iommu: Add option to group multi-function devices

The option iommu=group_mf indicates the that the iommu driver should
expose all functions of a multi-function PCI device as the same
iommu_device_group.  This is useful for disallowing individual functions
being exposed as independent devices to userspace as there are often
hidden dependencies.  Virtual functions are not affected by this option.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

Documentation/kernel-parameters.txt

@@ -1060,6 +1060,8 @@ 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
 			See comment before marvel_specify_io7 in

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);

arch/ia64/kernel/pci-dma.c

@@ -33,6 +33,7 @@ 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

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)

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). */
@@ -169,6 +178,8 @@ 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);
 

drivers/iommu/amd_iommu.c

@@ -2776,11 +2776,19 @@ static int amd_iommu_domain_has_cap(struct iommu_domain *domain,
 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;
 
-	*groupid = amd_iommu_alias_table[dev_data->devid];
+	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;
 }

drivers/iommu/intel-iommu.c

@@ -4100,6 +4100,9 @@ static int intel_iommu_device_group(struct device *dev, unsigned int *groupid)
 		}
 	}
 
+	if (!pdev->is_virtfn && iommu_group_mf)
+		id.pci.devfn = PCI_DEVFN(PCI_SLOT(id.pci.devfn), 0);
+
 	*groupid = id.group;
 
 	return 0;