9 files changed, 208 insertions, 31 deletions

diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c61934fbf22a..64a619d47d34 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -47,8 +47,9 @@ extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern unsigned long set_phys_range_identity(unsigned long pfn_s,
                                              unsigned long pfn_e);
 
-extern int m2p_add_override(unsigned long mfn, struct page *page);
-extern int m2p_remove_override(struct page *page);
+extern int m2p_add_override(unsigned long mfn, struct page *page,
+                            bool clear_pte);
+extern int m2p_remove_override(struct page *page, bool clear_pte);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index aa8620989162..4fbda9a3f339 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -15,10 +15,26 @@ static inline int pci_xen_hvm_init(void)
 #endif
 #if defined(CONFIG_XEN_DOM0)
 void __init xen_setup_pirqs(void);
+int xen_find_device_domain_owner(struct pci_dev *dev);
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
+int xen_unregister_device_domain_owner(struct pci_dev *dev);
 #else
 static inline void __init xen_setup_pirqs(void)
 {
 }
+static inline int xen_find_device_domain_owner(struct pci_dev *dev)
+{
+        return -1;
+}
+static inline int xen_register_device_domain_owner(struct pci_dev *dev,
+                                                   uint16_t domain)
+{
+        return -1;
+}
+static inline int xen_unregister_device_domain_owner(struct pci_dev *dev)
+{
+        return -1;
+}
 #endif
 
 #if defined(CONFIG_PCI_MSI)
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index e37b407a0ee8..8214724ce54d 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -108,7 +108,8 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
                 }
                 irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0,
                                                (type == PCI_CAP_ID_MSIX) ?
-                                               "msi-x" : "msi");
+                                               "msi-x" : "msi",
+                                               DOMID_SELF);
                 if (irq < 0)
                         goto error;
                 dev_dbg(&dev->dev,
@@ -148,7 +149,8 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
                 irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0,
                                                (type == PCI_CAP_ID_MSIX) ?
                                                "pcifront-msi-x" :
-                                               "pcifront-msi");
+                                               "pcifront-msi",
+                                                DOMID_SELF);
                 if (irq < 0)
                         goto free;
                 i++;
@@ -190,9 +192,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 
         list_for_each_entry(msidesc, &dev->msi_list, list) {
                 struct physdev_map_pirq map_irq;
+                domid_t domid;
+
+                domid = ret = xen_find_device_domain_owner(dev);
+                /* N.B. Casting int's -ENODEV to uint16_t results in 0xFFED,
+                 * hence check ret value for < 0. */
+                if (ret < 0)
+                        domid = DOMID_SELF;
 
                 memset(&map_irq, 0, sizeof(map_irq));
-                map_irq.domid = DOMID_SELF;
+                map_irq.domid = domid;
                 map_irq.type = MAP_PIRQ_TYPE_MSI;
                 map_irq.index = -1;
                 map_irq.pirq = -1;
@@ -215,14 +224,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 
                 ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
                 if (ret) {
-                        dev_warn(&dev->dev, "xen map irq failed %d\n", ret);
+                        dev_warn(&dev->dev, "xen map irq failed %d for %d domain\n",
+                                 ret, domid);
                         goto out;
                 }
 
                 ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
                                                map_irq.pirq, map_irq.index,
                                                (type == PCI_CAP_ID_MSIX) ?
-                                               "msi-x" : "msi");
+                                               "msi-x" : "msi",
+                                                domid);
                 if (ret < 0)
                         goto out;
         }
@@ -461,3 +472,78 @@ void __init xen_setup_pirqs(void)
         }
 }
 #endif
+
+#ifdef CONFIG_XEN_DOM0
+struct xen_device_domain_owner {
+        domid_t domain;
+        struct pci_dev *dev;
+        struct list_head list;
+};
+
+static DEFINE_SPINLOCK(dev_domain_list_spinlock);
+static struct list_head dev_domain_list = LIST_HEAD_INIT(dev_domain_list);
+
+static struct xen_device_domain_owner *find_device(struct pci_dev *dev)
+{
+        struct xen_device_domain_owner *owner;
+
+        list_for_each_entry(owner, &dev_domain_list, list) {
+                if (owner->dev == dev)
+                        return owner;
+        }
+        return NULL;
+}
+
+int xen_find_device_domain_owner(struct pci_dev *dev)
+{
+        struct xen_device_domain_owner *owner;
+        int domain = -ENODEV;
+
+        spin_lock(&dev_domain_list_spinlock);
+        owner = find_device(dev);
+        if (owner)
+                domain = owner->domain;
+        spin_unlock(&dev_domain_list_spinlock);
+        return domain;
+}
+EXPORT_SYMBOL_GPL(xen_find_device_domain_owner);
+
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain)
+{
+        struct xen_device_domain_owner *owner;
+
+        owner = kzalloc(sizeof(struct xen_device_domain_owner), GFP_KERNEL);
+        if (!owner)
+                return -ENODEV;
+
+        spin_lock(&dev_domain_list_spinlock);
+        if (find_device(dev)) {
+                spin_unlock(&dev_domain_list_spinlock);
+                kfree(owner);
+                return -EEXIST;
+        }
+        owner->domain = domain;
+        owner->dev = dev;
+        list_add_tail(&owner->list, &dev_domain_list);
+        spin_unlock(&dev_domain_list_spinlock);
+        return 0;
+}
+EXPORT_SYMBOL_GPL(xen_register_device_domain_owner);
+
+int xen_unregister_device_domain_owner(struct pci_dev *dev)
+{
+        struct xen_device_domain_owner *owner;
+
+        spin_lock(&dev_domain_list_spinlock);
+        owner = find_device(dev);
+        if (!owner) {
+                spin_unlock(&dev_domain_list_spinlock);
+                return -ENODEV;
+        }
+        list_del(&owner->list);
+        spin_unlock(&dev_domain_list_spinlock);
+        kfree(owner);
+        return 0;
+}
+EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner);
+#endif
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 141eb0de8b06..c851397e657c 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -650,7 +650,7 @@ static unsigned long mfn_hash(unsigned long mfn)
 }
 
 /* Add an MFN override for a particular page */
-int m2p_add_override(unsigned long mfn, struct page *page)
+int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
 {
         unsigned long flags;
         unsigned long pfn;
@@ -662,7 +662,6 @@ int m2p_add_override(unsigned long mfn, struct page *page)
         if (!PageHighMem(page)) {
                 address = (unsigned long)__va(pfn << PAGE_SHIFT);
                 ptep = lookup_address(address, &level);
-
                 if (WARN(ptep == NULL || level != PG_LEVEL_4K,
                                         "m2p_add_override: pfn %lx not mapped", pfn))
                         return -EINVAL;
@@ -674,18 +673,17 @@ int m2p_add_override(unsigned long mfn, struct page *page)
         if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
                 return -ENOMEM;
 
-        if (!PageHighMem(page))
+        if (clear_pte && !PageHighMem(page))
                 /* Just zap old mapping for now */
                 pte_clear(&init_mm, address, ptep);
-
         spin_lock_irqsave(&m2p_override_lock, flags);
         list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
         spin_unlock_irqrestore(&m2p_override_lock, flags);
 
         return 0;
 }
-
-int m2p_remove_override(struct page *page)
+EXPORT_SYMBOL_GPL(m2p_add_override);
+int m2p_remove_override(struct page *page, bool clear_pte)
 {
         unsigned long flags;
         unsigned long mfn;
@@ -713,7 +711,7 @@ int m2p_remove_override(struct page *page)
         spin_unlock_irqrestore(&m2p_override_lock, flags);
         set_phys_to_machine(pfn, page->index);
 
-        if (!PageHighMem(page))
+        if (clear_pte && !PageHighMem(page))
                 set_pte_at(&init_mm, address, ptep,
                                 pfn_pte(pfn, PAGE_KERNEL));
                 /* No tlb flush necessary because the caller already
@@ -721,6 +719,7 @@ int m2p_remove_override(struct page *page)
 
         return 0;
 }
+EXPORT_SYMBOL_GPL(m2p_remove_override);
 
 struct page *m2p_find_override(unsigned long mfn)
 {
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 33167b43ac7e..35e02a10110b 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -101,6 +101,7 @@ struct irq_info
                         unsigned short gsi;
                         unsigned char vector;
                         unsigned char flags;
+                        uint16_t domid;
                 } pirq;
         } u;
 };
@@ -184,6 +185,7 @@ static void xen_irq_info_pirq_init(unsigned irq,
                                    unsigned short pirq,
                                    unsigned short gsi,
                                    unsigned short vector,
+                                   uint16_t domid,
                                    unsigned char flags)
 {
         struct irq_info *info = info_for_irq(irq);
@@ -193,6 +195,7 @@ static void xen_irq_info_pirq_init(unsigned irq,
         info->u.pirq.pirq = pirq;
         info->u.pirq.gsi = gsi;
         info->u.pirq.vector = vector;
+        info->u.pirq.domid = domid;
         info->u.pirq.flags = flags;
 }
 
@@ -655,7 +658,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
                 goto out;
         }
 
-        xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector,
+        xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF,
                                shareable ? PIRQ_SHAREABLE : 0);
 
 out:
@@ -680,7 +683,8 @@ int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
 }
 
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-                             int pirq, int vector, const char *name)
+                             int pirq, int vector, const char *name,
+                             domid_t domid)
 {
         int irq, ret;
 
@@ -693,7 +697,7 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
         irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq,
                                       name);
 
-        xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, 0);
+        xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0);
         ret = irq_set_msi_desc(irq, msidesc);
         if (ret < 0)
                 goto error_irq;
@@ -722,9 +726,16 @@ int xen_destroy_irq(int irq)
 
         if (xen_initial_domain()) {
                 unmap_irq.pirq = info->u.pirq.pirq;
-                unmap_irq.domid = DOMID_SELF;
+                unmap_irq.domid = info->u.pirq.domid;
                 rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
-                if (rc) {
+                /* If another domain quits without making the pci_disable_msix
+                 * call, the Xen hypervisor takes care of freeing the PIRQs
+                 * (free_domain_pirqs).
+                 */
+                if ((rc == -ESRCH && info->u.pirq.domid != DOMID_SELF))
+                        printk(KERN_INFO "domain %d does not have %d anymore\n",
+                                info->u.pirq.domid, info->u.pirq.pirq);
+                else if (rc) {
                         printk(KERN_WARNING "unmap irq failed %d\n", rc);
                         goto out;
                 }
@@ -759,6 +770,12 @@ out:
         return irq;
 }
 
+
+int xen_pirq_from_irq(unsigned irq)
+{
+        return pirq_from_irq(irq);
+}
+EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
 int bind_evtchn_to_irq(unsigned int evtchn)
 {
         int irq;
@@ -1502,6 +1519,18 @@ void xen_poll_irq(int irq)
         xen_poll_irq_timeout(irq, 0 /* no timeout */);
 }
 
+/* Check whether the IRQ line is shared with other guests. */
+int xen_test_irq_shared(int irq)
+{
+        struct irq_info *info = info_for_irq(irq);
+        struct physdev_irq_status_query irq_status = { .irq = info->u.pirq.pirq };
+
+        if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
+                return 0;
+        return !(irq_status.flags & XENIRQSTAT_shared);
+}
+EXPORT_SYMBOL_GPL(xen_test_irq_shared);
+
 void xen_irq_resume(void)
 {
         unsigned int cpu, evtchn;
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
index a7ffdfe19fc9..f6832f46aea4 100644
--- a/drivers/xen/gntalloc.c
+++ b/drivers/xen/gntalloc.c
@@ -427,6 +427,17 @@ static long gntalloc_ioctl(struct file *filp, unsigned int cmd,
         return 0;
 }
 
+static void gntalloc_vma_open(struct vm_area_struct *vma)
+{
+        struct gntalloc_gref *gref = vma->vm_private_data;
+        if (!gref)
+                return;
+
+        spin_lock(&gref_lock);
+        gref->users++;
+        spin_unlock(&gref_lock);
+}
+
 static void gntalloc_vma_close(struct vm_area_struct *vma)
 {
         struct gntalloc_gref *gref = vma->vm_private_data;
@@ -441,6 +452,7 @@ static void gntalloc_vma_close(struct vm_area_struct *vma)
 }
 
 static struct vm_operations_struct gntalloc_vmops = {
+        .open = gntalloc_vma_open,
         .close = gntalloc_vma_close,
 };
 
@@ -471,8 +483,6 @@ static int gntalloc_mmap(struct file *filp, struct vm_area_struct *vma)
         vma->vm_private_data = gref;
 
         vma->vm_flags |= VM_RESERVED;
-        vma->vm_flags |= VM_DONTCOPY;
-        vma->vm_flags |= VM_PFNMAP | VM_PFN_AT_MMAP;
 
         vma->vm_ops = &gntalloc_vmops;
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index b0f9e8fb0052..f914b26cf0c2 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -330,17 +330,26 @@ static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
 
 /* ------------------------------------------------------------------ */
 
+static void gntdev_vma_open(struct vm_area_struct *vma)
+{
+        struct grant_map *map = vma->vm_private_data;
+
+        pr_debug("gntdev_vma_open %p\n", vma);
+        atomic_inc(&map->users);
+}
+
 static void gntdev_vma_close(struct vm_area_struct *vma)
 {
         struct grant_map *map = vma->vm_private_data;
 
-        pr_debug("close %p\n", vma);
+        pr_debug("gntdev_vma_close %p\n", vma);
         map->vma = NULL;
         vma->vm_private_data = NULL;
         gntdev_put_map(map);
 }
 
 static struct vm_operations_struct gntdev_vmops = {
+        .open = gntdev_vma_open,
         .close = gntdev_vma_close,
 };
 
@@ -652,7 +661,10 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 
         vma->vm_ops = &gntdev_vmops;
 
-        vma->vm_flags |= VM_RESERVED|VM_DONTCOPY|VM_DONTEXPAND|VM_PFNMAP;
+        vma->vm_flags |= VM_RESERVED|VM_DONTEXPAND;
+
+        if (use_ptemod)
+                vma->vm_flags |= VM_DONTCOPY|VM_PFNMAP;
 
         vma->vm_private_data = map;
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 3745a318defc..fd725cde6ad1 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -466,13 +466,30 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
                 if (map_ops[i].status)
                         continue;
 
-                /* m2p override only supported for GNTMAP_contains_pte mappings */
-                if (!(map_ops[i].flags & GNTMAP_contains_pte))
-                        continue;
-                pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
+                if (map_ops[i].flags & GNTMAP_contains_pte) {
+                        pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
                                 (map_ops[i].host_addr & ~PAGE_MASK));
-                mfn = pte_mfn(*pte);
-                ret = m2p_add_override(mfn, pages[i]);
+                        mfn = pte_mfn(*pte);
+                } else {
+                        /* If you really wanted to do this:
+                         * mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
+                         *
+                         * The reason we do not implement it is b/c on the
+                         * unmap path (gnttab_unmap_refs) we have no means of
+                         * checking whether the page is !GNTMAP_contains_pte.
+                         *
+                         * That is without some extra data-structure to carry
+                         * the struct page, bool clear_pte, and list_head next
+                         * tuples and deal with allocation/delallocation, etc.
+                         *
+                         * The users of this API set the GNTMAP_contains_pte
+                         * flag so lets just return not supported until it
+                         * becomes neccessary to implement.
+                         */
+                        return -EOPNOTSUPP;
+                }
+                ret = m2p_add_override(mfn, pages[i],
+                                       map_ops[i].flags & GNTMAP_contains_pte);
                 if (ret)
                         return ret;
         }
@@ -494,7 +511,7 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
                 return ret;
 
         for (i = 0; i < count; i++) {
-                ret = m2p_remove_override(pages[i]);
+                ret = m2p_remove_override(pages[i], true /* clear the PTE */);
                 if (ret)
                         return ret;
         }
diff --git a/include/xen/events.h b/include/xen/events.h
index f1b87ad48ac7..9af21e19545a 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -85,7 +85,8 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
 /* Bind an PSI pirq to an irq. */
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-                             int pirq, int vector, const char *name);
+                             int pirq, int vector, const char *name,
+                             domid_t domid);
 #endif
 
 /* De-allocates the above mentioned physical interrupt. */
@@ -94,4 +95,10 @@ int xen_destroy_irq(int irq);
 /* Return irq from pirq */
 int xen_irq_from_pirq(unsigned pirq);
 
+/* Return the pirq allocated to the irq. */
+int xen_pirq_from_irq(unsigned irq);
+
+/* Determine whether to ignore this IRQ if it is passed to a guest. */
+int xen_test_irq_shared(int irq);
+
 #endif  /* _XEN_EVENTS_H */