Merge remote-tracking branch 'stefano/swiotlb-xen-9.1' into stable/for-linus-3.13

* stefano/swiotlb-xen-9.1:
  swiotlb-xen: fix error code returned by xen_swiotlb_map_sg_attrs
  swiotlb-xen: static inline xen_phys_to_bus, xen_bus_to_phys, xen_virt_to_bus and range_straddles_page_boundary
  grant-table: call set_phys_to_machine after mapping grant refs
  arm,arm64: do not always merge biovec if we are running on Xen
  swiotlb: print a warning when the swiotlb is full
  swiotlb-xen: use xen_dma_map/unmap_page, xen_dma_sync_single_for_cpu/device
  xen: introduce xen_dma_map/unmap_page and xen_dma_sync_single_for_cpu/device
  swiotlb-xen: use xen_alloc/free_coherent_pages
  xen: introduce xen_alloc/free_coherent_pages
  arm64/xen: get_dma_ops: return xen_dma_ops if we are running as xen_initial_domain
  arm/xen: get_dma_ops: return xen_dma_ops if we are running as xen_initial_domain
  swiotlb-xen: introduce xen_swiotlb_set_dma_mask
  xen/arm,arm64: enable SWIOTLB_XEN
  xen: make xen_create_contiguous_region return the dma address
  xen/x86: allow __set_phys_to_machine for autotranslate guests
  arm/xen,arm64/xen: introduce p2m
  arm64: define DMA_ERROR_CODE
  arm: make SWIOTLB available

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Conflicts:
	arch/arm/include/asm/dma-mapping.h
	drivers/xen/swiotlb-xen.c

[Conflicts arose b/c "arm: make SWIOTLB available" v8 was in Stefano's
branch, while I had v9 + Ack from Russel. I also fixed up white-space
issues]

arch/arm/Kconfig

@@ -1888,6 +1888,7 @@ config XEN
 	depends on CPU_V7 && !CPU_V6
 	depends on !GENERIC_ATOMIC64
 	select ARM_PSCI
+	select SWIOTLB_XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
 

arch/arm/include/asm/dma-mapping.h

@@ -11,17 +11,28 @@
 #include <asm-generic/dma-coherent.h>
 #include <asm/memory.h>
 
+#include <xen/xen.h>
+#include <asm/xen/hypervisor.h>
+
 #define DMA_ERROR_CODE	(~0)
 extern struct dma_map_ops arm_dma_ops;
 extern struct dma_map_ops arm_coherent_dma_ops;
 
-static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
 	if (dev && dev->archdata.dma_ops)
 		return dev->archdata.dma_ops;
 	return &arm_dma_ops;
 }
 
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (xen_initial_domain())
+		return xen_dma_ops;
+	else
+		return __generic_dma_ops(dev);
+}
+
 static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 {
 	BUG_ON(!dev);

arch/arm/include/asm/io.h

@@ -24,9 +24,11 @@
 #ifdef __KERNEL__
 
 #include <linux/types.h>
+#include <linux/blk_types.h>
 #include <asm/byteorder.h>
 #include <asm/memory.h>
 #include <asm-generic/pci_iomap.h>
+#include <xen/xen.h>
 
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
@@ -372,6 +374,12 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
 #define BIOVEC_MERGEABLE(vec1, vec2)	\
 	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
 
+extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+				      const struct bio_vec *vec2);
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
+	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
+	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
+
 #ifdef CONFIG_MMU
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
 extern int valid_phys_addr_range(phys_addr_t addr, size_t size);

arch/arm/include/asm/xen/hypervisor.h

@@ -16,4 +16,6 @@ static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return PARAVIRT_LAZY_NONE;
 }
 
+extern struct dma_map_ops *xen_dma_ops;
+
 #endif /* _ASM_ARM_XEN_HYPERVISOR_H */

arch/arm/include/asm/xen/page-coherent.h

@@ -0,0 +1,50 @@
+#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
+#define _ASM_ARM_XEN_PAGE_COHERENT_H
+
+#include <asm/page.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-mapping.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags,
+		struct dma_attrs *attrs)
+{
+	return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle,
+		struct dma_attrs *attrs)
+{
+	__generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir,
+	     struct dma_attrs *attrs)
+{
+	__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	if (__generic_dma_ops(hwdev)->unmap_page)
+		__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (__generic_dma_ops(hwdev)->sync_single_for_cpu)
+		__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (__generic_dma_ops(hwdev)->sync_single_for_device)
+		__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+}
+#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */

arch/arm/include/asm/xen/page.h

@@ -6,12 +6,12 @@
 
 #include <linux/pfn.h>
 #include <linux/types.h>
+#include <linux/dma-mapping.h>
 
+#include <xen/xen.h>
 #include <xen/interface/grant_table.h>
 
-#define pfn_to_mfn(pfn)			(pfn)
 #define phys_to_machine_mapping_valid(pfn) (1)
-#define mfn_to_pfn(mfn)			(mfn)
 #define mfn_to_virt(m)			(__va(mfn_to_pfn(m) << PAGE_SHIFT))
 
 #define pte_mfn	    pte_pfn
@@ -32,6 +32,44 @@ typedef struct xpaddr {
 
 #define INVALID_P2M_ENTRY      (~0UL)
 
+unsigned long __pfn_to_mfn(unsigned long pfn);
+unsigned long __mfn_to_pfn(unsigned long mfn);
+extern struct rb_root phys_to_mach;
+
+static inline unsigned long pfn_to_mfn(unsigned long pfn)
+{
+	unsigned long mfn;
+
+	if (phys_to_mach.rb_node != NULL) {
+		mfn = __pfn_to_mfn(pfn);
+		if (mfn != INVALID_P2M_ENTRY)
+			return mfn;
+	}
+
+	if (xen_initial_domain())
+		return pfn;
+	else
+		return INVALID_P2M_ENTRY;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (phys_to_mach.rb_node != NULL) {
+		pfn = __mfn_to_pfn(mfn);
+		if (pfn != INVALID_P2M_ENTRY)
+			return pfn;
+	}
+
+	if (xen_initial_domain())
+		return mfn;
+	else
+		return INVALID_P2M_ENTRY;
+}
+
+#define mfn_to_local_pfn(mfn) mfn_to_pfn(mfn)
+
 static inline xmaddr_t phys_to_machine(xpaddr_t phys)
 {
 	unsigned offset = phys.paddr & ~PAGE_MASK;
@@ -76,11 +114,9 @@ static inline int m2p_remove_override(struct page *page, bool clear_pte)
 	return 0;
 }
 
-static inline bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
-	BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
-	return true;
-}
+bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn,
+		unsigned long nr_pages);
 
 static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {

arch/arm/xen/Makefile

@@ -1 +1 @@
-obj-y		:= enlighten.o hypercall.o grant-table.o
+obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o

arch/arm/xen/mm.c

@@ -0,0 +1,65 @@
+#include <linux/bootmem.h>
+#include <linux/gfp.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+#include <linux/swiotlb.h>
+
+#include <xen/xen.h>
+#include <xen/interface/memory.h>
+#include <xen/swiotlb-xen.h>
+
+#include <asm/cacheflush.h>
+#include <asm/xen/page.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/interface.h>
+
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
+				 unsigned int address_bits,
+				 dma_addr_t *dma_handle)
+{
+	if (!xen_initial_domain())
+		return -EINVAL;
+
+	/* we assume that dom0 is mapped 1:1 for now */
+	*dma_handle = pstart;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
+
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
+{
+	return;
+}
+EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
+
+struct dma_map_ops *xen_dma_ops;
+EXPORT_SYMBOL_GPL(xen_dma_ops);
+
+static struct dma_map_ops xen_swiotlb_dma_ops = {
+	.mapping_error = xen_swiotlb_dma_mapping_error,
+	.alloc = xen_swiotlb_alloc_coherent,
+	.free = xen_swiotlb_free_coherent,
+	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
+	.map_sg = xen_swiotlb_map_sg_attrs,
+	.unmap_sg = xen_swiotlb_unmap_sg_attrs,
+	.map_page = xen_swiotlb_map_page,
+	.unmap_page = xen_swiotlb_unmap_page,
+	.dma_supported = xen_swiotlb_dma_supported,
+	.set_dma_mask = xen_swiotlb_set_dma_mask,
+};
+
+int __init xen_mm_init(void)
+{
+	if (!xen_initial_domain())
+		return 0;
+	xen_swiotlb_init(1, false);
+	xen_dma_ops = &xen_swiotlb_dma_ops;
+	return 0;
+}
+arch_initcall(xen_mm_init);

arch/arm/xen/p2m.c

@@ -0,0 +1,208 @@
+#include <linux/bootmem.h>
+#include <linux/gfp.h>
+#include <linux/export.h>
+#include <linux/rwlock.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+#include <linux/swiotlb.h>
+
+#include <xen/xen.h>
+#include <xen/interface/memory.h>
+#include <xen/swiotlb-xen.h>
+
+#include <asm/cacheflush.h>
+#include <asm/xen/page.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/interface.h>
+
+struct xen_p2m_entry {
+	unsigned long pfn;
+	unsigned long mfn;
+	unsigned long nr_pages;
+	struct rb_node rbnode_mach;
+	struct rb_node rbnode_phys;
+};
+
+rwlock_t p2m_lock;
+struct rb_root phys_to_mach = RB_ROOT;
+static struct rb_root mach_to_phys = RB_ROOT;
+
+static int xen_add_phys_to_mach_entry(struct xen_p2m_entry *new)
+{
+	struct rb_node **link = &phys_to_mach.rb_node;
+	struct rb_node *parent = NULL;
+	struct xen_p2m_entry *entry;
+	int rc = 0;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct xen_p2m_entry, rbnode_phys);
+
+		if (new->mfn == entry->mfn)
+			goto err_out;
+		if (new->pfn == entry->pfn)
+			goto err_out;
+
+		if (new->pfn < entry->pfn)
+			link = &(*link)->rb_left;
+		else
+			link = &(*link)->rb_right;
+	}
+	rb_link_node(&new->rbnode_phys, parent, link);
+	rb_insert_color(&new->rbnode_phys, &phys_to_mach);
+	goto out;
+
+err_out:
+	rc = -EINVAL;
+	pr_warn("%s: cannot add pfn=%pa -> mfn=%pa: pfn=%pa -> mfn=%pa already exists\n",
+			__func__, &new->pfn, &new->mfn, &entry->pfn, &entry->mfn);
+out:
+	return rc;
+}
+
+unsigned long __pfn_to_mfn(unsigned long pfn)
+{
+	struct rb_node *n = phys_to_mach.rb_node;
+	struct xen_p2m_entry *entry;
+	unsigned long irqflags;
+
+	read_lock_irqsave(&p2m_lock, irqflags);
+	while (n) {
+		entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
+		if (entry->pfn <= pfn &&
+				entry->pfn + entry->nr_pages > pfn) {
+			read_unlock_irqrestore(&p2m_lock, irqflags);
+			return entry->mfn + (pfn - entry->pfn);
+		}
+		if (pfn < entry->pfn)
+			n = n->rb_left;
+		else
+			n = n->rb_right;
+	}
+	read_unlock_irqrestore(&p2m_lock, irqflags);
+
+	return INVALID_P2M_ENTRY;
+}
+EXPORT_SYMBOL_GPL(__pfn_to_mfn);
+
+static int xen_add_mach_to_phys_entry(struct xen_p2m_entry *new)
+{
+	struct rb_node **link = &mach_to_phys.rb_node;
+	struct rb_node *parent = NULL;
+	struct xen_p2m_entry *entry;
+	int rc = 0;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct xen_p2m_entry, rbnode_mach);
+
+		if (new->mfn == entry->mfn)
+			goto err_out;
+		if (new->pfn == entry->pfn)
+			goto err_out;
+
+		if (new->mfn < entry->mfn)
+			link = &(*link)->rb_left;
+		else
+			link = &(*link)->rb_right;
+	}
+	rb_link_node(&new->rbnode_mach, parent, link);
+	rb_insert_color(&new->rbnode_mach, &mach_to_phys);
+	goto out;
+
+err_out:
+	rc = -EINVAL;
+	pr_warn("%s: cannot add pfn=%pa -> mfn=%pa: pfn=%pa -> mfn=%pa already exists\n",
+			__func__, &new->pfn, &new->mfn, &entry->pfn, &entry->mfn);
+out:
+	return rc;
+}
+
+unsigned long __mfn_to_pfn(unsigned long mfn)
+{
+	struct rb_node *n = mach_to_phys.rb_node;
+	struct xen_p2m_entry *entry;
+	unsigned long irqflags;
+
+	read_lock_irqsave(&p2m_lock, irqflags);
+	while (n) {
+		entry = rb_entry(n, struct xen_p2m_entry, rbnode_mach);
+		if (entry->mfn <= mfn &&
+				entry->mfn + entry->nr_pages > mfn) {
+			read_unlock_irqrestore(&p2m_lock, irqflags);
+			return entry->pfn + (mfn - entry->mfn);
+		}
+		if (mfn < entry->mfn)
+			n = n->rb_left;
+		else
+			n = n->rb_right;
+	}
+	read_unlock_irqrestore(&p2m_lock, irqflags);
+
+	return INVALID_P2M_ENTRY;
+}
+EXPORT_SYMBOL_GPL(__mfn_to_pfn);
+
+bool __set_phys_to_machine_multi(unsigned long pfn,
+		unsigned long mfn, unsigned long nr_pages)
+{
+	int rc;
+	unsigned long irqflags;
+	struct xen_p2m_entry *p2m_entry;
+	struct rb_node *n = phys_to_mach.rb_node;
+
+	if (mfn == INVALID_P2M_ENTRY) {
+		write_lock_irqsave(&p2m_lock, irqflags);
+		while (n) {
+			p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
+			if (p2m_entry->pfn <= pfn &&
+					p2m_entry->pfn + p2m_entry->nr_pages > pfn) {
+				rb_erase(&p2m_entry->rbnode_mach, &mach_to_phys);
+				rb_erase(&p2m_entry->rbnode_phys, &phys_to_mach);
+				write_unlock_irqrestore(&p2m_lock, irqflags);
+				kfree(p2m_entry);
+				return true;
+			}
+			if (pfn < p2m_entry->pfn)
+				n = n->rb_left;
+			else
+				n = n->rb_right;
+		}
+		write_unlock_irqrestore(&p2m_lock, irqflags);
+		return true;
+	}
+
+	p2m_entry = kzalloc(sizeof(struct xen_p2m_entry), GFP_NOWAIT);
+	if (!p2m_entry) {
+		pr_warn("cannot allocate xen_p2m_entry\n");
+		return false;
+	}
+	p2m_entry->pfn = pfn;
+	p2m_entry->nr_pages = nr_pages;
+	p2m_entry->mfn = mfn;
+
+	write_lock_irqsave(&p2m_lock, irqflags);
+	if ((rc = xen_add_phys_to_mach_entry(p2m_entry) < 0) ||
+		(rc = xen_add_mach_to_phys_entry(p2m_entry) < 0)) {
+		write_unlock_irqrestore(&p2m_lock, irqflags);
+		return false;
+	}
+	write_unlock_irqrestore(&p2m_lock, irqflags);
+	return true;
+}
+EXPORT_SYMBOL_GPL(__set_phys_to_machine_multi);
+
+bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+	return __set_phys_to_machine_multi(pfn, mfn, 1);
+}
+EXPORT_SYMBOL_GPL(__set_phys_to_machine);
+
+int p2m_init(void)
+{
+	rwlock_init(&p2m_lock);
+	return 0;
+}
+arch_initcall(p2m_init);

arch/arm64/Kconfig

@@ -211,6 +211,7 @@ config XEN_DOM0
 config XEN
 	bool "Xen guest support on ARM64 (EXPERIMENTAL)"
 	depends on ARM64 && OF
+	select SWIOTLB_XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
 

arch/arm64/include/asm/dma-mapping.h

@@ -23,11 +23,15 @@
 
 #include <asm-generic/dma-coherent.h>
 
+#include <xen/xen.h>
+#include <asm/xen/hypervisor.h>
+
 #define ARCH_HAS_DMA_GET_REQUIRED_MASK
 
+#define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
 
-static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
 	if (unlikely(!dev) || !dev->archdata.dma_ops)
 		return dma_ops;
@@ -35,6 +39,14 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 		return dev->archdata.dma_ops;
 }
 
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (xen_initial_domain())
+		return xen_dma_ops;
+	else
+		return __generic_dma_ops(dev);
+}
+
 #include <asm-generic/dma-mapping-common.h>
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)

arch/arm64/include/asm/io.h

@@ -22,11 +22,14 @@
 #ifdef __KERNEL__
 
 #include <linux/types.h>
+#include <linux/blk_types.h>
 
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 #include <asm/pgtable.h>
 
+#include <xen/xen.h>
+
 /*
  * Generic IO read/write.  These perform native-endian accesses.
  */
@@ -263,5 +266,11 @@ extern int devmem_is_allowed(unsigned long pfn);
  */
 #define xlate_dev_kmem_ptr(p)	p
 
+extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+				      const struct bio_vec *vec2);
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
+	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
+	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
+
 #endif	/* __KERNEL__ */
 #endif	/* __ASM_IO_H */

arch/arm64/include/asm/xen/page-coherent.h

@@ -0,0 +1,47 @@
+#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H
+#define _ASM_ARM64_XEN_PAGE_COHERENT_H
+
+#include <asm/page.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-mapping.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags,
+		struct dma_attrs *attrs)
+{
+	return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle,
+		struct dma_attrs *attrs)
+{
+	__generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir,
+	     struct dma_attrs *attrs)
+{
+	__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+}
+#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */

arch/arm64/xen/Makefile

@@ -1,2 +1,2 @@
-xen-arm-y	+= $(addprefix ../../arm/xen/, enlighten.o grant-table.o)
+xen-arm-y	+= $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o)
 obj-y		:= xen-arm.o hypercall.o

arch/ia64/include/asm/xen/page-coherent.h

@@ -0,0 +1,38 @@
+#ifndef _ASM_IA64_XEN_PAGE_COHERENT_H
+#define _ASM_IA64_XEN_PAGE_COHERENT_H
+
+#include <asm/page.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-mapping.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags,
+		struct dma_attrs *attrs)
+{
+	void *vstart = (void*)__get_free_pages(flags, get_order(size));
+	*dma_handle = virt_to_phys(vstart);
+	return vstart;
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle,
+		struct dma_attrs *attrs)
+{
+	free_pages((unsigned long) cpu_addr, get_order(size));
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir,
+	     struct dma_attrs *attrs) { }
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs) { }
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
+
+#endif /* _ASM_IA64_XEN_PAGE_COHERENT_H */

arch/x86/include/asm/xen/page-coherent.h

@@ -0,0 +1,38 @@
+#ifndef _ASM_X86_XEN_PAGE_COHERENT_H
+#define _ASM_X86_XEN_PAGE_COHERENT_H
+
+#include <asm/page.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-mapping.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags,
+		struct dma_attrs *attrs)
+{
+	void *vstart = (void*)__get_free_pages(flags, get_order(size));
+	*dma_handle = virt_to_phys(vstart);
+	return vstart;
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle,
+		struct dma_attrs *attrs)
+{
+	free_pages((unsigned long) cpu_addr, get_order(size));
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir,
+	     struct dma_attrs *attrs) { }
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs) { }
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
+
+#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */

arch/x86/xen/mmu.c

@@ -2328,12 +2328,14 @@ static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
 	return success;
 }
 
-int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
-				 unsigned int address_bits)
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
+				 unsigned int address_bits,
+				 dma_addr_t *dma_handle)
 {
 	unsigned long *in_frames = discontig_frames, out_frame;
 	unsigned long  flags;
 	int            success;
+	unsigned long vstart = (unsigned long)phys_to_virt(pstart);
 
 	/*
 	 * Currently an auto-translated guest will not perform I/O, nor will
@@ -2368,15 +2370,17 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
 
 	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
+	*dma_handle = virt_to_machine(vstart).maddr;
 	return success ? 0 : -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
 
-void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 {
 	unsigned long *out_frames = discontig_frames, in_frame;
 	unsigned long  flags;
 	int success;
+	unsigned long vstart;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return;
@@ -2384,6 +2388,7 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
 	if (unlikely(order > MAX_CONTIG_ORDER))
 		return;
 
+	vstart = (unsigned long)phys_to_virt(pstart);
 	memset((void *) vstart, 0, PAGE_SIZE << order);
 
 	spin_lock_irqsave(&xen_reservation_lock, flags);

arch/x86/xen/p2m.c

@@ -799,10 +799,10 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	unsigned topidx, mididx, idx;
 
-	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
-		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+	/* don't track P2M changes in autotranslate guests */
+	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
 		return true;
-	}
+
 	if (unlikely(pfn >= MAX_P2M_PFN)) {
 		BUG_ON(mfn != INVALID_P2M_ENTRY);
 		return true;

drivers/xen/Kconfig

@@ -140,7 +140,6 @@ config XEN_GRANT_DEV_ALLOC
 
 config SWIOTLB_XEN
 	def_bool y
-	depends on PCI && X86
 	select SWIOTLB
 
 config XEN_TMEM

drivers/xen/grant-table.c

@@ -49,6 +49,7 @@
 #include <xen/grant_table.h>
 #include <xen/interface/memory.h>
 #include <xen/hvc-console.h>
+#include <xen/swiotlb-xen.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -898,8 +899,16 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 			gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
 						&map_ops[i].status, __func__);
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
+	/* this is basically a nop on x86 */
+	if (xen_feature(XENFEAT_auto_translated_physmap)) {
+		for (i = 0; i < count; i++) {
+			if (map_ops[i].status)
+				continue;
+			set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT,
+					map_ops[i].dev_bus_addr >> PAGE_SHIFT);
+		}
 		return ret;
+	}
 
 	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
 		arch_enter_lazy_mmu_mode();
@@ -942,8 +951,14 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 	if (ret)
 		return ret;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
+	/* this is basically a nop on x86 */
+	if (xen_feature(XENFEAT_auto_translated_physmap)) {
+		for (i = 0; i < count; i++) {
+			set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT,
+					INVALID_P2M_ENTRY);
+		}
 		return ret;
+	}
 
 	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
 		arch_enter_lazy_mmu_mode();