18 files changed, 239 insertions, 105 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 749bb6622404..bc2d2d75f706 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -18,6 +18,7 @@
 #endif
 
 #include <asm/ptrace.h>
+#include <asm/domain.h>
 
 /*
  * Endian independent macros for shifting bytes within registers.
@@ -157,16 +158,24 @@
 #ifdef CONFIG_SMP
 #define ALT_SMP(instr...)                                       \
 9998:   instr
+/*
+ * Note: if you get assembler errors from ALT_UP() when building with
+ * CONFIG_THUMB2_KERNEL, you almost certainly need to use
+ * ALT_SMP( W(instr) ... )
+ */
 #define ALT_UP(instr...)                                        \
         .pushsection ".alt.smp.init", "a"                       ;\
         .long   9998b                                           ;\
-        instr                                                   ;\
+9997:   instr                                                   ;\
+        .if . - 9997b != 4                                      ;\
+                .error "ALT_UP() content must assemble to exactly 4 bytes";\
+        .endif                                                  ;\
         .popsection
 #define ALT_UP_B(label)                                 \
         .equ    up_b_offset, label - 9998b                      ;\
         .pushsection ".alt.smp.init", "a"                       ;\
         .long   9998b                                           ;\
-        b       . + up_b_offset                                 ;\
+        W(b)    . + up_b_offset                                 ;\
         .popsection
 #else
 #define ALT_SMP(instr...)
@@ -177,16 +186,24 @@
 /*
  * SMP data memory barrier
  */
-        .macro  smp_dmb
+        .macro  smp_dmb mode
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
+        .ifeqs "\mode","arm"
         ALT_SMP(dmb)
+        .else
+        ALT_SMP(W(dmb))
+        .endif
 #elif __LINUX_ARM_ARCH__ == 6
         ALT_SMP(mcr     p15, 0, r0, c7, c10, 5) @ dmb
 #else
 #error Incompatible SMP platform
 #endif
+        .ifeqs "\mode","arm"
         ALT_UP(nop)
+        .else
+        ALT_UP(W(nop))
+        .endif
 #endif
         .endm
 
@@ -206,12 +223,12 @@
  */
 #ifdef CONFIG_THUMB2_KERNEL
 
-        .macro  usraccoff, instr, reg, ptr, inc, off, cond, abort
+        .macro  usraccoff, instr, reg, ptr, inc, off, cond, abort, t=T()
 9999:
         .if     \inc == 1
-        \instr\cond\()bt \reg, [\ptr, #\off]
+        \instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
         .elseif \inc == 4
-        \instr\cond\()t \reg, [\ptr, #\off]
+        \instr\cond\()\t\().w \reg, [\ptr, #\off]
         .else
         .error  "Unsupported inc macro argument"
         .endif
@@ -246,13 +263,13 @@
 
 #else   /* !CONFIG_THUMB2_KERNEL */
 
-        .macro  usracc, instr, reg, ptr, inc, cond, rept, abort
+        .macro  usracc, instr, reg, ptr, inc, cond, rept, abort, t=T()
         .rept   \rept
 9999:
         .if     \inc == 1
-        \instr\cond\()bt \reg, [\ptr], #\inc
+        \instr\cond\()b\()\t \reg, [\ptr], #\inc
         .elseif \inc == 4
-        \instr\cond\()t \reg, [\ptr], #\inc
+        \instr\cond\()\t \reg, [\ptr], #\inc
         .else
         .error  "Unsupported inc macro argument"
         .endif
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index 9d6122096fbe..75fe66bc02b4 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -23,4 +23,6 @@
 #define ARCH_SLAB_MINALIGN 8
 #endif
 
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
 #endif
diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h
index b56c1389b6fa..765d33222369 100644
--- a/arch/arm/include/asm/clkdev.h
+++ b/arch/arm/include/asm/clkdev.h
@@ -12,23 +12,13 @@
 #ifndef __ASM_CLKDEV_H
 #define __ASM_CLKDEV_H
 
-struct clk;
-struct device;
+#include <linux/slab.h>
 
-struct clk_lookup {
-        struct list_head        node;
-        const char              *dev_id;
-        const char              *con_id;
-        struct clk              *clk;
-};
+#include <mach/clkdev.h>
 
-struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
-        const char *dev_fmt, ...);
-
-void clkdev_add(struct clk_lookup *cl);
-void clkdev_drop(struct clk_lookup *cl);
-
-void clkdev_add_table(struct clk_lookup *, size_t);
-int clk_add_alias(const char *, const char *, char *, struct device *);
+static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
+{
+        return kzalloc(size, GFP_KERNEL);
+}
 
 #endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index c568da7dcae4..4fff837363ed 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -5,24 +5,29 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
 
 #include <asm-generic/dma-coherent.h>
 #include <asm/memory.h>
 
+#ifdef __arch_page_to_dma
+#error Please update to __arch_pfn_to_dma
+#endif
+
 /*
- * page_to_dma/dma_to_virt/virt_to_dma are architecture private functions
- * used internally by the DMA-mapping API to provide DMA addresses. They
- * must not be used by drivers.
+ * dma_to_pfn/pfn_to_dma/dma_to_virt/virt_to_dma are architecture private
+ * functions used internally by the DMA-mapping API to provide DMA
+ * addresses. They must not be used by drivers.
  */
-#ifndef __arch_page_to_dma
-static inline dma_addr_t page_to_dma(struct device *dev, struct page *page)
+#ifndef __arch_pfn_to_dma
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-        return (dma_addr_t)__pfn_to_bus(page_to_pfn(page));
+        return (dma_addr_t)__pfn_to_bus(pfn);
 }
 
-static inline struct page *dma_to_page(struct device *dev, dma_addr_t addr)
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
-        return pfn_to_page(__bus_to_pfn(addr));
+        return __bus_to_pfn(addr);
 }
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
@@ -35,14 +40,14 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
         return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
 }
 #else
-static inline dma_addr_t page_to_dma(struct device *dev, struct page *page)
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-        return __arch_page_to_dma(dev, page);
+        return __arch_pfn_to_dma(dev, pfn);
 }
 
-static inline struct page *dma_to_page(struct device *dev, dma_addr_t addr)
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
-        return __arch_dma_to_page(dev, addr);
+        return __arch_dma_to_pfn(dev, addr);
 }
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
@@ -293,13 +298,13 @@ extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
 /*
  * The DMA API, implemented by dmabounce.c.  See below for descriptions.
  */
-extern dma_addr_t dma_map_single(struct device *, void *, size_t,
+extern dma_addr_t __dma_map_single(struct device *, void *, size_t,
                 enum dma_data_direction);
-extern void dma_unmap_single(struct device *, dma_addr_t, size_t,
+extern void __dma_unmap_single(struct device *, dma_addr_t, size_t,
                 enum dma_data_direction);
-extern dma_addr_t dma_map_page(struct device *, struct page *,
+extern dma_addr_t __dma_map_page(struct device *, struct page *,
                 unsigned long, size_t, enum dma_data_direction);
-extern void dma_unmap_page(struct device *, dma_addr_t, size_t,
+extern void __dma_unmap_page(struct device *, dma_addr_t, size_t,
                 enum dma_data_direction);
 
 /*
@@ -323,6 +328,34 @@ static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
 }
 
 
+static inline dma_addr_t __dma_map_single(struct device *dev, void *cpu_addr,
+                size_t size, enum dma_data_direction dir)
+{
+        __dma_single_cpu_to_dev(cpu_addr, size, dir);
+        return virt_to_dma(dev, cpu_addr);
+}
+
+static inline dma_addr_t __dma_map_page(struct device *dev, struct page *page,
+             unsigned long offset, size_t size, enum dma_data_direction dir)
+{
+        __dma_page_cpu_to_dev(page, offset, size, dir);
+        return pfn_to_dma(dev, page_to_pfn(page)) + offset;
+}
+
+static inline void __dma_unmap_single(struct device *dev, dma_addr_t handle,
+                size_t size, enum dma_data_direction dir)
+{
+        __dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir);
+}
+
+static inline void __dma_unmap_page(struct device *dev, dma_addr_t handle,
+                size_t size, enum dma_data_direction dir)
+{
+        __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
+                handle & ~PAGE_MASK, size, dir);
+}
+#endif /* CONFIG_DMABOUNCE */
+
 /**
  * dma_map_single - map a single buffer for streaming DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
@@ -340,11 +373,16 @@ static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
 static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
                 size_t size, enum dma_data_direction dir)
 {
+        dma_addr_t addr;
+
         BUG_ON(!valid_dma_direction(dir));
 
-        __dma_single_cpu_to_dev(cpu_addr, size, dir);
+        addr = __dma_map_single(dev, cpu_addr, size, dir);
+        debug_dma_map_page(dev, virt_to_page(cpu_addr),
+                        (unsigned long)cpu_addr & ~PAGE_MASK, size,
+                        dir, addr, true);
 
-        return virt_to_dma(dev, cpu_addr);
+        return addr;
 }
 
 /**
@@ -364,11 +402,14 @@ static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
 static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
              unsigned long offset, size_t size, enum dma_data_direction dir)
 {
+        dma_addr_t addr;
+
         BUG_ON(!valid_dma_direction(dir));
 
-        __dma_page_cpu_to_dev(page, offset, size, dir);
+        addr = __dma_map_page(dev, page, offset, size, dir);
+        debug_dma_map_page(dev, page, offset, size, dir, addr, false);
 
-        return page_to_dma(dev, page) + offset;
+        return addr;
 }
 
 /**
@@ -388,7 +429,8 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
 static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
                 size_t size, enum dma_data_direction dir)
 {
-        __dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir);
+        debug_dma_unmap_page(dev, handle, size, dir, true);
+        __dma_unmap_single(dev, handle, size, dir);
 }
 
 /**
@@ -408,10 +450,9 @@ static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
 static inline void dma_unmap_page(struct device *dev, dma_addr_t handle,
                 size_t size, enum dma_data_direction dir)
 {
-        __dma_page_dev_to_cpu(dma_to_page(dev, handle), handle & ~PAGE_MASK,
-                size, dir);
+        debug_dma_unmap_page(dev, handle, size, dir, false);
+        __dma_unmap_page(dev, handle, size, dir);
 }
-#endif /* CONFIG_DMABOUNCE */
 
 /**
  * dma_sync_single_range_for_cpu
@@ -437,6 +478,8 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
 {
         BUG_ON(!valid_dma_direction(dir));
 
+        debug_dma_sync_single_for_cpu(dev, handle + offset, size, dir);
+
         if (!dmabounce_sync_for_cpu(dev, handle, offset, size, dir))
                 return;
 
@@ -449,6 +492,8 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 {
         BUG_ON(!valid_dma_direction(dir));
 
+        debug_dma_sync_single_for_device(dev, handle + offset, size, dir);
+
         if (!dmabounce_sync_for_device(dev, handle, offset, size, dir))
                 return;
 
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index cc7ef4080711..af18ceaacf5d 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -45,13 +45,17 @@
  */
 #define DOMAIN_NOACCESS 0
 #define DOMAIN_CLIENT   1
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define DOMAIN_MANAGER  3
+#else
+#define DOMAIN_MANAGER  1
+#endif
 
 #define domain_val(dom,type)    ((type) << (2*(dom)))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define set_domain(x)                                   \
         do {                                            \
         __asm__ __volatile__(                           \
@@ -74,5 +78,28 @@
 #define modify_domain(dom,type) do { } while (0)
 #endif
 
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions (inline assembly)
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)        #instr "t"
+#else
+#define T(instr)        #instr
 #endif
-#endif /* !__ASSEMBLY__ */
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)        instr ## t
+#else
+#define T(instr)        instr
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* !__ASM_PROC_DOMAIN_H */
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
new file mode 100644
index 000000000000..ec0bbf79c71f
--- /dev/null
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -0,0 +1,44 @@
+/*
+ * Interrupt handling.  Preserves r7, r8, r9
+ */
+        .macro  arch_irq_handler_default
+        get_irqnr_preamble r5, lr
+1:      get_irqnr_and_base r0, r6, r5, lr
+        movne   r1, sp
+        @
+        @ routine called with r0 = irq number, r1 = struct pt_regs *
+        @
+        adrne   lr, BSYM(1b)
+        bne     asm_do_IRQ
+
+#ifdef CONFIG_SMP
+        /*
+         * XXX
+         *
+         * this macro assumes that irqstat (r6) and base (r5) are
+         * preserved from get_irqnr_and_base above
+         */
+        ALT_SMP(test_for_ipi r0, r6, r5, lr)
+        ALT_UP_B(9997f)
+        movne   r1, sp
+        adrne   lr, BSYM(1b)
+        bne     do_IPI
+
+#ifdef CONFIG_LOCAL_TIMERS
+        test_for_ltirq r0, r6, r5, lr
+        movne   r0, sp
+        adrne   lr, BSYM(1b)
+        bne     do_local_timer
+#endif
+#endif
+9997:
+        .endm
+
+        .macro  arch_irq_handler, symbol_name
+        .align  5
+        .global \symbol_name
+\symbol_name:
+        mov     r4, lr
+        arch_irq_handler_default
+        mov     pc, r4
+        .endm
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 540a044153a5..b33fe7065b38 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -13,12 +13,13 @@
 #include <linux/preempt.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)      \
         __asm__ __volatile__(                                   \
-        "1:     ldrt    %1, [%2]\n"                             \
+        "1:     " T(ldr) "      %1, [%2]\n"                     \
         "       " insn "\n"                                     \
-        "2:     strt    %0, [%2]\n"                             \
+        "2:     " T(str) "      %0, [%2]\n"                     \
         "       mov     %0, #0\n"                               \
         "3:\n"                                                  \
         "       .pushsection __ex_table,\"a\"\n"                \
@@ -97,10 +98,10 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
         pagefault_disable();    /* implies preempt_disable() */
 
         __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-        "1:     ldrt    %0, [%3]\n"
+        "1:     " T(ldr) "      %0, [%3]\n"
         "       teq     %0, %1\n"
         "       it      eq      @ explicit IT needed for the 2b label\n"
-        "2:     streqt  %2, [%3]\n"
+        "2:     " T(streq) "    %2, [%3]\n"
         "3:\n"
         "       .pushsection __ex_table,\"a\"\n"
         "       .align  3\n"
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 6d7485aff955..89ad1805e579 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,13 +5,31 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
+#define NR_IPI  5
+
 typedef struct {
         unsigned int __softirq_pending;
+#ifdef CONFIG_LOCAL_TIMERS
         unsigned int local_timer_irqs;
+#endif
+#ifdef CONFIG_SMP
+        unsigned int ipi_irqs[NR_IPI];
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>  /* Standard mappings for irq_cpustat_t above */
 
+#define __inc_irq_stat(cpu, member)     __IRQ_STAT(cpu, member)++
+#define __get_irq_stat(cpu, member)     __IRQ_STAT(cpu, member)
+
+#ifdef CONFIG_SMP
+u64 smp_irq_stat_cpu(unsigned int cpu);
+#else
+#define smp_irq_stat_cpu(cpu)   0
+#endif
+
+#define arch_irq_stat_cpu       smp_irq_stat_cpu
+
 #if NR_IRQS > 512
 #define HARDIRQ_BITS    10
 #elif NR_IRQS > 256
diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h
index 50c7e7cfd670..6bc63ab498ce 100644
--- a/arch/arm/include/asm/localtimer.h
+++ b/arch/arm/include/asm/localtimer.h
@@ -30,7 +30,6 @@ asmlinkage void do_local_timer(struct pt_regs *);
 #include "smp_twd.h"
 
 #define local_timer_ack()       twd_timer_ack()
-#define local_timer_stop()      twd_timer_stop()
 
 #else
 
@@ -40,11 +39,6 @@ asmlinkage void do_local_timer(struct pt_regs *);
  */
 int local_timer_ack(void);
 
-/*
- * Stop a local timer interrupt.
- */
-void local_timer_stop(void);
-
 #endif
 
 /*
@@ -52,12 +46,6 @@ void local_timer_stop(void);
  */
 void local_timer_setup(struct clock_event_device *);
 
-#else
-
-static inline void local_timer_stop(void)
-{
-}
-
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index d97a964207fa..3a0893a76a3b 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -37,12 +37,21 @@ struct machine_desc {
                                          struct meminfo *);
         void                    (*reserve)(void);/* reserve mem blocks  */
         void                    (*map_io)(void);/* IO mapping function  */
+        void                    (*init_early)(void);
         void                    (*init_irq)(void);
         struct sys_timer        *timer;         /* system tick timer    */
         void                    (*init_machine)(void);
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+        void                    (*handle_irq)(struct pt_regs *);
+#endif
 };
 
 /*
+ * Current machine - only accessible during boot.
+ */
+extern struct machine_desc *machine_desc;
+
+/*
  * Set of macros to define architecture features.  This is built into
  * a table by the linker.
  */
diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h
index ce3eee9fe26c..22ac140edd9e 100644
--- a/arch/arm/include/asm/mach/irq.h
+++ b/arch/arm/include/asm/mach/irq.h
@@ -17,10 +17,12 @@ struct seq_file;
 /*
  * This is internal.  Do not use it.
  */
-extern unsigned int arch_nr_irqs;
-extern void (*init_arch_irq)(void);
 extern void init_FIQ(void);
-extern int show_fiq_list(struct seq_file *, void *);
+extern int show_fiq_list(struct seq_file *, int);
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+extern void (*handle_arch_irq)(struct pt_regs *);
+#endif
 
 /*
  * This is for easy migration, but should be changed in the source
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index 35d408f6dccf..883f6be5117a 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -43,7 +43,6 @@ struct sys_timer {
 #endif
 };
 
-extern struct sys_timer *system_timer;
 extern void timer_tick(void);
 
 #endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 3d05190797cb..96ed521f2408 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -33,27 +33,23 @@ struct seq_file;
 /*
  * generate IPI list text
  */
-extern void show_ipi_list(struct seq_file *p);
+extern void show_ipi_list(struct seq_file *, int);
 
 /*
  * Called from assembly code, this handles an IPI.
  */
-asmlinkage void do_IPI(struct pt_regs *regs);
+asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
 
 /*
  * Setup the set of possible CPUs (via set_cpu_possible)
  */
 extern void smp_init_cpus(void);
 
-/*
- * Move global data into per-processor storage.
- */
-extern void smp_store_cpu_info(unsigned int cpuid);
 
 /*
  * Raise an IPI cross call on CPUs in callmap.
  */
-extern void smp_cross_call(const struct cpumask *mask);
+extern void smp_cross_call(const struct cpumask *mask, int ipi);
 
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
@@ -73,6 +69,11 @@ asmlinkage void secondary_start_kernel(void);
 extern void platform_secondary_init(unsigned int cpu);
 
 /*
+ * Initialize cpu_possible map, and enable coherency
+ */
+extern void platform_smp_prepare_cpus(unsigned int);
+
+/*
  * Initial data for bringing up a secondary CPU.
  */
 struct secondary_data {
@@ -97,6 +98,6 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 /*
  * show local interrupt info
  */
-extern void show_local_irqs(struct seq_file *);
+extern void show_local_irqs(struct seq_file *, int);
 
 #endif /* ifndef __ASM_ARM_SMP_H */
diff --git a/arch/arm/include/asm/smp_mpidr.h b/arch/arm/include/asm/smp_mpidr.h
deleted file mode 100644
index 6a9307d64900..000000000000
--- a/arch/arm/include/asm/smp_mpidr.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef ASMARM_SMP_MIDR_H
-#define ASMARM_SMP_MIDR_H
-
-#define hard_smp_processor_id()                                         \
-        ({                                                              \
-                unsigned int cpunum;                                    \
-                __asm__("\n"                                            \
-                        "1:     mrc p15, 0, %0, c0, c0, 5\n"            \
-                        "       .pushsection \".alt.smp.init\", \"a\"\n"\
-                        "       .long   1b\n"                           \
-                        "       mov     %0, #0\n"                       \
-                        "       .popsection"                            \
-                        : "=r" (cpunum));                               \
-                cpunum &= 0x0F;                                         \
-        })
-
-#endif
diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h
index 634f357be6bb..fed9981fba08 100644
--- a/arch/arm/include/asm/smp_twd.h
+++ b/arch/arm/include/asm/smp_twd.h
@@ -22,7 +22,6 @@ struct clock_event_device;
 
 extern void __iomem *twd_base;
 
-void twd_timer_stop(void);
 int twd_timer_ack(void);
 void twd_timer_setup(struct clock_event_device *);
 
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 3222ab8b3447..97f6d60297d5 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -124,6 +124,13 @@ extern unsigned int user_debug;
 #define vectors_high()  (0)
 #endif
 
+#if __LINUX_ARM_ARCH__ >= 7 ||          \
+        (__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K))
+#define sev()   __asm__ __volatile__ ("sev" : : : "memory")
+#define wfe()   __asm__ __volatile__ ("wfe" : : : "memory")
+#define wfi()   __asm__ __volatile__ ("wfi" : : : "memory")
+#endif
+
 #if __LINUX_ARM_ARCH__ >= 7
 #define isb() __asm__ __volatile__ ("isb" : : : "memory")
 #define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 124475afb007..1b960d5ef6a5 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -46,4 +46,6 @@ static inline int in_exception_text(unsigned long ptr)
 extern void __init early_trap_init(void);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 
+extern void *vectors_page;
+
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 33e4a48fe103..b293616a1a1a 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -227,7 +227,7 @@ do {									\
 
 #define __get_user_asm_byte(x,addr,err)                         \
         __asm__ __volatile__(                                   \
-        "1:     ldrbt   %1,[%2]\n"                              \
+        "1:     " T(ldrb) "     %1,[%2],#0\n"                   \
         "2:\n"                                                  \
         "       .pushsection .fixup,\"ax\"\n"                   \
         "       .align  2\n"                                    \
@@ -263,7 +263,7 @@ do {									\
 
 #define __get_user_asm_word(x,addr,err)                         \
         __asm__ __volatile__(                                   \
-        "1:     ldrt    %1,[%2]\n"                              \
+        "1:     " T(ldr) "      %1,[%2],#0\n"                   \
         "2:\n"                                                  \
         "       .pushsection .fixup,\"ax\"\n"                   \
         "       .align  2\n"                                    \
@@ -308,7 +308,7 @@ do {									\
 
 #define __put_user_asm_byte(x,__pu_addr,err)                    \
         __asm__ __volatile__(                                   \
-        "1:     strbt   %1,[%2]\n"                              \
+        "1:     " T(strb) "     %1,[%2],#0\n"                   \
         "2:\n"                                                  \
         "       .pushsection .fixup,\"ax\"\n"                   \
         "       .align  2\n"                                    \
@@ -341,7 +341,7 @@ do {									\
 
 #define __put_user_asm_word(x,__pu_addr,err)                    \
         __asm__ __volatile__(                                   \
-        "1:     strt    %1,[%2]\n"                              \
+        "1:     " T(str) "      %1,[%2],#0\n"                   \
         "2:\n"                                                  \
         "       .pushsection .fixup,\"ax\"\n"                   \
         "       .align  2\n"                                    \
@@ -366,10 +366,10 @@ do {									\
 
 #define __put_user_asm_dword(x,__pu_addr,err)                   \
         __asm__ __volatile__(                                   \
- ARM(   "1:     strt    " __reg_oper1 ", [%1], #4\n"    )       \
- ARM(   "2:     strt    " __reg_oper0 ", [%1]\n"        )       \
- THUMB( "1:     strt    " __reg_oper1 ", [%1]\n"        )       \
- THUMB( "2:     strt    " __reg_oper0 ", [%1, #4]\n"    )       \
+ ARM(   "1:     " T(str) "      " __reg_oper1 ", [%1], #4\n"    )       \
+ ARM(   "2:     " T(str) "      " __reg_oper0 ", [%1]\n"        )       \
+ THUMB( "1:     " T(str) "      " __reg_oper1 ", [%1]\n"        )       \
+ THUMB( "2:     " T(str) "      " __reg_oper0 ", [%1, #4]\n"    )       \
         "3:\n"                                                  \
         "       .pushsection .fixup,\"ax\"\n"                   \
         "       .align  2\n"                                    \