Merge branch 'master' into for-next

41 files changed, 409 insertions, 699 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 346ae14824a..87ec141fcaa 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -717,17 +717,6 @@ config TLS_REG_EMUL
 	  a few prototypes like that in existence) and therefore access to
 	  that required register must be emulated.
 
-config HAS_TLS_REG
-	bool
-	depends on !TLS_REG_EMUL
-	default y if SMP || CPU_32v7
-	help
-	  This selects support for the CP15 thread register.
-	  It is defined to be available on some ARMv6 processors (including
-	  all SMP capable ARMv6's) or later processors.  User space may
-	  assume directly accessing that register and always obtain the
-	  expected value only on ARMv7 and above.
-
 config NEEDS_SYSCALL_FOR_CMPXCHG
 	bool
 	help
@@ -735,6 +724,25 @@ config NEEDS_SYSCALL_FOR_CMPXCHG
 	  Forget about fast user space cmpxchg support.
 	  It is just not possible.
 
+config DMA_CACHE_RWFO
+	bool "Enable read/write for ownership DMA cache maintenance"
+	depends on CPU_V6 && SMP
+	default y
+	help
+	  The Snoop Control Unit on ARM11MPCore does not detect the
+	  cache maintenance operations and the dma_{map,unmap}_area()
+	  functions may leave stale cache entries on other CPUs. By
+	  enabling this option, Read or Write For Ownership in the ARMv6
+	  DMA cache maintenance functions is performed. These LDR/STR
+	  instructions change the cache line state to shared or modified
+	  so that the cache operation has the desired effect.
+
+	  Note that the workaround is only valid on processors that do
+	  not perform speculative loads into the D-cache. For such
+	  processors, if cache maintenance operations are not broadcast
+	  in hardware, other workarounds are needed (e.g. cache
+	  maintenance broadcasting in software via FIQ).
+
 config OUTER_CACHE
 	bool
 
@@ -794,6 +802,8 @@ config ARM_L1_CACHE_SHIFT
 
 config ARM_DMA_MEM_BUFFERABLE
 	bool "Use non-cacheable memory for DMA" if CPU_V6 && !CPU_V7
+	depends on !(MACH_REALVIEW_PB1176 || REALVIEW_EB_ARM11MP || \
+		     MACH_REALVIEW_PB11MP)
 	default y if CPU_V6 || CPU_V7
 	help
 	  Historically, the kernel has used strongly ordered mappings to
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index e8d34a80851..d63b6c41375 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -15,7 +15,6 @@ endif
 obj-$(CONFIG_MODULES)		+= proc-syms.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
-obj-$(CONFIG_DISCONTIGMEM)	+= discontig.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 
 obj-$(CONFIG_CPU_ABRT_NOMMU)	+= abort-nommu.o
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 6f98c358989..d073b64ae87 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -924,8 +924,20 @@ static int __init alignment_init(void)
 		ai_usermode = UM_FIXUP;
 	}
 
-	hook_fault_code(1, do_alignment, SIGILL, "alignment exception");
-	hook_fault_code(3, do_alignment, SIGILL, "alignment exception");
+	hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,
+			"alignment exception");
+
+	/*
+	 * ARMv6K and ARMv7 use fault status 3 (0b00011) as Access Flag section
+	 * fault, not as alignment error.
+	 *
+	 * TODO: handle ARMv6K properly. Runtime check for 'K' extension is
+	 * needed.
+	 */
+	if (cpu_architecture() <= CPU_ARCH_ARMv6) {
+		hook_fault_code(3, do_alignment, SIGBUS, BUS_ADRALN,
+				"alignment exception");
+	}
 
 	return 0;
 }
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 9819869d2bc..9982eb385c0 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -32,14 +32,14 @@ static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
 static inline void cache_wait(void __iomem *reg, unsigned long mask)
 {
 	/* wait for the operation to complete */
-	while (readl(reg) & mask)
+	while (readl_relaxed(reg) & mask)
 		;
 }
 
 static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
-	writel(0, base + L2X0_CACHE_SYNC);
+	writel_relaxed(0, base + L2X0_CACHE_SYNC);
 	cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 
@@ -47,14 +47,14 @@ static inline void l2x0_clean_line(unsigned long addr)
 {
 	void __iomem *base = l2x0_base;
 	cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
-	writel(addr, base + L2X0_CLEAN_LINE_PA);
+	writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA);
 }
 
 static inline void l2x0_inv_line(unsigned long addr)
 {
 	void __iomem *base = l2x0_base;
 	cache_wait(base + L2X0_INV_LINE_PA, 1);
-	writel(addr, base + L2X0_INV_LINE_PA);
+	writel_relaxed(addr, base + L2X0_INV_LINE_PA);
 }
 
 #ifdef CONFIG_PL310_ERRATA_588369
@@ -75,9 +75,9 @@ static inline void l2x0_flush_line(unsigned long addr)
 
 	/* Clean by PA followed by Invalidate by PA */
 	cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
-	writel(addr, base + L2X0_CLEAN_LINE_PA);
+	writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA);
 	cache_wait(base + L2X0_INV_LINE_PA, 1);
-	writel(addr, base + L2X0_INV_LINE_PA);
+	writel_relaxed(addr, base + L2X0_INV_LINE_PA);
 }
 #else
 
@@ -90,7 +90,7 @@ static inline void l2x0_flush_line(unsigned long addr)
 {
 	void __iomem *base = l2x0_base;
 	cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-	writel(addr, base + L2X0_CLEAN_INV_LINE_PA);
+	writel_relaxed(addr, base + L2X0_CLEAN_INV_LINE_PA);
 }
 #endif
 
@@ -109,7 +109,7 @@ static inline void l2x0_inv_all(void)
 
 	/* invalidate all ways */
 	spin_lock_irqsave(&l2x0_lock, flags);
-	writel(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
+	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
 	cache_wait(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
 	cache_sync();
 	spin_unlock_irqrestore(&l2x0_lock, flags);
@@ -215,8 +215,11 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 
 	l2x0_base = base;
 
-	cache_id = readl(l2x0_base + L2X0_CACHE_ID);
-	aux = readl(l2x0_base + L2X0_AUX_CTRL);
+	cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
+	aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
+
+	aux &= aux_mask;
+	aux |= aux_val;
 
 	/* Determine the number of ways */
 	switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
@@ -245,17 +248,15 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	 * If you are booting from non-secure mode
 	 * accessing the below registers will fault.
 	 */
-	if (!(readl(l2x0_base + L2X0_CTRL) & 1)) {
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
 
 		/* l2x0 controller is disabled */
-		aux &= aux_mask;
-		aux |= aux_val;
-		writel(aux, l2x0_base + L2X0_AUX_CTRL);
+		writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL);
 
 		l2x0_inv_all();
 
 		/* enable L2X0 */
-		writel(1, l2x0_base + L2X0_CTRL);
+		writel_relaxed(1, l2x0_base + L2X0_CTRL);
 	}
 
 	outer_cache.inv_range = l2x0_inv_range;
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index e46ecd84713..86aa689ef1a 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -211,8 +211,9 @@ v6_dma_inv_range:
 	mcrne	p15, 0, r1, c7, c15, 1		@ clean & invalidate unified line
 #endif
 1:
-#ifdef CONFIG_SMP
-	str	r0, [r0]			@ write for ownership
+#ifdef CONFIG_DMA_CACHE_RWFO
+	ldr	r2, [r0]			@ read for ownership
+	str	r2, [r0]			@ write for ownership
 #endif
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D line
@@ -234,7 +235,7 @@ v6_dma_inv_range:
 v6_dma_clean_range:
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
-#ifdef CONFIG_SMP
+#ifdef CONFIG_DMA_CACHE_RWFO
 	ldr	r2, [r0]			@ read for ownership
 #endif
 #ifdef HARVARD_CACHE
@@ -257,7 +258,7 @@ v6_dma_clean_range:
 ENTRY(v6_dma_flush_range)
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
-#ifdef CONFIG_SMP
+#ifdef CONFIG_DMA_CACHE_RWFO
 	ldr	r2, [r0]			@ read for ownership
 	str	r2, [r0]			@ write for ownership
 #endif
@@ -283,9 +284,13 @@ ENTRY(v6_dma_map_area)
 	add	r1, r1, r0
 	teq	r2, #DMA_FROM_DEVICE
 	beq	v6_dma_inv_range
+#ifndef CONFIG_DMA_CACHE_RWFO
+	b	v6_dma_clean_range
+#else
 	teq	r2, #DMA_TO_DEVICE
 	beq	v6_dma_clean_range
 	b	v6_dma_flush_range
+#endif
 ENDPROC(v6_dma_map_area)
 
 /*
@@ -295,6 +300,11 @@ ENDPROC(v6_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(v6_dma_unmap_area)
+#ifndef CONFIG_DMA_CACHE_RWFO
+	add	r1, r1, r0
+	teq	r2, #DMA_TO_DEVICE
+	bne	v6_dma_inv_range
+#endif
 	mov	pc, lr
 ENDPROC(v6_dma_unmap_area)
 
diff --git a/arch/arm/mm/discontig.c b/arch/arm/mm/discontig.c
deleted file mode 100644
index c8c0c4b0f0a..00000000000
--- a/arch/arm/mm/discontig.c
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * linux/arch/arm/mm/discontig.c
- *
- * Discontiguous memory support.
- *
- * Initial code: Copyright (C) 1999-2000 Nicolas Pitre
- *
- * 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/module.h>
-#include <linux/mmzone.h>
-#include <linux/bootmem.h>
-
-#if MAX_NUMNODES != 4 && MAX_NUMNODES != 16
-# error Fix Me Please
-#endif
-
-/*
- * Our node_data structure for discontiguous memory.
- */
-
-pg_data_t discontig_node_data[MAX_NUMNODES] = {
-  { .bdata = &bootmem_node_data[0] },
-  { .bdata = &bootmem_node_data[1] },
-  { .bdata = &bootmem_node_data[2] },
-  { .bdata = &bootmem_node_data[3] },
-#if MAX_NUMNODES == 16
-  { .bdata = &bootmem_node_data[4] },
-  { .bdata = &bootmem_node_data[5] },
-  { .bdata = &bootmem_node_data[6] },
-  { .bdata = &bootmem_node_data[7] },
-  { .bdata = &bootmem_node_data[8] },
-  { .bdata = &bootmem_node_data[9] },
-  { .bdata = &bootmem_node_data[10] },
-  { .bdata = &bootmem_node_data[11] },
-  { .bdata = &bootmem_node_data[12] },
-  { .bdata = &bootmem_node_data[13] },
-  { .bdata = &bootmem_node_data[14] },
-  { .bdata = &bootmem_node_data[15] },
-#endif
-};
-
-EXPORT_SYMBOL(discontig_node_data);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 13fa536d82e..c704eed63c5 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -24,15 +24,6 @@
 #include <asm/tlbflush.h>
 #include <asm/sizes.h>
 
-/* Sanity check size */
-#if (CONSISTENT_DMA_SIZE % SZ_2M)
-#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
-#endif
-
-#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
-#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
-
 static u64 get_coherent_dma_mask(struct device *dev)
 {
 	u64 mask = ISA_DMA_THRESHOLD;
@@ -123,6 +114,15 @@ static void __dma_free_buffer(struct page *page, size_t size)
 }
 
 #ifdef CONFIG_MMU
+/* Sanity check size */
+#if (CONSISTENT_DMA_SIZE % SZ_2M)
+#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
+#endif
+
+#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
+#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
+#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
+
 /*
  * These are the page tables (2MB each) covering uncached, DMA consistent allocations
  */
@@ -183,6 +183,8 @@ static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
 {
 	struct arm_vmregion *c;
+	size_t align;
+	int bit;
 
 	if (!consistent_pte[0]) {
 		printk(KERN_ERR "%s: not initialised\n", __func__);
@@ -191,9 +193,20 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
 	}
 
 	/*
+	 * Align the virtual region allocation - maximum alignment is
+	 * a section size, minimum is a page size.  This helps reduce
+	 * fragmentation of the DMA space, and also prevents allocations
+	 * smaller than a section from crossing a section boundary.
+	 */
+	bit = fls(size - 1) + 1;
+	if (bit > SECTION_SHIFT)
+		bit = SECTION_SHIFT;
+	align = 1 << bit;
+
+	/*
 	 * Allocate a virtual address in the consistent mapping region.
 	 */
-	c = arm_vmregion_alloc(&consistent_head, size,
+	c = arm_vmregion_alloc(&consistent_head, align, size,
 			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
 	if (c) {
 		pte_t *pte;
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index cbfb2edcf7d..23b0b03af5e 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -413,7 +413,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	pmd_k = pmd_offset(pgd_k, addr);
 	pmd   = pmd_offset(pgd, addr);
 
-	if (pmd_none(*pmd_k))
+	/*
+	 * On ARM one Linux PGD entry contains two hardware entries (see page
+	 * tables layout in pgtable.h). We normally guarantee that we always
+	 * fill both L1 entries. But create_mapping() doesn't follow the rule.
+	 * It can create inidividual L1 entries, so here we have to call
+	 * pmd_none() check for the entry really corresponded to address, not
+	 * for the first of pair.
+	 */
+	index = (addr >> SECTION_SHIFT) & 1;
+	if (pmd_none(pmd_k[index]))
 		goto bad_area;
 
 	copy_pmd(pmd, pmd_k);
@@ -463,15 +472,10 @@ static struct fsr_info {
 	 * defines these to be "precise" aborts.
 	 */
 	{ do_bad,		SIGSEGV, 0,		"vector exception"		   },
-	{ do_bad,		SIGILL,	 BUS_ADRALN,	"alignment exception"		   },
+	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
 	{ do_bad,		SIGKILL, 0,		"terminal exception"		   },
-	{ do_bad,		SIGILL,	 BUS_ADRALN,	"alignment exception"		   },
-/* Do we need runtime check ? */
-#if __LINUX_ARM_ARCH__ < 6
+	{ do_bad,		SIGBUS,	 BUS_ADRALN,	"alignment exception"		   },
 	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
-#else
-	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"I-cache maintenance fault"	   },
-#endif
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"section translation fault"	   },
 	{ do_bad,		SIGBUS,	 0,		"external abort on linefetch"	   },
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"page translation fault"	   },
@@ -508,13 +512,15 @@ static struct fsr_info {
 
 void __init
 hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
-		int sig, const char *name)
+		int sig, int code, const char *name)
 {
-	if (nr >= 0 && nr < ARRAY_SIZE(fsr_info)) {
-		fsr_info[nr].fn   = fn;
-		fsr_info[nr].sig  = sig;
-		fsr_info[nr].name = name;
-	}
+	if (nr < 0 || nr >= ARRAY_SIZE(fsr_info))
+		BUG();
+
+	fsr_info[nr].fn   = fn;
+	fsr_info[nr].sig  = sig;
+	fsr_info[nr].code = code;
+	fsr_info[nr].name = name;
 }
 
 /*
@@ -594,3 +600,25 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 	arm_notify_die("", regs, &info, ifsr, 0);
 }
 
+static int __init exceptions_init(void)
+{
+	if (cpu_architecture() >= CPU_ARCH_ARMv6) {
+		hook_fault_code(4, do_translation_fault, SIGSEGV, SEGV_MAPERR,
+				"I-cache maintenance fault");
+	}
+
+	if (cpu_architecture() >= CPU_ARCH_ARMv7) {
+		/*
+		 * TODO: Access flag faults introduced in ARMv6K.
+		 * Runtime check for 'K' extension is needed
+		 */
+		hook_fault_code(3, do_bad, SIGSEGV, SEGV_MAPERR,
+				"section access flag fault");
+		hook_fault_code(6, do_bad, SIGSEGV, SEGV_MAPERR,
+				"section access flag fault");
+	}
+
+	return 0;
+}
+
+arch_initcall(exceptions_init);
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 086816b205b..6ab244062b4 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -163,19 +163,22 @@ static DEFINE_PER_CPU(int, kmap_high_l1_vipt_depth);
 
 void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte)
 {
-	unsigned int idx, cpu = smp_processor_id();
-	int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
+	unsigned int idx, cpu;
+	int *depth;
 	unsigned long vaddr, flags;
 	pte_t pte, *ptep;
 
+	if (!in_interrupt())
+		preempt_disable();
+
+	cpu = smp_processor_id();
+	depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
+
 	idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	ptep = TOP_PTE(vaddr);
 	pte = mk_pte(page, kmap_prot);
 
-	if (!in_interrupt())
-		preempt_disable();
-
 	raw_local_irq_save(flags);
 	(*depth)++;
 	if (pte_val(*ptep) == pte_val(pte)) {
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index f6a99946532..7185b00650f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -17,6 +17,7 @@
 #include <linux/initrd.h>
 #include <linux/highmem.h>
 #include <linux/gfp.h>
+#include <linux/memblock.h>
 
 #include <asm/mach-types.h>
 #include <asm/sections.h>
@@ -79,38 +80,37 @@ struct meminfo meminfo;
 void show_mem(void)
 {
 	int free = 0, total = 0, reserved = 0;
-	int shared = 0, cached = 0, slab = 0, node, i;
+	int shared = 0, cached = 0, slab = 0, i;
 	struct meminfo * mi = &meminfo;
 
 	printk("Mem-info:\n");
 	show_free_areas();
-	for_each_online_node(node) {
-		for_each_nodebank (i,mi,node) {
-			struct membank *bank = &mi->bank[i];
-			unsigned int pfn1, pfn2;
-			struct page *page, *end;
-
-			pfn1 = bank_pfn_start(bank);
-			pfn2 = bank_pfn_end(bank);
-
-			page = pfn_to_page(pfn1);
-			end  = pfn_to_page(pfn2 - 1) + 1;
-
-			do {
-				total++;
-				if (PageReserved(page))
-					reserved++;
-				else if (PageSwapCache(page))
-					cached++;
-				else if (PageSlab(page))
-					slab++;
-				else if (!page_count(page))
-					free++;
-				else
-					shared += page_count(page) - 1;
-				page++;
-			} while (page < end);
-		}
+
+	for_each_bank (i, mi) {
+		struct membank *bank = &mi->bank[i];
+		unsigned int pfn1, pfn2;
+		struct page *page, *end;
+
+		pfn1 = bank_pfn_start(bank);
+		pfn2 = bank_pfn_end(bank);
+
+		page = pfn_to_page(pfn1);
+		end  = pfn_to_page(pfn2 - 1) + 1;
+
+		do {
+			total++;
+			if (PageReserved(page))
+				reserved++;
+			else if (PageSwapCache(page))
+				cached++;
+			else if (PageSlab(page))
+				slab++;
+			else if (!page_count(page))
+				free++;
+			else
+				shared += page_count(page) - 1;
+			page++;
+		} while (page < end);
 	}
 
 	printk("%d pages of RAM\n", total);
@@ -121,7 +121,7 @@ void show_mem(void)
 	printk("%d pages swap cached\n", cached);
 }
 
-static void __init find_node_limits(int node, struct meminfo *mi,
+static void __init find_limits(struct meminfo *mi,
 	unsigned long *min, unsigned long *max_low, unsigned long *max_high)
 {
 	int i;
@@ -129,7 +129,7 @@ static void __init find_node_limits(int node, struct meminfo *mi,
 	*min = -1UL;
 	*max_low = *max_high = 0;
 
-	for_each_nodebank(i, mi, node) {
+	for_each_bank (i, mi) {
 		struct membank *bank = &mi->bank[i];
 		unsigned long start, end;
 
@@ -147,155 +147,64 @@ static void __init find_node_limits(int node, struct meminfo *mi,
 	}
 }
 
-/*
- * FIXME: We really want to avoid allocating the bootmap bitmap
- * over the top of the initrd.  Hopefully, this is located towards
- * the start of a bank, so if we allocate the bootmap bitmap at
- * the end, we won't clash.
- */
-static unsigned int __init
-find_bootmap_pfn(int node, struct meminfo *mi, unsigned int bootmap_pages)
-{
-	unsigned int start_pfn, i, bootmap_pfn;
-
-	start_pfn   = PAGE_ALIGN(__pa(_end)) >> PAGE_SHIFT;
-	bootmap_pfn = 0;
-
-	for_each_nodebank(i, mi, node) {
-		struct membank *bank = &mi->bank[i];
-		unsigned int start, end;
-
-		start = bank_pfn_start(bank);
-		end   = bank_pfn_end(bank);
-
-		if (end < start_pfn)
-			continue;
-
-		if (start < start_pfn)
-			start = start_pfn;
-
-		if (end <= start)
-			continue;
-
-		if (end - start >= bootmap_pages) {
-			bootmap_pfn = start;
-			break;
-		}
-	}
-
-	if (bootmap_pfn == 0)
-		BUG();
-
-	return bootmap_pfn;
-}
-
-static int __init check_initrd(struct meminfo *mi)
-{
-	int initrd_node = -2;
-#ifdef CONFIG_BLK_DEV_INITRD
-	unsigned long end = phys_initrd_start + phys_initrd_size;
-
-	/*
-	 * Make sure that the initrd is within a valid area of
-	 * memory.
-	 */
-	if (phys_initrd_size) {
-		unsigned int i;
-
-		initrd_node = -1;
-
-		for (i = 0; i < mi->nr_banks; i++) {
-			struct membank *bank = &mi->bank[i];
-			if (bank_phys_start(bank) <= phys_initrd_start &&
-			    end <= bank_phys_end(bank))
-				initrd_node = bank->node;
-		}
-	}
-
-	if (initrd_node == -1) {
-		printk(KERN_ERR "INITRD: 0x%08lx+0x%08lx extends beyond "
-		       "physical memory - disabling initrd\n",
-		       phys_initrd_start, phys_initrd_size);
-		phys_initrd_start = phys_initrd_size = 0;
-	}
-#endif
-
-	return initrd_node;
-}
-
-static void __init bootmem_init_node(int node, struct meminfo *mi,
+static void __init arm_bootmem_init(struct meminfo *mi,
 	unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long boot_pfn;
 	unsigned int boot_pages;
+	phys_addr_t bitmap;
 	pg_data_t *pgdat;
 	int i;
 
 	/*
-	 * Allocate the bootmem bitmap page.
+	 * Allocate the bootmem bitmap page.  This must be in a region
+	 * of memory which has already been mapped.
 	 */
 	boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-	boot_pfn = find_bootmap_pfn(node, mi, boot_pages);
+	bitmap = memblock_alloc_base(boot_pages << PAGE_SHIFT, L1_CACHE_BYTES,
+				__pfn_to_phys(end_pfn));
 
 	/*
-	 * Initialise the bootmem allocator for this node, handing the
+	 * Initialise the bootmem allocator, handing the
 	 * memory banks over to bootmem.
 	 */
-	node_set_online(node);
-	pgdat = NODE_DATA(node);
-	init_bootmem_node(pgdat, boot_pfn, start_pfn, end_pfn);
+	node_set_online(0);
+	pgdat = NODE_DATA(0);
+	init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn);
 
-	for_each_nodebank(i, mi, node) {
+	for_each_bank(i, mi) {
 		struct membank *bank = &mi->bank[i];
 		if (!bank->highmem)
-			free_bootmem_node(pgdat, bank_phys_start(bank), bank_phys_size(bank));
+			free_bootmem(bank_phys_start(bank), bank_phys_size(bank));
 	}
 
 	/*
-	 * Reserve the bootmem bitmap for this node.
+	 * Reserve the memblock reserved regions in bootmem.
 	 */
-	reserve_bootmem_node(pgdat, boot_pfn << PAGE_SHIFT,
-			     boot_pages << PAGE_SHIFT, BOOTMEM_DEFAULT);
-}
-
-static void __init bootmem_reserve_initrd(int node)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-	pg_data_t *pgdat = NODE_DATA(node);
-	int res;
-
-	res = reserve_bootmem_node(pgdat, phys_initrd_start,
-			     phys_initrd_size, BOOTMEM_EXCLUSIVE);
-
-	if (res == 0) {
-		initrd_start = __phys_to_virt(phys_initrd_start);
-		initrd_end = initrd_start + phys_initrd_size;
-	} else {
-		printk(KERN_ERR
-			"INITRD: 0x%08lx+0x%08lx overlaps in-use "
-			"memory region - disabling initrd\n",
-			phys_initrd_start, phys_initrd_size);
+	for (i = 0; i < memblock.reserved.cnt; i++) {
+		phys_addr_t start = memblock_start_pfn(&memblock.reserved, i);
+		if (start >= start_pfn &&
+		    memblock_end_pfn(&memblock.reserved, i) <= end_pfn)
+			reserve_bootmem_node(pgdat, __pfn_to_phys(start),
+				memblock_size_bytes(&memblock.reserved, i),
+				BOOTMEM_DEFAULT);
 	}
-#endif
 }
 
-static void __init bootmem_free_node(int node, struct meminfo *mi)
+static void __init arm_bootmem_free(struct meminfo *mi, unsigned long min,
+	unsigned long max_low, unsigned long max_high)
 {
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long min, max_low, max_high;
 	int i;
 
-	find_node_limits(node, mi, &min, &max_low, &max_high);
-
 	/*
-	 * initialise the zones within this node.
+	 * initialise the zones.
 	 */
 	memset(zone_size, 0, sizeof(zone_size));
 
 	/*
-	 * The size of this node has already been determined.  If we need
-	 * to do anything fancy with the allocation of this memory to the
-	 * zones, now is the time to do it.
+	 * The memory size has already been determined.  If we need
+	 * to do anything fancy with the allocation of this memory
+	 * to the zones, now is the time to do it.
 	 */
 	zone_size[0] = max_low - min;
 #ifdef CONFIG_HIGHMEM
@@ -303,11 +212,11 @@ static void __init bootmem_free_node(int node, struct meminfo *mi)
 #endif
 
 	/*
-	 * For each bank in this node, calculate the size of the holes.
-	 *  holes = node_size - sum(bank_sizes_in_node)
+	 * Calculate the size of the holes.
+	 *  holes = node_size - sum(bank_sizes)
 	 */
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
-	for_each_nodebank(i, mi, node) {
+	for_each_bank(i, mi) {
 		int idx = 0;
 #ifdef CONFIG_HIGHMEM
 		if (mi->bank[i].highmem)
@@ -320,24 +229,23 @@ static void __init bootmem_free_node(int node, struct meminfo *mi)
 	 * Adjust the sizes according to any special requirements for
 	 * this machine type.
 	 */
-	arch_adjust_zones(node, zone_size, zhole_size);
+	arch_adjust_zones(zone_size, zhole_size);
 
-	free_area_init_node(node, zone_size, min, zhole_size);
+	free_area_init_node(0, zone_size, min, zhole_size);
 }
 
 #ifndef CONFIG_SPARSEMEM
 int pfn_valid(unsigned long pfn)
 {
-	struct meminfo *mi = &meminfo;
-	unsigned int left = 0, right = mi->nr_banks;
+	struct memblock_region *mem = &memblock.memory;
+	unsigned int left = 0, right = mem->cnt;
 
 	do {
 		unsigned int mid = (right + left) / 2;
-		struct membank *bank = &mi->bank[mid];
 
-		if (pfn < bank_pfn_start(bank))
+		if (pfn < memblock_start_pfn(mem, mid))
 			right = mid;
-		else if (pfn >= bank_pfn_end(bank))
+		else if (pfn >= memblock_end_pfn(mem, mid))
 			left = mid + 1;
 		else
 			return 1;
@@ -346,73 +254,69 @@ int pfn_valid(unsigned long pfn)
 }
 EXPORT_SYMBOL(pfn_valid);
 
-static void arm_memory_present(struct meminfo *mi, int node)
+static void arm_memory_present(void)
 {
 }
 #else
-static void arm_memory_present(struct meminfo *mi, int node)
+static void arm_memory_present(void)
 {
 	int i;
-	for_each_nodebank(i, mi, node) {
-		struct membank *bank = &mi->bank[i];
-		memory_present(node, bank_pfn_start(bank), bank_pfn_end(bank));
-	}
+	for (i = 0; i < memblock.memory.cnt; i++)
+		memory_present(0, memblock_start_pfn(&memblock.memory, i),
+				  memblock_end_pfn(&memblock.memory, i));
 }
 #endif
 
-void __init bootmem_init(void)
+void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 {
-	struct meminfo *mi = &meminfo;
-	unsigned long min, max_low, max_high;
-	int node, initrd_node;
+	int i;
 
-	/*
-	 * Locate which node contains the ramdisk image, if any.
-	 */
-	initrd_node = check_initrd(mi);
+	memblock_init();
+	for (i = 0; i < mi->nr_banks; i++)
+		memblock_add(mi->bank[i].start, mi->bank[i].size);
 
-	max_low = max_high = 0;
+	/* Register the kernel text, kernel data and initrd with memblock. */
+#ifdef CONFIG_XIP_KERNEL
+	memblock_reserve(__pa(_data), _end - _data);
+#else
+	memblock_reserve(__pa(_stext), _end - _stext);
+#endif
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (phys_initrd_size) {
+		memblock_reserve(phys_initrd_start, phys_initrd_size);
 
-	/*
-	 * Run through each node initialising the bootmem allocator.
-	 */
-	for_each_node(node) {
-		unsigned long node_low, node_high;
+		/* Now convert initrd to virtual addresses */
+		initrd_start = __phys_to_virt(phys_initrd_start);
+		initrd_end = initrd_start + phys_initrd_size;
+	}
+#endif
 
-		find_node_limits(node, mi, &min, &node_low, &node_high);
+	arm_mm_memblock_reserve();
 
-		if (node_low > max_low)
-			max_low = node_low;
-		if (node_high > max_high)
-			max_high = node_high;
+	/* reserve any platform specific memblock areas */
+	if (mdesc->reserve)
+		mdesc->reserve();
 
-		/*
-		 * If there is no memory in this node, ignore it.
-		 * (We can't have nodes which have no lowmem)
-		 */
-		if (node_low == 0)
-			continue;
+	memblock_analyze();
+	memblock_dump_all();
+}
 
-		bootmem_init_node(node, mi, min, node_low);
+void __init bootmem_init(void)
+{
+	struct meminfo *mi = &meminfo;
+	unsigned long min, max_low, max_high;
 
-		/*
-		 * Reserve any special node zero regions.
-		 */
-		if (node == 0)
-			reserve_node_zero(NODE_DATA(node));
+	max_low = max_high = 0;
 
-		/*
-		 * If the initrd is in this node, reserve its memory.
-		 */
-		if (node == initrd_node)
-			bootmem_reserve_initrd(node);
+	find_limits(mi, &min, &max_low, &max_high);
 
-		/*
-		 * Sparsemem tries to allocate bootmem in memory_present(),
-		 * so must be done after the fixed reservations
-		 */
-		arm_memory_present(mi, node);
-	}
+	arm_bootmem_init(mi, min, max_low);
+
+	/*
+	 * Sparsemem tries to allocate bootmem in memory_present(),
+	 * so must be done after the fixed reservations
+	 */
+	arm_memory_present();
 
 	/*
 	 * sparse_init() needs the bootmem allocator up and running.
@@ -420,12 +324,11 @@ void __init bootmem_init(void)
 	sparse_init();
 
 	/*
-	 * Now free memory in each node - free_area_init_node needs
+	 * Now free the memory - free_area_init_node needs
 	 * the sparse mem_map arrays initialized by sparse_init()
 	 * for memmap_init_zone(), otherwise all PFNs are invalid.
 	 */
-	for_each_node(node)
-		bootmem_free_node(node, mi);
+	arm_bootmem_free(mi, min, max_low, max_high);
 
 	high_memory = __va((max_low << PAGE_SHIFT) - 1) + 1;
 
@@ -460,7 +363,7 @@ static inline int free_area(unsigned long pfn, unsigned long end, char *s)
 }
 
 static inline void
-free_memmap(int node, unsigned long start_pfn, unsigned long end_pfn)
+free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct page *start_pg, *end_pg;
 	unsigned long pg, pgend;
@@ -483,40 +386,39 @@ free_memmap(int node, unsigned long start_pfn, unsigned long end_pfn)
 	 * free the section of the memmap array.
 	 */
 	if (pg < pgend)
-		free_bootmem_node(NODE_DATA(node), pg, pgend - pg);
+		free_bootmem(pg, pgend - pg);
 }
 
 /*
  * The mem_map array can get very big.  Free the unused area of the memory map.
  */
-static void __init free_unused_memmap_node(int node, struct meminfo *mi)
+static void __init free_unused_memmap(struct meminfo *mi)
 {
 	unsigned long bank_start, prev_bank_end = 0;
 	unsigned int i;
 
 	/*
-	 * [FIXME] This relies on each bank being in address order.  This
-	 * may not be the case, especially if the user has provided the
-	 * information on the command line.
+	 * This relies on each bank being in address order.
+	 * The banks are sorted previously in bootmem_init().
 	 */
-	for_each_nodebank(i, mi, node) {
+	for_each_bank(i, mi) {
 		struct membank *bank = &mi->bank[i];
 
 		bank_start = bank_pfn_start(bank);
-		if (bank_start < prev_bank_end) {
-			printk(KERN_ERR "MEM: unordered memory banks.  "
-				"Not freeing memmap.\n");
-			break;
-		}
 
 		/*
 		 * If we had a previous bank, and there is a space
 		 * between the current bank and the previous, free it.
 		 */
-		if (prev_bank_end && prev_bank_end != bank_start)
-			free_memmap(node, prev_bank_end, bank_start);
+		if (prev_bank_end && prev_bank_end < bank_start)
+			free_memmap(prev_bank_end, bank_start);
 
-		prev_bank_end = bank_pfn_end(bank);
+		/*
+		 * Align up here since the VM subsystem insists that the
+		 * memmap entries are valid from the bank end aligned to
+		 * MAX_ORDER_NR_PAGES.
+		 */
+		prev_bank_end = ALIGN(bank_pfn_end(bank), MAX_ORDER_NR_PAGES);
 	}
 }
 
@@ -528,21 +430,19 @@ static void __init free_unused_memmap_node(int node, struct meminfo *mi)
 void __init mem_init(void)
 {
 	unsigned long reserved_pages, free_pages;
-	int i, node;
+	int i;
+#ifdef CONFIG_HAVE_TCM
+	/* These pointers are filled in on TCM detection */
+	extern u32 dtcm_end;
+	extern u32 itcm_end;
+#endif
 
-#ifndef CONFIG_DISCONTIGMEM
 	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
-#endif
 
 	/* this will put all unused low memory onto the freelists */
-	for_each_online_node(node) {
-		pg_data_t *pgdat = NODE_DATA(node);
+	free_unused_memmap(&meminfo);
 
-		free_unused_memmap_node(node, &meminfo);
-
-		if (pgdat->node_spanned_pages != 0)
-			totalram_pages += free_all_bootmem_node(pgdat);
-	}
+	totalram_pages += free_all_bootmem();
 
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
@@ -552,39 +452,35 @@ void __init mem_init(void)
 
 #ifdef CONFIG_HIGHMEM
 	/* set highmem page free */
-	for_each_online_node(node) {
-		for_each_nodebank (i, &meminfo, node) {
-			unsigned long start = bank_pfn_start(&meminfo.bank[i]);
-			unsigned long end = bank_pfn_end(&meminfo.bank[i]);
-			if (start >= max_low_pfn + PHYS_PFN_OFFSET)
-				totalhigh_pages += free_area(start, end, NULL);
-		}
+	for_each_bank (i, &meminfo) {
+		unsigned long start = bank_pfn_start(&meminfo.bank[i]);
+		unsigned long end = bank_pfn_end(&meminfo.bank[i]);
+		if (start >= max_low_pfn + PHYS_PFN_OFFSET)
+			totalhigh_pages += free_area(start, end, NULL);
 	}
 	totalram_pages += totalhigh_pages;
 #endif
 
 	reserved_pages = free_pages = 0;
 
-	for_each_online_node(node) {
-		for_each_nodebank(i, &meminfo, node) {
-			struct membank *bank = &meminfo.bank[i];
-			unsigned int pfn1, pfn2;
-			struct page *page, *end;
-
-			pfn1 = bank_pfn_start(bank);
-			pfn2 = bank_pfn_end(bank);
-
-			page = pfn_to_page(pfn1);
-			end  = pfn_to_page(pfn2 - 1) + 1;
-
-			do {
-				if (PageReserved(page))
-					reserved_pages++;
-				else if (!page_count(page))
-					free_pages++;
-				page++;
-			} while (page < end);
-		}
+	for_each_bank(i, &meminfo) {
+		struct membank *bank = &meminfo.bank[i];
+		unsigned int pfn1, pfn2;
+		struct page *page, *end;
+
+		pfn1 = bank_pfn_start(bank);
+		pfn2 = bank_pfn_end(bank);
+
+		page = pfn_to_page(pfn1);
+		end  = pfn_to_page(pfn2 - 1) + 1;
+
+		do {
+			if (PageReserved(page))
+				reserved_pages++;
+			else if (!page_count(page))
+				free_pages++;
+			page++;
+		} while (page < end);
 	}
 
 	/*
@@ -611,6 +507,10 @@ void __init mem_init(void)
 
 	printk(KERN_NOTICE "Virtual kernel memory layout:\n"
 			"    vector  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+#ifdef CONFIG_HAVE_TCM
+			"    DTCM    : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+			"    ITCM    : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+#endif
 			"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
 #ifdef CONFIG_MMU
 			"    DMA     : 0x%08lx - 0x%08lx   (%4ld MB)\n"
@@ -627,6 +527,10 @@ void __init mem_init(void)
 
 			MLK(UL(CONFIG_VECTORS_BASE), UL(CONFIG_VECTORS_BASE) +
 				(PAGE_SIZE)),
+#ifdef CONFIG_HAVE_TCM
+			MLK(DTCM_OFFSET, (unsigned long) dtcm_end),
+			MLK(ITCM_OFFSET, (unsigned long) itcm_end),
+#endif
 			MLK(FIXADDR_START, FIXADDR_TOP),
 #ifdef CONFIG_MMU
 			MLM(CONSISTENT_BASE, CONSISTENT_END),
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 28c8b950ef0..ab506272b2d 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -42,78 +42,11 @@
  */
 #define VM_ARM_SECTION_MAPPING	0x80000000
 
-static int remap_area_pte(pmd_t *pmd, unsigned long addr, unsigned long end,
-			  unsigned long phys_addr, const struct mem_type *type)
-{
-	pgprot_t prot = __pgprot(type->prot_pte);
-	pte_t *pte;
-
-	pte = pte_alloc_kernel(pmd, addr);
-	if (!pte)
-		return -ENOMEM;
-
-	do {
-		if (!pte_none(*pte))
-			goto bad;
-
-		set_pte_ext(pte, pfn_pte(phys_addr >> PAGE_SHIFT, prot), 0);
-		phys_addr += PAGE_SIZE;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	return 0;
-
- bad:
-	printk(KERN_CRIT "remap_area_pte: page already exists\n");
-	BUG();
-}
-
-static inline int remap_area_pmd(pgd_t *pgd, unsigned long addr,
-				 unsigned long end, unsigned long phys_addr,
-				 const struct mem_type *type)
-{
-	unsigned long next;
-	pmd_t *pmd;
-	int ret = 0;
-
-	pmd = pmd_alloc(&init_mm, pgd, addr);
-	if (!pmd)
-		return -ENOMEM;
-
-	do {
-		next = pmd_addr_end(addr, end);
-		ret = remap_area_pte(pmd, addr, next, phys_addr, type);
-		if (ret)
-			return ret;
-		phys_addr += next - addr;
-	} while (pmd++, addr = next, addr != end);
-	return ret;
-}
-
-static int remap_area_pages(unsigned long start, unsigned long pfn,
-			    size_t size, const struct mem_type *type)
-{
-	unsigned long addr = start;
-	unsigned long next, end = start + size;
-	unsigned long phys_addr = __pfn_to_phys(pfn);
-	pgd_t *pgd;
-	int err = 0;
-
-	BUG_ON(addr >= end);
-	pgd = pgd_offset_k(addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		err = remap_area_pmd(pgd, addr, next, phys_addr, type);
-		if (err)
-			break;
-		phys_addr += next - addr;
-	} while (pgd++, addr = next, addr != end);
-
-	return err;
-}
-
 int ioremap_page(unsigned long virt, unsigned long phys,
 		 const struct mem_type *mtype)
 {
-	return remap_area_pages(virt, __phys_to_pfn(phys), PAGE_SIZE, mtype);
+	return ioremap_page_range(virt, virt + PAGE_SIZE, phys,
+				  __pgprot(mtype->prot_pte));
 }
 EXPORT_SYMBOL(ioremap_page);
 
@@ -268,6 +201,12 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
 		return NULL;
 
+	/*
+	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
+	 */
+	if (WARN_ON(pfn_valid(pfn)))
+		return NULL;
+
 	type = get_mem_type(mtype);
 	if (!type)
 		return NULL;
@@ -294,7 +233,8 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 		err = remap_area_sections(addr, pfn, size, type);
 	} else
 #endif
-		err = remap_area_pages(addr, pfn, size, type);
+		err = ioremap_page_range(addr, addr + size, __pfn_to_phys(pfn),
+					 __pgprot(type->prot_pte));
 
 	if (err) {
  		vunmap((void *)addr);
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 815d08eecbb..6630620380a 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -28,7 +28,5 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 
 #endif
 
-struct pglist_data;
-
 void __init bootmem_init(void);
-void reserve_node_zero(struct pglist_data *pgdat);
+void arm_mm_memblock_reserve(void);
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index f5abc51c5a0..4f5b39687df 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -7,6 +7,7 @@
 #include <linux/shm.h>
 #include <linux/sched.h>
 #include <linux/io.h>
+#include <linux/random.h>
 #include <asm/cputype.h>
 #include <asm/system.h>
 
@@ -80,6 +81,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	        start_addr = addr = TASK_UNMAPPED_BASE;
 	        mm->cached_hole_size = 0;
 	}
+	/* 8 bits of randomness in 20 address space bits */
+	if (current->flags & PF_RANDOMIZE)
+		addr += (get_random_int() % (1 << 8)) << PAGE_SHIFT;
 
 full_search:
 	if (do_align)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 28589417118..6e1c4f6a2b3 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -11,13 +11,12 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
+#include <linux/memblock.h>
 #include <linux/sort.h>
 
 #include <asm/cputype.h>
-#include <asm/mach-types.h>
 #include <asm/sections.h>
 #include <asm/cachetype.h>
 #include <asm/setup.h>
@@ -258,6 +257,19 @@ static struct mem_type mem_types[] = {
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
+	[MT_MEMORY_DTCM] = {
+		.prot_pte	= L_PTE_PRESENT | L_PTE_YOUNG |
+		                  L_PTE_DIRTY | L_PTE_WRITE,
+		.prot_l1	= PMD_TYPE_TABLE,
+		.prot_sect	= PMD_TYPE_SECT | PMD_SECT_XN,
+		.domain		= DOMAIN_KERNEL,
+	},
+	[MT_MEMORY_ITCM] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_USER | L_PTE_EXEC,
+		.prot_l1   = PMD_TYPE_TABLE,
+		.domain    = DOMAIN_IO,
+	},
 };
 
 const struct mem_type *get_mem_type(unsigned int type)
@@ -488,18 +500,28 @@ static void __init build_mem_type_table(void)
 
 #define vectors_base()	(vectors_high() ? 0xffff0000 : 0)
 
-static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
-				  unsigned long end, unsigned long pfn,
-				  const struct mem_type *type)
+static void __init *early_alloc(unsigned long sz)
 {
-	pte_t *pte;
+	void *ptr = __va(memblock_alloc(sz, sz));
+	memset(ptr, 0, sz);
+	return ptr;
+}
 
+static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot)
+{
 	if (pmd_none(*pmd)) {
-		pte = alloc_bootmem_low_pages(2 * PTRS_PER_PTE * sizeof(pte_t));
-		__pmd_populate(pmd, __pa(pte) | type->prot_l1);
+		pte_t *pte = early_alloc(2 * PTRS_PER_PTE * sizeof(pte_t));
+		__pmd_populate(pmd, __pa(pte) | prot);
 	}
+	BUG_ON(pmd_bad(*pmd));
+	return pte_offset_kernel(pmd, addr);
+}
 
-	pte = pte_offset_kernel(pmd, addr);
+static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
+				  unsigned long end, unsigned long pfn,
+				  const struct mem_type *type)
+{
+	pte_t *pte = early_pte_alloc(pmd, addr, type->prot_l1);
 	do {
 		set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)), 0);
 		pfn++;
@@ -668,7 +690,7 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 		create_mapping(io_desc + i);
 }
 
-static unsigned long __initdata vmalloc_reserve = SZ_128M;
+static void * __initdata vmalloc_min = (void *)(VMALLOC_END - SZ_128M);
 
 /*
  * vmalloc=size forces the vmalloc area to be exactly 'size'
@@ -677,7 +699,7 @@ static unsigned long __initdata vmalloc_reserve = SZ_128M;
  */
 static int __init early_vmalloc(char *arg)
 {
-	vmalloc_reserve = memparse(arg, NULL);
+	unsigned long vmalloc_reserve = memparse(arg, NULL);
 
 	if (vmalloc_reserve < SZ_16M) {
 		vmalloc_reserve = SZ_16M;
@@ -692,22 +714,26 @@ static int __init early_vmalloc(char *arg)
 			"vmalloc area is too big, limiting to %luMB\n",
 			vmalloc_reserve >> 20);
 	}
+
+	vmalloc_min = (void *)(VMALLOC_END - vmalloc_reserve);
 	return 0;
 }
 early_param("vmalloc", early_vmalloc);
 
-#define VMALLOC_MIN	(void *)(VMALLOC_END - vmalloc_reserve)
+phys_addr_t lowmem_end_addr;
 
 static void __init sanity_check_meminfo(void)
 {
 	int i, j, highmem = 0;
 
+	lowmem_end_addr = __pa(vmalloc_min - 1) + 1;
+
 	for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
 		struct membank *bank = &meminfo.bank[j];
 		*bank = meminfo.bank[i];
 
 #ifdef CONFIG_HIGHMEM
-		if (__va(bank->start) > VMALLOC_MIN ||
+		if (__va(bank->start) > vmalloc_min ||
 		    __va(bank->start) < (void *)PAGE_OFFSET)
 			highmem = 1;
 
@@ -717,8 +743,8 @@ static void __init sanity_check_meminfo(void)
 		 * Split those memory banks which are partially overlapping
 		 * the vmalloc area greatly simplifying things later.
 		 */
-		if (__va(bank->start) < VMALLOC_MIN &&
-		    bank->size > VMALLOC_MIN - __va(bank->start)) {
+		if (__va(bank->start) < vmalloc_min &&
+		    bank->size > vmalloc_min - __va(bank->start)) {
 			if (meminfo.nr_banks >= NR_BANKS) {
 				printk(KERN_CRIT "NR_BANKS too low, "
 						 "ignoring high memory\n");
@@ -727,12 +753,12 @@ static void __init sanity_check_meminfo(void)
 					(meminfo.nr_banks - i) * sizeof(*bank));
 				meminfo.nr_banks++;
 				i++;
-				bank[1].size -= VMALLOC_MIN - __va(bank->start);
-				bank[1].start = __pa(VMALLOC_MIN - 1) + 1;
+				bank[1].size -= vmalloc_min - __va(bank->start);
+				bank[1].start = __pa(vmalloc_min - 1) + 1;
 				bank[1].highmem = highmem = 1;
 				j++;
 			}
-			bank->size = VMALLOC_MIN - __va(bank->start);
+			bank->size = vmalloc_min - __va(bank->start);
 		}
 #else
 		bank->highmem = highmem;
@@ -741,7 +767,7 @@ static void __init sanity_check_meminfo(void)
 		 * Check whether this memory bank would entirely overlap
 		 * the vmalloc area.
 		 */
-		if (__va(bank->start) >= VMALLOC_MIN ||
+		if (__va(bank->start) >= vmalloc_min ||
 		    __va(bank->start) < (void *)PAGE_OFFSET) {
 			printk(KERN_NOTICE "Ignoring RAM at %.8lx-%.8lx "
 			       "(vmalloc region overlap).\n",
@@ -753,9 +779,9 @@ static void __init sanity_check_meminfo(void)
 		 * Check whether this memory bank would partially overlap
 		 * the vmalloc area.
 		 */
-		if (__va(bank->start + bank->size) > VMALLOC_MIN ||
+		if (__va(bank->start + bank->size) > vmalloc_min ||
 		    __va(bank->start + bank->size) < __va(bank->start)) {
-			unsigned long newsize = VMALLOC_MIN - __va(bank->start);
+			unsigned long newsize = vmalloc_min - __va(bank->start);
 			printk(KERN_NOTICE "Truncating RAM at %.8lx-%.8lx "
 			       "to -%.8lx (vmalloc region overlap).\n",
 			       bank->start, bank->start + bank->size - 1,
@@ -827,101 +853,23 @@ static inline void prepare_page_table(void)
 }
 
 /*
- * Reserve the various regions of node 0
+ * Reserve the special regions of memory
  */
-void __init reserve_node_zero(pg_data_t *pgdat)
+void __init arm_mm_memblock_reserve(void)
 {
-	unsigned long res_size = 0;
-
-	/*
-	 * Register the kernel text and data with bootmem.
-	 * Note that this can only be in node 0.
-	 */
-#ifdef CONFIG_XIP_KERNEL
-	reserve_bootmem_node(pgdat, __pa(_data), _end - _data,
-			BOOTMEM_DEFAULT);
-#else
-	reserve_bootmem_node(pgdat, __pa(_stext), _end - _stext,
-			BOOTMEM_DEFAULT);
-#endif
-
 	/*
 	 * Reserve the page tables.  These are already in use,
 	 * and can only be in node 0.
 	 */
-	reserve_bootmem_node(pgdat, __pa(swapper_pg_dir),
-			     PTRS_PER_PGD * sizeof(pgd_t), BOOTMEM_DEFAULT);
-
-	/*
-	 * Hmm... This should go elsewhere, but we really really need to
-	 * stop things allocating the low memory; ideally we need a better
-	 * implementation of GFP_DMA which does not assume that DMA-able
-	 * memory starts at zero.
-	 */
-	if (machine_is_integrator() || machine_is_cintegrator())
-		res_size = __pa(swapper_pg_dir) - PHYS_OFFSET;
-
-	/*
-	 * These should likewise go elsewhere.  They pre-reserve the
-	 * screen memory region at the start of main system memory.
-	 */
-	if (machine_is_edb7211())
-		res_size = 0x00020000;
-	if (machine_is_p720t())
-		res_size = 0x00014000;
-
-	/* H1940, RX3715 and RX1950 need to reserve this for suspend */
-
-	if (machine_is_h1940() || machine_is_rx3715()
-		|| machine_is_rx1950()) {
-		reserve_bootmem_node(pgdat, 0x30003000, 0x1000,
-				BOOTMEM_DEFAULT);
-		reserve_bootmem_node(pgdat, 0x30081000, 0x1000,
-				BOOTMEM_DEFAULT);
-	}
-
-	if (machine_is_palmld() || machine_is_palmtx()) {
-		reserve_bootmem_node(pgdat, 0xa0000000, 0x1000,
-				BOOTMEM_EXCLUSIVE);
-		reserve_bootmem_node(pgdat, 0xa0200000, 0x1000,
-				BOOTMEM_EXCLUSIVE);
-	}
-
-	if (machine_is_treo680() || machine_is_centro()) {
-		reserve_bootmem_node(pgdat, 0xa0000000, 0x1000,
-				BOOTMEM_EXCLUSIVE);
-		reserve_bootmem_node(pgdat, 0xa2000000, 0x1000,
-				BOOTMEM_EXCLUSIVE);
-	}
-
-	if (machine_is_palmt5())
-		reserve_bootmem_node(pgdat, 0xa0200000, 0x1000,
-				BOOTMEM_EXCLUSIVE);
-
-	/*
-	 * U300 - This platform family can share physical memory
-	 * between two ARM cpus, one running Linux and the other
-	 * running another OS.
-	 */
-	if (machine_is_u300()) {
-#ifdef CONFIG_MACH_U300_SINGLE_RAM
-#if ((CONFIG_MACH_U300_ACCESS_MEM_SIZE & 1) == 1) &&	\
-	CONFIG_MACH_U300_2MB_ALIGNMENT_FIX
-		res_size = 0x00100000;
-#endif
-#endif
-	}
+	memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
 
 #ifdef CONFIG_SA1111
 	/*
 	 * Because of the SA1111 DMA bug, we want to preserve our
 	 * precious DMA-able memory...
 	 */
-	res_size = __pa(swapper_pg_dir) - PHYS_OFFSET;
+	memblock_reserve(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET);
 #endif
-	if (res_size)
-		reserve_bootmem_node(pgdat, PHYS_OFFSET, res_size,
-				BOOTMEM_DEFAULT);
 }
 
 /*
@@ -940,7 +888,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors = alloc_bootmem_low_pages(PAGE_SIZE);
+	vectors = early_alloc(PAGE_SIZE);
 
 	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -1011,11 +959,8 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 static void __init kmap_init(void)
 {
 #ifdef CONFIG_HIGHMEM
-	pmd_t *pmd = pmd_off_k(PKMAP_BASE);
-	pte_t *pte = alloc_bootmem_low_pages(2 * PTRS_PER_PTE * sizeof(pte_t));
-	BUG_ON(!pmd_none(*pmd) || !pte);
-	__pmd_populate(pmd, __pa(pte) | _PAGE_KERNEL_TABLE);
-	pkmap_page_table = pte + PTRS_PER_PTE;
+	pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE),
+		PKMAP_BASE, _PAGE_KERNEL_TABLE);
 #endif
 }
 
@@ -1066,17 +1011,16 @@ void __init paging_init(struct machine_desc *mdesc)
 	sanity_check_meminfo();
 	prepare_page_table();
 	map_lowmem();
-	bootmem_init();
 	devicemaps_init(mdesc);
 	kmap_init();
 
 	top_pmd = pmd_off_k(0xffff0000);
 
-	/*
-	 * allocate the zero page.  Note that this always succeeds and
-	 * returns a zeroed result.
-	 */
-	zero_page = alloc_bootmem_low_pages(PAGE_SIZE);
+	/* allocate the zero page. */
+	zero_page = early_alloc(PAGE_SIZE);
+
+	bootmem_init();
+
 	empty_zero_page = virt_to_page(zero_page);
 	__flush_dcache_page(NULL, empty_zero_page);
 }
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 33b327379f0..687d02319a4 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -6,8 +6,8 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
-#include <linux/bootmem.h>
 #include <linux/io.h>
+#include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -17,30 +17,14 @@
 
 #include "mm.h"
 
-/*
- * Reserve the various regions of node 0
- */
-void __init reserve_node_zero(pg_data_t *pgdat)
+void __init arm_mm_memblock_reserve(void)
 {
 	/*
-	 * Register the kernel text and data with bootmem.
-	 * Note that this can only be in node 0.
-	 */
-#ifdef CONFIG_XIP_KERNEL
-	reserve_bootmem_node(pgdat, __pa(_data), _end - _data,
-			BOOTMEM_DEFAULT);
-#else
-	reserve_bootmem_node(pgdat, __pa(_stext), _end - _stext,
-			BOOTMEM_DEFAULT);
-#endif
-
-	/*
 	 * Register the exception vector page.
 	 * some architectures which the DRAM is the exception vector to trap,
 	 * alloc_page breaks with error, although it is not NULL, but "0."
 	 */
-	reserve_bootmem_node(pgdat, CONFIG_VECTORS_BASE, PAGE_SIZE,
-			BOOTMEM_DEFAULT);
+	memblock_reserve(CONFIG_VECTORS_BASE, PAGE_SIZE);
 }
 
 /*
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 72507c630ce..203a4e944d9 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -79,15 +79,11 @@ ENTRY(cpu_arm1020_proc_init)
  * cpu_arm1020_proc_fin()
  */
 ENTRY(cpu_arm1020_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm1020_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000 		@ ...i............
 	bic	r0, r0, #0x000e 		@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm1020_reset(loc)
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index d2782980560..1a511e76590 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -79,15 +79,11 @@ ENTRY(cpu_arm1020e_proc_init)
  * cpu_arm1020e_proc_fin()
  */
 ENTRY(cpu_arm1020e_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm1020e_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000 		@ ...i............
 	bic	r0, r0, #0x000e 		@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm1020e_reset(loc)
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index ce13e4a827d..1ffa4eb9c34 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -68,15 +68,11 @@ ENTRY(cpu_arm1022_proc_init)
  * cpu_arm1022_proc_fin()
  */
 ENTRY(cpu_arm1022_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm1022_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000 		@ ...i............
 	bic	r0, r0, #0x000e 		@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm1022_reset(loc)
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index 636672a29c6..5697c34b95b 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -68,15 +68,11 @@ ENTRY(cpu_arm1026_proc_init)
  * cpu_arm1026_proc_fin()
  */
 ENTRY(cpu_arm1026_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm1026_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000 		@ ...i............
 	bic	r0, r0, #0x000e 		@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm1026_reset(loc)
diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S
index 795dc615f43..64e0b327c7c 100644
--- a/arch/arm/mm/proc-arm6_7.S
+++ b/arch/arm/mm/proc-arm6_7.S
@@ -184,8 +184,6 @@ ENTRY(cpu_arm7_proc_init)
 
 ENTRY(cpu_arm6_proc_fin)
 ENTRY(cpu_arm7_proc_fin)
-		mov	r0, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-		msr	cpsr_c, r0
 		mov	r0, #0x31			@ ....S..DP...M
 		mcr	p15, 0, r0, c1, c0, 0		@ disable caches
 		mov	pc, lr
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index 0b62de24466..9d96824134f 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -54,15 +54,11 @@ ENTRY(cpu_arm720_proc_init)
 		mov	pc, lr
 
 ENTRY(cpu_arm720_proc_fin)
-		stmfd	sp!, {lr}
-		mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-		msr	cpsr_c, ip
 		mrc	p15, 0, r0, c1, c0, 0
 		bic	r0, r0, #0x1000			@ ...i............
 		bic	r0, r0, #0x000e			@ ............wca.
 		mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-		mcr	p15, 0, r1, c7, c7, 0		@ invalidate cache
-		ldmfd	sp!, {pc}
+		mov	pc, lr
 
 /*
  * Function: arm720_proc_do_idle(void)
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index 01860cdeb2e..6c1a9ab059a 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -36,15 +36,11 @@ ENTRY(cpu_arm740_switch_mm)
  * cpu_arm740_proc_fin()
  */
 ENTRY(cpu_arm740_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
 	mrc	p15, 0, r0, c1, c0, 0
 	bic	r0, r0, #0x3f000000		@ bank/f/lock/s
 	bic	r0, r0, #0x0000000c		@ w-buffer/cache
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	mcr	p15, 0, r0, c7, c0, 0		@ invalidate cache
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm740_reset(loc)
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index 1201b986382..6a850dbba22 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -36,8 +36,6 @@ ENTRY(cpu_arm7tdmi_switch_mm)
  * cpu_arm7tdmi_proc_fin()
  */
 ENTRY(cpu_arm7tdmi_proc_fin)
-		mov	r0, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-		msr	cpsr_c, r0
 		mov	pc, lr
 
 /*
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 8be81992645..86f80aa5621 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -69,19 +69,11 @@ ENTRY(cpu_arm920_proc_init)
  * cpu_arm920_proc_fin()
  */
 ENTRY(cpu_arm920_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
-	bl	arm920_flush_kern_cache_all
-#else
-	bl	v4wt_flush_kern_cache_all
-#endif
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm920_reset(loc)
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index c0ff8e4b107..f76ce9b6288 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -71,19 +71,11 @@ ENTRY(cpu_arm922_proc_init)
  * cpu_arm922_proc_fin()
  */
 ENTRY(cpu_arm922_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
-	bl	arm922_flush_kern_cache_all
-#else
-	bl	v4wt_flush_kern_cache_all
-#endif
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm922_reset(loc)
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index 3c6cffe400f..657bd3f7c15 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -92,15 +92,11 @@ ENTRY(cpu_arm925_proc_init)
  * cpu_arm925_proc_fin()
  */
 ENTRY(cpu_arm925_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm925_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm925_reset(loc)
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 75b707c9cce..73f1f3c6891 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -61,15 +61,11 @@ ENTRY(cpu_arm926_proc_init)
  * cpu_arm926_proc_fin()
  */
 ENTRY(cpu_arm926_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm926_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm926_reset(loc)
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index 1af1657819e..fffb061a45a 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -37,15 +37,11 @@ ENTRY(cpu_arm940_switch_mm)
  * cpu_arm940_proc_fin()
  */
 ENTRY(cpu_arm940_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm940_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x00001000		@ i-cache
 	bic	r0, r0, #0x00000004		@ d-cache
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm940_reset(loc)
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 1664b6aaff7..249a6053760 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -44,15 +44,11 @@ ENTRY(cpu_arm946_switch_mm)
  * cpu_arm946_proc_fin()
  */
 ENTRY(cpu_arm946_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm946_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x00001000		@ i-cache
 	bic	r0, r0, #0x00000004		@ d-cache
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm946_reset(loc)
diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S
index 28545c29dbc..db475667fac 100644
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -36,8 +36,6 @@ ENTRY(cpu_arm9tdmi_switch_mm)
  * cpu_arm9tdmi_proc_fin()
  */
 ENTRY(cpu_arm9tdmi_proc_fin)
-		mov	r0, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-		msr	cpsr_c, r0
 		mov	pc, lr
 
 /*
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index 08f5ac237ad..7803fdf7002 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -39,17 +39,13 @@ ENTRY(cpu_fa526_proc_init)
  * cpu_fa526_proc_fin()
  */
 ENTRY(cpu_fa526_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	fa_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
 	nop
 	nop
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_fa526_reset(loc)
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index 53e63234384..b304d0104a4 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -75,11 +75,6 @@ ENTRY(cpu_feroceon_proc_init)
  * cpu_feroceon_proc_fin()
  */
 ENTRY(cpu_feroceon_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	feroceon_flush_kern_cache_all
-
 #if defined(CONFIG_CACHE_FEROCEON_L2) && \
 	!defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH)
 	mov	r0, #0
@@ -91,7 +86,7 @@ ENTRY(cpu_feroceon_proc_fin)
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_feroceon_reset(loc)
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index caa31154e7d..5f6892fcc16 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -51,15 +51,11 @@ ENTRY(cpu_mohawk_proc_init)
  * cpu_mohawk_proc_fin()
  */
 ENTRY(cpu_mohawk_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	mohawk_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1800			@ ...iz...........
 	bic	r0, r0, #0x0006			@ .............ca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_mohawk_reset(loc)
diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S
index 7b706b38990..a201eb04b5e 100644
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -44,17 +44,13 @@ ENTRY(cpu_sa110_proc_init)
  * cpu_sa110_proc_fin()
  */
 ENTRY(cpu_sa110_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	v4wb_flush_kern_cache_all	@ clean caches
-1:	mov	r0, #0
+	mov	r0, #0
 	mcr	p15, 0, r0, c15, c2, 2		@ Disable clock switching
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_sa110_reset(loc)
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 5c47760c206..7ddc4805bf9 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -55,16 +55,12 @@ ENTRY(cpu_sa1100_proc_init)
  *  - Clean and turn off caches.
  */
 ENTRY(cpu_sa1100_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	v4wb_flush_kern_cache_all
 	mcr	p15, 0, ip, c15, c2, 2		@ Disable clock switching
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x000e			@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_sa1100_reset(loc)
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 7a5337ed7d6..22aac851519 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -42,14 +42,11 @@ ENTRY(cpu_v6_proc_init)
 	mov	pc, lr
 
 ENTRY(cpu_v6_proc_fin)
-	stmfd	sp!, {lr}
-	cpsid	if				@ disable interrupts
-	bl	v6_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x0006			@ .............ca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  *	cpu_v6_reset(loc)
@@ -239,7 +236,8 @@ __v6_proc_info:
 	b	__v6_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
-	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_JAVA
+	/* See also feat_v6_fixup() for HWCAP_TLS */
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_JAVA|HWCAP_TLS
 	.long	cpu_v6_name
 	.long	v6_processor_functions
 	.long	v6wbi_tlb_fns
@@ -262,7 +260,7 @@ __pj4_v6_proc_info:
 	b	__v6_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
-	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
 	.long	cpu_pj4_name
 	.long	v6_processor_functions
 	.long	v6wbi_tlb_fns
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 7aaf88a3b7a..6a8506d99ee 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -45,14 +45,11 @@ ENTRY(cpu_v7_proc_init)
 ENDPROC(cpu_v7_proc_init)
 
 ENTRY(cpu_v7_proc_fin)
-	stmfd	sp!, {lr}
-	cpsid	if				@ disable interrupts
-	bl	v7_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000			@ ...i............
 	bic	r0, r0, #0x0006			@ .............ca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 ENDPROC(cpu_v7_proc_fin)
 
 /*
@@ -344,7 +341,7 @@ __v7_proc_info:
 	b	__v7_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
-	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
 	.long	cpu_v7_name
 	.long	v7_processor_functions
 	.long	v7wbi_tlb_fns
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index e5797f1c1db..361a51e4903 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -90,15 +90,11 @@ ENTRY(cpu_xsc3_proc_init)
  * cpu_xsc3_proc_fin()
  */
 ENTRY(cpu_xsc3_proc_fin)
-	str	lr, [sp, #-4]!
-	mov	r0, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
-	msr	cpsr_c, r0
-	bl	xsc3_flush_kern_cache_all	@ clean caches
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1800			@ ...IZ...........
 	bic	r0, r0, #0x0006			@ .............CA.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldr	pc, [sp], #4
+	mov	pc, lr
 
 /*
  * cpu_xsc3_reset(loc)
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 63037e2162f..14075979bcb 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -124,15 +124,11 @@ ENTRY(cpu_xscale_proc_init)
  * cpu_xscale_proc_fin()
  */
 ENTRY(cpu_xscale_proc_fin)
-	str	lr, [sp, #-4]!
-	mov	r0, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
-	msr	cpsr_c, r0
-	bl	xscale_flush_kern_cache_all	@ clean caches
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1800			@ ...IZ...........
 	bic	r0, r0, #0x0006			@ .............CA.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldr	pc, [sp], #4
+	mov	pc, lr
 
 /*
  * cpu_xscale_reset(loc)
diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c
index 19e09bdb1b8..935993e1b1e 100644
--- a/arch/arm/mm/vmregion.c
+++ b/arch/arm/mm/vmregion.c
@@ -35,7 +35,8 @@
  */
 
 struct arm_vmregion *
-arm_vmregion_alloc(struct arm_vmregion_head *head, size_t size, gfp_t gfp)
+arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
+		   size_t size, gfp_t gfp)
 {
 	unsigned long addr = head->vm_start, end = head->vm_end - size;
 	unsigned long flags;
@@ -58,7 +59,7 @@ arm_vmregion_alloc(struct arm_vmregion_head *head, size_t size, gfp_t gfp)
 			goto nospc;
 		if ((addr + size) <= c->vm_start)
 			goto found;
-		addr = c->vm_end;
+		addr = ALIGN(c->vm_end, align);
 		if (addr > end)
 			goto nospc;
 	}
diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h
index 6b2cdbdf3a8..15e9f044db9 100644
--- a/arch/arm/mm/vmregion.h
+++ b/arch/arm/mm/vmregion.h
@@ -21,7 +21,7 @@ struct arm_vmregion {
 	int			vm_active;
 };
 
-struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, gfp_t);
+struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t);
 struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *, unsigned long);
 struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *, unsigned long);
 void arm_vmregion_free(struct arm_vmregion_head *, struct arm_vmregion *);