42 files changed, 673 insertions, 284 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 4414a01e1e8a..89266382b536 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -382,9 +382,15 @@ config CPU_FEROCEON_OLD_ID
           for which the CPU ID is equal to the ARM926 ID.
           Relevant for Feroceon-1850 and early Feroceon-2850.
 
+# Marvell PJ4
+config CPU_PJ4
+        bool
+        select CPU_V7
+        select ARM_THUMBEE
+
 # ARMv6
 config CPU_V6
-        bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX || ARCH_DOVE
+        bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
         select CPU_32v6
         select CPU_ABRT_EV6
         select CPU_PABRT_V6
@@ -396,21 +402,23 @@ config CPU_V6
         select CPU_TLB_V6 if MMU
 
 # ARMv6k
-config CPU_32v6K
-        bool "Support ARM V6K processor extensions" if !SMP
-        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.
-          This enables the kernel to use some instructions not present
-          on previous processors, and as such a kernel build with this
-          enabled will not boot on processors with do not support these
-          instructions.
+config CPU_V6K
+        bool "Support ARM V6K processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
+        select CPU_32v6
+        select CPU_32v6K
+        select CPU_ABRT_EV6
+        select CPU_PABRT_V6
+        select CPU_CACHE_V6
+        select CPU_CACHE_VIPT
+        select CPU_CP15_MMU
+        select CPU_HAS_ASID if MMU
+        select CPU_COPY_V6 if MMU
+        select CPU_TLB_V6 if MMU
 
 # ARMv7
 config CPU_V7
         bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
-        select CPU_32v6K if !ARCH_OMAP2
+        select CPU_32v6K
         select CPU_32v7
         select CPU_ABRT_EV7
         select CPU_PABRT_V7
@@ -427,25 +435,33 @@ config CPU_32v3
         bool
         select TLS_REG_EMUL if SMP || !MMU
         select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+        select CPU_USE_DOMAINS if MMU
 
 config CPU_32v4
         bool
         select TLS_REG_EMUL if SMP || !MMU
         select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+        select CPU_USE_DOMAINS if MMU
 
 config CPU_32v4T
         bool
         select TLS_REG_EMUL if SMP || !MMU
         select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+        select CPU_USE_DOMAINS if MMU
 
 config CPU_32v5
         bool
         select TLS_REG_EMUL if SMP || !MMU
         select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+        select CPU_USE_DOMAINS if MMU
 
 config CPU_32v6
         bool
         select TLS_REG_EMUL if !CPU_32v6K && !MMU
+        select CPU_USE_DOMAINS if CPU_V6 && MMU
+
+config CPU_32v6K
+        bool
 
 config CPU_32v7
         bool
@@ -599,6 +615,12 @@ config CPU_CP15_MPU
         help
           Processor has the CP15 register, which has MPU related registers.
 
+config CPU_USE_DOMAINS
+        bool
+        help
+          This option enables or disables the use of domain switching
+          via the set_fs() function.
+
 #
 # CPU supports 36-bit I/O
 #
@@ -609,7 +631,7 @@ comment "Processor Features"
 
 config ARM_THUMB
         bool "Support Thumb user binaries"
-        depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V7 || CPU_FEROCEON
+        depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
         default y
         help
           Say Y if you want to include kernel support for running user space
@@ -628,6 +650,33 @@ config ARM_THUMBEE
           Say Y here if you have a CPU with the ThumbEE extension and code to
           make use of it. Say N for code that can run on CPUs without ThumbEE.
 
+config SWP_EMULATE
+        bool "Emulate SWP/SWPB instructions"
+        depends on !CPU_USE_DOMAINS && CPU_V7
+        select HAVE_PROC_CPU if PROC_FS
+        default y if SMP
+        help
+          ARMv6 architecture deprecates use of the SWP/SWPB instructions.
+          ARMv7 multiprocessing extensions introduce the ability to disable
+          these instructions, triggering an undefined instruction exception
+          when executed. Say Y here to enable software emulation of these
+          instructions for userspace (not kernel) using LDREX/STREX.
+          Also creates /proc/cpu/swp_emulation for statistics.
+
+          In some older versions of glibc [<=2.8] SWP is used during futex
+          trylock() operations with the assumption that the code will not
+          be preempted. This invalid assumption may be more likely to fail
+          with SWP emulation enabled, leading to deadlock of the user
+          application.
+
+          NOTE: when accessing uncached shared regions, LDREX/STREX rely
+          on an external transaction monitoring block called a global
+          monitor to maintain update atomicity. If your system does not
+          implement a global monitor, this option can cause programs that
+          perform SWP operations to uncached memory to deadlock.
+
+          If unsure, say Y.
+
 config CPU_BIG_ENDIAN
         bool "Build big-endian kernel"
         depends on ARCH_SUPPORTS_BIG_ENDIAN
@@ -640,7 +689,7 @@ config CPU_BIG_ENDIAN
 config CPU_ENDIAN_BE8
         bool
         depends on CPU_BIG_ENDIAN
-        default CPU_V6 || CPU_V7
+        default CPU_V6 || CPU_V6K || CPU_V7
         help
           Support for the BE-8 (big-endian) mode on ARMv6 and ARMv7 processors.
 
@@ -706,7 +755,7 @@ config CPU_CACHE_ROUND_ROBIN
 
 config CPU_BPREDICT_DISABLE
         bool "Disable branch prediction"
-        depends on CPU_ARM1020 || CPU_V6 || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526
+        depends on CPU_ARM1020 || CPU_V6 || CPU_V6K || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526
         help
           Say Y here to disable branch prediction.  If unsure, say N.
 
@@ -726,7 +775,7 @@ config NEEDS_SYSCALL_FOR_CMPXCHG
 
 config DMA_CACHE_RWFO
         bool "Enable read/write for ownership DMA cache maintenance"
-        depends on CPU_V6 && SMP
+        depends on CPU_V6K && SMP
         default y
         help
           The Snoop Control Unit on ARM11MPCore does not detect the
@@ -772,7 +821,7 @@ config CACHE_L2X0
         depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176 || \
                    REALVIEW_EB_A9MP || ARCH_MX35 || ARCH_MX31 || MACH_REALVIEW_PBX || \
                    ARCH_NOMADIK || ARCH_OMAP4 || ARCH_S5PV310 || ARCH_TEGRA || \
-                   ARCH_U8500 || ARCH_VEXPRESS_CA9X4
+                   ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || ARCH_SHMOBILE
         default y
         select OUTER_CACHE
         select OUTER_CACHE_SYNC
@@ -782,14 +831,14 @@ config CACHE_L2X0
 config CACHE_PL310
         bool
         depends on CACHE_L2X0
-        default y if CPU_V7 && !CPU_V6
+        default y if CPU_V7 && !(CPU_V6 || CPU_V6K)
         help
           This option enables optimisations for the PL310 cache
           controller.
 
 config CACHE_TAUROS2
         bool "Enable the Tauros2 L2 cache controller"
-        depends on (ARCH_DOVE || ARCH_MMP)
+        depends on (ARCH_DOVE || ARCH_MMP || CPU_PJ4)
         default y
         select OUTER_CACHE
         help
@@ -804,16 +853,21 @@ config CACHE_XSC3L2
         help
           This option enables the L2 cache on XScale3.
 
+config ARM_L1_CACHE_SHIFT_6
+        bool
+        help
+          Setting ARM L1 cache line size to 64 Bytes.
+
 config ARM_L1_CACHE_SHIFT
         int
         default 6 if ARM_L1_CACHE_SHIFT_6
         default 5
 
 config ARM_DMA_MEM_BUFFERABLE
-        bool "Use non-cacheable memory for DMA" if CPU_V6 && !CPU_V7
+        bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7
         depends on !(MACH_REALVIEW_PB1176 || REALVIEW_EB_ARM11MP || \
                      MACH_REALVIEW_PB11MP)
-        default y if CPU_V6 || CPU_V7
+        default y if CPU_V6 || CPU_V6K || CPU_V7
         help
           Historically, the kernel has used strongly ordered mappings to
           provide DMA coherent memory.  With the advent of ARMv7, mapping
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 00d74a04af3a..bca7e61928c7 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -90,6 +90,7 @@ obj-$(CONFIG_CPU_XSC3)		+= proc-xsc3.o
 obj-$(CONFIG_CPU_MOHAWK)        += proc-mohawk.o
 obj-$(CONFIG_CPU_FEROCEON)      += proc-feroceon.o
 obj-$(CONFIG_CPU_V6)            += proc-v6.o
+obj-$(CONFIG_CPU_V6K)           += proc-v6.o
 obj-$(CONFIG_CPU_V7)            += proc-v7.o
 
 AFLAGS_proc-v6.o        :=-Wa,-march=armv6
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index f332df7f0d37..1478aa522144 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -20,11 +20,11 @@
  */
         .align  5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_32v6K
-        clrex
-#else
+#ifdef CONFIG_CPU_V6
         sub     r1, sp, #4                      @ Get unused stack location
         strex   r0, r1, [r1]                    @ Clear the exclusive monitor
+#elif defined(CONFIG_CPU_32v6K)
+        clrex
 #endif
         mrc     p15, 0, r1, c5, c0, 0           @ get FSR
         mrc     p15, 0, r0, c6, c0, 0           @ get FAR
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index 6e77c042d8e9..e0b0e7a4ec68 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -13,13 +13,9 @@
  */
 
 #include <linux/init.h>
+#include <linux/highmem.h>
 #include <asm/cacheflush.h>
-#include <asm/kmap_types.h>
-#include <asm/fixmap.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
 #include <plat/cache-feroceon-l2.h>
-#include "mm.h"
 
 /*
  * Low-level cache maintenance operations.
@@ -39,27 +35,30 @@
  * between which we don't want to be preempted.
  */
 
-static inline unsigned long l2_start_va(unsigned long paddr)
+static inline unsigned long l2_get_va(unsigned long paddr)
 {
 #ifdef CONFIG_HIGHMEM
         /*
-         * Let's do our own fixmap stuff in a minimal way here.
          * Because range ops can't be done on physical addresses,
          * we simply install a virtual mapping for it only for the
          * TLB lookup to occur, hence no need to flush the untouched
-         * memory mapping.  This is protected with the disabling of
-         * interrupts by the caller.
+         * memory mapping afterwards (note: a cache flush may happen
+         * in some circumstances depending on the path taken in kunmap_atomic).
          */
-        unsigned long idx = KM_L2_CACHE + KM_TYPE_NR * smp_processor_id();
-        unsigned long vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-        set_pte_ext(TOP_PTE(vaddr), pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL), 0);
-        local_flush_tlb_kernel_page(vaddr);
-        return vaddr + (paddr & ~PAGE_MASK);
+        void *vaddr = kmap_atomic_pfn(paddr >> PAGE_SHIFT);
+        return (unsigned long)vaddr + (paddr & ~PAGE_MASK);
 #else
         return __phys_to_virt(paddr);
 #endif
 }
 
+static inline void l2_put_va(unsigned long vaddr)
+{
+#ifdef CONFIG_HIGHMEM
+        kunmap_atomic((void *)vaddr);
+#endif
+}
+
 static inline void l2_clean_pa(unsigned long addr)
 {
         __asm__("mcr p15, 1, %0, c15, c9, 3" : : "r" (addr));
@@ -76,13 +75,14 @@ static inline void l2_clean_pa_range(unsigned long start, unsigned long end)
          */
         BUG_ON((start ^ end) >> PAGE_SHIFT);
 
-        raw_local_irq_save(flags);
-        va_start = l2_start_va(start);
+        va_start = l2_get_va(start);
         va_end = va_start + (end - start);
+        raw_local_irq_save(flags);
         __asm__("mcr p15, 1, %0, c15, c9, 4\n\t"
                 "mcr p15, 1, %1, c15, c9, 5"
                 : : "r" (va_start), "r" (va_end));
         raw_local_irq_restore(flags);
+        l2_put_va(va_start);
 }
 
 static inline void l2_clean_inv_pa(unsigned long addr)
@@ -106,13 +106,14 @@ static inline void l2_inv_pa_range(unsigned long start, unsigned long end)
          */
         BUG_ON((start ^ end) >> PAGE_SHIFT);
 
-        raw_local_irq_save(flags);
-        va_start = l2_start_va(start);
+        va_start = l2_get_va(start);
         va_end = va_start + (end - start);
+        raw_local_irq_save(flags);
         __asm__("mcr p15, 1, %0, c15, c11, 4\n\t"
                 "mcr p15, 1, %1, c15, c11, 5"
                 : : "r" (va_start), "r" (va_end));
         raw_local_irq_restore(flags);
+        l2_put_va(va_start);
 }
 
 static inline void l2_inv_all(void)
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 170c9bb95866..ef59099a5463 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -49,7 +49,13 @@ static inline void cache_wait(void __iomem *reg, unsigned long mask)
 static inline void cache_sync(void)
 {
         void __iomem *base = l2x0_base;
+
+#ifdef CONFIG_ARM_ERRATA_753970
+        /* write to an unmmapped register */
+        writel_relaxed(0, base + L2X0_DUMMY_REG);
+#else
         writel_relaxed(0, base + L2X0_CACHE_SYNC);
+#endif
         cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 
@@ -67,18 +73,24 @@ static inline void l2x0_inv_line(unsigned long addr)
         writel_relaxed(addr, base + L2X0_INV_LINE_PA);
 }
 
-#ifdef CONFIG_PL310_ERRATA_588369
-static void debug_writel(unsigned long val)
-{
-        extern void omap_smc1(u32 fn, u32 arg);
+#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915)
 
-        /*
-         * Texas Instrument secure monitor api to modify the
-         * PL310 Debug Control Register.
-         */
-        omap_smc1(0x100, val);
+#define debug_writel(val)       outer_cache.set_debug(val)
+
+static void l2x0_set_debug(unsigned long val)
+{
+        writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL);
+}
+#else
+/* Optimised out for non-errata case */
+static inline void debug_writel(unsigned long val)
+{
 }
 
+#define l2x0_set_debug  NULL
+#endif
+
+#ifdef CONFIG_PL310_ERRATA_588369
 static inline void l2x0_flush_line(unsigned long addr)
 {
         void __iomem *base = l2x0_base;
@@ -91,11 +103,6 @@ static inline void l2x0_flush_line(unsigned long addr)
 }
 #else
 
-/* Optimised out for non-errata case */
-static inline void debug_writel(unsigned long val)
-{
-}
-
 static inline void l2x0_flush_line(unsigned long addr)
 {
         void __iomem *base = l2x0_base;
@@ -119,9 +126,11 @@ static void l2x0_flush_all(void)
 
         /* clean all ways */
         spin_lock_irqsave(&l2x0_lock, flags);
+        debug_writel(0x03);
         writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY);
         cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask);
         cache_sync();
+        debug_writel(0x00);
         spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
@@ -329,6 +338,7 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
         outer_cache.flush_all = l2x0_flush_all;
         outer_cache.inv_all = l2x0_inv_all;
         outer_cache.disable = l2x0_disable;
+        outer_cache.set_debug = l2x0_set_debug;
 
         printk(KERN_INFO "%s cache controller enabled\n", type);
         printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 99fa688dfadd..c96fa1b3f49f 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -203,6 +203,10 @@ ENTRY(v6_flush_kern_dcache_area)
  *      - end     - virtual end address of region
  */
 v6_dma_inv_range:
+#ifdef CONFIG_DMA_CACHE_RWFO
+        ldrb    r2, [r0]                        @ read for ownership
+        strb    r2, [r0]                        @ write for ownership
+#endif
         tst     r0, #D_CACHE_LINE_SIZE - 1
         bic     r0, r0, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
@@ -211,6 +215,10 @@ v6_dma_inv_range:
         mcrne   p15, 0, r0, c7, c11, 1          @ clean unified line
 #endif
         tst     r1, #D_CACHE_LINE_SIZE - 1
+#ifdef CONFIG_DMA_CACHE_RWFO
+        ldrneb  r2, [r1, #-1]                   @ read for ownership
+        strneb  r2, [r1, #-1]                   @ write for ownership
+#endif
         bic     r1, r1, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
         mcrne   p15, 0, r1, c7, c14, 1          @ clean & invalidate D line
@@ -218,10 +226,6 @@ v6_dma_inv_range:
         mcrne   p15, 0, r1, c7, c15, 1          @ clean & invalidate unified line
 #endif
 1:
-#ifdef CONFIG_DMA_CACHE_RWFO
-        ldr     r2, [r0]                        @ read for ownership
-        str     r2, [r0]                        @ write for ownership
-#endif
 #ifdef HARVARD_CACHE
         mcr     p15, 0, r0, c7, c6, 1           @ invalidate D line
 #else
@@ -229,6 +233,10 @@ v6_dma_inv_range:
 #endif
         add     r0, r0, #D_CACHE_LINE_SIZE
         cmp     r0, r1
+#ifdef CONFIG_DMA_CACHE_RWFO
+        ldrlo   r2, [r0]                        @ read for ownership
+        strlo   r2, [r0]                        @ write for ownership
+#endif
         blo     1b
         mov     r0, #0
         mcr     p15, 0, r0, c7, c10, 4          @ drain write buffer
@@ -263,12 +271,12 @@ v6_dma_clean_range:
  *      - end     - virtual end address of region
  */
 ENTRY(v6_dma_flush_range)
-        bic     r0, r0, #D_CACHE_LINE_SIZE - 1
-1:
 #ifdef CONFIG_DMA_CACHE_RWFO
-        ldr     r2, [r0]                        @ read for ownership
-        str     r2, [r0]                        @ write for ownership
+        ldrb    r2, [r0]                @ read for ownership
+        strb    r2, [r0]                @ write for ownership
 #endif
+        bic     r0, r0, #D_CACHE_LINE_SIZE - 1
+1:
 #ifdef HARVARD_CACHE
         mcr     p15, 0, r0, c7, c14, 1          @ clean & invalidate D line
 #else
@@ -276,6 +284,10 @@ ENTRY(v6_dma_flush_range)
 #endif
         add     r0, r0, #D_CACHE_LINE_SIZE
         cmp     r0, r1
+#ifdef CONFIG_DMA_CACHE_RWFO
+        ldrlob  r2, [r0]                        @ read for ownership
+        strlob  r2, [r0]                        @ write for ownership
+#endif
         blo     1b
         mov     r0, #0
         mcr     p15, 0, r0, c7, c10, 4          @ drain write buffer
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index a3ebf7a4f49b..6136e68ce953 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -173,15 +173,22 @@ ENTRY(v7_coherent_user_range)
  UNWIND(.fnstart                )
         dcache_line_size r2, r3
         sub     r3, r2, #1
-        bic     r0, r0, r3
+        bic     r12, r0, r3
 1:
- USER(  mcr     p15, 0, r0, c7, c11, 1  )       @ clean D line to the point of unification
+ USER(  mcr     p15, 0, r12, c7, c11, 1 )       @ clean D line to the point of unification
+        add     r12, r12, r2
+        cmp     r12, r1
+        blo     1b
         dsb
- USER(  mcr     p15, 0, r0, c7, c5, 1   )       @ invalidate I line
-        add     r0, r0, r2
+        icache_line_size r2, r3
+        sub     r3, r2, #1
+        bic     r12, r0, r3
 2:
-        cmp     r0, r1
-        blo     1b
+ USER(  mcr     p15, 0, r12, c7, c5, 1  )       @ invalidate I line
+        add     r12, r12, r2
+        cmp     r12, r1
+        blo     2b
+3:
         mov     r0, #0
         ALT_SMP(mcr     p15, 0, r0, c7, c1, 6)  @ invalidate BTB Inner Shareable
         ALT_UP(mcr      p15, 0, r0, c7, c5, 6)  @ invalidate BTB
@@ -194,10 +201,10 @@ ENTRY(v7_coherent_user_range)
  * isn't mapped, just try the next page.
  */
 9001:
-        mov     r0, r0, lsr #12
-        mov     r0, r0, lsl #12
-        add     r0, r0, #4096
-        b       2b
+        mov     r12, r12, lsr #12
+        mov     r12, r12, lsl #12
+        add     r12, r12, #4096
+        b       3b
  UNWIND(.fnend          )
 ENDPROC(v7_coherent_kern_range)
 ENDPROC(v7_coherent_user_range)
diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c
index c3154928bccd..5a32020471e3 100644
--- a/arch/arm/mm/cache-xsc3l2.c
+++ b/arch/arm/mm/cache-xsc3l2.c
@@ -17,14 +17,10 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 #include <linux/init.h>
+#include <linux/highmem.h>
 #include <asm/system.h>
 #include <asm/cputype.h>
 #include <asm/cacheflush.h>
-#include <asm/kmap_types.h>
-#include <asm/fixmap.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#include "mm.h"
 
 #define CR_L2   (1 << 26)
 
@@ -71,16 +67,15 @@ static inline void xsc3_l2_inv_all(void)
         dsb();
 }
 
+static inline void l2_unmap_va(unsigned long va)
+{
 #ifdef CONFIG_HIGHMEM
-#define l2_map_save_flags(x)            raw_local_save_flags(x)
-#define l2_map_restore_flags(x)         raw_local_irq_restore(x)
-#else
-#define l2_map_save_flags(x)            ((x) = 0)
-#define l2_map_restore_flags(x)         ((void)(x))
+        if (va != -1)
+                kunmap_atomic((void *)va);
 #endif
+}
 
-static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va,
-                                      unsigned long flags)
+static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va)
 {
 #ifdef CONFIG_HIGHMEM
         unsigned long va = prev_va & PAGE_MASK;
@@ -89,17 +84,10 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va,
                 /*
                  * Switching to a new page.  Because cache ops are
                  * using virtual addresses only, we must put a mapping
-                 * in place for it.  We also enable interrupts for a
-                 * short while and disable them again to protect this
-                 * mapping.
+                 * in place for it.
                  */
-                unsigned long idx;
-                raw_local_irq_restore(flags);
-                idx = KM_L2_CACHE + KM_TYPE_NR * smp_processor_id();
-                va = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-                raw_local_irq_restore(flags | PSR_I_BIT);
-                set_pte_ext(TOP_PTE(va), pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL), 0);
-                local_flush_tlb_kernel_page(va);
+                l2_unmap_va(prev_va);
+                va = (unsigned long)kmap_atomic_pfn(pa >> PAGE_SHIFT);
         }
         return va + (pa_offset >> (32 - PAGE_SHIFT));
 #else
@@ -109,7 +97,7 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va,
 
 static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 {
-        unsigned long vaddr, flags;
+        unsigned long vaddr;
 
         if (start == 0 && end == -1ul) {
                 xsc3_l2_inv_all();
@@ -117,13 +105,12 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
         }
 
         vaddr = -1;  /* to force the first mapping */
-        l2_map_save_flags(flags);
 
         /*
          * Clean and invalidate partial first cache line.
          */
         if (start & (CACHE_LINE_SIZE - 1)) {
-                vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr, flags);
+                vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr);
                 xsc3_l2_clean_mva(vaddr);
                 xsc3_l2_inv_mva(vaddr);
                 start = (start | (CACHE_LINE_SIZE - 1)) + 1;
@@ -133,7 +120,7 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
          * Invalidate all full cache lines between 'start' and 'end'.
          */
         while (start < (end & ~(CACHE_LINE_SIZE - 1))) {
-                vaddr = l2_map_va(start, vaddr, flags);
+                vaddr = l2_map_va(start, vaddr);
                 xsc3_l2_inv_mva(vaddr);
                 start += CACHE_LINE_SIZE;
         }
@@ -142,31 +129,30 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
          * Clean and invalidate partial last cache line.
          */
         if (start < end) {
-                vaddr = l2_map_va(start, vaddr, flags);
+                vaddr = l2_map_va(start, vaddr);
                 xsc3_l2_clean_mva(vaddr);
                 xsc3_l2_inv_mva(vaddr);
         }
 
-        l2_map_restore_flags(flags);
+        l2_unmap_va(vaddr);
 
         dsb();
 }
 
 static void xsc3_l2_clean_range(unsigned long start, unsigned long end)
 {
-        unsigned long vaddr, flags;
+        unsigned long vaddr;
 
         vaddr = -1;  /* to force the first mapping */
-        l2_map_save_flags(flags);
 
         start &= ~(CACHE_LINE_SIZE - 1);
         while (start < end) {
-                vaddr = l2_map_va(start, vaddr, flags);
+                vaddr = l2_map_va(start, vaddr);
                 xsc3_l2_clean_mva(vaddr);
                 start += CACHE_LINE_SIZE;
         }
 
-        l2_map_restore_flags(flags);
+        l2_unmap_va(vaddr);
 
         dsb();
 }
@@ -193,7 +179,7 @@ static inline void xsc3_l2_flush_all(void)
 
 static void xsc3_l2_flush_range(unsigned long start, unsigned long end)
 {
-        unsigned long vaddr, flags;
+        unsigned long vaddr;
 
         if (start == 0 && end == -1ul) {
                 xsc3_l2_flush_all();
@@ -201,17 +187,16 @@ static void xsc3_l2_flush_range(unsigned long start, unsigned long end)
         }
 
         vaddr = -1;  /* to force the first mapping */
-        l2_map_save_flags(flags);
 
         start &= ~(CACHE_LINE_SIZE - 1);
         while (start < end) {
-                vaddr = l2_map_va(start, vaddr, flags);
+                vaddr = l2_map_va(start, vaddr);
                 xsc3_l2_clean_mva(vaddr);
                 xsc3_l2_inv_mva(vaddr);
                 start += CACHE_LINE_SIZE;
         }
 
-        l2_map_restore_flags(flags);
+        l2_unmap_va(vaddr);
 
         dsb();
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index a9bdfcda23f4..82a093cee09a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/highmem.h>
 
 #include <asm/memory.h>
 #include <asm/highmem.h>
@@ -320,7 +321,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
                 addr = page_address(page);
 
         if (addr)
-                *handle = page_to_dma(dev, page);
+                *handle = pfn_to_dma(dev, page_to_pfn(page));
 
         return addr;
 }
@@ -415,7 +416,7 @@ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr
         if (!arch_is_coherent())
                 __dma_free_remap(cpu_addr, size);
 
-        __dma_free_buffer(dma_to_page(dev, handle), size);
+        __dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
 }
 EXPORT_SYMBOL(dma_free_coherent);
 
@@ -489,10 +490,10 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
                                 op(vaddr, len, dir);
                                 kunmap_high(page);
                         } else if (cache_is_vipt()) {
-                                pte_t saved_pte;
-                                vaddr = kmap_high_l1_vipt(page, &saved_pte);
+                                /* unmapped pages might still be cached */
+                                vaddr = kmap_atomic(page);
                                 op(vaddr + offset, len, dir);
-                                kunmap_high_l1_vipt(page, saved_pte);
+                                kunmap_atomic(vaddr);
                         }
                 } else {
                         vaddr = page_address(page) + offset;
@@ -563,17 +564,20 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
         struct scatterlist *s;
         int i, j;
 
+        BUG_ON(!valid_dma_direction(dir));
+
         for_each_sg(sg, s, nents, i) {
-                s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
+                s->dma_address = __dma_map_page(dev, sg_page(s), s->offset,
                                                 s->length, dir);
                 if (dma_mapping_error(dev, s->dma_address))
                         goto bad_mapping;
         }
+        debug_dma_map_sg(dev, sg, nents, nents, dir);
         return nents;
 
  bad_mapping:
         for_each_sg(sg, s, i, j)
-                dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+                __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
         return 0;
 }
 EXPORT_SYMBOL(dma_map_sg);
@@ -582,7 +586,7 @@ EXPORT_SYMBOL(dma_map_sg);
  * dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @sg: list of buffers
- * @nents: number of buffers to unmap (returned from dma_map_sg)
+ * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
  * @dir: DMA transfer direction (same as was passed to dma_map_sg)
  *
  * Unmap a set of streaming mode DMA translations.  Again, CPU access
@@ -594,8 +598,10 @@ void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
         struct scatterlist *s;
         int i;
 
+        debug_dma_unmap_sg(dev, sg, nents, dir);
+
         for_each_sg(sg, s, nents, i)
-                dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+                __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
 }
 EXPORT_SYMBOL(dma_unmap_sg);
 
@@ -620,6 +626,8 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
                 __dma_page_dev_to_cpu(sg_page(s), s->offset,
                                       s->length, dir);
         }
+
+        debug_dma_sync_sg_for_cpu(dev, sg, nents, dir);
 }
 EXPORT_SYMBOL(dma_sync_sg_for_cpu);
 
@@ -644,5 +652,16 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
                 __dma_page_cpu_to_dev(sg_page(s), s->offset,
                                       s->length, dir);
         }
+
+        debug_dma_sync_sg_for_device(dev, sg, nents, dir);
 }
 EXPORT_SYMBOL(dma_sync_sg_for_device);
+
+#define PREALLOC_DMA_DEBUG_ENTRIES      4096
+
+static int __init dma_debug_do_init(void)
+{
+        dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+        return 0;
+}
+fs_initcall(dma_debug_do_init);
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 391ffae75098..2b269c955524 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
+#include <linux/highmem.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
@@ -17,7 +18,6 @@
 #include <asm/smp_plat.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
-#include <asm/smp_plat.h>
 
 #include "mm.h"
 
@@ -180,10 +180,10 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
                         __cpuc_flush_dcache_area(addr, PAGE_SIZE);
                         kunmap_high(page);
                 } else if (cache_is_vipt()) {
-                        pte_t saved_pte;
-                        addr = kmap_high_l1_vipt(page, &saved_pte);
+                        /* unmapped pages might still be cached */
+                        addr = kmap_atomic(page);
                         __cpuc_flush_dcache_area(addr, PAGE_SIZE);
-                        kunmap_high_l1_vipt(page, saved_pte);
+                        kunmap_atomic(addr);
                 }
         }
 
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index c435fd9e1da9..807c0573abbe 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -140,90 +140,3 @@ struct page *kmap_atomic_to_page(const void *ptr)
         pte = TOP_PTE(vaddr);
         return pte_page(*pte);
 }
-
-#ifdef CONFIG_CPU_CACHE_VIPT
-
-#include <linux/percpu.h>
-
-/*
- * The VIVT cache of a highmem page is always flushed before the page
- * is unmapped. Hence unmapped highmem pages need no cache maintenance
- * in that case.
- *
- * However unmapped pages may still be cached with a VIPT cache, and
- * it is not possible to perform cache maintenance on them using physical
- * addresses unfortunately.  So we have no choice but to set up a temporary
- * virtual mapping for that purpose.
- *
- * Yet this VIPT cache maintenance may be triggered from DMA support
- * functions which are possibly called from interrupt context. As we don't
- * want to keep interrupt disabled all the time when such maintenance is
- * taking place, we therefore allow for some reentrancy by preserving and
- * restoring the previous fixmap entry before the interrupted context is
- * resumed.  If the reentrancy depth is 0 then there is no need to restore
- * the previous fixmap, and leaving the current one in place allow it to
- * be reused the next time without a TLB flush (common with DMA).
- */
-
-static DEFINE_PER_CPU(int, kmap_high_l1_vipt_depth);
-
-void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte)
-{
-        unsigned int idx, cpu;
-        int *depth;
-        unsigned long vaddr, flags;
-        pte_t pte, *ptep;
-
-        if (!in_interrupt())
-                preempt_disable();
-
-        cpu = smp_processor_id();
-        depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
-
-        idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
-        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-        ptep = TOP_PTE(vaddr);
-        pte = mk_pte(page, kmap_prot);
-
-        raw_local_irq_save(flags);
-        (*depth)++;
-        if (pte_val(*ptep) == pte_val(pte)) {
-                *saved_pte = pte;
-        } else {
-                *saved_pte = *ptep;
-                set_pte_ext(ptep, pte, 0);
-                local_flush_tlb_kernel_page(vaddr);
-        }
-        raw_local_irq_restore(flags);
-
-        return (void *)vaddr;
-}
-
-void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte)
-{
-        unsigned int idx, cpu = smp_processor_id();
-        int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
-        unsigned long vaddr, flags;
-        pte_t pte, *ptep;
-
-        idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
-        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-        ptep = TOP_PTE(vaddr);
-        pte = mk_pte(page, kmap_prot);
-
-        BUG_ON(pte_val(*ptep) != pte_val(pte));
-        BUG_ON(*depth <= 0);
-
-        raw_local_irq_save(flags);
-        (*depth)--;
-        if (*depth != 0 && pte_val(pte) != pte_val(saved_pte)) {
-                set_pte_ext(ptep, saved_pte, 0);
-                local_flush_tlb_kernel_page(vaddr);
-        }
-        raw_local_irq_restore(flags);
-
-        if (!in_interrupt())
-                preempt_enable();
-}
-
-#endif  /* CONFIG_CPU_CACHE_VIPT */
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 14a00a1ef52f..b3b0f0f5053d 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -297,6 +297,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
         memblock_reserve(__pa(_stext), _end - _stext);
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
+        if (phys_initrd_size &&
+            memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) {
+                pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n",
+                       phys_initrd_start, phys_initrd_size);
+                phys_initrd_start = phys_initrd_size = 0;
+        }
         if (phys_initrd_size) {
                 memblock_reserve(phys_initrd_start, phys_initrd_size);
 
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 17e7b0b57e49..ab506272b2d3 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -204,12 +204,8 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
         /*
          * Don't allow RAM to be mapped - this causes problems with ARMv6+
          */
-        if (pfn_valid(pfn)) {
-                printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory.  This leads\n"
-                       KERN_WARNING "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n"
-                       KERN_WARNING "will fail in the next kernel release.  Please fix your driver.\n");
-                WARN_ON(1);
-        }
+        if (WARN_ON(pfn_valid(pfn)))
+                return NULL;
 
         type = get_mem_type(mtype);
         if (!type)
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index b0a98305055c..afe209e1e1f8 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -31,7 +31,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
         struct mm_struct *mm = current->mm;
         struct vm_area_struct *vma;
         unsigned long start_addr;
-#ifdef CONFIG_CPU_V6
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
         unsigned int cache_type;
         int do_align = 0, aliasing = 0;
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 82ef6966ae09..6cf76b3b68d1 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -24,6 +24,7 @@
 #include <asm/smp_plat.h>
 #include <asm/tlb.h>
 #include <asm/highmem.h>
+#include <asm/traps.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -843,16 +844,6 @@ static void __init sanity_check_meminfo(void)
                          * rather difficult.
                          */
                         reason = "with VIPT aliasing cache";
-                } 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
-                         * we may deadlock:
-                         *  kmap_high(irqs off)->flush_all_zero_pkmaps->
-                         *  flush_tlb_kernel_range->smp_call_function_many
-                         *   (must not be called with irqs off)
-                         */
-                        reason = "without hardware TLB ops broadcasting";
                 }
                 if (reason) {
                         printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
@@ -930,12 +921,11 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 {
         struct map_desc map;
         unsigned long addr;
-        void *vectors;
 
         /*
          * Allocate the vector page early.
          */
-        vectors = early_alloc(PAGE_SIZE);
+        vectors_page = early_alloc(PAGE_SIZE);
 
         for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
                 pmd_clear(pmd_off_k(addr));
@@ -975,7 +965,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
          * location (0xffff0000).  If we aren't using high-vectors, also
          * create a mapping at the low-vectors virtual address.
          */
-        map.pfn = __phys_to_pfn(virt_to_phys(vectors));
+        map.pfn = __phys_to_pfn(virt_to_phys(vectors_page));
         map.virtual = 0xffff0000;
         map.length = PAGE_SIZE;
         map.type = MT_HIGH_VECTORS;
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index f7fafb1741f4..b2027c154b2a 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -55,7 +55,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
                 if (!new_pmd)
                         goto no_pmd;
 
-                new_pte = pte_alloc_map(mm, new_pmd, 0);
+                new_pte = pte_alloc_map(mm, NULL, new_pmd, 0);
                 if (!new_pte)
                         goto no_pte;
 
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index bcf748d9f4e2..226e3d8351c2 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -493,6 +493,9 @@ arm1020_processor_functions:
         .word   cpu_arm1020_dcache_clean_area
         .word   cpu_arm1020_switch_mm
         .word   cpu_arm1020_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   arm1020_processor_functions, . - arm1020_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index ab7ec26657ea..86d9c2cf0bce 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -474,6 +474,9 @@ arm1020e_processor_functions:
         .word   cpu_arm1020e_dcache_clean_area
         .word   cpu_arm1020e_switch_mm
         .word   cpu_arm1020e_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   arm1020e_processor_functions, . - arm1020e_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 831c5e54e22f..83d3dd34f846 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -457,6 +457,9 @@ arm1022_processor_functions:
         .word   cpu_arm1022_dcache_clean_area
         .word   cpu_arm1022_switch_mm
         .word   cpu_arm1022_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   arm1022_processor_functions, . - arm1022_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index e3f7e9a166bf..686043ee7281 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -452,6 +452,9 @@ arm1026_processor_functions:
         .word   cpu_arm1026_dcache_clean_area
         .word   cpu_arm1026_switch_mm
         .word   cpu_arm1026_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   arm1026_processor_functions, . - arm1026_processor_functions
 
         .section .rodata
diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S
index 6a7be1863edd..5f79dc4ce3fb 100644
--- a/arch/arm/mm/proc-arm6_7.S
+++ b/arch/arm/mm/proc-arm6_7.S
@@ -284,6 +284,9 @@ ENTRY(arm6_processor_functions)
                 .word   cpu_arm6_dcache_clean_area
                 .word   cpu_arm6_switch_mm
                 .word   cpu_arm6_set_pte_ext
+                .word   0
+                .word   0
+                .word   0
                 .size   arm6_processor_functions, . - arm6_processor_functions
 
 /*
@@ -301,6 +304,9 @@ ENTRY(arm7_processor_functions)
                 .word   cpu_arm7_dcache_clean_area
                 .word   cpu_arm7_switch_mm
                 .word   cpu_arm7_set_pte_ext
+                .word   0
+                .word   0
+                .word   0
                 .size   arm7_processor_functions, . - arm7_processor_functions
 
                 .section ".rodata"
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index c285395f44b2..665266da143c 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -185,6 +185,9 @@ ENTRY(arm720_processor_functions)
                 .word   cpu_arm720_dcache_clean_area
                 .word   cpu_arm720_switch_mm
                 .word   cpu_arm720_set_pte_ext
+                .word   0
+                .word   0
+                .word   0
                 .size   arm720_processor_functions, . - arm720_processor_functions
 
                 .section ".rodata"
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index 38b27dcba727..6f9d12effee1 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -130,6 +130,9 @@ ENTRY(arm740_processor_functions)
         .word   cpu_arm740_dcache_clean_area
         .word   cpu_arm740_switch_mm
         .word   0                       @ cpu_*_set_pte
+        .word   0
+        .word   0
+        .word   0
         .size   arm740_processor_functions, . - arm740_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index 0c9786de20af..e4c165ca6696 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -70,6 +70,9 @@ ENTRY(arm7tdmi_processor_functions)
                 .word   cpu_arm7tdmi_dcache_clean_area
                 .word   cpu_arm7tdmi_switch_mm
                 .word   0               @ cpu_*_set_pte
+                .word   0
+                .word   0
+                .word   0
                 .size   arm7tdmi_processor_functions, . - arm7tdmi_processor_functions
 
                 .section ".rodata"
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 6109f278a904..219980ec8b6e 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -387,6 +387,40 @@ ENTRY(cpu_arm920_set_pte_ext)
 #endif
         mov     pc, lr
 
+/* 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
+ENTRY(cpu_arm920_do_suspend)
+        stmfd   sp!, {r4 - r7, lr}
+        mrc     p15, 0, r4, c13, c0, 0  @ PID
+        mrc     p15, 0, r5, c3, c0, 0   @ Domain ID
+        mrc     p15, 0, r6, c2, c0, 0   @ TTB address
+        mrc     p15, 0, r7, c1, c0, 0   @ Control register
+        stmia   r0, {r4 - r7}
+        ldmfd   sp!, {r4 - r7, pc}
+ENDPROC(cpu_arm920_do_suspend)
+
+ENTRY(cpu_arm920_do_resume)
+        mov     ip, #0
+        mcr     p15, 0, ip, c8, c7, 0   @ invalidate I+D TLBs
+        mcr     p15, 0, ip, c7, c7, 0   @ invalidate I+D caches
+        ldmia   r0, {r4 - r7}
+        mcr     p15, 0, r4, c13, c0, 0  @ PID
+        mcr     p15, 0, r5, c3, c0, 0   @ Domain ID
+        mcr     p15, 0, r6, c2, c0, 0   @ TTB address
+        mov     r0, r7                  @ control register
+        mov     r2, r6, lsr #14         @ get TTB0 base
+        mov     r2, r2, lsl #14
+        ldr     r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
+                     PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE
+        b       cpu_resume_mmu
+ENDPROC(cpu_arm920_do_resume)
+#else
+#define cpu_arm920_do_suspend   0
+#define cpu_arm920_do_resume    0
+#endif
+
         __CPUINIT
 
         .type   __arm920_setup, #function
@@ -432,6 +466,9 @@ arm920_processor_functions:
         .word   cpu_arm920_dcache_clean_area
         .word   cpu_arm920_switch_mm
         .word   cpu_arm920_set_pte_ext
+        .word   cpu_arm920_suspend_size
+        .word   cpu_arm920_do_suspend
+        .word   cpu_arm920_do_resume
         .size   arm920_processor_functions, . - arm920_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index bb2f0f46a5e6..36154b1e792a 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -436,6 +436,9 @@ arm922_processor_functions:
         .word   cpu_arm922_dcache_clean_area
         .word   cpu_arm922_switch_mm
         .word   cpu_arm922_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   arm922_processor_functions, . - arm922_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index c13e01accfe2..89c5e0009c4c 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -503,6 +503,9 @@ arm925_processor_functions:
         .word   cpu_arm925_dcache_clean_area
         .word   cpu_arm925_switch_mm
         .word   cpu_arm925_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   arm925_processor_functions, . - arm925_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 42eb4315740b..6a4bdb2c94a7 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -401,6 +401,40 @@ ENTRY(cpu_arm926_set_pte_ext)
 #endif
         mov     pc, lr
 
+/* 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
+ENTRY(cpu_arm926_do_suspend)
+        stmfd   sp!, {r4 - r7, lr}
+        mrc     p15, 0, r4, c13, c0, 0  @ PID
+        mrc     p15, 0, r5, c3, c0, 0   @ Domain ID
+        mrc     p15, 0, r6, c2, c0, 0   @ TTB address
+        mrc     p15, 0, r7, c1, c0, 0   @ Control register
+        stmia   r0, {r4 - r7}
+        ldmfd   sp!, {r4 - r7, pc}
+ENDPROC(cpu_arm926_do_suspend)
+
+ENTRY(cpu_arm926_do_resume)
+        mov     ip, #0
+        mcr     p15, 0, ip, c8, c7, 0   @ invalidate I+D TLBs
+        mcr     p15, 0, ip, c7, c7, 0   @ invalidate I+D caches
+        ldmia   r0, {r4 - r7}
+        mcr     p15, 0, r4, c13, c0, 0  @ PID
+        mcr     p15, 0, r5, c3, c0, 0   @ Domain ID
+        mcr     p15, 0, r6, c2, c0, 0   @ TTB address
+        mov     r0, r7                  @ control register
+        mov     r2, r6, lsr #14         @ get TTB0 base
+        mov     r2, r2, lsl #14
+        ldr     r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
+                     PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE
+        b       cpu_resume_mmu
+ENDPROC(cpu_arm926_do_resume)
+#else
+#define cpu_arm926_do_suspend   0
+#define cpu_arm926_do_resume    0
+#endif
+
         __CPUINIT
 
         .type   __arm926_setup, #function
@@ -456,6 +490,9 @@ arm926_processor_functions:
         .word   cpu_arm926_dcache_clean_area
         .word   cpu_arm926_switch_mm
         .word   cpu_arm926_set_pte_ext
+        .word   cpu_arm926_suspend_size
+        .word   cpu_arm926_do_suspend
+        .word   cpu_arm926_do_resume
         .size   arm926_processor_functions, . - arm926_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index 7b11cdb9935f..26aea3f71c26 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -363,6 +363,9 @@ ENTRY(arm940_processor_functions)
         .word   cpu_arm940_dcache_clean_area
         .word   cpu_arm940_switch_mm
         .word   0               @ cpu_*_set_pte
+        .word   0
+        .word   0
+        .word   0
         .size   arm940_processor_functions, . - arm940_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 1a5bbf080342..8063345406fe 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -419,6 +419,9 @@ ENTRY(arm946_processor_functions)
         .word   cpu_arm946_dcache_clean_area
         .word   cpu_arm946_switch_mm
         .word   0               @ cpu_*_set_pte
+        .word   0
+        .word   0
+        .word   0
         .size   arm946_processor_functions, . - arm946_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S
index db67e3134d7a..7b7ebd4d096d 100644
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -70,6 +70,9 @@ ENTRY(arm9tdmi_processor_functions)
                 .word   cpu_arm9tdmi_dcache_clean_area
                 .word   cpu_arm9tdmi_switch_mm
                 .word   0               @ cpu_*_set_pte
+                .word   0
+                .word   0
+                .word   0
                 .size   arm9tdmi_processor_functions, . - arm9tdmi_processor_functions
 
                 .section ".rodata"
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index 7c9ad621f0e6..fc2a4ae15cf4 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -195,6 +195,9 @@ fa526_processor_functions:
         .word   cpu_fa526_dcache_clean_area
         .word   cpu_fa526_switch_mm
         .word   cpu_fa526_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   fa526_processor_functions, . - fa526_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index b4597edbff97..d3883eed7a4a 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -554,6 +554,9 @@ feroceon_processor_functions:
         .word   cpu_feroceon_dcache_clean_area
         .word   cpu_feroceon_switch_mm
         .word   cpu_feroceon_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   feroceon_processor_functions, . - feroceon_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index f5ca6aaecdbd..e32fa499194c 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -61,17 +61,27 @@
         .endm
 
 /*
- * cache_line_size - get the cache line size from the CSIDR register
- * (available on ARMv7+). It assumes that the CSSR register was configured
- * to access the L1 data cache CSIDR.
+ * dcache_line_size - get the minimum D-cache line size from the CTR register
+ * on ARMv7.
  */
         .macro  dcache_line_size, reg, tmp
-        mrc     p15, 1, \tmp, c0, c0, 0         @ read CSIDR
-        and     \tmp, \tmp, #7                  @ cache line size encoding
-        mov     \reg, #16                       @ size offset
+        mrc     p15, 0, \tmp, c0, c0, 1         @ read ctr
+        lsr     \tmp, \tmp, #16
+        and     \tmp, \tmp, #0xf                @ cache line size encoding
+        mov     \reg, #4                        @ bytes per word
         mov     \reg, \reg, lsl \tmp            @ actual cache line size
         .endm
 
+/*
+ * icache_line_size - get the minimum I-cache line size from the CTR register
+ * on ARMv7.
+ */
+        .macro  icache_line_size, reg, tmp
+        mrc     p15, 0, \tmp, c0, c0, 1         @ read ctr
+        and     \tmp, \tmp, #0xf                @ cache line size encoding
+        mov     \reg, #4                        @ bytes per word
+        mov     \reg, \reg, lsl \tmp            @ actual cache line size
+        .endm
 
 /*
  * Sanity check the PTE configuration for the code below - which makes
@@ -99,6 +109,10 @@
  *  110x   0   1   0    r/w     r/o
  *  11x0   0   1   0    r/w     r/o
  *  1111   0   1   1    r/w     r/w
+ *
+ * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
+ *  110x   1   1   1    r/o     r/o
+ *  11x0   1   1   1    r/o     r/o
  */
         .macro  armv6_mt_table pfx
 \pfx\()_mt_table:
@@ -138,8 +152,11 @@
 
         tst     r1, #L_PTE_USER
         orrne   r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+        @ allow kernel read/write access to read-only user pages
         tstne   r3, #PTE_EXT_APX
         bicne   r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
         tst     r1, #L_PTE_XN
         orrne   r3, r3, #PTE_EXT_XN
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 4458ee6aa713..9d4f2ae63370 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -388,6 +388,9 @@ mohawk_processor_functions:
         .word   cpu_mohawk_dcache_clean_area
         .word   cpu_mohawk_switch_mm
         .word   cpu_mohawk_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   mohawk_processor_functions, . - mohawk_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S
index 5aa8d59c2e85..46f09ed16b98 100644
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -203,6 +203,9 @@ ENTRY(sa110_processor_functions)
         .word   cpu_sa110_dcache_clean_area
         .word   cpu_sa110_switch_mm
         .word   cpu_sa110_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   sa110_processor_functions, . - sa110_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 2ac4e6f10713..74483d1977fe 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -169,6 +169,42 @@ ENTRY(cpu_sa1100_set_pte_ext)
 #endif
         mov     pc, lr
 
+.globl  cpu_sa1100_suspend_size
+.equ    cpu_sa1100_suspend_size, 4*4
+#ifdef CONFIG_PM
+ENTRY(cpu_sa1100_do_suspend)
+        stmfd   sp!, {r4 - r7, lr}
+        mrc     p15, 0, r4, c3, c0, 0           @ domain ID
+        mrc     p15, 0, r5, c2, c0, 0           @ translation table base addr
+        mrc     p15, 0, r6, c13, c0, 0          @ PID
+        mrc     p15, 0, r7, c1, c0, 0           @ control reg
+        stmia   r0, {r4 - r7}                   @ store cp regs
+        ldmfd   sp!, {r4 - r7, pc}
+ENDPROC(cpu_sa1100_do_suspend)
+
+ENTRY(cpu_sa1100_do_resume)
+        ldmia   r0, {r4 - r7}                   @ load cp regs
+        mov     r1, #0
+        mcr     p15, 0, r1, c8, c7, 0           @ flush I+D TLBs
+        mcr     p15, 0, r1, c7, c7, 0           @ flush I&D cache
+        mcr     p15, 0, r1, c9, c0, 0           @ invalidate RB
+        mcr     p15, 0, r1, c9, c0, 5           @ allow user space to use RB
+
+        mcr     p15, 0, r4, c3, c0, 0           @ domain ID
+        mcr     p15, 0, r5, c2, c0, 0           @ translation table base addr
+        mcr     p15, 0, r6, c13, c0, 0          @ PID
+        mov     r0, r7                          @ control register
+        mov     r2, r5, lsr #14                 @ get TTB0 base
+        mov     r2, r2, lsl #14
+        ldr     r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
+                     PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE
+        b       cpu_resume_mmu
+ENDPROC(cpu_sa1100_do_resume)
+#else
+#define cpu_sa1100_do_suspend   0
+#define cpu_sa1100_do_resume    0
+#endif
+
         __CPUINIT
 
         .type   __sa1100_setup, #function
@@ -218,6 +254,9 @@ ENTRY(sa1100_processor_functions)
         .word   cpu_sa1100_dcache_clean_area
         .word   cpu_sa1100_switch_mm
         .word   cpu_sa1100_set_pte_ext
+        .word   cpu_sa1100_suspend_size
+        .word   cpu_sa1100_do_suspend
+        .word   cpu_sa1100_do_resume
         .size   sa1100_processor_functions, . - sa1100_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 59a7e1ffe7bc..832b6bdc192c 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -121,6 +121,53 @@ ENTRY(cpu_v6_set_pte_ext)
 #endif
         mov     pc, lr
 
+/* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
+.globl  cpu_v6_suspend_size
+.equ    cpu_v6_suspend_size, 4 * 8
+#ifdef CONFIG_PM
+ENTRY(cpu_v6_do_suspend)
+        stmfd   sp!, {r4 - r11, lr}
+        mrc     p15, 0, r4, c13, c0, 0  @ FCSE/PID
+        mrc     p15, 0, r5, c13, c0, 1  @ Context ID
+        mrc     p15, 0, r6, c3, c0, 0   @ Domain ID
+        mrc     p15, 0, r7, c2, c0, 0   @ Translation table base 0
+        mrc     p15, 0, r8, c2, c0, 1   @ Translation table base 1
+        mrc     p15, 0, r9, c1, c0, 1   @ auxillary control register
+        mrc     p15, 0, r10, c1, c0, 2  @ co-processor access control
+        mrc     p15, 0, r11, c1, c0, 0  @ control register
+        stmia   r0, {r4 - r11}
+        ldmfd   sp!, {r4- r11, pc}
+ENDPROC(cpu_v6_do_suspend)
+
+ENTRY(cpu_v6_do_resume)
+        mov     ip, #0
+        mcr     p15, 0, ip, c7, c14, 0  @ clean+invalidate D cache
+        mcr     p15, 0, ip, c7, c5, 0   @ invalidate I cache
+        mcr     p15, 0, ip, c7, c15, 0  @ clean+invalidate cache
+        mcr     p15, 0, ip, c7, c10, 4  @ drain write buffer
+        ldmia   r0, {r4 - r11}
+        mcr     p15, 0, r4, c13, c0, 0  @ FCSE/PID
+        mcr     p15, 0, r5, c13, c0, 1  @ Context ID
+        mcr     p15, 0, r6, c3, c0, 0   @ Domain ID
+        mcr     p15, 0, r7, c2, c0, 0   @ Translation table base 0
+        mcr     p15, 0, r8, c2, c0, 1   @ Translation table base 1
+        mcr     p15, 0, r9, c1, c0, 1   @ auxillary control register
+        mcr     p15, 0, r10, c1, c0, 2  @ co-processor access control
+        mcr     p15, 0, ip, c2, c0, 2   @ TTB control register
+        mcr     p15, 0, ip, c7, c5, 4   @ ISB
+        mov     r0, r11                 @ control register
+        mov     r2, r7, lsr #14         @ get TTB0 base
+        mov     r2, r2, lsl #14
+        ldr     r3, cpu_resume_l1_flags
+        b       cpu_resume_mmu
+ENDPROC(cpu_v6_do_resume)
+cpu_resume_l1_flags:
+        ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP)
+        ALT_UP(.long  PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP)
+#else
+#define cpu_v6_do_suspend 0
+#define cpu_v6_do_resume 0
+#endif
 
 
         .type   cpu_v6_name, #object
@@ -206,6 +253,9 @@ ENTRY(v6_processor_functions)
         .word   cpu_v6_dcache_clean_area
         .word   cpu_v6_switch_mm
         .word   cpu_v6_set_pte_ext
+        .word   cpu_v6_suspend_size
+        .word   cpu_v6_do_suspend
+        .word   cpu_v6_do_resume
         .size   v6_processor_functions, . - v6_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 210d051c54d7..262fa88a7439 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -108,10 +108,16 @@ ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_ARM_ERRATA_430973
         mcr     p15, 0, r2, c7, c5, 6           @ flush BTAC/BTB
 #endif
+#ifdef CONFIG_ARM_ERRATA_754322
+        dsb
+#endif
         mcr     p15, 0, r2, c13, c0, 1          @ set reserved context ID
         isb
 1:      mcr     p15, 0, r0, c2, c0, 0           @ set TTB 0
         isb
+#ifdef CONFIG_ARM_ERRATA_754322
+        dsb
+#endif
         mcr     p15, 0, r1, c13, c0, 1          @ set context ID
         isb
 #endif
@@ -146,8 +152,11 @@ ENTRY(cpu_v7_set_pte_ext)
 
         tst     r1, #L_PTE_USER
         orrne   r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+        @ allow kernel read/write access to read-only user pages
         tstne   r3, #PTE_EXT_APX
         bicne   r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
         tst     r1, #L_PTE_XN
         orrne   r3, r3, #PTE_EXT_XN
@@ -156,7 +165,9 @@ ENTRY(cpu_v7_set_pte_ext)
         tstne   r1, #L_PTE_PRESENT
         moveq   r3, #0
 
-        str     r3, [r0, #2048]!
+ ARM(   str     r3, [r0, #2048]! )
+ THUMB( add     r0, r0, #2048 )
+ THUMB( str     r3, [r0] )
         mcr     p15, 0, r0, c7, c10, 1          @ flush_pte
 #endif
         mov     pc, lr
@@ -166,6 +177,87 @@ cpu_v7_name:
         .ascii  "ARMv7 Processor"
         .align
 
+        /*
+         * Memory region attributes with SCTLR.TRE=1
+         *
+         *   n = TEX[0],C,B
+         *   TR = PRRR[2n+1:2n]         - memory type
+         *   IR = NMRR[2n+1:2n]         - inner cacheable property
+         *   OR = NMRR[2n+17:2n+16]     - outer cacheable property
+         *
+         *                      n       TR      IR      OR
+         *   UNCACHED           000     00
+         *   BUFFERABLE         001     10      00      00
+         *   WRITETHROUGH       010     10      10      10
+         *   WRITEBACK          011     10      11      11
+         *   reserved           110
+         *   WRITEALLOC         111     10      01      01
+         *   DEV_SHARED         100     01
+         *   DEV_NONSHARED      100     01
+         *   DEV_WC             001     10
+         *   DEV_CACHED         011     10
+         *
+         * Other attributes:
+         *
+         *   DS0 = PRRR[16] = 0         - device shareable property
+         *   DS1 = PRRR[17] = 1         - device shareable property
+         *   NS0 = PRRR[18] = 0         - normal shareable property
+         *   NS1 = PRRR[19] = 1         - normal shareable property
+         *   NOS = PRRR[24+n] = 1       - not outer shareable
+         */
+.equ    PRRR,   0xff0a81a8
+.equ    NMRR,   0x40e040e0
+
+/* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
+.globl  cpu_v7_suspend_size
+.equ    cpu_v7_suspend_size, 4 * 8
+#ifdef CONFIG_PM
+ENTRY(cpu_v7_do_suspend)
+        stmfd   sp!, {r4 - r11, lr}
+        mrc     p15, 0, r4, c13, c0, 0  @ FCSE/PID
+        mrc     p15, 0, r5, c13, c0, 1  @ Context ID
+        mrc     p15, 0, r6, c3, c0, 0   @ Domain ID
+        mrc     p15, 0, r7, c2, c0, 0   @ TTB 0
+        mrc     p15, 0, r8, c2, c0, 1   @ TTB 1
+        mrc     p15, 0, r9, c1, c0, 0   @ Control register
+        mrc     p15, 0, r10, c1, c0, 1  @ Auxiliary control register
+        mrc     p15, 0, r11, c1, c0, 2  @ Co-processor access control
+        stmia   r0, {r4 - r11}
+        ldmfd   sp!, {r4 - r11, pc}
+ENDPROC(cpu_v7_do_suspend)
+
+ENTRY(cpu_v7_do_resume)
+        mov     ip, #0
+        mcr     p15, 0, ip, c8, c7, 0   @ invalidate TLBs
+        mcr     p15, 0, ip, c7, c5, 0   @ invalidate I cache
+        ldmia   r0, {r4 - r11}
+        mcr     p15, 0, r4, c13, c0, 0  @ FCSE/PID
+        mcr     p15, 0, r5, c13, c0, 1  @ Context ID
+        mcr     p15, 0, r6, c3, c0, 0   @ Domain ID
+        mcr     p15, 0, r7, c2, c0, 0   @ TTB 0
+        mcr     p15, 0, r8, c2, c0, 1   @ TTB 1
+        mcr     p15, 0, ip, c2, c0, 2   @ TTB control register
+        mcr     p15, 0, r10, c1, c0, 1  @ Auxillary control register
+        mcr     p15, 0, r11, c1, c0, 2  @ Co-processor access control
+        ldr     r4, =PRRR               @ PRRR
+        ldr     r5, =NMRR               @ NMRR
+        mcr     p15, 0, r4, c10, c2, 0  @ write PRRR
+        mcr     p15, 0, r5, c10, c2, 1  @ write NMRR
+        isb
+        mov     r0, r9                  @ control register
+        mov     r2, r7, lsr #14         @ get TTB0 base
+        mov     r2, r2, lsl #14
+        ldr     r3, cpu_resume_l1_flags
+        b       cpu_resume_mmu
+ENDPROC(cpu_v7_do_resume)
+cpu_resume_l1_flags:
+        ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP)
+        ALT_UP(.long  PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP)
+#else
+#define cpu_v7_do_suspend       0
+#define cpu_v7_do_resume        0
+#endif
+
         __CPUINIT
 
 /*
@@ -259,6 +351,12 @@ __v7_setup:
         orreq   r10, r10, #1 << 6               @ set bit #6
         mcreq   p15, 0, r10, c15, c0, 1         @ write diagnostic register
 #endif
+#ifdef CONFIG_ARM_ERRATA_751472
+        cmp     r6, #0x30                       @ present prior to r3p0
+        mrclt   p15, 0, r10, c15, c0, 1         @ read diagnostic register
+        orrlt   r10, r10, #1 << 11              @ set bit #11
+        mcrlt   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+#endif
 
 3:      mov     r10, #0
 #ifdef HARVARD_CACHE
@@ -271,38 +369,8 @@ __v7_setup:
         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
-        /*
-         * Memory region attributes with SCTLR.TRE=1
-         *
-         *   n = TEX[0],C,B
-         *   TR = PRRR[2n+1:2n]         - memory type
-         *   IR = NMRR[2n+1:2n]         - inner cacheable property
-         *   OR = NMRR[2n+17:2n+16]     - outer cacheable property
-         *
-         *                      n       TR      IR      OR
-         *   UNCACHED           000     00
-         *   BUFFERABLE         001     10      00      00
-         *   WRITETHROUGH       010     10      10      10
-         *   WRITEBACK          011     10      11      11
-         *   reserved           110
-         *   WRITEALLOC         111     10      01      01
-         *   DEV_SHARED         100     01
-         *   DEV_NONSHARED      100     01
-         *   DEV_WC             001     10
-         *   DEV_CACHED         011     10
-         *
-         * Other attributes:
-         *
-         *   DS0 = PRRR[16] = 0         - device shareable property
-         *   DS1 = PRRR[17] = 1         - device shareable property
-         *   NS0 = PRRR[18] = 0         - normal shareable property
-         *   NS1 = PRRR[19] = 1         - normal shareable property
-         *   NOS = PRRR[24+n] = 1       - not outer shareable
-         */
-        ldr     r5, =0xff0a81a8                 @ PRRR
-        ldr     r6, =0x40e040e0                 @ NMRR
+        ldr     r5, =PRRR                       @ PRRR
+        ldr     r6, =NMRR                       @ NMRR
         mcr     p15, 0, r5, c10, c2, 0          @ write PRRR
         mcr     p15, 0, r6, c10, c2, 1          @ write NMRR
 #endif
@@ -311,6 +379,10 @@ __v7_setup:
 #ifdef CONFIG_CPU_ENDIAN_BE8
         orr     r6, r6, #1 << 25                @ big-endian page tables
 #endif
+#ifdef CONFIG_SWP_EMULATE
+        orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
+        bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"
+#endif
         mrc     p15, 0, r0, c1, c0, 0           @ read control register
         bic     r0, r0, r5                      @ clear bits them
         orr     r0, r0, r6                      @ set them
@@ -344,6 +416,9 @@ ENTRY(v7_processor_functions)
         .word   cpu_v7_dcache_clean_area
         .word   cpu_v7_switch_mm
         .word   cpu_v7_set_pte_ext
+        .word   0
+        .word   0
+        .word   0
         .size   v7_processor_functions, . - v7_processor_functions
 
         .section ".rodata"
@@ -379,7 +454,7 @@ __v7_ca9mp_proc_info:
                 PMD_SECT_XN | \
                 PMD_SECT_AP_WRITE | \
                 PMD_SECT_AP_READ
-        b       __v7_ca9mp_setup
+        W(b)    __v7_ca9mp_setup
         .long   cpu_arch_name
         .long   cpu_elf_name
         .long   HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
@@ -411,7 +486,7 @@ __v7_proc_info:
                 PMD_SECT_XN | \
                 PMD_SECT_AP_WRITE | \
                 PMD_SECT_AP_READ
-        b       __v7_setup
+        W(b)    __v7_setup
         .long   cpu_arch_name
         .long   cpu_elf_name
         .long   HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index ec26355cb7c2..63d8b2044e84 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -413,9 +413,52 @@ ENTRY(cpu_xsc3_set_pte_ext)
         mov     pc, lr
 
         .ltorg
-
         .align
 
+.globl  cpu_xsc3_suspend_size
+.equ    cpu_xsc3_suspend_size, 4 * 8
+#ifdef CONFIG_PM
+ENTRY(cpu_xsc3_do_suspend)
+        stmfd   sp!, {r4 - r10, lr}
+        mrc     p14, 0, r4, c6, c0, 0   @ clock configuration, for turbo mode
+        mrc     p15, 0, r5, c15, c1, 0  @ CP access reg
+        mrc     p15, 0, r6, c13, c0, 0  @ PID
+        mrc     p15, 0, r7, c3, c0, 0   @ domain ID
+        mrc     p15, 0, r8, c2, c0, 0   @ translation table base addr
+        mrc     p15, 0, r9, c1, c0, 1   @ auxiliary control reg
+        mrc     p15, 0, r10, c1, c0, 0  @ control reg
+        bic     r4, r4, #2              @ clear frequency change bit
+        stmia   r0, {r1, r4 - r10}      @ store v:p offset + cp regs
+        ldmia   sp!, {r4 - r10, pc}
+ENDPROC(cpu_xsc3_do_suspend)
+
+ENTRY(cpu_xsc3_do_resume)
+        ldmia   r0, {r1, r4 - r10}      @ load v:p offset + cp regs
+        mov     ip, #0
+        mcr     p15, 0, ip, c7, c7, 0   @ invalidate I & D caches, BTB
+        mcr     p15, 0, ip, c7, c10, 4  @ drain write (&fill) buffer
+        mcr     p15, 0, ip, c7, c5, 4   @ flush prefetch buffer
+        mcr     p15, 0, ip, c8, c7, 0   @ invalidate I & D TLBs
+        mcr     p14, 0, r4, c6, c0, 0   @ clock configuration, turbo mode.
+        mcr     p15, 0, r5, c15, c1, 0  @ CP access reg
+        mcr     p15, 0, r6, c13, c0, 0  @ PID
+        mcr     p15, 0, r7, c3, c0, 0   @ domain ID
+        mcr     p15, 0, r8, c2, c0, 0   @ translation table base addr
+        mcr     p15, 0, r9, c1, c0, 1   @ auxiliary control reg
+
+        @ temporarily map resume_turn_on_mmu into the page table,
+        @ otherwise prefetch abort occurs after MMU is turned on
+        mov     r0, r10                 @ control register
+        mov     r2, r8, lsr #14         @ get TTB0 base
+        mov     r2, r2, lsl #14
+        ldr     r3, =0x542e             @ section flags
+        b       cpu_resume_mmu
+ENDPROC(cpu_xsc3_do_resume)
+#else
+#define cpu_xsc3_do_suspend     0
+#define cpu_xsc3_do_resume      0
+#endif
+
         __CPUINIT
 
         .type   __xsc3_setup, #function
@@ -476,6 +519,9 @@ ENTRY(xsc3_processor_functions)
         .word   cpu_xsc3_dcache_clean_area
         .word   cpu_xsc3_switch_mm
         .word   cpu_xsc3_set_pte_ext
+        .word   cpu_xsc3_suspend_size
+        .word   cpu_xsc3_do_suspend
+        .word   cpu_xsc3_do_resume
         .size   xsc3_processor_functions, . - xsc3_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 5a37c5e45c41..086038cd86ab 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -513,11 +513,49 @@ ENTRY(cpu_xscale_set_pte_ext)
         xscale_set_pte_ext_epilogue
         mov     pc, lr
 
-
         .ltorg
-
         .align
 
+.globl  cpu_xscale_suspend_size
+.equ    cpu_xscale_suspend_size, 4 * 7
+#ifdef CONFIG_PM
+ENTRY(cpu_xscale_do_suspend)
+        stmfd   sp!, {r4 - r10, lr}
+        mrc     p14, 0, r4, c6, c0, 0   @ clock configuration, for turbo mode
+        mrc     p15, 0, r5, c15, c1, 0  @ CP access reg
+        mrc     p15, 0, r6, c13, c0, 0  @ PID
+        mrc     p15, 0, r7, c3, c0, 0   @ domain ID
+        mrc     p15, 0, r8, c2, c0, 0   @ translation table base addr
+        mrc     p15, 0, r9, c1, c1, 0   @ auxiliary control reg
+        mrc     p15, 0, r10, c1, c0, 0  @ control reg
+        bic     r4, r4, #2              @ clear frequency change bit
+        stmia   r0, {r4 - r10}          @ store cp regs
+        ldmfd   sp!, {r4 - r10, pc}
+ENDPROC(cpu_xscale_do_suspend)
+
+ENTRY(cpu_xscale_do_resume)
+        ldmia   r0, {r4 - r10}          @ load cp regs
+        mov     ip, #0
+        mcr     p15, 0, ip, c8, c7, 0   @ invalidate I & D TLBs
+        mcr     p15, 0, ip, c7, c7, 0   @ invalidate I & D caches, BTB
+        mcr     p14, 0, r4, c6, c0, 0   @ clock configuration, turbo mode.
+        mcr     p15, 0, r5, c15, c1, 0  @ CP access reg
+        mcr     p15, 0, r6, c13, c0, 0  @ PID
+        mcr     p15, 0, r7, c3, c0, 0   @ domain ID
+        mcr     p15, 0, r8, c2, c0, 0   @ translation table base addr
+        mcr     p15, 0, r9, c1, c1, 0   @ auxiliary control reg
+        mov     r0, r10                 @ control register
+        mov     r2, r8, lsr #14         @ get TTB0 base
+        mov     r2, r2, lsl #14
+        ldr     r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
+                     PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE
+        b       cpu_resume_mmu
+ENDPROC(cpu_xscale_do_resume)
+#else
+#define cpu_xscale_do_suspend   0
+#define cpu_xscale_do_resume    0
+#endif
+
         __CPUINIT
 
         .type   __xscale_setup, #function
@@ -565,6 +603,9 @@ ENTRY(xscale_processor_functions)
         .word   cpu_xscale_dcache_clean_area
         .word   cpu_xscale_switch_mm
         .word   cpu_xscale_set_pte_ext
+        .word   cpu_xscale_suspend_size
+        .word   cpu_xscale_do_suspend
+        .word   cpu_xscale_do_resume
         .size   xscale_processor_functions, . - xscale_processor_functions
 
         .section ".rodata"
diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c
index 935993e1b1ef..036fdbfdd62f 100644
--- a/arch/arm/mm/vmregion.c
+++ b/arch/arm/mm/vmregion.c
@@ -38,7 +38,7 @@ struct arm_vmregion *
 arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
                    size_t size, gfp_t gfp)
 {
-        unsigned long addr = head->vm_start, end = head->vm_end - size;
+        unsigned long start = head->vm_start, addr = head->vm_end;
         unsigned long flags;
         struct arm_vmregion *c, *new;
 
@@ -54,21 +54,20 @@ arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
 
         spin_lock_irqsave(&head->vm_lock, flags);
 
-        list_for_each_entry(c, &head->vm_list, vm_list) {
-                if ((addr + size) < addr)
-                        goto nospc;
-                if ((addr + size) <= c->vm_start)
+        addr = rounddown(addr - size, align);
+        list_for_each_entry_reverse(c, &head->vm_list, vm_list) {
+                if (addr >= c->vm_end)
                         goto found;
-                addr = ALIGN(c->vm_end, align);
-                if (addr > end)
+                addr = rounddown(c->vm_start - size, align);
+                if (addr < start)
                         goto nospc;
         }
 
  found:
         /*
-         * Insert this entry _before_ the one we found.
+         * Insert this entry after the one we found.
          */
-        list_add_tail(&new->vm_list, &c->vm_list);
+        list_add(&new->vm_list, &c->vm_list);
         new->vm_start = addr;
         new->vm_end = addr + size;
         new->vm_active = 1;