Merge tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping

Pull DMA mapping updates from Christoph Hellwig:
 "A huge update this time, but a lot of that is just consolidating or
  removing code:

   - provide a common DMA_MAPPING_ERROR definition and avoid indirect
     calls for dma_map_* error checking

   - use direct calls for the DMA direct mapping case, avoiding huge
     retpoline overhead for high performance workloads

   - merge the swiotlb dma_map_ops into dma-direct

   - provide a generic remapping DMA consistent allocator for
     architectures that have devices that perform DMA that is not cache
     coherent. Based on the existing arm64 implementation and also used
     for csky now.

   - improve the dma-debug infrastructure, including dynamic allocation
     of entries (Robin Murphy)

   - default to providing chaining scatterlist everywhere, with opt-outs
     for the few architectures (alpha, parisc, most arm32 variants) that
     can't cope with it

   - misc sparc32 dma-related cleanups

   - remove the dma_mark_clean arch hook used by swiotlb on ia64 and
     replace it with the generic noncoherent infrastructure

   - fix the return type of dma_set_max_seg_size (Niklas Söderlund)

   - move the dummy dma ops for not DMA capable devices from arm64 to
     common code (Robin Murphy)

   - ensure dma_alloc_coherent returns zeroed memory to avoid kernel
     data leaks through userspace. We already did this for most common
     architectures, but this ensures we do it everywhere.
     dma_zalloc_coherent has been deprecated and can hopefully be
     removed after -rc1 with a coccinelle script"

* tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping: (73 commits)
  dma-mapping: fix inverted logic in dma_supported
  dma-mapping: deprecate dma_zalloc_coherent
  dma-mapping: zero memory returned from dma_alloc_*
  sparc/iommu: fix ->map_sg return value
  sparc/io-unit: fix ->map_sg return value
  arm64: default to the direct mapping in get_arch_dma_ops
  PCI: Remove unused attr variable in pci_dma_configure
  ia64: only select ARCH_HAS_DMA_COHERENT_TO_PFN if swiotlb is enabled
  dma-mapping: bypass indirect calls for dma-direct
  vmd: use the proper dma_* APIs instead of direct methods calls
  dma-direct: merge swiotlb_dma_ops into the dma_direct code
  dma-direct: use dma_direct_map_page to implement dma_direct_map_sg
  dma-direct: improve addressability error reporting
  swiotlb: remove dma_mark_clean
  swiotlb: remove SWIOTLB_MAP_ERROR
  ACPI / scan: Refactor _CCA enforcement
  dma-mapping: factor out dummy DMA ops
  dma-mapping: always build the direct mapping code
  dma-mapping: move dma_cache_sync out of line
  dma-mapping: move various slow path functions out of line
  ...

1 files changed, 256 insertions, 0 deletions

diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
new file mode 100644
index 000000000000..18cc09fc27b9
--- /dev/null
+++ b/kernel/dma/remap.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (c) 2014 The Linux Foundation
+ */
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/dma-contiguous.h>
+#include <linux/init.h>
+#include <linux/genalloc.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+static struct vm_struct *__dma_common_pages_remap(struct page **pages,
+			size_t size, unsigned long vm_flags, pgprot_t prot,
+			const void *caller)
+{
+	struct vm_struct *area;
+
+	area = get_vm_area_caller(size, vm_flags, caller);
+	if (!area)
+		return NULL;
+
+	if (map_vm_area(area, prot, pages)) {
+		vunmap(area->addr);
+		return NULL;
+	}
+
+	return area;
+}
+
+/*
+ * Remaps an array of PAGE_SIZE pages into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller)
+{
+	struct vm_struct *area;
+
+	area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+	if (!area)
+		return NULL;
+
+	area->pages = pages;
+
+	return area->addr;
+}
+
+/*
+ * Remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller)
+{
+	int i;
+	struct page **pages;
+	struct vm_struct *area;
+
+	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+
+	for (i = 0; i < (size >> PAGE_SHIFT); i++)
+		pages[i] = nth_page(page, i);
+
+	area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+	kfree(pages);
+
+	if (!area)
+		return NULL;
+	return area->addr;
+}
+
+/*
+ * Unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || (area->flags & vm_flags) != vm_flags) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
+	}
+
+	unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
+	vunmap(cpu_addr);
+}
+
+#ifdef CONFIG_DMA_DIRECT_REMAP
+static struct gen_pool *atomic_pool __ro_after_init;
+
+#define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
+static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
+
+static int __init early_coherent_pool(char *p)
+{
+	atomic_pool_size = memparse(p, &p);
+	return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot)
+{
+	unsigned int pool_size_order = get_order(atomic_pool_size);
+	unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
+	struct page *page;
+	void *addr;
+	int ret;
+
+	if (dev_get_cma_area(NULL))
+		page = dma_alloc_from_contiguous(NULL, nr_pages,
+						 pool_size_order, false);
+	else
+		page = alloc_pages(gfp, pool_size_order);
+	if (!page)
+		goto out;
+
+	arch_dma_prep_coherent(page, atomic_pool_size);
+
+	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+	if (!atomic_pool)
+		goto free_page;
+
+	addr = dma_common_contiguous_remap(page, atomic_pool_size, VM_USERMAP,
+					   prot, __builtin_return_address(0));
+	if (!addr)
+		goto destroy_genpool;
+
+	ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
+				page_to_phys(page), atomic_pool_size, -1);
+	if (ret)
+		goto remove_mapping;
+	gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, NULL);
+
+	pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
+		atomic_pool_size / 1024);
+	return 0;
+
+remove_mapping:
+	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+destroy_genpool:
+	gen_pool_destroy(atomic_pool);
+	atomic_pool = NULL;
+free_page:
+	if (!dma_release_from_contiguous(NULL, page, nr_pages))
+		__free_pages(page, pool_size_order);
+out:
+	pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
+		atomic_pool_size / 1024);
+	return -ENOMEM;
+}
+
+bool dma_in_atomic_pool(void *start, size_t size)
+{
+	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+}
+
+void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
+{
+	unsigned long val;
+	void *ptr = NULL;
+
+	if (!atomic_pool) {
+		WARN(1, "coherent pool not initialised!\n");
+		return NULL;
+	}
+
+	val = gen_pool_alloc(atomic_pool, size);
+	if (val) {
+		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+		*ret_page = pfn_to_page(__phys_to_pfn(phys));
+		ptr = (void *)val;
+		memset(ptr, 0, size);
+	}
+
+	return ptr;
+}
+
+bool dma_free_from_pool(void *start, size_t size)
+{
+	if (!dma_in_atomic_pool(start, size))
+		return false;
+	gen_pool_free(atomic_pool, (unsigned long)start, size);
+	return true;
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t flags, unsigned long attrs)
+{
+	struct page *page = NULL;
+	void *ret;
+
+	size = PAGE_ALIGN(size);
+
+	if (!gfpflags_allow_blocking(flags) &&
+	    !(attrs & DMA_ATTR_NO_KERNEL_MAPPING)) {
+		ret = dma_alloc_from_pool(size, &page, flags);
+		if (!ret)
+			return NULL;
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
+		return ret;
+	}
+
+	page = __dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs);
+	if (!page)
+		return NULL;
+
+	/* remove any dirty cache lines on the kernel alias */
+	arch_dma_prep_coherent(page, size);
+
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
+		return page; /* opaque cookie */
+
+	/* create a coherent mapping */
+	ret = dma_common_contiguous_remap(page, size, VM_USERMAP,
+			arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs),
+			__builtin_return_address(0));
+	if (!ret) {
+		__dma_direct_free_pages(dev, size, page);
+		return ret;
+	}
+
+	*dma_handle = phys_to_dma(dev, page_to_phys(page));
+	memset(ret, 0, size);
+
+	return ret;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
+		/* vaddr is a struct page cookie, not a kernel address */
+		__dma_direct_free_pages(dev, size, vaddr);
+	} else if (!dma_free_from_pool(vaddr, PAGE_ALIGN(size))) {
+		phys_addr_t phys = dma_to_phys(dev, dma_handle);
+		struct page *page = pfn_to_page(__phys_to_pfn(phys));
+
+		vunmap(vaddr);
+		__dma_direct_free_pages(dev, size, page);
+	}
+}
+
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+		dma_addr_t dma_addr)
+{
+	return __phys_to_pfn(dma_to_phys(dev, dma_addr));
+}
+#endif /* CONFIG_DMA_DIRECT_REMAP */