25 files changed, 184 insertions, 297 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index cce78b070825..9e8101ecd63e 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -43,7 +43,7 @@ config CPU_ARM740T
 	depends on !MMU
 	select CPU_32v4T
 	select CPU_ABRT_LV4T
-	select CPU_CACHE_V3	# although the core is v4t
+	select CPU_CACHE_V4
 	select CPU_CP15_MPU
 	select CPU_PABRT_LEGACY
 	help
@@ -488,9 +488,6 @@ config CPU_PABRT_V7
 	bool
 
 # The cache model
-config CPU_CACHE_V3
-	bool
-
 config CPU_CACHE_V4
 	bool
 
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 317b57559340..ee558a01f390 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY)	+= pabort-legacy.o
 obj-$(CONFIG_CPU_PABRT_V6)	+= pabort-v6.o
 obj-$(CONFIG_CPU_PABRT_V7)	+= pabort-v7.o
 
-obj-$(CONFIG_CPU_CACHE_V3)	+= cache-v3.o
 obj-$(CONFIG_CPU_CACHE_V4)	+= cache-v4.o
 obj-$(CONFIG_CPU_CACHE_V4WT)	+= cache-v4wt.o
 obj-$(CONFIG_CPU_CACHE_V4WB)	+= cache-v4wb.o
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index dd3d59122cc3..48bc3c0a87ce 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override)
 	outer_cache.inv_range = feroceon_l2_inv_range;
 	outer_cache.clean_range = feroceon_l2_clean_range;
 	outer_cache.flush_range = feroceon_l2_flush_range;
+	outer_cache.inv_all = l2_inv_all;
 
 	enable_l2();
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c2f37390308a..c465faca51b0 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -299,7 +299,7 @@ static void l2x0_unlock(u32 cache_id)
 	int lockregs;
 	int i;
 
-	switch (cache_id) {
+	switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
 	case L2X0_CACHE_ID_PART_L310:
 		lockregs = 8;
 		break;
@@ -333,15 +333,14 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	if (cache_id_part_number_from_dt)
 		cache_id = cache_id_part_number_from_dt;
 	else
-		cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID)
-			& L2X0_CACHE_ID_PART_MASK;
+		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) {
+	switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
 	case L2X0_CACHE_ID_PART_L310:
 		if (aux & (1 << 16))
 			ways = 16;
@@ -725,7 +724,6 @@ static const struct l2x0_of_data pl310_data = {
 		.flush_all   = l2x0_flush_all,
 		.inv_all     = l2x0_inv_all,
 		.disable     = l2x0_disable,
-		.set_debug   = pl310_set_debug,
 	},
 };
 
@@ -814,9 +812,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 		data->save();
 
 	of_init = true;
-	l2x0_init(l2x0_base, aux_val, aux_mask);
-
 	memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache));
+	l2x0_init(l2x0_base, aux_val, aux_mask);
 
 	return 0;
 }
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
deleted file mode 100644
index 8a3fadece8d3..000000000000
--- a/arch/arm/mm/cache-v3.S
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- *  linux/arch/arm/mm/cache-v3.S
- *
- *  Copyright (C) 1997-2002 Russell king
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/page.h>
-#include "proc-macros.S"
-
-/*
- *	flush_icache_all()
- *
- *	Unconditionally clean and invalidate the entire icache.
- */
-ENTRY(v3_flush_icache_all)
-	mov	pc, lr
-ENDPROC(v3_flush_icache_all)
-
-/*
- *	flush_user_cache_all()
- *
- *	Invalidate all cache entries in a particular address
- *	space.
- *
- *	- mm	- mm_struct describing address space
- */
-ENTRY(v3_flush_user_cache_all)
-	/* FALLTHROUGH */
-/*
- *	flush_kern_cache_all()
- *
- *	Clean and invalidate the entire cache.
- */
-ENTRY(v3_flush_kern_cache_all)
-	/* FALLTHROUGH */
-
-/*
- *	flush_user_cache_range(start, end, flags)
- *
- *	Invalidate a range of cache entries in the specified
- *	address space.
- *
- *	- start - start address (may not be aligned)
- *	- end	- end address (exclusive, may not be aligned)
- *	- flags	- vma_area_struct flags describing address space
- */
-ENTRY(v3_flush_user_cache_range)
-	mov	ip, #0
-	mcreq	p15, 0, ip, c7, c0, 0		@ flush ID cache
-	mov	pc, lr
-
-/*
- *	coherent_kern_range(start, end)
- *
- *	Ensure coherency between the Icache and the Dcache in the
- *	region described by start.  If you have non-snooping
- *	Harvard caches, you need to implement this function.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_coherent_kern_range)
-	/* FALLTHROUGH */
-
-/*
- *	coherent_user_range(start, end)
- *
- *	Ensure coherency between the Icache and the Dcache in the
- *	region described by start.  If you have non-snooping
- *	Harvard caches, you need to implement this function.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_coherent_user_range)
-	mov	r0, #0
-	mov	pc, lr
-
-/*
- *	flush_kern_dcache_area(void *page, size_t size)
- *
- *	Ensure no D cache aliasing occurs, either with itself or
- *	the I cache
- *
- *	- addr	- kernel address
- *	- size	- region size
- */
-ENTRY(v3_flush_kern_dcache_area)
-	/* FALLTHROUGH */
-
-/*
- *	dma_flush_range(start, end)
- *
- *	Clean and invalidate the specified virtual address range.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_dma_flush_range)
-	mov	r0, #0
-	mcr	p15, 0, r0, c7, c0, 0		@ flush ID cache
-	mov	pc, lr
-
-/*
- *	dma_unmap_area(start, size, dir)
- *	- start	- kernel virtual start address
- *	- size	- size of region
- *	- dir	- DMA direction
- */
-ENTRY(v3_dma_unmap_area)
-	teq	r2, #DMA_TO_DEVICE
-	bne	v3_dma_flush_range
-	/* FALLTHROUGH */
-
-/*
- *	dma_map_area(start, size, dir)
- *	- start	- kernel virtual start address
- *	- size	- size of region
- *	- dir	- DMA direction
- */
-ENTRY(v3_dma_map_area)
-	mov	pc, lr
-ENDPROC(v3_dma_unmap_area)
-ENDPROC(v3_dma_map_area)
-
-	.globl	v3_flush_kern_cache_louis
-	.equ	v3_flush_kern_cache_louis, v3_flush_kern_cache_all
-
-	__INITDATA
-
-	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
-	define_cache_functions v3
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 43e5d77be677..a7ba68f59f0c 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all)
 ENTRY(v4_flush_user_cache_range)
 #ifdef CONFIG_CPU_CP15
 	mov	ip, #0
-	mcreq	p15, 0, ip, c7, c7, 0		@ flush ID cache
+	mcr	p15, 0, ip, c7, c7, 0		@ flush ID cache
 	mov	pc, lr
 #else
 	/* FALLTHROUGH */
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 7a0511191f6b..2ac37372ef52 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -48,7 +48,7 @@ static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
 static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
 static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);
 
-static DEFINE_PER_CPU(atomic64_t, active_asids);
+DEFINE_PER_CPU(atomic64_t, active_asids);
 static DEFINE_PER_CPU(u64, reserved_asids);
 static cpumask_t tlb_flush_pending;
 
@@ -152,9 +152,9 @@ static int is_reserved_asid(u64 asid)
 	return 0;
 }
 
-static void new_context(struct mm_struct *mm, unsigned int cpu)
+static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 {
-	u64 asid = mm->context.id;
+	u64 asid = atomic64_read(&mm->context.id);
 	u64 generation = atomic64_read(&asid_generation);
 
 	if (asid != 0 && is_reserved_asid(asid)) {
@@ -181,13 +181,14 @@ static void new_context(struct mm_struct *mm, unsigned int cpu)
 		cpumask_clear(mm_cpumask(mm));
 	}
 
-	mm->context.id = asid;
+	return asid;
 }
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 {
 	unsigned long flags;
 	unsigned int cpu = smp_processor_id();
+	u64 asid;
 
 	if (unlikely(mm->context.vmalloc_seq != init_mm.context.vmalloc_seq))
 		__check_vmalloc_seq(mm);
@@ -198,20 +199,27 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 	 */
 	cpu_set_reserved_ttbr0();
 
-	if (!((mm->context.id ^ atomic64_read(&asid_generation)) >> ASID_BITS)
-	    && atomic64_xchg(&per_cpu(active_asids, cpu), mm->context.id))
+	asid = atomic64_read(&mm->context.id);
+	if (!((asid ^ atomic64_read(&asid_generation)) >> ASID_BITS)
+	    && atomic64_xchg(&per_cpu(active_asids, cpu), asid))
 		goto switch_mm_fastpath;
 
 	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
 	/* Check that our ASID belongs to the current generation. */
-	if ((mm->context.id ^ atomic64_read(&asid_generation)) >> ASID_BITS)
-		new_context(mm, cpu);
-
-	atomic64_set(&per_cpu(active_asids, cpu), mm->context.id);
-	cpumask_set_cpu(cpu, mm_cpumask(mm));
+	asid = atomic64_read(&mm->context.id);
+	if ((asid ^ atomic64_read(&asid_generation)) >> ASID_BITS) {
+		asid = new_context(mm, cpu);
+		atomic64_set(&mm->context.id, asid);
+	}
 
-	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending))
+	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) {
+		local_flush_bp_all();
 		local_flush_tlb_all();
+		dummy_flush_tlb_a15_erratum();
+	}
+
+	atomic64_set(&per_cpu(active_asids, cpu), asid);
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
 	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
 
 switch_mm_fastpath:
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c7e3759f16d3..ef3e0f3aac96 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -342,6 +342,7 @@ static int __init atomic_pool_init(void)
 {
 	struct dma_pool *pool = &atomic_pool;
 	pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);
+	gfp_t gfp = GFP_KERNEL | GFP_DMA;
 	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
 	unsigned long *bitmap;
 	struct page *page;
@@ -361,8 +362,8 @@ static int __init atomic_pool_init(void)
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
 					      atomic_pool_init);
 	else
-		ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
-					   &page, atomic_pool_init);
+		ptr = __alloc_remap_buffer(NULL, pool->size, gfp, prot, &page,
+					   atomic_pool_init);
 	if (ptr) {
 		int i;
 
@@ -822,16 +823,17 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 		if (PageHighMem(page)) {
 			if (len + offset > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
-			vaddr = kmap_high_get(page);
-			if (vaddr) {
-				vaddr += offset;
-				op(vaddr, len, dir);
-				kunmap_high(page);
-			} else if (cache_is_vipt()) {
-				/* unmapped pages might still be cached */
+
+			if (cache_is_vipt_nonaliasing()) {
 				vaddr = kmap_atomic(page);
 				op(vaddr + offset, len, dir);
 				kunmap_atomic(vaddr);
+			} else {
+				vaddr = kmap_high_get(page);
+				if (vaddr) {
+					op(vaddr + offset, len, dir);
+					kunmap_high(page);
+				}
 			}
 		} else {
 			vaddr = page_address(page) + offset;
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 1c8f7f564175..0d473cce501c 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -170,15 +170,18 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 	if (!PageHighMem(page)) {
 		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 	} else {
-		void *addr = kmap_high_get(page);
-		if (addr) {
-			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-			kunmap_high(page);
-		} else if (cache_is_vipt()) {
-			/* unmapped pages might still be cached */
+		void *addr;
+
+		if (cache_is_vipt_nonaliasing()) {
 			addr = kmap_atomic(page);
 			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
 			kunmap_atomic(addr);
+		} else {
+			addr = kmap_high_get(page);
+			if (addr) {
+				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+				kunmap_high(page);
+			}
 		}
 	}
 
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 2dffc010cc41..83cb3ac27095 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -8,7 +8,6 @@
 #include <asm/pgtable.h>
 #include <asm/sections.h>
 #include <asm/system_info.h>
-#include <asm/virt.h>
 
 pgd_t *idmap_pgd;
 
@@ -83,37 +82,10 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start,
 	} while (pgd++, addr = next, addr != end);
 }
 
-#if defined(CONFIG_ARM_VIRT_EXT) && defined(CONFIG_ARM_LPAE)
-pgd_t *hyp_pgd;
-
-extern char  __hyp_idmap_text_start[], __hyp_idmap_text_end[];
-
-static int __init init_static_idmap_hyp(void)
-{
-	hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
-	if (!hyp_pgd)
-		return -ENOMEM;
-
-	pr_info("Setting up static HYP identity map for 0x%p - 0x%p\n",
-		__hyp_idmap_text_start, __hyp_idmap_text_end);
-	identity_mapping_add(hyp_pgd, __hyp_idmap_text_start,
-			     __hyp_idmap_text_end, PMD_SECT_AP1);
-
-	return 0;
-}
-#else
-static int __init init_static_idmap_hyp(void)
-{
-	return 0;
-}
-#endif
-
 extern char  __idmap_text_start[], __idmap_text_end[];
 
 static int __init init_static_idmap(void)
 {
-	int ret;
-
 	idmap_pgd = pgd_alloc(&init_mm);
 	if (!idmap_pgd)
 		return -ENOMEM;
@@ -123,12 +95,10 @@ static int __init init_static_idmap(void)
 	identity_mapping_add(idmap_pgd, __idmap_text_start,
 			     __idmap_text_end, 0);
 
-	ret = init_static_idmap_hyp();
-
 	/* Flush L1 for the hardware to see this page table content */
 	flush_cache_louis();
 
-	return ret;
+	return 0;
 }
 early_initcall(init_static_idmap);
 
@@ -141,6 +111,7 @@ void setup_mm_for_reboot(void)
 {
 	/* Switch to the identity mapping. */
 	cpu_switch_mm(idmap_pgd, &init_mm);
+	local_flush_bp_all();
 
 #ifdef CONFIG_CPU_HAS_ASID
 	/*
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index ad722f1208a5..9a5cdc01fcdf 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -99,6 +99,9 @@ void show_mem(unsigned int filter)
 	printk("Mem-info:\n");
 	show_free_areas(filter);
 
+	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+		return;
+
 	for_each_bank (i, mi) {
 		struct membank *bank = &mi->bank[i];
 		unsigned int pfn1, pfn2;
@@ -424,24 +427,6 @@ void __init bootmem_init(void)
 	max_pfn = max_high - PHYS_PFN_OFFSET;
 }
 
-static inline int free_area(unsigned long pfn, unsigned long end, char *s)
-{
-	unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10);
-
-	for (; pfn < end; pfn++) {
-		struct page *page = pfn_to_page(pfn);
-		ClearPageReserved(page);
-		init_page_count(page);
-		__free_page(page);
-		pages++;
-	}
-
-	if (size && s)
-		printk(KERN_INFO "Freeing %s memory: %dK\n", s, size);
-
-	return pages;
-}
-
 /*
  * Poison init memory with an undefined instruction (ARM) or a branch to an
  * undefined instruction (Thumb).
@@ -534,6 +519,14 @@ static void __init free_unused_memmap(struct meminfo *mi)
 #endif
 }
 
+#ifdef CONFIG_HIGHMEM
+static inline void free_area_high(unsigned long pfn, unsigned long end)
+{
+	for (; pfn < end; pfn++)
+		free_highmem_page(pfn_to_page(pfn));
+}
+#endif
+
 static void __init free_highpages(void)
 {
 #ifdef CONFIG_HIGHMEM
@@ -569,8 +562,7 @@ static void __init free_highpages(void)
 			if (res_end > end)
 				res_end = end;
 			if (res_start != start)
-				totalhigh_pages += free_area(start, res_start,
-							     NULL);
+				free_area_high(start, res_start);
 			start = res_end;
 			if (start == end)
 				break;
@@ -578,9 +570,8 @@ static void __init free_highpages(void)
 
 		/* And now free anything which remains */
 		if (start < end)
-			totalhigh_pages += free_area(start, end, NULL);
+			free_area_high(start, end);
 	}
-	totalram_pages += totalhigh_pages;
 #endif
 }
 
@@ -609,8 +600,7 @@ void __init mem_init(void)
 
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
-	totalram_pages += free_area(PHYS_PFN_OFFSET,
-				    __phys_to_pfn(__pa(swapper_pg_dir)), NULL);
+	free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL);
 #endif
 
 	free_highpages();
@@ -738,16 +728,12 @@ void free_initmem(void)
 	extern char __tcm_start, __tcm_end;
 
 	poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start);
-	totalram_pages += free_area(__phys_to_pfn(__pa(&__tcm_start)),
-				    __phys_to_pfn(__pa(&__tcm_end)),
-				    "TCM link");
+	free_reserved_area(&__tcm_start, &__tcm_end, 0, "TCM link");
 #endif
 
 	poison_init_mem(__init_begin, __init_end - __init_begin);
 	if (!machine_is_integrator() && !machine_is_cintegrator())
-		totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),
-					    __phys_to_pfn(__pa(__init_end)),
-					    "init");
+		free_initmem_default(0);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -758,9 +744,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd) {
 		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		totalram_pages += free_area(__phys_to_pfn(__pa(start)),
-					    __phys_to_pfn(__pa(end)),
-					    "initrd");
+		free_reserved_area(start, end, 0, "initrd");
 	}
 }
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index c6d45c87540e..e0d8565671a6 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -34,6 +34,7 @@
 #include <asm/mach/pci.h>
 
 #include "mm.h"
+#include "tcm.h"
 
 /*
  * empty_zero_page is a special page that is used for
@@ -615,39 +616,60 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void __init alloc_init_section(pud_t *pud, unsigned long addr,
-				      unsigned long end, phys_addr_t phys,
-				      const struct mem_type *type)
+static void __init map_init_section(pmd_t *pmd, unsigned long addr,
+			unsigned long end, phys_addr_t phys,
+			const struct mem_type *type)
 {
-	pmd_t *pmd = pmd_offset(pud, addr);
-
+#ifndef CONFIG_ARM_LPAE
 	/*
-	 * Try a section mapping - end, addr and phys must all be aligned
-	 * to a section boundary.  Note that PMDs refer to the individual
-	 * L1 entries, whereas PGDs refer to a group of L1 entries making
-	 * up one logical pointer to an L2 table.
+	 * In classic MMU format, puds and pmds are folded in to
+	 * the pgds. pmd_offset gives the PGD entry. PGDs refer to a
+	 * group of L1 entries making up one logical pointer to
+	 * an L2 table (2MB), where as PMDs refer to the individual
+	 * L1 entries (1MB). Hence increment to get the correct
+	 * offset for odd 1MB sections.
+	 * (See arch/arm/include/asm/pgtable-2level.h)
 	 */
-	if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) {
-		pmd_t *p = pmd;
-
-#ifndef CONFIG_ARM_LPAE
-		if (addr & SECTION_SIZE)
-			pmd++;
+	if (addr & SECTION_SIZE)
+		pmd++;
 #endif
+	do {
+		*pmd = __pmd(phys | type->prot_sect);
+		phys += SECTION_SIZE;
+	} while (pmd++, addr += SECTION_SIZE, addr != end);
 
-		do {
-			*pmd = __pmd(phys | type->prot_sect);
-			phys += SECTION_SIZE;
-		} while (pmd++, addr += SECTION_SIZE, addr != end);
+	flush_pmd_entry(pmd);
+}
 
-		flush_pmd_entry(p);
-	} else {
+static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
+				      unsigned long end, phys_addr_t phys,
+				      const struct mem_type *type)
+{
+	pmd_t *pmd = pmd_offset(pud, addr);
+	unsigned long next;
+
+	do {
 		/*
-		 * No need to loop; pte's aren't interested in the
-		 * individual L1 entries.
+		 * With LPAE, we must loop over to map
+		 * all the pmds for the given range.
 		 */
-		alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type);
-	}
+		next = pmd_addr_end(addr, end);
+
+		/*
+		 * Try a section mapping - addr, next and phys must all be
+		 * aligned to a section boundary.
+		 */
+		if (type->prot_sect &&
+				((addr | next | phys) & ~SECTION_MASK) == 0) {
+			map_init_section(pmd, addr, next, phys, type);
+		} else {
+			alloc_init_pte(pmd, addr, next,
+						__phys_to_pfn(phys), type);
+		}
+
+		phys += next - addr;
+
+	} while (pmd++, addr = next, addr != end);
 }
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
@@ -658,7 +680,7 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 
 	do {
 		next = pud_addr_end(addr, end);
-		alloc_init_section(pud, addr, next, phys, type);
+		alloc_init_pmd(pud, addr, next, phys, type);
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
 }
@@ -1273,6 +1295,7 @@ void __init paging_init(struct machine_desc *mdesc)
 	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();
+	tcm_init();
 
 	top_pmd = pmd_off_k(0xffff0000);
 
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index dc5de5d53f20..fde2d2a794cf 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -77,24 +77,27 @@ __arm740_setup:
 	mcr	p15, 0, r0, c6,	c0		@ set area 0, default
 
 	ldr	r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
-	ldr	r1, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
+	ldr	r3, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
+	mov	r4, #10				@ 11 is the minimum (4KB)
+1:	add	r4, r4, #1			@ area size *= 2
+	movs	r3, r3, lsr #1
 	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, r4, lsl #1		@ the area register value
 	orr	r0, r0, #1			@ set enable bit
 	mcr	p15, 0, r0, c6,	c1		@ set area 1, RAM
 
 	ldr	r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
-	ldr	r1, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
+	ldr	r3, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
+	cmp	r3, #0
+	moveq	r0, #0
+	beq	2f
+	mov	r4, #10				@ 11 is the minimum (4KB)
+1:	add	r4, r4, #1			@ area size *= 2
+	movs	r3, r3, lsr #1
 	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, r4, lsl #1		@ the area register value
 	orr	r0, r0, #1			@ set enable bit
-	mcr	p15, 0, r0, c6,	c2		@ set area 2, ROM/FLASH
+2:	mcr	p15, 0, r0, c6,	c2		@ set area 2, ROM/FLASH
 
 	mov	r0, #0x06
 	mcr	p15, 0, r0, c2, c0		@ Region 1&2 cacheable
@@ -137,13 +140,14 @@ __arm740_proc_info:
 	.long	0x41807400
 	.long	0xfffffff0
 	.long	0
+	.long	0
 	b	__arm740_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
-	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT
+	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT
 	.long	cpu_arm740_name
 	.long	arm740_processor_functions
 	.long	0
 	.long	0
-	.long	v3_cache_fns			@ cache model
+	.long	v4_cache_fns			@ cache model
 	.size	__arm740_proc_info, . - __arm740_proc_info
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 2c3b9421ab5e..2556cf1c2da1 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm920_suspend_size
 .equ	cpu_arm920_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_arm920_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index f1803f7e2972..344c8a548cc0 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm926_suspend_size
 .equ	cpu_arm926_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_arm926_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 82f9cdc751d6..0b60dd3d742a 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext)
 
 .globl	cpu_mohawk_suspend_size
 .equ	cpu_mohawk_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_mohawk_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 3aa0da11fd84..d92dfd081429 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext)
 
 .globl	cpu_sa1100_suspend_size
 .equ	cpu_sa1100_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_sa1100_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c3, c0, 0		@ domain ID
diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c
index 3e6210b4d6d4..054b491ff764 100644
--- a/arch/arm/mm/proc-syms.c
+++ b/arch/arm/mm/proc-syms.c
@@ -17,7 +17,9 @@
 
 #ifndef MULTI_CPU
 EXPORT_SYMBOL(cpu_dcache_clean_area);
+#ifdef CONFIG_MMU
 EXPORT_SYMBOL(cpu_set_pte_ext);
+#endif
 #else
 EXPORT_SYMBOL(processor);
 #endif
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index bcaaa8de9325..919405e20b80 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -80,12 +80,10 @@ ENTRY(cpu_v6_do_idle)
 	mov	pc, lr
 
 ENTRY(cpu_v6_dcache_clean_area)
-#ifndef TLB_CAN_READ_FROM_L1_CACHE
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	subs	r1, r1, #D_CACHE_LINE_SIZE
 	bhi	1b
-#endif
 	mov	pc, lr
 
 /*
@@ -138,7 +136,7 @@ ENTRY(cpu_v6_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
 .globl	cpu_v6_suspend_size
 .equ	cpu_v6_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v6_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 78f520bc0e99..9704097c450e 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -110,7 +110,8 @@ ENTRY(cpu_v7_set_pte_ext)
  ARM(	str	r3, [r0, #2048]! )
  THUMB(	add	r0, r0, #2048 )
  THUMB(	str	r3, [r0] )
-	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+	ALT_SMP(mov	pc,lr)
+	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
 #endif
 	mov	pc, lr
 ENDPROC(cpu_v7_set_pte_ext)
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 50bf1dafc9ea..363027e811d6 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -48,7 +48,7 @@
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
 	mmid	r1, r1				@ get mm->context.id
-	and	r3, r1, #0xff
+	asid	r3, r1
 	mov	r3, r3, lsl #(48 - 32)		@ ASID
 	mcrr	p15, 0, r0, r3, c2		@ set TTB 0
 	isb
@@ -73,7 +73,8 @@ ENTRY(cpu_v7_set_pte_ext)
 	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
 	orreq	r2, #L_PTE_RDONLY
 1:	strd	r2, r3, [r0]
-	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+	ALT_SMP(mov	pc, lr)
+	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
 #endif
 	mov	pc, lr
 ENDPROC(cpu_v7_set_pte_ext)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3a3c015f8d5c..2c73a7301ff7 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -75,14 +75,14 @@ ENTRY(cpu_v7_do_idle)
 ENDPROC(cpu_v7_do_idle)
 
 ENTRY(cpu_v7_dcache_clean_area)
-#ifndef TLB_CAN_READ_FROM_L1_CACHE
+	ALT_SMP(mov	pc, lr)			@ MP extensions imply L1 PTW
+	ALT_UP(W(nop))
 	dcache_line_size r2, r3
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, r2
 	subs	r1, r1, r2
 	bhi	1b
 	dsb
-#endif
 	mov	pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)
 
@@ -402,6 +402,8 @@ __v7_ca9mp_proc_info:
 	__v7_proc __v7_ca9mp_setup
 	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
 
+#endif	/* CONFIG_ARM_LPAE */
+
 	/*
 	 * Marvell PJ4B processor.
 	 */
@@ -411,7 +413,6 @@ __v7_pj4b_proc_info:
 	.long	0xfffffff0
 	__v7_proc __v7_pj4b_setup
 	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
-#endif	/* CONFIG_ARM_LPAE */
 
 	/*
 	 * ARM Ltd. Cortex A7 processor.
@@ -420,7 +421,7 @@ __v7_pj4b_proc_info:
 __v7_ca7mp_proc_info:
 	.long	0x410fc070
 	.long	0xff0ffff0
-	__v7_proc __v7_ca7mp_setup, hwcaps = HWCAP_IDIV
+	__v7_proc __v7_ca7mp_setup
 	.size	__v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info
 
 	/*
@@ -430,10 +431,25 @@ __v7_ca7mp_proc_info:
 __v7_ca15mp_proc_info:
 	.long	0x410fc0f0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca15mp_setup, hwcaps = HWCAP_IDIV
+	__v7_proc __v7_ca15mp_setup
 	.size	__v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
 
 	/*
+	 * Qualcomm Inc. Krait processors.
+	 */
+	.type	__krait_proc_info, #object
+__krait_proc_info:
+	.long	0x510f0400		@ Required ID value
+	.long	0xff0ffc00		@ Mask for ID
+	/*
+	 * Some Krait processors don't indicate support for SDIV and UDIV
+	 * instructions in the ARM instruction set, even though they actually
+	 * do support them.
+	 */
+	__v7_proc __v7_setup, hwcaps = HWCAP_IDIV
+	.size	__krait_proc_info, . - __krait_proc_info
+
+	/*
 	 * Match any ARMv7 processor core.
 	 */
 	.type	__v7_proc_info, #object
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index eb93d6487f35..e8efd83b6f25 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext)
 
 .globl	cpu_xsc3_suspend_size
 .equ	cpu_xsc3_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_xsc3_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 25510361aa18..e766f889bfd6 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext)
 
 .globl	cpu_xscale_suspend_size
 .equ	cpu_xscale_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_xscale_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
diff --git a/arch/arm/mm/tcm.h b/arch/arm/mm/tcm.h
new file mode 100644
index 000000000000..8015ad434a40
--- /dev/null
+++ b/arch/arm/mm/tcm.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+
+#ifdef CONFIG_HAVE_TCM
+void __init tcm_init(void);
+#else
+/* No TCM support, just blank inlines to be optimized out */
+inline void tcm_init(void)
+{
+}
+#endif