Merge tag 'dma-mapping-6.16-2025-05-26' of git://git.kernel.org/pub/scm/linux/kernel/git/mszyprowski/linux

Pull dma-mapping updates from Marek Szyprowski:
 "New two step DMA mapping API, which is is a first step to a long path
  to provide alternatives to scatterlist and to remove hacks, abuses and
  design mistakes related to scatterlists.

  This new approach optimizes some calls to DMA-IOMMU layer and cache
  maintenance by batching them, reduces memory usage as it is no need to
  store mapped DMA addresses to unmap them, and reduces some function
  call overhead.  It is a combination effort of many people, lead and
  developed by Christoph Hellwig and Leon Romanovsky"

* tag 'dma-mapping-6.16-2025-05-26' of git://git.kernel.org/pub/scm/linux/kernel/git/mszyprowski/linux:
  docs: core-api: document the IOVA-based API
  dma-mapping: add a dma_need_unmap helper
  dma-mapping: Implement link/unlink ranges API
  iommu/dma: Factor out a iommu_dma_map_swiotlb helper
  dma-mapping: Provide an interface to allow allocate IOVA
  iommu: add kernel-doc for iommu_unmap_fast
  iommu: generalize the batched sync after map interface
  dma-mapping: move the PCI P2PDMA mapping helpers to pci-p2pdma.h
  PCI/P2PDMA: Refactor the p2pdma mapping helpers

4 files changed, 174 insertions, 54 deletions

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index e172522cd936..f48e5fb88bd5 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -434,58 +434,4 @@ static inline void debug_dma_dump_mappings(struct device *dev)
 #endif /* CONFIG_DMA_API_DEBUG */
 
 extern const struct dma_map_ops dma_dummy_ops;
-
-enum pci_p2pdma_map_type {
-	/*
-	 * PCI_P2PDMA_MAP_UNKNOWN: Used internally for indicating the mapping
-	 * type hasn't been calculated yet. Functions that return this enum
-	 * never return this value.
-	 */
-	PCI_P2PDMA_MAP_UNKNOWN = 0,
-
-	/*
-	 * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will
-	 * traverse the host bridge and the host bridge is not in the
-	 * allowlist. DMA Mapping routines should return an error when
-	 * this is returned.
-	 */
-	PCI_P2PDMA_MAP_NOT_SUPPORTED,
-
-	/*
-	 * PCI_P2PDMA_BUS_ADDR: Indicates that two devices can talk to
-	 * each other directly through a PCI switch and the transaction will
-	 * not traverse the host bridge. Such a mapping should program
-	 * the DMA engine with PCI bus addresses.
-	 */
-	PCI_P2PDMA_MAP_BUS_ADDR,
-
-	/*
-	 * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk
-	 * to each other, but the transaction traverses a host bridge on the
-	 * allowlist. In this case, a normal mapping either with CPU physical
-	 * addresses (in the case of dma-direct) or IOVA addresses (in the
-	 * case of IOMMUs) should be used to program the DMA engine.
-	 */
-	PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
-};
-
-struct pci_p2pdma_map_state {
-	struct dev_pagemap *pgmap;
-	int map;
-	u64 bus_off;
-};
-
-#ifdef CONFIG_PCI_P2PDMA
-enum pci_p2pdma_map_type
-pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
-		       struct scatterlist *sg);
-#else /* CONFIG_PCI_P2PDMA */
-static inline enum pci_p2pdma_map_type
-pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
-		       struct scatterlist *sg)
-{
-	return PCI_P2PDMA_MAP_NOT_SUPPORTED;
-}
-#endif /* CONFIG_PCI_P2PDMA */
-
 #endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 85ab710ec0e7..55c03e5fe8cb 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -72,6 +72,22 @@
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
+struct dma_iova_state {
+	dma_addr_t addr;
+	u64 __size;
+};
+
+/*
+ * Use the high bit to mark if we used swiotlb for one or more ranges.
+ */
+#define DMA_IOVA_USE_SWIOTLB		(1ULL << 63)
+
+static inline size_t dma_iova_size(struct dma_iova_state *state)
+{
+	/* Casting is needed for 32-bits systems */
+	return (size_t)(state->__size & ~DMA_IOVA_USE_SWIOTLB);
+}
+
 #ifdef CONFIG_DMA_API_DEBUG
 void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 void debug_dma_map_single(struct device *dev, const void *addr,
@@ -277,6 +293,70 @@ static inline int dma_mmap_noncontiguous(struct device *dev,
 }
 #endif /* CONFIG_HAS_DMA */
 
+#ifdef CONFIG_IOMMU_DMA
+/**
+ * dma_use_iova - check if the IOVA API is used for this state
+ * @state: IOVA state
+ *
+ * Return %true if the DMA transfers uses the dma_iova_*() calls or %false if
+ * they can't be used.
+ */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return state->__size != 0;
+}
+
+bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t size);
+void dma_iova_free(struct device *dev, struct dma_iova_state *state);
+void dma_iova_destroy(struct device *dev, struct dma_iova_state *state,
+		size_t mapped_len, enum dma_data_direction dir,
+		unsigned long attrs);
+int dma_iova_sync(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size);
+int dma_iova_link(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_iova_unlink(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+#else /* CONFIG_IOMMU_DMA */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return false;
+}
+static inline bool dma_iova_try_alloc(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t size)
+{
+	return false;
+}
+static inline void dma_iova_free(struct device *dev,
+		struct dma_iova_state *state)
+{
+}
+static inline void dma_iova_destroy(struct device *dev,
+		struct dma_iova_state *state, size_t mapped_len,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+}
+static inline int dma_iova_sync(struct device *dev,
+		struct dma_iova_state *state, size_t offset, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+static inline int dma_iova_link(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t offset,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return -EOPNOTSUPP;
+}
+static inline void dma_iova_unlink(struct device *dev,
+		struct dma_iova_state *state, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+}
+#endif /* CONFIG_IOMMU_DMA */
+
 #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
 void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir);
@@ -326,6 +406,7 @@ static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_dev_need_sync(dev) ? __dma_need_sync(dev, dma_addr) : false;
 }
+bool dma_need_unmap(struct device *dev);
 #else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */
 static inline bool dma_dev_need_sync(const struct device *dev)
 {
@@ -351,6 +432,10 @@ static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return false;
 }
+static inline bool dma_need_unmap(struct device *dev)
+{
+	return false;
+}
 #endif /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */
 
 struct page *dma_alloc_pages(struct device *dev, size_t size,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3a8d35d41fda..15cdadace993 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -872,6 +872,10 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
+int iommu_map_nosync(struct iommu_domain *domain, unsigned long iova,
+		phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
+int iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+		size_t size);
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			  size_t size);
 extern size_t iommu_unmap_fast(struct iommu_domain *domain,
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
index 2c07aa6b7665..075c20b161d9 100644
--- a/include/linux/pci-p2pdma.h
+++ b/include/linux/pci-p2pdma.h
@@ -104,4 +104,89 @@ static inline struct pci_dev *pci_p2pmem_find(struct device *client)
 	return pci_p2pmem_find_many(&client, 1);
 }
 
+enum pci_p2pdma_map_type {
+	/*
+	 * PCI_P2PDMA_MAP_UNKNOWN: Used internally as an initial state before
+	 * the mapping type has been calculated. Exported routines for the API
+	 * will never return this value.
+	 */
+	PCI_P2PDMA_MAP_UNKNOWN = 0,
+
+	/*
+	 * Not a PCI P2PDMA transfer.
+	 */
+	PCI_P2PDMA_MAP_NONE,
+
+	/*
+	 * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will
+	 * traverse the host bridge and the host bridge is not in the
+	 * allowlist. DMA Mapping routines should return an error when
+	 * this is returned.
+	 */
+	PCI_P2PDMA_MAP_NOT_SUPPORTED,
+
+	/*
+	 * PCI_P2PDMA_MAP_BUS_ADDR: Indicates that two devices can talk to
+	 * each other directly through a PCI switch and the transaction will
+	 * not traverse the host bridge. Such a mapping should program
+	 * the DMA engine with PCI bus addresses.
+	 */
+	PCI_P2PDMA_MAP_BUS_ADDR,
+
+	/*
+	 * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk
+	 * to each other, but the transaction traverses a host bridge on the
+	 * allowlist. In this case, a normal mapping either with CPU physical
+	 * addresses (in the case of dma-direct) or IOVA addresses (in the
+	 * case of IOMMUs) should be used to program the DMA engine.
+	 */
+	PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
+};
+
+struct pci_p2pdma_map_state {
+	struct dev_pagemap *pgmap;
+	enum pci_p2pdma_map_type map;
+	u64 bus_off;
+};
+
+/* helper for pci_p2pdma_state(), do not use directly */
+void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state,
+		struct device *dev, struct page *page);
+
+/**
+ * pci_p2pdma_state - check the P2P transfer state of a page
+ * @state:	P2P state structure
+ * @dev:	device to transfer to/from
+ * @page:	page to map
+ *
+ * Check if @page is a PCI P2PDMA page, and if yes of what kind.  Returns the
+ * map type, and updates @state with all information needed for a P2P transfer.
+ */
+static inline enum pci_p2pdma_map_type
+pci_p2pdma_state(struct pci_p2pdma_map_state *state, struct device *dev,
+		struct page *page)
+{
+	if (IS_ENABLED(CONFIG_PCI_P2PDMA) && is_pci_p2pdma_page(page)) {
+		if (state->pgmap != page_pgmap(page))
+			__pci_p2pdma_update_state(state, dev, page);
+		return state->map;
+	}
+	return PCI_P2PDMA_MAP_NONE;
+}
+
+/**
+ * pci_p2pdma_bus_addr_map - Translate a physical address to a bus address
+ *			     for a PCI_P2PDMA_MAP_BUS_ADDR transfer.
+ * @state:	P2P state structure
+ * @paddr:	physical address to map
+ *
+ * Map a physically contiguous PCI_P2PDMA_MAP_BUS_ADDR transfer.
+ */
+static inline dma_addr_t
+pci_p2pdma_bus_addr_map(struct pci_p2pdma_map_state *state, phys_addr_t paddr)
+{
+	WARN_ON_ONCE(state->map != PCI_P2PDMA_MAP_BUS_ADDR);
+	return paddr + state->bus_off;
+}
+
 #endif /* _LINUX_PCI_P2P_H */