mips/atomic: Fix smp_mb__{before,after}_atomic()

Recent probing at the Linux Kernel Memory Model uncovered a
'surprise'. Strongly ordered architectures where the atomic RmW
primitive implies full memory ordering and
smp_mb__{before,after}_atomic() are a simple barrier() (such as MIPS
without WEAK_REORDERING_BEYOND_LLSC) fail for:

	*x = 1;
	atomic_inc(u);
	smp_mb__after_atomic();
	r0 = *y;

Because, while the atomic_inc() implies memory order, it
(surprisingly) does not provide a compiler barrier. This then allows
the compiler to re-order like so:

	atomic_inc(u);
	*x = 1;
	smp_mb__after_atomic();
	r0 = *y;

Which the CPU is then allowed to re-order (under TSO rules) like:

	atomic_inc(u);
	r0 = *y;
	*x = 1;

And this very much was not intended. Therefore strengthen the atomic
RmW ops to include a compiler barrier.

Reported-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>

1 files changed, 25 insertions, 17 deletions

diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index 7bd35e5e2a9e..985d6a02f9ea 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -66,7 +66,8 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		"	beqzl	%0, 1b					\n"
 		"	.set	pop					\n"
 		: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*m)
-		: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m));
+		: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m)
+		: __LLSC_CLOBBER);
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
 		loongson_llsc_mb();
@@ -76,7 +77,8 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 			"	" __INS "%0, %3, %2, 1			\n"
 			"	" __SC "%0, %1				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (bit), "r" (~0));
+			: "ir" (bit), "r" (~0)
+			: __LLSC_CLOBBER);
 		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
@@ -90,7 +92,8 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 			"	" __SC	"%0, %1				\n"
 			"	.set	pop				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (1UL << bit));
+			: "ir" (1UL << bit)
+			: __LLSC_CLOBBER);
 		} while (unlikely(!temp));
 	} else
 		__mips_set_bit(nr, addr);
@@ -122,7 +125,8 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		"	beqzl	%0, 1b					\n"
 		"	.set	pop					\n"
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-		: "ir" (~(1UL << bit)));
+		: "ir" (~(1UL << bit))
+		: __LLSC_CLOBBER);
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
 		loongson_llsc_mb();
@@ -132,7 +136,8 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 			"	" __INS "%0, $0, %2, 1			\n"
 			"	" __SC "%0, %1				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (bit));
+			: "ir" (bit)
+			: __LLSC_CLOBBER);
 		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
@@ -146,7 +151,8 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 			"	" __SC "%0, %1				\n"
 			"	.set	pop				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (~(1UL << bit)));
+			: "ir" (~(1UL << bit))
+			: __LLSC_CLOBBER);
 		} while (unlikely(!temp));
 	} else
 		__mips_clear_bit(nr, addr);
@@ -192,7 +198,8 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 		"	beqzl	%0, 1b				\n"
 		"	.set	pop				\n"
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-		: "ir" (1UL << bit));
+		: "ir" (1UL << bit)
+		: __LLSC_CLOBBER);
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
@@ -207,7 +214,8 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 			"	" __SC	"%0, %1				\n"
 			"	.set	pop				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
-			: "ir" (1UL << bit));
+			: "ir" (1UL << bit)
+			: __LLSC_CLOBBER);
 		} while (unlikely(!temp));
 	} else
 		__mips_change_bit(nr, addr);
@@ -244,7 +252,7 @@ static inline int test_and_set_bit(unsigned long nr,
 		"	.set	pop					\n"
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
-		: "memory");
+		: __LLSC_CLOBBER);
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
@@ -260,7 +268,7 @@ static inline int test_and_set_bit(unsigned long nr,
 			"	.set	pop				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
-			: "memory");
+			: __LLSC_CLOBBER);
 		} while (unlikely(!res));
 
 		res = temp & (1UL << bit);
@@ -301,7 +309,7 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 		"	.set	pop					\n"
 		: "=&r" (temp), "+m" (*m), "=&r" (res)
 		: "r" (1UL << bit)
-		: "memory");
+		: __LLSC_CLOBBER);
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
@@ -317,7 +325,7 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 			"	.set	pop				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
-			: "memory");
+			: __LLSC_CLOBBER);
 		} while (unlikely(!res));
 
 		res = temp & (1UL << bit);
@@ -360,7 +368,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 		"	.set	pop					\n"
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
-		: "memory");
+		: __LLSC_CLOBBER);
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(nr)) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
@@ -375,7 +383,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 			"	" __SC	"%0, %1				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "ir" (bit)
-			: "memory");
+			: __LLSC_CLOBBER);
 		} while (unlikely(!temp));
 #endif
 	} else if (kernel_uses_llsc) {
@@ -394,7 +402,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 			"	.set	pop				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
-			: "memory");
+			: __LLSC_CLOBBER);
 		} while (unlikely(!res));
 
 		res = temp & (1UL << bit);
@@ -437,7 +445,7 @@ static inline int test_and_change_bit(unsigned long nr,
 		"	.set	pop					\n"
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
-		: "memory");
+		: __LLSC_CLOBBER);
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
@@ -453,7 +461,7 @@ static inline int test_and_change_bit(unsigned long nr,
 			"	.set	pop				\n"
 			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
-			: "memory");
+			: __LLSC_CLOBBER);
 		} while (unlikely(!res));
 
 		res = temp & (1UL << bit);