Merge branch 'pci/host-vmd'

- Save VMD's pci_dev in x86 struct pci_sysdata (Jon Derrick)

  - Add pci_real_dma_dev() for DMA aliases not on the same bus as requester
    (Jon Derrick)

  - Add IOMMU mappings for pci_real_dma_dev() (Jon Derrick)

  - Remove IOMMU sanity checks for VMD devices (Jon Derrick)

  - Remove VMD dma_map_ops overrides (Jon Derrick)

  - Remove unused X86_DEV_DMA_OPS (Christoph Hellwig)

  - Add VMD device IDs that need bus restriction mode (Sushma Kalakota)

* pci/host-vmd:
  PCI: vmd: Add two VMD Device IDs
  x86/PCI: Remove X86_DEV_DMA_OPS
  PCI: vmd: Remove dma_map_ops overrides
  iommu/vt-d: Remove VMD child device sanity check
  iommu/vt-d: Use pci_real_dma_dev() for mapping
  PCI: Introduce pci_real_dma_dev()
  x86/PCI: Expose VMD's pci_dev in struct pci_sysdata
  x86/PCI: Add to_pci_sysdata() helper

arch/x86/Kconfig

@@ -2955,9 +2955,6 @@ config HAVE_ATOMIC_IOMAP
 	def_bool y
 	depends on X86_32
 
-config X86_DEV_DMA_OPS
-	bool
-
 source "drivers/firmware/Kconfig"
 
 source "arch/x86/kvm/Kconfig"

arch/x86/include/asm/device.h

@@ -8,16 +8,6 @@ struct dev_archdata {
 #endif
 };
 
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-struct dma_domain {
-	struct list_head node;
-	const struct dma_map_ops *dma_ops;
-	int domain_nr;
-};
-void add_dma_domain(struct dma_domain *domain);
-void del_dma_domain(struct dma_domain *domain);
-#endif
-
 struct pdev_archdata {
 };
 

arch/x86/include/asm/pci.h

@@ -25,7 +25,7 @@ struct pci_sysdata {
 	void		*fwnode;	/* IRQ domain for MSI assignment */
 #endif
 #if IS_ENABLED(CONFIG_VMD)
-	bool vmd_domain;		/* True if in Intel VMD domain */
+	struct pci_dev	*vmd_dev;	/* VMD Device if in Intel VMD domain */
 #endif
 };
 
@@ -35,12 +35,15 @@ extern int noioapicreroute;
 
 #ifdef CONFIG_PCI
 
+static inline struct pci_sysdata *to_pci_sysdata(const struct pci_bus *bus)
+{
+	return bus->sysdata;
+}
+
 #ifdef CONFIG_PCI_DOMAINS
 static inline int pci_domain_nr(struct pci_bus *bus)
 {
-	struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->domain;
+	return to_pci_sysdata(bus)->domain;
 }
 
 static inline int pci_proc_domain(struct pci_bus *bus)
@@ -52,24 +55,20 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
 static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
 {
-	struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->fwnode;
+	return to_pci_sysdata(bus)->fwnode;
 }
 
 #define pci_root_bus_fwnode	_pci_root_bus_fwnode
 #endif
 
+#if IS_ENABLED(CONFIG_VMD)
 static inline bool is_vmd(struct pci_bus *bus)
 {
-#if IS_ENABLED(CONFIG_VMD)
-	struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->vmd_domain;
-#else
-	return false;
-#endif
+	return to_pci_sysdata(bus)->vmd_dev != NULL;
 }
+#else
+#define is_vmd(bus)		false
+#endif /* CONFIG_VMD */
 
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
@@ -124,9 +123,7 @@ void native_restore_msi_irqs(struct pci_dev *dev);
 /* Returns the node based on pci bus */
 static inline int __pcibus_to_node(const struct pci_bus *bus)
 {
-	const struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->node;
+	return to_pci_sysdata(bus)->node;
 }
 
 static inline const struct cpumask *

arch/x86/pci/common.c

@@ -625,43 +625,6 @@ unsigned int pcibios_assign_all_busses(void)
 	return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
 }
 
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-static LIST_HEAD(dma_domain_list);
-static DEFINE_SPINLOCK(dma_domain_list_lock);
-
-void add_dma_domain(struct dma_domain *domain)
-{
-	spin_lock(&dma_domain_list_lock);
-	list_add(&domain->node, &dma_domain_list);
-	spin_unlock(&dma_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(add_dma_domain);
-
-void del_dma_domain(struct dma_domain *domain)
-{
-	spin_lock(&dma_domain_list_lock);
-	list_del(&domain->node);
-	spin_unlock(&dma_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(del_dma_domain);
-
-static void set_dma_domain_ops(struct pci_dev *pdev)
-{
-	struct dma_domain *domain;
-
-	spin_lock(&dma_domain_list_lock);
-	list_for_each_entry(domain, &dma_domain_list, node) {
-		if (pci_domain_nr(pdev->bus) == domain->domain_nr) {
-			pdev->dev.dma_ops = domain->dma_ops;
-			break;
-		}
-	}
-	spin_unlock(&dma_domain_list_lock);
-}
-#else
-static void set_dma_domain_ops(struct pci_dev *pdev) {}
-#endif
-
 static void set_dev_domain_options(struct pci_dev *pdev)
 {
 	if (is_vmd(pdev->bus))
@@ -697,7 +660,6 @@ int pcibios_add_device(struct pci_dev *dev)
 		pa_data = data->next;
 		memunmap(data);
 	}
-	set_dma_domain_ops(dev);
 	set_dev_domain_options(dev);
 	return 0;
 }
@@ -736,3 +698,13 @@ int pci_ext_cfg_avail(void)
 	else
 		return 0;
 }
+
+#if IS_ENABLED(CONFIG_VMD)
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev)
+{
+	if (is_vmd(dev->bus))
+		return to_pci_sysdata(dev->bus)->vmd_dev;
+
+	return dev;
+}
+#endif

drivers/iommu/intel-iommu.c

@@ -774,13 +774,7 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pf_pdev;
 
-		pdev = to_pci_dev(dev);
-
-#ifdef CONFIG_X86
-		/* VMD child devices currently cannot be handled individually */
-		if (is_vmd(pdev->bus))
-			return NULL;
-#endif
+		pdev = pci_real_dma_dev(to_pci_dev(dev));
 
 		/* VFs aren't listed in scope tables; we need to look up
 		 * the PF instead to find the IOMMU. */
@@ -2428,6 +2422,9 @@ static struct dmar_domain *find_domain(struct device *dev)
 		     dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
 		return NULL;
 
+	if (dev_is_pci(dev))
+		dev = &pci_real_dma_dev(to_pci_dev(dev))->dev;
+
 	/* No lock here, assumes no domain exit in normal case */
 	info = dev->archdata.iommu;
 	if (likely(info))

drivers/pci/controller/Kconfig

@@ -239,7 +239,6 @@ config PCIE_TANGO_SMP8759
 
 config VMD
 	depends on PCI_MSI && X86_64 && SRCU
-	select X86_DEV_DMA_OPS
 	tristate "Intel Volume Management Device Driver"
 	---help---
 	  Adds support for the Intel Volume Management Device (VMD). VMD is a

drivers/pci/controller/vmd.c

@@ -98,9 +98,6 @@ struct vmd_dev {
 	struct irq_domain	*irq_domain;
 	struct pci_bus		*bus;
 	u8			busn_start;
-
-	struct dma_map_ops	dma_ops;
-	struct dma_domain	dma_domain;
 };
 
 static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -295,151 +292,6 @@ static struct msi_domain_info vmd_msi_domain_info = {
 	.chip		= &vmd_msi_controller,
 };
 
-/*
- * VMD replaces the requester ID with its own.  DMA mappings for devices in a
- * VMD domain need to be mapped for the VMD, not the device requiring
- * the mapping.
- */
-static struct device *to_vmd_dev(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct vmd_dev *vmd = vmd_from_bus(pdev->bus);
-
-	return &vmd->dev->dev;
-}
-
-static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
-		       gfp_t flag, unsigned long attrs)
-{
-	return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
-}
-
-static void vmd_free(struct device *dev, size_t size, void *vaddr,
-		     dma_addr_t addr, unsigned long attrs)
-{
-	return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
-}
-
-static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
-		    void *cpu_addr, dma_addr_t addr, size_t size,
-		    unsigned long attrs)
-{
-	return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size,
-			attrs);
-}
-
-static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
-			   void *cpu_addr, dma_addr_t addr, size_t size,
-			   unsigned long attrs)
-{
-	return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size,
-			attrs);
-}
-
-static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
-			       unsigned long offset, size_t size,
-			       enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-	return dma_map_page_attrs(to_vmd_dev(dev), page, offset, size, dir,
-			attrs);
-}
-
-static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size,
-			   enum dma_data_direction dir, unsigned long attrs)
-{
-	dma_unmap_page_attrs(to_vmd_dev(dev), addr, size, dir, attrs);
-}
-
-static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		      enum dma_data_direction dir, unsigned long attrs)
-{
-	return dma_map_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
-}
-
-static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-			 enum dma_data_direction dir, unsigned long attrs)
-{
-	dma_unmap_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
-}
-
-static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
-				    size_t size, enum dma_data_direction dir)
-{
-	dma_sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
-}
-
-static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr,
-				       size_t size, enum dma_data_direction dir)
-{
-	dma_sync_single_for_device(to_vmd_dev(dev), addr, size, dir);
-}
-
-static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction dir)
-{
-	dma_sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
-}
-
-static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction dir)
-{
-	dma_sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir);
-}
-
-static int vmd_dma_supported(struct device *dev, u64 mask)
-{
-	return dma_supported(to_vmd_dev(dev), mask);
-}
-
-static u64 vmd_get_required_mask(struct device *dev)
-{
-	return dma_get_required_mask(to_vmd_dev(dev));
-}
-
-static void vmd_teardown_dma_ops(struct vmd_dev *vmd)
-{
-	struct dma_domain *domain = &vmd->dma_domain;
-
-	if (get_dma_ops(&vmd->dev->dev))
-		del_dma_domain(domain);
-}
-
-#define ASSIGN_VMD_DMA_OPS(source, dest, fn)	\
-	do {					\
-		if (source->fn)			\
-			dest->fn = vmd_##fn;	\
-	} while (0)
-
-static void vmd_setup_dma_ops(struct vmd_dev *vmd)
-{
-	const struct dma_map_ops *source = get_dma_ops(&vmd->dev->dev);
-	struct dma_map_ops *dest = &vmd->dma_ops;
-	struct dma_domain *domain = &vmd->dma_domain;
-
-	domain->domain_nr = vmd->sysdata.domain;
-	domain->dma_ops = dest;
-
-	if (!source)
-		return;
-	ASSIGN_VMD_DMA_OPS(source, dest, alloc);
-	ASSIGN_VMD_DMA_OPS(source, dest, free);
-	ASSIGN_VMD_DMA_OPS(source, dest, mmap);
-	ASSIGN_VMD_DMA_OPS(source, dest, get_sgtable);
-	ASSIGN_VMD_DMA_OPS(source, dest, map_page);
-	ASSIGN_VMD_DMA_OPS(source, dest, unmap_page);
-	ASSIGN_VMD_DMA_OPS(source, dest, map_sg);
-	ASSIGN_VMD_DMA_OPS(source, dest, unmap_sg);
-	ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_cpu);
-	ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device);
-	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu);
-	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device);
-	ASSIGN_VMD_DMA_OPS(source, dest, dma_supported);
-	ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask);
-	add_dma_domain(domain);
-}
-#undef ASSIGN_VMD_DMA_OPS
-
 static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
 				  unsigned int devfn, int reg, int len)
 {
@@ -679,7 +531,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 		.parent = res,
 	};
 
-	sd->vmd_domain = true;
+	sd->vmd_dev = vmd->dev;
 	sd->domain = vmd_find_free_domain();
 	if (sd->domain < 0)
 		return sd->domain;
@@ -709,7 +561,6 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 	}
 
 	vmd_attach_resources(vmd);
-	vmd_setup_dma_ops(vmd);
 	dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain);
 
 	pci_scan_child_bus(vmd->bus);
@@ -824,7 +675,6 @@ static void vmd_remove(struct pci_dev *dev)
 	pci_stop_root_bus(vmd->bus);
 	pci_remove_root_bus(vmd->bus);
 	vmd_cleanup_srcu(vmd);
-	vmd_teardown_dma_ops(vmd);
 	vmd_detach_resources(vmd);
 	irq_domain_remove(vmd->irq_domain);
 }
@@ -868,6 +718,10 @@ static const struct pci_device_id vmd_ids[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0),
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW |
 				VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x467f),
+		.driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4c3d),
+		.driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B),
 		.driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,},
 	{0,}

drivers/pci/pci.c

@@ -6048,7 +6048,9 @@ bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2)
 	return (dev1->dma_alias_mask &&
 		test_bit(dev2->devfn, dev1->dma_alias_mask)) ||
 	       (dev2->dma_alias_mask &&
-		test_bit(dev1->devfn, dev2->dma_alias_mask));
+		test_bit(dev1->devfn, dev2->dma_alias_mask)) ||
+	       pci_real_dma_dev(dev1) == dev2 ||
+	       pci_real_dma_dev(dev2) == dev1;
 }
 
 bool pci_device_is_present(struct pci_dev *pdev)
@@ -6072,6 +6074,21 @@ void pci_ignore_hotplug(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
 
+/**
+ * pci_real_dma_dev - Get PCI DMA device for PCI device
+ * @dev: the PCI device that may have a PCI DMA alias
+ *
+ * Permits the platform to provide architecture-specific functionality to
+ * devices needing to alias DMA to another PCI device on another PCI bus. If
+ * the PCI device is on the same bus, it is recommended to use
+ * pci_add_dma_alias(). This is the default implementation. Architecture
+ * implementations can override this.
+ */
+struct pci_dev __weak *pci_real_dma_dev(struct pci_dev *dev)
+{
+	return dev;
+}
+
 resource_size_t __weak pcibios_default_alignment(void)
 {
 	return 0;

drivers/pci/search.c

@@ -32,6 +32,12 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
 	struct pci_bus *bus;
 	int ret;
 
+	/*
+	 * The device may have an explicit alias requester ID for DMA where the
+	 * requester is on another PCI bus.
+	 */
+	pdev = pci_real_dma_dev(pdev);
+
 	ret = fn(pdev, pci_dev_id(pdev), data);
 	if (ret)
 		return ret;

include/linux/pci.h

@@ -1202,6 +1202,7 @@ int __must_check pci_resize_resource(struct pci_dev *dev, int i, int size);
 int pci_select_bars(struct pci_dev *dev, unsigned long flags);
 bool pci_device_is_present(struct pci_dev *pdev);
 void pci_ignore_hotplug(struct pci_dev *dev);
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev);
 
 int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr,
 		irq_handler_t handler, irq_handler_t thread_fn, void *dev_id,