powerpc: add compile-time support for lbarx, lharx

ISA v2.06 (POWER7 and up) as well as e6500 support lbarx and lharx.
Add a compile option that allows code to use it, and add support in
cmpxchg and xchg 8 and 16 bit values without shifting and masking.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220909052312.63916-1-npiggin@gmail.com

arch/powerpc/Kconfig

@@ -293,6 +293,9 @@ config PPC_BARRIER_NOSPEC
 	default y
 	depends on PPC_BOOK3S_64 || PPC_E500
 
+config PPC_HAS_LBARX_LHARX
+	bool
+
 config EARLY_PRINTK
 	bool
 	default y

arch/powerpc/include/asm/cmpxchg.h

@@ -77,10 +77,76 @@ u32 __cmpxchg_##type##sfx(volatile void *p, u32 old, u32 new)	\
  * the previous value stored there.
  */
 
+#ifndef CONFIG_PPC_HAS_LBARX_LHARX
 XCHG_GEN(u8, _local, "memory");
 XCHG_GEN(u8, _relaxed, "cc");
 XCHG_GEN(u16, _local, "memory");
 XCHG_GEN(u16, _relaxed, "cc");
+#else
+static __always_inline unsigned long
+__xchg_u8_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lbarx	%0,0,%2		# __xchg_u8_local\n"
+"	stbcx.	%3,0,%2 \n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned char *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u8_relaxed(u8 *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lbarx	%0,0,%2		# __xchg_u8_relaxed\n"
+"	stbcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (val)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u16_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lharx	%0,0,%2		# __xchg_u16_local\n"
+"	sthcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned short *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u16_relaxed(u16 *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lharx	%0,0,%2		# __xchg_u16_relaxed\n"
+"	sthcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (val)
+	: "cc");
+
+	return prev;
+}
+#endif
 
 static __always_inline unsigned long
 __xchg_u32_local(volatile void *p, unsigned long val)
@@ -198,11 +264,12 @@ __xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
 	(__typeof__(*(ptr))) __xchg_relaxed((ptr),			\
 			(unsigned long)_x_, sizeof(*(ptr)));		\
 })
+
 /*
  * Compare and exchange - if *p == old, set it to new,
  * and return the old value of *p.
  */
-
+#ifndef CONFIG_PPC_HAS_LBARX_LHARX
 CMPXCHG_GEN(u8, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory");
 CMPXCHG_GEN(u8, _local, , , "memory");
 CMPXCHG_GEN(u8, _acquire, , PPC_ACQUIRE_BARRIER, "memory");
@@ -211,6 +278,168 @@ CMPXCHG_GEN(u16, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory");
 CMPXCHG_GEN(u16, _local, , , "memory");
 CMPXCHG_GEN(u16, _acquire, , PPC_ACQUIRE_BARRIER, "memory");
 CMPXCHG_GEN(u16, _relaxed, , , "cc");
+#else
+static __always_inline unsigned long
+__cmpxchg_u8(volatile unsigned char *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_local(volatile unsigned char *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_local\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_relaxed(u8 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_acquire(u8 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16(volatile unsigned short *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lharx	%0,0,%2		# __cmpxchg_u16\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ATOMIC_EXIT_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_local(volatile unsigned short *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_local\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_relaxed(u16 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_acquire(u16 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+#endif
 
 static __always_inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)

arch/powerpc/lib/sstep.c

@@ -2284,15 +2284,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 			op->type = MKOP(STCX, 0, 4);
 			break;
 
-#ifdef __powerpc64__
-		case 84:	/* ldarx */
-			op->type = MKOP(LARX, 0, 8);
-			break;
-
-		case 214:	/* stdcx. */
-			op->type = MKOP(STCX, 0, 8);
-			break;
-
+#ifdef CONFIG_PPC_HAS_LBARX_LHARX
 		case 52:	/* lbarx */
 			op->type = MKOP(LARX, 0, 1);
 			break;
@@ -2308,6 +2300,15 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 		case 726:	/* sthcx. */
 			op->type = MKOP(STCX, 0, 2);
 			break;
+#endif
+#ifdef __powerpc64__
+		case 84:	/* ldarx */
+			op->type = MKOP(LARX, 0, 8);
+			break;
+
+		case 214:	/* stdcx. */
+			op->type = MKOP(STCX, 0, 8);
+			break;
 
 		case 276:	/* lqarx */
 			if (!((rd & 1) || rd == ra || rd == rb))
@@ -3334,7 +3335,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 		err = 0;
 		val = 0;
 		switch (size) {
-#ifdef __powerpc64__
+#ifdef CONFIG_PPC_HAS_LBARX_LHARX
 		case 1:
 			__get_user_asmx(val, ea, err, "lbarx");
 			break;

arch/powerpc/platforms/Kconfig.cputype

@@ -135,6 +135,7 @@ config GENERIC_CPU
 	depends on PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
 	select ARCH_HAS_FAST_MULTIPLIER
 	select PPC_64S_HASH_MMU
+	select PPC_HAS_LBARX_LHARX
 
 config POWERPC_CPU
 	bool "Generic 32 bits powerpc"
@@ -160,17 +161,20 @@ config POWER7_CPU
 	depends on PPC_BOOK3S_64
 	select ARCH_HAS_FAST_MULTIPLIER
 	select PPC_64S_HASH_MMU
+	select PPC_HAS_LBARX_LHARX
 
 config POWER8_CPU
 	bool "POWER8"
 	depends on PPC_BOOK3S_64
 	select ARCH_HAS_FAST_MULTIPLIER
 	select PPC_64S_HASH_MMU
+	select PPC_HAS_LBARX_LHARX
 
 config POWER9_CPU
 	bool "POWER9"
 	depends on PPC_BOOK3S_64
 	select ARCH_HAS_FAST_MULTIPLIER
+	select PPC_HAS_LBARX_LHARX
 
 config POWER10_CPU
 	bool "POWER10"
@@ -184,6 +188,7 @@ config E5500_CPU
 config E6500_CPU
 	bool "Freescale e6500"
 	depends on PPC64 && PPC_E500
+	select PPC_HAS_LBARX_LHARX
 
 config 405_CPU
 	bool "40x family"