Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd

Pull iommufd updates from Jason Gunthorpe:
 "Two significant new items:

   - Allow reporting IOMMU HW events to userspace when the events are
     clearly linked to a device.

     This is linked to the VIOMMU object and is intended to be used by a
     VMM to forward HW events to the virtual machine as part of
     emulating a vIOMMU. ARM SMMUv3 is the first driver to use this
     mechanism. Like the existing fault events the data is delivered
     through a simple FD returning event records on read().

   - PASID support in VFIO.

     The "Process Address Space ID" is a PCI feature that allows the
     device to tag all PCI DMA operations with an ID. The IOMMU will
     then use the ID to select a unique translation for those DMAs. This
     is part of Intel's vIOMMU support as VT-D HW requires the
     hypervisor to manage each PASID entry.

     The support is generic so any VFIO user could attach any
     translation to a PASID, and the support should work on ARM SMMUv3
     as well. AMD requires additional driver work.

  Some minor updates, along with fixes:

   - Prevent using nested parents with fault's, no driver support today

   - Put a single "cookie_type" value in the iommu_domain to indicate
     what owns the various opaque owner fields"

* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (49 commits)
  iommufd: Test attach before detaching pasid
  iommufd: Fix iommu_vevent_header tables markup
  iommu: Convert unreachable() to BUG()
  iommufd: Balance veventq->num_events inc/dec
  iommufd: Initialize the flags of vevent in iommufd_viommu_report_event()
  iommufd/selftest: Add coverage for reporting max_pasid_log2 via IOMMU_HW_INFO
  iommufd: Extend IOMMU_GET_HW_INFO to report PASID capability
  vfio: VFIO_DEVICE_[AT|DE]TACH_IOMMUFD_PT support pasid
  vfio-iommufd: Support pasid [at|de]tach for physical VFIO devices
  ida: Add ida_find_first_range()
  iommufd/selftest: Add coverage for iommufd pasid attach/detach
  iommufd/selftest: Add test ops to test pasid attach/detach
  iommufd/selftest: Add a helper to get test device
  iommufd/selftest: Add set_dev_pasid in mock iommu
  iommufd: Allow allocating PASID-compatible domain
  iommu/vt-d: Add IOMMU_HWPT_ALLOC_PASID support
  iommufd: Enforce PASID-compatible domain for RID
  iommufd: Support pasid attach/replace
  iommufd: Enforce PASID-compatible domain in PASID path
  iommufd/device: Add pasid_attach array to track per-PASID attach
  ...

5 files changed, 72 insertions, 23 deletions

diff --git a/include/linux/idr.h b/include/linux/idr.h
index cd729be369b3..2267902d29a7 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -274,6 +274,7 @@ struct ida {
 int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t);
 void ida_free(struct ida *, unsigned int id);
 void ida_destroy(struct ida *ida);
+int ida_find_first_range(struct ida *ida, unsigned int min, unsigned int max);
 
 /**
  * ida_alloc() - Allocate an unused ID.
@@ -345,4 +346,14 @@ static inline bool ida_is_empty(const struct ida *ida)
 {
 	return xa_empty(&ida->xa);
 }
+
+static inline bool ida_exists(struct ida *ida, unsigned int id)
+{
+	return ida_find_first_range(ida, id, id) == id;
+}
+
+static inline int ida_find_first(struct ida *ida)
+{
+	return ida_find_first_range(ida, 0, ~0);
+}
 #endif /* __IDR_H__ */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index cf8c16ba04a0..ccce8a751e2a 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -41,6 +41,7 @@ struct iommu_dirty_ops;
 struct notifier_block;
 struct iommu_sva;
 struct iommu_dma_cookie;
+struct iommu_dma_msi_cookie;
 struct iommu_fault_param;
 struct iommufd_ctx;
 struct iommufd_viommu;
@@ -165,6 +166,15 @@ struct iommu_domain_geometry {
 	bool force_aperture;       /* DMA only allowed in mappable range? */
 };
 
+enum iommu_domain_cookie_type {
+	IOMMU_COOKIE_NONE,
+	IOMMU_COOKIE_DMA_IOVA,
+	IOMMU_COOKIE_DMA_MSI,
+	IOMMU_COOKIE_FAULT_HANDLER,
+	IOMMU_COOKIE_SVA,
+	IOMMU_COOKIE_IOMMUFD,
+};
+
 /* Domain feature flags */
 #define __IOMMU_DOMAIN_PAGING	(1U << 0)  /* Support for iommu_map/unmap */
 #define __IOMMU_DOMAIN_DMA_API	(1U << 1)  /* Domain for use in DMA-API
@@ -211,23 +221,18 @@ struct iommu_domain_geometry {
 
 struct iommu_domain {
 	unsigned type;
+	enum iommu_domain_cookie_type cookie_type;
 	const struct iommu_domain_ops *ops;
 	const struct iommu_dirty_ops *dirty_ops;
 	const struct iommu_ops *owner; /* Whose domain_alloc we came from */
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	struct iommu_domain_geometry geometry;
-	struct iommu_dma_cookie *iova_cookie;
 	int (*iopf_handler)(struct iopf_group *group);
 
-#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU)
-	int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc,
-		      phys_addr_t msi_addr);
-#endif
-
-	union { /* Pointer usable by owner of the domain */
-		struct iommufd_hw_pagetable *iommufd_hwpt; /* iommufd */
-	};
-	union { /* Fault handler */
+	union { /* cookie */
+		struct iommu_dma_cookie *iova_cookie;
+		struct iommu_dma_msi_cookie *msi_cookie;
+		struct iommufd_hw_pagetable *iommufd_hwpt;
 		struct {
 			iommu_fault_handler_t handler;
 			void *handler_token;
@@ -244,16 +249,6 @@ struct iommu_domain {
 	};
 };
 
-static inline void iommu_domain_set_sw_msi(
-	struct iommu_domain *domain,
-	int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc,
-		      phys_addr_t msi_addr))
-{
-#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU)
-	domain->sw_msi = sw_msi;
-#endif
-}
-
 static inline bool iommu_is_dma_domain(struct iommu_domain *domain)
 {
 	return domain->type & __IOMMU_DOMAIN_DMA_API;
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 11110c749200..34b6e6ca4bfa 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -8,9 +8,11 @@
 
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/iommu.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
 #include <linux/xarray.h>
+#include <uapi/linux/iommufd.h>
 
 struct device;
 struct file;
@@ -34,6 +36,7 @@ enum iommufd_object_type {
 	IOMMUFD_OBJ_FAULT,
 	IOMMUFD_OBJ_VIOMMU,
 	IOMMUFD_OBJ_VDEVICE,
+	IOMMUFD_OBJ_VEVENTQ,
 #ifdef CONFIG_IOMMUFD_TEST
 	IOMMUFD_OBJ_SELFTEST,
 #endif
@@ -52,9 +55,11 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 					   struct device *dev, u32 *id);
 void iommufd_device_unbind(struct iommufd_device *idev);
 
-int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id);
-int iommufd_device_replace(struct iommufd_device *idev, u32 *pt_id);
-void iommufd_device_detach(struct iommufd_device *idev);
+int iommufd_device_attach(struct iommufd_device *idev, ioasid_t pasid,
+			  u32 *pt_id);
+int iommufd_device_replace(struct iommufd_device *idev, ioasid_t pasid,
+			   u32 *pt_id);
+void iommufd_device_detach(struct iommufd_device *idev, ioasid_t pasid);
 
 struct iommufd_ctx *iommufd_device_to_ictx(struct iommufd_device *idev);
 u32 iommufd_device_to_id(struct iommufd_device *idev);
@@ -93,6 +98,8 @@ struct iommufd_viommu {
 	const struct iommufd_viommu_ops *ops;
 
 	struct xarray vdevs;
+	struct list_head veventqs;
+	struct rw_semaphore veventqs_rwsem;
 
 	unsigned int type;
 };
@@ -187,6 +194,11 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 					     enum iommufd_object_type type);
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id);
+int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
+			       struct device *dev, unsigned long *vdev_id);
+int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
+				enum iommu_veventq_type type, void *event_data,
+				size_t data_len);
 #else /* !CONFIG_IOMMUFD_DRIVER_CORE */
 static inline struct iommufd_object *
 _iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size,
@@ -200,6 +212,20 @@ iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)
 {
 	return NULL;
 }
+
+static inline int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
+					     struct device *dev,
+					     unsigned long *vdev_id)
+{
+	return -ENOENT;
+}
+
+static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
+					      enum iommu_veventq_type type,
+					      void *event_data, size_t data_len)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_IOMMUFD_DRIVER_CORE */
 
 /*
diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
index 0e8b74e63767..75c6c86cf09d 100644
--- a/include/linux/pci-ats.h
+++ b/include/linux/pci-ats.h
@@ -42,6 +42,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features);
 void pci_disable_pasid(struct pci_dev *pdev);
 int pci_pasid_features(struct pci_dev *pdev);
 int pci_max_pasids(struct pci_dev *pdev);
+int pci_pasid_status(struct pci_dev *pdev);
 #else /* CONFIG_PCI_PASID */
 static inline int pci_enable_pasid(struct pci_dev *pdev, int features)
 { return -EINVAL; }
@@ -50,6 +51,8 @@ static inline int pci_pasid_features(struct pci_dev *pdev)
 { return -EINVAL; }
 static inline int pci_max_pasids(struct pci_dev *pdev)
 { return -EINVAL; }
+static inline int pci_pasid_status(struct pci_dev *pdev)
+{ return -EINVAL; }
 #endif /* CONFIG_PCI_PASID */
 
 #endif /* LINUX_PCI_ATS_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 000a6cab2d31..707b00772ce1 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -67,6 +67,7 @@ struct vfio_device {
 	struct inode *inode;
 #if IS_ENABLED(CONFIG_IOMMUFD)
 	struct iommufd_device *iommufd_device;
+	struct ida pasids;
 	u8 iommufd_attached:1;
 #endif
 	u8 cdev_opened:1;
@@ -91,6 +92,8 @@ struct vfio_device {
  *		 bound iommufd. Undo in unbind_iommufd if @detach_ioas is not
  *		 called.
  * @detach_ioas: Opposite of attach_ioas
+ * @pasid_attach_ioas: The pasid variation of attach_ioas
+ * @pasid_detach_ioas: Opposite of pasid_attach_ioas
  * @open_device: Called when the first file descriptor is opened for this device
  * @close_device: Opposite of open_device
  * @read: Perform read(2) on device file descriptor
@@ -115,6 +118,9 @@ struct vfio_device_ops {
 	void	(*unbind_iommufd)(struct vfio_device *vdev);
 	int	(*attach_ioas)(struct vfio_device *vdev, u32 *pt_id);
 	void	(*detach_ioas)(struct vfio_device *vdev);
+	int	(*pasid_attach_ioas)(struct vfio_device *vdev, u32 pasid,
+				     u32 *pt_id);
+	void	(*pasid_detach_ioas)(struct vfio_device *vdev, u32 pasid);
 	int	(*open_device)(struct vfio_device *vdev);
 	void	(*close_device)(struct vfio_device *vdev);
 	ssize_t	(*read)(struct vfio_device *vdev, char __user *buf,
@@ -139,6 +145,10 @@ int vfio_iommufd_physical_bind(struct vfio_device *vdev,
 void vfio_iommufd_physical_unbind(struct vfio_device *vdev);
 int vfio_iommufd_physical_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
 void vfio_iommufd_physical_detach_ioas(struct vfio_device *vdev);
+int vfio_iommufd_physical_pasid_attach_ioas(struct vfio_device *vdev,
+					    u32 pasid, u32 *pt_id);
+void vfio_iommufd_physical_pasid_detach_ioas(struct vfio_device *vdev,
+					     u32 pasid);
 int vfio_iommufd_emulated_bind(struct vfio_device *vdev,
 			       struct iommufd_ctx *ictx, u32 *out_device_id);
 void vfio_iommufd_emulated_unbind(struct vfio_device *vdev);
@@ -166,6 +176,10 @@ vfio_iommufd_get_dev_id(struct vfio_device *vdev, struct iommufd_ctx *ictx)
 	((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL)
 #define vfio_iommufd_physical_detach_ioas \
 	((void (*)(struct vfio_device *vdev)) NULL)
+#define vfio_iommufd_physical_pasid_attach_ioas \
+	((int (*)(struct vfio_device *vdev, u32 pasid, u32 *pt_id)) NULL)
+#define vfio_iommufd_physical_pasid_detach_ioas \
+	((void (*)(struct vfio_device *vdev, u32 pasid)) NULL)
 #define vfio_iommufd_emulated_bind                                      \
 	((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx,   \
 		  u32 *out_device_id)) NULL)