Merge branches 'fixes' and 'misc' into for-linus

arch/arm/mm/Kconfig

@@ -679,7 +679,7 @@ config ARCH_DMA_ADDR_T_64BIT
 	bool
 
 config ARM_THUMB
-	bool "Support Thumb user binaries" if !CPU_THUMBONLY
+	bool "Support Thumb user binaries" if !CPU_THUMBONLY && EXPERT
 	depends on CPU_THUMB_CAPABLE
 	default y
 	help
@@ -690,6 +690,10 @@ config ARM_THUMB
 	  instruction set resulting in smaller binaries at the expense of
 	  slightly less efficient code.
 
+	  If this option is disabled, and you run userspace that switches to
+	  Thumb mode, signal handling will not work correctly, resulting in
+	  segmentation faults or illegal instruction aborts.
+
 	  If you don't know what this all is, saying Y is a safe choice.
 
 config ARM_THUMBEE
@@ -1045,8 +1049,8 @@ config ARM_L1_CACHE_SHIFT
 	default 5
 
 config ARM_DMA_MEM_BUFFERABLE
-	bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7
-	default y if CPU_V6 || CPU_V6K || CPU_V7
+	bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K || CPU_V7M) && !CPU_V7
+	default y if CPU_V6 || CPU_V6K || CPU_V7 || CPU_V7M
 	help
 	  Historically, the kernel has used strongly ordered mappings to
 	  provide DMA coherent memory.  With the advent of ARMv7, mapping
@@ -1061,6 +1065,10 @@ config ARM_DMA_MEM_BUFFERABLE
 	  and therefore turning this on may result in unpredictable driver
 	  behaviour.  Therefore, we offer this as an option.
 
+	  On some of the beefier ARMv7-M machines (with DMA and write
+	  buffers) you likely want this enabled, while those that
+	  didn't need it until now also won't need it in the future.
+
 	  You are recommended say 'Y' here and debug any affected drivers.
 
 config ARM_HEAVY_MB

arch/arm/mm/Makefile

@@ -2,9 +2,8 @@
 # Makefile for the linux arm-specific parts of the memory manager.
 #
 
-obj-y				:= dma-mapping.o extable.o fault.o init.o \
-				   iomap.o
-
+obj-y				:= extable.o fault.o init.o iomap.o
+obj-y				+= dma-mapping$(MMUEXT).o
 obj-$(CONFIG_MMU)		+= fault-armv.o flush.o idmap.o ioremap.o \
 				   mmap.o pgd.o mmu.o pageattr.o
 

arch/arm/mm/dma-mapping-nommu.c

@@ -0,0 +1,228 @@
+/*
+ *  Based on linux/arch/arm/mm/dma-mapping.c
+ *
+ *  Copyright (C) 2000-2004 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+
+#include <asm/cachetype.h>
+#include <asm/cacheflush.h>
+#include <asm/outercache.h>
+#include <asm/cp15.h>
+
+#include "dma.h"
+
+/*
+ *  dma_noop_ops is used if
+ *   - MMU/MPU is off
+ *   - cpu is v7m w/o cache support
+ *   - device is coherent
+ *  otherwise arm_nommu_dma_ops is used.
+ *
+ *  arm_nommu_dma_ops rely on consistent DMA memory (please, refer to
+ *  [1] on how to declare such memory).
+ *
+ *  [1] Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+ */
+
+static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
+				 dma_addr_t *dma_handle, gfp_t gfp,
+				 unsigned long attrs)
+
+{
+	const struct dma_map_ops *ops = &dma_noop_ops;
+
+	/*
+	 * We are here because:
+	 * - no consistent DMA region has been defined, so we can't
+	 *   continue.
+	 * - there is no space left in consistent DMA region, so we
+	 *   only can fallback to generic allocator if we are
+	 *   advertised that consistency is not required.
+	 */
+
+	if (attrs & DMA_ATTR_NON_CONSISTENT)
+		return ops->alloc(dev, size, dma_handle, gfp, attrs);
+
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
+static void arm_nommu_dma_free(struct device *dev, size_t size,
+			       void *cpu_addr, dma_addr_t dma_addr,
+			       unsigned long attrs)
+{
+	const struct dma_map_ops *ops = &dma_noop_ops;
+
+	if (attrs & DMA_ATTR_NON_CONSISTENT)
+		ops->free(dev, size, cpu_addr, dma_addr, attrs);
+	else
+		WARN_ON_ONCE(1);
+
+	return;
+}
+
+static void __dma_page_cpu_to_dev(phys_addr_t paddr, size_t size,
+				  enum dma_data_direction dir)
+{
+	dmac_map_area(__va(paddr), size, dir);
+
+	if (dir == DMA_FROM_DEVICE)
+		outer_inv_range(paddr, paddr + size);
+	else
+		outer_clean_range(paddr, paddr + size);
+}
+
+static void __dma_page_dev_to_cpu(phys_addr_t paddr, size_t size,
+				  enum dma_data_direction dir)
+{
+	if (dir != DMA_TO_DEVICE) {
+		outer_inv_range(paddr, paddr + size);
+		dmac_unmap_area(__va(paddr), size, dir);
+	}
+}
+
+static dma_addr_t arm_nommu_dma_map_page(struct device *dev, struct page *page,
+					 unsigned long offset, size_t size,
+					 enum dma_data_direction dir,
+					 unsigned long attrs)
+{
+	dma_addr_t handle = page_to_phys(page) + offset;
+
+	__dma_page_cpu_to_dev(handle, size, dir);
+
+	return handle;
+}
+
+static void arm_nommu_dma_unmap_page(struct device *dev, dma_addr_t handle,
+				     size_t size, enum dma_data_direction dir,
+				     unsigned long attrs)
+{
+	__dma_page_dev_to_cpu(handle, size, dir);
+}
+
+
+static int arm_nommu_dma_map_sg(struct device *dev, struct scatterlist *sgl,
+				int nents, enum dma_data_direction dir,
+				unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+		sg_dma_address(sg) = sg_phys(sg);
+		sg_dma_len(sg) = sg->length;
+		__dma_page_cpu_to_dev(sg_dma_address(sg), sg_dma_len(sg), dir);
+	}
+
+	return nents;
+}
+
+static void arm_nommu_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
+				   int nents, enum dma_data_direction dir,
+				   unsigned long attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		__dma_page_dev_to_cpu(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+static void arm_nommu_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	__dma_page_cpu_to_dev(handle, size, dir);
+}
+
+static void arm_nommu_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	__dma_page_cpu_to_dev(handle, size, dir);
+}
+
+static void arm_nommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+					     int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		__dma_page_cpu_to_dev(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+static void arm_nommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+					  int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		__dma_page_dev_to_cpu(sg_dma_address(sg), sg_dma_len(sg), dir);
+}
+
+const struct dma_map_ops arm_nommu_dma_ops = {
+	.alloc			= arm_nommu_dma_alloc,
+	.free			= arm_nommu_dma_free,
+	.map_page		= arm_nommu_dma_map_page,
+	.unmap_page		= arm_nommu_dma_unmap_page,
+	.map_sg			= arm_nommu_dma_map_sg,
+	.unmap_sg		= arm_nommu_dma_unmap_sg,
+	.sync_single_for_device	= arm_nommu_dma_sync_single_for_device,
+	.sync_single_for_cpu	= arm_nommu_dma_sync_single_for_cpu,
+	.sync_sg_for_device	= arm_nommu_dma_sync_sg_for_device,
+	.sync_sg_for_cpu	= arm_nommu_dma_sync_sg_for_cpu,
+};
+EXPORT_SYMBOL(arm_nommu_dma_ops);
+
+static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
+{
+	return coherent ? &dma_noop_ops : &arm_nommu_dma_ops;
+}
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+			const struct iommu_ops *iommu, bool coherent)
+{
+	const struct dma_map_ops *dma_ops;
+
+	if (IS_ENABLED(CONFIG_CPU_V7M)) {
+		/*
+		 * Cache support for v7m is optional, so can be treated as
+		 * coherent if no cache has been detected. Note that it is not
+		 * enough to check if MPU is in use or not since in absense of
+		 * MPU system memory map is used.
+		 */
+		dev->archdata.dma_coherent = (cacheid) ? coherent : true;
+	} else {
+		/*
+		 * Assume coherent DMA in case MMU/MPU has not been set up.
+		 */
+		dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true;
+	}
+
+	dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent);
+
+	set_dma_ops(dev, dma_ops);
+}
+
+void arch_teardown_dma_ops(struct device *dev)
+{
+}
+
+#define PREALLOC_DMA_DEBUG_ENTRIES	4096
+
+static int __init dma_debug_do_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	return 0;
+}
+core_initcall(dma_debug_do_init);

arch/arm/mm/dma-mapping.c

@@ -180,6 +180,11 @@ static void arm_dma_sync_single_for_device(struct device *dev,
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
+static int arm_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == ARM_MAPPING_ERROR;
+}
+
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
@@ -193,6 +198,8 @@ const struct dma_map_ops arm_dma_ops = {
 	.sync_single_for_device	= arm_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
+	.mapping_error		= arm_dma_mapping_error,
+	.dma_supported		= arm_dma_supported,
 };
 EXPORT_SYMBOL(arm_dma_ops);
 
@@ -211,6 +218,8 @@ const struct dma_map_ops arm_coherent_dma_ops = {
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
 	.map_sg			= arm_dma_map_sg,
+	.mapping_error		= arm_dma_mapping_error,
+	.dma_supported		= arm_dma_supported,
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
 
@@ -344,8 +353,6 @@ static void __dma_free_buffer(struct page *page, size_t size)
 	}
 }
 
-#ifdef CONFIG_MMU
-
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
 				     const void *caller, bool want_vaddr,
@@ -647,22 +654,6 @@ static inline pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot)
 	return prot;
 }
 
-#define nommu() 0
-
-#else	/* !CONFIG_MMU */
-
-#define nommu() 1
-
-#define __get_dma_pgprot(attrs, prot)				__pgprot(0)
-#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv)	NULL
-#define __alloc_from_pool(size, ret_page)			NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag, gfp)	NULL
-#define __free_from_pool(cpu_addr, size)			do { } while (0)
-#define __free_from_contiguous(dev, page, cpu_addr, size, wv)	do { } while (0)
-#define __dma_free_remap(cpu_addr, size)			do { } while (0)
-
-#endif	/* CONFIG_MMU */
-
 static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
 				   struct page **ret_page)
 {
@@ -799,13 +790,13 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	gfp &= ~(__GFP_COMP);
 	args.gfp = gfp;
 
-	*handle = DMA_ERROR_CODE;
+	*handle = ARM_MAPPING_ERROR;
 	allowblock = gfpflags_allow_blocking(gfp);
 	cma = allowblock ? dev_get_cma_area(dev) : false;
 
 	if (cma)
 		buf->allocator = &cma_allocator;
-	else if (nommu() || is_coherent)
+	else if (is_coherent)
 		buf->allocator = &simple_allocator;
 	else if (allowblock)
 		buf->allocator = &remap_allocator;
@@ -854,8 +845,7 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		 unsigned long attrs)
 {
-	int ret = -ENXIO;
-#ifdef CONFIG_MMU
+	int ret;
 	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long pfn = dma_to_pfn(dev, dma_addr);
@@ -870,10 +860,6 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 				      vma->vm_end - vma->vm_start,
 				      vma->vm_page_prot);
 	}
-#else
-	ret = vm_iomap_memory(vma, vma->vm_start,
-			      (vma->vm_end - vma->vm_start));
-#endif	/* CONFIG_MMU */
 
 	return ret;
 }
@@ -892,9 +878,7 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		 unsigned long attrs)
 {
-#ifdef CONFIG_MMU
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-#endif	/* CONFIG_MMU */
 	return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
 }
 
@@ -1177,11 +1161,10 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
  * during bus mastering, then you would pass 0x00ffffff as the mask
  * to this function.
  */
-int dma_supported(struct device *dev, u64 mask)
+int arm_dma_supported(struct device *dev, u64 mask)
 {
 	return __dma_supported(dev, mask, false);
 }
-EXPORT_SYMBOL(dma_supported);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
@@ -1254,7 +1237,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 	if (i == mapping->nr_bitmaps) {
 		if (extend_iommu_mapping(mapping)) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return DMA_ERROR_CODE;
+			return ARM_MAPPING_ERROR;
 		}
 
 		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
@@ -1262,7 +1245,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 
 		if (start > mapping->bits) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return DMA_ERROR_CODE;
+			return ARM_MAPPING_ERROR;
 		}
 
 		bitmap_set(mapping->bitmaps[i], start, count);
@@ -1445,7 +1428,7 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
 	int i;
 
 	dma_addr = __alloc_iova(mapping, size);
-	if (dma_addr == DMA_ERROR_CODE)
+	if (dma_addr == ARM_MAPPING_ERROR)
 		return dma_addr;
 
 	iova = dma_addr;
@@ -1472,7 +1455,7 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
 fail:
 	iommu_unmap(mapping->domain, dma_addr, iova-dma_addr);
 	__free_iova(mapping, dma_addr, size);
-	return DMA_ERROR_CODE;
+	return ARM_MAPPING_ERROR;
 }
 
 static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
@@ -1533,7 +1516,7 @@ static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, &page, size, attrs);
-	if (*handle == DMA_ERROR_CODE)
+	if (*handle == ARM_MAPPING_ERROR)
 		goto err_mapping;
 
 	return addr;
@@ -1561,7 +1544,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	struct page **pages;
 	void *addr = NULL;
 
-	*handle = DMA_ERROR_CODE;
+	*handle = ARM_MAPPING_ERROR;
 	size = PAGE_ALIGN(size);
 
 	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
@@ -1582,7 +1565,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, pages, size, attrs);
-	if (*handle == DMA_ERROR_CODE)
+	if (*handle == ARM_MAPPING_ERROR)
 		goto err_buffer;
 
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
@@ -1732,10 +1715,10 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 	int prot;
 
 	size = PAGE_ALIGN(size);
-	*handle = DMA_ERROR_CODE;
+	*handle = ARM_MAPPING_ERROR;
 
 	iova_base = iova = __alloc_iova(mapping, size);
-	if (iova == DMA_ERROR_CODE)
+	if (iova == ARM_MAPPING_ERROR)
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
@@ -1775,7 +1758,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	for (i = 1; i < nents; i++) {
 		s = sg_next(s);
 
-		s->dma_address = DMA_ERROR_CODE;
+		s->dma_address = ARM_MAPPING_ERROR;
 		s->dma_length = 0;
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
@@ -1950,7 +1933,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == DMA_ERROR_CODE)
+	if (dma_addr == ARM_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs);
@@ -1962,7 +1945,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return DMA_ERROR_CODE;
+	return ARM_MAPPING_ERROR;
 }
 
 /**
@@ -2056,7 +2039,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 	size_t len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == DMA_ERROR_CODE)
+	if (dma_addr == ARM_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
@@ -2068,7 +2051,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return DMA_ERROR_CODE;
+	return ARM_MAPPING_ERROR;
 }
 
 /**
@@ -2140,6 +2123,9 @@ const struct dma_map_ops iommu_ops = {
 
 	.map_resource		= arm_iommu_map_resource,
 	.unmap_resource		= arm_iommu_unmap_resource,
+
+	.mapping_error		= arm_dma_mapping_error,
+	.dma_supported		= arm_dma_supported,
 };
 
 const struct dma_map_ops iommu_coherent_ops = {
@@ -2156,6 +2142,9 @@ const struct dma_map_ops iommu_coherent_ops = {
 
 	.map_resource	= arm_iommu_map_resource,
 	.unmap_resource	= arm_iommu_unmap_resource,
+
+	.mapping_error		= arm_dma_mapping_error,
+	.dma_supported		= arm_dma_supported,
 };
 
 /**

arch/arm/mm/proc-macros.S

@@ -25,11 +25,6 @@
 	ldr	\rd, [\rn, #VMA_VM_FLAGS]
 	.endm
 
-	.macro	tsk_mm, rd, rn
-	ldr	\rd, [\rn, #TI_TASK]
-	ldr	\rd, [\rd, #TSK_ACTIVE_MM]
-	.endm
-
 /*
  * act_mm - get current->active_mm
  */
@@ -37,7 +32,10 @@
 	bic	\rd, sp, #8128
 	bic	\rd, \rd, #63
 	ldr	\rd, [\rd, #TI_TASK]
-	ldr	\rd, [\rd, #TSK_ACTIVE_MM]
+	.if (TSK_ACTIVE_MM > IMM12_MASK)
+	add	\rd, \rd, #TSK_ACTIVE_MM & ~IMM12_MASK
+	.endif
+	ldr	\rd, [\rd, #TSK_ACTIVE_MM & IMM12_MASK]
 	.endm
 
 /*