Merge tag 'iommu-updates-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - New DART IOMMU driver for Apple Silicon M1 chips

 - Optimizations for iommu_[map/unmap] performance

 - Selective TLB flush support for the AMD IOMMU driver to make it more
   efficient on emulated IOMMUs

 - Rework IOVA setup and default domain type setting to move more code
   out of IOMMU drivers and to support runtime switching between certain
   types of default domains

 - VT-d Updates from Lu Baolu:
      - Update the virtual command related registers
      - Enable Intel IOMMU scalable mode by default
      - Preset A/D bits for user space DMA usage
      - Allow devices to have more than 32 outstanding PRs
      - Various cleanups

 - ARM SMMU Updates from Will Deacon:
      SMMUv3:
       - Minor optimisation to avoid zeroing struct members on CMD submission
       - Increased use of batched commands to reduce submission latency
       - Refactoring in preparation for ECMDQ support
      SMMUv2:
       - Fix races when probing devices with identical StreamIDs
       - Optimise walk cache flushing for Qualcomm implementations
       - Allow deep sleep states for some Qualcomm SoCs with shared clocks

 - Various smaller optimizations, cleanups, and fixes

* tag 'iommu-updates-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (85 commits)
  iommu/io-pgtable: Abstract iommu_iotlb_gather access
  iommu/arm-smmu: Fix missing unlock on error in arm_smmu_device_group()
  iommu/vt-d: Add present bit check in pasid entry setup helpers
  iommu/vt-d: Use pasid_pte_is_present() helper function
  iommu/vt-d: Drop the kernel doc annotation
  iommu/vt-d: Allow devices to have more than 32 outstanding PRs
  iommu/vt-d: Preset A/D bits for user space DMA usage
  iommu/vt-d: Enable Intel IOMMU scalable mode by default
  iommu/vt-d: Refactor Kconfig a bit
  iommu/vt-d: Remove unnecessary oom message
  iommu/vt-d: Update the virtual command related registers
  iommu: Allow enabling non-strict mode dynamically
  iommu: Merge strictness and domain type configs
  iommu: Only log strictness for DMA domains
  iommu: Expose DMA domain strictness via sysfs
  iommu: Express DMA strictness via the domain type
  iommu/vt-d: Prepare for multiple DMA domain types
  iommu/arm-smmu: Prepare for multiple DMA domain types
  iommu/amd: Prepare for multiple DMA domain types
  iommu: Introduce explicit type for non-strict DMA domains
  ...

5 files changed, 127 insertions, 24 deletions

diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index 758ca4694257..24607dc3c2ac 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -20,6 +20,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain);
 
 /* Setup call for arch DMA mapping code */
 void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit);
+int iommu_dma_init_fq(struct iommu_domain *domain);
 
 /* The DMA API isn't _quite_ the whole story, though... */
 /*
@@ -54,6 +55,11 @@ static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base,
 {
 }
 
+static inline int iommu_dma_init_fq(struct iommu_domain *domain)
+{
+	return -EINVAL;
+}
+
 static inline int iommu_get_dma_cookie(struct iommu_domain *domain)
 {
 	return -ENODEV;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index d0fa0b31994d..05a65eb155f7 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -124,9 +124,9 @@
 #define DMAR_MTRR_PHYSMASK8_REG 0x208
 #define DMAR_MTRR_PHYSBASE9_REG 0x210
 #define DMAR_MTRR_PHYSMASK9_REG 0x218
-#define DMAR_VCCAP_REG		0xe00 /* Virtual command capability register */
-#define DMAR_VCMD_REG		0xe10 /* Virtual command register */
-#define DMAR_VCRSP_REG		0xe20 /* Virtual command response register */
+#define DMAR_VCCAP_REG		0xe30 /* Virtual command capability register */
+#define DMAR_VCMD_REG		0xe00 /* Virtual command register */
+#define DMAR_VCRSP_REG		0xe10 /* Virtual command response register */
 
 #define DMAR_IQER_REG_IQEI(reg)		FIELD_GET(GENMASK_ULL(3, 0), reg)
 #define DMAR_IQER_REG_ITESID(reg)	FIELD_GET(GENMASK_ULL(47, 32), reg)
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index 10fa80eef13a..57cceecbe37f 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -14,6 +14,11 @@
 #define SVM_REQ_EXEC	(1<<1)
 #define SVM_REQ_PRIV	(1<<0)
 
+/* Page Request Queue depth */
+#define PRQ_ORDER	2
+#define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
+#define PRQ_DEPTH	((0x1000 << PRQ_ORDER) >> 5)
+
 /*
  * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only
  * for access to kernel addresses. No IOTLB flushes are automatically done
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 4d40dfa75b55..86af6f0a00a2 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -16,6 +16,7 @@ enum io_pgtable_fmt {
 	ARM_V7S,
 	ARM_MALI_LPAE,
 	AMD_IOMMU_V1,
+	APPLE_DART,
 	IO_PGTABLE_NUM_FMTS,
 };
 
@@ -73,10 +74,6 @@ struct io_pgtable_cfg {
 	 *	to support up to 35 bits PA where the bit32, bit33 and bit34 are
 	 *	encoded in the bit9, bit4 and bit5 of the PTE respectively.
 	 *
-	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
-	 *	on unmap, for DMA domains using the flush queue mechanism for
-	 *	delayed invalidation.
-	 *
 	 * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
 	 *	for use in the upper half of a split address space.
 	 *
@@ -86,7 +83,6 @@ struct io_pgtable_cfg {
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
 	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
-	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
 	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
 	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA	BIT(6)
 	unsigned long			quirks;
@@ -136,6 +132,11 @@ struct io_pgtable_cfg {
 			u64	transtab;
 			u64	memattr;
 		} arm_mali_lpae_cfg;
+
+		struct {
+			u64 ttbr[4];
+			u32 n_ttbrs;
+		} apple_dart_cfg;
 	};
 };
 
@@ -143,7 +144,9 @@ struct io_pgtable_cfg {
  * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers.
  *
  * @map:          Map a physically contiguous memory region.
+ * @map_pages:    Map a physically contiguous range of pages of the same size.
  * @unmap:        Unmap a physically contiguous memory region.
+ * @unmap_pages:  Unmap a range of virtually contiguous pages of the same size.
  * @iova_to_phys: Translate iova to physical address.
  *
  * These functions map directly onto the iommu_ops member functions with
@@ -152,8 +155,14 @@ struct io_pgtable_cfg {
 struct io_pgtable_ops {
 	int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
+	int (*map_pages)(struct io_pgtable_ops *ops, unsigned long iova,
+			 phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			 int prot, gfp_t gfp, size_t *mapped);
 	size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
 			size_t size, struct iommu_iotlb_gather *gather);
+	size_t (*unmap_pages)(struct io_pgtable_ops *ops, unsigned long iova,
+			      size_t pgsize, size_t pgcount,
+			      struct iommu_iotlb_gather *gather);
 	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
 				    unsigned long iova);
 };
@@ -246,5 +255,6 @@ extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns;
 extern struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns;
 extern struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns;
 extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns;
+extern struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns;
 
 #endif /* __IO_PGTABLE_H */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 9369458ba1bd..d2f3435e7d17 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -40,6 +40,7 @@ struct iommu_domain;
 struct notifier_block;
 struct iommu_sva;
 struct iommu_fault_event;
+struct iommu_dma_cookie;
 
 /* iommu fault flags */
 #define IOMMU_FAULT_READ	0x0
@@ -60,6 +61,7 @@ struct iommu_domain_geometry {
 #define __IOMMU_DOMAIN_DMA_API	(1U << 1)  /* Domain for use in DMA-API
 					      implementation              */
 #define __IOMMU_DOMAIN_PT	(1U << 2)  /* Domain is identity mapped   */
+#define __IOMMU_DOMAIN_DMA_FQ	(1U << 3)  /* DMA-API uses flush queue    */
 
 /*
  * This are the possible domain-types
@@ -72,12 +74,17 @@ struct iommu_domain_geometry {
  *	IOMMU_DOMAIN_DMA	- Internally used for DMA-API implementations.
  *				  This flag allows IOMMU drivers to implement
  *				  certain optimizations for these domains
+ *	IOMMU_DOMAIN_DMA_FQ	- As above, but definitely using batched TLB
+ *				  invalidation.
  */
 #define IOMMU_DOMAIN_BLOCKED	(0U)
 #define IOMMU_DOMAIN_IDENTITY	(__IOMMU_DOMAIN_PT)
 #define IOMMU_DOMAIN_UNMANAGED	(__IOMMU_DOMAIN_PAGING)
 #define IOMMU_DOMAIN_DMA	(__IOMMU_DOMAIN_PAGING |	\
 				 __IOMMU_DOMAIN_DMA_API)
+#define IOMMU_DOMAIN_DMA_FQ	(__IOMMU_DOMAIN_PAGING |	\
+				 __IOMMU_DOMAIN_DMA_API |	\
+				 __IOMMU_DOMAIN_DMA_FQ)
 
 struct iommu_domain {
 	unsigned type;
@@ -86,9 +93,14 @@ struct iommu_domain {
 	iommu_fault_handler_t handler;
 	void *handler_token;
 	struct iommu_domain_geometry geometry;
-	void *iova_cookie;
+	struct iommu_dma_cookie *iova_cookie;
 };
 
+static inline bool iommu_is_dma_domain(struct iommu_domain *domain)
+{
+	return domain->type & __IOMMU_DOMAIN_DMA_API;
+}
+
 enum iommu_cap {
 	IOMMU_CAP_CACHE_COHERENCY,	/* IOMMU can enforce cache coherent DMA
 					   transactions */
@@ -160,16 +172,22 @@ enum iommu_dev_features {
  * @start: IOVA representing the start of the range to be flushed
  * @end: IOVA representing the end of the range to be flushed (inclusive)
  * @pgsize: The interval at which to perform the flush
+ * @freelist: Removed pages to free after sync
+ * @queued: Indicates that the flush will be queued
  *
  * This structure is intended to be updated by multiple calls to the
  * ->unmap() function in struct iommu_ops before eventually being passed
- * into ->iotlb_sync().
+ * into ->iotlb_sync(). Drivers can add pages to @freelist to be freed after
+ * ->iotlb_sync() or ->iotlb_flush_all() have cleared all cached references to
+ * them. @queued is set to indicate when ->iotlb_flush_all() will be called
+ * later instead of ->iotlb_sync(), so drivers may optimise accordingly.
  */
 struct iommu_iotlb_gather {
 	unsigned long		start;
 	unsigned long		end;
 	size_t			pgsize;
 	struct page		*freelist;
+	bool			queued;
 };
 
 /**
@@ -180,7 +198,10 @@ struct iommu_iotlb_gather {
  * @attach_dev: attach device to an iommu domain
  * @detach_dev: detach device from an iommu domain
  * @map: map a physically contiguous memory region to an iommu domain
+ * @map_pages: map a physically contiguous set of pages of the same size to
+ *             an iommu domain.
  * @unmap: unmap a physically contiguous memory region from an iommu domain
+ * @unmap_pages: unmap a number of pages of the same size from an iommu domain
  * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
@@ -229,8 +250,14 @@ struct iommu_ops {
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
+	int (*map_pages)(struct iommu_domain *domain, unsigned long iova,
+			 phys_addr_t paddr, size_t pgsize, size_t pgcount,
+			 int prot, gfp_t gfp, size_t *mapped);
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size, struct iommu_iotlb_gather *iotlb_gather);
+	size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova,
+			      size_t pgsize, size_t pgcount,
+			      struct iommu_iotlb_gather *iotlb_gather);
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
 	void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova,
 			       size_t size);
@@ -476,8 +503,7 @@ int iommu_enable_nesting(struct iommu_domain *domain);
 int iommu_set_pgtable_quirks(struct iommu_domain *domain,
 		unsigned long quirks);
 
-void iommu_set_dma_strict(bool val);
-bool iommu_get_dma_strict(struct iommu_domain *domain);
+void iommu_set_dma_strict(void);
 
 extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
 			      unsigned long iova, int flags);
@@ -497,29 +523,80 @@ static inline void iommu_iotlb_sync(struct iommu_domain *domain,
 	iommu_iotlb_gather_init(iotlb_gather);
 }
 
+/**
+ * iommu_iotlb_gather_is_disjoint - Checks whether a new range is disjoint
+ *
+ * @gather: TLB gather data
+ * @iova: start of page to invalidate
+ * @size: size of page to invalidate
+ *
+ * Helper for IOMMU drivers to check whether a new range and the gathered range
+ * are disjoint. For many IOMMUs, flushing the IOMMU in this case is better
+ * than merging the two, which might lead to unnecessary invalidations.
+ */
+static inline
+bool iommu_iotlb_gather_is_disjoint(struct iommu_iotlb_gather *gather,
+				    unsigned long iova, size_t size)
+{
+	unsigned long start = iova, end = start + size - 1;
+
+	return gather->end != 0 &&
+		(end + 1 < gather->start || start > gather->end + 1);
+}
+
+
+/**
+ * iommu_iotlb_gather_add_range - Gather for address-based TLB invalidation
+ * @gather: TLB gather data
+ * @iova: start of page to invalidate
+ * @size: size of page to invalidate
+ *
+ * Helper for IOMMU drivers to build arbitrarily-sized invalidation commands
+ * where only the address range matters, and simply minimising intermediate
+ * syncs is preferred.
+ */
+static inline void iommu_iotlb_gather_add_range(struct iommu_iotlb_gather *gather,
+						unsigned long iova, size_t size)
+{
+	unsigned long end = iova + size - 1;
+
+	if (gather->start > iova)
+		gather->start = iova;
+	if (gather->end < end)
+		gather->end = end;
+}
+
+/**
+ * iommu_iotlb_gather_add_page - Gather for page-based TLB invalidation
+ * @domain: IOMMU domain to be invalidated
+ * @gather: TLB gather data
+ * @iova: start of page to invalidate
+ * @size: size of page to invalidate
+ *
+ * Helper for IOMMU drivers to build invalidation commands based on individual
+ * pages, or with page size/table level hints which cannot be gathered if they
+ * differ.
+ */
 static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
 					       struct iommu_iotlb_gather *gather,
 					       unsigned long iova, size_t size)
 {
-	unsigned long start = iova, end = start + size - 1;
-
 	/*
 	 * If the new page is disjoint from the current range or is mapped at
 	 * a different granularity, then sync the TLB so that the gather
 	 * structure can be rewritten.
 	 */
-	if (gather->pgsize != size ||
-	    end + 1 < gather->start || start > gather->end + 1) {
-		if (gather->pgsize)
-			iommu_iotlb_sync(domain, gather);
-		gather->pgsize = size;
-	}
+	if ((gather->pgsize && gather->pgsize != size) ||
+	    iommu_iotlb_gather_is_disjoint(gather, iova, size))
+		iommu_iotlb_sync(domain, gather);
 
-	if (gather->end < end)
-		gather->end = end;
+	gather->pgsize = size;
+	iommu_iotlb_gather_add_range(gather, iova, size);
+}
 
-	if (gather->start > start)
-		gather->start = start;
+static inline bool iommu_iotlb_gather_queued(struct iommu_iotlb_gather *gather)
+{
+	return gather && gather->queued;
 }
 
 /* PCI device grouping function */
@@ -870,6 +947,11 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
 {
 }
 
+static inline bool iommu_iotlb_gather_queued(struct iommu_iotlb_gather *gather)
+{
+	return false;
+}
+
 static inline void iommu_device_unregister(struct iommu_device *iommu)
 {
 }