Merge branches 'iommu/fixes', 'x86/amd', 'groups', 'arm/tegra' and 'api/domain-attr' into next

Conflicts:
	drivers/iommu/iommu.c
	include/linux/iommu.h

Documentation/ABI/testing/sysfs-kernel-iommu_groups

+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

+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

 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;
 
 		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,
 };
 

drivers/iommu/amd_iommu_types.h

@@ -487,7 +487,7 @@ struct amd_iommu {
 	/* physical address of MMIO space */
 	u64 mmio_phys;
 	/* virtual address of MMIO space */
-	u8 *mmio_base;
+	u8 __iomem *mmio_base;
 
 	/* capabilities of that IOMMU read from ACPI */
 	u32 cap;
@@ -501,6 +501,9 @@ struct amd_iommu {
 	/* IOMMUv2 */
 	bool is_iommu_v2;
 
+	/* PCI device id of the IOMMU device */
+	u16 devid;
+
 	/*
 	 * Capability pointer. There could be more than one IOMMU per PCI
 	 * device function if there are more than one AMD IOMMU capability
@@ -530,8 +533,6 @@ struct amd_iommu {
 	u32 evt_buf_size;
 	/* event buffer virtual address */
 	u8 *evt_buf;
-	/* MSI number for event interrupt */
-	u16 evt_msi_num;
 
 	/* Base of the PPR log, if present */
 	u8 *ppr_log;
@@ -664,6 +665,12 @@ extern bool amd_iommu_force_isolation;
 /* Max levels of glxval supported */
 extern int amd_iommu_max_glx_val;
 
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+extern void iommu_flush_all_caches(struct amd_iommu *iommu);
+
 /* takes bus and device/function and returns the device id
  * FIXME: should that be in generic PCI code? */
 static inline u16 calc_devid(u8 bus, u8 devfn)

drivers/iommu/amd_iommu_v2.c

@@ -81,7 +81,7 @@ struct fault {
 	u16 flags;
 };
 
-struct device_state **state_table;
+static struct device_state **state_table;
 static spinlock_t state_lock;
 
 /* List and lock for all pasid_states */
@@ -681,6 +681,8 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
 
 	atomic_set(&pasid_state->count, 1);
 	init_waitqueue_head(&pasid_state->wq);
+	spin_lock_init(&pasid_state->lock);
+
 	pasid_state->task         = task;
 	pasid_state->mm           = get_task_mm(task);
 	pasid_state->device_state = dev_state;

drivers/iommu/exynos-iommu.c

@@ -732,6 +732,10 @@ static int exynos_iommu_domain_init(struct iommu_domain *domain)
 	spin_lock_init(&priv->pgtablelock);
 	INIT_LIST_HEAD(&priv->clients);
 
+	dom->geometry.aperture_start = 0;
+	dom->geometry.aperture_end   = ~0UL;
+	dom->geometry.force_aperture = true;
+
 	domain->priv = priv;
 	return 0;
 

drivers/iommu/intel-iommu.c

@@ -3932,6 +3932,10 @@ static int intel_iommu_domain_init(struct iommu_domain *domain)
 	domain_update_iommu_cap(dmar_domain);
 	domain->priv = dmar_domain;
 
+	domain->geometry.aperture_start = 0;
+	domain->geometry.aperture_end   = __DOMAIN_MAX_ADDR(dmar_domain->gaw);
+	domain->geometry.force_aperture = true;
+
 	return 0;
 }
 
@@ -4090,52 +4094,70 @@ 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)
+static void swap_pci_ref(struct pci_dev **from, struct pci_dev *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;
+	pci_dev_put(*from);
+	*from = to;
+}
 
-	if (iommu_no_mapping(dev))
-		return -ENODEV;
+#define REQ_ACS_FLAGS	(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
 
-	id.pci.segment = pci_domain_nr(pdev->bus);
-	id.pci.bus = pdev->bus->number;
-	id.pci.devfn = pdev->devfn;
+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;
 
-	if (!device_to_iommu(id.pci.segment, id.pci.bus, id.pci.devfn))
+	if (!device_to_iommu(pci_domain_nr(pdev->bus),
+			     pdev->bus->number, pdev->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 (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 (!pdev->is_virtfn && iommu_group_mf)
-		id.pci.devfn = PCI_DEVFN(PCI_SLOT(id.pci.devfn), 0);
+	ret = iommu_group_add_device(group, dev);
 
-	*groupid = id.group;
+	iommu_group_put(group);
+	return ret;
+}
 
-	return 0;
+static void intel_iommu_remove_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
 }
 
 static struct iommu_ops intel_iommu_ops = {
@@ -4147,7 +4169,8 @@ 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,
+	.add_device	= intel_iommu_add_device,
+	.remove_device	= intel_iommu_remove_device,
 	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
 };
 

drivers/iommu/irq_remapping.c

 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/cpumask.h>
 #include <linux/errno.h>
+#include <linux/msi.h>
+
+#include <asm/hw_irq.h>
+#include <asm/irq_remapping.h>
 
 #include "irq_remapping.h"
 

drivers/iommu/msm_iommu.c

@@ -226,6 +226,11 @@ static int msm_iommu_domain_init(struct iommu_domain *domain)
 
 	memset(priv->pgtable, 0, SZ_16K);
 	domain->priv = priv;
+
+	domain->geometry.aperture_start = 0;
+	domain->geometry.aperture_end   = (1ULL << 32) - 1;
+	domain->geometry.force_aperture = true;
+
 	return 0;
 
 fail_nomem:

drivers/iommu/of_iommu.c

+/*
+ * OF helpers for IOMMU
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <linux/export.h>
+#include <linux/limits.h>
+#include <linux/of.h>
+
+/**
+ * of_get_dma_window - Parse *dma-window property and returns 0 if found.
+ *
+ * @dn: device node
+ * @prefix: prefix for property name if any
+ * @index: index to start to parse
+ * @busno: Returns busno if supported. Otherwise pass NULL
+ * @addr: Returns address that DMA starts
+ * @size: Returns the range that DMA can handle
+ *
+ * This supports different formats flexibly. "prefix" can be
+ * configured if any. "busno" and "index" are optionally
+ * specified. Set 0(or NULL) if not used.
+ */
+int of_get_dma_window(struct device_node *dn, const char *prefix, int index,
+		      unsigned long *busno, dma_addr_t *addr, size_t *size)
+{
+	const __be32 *dma_window, *end;
+	int bytes, cur_index = 0;
+	char propname[NAME_MAX], addrname[NAME_MAX], sizename[NAME_MAX];
+
+	if (!dn || !addr || !size)
+		return -EINVAL;
+
+	if (!prefix)
+		prefix = "";
+
+	snprintf(propname, sizeof(propname), "%sdma-window", prefix);
+	snprintf(addrname, sizeof(addrname), "%s#dma-address-cells", prefix);
+	snprintf(sizename, sizeof(sizename), "%s#dma-size-cells", prefix);
+
+	dma_window = of_get_property(dn, propname, &bytes);
+	if (!dma_window)
+		return -ENODEV;
+	end = dma_window + bytes / sizeof(*dma_window);
+
+	while (dma_window < end) {
+		u32 cells;
+		const void *prop;
+
+		/* busno is one cell if supported */
+		if (busno)
+			*busno = be32_to_cpup(dma_window++);
+
+		prop = of_get_property(dn, addrname, NULL);
+		if (!prop)
+			prop = of_get_property(dn, "#address-cells", NULL);
+
+		cells = prop ? be32_to_cpup(prop) : of_n_addr_cells(dn);
+		if (!cells)
+			return -EINVAL;
+		*addr = of_read_number(dma_window, cells);
+		dma_window += cells;
+
+		prop = of_get_property(dn, sizename, NULL);
+		cells = prop ? be32_to_cpup(prop) : of_n_size_cells(dn);
+		if (!cells)
+			return -EINVAL;
+		*size = of_read_number(dma_window, cells);
+		dma_window += cells;
+
+		if (cur_index++ == index)
+			break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_get_dma_window);

drivers/iommu/omap-iommu.c

@@ -1148,6 +1148,10 @@ static int omap_iommu_domain_init(struct iommu_domain *domain)
 
 	domain->priv = omap_domain;
 
+	domain->geometry.aperture_start = 0;
+	domain->geometry.aperture_end   = (1ULL << 32) - 1;
+	domain->geometry.force_aperture = true;
+
 	return 0;
 
 fail_nomem:

drivers/iommu/tegra-gart.c

@@ -165,6 +165,11 @@ static int gart_iommu_attach_dev(struct iommu_domain *domain,
 		return -EINVAL;
 	domain->priv = gart;
 
+	domain->geometry.aperture_start = gart->iovmm_base;
+	domain->geometry.aperture_end   = gart->iovmm_base +
+					gart->page_count * GART_PAGE_SIZE - 1;
+	domain->geometry.force_aperture = true;
+
 	client = devm_kzalloc(gart->dev, sizeof(*c), GFP_KERNEL);
 	if (!client)
 		return -ENOMEM;

drivers/pci/access.c

@@ -162,7 +162,8 @@ int pci_user_read_config_##size						\
 	if (ret > 0)							\
 		ret = -EINVAL;						\
 	return ret;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(pci_user_read_config_##size);
 
 /* Returns 0 on success, negative values indicate error. */
 #define PCI_USER_WRITE_CONFIG(size,type)				\
@@ -181,7 +182,8 @@ int pci_user_write_config_##size					\
 	if (ret > 0)							\
 		ret = -EINVAL;						\
 	return ret;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(pci_user_write_config_##size);
 
 PCI_USER_READ_CONFIG(byte, u8)
 PCI_USER_READ_CONFIG(word, u16)

drivers/pci/pci.c

@@ -2359,6 +2359,75 @@ void pci_enable_acs(struct pci_dev *dev)
 	pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
 }
 
+/**
+ * pci_acs_enabled - test ACS against required flags for a given device
+ * @pdev: device to test
+ * @acs_flags: required PCI ACS flags
+ *
+ * Return true if the device supports the provided flags.  Automatically
+ * filters out flags that are not implemented on multifunction devices.
+ */
+bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
+{
+	int pos, ret;
+	u16 ctrl;
+
+	ret = pci_dev_specific_acs_enabled(pdev, acs_flags);
+	if (ret >= 0)
+		return ret > 0;
+
+	if (!pci_is_pcie(pdev))
+		return false;
+
+	/* Filter out flags not applicable to multifunction */
+	if (pdev->multifunction)
+		acs_flags &= (PCI_ACS_RR | PCI_ACS_CR |
+			      PCI_ACS_EC | PCI_ACS_DT);
+
+	if (pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM ||
+	    pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT ||
+	    pdev->multifunction) {
+		pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS);
+		if (!pos)
+			return false;
+
+		pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl);
+		if ((ctrl & acs_flags) != acs_flags)
+			return false;
+	}
+
+	return true;
+}
+
+/**
+ * pci_acs_path_enable - test ACS flags from start to end in a hierarchy
+ * @start: starting downstream device
+ * @end: ending upstream device or NULL to search to the root bus
+ * @acs_flags: required flags
+ *
+ * Walk up a device tree from start to end testing PCI ACS support.  If
+ * any step along the way does not support the required flags, return false.
+ */
+bool pci_acs_path_enabled(struct pci_dev *start,
+			  struct pci_dev *end, u16 acs_flags)
+{
+	struct pci_dev *pdev, *parent = start;
+
+	do {
+		pdev = parent;
+
+		if (!pci_acs_enabled(pdev, acs_flags))
+			return false;
+
+		if (pci_is_root_bus(pdev->bus))
+			return (end == NULL);
+
+		parent = pdev->bus->self;
+	} while (pdev != end);
+
+	return true;
+}
+
 /**
  * pci_swizzle_interrupt_pin - swizzle INTx for device behind bridge
  * @dev: the PCI device

drivers/pci/pci.h

@@ -86,13 +86,6 @@ static inline bool pci_is_bridge(struct pci_dev *pci_dev)
 	return !!(pci_dev->subordinate);
 }
 
-extern int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val);
-extern int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val);
-extern int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val);
-extern int pci_user_write_config_byte(struct pci_dev *dev, int where, u8 val);
-extern int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val);
-extern int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val);
-
 struct pci_vpd_ops {
 	ssize_t (*read)(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
 	ssize_t (*write)(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);

drivers/pci/quirks.c

@@ -3179,3 +3179,87 @@ int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 
 	return -ENOTTY;
 }
+
+static struct pci_dev *pci_func_0_dma_source(struct pci_dev *dev)
+{
+	if (!PCI_FUNC(dev->devfn))
+		return pci_dev_get(dev);
+
+	return pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+}
+
+static const struct pci_dev_dma_source {
+	u16 vendor;
+	u16 device;
+	struct pci_dev *(*dma_source)(struct pci_dev *dev);
+} pci_dev_dma_source[] = {
+	/*
+	 * https://bugzilla.redhat.com/show_bug.cgi?id=605888
+	 *
+	 * Some Ricoh devices use the function 0 source ID for DMA on
+	 * other functions of a multifunction device.  The DMA devices
+	 * is therefore function 0, which will have implications of the
+	 * iommu grouping of these devices.
+	 */
+	{ PCI_VENDOR_ID_RICOH, 0xe822, pci_func_0_dma_source },
+	{ PCI_VENDOR_ID_RICOH, 0xe230, pci_func_0_dma_source },
+	{ PCI_VENDOR_ID_RICOH, 0xe832, pci_func_0_dma_source },
+	{ PCI_VENDOR_ID_RICOH, 0xe476, pci_func_0_dma_source },
+	{ 0 }
+};
+
+/*
+ * IOMMUs with isolation capabilities need to be programmed with the
+ * correct source ID of a device.  In most cases, the source ID matches
+ * the device doing the DMA, but sometimes hardware is broken and will
+ * tag the DMA as being sourced from a different device.  This function
+ * allows that translation.  Note that the reference count of the
+ * returned device is incremented on all paths.
+ */
+struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
+{
+	const struct pci_dev_dma_source *i;
+
+	for (i = pci_dev_dma_source; i->dma_source; i++) {
+		if ((i->vendor == dev->vendor ||
+		     i->vendor == (u16)PCI_ANY_ID) &&
+		    (i->device == dev->device ||
+		     i->device == (u16)PCI_ANY_ID))
+			return i->dma_source(dev);
+	}
+
+	return pci_dev_get(dev);
+}
+
+static const struct pci_dev_acs_enabled {
+	u16 vendor;
+	u16 device;
+	int (*acs_enabled)(struct pci_dev *dev, u16 acs_flags);
+} pci_dev_acs_enabled[] = {
+	{ 0 }
+};
+
+int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags)
+{
+	const struct pci_dev_acs_enabled *i;
+	int ret;
+
+	/*
+	 * Allow devices that do not expose standard PCIe ACS capabilities
+	 * or control to indicate their support here.  Multi-function express
+	 * devices which do not allow internal peer-to-peer between functions,
+	 * but do not implement PCIe ACS may wish to return true here.
+	 */
+	for (i = pci_dev_acs_enabled; i->acs_enabled; i++) {
+		if ((i->vendor == dev->vendor ||
+		     i->vendor == (u16)PCI_ANY_ID) &&
+		    (i->device == dev->device ||
+		     i->device == (u16)PCI_ANY_ID)) {
+			ret = i->acs_enabled(dev, acs_flags);
+			if (ret >= 0)
+				return ret;
+		}
+	}
+
+	return -ENOTTY;
+}

drivers/xen/xen-pciback/conf_space.c

@@ -124,7 +124,7 @@ static inline u32 merge_value(u32 val, u32 new_val, u32 new_val_mask,
 	return val;
 }
 
-static int pcibios_err_to_errno(int err)
+static int xen_pcibios_err_to_errno(int err)
 {
 	switch (err) {
 	case PCIBIOS_SUCCESSFUL:
@@ -202,7 +202,7 @@ int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
 		       pci_name(dev), size, offset, value);
 
 	*ret_val = value;
-	return pcibios_err_to_errno(err);
+	return xen_pcibios_err_to_errno(err);
 }
 
 int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
@@ -290,7 +290,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 		}
 	}
 
-	return pcibios_err_to_errno(err);
+	return xen_pcibios_err_to_errno(err);
 }
 
 void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev)

include/linux/device.h

@@ -36,6 +36,7 @@ struct subsys_private;
 struct bus_type;
 struct device_node;
 struct iommu_ops;
+struct iommu_group;
 
 struct bus_attribute {
 	struct attribute	attr;
@@ -687,6 +688,7 @@ struct device {
 	const struct attribute_group **groups;	/* optional groups */
 
 	void	(*release)(struct device *dev);
+	struct iommu_group	*iommu_group;
 };
 
 /* Get the wakeup routines, which depend on struct device */

include/linux/iommu.h

@@ -26,6 +26,7 @@
 #define IOMMU_CACHE	(4) /* DMA cache coherency */
 
 struct iommu_ops;
+struct iommu_group;
 struct bus_type;
 struct device;
 struct iommu_domain;
@@ -37,16 +38,28 @@ struct iommu_domain;
 typedef int (*iommu_fault_handler_t)(struct iommu_domain *,
 			struct device *, unsigned long, int, void *);
 
+struct iommu_domain_geometry {
+	dma_addr_t aperture_start; /* First address that can be mapped    */
+	dma_addr_t aperture_end;   /* Last address that can be mapped     */
+	bool force_aperture;       /* DMA only allowed in mappable range? */
+};
+
 struct iommu_domain {
 	struct iommu_ops *ops;
 	void *priv;
 	iommu_fault_handler_t handler;
 	void *handler_token;
+	struct iommu_domain_geometry geometry;
 };
 
 #define IOMMU_CAP_CACHE_COHERENCY	0x1
 #define IOMMU_CAP_INTR_REMAP		0x2	/* isolates device intrs */
 
+enum iommu_attr {
+	DOMAIN_ATTR_MAX,
+	DOMAIN_ATTR_GEOMETRY,
+};
+
 #ifdef CONFIG_IOMMU_API
 
 /**
@@ -59,7 +72,10 @@ struct iommu_domain {
  * @unmap: unmap a physically contiguous memory region from an iommu domain
  * @iova_to_phys: translate iova to physical address
  * @domain_has_cap: domain capabilities query
- * @commit: commit iommu domain
+ * @add_device: add device to iommu grouping
+ * @remove_device: remove device from iommu grouping
+ * @domain_get_attr: Query domain attributes
+ * @domain_set_attr: Change domain attributes
  * @pgsize_bitmap: bitmap of supported page sizes
  */
 struct iommu_ops {
@@ -75,10 +91,23 @@ struct iommu_ops {
 				    unsigned long iova);
 	int (*domain_has_cap)(struct iommu_domain *domain,
 			      unsigned long cap);
+	int (*add_device)(struct device *dev);
+	void (*remove_device)(struct device *dev);
 	int (*device_group)(struct device *dev, unsigned int *groupid);
+	int (*domain_get_attr)(struct iommu_domain *domain,
+			       enum iommu_attr attr, void *data);
+	int (*domain_set_attr)(struct iommu_domain *domain,
+			       enum iommu_attr attr, void *data);
 	unsigned long pgsize_bitmap;
 };
 
+#define IOMMU_GROUP_NOTIFY_ADD_DEVICE		1 /* Device added */
+#define IOMMU_GROUP_NOTIFY_DEL_DEVICE		2 /* Pre Device removed */
+#define IOMMU_GROUP_NOTIFY_BIND_DRIVER		3 /* Pre Driver bind */
+#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER		4 /* Post Driver bind */
+#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER	5 /* Pre Driver unbind */
+#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER	6 /* Post Driver unbind */
+
 extern int bus_set_iommu(struct bus_type *bus, struct iommu_ops *ops);
 extern bool iommu_present(struct bus_type *bus);
 extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus);
@@ -97,7 +126,34 @@ extern int iommu_domain_has_cap(struct iommu_domain *domain,
 				unsigned long cap);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
-extern int iommu_device_group(struct device *dev, unsigned int *groupid);
+
+extern int iommu_attach_group(struct iommu_domain *domain,
+			      struct iommu_group *group);
+extern void iommu_detach_group(struct iommu_domain *domain,
+			       struct iommu_group *group);
+extern struct iommu_group *iommu_group_alloc(void);
+extern void *iommu_group_get_iommudata(struct iommu_group *group);
+extern void iommu_group_set_iommudata(struct iommu_group *group,
+				      void *iommu_data,
+				      void (*release)(void *iommu_data));
+extern int iommu_group_set_name(struct iommu_group *group, const char *name);
+extern int iommu_group_add_device(struct iommu_group *group,
+				  struct device *dev);
+extern void iommu_group_remove_device(struct device *dev);
+extern int iommu_group_for_each_dev(struct iommu_group *group, void *data,
+				    int (*fn)(struct device *, void *));
+extern struct iommu_group *iommu_group_get(struct device *dev);
+extern void iommu_group_put(struct iommu_group *group);
+extern int iommu_group_register_notifier(struct iommu_group *group,
+					 struct notifier_block *nb);
+extern int iommu_group_unregister_notifier(struct iommu_group *group,
+					   struct notifier_block *nb);
+extern int iommu_group_id(struct iommu_group *group);
+
+extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr,
+				 void *data);
+extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
+				 void *data);
 
 /**
  * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
@@ -142,6 +198,7 @@ static inline int report_iommu_fault(struct iommu_domain *domain,
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
+struct iommu_group {};
 
 static inline bool iommu_present(struct bus_type *bus)
 {
@@ -197,11 +254,88 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain,
 {
 }
 
-static inline int iommu_device_group(struct device *dev, unsigned int *groupid)
+int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
 {
 	return -ENODEV;
 }
 
+void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
+{
+}
+
+struct iommu_group *iommu_group_alloc(void)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+void *iommu_group_get_iommudata(struct iommu_group *group)
+{
+	return NULL;
+}
+
+void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data,
+			       void (*release)(void *iommu_data))
+{
+}
+
+int iommu_group_set_name(struct iommu_group *group, const char *name)
+{
+	return -ENODEV;
+}
+
+int iommu_group_add_device(struct iommu_group *group, struct device *dev)
+{
+	return -ENODEV;
+}
+
+void iommu_group_remove_device(struct device *dev)
+{
+}
+
+int iommu_group_for_each_dev(struct iommu_group *group, void *data,
+			     int (*fn)(struct device *, void *))
+{
+	return -ENODEV;
+}
+
+struct iommu_group *iommu_group_get(struct device *dev)
+{
+	return NULL;
+}
+
+void iommu_group_put(struct iommu_group *group)
+{
+}
+
+int iommu_group_register_notifier(struct iommu_group *group,
+				  struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+
+int iommu_group_unregister_notifier(struct iommu_group *group,
+				    struct notifier_block *nb)
+{
+	return 0;
+}
+
+int iommu_group_id(struct iommu_group *group)
+{
+	return -ENODEV;
+}
+
+static inline int iommu_domain_get_attr(struct iommu_domain *domain,
+					enum iommu_attr attr, void *data)
+{
+	return -EINVAL;
+}
+
+static inline int iommu_domain_set_attr(struct iommu_domain *domain,
+					enum iommu_attr attr, void *data)
+{
+	return -EINVAL;
+}
+
 #endif /* CONFIG_IOMMU_API */
 
 #endif /* __LINUX_IOMMU_H */

include/linux/of_iommu.h

+#ifndef __OF_IOMMU_H
+#define __OF_IOMMU_H
+
+#ifdef CONFIG_OF_IOMMU
+
+extern int of_get_dma_window(struct device_node *dn, const char *prefix,
+			     int index, unsigned long *busno, dma_addr_t *addr,
+			     size_t *size);
+
+#else
+
+static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
+			    int index, unsigned long *busno, dma_addr_t *addr,
+			    size_t *size)
+{
+	return -EINVAL;
+}
+
+#endif	/* CONFIG_OF_IOMMU */
+
+#endif /* __OF_IOMMU_H */

include/linux/pci.h

@@ -474,6 +474,32 @@ static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false;
 #define PCIBIOS_SET_FAILED		0x88
 #define PCIBIOS_BUFFER_TOO_SMALL	0x89
 
+/*
+ * Translate above to generic errno for passing back through non-pci.
+ */
+static inline int pcibios_err_to_errno(int err)
+{
+	if (err <= PCIBIOS_SUCCESSFUL)
+		return err; /* Assume already errno */
+
+	switch (err) {
+	case PCIBIOS_FUNC_NOT_SUPPORTED:
+		return -ENOENT;
+	case PCIBIOS_BAD_VENDOR_ID:
+		return -EINVAL;
+	case PCIBIOS_DEVICE_NOT_FOUND:
+		return -ENODEV;
+	case PCIBIOS_BAD_REGISTER_NUMBER:
+		return -EFAULT;
+	case PCIBIOS_SET_FAILED:
+		return -EIO;
+	case PCIBIOS_BUFFER_TOO_SMALL:
+		return -ENOSPC;
+	}
+
+	return -ENOTTY;
+}
+
 /* Low-level architecture-dependent routines */
 
 struct pci_ops {
@@ -777,6 +803,14 @@ static inline int pci_write_config_dword(const struct pci_dev *dev, int where,
 	return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
 }
 
+/* user-space driven config access */
+int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val);
+int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val);
+int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val);
+int pci_user_write_config_byte(struct pci_dev *dev, int where, u8 val);
+int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val);
+int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val);
+
 int __must_check pci_enable_device(struct pci_dev *dev);
 int __must_check pci_enable_device_io(struct pci_dev *dev);
 int __must_check pci_enable_device_mem(struct pci_dev *dev);
@@ -1332,6 +1366,9 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus,
 static inline int pci_domain_nr(struct pci_bus *bus)
 { return 0; }
 
+static inline struct pci_dev *pci_dev_get(struct pci_dev *dev)
+{ return NULL; }
+
 #define dev_is_pci(d) (false)
 #define dev_is_pf(d) (false)
 #define dev_num_vf(d) (0)
@@ -1486,9 +1523,20 @@ enum pci_fixup_pass {
 
 #ifdef CONFIG_PCI_QUIRKS
 void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
+struct pci_dev *pci_get_dma_source(struct pci_dev *dev);
+int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
 #else
 static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) {}
+static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
+{
+	return pci_dev_get(dev);
+}
+static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
+					       u16 acs_flags)
+{
+	return -ENOTTY;
+}
 #endif
 
 void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);
@@ -1591,7 +1639,9 @@ static inline bool pci_is_pcie(struct pci_dev *dev)
 }
 
 void pci_request_acs(void);
-
+bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags);
+bool pci_acs_path_enabled(struct pci_dev *start,
+			  struct pci_dev *end, u16 acs_flags);
 
 #define PCI_VPD_LRDT			0x80	/* Large Resource Data Type */
 #define PCI_VPD_LRDT_ID(x)		(x | PCI_VPD_LRDT)