Merge tag 'dma-mapping-5.10' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - rework the non-coherent DMA allocator

 - move private definitions out of <linux/dma-mapping.h>

 - lower CMA_ALIGNMENT (Paul Cercueil)

 - remove the omap1 dma address translation in favor of the common code

 - make dma-direct aware of multiple dma offset ranges (Jim Quinlan)

 - support per-node DMA CMA areas (Barry Song)

 - increase the default seg boundary limit (Nicolin Chen)

 - misc fixes (Robin Murphy, Thomas Tai, Xu Wang)

 - various cleanups

* tag 'dma-mapping-5.10' of git://git.infradead.org/users/hch/dma-mapping: (63 commits)
  ARM/ixp4xx: add a missing include of dma-map-ops.h
  dma-direct: simplify the DMA_ATTR_NO_KERNEL_MAPPING handling
  dma-direct: factor out a dma_direct_alloc_from_pool helper
  dma-direct check for highmem pages in dma_direct_alloc_pages
  dma-mapping: merge <linux/dma-noncoherent.h> into <linux/dma-map-ops.h>
  dma-mapping: move large parts of <linux/dma-direct.h> to kernel/dma
  dma-mapping: move dma-debug.h to kernel/dma/
  dma-mapping: remove <asm/dma-contiguous.h>
  dma-mapping: merge <linux/dma-contiguous.h> into <linux/dma-map-ops.h>
  dma-contiguous: remove dma_contiguous_set_default
  dma-contiguous: remove dev_set_cma_area
  dma-contiguous: remove dma_declare_contiguous
  dma-mapping: split <linux/dma-mapping.h>
  cma: decrease CMA_ALIGNMENT lower limit to 2
  firewire-ohci: use dma_alloc_pages
  dma-iommu: implement ->alloc_noncoherent
  dma-mapping: add new {alloc,free}_noncoherent dma_map_ops methods
  dma-mapping: add a new dma_alloc_pages API
  dma-mapping: remove dma_cache_sync
  53c700: convert to dma_alloc_noncoherent
  ...

4 files changed, 48 insertions, 16 deletions

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 4b1b02c80f55..b9cf59443843 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-iommu.h>
 #include <linux/iommu-helper.h>
@@ -28,7 +28,6 @@
 #include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
-#include <linux/dma-contiguous.h>
 #include <linux/irqdomain.h>
 #include <linux/percpu.h>
 #include <linux/iova.h>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index cd6e3c70ebb3..0cbcd3fc3e7e 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -10,9 +10,8 @@
 
 #include <linux/acpi_iort.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-iommu.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
@@ -572,6 +571,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
  * @size: Size of buffer in bytes
  * @dma_handle: Out argument for allocated DMA handle
  * @gfp: Allocation flags
+ * @prot: pgprot_t to use for the remapped mapping
  * @attrs: DMA attributes for this allocation
  *
  * If @size is less than PAGE_SIZE, then a full CPU page will be allocated,
@@ -580,14 +580,14 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
  * Return: Mapped virtual address, or NULL on failure.
  */
 static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+		dma_addr_t *dma_handle, gfp_t gfp, pgprot_t prot,
+		unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	bool coherent = dev_is_dma_coherent(dev);
 	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
-	pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 	struct page **pages;
 	struct sg_table sgt;
@@ -1030,8 +1030,10 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	gfp |= __GFP_ZERO;
 
 	if (IS_ENABLED(CONFIG_DMA_REMAP) && gfpflags_allow_blocking(gfp) &&
-	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS))
-		return iommu_dma_alloc_remap(dev, size, handle, gfp, attrs);
+	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS)) {
+		return iommu_dma_alloc_remap(dev, size, handle, gfp,
+				dma_pgprot(dev, PAGE_KERNEL, attrs), attrs);
+	}
 
 	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    !gfpflags_allow_blocking(gfp) && !coherent)
@@ -1052,6 +1054,34 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	return cpu_addr;
 }
 
+#ifdef CONFIG_DMA_REMAP
+static void *iommu_dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	if (!gfpflags_allow_blocking(gfp)) {
+		struct page *page;
+
+		page = dma_common_alloc_pages(dev, size, handle, dir, gfp);
+		if (!page)
+			return NULL;
+		return page_address(page);
+	}
+
+	return iommu_dma_alloc_remap(dev, size, handle, gfp | __GFP_ZERO,
+				     PAGE_KERNEL, 0);
+}
+
+static void iommu_dma_free_noncoherent(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t handle, enum dma_data_direction dir)
+{
+	__iommu_dma_unmap(dev, handle, size);
+	__iommu_dma_free(dev, size, cpu_addr);
+}
+#else
+#define iommu_dma_alloc_noncoherent		NULL
+#define iommu_dma_free_noncoherent		NULL
+#endif /* CONFIG_DMA_REMAP */
+
 static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
@@ -1120,6 +1150,10 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
+	.alloc_noncoherent	= iommu_dma_alloc_noncoherent,
+	.free_noncoherent	= iommu_dma_free_noncoherent,
 	.mmap			= iommu_dma_mmap,
 	.get_sgtable		= iommu_dma_get_sgtable,
 	.map_page		= iommu_dma_map_page,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 2e2ba294bb15..8651f6d4dfa0 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -23,7 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/dmar.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mempool.h>
 #include <linux/memory.h>
 #include <linux/cpu.h>
@@ -37,7 +37,7 @@
 #include <linux/dmi.h>
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/crash_dump.h>
 #include <linux/numa.h>
@@ -3747,6 +3747,8 @@ static const struct dma_map_ops intel_dma_ops = {
 	.dma_supported = dma_direct_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 	.get_required_mask = intel_get_required_mask,
 };
 
@@ -3814,7 +3816,7 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
 	 */
 	if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
 		tlb_addr = swiotlb_tbl_map_single(dev,
-				__phys_to_dma(dev, io_tlb_start),
+				phys_to_dma_unencrypted(dev, io_tlb_start),
 				paddr, size, aligned_size, dir, attrs);
 		if (tlb_addr == DMA_MAPPING_ERROR) {
 			goto swiotlb_error;
@@ -4000,6 +4002,8 @@ static const struct dma_map_ops bounce_dma_ops = {
 	.sync_sg_for_device	= bounce_sync_sg_for_device,
 	.map_resource		= bounce_map_resource,
 	.unmap_resource		= bounce_unmap_resource,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 	.dma_supported		= dma_direct_supported,
 };
 
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 534810b6be77..a7a9bc08dcd1 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -728,11 +728,6 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
 		return NULL;
 
-	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
-		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
-		return NULL;
-	}
-
 	data = kmalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return NULL;