12 files changed, 210 insertions, 173 deletions

diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 3815a8262af0..8c48c5c22a33 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -17,12 +17,6 @@
  */
 	.align	5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_V6
-	sub	r1, sp, #4			@ Get unused stack location
-	strex	r0, r1, [r1]			@ Clear the exclusive monitor
-#elif defined(CONFIG_CPU_32v6K)
-	clrex
-#endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 703375277ba6..4812ad054214 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -13,12 +13,6 @@
  */
 	.align	5
 ENTRY(v7_early_abort)
-	/*
-	 * The effect of data aborts on on the exclusive access monitor are
-	 * UNPREDICTABLE. Do a CLREX to clear the state
-	 */
-	clrex
-
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 0c1ab49e5f7b..83792f4324ea 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -41,6 +41,7 @@
  * This code is not portable to processors with late data abort handling.
  */
 #define CODING_BITS(i)	(i & 0x0e000000)
+#define COND_BITS(i)	(i & 0xf0000000)
 
 #define LDST_I_BIT(i)	(i & (1 << 26))		/* Immediate constant	*/
 #define LDST_P_BIT(i)	(i & (1 << 24))		/* Preindex		*/
@@ -821,6 +822,8 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		break;
 
 	case 0x04000000:	/* ldr or str immediate */
+		if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */
+			goto bad;
 		offset.un = OFFSET_BITS(instr);
 		handler = do_alignment_ldrstr;
 		break;
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 5f2c988a06ac..55f9d6e0cc88 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/spinlock.h>
+#include <linux/log2.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -945,6 +946,98 @@ static int l2_wt_override;
  * pass it though the device tree */
 static u32 cache_id_part_number_from_dt;
 
+/**
+ * l2x0_cache_size_of_parse() - read cache size parameters from DT
+ * @np: the device tree node for the l2 cache
+ * @aux_val: pointer to machine-supplied auxilary register value, to
+ * be augmented by the call (bits to be set to 1)
+ * @aux_mask: pointer to machine-supplied auxilary register mask, to
+ * be augmented by the call (bits to be set to 0)
+ * @associativity: variable to return the calculated associativity in
+ * @max_way_size: the maximum size in bytes for the cache ways
+ */
+static void __init l2x0_cache_size_of_parse(const struct device_node *np,
+					    u32 *aux_val, u32 *aux_mask,
+					    u32 *associativity,
+					    u32 max_way_size)
+{
+	u32 mask = 0, val = 0;
+	u32 cache_size = 0, sets = 0;
+	u32 way_size_bits = 1;
+	u32 way_size = 0;
+	u32 block_size = 0;
+	u32 line_size = 0;
+
+	of_property_read_u32(np, "cache-size", &cache_size);
+	of_property_read_u32(np, "cache-sets", &sets);
+	of_property_read_u32(np, "cache-block-size", &block_size);
+	of_property_read_u32(np, "cache-line-size", &line_size);
+
+	if (!cache_size || !sets)
+		return;
+
+	/* All these l2 caches have the same line = block size actually */
+	if (!line_size) {
+		if (block_size) {
+			/* If linesize if not given, it is equal to blocksize */
+			line_size = block_size;
+		} else {
+			/* Fall back to known size */
+			pr_warn("L2C OF: no cache block/line size given: "
+				"falling back to default size %d bytes\n",
+				CACHE_LINE_SIZE);
+			line_size = CACHE_LINE_SIZE;
+		}
+	}
+
+	if (line_size != CACHE_LINE_SIZE)
+		pr_warn("L2C OF: DT supplied line size %d bytes does "
+			"not match hardware line size of %d bytes\n",
+			line_size,
+			CACHE_LINE_SIZE);
+
+	/*
+	 * Since:
+	 * set size = cache size / sets
+	 * ways = cache size / (sets * line size)
+	 * way size = cache size / (cache size / (sets * line size))
+	 * way size = sets * line size
+	 * associativity = ways = cache size / way size
+	 */
+	way_size = sets * line_size;
+	*associativity = cache_size / way_size;
+
+	if (way_size > max_way_size) {
+		pr_err("L2C OF: set size %dKB is too large\n", way_size);
+		return;
+	}
+
+	pr_info("L2C OF: override cache size: %d bytes (%dKB)\n",
+		cache_size, cache_size >> 10);
+	pr_info("L2C OF: override line size: %d bytes\n", line_size);
+	pr_info("L2C OF: override way size: %d bytes (%dKB)\n",
+		way_size, way_size >> 10);
+	pr_info("L2C OF: override associativity: %d\n", *associativity);
+
+	/*
+	 * Calculates the bits 17:19 to set for way size:
+	 * 512KB -> 6, 256KB -> 5, ... 16KB -> 1
+	 */
+	way_size_bits = ilog2(way_size >> 10) - 3;
+	if (way_size_bits < 1 || way_size_bits > 6) {
+		pr_err("L2C OF: cache way size illegal: %dKB is not mapped\n",
+		       way_size);
+		return;
+	}
+
+	mask |= L2C_AUX_CTRL_WAY_SIZE_MASK;
+	val |= (way_size_bits << L2C_AUX_CTRL_WAY_SIZE_SHIFT);
+
+	*aux_val &= ~mask;
+	*aux_val |= val;
+	*aux_mask &= ~mask;
+}
+
 static void __init l2x0_of_parse(const struct device_node *np,
 				 u32 *aux_val, u32 *aux_mask)
 {
@@ -952,6 +1045,7 @@ static void __init l2x0_of_parse(const struct device_node *np,
 	u32 tag = 0;
 	u32 dirty = 0;
 	u32 val = 0, mask = 0;
+	u32 assoc;
 
 	of_property_read_u32(np, "arm,tag-latency", &tag);
 	if (tag) {
@@ -974,6 +1068,15 @@ static void __init l2x0_of_parse(const struct device_node *np,
 		val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT;
 	}
 
+	l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_256K);
+	if (assoc > 8) {
+		pr_err("l2x0 of: cache setting yield too high associativity\n");
+		pr_err("l2x0 of: %d calculated, max 8\n", assoc);
+	} else {
+		mask |= L2X0_AUX_CTRL_ASSOC_MASK;
+		val |= (assoc << L2X0_AUX_CTRL_ASSOC_SHIFT);
+	}
+
 	*aux_val &= ~mask;
 	*aux_val |= val;
 	*aux_mask &= ~mask;
@@ -1021,6 +1124,7 @@ static void __init l2c310_of_parse(const struct device_node *np,
 	u32 data[3] = { 0, 0, 0 };
 	u32 tag[3] = { 0, 0, 0 };
 	u32 filter[2] = { 0, 0 };
+	u32 assoc;
 
 	of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag));
 	if (tag[0] && tag[1] && tag[2])
@@ -1047,6 +1151,23 @@ static void __init l2c310_of_parse(const struct device_node *np,
 		writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L310_ADDR_FILTER_EN,
 			       l2x0_base + L310_ADDR_FILTER_START);
 	}
+
+	l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_512K);
+	switch (assoc) {
+	case 16:
+		*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+		*aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16;
+		*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+		break;
+	case 8:
+		*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+		*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+		break;
+	default:
+		pr_err("PL310 OF: cache setting yield illegal associativity\n");
+		pr_err("PL310 OF: %d calculated, only 8 and 16 legal\n", assoc);
+		break;
+	}
 }
 
 static const struct l2c_init_data of_l2c310_data __initconst = {
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7a996aaa061e..c245d903927f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -12,6 +12,7 @@
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/genalloc.h>
 #include <linux/gfp.h>
 #include <linux/errno.h>
 #include <linux/list.h>
@@ -298,57 +299,29 @@ static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
 	const void *caller)
 {
-	struct vm_struct *area;
-	unsigned long addr;
-
 	/*
 	 * DMA allocation can be mapped to user space, so lets
 	 * set VM_USERMAP flags too.
 	 */
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-	addr = (unsigned long)area->addr;
-	area->phys_addr = __pfn_to_phys(page_to_pfn(page));
-
-	if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
-		vunmap((void *)addr);
-		return NULL;
-	}
-	return (void *)addr;
+	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)
 {
-	unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;
-	struct vm_struct *area = find_vm_area(cpu_addr);
-	if (!area || (area->flags & flags) != flags) {
-		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
-		return;
-	}
-	unmap_kernel_range((unsigned long)cpu_addr, size);
-	vunmap(cpu_addr);
+	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;
 
-struct dma_pool {
-	size_t size;
-	spinlock_t lock;
-	unsigned long *bitmap;
-	unsigned long nr_pages;
-	void *vaddr;
-	struct page **pages;
-};
-
-static struct dma_pool atomic_pool = {
-	.size = DEFAULT_DMA_COHERENT_POOL_SIZE,
-};
+static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
 
 static int __init early_coherent_pool(char *p)
 {
-	atomic_pool.size = memparse(p, &p);
+	atomic_pool_size = memparse(p, &p);
 	return 0;
 }
 early_param("coherent_pool", early_coherent_pool);
@@ -358,14 +331,14 @@ void __init init_dma_coherent_pool_size(unsigned long size)
 	/*
 	 * Catch any attempt to set the pool size too late.
 	 */
-	BUG_ON(atomic_pool.vaddr);
+	BUG_ON(atomic_pool);
 
 	/*
 	 * Set architecture specific coherent pool size only if
 	 * it has not been changed by kernel command line parameter.
 	 */
-	if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE)
-		atomic_pool.size = size;
+	if (atomic_pool_size == DEFAULT_DMA_COHERENT_POOL_SIZE)
+		atomic_pool_size = size;
 }
 
 /*
@@ -373,52 +346,44 @@ void __init init_dma_coherent_pool_size(unsigned long size)
  */
 static int __init atomic_pool_init(void)
 {
-	struct dma_pool *pool = &atomic_pool;
 	pgprot_t prot = pgprot_dmacoherent(PAGE_KERNEL);
 	gfp_t gfp = GFP_KERNEL | GFP_DMA;
-	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
-	unsigned long *bitmap;
 	struct page *page;
-	struct page **pages;
 	void *ptr;
-	int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
 
-	bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!bitmap)
-		goto no_bitmap;
-
-	pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);
-	if (!pages)
-		goto no_pages;
+	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+	if (!atomic_pool)
+		goto out;
 
 	if (dev_get_cma_area(NULL))
-		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
-					      atomic_pool_init);
+		ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
+					      &page, atomic_pool_init);
 	else
-		ptr = __alloc_remap_buffer(NULL, pool->size, gfp, prot, &page,
-					   atomic_pool_init);
+		ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
+					   &page, atomic_pool_init);
 	if (ptr) {
-		int i;
-
-		for (i = 0; i < nr_pages; i++)
-			pages[i] = page + i;
-
-		spin_lock_init(&pool->lock);
-		pool->vaddr = ptr;
-		pool->pages = pages;
-		pool->bitmap = bitmap;
-		pool->nr_pages = nr_pages;
-		pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",
-		       (unsigned)pool->size / 1024);
+		int ret;
+
+		ret = gen_pool_add_virt(atomic_pool, (unsigned long)ptr,
+					page_to_phys(page),
+					atomic_pool_size, -1);
+		if (ret)
+			goto destroy_genpool;
+
+		gen_pool_set_algo(atomic_pool,
+				gen_pool_first_fit_order_align,
+				(void *)PAGE_SHIFT);
+		pr_info("DMA: preallocated %zd KiB pool for atomic coherent allocations\n",
+		       atomic_pool_size / 1024);
 		return 0;
 	}
 
-	kfree(pages);
-no_pages:
-	kfree(bitmap);
-no_bitmap:
-	pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
-	       (unsigned)pool->size / 1024);
+destroy_genpool:
+	gen_pool_destroy(atomic_pool);
+	atomic_pool = NULL;
+out:
+	pr_err("DMA: failed to allocate %zx KiB pool for atomic coherent allocation\n",
+	       atomic_pool_size / 1024);
 	return -ENOMEM;
 }
 /*
@@ -522,76 +487,36 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 
 static void *__alloc_from_pool(size_t size, struct page **ret_page)
 {
-	struct dma_pool *pool = &atomic_pool;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned int pageno;
-	unsigned long flags;
+	unsigned long val;
 	void *ptr = NULL;
-	unsigned long align_mask;
 
-	if (!pool->vaddr) {
+	if (!atomic_pool) {
 		WARN(1, "coherent pool not initialised!\n");
 		return NULL;
 	}
 
-	/*
-	 * Align the region allocation - allocations from pool are rather
-	 * small, so align them to their order in pages, minimum is a page
-	 * size. This helps reduce fragmentation of the DMA space.
-	 */
-	align_mask = (1 << get_order(size)) - 1;
-
-	spin_lock_irqsave(&pool->lock, flags);
-	pageno = bitmap_find_next_zero_area(pool->bitmap, pool->nr_pages,
-					    0, count, align_mask);
-	if (pageno < pool->nr_pages) {
-		bitmap_set(pool->bitmap, pageno, count);
-		ptr = pool->vaddr + PAGE_SIZE * pageno;
-		*ret_page = pool->pages[pageno];
-	} else {
-		pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n"
-			    "Please increase it with coherent_pool= kernel parameter!\n",
-			    (unsigned)pool->size / 1024);
+	val = gen_pool_alloc(atomic_pool, size);
+	if (val) {
+		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+		*ret_page = phys_to_page(phys);
+		ptr = (void *)val;
 	}
-	spin_unlock_irqrestore(&pool->lock, flags);
 
 	return ptr;
 }
 
 static bool __in_atomic_pool(void *start, size_t size)
 {
-	struct dma_pool *pool = &atomic_pool;
-	void *end = start + size;
-	void *pool_start = pool->vaddr;
-	void *pool_end = pool->vaddr + pool->size;
-
-	if (start < pool_start || start >= pool_end)
-		return false;
-
-	if (end <= pool_end)
-		return true;
-
-	WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n",
-	     start, end - 1, pool_start, pool_end - 1);
-
-	return false;
+	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
 }
 
 static int __free_from_pool(void *start, size_t size)
 {
-	struct dma_pool *pool = &atomic_pool;
-	unsigned long pageno, count;
-	unsigned long flags;
-
 	if (!__in_atomic_pool(start, size))
 		return 0;
 
-	pageno = (start - pool->vaddr) >> PAGE_SHIFT;
-	count = size >> PAGE_SHIFT;
-
-	spin_lock_irqsave(&pool->lock, flags);
-	bitmap_clear(pool->bitmap, pageno, count);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	gen_pool_free(atomic_pool, (unsigned long)start, size);
 
 	return 1;
 }
@@ -1271,29 +1196,8 @@ static void *
 __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
 		    const void *caller)
 {
-	unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct vm_struct *area;
-	unsigned long p;
-
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-
-	area->pages = pages;
-	area->nr_pages = nr_pages;
-	p = (unsigned long)area->addr;
-
-	for (i = 0; i < nr_pages; i++) {
-		phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
-		if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
-			goto err;
-		p += PAGE_SIZE;
-	}
-	return area->addr;
-err:
-	unmap_kernel_range((unsigned long)area->addr, size);
-	vunmap(area->addr);
+	return dma_common_pages_remap(pages, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
 	return NULL;
 }
 
@@ -1355,11 +1259,13 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
 
 static struct page **__atomic_get_pages(void *addr)
 {
-	struct dma_pool *pool = &atomic_pool;
-	struct page **pages = pool->pages;
-	int offs = (addr - pool->vaddr) >> PAGE_SHIFT;
+	struct page *page;
+	phys_addr_t phys;
+
+	phys = gen_pool_virt_to_phys(atomic_pool, (unsigned long)addr);
+	page = phys_to_page(phys);
 
-	return pages + offs;
+	return (struct page **)page;
 }
 
 static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
@@ -1501,8 +1407,8 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	}
 
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
-		unmap_kernel_range((unsigned long)cpu_addr, size);
-		vunmap(cpu_addr);
+		dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 	}
 
 	__iommu_remove_mapping(dev, handle, size);
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 43d54f5b26b9..265b836b3bd1 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -400,3 +400,18 @@ void __flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned l
 	 */
 	__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 }
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp)
+{
+	pmd_t pmd = pmd_mksplitting(*pmdp);
+	VM_BUG_ON(address & ~PMD_MASK);
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+
+	/* dummy IPI to serialise against fast_gup */
+	kick_all_cpus_sync();
+}
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index c447ec70e868..e7a81cebbb2e 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -27,7 +27,7 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 	if (pud_none_or_clear_bad(pud) || (pud_val(*pud) & L_PGD_SWAPPER)) {
 		pmd = pmd_alloc_one(&init_mm, addr);
 		if (!pmd) {
-			pr_warning("Failed to allocate identity pmd.\n");
+			pr_warn("Failed to allocate identity pmd.\n");
 			return;
 		}
 		/*
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 659c75d808dc..92bba32d9230 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -322,7 +322,7 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
 	 * reserve memory for DMA contigouos allocations,
 	 * must come from DMA area inside low memory
 	 */
-	dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit));
+	dma_contiguous_reserve(arm_dma_limit);
 
 	arm_memblock_steal_permitted = false;
 	memblock_dump_all();
@@ -636,6 +636,11 @@ static int keep_initrd;
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd) {
+		if (start == initrd_start)
+			start = round_down(start, PAGE_SIZE);
+		if (end == initrd_end)
+			end = round_up(end, PAGE_SIZE);
+
 		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
 		free_reserved_area((void *)start, (void *)end, -1, "initrd");
 	}
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 8348ed6b2efe..9f98cec7fe1e 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -223,13 +223,13 @@ early_param("ecc", early_ecc);
 
 static int __init early_cachepolicy(char *p)
 {
-	pr_warning("cachepolicy kernel parameter not supported without cp15\n");
+	pr_warn("cachepolicy kernel parameter not supported without cp15\n");
 }
 early_param("cachepolicy", early_cachepolicy);
 
 static int __init noalign_setup(char *__unused)
 {
-	pr_warning("noalign kernel parameter not supported without cp15\n");
+	pr_warn("noalign kernel parameter not supported without cp15\n");
 }
 __setup("noalign", noalign_setup);
 
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index ee1d80593958..ba1196c968d8 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -279,7 +279,7 @@ ENTRY(\name\()_processor_functions)
 
 	.if \suspend
 	.word	cpu_\name\()_suspend_size
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 	.word	cpu_\name\()_do_suspend
 	.word	cpu_\name\()_do_resume
 #else
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 1a24e9232ec8..d3daed0ae0ad 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -146,7 +146,6 @@ ENDPROC(cpu_v7_set_pte_ext)
 	mov	\tmp, \ttbr1, lsr #(32 - ARCH_PGD_SHIFT)	@ upper bits
 	mov	\ttbr1, \ttbr1, lsl #ARCH_PGD_SHIFT		@ lower bits
 	addls	\ttbr1, \ttbr1, #TTBR1_OFFSET
-	adcls	\tmp, \tmp, #0
 	mcrr	p15, 1, \ttbr1, \tmp, c2			@ load TTBR1
 	mov	\tmp, \ttbr0, lsr #(32 - ARCH_PGD_SHIFT)	@ upper bits
 	mov	\ttbr0, \ttbr0, lsl #ARCH_PGD_SHIFT		@ lower bits
@@ -158,9 +157,9 @@ ENDPROC(cpu_v7_set_pte_ext)
 	 *  TFR   EV X F   IHD LR    S
 	 * .EEE ..EE PUI. .TAT 4RVI ZWRS BLDP WCAM
 	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
-	 *   11    0 110    1  0011 1100 .111 1101 < we want
+	 *   11    0 110    0  0011 1100 .111 1101 < we want
 	 */
 	.align	2
 	.type	v7_crval, #object
 v7_crval:
-	crval	clear=0x0120c302, mmuset=0x30c23c7d, ucset=0x00c01c7c
+	crval	clear=0x0122c302, mmuset=0x30c03c7d, ucset=0x00c01c7c
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index b5d67db20897..b3a947863ac7 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -570,7 +570,7 @@ __v7_ca15mp_proc_info:
 __v7_b15mp_proc_info:
 	.long	0x420f00f0
 	.long	0xff0ffff0
-	__v7_proc __v7_b15mp_setup, hwcaps = HWCAP_IDIV
+	__v7_proc __v7_b15mp_setup
 	.size	__v7_b15mp_proc_info, . - __v7_b15mp_proc_info
 
 	/*