15 files changed, 299 insertions, 125 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 33c3f570aaa0..a0a2928ae4dd 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -398,7 +398,7 @@ config CPU_V6
 # ARMv6k
 config CPU_32v6K
         bool "Support ARM V6K processor extensions" if !SMP
-        depends on CPU_V6
+        depends on CPU_V6 || CPU_V7
         default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
         help
           Say Y here if your ARMv6 processor supports the 'K' extension.
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index d073b64ae87e..724ba3bce72c 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -885,8 +885,23 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
         if (ai_usermode & UM_SIGNAL)
                 force_sig(SIGBUS, current);
-        else
-                set_cr(cr_no_alignment);
+        else {
+                /*
+                 * We're about to disable the alignment trap and return to
+                 * user space.  But if an interrupt occurs before actually
+                 * reaching user space, then the IRQ vector entry code will
+                 * notice that we were still in kernel space and therefore
+                 * the alignment trap won't be re-enabled in that case as it
+                 * is presumed to be always on from kernel space.
+                 * Let's prevent that race by disabling interrupts here (they
+                 * are disabled on the way back to user space anyway in
+                 * entry-common.S) and disable the alignment trap only if
+                 * there is no work pending for this thread.
+                 */
+                raw_local_irq_disable();
+                if (!(current_thread_info()->flags & _TIF_WORK_MASK))
+                        set_cr(cr_no_alignment);
+        }
 
         return 0;
 }
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 86aa689ef1aa..99fa688dfadd 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -21,18 +21,22 @@
 #define D_CACHE_LINE_SIZE       32
 #define BTB_FLUSH_SIZE          8
 
-#ifdef CONFIG_ARM_ERRATA_411920
 /*
- * Invalidate the entire I cache (this code is a workaround for the ARM1136
- * erratum 411920 - Invalidate Instruction Cache operation can fail. This
- * erratum is present in 1136, 1156 and 1176. It does not affect the MPCore.
+ *      v6_flush_icache_all()
+ *
+ *      Flush the whole I-cache.
  *
- * Registers:
- *   r0 - set to 0
- *   r1 - corrupted
+ *      ARM1136 erratum 411920 - Invalidate Instruction Cache operation can fail.
+ *      This erratum is present in 1136, 1156 and 1176. It does not affect the
+ *      MPCore.
+ *
+ *      Registers:
+ *      r0 - set to 0
+ *      r1 - corrupted
  */
-ENTRY(v6_icache_inval_all)
+ENTRY(v6_flush_icache_all)
         mov     r0, #0
+#ifdef CONFIG_ARM_ERRATA_411920
         mrs     r1, cpsr
         cpsid   ifa                             @ disable interrupts
         mcr     p15, 0, r0, c7, c5, 0           @ invalidate entire I-cache
@@ -43,8 +47,11 @@ ENTRY(v6_icache_inval_all)
         .rept   11                              @ ARM Ltd recommends at least
         nop                                     @ 11 NOPs
         .endr
-        mov     pc, lr
+#else
+        mcr     p15, 0, r0, c7, c5, 0           @ invalidate I-cache
 #endif
+        mov     pc, lr
+ENDPROC(v6_flush_icache_all)
 
 /*
  *      v6_flush_cache_all()
@@ -60,7 +67,7 @@ ENTRY(v6_flush_kern_cache_all)
 #ifndef CONFIG_ARM_ERRATA_411920
         mcr     p15, 0, r0, c7, c5, 0           @ I+BTB cache invalidate
 #else
-        b       v6_icache_inval_all
+        b       v6_flush_icache_all
 #endif
 #else
         mcr     p15, 0, r0, c7, c15, 0          @ Cache clean+invalidate
@@ -138,7 +145,7 @@ ENTRY(v6_coherent_user_range)
 #ifndef CONFIG_ARM_ERRATA_411920
         mcr     p15, 0, r0, c7, c5, 0           @ I+BTB cache invalidate
 #else
-        b       v6_icache_inval_all
+        b       v6_flush_icache_all
 #endif
 #else
         mcr     p15, 0, r0, c7, c5, 6           @ invalidate BTB
@@ -312,6 +319,7 @@ ENDPROC(v6_dma_unmap_area)
 
         .type   v6_cache_fns, #object
 ENTRY(v6_cache_fns)
+        .long   v6_flush_icache_all
         .long   v6_flush_kern_cache_all
         .long   v6_flush_user_cache_all
         .long   v6_flush_user_cache_range
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 37c8157e116e..a3ebf7a4f49b 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -18,6 +18,21 @@
 #include "proc-macros.S"
 
 /*
+ *      v7_flush_icache_all()
+ *
+ *      Flush the whole I-cache.
+ *
+ *      Registers:
+ *      r0 - set to 0
+ */
+ENTRY(v7_flush_icache_all)
+        mov     r0, #0
+        ALT_SMP(mcr     p15, 0, r0, c7, c1, 0)          @ invalidate I-cache inner shareable
+        ALT_UP(mcr      p15, 0, r0, c7, c5, 0)          @ I+BTB cache invalidate
+        mov     pc, lr
+ENDPROC(v7_flush_icache_all)
+
+/*
  *      v7_flush_dcache_all()
  *
  *      Flush the whole D-cache.
@@ -91,11 +106,8 @@ ENTRY(v7_flush_kern_cache_all)
  THUMB( stmfd   sp!, {r4-r7, r9-r11, lr}        )
         bl      v7_flush_dcache_all
         mov     r0, #0
-#ifdef CONFIG_SMP
-        mcr     p15, 0, r0, c7, c1, 0           @ invalidate I-cache inner shareable
-#else
-        mcr     p15, 0, r0, c7, c5, 0           @ I+BTB cache invalidate
-#endif
+        ALT_SMP(mcr     p15, 0, r0, c7, c1, 0)  @ invalidate I-cache inner shareable
+        ALT_UP(mcr      p15, 0, r0, c7, c5, 0)  @ I+BTB cache invalidate
  ARM(   ldmfd   sp!, {r4-r5, r7, r9-r11, lr}    )
  THUMB( ldmfd   sp!, {r4-r7, r9-r11, lr}        )
         mov     pc, lr
@@ -171,11 +183,8 @@ ENTRY(v7_coherent_user_range)
         cmp     r0, r1
         blo     1b
         mov     r0, #0
-#ifdef CONFIG_SMP
-        mcr     p15, 0, r0, c7, c1, 6           @ invalidate BTB Inner Shareable
-#else
-        mcr     p15, 0, r0, c7, c5, 6           @ invalidate BTB
-#endif
+        ALT_SMP(mcr     p15, 0, r0, c7, c1, 6)  @ invalidate BTB Inner Shareable
+        ALT_UP(mcr      p15, 0, r0, c7, c5, 6)  @ invalidate BTB
         dsb
         isb
         mov     pc, lr
@@ -309,6 +318,7 @@ ENDPROC(v7_dma_unmap_area)
 
         .type   v7_cache_fns, #object
 ENTRY(v7_cache_fns)
+        .long   v7_flush_icache_all
         .long   v7_flush_kern_cache_all
         .long   v7_flush_user_cache_all
         .long   v7_flush_user_cache_range
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index 598c51ad5071..b8061519ce77 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -73,7 +73,7 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from,
 {
         void *kto = kmap_atomic(to, KM_USER1);
 
-        if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+        if (!test_and_set_bit(PG_dcache_clean, &from->flags))
                 __flush_dcache_page(page_mapping(from), from);
 
         spin_lock(&minicache_lock);
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index f55fa1044f72..bdba6c65c901 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -79,7 +79,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to,
         unsigned int offset = CACHE_COLOUR(vaddr);
         unsigned long kfrom, kto;
 
-        if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+        if (!test_and_set_bit(PG_dcache_clean, &from->flags))
                 __flush_dcache_page(page_mapping(from), from);
 
         /* FIXME: not highmem safe */
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 9920c0ae2096..649bbcd325bf 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -95,7 +95,7 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
 {
         void *kto = kmap_atomic(to, KM_USER1);
 
-        if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+        if (!test_and_set_bit(PG_dcache_clean, &from->flags))
                 __flush_dcache_page(page_mapping(from), from);
 
         spin_lock(&minicache_lock);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c704eed63c5d..e4dd0646e859 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -229,6 +229,8 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
                         }
                 } while (size -= PAGE_SIZE);
 
+                dsb();
+
                 return (void *)c->vm_start;
         }
         return NULL;
@@ -521,6 +523,12 @@ void ___dma_page_dev_to_cpu(struct page *page, unsigned long off,
                 outer_inv_range(paddr, paddr + size);
 
         dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+
+        /*
+         * Mark the D-cache clean for this page to avoid extra flushing.
+         */
+        if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
+                set_bit(PG_dcache_clean, &page->flags);
 }
 EXPORT_SYMBOL(___dma_page_dev_to_cpu);
 
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 9b906dec1ca1..8440d952ba6d 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -28,6 +28,7 @@
 
 static unsigned long shared_pte_mask = L_PTE_MT_BUFFERABLE;
 
+#if __LINUX_ARM_ARCH__ < 6
 /*
  * We take the easy way out of this problem - we make the
  * PTE uncacheable.  However, we leave the write buffer on.
@@ -141,7 +142,7 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
  * a page table, or changing an existing PTE.  Basically, there are two
  * things that we need to take care of:
  *
- *  1. If PG_dcache_dirty is set for the page, we need to ensure
+ *  1. If PG_dcache_clean is not set for the page, we need to ensure
  *     that any cache entries for the kernels virtual memory
  *     range are written back to the page.
  *  2. If we have multiple shared mappings of the same space in
@@ -168,10 +169,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
                 return;
 
         mapping = page_mapping(page);
-#ifndef CONFIG_SMP
-        if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
+        if (!test_and_set_bit(PG_dcache_clean, &page->flags))
                 __flush_dcache_page(mapping, page);
-#endif
         if (mapping) {
                 if (cache_is_vivt())
                         make_coherent(mapping, vma, addr, ptep, pfn);
@@ -179,6 +178,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
                         __flush_icache_all();
         }
 }
+#endif  /* __LINUX_ARM_ARCH__ < 6 */
 
 /*
  * Check whether the write buffer has physical address aliasing
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index c6844cb9b508..391ffae75098 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -17,6 +17,7 @@
 #include <asm/smp_plat.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
+#include <asm/smp_plat.h>
 
 #include "mm.h"
 
@@ -39,6 +40,18 @@ static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
             : "cc");
 }
 
+static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned long len)
+{
+        unsigned long colour = CACHE_COLOUR(vaddr);
+        unsigned long offset = vaddr & (PAGE_SIZE - 1);
+        unsigned long to;
+
+        set_pte_ext(TOP_PTE(ALIAS_FLUSH_START) + colour, pfn_pte(pfn, PAGE_KERNEL), 0);
+        to = ALIAS_FLUSH_START + (colour << PAGE_SHIFT) + offset;
+        flush_tlb_kernel_page(to);
+        flush_icache_range(to, to + len);
+}
+
 void flush_cache_mm(struct mm_struct *mm)
 {
         if (cache_is_vivt()) {
@@ -89,16 +102,16 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig
         if (vma->vm_flags & VM_EXEC && icache_is_vivt_asid_tagged())
                 __flush_icache_all();
 }
+
 #else
-#define flush_pfn_alias(pfn,vaddr)      do { } while (0)
+#define flush_pfn_alias(pfn,vaddr)              do { } while (0)
+#define flush_icache_alias(pfn,vaddr,len)       do { } while (0)
 #endif
 
-#ifdef CONFIG_SMP
 static void flush_ptrace_access_other(void *args)
 {
         __flush_icache_all();
 }
-#endif
 
 static
 void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
@@ -118,15 +131,16 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
                 return;
         }
 
-        /* VIPT non-aliasing cache */
+        /* VIPT non-aliasing D-cache */
         if (vma->vm_flags & VM_EXEC) {
                 unsigned long addr = (unsigned long)kaddr;
-                __cpuc_coherent_kern_range(addr, addr + len);
-#ifdef CONFIG_SMP
+                if (icache_is_vipt_aliasing())
+                        flush_icache_alias(page_to_pfn(page), uaddr, len);
+                else
+                        __cpuc_coherent_kern_range(addr, addr + len);
                 if (cache_ops_need_broadcast())
                         smp_call_function(flush_ptrace_access_other,
                                           NULL, 1);
-#endif
         }
 }
 
@@ -215,6 +229,36 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p
         flush_dcache_mmap_unlock(mapping);
 }
 
+#if __LINUX_ARM_ARCH__ >= 6
+void __sync_icache_dcache(pte_t pteval)
+{
+        unsigned long pfn;
+        struct page *page;
+        struct address_space *mapping;
+
+        if (!pte_present_user(pteval))
+                return;
+        if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
+                /* only flush non-aliasing VIPT caches for exec mappings */
+                return;
+        pfn = pte_pfn(pteval);
+        if (!pfn_valid(pfn))
+                return;
+
+        page = pfn_to_page(pfn);
+        if (cache_is_vipt_aliasing())
+                mapping = page_mapping(page);
+        else
+                mapping = NULL;
+
+        if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+                __flush_dcache_page(mapping, page);
+        /* pte_exec() already checked above for non-aliasing VIPT cache */
+        if (cache_is_vipt_nonaliasing() || pte_exec(pteval))
+                __flush_icache_all();
+}
+#endif
+
 /*
  * Ensure cache coherency between kernel mapping and userspace mapping
  * of this page.
@@ -246,17 +290,16 @@ void flush_dcache_page(struct page *page)
 
         mapping = page_mapping(page);
 
-#ifndef CONFIG_SMP
-        if (!PageHighMem(page) && mapping && !mapping_mapped(mapping))
-                set_bit(PG_dcache_dirty, &page->flags);
-        else
-#endif
-        {
+        if (!cache_ops_need_broadcast() &&
+            mapping && !mapping_mapped(mapping))
+                clear_bit(PG_dcache_clean, &page->flags);
+        else {
                 __flush_dcache_page(mapping, page);
                 if (mapping && cache_is_vivt())
                         __flush_dcache_aliases(mapping, page);
                 else if (mapping)
                         __flush_icache_all();
+                set_bit(PG_dcache_clean, &page->flags);
         }
 }
 EXPORT_SYMBOL(flush_dcache_page);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 7185b00650fe..36c4553ffcce 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -277,7 +277,7 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 
         /* Register the kernel text, kernel data and initrd with memblock. */
 #ifdef CONFIG_XIP_KERNEL
-        memblock_reserve(__pa(_data), _end - _data);
+        memblock_reserve(__pa(_sdata), _end - _sdata);
 #else
         memblock_reserve(__pa(_stext), _end - _stext);
 #endif
@@ -545,7 +545,7 @@ void __init mem_init(void)
 
                         MLK_ROUNDUP(__init_begin, __init_end),
                         MLK_ROUNDUP(_text, _etext),
-                        MLK_ROUNDUP(_data, _edata));
+                        MLK_ROUNDUP(_sdata, _edata));
 
 #undef MLK
 #undef MLM
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6e1c4f6a2b3f..e2335811c02e 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/fs.h>
 
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -246,6 +247,9 @@ static struct mem_type mem_types[] = {
                 .domain    = DOMAIN_USER,
         },
         [MT_MEMORY] = {
+                .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+                                L_PTE_USER | L_PTE_EXEC,
+                .prot_l1   = PMD_TYPE_TABLE,
                 .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
                 .domain    = DOMAIN_KERNEL,
         },
@@ -254,6 +258,9 @@ static struct mem_type mem_types[] = {
                 .domain    = DOMAIN_KERNEL,
         },
         [MT_MEMORY_NONCACHED] = {
+                .prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+                                L_PTE_USER | L_PTE_EXEC | L_PTE_MT_BUFFERABLE,
+                .prot_l1   = PMD_TYPE_TABLE,
                 .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
                 .domain    = DOMAIN_KERNEL,
         },
@@ -303,9 +310,8 @@ static void __init build_mem_type_table(void)
                         cachepolicy = CPOLICY_WRITEBACK;
                 ecc_mask = 0;
         }
-#ifdef CONFIG_SMP
-        cachepolicy = CPOLICY_WRITEALLOC;
-#endif
+        if (is_smp())
+                cachepolicy = CPOLICY_WRITEALLOC;
 
         /*
          * Strip out features not present on earlier architectures.
@@ -399,21 +405,22 @@ static void __init build_mem_type_table(void)
         cp = &cache_policies[cachepolicy];
         vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
 
-#ifndef CONFIG_SMP
         /*
          * Only use write-through for non-SMP systems
          */
-        if (cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH)
+        if (!is_smp() && cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH)
                 vecs_pgprot = cache_policies[CPOLICY_WRITETHROUGH].pte;
-#endif
 
         /*
          * Enable CPU-specific coherency if supported.
          * (Only available on XSC3 at the moment.)
          */
-        if (arch_is_coherent() && cpu_is_xsc3())
+        if (arch_is_coherent() && cpu_is_xsc3()) {
                 mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-
+                mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+                mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+                mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+        }
         /*
          * ARMv6 and above have extended page tables.
          */
@@ -426,20 +433,23 @@ static void __init build_mem_type_table(void)
                 mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
                 mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 
-#ifdef CONFIG_SMP
-                /*
-                 * Mark memory with the "shared" attribute for SMP systems
-                 */
-                user_pgprot |= L_PTE_SHARED;
-                kern_pgprot |= L_PTE_SHARED;
-                vecs_pgprot |= L_PTE_SHARED;
-                mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
-                mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
-                mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
-                mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
-                mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-                mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
-#endif
+                if (is_smp()) {
+                        /*
+                         * Mark memory with the "shared" attribute
+                         * for SMP systems
+                         */
+                        user_pgprot |= L_PTE_SHARED;
+                        kern_pgprot |= L_PTE_SHARED;
+                        vecs_pgprot |= L_PTE_SHARED;
+                        mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
+                        mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
+                        mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
+                        mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
+                        mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+                        mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+                        mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+                        mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+                }
         }
 
         /*
@@ -475,6 +485,8 @@ static void __init build_mem_type_table(void)
         mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
         mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
         mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
+        mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+        mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
         mem_types[MT_ROM].prot_sect |= cp->pmd;
 
         switch (cp->pmd) {
@@ -498,6 +510,19 @@ static void __init build_mem_type_table(void)
         }
 }
 
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+                              unsigned long size, pgprot_t vma_prot)
+{
+        if (!pfn_valid(pfn))
+                return pgprot_noncached(vma_prot);
+        else if (file->f_flags & O_SYNC)
+                return pgprot_writecombine(vma_prot);
+        return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
+#endif
+
 #define vectors_base()  (vectors_high() ? 0xffff0000 : 0)
 
 static void __init *early_alloc(unsigned long sz)
@@ -802,8 +827,7 @@ static void __init sanity_check_meminfo(void)
                          * rather difficult.
                          */
                         reason = "with VIPT aliasing cache";
-#ifdef CONFIG_SMP
-                } else if (tlb_ops_need_broadcast()) {
+                } else if (is_smp() && tlb_ops_need_broadcast()) {
                         /*
                          * kmap_high needs to occasionally flush TLB entries,
                          * however, if the TLB entries need to be broadcast
@@ -813,7 +837,6 @@ static void __init sanity_check_meminfo(void)
                          *   (must not be called with irqs off)
                          */
                         reason = "without hardware TLB ops broadcasting";
-#endif
                 }
                 if (reason) {
                         printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 22aac8515196..b95662dedb64 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -30,13 +30,10 @@
 #define TTB_RGN_WT      (2 << 3)
 #define TTB_RGN_WB      (3 << 3)
 
-#ifndef CONFIG_SMP
-#define TTB_FLAGS       TTB_RGN_WBWA
-#define PMD_FLAGS       PMD_SECT_WB
-#else
-#define TTB_FLAGS       TTB_RGN_WBWA|TTB_S
-#define PMD_FLAGS       PMD_SECT_WBWA|PMD_SECT_S
-#endif
+#define TTB_FLAGS_UP    TTB_RGN_WBWA
+#define PMD_FLAGS_UP    PMD_SECT_WB
+#define TTB_FLAGS_SMP   TTB_RGN_WBWA|TTB_S
+#define PMD_FLAGS_SMP   PMD_SECT_WBWA|PMD_SECT_S
 
 ENTRY(cpu_v6_proc_init)
         mov     pc, lr
@@ -97,7 +94,8 @@ ENTRY(cpu_v6_switch_mm)
 #ifdef CONFIG_MMU
         mov     r2, #0
         ldr     r1, [r1, #MM_CONTEXT_ID]        @ get mm->context.id
-        orr     r0, r0, #TTB_FLAGS
+        ALT_SMP(orr     r0, r0, #TTB_FLAGS_SMP)
+        ALT_UP(orr      r0, r0, #TTB_FLAGS_UP)
         mcr     p15, 0, r2, c7, c5, 6           @ flush BTAC/BTB
         mcr     p15, 0, r2, c7, c10, 4          @ drain write buffer
         mcr     p15, 0, r0, c2, c0, 0           @ set TTB 0
@@ -156,9 +154,11 @@ cpu_pj4_name:
  */
 __v6_setup:
 #ifdef CONFIG_SMP
-        mrc     p15, 0, r0, c1, c0, 1           @ Enable SMP/nAMP mode
+        ALT_SMP(mrc     p15, 0, r0, c1, c0, 1)  @ Enable SMP/nAMP mode
+        ALT_UP(nop)
         orr     r0, r0, #0x20
-        mcr     p15, 0, r0, c1, c0, 1
+        ALT_SMP(mcr     p15, 0, r0, c1, c0, 1)
+        ALT_UP(nop)
 #endif
 
         mov     r0, #0
@@ -169,7 +169,8 @@ __v6_setup:
 #ifdef CONFIG_MMU
         mcr     p15, 0, r0, c8, c7, 0           @ invalidate I + D TLBs
         mcr     p15, 0, r0, c2, c0, 2           @ TTB control register
-        orr     r4, r4, #TTB_FLAGS
+        ALT_SMP(orr     r4, r4, #TTB_FLAGS_SMP)
+        ALT_UP(orr      r4, r4, #TTB_FLAGS_UP)
         mcr     p15, 0, r4, c2, c0, 1           @ load TTB1
 #endif /* CONFIG_MMU */
         adr     r5, v6_crval
@@ -225,10 +226,16 @@ cpu_elf_name:
 __v6_proc_info:
         .long   0x0007b000
         .long   0x0007f000
-        .long   PMD_TYPE_SECT | \
+        ALT_SMP(.long \
+                PMD_TYPE_SECT | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ | \
+                PMD_FLAGS_SMP)
+        ALT_UP(.long \
+                PMD_TYPE_SECT | \
                 PMD_SECT_AP_WRITE | \
                 PMD_SECT_AP_READ | \
-                PMD_FLAGS
+                PMD_FLAGS_UP)
         .long   PMD_TYPE_SECT | \
                 PMD_SECT_XN | \
                 PMD_SECT_AP_WRITE | \
@@ -249,10 +256,16 @@ __v6_proc_info:
 __pj4_v6_proc_info:
         .long   0x560f5810
         .long   0xff0ffff0
-        .long   PMD_TYPE_SECT | \
+        ALT_SMP(.long \
+                PMD_TYPE_SECT | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ | \
+                PMD_FLAGS_SMP)
+        ALT_UP(.long \
+                PMD_TYPE_SECT | \
                 PMD_SECT_AP_WRITE | \
                 PMD_SECT_AP_READ | \
-                PMD_FLAGS
+                PMD_FLAGS_UP)
         .long   PMD_TYPE_SECT | \
                 PMD_SECT_XN | \
                 PMD_SECT_AP_WRITE | \
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6a8506d99ee9..df422fee1cb6 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -30,15 +30,13 @@
 #define TTB_IRGN_WT     ((1 << 0) | (0 << 6))
 #define TTB_IRGN_WB     ((1 << 0) | (1 << 6))
 
-#ifndef CONFIG_SMP
 /* PTWs cacheable, inner WB not shareable, outer WB not shareable */
-#define TTB_FLAGS       TTB_IRGN_WB|TTB_RGN_OC_WB
-#define PMD_FLAGS       PMD_SECT_WB
-#else
+#define TTB_FLAGS_UP    TTB_IRGN_WB|TTB_RGN_OC_WB
+#define PMD_FLAGS_UP    PMD_SECT_WB
+
 /* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
-#define TTB_FLAGS       TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
-#define PMD_FLAGS       PMD_SECT_WBWA|PMD_SECT_S
-#endif
+#define TTB_FLAGS_SMP   TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
+#define PMD_FLAGS_SMP   PMD_SECT_WBWA|PMD_SECT_S
 
 ENTRY(cpu_v7_proc_init)
         mov     pc, lr
@@ -105,7 +103,8 @@ ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
         mov     r2, #0
         ldr     r1, [r1, #MM_CONTEXT_ID]        @ get mm->context.id
-        orr     r0, r0, #TTB_FLAGS
+        ALT_SMP(orr     r0, r0, #TTB_FLAGS_SMP)
+        ALT_UP(orr      r0, r0, #TTB_FLAGS_UP)
 #ifdef CONFIG_ARM_ERRATA_430973
         mcr     p15, 0, r2, c7, c5, 6           @ flush BTAC/BTB
 #endif
@@ -186,13 +185,15 @@ cpu_v7_name:
  *      It is assumed that:
  *      - cache type register is implemented
  */
-__v7_setup:
+__v7_ca9mp_setup:
 #ifdef CONFIG_SMP
-        mrc     p15, 0, r0, c1, c0, 1
+        ALT_SMP(mrc     p15, 0, r0, c1, c0, 1)
+        ALT_UP(mov      r0, #(1 << 6))          @ fake it for UP
         tst     r0, #(1 << 6)                   @ SMP/nAMP mode enabled?
         orreq   r0, r0, #(1 << 6) | (1 << 0)    @ Enable SMP/nAMP mode and
         mcreq   p15, 0, r0, c1, c0, 1           @ TLB ops broadcasting
 #endif
+__v7_setup:
         adr     r12, __v7_setup_stack           @ the local stack
         stmia   r12, {r0-r5, r7, r9, r11, lr}
         bl      v7_flush_dcache_all
@@ -201,11 +202,16 @@ __v7_setup:
         mrc     p15, 0, r0, c0, c0, 0           @ read main ID register
         and     r10, r0, #0xff000000            @ ARM?
         teq     r10, #0x41000000
-        bne     2f
+        bne     3f
         and     r5, r0, #0x00f00000             @ variant
         and     r6, r0, #0x0000000f             @ revision
-        orr     r0, r6, r5, lsr #20-4           @ combine variant and revision
+        orr     r6, r6, r5, lsr #20-4           @ combine variant and revision
+        ubfx    r0, r0, #4, #12                 @ primary part number
 
+        /* Cortex-A8 Errata */
+        ldr     r10, =0x00000c08                @ Cortex-A8 primary part number
+        teq     r0, r10
+        bne     2f
 #ifdef CONFIG_ARM_ERRATA_430973
         teq     r5, #0x00100000                 @ only present in r1p*
         mrceq   p15, 0, r10, c1, c0, 1          @ read aux control register
@@ -213,21 +219,42 @@ __v7_setup:
         mcreq   p15, 0, r10, c1, c0, 1          @ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_458693
-        teq     r0, #0x20                       @ only present in r2p0
+        teq     r6, #0x20                       @ only present in r2p0
         mrceq   p15, 0, r10, c1, c0, 1          @ read aux control register
         orreq   r10, r10, #(1 << 5)             @ set L1NEON to 1
         orreq   r10, r10, #(1 << 9)             @ set PLDNOP to 1
         mcreq   p15, 0, r10, c1, c0, 1          @ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_460075
-        teq     r0, #0x20                       @ only present in r2p0
+        teq     r6, #0x20                       @ only present in r2p0
         mrceq   p15, 1, r10, c9, c0, 2          @ read L2 cache aux ctrl register
         tsteq   r10, #1 << 22
         orreq   r10, r10, #(1 << 22)            @ set the Write Allocate disable bit
         mcreq   p15, 1, r10, c9, c0, 2          @ write the L2 cache aux ctrl register
 #endif
+        b       3f
+
+        /* Cortex-A9 Errata */
+2:      ldr     r10, =0x00000c09                @ Cortex-A9 primary part number
+        teq     r0, r10
+        bne     3f
+#ifdef CONFIG_ARM_ERRATA_742230
+        cmp     r6, #0x22                       @ only present up to r2p2
+        mrcle   p15, 0, r10, c15, c0, 1         @ read diagnostic register
+        orrle   r10, r10, #1 << 4               @ set bit #4
+        mcrle   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_742231
+        teq     r6, #0x20                       @ present in r2p0
+        teqne   r6, #0x21                       @ present in r2p1
+        teqne   r6, #0x22                       @ present in r2p2
+        mrceq   p15, 0, r10, c15, c0, 1         @ read diagnostic register
+        orreq   r10, r10, #1 << 12              @ set bit #12
+        orreq   r10, r10, #1 << 22              @ set bit #22
+        mcreq   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+#endif
 
-2:      mov     r10, #0
+3:      mov     r10, #0
 #ifdef HARVARD_CACHE
         mcr     p15, 0, r10, c7, c5, 0          @ I+BTB cache invalidate
 #endif
@@ -235,7 +262,8 @@ __v7_setup:
 #ifdef CONFIG_MMU
         mcr     p15, 0, r10, c8, c7, 0          @ invalidate I + D TLBs
         mcr     p15, 0, r10, c2, c0, 2          @ TTB control register
-        orr     r4, r4, #TTB_FLAGS
+        ALT_SMP(orr     r4, r4, #TTB_FLAGS_SMP)
+        ALT_UP(orr      r4, r4, #TTB_FLAGS_UP)
         mcr     p15, 0, r4, c2, c0, 1           @ load TTB1
         mov     r10, #0x1f                      @ domains 0, 1 = manager
         mcr     p15, 0, r10, c3, c0, 0          @ load domain access register
@@ -323,6 +351,35 @@ cpu_elf_name:
 
         .section ".proc.info.init", #alloc, #execinstr
 
+        .type   __v7_ca9mp_proc_info, #object
+__v7_ca9mp_proc_info:
+        .long   0x410fc090              @ Required ID value
+        .long   0xff0ffff0              @ Mask for ID
+        ALT_SMP(.long \
+                PMD_TYPE_SECT | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ | \
+                PMD_FLAGS_SMP)
+        ALT_UP(.long \
+                PMD_TYPE_SECT | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ | \
+                PMD_FLAGS_UP)
+        .long   PMD_TYPE_SECT | \
+                PMD_SECT_XN | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ
+        b       __v7_ca9mp_setup
+        .long   cpu_arch_name
+        .long   cpu_elf_name
+        .long   HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+        .long   cpu_v7_name
+        .long   v7_processor_functions
+        .long   v7wbi_tlb_fns
+        .long   v6_user_fns
+        .long   v7_cache_fns
+        .size   __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+
         /*
          * Match any ARMv7 processor core.
          */
@@ -330,10 +387,16 @@ cpu_elf_name:
 __v7_proc_info:
         .long   0x000f0000              @ Required ID value
         .long   0x000f0000              @ Mask for ID
-        .long   PMD_TYPE_SECT | \
+        ALT_SMP(.long \
+                PMD_TYPE_SECT | \
+                PMD_SECT_AP_WRITE | \
+                PMD_SECT_AP_READ | \
+                PMD_FLAGS_SMP)
+        ALT_UP(.long \
+                PMD_TYPE_SECT | \
                 PMD_SECT_AP_WRITE | \
                 PMD_SECT_AP_READ | \
-                PMD_FLAGS
+                PMD_FLAGS_UP)
         .long   PMD_TYPE_SECT | \
                 PMD_SECT_XN | \
                 PMD_SECT_AP_WRITE | \
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index f3f288a9546d..53cd5b454673 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -13,6 +13,7 @@
  */
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/tlbflush.h>
@@ -41,20 +42,15 @@ ENTRY(v7wbi_flush_user_tlb_range)
         orr     r0, r3, r0, lsl #PAGE_SHIFT     @ Create initial MVA
         mov     r1, r1, lsl #PAGE_SHIFT
 1:
-#ifdef CONFIG_SMP
-        mcr     p15, 0, r0, c8, c3, 1           @ TLB invalidate U MVA (shareable) 
-#else
-        mcr     p15, 0, r0, c8, c7, 1           @ TLB invalidate U MVA
-#endif
+        ALT_SMP(mcr     p15, 0, r0, c8, c3, 1)  @ TLB invalidate U MVA (shareable)
+        ALT_UP(mcr      p15, 0, r0, c8, c7, 1)  @ TLB invalidate U MVA
+
         add     r0, r0, #PAGE_SZ
         cmp     r0, r1
         blo     1b
         mov     ip, #0
-#ifdef CONFIG_SMP
-        mcr     p15, 0, ip, c7, c1, 6           @ flush BTAC/BTB Inner Shareable
-#else
-        mcr     p15, 0, ip, c7, c5, 6           @ flush BTAC/BTB
-#endif
+        ALT_SMP(mcr     p15, 0, ip, c7, c1, 6)  @ flush BTAC/BTB Inner Shareable
+        ALT_UP(mcr      p15, 0, ip, c7, c5, 6)  @ flush BTAC/BTB
         dsb
         mov     pc, lr
 ENDPROC(v7wbi_flush_user_tlb_range)
@@ -74,20 +70,14 @@ ENTRY(v7wbi_flush_kern_tlb_range)
         mov     r0, r0, lsl #PAGE_SHIFT
         mov     r1, r1, lsl #PAGE_SHIFT
 1:
-#ifdef CONFIG_SMP
-        mcr     p15, 0, r0, c8, c3, 1           @ TLB invalidate U MVA (shareable)
-#else
-        mcr     p15, 0, r0, c8, c7, 1           @ TLB invalidate U MVA
-#endif
+        ALT_SMP(mcr     p15, 0, r0, c8, c3, 1)  @ TLB invalidate U MVA (shareable)
+        ALT_UP(mcr      p15, 0, r0, c8, c7, 1)  @ TLB invalidate U MVA
         add     r0, r0, #PAGE_SZ
         cmp     r0, r1
         blo     1b
         mov     r2, #0
-#ifdef CONFIG_SMP
-        mcr     p15, 0, r2, c7, c1, 6           @ flush BTAC/BTB Inner Shareable
-#else
-        mcr     p15, 0, r2, c7, c5, 6           @ flush BTAC/BTB
-#endif
+        ALT_SMP(mcr     p15, 0, r2, c7, c1, 6)  @ flush BTAC/BTB Inner Shareable
+        ALT_UP(mcr      p15, 0, r2, c7, c5, 6)  @ flush BTAC/BTB
         dsb
         isb
         mov     pc, lr
@@ -99,5 +89,6 @@ ENDPROC(v7wbi_flush_kern_tlb_range)
 ENTRY(v7wbi_tlb_fns)
         .long   v7wbi_flush_user_tlb_range
         .long   v7wbi_flush_kern_tlb_range
-        .long   v7wbi_tlb_flags
+        ALT_SMP(.long   v7wbi_tlb_flags_smp)
+        ALT_UP(.long    v7wbi_tlb_flags_up)
         .size   v7wbi_tlb_fns, . - v7wbi_tlb_fns