Merge branch 'x86/asm' into x86/atomic

Merge reason:
	Conflict between LOCK_PREFIX_HERE and relative alternatives
	pointers

Resolved Conflicts:
	arch/x86/include/asm/alternative.h
	arch/x86/kernel/alternative.c

Signed-off-by: H. Peter Anvin <hpa@zytor.com>

36 files changed, 742 insertions, 197 deletions

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index d0daeab2234..e8ddec2cb15 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -235,6 +235,234 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 #define smp_mb__before_atomic_inc()     smp_mb()
 #define smp_mb__after_atomic_inc()      smp_mb()
 
+#ifndef CONFIG_GENERIC_ATOMIC64
+typedef struct {
+        u64 __aligned(8) counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(i) { (i) }
+
+static inline u64 atomic64_read(atomic64_t *v)
+{
+        u64 result;
+
+        __asm__ __volatile__("@ atomic64_read\n"
+"       ldrexd  %0, %H0, [%1]"
+        : "=&r" (result)
+        : "r" (&v->counter)
+        );
+
+        return result;
+}
+
+static inline void atomic64_set(atomic64_t *v, u64 i)
+{
+        u64 tmp;
+
+        __asm__ __volatile__("@ atomic64_set\n"
+"1:     ldrexd  %0, %H0, [%1]\n"
+"       strexd  %0, %2, %H2, [%1]\n"
+"       teq     %0, #0\n"
+"       bne     1b"
+        : "=&r" (tmp)
+        : "r" (&v->counter), "r" (i)
+        : "cc");
+}
+
+static inline void atomic64_add(u64 i, atomic64_t *v)
+{
+        u64 result;
+        unsigned long tmp;
+
+        __asm__ __volatile__("@ atomic64_add\n"
+"1:     ldrexd  %0, %H0, [%2]\n"
+"       adds    %0, %0, %3\n"
+"       adc     %H0, %H0, %H3\n"
+"       strexd  %1, %0, %H0, [%2]\n"
+"       teq     %1, #0\n"
+"       bne     1b"
+        : "=&r" (result), "=&r" (tmp)
+        : "r" (&v->counter), "r" (i)
+        : "cc");
+}
+
+static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+{
+        u64 result;
+        unsigned long tmp;
+
+        smp_mb();
+
+        __asm__ __volatile__("@ atomic64_add_return\n"
+"1:     ldrexd  %0, %H0, [%2]\n"
+"       adds    %0, %0, %3\n"
+"       adc     %H0, %H0, %H3\n"
+"       strexd  %1, %0, %H0, [%2]\n"
+"       teq     %1, #0\n"
+"       bne     1b"
+        : "=&r" (result), "=&r" (tmp)
+        : "r" (&v->counter), "r" (i)
+        : "cc");
+
+        smp_mb();
+
+        return result;
+}
+
+static inline void atomic64_sub(u64 i, atomic64_t *v)
+{
+        u64 result;
+        unsigned long tmp;
+
+        __asm__ __volatile__("@ atomic64_sub\n"
+"1:     ldrexd  %0, %H0, [%2]\n"
+"       subs    %0, %0, %3\n"
+"       sbc     %H0, %H0, %H3\n"
+"       strexd  %1, %0, %H0, [%2]\n"
+"       teq     %1, #0\n"
+"       bne     1b"
+        : "=&r" (result), "=&r" (tmp)
+        : "r" (&v->counter), "r" (i)
+        : "cc");
+}
+
+static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
+{
+        u64 result;
+        unsigned long tmp;
+
+        smp_mb();
+
+        __asm__ __volatile__("@ atomic64_sub_return\n"
+"1:     ldrexd  %0, %H0, [%2]\n"
+"       subs    %0, %0, %3\n"
+"       sbc     %H0, %H0, %H3\n"
+"       strexd  %1, %0, %H0, [%2]\n"
+"       teq     %1, #0\n"
+"       bne     1b"
+        : "=&r" (result), "=&r" (tmp)
+        : "r" (&v->counter), "r" (i)
+        : "cc");
+
+        smp_mb();
+
+        return result;
+}
+
+static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
+{
+        u64 oldval;
+        unsigned long res;
+
+        smp_mb();
+
+        do {
+                __asm__ __volatile__("@ atomic64_cmpxchg\n"
+                "ldrexd         %1, %H1, [%2]\n"
+                "mov            %0, #0\n"
+                "teq            %1, %3\n"
+                "teqeq          %H1, %H3\n"
+                "strexdeq       %0, %4, %H4, [%2]"
+                : "=&r" (res), "=&r" (oldval)
+                : "r" (&ptr->counter), "r" (old), "r" (new)
+                : "cc");
+        } while (res);
+
+        smp_mb();
+
+        return oldval;
+}
+
+static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
+{
+        u64 result;
+        unsigned long tmp;
+
+        smp_mb();
+
+        __asm__ __volatile__("@ atomic64_xchg\n"
+"1:     ldrexd  %0, %H0, [%2]\n"
+"       strexd  %1, %3, %H3, [%2]\n"
+"       teq     %1, #0\n"
+"       bne     1b"
+        : "=&r" (result), "=&r" (tmp)
+        : "r" (&ptr->counter), "r" (new)
+        : "cc");
+
+        smp_mb();
+
+        return result;
+}
+
+static inline u64 atomic64_dec_if_positive(atomic64_t *v)
+{
+        u64 result;
+        unsigned long tmp;
+
+        smp_mb();
+
+        __asm__ __volatile__("@ atomic64_dec_if_positive\n"
+"1:     ldrexd  %0, %H0, [%2]\n"
+"       subs    %0, %0, #1\n"
+"       sbc     %H0, %H0, #0\n"
+"       teq     %H0, #0\n"
+"       bmi     2f\n"
+"       strexd  %1, %0, %H0, [%2]\n"
+"       teq     %1, #0\n"
+"       bne     1b\n"
+"2:"
+        : "=&r" (result), "=&r" (tmp)
+        : "r" (&v->counter)
+        : "cc");
+
+        smp_mb();
+
+        return result;
+}
+
+static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+{
+        u64 val;
+        unsigned long tmp;
+        int ret = 1;
+
+        smp_mb();
+
+        __asm__ __volatile__("@ atomic64_add_unless\n"
+"1:     ldrexd  %0, %H0, [%3]\n"
+"       teq     %0, %4\n"
+"       teqeq   %H0, %H4\n"
+"       moveq   %1, #0\n"
+"       beq     2f\n"
+"       adds    %0, %0, %5\n"
+"       adc     %H0, %H0, %H5\n"
+"       strexd  %2, %0, %H0, [%3]\n"
+"       teq     %2, #0\n"
+"       bne     1b\n"
+"2:"
+        : "=&r" (val), "=&r" (ret), "=&r" (tmp)
+        : "r" (&v->counter), "r" (u), "r" (a)
+        : "cc");
+
+        if (ret)
+                smp_mb();
+
+        return ret;
+}
+
+#define atomic64_add_negative(a, v)     (atomic64_add_return((a), (v)) < 0)
+#define atomic64_inc(v)                 atomic64_add(1LL, (v))
+#define atomic64_inc_return(v)          atomic64_add_return(1LL, (v))
+#define atomic64_inc_and_test(v)        (atomic64_inc_return(v) == 0)
+#define atomic64_sub_and_test(a, v)     (atomic64_sub_return((a), (v)) == 0)
+#define atomic64_dec(v)                 atomic64_sub(1LL, (v))
+#define atomic64_dec_return(v)          atomic64_sub_return(1LL, (v))
+#define atomic64_dec_and_test(v)        (atomic64_dec_return((v)) == 0)
+#define atomic64_inc_not_zero(v)        atomic64_add_unless((v), 1LL, 0LL)
+
+#else /* !CONFIG_GENERIC_ATOMIC64 */
+#include <asm-generic/atomic64.h>
+#endif
 #include <asm-generic/atomic-long.h>
 #endif
 #endif
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 730aefcfbee..0d08d4170b6 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -15,6 +15,7 @@
 #include <asm/glue.h>
 #include <asm/shmparam.h>
 #include <asm/cachetype.h>
+#include <asm/outercache.h>
 
 #define CACHE_COLOUR(vaddr)     ((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
 
@@ -42,7 +43,8 @@
 #endif
 
 #if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \
-    defined(CONFIG_CPU_ARM925T) || defined(CONFIG_CPU_ARM1020)
+    defined(CONFIG_CPU_ARM925T) || defined(CONFIG_CPU_ARM1020) || \
+    defined(CONFIG_CPU_ARM1026)
 # define MULTI_CACHE 1
 #endif
 
@@ -154,16 +156,16 @@
  *      Please note that the implementation of these, and the required
  *      effects are cache-type (VIVT/VIPT/PIPT) specific.
  *
- *      flush_cache_kern_all()
+ *      flush_kern_all()
  *
  *              Unconditionally clean and invalidate the entire cache.
  *
- *      flush_cache_user_mm(mm)
+ *      flush_user_all()
  *
  *              Clean and invalidate all user space cache entries
  *              before a change of page tables.
  *
- *      flush_cache_user_range(start, end, flags)
+ *      flush_user_range(start, end, flags)
  *
  *              Clean and invalidate a range of cache entries in the
  *              specified address space before a change of page tables.
@@ -179,23 +181,22 @@
  *              - start  - virtual start address
  *              - end    - virtual end address
  *
- *      DMA Cache Coherency
- *      ===================
- *
- *      dma_inv_range(start, end)
+ *      coherent_user_range(start, end)
  *
- *              Invalidate (discard) the specified virtual address range.
- *              May not write back any entries.  If 'start' or 'end'
- *              are not cache line aligned, those lines must be written
- *              back.
+ *              Ensure coherency between the Icache and the Dcache in the
+ *              region described by start, end.  If you have non-snooping
+ *              Harvard caches, you need to implement this function.
  *              - start  - virtual start address
  *              - end    - virtual end address
  *
- *      dma_clean_range(start, end)
+ *      flush_kern_dcache_area(kaddr, size)
  *
- *              Clean (write back) the specified virtual address range.
- *              - start  - virtual start address
- *              - end    - virtual end address
+ *              Ensure that the data held in page is written back.
+ *              - kaddr  - page address
+ *              - size   - region size
+ *
+ *      DMA Cache Coherency
+ *      ===================
  *
  *      dma_flush_range(start, end)
  *
@@ -213,15 +214,10 @@ struct cpu_cache_fns {
         void (*coherent_user_range)(unsigned long, unsigned long);
         void (*flush_kern_dcache_area)(void *, size_t);
 
-        void (*dma_inv_range)(const void *, const void *);
-        void (*dma_clean_range)(const void *, const void *);
-        void (*dma_flush_range)(const void *, const void *);
-};
+        void (*dma_map_area)(const void *, size_t, int);
+        void (*dma_unmap_area)(const void *, size_t, int);
 
-struct outer_cache_fns {
-        void (*inv_range)(unsigned long, unsigned long);
-        void (*clean_range)(unsigned long, unsigned long);
-        void (*flush_range)(unsigned long, unsigned long);
+        void (*dma_flush_range)(const void *, const void *);
 };
 
 /*
@@ -244,8 +240,8 @@ extern struct cpu_cache_fns cpu_cache;
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-#define dmac_inv_range                  cpu_cache.dma_inv_range
-#define dmac_clean_range                cpu_cache.dma_clean_range
+#define dmac_map_area                   cpu_cache.dma_map_area
+#define dmac_unmap_area         cpu_cache.dma_unmap_area
 #define dmac_flush_range                cpu_cache.dma_flush_range
 
 #else
@@ -270,58 +266,23 @@ extern void __cpuc_flush_dcache_area(void *, size_t);
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-#define dmac_inv_range                  __glue(_CACHE,_dma_inv_range)
-#define dmac_clean_range                __glue(_CACHE,_dma_clean_range)
+#define dmac_map_area                   __glue(_CACHE,_dma_map_area)
+#define dmac_unmap_area         __glue(_CACHE,_dma_unmap_area)
 #define dmac_flush_range                __glue(_CACHE,_dma_flush_range)
 
-extern void dmac_inv_range(const void *, const void *);
-extern void dmac_clean_range(const void *, const void *);
+extern void dmac_map_area(const void *, size_t, int);
+extern void dmac_unmap_area(const void *, size_t, int);
 extern void dmac_flush_range(const void *, const void *);
 
 #endif
 
-#ifdef CONFIG_OUTER_CACHE
-
-extern struct outer_cache_fns outer_cache;
-
-static inline void outer_inv_range(unsigned long start, unsigned long end)
-{
-        if (outer_cache.inv_range)
-                outer_cache.inv_range(start, end);
-}
-static inline void outer_clean_range(unsigned long start, unsigned long end)
-{
-        if (outer_cache.clean_range)
-                outer_cache.clean_range(start, end);
-}
-static inline void outer_flush_range(unsigned long start, unsigned long end)
-{
-        if (outer_cache.flush_range)
-                outer_cache.flush_range(start, end);
-}
-
-#else
-
-static inline void outer_inv_range(unsigned long start, unsigned long end)
-{ }
-static inline void outer_clean_range(unsigned long start, unsigned long end)
-{ }
-static inline void outer_flush_range(unsigned long start, unsigned long end)
-{ }
-
-#endif
-
 /*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
  * space" model to handle this.
  */
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-        do {                                                    \
-                memcpy(dst, src, len);                          \
-                flush_ptrace_access(vma, page, vaddr, dst, len, 1);\
-        } while (0)
-
+extern void copy_to_user_page(struct vm_area_struct *, struct page *,
+        unsigned long, void *, const void *, unsigned long);
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
         do {                                                    \
                 memcpy(dst, src, len);                          \
@@ -355,17 +316,6 @@ vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig
         }
 }
 
-static inline void
-vivt_flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
-                         unsigned long uaddr, void *kaddr,
-                         unsigned long len, int write)
-{
-        if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-                unsigned long addr = (unsigned long)kaddr;
-                __cpuc_coherent_kern_range(addr, addr + len);
-        }
-}
-
 #ifndef CONFIG_CPU_CACHE_VIPT
 #define flush_cache_mm(mm) \
                 vivt_flush_cache_mm(mm)
@@ -373,15 +323,10 @@ vivt_flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
                 vivt_flush_cache_range(vma,start,end)
 #define flush_cache_page(vma,addr,pfn) \
                 vivt_flush_cache_page(vma,addr,pfn)
-#define flush_ptrace_access(vma,page,ua,ka,len,write) \
-                vivt_flush_ptrace_access(vma,page,ua,ka,len,write)
 #else
 extern void flush_cache_mm(struct mm_struct *mm);
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn);
-extern void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
-                                unsigned long uaddr, void *kaddr,
-                                unsigned long len, int write);
 #endif
 
 #define flush_cache_dup_mm(mm) flush_cache_mm(mm)
@@ -432,6 +377,16 @@ static inline void __flush_icache_all(void)
             : "r" (0));
 #endif
 }
+static inline void flush_kernel_vmap_range(void *addr, int size)
+{
+        if ((cache_is_vivt() || cache_is_vipt_aliasing()))
+          __cpuc_flush_dcache_area(addr, (size_t)size);
+}
+static inline void invalidate_kernel_vmap_range(void *addr, int size)
+{
+        if ((cache_is_vivt() || cache_is_vipt_aliasing()))
+          __cpuc_flush_dcache_area(addr, (size_t)size);
+}
 
 #define ARCH_HAS_FLUSH_ANON_PAGE
 static inline void flush_anon_page(struct vm_area_struct *vma,
diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h
index b6ec7c627b3..b56c1389b6f 100644
--- a/arch/arm/include/asm/clkdev.h
+++ b/arch/arm/include/asm/clkdev.h
@@ -13,6 +13,7 @@
 #define __ASM_CLKDEV_H
 
 struct clk;
+struct device;
 
 struct clk_lookup {
         struct list_head        node;
@@ -27,4 +28,7 @@ struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
 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 *);
+
 #endif
diff --git a/arch/arm/include/asm/cpu.h b/arch/arm/include/asm/cpu.h
index 634b2d7c612..793968173be 100644
--- a/arch/arm/include/asm/cpu.h
+++ b/arch/arm/include/asm/cpu.h
@@ -11,6 +11,7 @@
 #define __ASM_ARM_CPU_H
 
 #include <linux/percpu.h>
+#include <linux/cpu.h>
 
 struct cpuinfo_arm {
         struct cpu      cpu;
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index a96300bf83f..69ce0727edb 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -57,18 +57,58 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 #endif
 
 /*
- * DMA-consistent mapping functions.  These allocate/free a region of
- * uncached, unwrite-buffered mapped memory space for use with DMA
- * devices.  This is the "generic" version.  The PCI specific version
- * is in pci.h
+ * The DMA API is built upon the notion of "buffer ownership".  A buffer
+ * is either exclusively owned by the CPU (and therefore may be accessed
+ * by it) or exclusively owned by the DMA device.  These helper functions
+ * represent the transitions between these two ownership states.
  *
- * Note: Drivers should NOT use this function directly, as it will break
- * platforms with CONFIG_DMABOUNCE.
- * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
+ * Note, however, that on later ARMs, this notion does not work due to
+ * speculative prefetches.  We model our approach on the assumption that
+ * the CPU does do speculative prefetches, which means we clean caches
+ * before transfers and delay cache invalidation until transfer completion.
+ *
+ * Private support functions: these are not part of the API and are
+ * liable to change.  Drivers must not use these.
  */
-extern void dma_cache_maint(const void *kaddr, size_t size, int rw);
-extern void dma_cache_maint_page(struct page *page, unsigned long offset,
-                                 size_t size, int rw);
+static inline void __dma_single_cpu_to_dev(const void *kaddr, size_t size,
+        enum dma_data_direction dir)
+{
+        extern void ___dma_single_cpu_to_dev(const void *, size_t,
+                enum dma_data_direction);
+
+        if (!arch_is_coherent())
+                ___dma_single_cpu_to_dev(kaddr, size, dir);
+}
+
+static inline void __dma_single_dev_to_cpu(const void *kaddr, size_t size,
+        enum dma_data_direction dir)
+{
+        extern void ___dma_single_dev_to_cpu(const void *, size_t,
+                enum dma_data_direction);
+
+        if (!arch_is_coherent())
+                ___dma_single_dev_to_cpu(kaddr, size, dir);
+}
+
+static inline void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
+        size_t size, enum dma_data_direction dir)
+{
+        extern void ___dma_page_cpu_to_dev(struct page *, unsigned long,
+                size_t, enum dma_data_direction);
+
+        if (!arch_is_coherent())
+                ___dma_page_cpu_to_dev(page, off, size, dir);
+}
+
+static inline void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
+        size_t size, enum dma_data_direction dir)
+{
+        extern void ___dma_page_dev_to_cpu(struct page *, unsigned long,
+                size_t, enum dma_data_direction);
+
+        if (!arch_is_coherent())
+                ___dma_page_dev_to_cpu(page, off, size, dir);
+}
 
 /*
  * Return whether the given device DMA address mask can be supported
@@ -88,6 +128,14 @@ static inline int dma_supported(struct device *dev, u64 mask)
 
 static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 {
+#ifdef CONFIG_DMABOUNCE
+        if (dev->archdata.dmabounce) {
+                if (dma_mask >= ISA_DMA_THRESHOLD)
+                        return 0;
+                else
+                        return -EIO;
+        }
+#endif
         if (!dev->dma_mask || !dma_supported(dev, dma_mask))
                 return -EIO;
 
@@ -304,8 +352,7 @@ static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
 {
         BUG_ON(!valid_dma_direction(dir));
 
-        if (!arch_is_coherent())
-                dma_cache_maint(cpu_addr, size, dir);
+        __dma_single_cpu_to_dev(cpu_addr, size, dir);
 
         return virt_to_dma(dev, cpu_addr);
 }
@@ -329,8 +376,7 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
 {
         BUG_ON(!valid_dma_direction(dir));
 
-        if (!arch_is_coherent())
-                dma_cache_maint_page(page, offset, size, dir);
+        __dma_page_cpu_to_dev(page, offset, size, dir);
 
         return page_to_dma(dev, page) + offset;
 }
@@ -352,7 +398,7 @@ 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)
 {
-        /* nothing to do */
+        __dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir);
 }
 
 /**
@@ -372,7 +418,8 @@ 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)
 {
-        /* nothing to do */
+        __dma_page_dev_to_cpu(dma_to_page(dev, handle), handle & ~PAGE_MASK,
+                size, dir);
 }
 #endif /* CONFIG_DMABOUNCE */
 
@@ -400,7 +447,10 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
 {
         BUG_ON(!valid_dma_direction(dir));
 
-        dmabounce_sync_for_cpu(dev, handle, offset, size, dir);
+        if (!dmabounce_sync_for_cpu(dev, handle, offset, size, dir))
+                return;
+
+        __dma_single_dev_to_cpu(dma_to_virt(dev, handle) + offset, size, dir);
 }
 
 static inline void dma_sync_single_range_for_device(struct device *dev,
@@ -412,8 +462,7 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
         if (!dmabounce_sync_for_device(dev, handle, offset, size, dir))
                 return;
 
-        if (!arch_is_coherent())
-                dma_cache_maint(dma_to_virt(dev, handle) + offset, size, dir);
+        __dma_single_cpu_to_dev(dma_to_virt(dev, handle) + offset, size, dir);
 }
 
 static inline void dma_sync_single_for_cpu(struct device *dev,
diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index 7edf3536df2..ca51143f97f 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -138,12 +138,12 @@ extern int  get_dma_residue(unsigned int chan);
 #define NO_DMA  255
 #endif
 
+#endif /* CONFIG_ISA_DMA_API */
+
 #ifdef CONFIG_PCI
 extern int isa_dma_bridge_buggy;
 #else
 #define isa_dma_bridge_buggy    (0)
 #endif
 
-#endif /* CONFIG_ISA_DMA_API */
-
 #endif /* __ASM_ARM_DMA_H */
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index a399bb5730f..bff056489cc 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -98,6 +98,7 @@ extern int elf_check_arch(const struct elf32_hdr *);
 extern int arm_elf_read_implies_exec(const struct elf32_hdr *, int);
 #define elf_read_implies_exec(ex,stk) arm_elf_read_implies_exec(&(ex), stk)
 
+struct task_struct;
 int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
 #define ELF_CORE_COPY_TASK_REGS dump_task_regs
 
diff --git a/arch/arm/include/asm/entry-macro-vic2.S b/arch/arm/include/asm/entry-macro-vic2.S
new file mode 100644
index 00000000000..3ceb85e4385
--- /dev/null
+++ b/arch/arm/include/asm/entry-macro-vic2.S
@@ -0,0 +1,57 @@
+/* arch/arm/include/asm/entry-macro-vic2.S
+ *
+ * Originally arch/arm/mach-s3c6400/include/mach/entry-macro.S
+ *
+ * Copyright 2008 Openmoko, Inc.
+ * Copyright 2008 Simtec Electronics
+ *      http://armlinux.simtec.co.uk/
+ *      Ben Dooks <ben@simtec.co.uk>
+ *
+ * Low-level IRQ helper macros for a device with two VICs
+ *
+ * This file is licensed under  the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+*/
+
+/* This should be included from <mach/entry-macro.S> with the necessary
+ * defines for virtual addresses and IRQ bases for the two vics.
+ *
+ * The code needs the following defined:
+ *      IRQ_VIC0_BASE   IRQ number of VIC0's first IRQ
+ *      IRQ_VIC1_BASE   IRQ number of VIC1's first IRQ
+ *      VA_VIC0         Virtual address of VIC0
+ *      VA_VIC1         Virtual address of VIC1
+ *
+ * Note, code assumes VIC0's virtual address is an ARM immediate constant
+ * away from VIC1.
+*/
+
+#include <asm/hardware/vic.h>
+
+        .macro  disable_fiq
+        .endm
+
+        .macro  get_irqnr_preamble, base, tmp
+        ldr     \base, =VA_VIC0
+        .endm
+
+        .macro  arch_ret_to_user, tmp1, tmp2
+        .endm
+
+        .macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
+
+        @ check the vic0
+        mov     \irqnr, #IRQ_VIC0_BASE + 31
+        ldr     \irqstat, [ \base, # VIC_IRQ_STATUS ]
+        teq     \irqstat, #0
+
+        @ otherwise try vic1
+        addeq   \tmp, \base, #(VA_VIC1 - VA_VIC0)
+        addeq   \irqnr, \irqnr, #(IRQ_VIC1_BASE - IRQ_VIC0_BASE)
+        ldreq   \irqstat, [ \tmp, # VIC_IRQ_STATUS ]
+        teqeq   \irqstat, #0
+
+        clzne   \irqstat, \irqstat
+        subne   \irqnr, \irqnr, \irqstat
+        .endm
diff --git a/arch/arm/include/asm/hardware/iop3xx-adma.h b/arch/arm/include/asm/hardware/iop3xx-adma.h
index 1a8c7279a28..9b28f1243bd 100644
--- a/arch/arm/include/asm/hardware/iop3xx-adma.h
+++ b/arch/arm/include/asm/hardware/iop3xx-adma.h
@@ -366,8 +366,7 @@ static inline int iop_chan_xor_slot_count(size_t len, int src_cnt,
                 slot_cnt += *slots_per_op;
         }
 
-        if (len)
-                slot_cnt += *slots_per_op;
+        slot_cnt += *slots_per_op;
 
         return slot_cnt;
 }
@@ -389,8 +388,7 @@ static inline int iop_chan_zero_sum_slot_count(size_t len, int src_cnt,
                 slot_cnt += *slots_per_op;
         }
 
-        if (len)
-                slot_cnt += *slots_per_op;
+        slot_cnt += *slots_per_op;
 
         return slot_cnt;
 }
@@ -737,10 +735,8 @@ iop_desc_set_zero_sum_byte_count(struct iop_adma_desc_slot *desc, u32 len)
                         i += slots_per_op;
                 } while (len > IOP_ADMA_ZERO_SUM_MAX_BYTE_COUNT);
 
-                if (len) {
-                        iter = iop_hw_desc_slot_idx(hw_desc, i);
-                        iter->byte_count = len;
-                }
+                iter = iop_hw_desc_slot_idx(hw_desc, i);
+                iter->byte_count = len;
         }
 }
 
diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h
index 74b5fff7f57..6700c7fc7eb 100644
--- a/arch/arm/include/asm/hardware/it8152.h
+++ b/arch/arm/include/asm/hardware/it8152.h
@@ -75,6 +75,18 @@ extern unsigned long it8152_base_address;
   IT8152_PD_IRQ(1)  USB (USBR)
   IT8152_PD_IRQ(0)  Audio controller (ACR)
  */
+#define IT8152_IRQ(x)   (IRQ_BOARD_END + (x))
+
+/* IRQ-sources in 3 groups - local devices, LPC (serial), and external PCI */
+#define IT8152_LD_IRQ_COUNT     9
+#define IT8152_LP_IRQ_COUNT     16
+#define IT8152_PD_IRQ_COUNT     15
+
+/* Priorities: */
+#define IT8152_PD_IRQ(i)        IT8152_IRQ(i)
+#define IT8152_LP_IRQ(i)        (IT8152_IRQ(i) + IT8152_PD_IRQ_COUNT)
+#define IT8152_LD_IRQ(i)        (IT8152_IRQ(i) + IT8152_PD_IRQ_COUNT + IT8152_LP_IRQ_COUNT)
+
 /* frequently used interrupts */
 #define IT8152_PCISERR          IT8152_PD_IRQ(14)
 #define IT8152_H2PTADR          IT8152_PD_IRQ(13)
diff --git a/arch/arm/include/asm/hardware/locomo.h b/arch/arm/include/asm/hardware/locomo.h
index 954b1be991b..74e51d6bd93 100644
--- a/arch/arm/include/asm/hardware/locomo.h
+++ b/arch/arm/include/asm/hardware/locomo.h
@@ -214,4 +214,8 @@ void locomo_m62332_senddata(struct locomo_dev *ldev, unsigned int dac_data, int
 /* Frontlight control */
 void locomo_frontlight_set(struct locomo_dev *dev, int duty, int vr, int bpwf);
 
+struct locomo_platform_data {
+        int     irq_base;       /* IRQ base for cascaded on-chip IRQs */
+};
+
 #endif
diff --git a/arch/arm/include/asm/hardware/sa1111.h b/arch/arm/include/asm/hardware/sa1111.h
index 5da2595759e..92ed254c175 100644
--- a/arch/arm/include/asm/hardware/sa1111.h
+++ b/arch/arm/include/asm/hardware/sa1111.h
@@ -578,4 +578,8 @@ void sa1111_set_io_dir(struct sa1111_dev *sadev, unsigned int bits, unsigned int
 void sa1111_set_io(struct sa1111_dev *sadev, unsigned int bits, unsigned int v);
 void sa1111_set_sleep_io(struct sa1111_dev *sadev, unsigned int bits, unsigned int v);
 
+struct sa1111_platform_data {
+        int     irq_base;       /* base for cascaded on-chip IRQs */
+};
+
 #endif  /* _ASM_ARCH_SA1111 */
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index 7f36d00600b..feb988a7ec3 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -11,7 +11,11 @@
 
 #define kmap_prot               PAGE_KERNEL
 
-#define flush_cache_kmaps()     flush_cache_all()
+#define flush_cache_kmaps() \
+        do { \
+                if (cache_is_vivt()) \
+                        flush_cache_all(); \
+        } while (0)
 
 extern pte_t *pkmap_page_table;
 
@@ -21,11 +25,20 @@ extern void *kmap_high(struct page *page);
 extern void *kmap_high_get(struct page *page);
 extern void kunmap_high(struct page *page);
 
+extern void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte);
+extern void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte);
+
+/*
+ * The following functions are already defined by <linux/highmem.h>
+ * when CONFIG_HIGHMEM is not set.
+ */
+#ifdef CONFIG_HIGHMEM
 extern void *kmap(struct page *page);
 extern void kunmap(struct page *page);
 extern void *kmap_atomic(struct page *page, enum km_type type);
 extern void kunmap_atomic(void *kvaddr, enum km_type type);
 extern void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
 extern struct page *kmap_atomic_to_page(const void *ptr);
+#endif
 
 #endif
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index d2a59cfc30c..c980156f326 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -69,9 +69,16 @@ extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
 /*
  * __arm_ioremap takes CPU physical address.
  * __arm_ioremap_pfn takes a Page Frame Number and an offset into that page
+ * The _caller variety takes a __builtin_return_address(0) value for
+ * /proc/vmalloc to use - and should only be used in non-inline functions.
  */
-extern void __iomem * __arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem * __arm_ioremap(unsigned long, size_t, unsigned int);
+extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
+        size_t, unsigned int, void *);
+extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int,
+        void *);
+
+extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
+extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int);
 extern void __iounmap(volatile void __iomem *addr);
 
 /*
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 328f14a8b79..237282f7c76 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -17,6 +17,7 @@
 
 #ifndef __ASSEMBLY__
 struct irqaction;
+struct pt_regs;
 extern void migrate_irqs(void);
 
 extern void asm_do_IRQ(unsigned int, struct pt_regs *);
diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h
index c019949a518..c4b2ea3fbe4 100644
--- a/arch/arm/include/asm/kmap_types.h
+++ b/arch/arm/include/asm/kmap_types.h
@@ -18,6 +18,7 @@ enum km_type {
         KM_IRQ1,
         KM_SOFTIRQ0,
         KM_SOFTIRQ1,
+        KM_L1_CACHE,
         KM_L2_CACHE,
         KM_TYPE_NR
 };
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index b2cc1fcd040..8bffc3ff3ac 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -46,12 +46,4 @@ struct sys_timer {
 extern struct sys_timer *system_timer;
 extern void timer_tick(void);
 
-/*
- * Kernel time keeping support.
- */
-struct timespec;
-extern int (*set_rtc)(void);
-extern void save_time_delta(struct timespec *delta, struct timespec *rtc);
-extern void restore_time_delta(struct timespec *delta, struct timespec *rtc);
-
 #endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 5421d82a257..4312ee5e3d0 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -76,6 +76,17 @@
  */
 #define IOREMAP_MAX_ORDER       24
 
+/*
+ * Size of DMA-consistent memory region.  Must be multiple of 2M,
+ * between 2MB and 14MB inclusive.
+ */
+#ifndef CONSISTENT_DMA_SIZE
+#define CONSISTENT_DMA_SIZE     SZ_2M
+#endif
+
+#define CONSISTENT_END          (0xffe00000UL)
+#define CONSISTENT_BASE         (CONSISTENT_END - CONSISTENT_DMA_SIZE)
+
 #else /* CONFIG_MMU */
 
 /*
@@ -93,11 +104,11 @@
 #endif
 
 #ifndef PHYS_OFFSET
-#define PHYS_OFFSET             (CONFIG_DRAM_BASE)
+#define PHYS_OFFSET             UL(CONFIG_DRAM_BASE)
 #endif
 
 #ifndef END_MEM
-#define END_MEM                 (CONFIG_DRAM_BASE + CONFIG_DRAM_SIZE)
+#define END_MEM                 (UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
 #endif
 
 #ifndef PAGE_OFFSET
@@ -113,14 +124,6 @@
 #endif /* !CONFIG_MMU */
 
 /*
- * Size of DMA-consistent memory region.  Must be multiple of 2M,
- * between 2MB and 14MB inclusive.
- */
-#ifndef CONSISTENT_DMA_SIZE
-#define CONSISTENT_DMA_SIZE SZ_2M
-#endif
-
-/*
  * Physical vs virtual RAM address space conversion.  These are
  * private definitions which should NOT be used outside memory.h
  * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index b561584d04a..68870c77667 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -6,6 +6,7 @@
 typedef struct {
 #ifdef CONFIG_CPU_HAS_ASID
         unsigned int id;
+        spinlock_t id_lock;
 #endif
         unsigned int kvm_seq;
 } mm_context_t;
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index de6cefb329d..a0b3cac0547 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -43,12 +43,23 @@ void __check_kvm_seq(struct mm_struct *mm);
 #define ASID_FIRST_VERSION      (1 << ASID_BITS)
 
 extern unsigned int cpu_last_asid;
+#ifdef CONFIG_SMP
+DECLARE_PER_CPU(struct mm_struct *, current_mm);
+#endif
 
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void __new_context(struct mm_struct *mm);
 
 static inline void check_context(struct mm_struct *mm)
 {
+        /*
+         * This code is executed with interrupts enabled. Therefore,
+         * mm->context.id cannot be updated to the latest ASID version
+         * on a different CPU (and condition below not triggered)
+         * without first getting an IPI to reset the context. The
+         * alternative is to take a read_lock on mm->context.id_lock
+         * (after changing its type to rwlock_t).
+         */
         if (unlikely((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
                 __new_context(mm);
 
@@ -108,6 +119,10 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
                 __flush_icache_all();
 #endif
         if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
+#ifdef CONFIG_SMP
+                struct mm_struct **crt_mm = &per_cpu(current_mm, cpu);
+                *crt_mm = next;
+#endif
                 check_context(next);
                 cpu_switch_mm(next->pgd, next);
                 if (cache_is_vivt())
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
new file mode 100644
index 00000000000..25f76bae57a
--- /dev/null
+++ b/arch/arm/include/asm/outercache.h
@@ -0,0 +1,75 @@
+/*
+ * arch/arm/include/asm/outercache.h
+ *
+ * Copyright (C) 2010 ARM Ltd.
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_OUTERCACHE_H
+#define __ASM_OUTERCACHE_H
+
+struct outer_cache_fns {
+        void (*inv_range)(unsigned long, unsigned long);
+        void (*clean_range)(unsigned long, unsigned long);
+        void (*flush_range)(unsigned long, unsigned long);
+#ifdef CONFIG_OUTER_CACHE_SYNC
+        void (*sync)(void);
+#endif
+};
+
+#ifdef CONFIG_OUTER_CACHE
+
+extern struct outer_cache_fns outer_cache;
+
+static inline void outer_inv_range(unsigned long start, unsigned long end)
+{
+        if (outer_cache.inv_range)
+                outer_cache.inv_range(start, end);
+}
+static inline void outer_clean_range(unsigned long start, unsigned long end)
+{
+        if (outer_cache.clean_range)
+                outer_cache.clean_range(start, end);
+}
+static inline void outer_flush_range(unsigned long start, unsigned long end)
+{
+        if (outer_cache.flush_range)
+                outer_cache.flush_range(start, end);
+}
+
+#else
+
+static inline void outer_inv_range(unsigned long start, unsigned long end)
+{ }
+static inline void outer_clean_range(unsigned long start, unsigned long end)
+{ }
+static inline void outer_flush_range(unsigned long start, unsigned long end)
+{ }
+
+#endif
+
+#ifdef CONFIG_OUTER_CACHE_SYNC
+static inline void outer_sync(void)
+{
+        if (outer_cache.sync)
+                outer_cache.sync();
+}
+#else
+static inline void outer_sync(void)
+{ }
+#endif
+
+#endif  /* __ASM_OUTERCACHE_H */
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 3a32af4cce3..a485ac3c869 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -117,11 +117,12 @@
 #endif
 
 struct page;
+struct vm_area_struct;
 
 struct cpu_user_fns {
         void (*cpu_clear_user_highpage)(struct page *page, unsigned long vaddr);
         void (*cpu_copy_user_highpage)(struct page *to, struct page *from,
-                        unsigned long vaddr);
+                        unsigned long vaddr, struct vm_area_struct *vma);
 };
 
 #ifdef MULTI_USER
@@ -137,7 +138,7 @@ extern struct cpu_user_fns cpu_user;
 
 extern void __cpu_clear_user_highpage(struct page *page, unsigned long vaddr);
 extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
-                        unsigned long vaddr);
+                        unsigned long vaddr, struct vm_area_struct *vma);
 #endif
 
 #define clear_user_highpage(page,vaddr)         \
@@ -145,7 +146,7 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
 
 #define __HAVE_ARCH_COPY_USER_HIGHPAGE
 #define copy_user_highpage(to,from,vaddr,vma)   \
-        __cpu_copy_user_highpage(to, from, vaddr)
+        __cpu_copy_user_highpage(to, from, vaddr, vma)
 
 #define clear_page(page)        memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index 226cddd2fb6..47980118d0a 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -30,17 +30,6 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
  */
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
-/*
- * Whether pci_unmap_{single,page} is a nop depends upon the
- * configuration.
- */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       dma_addr_t ADDR_NAME;
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)         __u32 LEN_NAME;
-#define pci_unmap_addr(PTR, ADDR_NAME)          ((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) (((PTR)->ADDR_NAME) = (VAL))
-#define pci_unmap_len(PTR, LEN_NAME)            ((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)   (((PTR)->LEN_NAME) = (VAL))
-
 #ifdef CONFIG_PCI
 static inline void pci_dma_burst_advice(struct pci_dev *pdev,
                                         enum pci_dma_burst_strategy *strat,
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
new file mode 100644
index 00000000000..49e3049aba3
--- /dev/null
+++ b/arch/arm/include/asm/perf_event.h
@@ -0,0 +1,31 @@
+/*
+ *  linux/arch/arm/include/asm/perf_event.h
+ *
+ *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __ARM_PERF_EVENT_H__
+#define __ARM_PERF_EVENT_H__
+
+/*
+ * NOP: on *most* (read: all supported) ARM platforms, the performance
+ * counter interrupts are regular interrupts and not an NMI. This
+ * means that when we receive the interrupt we can call
+ * perf_event_do_pending() that handles all of the work with
+ * interrupts enabled.
+ */
+static inline void
+set_perf_event_pending(void)
+{
+}
+
+/* ARM performance counters start from 1 (in the cp15 accesses) so use the
+ * same indexes here for consistency. */
+#define PERF_EVENT_INDEX_OFFSET 1
+
+#endif /* __ARM_PERF_EVENT_H__ */
diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h
index b011f2e939a..ffc0e85775b 100644
--- a/arch/arm/include/asm/pgtable-nommu.h
+++ b/arch/arm/include/asm/pgtable-nommu.h
@@ -67,6 +67,7 @@ static inline int pte_file(pte_t pte) { return 0; }
  */
 #define pgprot_noncached(prot)  __pgprot(0)
 #define pgprot_writecombine(prot) __pgprot(0)
+#define pgprot_dmacoherent(prot) __pgprot(0)
 
 
 /*
@@ -86,8 +87,8 @@ extern unsigned int kobjsize(const void *objp);
  * All 32bit addresses are effectively valid for vmalloc...
  * Sort of meaningless for non-VM targets.
  */
-#define VMALLOC_START   0
-#define VMALLOC_END     0xffffffff
+#define VMALLOC_START   0UL
+#define VMALLOC_END     0xffffffffUL
 
 #define FIRST_USER_ADDRESS      (0)
 
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
new file mode 100644
index 00000000000..2829b9f981a
--- /dev/null
+++ b/arch/arm/include/asm/pmu.h
@@ -0,0 +1,75 @@
+/*
+ *  linux/arch/arm/include/asm/pmu.h
+ *
+ *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __ARM_PMU_H__
+#define __ARM_PMU_H__
+
+#ifdef CONFIG_CPU_HAS_PMU
+
+struct pmu_irqs {
+        const int   *irqs;
+        int         num_irqs;
+};
+
+/**
+ * reserve_pmu() - reserve the hardware performance counters
+ *
+ * Reserve the hardware performance counters in the system for exclusive use.
+ * The 'struct pmu_irqs' for the system is returned on success, ERR_PTR()
+ * encoded error on failure.
+ */
+extern const struct pmu_irqs *
+reserve_pmu(void);
+
+/**
+ * release_pmu() - Relinquish control of the performance counters
+ *
+ * Release the performance counters and allow someone else to use them.
+ * Callers must have disabled the counters and released IRQs before calling
+ * this. The 'struct pmu_irqs' returned from reserve_pmu() must be passed as
+ * a cookie.
+ */
+extern int
+release_pmu(const struct pmu_irqs *irqs);
+
+/**
+ * init_pmu() - Initialise the PMU.
+ *
+ * Initialise the system ready for PMU enabling. This should typically set the
+ * IRQ affinity and nothing else. The users (oprofile/perf events etc) will do
+ * the actual hardware initialisation.
+ */
+extern int
+init_pmu(void);
+
+#else /* CONFIG_CPU_HAS_PMU */
+
+static inline const struct pmu_irqs *
+reserve_pmu(void)
+{
+        return ERR_PTR(-ENODEV);
+}
+
+static inline int
+release_pmu(const struct pmu_irqs *irqs)
+{
+        return -ENODEV;
+}
+
+static inline int
+init_pmu(void)
+{
+        return -ENODEV;
+}
+
+#endif /* CONFIG_CPU_HAS_PMU */
+
+#endif /* __ARM_PMU_H__ */
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index bbecccda76d..9dcb11e5902 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -97,9 +97,15 @@
  * stack during a system call.  Note that sizeof(struct pt_regs)
  * has to be a multiple of 8.
  */
+#ifndef __KERNEL__
 struct pt_regs {
         long uregs[18];
 };
+#else /* __KERNEL__ */
+struct pt_regs {
+        unsigned long uregs[18];
+};
+#endif /* __KERNEL__ */
 
 #define ARM_cpsr        uregs[16]
 #define ARM_pc          uregs[15]
@@ -122,6 +128,8 @@ struct pt_regs {
 
 #ifdef __KERNEL__
 
+#define arch_has_single_step()  (1)
+
 #define user_mode(regs) \
         (((regs)->ARM_cpsr & 0xf) == 0)
 
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 5ccce0a9b03..f392fb4437a 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -223,18 +223,6 @@ extern struct meminfo meminfo;
 #define bank_phys_end(bank)     ((bank)->start + (bank)->size)
 #define bank_phys_size(bank)    (bank)->size
 
-/*
- * Early command line parameters.
- */
-struct early_params {
-        const char *arg;
-        void (*fn)(char **p);
-};
-
-#define __early_param(name,fn)                                  \
-static struct early_params __early_##fn __used                  \
-__attribute__((__section__(".early_param.init"))) = { name, fn }
-
 #endif  /*  __KERNEL__  */
 
 #endif
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 59303e20084..e6215305544 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -13,4 +13,9 @@ static inline int tlb_ops_need_broadcast(void)
         return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
 }
 
+static inline int cache_ops_need_broadcast(void)
+{
+        return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 1;
+}
+
 #endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index c91c64cab92..17eb355707d 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -5,6 +5,22 @@
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
+static inline void dsb_sev(void)
+{
+#if __LINUX_ARM_ARCH__ >= 7
+        __asm__ __volatile__ (
+                "dsb\n"
+                "sev"
+        );
+#elif defined(CONFIG_CPU_32v6K)
+        __asm__ __volatile__ (
+                "mcr p15, 0, %0, c7, c10, 4\n"
+                "sev"
+                : : "r" (0)
+        );
+#endif
+}
+
 /*
  * ARMv6 Spin-locking.
  *
@@ -69,13 +85,11 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
         __asm__ __volatile__(
 "       str     %1, [%0]\n"
-#ifdef CONFIG_CPU_32v6K
-"       mcr     p15, 0, %1, c7, c10, 4\n" /* DSB */
-"       sev"
-#endif
         :
         : "r" (&lock->lock), "r" (0)
         : "cc");
+
+        dsb_sev();
 }
 
 /*
@@ -132,13 +146,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 
         __asm__ __volatile__(
         "str    %1, [%0]\n"
-#ifdef CONFIG_CPU_32v6K
-"       mcr     p15, 0, %1, c7, c10, 4\n" /* DSB */
-"       sev\n"
-#endif
         :
         : "r" (&rw->lock), "r" (0)
         : "cc");
+
+        dsb_sev();
 }
 
 /* write_can_lock - would write_trylock() succeed? */
@@ -188,14 +200,12 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 "       strex   %1, %0, [%2]\n"
 "       teq     %1, #0\n"
 "       bne     1b"
-#ifdef CONFIG_CPU_32v6K
-"\n     cmp     %0, #0\n"
-"       mcreq   p15, 0, %0, c7, c10, 4\n"
-"       seveq"
-#endif
         : "=&r" (tmp), "=&r" (tmp2)
         : "r" (&rw->lock)
         : "cc");
+
+        if (tmp == 0)
+                dsb_sev();
 }
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 058e7e90881..4ace45ec3ef 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -60,6 +60,8 @@
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
 
+#include <asm/outercache.h>
+
 #define __exception     __attribute__((section(".exception.text")))
 
 struct thread_info;
@@ -73,8 +75,7 @@ extern unsigned int mem_fclk_21285;
 
 struct pt_regs;
 
-void die(const char *msg, struct pt_regs *regs, int err)
-                __attribute__((noreturn));
+void die(const char *msg, struct pt_regs *regs, int err);
 
 struct siginfo;
 void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
@@ -138,10 +139,12 @@ extern unsigned int user_debug;
 #define dmb() __asm__ __volatile__ ("" : : : "memory")
 #endif
 
-#if __LINUX_ARM_ARCH__ >= 7 || defined(CONFIG_SMP)
-#define mb()            dmb()
+#ifdef CONFIG_ARCH_HAS_BARRIERS
+#include <mach/barriers.h>
+#elif __LINUX_ARM_ARCH__ >= 7 || defined(CONFIG_SMP)
+#define mb()            do { dsb(); outer_sync(); } while (0)
 #define rmb()           dmb()
-#define wmb()           dmb()
+#define wmb()           mb()
 #else
 #define mb()    do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
 #define rmb()   do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
@@ -153,9 +156,9 @@ extern unsigned int user_debug;
 #define smp_rmb()       barrier()
 #define smp_wmb()       barrier()
 #else
-#define smp_mb()        mb()
-#define smp_rmb()       rmb()
-#define smp_wmb()       wmb()
+#define smp_mb()        dmb()
+#define smp_rmb()       dmb()
+#define smp_wmb()       dmb()
 #endif
 
 #define read_barrier_depends()          do { } while(0)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 2dfb7d7a66e..b74970ec02c 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -115,7 +115,8 @@ extern void iwmmxt_task_restore(struct thread_info *, void *);
 extern void iwmmxt_task_release(struct thread_info *);
 extern void iwmmxt_task_switch(struct thread_info *);
 
-extern void vfp_sync_state(struct thread_info *thread);
+extern void vfp_sync_hwstate(struct thread_info *);
+extern void vfp_flush_hwstate(struct thread_info *);
 
 #endif
 
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index c2f1605de35..e085e2c545e 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -529,7 +529,8 @@ extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
  * cache entries for the kernels virtual memory range are written
  * back to the page.
  */
-extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t pte);
+extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
+        pte_t *ptep);
 
 #endif
 
diff --git a/arch/arm/include/asm/ucontext.h b/arch/arm/include/asm/ucontext.h
index bf65e9f4525..47f023aa849 100644
--- a/arch/arm/include/asm/ucontext.h
+++ b/arch/arm/include/asm/ucontext.h
@@ -59,23 +59,22 @@ struct iwmmxt_sigframe {
 #endif /* CONFIG_IWMMXT */
 
 #ifdef CONFIG_VFP
-#if __LINUX_ARM_ARCH__ < 6
-/* For ARM pre-v6, we use fstmiax and fldmiax.  This adds one extra
- * word after the registers, and a word of padding at the end for
- * alignment.  */
 #define VFP_MAGIC               0x56465001
-#define VFP_STORAGE_SIZE        152
-#else
-#define VFP_MAGIC               0x56465002
-#define VFP_STORAGE_SIZE        144
-#endif
 
 struct vfp_sigframe
 {
         unsigned long           magic;
         unsigned long           size;
-        union vfp_state         storage;
-};
+        struct user_vfp         ufp;
+        struct user_vfp_exc     ufp_exc;
+} __attribute__((__aligned__(8)));
+
+/*
+ *  8 byte for magic and size, 264 byte for ufp, 12 bytes for ufp_exc,
+ *  4 bytes padding.
+ */
+#define VFP_STORAGE_SIZE        sizeof(struct vfp_sigframe)
+
 #endif /* CONFIG_VFP */
 
 /*
@@ -91,7 +90,7 @@ struct aux_sigframe {
 #ifdef CONFIG_IWMMXT
         struct iwmmxt_sigframe  iwmmxt;
 #endif
-#if 0 && defined CONFIG_VFP /* Not yet saved.  */
+#ifdef CONFIG_VFP
         struct vfp_sigframe     vfp;
 #endif
         /* Something that isn't a valid magic number for any coprocessor.  */
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 4e506d09e5f..dd2bf53000f 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -391,6 +391,7 @@
 #define __NR_pwritev                    (__NR_SYSCALL_BASE+362)
 #define __NR_rt_tgsigqueueinfo          (__NR_SYSCALL_BASE+363)
 #define __NR_perf_event_open            (__NR_SYSCALL_BASE+364)
+#define __NR_recvmmsg                   (__NR_SYSCALL_BASE+365)
 
 /*
  * The following SWIs are ARM private.
@@ -442,9 +443,12 @@
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#define __ARCH_WANT_SYS_OLD_MMAP
+#define __ARCH_WANT_SYS_OLD_SELECT
 
 #if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT)
 #define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_SYS_IPC
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_UTIME
diff --git a/arch/arm/include/asm/user.h b/arch/arm/include/asm/user.h
index df95e050f9d..05ac4b06876 100644
--- a/arch/arm/include/asm/user.h
+++ b/arch/arm/include/asm/user.h
@@ -83,11 +83,21 @@ struct user{
 
 /*
  * User specific VFP registers. If only VFPv2 is present, registers 16 to 31
- * are ignored by the ptrace system call.
+ * are ignored by the ptrace system call and the signal handler.
  */
 struct user_vfp {
         unsigned long long fpregs[32];
         unsigned long fpscr;
 };
 
+/*
+ * VFP exception registers exposed to user space during signal delivery.
+ * Fields not relavant to the current VFP architecture are ignored.
+ */
+struct user_vfp_exc {
+        unsigned long   fpexc;
+        unsigned long   fpinst;
+        unsigned long   fpinst2;
+};
+
 #endif /* _ARM_USER_H */