Clear the exclusive monitor in the vector stub

The patch adds CLREX (or a dummy STREX) to the vector stub and removes
it from the __switch_to function. This allows the atomic_set to be a
simple STR instruction.

Linux currently clears the exclusive monitor at every context switch,
allowing threads to use plain STR for atomic store
operations. However, this is not enough for atomic operations in
signal handler. The patch fixes this case as well.

Note that for the SMP case, plain STR clears the state of the global
exclusive monitor. The effect of an STR on the local exclusive monitor
is implementation defined and therefore a CLREX is needed at exception
taking.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm/kernel/entry-armv.S

@@ -709,13 +709,6 @@ ENTRY(__switch_to)
 #ifdef CONFIG_MMU
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
-#if __LINUX_ARM_ARCH__ >= 6
-#ifdef CONFIG_CPU_32v6K
-	clrex
-#else
-	strex	r5, r4, [ip]			@ Clear exclusive monitor
-#endif
-#endif
 #if defined(CONFIG_HAS_TLS_REG)
 	mcr	p15, 0, r3, c13, c0, 3		@ set TLS register
 #elif !defined(CONFIG_TLS_REG_EMUL)
@@ -1050,6 +1043,13 @@ vector_\name:
 	@ (parent CPSR)
 	@
 	stmia	sp, {r0, lr}		@ save r0, lr
+#if __LINUX_ARM_ARCH__ >= 6
+#ifdef CONFIG_CPU_32v6K
+	clrex				@ clear the exclusive monitor
+#else
+	strex	lr, r0, [sp]		@ clear the exclusive monitor
+#endif
+#endif
 	mrs	lr, spsr
 	str	lr, [sp, #8]		@ save spsr
 

arch/arm/mm/abort-ev6.S

@@ -20,11 +20,6 @@
  */
 	.align	5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_32v6K
-	clrex
-#else
-	strex	r0, r1, [sp]			@ Clear the exclusive monitor
-#endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*

arch/arm/mm/abort-ev7.S

@@ -16,12 +16,6 @@
  */
 	.align	5
 ENTRY(v7_early_abort)
-	/*
-	 * The effect of data aborts on on the exclusive access monitor are
-	 * UNPREDICTABLE. Do a CLREX to clear the state
-	 */
-	clrex
-
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 

include/asm-arm/atomic.h

@@ -21,6 +21,7 @@ typedef struct { volatile int counter; } atomic_t;
 #ifdef __KERNEL__
 
 #define atomic_read(v)	((v)->counter)
+#define atomic_set(v,i)	(((v)->counter) = (i))
 
 #if __LINUX_ARM_ARCH__ >= 6
 
@@ -31,20 +32,6 @@ typedef struct { volatile int counter; } atomic_t;
  * without using the following operations WILL break the atomic
  * nature of these ops.
  */
-static inline void atomic_set(atomic_t *v, int i)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__("@ atomic_set\n"
-"1:	ldrex	%0, [%1]\n"
-"	strex	%0, %2, [%1]\n"
-"	teq	%0, #0\n"
-"	bne	1b"
-	: "=&r" (tmp)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
-}
-
 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	unsigned long tmp;
@@ -123,8 +110,6 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
-#define atomic_set(v,i)	(((v)->counter) = (i))
-
 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	unsigned long flags;