1 files changed, 32 insertions, 21 deletions

diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index f8b8965666e9..4f2c28060c9a 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -46,7 +46,7 @@ static inline void dsb_sev(void)
 {
 #if __LINUX_ARM_ARCH__ >= 7
         __asm__ __volatile__ (
-                "dsb\n"
+                "dsb ishst\n"
                 SEV
         );
 #else
@@ -107,7 +107,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
                 "       subs    %1, %0, %0, ror #16\n"
                 "       addeq   %0, %0, %4\n"
                 "       strexeq %2, %0, [%3]"
-                : "=&r" (slock), "=&r" (contended), "=r" (res)
+                : "=&r" (slock), "=&r" (contended), "=&r" (res)
                 : "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
                 : "cc");
         } while (res);
@@ -168,17 +168,20 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-        unsigned long tmp;
+        unsigned long contended, res;
 
-        __asm__ __volatile__(
-"       ldrex   %0, [%1]\n"
-"       teq     %0, #0\n"
-"       strexeq %0, %2, [%1]"
-        : "=&r" (tmp)
-        : "r" (&rw->lock), "r" (0x80000000)
-        : "cc");
+        do {
+                __asm__ __volatile__(
+                "       ldrex   %0, [%2]\n"
+                "       mov     %1, #0\n"
+                "       teq     %0, #0\n"
+                "       strexeq %1, %3, [%2]"
+                : "=&r" (contended), "=&r" (res)
+                : "r" (&rw->lock), "r" (0x80000000)
+                : "cc");
+        } while (res);
 
-        if (tmp == 0) {
+        if (!contended) {
                 smp_mb();
                 return 1;
         } else {
@@ -254,18 +257,26 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-        unsigned long tmp, tmp2 = 1;
+        unsigned long contended, res;
 
-        __asm__ __volatile__(
-"       ldrex   %0, [%2]\n"
-"       adds    %0, %0, #1\n"
-"       strexpl %1, %0, [%2]\n"
-        : "=&r" (tmp), "+r" (tmp2)
-        : "r" (&rw->lock)
-        : "cc");
+        do {
+                __asm__ __volatile__(
+                "       ldrex   %0, [%2]\n"
+                "       mov     %1, #0\n"
+                "       adds    %0, %0, #1\n"
+                "       strexpl %1, %0, [%2]"
+                : "=&r" (contended), "=&r" (res)
+                : "r" (&rw->lock)
+                : "cc");
+        } while (res);
 
-        smp_mb();
-        return tmp2 == 0;
+        /* If the lock is negative, then it is already held for write. */
+        if (contended < 0x80000000) {
+                smp_mb();
+                return 1;
+        } else {
+                return 0;
+        }
 }
 
 /* read_can_lock - would read_trylock() succeed? */