riscv: Fix fully ordered LR/SC xchg[8|16]() implementations

The fully ordered versions of xchg[8|16]() using LR/SC lack the
necessary memory barriers to guarantee the order.

Fix this by matching what is already implemented in the fully ordered
versions of cmpxchg() using LR/SC.
Suggested-by: Andrea Parri <parri.andrea@gmail.com>
Reported-by: Andrea Parri <parri.andrea@gmail.com>
Closes: https://lore.kernel.org/linux-riscv/ZlYbupL5XgzgA0MX@andrea/T/#u
Fixes: a8ed2b7a ("riscv/cmpxchg: Implement xchg for variables of size 1 and 2")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20240530145546.394248-1-alexghiti@rivosinc.comSigned-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/include/asm/cmpxchg.h

@@ -10,7 +10,7 @@
 
 #include <asm/fence.h>
 
-#define __arch_xchg_masked(prepend, append, r, p, n)			\
+#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n)		\
 ({									\
 	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
 	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
@@ -25,7 +25,7 @@
 	       "0:	lr.w %0, %2\n"					\
 	       "	and  %1, %0, %z4\n"				\
 	       "	or   %1, %1, %z3\n"				\
-	       "	sc.w %1, %1, %2\n"				\
+	       "	sc.w" sc_sfx " %1, %1, %2\n"			\
 	       "	bnez %1, 0b\n"					\
 	       append							\
 	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
@@ -46,7 +46,8 @@
 		: "memory");						\
 })
 
-#define _arch_xchg(ptr, new, sfx, prepend, append)			\
+#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend,			\
+		   sc_append, swap_append)				\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __new = (new);				\
@@ -55,15 +56,15 @@
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
 	case 2:								\
-		__arch_xchg_masked(prepend, append,			\
+		__arch_xchg_masked(sc_sfx, prepend, sc_append,		\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\
-		__arch_xchg(".w" sfx, prepend, append,			\
+		__arch_xchg(".w" swap_sfx, prepend, swap_append,	\
 			      __ret, __ptr, __new);			\
 		break;							\
 	case 8:								\
-		__arch_xchg(".d" sfx, prepend, append,			\
+		__arch_xchg(".d" swap_sfx, prepend, swap_append,	\
 			      __ret, __ptr, __new);			\
 		break;							\
 	default:							\
@@ -73,16 +74,17 @@
 })
 
 #define arch_xchg_relaxed(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", "")
+	_arch_xchg(ptr, x, "", "", "", "", "")
 
 #define arch_xchg_acquire(ptr, x)					\
-	_arch_xchg(ptr, x, "", "", RISCV_ACQUIRE_BARRIER)
+	_arch_xchg(ptr, x, "", "", "",					\
+		   RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER)
 
 #define arch_xchg_release(ptr, x)					\
-	_arch_xchg(ptr, x, "", RISCV_RELEASE_BARRIER, "")
+	_arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "")
 
 #define arch_xchg(ptr, x)						\
-	_arch_xchg(ptr, x, ".aqrl", "", "")
+	_arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
 
 #define xchg32(ptr, x)							\
 ({									\