Merge remote-tracking branch 'xen-two/linux-next'

5 files changed, 143 insertions, 17 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..393981feb12f 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 +472,76 @@ void __init xen_setup_pirqs(void)
 	}
 }
 #endif
+
+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);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 141eb0de8b06..58efeb9d5440 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -522,11 +522,20 @@ static bool __init __early_alloc_p2m(unsigned long pfn)
 	/* Boundary cross-over for the edges: */
 	if (idx) {
 		unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
+		unsigned long *mid_mfn_p;
 
 		p2m_init(p2m);
 
 		p2m_top[topidx][mididx] = p2m;
 
+		/* For save/restore we need to MFN of the P2M saved */
+		
+		mid_mfn_p = p2m_top_mfn_p[topidx];
+		WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
+			"P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
+			topidx, mididx);
+		mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
 	}
 	return idx != 0;
 }
@@ -549,12 +558,29 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 		pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
 	{
 		unsigned topidx = p2m_top_index(pfn);
-		if (p2m_top[topidx] == p2m_mid_missing) {
-			unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+		unsigned long *mid_mfn_p;
+		unsigned long **mid;
+
+		mid = p2m_top[topidx];
+		mid_mfn_p = p2m_top_mfn_p[topidx];
+		if (mid == p2m_mid_missing) {
+			mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
 
 			p2m_mid_init(mid);
 
 			p2m_top[topidx] = mid;
+
+			BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
+		}
+		/* And the save/restore P2M tables.. */
+		if (mid_mfn_p == p2m_mid_missing_mfn) {
+			mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+			p2m_mid_mfn_init(mid_mfn_p);
+
+			p2m_top_mfn_p[topidx] = mid_mfn_p;
+			p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
+			/* Note: we don't set mid_mfn_p[midix] here,
+		 	 * look in __early_alloc_p2m */
 		}
 	}
 
@@ -650,7 +676,7 @@ 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 +688,6 @@ 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 +699,17 @@ 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 +737,7 @@ 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 +745,7 @@ 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/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 90bac0aac3a5..fba4a6cc3a2d 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -166,7 +166,7 @@ static unsigned long __init xen_set_identity(const struct e820entry *list,
 		if (last > end)
 			continue;
 
-		if (entry->type == E820_RAM) {
+		if ((entry->type == E820_RAM) || (entry->type == E820_UNUSABLE)) {
 			if (start > start_pci)
 				identity += set_phys_range_identity(
 						PFN_UP(start_pci), PFN_DOWN(start));