13 files changed, 318 insertions, 249 deletions

diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 924036473b16..b8cb1a2688a0 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -28,6 +28,7 @@
 #include <asm/opcodes.h>
 
 #include "fault.h"
+#include "mm.h"
 
 /*
  * 32-bit misaligned trap handler (c) 1998 San Mehat (CCC) -July 1998
@@ -81,6 +82,7 @@ static unsigned long ai_word;
 static unsigned long ai_dword;
 static unsigned long ai_multi;
 static int ai_usermode;
+static unsigned long cr_no_alignment;
 
 core_param(alignment, ai_usermode, int, 0600);
 
@@ -91,7 +93,7 @@ core_param(alignment, ai_usermode, int, 0600);
 /* Return true if and only if the ARMv6 unaligned access model is in use. */
 static bool cpu_is_v6_unaligned(void)
 {
-	return cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U);
+	return cpu_architecture() >= CPU_ARCH_ARMv6 && get_cr() & CR_U;
 }
 
 static int safe_usermode(int new_usermode, bool warn)
@@ -949,6 +951,13 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	return 0;
 }
 
+static int __init noalign_setup(char *__unused)
+{
+	set_cr(__clear_cr(CR_A));
+	return 1;
+}
+__setup("noalign", noalign_setup);
+
 /*
  * This needs to be done after sysctl_init, otherwise sys/ will be
  * overwritten.  Actually, this shouldn't be in sys/ at all since
@@ -966,14 +975,12 @@ static int __init alignment_init(void)
 		return -ENOMEM;
 #endif
 
-#ifdef CONFIG_CPU_CP15
 	if (cpu_is_v6_unaligned()) {
-		cr_alignment &= ~CR_A;
-		cr_no_alignment &= ~CR_A;
-		set_cr(cr_alignment);
+		set_cr(__clear_cr(CR_A));
 		ai_usermode = safe_usermode(ai_usermode, false);
 	}
-#endif
+
+	cr_no_alignment = get_cr() & ~CR_A;
 
 	hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN,
 			"alignment exception");
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 778bcf88ee79..615c99e38ba1 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -59,7 +59,7 @@ ENTRY(v7_invalidate_l1)
        bgt     2b
        cmp     r2, #0
        bgt     1b
-       dsb
+       dsb     st
        isb
        mov     pc, lr
 ENDPROC(v7_invalidate_l1)
@@ -166,7 +166,7 @@ skip:
 finished:
 	mov	r10, #0				@ swith back to cache level 0
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
-	dsb
+	dsb	st
 	isb
 	mov	pc, lr
 ENDPROC(v7_flush_dcache_all)
@@ -335,7 +335,7 @@ ENTRY(v7_flush_kern_dcache_area)
 	add	r0, r0, r2
 	cmp	r0, r1
 	blo	1b
-	dsb
+	dsb	st
 	mov	pc, lr
 ENDPROC(v7_flush_kern_dcache_area)
 
@@ -368,7 +368,7 @@ v7_dma_inv_range:
 	add	r0, r0, r2
 	cmp	r0, r1
 	blo	1b
-	dsb
+	dsb	st
 	mov	pc, lr
 ENDPROC(v7_dma_inv_range)
 
@@ -390,7 +390,7 @@ v7_dma_clean_range:
 	add	r0, r0, r2
 	cmp	r0, r1
 	blo	1b
-	dsb
+	dsb	st
 	mov	pc, lr
 ENDPROC(v7_dma_clean_range)
 
@@ -412,7 +412,7 @@ ENTRY(v7_dma_flush_range)
 	add	r0, r0, r2
 	cmp	r0, r1
 	blo	1b
-	dsb
+	dsb	st
 	mov	pc, lr
 ENDPROC(v7_dma_flush_range)
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 6b00be1f971e..b05e08c4734c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -904,11 +904,12 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 	unsigned long paddr = page_to_phys(page) + off;
 
 	/* FIXME: non-speculating: not required */
-	/* don't bother invalidating if DMA to device */
-	if (dir != DMA_TO_DEVICE)
+	/* in any case, don't bother invalidating if DMA to device */
+	if (dir != DMA_TO_DEVICE) {
 		outer_inv_range(paddr, paddr + size);
 
-	dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+		dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+	}
 
 	/*
 	 * Mark the D-cache clean for these pages to avoid extra flushing.
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 3387e60e4ea3..43d54f5b26b9 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -104,17 +104,20 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig
 #define flush_icache_alias(pfn,vaddr,len)	do { } while (0)
 #endif
 
+#define FLAG_PA_IS_EXEC 1
+#define FLAG_PA_CORE_IN_MM 2
+
 static void flush_ptrace_access_other(void *args)
 {
 	__flush_icache_all();
 }
 
-static
-void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
-			 unsigned long uaddr, void *kaddr, unsigned long len)
+static inline
+void __flush_ptrace_access(struct page *page, unsigned long uaddr, void *kaddr,
+			   unsigned long len, unsigned int flags)
 {
 	if (cache_is_vivt()) {
-		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+		if (flags & FLAG_PA_CORE_IN_MM) {
 			unsigned long addr = (unsigned long)kaddr;
 			__cpuc_coherent_kern_range(addr, addr + len);
 		}
@@ -128,7 +131,7 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
 	}
 
 	/* VIPT non-aliasing D-cache */
-	if (vma->vm_flags & VM_EXEC) {
+	if (flags & FLAG_PA_IS_EXEC) {
 		unsigned long addr = (unsigned long)kaddr;
 		if (icache_is_vipt_aliasing())
 			flush_icache_alias(page_to_pfn(page), uaddr, len);
@@ -140,6 +143,26 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
 	}
 }
 
+static
+void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
+			 unsigned long uaddr, void *kaddr, unsigned long len)
+{
+	unsigned int flags = 0;
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
+		flags |= FLAG_PA_CORE_IN_MM;
+	if (vma->vm_flags & VM_EXEC)
+		flags |= FLAG_PA_IS_EXEC;
+	__flush_ptrace_access(page, uaddr, kaddr, len, flags);
+}
+
+void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
+			     void *kaddr, unsigned long len)
+{
+	unsigned int flags = FLAG_PA_CORE_IN_MM|FLAG_PA_IS_EXEC;
+
+	__flush_ptrace_access(page, uaddr, kaddr, len, flags);
+}
+
 /*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 21b9e1bf9b77..45aeaaca9052 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -18,6 +18,21 @@
 #include <asm/tlbflush.h>
 #include "mm.h"
 
+pte_t *fixmap_page_table;
+
+static inline void set_fixmap_pte(int idx, pte_t pte)
+{
+	unsigned long vaddr = __fix_to_virt(idx);
+	set_pte_ext(fixmap_page_table + idx, pte, 0);
+	local_flush_tlb_kernel_page(vaddr);
+}
+
+static inline pte_t get_fixmap_pte(unsigned long vaddr)
+{
+	unsigned long idx = __virt_to_fix(vaddr);
+	return *(fixmap_page_table + idx);
+}
+
 void *kmap(struct page *page)
 {
 	might_sleep();
@@ -63,20 +78,20 @@ void *kmap_atomic(struct page *page)
 	type = kmap_atomic_idx_push();
 
 	idx = type + KM_TYPE_NR * smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
 	 * With debugging enabled, kunmap_atomic forces that entry to 0.
 	 * Make sure it was indeed properly unmapped.
 	 */
-	BUG_ON(!pte_none(get_top_pte(vaddr)));
+	BUG_ON(!pte_none(*(fixmap_page_table + idx)));
 #endif
 	/*
 	 * When debugging is off, kunmap_atomic leaves the previous mapping
 	 * in place, so the contained TLB flush ensures the TLB is updated
 	 * with the new mapping.
 	 */
-	set_top_pte(vaddr, mk_pte(page, kmap_prot));
+	set_fixmap_pte(idx, mk_pte(page, kmap_prot));
 
 	return (void *)vaddr;
 }
@@ -94,8 +109,8 @@ void __kunmap_atomic(void *kvaddr)
 		if (cache_is_vivt())
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
 #ifdef CONFIG_DEBUG_HIGHMEM
-		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-		set_top_pte(vaddr, __pte(0));
+		BUG_ON(vaddr != __fix_to_virt(idx));
+		set_fixmap_pte(idx, __pte(0));
 #else
 		(void) idx;  /* to kill a warning */
 #endif
@@ -117,11 +132,11 @@ void *kmap_atomic_pfn(unsigned long pfn)
 
 	type = kmap_atomic_idx_push();
 	idx = type + KM_TYPE_NR * smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(get_top_pte(vaddr)));
+	BUG_ON(!pte_none(*(fixmap_page_table + idx)));
 #endif
-	set_top_pte(vaddr, pfn_pte(pfn, kmap_prot));
+	set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot));
 
 	return (void *)vaddr;
 }
@@ -133,5 +148,5 @@ struct page *kmap_atomic_to_page(const void *ptr)
 	if (vaddr < FIXADDR_START)
 		return virt_to_page(ptr);
 
-	return pte_page(get_top_pte(vaddr));
+	return pte_page(get_fixmap_pte(vaddr));
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 2a77ba8796ae..5958ac05181e 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -23,6 +23,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/sizes.h>
 
+#include <asm/cp15.h>
 #include <asm/mach-types.h>
 #include <asm/memblock.h>
 #include <asm/prom.h>
@@ -36,6 +37,14 @@
 
 #include "mm.h"
 
+#ifdef CONFIG_CPU_CP15_MMU
+unsigned long __init __clear_cr(unsigned long mask)
+{
+	cr_alignment = cr_alignment & ~mask;
+	return cr_alignment;
+}
+#endif
+
 static phys_addr_t phys_initrd_start __initdata = 0;
 static unsigned long phys_initrd_size __initdata = 0;
 
@@ -81,24 +90,21 @@ __tagtable(ATAG_INITRD2, parse_tag_initrd2);
  * initialization functions, as well as show_mem() for the skipping
  * of holes in the memory map.  It is populated by arm_add_memory().
  */
-struct meminfo meminfo;
-
 void show_mem(unsigned int filter)
 {
 	int free = 0, total = 0, reserved = 0;
-	int shared = 0, cached = 0, slab = 0, i;
-	struct meminfo * mi = &meminfo;
+	int shared = 0, cached = 0, slab = 0;
+	struct memblock_region *reg;
 
 	printk("Mem-info:\n");
 	show_free_areas(filter);
 
-	for_each_bank (i, mi) {
-		struct membank *bank = &mi->bank[i];
+	for_each_memblock (memory, reg) {
 		unsigned int pfn1, pfn2;
 		struct page *page, *end;
 
-		pfn1 = bank_pfn_start(bank);
-		pfn2 = bank_pfn_end(bank);
+		pfn1 = memblock_region_memory_base_pfn(reg);
+		pfn2 = memblock_region_memory_end_pfn(reg);
 
 		page = pfn_to_page(pfn1);
 		end  = pfn_to_page(pfn2 - 1) + 1;
@@ -115,8 +121,9 @@ void show_mem(unsigned int filter)
 				free++;
 			else
 				shared += page_count(page) - 1;
-			page++;
-		} while (page < end);
+			pfn1++;
+			page = pfn_to_page(pfn1);
+		} while (pfn1 < pfn2);
 	}
 
 	printk("%d pages of RAM\n", total);
@@ -130,16 +137,9 @@ void show_mem(unsigned int filter)
 static void __init find_limits(unsigned long *min, unsigned long *max_low,
 			       unsigned long *max_high)
 {
-	struct meminfo *mi = &meminfo;
-	int i;
-
-	/* This assumes the meminfo array is properly sorted */
-	*min = bank_pfn_start(&mi->bank[0]);
-	for_each_bank (i, mi)
-		if (mi->bank[i].highmem)
-				break;
-	*max_low = bank_pfn_end(&mi->bank[i - 1]);
-	*max_high = bank_pfn_end(&mi->bank[mi->nr_banks - 1]);
+	*max_low = PFN_DOWN(memblock_get_current_limit());
+	*min = PFN_UP(memblock_start_of_DRAM());
+	*max_high = PFN_DOWN(memblock_end_of_DRAM());
 }
 
 #ifdef CONFIG_ZONE_DMA
@@ -274,14 +274,8 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
 	return phys;
 }
 
-void __init arm_memblock_init(struct meminfo *mi,
-	const struct machine_desc *mdesc)
+void __init arm_memblock_init(const struct machine_desc *mdesc)
 {
-	int i;
-
-	for (i = 0; i < mi->nr_banks; i++)
-		memblock_add(mi->bank[i].start, mi->bank[i].size);
-
 	/* Register the kernel text, kernel data and initrd with memblock. */
 #ifdef CONFIG_XIP_KERNEL
 	memblock_reserve(__pa(_sdata), _end - _sdata);
@@ -413,54 +407,53 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 /*
  * The mem_map array can get very big.  Free the unused area of the memory map.
  */
-static void __init free_unused_memmap(struct meminfo *mi)
+static void __init free_unused_memmap(void)
 {
-	unsigned long bank_start, prev_bank_end = 0;
-	unsigned int i;
+	unsigned long start, prev_end = 0;
+	struct memblock_region *reg;
 
 	/*
 	 * This relies on each bank being in address order.
 	 * The banks are sorted previously in bootmem_init().
 	 */
-	for_each_bank(i, mi) {
-		struct membank *bank = &mi->bank[i];
-
-		bank_start = bank_pfn_start(bank);
+	for_each_memblock(memory, reg) {
+		start = memblock_region_memory_base_pfn(reg);
 
 #ifdef CONFIG_SPARSEMEM
 		/*
 		 * Take care not to free memmap entries that don't exist
 		 * due to SPARSEMEM sections which aren't present.
 		 */
-		bank_start = min(bank_start,
-				 ALIGN(prev_bank_end, PAGES_PER_SECTION));
+		start = min(start,
+				 ALIGN(prev_end, PAGES_PER_SECTION));
 #else
 		/*
 		 * Align down here since the VM subsystem insists that the
 		 * memmap entries are valid from the bank start aligned to
 		 * MAX_ORDER_NR_PAGES.
 		 */
-		bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES);
+		start = round_down(start, MAX_ORDER_NR_PAGES);
 #endif
 		/*
 		 * 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(prev_bank_end, bank_start);
+		if (prev_end && prev_end < start)
+			free_memmap(prev_end, start);
 
 		/*
 		 * 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);
+		prev_end = ALIGN(memblock_region_memory_end_pfn(reg),
+				 MAX_ORDER_NR_PAGES);
 	}
 
 #ifdef CONFIG_SPARSEMEM
-	if (!IS_ALIGNED(prev_bank_end, PAGES_PER_SECTION))
-		free_memmap(prev_bank_end,
-			    ALIGN(prev_bank_end, PAGES_PER_SECTION));
+	if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))
+		free_memmap(prev_end,
+			    ALIGN(prev_end, PAGES_PER_SECTION));
 #endif
 }
 
@@ -536,7 +529,7 @@ void __init mem_init(void)
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
 
 	/* this will put all unused low memory onto the freelists */
-	free_unused_memmap(&meminfo);
+	free_unused_memmap();
 	free_all_bootmem();
 
 #ifdef CONFIG_SA1111
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index f9c32ba73544..d1e5ad7ab3bc 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -438,6 +438,13 @@ void __arm_iounmap(volatile void __iomem *io_addr)
 EXPORT_SYMBOL(__arm_iounmap);
 
 #ifdef CONFIG_PCI
+static int pci_ioremap_mem_type = MT_DEVICE;
+
+void pci_ioremap_set_mem_type(int mem_type)
+{
+	pci_ioremap_mem_type = mem_type;
+}
+
 int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
 {
 	BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT);
@@ -445,7 +452,7 @@ int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
 	return ioremap_page_range(PCI_IO_VIRT_BASE + offset,
 				  PCI_IO_VIRT_BASE + offset + SZ_64K,
 				  phys_addr,
-				  __pgprot(get_mem_type(MT_DEVICE)->prot_pte));
+				  __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte));
 }
 EXPORT_SYMBOL_GPL(pci_ioremap_io);
 #endif
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 7ea641b7aa7d..ce727d47275c 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -2,6 +2,8 @@
 #include <linux/list.h>
 #include <linux/vmalloc.h>
 
+#include <asm/pgtable.h>
+
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
 
@@ -93,3 +95,5 @@ extern phys_addr_t arm_lowmem_limit;
 void __init bootmem_init(void);
 void arm_mm_memblock_reserve(void);
 void dma_contiguous_remap(void);
+
+unsigned long __clear_cr(unsigned long mask);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index b68c6b22e1c8..ab14b79b03f0 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -35,6 +35,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/pci.h>
+#include <asm/fixmap.h>
 
 #include "mm.h"
 #include "tcm.h"
@@ -117,28 +118,54 @@ static struct cachepolicy cache_policies[] __initdata = {
 };
 
 #ifdef CONFIG_CPU_CP15
+static unsigned long initial_pmd_value __initdata = 0;
+
 /*
- * These are useful for identifying cache coherency
- * problems by allowing the cache or the cache and
- * writebuffer to be turned off.  (Note: the write
- * buffer should not be on and the cache off).
+ * Initialise the cache_policy variable with the initial state specified
+ * via the "pmd" value.  This is used to ensure that on ARMv6 and later,
+ * the C code sets the page tables up with the same policy as the head
+ * assembly code, which avoids an illegal state where the TLBs can get
+ * confused.  See comments in early_cachepolicy() for more information.
  */
-static int __init early_cachepolicy(char *p)
+void __init init_default_cache_policy(unsigned long pmd)
 {
 	int i;
 
+	initial_pmd_value = pmd;
+
+	pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE;
+
+	for (i = 0; i < ARRAY_SIZE(cache_policies); i++)
+		if (cache_policies[i].pmd == pmd) {
+			cachepolicy = i;
+			break;
+		}
+
+	if (i == ARRAY_SIZE(cache_policies))
+		pr_err("ERROR: could not find cache policy\n");
+}
+
+/*
+ * These are useful for identifying cache coherency problems by allowing
+ * the cache or the cache and writebuffer to be turned off.  (Note: the
+ * write buffer should not be on and the cache off).
+ */
+static int __init early_cachepolicy(char *p)
+{
+	int i, selected = -1;
+
 	for (i = 0; i < ARRAY_SIZE(cache_policies); i++) {
 		int len = strlen(cache_policies[i].policy);
 
 		if (memcmp(p, cache_policies[i].policy, len) == 0) {
-			cachepolicy = i;
-			cr_alignment &= ~cache_policies[i].cr_mask;
-			cr_no_alignment &= ~cache_policies[i].cr_mask;
+			selected = i;
 			break;
 		}
 	}
-	if (i == ARRAY_SIZE(cache_policies))
-		printk(KERN_ERR "ERROR: unknown or unsupported cache policy\n");
+
+	if (selected == -1)
+		pr_err("ERROR: unknown or unsupported cache policy\n");
+
 	/*
 	 * This restriction is partly to do with the way we boot; it is
 	 * unpredictable to have memory mapped using two different sets of
@@ -146,12 +173,18 @@ static int __init early_cachepolicy(char *p)
 	 * change these attributes once the initial assembly has setup the
 	 * page tables.
 	 */
-	if (cpu_architecture() >= CPU_ARCH_ARMv6) {
-		printk(KERN_WARNING "Only cachepolicy=writeback supported on ARMv6 and later\n");
-		cachepolicy = CPOLICY_WRITEBACK;
+	if (cpu_architecture() >= CPU_ARCH_ARMv6 && selected != cachepolicy) {
+		pr_warn("Only cachepolicy=%s supported on ARMv6 and later\n",
+			cache_policies[cachepolicy].policy);
+		return 0;
+	}
+
+	if (selected != cachepolicy) {
+		unsigned long cr = __clear_cr(cache_policies[selected].cr_mask);
+		cachepolicy = selected;
+		flush_cache_all();
+		set_cr(cr);
 	}
-	flush_cache_all();
-	set_cr(cr_alignment);
 	return 0;
 }
 early_param("cachepolicy", early_cachepolicy);
@@ -186,35 +219,6 @@ static int __init early_ecc(char *p)
 early_param("ecc", early_ecc);
 #endif
 
-static int __init noalign_setup(char *__unused)
-{
-	cr_alignment &= ~CR_A;
-	cr_no_alignment &= ~CR_A;
-	set_cr(cr_alignment);
-	return 1;
-}
-__setup("noalign", noalign_setup);
-
-#ifndef CONFIG_SMP
-void adjust_cr(unsigned long mask, unsigned long set)
-{
-	unsigned long flags;
-
-	mask &= ~CR_A;
-
-	set &= mask;
-
-	local_irq_save(flags);
-
-	cr_no_alignment = (cr_no_alignment & ~mask) | set;
-	cr_alignment = (cr_alignment & ~mask) | set;
-
-	set_cr((get_cr() & ~mask) | set);
-
-	local_irq_restore(flags);
-}
-#endif
-
 #else /* ifdef CONFIG_CPU_CP15 */
 
 static int __init early_cachepolicy(char *p)
@@ -414,8 +418,17 @@ static void __init build_mem_type_table(void)
 			cachepolicy = CPOLICY_WRITEBACK;
 		ecc_mask = 0;
 	}
-	if (is_smp())
-		cachepolicy = CPOLICY_WRITEALLOC;
+
+	if (is_smp()) {
+		if (cachepolicy != CPOLICY_WRITEALLOC) {
+			pr_warn("Forcing write-allocate cache policy for SMP\n");
+			cachepolicy = CPOLICY_WRITEALLOC;
+		}
+		if (!(initial_pmd_value & PMD_SECT_S)) {
+			pr_warn("Forcing shared mappings for SMP\n");
+			initial_pmd_value |= PMD_SECT_S;
+		}
+	}
 
 	/*
 	 * Strip out features not present on earlier architectures.
@@ -539,11 +552,12 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 #endif
 
-		if (is_smp()) {
-			/*
-			 * Mark memory with the "shared" attribute
-			 * for SMP systems
-			 */
+		/*
+		 * If the initial page tables were created with the S bit
+		 * set, then we need to do the same here for the same
+		 * reasons given in early_cachepolicy().
+		 */
+		if (initial_pmd_value & PMD_SECT_S) {
 			user_pgprot |= L_PTE_SHARED;
 			kern_pgprot |= L_PTE_SHARED;
 			vecs_pgprot |= L_PTE_SHARED;
@@ -1061,74 +1075,47 @@ phys_addr_t arm_lowmem_limit __initdata = 0;
 void __init sanity_check_meminfo(void)
 {
 	phys_addr_t memblock_limit = 0;
-	int i, j, highmem = 0;
+	int highmem = 0;
 	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
+	struct memblock_region *reg;
 
-	for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
-		struct membank *bank = &meminfo.bank[j];
-		phys_addr_t size_limit;
-
-		*bank = meminfo.bank[i];
-		size_limit = bank->size;
+	for_each_memblock(memory, reg) {
+		phys_addr_t block_start = reg->base;
+		phys_addr_t block_end = reg->base + reg->size;
+		phys_addr_t size_limit = reg->size;
 
-		if (bank->start >= vmalloc_limit)
+		if (reg->base >= vmalloc_limit)
 			highmem = 1;
 		else
-			size_limit = vmalloc_limit - bank->start;
+			size_limit = vmalloc_limit - reg->base;
 
-		bank->highmem = highmem;
 
-#ifdef CONFIG_HIGHMEM
-		/*
-		 * Split those memory banks which are partially overlapping
-		 * the vmalloc area greatly simplifying things later.
-		 */
-		if (!highmem && bank->size > size_limit) {
-			if (meminfo.nr_banks >= NR_BANKS) {
-				printk(KERN_CRIT "NR_BANKS too low, "
-						 "ignoring high memory\n");
-			} else {
-				memmove(bank + 1, bank,
-					(meminfo.nr_banks - i) * sizeof(*bank));
-				meminfo.nr_banks++;
-				i++;
-				bank[1].size -= size_limit;
-				bank[1].start = vmalloc_limit;
-				bank[1].highmem = highmem = 1;
-				j++;
+		if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
+
+			if (highmem) {
+				pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
+					&block_start, &block_end);
+				memblock_remove(reg->base, reg->size);
+				continue;
 			}
-			bank->size = size_limit;
-		}
-#else
-		/*
-		 * Highmem banks not allowed with !CONFIG_HIGHMEM.
-		 */
-		if (highmem) {
-			printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
-			       "(!CONFIG_HIGHMEM).\n",
-			       (unsigned long long)bank->start,
-			       (unsigned long long)bank->start + bank->size - 1);
-			continue;
-		}
 
-		/*
-		 * Check whether this memory bank would partially overlap
-		 * the vmalloc area.
-		 */
-		if (bank->size > size_limit) {
-			printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
-			       "to -%.8llx (vmalloc region overlap).\n",
-			       (unsigned long long)bank->start,
-			       (unsigned long long)bank->start + bank->size - 1,
-			       (unsigned long long)bank->start + size_limit - 1);
-			bank->size = size_limit;
+			if (reg->size > size_limit) {
+				phys_addr_t overlap_size = reg->size - size_limit;
+
+				pr_notice("Truncating RAM at %pa-%pa to -%pa",
+				      &block_start, &block_end, &vmalloc_limit);
+				memblock_remove(vmalloc_limit, overlap_size);
+				block_end = vmalloc_limit;
+			}
 		}
-#endif
-		if (!bank->highmem) {
-			phys_addr_t bank_end = bank->start + bank->size;
 
-			if (bank_end > arm_lowmem_limit)
-				arm_lowmem_limit = bank_end;
+		if (!highmem) {
+			if (block_end > arm_lowmem_limit) {
+				if (reg->size > size_limit)
+					arm_lowmem_limit = vmalloc_limit;
+				else
+					arm_lowmem_limit = block_end;
+			}
 
 			/*
 			 * Find the first non-section-aligned page, and point
@@ -1144,35 +1131,15 @@ void __init sanity_check_meminfo(void)
 			 * occurs before any free memory is mapped.
 			 */
 			if (!memblock_limit) {
-				if (!IS_ALIGNED(bank->start, SECTION_SIZE))
-					memblock_limit = bank->start;
-				else if (!IS_ALIGNED(bank_end, SECTION_SIZE))
-					memblock_limit = bank_end;
+				if (!IS_ALIGNED(block_start, SECTION_SIZE))
+					memblock_limit = block_start;
+				else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+					memblock_limit = arm_lowmem_limit;
 			}
-		}
-		j++;
-	}
-#ifdef CONFIG_HIGHMEM
-	if (highmem) {
-		const char *reason = NULL;
 
-		if (cache_is_vipt_aliasing()) {
-			/*
-			 * Interactions between kmap and other mappings
-			 * make highmem support with aliasing VIPT caches
-			 * rather difficult.
-			 */
-			reason = "with VIPT aliasing cache";
-		}
-		if (reason) {
-			printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
-				reason);
-			while (j > 0 && meminfo.bank[j - 1].highmem)
-				j--;
 		}
 	}
-#endif
-	meminfo.nr_banks = j;
+
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
 	/*
@@ -1359,6 +1326,9 @@ static void __init kmap_init(void)
 #ifdef CONFIG_HIGHMEM
 	pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE),
 		PKMAP_BASE, _PAGE_KERNEL_TABLE);
+
+	fixmap_page_table = early_pte_alloc(pmd_off_k(FIXADDR_START),
+		FIXADDR_START, _PAGE_KERNEL_TABLE);
 #endif
 }
 
@@ -1461,7 +1431,7 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 	 * just complicate the code.
 	 */
 	flush_cache_louis();
-	dsb();
+	dsb(ishst);
 	isb();
 
 	/* remap level 1 table */
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 55764a7ef1f0..da1874f9f8cf 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -88,30 +88,35 @@ static unsigned long irbar_read(void)
 void __init sanity_check_meminfo_mpu(void)
 {
 	int i;
-	struct membank *bank = meminfo.bank;
 	phys_addr_t phys_offset = PHYS_OFFSET;
 	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
-
-	/* Initially only use memory continuous from PHYS_OFFSET */
-	if (bank_phys_start(&bank[0]) != phys_offset)
-		panic("First memory bank must be contiguous from PHYS_OFFSET");
-
-	/* Banks have already been sorted by start address */
-	for (i = 1; i < meminfo.nr_banks; i++) {
-		if (bank[i].start <= bank_phys_end(&bank[0]) &&
-		    bank_phys_end(&bank[i]) > bank_phys_end(&bank[0])) {
-			bank[0].size = bank_phys_end(&bank[i]) - bank[0].start;
+	struct memblock_region *reg;
+	bool first = true;
+	phys_addr_t mem_start;
+	phys_addr_t mem_end;
+
+	for_each_memblock(memory, reg) {
+		if (first) {
+			/*
+			 * Initially only use memory continuous from
+			 * PHYS_OFFSET */
+			if (reg->base != phys_offset)
+				panic("First memory bank must be contiguous from PHYS_OFFSET");
+
+			mem_start = reg->base;
+			mem_end = reg->base + reg->size;
+			specified_mem_size = reg->size;
+			first = false;
 		} else {
-			pr_notice("Ignoring RAM after 0x%.8lx. "
-			"First non-contiguous (ignored) bank start: 0x%.8lx\n",
-				(unsigned long)bank_phys_end(&bank[0]),
-				(unsigned long)bank_phys_start(&bank[i]));
-			break;
+			/*
+			 * memblock auto merges contiguous blocks, remove
+			 * all blocks afterwards
+			 */
+			pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
+				  &mem_start, &reg->base);
+			memblock_remove(reg->base, reg->size);
 		}
 	}
-	/* All contiguous banks are now merged in to the first bank */
-	meminfo.nr_banks = 1;
-	specified_mem_size = bank[0].size;
 
 	/*
 	 * MPU has curious alignment requirements: Size must be power of 2, and
@@ -128,23 +133,24 @@ void __init sanity_check_meminfo_mpu(void)
 	 */
 	aligned_region_size = (phys_offset - 1) ^ (phys_offset);
 	/* Find the max power-of-two sized region that fits inside our bank */
-	rounded_mem_size = (1 <<  __fls(bank[0].size)) - 1;
+	rounded_mem_size = (1 <<  __fls(specified_mem_size)) - 1;
 
 	/* The actual region size is the smaller of the two */
 	aligned_region_size = aligned_region_size < rounded_mem_size
 				? aligned_region_size + 1
 				: rounded_mem_size + 1;
 
-	if (aligned_region_size != specified_mem_size)
-		pr_warn("Truncating memory from 0x%.8lx to 0x%.8lx (MPU region constraints)",
-				(unsigned long)specified_mem_size,
-				(unsigned long)aligned_region_size);
+	if (aligned_region_size != specified_mem_size) {
+		pr_warn("Truncating memory from %pa to %pa (MPU region constraints)",
+				&specified_mem_size, &aligned_region_size);
+		memblock_remove(mem_start + aligned_region_size,
+				specified_mem_size - aligned_round_size);
+
+		mem_end = mem_start + aligned_region_size;
+	}
 
-	meminfo.bank[0].size = aligned_region_size;
-	pr_debug("MPU Region from 0x%.8lx size 0x%.8lx (end 0x%.8lx))\n",
-		(unsigned long)phys_offset,
-		(unsigned long)aligned_region_size,
-		(unsigned long)bank_phys_end(&bank[0]));
+	pr_debug("MPU Region from %pa size %pa (end %pa))\n",
+		&phys_offset, &aligned_region_size, &mem_end);
 
 }
 
@@ -292,7 +298,7 @@ void __init sanity_check_meminfo(void)
 {
 	phys_addr_t end;
 	sanity_check_meminfo_mpu();
-	end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
+	end = memblock_end_of_DRAM();
 	high_memory = __va(end - 1) + 1;
 }
 
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 01a719e18bb0..22e3ad63500c 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -64,6 +64,14 @@ ENTRY(cpu_v7_switch_mm)
 	mov	pc, lr
 ENDPROC(cpu_v7_switch_mm)
 
+#ifdef __ARMEB__
+#define rl r3
+#define rh r2
+#else
+#define rl r2
+#define rh r3
+#endif
+
 /*
  * cpu_v7_set_pte_ext(ptep, pte)
  *
@@ -73,13 +81,13 @@ ENDPROC(cpu_v7_switch_mm)
  */
 ENTRY(cpu_v7_set_pte_ext)
 #ifdef CONFIG_MMU
-	tst	r2, #L_PTE_VALID
+	tst	rl, #L_PTE_VALID
 	beq	1f
-	tst	r3, #1 << (57 - 32)		@ L_PTE_NONE
-	bicne	r2, #L_PTE_VALID
+	tst	rh, #1 << (57 - 32)		@ L_PTE_NONE
+	bicne	rl, #L_PTE_VALID
 	bne	1f
-	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
-	orreq	r2, #L_PTE_RDONLY
+	tst	rh, #1 << (55 - 32)		@ L_PTE_DIRTY
+	orreq	rl, #L_PTE_RDONLY
 1:	strd	r2, r3, [r0]
 	ALT_SMP(W(nop))
 	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 195731d3813b..3db2c2f04a30 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -169,9 +169,31 @@ ENDPROC(cpu_pj4b_do_idle)
 	globl_equ	cpu_pj4b_do_idle,  	cpu_v7_do_idle
 #endif
 	globl_equ	cpu_pj4b_dcache_clean_area,	cpu_v7_dcache_clean_area
-	globl_equ	cpu_pj4b_do_suspend,	cpu_v7_do_suspend
-	globl_equ	cpu_pj4b_do_resume,	cpu_v7_do_resume
-	globl_equ	cpu_pj4b_suspend_size,	cpu_v7_suspend_size
+#ifdef CONFIG_ARM_CPU_SUSPEND
+ENTRY(cpu_pj4b_do_suspend)
+	stmfd	sp!, {r6 - r10}
+	mrc	p15, 1, r6, c15, c1, 0  @ save CP15 - extra features
+	mrc	p15, 1, r7, c15, c2, 0	@ save CP15 - Aux Func Modes Ctrl 0
+	mrc	p15, 1, r8, c15, c1, 2	@ save CP15 - Aux Debug Modes Ctrl 2
+	mrc	p15, 1, r9, c15, c1, 1  @ save CP15 - Aux Debug Modes Ctrl 1
+	mrc	p15, 0, r10, c9, c14, 0  @ save CP15 - PMC
+	stmia	r0!, {r6 - r10}
+	ldmfd	sp!, {r6 - r10}
+	b cpu_v7_do_suspend
+ENDPROC(cpu_pj4b_do_suspend)
+
+ENTRY(cpu_pj4b_do_resume)
+	ldmia	r0!, {r6 - r10}
+	mcr	p15, 1, r6, c15, c1, 0  @ save CP15 - extra features
+	mcr	p15, 1, r7, c15, c2, 0	@ save CP15 - Aux Func Modes Ctrl 0
+	mcr	p15, 1, r8, c15, c1, 2	@ save CP15 - Aux Debug Modes Ctrl 2
+	mcr	p15, 1, r9, c15, c1, 1  @ save CP15 - Aux Debug Modes Ctrl 1
+	mcr	p15, 0, r10, c9, c14, 0  @ save CP15 - PMC
+	b cpu_v7_do_resume
+ENDPROC(cpu_pj4b_do_resume)
+#endif
+.globl	cpu_pj4b_suspend_size
+.equ	cpu_pj4b_suspend_size, 4 * 14
 
 #endif
 
@@ -194,6 +216,7 @@ __v7_cr7mp_setup:
 __v7_ca7mp_setup:
 __v7_ca12mp_setup:
 __v7_ca15mp_setup:
+__v7_ca17mp_setup:
 	mov	r10, #0
 1:
 #ifdef CONFIG_SMP
@@ -505,6 +528,16 @@ __v7_ca15mp_proc_info:
 	.size	__v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
 
 	/*
+	 * ARM Ltd. Cortex A17 processor.
+	 */
+	.type	__v7_ca17mp_proc_info, #object
+__v7_ca17mp_proc_info:
+	.long	0x410fc0e0
+	.long	0xff0ffff0
+	__v7_proc __v7_ca17mp_setup
+	.size	__v7_ca17mp_proc_info, . - __v7_ca17mp_proc_info
+
+	/*
 	 * Qualcomm Inc. Krait processors.
 	 */
 	.type	__krait_proc_info, #object
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 0c93588fcb91..1ca37c72f12f 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -123,6 +123,11 @@ __v7m_setup:
 	mov	pc, lr
 ENDPROC(__v7m_setup)
 
+	.align 2
+__v7m_setup_stack:
+	.space	4 * 8				@ 8 registers
+__v7m_setup_stack_top:
+
 	define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1
 
 	.section ".rodata"
@@ -152,6 +157,3 @@ __v7m_proc_info:
 	.long	nop_cache_fns		@ proc_info_list.cache
 	.size	__v7m_proc_info, . - __v7m_proc_info
 
-__v7m_setup_stack:
-	.space	4 * 8				@ 8 registers
-__v7m_setup_stack_top: