6 files changed, 257 insertions, 19 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 6116e4893c0a..15f8a092b700 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -114,3 +114,16 @@
         .align  3;                              \
         .long   9999b,9001f;                    \
         .previous
+
+/*
+ * SMP data memory barrier
+ */
+        .macro  smp_dmb
+#ifdef CONFIG_SMP
+#if __LINUX_ARM_ARCH__ >= 7
+        dmb
+#elif __LINUX_ARM_ARCH__ == 6
+        mcr     p15, 0, r0, c7, c10, 5  @ dmb
+#endif
+#endif
+        .endm
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index ee99723b3a6c..16b52f397983 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -44,11 +44,29 @@ static inline void atomic_set(atomic_t *v, int i)
         : "cc");
 }
 
+static inline void atomic_add(int i, atomic_t *v)
+{
+        unsigned long tmp;
+        int result;
+
+        __asm__ __volatile__("@ atomic_add\n"
+"1:     ldrex   %0, [%2]\n"
+"       add     %0, %0, %3\n"
+"       strex   %1, %0, [%2]\n"
+"       teq     %1, #0\n"
+"       bne     1b"
+        : "=&r" (result), "=&r" (tmp)
+        : "r" (&v->counter), "Ir" (i)
+        : "cc");
+}
+
 static inline int atomic_add_return(int i, atomic_t *v)
 {
         unsigned long tmp;
         int result;
 
+        smp_mb();
+
         __asm__ __volatile__("@ atomic_add_return\n"
 "1:     ldrex   %0, [%2]\n"
 "       add     %0, %0, %3\n"
@@ -59,14 +77,34 @@ static inline int atomic_add_return(int i, atomic_t *v)
         : "r" (&v->counter), "Ir" (i)
         : "cc");
 
+        smp_mb();
+
         return result;
 }
 
+static inline void atomic_sub(int i, atomic_t *v)
+{
+        unsigned long tmp;
+        int result;
+
+        __asm__ __volatile__("@ atomic_sub\n"
+"1:     ldrex   %0, [%2]\n"
+"       sub     %0, %0, %3\n"
+"       strex   %1, %0, [%2]\n"
+"       teq     %1, #0\n"
+"       bne     1b"
+        : "=&r" (result), "=&r" (tmp)
+        : "r" (&v->counter), "Ir" (i)
+        : "cc");
+}
+
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
         unsigned long tmp;
         int result;
 
+        smp_mb();
+
         __asm__ __volatile__("@ atomic_sub_return\n"
 "1:     ldrex   %0, [%2]\n"
 "       sub     %0, %0, %3\n"
@@ -77,6 +115,8 @@ static inline int atomic_sub_return(int i, atomic_t *v)
         : "r" (&v->counter), "Ir" (i)
         : "cc");
 
+        smp_mb();
+
         return result;
 }
 
@@ -84,6 +124,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 {
         unsigned long oldval, res;
 
+        smp_mb();
+
         do {
                 __asm__ __volatile__("@ atomic_cmpxchg\n"
                 "ldrex  %1, [%2]\n"
@@ -95,6 +137,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
                     : "cc");
         } while (res);
 
+        smp_mb();
+
         return oldval;
 }
 
@@ -135,6 +179,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
 
         return val;
 }
+#define atomic_add(i, v)        (void) atomic_add_return(i, v)
 
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
@@ -148,6 +193,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 
         return val;
 }
+#define atomic_sub(i, v)        (void) atomic_sub_return(i, v)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
@@ -187,10 +233,8 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 }
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
-#define atomic_add(i, v)        (void) atomic_add_return(i, v)
-#define atomic_inc(v)           (void) atomic_add_return(1, v)
-#define atomic_sub(i, v)        (void) atomic_sub_return(i, v)
-#define atomic_dec(v)           (void) atomic_sub_return(1, v)
+#define atomic_inc(v)           atomic_add(1, v)
+#define atomic_dec(v)           atomic_sub(1, v)
 
 #define atomic_inc_and_test(v)  (atomic_add_return(1, v) == 0)
 #define atomic_dec_and_test(v)  (atomic_sub_return(1, v) == 0)
@@ -200,11 +244,10 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 
 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
 
-/* Atomic operations are already serializing on ARM */
-#define smp_mb__before_atomic_dec()     barrier()
-#define smp_mb__after_atomic_dec()      barrier()
-#define smp_mb__before_atomic_inc()     barrier()
-#define smp_mb__after_atomic_inc()      barrier()
+#define smp_mb__before_atomic_dec()     smp_mb()
+#define smp_mb__after_atomic_dec()      smp_mb()
+#define smp_mb__before_atomic_inc()     smp_mb()
+#define smp_mb__after_atomic_inc()      smp_mb()
 
 #include <asm-generic/atomic.h>
 #endif
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index cb7a9e97fd7e..feaa75f0013e 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -7,4 +7,20 @@
 #define L1_CACHE_SHIFT          5
 #define L1_CACHE_BYTES          (1 << L1_CACHE_SHIFT)
 
+/*
+ * Memory returned by kmalloc() may be used for DMA, so we must make
+ * sure that all such allocations are cache aligned. Otherwise,
+ * unrelated code may cause parts of the buffer to be read into the
+ * cache before the transfer is done, causing old data to be seen by
+ * the CPU.
+ */
+#define ARCH_KMALLOC_MINALIGN   L1_CACHE_BYTES
+
+/*
+ * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
+ */
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
+#define ARCH_SLAB_MINALIGN 8
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h
index 1d77e51907f6..59426a4595c9 100644
--- a/arch/arm/include/asm/flat.h
+++ b/arch/arm/include/asm/flat.h
@@ -5,9 +5,6 @@
 #ifndef __ARM_FLAT_H__
 #define __ARM_FLAT_H__
 
-/* An odd number of words will be pushed after this alignment, so
-   deliberately misalign the value.  */
-#define flat_stack_align(sp)    sp = (void *)(((unsigned long)(sp) - 4) | 4)
 #define flat_argvp_envp_on_stack()              1
 #define flat_old_ram_flag(flags)                (flags)
 #define flat_reloc_valid(reloc, size)           ((reloc) <= (size))
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index e6eb8a67b807..7b522770f29d 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -202,13 +202,6 @@ typedef struct page *pgtable_t;
         (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
          VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
-/*
- * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
- */
-#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
-#define ARCH_SLAB_MINALIGN 8
-#endif
-
 #include <asm-generic/page.h>
 
 #endif
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index bd4dc8ed53d5..d65b2f5bf41f 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -248,6 +248,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
         unsigned int tmp;
 #endif
 
+        smp_mb();
+
         switch (size) {
 #if __LINUX_ARM_ARCH__ >= 6
         case 1:
@@ -307,6 +309,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
                 __bad_xchg(ptr, size), ret = 0;
                 break;
         }
+        smp_mb();
 
         return ret;
 }
@@ -316,6 +319,12 @@ extern void enable_hlt(void);
 
 #include <asm-generic/cmpxchg-local.h>
 
+#if __LINUX_ARM_ARCH__ < 6
+
+#ifdef CONFIG_SMP
+#error "SMP is not supported on this platform"
+#endif
+
 /*
  * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
  * them available.
@@ -329,6 +338,173 @@ extern void enable_hlt(void);
 #include <asm-generic/cmpxchg.h>
 #endif
 
+#else   /* __LINUX_ARM_ARCH__ >= 6 */
+
+extern void __bad_cmpxchg(volatile void *ptr, int size);
+
+/*
+ * cmpxchg only support 32-bits operands on ARMv6.
+ */
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+                                      unsigned long new, int size)
+{
+        unsigned long oldval, res;
+
+        switch (size) {
+#ifdef CONFIG_CPU_32v6K
+        case 1:
+                do {
+                        asm volatile("@ __cmpxchg1\n"
+                        "       ldrexb  %1, [%2]\n"
+                        "       mov     %0, #0\n"
+                        "       teq     %1, %3\n"
+                        "       strexbeq %0, %4, [%2]\n"
+                                : "=&r" (res), "=&r" (oldval)
+                                : "r" (ptr), "Ir" (old), "r" (new)
+                                : "memory", "cc");
+                } while (res);
+                break;
+        case 2:
+                do {
+                        asm volatile("@ __cmpxchg1\n"
+                        "       ldrexh  %1, [%2]\n"
+                        "       mov     %0, #0\n"
+                        "       teq     %1, %3\n"
+                        "       strexheq %0, %4, [%2]\n"
+                                : "=&r" (res), "=&r" (oldval)
+                                : "r" (ptr), "Ir" (old), "r" (new)
+                                : "memory", "cc");
+                } while (res);
+                break;
+#endif /* CONFIG_CPU_32v6K */
+        case 4:
+                do {
+                        asm volatile("@ __cmpxchg4\n"
+                        "       ldrex   %1, [%2]\n"
+                        "       mov     %0, #0\n"
+                        "       teq     %1, %3\n"
+                        "       strexeq %0, %4, [%2]\n"
+                                : "=&r" (res), "=&r" (oldval)
+                                : "r" (ptr), "Ir" (old), "r" (new)
+                                : "memory", "cc");
+                } while (res);
+                break;
+        default:
+                __bad_cmpxchg(ptr, size);
+                oldval = 0;
+        }
+
+        return oldval;
+}
+
+static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
+                                         unsigned long new, int size)
+{
+        unsigned long ret;
+
+        smp_mb();
+        ret = __cmpxchg(ptr, old, new, size);
+        smp_mb();
+
+        return ret;
+}
+
+#define cmpxchg(ptr,o,n)                                                \
+        ((__typeof__(*(ptr)))__cmpxchg_mb((ptr),                        \
+                                          (unsigned long)(o),           \
+                                          (unsigned long)(n),           \
+                                          sizeof(*(ptr))))
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+                                            unsigned long old,
+                                            unsigned long new, int size)
+{
+        unsigned long ret;
+
+        switch (size) {
+#ifndef CONFIG_CPU_32v6K
+        case 1:
+        case 2:
+                ret = __cmpxchg_local_generic(ptr, old, new, size);
+                break;
+#endif  /* !CONFIG_CPU_32v6K */
+        default:
+                ret = __cmpxchg(ptr, old, new, size);
+        }
+
+        return ret;
+}
+
+#define cmpxchg_local(ptr,o,n)                                          \
+        ((__typeof__(*(ptr)))__cmpxchg_local((ptr),                     \
+                                       (unsigned long)(o),              \
+                                       (unsigned long)(n),              \
+                                       sizeof(*(ptr))))
+
+#ifdef CONFIG_CPU_32v6K
+
+/*
+ * Note : ARMv7-M (currently unsupported by Linux) does not support
+ * ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should
+ * not be allowed to use __cmpxchg64.
+ */
+static inline unsigned long long __cmpxchg64(volatile void *ptr,
+                                             unsigned long long old,
+                                             unsigned long long new)
+{
+        register unsigned long long oldval asm("r0");
+        register unsigned long long __old asm("r2") = old;
+        register unsigned long long __new asm("r4") = new;
+        unsigned long res;
+
+        do {
+                asm volatile(
+                "       @ __cmpxchg8\n"
+                "       ldrexd  %1, %H1, [%2]\n"
+                "       mov     %0, #0\n"
+                "       teq     %1, %3\n"
+                "       teqeq   %H1, %H3\n"
+                "       strexdeq %0, %4, %H4, [%2]\n"
+                        : "=&r" (res), "=&r" (oldval)
+                        : "r" (ptr), "Ir" (__old), "r" (__new)
+                        : "memory", "cc");
+        } while (res);
+
+        return oldval;
+}
+
+static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
+                                                unsigned long long old,
+                                                unsigned long long new)
+{
+        unsigned long long ret;
+
+        smp_mb();
+        ret = __cmpxchg64(ptr, old, new);
+        smp_mb();
+
+        return ret;
+}
+
+#define cmpxchg64(ptr,o,n)                                              \
+        ((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),                      \
+                                            (unsigned long long)(o),    \
+                                            (unsigned long long)(n)))
+
+#define cmpxchg64_local(ptr,o,n)                                        \
+        ((__typeof__(*(ptr)))__cmpxchg64((ptr),                         \
+                                         (unsigned long long)(o),       \
+                                         (unsigned long long)(n)))
+
+#else   /* !CONFIG_CPU_32v6K */
+
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#endif  /* CONFIG_CPU_32v6K */
+
+#endif  /* __LINUX_ARM_ARCH__ >= 6 */
+
 #endif /* __ASSEMBLY__ */
 
 #define arch_align_stack(x) (x)