19 files changed, 211 insertions, 285 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index b169e580bf82..0ab3a86b1f52 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -106,7 +106,7 @@ config CPU_ARM922T
 	help
 	  The ARM922T is a version of the ARM920T, but with smaller
 	  instruction and data caches. It is used in Altera's
-	  Excalibur XA device family and Micrel's KS8695 Centaur.
+	  Excalibur XA device family and the ARM Integrator.
 
 	  Say Y if you want support for the ARM922T processor.
 	  Otherwise, say N.
@@ -663,6 +663,7 @@ config ARM_LPAE
 	depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \
 		!CPU_32v4 && !CPU_32v3
 	select PHYS_ADDR_T_64BIT
+	select SWIOTLB
 	help
 	  Say Y if you have an ARMv7 processor supporting the LPAE page
 	  table format and you would like to access memory beyond the
@@ -709,7 +710,7 @@ config ARM_VIRT_EXT
 	  assistance.
 
 	  A compliant bootloader is required in order to make maximum
-	  use of this feature.  Refer to Documentation/arm/Booting for
+	  use of this feature.  Refer to Documentation/arm/booting.rst for
 	  details.
 
 config SWP_EMULATE
@@ -780,6 +781,14 @@ config CPU_ICACHE_DISABLE
 	  Say Y here to disable the processor instruction cache. Unless
 	  you have a reason not to or are unsure, say N.
 
+config CPU_ICACHE_MISMATCH_WORKAROUND
+	bool "Workaround for I-Cache line size mismatch between CPU cores"
+	depends on SMP && CPU_V7
+	help
+	  Some big.LITTLE systems have I-Cache line size mismatch between
+	  LITTLE and big cores.  Say Y here to enable a workaround for
+	  proper I-Cache support on such systems.  If unsure, say N.
+
 config CPU_DCACHE_DISABLE
 	bool "Disable D-Cache (C-bit)"
 	depends on (CPU_CP15 && !SMP) || CPU_V7M
@@ -867,7 +876,7 @@ config KUSER_HELPERS
 	  the CPU type fitted to the system.  This permits binaries to be
 	  run on ARMv4 through to ARMv7 without modification.
 
-	  See Documentation/arm/kernel_user_helpers.txt for details.
+	  See Documentation/arm/kernel_user_helpers.rst for details.
 
 	  However, the fixed address nature of these helpers can be used
 	  by ROP (return orientated programming) authors when creating
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 6067fa4de22b..04b36436cbc0 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -695,7 +695,7 @@ thumb2arm(u16 tinstr)
 			return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] |
 			    (tinstr & 255);		/* register_list */
 		}
-		/* Else fall through for illegal instruction case */
+		/* Else, fall through - for illegal instruction case */
 
 	default:
 		return BAD_INSTR;
@@ -751,6 +751,8 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
 	case 0xe8e0:
 	case 0xe9e0:
 		poffset->un = (tinst2 & 0xff) << 2;
+		/* Fall through */
+
 	case 0xe940:
 	case 0xe9c0:
 		return do_alignment_ldrdstrd;
@@ -945,7 +947,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		goto fixup;
 
 	if (ai_usermode & UM_SIGNAL) {
-		force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr, current);
+		force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr);
 	} else {
 		/*
 		 * We're about to disable the alignment trap and return to
diff --git a/arch/arm/mm/cache-aurora-l2.h b/arch/arm/mm/cache-aurora-l2.h
deleted file mode 100644
index c86124769831..000000000000
--- a/arch/arm/mm/cache-aurora-l2.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * AURORA shared L2 cache controller support
- *
- * Copyright (C) 2012 Marvell
- *
- * Yehuda Yitschak <yehuday@marvell.com>
- * Gregory CLEMENT <gregory.clement@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __ASM_ARM_HARDWARE_AURORA_L2_H
-#define __ASM_ARM_HARDWARE_AURORA_L2_H
-
-#define AURORA_SYNC_REG		    0x700
-#define AURORA_RANGE_BASE_ADDR_REG  0x720
-#define AURORA_FLUSH_PHY_ADDR_REG   0x7f0
-#define AURORA_INVAL_RANGE_REG	    0x774
-#define AURORA_CLEAN_RANGE_REG	    0x7b4
-#define AURORA_FLUSH_RANGE_REG	    0x7f4
-
-#define AURORA_ACR_REPLACEMENT_OFFSET	    27
-#define AURORA_ACR_REPLACEMENT_MASK	     \
-	(0x3 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_WAYRR    \
-	(0 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_LFSR     \
-	(1 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU \
-	(3 << AURORA_ACR_REPLACEMENT_OFFSET)
-
-#define AURORA_ACR_FORCE_WRITE_POLICY_OFFSET	0
-#define AURORA_ACR_FORCE_WRITE_POLICY_MASK	\
-	(0x3 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_POLICY_DIS	\
-	(0 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_BACK_POLICY	\
-	(1 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_THRO_POLICY	\
-	(2 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-
-#define MAX_RANGE_SIZE		1024
-
-#define AURORA_WAY_SIZE_SHIFT	2
-
-#define AURORA_CTRL_FW		0x100
-
-/* chose a number outside L2X0_CACHE_ID_PART_MASK to be sure to make
- * the distinction between a number coming from hardware and a number
- * coming from the device tree */
-#define AURORA_CACHE_ID	       0x100
-
-#endif /* __ASM_ARM_HARDWARE_AURORA_L2_H */
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 5b251c8ecd45..12c26eb88afb 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -18,8 +18,8 @@
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/hardware/cache-l2x0.h>
+#include <asm/hardware/cache-aurora-l2.h>
 #include "cache-tauros3.h"
-#include "cache-aurora-l2.h"
 
 struct l2c_init_data {
 	const char *type;
@@ -1352,8 +1352,8 @@ static unsigned long aurora_range_end(unsigned long start, unsigned long end)
 	 * since cache range operations stall the CPU pipeline
 	 * until completion.
 	 */
-	if (end > start + MAX_RANGE_SIZE)
-		end = start + MAX_RANGE_SIZE;
+	if (end > start + AURORA_MAX_RANGE_SIZE)
+		end = start + AURORA_MAX_RANGE_SIZE;
 
 	/*
 	 * Cache range operations can't straddle a page boundary.
@@ -1493,6 +1493,18 @@ static void __init aurora_of_parse(const struct device_node *np,
 		mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
 	}
 
+	if (of_property_read_bool(np, "marvell,ecc-enable")) {
+		mask |= AURORA_ACR_ECC_EN;
+		val |= AURORA_ACR_ECC_EN;
+	}
+
+	if (of_property_read_bool(np, "arm,parity-enable")) {
+		mask |= AURORA_ACR_PARITY_EN;
+		val |= AURORA_ACR_PARITY_EN;
+	} else if (of_property_read_bool(np, "arm,parity-disable")) {
+		mask |= AURORA_ACR_PARITY_EN;
+	}
+
 	*aux_val &= ~mask;
 	*aux_val |= val;
 	*aux_mask &= ~mask;
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 8c83b4586883..0ee8fc4b4672 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -16,6 +16,14 @@
 
 #include "proc-macros.S"
 
+#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
+.globl icache_size
+	.data
+	.align	2
+icache_size:
+	.long	64
+	.text
+#endif
 /*
  * The secondary kernel init calls v7_flush_dcache_all before it enables
  * the L1; however, the L1 comes out of reset in an undefined state, so
@@ -160,6 +168,9 @@ loop2:
 skip:
 	add	r10, r10, #2			@ increment cache number
 	cmp	r3, r10
+#ifdef CONFIG_ARM_ERRATA_814220
+	dsb
+#endif
 	bgt	flush_levels
 finished:
 	mov	r10, #0				@ switch back to cache level 0
@@ -281,7 +292,12 @@ ENTRY(v7_coherent_user_range)
 	cmp	r12, r1
 	blo	1b
 	dsb	ishst
+#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
+	ldr	r3, =icache_size
+	ldr	r2, [r3, #0]
+#else
 	icache_line_size r2, r3
+#endif
 	sub	r3, r2, #1
 	bic	r12, r0, r3
 2:
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 61d834157bc0..382e1c2855e8 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -42,6 +42,7 @@ static void mc_copy_user_page(void *from, void *to)
 	 * when prefetching destination as well.  (NP)
 	 */
 	asm volatile ("\
+.arch xscale					\n\
 	pld	[%0, #0]			\n\
 	pld	[%0, #32]			\n\
 	pld	[%1, #0]			\n\
@@ -106,8 +107,9 @@ void
 xscale_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
 {
 	void *ptr, *kaddr = kmap_atomic(page);
-	asm volatile(
-	"mov	r1, %2				\n\
+	asm volatile("\
+.arch xscale					\n\
+	mov	r1, %2				\n\
 	mov	r2, #0				\n\
 	mov	r3, #0				\n\
 1:	mov	ip, %0				\n\
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 1aea01ba1262..db9247898300 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -35,18 +35,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
 				 unsigned long attrs)
 
 {
-	void *ret;
-
-	/*
-	 * Try generic allocator first if we are advertised that
-	 * consistency is not required.
-	 */
-
-	if (attrs & DMA_ATTR_NON_CONSISTENT)
-		return dma_direct_alloc_pages(dev, size, dma_handle, gfp,
-				attrs);
-
-	ret = dma_alloc_from_global_coherent(size, dma_handle);
+	void *ret = dma_alloc_from_global_coherent(size, dma_handle);
 
 	/*
 	 * dma_alloc_from_global_coherent() may fail because:
@@ -66,16 +55,9 @@ static void arm_nommu_dma_free(struct device *dev, size_t size,
 			       void *cpu_addr, dma_addr_t dma_addr,
 			       unsigned long attrs)
 {
-	if (attrs & DMA_ATTR_NON_CONSISTENT) {
-		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
-	} else {
-		int ret = dma_release_from_global_coherent(get_order(size),
-							   cpu_addr);
-
-		WARN_ON_ONCE(ret == 0);
-	}
+	int ret = dma_release_from_global_coherent(get_order(size), cpu_addr);
 
-	return;
+	WARN_ON_ONCE(ret == 0);
 }
 
 static int arm_nommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
@@ -86,8 +68,9 @@ static int arm_nommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 
 	if (dma_mmap_from_global_coherent(vma, cpu_addr, size, &ret))
 		return ret;
-
-	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+	return -ENXIO;
 }
 
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 439bb6a59a04..7d042d5c43e3 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -14,7 +14,9 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/device.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
 #include <linux/memblock.h>
@@ -34,6 +36,7 @@
 #include <asm/mach/map.h>
 #include <asm/system_info.h>
 #include <asm/dma-contiguous.h>
+#include <xen/swiotlb-xen.h>
 
 #include "dma.h"
 #include "mm.h"
@@ -191,6 +194,7 @@ const struct dma_map_ops arm_dma_ops = {
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
 	.dma_supported		= arm_dma_supported,
+	.get_required_mask	= dma_direct_get_required_mask,
 };
 EXPORT_SYMBOL(arm_dma_ops);
 
@@ -211,30 +215,13 @@ const struct dma_map_ops arm_coherent_dma_ops = {
 	.map_sg			= arm_dma_map_sg,
 	.map_resource		= dma_direct_map_resource,
 	.dma_supported		= arm_dma_supported,
+	.get_required_mask	= dma_direct_get_required_mask,
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
 
 static int __dma_supported(struct device *dev, u64 mask, bool warn)
 {
-	unsigned long max_dma_pfn;
-
-	/*
-	 * If the mask allows for more memory than we can address,
-	 * and we actually have that much memory, then we must
-	 * indicate that DMA to this device is not supported.
-	 */
-	if (sizeof(mask) != sizeof(dma_addr_t) &&
-	    mask > (dma_addr_t)~0 &&
-	    dma_to_pfn(dev, ~0) < max_pfn - 1) {
-		if (warn) {
-			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
-				 mask);
-			dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
-		}
-		return 0;
-	}
-
-	max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
+	unsigned long max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
 
 	/*
 	 * Translate the device's DMA mask to a PFN limit.  This
@@ -353,25 +340,6 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 				 pgprot_t prot, struct page **ret_page,
 				 const void *caller, bool want_vaddr);
 
-static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
-	const void *caller)
-{
-	/*
-	 * DMA allocation can be mapped to user space, so lets
-	 * set VM_USERMAP flags too.
-	 */
-	return dma_common_contiguous_remap(page, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-			prot, caller);
-}
-
-static void __dma_free_remap(void *cpu_addr, size_t size)
-{
-	dma_common_free_remap(cpu_addr, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
-}
-
 #define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
 static struct gen_pool *atomic_pool __ro_after_init;
 
@@ -493,8 +461,7 @@ void __init dma_contiguous_remap(void)
 	}
 }
 
-static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
-			    void *data)
+static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data)
 {
 	struct page *page = virt_to_page(addr);
 	pgprot_t prot = *(pgprot_t *)data;
@@ -528,7 +495,7 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 	if (!want_vaddr)
 		goto out;
 
-	ptr = __dma_alloc_remap(page, size, gfp, prot, caller);
+	ptr = dma_common_contiguous_remap(page, size, prot, caller);
 	if (!ptr) {
 		__dma_free_buffer(page, size);
 		return NULL;
@@ -595,7 +562,7 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
 		goto out;
 
 	if (PageHighMem(page)) {
-		ptr = __dma_alloc_remap(page, size, GFP_KERNEL, prot, caller);
+		ptr = dma_common_contiguous_remap(page, size, prot, caller);
 		if (!ptr) {
 			dma_release_from_contiguous(dev, page, count);
 			return NULL;
@@ -615,7 +582,7 @@ static void __free_from_contiguous(struct device *dev, struct page *page,
 {
 	if (want_vaddr) {
 		if (PageHighMem(page))
-			__dma_free_remap(cpu_addr, size);
+			dma_common_free_remap(cpu_addr, size);
 		else
 			__dma_remap(page, size, PAGE_KERNEL);
 	}
@@ -707,7 +674,7 @@ static void *remap_allocator_alloc(struct arm_dma_alloc_args *args,
 static void remap_allocator_free(struct arm_dma_free_args *args)
 {
 	if (args->want_vaddr)
-		__dma_free_remap(args->cpu_addr, args->size);
+		dma_common_free_remap(args->cpu_addr, args->size);
 
 	__dma_free_buffer(args->page, args->size);
 }
@@ -895,17 +862,6 @@ static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_add
 	__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
 }
 
-/*
- * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
- * that the intention is to allow exporting memory allocated via the
- * coherent DMA APIs through the dma_buf API, which only accepts a
- * scattertable.  This presents a couple of problems:
- * 1. Not all memory allocated via the coherent DMA APIs is backed by
- *    a struct page
- * 2. Passing coherent DMA memory into the streaming APIs is not allowed
- *    as we will try to flush the memory through a different alias to that
- *    actually being used (and the flushes are redundant.)
- */
 int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 		 void *cpu_addr, dma_addr_t handle, size_t size,
 		 unsigned long attrs)
@@ -1144,6 +1100,15 @@ int arm_dma_supported(struct device *dev, u64 mask)
 
 static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
 {
+	/*
+	 * When CONFIG_ARM_LPAE is set, physical address can extend above
+	 * 32-bits, which then can't be addressed by devices that only support
+	 * 32-bit DMA.
+	 * Use the generic dma-direct / swiotlb ops code in that case, as that
+	 * handles bounce buffering for us.
+	 */
+	if (IS_ENABLED(CONFIG_ARM_LPAE))
+		return NULL;
 	return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
 }
 
@@ -1378,17 +1343,6 @@ static int __iommu_free_buffer(struct device *dev, struct page **pages,
 }
 
 /*
- * Create a CPU mapping for a specified pages
- */
-static void *
-__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
-		    const void *caller)
-{
-	return dma_common_pages_remap(pages, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
-}
-
-/*
  * Create a mapping in device IO address space for specified pages
  */
 static dma_addr_t
@@ -1460,18 +1414,13 @@ static struct page **__atomic_get_pages(void *addr)
 
 static struct page **__iommu_get_pages(void *cpu_addr, unsigned long attrs)
 {
-	struct vm_struct *area;
-
 	if (__in_atomic_pool(cpu_addr, PAGE_SIZE))
 		return __atomic_get_pages(cpu_addr);
 
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
 		return cpu_addr;
 
-	area = find_vm_area(cpu_addr);
-	if (area && (area->flags & VM_ARM_DMA_CONSISTENT))
-		return area->pages;
-	return NULL;
+	return dma_common_find_pages(cpu_addr);
 }
 
 static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
@@ -1544,7 +1493,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
 		return pages;
 
-	addr = __iommu_alloc_remap(pages, size, gfp, prot,
+	addr = dma_common_pages_remap(pages, size, prot,
 				   __builtin_return_address(0));
 	if (!addr)
 		goto err_mapping;
@@ -1627,10 +1576,8 @@ void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		return;
 	}
 
-	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0) {
-		dma_common_free_remap(cpu_addr, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
-	}
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0)
+		dma_common_free_remap(cpu_addr, size);
 
 	__iommu_remove_mapping(dev, handle, size);
 	__iommu_free_buffer(dev, pages, size, attrs);
@@ -2348,6 +2295,9 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	const struct dma_map_ops *dma_ops;
 
 	dev->archdata.dma_coherent = coherent;
+#ifdef CONFIG_SWIOTLB
+	dev->dma_coherent = coherent;
+#endif
 
 	/*
 	 * Don't override the dma_ops if they have already been set. Ideally
@@ -2365,10 +2315,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	set_dma_ops(dev, dma_ops);
 
 #ifdef CONFIG_XEN
-	if (xen_initial_domain()) {
-		dev->archdata.dev_dma_ops = dev->dma_ops;
-		dev->dma_ops = xen_dma_ops;
-	}
+	if (xen_initial_domain())
+		dev->dma_ops = &xen_swiotlb_dma_ops;
 #endif
 	dev->archdata.dma_ops_setup = true;
 }
@@ -2382,3 +2330,39 @@ void arch_teardown_dma_ops(struct device *dev)
 	/* Let arch_setup_dma_ops() start again from scratch upon re-probe */
 	set_dma_ops(dev, NULL);
 }
+
+#ifdef CONFIG_SWIOTLB
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
+			      size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
+			      size, dir);
+}
+
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+		dma_addr_t dma_addr)
+{
+	return dma_to_pfn(dev, dma_addr);
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
+{
+	return __dma_alloc(dev, size, dma_handle, gfp,
+			   __get_dma_pgprot(attrs, PAGE_KERNEL), false,
+			   attrs, __builtin_return_address(0));
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	__arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false);
+}
+#endif /* CONFIG_SWIOTLB */
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 006d27ee4fc6..7d6291f23251 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -446,7 +446,7 @@ void ptdump_check_wx(void)
 static int ptdump_init(void)
 {
 	ptdump_initialize();
-	return ptdump_debugfs_register(&kernel_ptdump_info,
-					"kernel_page_tables");
+	ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables");
+	return 0;
 }
 __initcall(ptdump_init);
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 0048eadd0681..bd0f4821f7e1 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -27,43 +27,20 @@
 
 #ifdef CONFIG_MMU
 
-#ifdef CONFIG_KPROBES
-static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
-{
-	int ret = 0;
-
-	if (!user_mode(regs)) {
-		/* kprobe_running() needs smp_processor_id() */
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, fsr))
-			ret = 1;
-		preempt_enable();
-	}
-
-	return ret;
-}
-#else
-static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
-{
-	return 0;
-}
-#endif
-
 /*
  * This is useful to dump out the page tables associated with
  * 'addr' in mm 'mm'.
  */
-void show_pte(struct mm_struct *mm, unsigned long addr)
+void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 
 	if (!mm)
 		mm = &init_mm;
 
-	pr_alert("pgd = %p\n", mm->pgd);
+	printk("%spgd = %p\n", lvl, mm->pgd);
 	pgd = pgd_offset(mm, addr);
-	pr_alert("[%08lx] *pgd=%08llx",
-			addr, (long long)pgd_val(*pgd));
+	printk("%s[%08lx] *pgd=%08llx", lvl, addr, (long long)pgd_val(*pgd));
 
 	do {
 		pud_t *pud;
@@ -118,7 +95,7 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 	pr_cont("\n");
 }
 #else					/* CONFIG_MMU */
-void show_pte(struct mm_struct *mm, unsigned long addr)
+void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 { }
 #endif					/* CONFIG_MMU */
 
@@ -139,11 +116,12 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 	 * No handler, we'll have to terminate things with extreme prejudice.
 	 */
 	bust_spinlocks(1);
+	pr_alert("8<--- cut here ---\n");
 	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
 		 (addr < PAGE_SIZE) ? "NULL pointer dereference" :
 		 "paging request", addr);
 
-	show_pte(mm, addr);
+	show_pte(KERN_ALERT, mm, addr);
 	die("Oops", regs, fsr);
 	bust_spinlocks(0);
 	do_exit(SIGKILL);
@@ -154,19 +132,21 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
  * User mode accesses just cause a SIGSEGV
  */
 static void
-__do_user_fault(struct task_struct *tsk, unsigned long addr,
-		unsigned int fsr, unsigned int sig, int code,
-		struct pt_regs *regs)
+__do_user_fault(unsigned long addr, unsigned int fsr, unsigned int sig,
+		int code, struct pt_regs *regs)
 {
+	struct task_struct *tsk = current;
+
 	if (addr > TASK_SIZE)
 		harden_branch_predictor();
 
 #ifdef CONFIG_DEBUG_USER
 	if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
 	    ((user_debug & UDBG_BUS)  && (sig == SIGBUS))) {
-		printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
+		pr_err("8<--- cut here ---\n");
+		pr_err("%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
 		       tsk->comm, sig, addr, fsr);
-		show_pte(tsk->mm, addr);
+		show_pte(KERN_ERR, tsk->mm, addr);
 		show_regs(regs);
 	}
 #endif
@@ -180,7 +160,7 @@ __do_user_fault(struct task_struct *tsk, unsigned long addr,
 	tsk->thread.address = addr;
 	tsk->thread.error_code = fsr;
 	tsk->thread.trap_no = 14;
-	force_sig_fault(sig, code, (void __user *)addr, tsk);
+	force_sig_fault(sig, code, (void __user *)addr);
 }
 
 void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
@@ -193,7 +173,7 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * have no context to handle this fault with.
 	 */
 	if (user_mode(regs))
-		__do_user_fault(tsk, addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
+		__do_user_fault(addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
 	else
 		__do_kernel_fault(mm, addr, fsr, regs);
 }
@@ -211,7 +191,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
 {
 	unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
 
-	if (fsr & FSR_WRITE)
+	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		mask = VM_WRITE;
 	if (fsr & FSR_LNX_PF)
 		mask = VM_EXEC;
@@ -263,7 +243,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	vm_fault_t fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-	if (notify_page_fault(regs, fsr))
+	if (kprobe_page_fault(regs, fsr))
 		return 0;
 
 	tsk = current;
@@ -282,7 +262,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
-	if (fsr & FSR_WRITE)
+	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		flags |= FAULT_FLAG_WRITE;
 
 	/*
@@ -389,7 +369,7 @@ retry:
 			SEGV_ACCERR : SEGV_MAPERR;
 	}
 
-	__do_user_fault(tsk, addr, fsr, sig, code, regs);
+	__do_user_fault(addr, fsr, sig, code, regs);
 	return 0;
 
 no_context:
@@ -553,9 +533,10 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs))
 		return;
 
+	pr_alert("8<--- cut here ---\n");
 	pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n",
 		inf->name, fsr, addr);
-	show_pte(current->mm, addr);
+	show_pte(KERN_ALERT, current->mm, addr);
 
 	arm_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
 		       fsr, 0);
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index c063708fa503..9ecc2097a87a 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -6,6 +6,7 @@
  * Fault status register encodings.  We steal bit 31 for our own purposes.
  */
 #define FSR_LNX_PF		(1 << 31)
+#define FSR_CM			(1 << 13)
 #define FSR_WRITE		(1 << 11)
 #define FSR_FS4			(1 << 10)
 #define FSR_FS3_0		(15)
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 6ecbda87ee46..6d89db7895d1 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -204,18 +204,17 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 	 * coherent with the kernels mapping.
 	 */
 	if (!PageHighMem(page)) {
-		size_t page_size = PAGE_SIZE << compound_order(page);
-		__cpuc_flush_dcache_area(page_address(page), page_size);
+		__cpuc_flush_dcache_area(page_address(page), page_size(page));
 	} else {
 		unsigned long i;
 		if (cache_is_vipt_nonaliasing()) {
-			for (i = 0; i < (1 << compound_order(page)); i++) {
+			for (i = 0; i < compound_nr(page); i++) {
 				void *addr = kmap_atomic(page + i);
 				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
 				kunmap_atomic(addr);
 			}
 		} else {
-			for (i = 0; i < (1 << compound_order(page)); i++) {
+			for (i = 0; i < compound_nr(page); i++) {
 				void *addr = kmap_high_get(page + i);
 				if (addr) {
 					__cpuc_flush_dcache_area(addr, PAGE_SIZE);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 749a5a6f6143..b4be3baa83d4 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -21,6 +21,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/sizes.h>
 #include <linux/stop_machine.h>
+#include <linux/swiotlb.h>
 
 #include <asm/cp15.h>
 #include <asm/mach-types.h>
@@ -174,6 +175,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
+	phys_addr_t addr = __pfn_to_phys(pfn);
+
+	if (__phys_to_pfn(addr) != pfn)
+		return 0;
+
 	return memblock_is_map_memory(__pfn_to_phys(pfn));
 }
 EXPORT_SYMBOL(pfn_valid);
@@ -239,6 +245,22 @@ static void __init arm_initrd_init(void)
 #endif
 }
 
+#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
+void check_cpu_icache_size(int cpuid)
+{
+	u32 size, ctr;
+
+	asm("mrc p15, 0, %0, c0, c0, 1" : "=r" (ctr));
+
+	size = 1 << ((ctr & 0xf) + 2);
+	if (cpuid != 0 && icache_size != size)
+		pr_info("CPU%u: detected I-Cache line size mismatch, workaround enabled\n",
+			cpuid);
+	if (icache_size > size)
+		icache_size = size;
+}
+#endif
+
 void __init arm_memblock_init(const struct machine_desc *mdesc)
 {
 	/* Register the kernel text, kernel data and initrd with memblock. */
@@ -447,10 +469,8 @@ static void __init free_highpages(void)
  */
 void __init mem_init(void)
 {
-#ifdef CONFIG_HAVE_TCM
-	/* These pointers are filled in on TCM detection */
-	extern u32 dtcm_end;
-	extern u32 itcm_end;
+#ifdef CONFIG_ARM_LPAE
+	swiotlb_init(1);
 #endif
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
@@ -613,7 +633,8 @@ static void update_sections_early(struct section_perm perms[], int n)
 		if (t->flags & PF_KTHREAD)
 			continue;
 		for_each_thread(t, s)
-			set_section_perms(perms, n, true, s->mm);
+			if (s->mm)
+				set_section_perms(perms, n, true, s->mm);
 	}
 	set_section_perms(perms, n, true, current->active_mm);
 	set_section_perms(perms, n, true, &init_mm);
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 6b045c6653ea..88c121ac14b3 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -8,6 +8,8 @@
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
 
+extern int icache_size;
+
 /*
  * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
  * specific hacks for copying pages efficiently, while 0xffff4000
@@ -68,9 +70,6 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 #define VM_ARM_MTYPE(mt)		((mt) << 20)
 #define VM_ARM_MTYPE_MASK	(0x1f << 20)
 
-/* consistent regions used by dma_alloc_attrs() */
-#define VM_ARM_DMA_CONSISTENT	0x20000000
-
 
 struct static_vm {
 	struct vm_struct vm;
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index f866870db749..b8d912ac9e61 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -17,33 +17,6 @@
 	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
 	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
 
-/* gap between mmap and stack */
-#define MIN_GAP (128*1024*1024UL)
-#define MAX_GAP ((TASK_SIZE)/6*5)
-
-static int mmap_is_legacy(struct rlimit *rlim_stack)
-{
-	if (current->personality & ADDR_COMPAT_LAYOUT)
-		return 1;
-
-	if (rlim_stack->rlim_cur == RLIM_INFINITY)
-		return 1;
-
-	return sysctl_legacy_va_layout;
-}
-
-static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
-{
-	unsigned long gap = rlim_stack->rlim_cur;
-
-	if (gap < MIN_GAP)
-		gap = MIN_GAP;
-	else if (gap > MAX_GAP)
-		gap = MAX_GAP;
-
-	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
-}
-
 /*
  * We need to ensure that shared mappings are correctly aligned to
  * avoid aliasing issues with VIPT caches.  We need to ensure that
@@ -171,31 +144,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	return addr;
 }
 
-unsigned long arch_mmap_rnd(void)
-{
-	unsigned long rnd;
-
-	rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
-
-	return rnd << PAGE_SHIFT;
-}
-
-void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
-{
-	unsigned long random_factor = 0UL;
-
-	if (current->flags & PF_RANDOMIZE)
-		random_factor = arch_mmap_rnd();
-
-	if (mmap_is_legacy(rlim_stack)) {
-		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
-		mm->get_unmapped_area = arch_get_unmapped_area;
-	} else {
-		mm->mmap_base = mmap_base(random_factor, rlim_stack);
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-	}
-}
-
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This
  * might go away in the future.
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 1aa2586fa597..48c2888297dd 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -729,9 +729,9 @@ static void __init *early_alloc(unsigned long sz)
 
 static void *__init late_alloc(unsigned long sz)
 {
-	void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz));
+	void *ptr = (void *)__get_free_pages(GFP_PGTABLE_KERNEL, get_order(sz));
 
-	if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+	if (!ptr || !pgtable_pte_page_ctor(virt_to_page(ptr)))
 		BUG();
 	return ptr;
 }
@@ -1177,10 +1177,29 @@ void __init adjust_lowmem_bounds(void)
 	 */
 	vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
 
+	/*
+	 * The first usable region must be PMD aligned. Mark its start
+	 * as MEMBLOCK_NOMAP if it isn't
+	 */
+	for_each_memblock(memory, reg) {
+		if (!memblock_is_nomap(reg)) {
+			if (!IS_ALIGNED(reg->base, PMD_SIZE)) {
+				phys_addr_t len;
+
+				len = round_up(reg->base, PMD_SIZE) - reg->base;
+				memblock_mark_nomap(reg->base, len);
+			}
+			break;
+		}
+	}
+
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
 
+		if (memblock_is_nomap(reg))
+			continue;
+
 		if (reg->base < vmalloc_limit) {
 			if (block_end > lowmem_limit)
 				/*
diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c
index 0f5faf30d9bf..d546efad7e97 100644
--- a/arch/arm/mm/pageattr.c
+++ b/arch/arm/mm/pageattr.c
@@ -14,8 +14,7 @@ struct page_change_data {
 	pgprot_t clear_mask;
 };
 
-static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
-			void *data)
+static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
 {
 	struct page_change_data *cdata = data;
 	pte_t pte = *ptep;
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 83741c31757d..c4e8006a1a8c 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -389,6 +389,11 @@ __ca12_errata:
 	orr	r10, r10, #1 << 24		@ set bit #24
 	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
 #endif
+#ifdef CONFIG_ARM_ERRATA_857271
+	mrc	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orr	r10, r10, #3 << 10		@ set bits #10 and #11
+	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
 	b	__errata_finish
 
 __ca17_errata:
@@ -404,6 +409,11 @@ __ca17_errata:
 	orrle	r10, r10, #1 << 12		@ set bit #12
 	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
 #endif
+#ifdef CONFIG_ARM_ERRATA_857272
+	mrc	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orr	r10, r10, #3 << 10		@ set bits #10 and #11
+	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
 	b	__errata_finish
 
 __v7_pj4b_setup:
diff --git a/arch/arm/mm/ptdump_debugfs.c b/arch/arm/mm/ptdump_debugfs.c
index be8d87be4b93..598b636615a2 100644
--- a/arch/arm/mm/ptdump_debugfs.c
+++ b/arch/arm/mm/ptdump_debugfs.c
@@ -24,11 +24,7 @@ static const struct file_operations ptdump_fops = {
 	.release	= single_release,
 };
 
-int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
+void ptdump_debugfs_register(struct ptdump_info *info, const char *name)
 {
-	struct dentry *pe;
-
-	pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
-	return pe ? 0 : -ENOMEM;
-
+	debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
 }