Merge tag 'iommu-updates-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
 "Core changes:
   - Fix race conditions in device probe path
   - Retire IOMMU bus_ops
   - Support for passing custom allocators to page table drivers
   - Clean up Kconfig around IOMMU_SVA
   - Support for sharing SVA domains with all devices bound to a mm
   - Firmware data parsing cleanup
   - Tracing improvements for iommu-dma code
   - Some smaller fixes and cleanups

  ARM-SMMU drivers:
   - Device-tree binding updates:
      - Add additional compatible strings for Qualcomm SoCs
      - Document Adreno clocks for Qualcomm's SM8350 SoC
   - SMMUv2:
      - Implement support for the ->domain_alloc_paging() callback
      - Ensure Secure context is restored following suspend of Qualcomm
        SMMU implementation
   - SMMUv3:
      - Disable stalling mode for the "quiet" context descriptor
      - Minor refactoring and driver cleanups

  Intel VT-d driver:
   - Cleanup and refactoring

  AMD IOMMU driver:
   - Improve IO TLB invalidation logic
   - Small cleanups and improvements

  Rockchip IOMMU driver:
   - DT binding update to add Rockchip RK3588

  Apple DART driver:
   - Apple M1 USB4/Thunderbolt DART support
   - Cleanups

  Virtio IOMMU driver:
   - Add support for iotlb_sync_map
   - Enable deferred IO TLB flushes"

* tag 'iommu-updates-v6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (66 commits)
  iommu: Don't reserve 0-length IOVA region
  iommu/vt-d: Move inline helpers to header files
  iommu/vt-d: Remove unused vcmd interfaces
  iommu/vt-d: Remove unused parameter of intel_pasid_setup_pass_through()
  iommu/vt-d: Refactor device_to_iommu() to retrieve iommu directly
  iommu/sva: Fix memory leak in iommu_sva_bind_device()
  dt-bindings: iommu: rockchip: Add Rockchip RK3588
  iommu/dma: Trace bounce buffer usage when mapping buffers
  iommu/arm-smmu: Convert to domain_alloc_paging()
  iommu/arm-smmu: Pass arm_smmu_domain to internal functions
  iommu/arm-smmu: Implement IOMMU_DOMAIN_BLOCKED
  iommu/arm-smmu: Convert to a global static identity domain
  iommu/arm-smmu: Reorganize arm_smmu_domain_add_master()
  iommu/arm-smmu-v3: Remove ARM_SMMU_DOMAIN_NESTED
  iommu/arm-smmu-v3: Master cannot be NULL in arm_smmu_write_strtab_ent()
  iommu/arm-smmu-v3: Add a type for the STE
  iommu/arm-smmu-v3: disable stall for quiet_cd
  iommu/qcom: restore IOMMU state if needed
  iommu/arm-smmu-qcom: Add QCM2290 MDSS compatible
  iommu/arm-smmu-qcom: Add missing GMU entry to match table
  ...

8 files changed, 86 insertions, 26 deletions

diff --git a/include/linux/device.h b/include/linux/device.h
index 58af8307c7dd..97c4b046c09d 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -42,7 +42,6 @@ struct class;
 struct subsys_private;
 struct device_node;
 struct fwnode_handle;
-struct iommu_ops;
 struct iommu_group;
 struct dev_pin_info;
 struct dev_iommu;
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index 25127f750349..5ef4ec1c36c3 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -62,9 +62,6 @@ struct fwnode_handle;
  *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
- * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
- *              driver implementations to a bus and allow the driver to do
- *              bus-specific setup
  * @need_parent_lock:	When probing or removing a device on this bus, the
  *			device core should lock the device's parent.
  *
@@ -104,8 +101,6 @@ struct bus_type {
 
 	const struct dev_pm_ops *pm;
 
-	const struct iommu_ops *iommu_ops;
-
 	bool need_parent_lock;
 };
 
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index e401f824a007..4abc60f04209 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 
 struct cma;
+struct iommu_ops;
 
 /*
  * Values for struct dma_map_ops.flags:
@@ -426,10 +427,10 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent);
+		bool coherent);
 #else
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
+		u64 size, bool coherent)
 {
 }
 #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 25142a0e2fc2..86cf1f7ae389 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -100,6 +100,30 @@ struct io_pgtable_cfg {
 	const struct iommu_flush_ops	*tlb;
 	struct device			*iommu_dev;
 
+	/**
+	 * @alloc: Custom page allocator.
+	 *
+	 * Optional hook used to allocate page tables. If this function is NULL,
+	 * @free must be NULL too.
+	 *
+	 * Memory returned should be zeroed and suitable for dma_map_single() and
+	 * virt_to_phys().
+	 *
+	 * Not all formats support custom page allocators. Before considering
+	 * passing a non-NULL value, make sure the chosen page format supports
+	 * this feature.
+	 */
+	void *(*alloc)(void *cookie, size_t size, gfp_t gfp);
+
+	/**
+	 * @free: Custom page de-allocator.
+	 *
+	 * Optional hook used to free page tables allocated with the @alloc
+	 * hook. Must be non-NULL if @alloc is not NULL, must be NULL
+	 * otherwise.
+	 */
+	void (*free)(void *cookie, void *pages, size_t size);
+
 	/* Low-level data specific to the table format */
 	union {
 		struct {
@@ -242,15 +266,25 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop,
 }
 
 /**
+ * enum io_pgtable_caps - IO page table backend capabilities.
+ */
+enum io_pgtable_caps {
+	/** @IO_PGTABLE_CAP_CUSTOM_ALLOCATOR: Backend accepts custom page table allocators. */
+	IO_PGTABLE_CAP_CUSTOM_ALLOCATOR = BIT(0),
+};
+
+/**
  * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
  *                              particular format.
  *
  * @alloc: Allocate a set of page tables described by cfg.
  * @free:  Free the page tables associated with iop.
+ * @caps:  Combination of @io_pgtable_caps flags encoding the backend capabilities.
  */
 struct io_pgtable_init_fns {
 	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
 	void (*free)(struct io_pgtable *iop);
+	u32 caps;
 };
 
 extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 6291aa7b079b..3a556996fea7 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -106,7 +106,7 @@ struct iommu_domain {
 	unsigned 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;
@@ -121,6 +121,11 @@ struct iommu_domain {
 		struct {	/* IOMMU_DOMAIN_SVA */
 			struct mm_struct *mm;
 			int users;
+			/*
+			 * Next iommu_domain in mm->iommu_mm->sva-domains list
+			 * protected by iommu_sva_lock.
+			 */
+			struct list_head next;
 		};
 	};
 };
@@ -812,6 +817,11 @@ struct iommu_sva {
 	struct iommu_domain		*domain;
 };
 
+struct iommu_mm_data {
+	u32			pasid;
+	struct list_head	sva_domains;
+};
+
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
 		      const struct iommu_ops *ops);
 void iommu_fwspec_free(struct device *dev);
@@ -840,10 +850,7 @@ static inline void *dev_iommu_priv_get(struct device *dev)
 		return NULL;
 }
 
-static inline void dev_iommu_priv_set(struct device *dev, void *priv)
-{
-	dev->iommu->priv = priv;
-}
+void dev_iommu_priv_set(struct device *dev, void *priv);
 
 extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
@@ -1337,15 +1344,33 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream
 	return false;
 }
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 static inline void mm_pasid_init(struct mm_struct *mm)
 {
-	mm->pasid = IOMMU_PASID_INVALID;
+	/*
+	 * During dup_mm(), a new mm will be memcpy'd from an old one and that makes
+	 * the new mm and the old one point to a same iommu_mm instance. When either
+	 * one of the two mms gets released, the iommu_mm instance is freed, leaving
+	 * the other mm running into a use-after-free/double-free problem. To avoid
+	 * the problem, zeroing the iommu_mm pointer of a new mm is needed here.
+	 */
+	mm->iommu_mm = NULL;
 }
+
 static inline bool mm_valid_pasid(struct mm_struct *mm)
 {
-	return mm->pasid != IOMMU_PASID_INVALID;
+	return READ_ONCE(mm->iommu_mm);
+}
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	struct iommu_mm_data *iommu_mm = READ_ONCE(mm->iommu_mm);
+
+	if (!iommu_mm)
+		return IOMMU_PASID_INVALID;
+	return iommu_mm->pasid;
 }
+
 void mm_pasid_drop(struct mm_struct *mm);
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm);
@@ -1368,6 +1393,12 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 }
 static inline void mm_pasid_init(struct mm_struct *mm) {}
 static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	return IOMMU_PASID_INVALID;
+}
+
 static inline void mm_pasid_drop(struct mm_struct *mm) {}
 #endif /* CONFIG_IOMMU_SVA */
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index b2d3a88a34d1..8b611e13153e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -730,6 +730,7 @@ struct mm_cid {
 #endif
 
 struct kioctx_table;
+struct iommu_mm_data;
 struct mm_struct {
 	struct {
 		/*
@@ -941,8 +942,8 @@ struct mm_struct {
 #endif
 		struct work_struct async_put_work;
 
-#ifdef CONFIG_IOMMU_SVA
-		u32 pasid;
+#ifdef CONFIG_IOMMU_MM_DATA
+		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
 		/*
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 9a5e6b410dd2..e61cbbe12dac 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -8,20 +8,19 @@ struct iommu_ops;
 
 #ifdef CONFIG_OF_IOMMU
 
-extern const struct iommu_ops *of_iommu_configure(struct device *dev,
-					struct device_node *master_np,
-					const u32 *id);
+extern int of_iommu_configure(struct device *dev, struct device_node *master_np,
+			      const u32 *id);
 
 extern void of_iommu_get_resv_regions(struct device *dev,
 				      struct list_head *list);
 
 #else
 
-static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
-					 struct device_node *master_np,
-					 const u32 *id)
+static inline int of_iommu_configure(struct device *dev,
+				     struct device_node *master_np,
+				     const u32 *id)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 static inline void of_iommu_get_resv_regions(struct device *dev,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9a66147915b2..cdb8ea53c365 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -957,7 +957,7 @@ struct task_struct {
 	/* Recursion prevention for eventfd_signal() */
 	unsigned			in_eventfd:1;
 #endif
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	unsigned			pasid_activated:1;
 #endif
 #ifdef	CONFIG_CPU_SUP_INTEL