percpu: Add {raw,this}_cpu_try_cmpxchg()

Add the try_cmpxchg() form to the per-cpu ops.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20230531132323.587480729@infradead.org

2 files changed, 128 insertions, 4 deletions

diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 6432a7fade91..96af32c283b2 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -89,16 +89,37 @@ do {									\
 	__ret;								\
 })
 
-#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
+#define __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, _cmpxchg)		\
+({									\
+	typeof(pcp) __val, __old = *(ovalp);				\
+	__val = _cmpxchg(pcp, __old, nval);				\
+	if (__val != __old)						\
+		*(ovalp) = __val;					\
+	__val == __old;							\
+})
+
+#define raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)			\
 ({									\
 	typeof(pcp) *__p = raw_cpu_ptr(&(pcp));				\
-	typeof(pcp) __ret;						\
-	__ret = *__p;							\
-	if (__ret == (oval))						\
+	typeof(pcp) __val = *__p, __old = *(ovalp);			\
+	bool __ret;							\
+	if (__val == __old) {						\
 		*__p = nval;						\
+		__ret = true;						\
+	} else {							\
+		*(ovalp) = __val;					\
+		__ret = false;						\
+	}								\
 	__ret;								\
 })
 
+#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) __old = (oval);					\
+	raw_cpu_generic_try_cmpxchg(pcp, &__old, nval);			\
+	__old;								\
+})
+
 #define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
 ({									\
 	typeof(pcp1) *__p1 = raw_cpu_ptr(&(pcp1));			\
@@ -170,6 +191,16 @@ do {									\
 	__ret;								\
 })
 
+#define this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)			\
+({									\
+	bool __ret;							\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval);		\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
 #define this_cpu_generic_cmpxchg(pcp, oval, nval)			\
 ({									\
 	typeof(pcp) __ret;						\
@@ -282,6 +313,43 @@ do {									\
 #define raw_cpu_xchg_8(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 #endif
 
+#ifndef raw_cpu_try_cmpxchg_1
+#ifdef raw_cpu_cmpxchg_1
+#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg_1)
+#else
+#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) \
+	raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+#ifndef raw_cpu_try_cmpxchg_2
+#ifdef raw_cpu_cmpxchg_2
+#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg_2)
+#else
+#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) \
+	raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+#ifndef raw_cpu_try_cmpxchg_4
+#ifdef raw_cpu_cmpxchg_4
+#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg_4)
+#else
+#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) \
+	raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+#ifndef raw_cpu_try_cmpxchg_8
+#ifdef raw_cpu_cmpxchg_8
+#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg_8)
+#else
+#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) \
+	raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+
 #ifndef raw_cpu_cmpxchg_1
 #define raw_cpu_cmpxchg_1(pcp, oval, nval) \
 	raw_cpu_generic_cmpxchg(pcp, oval, nval)
@@ -407,6 +475,43 @@ do {									\
 #define this_cpu_xchg_8(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
 #endif
 
+#ifndef this_cpu_try_cmpxchg_1
+#ifdef this_cpu_cmpxchg_1
+#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg_1)
+#else
+#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) \
+	this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+#ifndef this_cpu_try_cmpxchg_2
+#ifdef this_cpu_cmpxchg_2
+#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg_2)
+#else
+#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) \
+	this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+#ifndef this_cpu_try_cmpxchg_4
+#ifdef this_cpu_cmpxchg_4
+#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg_4)
+#else
+#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) \
+	this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+#ifndef this_cpu_try_cmpxchg_8
+#ifdef this_cpu_cmpxchg_8
+#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg_8)
+#else
+#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) \
+	this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+
 #ifndef this_cpu_cmpxchg_1
 #define this_cpu_cmpxchg_1(pcp, oval, nval) \
 	this_cpu_generic_cmpxchg(pcp, oval, nval)
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index e60727be79c4..cbbf6d189a3a 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -343,6 +343,21 @@ static __always_inline void __this_cpu_preempt_check(const char *op) { }
 	pscr2_ret__;							\
 })
 
+#define __pcpu_size_call_return2bool(stem, variable, ...)		\
+({									\
+	bool pscr2_ret__;						\
+	__verify_pcpu_ptr(&(variable));					\
+	switch(sizeof(variable)) {					\
+	case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break;	\
+	case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break;	\
+	case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break;	\
+	case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break;	\
+	default:							\
+		__bad_size_call_parameter(); break;			\
+	}								\
+	pscr2_ret__;							\
+})
+
 /*
  * Special handling for cmpxchg_double.  cmpxchg_double is passed two
  * percpu variables.  The first has to be aligned to a double word
@@ -426,6 +441,8 @@ do {									\
 #define raw_cpu_xchg(pcp, nval)		__pcpu_size_call_return2(raw_cpu_xchg_, pcp, nval)
 #define raw_cpu_cmpxchg(pcp, oval, nval) \
 	__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
+#define raw_cpu_try_cmpxchg(pcp, ovalp, nval) \
+	__pcpu_size_call_return2bool(raw_cpu_try_cmpxchg_, pcp, ovalp, nval)
 #define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
 	__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
 
@@ -513,6 +530,8 @@ do {									\
 #define this_cpu_xchg(pcp, nval)	__pcpu_size_call_return2(this_cpu_xchg_, pcp, nval)
 #define this_cpu_cmpxchg(pcp, oval, nval) \
 	__pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
+#define this_cpu_try_cmpxchg(pcp, ovalp, nval) \
+	__pcpu_size_call_return2bool(this_cpu_try_cmpxchg_, pcp, ovalp, nval)
 #define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
 	__pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)