Merge tag 'stable/for-linus-3.19-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen features and fixes from David Vrabel:

 - Fully support non-coherent devices on ARM by introducing the
   mechanisms to request the hypervisor to perform the required cache
   maintainance operations.

 - A number of pciback bug fixes and cleanups.  Notably a deadlock fix
   if a PCI device was manually uunbound and a fix for incorrectly
   restoring state after a function reset.

 - In x86 PVHVM guests, use the APIC for interrupts if this has been
   virtualized by the hardware.  This reduces the number of interrupt-
   related VM exits on such hardware.

* tag 'stable/for-linus-3.19-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (26 commits)
  Revert "swiotlb-xen: pass dev_addr to swiotlb_tbl_unmap_single"
  xen/pci: Use APIC directly when APIC virtualization hardware is available
  xen/pci: Defer initialization of MSI ops on HVM guests
  xen-pciback: drop SR-IOV VFs when PF driver unloads
  xen/pciback: Restore configuration space when detaching from a guest.
  PCI: Expose pci_load_saved_state for public consumption.
  xen/pciback: Remove tons of dereferences
  xen/pciback: Print out the domain owning the device.
  xen/pciback: Include the domain id if removing the device whilst still in use
  driver core: Provide an wrapper around the mutex to do lockdep warnings
  xen/pciback: Don't deadlock when unbinding.
  swiotlb-xen: pass dev_addr to swiotlb_tbl_unmap_single
  swiotlb-xen: call xen_dma_sync_single_for_device when appropriate
  swiotlb-xen: remove BUG_ON in xen_bus_to_phys
  swiotlb-xen: pass dev_addr to xen_dma_unmap_page and xen_dma_sync_single_for_cpu
  xen/arm: introduce GNTTABOP_cache_flush
  xen/arm/arm64: introduce xen_arch_need_swiotlb
  xen/arm/arm64: merge xen/mm32.c into xen/mm.c
  xen/arm: use hypercall to flush caches in map_page
  xen: add a dma_addr_t dev_addr argument to xen_dma_map_page
  ...

arch/arm/include/asm/device.h

@@ -17,6 +17,7 @@ struct dev_archdata {
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 	struct dma_iommu_mapping	*mapping;
 #endif
+	bool dma_coherent;
 };
 
 struct omap_device;

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

@@ -123,11 +123,18 @@ static inline unsigned long dma_max_pfn(struct device *dev)
 
 static inline int set_arch_dma_coherent_ops(struct device *dev)
 {
+	dev->archdata.dma_coherent = true;
 	set_dma_ops(dev, &arm_coherent_dma_ops);
 	return 0;
 }
 #define set_arch_dma_coherent_ops(dev)	set_arch_dma_coherent_ops(dev)
 
+/* do not use this function in a driver */
+static inline bool is_device_dma_coherent(struct device *dev)
+{
+	return dev->archdata.dma_coherent;
+}
+
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	unsigned int offset = paddr & ~PAGE_MASK;

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

@@ -5,6 +5,18 @@
 #include <linux/dma-attrs.h>
 #include <linux/dma-mapping.h>
 
+void __xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, struct dma_attrs *attrs);
+void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs);
+void __xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir);
+
+void __xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir);
+
 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)
@@ -20,20 +32,56 @@ static inline void xen_free_coherent_pages(struct device *hwdev, size_t 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)
+	     dma_addr_t dev_addr, 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);
+	bool local = PFN_DOWN(dev_addr) == page_to_pfn(page);
+	/* Dom0 is mapped 1:1, so if pfn == mfn the page is local otherwise
+	 * is a foreign page grant-mapped in dom0. If the page is local we
+	 * can safely call the native dma_ops function, otherwise we call
+	 * the xen specific function. */
+	if (local)
+		__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+	else
+		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
 }
 
-void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+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);
+		struct dma_attrs *attrs)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	/* Dom0 is mapped 1:1, so calling pfn_valid on a foreign mfn will
+	 * always return false. If the page is local we can safely call the
+	 * native dma_ops function, otherwise we call the xen specific
+	 * function. */
+	if (pfn_valid(pfn)) {
+		if (__generic_dma_ops(hwdev)->unmap_page)
+			__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+	} else
+		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
 
-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_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn)) {
+		if (__generic_dma_ops(hwdev)->sync_single_for_cpu)
+			__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+	} else
+		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
 
-void xen_dma_sync_single_for_device(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)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn)) {
+		if (__generic_dma_ops(hwdev)->sync_single_for_device)
+			__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+	} else
+		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
 
 #endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */

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

@@ -107,4 +107,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 #define xen_remap(cookie, size) ioremap_cache((cookie), (size))
 #define xen_unmap(cookie) iounmap((cookie))
 
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn);
+
 #endif /* _ASM_ARM_XEN_PAGE_H */

arch/arm/xen/Makefile

@@ -1 +1 @@
-obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o mm32.o
+obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o

arch/arm/xen/enlighten.c

@@ -261,11 +261,6 @@ static int __init xen_guest_init(void)
 
 	xen_setup_features();
 
-	if (!xen_feature(XENFEAT_grant_map_identity)) {
-		pr_warn("Please upgrade your Xen.\n"
-				"If your platform has any non-coherent DMA devices, they won't work properly.\n");
-	}
-
 	if (xen_feature(XENFEAT_dom0))
 		xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
 	else

arch/arm/xen/mm.c

@@ -1,6 +1,10 @@
+#include <linux/cpu.h>
+#include <linux/dma-mapping.h>
 #include <linux/bootmem.h>
 #include <linux/gfp.h>
+#include <linux/highmem.h>
 #include <linux/export.h>
+#include <linux/of_address.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
@@ -8,6 +12,7 @@
 #include <linux/swiotlb.h>
 
 #include <xen/xen.h>
+#include <xen/interface/grant_table.h>
 #include <xen/interface/memory.h>
 #include <xen/swiotlb-xen.h>
 
@@ -16,6 +21,114 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
+enum dma_cache_op {
+       DMA_UNMAP,
+       DMA_MAP,
+};
+static bool hypercall_cflush = false;
+
+/* functions called by SWIOTLB */
+
+static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
+	size_t size, enum dma_data_direction dir, enum dma_cache_op op)
+{
+	struct gnttab_cache_flush cflush;
+	unsigned long pfn;
+	size_t left = size;
+
+	pfn = (handle >> PAGE_SHIFT) + offset / PAGE_SIZE;
+	offset %= PAGE_SIZE;
+
+	do {
+		size_t len = left;
+	
+		/* buffers in highmem or foreign pages cannot cross page
+		 * boundaries */
+		if (len + offset > PAGE_SIZE)
+			len = PAGE_SIZE - offset;
+
+		cflush.op = 0;
+		cflush.a.dev_bus_addr = pfn << PAGE_SHIFT;
+		cflush.offset = offset;
+		cflush.length = len;
+
+		if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
+			cflush.op = GNTTAB_CACHE_INVAL;
+		if (op == DMA_MAP) {
+			if (dir == DMA_FROM_DEVICE)
+				cflush.op = GNTTAB_CACHE_INVAL;
+			else
+				cflush.op = GNTTAB_CACHE_CLEAN;
+		}
+		if (cflush.op)
+			HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
+
+		offset = 0;
+		pfn++;
+		left -= len;
+	} while (left);
+}
+
+static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
+{
+	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
+}
+
+static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
+{
+	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
+}
+
+void __xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	if (is_device_dma_coherent(hwdev))
+		return;
+	if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+		return;
+
+	__xen_dma_page_cpu_to_dev(hwdev, dev_addr, size, dir);
+}
+
+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 (is_device_dma_coherent(hwdev))
+		return;
+	if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+		return;
+
+	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
+}
+
+void __xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (is_device_dma_coherent(hwdev))
+		return;
+	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
+}
+
+void __xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (is_device_dma_coherent(hwdev))
+		return;
+	__xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
+}
+
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn)
+{
+	return (!hypercall_cflush && (pfn != mfn) && !is_device_dma_coherent(dev));
+}
+
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				 unsigned int address_bits,
 				 dma_addr_t *dma_handle)
@@ -56,10 +169,18 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
 
 int __init xen_mm_init(void)
 {
+	struct gnttab_cache_flush cflush;
 	if (!xen_initial_domain())
 		return 0;
 	xen_swiotlb_init(1, false);
 	xen_dma_ops = &xen_swiotlb_dma_ops;
+
+	cflush.op = 0;
+	cflush.a.dev_bus_addr = 0;
+	cflush.offset = 0;
+	cflush.length = 0;
+	if (HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1) != -ENOSYS)
+		hypercall_cflush = true;
 	return 0;
 }
 arch_initcall(xen_mm_init);

arch/arm/xen/mm32.c

@@ -1,202 +0,0 @@
-#include <linux/cpu.h>
-#include <linux/dma-mapping.h>
-#include <linux/gfp.h>
-#include <linux/highmem.h>
-
-#include <xen/features.h>
-
-static DEFINE_PER_CPU(unsigned long, xen_mm32_scratch_virt);
-static DEFINE_PER_CPU(pte_t *, xen_mm32_scratch_ptep);
-
-static int alloc_xen_mm32_scratch_page(int cpu)
-{
-	struct page *page;
-	unsigned long virt;
-	pmd_t *pmdp;
-	pte_t *ptep;
-
-	if (per_cpu(xen_mm32_scratch_ptep, cpu) != NULL)
-		return 0;
-
-	page = alloc_page(GFP_KERNEL);
-	if (page == NULL) {
-		pr_warn("Failed to allocate xen_mm32_scratch_page for cpu %d\n", cpu);
-		return -ENOMEM;
-	}
-
-	virt = (unsigned long)__va(page_to_phys(page));
-	pmdp = pmd_offset(pud_offset(pgd_offset_k(virt), virt), virt);
-	ptep = pte_offset_kernel(pmdp, virt);
-
-	per_cpu(xen_mm32_scratch_virt, cpu) = virt;
-	per_cpu(xen_mm32_scratch_ptep, cpu) = ptep;
-
-	return 0;
-}
-
-static int xen_mm32_cpu_notify(struct notifier_block *self,
-				    unsigned long action, void *hcpu)
-{
-	int cpu = (long)hcpu;
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (alloc_xen_mm32_scratch_page(cpu))
-			return NOTIFY_BAD;
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block xen_mm32_cpu_notifier = {
-	.notifier_call	= xen_mm32_cpu_notify,
-};
-
-static void* xen_mm32_remap_page(dma_addr_t handle)
-{
-	unsigned long virt = get_cpu_var(xen_mm32_scratch_virt);
-	pte_t *ptep = __get_cpu_var(xen_mm32_scratch_ptep);
-
-	*ptep = pfn_pte(handle >> PAGE_SHIFT, PAGE_KERNEL);
-	local_flush_tlb_kernel_page(virt);
-
-	return (void*)virt;
-}
-
-static void xen_mm32_unmap(void *vaddr)
-{
-	put_cpu_var(xen_mm32_scratch_virt);
-}
-
-
-/* functions called by SWIOTLB */
-
-static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
-	size_t size, enum dma_data_direction dir,
-	void (*op)(const void *, size_t, int))
-{
-	unsigned long pfn;
-	size_t left = size;
-
-	pfn = (handle >> PAGE_SHIFT) + offset / PAGE_SIZE;
-	offset %= PAGE_SIZE;
-
-	do {
-		size_t len = left;
-		void *vaddr;
-	
-		if (!pfn_valid(pfn))
-		{
-			/* Cannot map the page, we don't know its physical address.
-			 * Return and hope for the best */
-			if (!xen_feature(XENFEAT_grant_map_identity))
-				return;
-			vaddr = xen_mm32_remap_page(handle) + offset;
-			op(vaddr, len, dir);
-			xen_mm32_unmap(vaddr - offset);
-		} else {
-			struct page *page = pfn_to_page(pfn);
-
-			if (PageHighMem(page)) {
-				if (len + offset > PAGE_SIZE)
-					len = PAGE_SIZE - offset;
-
-				if (cache_is_vipt_nonaliasing()) {
-					vaddr = kmap_atomic(page);
-					op(vaddr + offset, len, dir);
-					kunmap_atomic(vaddr);
-				} else {
-					vaddr = kmap_high_get(page);
-					if (vaddr) {
-						op(vaddr + offset, len, dir);
-						kunmap_high(page);
-					}
-				}
-			} else {
-				vaddr = page_address(page) + offset;
-				op(vaddr, len, dir);
-			}
-		}
-
-		offset = 0;
-		pfn++;
-		left -= len;
-	} while (left);
-}
-
-static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	/* Cannot use __dma_page_dev_to_cpu because we don't have a
-	 * struct page for handle */
-
-	if (dir != DMA_TO_DEVICE)
-		outer_inv_range(handle, handle + size);
-
-	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, dmac_unmap_area);
-}
-
-static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-
-	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, dmac_map_area);
-
-	if (dir == DMA_FROM_DEVICE) {
-		outer_inv_range(handle, handle + size);
-	} else {
-		outer_clean_range(handle, handle + size);
-	}
-}
-
-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)
-		return;
-	if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
-		return;
-
-	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
-}
-
-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)
-		return;
-	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
-}
-
-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)
-		return;
-	__xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
-}
-
-int __init xen_mm32_init(void)
-{
-	int cpu;
-
-	if (!xen_initial_domain())
-		return 0;
-
-	register_cpu_notifier(&xen_mm32_cpu_notifier);
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		if (alloc_xen_mm32_scratch_page(cpu)) {
-			put_online_cpus();
-			unregister_cpu_notifier(&xen_mm32_cpu_notifier);
-			return -ENOMEM;
-		}
-	}
-	put_online_cpus();
-
-	return 0;
-}
-arch_initcall(xen_mm32_init);

arch/arm64/include/asm/device.h

@@ -21,6 +21,7 @@ struct dev_archdata {
 #ifdef CONFIG_IOMMU_API
 	void *iommu;			/* private IOMMU data */
 #endif
+	bool dma_coherent;
 };
 
 struct pdev_archdata {

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

@@ -54,11 +54,18 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 
 static inline int set_arch_dma_coherent_ops(struct device *dev)
 {
+	dev->archdata.dma_coherent = true;
 	set_dma_ops(dev, &coherent_swiotlb_dma_ops);
 	return 0;
 }
 #define set_arch_dma_coherent_ops	set_arch_dma_coherent_ops
 
+/* do not use this function in a driver */
+static inline bool is_device_dma_coherent(struct device *dev)
+{
+	return dev->archdata.dma_coherent;
+}
+
 #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/xen/page-coherent.h

@@ -1,43 +1 @@
-#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)
-{
-}
-
-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_ARM64_XEN_PAGE_COHERENT_H */
+#include <../../arm/include/asm/xen/page-coherent.h>

arch/x86/include/asm/xen/cpuid.h

@@ -0,0 +1,91 @@
+/******************************************************************************
+ * arch-x86/cpuid.h
+ *
+ * CPUID interface to Xen.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright (c) 2007 Citrix Systems, Inc.
+ *
+ * Authors:
+ *    Keir Fraser <keir@xen.org>
+ */
+
+#ifndef __XEN_PUBLIC_ARCH_X86_CPUID_H__
+#define __XEN_PUBLIC_ARCH_X86_CPUID_H__
+
+/*
+ * For compatibility with other hypervisor interfaces, the Xen cpuid leaves
+ * can be found at the first otherwise unused 0x100 aligned boundary starting
+ * from 0x40000000.
+ *
+ * e.g If viridian extensions are enabled for an HVM domain, the Xen cpuid
+ * leaves will start at 0x40000100
+ */
+
+#define XEN_CPUID_FIRST_LEAF 0x40000000
+#define XEN_CPUID_LEAF(i)    (XEN_CPUID_FIRST_LEAF + (i))
+
+/*
+ * Leaf 1 (0x40000x00)
+ * EAX: Largest Xen-information leaf. All leaves up to an including @EAX
+ *      are supported by the Xen host.
+ * EBX-EDX: "XenVMMXenVMM" signature, allowing positive identification
+ *      of a Xen host.
+ */
+#define XEN_CPUID_SIGNATURE_EBX 0x566e6558 /* "XenV" */
+#define XEN_CPUID_SIGNATURE_ECX 0x65584d4d /* "MMXe" */
+#define XEN_CPUID_SIGNATURE_EDX 0x4d4d566e /* "nVMM" */
+
+/*
+ * Leaf 2 (0x40000x01)
+ * EAX[31:16]: Xen major version.
+ * EAX[15: 0]: Xen minor version.
+ * EBX-EDX: Reserved (currently all zeroes).
+ */
+
+/*
+ * Leaf 3 (0x40000x02)
+ * EAX: Number of hypercall transfer pages. This register is always guaranteed
+ *      to specify one hypercall page.
+ * EBX: Base address of Xen-specific MSRs.
+ * ECX: Features 1. Unused bits are set to zero.
+ * EDX: Features 2. Unused bits are set to zero.
+ */
+
+/* Does the host support MMU_PT_UPDATE_PRESERVE_AD for this guest? */
+#define _XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD 0
+#define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD  (1u<<0)
+
+/*
+ * Leaf 5 (0x40000x04)
+ * HVM-specific features
+ */
+
+/* EAX Features */
+/* Virtualized APIC registers */
+#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0)
+/* Virtualized x2APIC accesses */
+#define XEN_HVM_CPUID_X2APIC_VIRT      (1u << 1)
+/* Memory mapped from other domains has valid IOMMU entries */
+#define XEN_HVM_CPUID_IOMMU_MAPPINGS   (1u << 2)
+
+#define XEN_CPUID_MAX_NUM_LEAVES 4
+
+#endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */

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

@@ -22,8 +22,8 @@ static inline void xen_free_coherent_pages(struct device *hwdev, size_t 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) { }
+	     dma_addr_t dev_addr, 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,

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

@@ -236,4 +236,11 @@ void make_lowmem_page_readwrite(void *vaddr);
 #define xen_remap(cookie, size) ioremap((cookie), (size));
 #define xen_unmap(cookie) iounmap((cookie))
 
+static inline bool xen_arch_need_swiotlb(struct device *dev,
+					 unsigned long pfn,
+					 unsigned long mfn)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_XEN_PAGE_H */

arch/x86/pci/xen.c

@@ -23,6 +23,8 @@
 #include <xen/features.h>
 #include <xen/events.h>
 #include <asm/xen/pci.h>
+#include <asm/xen/cpuid.h>
+#include <asm/apic.h>
 #include <asm/i8259.h>
 
 static int xen_pcifront_enable_irq(struct pci_dev *dev)
@@ -423,6 +425,28 @@ int __init pci_xen_init(void)
 	return 0;
 }
 
+#ifdef CONFIG_PCI_MSI
+void __init xen_msi_init(void)
+{
+	if (!disable_apic) {
+		/*
+		 * If hardware supports (x2)APIC virtualization (as indicated
+		 * by hypervisor's leaf 4) then we don't need to use pirqs/
+		 * event channels for MSI handling and instead use regular
+		 * APIC processing
+		 */
+		uint32_t eax = cpuid_eax(xen_cpuid_base() + 4);
+
+		if (((eax & XEN_HVM_CPUID_X2APIC_VIRT) && x2apic_mode) ||
+		    ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && cpu_has_apic))
+			return;
+	}
+
+	x86_msi.setup_msi_irqs = xen_hvm_setup_msi_irqs;
+	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+}
+#endif
+
 int __init pci_xen_hvm_init(void)
 {
 	if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
@@ -437,8 +461,11 @@ int __init pci_xen_hvm_init(void)
 #endif
 
 #ifdef CONFIG_PCI_MSI
-	x86_msi.setup_msi_irqs = xen_hvm_setup_msi_irqs;
-	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+	/*
+	 * We need to wait until after x2apic is initialized
+	 * before we can set MSI IRQ ops.
+	 */
+	x86_platform.apic_post_init = xen_msi_init;
 #endif
 	return 0;
 }

drivers/pci/pci.c

@@ -1138,8 +1138,8 @@ EXPORT_SYMBOL_GPL(pci_store_saved_state);
  * @dev: PCI device that we're dealing with
  * @state: Saved state returned from pci_store_saved_state()
  */
-static int pci_load_saved_state(struct pci_dev *dev,
-				struct pci_saved_state *state)
+int pci_load_saved_state(struct pci_dev *dev,
+			 struct pci_saved_state *state)
 {
 	struct pci_cap_saved_data *cap;
 
@@ -1167,6 +1167,7 @@ static int pci_load_saved_state(struct pci_dev *dev,
 	dev->state_saved = true;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_load_saved_state);
 
 /**
  * pci_load_and_free_saved_state - Reload the save state pointed to by state,

drivers/xen/swiotlb-xen.c

@@ -96,8 +96,6 @@ static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
 	dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT;
 	phys_addr_t paddr = dma;
 
-	BUG_ON(paddr != dma); /* truncation has occurred, should never happen */
-
 	paddr |= baddr & ~PAGE_MASK;
 
 	return paddr;
@@ -399,11 +397,13 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * buffering it.
 	 */
 	if (dma_capable(dev, dev_addr, size) &&
-	    !range_straddles_page_boundary(phys, size) && !swiotlb_force) {
+	    !range_straddles_page_boundary(phys, size) &&
+		!xen_arch_need_swiotlb(dev, PFN_DOWN(phys), PFN_DOWN(dev_addr)) &&
+		!swiotlb_force) {
 		/* we are not interested in the dma_addr returned by
 		 * xen_dma_map_page, only in the potential cache flushes executed
 		 * by the function. */
-		xen_dma_map_page(dev, page, offset, size, dir, attrs);
+		xen_dma_map_page(dev, page, dev_addr, offset, size, dir, attrs);
 		return dev_addr;
 	}
 
@@ -417,7 +417,7 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 		return DMA_ERROR_CODE;
 
 	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
-					map & ~PAGE_MASK, size, dir, attrs);
+					dev_addr, map & ~PAGE_MASK, size, dir, attrs);
 	dev_addr = xen_phys_to_bus(map);
 
 	/*
@@ -447,7 +447,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	xen_dma_unmap_page(hwdev, paddr, size, dir, attrs);
+	xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
@@ -495,14 +495,14 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 	BUG_ON(dir == DMA_NONE);
 
 	if (target == SYNC_FOR_CPU)
-		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+		xen_dma_sync_single_for_cpu(hwdev, dev_addr, size, dir);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr))
 		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
 
 	if (target == SYNC_FOR_DEVICE)
-		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+		xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir);
 
 	if (dir != DMA_FROM_DEVICE)
 		return;
@@ -557,6 +557,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
 
 		if (swiotlb_force ||
+		    xen_arch_need_swiotlb(hwdev, PFN_DOWN(paddr), PFN_DOWN(dev_addr)) ||
 		    !dma_capable(hwdev, dev_addr, sg->length) ||
 		    range_straddles_page_boundary(paddr, sg->length)) {
 			phys_addr_t map = swiotlb_tbl_map_single(hwdev,
@@ -574,6 +575,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 				return 0;
 			}
 			xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT),
+						dev_addr,
 						map & ~PAGE_MASK,
 						sg->length,
 						dir,
@@ -584,6 +586,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 			 * xen_dma_map_page, only in the potential cache flushes executed
 			 * by the function. */
 			xen_dma_map_page(hwdev, pfn_to_page(paddr >> PAGE_SHIFT),
+						dev_addr,
 						paddr & ~PAGE_MASK,
 						sg->length,
 						dir,

drivers/xen/xen-pciback/passthrough.c

@@ -69,7 +69,7 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
 }
 
 static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-					struct pci_dev *dev)
+					struct pci_dev *dev, bool lock)
 {
 	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
 	struct pci_dev_entry *dev_entry, *t;
@@ -87,8 +87,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
 
 	mutex_unlock(&dev_data->lock);
 
-	if (found_dev)
+	if (found_dev) {
+		if (lock)
+			device_lock(&found_dev->dev);
 		pcistub_put_pci_dev(found_dev);
+		if (lock)
+			device_unlock(&found_dev->dev);
+	}
 }
 
 static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
@@ -156,8 +161,11 @@ static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
 	struct pci_dev_entry *dev_entry, *t;
 
 	list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) {
+		struct pci_dev *dev = dev_entry->dev;
 		list_del(&dev_entry->list);
-		pcistub_put_pci_dev(dev_entry->dev);
+		device_lock(&dev->dev);
+		pcistub_put_pci_dev(dev);
+		device_unlock(&dev->dev);
 		kfree(dev_entry);
 	}
 

drivers/xen/xen-pciback/pci_stub.c

@@ -105,7 +105,7 @@ static void pcistub_device_release(struct kref *kref)
 	 */
 	__pci_reset_function_locked(dev);
 	if (pci_load_and_free_saved_state(dev, &dev_data->pci_saved_state))
-		dev_dbg(&dev->dev, "Could not reload PCI state\n");
+		dev_info(&dev->dev, "Could not reload PCI state\n");
 	else
 		pci_restore_state(dev);
 
@@ -250,11 +250,15 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
  *  - 'echo BDF > unbind' with a guest still using it. See pcistub_remove
  *
  *  As such we have to be careful.
+ *
+ *  To make this easier, the caller has to hold the device lock.
  */
 void pcistub_put_pci_dev(struct pci_dev *dev)
 {
 	struct pcistub_device *psdev, *found_psdev = NULL;
 	unsigned long flags;
+	struct xen_pcibk_dev_data *dev_data;
+	int ret;
 
 	spin_lock_irqsave(&pcistub_devices_lock, flags);
 
@@ -276,13 +280,20 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
 	/* Cleanup our device
 	 * (so it's ready for the next domain)
 	 */
+	device_lock_assert(&dev->dev);
+	__pci_reset_function_locked(dev);
 
-	/* This is OK - we are running from workqueue context
-	 * and want to inhibit the user from fiddling with 'reset'
-	 */
-	pci_reset_function(dev);
-	pci_restore_state(dev);
-
+	dev_data = pci_get_drvdata(dev);
+	ret = pci_load_saved_state(dev, dev_data->pci_saved_state);
+	if (!ret) {
+		/*
+		 * The usual sequence is pci_save_state & pci_restore_state
+		 * but the guest might have messed the configuration space up.
+		 * Use the initial version (when device was bound to us).
+		 */
+		pci_restore_state(dev);
+	} else
+		dev_info(&dev->dev, "Could not reload PCI state\n");
 	/* This disables the device. */
 	xen_pcibk_reset_device(dev);
 
@@ -554,12 +565,14 @@ static void pcistub_remove(struct pci_dev *dev)
 	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
 
 	if (found_psdev) {
-		dev_dbg(&dev->dev, "found device to remove - in use? %p\n",
-			found_psdev->pdev);
+		dev_dbg(&dev->dev, "found device to remove %s\n",
+			found_psdev->pdev ? "- in-use" : "");
 
 		if (found_psdev->pdev) {
-			pr_warn("****** removing device %s while still in-use! ******\n",
-			       pci_name(found_psdev->dev));
+			int domid = xen_find_device_domain_owner(dev);
+
+			pr_warn("****** removing device %s while still in-use by domain %d! ******\n",
+			       pci_name(found_psdev->dev), domid);
 			pr_warn("****** driver domain may still access this device's i/o resources!\n");
 			pr_warn("****** shutdown driver domain before binding device\n");
 			pr_warn("****** to other drivers or domains\n");
@@ -567,7 +580,8 @@ static void pcistub_remove(struct pci_dev *dev)
 			/* N.B. This ends up calling pcistub_put_pci_dev which ends up
 			 * doing the FLR. */
 			xen_pcibk_release_pci_dev(found_psdev->pdev,
-						found_psdev->dev);
+						found_psdev->dev,
+						false /* caller holds the lock. */);
 		}
 
 		spin_lock_irqsave(&pcistub_devices_lock, flags);
@@ -629,10 +643,12 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev,
 {
 	pci_ers_result_t res = result;
 	struct xen_pcie_aer_op *aer_op;
+	struct xen_pcibk_device *pdev = psdev->pdev;
+	struct xen_pci_sharedinfo *sh_info = pdev->sh_info;
 	int ret;
 
 	/*with PV AER drivers*/
-	aer_op = &(psdev->pdev->sh_info->aer_op);
+	aer_op = &(sh_info->aer_op);
 	aer_op->cmd = aer_cmd ;
 	/*useful for error_detected callback*/
 	aer_op->err = state;
@@ -653,36 +669,36 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev,
 	* this flag to judge whether we need to check pci-front give aer
 	* service ack signal
 	*/
-	set_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags);
+	set_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags);
 
 	/*It is possible that a pcifront conf_read_write ops request invokes
 	* the callback which cause the spurious execution of wake_up.
 	* Yet it is harmless and better than a spinlock here
 	*/
 	set_bit(_XEN_PCIB_active,
-		(unsigned long *)&psdev->pdev->sh_info->flags);
+		(unsigned long *)&sh_info->flags);
 	wmb();
-	notify_remote_via_irq(psdev->pdev->evtchn_irq);
+	notify_remote_via_irq(pdev->evtchn_irq);
 
 	ret = wait_event_timeout(xen_pcibk_aer_wait_queue,
 				 !(test_bit(_XEN_PCIB_active, (unsigned long *)
-				 &psdev->pdev->sh_info->flags)), 300*HZ);
+				 &sh_info->flags)), 300*HZ);
 
 	if (!ret) {
 		if (test_bit(_XEN_PCIB_active,
-			(unsigned long *)&psdev->pdev->sh_info->flags)) {
+			(unsigned long *)&sh_info->flags)) {
 			dev_err(&psdev->dev->dev,
 				"pcifront aer process not responding!\n");
 			clear_bit(_XEN_PCIB_active,
-			  (unsigned long *)&psdev->pdev->sh_info->flags);
+			  (unsigned long *)&sh_info->flags);
 			aer_op->err = PCI_ERS_RESULT_NONE;
 			return res;
 		}
 	}
-	clear_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags);
+	clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags);
 
 	if (test_bit(_XEN_PCIF_active,
-		(unsigned long *)&psdev->pdev->sh_info->flags)) {
+		(unsigned long *)&sh_info->flags)) {
 		dev_dbg(&psdev->dev->dev,
 			"schedule pci_conf service in " DRV_NAME "\n");
 		xen_pcibk_test_and_schedule_op(psdev->pdev);
@@ -1502,6 +1518,53 @@ parse_error:
 fs_initcall(pcistub_init);
 #endif
 
+#ifdef CONFIG_PCI_IOV
+static struct pcistub_device *find_vfs(const struct pci_dev *pdev)
+{
+	struct pcistub_device *psdev = NULL;
+	unsigned long flags;
+	bool found = false;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (!psdev->pdev && psdev->dev != pdev
+		    && pci_physfn(psdev->dev) == pdev) {
+			found = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	if (found)
+		return psdev;
+	return NULL;
+}
+
+static int pci_stub_notifier(struct notifier_block *nb,
+			     unsigned long action, void *data)
+{
+	struct device *dev = data;
+	const struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (action != BUS_NOTIFY_UNBIND_DRIVER)
+		return NOTIFY_DONE;
+
+	if (!pdev->is_physfn)
+		return NOTIFY_DONE;
+
+	for (;;) {
+		struct pcistub_device *psdev = find_vfs(pdev);
+		if (!psdev)
+			break;
+		device_release_driver(&psdev->dev->dev);
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block pci_stub_nb = {
+	.notifier_call = pci_stub_notifier,
+};
+#endif
+
 static int __init xen_pcibk_init(void)
 {
 	int err;
@@ -1523,12 +1586,19 @@ static int __init xen_pcibk_init(void)
 	err = xen_pcibk_xenbus_register();
 	if (err)
 		pcistub_exit();
+#ifdef CONFIG_PCI_IOV
+	else
+		bus_register_notifier(&pci_bus_type, &pci_stub_nb);
+#endif
 
 	return err;
 }
 
 static void __exit xen_pcibk_cleanup(void)
 {
+#ifdef CONFIG_PCI_IOV
+	bus_unregister_notifier(&pci_bus_type, &pci_stub_nb);
+#endif
 	xen_pcibk_xenbus_unregister();
 	pcistub_exit();
 }

drivers/xen/xen-pciback/pciback.h

@@ -99,7 +99,8 @@ struct xen_pcibk_backend {
 		    unsigned int *domain, unsigned int *bus,
 		    unsigned int *devfn);
 	int (*publish)(struct xen_pcibk_device *pdev, publish_pci_root_cb cb);
-	void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev);
+	void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev,
+                        bool lock);
 	int (*add)(struct xen_pcibk_device *pdev, struct pci_dev *dev,
 		   int devid, publish_pci_dev_cb publish_cb);
 	struct pci_dev *(*get)(struct xen_pcibk_device *pdev,
@@ -122,10 +123,10 @@ static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
 }
 
 static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-					     struct pci_dev *dev)
+					     struct pci_dev *dev, bool lock)
 {
 	if (xen_pcibk_backend && xen_pcibk_backend->release)
-		return xen_pcibk_backend->release(pdev, dev);
+		return xen_pcibk_backend->release(pdev, dev, lock);
 }
 
 static inline struct pci_dev *

drivers/xen/xen-pciback/vpci.c

@@ -145,7 +145,7 @@ out:
 }
 
 static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-					struct pci_dev *dev)
+					struct pci_dev *dev, bool lock)
 {
 	int slot;
 	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
@@ -169,8 +169,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
 out:
 	mutex_unlock(&vpci_dev->lock);
 
-	if (found_dev)
+	if (found_dev) {
+		if (lock)
+			device_lock(&found_dev->dev);
 		pcistub_put_pci_dev(found_dev);
+		if (lock)
+			device_unlock(&found_dev->dev);
+	}
 }
 
 static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
@@ -208,8 +213,11 @@ static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
 		struct pci_dev_entry *e, *tmp;
 		list_for_each_entry_safe(e, tmp, &vpci_dev->dev_list[slot],
 					 list) {
+			struct pci_dev *dev = e->dev;
 			list_del(&e->list);
-			pcistub_put_pci_dev(e->dev);
+			device_lock(&dev->dev);
+			pcistub_put_pci_dev(dev);
+			device_unlock(&dev->dev);
 			kfree(e);
 		}
 	}

drivers/xen/xen-pciback/xenbus.c

@@ -247,7 +247,7 @@ static int xen_pcibk_export_device(struct xen_pcibk_device *pdev,
 	if (err)
 		goto out;
 
-	dev_dbg(&dev->dev, "registering for %d\n", pdev->xdev->otherend_id);
+	dev_info(&dev->dev, "registering for %d\n", pdev->xdev->otherend_id);
 	if (xen_register_device_domain_owner(dev,
 					     pdev->xdev->otherend_id) != 0) {
 		dev_err(&dev->dev, "Stealing ownership from dom%d.\n",
@@ -291,7 +291,7 @@ static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev,
 
 	/* N.B. This ends up calling pcistub_put_pci_dev which ends up
 	 * doing the FLR. */
-	xen_pcibk_release_pci_dev(pdev, dev);
+	xen_pcibk_release_pci_dev(pdev, dev, true /* use the lock. */);
 
 out:
 	return err;

include/linux/device.h

@@ -911,6 +911,11 @@ static inline void device_unlock(struct device *dev)
 	mutex_unlock(&dev->mutex);
 }
 
+static inline void device_lock_assert(struct device *dev)
+{
+	lockdep_assert_held(&dev->mutex);
+}
+
 void driver_init(void);
 
 /*

include/linux/pci.h

@@ -1004,6 +1004,8 @@ void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size);
 int pci_save_state(struct pci_dev *dev);
 void pci_restore_state(struct pci_dev *dev);
 struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev);
+int pci_load_saved_state(struct pci_dev *dev,
+			 struct pci_saved_state *state);
 int pci_load_and_free_saved_state(struct pci_dev *dev,
 				  struct pci_saved_state **state);
 struct pci_cap_saved_state *pci_find_saved_cap(struct pci_dev *dev, char cap);

include/xen/interface/features.h

@@ -53,9 +53,6 @@
 /* operation as Dom0 is supported */
 #define XENFEAT_dom0                      11
 
-/* Xen also maps grant references at pfn = mfn */
-#define XENFEAT_grant_map_identity        12
-
 #define XENFEAT_NR_SUBMAPS 1
 
 #endif /* __XEN_PUBLIC_FEATURES_H__ */

include/xen/interface/grant_table.h

@@ -478,6 +478,25 @@ struct gnttab_get_version {
 };
 DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version);
 
+/*
+ * Issue one or more cache maintenance operations on a portion of a
+ * page granted to the calling domain by a foreign domain.
+ */
+#define GNTTABOP_cache_flush          12
+struct gnttab_cache_flush {
+    union {
+        uint64_t dev_bus_addr;
+        grant_ref_t ref;
+    } a;
+    uint16_t offset;   /* offset from start of grant */
+    uint16_t length;   /* size within the grant */
+#define GNTTAB_CACHE_CLEAN          (1<<0)
+#define GNTTAB_CACHE_INVAL          (1<<1)
+#define GNTTAB_CACHE_SOURCE_GREF    (1<<31)
+    uint32_t op;
+};
+DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush);
+
 /*
  * Bitfield values for update_pin_status.flags.
  */