[PATCH 1/7] riscv: Implement cmpxchg32/64() using Zacas

[Alexandre Ghiti]

This adds runtime support for Zacas in cmpxchg operations.

Signed-off-by: Alexandre Ghiti <alexghiti at rivosinc.com>
---
 arch/riscv/Kconfig               | 17 +++++++++++++++++
 arch/riscv/Makefile              | 11 +++++++++++
 arch/riscv/include/asm/cmpxchg.h | 23 ++++++++++++++++++++---
 3 files changed, 48 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 8a0f403432e8..b443def70139 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -579,6 +579,23 @@ config RISCV_ISA_V_PREEMPTIVE
 	  preemption. Enabling this config will result in higher memory
 	  consumption due to the allocation of per-task's kernel Vector context.
 
+config TOOLCHAIN_HAS_ZACAS
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zacas)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zacas)
+	depends on AS_HAS_OPTION_ARCH
+
+config RISCV_ISA_ZACAS
+	bool "Zacas extension support for atomic CAS"
+	depends on TOOLCHAIN_HAS_ZACAS
+	default y
+	help
+	  Adds support to use atomic CAS instead of LR/SC to implement kernel
+	  atomic cmpxchg operation.
+
+	  If you don't know what to do here, say Y.
+
 config TOOLCHAIN_HAS_ZBB
 	bool
 	default y
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 5b3115a19852..d5b60b87998c 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -78,6 +78,17 @@ endif
 # Check if the toolchain supports Zihintpause extension
 riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE) := $(riscv-march-y)_zihintpause
 
+# Check if the toolchain supports Zacas
+ifdef CONFIG_AS_IS_LLVM
+# Support for experimental Zacas was merged in LLVM 17, but the removal of
+# the "experimental" was merged in LLVM 19.
+KBUILD_CFLAGS += -menable-experimental-extensions
+KBUILD_AFLAGS += -menable-experimental-extensions
+riscv-march-y := $(riscv-march-y)_zacas1p0
+else
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZACAS) := $(riscv-march-y)_zacas
+endif
+
 # Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by
 # matching non-v and non-multi-letter extensions out with the filter ([^v_]*)
 KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/')
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 4d23f0c35b94..1c50b4821ac8 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -9,6 +9,7 @@
 #include <linux/bug.h>
 
 #include <asm/fence.h>
+#include <asm/alternative.h>
 
 #define __arch_xchg_masked(prepend, append, r, p, n)			\
 ({									\
@@ -132,21 +133,37 @@
 	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
 })
 
-#define __arch_cmpxchg(lr_sfx, sc_sfx, prepend, append, r, p, co, o, n)	\
+#define __arch_cmpxchg(lr_sfx, sc_cas_sfx, prepend, append, r, p, co, o, n)	\
 ({									\
+	__label__ zacas, end;						\
 	register unsigned int __rc;					\
 									\
+	asm goto(ALTERNATIVE("nop", "j %[zacas]", 0,			\
+			     RISCV_ISA_EXT_ZACAS, 1)			\
+			: : : : zacas);					\
+									\
 	__asm__ __volatile__ (						\
 		prepend							\
 		"0:	lr" lr_sfx " %0, %2\n"				\
 		"	bne  %0, %z3, 1f\n"				\
-		"	sc" sc_sfx " %1, %z4, %2\n"			\
+		"	sc" sc_cas_sfx " %1, %z4, %2\n"			\
 		"	bnez %1, 0b\n"					\
 		append							\
 		"1:\n"							\
 		: "=&r" (r), "=&r" (__rc), "+A" (*(p))			\
 		: "rJ" (co o), "rJ" (n)					\
 		: "memory");						\
+	goto end;							\
+									\
+zacas:									\
+	__asm__ __volatile__ (						\
+		prepend							\
+		"	amocas" sc_cas_sfx " %0, %z2, %1\n"		\
+		append							\
+		: "+&r" (r), "+A" (*(p))				\
+		: "rJ" (n)						\
+		: "memory");						\
+end:									\
 })
 
 #define _arch_cmpxchg(ptr, old, new, sc_sfx, prepend, append)		\
@@ -154,7 +171,7 @@
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __old = (old);				\
 	__typeof__(*(__ptr)) __new = (new);				\
-	__typeof__(*(__ptr)) __ret;					\
+	__typeof__(*(__ptr)) __ret = (old);				\
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
-- 
2.39.2