riscv: Implement xchg8/16() using Zabha

This adds runtime support for Zabha in xchg8/16() operations.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20241103145153.105097-9-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: Alexandre Ghiti

arch/riscv/include/asm/cmpxchg.h

@@ -14,29 +14,41 @@
 #include <asm/insn-def.h>
 #include <asm/cpufeature-macros.h>
 
-#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;	\
-	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
-			<< __s;						\
-	ulong __newx = (ulong)(n) << __s;				\
-	ulong __retx;							\
-	ulong __rc;							\
-									\
-	__asm__ __volatile__ (						\
-	       prepend							\
-	       "0:	lr.w %0, %2\n"					\
-	       "	and  %1, %0, %z4\n"				\
-	       "	or   %1, %1, %z3\n"				\
-	       "	sc.w" sc_sfx " %1, %1, %2\n"			\
-	       "	bnez %1, 0b\n"					\
-	       append							\
-	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
-	       : "rJ" (__newx), "rJ" (~__mask)				\
-	       : "memory");						\
-									\
-	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append,		\
+			   swap_append, r, p, n)				\
+({										\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) {		\
+		__asm__ __volatile__ (						\
+			prepend							\
+			"	amoswap" swap_sfx " %0, %z2, %1\n"		\
+			swap_append						\
+			: "=&r" (r), "+A" (*(p))				\
+			: "rJ" (n)						\
+			: "memory");						\
+	} else {								\
+		u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+		ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+		ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+				<< __s;						\
+		ulong __newx = (ulong)(n) << __s;				\
+		ulong __retx;							\
+		ulong __rc;							\
+										\
+		__asm__ __volatile__ (						\
+		       prepend							\
+		       "0:	lr.w %0, %2\n"					\
+		       "	and  %1, %0, %z4\n"				\
+		       "	or   %1, %1, %z3\n"				\
+		       "	sc.w" sc_sfx " %1, %1, %2\n"			\
+		       "	bnez %1, 0b\n"					\
+		       sc_append						\
+		       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+		       : "rJ" (__newx), "rJ" (~__mask)				\
+		       : "memory");						\
+										\
+		r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+	}									\
 })
 
 #define __arch_xchg(sfx, prepend, append, r, p, n)			\
@@ -59,8 +71,13 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
+		__arch_xchg_masked(sc_sfx, ".b" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
+				   __ret, __ptr, __new);		\
+		break;							\
 	case 2:								\
-		__arch_xchg_masked(sc_sfx, prepend, sc_append,		\
+		__arch_xchg_masked(sc_sfx, ".h" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\