;
+        else {
                 if (xen_create_contiguous_region(vstart, order,
                                                  fls64(dma_mask)) != 0) {
                         free_pages(vstart, order);
                         return NULL;
                 }
-                memset(ret, 0, size);
                 *dma_handle = virt_to_machine(ret).maddr;
         }
+        memset(ret, 0, size);
         return ret;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
@@ -230,11 +255,21 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
                           dma_addr_t dev_addr)
 {
         int order = get_order(size);
+        phys_addr_t phys;
+        u64 dma_mask = DMA_BIT_MASK(32);
 
         if (dma_release_from_coherent(hwdev, order, vaddr))
                 return;
 
-        xen_destroy_contiguous_region((unsigned long)vaddr, order);
+        if (hwdev && hwdev->coherent_dma_mask)
+                dma_mask = hwdev->coherent_dma_mask;
+
+        phys = virt_to_phys(vaddr);
+
+        if (((dev_addr + size - 1 > dma_mask)) ||
+            range_straddles_page_boundary(phys, size))
+                xen_destroy_contiguous_region((unsigned long)vaddr, order);
+
         free_pages((unsigned long)vaddr, order);
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
@@ -278,9 +313,10 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
         /*
          * Ensure that the address returned is DMA'ble
          */
-        if (!dma_capable(dev, dev_addr, size))
-                panic("map_single: bounce buffer is not DMA'ble");
-
+        if (!dma_capable(dev, dev_addr, size)) {
+                swiotlb_tbl_unmap_single(dev, map, size, dir);
+                dev_addr = 0;
+        }
         return dev_addr;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c
index 6ea852e25162..d93c70857e03 100644
--- a/drivers/xen/xen-selfballoon.c
+++ b/drivers/xen/xen-selfballoon.c
@@ -68,6 +68,8 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/bootmem.h>
+#include <linux/swap.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/module.h>
@@ -93,6 +95,15 @@ static unsigned int selfballoon_uphysteresis __read_mostly = 1;
 /* In HZ, controls frequency of worker invocation. */
 static unsigned int selfballoon_interval __read_mostly = 5;
 
+/*
+ * Minimum usable RAM in MB for selfballooning target for balloon.
+ * If non-zero, it is added to totalreserve_pages and self-ballooning
+ * will not balloon below the sum.  If zero, a piecewise linear function
+ * is calculated as a minimum and added to totalreserve_pages.  Note that
+ * setting this value indiscriminately may cause OOMs and crashes.
+ */
+static unsigned int selfballoon_min_usable_mb;
+
 static void selfballoon_process(struct work_struct *work);
 static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
 
@@ -189,20 +200,23 @@ static int __init xen_selfballooning_setup(char *s)
 __setup("selfballooning", xen_selfballooning_setup);
 #endif /* CONFIG_FRONTSWAP */
 
+#define MB2PAGES(mb)    ((mb) << (20 - PAGE_SHIFT))
+
 /*
  * Use current balloon size, the goal (vm_committed_as), and hysteresis
  * parameters to set a new target balloon size
  */
 static void selfballoon_process(struct work_struct *work)
 {
-        unsigned long cur_pages, goal_pages, tgt_pages;
+        unsigned long cur_pages, goal_pages, tgt_pages, floor_pages;
+        unsigned long useful_pages;
         bool reset_timer = false;
 
         if (xen_selfballooning_enabled) {
-                cur_pages = balloon_stats.current_pages;
+                cur_pages = totalram_pages;
                 tgt_pages = cur_pages; /* default is no change */
                 goal_pages = percpu_counter_read_positive(&vm_committed_as) +
-                        balloon_stats.current_pages - totalram_pages;
+                                totalreserve_pages;
 #ifdef CONFIG_FRONTSWAP
                 /* allow space for frontswap pages to be repatriated */
                 if (frontswap_selfshrinking && frontswap_enabled)
@@ -217,7 +231,26 @@ static void selfballoon_process(struct work_struct *work)
                                 ((goal_pages - cur_pages) /
                                   selfballoon_uphysteresis);
                 /* else if cur_pages == goal_pages, no change */
-                balloon_set_new_target(tgt_pages);
+                useful_pages = max_pfn - totalreserve_pages;
+                if (selfballoon_min_usable_mb != 0)
+                        floor_pages = totalreserve_pages +
+                                        MB2PAGES(selfballoon_min_usable_mb);
+                /* piecewise linear function ending in ~3% slope */
+                else if (useful_pages < MB2PAGES(16))
+                        floor_pages = max_pfn; /* not worth ballooning */
+                else if (useful_pages < MB2PAGES(64))
+                        floor_pages = totalreserve_pages + MB2PAGES(16) +
+                                        ((useful_pages - MB2PAGES(16)) >> 1);
+                else if (useful_pages < MB2PAGES(512))
+                        floor_pages = totalreserve_pages + MB2PAGES(40) +
+                                        ((useful_pages - MB2PAGES(40)) >> 3);
+                else /* useful_pages >= MB2PAGES(512) */
+                        floor_pages = totalreserve_pages + MB2PAGES(99) +
+                                        ((useful_pages - MB2PAGES(99)) >> 5);
+                if (tgt_pages < floor_pages)
+                        tgt_pages = floor_pages;
+                balloon_set_new_target(tgt_pages +
+                        balloon_stats.current_pages - totalram_pages);
                 reset_timer = true;
         }
 #ifdef CONFIG_FRONTSWAP
@@ -340,6 +373,31 @@ static ssize_t store_selfballoon_uphys(struct sys_device *dev,
 static SYSDEV_ATTR(selfballoon_uphysteresis, S_IRUGO | S_IWUSR,
                    show_selfballoon_uphys, store_selfballoon_uphys);
 
+SELFBALLOON_SHOW(selfballoon_min_usable_mb, "%d\n",
+                                selfballoon_min_usable_mb);
+
+static ssize_t store_selfballoon_min_usable_mb(struct sys_device *dev,
+                                               struct sysdev_attribute *attr,
+                                               const char *buf,
+                                               size_t count)
+{
+        unsigned long val;
+        int err;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+        err = strict_strtoul(buf, 10, &val);
+        if (err || val == 0)
+                return -EINVAL;
+        selfballoon_min_usable_mb = val;
+        return count;
+}
+
+static SYSDEV_ATTR(selfballoon_min_usable_mb, S_IRUGO | S_IWUSR,
+                   show_selfballoon_min_usable_mb,
+                   store_selfballoon_min_usable_mb);
+
+
 #ifdef CONFIG_FRONTSWAP
 SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking);
 
@@ -421,6 +479,7 @@ static struct attribute *selfballoon_attrs[] = {
         &attr_selfballoon_interval.attr,
         &attr_selfballoon_downhysteresis.attr,
         &attr_selfballoon_uphysteresis.attr,
+        &attr_selfballoon_min_usable_mb.attr,
 #ifdef CONFIG_FRONTSWAP
         &attr_frontswap_selfshrinking.attr,
         &attr_frontswap_hysteresis.attr,
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index 090c61ee8fd0..2eff7a6aaa20 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -212,7 +212,9 @@ int xb_init_comms(void)
                 printk(KERN_WARNING "XENBUS response ring is not quiescent "
                        "(%08x:%08x): fixing up\n",
                        intf->rsp_cons, intf->rsp_prod);
-                intf->rsp_cons = intf->rsp_prod;
+                /* breaks kdump */
+                if (!reset_devices)
+                        intf->rsp_cons = intf->rsp_prod;
         }
 
         if (xenbus_irq) {
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index bd2f90c9ac8b..cef9b0bf63d5 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -684,64 +684,74 @@ static int __init xenbus_probe_initcall(void)
 
 device_initcall(xenbus_probe_initcall);
 
-static int __init xenbus_init(void)
+/* Set up event channel for xenstored which is run as a local process
+ * (this is normally used only in dom0)
+ */
+static int __init xenstored_local_init(void)
 {
         int err = 0;
         unsigned long page = 0;
+        struct evtchn_alloc_unbound alloc_unbound;
 
-        DPRINTK("");
+        /* Allocate Xenstore page */
+        page = get_zeroed_page(GFP_KERNEL);
+        if (!page)
+                goto out_err;
 
-        err = -ENODEV;
-        if (!xen_domain())
-                return err;
+        xen_store_mfn = xen_start_info->store_mfn =
+                pfn_to_mfn(virt_to_phys((void *)page) >>
+                           PAGE_SHIFT);
 
-        /*
-         * Domain0 doesn't have a store_evtchn or store_mfn yet.
-         */
-        if (xen_initial_domain()) {
-                struct evtchn_alloc_unbound alloc_unbound;
+        /* Next allocate a local port which xenstored can bind to */
+        alloc_unbound.dom        = DOMID_SELF;
+        alloc_unbound.remote_dom = DOMID_SELF;
 
-                /* Allocate Xenstore page */
-                page = get_zeroed_page(GFP_KERNEL);
-                if (!page)
-                        goto out_error;
+        err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+                                          &alloc_unbound);
+        if (err == -ENOSYS)
+                goto out_err;
 
-                xen_store_mfn = xen_start_info->store_mfn =
-                        pfn_to_mfn(virt_to_phys((void *)page) >>
-                                   PAGE_SHIFT);
+        BUG_ON(err);
+        xen_store_evtchn = xen_start_info->store_evtchn =
+                alloc_unbound.port;
 
-                /* Next allocate a local port which xenstored can bind to */
-                alloc_unbound.dom        = DOMID_SELF;
-                alloc_unbound.remote_dom = 0;
+        return 0;
 
-                err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
-                                                  &alloc_unbound);
-                if (err == -ENOSYS)
-                        goto out_error;
+ out_err:
+        if (page != 0)
+                free_page(page);
+        return err;
+}
 
-                BUG_ON(err);
-                xen_store_evtchn = xen_start_info->store_evtchn =
-                        alloc_unbound.port;
+static int __init xenbus_init(void)
+{
+        int err = 0;
 
-                xen_store_interface = mfn_to_virt(xen_store_mfn);
+        if (!xen_domain())
+                return -ENODEV;
+
+        if (xen_hvm_domain()) {
+                uint64_t v = 0;
+                err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
+                if (err)
+                        goto out_error;
+                xen_store_evtchn = (int)v;
+                err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
+                if (err)
+                        goto out_error;
+                xen_store_mfn = (unsigned long)v;
+                xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
         } else {
-                if (xen_hvm_domain()) {
-                        uint64_t v = 0;
-                        err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
-                        if (err)
-                                goto out_error;
-                        xen_store_evtchn = (int)v;
-                        err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
+                xen_store_evtchn = xen_start_info->store_evtchn;
+                xen_store_mfn = xen_start_info->store_mfn;
+                if (xen_store_evtchn)
+                        xenstored_ready = 1;
+                else {
+                        err = xenstored_local_init();
                         if (err)
                                 goto out_error;
-                        xen_store_mfn = (unsigned long)v;
-                        xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
-                } else {
-                        xen_store_evtchn = xen_start_info->store_evtchn;
-                        xen_store_mfn = xen_start_info->store_mfn;
-                        xen_store_interface = mfn_to_virt(xen_store_mfn);
-                        xenstored_ready = 1;
                 }
+                xen_store_interface = mfn_to_virt(xen_store_mfn);
         }
 
         /* Initialize the interface to xenstore. */
@@ -760,12 +770,7 @@ static int __init xenbus_init(void)
         proc_mkdir("xen", NULL);
 #endif
 
-        return 0;
-
-  out_error:
-        if (page != 0)
-                free_page(page);
-
+ out_error:
         return err;
 }
 
diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c
index 60adf919d78d..32417b5064fd 100644
--- a/drivers/xen/xenbus/xenbus_probe_backend.c
+++ b/drivers/xen/xenbus/xenbus_probe_backend.c
@@ -104,8 +104,6 @@ static int xenbus_uevent_backend(struct device *dev,
 
         xdev = to_xenbus_device(dev);
         bus = container_of(xdev->dev.bus, struct xen_bus_type, bus);
-        if (xdev == NULL)
-                return -ENODEV;
 
         if (add_uevent_var(env, "MODALIAS=xen-backend:%s", xdev->devicetype))
                 return -ENOMEM;
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index ed2ba474a560..540587e18a94 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -248,10 +248,131 @@ int __xenbus_register_frontend(struct xenbus_driver *drv,
 }
 EXPORT_SYMBOL_GPL(__xenbus_register_frontend);
 
+static DECLARE_WAIT_QUEUE_HEAD(backend_state_wq);
+static int backend_state;
+
+static void xenbus_reset_backend_state_changed(struct xenbus_watch *w,
+                                        const char **v, unsigned int l)
+{
+        xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i", &backend_state);
+        printk(KERN_DEBUG "XENBUS: backend %s %s\n",
+                        v[XS_WATCH_PATH], xenbus_strstate(backend_state));
+        wake_up(&backend_state_wq);
+}
+
+static void xenbus_reset_wait_for_backend(char *be, int expected)
+{
+        long timeout;
+        timeout = wait_event_interruptible_timeout(backend_state_wq,
+                        backend_state == expected, 5 * HZ);
+        if (timeout <= 0)
+                printk(KERN_INFO "XENBUS: backend %s timed out.\n", be);
+}
+
+/*
+ * Reset frontend if it is in Connected or Closed state.
+ * Wait for backend to catch up.
+ * State Connected happens during kdump, Closed after kexec.
+ */
+static void xenbus_reset_frontend(char *fe, char *be, int be_state)
+{
+        struct xenbus_watch be_watch;
+
+        printk(KERN_DEBUG "XENBUS: backend %s %s\n",
+                        be, xenbus_strstate(be_state));
+
+        memset(&be_watch, 0, sizeof(be_watch));
+        be_watch.node = kasprintf(GFP_NOIO | __GFP_HIGH, "%s/state", be);
+        if (!be_watch.node)
+                return;
+
+        be_watch.callback = xenbus_reset_backend_state_changed;
+        backend_state = XenbusStateUnknown;
+
+        printk(KERN_INFO "XENBUS: triggering reconnect on %s\n", be);
+        register_xenbus_watch(&be_watch);
+
+        /* fall through to forward backend to state XenbusStateInitialising */
+        switch (be_state) {
+        case XenbusStateConnected:
+                xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosing);
+                xenbus_reset_wait_for_backend(be, XenbusStateClosing);
+
+        case XenbusStateClosing:
+                xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateClosed);
+                xenbus_reset_wait_for_backend(be, XenbusStateClosed);
+
+        case XenbusStateClosed:
+                xenbus_printf(XBT_NIL, fe, "state", "%d", XenbusStateInitialising);
+                xenbus_reset_wait_for_backend(be, XenbusStateInitWait);
+        }
+
+        unregister_xenbus_watch(&be_watch);
+        printk(KERN_INFO "XENBUS: reconnect done on %s\n", be);
+        kfree(be_watch.node);
+}
+
+static void xenbus_check_frontend(char *class, char *dev)
+{
+        int be_state, fe_state, err;
+        char *backend, *frontend;
+
+        frontend = kasprintf(GFP_NOIO | __GFP_HIGH, "device/%s/%s", class, dev);
+        if (!frontend)
+                return;
+
+        err = xenbus_scanf(XBT_NIL, frontend, "state", "%i", &fe_state);
+        if (err != 1)
+                goto out;
+
+        switch (fe_state) {
+        case XenbusStateConnected:
+        case XenbusStateClosed:
+                printk(KERN_DEBUG "XENBUS: frontend %s %s\n",
+                                frontend, xenbus_strstate(fe_state));
+                backend = xenbus_read(XBT_NIL, frontend, "backend", NULL);
+                if (!backend || IS_ERR(backend))
+                        goto out;
+                err = xenbus_scanf(XBT_NIL, backend, "state", "%i", &be_state);
+                if (err == 1)
+                        xenbus_reset_frontend(frontend, backend, be_state);
+                kfree(backend);
+                break;
+        default:
+                break;
+        }
+out:
+        kfree(frontend);
+}
+
+static void xenbus_reset_state(void)
+{
+        char **devclass, **dev;
+        int devclass_n, dev_n;
+        int i, j;
+
+        devclass = xenbus_directory(XBT_NIL, "device", "", &devclass_n);
+        if (IS_ERR(devclass))
+                return;
+
+        for (i = 0; i < devclass_n; i++) {
+                dev = xenbus_directory(XBT_NIL, "device", devclass[i], &dev_n);
+                if (IS_ERR(dev))
+                        continue;
+                for (j = 0; j < dev_n; j++)
+                        xenbus_check_frontend(devclass[i], dev[j]);
+                kfree(dev);
+        }
+        kfree(devclass);
+}
+
 static int frontend_probe_and_watch(struct notifier_block *notifier,
                                    unsigned long event,
                                    void *data)
 {
+        /* reset devices in Connected or Closed state */
+        if (xen_hvm_domain())
+                xenbus_reset_state();
         /* Enumerate devices in xenstore and watch for changes. */
         xenbus_probe_devices(&xenbus_frontend);
         register_xenbus_watch(&fe_watch);
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index 5534690075af..b3b8f2f3ad10 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -45,6 +45,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <xen/xenbus.h>
+#include <xen/xen.h>
 #include "xenbus_comms.h"
 
 struct xs_stored_msg {
@@ -620,6 +621,15 @@ static struct xenbus_watch *find_watch(const char *token)
         return NULL;
 }
 
+static void xs_reset_watches(void)
+{
+        int err;
+
+        err = xs_error(xs_single(XBT_NIL, XS_RESET_WATCHES, "", NULL));
+        if (err && err != -EEXIST)
+                printk(KERN_WARNING "xs_reset_watches failed: %d\n", err);
+}
+
 /* Register callback to watch this node. */
 int register_xenbus_watch(struct xenbus_watch *watch)
 {
@@ -638,8 +648,7 @@ int register_xenbus_watch(struct xenbus_watch *watch)
 
         err = xs_watch(watch->node, token);
 
-        /* Ignore errors due to multiple registration. */
-        if ((err != 0) && (err != -EEXIST)) {
+        if (err) {
                 spin_lock(&watches_lock);
                 list_del(&watch->list);
                 spin_unlock(&watches_lock);
@@ -897,5 +906,9 @@ int xs_init(void)
         if (IS_ERR(task))
                 return PTR_ERR(task);
 
+        /* shutdown watches for kexec boot */
+        if (xen_hvm_domain())
+                xs_reset_watches();
+
         return 0;
 }