---

yaml
---
r: 316585
b: refs/heads/master
c: 4e0ee78
h: refs/heads/master
i:
  316583: 5a5394d
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 7d43c2e42cb1e436f97c1763150e4e1122ae0d57
+refs/heads/master: 4e0ee78f2af96676c9dca898c13250f62c513058

trunk/Documentation/kernel-parameters.txt

@@ -1134,6 +1134,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 		forcesac
 		soft
 		pt		[x86, IA-64]
+		group_mf	[x86, IA-64]
 
 
 	io7=		[HW] IO7 for Marvel based alpha systems

trunk/arch/ia64/include/asm/iommu.h

@@ -11,10 +11,12 @@ extern void no_iommu_init(void);
 extern int force_iommu, no_iommu;
 extern int iommu_pass_through;
 extern int iommu_detected;
+extern int iommu_group_mf;
 #else
 #define iommu_pass_through	(0)
 #define no_iommu		(1)
 #define iommu_detected		(0)
+#define iommu_group_mf		(0)
 #endif
 extern void iommu_dma_init(void);
 extern void machvec_init(const char *name);

trunk/arch/ia64/kernel/pci-dma.c

@@ -32,6 +32,7 @@ int force_iommu __read_mostly;
 #endif
 
 int iommu_pass_through;
+int iommu_group_mf;
 
 /* Dummy device used for NULL arguments (normally ISA). Better would
    be probably a smaller DMA mask, but this is bug-to-bug compatible

trunk/arch/x86/include/asm/iommu.h

@@ -5,6 +5,7 @@ extern struct dma_map_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 extern int iommu_pass_through;
+extern int iommu_group_mf;
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)

trunk/arch/x86/kernel/pci-dma.c

@@ -45,6 +45,15 @@ int iommu_detected __read_mostly = 0;
  */
 int iommu_pass_through __read_mostly;
 
+/*
+ * Group multi-function PCI devices into a single device-group for the
+ * iommu_device_group interface.  This tells the iommu driver to pretend
+ * it cannot distinguish between functions of a device, exposing only one
+ * group for the device.  Useful for disallowing use of individual PCI
+ * functions from userspace drivers.
+ */
+int iommu_group_mf __read_mostly;
+
 extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
 
 /* Dummy device used for NULL arguments (normally ISA). */
@@ -185,6 +194,8 @@ static __init int iommu_setup(char *p)
 #endif
 		if (!strncmp(p, "pt", 2))
 			iommu_pass_through = 1;
+		if (!strncmp(p, "group_mf", 8))
+			iommu_group_mf = 1;
 
 		gart_parse_options(p);
 

trunk/drivers/iommu/Kconfig

@@ -13,6 +13,10 @@ menuconfig IOMMU_SUPPORT
 
 if IOMMU_SUPPORT
 
+config OF_IOMMU
+       def_bool y
+       depends on OF
+
 # MSM IOMMU support
 config MSM_IOMMU
 	bool "MSM IOMMU Support"

trunk/drivers/iommu/Makefile

@@ -1,4 +1,5 @@
 obj-$(CONFIG_IOMMU_API) += iommu.o
+obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o

trunk/drivers/iommu/amd_iommu.c

@@ -254,21 +254,11 @@ static bool check_device(struct device *dev)
 	return true;
 }
 
-static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to)
-{
-	pci_dev_put(*from);
-	*from = to;
-}
-
-#define REQ_ACS_FLAGS	(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
-
 static int iommu_init_device(struct device *dev)
 {
-	struct pci_dev *dma_pdev, *pdev = to_pci_dev(dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
 	struct iommu_dev_data *dev_data;
-	struct iommu_group *group;
 	u16 alias;
-	int ret;
 
 	if (dev->archdata.iommu)
 		return 0;
@@ -289,43 +279,8 @@ static int iommu_init_device(struct device *dev)
 			return -ENOTSUPP;
 		}
 		dev_data->alias_data = alias_data;
-
-		dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff);
-	} else
-		dma_pdev = pci_dev_get(pdev);
-
-	swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev));
-
-	if (dma_pdev->multifunction &&
-	    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS))
-		swap_pci_ref(&dma_pdev,
-			     pci_get_slot(dma_pdev->bus,
-					  PCI_DEVFN(PCI_SLOT(dma_pdev->devfn),
-					  0)));
-
-	while (!pci_is_root_bus(dma_pdev->bus)) {
-		if (pci_acs_path_enabled(dma_pdev->bus->self,
-					 NULL, REQ_ACS_FLAGS))
-			break;
-
-		swap_pci_ref(&dma_pdev, pci_dev_get(dma_pdev->bus->self));
 	}
 
-	group = iommu_group_get(&dma_pdev->dev);
-	pci_dev_put(dma_pdev);
-	if (!group) {
-		group = iommu_group_alloc();
-		if (IS_ERR(group))
-			return PTR_ERR(group);
-	}
-
-	ret = iommu_group_add_device(group, dev);
-
-	iommu_group_put(group);
-
-	if (ret)
-		return ret;
-
 	if (pci_iommuv2_capable(pdev)) {
 		struct amd_iommu *iommu;
 
@@ -354,8 +309,6 @@ static void iommu_ignore_device(struct device *dev)
 
 static void iommu_uninit_device(struct device *dev)
 {
-	iommu_group_remove_device(dev);
-
 	/*
 	 * Nothing to do here - we keep dev_data around for unplugged devices
 	 * and reuse it when the device is re-plugged - not doing so would
@@ -3274,6 +3227,26 @@ static int amd_iommu_domain_has_cap(struct iommu_domain *domain,
 	return 0;
 }
 
+static int amd_iommu_device_group(struct device *dev, unsigned int *groupid)
+{
+	struct iommu_dev_data *dev_data = dev->archdata.iommu;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	u16 devid;
+
+	if (!dev_data)
+		return -ENODEV;
+
+	if (pdev->is_virtfn || !iommu_group_mf)
+		devid = dev_data->devid;
+	else
+		devid = calc_devid(pdev->bus->number,
+				   PCI_DEVFN(PCI_SLOT(pdev->devfn), 0));
+
+	*groupid = amd_iommu_alias_table[devid];
+
+	return 0;
+}
+
 static struct iommu_ops amd_iommu_ops = {
 	.domain_init = amd_iommu_domain_init,
 	.domain_destroy = amd_iommu_domain_destroy,
@@ -3283,6 +3256,7 @@ static struct iommu_ops amd_iommu_ops = {
 	.unmap = amd_iommu_unmap,
 	.iova_to_phys = amd_iommu_iova_to_phys,
 	.domain_has_cap = amd_iommu_domain_has_cap,
+	.device_group = amd_iommu_device_group,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
 

trunk/drivers/iommu/intel-iommu.c

@@ -4090,70 +4090,52 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain,
 	return 0;
 }
 
-static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to)
+/*
+ * 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)
 {
-	pci_dev_put(*from);
-	*from = to;
-}
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_dev *bridge;
+	union {
+		struct {
+			u8 devfn;
+			u8 bus;
+			u16 segment;
+		} pci;
+		u32 group;
+	} id;
 
-#define REQ_ACS_FLAGS	(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
+	if (iommu_no_mapping(dev))
+		return -ENODEV;
 
-static int intel_iommu_add_device(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct pci_dev *bridge, *dma_pdev;
-	struct iommu_group *group;
-	int ret;
+	id.pci.segment = pci_domain_nr(pdev->bus);
+	id.pci.bus = pdev->bus->number;
+	id.pci.devfn = pdev->devfn;
 
-	if (!device_to_iommu(pci_domain_nr(pdev->bus),
-			     pdev->bus->number, 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))
-			dma_pdev = pci_get_domain_bus_and_slot(
-						pci_domain_nr(pdev->bus),
-						bridge->subordinate->number, 0);
-		else
-			dma_pdev = pci_dev_get(bridge);
-	} else
-		dma_pdev = pci_dev_get(pdev);
-
-	swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev));
-
-	if (dma_pdev->multifunction &&
-	    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS))
-		swap_pci_ref(&dma_pdev,
-			     pci_get_slot(dma_pdev->bus,
-					  PCI_DEVFN(PCI_SLOT(dma_pdev->devfn),
-					  0)));
-
-	while (!pci_is_root_bus(dma_pdev->bus)) {
-		if (pci_acs_path_enabled(dma_pdev->bus->self,
-					 NULL, REQ_ACS_FLAGS))
-			break;
-
-		swap_pci_ref(&dma_pdev, pci_dev_get(dma_pdev->bus->self));
-	}
-
-	group = iommu_group_get(&dma_pdev->dev);
-	pci_dev_put(dma_pdev);
-	if (!group) {
-		group = iommu_group_alloc();
-		if (IS_ERR(group))
-			return PTR_ERR(group);
+		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;
+		}
 	}
 
-	ret = iommu_group_add_device(group, dev);
+	if (!pdev->is_virtfn && iommu_group_mf)
+		id.pci.devfn = PCI_DEVFN(PCI_SLOT(id.pci.devfn), 0);
 
-	iommu_group_put(group);
-	return ret;
-}
+	*groupid = id.group;
 
-static void intel_iommu_remove_device(struct device *dev)
-{
-	iommu_group_remove_device(dev);
+	return 0;
 }
 
 static struct iommu_ops intel_iommu_ops = {
@@ -4165,8 +4147,7 @@ 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,
-	.add_device	= intel_iommu_add_device,
-	.remove_device	= intel_iommu_remove_device,
+	.device_group	= intel_iommu_device_group,
 	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
 };