Merge branch 'core' into x86/vt-d

Conflicts:
	drivers/iommu/intel-iommu.c

Documentation/ABI/testing/sysfs-class-iommu

@@ -0,0 +1,17 @@
+What:		/sys/class/iommu/<iommu>/devices/
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:
+		IOMMU drivers are able to link devices managed by a
+		given IOMMU here to allow association of IOMMU to
+		device.
+
+What:		/sys/devices/.../iommu
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:
+		IOMMU drivers are able to link the IOMMU for a
+		given device here to allow association of device to
+		IOMMU.

Documentation/ABI/testing/sysfs-class-iommu-amd-iommu

@@ -0,0 +1,14 @@
+What:		/sys/class/iommu/<iommu>/amd-iommu/cap
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:
+		IOMMU capability header as documented in the AMD IOMMU
+		specification.  Format: %x
+
+What:		/sys/class/iommu/<iommu>/amd-iommu/features
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:
+		Extended features of the IOMMU.  Format: %llx

Documentation/ABI/testing/sysfs-class-iommu-intel-iommu

@@ -0,0 +1,32 @@
+What:		/sys/class/iommu/<iommu>/intel-iommu/address
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:
+		Physical address of the VT-d DRHD for this IOMMU.
+		Format: %llx.  This allows association of a sysfs
+		intel-iommu with a DMAR DRHD table entry.
+
+What:		/sys/class/iommu/<iommu>/intel-iommu/cap
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:
+		The cached hardware capability register value
+		of this DRHD unit.  Format: %llx.
+
+What:		/sys/class/iommu/<iommu>/intel-iommu/ecap
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:
+		The cached hardware extended capability register
+		value of this DRHD unit.  Format: %llx.
+
+What:		/sys/class/iommu/<iommu>/intel-iommu/version
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <alex.williamson@redhat.com>
+Description:
+		The architecture version as reported from the
+		VT-d VER_REG.  Format: %d:%d, major:minor

drivers/iommu/Makefile

@@ -1,5 +1,6 @@
 obj-$(CONFIG_IOMMU_API) += iommu.o
 obj-$(CONFIG_IOMMU_API) += iommu-traces.o
+obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o
 obj-$(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

drivers/iommu/amd_iommu.c

@@ -46,7 +46,6 @@
 #include "amd_iommu_proto.h"
 #include "amd_iommu_types.h"
 #include "irq_remapping.h"
-#include "pci.h"
 
 #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
 
@@ -81,7 +80,7 @@ LIST_HEAD(hpet_map);
  */
 static struct protection_domain *pt_domain;
 
-static struct iommu_ops amd_iommu_ops;
+static const struct iommu_ops amd_iommu_ops;
 
 static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
 int amd_iommu_max_glx_val = -1;
@@ -133,9 +132,6 @@ static void free_dev_data(struct iommu_dev_data *dev_data)
 	list_del(&dev_data->dev_data_list);
 	spin_unlock_irqrestore(&dev_data_list_lock, flags);
 
-	if (dev_data->group)
-		iommu_group_put(dev_data->group);
-
 	kfree(dev_data);
 }
 
@@ -264,167 +260,79 @@ static bool check_device(struct device *dev)
 	return true;
 }
 
-static struct pci_bus *find_hosted_bus(struct pci_bus *bus)
-{
-	while (!bus->self) {
-		if (!pci_is_root_bus(bus))
-			bus = bus->parent;
-		else
-			return ERR_PTR(-ENODEV);
-	}
-
-	return bus;
-}
-
-#define REQ_ACS_FLAGS	(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
-
-static struct pci_dev *get_isolation_root(struct pci_dev *pdev)
-{
-	struct pci_dev *dma_pdev = pdev;
-
-	/* Account for quirked devices */
-	swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev));
-
-	/*
-	 * If it's a multifunction device that does not support our
-	 * required ACS flags, add to the same group as lowest numbered
-	 * function that also does not suport the required ACS flags.
-	 */
-	if (dma_pdev->multifunction &&
-	    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) {
-		u8 i, slot = PCI_SLOT(dma_pdev->devfn);
-
-		for (i = 0; i < 8; i++) {
-			struct pci_dev *tmp;
-
-			tmp = pci_get_slot(dma_pdev->bus, PCI_DEVFN(slot, i));
-			if (!tmp)
-				continue;
-
-			if (!pci_acs_enabled(tmp, REQ_ACS_FLAGS)) {
-				swap_pci_ref(&dma_pdev, tmp);
-				break;
-			}
-			pci_dev_put(tmp);
-		}
-	}
-
-	/*
-	 * Devices on the root bus go through the iommu.  If that's not us,
-	 * find the next upstream device and test ACS up to the root bus.
-	 * Finding the next device may require skipping virtual buses.
-	 */
-	while (!pci_is_root_bus(dma_pdev->bus)) {
-		struct pci_bus *bus = find_hosted_bus(dma_pdev->bus);
-		if (IS_ERR(bus))
-			break;
-
-		if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS))
-			break;
-
-		swap_pci_ref(&dma_pdev, pci_dev_get(bus->self));
-	}
-
-	return dma_pdev;
-}
-
-static int use_pdev_iommu_group(struct pci_dev *pdev, struct device *dev)
+static int init_iommu_group(struct device *dev)
 {
-	struct iommu_group *group = iommu_group_get(&pdev->dev);
-	int ret;
+	struct iommu_group *group;
 
-	if (!group) {
-		group = iommu_group_alloc();
-		if (IS_ERR(group))
-			return PTR_ERR(group);
+	group = iommu_group_get_for_dev(dev);
 
-		WARN_ON(&pdev->dev != dev);
-	}
+	if (IS_ERR(group))
+		return PTR_ERR(group);
 
-	ret = iommu_group_add_device(group, dev);
 	iommu_group_put(group);
-	return ret;
+	return 0;
 }
 
-static int use_dev_data_iommu_group(struct iommu_dev_data *dev_data,
-				    struct device *dev)
+static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
 {
-	if (!dev_data->group) {
-		struct iommu_group *group = iommu_group_alloc();
-		if (IS_ERR(group))
-			return PTR_ERR(group);
-
-		dev_data->group = group;
-	}
-
-	return iommu_group_add_device(dev_data->group, dev);
+	*(u16 *)data = alias;
+	return 0;
 }
 
-static int init_iommu_group(struct device *dev)
+static u16 get_alias(struct device *dev)
 {
-	struct iommu_dev_data *dev_data;
-	struct iommu_group *group;
-	struct pci_dev *dma_pdev;
-	int ret;
-
-	group = iommu_group_get(dev);
-	if (group) {
-		iommu_group_put(group);
-		return 0;
-	}
-
-	dev_data = find_dev_data(get_device_id(dev));
-	if (!dev_data)
-		return -ENOMEM;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	u16 devid, ivrs_alias, pci_alias;
 
-	if (dev_data->alias_data) {
-		u16 alias;
-		struct pci_bus *bus;
+	devid = get_device_id(dev);
+	ivrs_alias = amd_iommu_alias_table[devid];
+	pci_for_each_dma_alias(pdev, __last_alias, &pci_alias);
 
-		if (dev_data->alias_data->group)
-			goto use_group;
+	if (ivrs_alias == pci_alias)
+		return ivrs_alias;
 
-		/*
-		 * If the alias device exists, it's effectively just a first
-		 * level quirk for finding the DMA source.
-		 */
-		alias = amd_iommu_alias_table[dev_data->devid];
-		dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff);
-		if (dma_pdev) {
-			dma_pdev = get_isolation_root(dma_pdev);
-			goto use_pdev;
+	/*
+	 * DMA alias showdown
+	 *
+	 * The IVRS is fairly reliable in telling us about aliases, but it
+	 * can't know about every screwy device.  If we don't have an IVRS
+	 * reported alias, use the PCI reported alias.  In that case we may
+	 * still need to initialize the rlookup and dev_table entries if the
+	 * alias is to a non-existent device.
+	 */
+	if (ivrs_alias == devid) {
+		if (!amd_iommu_rlookup_table[pci_alias]) {
+			amd_iommu_rlookup_table[pci_alias] =
+				amd_iommu_rlookup_table[devid];
+			memcpy(amd_iommu_dev_table[pci_alias].data,
+			       amd_iommu_dev_table[devid].data,
+			       sizeof(amd_iommu_dev_table[pci_alias].data));
 		}
 
-		/*
-		 * If the alias is virtual, try to find a parent device
-		 * and test whether the IOMMU group is actualy rooted above
-		 * the alias.  Be careful to also test the parent device if
-		 * we think the alias is the root of the group.
-		 */
-		bus = pci_find_bus(0, alias >> 8);
-		if (!bus)
-			goto use_group;
-
-		bus = find_hosted_bus(bus);
-		if (IS_ERR(bus) || !bus->self)
-			goto use_group;
+		return pci_alias;
+	}
 
-		dma_pdev = get_isolation_root(pci_dev_get(bus->self));
-		if (dma_pdev != bus->self || (dma_pdev->multifunction &&
-		    !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)))
-			goto use_pdev;
+	pr_info("AMD-Vi: Using IVRS reported alias %02x:%02x.%d "
+		"for device %s[%04x:%04x], kernel reported alias "
+		"%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias),
+		PCI_FUNC(ivrs_alias), dev_name(dev), pdev->vendor, pdev->device,
+		PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias),
+		PCI_FUNC(pci_alias));
 
-		pci_dev_put(dma_pdev);
-		goto use_group;
+	/*
+	 * If we don't have a PCI DMA alias and the IVRS alias is on the same
+	 * bus, then the IVRS table may know about a quirk that we don't.
+	 */
+	if (pci_alias == devid &&
+	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
+		pdev->dev_flags |= PCI_DEV_FLAGS_DMA_ALIAS_DEVFN;
+		pdev->dma_alias_devfn = ivrs_alias & 0xff;
+		pr_info("AMD-Vi: Added PCI DMA alias %02x.%d for %s\n",
+			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias),
+			dev_name(dev));
 	}
 
-	dma_pdev = get_isolation_root(pci_dev_get(to_pci_dev(dev)));
-use_pdev:
-	ret = use_pdev_iommu_group(dma_pdev, dev);
-	pci_dev_put(dma_pdev);
-	return ret;
-use_group:
-	return use_dev_data_iommu_group(dev_data->alias_data, dev);
+	return ivrs_alias;
 }
 
 static int iommu_init_device(struct device *dev)
@@ -441,7 +349,8 @@ static int iommu_init_device(struct device *dev)
 	if (!dev_data)
 		return -ENOMEM;
 
-	alias = amd_iommu_alias_table[dev_data->devid];
+	alias = get_alias(dev);
+
 	if (alias != dev_data->devid) {
 		struct iommu_dev_data *alias_data;
 
@@ -470,6 +379,9 @@ static int iommu_init_device(struct device *dev)
 
 	dev->archdata.iommu = dev_data;
 
+	iommu_device_link(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
+			  dev);
+
 	return 0;
 }
 
@@ -489,12 +401,22 @@ static void iommu_ignore_device(struct device *dev)
 
 static void iommu_uninit_device(struct device *dev)
 {
+	struct iommu_dev_data *dev_data = search_dev_data(get_device_id(dev));
+
+	if (!dev_data)
+		return;
+
+	iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
+			    dev);
+
 	iommu_group_remove_device(dev);
 
+	/* Unlink from alias, it may change if another device is re-plugged */
+	dev_data->alias_data = NULL;
+
 	/*
-	 * 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
-	 * introduce a ton of races.
+	 * We keep dev_data around for unplugged devices and reuse it when the
+	 * device is re-plugged - not doing so would introduce a ton of races.
 	 */
 }
 
@@ -3473,7 +3395,7 @@ static int amd_iommu_domain_has_cap(struct iommu_domain *domain,
 	return 0;
 }
 
-static struct iommu_ops amd_iommu_ops = {
+static const struct iommu_ops amd_iommu_ops = {
 	.domain_init = amd_iommu_domain_init,
 	.domain_destroy = amd_iommu_domain_destroy,
 	.attach_dev = amd_iommu_attach_device,