Merge tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - add dma-mapping and block layer helpers to take care of IOMMU merging
   for mmc plus subsequent fixups (Yoshihiro Shimoda)

 - rework handling of the pgprot bits for remapping (me)

 - take care of the dma direct infrastructure for swiotlb-xen (me)

 - improve the dma noncoherent remapping infrastructure (me)

 - better defaults for ->mmap, ->get_sgtable and ->get_required_mask
   (me)

 - cleanup mmaping of coherent DMA allocations (me)

 - various misc cleanups (Andy Shevchenko, me)

* tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping: (41 commits)
  mmc: renesas_sdhi_internal_dmac: Add MMC_CAP2_MERGE_CAPABLE
  mmc: queue: Fix bigger segments usage
  arm64: use asm-generic/dma-mapping.h
  swiotlb-xen: merge xen_unmap_single into xen_swiotlb_unmap_page
  swiotlb-xen: simplify cache maintainance
  swiotlb-xen: use the same foreign page check everywhere
  swiotlb-xen: remove xen_swiotlb_dma_mmap and xen_swiotlb_dma_get_sgtable
  xen: remove the exports for xen_{create,destroy}_contiguous_region
  xen/arm: remove xen_dma_ops
  xen/arm: simplify dma_cache_maint
  xen/arm: use dev_is_dma_coherent
  xen/arm: consolidate page-coherent.h
  xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance
  arm: remove wrappers for the generic dma remap helpers
  dma-mapping: introduce a dma_common_find_pages helper
  dma-mapping: always use VM_DMA_COHERENT for generic DMA remap
  vmalloc: lift the arm flag for coherent mappings to common code
  dma-mapping: provide a better default ->get_required_mask
  dma-mapping: remove the dma_declare_coherent_memory export
  remoteproc: don't allow modular build
  ...

5 files changed, 31 insertions, 22 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3094f2d513b2..d9db32fb75ee 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1110,6 +1110,8 @@ extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
 extern void blk_queue_required_elevator_features(struct request_queue *q,
                                                  unsigned int features);
+extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
+                                              struct device *dev);
 
 /*
  * Number of physical segments as sent to the device.
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 14702e2d6fa8..4a1c4fca475a 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -131,6 +131,7 @@ 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);
+        unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
 #define DMA_MAPPING_ERROR               (~(dma_addr_t)0)
@@ -457,11 +458,13 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
                 void *cpu_addr, dma_addr_t dma_addr, size_t size,
                 unsigned long attrs);
+bool dma_can_mmap(struct device *dev);
 int dma_supported(struct device *dev, u64 mask);
 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);
+unsigned long dma_get_merge_boundary(struct device *dev);
 #else /* CONFIG_HAS_DMA */
 static inline dma_addr_t dma_map_page_attrs(struct device *dev,
                 struct page *page, size_t offset, size_t size,
@@ -547,6 +550,10 @@ static inline int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 {
         return -ENXIO;
 }
+static inline bool dma_can_mmap(struct device *dev)
+{
+        return false;
+}
 static inline int dma_supported(struct device *dev, u64 mask)
 {
         return 0;
@@ -567,6 +574,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
         return 0;
 }
+static inline unsigned long dma_get_merge_boundary(struct device *dev)
+{
+        return 0;
+}
 #endif /* CONFIG_HAS_DMA */
 
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
@@ -610,16 +621,14 @@ extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
                 void *cpu_addr, dma_addr_t dma_addr, size_t size,
                 unsigned long attrs);
 
+struct page **dma_common_find_pages(void *cpu_addr);
 void *dma_common_contiguous_remap(struct page *page, size_t size,
-                        unsigned long vm_flags,
                         pgprot_t prot, const void *caller);
 
 void *dma_common_pages_remap(struct page **pages, size_t size,
-                        unsigned long vm_flags, pgprot_t prot,
-                        const void *caller);
-void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
+                        pgprot_t prot, const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size);
 
-int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot);
 bool dma_in_atomic_pool(void *start, size_t size);
 void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags);
 bool dma_free_from_pool(void *start, size_t size);
@@ -749,7 +758,6 @@ static inline int dma_get_cache_alignment(void)
 #ifdef CONFIG_DMA_DECLARE_COHERENT
 int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
                                 dma_addr_t device_addr, size_t size);
-void dma_release_declared_memory(struct device *dev);
 #else
 static inline int
 dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
@@ -757,11 +765,6 @@ dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 {
         return -ENOSYS;
 }
-
-static inline void
-dma_release_declared_memory(struct device *dev)
-{
-}
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
 static inline void *dmam_alloc_coherent(struct device *dev, size_t size,
@@ -781,9 +784,6 @@ static inline void *dma_alloc_wc(struct device *dev, size_t size,
 
         return dma_alloc_attrs(dev, size, dma_addr, gfp, attrs);
 }
-#ifndef dma_alloc_writecombine
-#define dma_alloc_writecombine dma_alloc_wc
-#endif
 
 static inline void dma_free_wc(struct device *dev, size_t size,
                                void *cpu_addr, dma_addr_t dma_addr)
@@ -791,9 +791,6 @@ static inline void dma_free_wc(struct device *dev, size_t size,
         return dma_free_attrs(dev, size, cpu_addr, dma_addr,
                               DMA_ATTR_WRITE_COMBINE);
 }
-#ifndef dma_free_writecombine
-#define dma_free_writecombine dma_free_wc
-#endif
 
 static inline int dma_mmap_wc(struct device *dev,
                               struct vm_area_struct *vma,
@@ -803,9 +800,6 @@ static inline int dma_mmap_wc(struct device *dev,
         return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size,
                               DMA_ATTR_WRITE_COMBINE);
 }
-#ifndef dma_mmap_writecombine
-#define dma_mmap_writecombine dma_mmap_wc
-#endif
 
 #ifdef CONFIG_NEED_DMA_MAP_STATE
 #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)        dma_addr_t ADDR_NAME
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 0bff3d7fac92..dd3de6d88fc0 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -3,6 +3,7 @@
 #define _LINUX_DMA_NONCOHERENT_H 1
 
 #include <linux/dma-mapping.h>
+#include <asm/pgtable.h>
 
 #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
 #include <asm/dma-coherence.h>
@@ -42,10 +43,18 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
                 dma_addr_t dma_addr, unsigned long attrs);
 long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
                 dma_addr_t dma_addr);
-pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
-                unsigned long attrs);
 
 #ifdef CONFIG_MMU
+/*
+ * Page protection so that devices that can't snoop CPU caches can use the
+ * memory coherently.  We default to pgprot_noncached which is usually used
+ * for ioremap as a safe bet, but architectures can override this with less
+ * strict semantics if possible.
+ */
+#ifndef pgprot_dmacoherent
+#define pgprot_dmacoherent(prot)        pgprot_noncached(prot)
+#endif
+
 pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
 #else
 static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 4704b77259ee..ba703384bea0 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -368,6 +368,7 @@ struct mmc_host {
 #define MMC_CAP2_CQE            (1 << 23)       /* Has eMMC command queue engine */
 #define MMC_CAP2_CQE_DCMD       (1 << 24)       /* CQE can issue a direct command */
 #define MMC_CAP2_AVOID_3_3V     (1 << 25)       /* Host must negotiate down from 3.3V */
+#define MMC_CAP2_MERGE_CAPABLE  (1 << 26)       /* Host can merge a segment over the segment size */
 
         int                     fixed_drv_type; /* fixed driver type for non-removable media */
 
@@ -397,6 +398,7 @@ struct mmc_host {
         unsigned int            retune_paused:1; /* re-tuning is temporarily disabled */
         unsigned int            use_blk_mq:1;   /* use blk-mq */
         unsigned int            retune_crc_disable:1; /* don't trigger retune upon crc */
+        unsigned int            can_dma_map_merge:1; /* merging can be used */
 
         int                     rescan_disable; /* disable card detection */
         int                     rescan_entered; /* used with nonremovable devices */
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 9b21d0047710..dfa718ffdd4f 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -18,6 +18,7 @@ struct notifier_block;		/* in notifier.h */
 #define VM_ALLOC                0x00000002      /* vmalloc() */
 #define VM_MAP                  0x00000004      /* vmap()ed pages */
 #define VM_USERMAP              0x00000008      /* suitable for remap_vmalloc_range */
+#define VM_DMA_COHERENT         0x00000010      /* dma_alloc_coherent */
 #define VM_UNINITIALIZED        0x00000020      /* vm_struct is not fully initialized */
 #define VM_NO_GUARD             0x00000040      /* don't add guard page */
 #define VM_KASAN                0x00000080      /* has allocated kasan shadow memory */
@@ -26,6 +27,7 @@ struct notifier_block;		/* in notifier.h */
  * vfree_atomic().
  */
 #define VM_FLUSH_RESET_PERMS    0x00000100      /* Reset direct map and flush TLB on unmap */
+
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*