Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (53 commits)
  iommu/amd: Set IOTLB invalidation timeout
  iommu/amd: Init stats for iommu=pt
  iommu/amd: Remove unnecessary cache flushes in amd_iommu_resume
  iommu/amd: Add invalidate-context call-back
  iommu/amd: Add amd_iommu_device_info() function
  iommu/amd: Adapt IOMMU driver to PCI register name changes
  iommu/amd: Add invalid_ppr callback
  iommu/amd: Implement notifiers for IOMMUv2
  iommu/amd: Implement IO page-fault handler
  iommu/amd: Add routines to bind/unbind a pasid
  iommu/amd: Implement device aquisition code for IOMMUv2
  iommu/amd: Add driver stub for AMD IOMMUv2 support
  iommu/amd: Add stat counter for IOMMUv2 events
  iommu/amd: Add device errata handling
  iommu/amd: Add function to get IOMMUv2 domain for pdev
  iommu/amd: Implement function to send PPR completions
  iommu/amd: Implement functions to manage GCR3 table
  iommu/amd: Implement IOMMUv2 TLB flushing routines
  iommu/amd: Add support for IOMMUv2 domain mode
  iommu/amd: Add amd_iommu_domain_direct_map function
  ...

1 files changed, 72 insertions, 7 deletions

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 31053a951c3..c9c6053198d 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -79,6 +79,24 @@
 #define LEVEL_STRIDE		(9)
 #define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
 
+/*
+ * This bitmap is used to advertise the page sizes our hardware support
+ * to the IOMMU core, which will then use this information to split
+ * physically contiguous memory regions it is mapping into page sizes
+ * that we support.
+ *
+ * Traditionally the IOMMU core just handed us the mappings directly,
+ * after making sure the size is an order of a 4KiB page and that the
+ * mapping has natural alignment.
+ *
+ * To retain this behavior, we currently advertise that we support
+ * all page sizes that are an order of 4KiB.
+ *
+ * If at some point we'd like to utilize the IOMMU core's new behavior,
+ * we could change this to advertise the real page sizes we support.
+ */
+#define INTEL_IOMMU_PGSIZES	(~0xFFFUL)
+
 static inline int agaw_to_level(int agaw)
 {
 	return agaw + 2;
@@ -3979,12 +3997,11 @@ static void intel_iommu_detach_device(struct iommu_domain *domain,
 
 static int intel_iommu_map(struct iommu_domain *domain,
 			   unsigned long iova, phys_addr_t hpa,
-			   int gfp_order, int iommu_prot)
+			   size_t size, int iommu_prot)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
 	u64 max_addr;
 	int prot = 0;
-	size_t size;
 	int ret;
 
 	if (iommu_prot & IOMMU_READ)
@@ -3994,7 +4011,6 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
 		prot |= DMA_PTE_SNP;
 
-	size     = PAGE_SIZE << gfp_order;
 	max_addr = iova + size;
 	if (dmar_domain->max_addr < max_addr) {
 		u64 end;
@@ -4017,11 +4033,10 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	return ret;
 }
 
-static int intel_iommu_unmap(struct iommu_domain *domain,
-			     unsigned long iova, int gfp_order)
+static size_t intel_iommu_unmap(struct iommu_domain *domain,
+			     unsigned long iova, size_t size)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
-	size_t size = PAGE_SIZE << gfp_order;
 	int order;
 
 	order = dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT,
@@ -4030,7 +4045,7 @@ static int intel_iommu_unmap(struct iommu_domain *domain,
 	if (dmar_domain->max_addr == iova + size)
 		dmar_domain->max_addr = iova;
 
-	return order;
+	return PAGE_SIZE << order;
 }
 
 static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
@@ -4060,6 +4075,54 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain,
 	return 0;
 }
 
+/*
+ * Group numbers are arbitrary.  Device with the same group number
+ * indicate the iommu cannot differentiate between them.  To avoid
+ * tracking used groups we just use the seg|bus|devfn of the lowest
+ * level we're able to differentiate devices
+ */
+static int intel_iommu_device_group(struct device *dev, unsigned int *groupid)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_dev *bridge;
+	union {
+		struct {
+			u8 devfn;
+			u8 bus;
+			u16 segment;
+		} pci;
+		u32 group;
+	} id;
+
+	if (iommu_no_mapping(dev))
+		return -ENODEV;
+
+	id.pci.segment = pci_domain_nr(pdev->bus);
+	id.pci.bus = pdev->bus->number;
+	id.pci.devfn = pdev->devfn;
+
+	if (!device_to_iommu(id.pci.segment, id.pci.bus, id.pci.devfn))
+		return -ENODEV;
+
+	bridge = pci_find_upstream_pcie_bridge(pdev);
+	if (bridge) {
+		if (pci_is_pcie(bridge)) {
+			id.pci.bus = bridge->subordinate->number;
+			id.pci.devfn = 0;
+		} else {
+			id.pci.bus = bridge->bus->number;
+			id.pci.devfn = bridge->devfn;
+		}
+	}
+
+	if (!pdev->is_virtfn && iommu_group_mf)
+		id.pci.devfn = PCI_DEVFN(PCI_SLOT(id.pci.devfn), 0);
+
+	*groupid = id.group;
+
+	return 0;
+}
+
 static struct iommu_ops intel_iommu_ops = {
 	.domain_init	= intel_iommu_domain_init,
 	.domain_destroy = intel_iommu_domain_destroy,
@@ -4069,6 +4132,8 @@ static struct iommu_ops intel_iommu_ops = {
 	.unmap		= intel_iommu_unmap,
 	.iova_to_phys	= intel_iommu_iova_to_phys,
 	.domain_has_cap = intel_iommu_domain_has_cap,
+	.device_group	= intel_iommu_device_group,
+	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
 };
 
 static void __devinit quirk_iommu_rwbf(struct pci_dev *dev)