Merge tag 'iommu-updates-v3.6-rc1' of git://git.kernel.org/pub/scm/li…

…nux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "The most important part of these updates is the IOMMU groups code
  enhancement written by Alex Williamson.  It abstracts the problem that
  a given hardware IOMMU can't isolate any given device from any other
  device (e.g.  32 bit PCI devices can't usually be isolated).  Devices
  that can't be isolated are grouped together.  This code is required
  for the upcoming VFIO framework.

  Another IOMMU-API change written by me is the introduction of domain
  attributes.  This makes it easier to handle GART-like IOMMUs with the
  IOMMU-API because now the start-address and the size of the domain
  address space can be queried.

  Besides that there are a few cleanups and fixes for the NVidia Tegra
  IOMMU drivers and the reworked init-code for the AMD IOMMU.  The
  latter is from my patch-set to support interrupt remapping.  The rest
  of this patch-set requires x86 changes which are not mergabe yet.  So
  full support for interrupt remapping with AMD IOMMUs will come in a
  future merge window."

* tag 'iommu-updates-v3.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (33 commits)
  iommu/amd: Fix hotplug with iommu=pt
  iommu/amd: Add missing spin_lock initialization
  iommu/amd: Convert iommu initialization to state machine
  iommu/amd: Introduce amd_iommu_init_dma routine
  iommu/amd: Move unmap_flush message to amd_iommu_init_dma_ops()
  iommu/amd: Split enable_iommus() routine
  iommu/amd: Introduce early_amd_iommu_init routine
  iommu/amd: Move informational prinks out of iommu_enable
  iommu/amd: Split out PCI related parts of IOMMU initialization
  iommu/amd: Use acpi_get_table instead of acpi_table_parse
  iommu/amd: Fix sparse warnings
  iommu/tegra: Don't call alloc_pdir with as->lock
  iommu/tegra: smmu: Fix unsleepable memory allocation at alloc_pdir()
  iommu/tegra: smmu: Remove unnecessary sanity check at alloc_pdir()
  iommu/exynos: Implement DOMAIN_ATTR_GEOMETRY attribute
  iommu/tegra: Implement DOMAIN_ATTR_GEOMETRY attribute
  iommu/msm: Implement DOMAIN_ATTR_GEOMETRY attribute
  iommu/omap: Implement DOMAIN_ATTR_GEOMETRY attribute
  iommu/vt-d: Implement DOMAIN_ATTR_GEOMETRY attribute
  iommu/amd: Implement DOMAIN_ATTR_GEOMETRY attribute
  ...

Documentation/ABI/testing/sysfs-kernel-iommu_groups

@@ -0,0 +1,14 @@
+What:		/sys/kernel/iommu_groups/
+Date:		May 2012
+KernelVersion:	v3.5
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:	/sys/kernel/iommu_groups/ contains a number of sub-
+		directories, each representing an IOMMU group.  The
+		name of the sub-directory matches the iommu_group_id()
+		for the group, which is an integer value.  Within each
+		subdirectory is another directory named "devices" with
+		links to the sysfs devices contained in this group.
+		The group directory also optionally contains a "name"
+		file if the IOMMU driver has chosen to register a more
+		common name for the group.
+Users:

Documentation/devicetree/bindings/iommu/nvidia,tegra30-smmu.txt

@@ -0,0 +1,21 @@
+NVIDIA Tegra 30 IOMMU H/W, SMMU (System Memory Management Unit)
+
+Required properties:
+- compatible : "nvidia,tegra30-smmu"
+- reg : Should contain 3 register banks(address and length) for each
+  of the SMMU register blocks.
+- interrupts : Should contain MC General interrupt.
+- nvidia,#asids : # of ASIDs
+- dma-window : IOVA start address and length.
+- nvidia,ahb : phandle to the ahb bus connected to SMMU.
+
+Example:
+	smmu {
+		compatible = "nvidia,tegra30-smmu";
+		reg = <0x7000f010 0x02c
+		       0x7000f1f0 0x010
+		       0x7000f228 0x05c>;
+		nvidia,#asids = <4>;		/* # of ASIDs */
+		dma-window = <0 0x40000000>;	/* IOVA start & length */
+		nvidia,ahb = <&ahb>;
+	};

Documentation/kernel-parameters.txt

@@ -1134,7 +1134,6 @@ 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

arch/ia64/include/asm/iommu.h

@@ -11,12 +11,10 @@ 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

@@ -32,7 +32,6 @@ 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

@@ -5,7 +5,6 @@ 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

@@ -45,15 +45,6 @@ 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). */
@@ -194,8 +185,6 @@ 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/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"
@@ -154,7 +158,7 @@ config TEGRA_IOMMU_GART
 
 config TEGRA_IOMMU_SMMU
 	bool "Tegra SMMU IOMMU Support"
-	depends on ARCH_TEGRA_3x_SOC
+	depends on ARCH_TEGRA_3x_SOC && TEGRA_AHB
 	select IOMMU_API
 	help
 	  Enables support for remapping discontiguous physical memory

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

drivers/iommu/amd_iommu.c

@@ -256,11 +256,21 @@ 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 *pdev = to_pci_dev(dev);
+	struct pci_dev *dma_pdev, *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;
@@ -281,8 +291,43 @@ 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;
 
@@ -311,6 +356,8 @@ 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
@@ -384,7 +431,6 @@ DECLARE_STATS_COUNTER(invalidate_iotlb);
 DECLARE_STATS_COUNTER(invalidate_iotlb_all);
 DECLARE_STATS_COUNTER(pri_requests);
 
-
 static struct dentry *stats_dir;
 static struct dentry *de_fflush;
 
@@ -2073,7 +2119,7 @@ static int pdev_iommuv2_enable(struct pci_dev *pdev)
 /* FIXME: Move this to PCI code */
 #define PCI_PRI_TLP_OFF		(1 << 15)
 
-bool pci_pri_tlp_required(struct pci_dev *pdev)
+static bool pci_pri_tlp_required(struct pci_dev *pdev)
 {
 	u16 status;
 	int pos;
@@ -2254,6 +2300,18 @@ static int device_change_notifier(struct notifier_block *nb,
 
 		iommu_init_device(dev);
 
+		/*
+		 * dev_data is still NULL and
+		 * got initialized in iommu_init_device
+		 */
+		dev_data = get_dev_data(dev);
+
+		if (iommu_pass_through || dev_data->iommu_v2) {
+			dev_data->passthrough = true;
+			attach_device(dev, pt_domain);
+			break;
+		}
+
 		domain = domain_for_device(dev);
 
 		/* allocate a protection domain if a device is added */
@@ -2271,10 +2329,7 @@ static int device_change_notifier(struct notifier_block *nb,
 
 		dev_data = get_dev_data(dev);
 
-		if (!dev_data->passthrough)
-			dev->archdata.dma_ops = &amd_iommu_dma_ops;
-		else
-			dev->archdata.dma_ops = &nommu_dma_ops;
+		dev->archdata.dma_ops = &amd_iommu_dma_ops;
 
 		break;
 	case BUS_NOTIFY_DEL_DEVICE:
@@ -2972,6 +3027,11 @@ int __init amd_iommu_init_dma_ops(void)
 
 	amd_iommu_stats_init();
 
+	if (amd_iommu_unmap_flush)
+		pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n");
+	else
+		pr_info("AMD-Vi: Lazy IO/TLB flushing enabled\n");
+
 	return 0;
 
 free_domains:
@@ -3078,6 +3138,10 @@ static int amd_iommu_domain_init(struct iommu_domain *dom)
 
 	dom->priv = domain;
 
+	dom->geometry.aperture_start = 0;
+	dom->geometry.aperture_end   = ~0ULL;
+	dom->geometry.force_aperture = true;
+
 	return 0;
 
 out_free:
@@ -3236,26 +3300,6 @@ 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,
@@ -3265,7 +3309,6 @@ 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,
 };