Merge tag 'dma-mapping-5.18' of git://git.infradead.org/users/hch/dma…

…-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - do not zero buffer in set_memory_decrypted (Kirill A. Shutemov)

 - fix return value of dma-debug __setup handlers (Randy Dunlap)

 - swiotlb cleanups (Robin Murphy)

 - remove most remaining users of the pci-dma-compat.h API
   (Christophe JAILLET)

 - share the ABI header for the DMA map_benchmark with userspace
   (Tian Tao)

 - update the maintainer for DMA MAPPING BENCHMARK (Xiang Chen)

 - remove CONFIG_DMA_REMAP (me)

* tag 'dma-mapping-5.18' of git://git.infradead.org/users/hch/dma-mapping:
  dma-mapping: benchmark: extract a common header file for map_benchmark definition
  dma-debug: fix return value of __setup handlers
  dma-mapping: remove CONFIG_DMA_REMAP
  media: v4l2-pci-skeleton: Remove usage of the deprecated "pci-dma-compat.h" API
  rapidio/tsi721: Remove usage of the deprecated "pci-dma-compat.h" API
  sparc: Remove usage of the deprecated "pci-dma-compat.h" API
  agp/intel: Remove usage of the deprecated "pci-dma-compat.h" API
  alpha: Remove usage of the deprecated "pci-dma-compat.h" API
  MAINTAINERS: update maintainer list of DMA MAPPING BENCHMARK
  swiotlb: simplify array allocation
  swiotlb: tidy up includes
  swiotlb: simplify debugfs setup
  swiotlb: do not zero buffer in set_memory_decrypted()

MAINTAINERS

@@ -5880,7 +5880,7 @@ F:	include/linux/dma-map-ops.h
 F:	kernel/dma/
 
 DMA MAPPING BENCHMARK
-M:	Barry Song <song.bao.hua@hisilicon.com>
+M:	Xiang Chen <chenxiang66@hisilicon.com>
 L:	[email protected]
 F:	kernel/dma/map_benchmark.c
 F:	tools/testing/selftests/dma/

arch/alpha/include/asm/floppy.h

@@ -43,17 +43,18 @@ alpha_fd_dma_setup(char *addr, unsigned long size, int mode, int io)
 	static int prev_dir;
 	int dir;
 
-	dir = (mode != DMA_MODE_READ) ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE;
+	dir = (mode != DMA_MODE_READ) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 
 	if (bus_addr 
 	    && (addr != prev_addr || size != prev_size || dir != prev_dir)) {
 		/* different from last time -- unmap prev */
-		pci_unmap_single(isa_bridge, bus_addr, prev_size, prev_dir);
+		dma_unmap_single(&isa_bridge->dev, bus_addr, prev_size,
+				 prev_dir);
 		bus_addr = 0;
 	}
 
 	if (!bus_addr)	/* need to map it */
-		bus_addr = pci_map_single(isa_bridge, addr, size, dir);
+		bus_addr = dma_map_single(&isa_bridge->dev, addr, size, dir);
 
 	/* remember this one as prev */
 	prev_addr = addr;

arch/alpha/kernel/pci_iommu.c

@@ -333,7 +333,7 @@ static dma_addr_t alpha_pci_map_page(struct device *dev, struct page *page,
 	struct pci_dev *pdev = alpha_gendev_to_pci(dev);
 	int dac_allowed;
 
-	BUG_ON(dir == PCI_DMA_NONE);
+	BUG_ON(dir == DMA_NONE);
 
 	dac_allowed = pdev ? pci_dac_dma_supported(pdev, pdev->dma_mask) : 0; 
 	return pci_map_single_1(pdev, (char *)page_address(page) + offset, 
@@ -356,7 +356,7 @@ static void alpha_pci_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	struct pci_iommu_arena *arena;
 	long dma_ofs, npages;
 
-	BUG_ON(dir == PCI_DMA_NONE);
+	BUG_ON(dir == DMA_NONE);
 
 	if (dma_addr >= __direct_map_base
 	    && dma_addr < __direct_map_base + __direct_map_size) {
@@ -460,7 +460,7 @@ static void alpha_pci_free_coherent(struct device *dev, size_t size,
 				    unsigned long attrs)
 {
 	struct pci_dev *pdev = alpha_gendev_to_pci(dev);
-	pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_single(&pdev->dev, dma_addr, size, DMA_BIDIRECTIONAL);
 	free_pages((unsigned long)cpu_addr, get_order(size));
 
 	DBGA2("pci_free_consistent: [%llx,%zx] from %ps\n",
@@ -639,7 +639,7 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg,
 	dma_addr_t max_dma;
 	int dac_allowed;
 
-	BUG_ON(dir == PCI_DMA_NONE);
+	BUG_ON(dir == DMA_NONE);
 
 	dac_allowed = dev ? pci_dac_dma_supported(pdev, pdev->dma_mask) : 0;
 
@@ -702,7 +702,7 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg,
 	/* Some allocation failed while mapping the scatterlist
 	   entries.  Unmap them now.  */
 	if (out > start)
-		pci_unmap_sg(pdev, start, out - start, dir);
+		dma_unmap_sg(&pdev->dev, start, out - start, dir);
 	return -ENOMEM;
 }
 
@@ -722,7 +722,7 @@ static void alpha_pci_unmap_sg(struct device *dev, struct scatterlist *sg,
 	dma_addr_t max_dma;
 	dma_addr_t fbeg, fend;
 
-	BUG_ON(dir == PCI_DMA_NONE);
+	BUG_ON(dir == DMA_NONE);
 
 	if (! alpha_mv.mv_pci_tbi)
 		return;

arch/arm/Kconfig

@@ -49,7 +49,7 @@ config ARM
 	select DMA_DECLARE_COHERENT
 	select DMA_GLOBAL_POOL if !MMU
 	select DMA_OPS
-	select DMA_REMAP if MMU
+	select DMA_NONCOHERENT_MMAP if MMU
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
 	select GENERIC_ALLOCATOR

arch/sparc/kernel/ioport.c

@@ -309,7 +309,7 @@ arch_initcall(sparc_register_ioport);
 void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
-	if (dir != PCI_DMA_TODEVICE &&
+	if (dir != DMA_TO_DEVICE &&
 	    sparc_cpu_model == sparc_leon &&
 	    !sparc_leon3_snooping_enabled())
 		leon_flush_dcache_all();

arch/xtensa/Kconfig

@@ -18,7 +18,7 @@ config XTENSA
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select DMA_REMAP if MMU
+	select DMA_NONCOHERENT_MMAP if MMU
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_SHOW
 	select GENERIC_LIB_CMPDI2

drivers/char/agp/intel-gtt.c

@@ -111,8 +111,8 @@ static int intel_gtt_map_memory(struct page **pages,
 	for_each_sg(st->sgl, sg, num_entries, i)
 		sg_set_page(sg, pages[i], PAGE_SIZE, 0);
 
-	if (!pci_map_sg(intel_private.pcidev,
-			st->sgl, st->nents, PCI_DMA_BIDIRECTIONAL))
+	if (!dma_map_sg(&intel_private.pcidev->dev, st->sgl, st->nents,
+			DMA_BIDIRECTIONAL))
 		goto err;
 
 	return 0;
@@ -127,8 +127,8 @@ static void intel_gtt_unmap_memory(struct scatterlist *sg_list, int num_sg)
 	struct sg_table st;
 	DBG("try unmapping %lu pages\n", (unsigned long)mem->page_count);
 
-	pci_unmap_sg(intel_private.pcidev, sg_list,
-		     num_sg, PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_sg(&intel_private.pcidev->dev, sg_list, num_sg,
+		     DMA_BIDIRECTIONAL);
 
 	st.sgl = sg_list;
 	st.orig_nents = st.nents = num_sg;
@@ -303,9 +303,9 @@ static int intel_gtt_setup_scratch_page(void)
 	set_pages_uc(page, 1);
 
 	if (intel_private.needs_dmar) {
-		dma_addr = pci_map_page(intel_private.pcidev, page, 0,
-				    PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-		if (pci_dma_mapping_error(intel_private.pcidev, dma_addr)) {
+		dma_addr = dma_map_page(&intel_private.pcidev->dev, page, 0,
+					PAGE_SIZE, DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(&intel_private.pcidev->dev, dma_addr)) {
 			__free_page(page);
 			return -EINVAL;
 		}
@@ -552,9 +552,9 @@ static void intel_gtt_teardown_scratch_page(void)
 {
 	set_pages_wb(intel_private.scratch_page, 1);
 	if (intel_private.needs_dmar)
-		pci_unmap_page(intel_private.pcidev,
-			       intel_private.scratch_page_dma,
-			       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+		dma_unmap_page(&intel_private.pcidev->dev,
+			       intel_private.scratch_page_dma, PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
 	__free_page(intel_private.scratch_page);
 }
 
@@ -1412,13 +1412,13 @@ int intel_gmch_probe(struct pci_dev *bridge_pdev, struct pci_dev *gpu_pdev,
 
 	if (bridge) {
 		mask = intel_private.driver->dma_mask_size;
-		if (pci_set_dma_mask(intel_private.pcidev, DMA_BIT_MASK(mask)))
+		if (dma_set_mask(&intel_private.pcidev->dev, DMA_BIT_MASK(mask)))
 			dev_err(&intel_private.pcidev->dev,
 				"set gfx device dma mask %d-bit failed!\n",
 				mask);
 		else
-			pci_set_consistent_dma_mask(intel_private.pcidev,
-						    DMA_BIT_MASK(mask));
+			dma_set_coherent_mask(&intel_private.pcidev->dev,
+					      DMA_BIT_MASK(mask));
 	}
 
 	if (intel_gtt_init() != 0) {

drivers/iommu/dma-iommu.c

@@ -856,7 +856,6 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 	return NULL;
 }
 
-#ifdef CONFIG_DMA_REMAP
 static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev,
 		size_t size, enum dma_data_direction dir, gfp_t gfp,
 		unsigned long attrs)
@@ -886,7 +885,6 @@ static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
 	sg_free_table(&sh->sgt);
 	kfree(sh);
 }
-#endif /* CONFIG_DMA_REMAP */
 
 static void iommu_dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
@@ -1280,7 +1278,7 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 	    dma_free_from_pool(dev, cpu_addr, alloc_size))
 		return;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		/*
 		 * If it the address is remapped, then it's either non-coherent
 		 * or highmem CMA, or an iommu_dma_alloc_remap() construction.
@@ -1322,7 +1320,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) {
+	if (!coherent || PageHighMem(page)) {
 		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 
 		cpu_addr = dma_common_contiguous_remap(page, alloc_size,
@@ -1354,7 +1352,7 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 
 	gfp |= __GFP_ZERO;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && gfpflags_allow_blocking(gfp) &&
+	if (gfpflags_allow_blocking(gfp) &&
 	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS)) {
 		return iommu_dma_alloc_remap(dev, size, handle, gfp,
 				dma_pgprot(dev, PAGE_KERNEL, attrs), attrs);
@@ -1395,7 +1393,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	if (off >= nr_pages || vma_pages(vma) > nr_pages - off)
 		return -ENXIO;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		struct page **pages = dma_common_find_pages(cpu_addr);
 
 		if (pages)
@@ -1417,7 +1415,7 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 	struct page *page;
 	int ret;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		struct page **pages = dma_common_find_pages(cpu_addr);
 
 		if (pages) {
@@ -1449,10 +1447,8 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.free			= iommu_dma_free,
 	.alloc_pages		= dma_common_alloc_pages,
 	.free_pages		= dma_common_free_pages,
-#ifdef CONFIG_DMA_REMAP
 	.alloc_noncontiguous	= iommu_dma_alloc_noncontiguous,
 	.free_noncontiguous	= iommu_dma_free_noncontiguous,
-#endif
 	.mmap			= iommu_dma_mmap,
 	.get_sgtable		= iommu_dma_get_sgtable,
 	.map_page		= iommu_dma_map_page,

drivers/rapidio/devices/tsi721.c

@@ -2836,17 +2836,17 @@ static int tsi721_probe(struct pci_dev *pdev,
 	}
 
 	/* Configure DMA attributes. */
-	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) {
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			tsi_err(&pdev->dev, "Unable to set DMA mask");
 			goto err_unmap_bars;
 		}
 
-		if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)))
+		if (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)))
 			tsi_info(&pdev->dev, "Unable to set consistent DMA mask");
 	} else {
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+		err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
 		if (err)
 			tsi_info(&pdev->dev, "Unable to set consistent DMA mask");
 	}

include/linux/map_benchmark.h

@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 HiSilicon Limited.
+ */
+
+#ifndef _KERNEL_DMA_BENCHMARK_H
+#define _KERNEL_DMA_BENCHMARK_H
+
+#define DMA_MAP_BENCHMARK       _IOWR('d', 1, struct map_benchmark)
+#define DMA_MAP_MAX_THREADS     1024
+#define DMA_MAP_MAX_SECONDS     300
+#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC)
+
+#define DMA_MAP_BIDIRECTIONAL   0
+#define DMA_MAP_TO_DEVICE       1
+#define DMA_MAP_FROM_DEVICE     2
+
+struct map_benchmark {
+	__u64 avg_map_100ns; /* average map latency in 100ns */
+	__u64 map_stddev; /* standard deviation of map latency */
+	__u64 avg_unmap_100ns; /* as above */
+	__u64 unmap_stddev;
+	__u32 threads; /* how many threads will do map/unmap in parallel */
+	__u32 seconds; /* how long the test will last */
+	__s32 node; /* which numa node this benchmark will run on */
+	__u32 dma_bits; /* DMA addressing capability */
+	__u32 dma_dir; /* DMA data direction */
+	__u32 dma_trans_ns; /* time for DMA transmission in ns */
+	__u32 granule;  /* how many PAGE_SIZE will do map/unmap once a time */
+};
+#endif /* _KERNEL_DMA_BENCHMARK_H */

kernel/dma/Kconfig

@@ -110,15 +110,10 @@ config DMA_GLOBAL_POOL
 	select DMA_DECLARE_COHERENT
 	bool
 
-config DMA_REMAP
-	bool
-	depends on MMU
-	select DMA_NONCOHERENT_MMAP
-
 config DMA_DIRECT_REMAP
 	bool
-	select DMA_REMAP
 	select DMA_COHERENT_POOL
+	select DMA_NONCOHERENT_MMAP
 
 config DMA_CMA
 	bool "DMA Contiguous Memory Allocator"

kernel/dma/Makefile

@@ -8,5 +8,5 @@ obj-$(CONFIG_DMA_DECLARE_COHERENT)	+= coherent.o
 obj-$(CONFIG_DMA_API_DEBUG)		+= debug.o
 obj-$(CONFIG_SWIOTLB)			+= swiotlb.o
 obj-$(CONFIG_DMA_COHERENT_POOL)		+= pool.o
-obj-$(CONFIG_DMA_REMAP)			+= remap.o
+obj-$(CONFIG_MMU)			+= remap.o
 obj-$(CONFIG_DMA_MAP_BENCHMARK)		+= map_benchmark.o

kernel/dma/debug.c

@@ -927,7 +927,7 @@ static __init int dma_debug_cmdline(char *str)
 		global_disable = true;
 	}
 
-	return 0;
+	return 1;
 }
 
 static __init int dma_debug_entries_cmdline(char *str)
@@ -936,7 +936,7 @@ static __init int dma_debug_entries_cmdline(char *str)
 		return -EINVAL;
 	if (!get_option(&str, &nr_prealloc_entries))
 		nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
-	return 0;
+	return 1;
 }
 
 __setup("dma_debug=", dma_debug_cmdline);

kernel/dma/direct.c

@@ -265,17 +265,13 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
 	if (!page)
 		return NULL;
+
+	/*
+	 * dma_alloc_contiguous can return highmem pages depending on a
+	 * combination the cma= arguments and per-arch setup.  These need to be
+	 * remapped to return a kernel virtual address.
+	 */
 	if (PageHighMem(page)) {
-		/*
-		 * Depending on the cma= arguments and per-arch setup,
-		 * dma_alloc_contiguous could return highmem pages.
-		 * Without remapping there is no way to return them here, so
-		 * log an error and fail.
-		 */
-		if (!IS_ENABLED(CONFIG_DMA_REMAP)) {
-			dev_info(dev, "Rejecting highmem page from CMA.\n");
-			goto out_free_pages;
-		}
 		remap = true;
 		set_uncached = false;
 	}
@@ -349,7 +345,7 @@ void dma_direct_free(struct device *dev, size_t size,
 	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
 		return;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		vunmap(cpu_addr);
 	} else {
 		if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))