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
  ...

26 files changed, 488 insertions, 309 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))