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
  ...

8 files changed, 191 insertions, 217 deletions

diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
index dc662fca9230..4111592f0130 100644
--- a/arch/arm/include/asm/device.h
+++ b/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;
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 85738b200023..e6e3446abdf6 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/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;
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index e8275ea88e88..efd562412850 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/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 */
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 135c24a5ba26..68c739b3fdf4 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/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 */
diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile
index 1f85bfe6b470..12969523414c 100644
--- a/arch/arm/xen/Makefile
+++ b/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
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 0e15f011f9c8..c7ca936ebd99 100644
--- a/arch/arm/xen/enlighten.c
+++ b/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
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index b0e77de99148..351b24a979d4 100644
--- a/arch/arm/xen/mm.c
+++ b/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);
diff --git a/arch/arm/xen/mm32.c b/arch/arm/xen/mm32.c
deleted file mode 100644
index 3b99860fd7ae..000000000000
--- a/arch/arm/xen/mm32.c
+++ /dev/null
@@ -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);