Merge tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - convert arm32 to the common dma-direct code (Arnd Bergmann, Robin
   Murphy, Christoph Hellwig)

 - restructure the PCIe peer to peer mapping support (Logan Gunthorpe)

 - allow the IOMMU code to communicate an optional DMA mapping length
   and use that in scsi and libata (John Garry)

 - split the global swiotlb lock (Tianyu Lan)

 - various fixes and cleanup (Chao Gao, Dan Carpenter, Dongli Zhang,
   Lukas Bulwahn, Robin Murphy)

* tag 'dma-mapping-5.20-2022-08-06' of git://git.infradead.org/users/hch/dma-mapping: (45 commits)
  swiotlb: fix passing local variable to debugfs_create_ulong()
  dma-mapping: reformat comment to suppress htmldoc warning
  PCI/P2PDMA: Remove pci_p2pdma_[un]map_sg()
  RDMA/rw: drop pci_p2pdma_[un]map_sg()
  RDMA/core: introduce ib_dma_pci_p2p_dma_supported()
  nvme-pci: convert to using dma_map_sgtable()
  nvme-pci: check DMA ops when indicating support for PCI P2PDMA
  iommu/dma: support PCI P2PDMA pages in dma-iommu map_sg
  iommu: Explicitly skip bus address marked segments in __iommu_map_sg()
  dma-mapping: add flags to dma_map_ops to indicate PCI P2PDMA support
  dma-direct: support PCI P2PDMA pages in dma-direct map_sg
  dma-mapping: allow EREMOTEIO return code for P2PDMA transfers
  PCI/P2PDMA: Introduce helpers for dma_map_sg implementations
  PCI/P2PDMA: Attempt to set map_type if it has not been set
  lib/scatterlist: add flag for indicating P2PDMA segments in an SGL
  swiotlb: clean up some coding style and minor issues
  dma-mapping: update comment after dmabounce removal
  scsi: sd: Add a comment about limiting max_sectors to shost optimal limit
  ata: libata-scsi: cap ata_device->max_sectors according to shost->max_sectors
  scsi: scsi_transport_sas: cap shost opt_sectors according to DMA optimal limit
  ...

8 files changed, 163 insertions, 38 deletions

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 0d5b06b3a4a6..010df04358aa 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -11,7 +11,17 @@
 
 struct cma;
 
+/*
+ * Values for struct dma_map_ops.flags:
+ *
+ * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can
+ * handle PCI P2PDMA pages in the map_sg/unmap_sg operation.
+ */
+#define DMA_F_PCI_P2PDMA_SUPPORTED     (1 << 0)
+
 struct dma_map_ops {
+	unsigned int flags;
+
 	void *(*alloc)(struct device *dev, size_t size,
 			dma_addr_t *dma_handle, gfp_t gfp,
 			unsigned long attrs);
@@ -69,6 +79,7 @@ struct dma_map_ops {
 	int (*dma_supported)(struct device *dev, u64 mask);
 	u64 (*get_required_mask)(struct device *dev);
 	size_t (*max_mapping_size)(struct device *dev);
+	size_t (*opt_mapping_size)(void);
 	unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
@@ -379,4 +390,57 @@ static inline void debug_dma_dump_mappings(struct device *dev)
 
 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 dca2b1355bb1..25a30906289d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -140,10 +140,12 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		unsigned long attrs);
 bool dma_can_mmap(struct device *dev);
 int dma_supported(struct device *dev, u64 mask);
+bool dma_pci_p2pdma_supported(struct device *dev);
 int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
+size_t dma_opt_mapping_size(struct device *dev);
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
 struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
@@ -250,6 +252,10 @@ static inline int dma_supported(struct device *dev, u64 mask)
 {
 	return 0;
 }
+static inline bool dma_pci_p2pdma_supported(struct device *dev)
+{
+	return false;
+}
 static inline int dma_set_mask(struct device *dev, u64 mask)
 {
 	return -EIO;
@@ -266,6 +272,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
 }
+static inline size_t dma_opt_mapping_size(struct device *dev)
+{
+	return 0;
+}
 static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return false;
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 320a70e40233..c6ba6d95d79c 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -79,6 +79,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
 int iova_cache_get(void);
 void iova_cache_put(void);
 
+unsigned long iova_rcache_range(void);
+
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
 void __free_iova(struct iova_domain *iovad, struct iova *iova);
 struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
index 8318a97c9c61..2c07aa6b7665 100644
--- a/include/linux/pci-p2pdma.h
+++ b/include/linux/pci-p2pdma.h
@@ -30,10 +30,6 @@ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev,
 					 unsigned int *nents, u32 length);
 void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl);
 void pci_p2pmem_publish(struct pci_dev *pdev, bool publish);
-int pci_p2pdma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
-void pci_p2pdma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
 int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev,
 			    bool *use_p2pdma);
 ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev,
@@ -83,17 +79,6 @@ static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev,
 static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish)
 {
 }
-static inline int pci_p2pdma_map_sg_attrs(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	return 0;
-}
-static inline void pci_p2pdma_unmap_sg_attrs(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-}
 static inline int pci_p2pdma_enable_store(const char *page,
 		struct pci_dev **p2p_dev, bool *use_p2pdma)
 {
@@ -119,16 +104,4 @@ static inline struct pci_dev *pci_p2pmem_find(struct device *client)
 	return pci_p2pmem_find_many(&client, 1);
 }
 
-static inline int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg,
-				    int nents, enum dma_data_direction dir)
-{
-	return pci_p2pdma_map_sg_attrs(dev, sg, nents, dir, 0);
-}
-
-static inline void pci_p2pdma_unmap_sg(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir)
-{
-	pci_p2pdma_unmap_sg_attrs(dev, sg, nents, dir, 0);
-}
-
 #endif /* _LINUX_PCI_P2P_H */
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 7ff9d6386c12..375a5e90d86a 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -16,6 +16,9 @@ struct scatterlist {
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
 	unsigned int	dma_length;
 #endif
+#ifdef CONFIG_PCI_P2PDMA
+	unsigned int    dma_flags;
+#endif
 };
 
 /*
@@ -245,6 +248,72 @@ static inline void sg_unmark_end(struct scatterlist *sg)
 	sg->page_link &= ~SG_END;
 }
 
+/*
+ * CONFGI_PCI_P2PDMA depends on CONFIG_64BIT which means there is 4 bytes
+ * in struct scatterlist (assuming also CONFIG_NEED_SG_DMA_LENGTH is set).
+ * Use this padding for DMA flags bits to indicate when a specific
+ * dma address is a bus address.
+ */
+#ifdef CONFIG_PCI_P2PDMA
+
+#define SG_DMA_BUS_ADDRESS (1 << 0)
+
+/**
+ * sg_dma_is_bus address - Return whether a given segment was marked
+ *			   as a bus address
+ * @sg:		 SG entry
+ *
+ * Description:
+ *   Returns true if sg_dma_mark_bus_address() has been called on
+ *   this segment.
+ **/
+static inline bool sg_is_dma_bus_address(struct scatterlist *sg)
+{
+	return sg->dma_flags & SG_DMA_BUS_ADDRESS;
+}
+
+/**
+ * sg_dma_mark_bus address - Mark the scatterlist entry as a bus address
+ * @sg:		 SG entry
+ *
+ * Description:
+ *   Marks the passed in sg entry to indicate that the dma_address is
+ *   a bus address and doesn't need to be unmapped. This should only be
+ *   used by dma_map_sg() implementations to mark bus addresses
+ *   so they can be properly cleaned up in dma_unmap_sg().
+ **/
+static inline void sg_dma_mark_bus_address(struct scatterlist *sg)
+{
+	sg->dma_flags |= SG_DMA_BUS_ADDRESS;
+}
+
+/**
+ * sg_unmark_bus_address - Unmark the scatterlist entry as a bus address
+ * @sg:		 SG entry
+ *
+ * Description:
+ *   Clears the bus address mark.
+ **/
+static inline void sg_dma_unmark_bus_address(struct scatterlist *sg)
+{
+	sg->dma_flags &= ~SG_DMA_BUS_ADDRESS;
+}
+
+#else
+
+static inline bool sg_is_dma_bus_address(struct scatterlist *sg)
+{
+	return false;
+}
+static inline void sg_dma_mark_bus_address(struct scatterlist *sg)
+{
+}
+static inline void sg_dma_unmark_bus_address(struct scatterlist *sg)
+{
+}
+
+#endif
+
 /**
  * sg_phys - Return physical address of an sg entry
  * @sg:	     SG entry
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 7ed35dd3de6e..35bc4e281c21 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -60,7 +60,6 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 
 #ifdef CONFIG_SWIOTLB
-extern enum swiotlb_force swiotlb_force;
 
 /**
  * struct io_tlb_mem - IO TLB Memory Pool Descriptor
@@ -80,15 +79,14 @@ extern enum swiotlb_force swiotlb_force;
  * @used:	The number of used IO TLB block.
  * @list:	The free list describing the number of free entries available
  *		from each index.
- * @index:	The index to start searching in the next round.
  * @orig_addr:	The original address corresponding to a mapped entry.
  * @alloc_size:	Size of the allocated buffer.
- * @lock:	The lock to protect the above data structures in the map and
- *		unmap calls.
  * @debugfs:	The dentry to debugfs.
  * @late_alloc:	%true if allocated using the page allocator
  * @force_bounce: %true if swiotlb bouncing is forced
  * @for_alloc:  %true if the pool is used for memory allocation
+ * @nareas:  The area number in the pool.
+ * @area_nslabs: The slot number in the area.
  */
 struct io_tlb_mem {
 	phys_addr_t start;
@@ -96,17 +94,14 @@ struct io_tlb_mem {
 	void *vaddr;
 	unsigned long nslabs;
 	unsigned long used;
-	unsigned int index;
-	spinlock_t lock;
 	struct dentry *debugfs;
 	bool late_alloc;
 	bool force_bounce;
 	bool for_alloc;
-	struct io_tlb_slot {
-		phys_addr_t orig_addr;
-		size_t alloc_size;
-		unsigned int list;
-	} *slots;
+	unsigned int nareas;
+	unsigned int area_nslabs;
+	struct io_tlb_area *areas;
+	struct io_tlb_slot *slots;
 };
 extern struct io_tlb_mem io_tlb_default_mem;
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 7c2f76f34f6f..975d6e9efbcb 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4013,6 +4013,17 @@ static inline bool ib_uses_virt_dma(struct ib_device *dev)
 	return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device;
 }
 
+/*
+ * Check if a IB device's underlying DMA mapping supports P2PDMA transfers.
+ */
+static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev)
+{
+	if (ib_uses_virt_dma(dev))
+		return false;
+
+	return dma_pci_p2pdma_supported(dev->dma_device);
+}
+
 /**
  * ib_dma_mapping_error - check a DMA addr for error
  * @dev: The device for which the dma_addr was created
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 65082ecdd557..b6e41ee3d566 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -607,6 +607,7 @@ struct Scsi_Host {
 	short unsigned int sg_tablesize;
 	short unsigned int sg_prot_tablesize;
 	unsigned int max_sectors;
+	unsigned int opt_sectors;
 	unsigned int max_segment_size;
 	unsigned long dma_boundary;
 	unsigned long virt_boundary_mask;