Merge tag 'locking-core-2023-05-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Introduce local{,64}_try_cmpxchg() - a slightly more optimal
   primitive, which will be used in perf events ring-buffer code

 - Simplify/modify rwsems on PREEMPT_RT, to address writer starvation

 - Misc cleanups/fixes

* tag 'locking-core-2023-05-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/atomic: Correct (cmp)xchg() instrumentation
  locking/x86: Define arch_try_cmpxchg_local()
  locking/arch: Wire up local_try_cmpxchg()
  locking/generic: Wire up local{,64}_try_cmpxchg()
  locking/atomic: Add generic try_cmpxchg{,64}_local() support
  locking/rwbase: Mitigate indefinite writer starvation
  locking/arch: Rename all internal __xchg() names to __arch_xchg()

arch/alpha/include/asm/cmpxchg.h

@@ -6,15 +6,15 @@
  * Atomic exchange routines.
  */
 
-#define ____xchg(type, args...)		__xchg ## type ## _local(args)
+#define ____xchg(type, args...)		__arch_xchg ## type ## _local(args)
 #define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
 #include <asm/xchg.h>
 
 #define xchg_local(ptr, x)						\
 ({									\
 	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_,	\
-				       sizeof(*(ptr)));			\
+	(__typeof__(*(ptr))) __arch_xchg_local((ptr), (unsigned long)_x_,\
+					       sizeof(*(ptr)));		\
 })
 
 #define arch_cmpxchg_local(ptr, o, n)					\
@@ -34,7 +34,7 @@
 
 #undef ____xchg
 #undef ____cmpxchg
-#define ____xchg(type, args...)		__xchg ##type(args)
+#define ____xchg(type, args...)		__arch_xchg ##type(args)
 #define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
 #include <asm/xchg.h>
 
@@ -48,7 +48,7 @@
 	__typeof__(*(ptr)) _x_ = (x);					\
 	smp_mb();							\
 	__ret = (__typeof__(*(ptr)))					\
-		__xchg((ptr), (unsigned long)_x_, sizeof(*(ptr)));	\
+		__arch_xchg((ptr), (unsigned long)_x_, sizeof(*(ptr)));	\
 	smp_mb();							\
 	__ret;								\
 })

arch/alpha/include/asm/local.h

@@ -52,8 +52,16 @@ static __inline__ long local_sub_return(long i, local_t * l)
 	return result;
 }
 
-#define local_cmpxchg(l, o, n) \
-	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+static __inline__ long local_cmpxchg(local_t *l, long old, long new)
+{
+	return cmpxchg_local(&l->a.counter, old, new);
+}
+
+static __inline__ bool local_try_cmpxchg(local_t *l, long *old, long new)
+{
+	return try_cmpxchg_local(&l->a.counter, (s64 *)old, new);
+}
+
 #define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
 
 /**

arch/arc/include/asm/cmpxchg.h

@@ -85,7 +85,7 @@
  */
 #ifdef CONFIG_ARC_HAS_LLSC
 
-#define __xchg(ptr, val)						\
+#define __arch_xchg(ptr, val)						\
 ({									\
 	__asm__ __volatile__(						\
 	"	ex  %0, [%1]	\n"	/* set new value */	        \
@@ -102,7 +102,7 @@
 									\
 	switch(sizeof(*(_p_))) {					\
 	case 4:								\
-		_val_ = __xchg(_p_, _val_);				\
+		_val_ = __arch_xchg(_p_, _val_);			\
 		break;							\
 	default:							\
 		BUILD_BUG();						\

arch/arm/include/asm/cmpxchg.h

@@ -25,7 +25,8 @@
 #define swp_is_buggy
 #endif
 
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
+static inline unsigned long
+__arch_xchg(unsigned long x, volatile void *ptr, int size)
 {
 	extern void __bad_xchg(volatile void *, int);
 	unsigned long ret;
@@ -115,8 +116,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 }
 
 #define arch_xchg_relaxed(ptr, x) ({					\
-	(__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr),		\
-				   sizeof(*(ptr)));			\
+	(__typeof__(*(ptr)))__arch_xchg((unsigned long)(x), (ptr),	\
+					sizeof(*(ptr)));		\
 })
 
 #include <asm-generic/cmpxchg-local.h>

arch/arm64/include/asm/cmpxchg.h

@@ -62,9 +62,8 @@ __XCHG_CASE( ,  ,  mb_, 64, dmb ish, nop,  , a, l, "memory")
 #undef __XCHG_CASE
 
 #define __XCHG_GEN(sfx)							\
-static __always_inline  unsigned long __xchg##sfx(unsigned long x,	\
-					volatile void *ptr,		\
-					int size)			\
+static __always_inline unsigned long					\
+__arch_xchg##sfx(unsigned long x, volatile void *ptr, int size)		\
 {									\
 	switch (size) {							\
 	case 1:								\
@@ -93,7 +92,7 @@ __XCHG_GEN(_mb)
 ({									\
 	__typeof__(*(ptr)) __ret;					\
 	__ret = (__typeof__(*(ptr)))					\
-		__xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+		__arch_xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \
 	__ret;								\
 })
 

arch/hexagon/include/asm/cmpxchg.h

@@ -9,7 +9,7 @@
 #define _ASM_CMPXCHG_H
 
 /*
- * __xchg - atomically exchange a register and a memory location
+ * __arch_xchg - atomically exchange a register and a memory location
  * @x: value to swap
  * @ptr: pointer to memory
  * @size:  size of the value
@@ -19,8 +19,8 @@
  * Note:  there was an errata for V2 about .new's and memw_locked.
  *
  */
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
-				   int size)
+static inline unsigned long
+__arch_xchg(unsigned long x, volatile void *ptr, int size)
 {
 	unsigned long retval;
 
@@ -42,8 +42,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
  * Atomically swap the contents of a register with memory.  Should be atomic
  * between multiple CPU's and within interrupts on the same CPU.
  */
-#define arch_xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), \
-	sizeof(*(ptr))))
+#define arch_xchg(ptr, v) ((__typeof__(*(ptr)))__arch_xchg((unsigned long)(v), (ptr), \
+							   sizeof(*(ptr))))
 
 /*
  *  see rt-mutex-design.txt; cmpxchg supposedly checks if *ptr == A and swaps.

arch/ia64/include/asm/cmpxchg.h

@@ -5,7 +5,7 @@
 #include <uapi/asm/cmpxchg.h>
 
 #define arch_xchg(ptr, x)	\
-({(__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));})
+({(__typeof__(*(ptr))) __arch_xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));})
 
 #define arch_cmpxchg(ptr, o, n)		cmpxchg_acq((ptr), (o), (n))
 #define arch_cmpxchg64(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))

arch/ia64/include/uapi/asm/cmpxchg.h

@@ -23,7 +23,7 @@
  */
 extern void ia64_xchg_called_with_bad_pointer(void);
 
-#define __xchg(x, ptr, size)						\
+#define __arch_xchg(x, ptr, size)					\
 ({									\
 	unsigned long __xchg_result;					\
 									\
@@ -51,7 +51,7 @@ extern void ia64_xchg_called_with_bad_pointer(void);
 
 #ifndef __KERNEL__
 #define xchg(ptr, x)							\
-({(__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));})
+({(__typeof__(*(ptr))) __arch_xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));})
 #endif
 
 /*

arch/loongarch/include/asm/cmpxchg.h

@@ -62,7 +62,7 @@ static inline unsigned int __xchg_small(volatile void *ptr, unsigned int val,
 }
 
 static __always_inline unsigned long
-__xchg(volatile void *ptr, unsigned long x, int size)
+__arch_xchg(volatile void *ptr, unsigned long x, int size)
 {
 	switch (size) {
 	case 1:
@@ -87,7 +87,7 @@ __xchg(volatile void *ptr, unsigned long x, int size)
 	__typeof__(*(ptr)) __res;					\
 									\
 	__res = (__typeof__(*(ptr)))					\
-		__xchg((ptr), (unsigned long)(x), sizeof(*(ptr)));	\
+		__arch_xchg((ptr), (unsigned long)(x), sizeof(*(ptr)));	\
 									\
 	__res;								\
 })

arch/loongarch/include/asm/local.h

@@ -56,8 +56,17 @@ static inline long local_sub_return(long i, local_t *l)
 	return result;
 }
 
-#define local_cmpxchg(l, o, n) \
-	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
+static inline long local_cmpxchg(local_t *l, long old, long new)
+{
+	return cmpxchg_local(&l->a.counter, old, new);
+}
+
+static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
+{
+	typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old;
+	return try_cmpxchg_local(&l->a.counter, __old, new);
+}
+
 #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n)))
 
 /**

arch/m68k/include/asm/cmpxchg.h

@@ -9,7 +9,7 @@
 extern unsigned long __invalid_xchg_size(unsigned long, volatile void *, int);
 
 #ifndef CONFIG_RMW_INSNS
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+static inline unsigned long __arch_xchg(unsigned long x, volatile void * ptr, int size)
 {
 	unsigned long flags, tmp;
 
@@ -40,7 +40,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 	return x;
 }
 #else
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
+static inline unsigned long __arch_xchg(unsigned long x, volatile void * ptr, int size)
 {
 	switch (size) {
 	case 1:
@@ -75,7 +75,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 }
 #endif
 
-#define arch_xchg(ptr,x) ({(__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));})
+#define arch_xchg(ptr,x) ({(__typeof__(*(ptr)))__arch_xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));})
 
 #include <asm-generic/cmpxchg-local.h>
 

arch/mips/include/asm/cmpxchg.h

@@ -68,7 +68,7 @@ extern unsigned long __xchg_small(volatile void *ptr, unsigned long val,
 				  unsigned int size);
 
 static __always_inline
-unsigned long __xchg(volatile void *ptr, unsigned long x, int size)
+unsigned long __arch_xchg(volatile void *ptr, unsigned long x, int size)
 {
 	switch (size) {
 	case 1:
@@ -102,7 +102,7 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size)
 		smp_mb__before_llsc();					\
 									\
 	__res = (__typeof__(*(ptr)))					\
-		__xchg((ptr), (unsigned long)(x), sizeof(*(ptr)));	\
+		__arch_xchg((ptr), (unsigned long)(x), sizeof(*(ptr)));	\
 									\
 	smp_llsc_mb();							\
 									\

arch/mips/include/asm/local.h

@@ -94,8 +94,17 @@ static __inline__ long local_sub_return(long i, local_t * l)
 	return result;
 }
 
-#define local_cmpxchg(l, o, n) \
-	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
+static __inline__ long local_cmpxchg(local_t *l, long old, long new)
+{
+	return cmpxchg_local(&l->a.counter, old, new);
+}
+
+static __inline__ bool local_try_cmpxchg(local_t *l, long *old, long new)
+{
+	typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old;
+	return try_cmpxchg_local(&l->a.counter, __old, new);
+}
+
 #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n)))
 
 /**

arch/openrisc/include/asm/cmpxchg.h

@@ -147,8 +147,8 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 extern unsigned long __xchg_called_with_bad_pointer(void)
 	__compiletime_error("Bad argument size for xchg");
 
-static inline unsigned long __xchg(volatile void *ptr, unsigned long with,
-		int size)
+static inline unsigned long
+__arch_xchg(volatile void *ptr, unsigned long with, int size)
 {
 	switch (size) {
 	case 1:
@@ -163,9 +163,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long with,
 
 #define arch_xchg(ptr, with) 						\
 	({								\
-		(__typeof__(*(ptr))) __xchg((ptr),			\
-					    (unsigned long)(with),	\
-					    sizeof(*(ptr)));		\
+		(__typeof__(*(ptr))) __arch_xchg((ptr),			\
+						 (unsigned long)(with),	\
+						 sizeof(*(ptr)));	\
 	})
 
 #endif /* __ASM_OPENRISC_CMPXCHG_H */

arch/parisc/include/asm/cmpxchg.h

@@ -22,7 +22,7 @@ extern unsigned long __xchg64(unsigned long, volatile unsigned long *);
 
 /* optimizer better get rid of switch since size is a constant */
 static inline unsigned long
-__xchg(unsigned long x, volatile void *ptr, int size)
+__arch_xchg(unsigned long x, volatile void *ptr, int size)
 {
 	switch (size) {
 #ifdef CONFIG_64BIT
@@ -49,7 +49,7 @@ __xchg(unsigned long x, volatile void *ptr, int size)
 	__typeof__(*(ptr)) __ret;					\
 	__typeof__(*(ptr)) _x_ = (x);					\
 	__ret = (__typeof__(*(ptr)))					\
-		__xchg((unsigned long)_x_, (ptr), sizeof(*(ptr)));	\
+		__arch_xchg((unsigned long)_x_, (ptr), sizeof(*(ptr)));	\
 	__ret;								\
 })
 

arch/powerpc/include/asm/cmpxchg.h

@@ -229,7 +229,7 @@ __xchg_local(void *ptr, unsigned long x, unsigned int size)
 		return __xchg_u64_local(ptr, x);
 #endif
 	}
-	BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg");
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local");
 	return x;
 }
 
@@ -248,7 +248,7 @@ __xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
 		return __xchg_u64_relaxed(ptr, x);
 #endif
 	}
-	BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local");
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_relaxed");
 	return x;
 }
 #define arch_xchg_local(ptr,x)						     \

arch/powerpc/include/asm/local.h

@@ -90,6 +90,17 @@ static __inline__ long local_cmpxchg(local_t *l, long o, long n)
 	return t;
 }
 
+static __inline__ bool local_try_cmpxchg(local_t *l, long *po, long n)
+{
+	long o = *po, r;
+
+	r = local_cmpxchg(l, o, n);
+	if (unlikely(r != o))
+		*po = r;
+
+	return likely(r == o);
+}
+
 static __inline__ long local_xchg(local_t *l, long n)
 {
 	long t;

arch/riscv/include/asm/atomic.h

@@ -261,7 +261,7 @@ c_t arch_atomic##prefix##_xchg_release(atomic##prefix##_t *v, c_t n)	\
 static __always_inline							\
 c_t arch_atomic##prefix##_xchg(atomic##prefix##_t *v, c_t n)		\
 {									\
-	return __xchg(&(v->counter), n, size);				\
+	return __arch_xchg(&(v->counter), n, size);			\
 }									\
 static __always_inline							\
 c_t arch_atomic##prefix##_cmpxchg_relaxed(atomic##prefix##_t *v,	\

arch/riscv/include/asm/cmpxchg.h

@@ -114,7 +114,7 @@
 					    _x_, sizeof(*(ptr)));	\
 })
 
-#define __xchg(ptr, new, size)						\
+#define __arch_xchg(ptr, new, size)					\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(new) __new = (new);					\
@@ -143,7 +143,7 @@
 #define arch_xchg(ptr, x)						\
 ({									\
 	__typeof__(*(ptr)) _x_ = (x);					\
-	(__typeof__(*(ptr))) __xchg((ptr), _x_, sizeof(*(ptr)));	\
+	(__typeof__(*(ptr))) __arch_xchg((ptr), _x_, sizeof(*(ptr)));	\
 })
 
 #define xchg32(ptr, x)							\

arch/s390/include/asm/cmpxchg.h

@@ -14,8 +14,8 @@
 
 void __xchg_called_with_bad_pointer(void);
 
-static __always_inline unsigned long __xchg(unsigned long x,
-					    unsigned long address, int size)
+static __always_inline unsigned long
+__arch_xchg(unsigned long x, unsigned long address, int size)
 {
 	unsigned long old;
 	int shift;
@@ -77,8 +77,8 @@ static __always_inline unsigned long __xchg(unsigned long x,
 	__typeof__(*(ptr)) __ret;					\
 									\
 	__ret = (__typeof__(*(ptr)))					\
-		__xchg((unsigned long)(x), (unsigned long)(ptr),	\
-		       sizeof(*(ptr)));					\
+		__arch_xchg((unsigned long)(x), (unsigned long)(ptr),	\
+			    sizeof(*(ptr)));				\
 	__ret;								\
 })
 

arch/sh/include/asm/cmpxchg.h

@@ -22,7 +22,7 @@
 
 extern void __xchg_called_with_bad_pointer(void);
 
-#define __xchg(ptr, x, size)				\
+#define __arch_xchg(ptr, x, size)				\
 ({							\
 	unsigned long __xchg__res;			\
 	volatile void *__xchg_ptr = (ptr);		\
@@ -46,7 +46,7 @@ extern void __xchg_called_with_bad_pointer(void);
 })
 
 #define arch_xchg(ptr,x)	\
-	((__typeof__(*(ptr)))__xchg((ptr),(unsigned long)(x), sizeof(*(ptr))))
+	((__typeof__(*(ptr)))__arch_xchg((ptr),(unsigned long)(x), sizeof(*(ptr))))
 
 /* This function doesn't exist, so you'll get a linker error
  * if something tries to do an invalid cmpxchg(). */

arch/sparc/include/asm/cmpxchg_32.h

@@ -15,7 +15,7 @@
 unsigned long __xchg_u32(volatile u32 *m, u32 new);
 void __xchg_called_with_bad_pointer(void);
 
-static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
+static inline unsigned long __arch_xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
 	switch (size) {
 	case 4:
@@ -25,7 +25,7 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int
 	return x;
 }
 
-#define arch_xchg(ptr,x) ({(__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));})
+#define arch_xchg(ptr,x) ({(__typeof__(*(ptr)))__arch_xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));})
 
 /* Emulate cmpxchg() the same way we emulate atomics,
  * by hashing the object address and indexing into an array

arch/sparc/include/asm/cmpxchg_64.h

@@ -55,7 +55,7 @@ static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long
 #define arch_xchg(ptr,x)							\
 ({	__typeof__(*(ptr)) __ret;					\
 	__ret = (__typeof__(*(ptr)))					\
-		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)));	\
+		__arch_xchg((unsigned long)(x), (ptr), sizeof(*(ptr)));	\
 	__ret;								\
 })
 
@@ -87,8 +87,8 @@ xchg16(__volatile__ unsigned short *m, unsigned short val)
 	return (load32 & mask) >> bit_shift;
 }
 
-static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
-				       int size)
+static inline unsigned long
+__arch_xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
 	switch (size) {
 	case 2:

arch/x86/include/asm/cmpxchg.h

@@ -221,9 +221,15 @@ extern void __add_wrong_size(void)
 #define __try_cmpxchg(ptr, pold, new, size)				\
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
 
+#define __try_cmpxchg_local(ptr, pold, new, size)			\
+	__raw_try_cmpxchg((ptr), (pold), (new), (size), "")
+
 #define arch_try_cmpxchg(ptr, pold, new) 				\
 	__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
 
+#define arch_try_cmpxchg_local(ptr, pold, new)				\
+	__try_cmpxchg_local((ptr), (pold), (new), sizeof(*(ptr)))
+
 /*
  * xadd() adds "inc" to "*ptr" and atomically returns the previous
  * value of "*ptr".

arch/x86/include/asm/local.h

@@ -120,8 +120,17 @@ static inline long local_sub_return(long i, local_t *l)
 #define local_inc_return(l)  (local_add_return(1, l))
 #define local_dec_return(l)  (local_sub_return(1, l))
 
-#define local_cmpxchg(l, o, n) \
-	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+static inline long local_cmpxchg(local_t *l, long old, long new)
+{
+	return cmpxchg_local(&l->a.counter, old, new);
+}
+
+static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
+{
+	typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old;
+	return try_cmpxchg_local(&l->a.counter, __old, new);
+}
+
 /* Always has a lock prefix */
 #define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
 

arch/xtensa/include/asm/cmpxchg.h

@@ -170,7 +170,7 @@ static inline unsigned long xchg_u32(volatile int * m, unsigned long val)
 }
 
 #define arch_xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+	((__typeof__(*(ptr)))__arch_xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
 static inline u32 xchg_small(volatile void *ptr, u32 x, int size)
 {
@@ -203,7 +203,7 @@ static inline u32 xchg_small(volatile void *ptr, u32 x, int size)
 extern void __xchg_called_with_bad_pointer(void);
 
 static __inline__ unsigned long
-__xchg(unsigned long x, volatile void * ptr, int size)
+__arch_xchg(unsigned long x, volatile void * ptr, int size)
 {
 	switch (size) {
 	case 1:

include/asm-generic/local.h

@@ -42,6 +42,7 @@ typedef struct
 #define local_inc_return(l) atomic_long_inc_return(&(l)->a)
 
 #define local_cmpxchg(l, o, n) atomic_long_cmpxchg((&(l)->a), (o), (n))
+#define local_try_cmpxchg(l, po, n) atomic_long_try_cmpxchg((&(l)->a), (po), (n))
 #define local_xchg(l, n) atomic_long_xchg((&(l)->a), (n))
 #define local_add_unless(l, _a, u) atomic_long_add_unless((&(l)->a), (_a), (u))
 #define local_inc_not_zero(l) atomic_long_inc_not_zero(&(l)->a)

include/asm-generic/local64.h

@@ -42,7 +42,16 @@ typedef struct {
 #define local64_sub_return(i, l) local_sub_return((i), (&(l)->a))
 #define local64_inc_return(l)	local_inc_return(&(l)->a)
 
-#define local64_cmpxchg(l, o, n) local_cmpxchg((&(l)->a), (o), (n))
+static inline s64 local64_cmpxchg(local64_t *l, s64 old, s64 new)
+{
+	return local_cmpxchg(&l->a, old, new);
+}
+
+static inline bool local64_try_cmpxchg(local64_t *l, s64 *old, s64 new)
+{
+	return local_try_cmpxchg(&l->a, (long *)old, new);
+}
+
 #define local64_xchg(l, n)	local_xchg((&(l)->a), (n))
 #define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u))
 #define local64_inc_not_zero(l)	local_inc_not_zero(&(l)->a)
@@ -81,6 +90,7 @@ typedef struct {
 #define local64_inc_return(l)	atomic64_inc_return(&(l)->a)
 
 #define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n))
+#define local64_try_cmpxchg(l, po, n) atomic64_try_cmpxchg((&(l)->a), (po), (n))
 #define local64_xchg(l, n)	atomic64_xchg((&(l)->a), (n))
 #define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u))
 #define local64_inc_not_zero(l)	atomic64_inc_not_zero(&(l)->a)

include/linux/atomic/atomic-arch-fallback.h

@@ -217,6 +217,28 @@
 
 #endif /* arch_try_cmpxchg64_relaxed */
 
+#ifndef arch_try_cmpxchg_local
+#define arch_try_cmpxchg_local(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg_local((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg_local */
+
+#ifndef arch_try_cmpxchg64_local
+#define arch_try_cmpxchg64_local(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg64_local((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg64_local */
+
 #ifndef arch_atomic_read_acquire
 static __always_inline int
 arch_atomic_read_acquire(const atomic_t *v)
@@ -2646,4 +2668,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// 00071fffa021cec66f6290d706d69c91df87bade
+// ad2e2b4d168dbc60a73922616047a9bfa446af36

include/linux/atomic/atomic-instrumented.h

@@ -1948,14 +1948,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_xchg(__ai_ptr, __VA_ARGS__); \
 })
 
 #define xchg_acquire(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \
 })
 
@@ -1963,14 +1963,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_release(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_xchg_release(__ai_ptr, __VA_ARGS__); \
 })
 
 #define xchg_relaxed(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 
@@ -1978,14 +1978,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg_acquire(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \
 })
 
@@ -1993,14 +1993,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_release(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg_relaxed(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 
@@ -2008,14 +2008,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg64_acquire(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \
 })
 
@@ -2023,14 +2023,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_release(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg64_relaxed(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 
@@ -2039,8 +2039,8 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	typeof(oldp) __ai_oldp = (oldp); \
 	kcsan_mb(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
 	arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
@@ -2048,8 +2048,8 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	typeof(oldp) __ai_oldp = (oldp); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
 	arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
@@ -2058,8 +2058,8 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	typeof(oldp) __ai_oldp = (oldp); \
 	kcsan_release(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
 	arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
@@ -2067,8 +2067,8 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	typeof(oldp) __ai_oldp = (oldp); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
 	arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
@@ -2077,8 +2077,8 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	typeof(oldp) __ai_oldp = (oldp); \
 	kcsan_mb(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
 	arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
@@ -2086,8 +2086,8 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	typeof(oldp) __ai_oldp = (oldp); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
 	arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
@@ -2096,8 +2096,8 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	typeof(oldp) __ai_oldp = (oldp); \
 	kcsan_release(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
 	arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
@@ -2105,22 +2105,22 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	typeof(oldp) __ai_oldp = (oldp); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
 	arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define cmpxchg_local(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg64_local(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \
 })
 
@@ -2128,15 +2128,33 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \
 })
 
+#define try_cmpxchg_local(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg64_local(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
 #define cmpxchg_double(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
-	instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
 	arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \
 })
 
@@ -2144,9 +2162,9 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 #define cmpxchg_double_local(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
+	instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
 	arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \
 })
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-// 1b485de9cbaa4900de59e14ee2084357eaeb1c3a
+// 6b513a42e1a1b5962532a019b7fc91eaa044ad5e

kernel/locking/rwbase_rt.c

@@ -72,15 +72,6 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb,
 	int ret;
 
 	raw_spin_lock_irq(&rtm->wait_lock);
-	/*
-	 * Allow readers, as long as the writer has not completely
-	 * acquired the semaphore for write.
-	 */
-	if (atomic_read(&rwb->readers) != WRITER_BIAS) {
-		atomic_inc(&rwb->readers);
-		raw_spin_unlock_irq(&rtm->wait_lock);
-		return 0;
-	}
 
 	/*
 	 * Call into the slow lock path with the rtmutex->wait_lock

scripts/atomic/gen-atomic-fallback.sh

@@ -225,6 +225,10 @@ for cmpxchg in "cmpxchg" "cmpxchg64"; do
 	gen_try_cmpxchg_fallbacks "${cmpxchg}"
 done
 
+for cmpxchg in "cmpxchg_local" "cmpxchg64_local"; do
+	gen_try_cmpxchg_fallback "${cmpxchg}" ""
+done
+
 grep '^[a-z]' "$1" | while read name meta args; do
 	gen_proto "${meta}" "${name}" "atomic" "int" ${args}
 done

scripts/atomic/gen-atomic-instrumented.sh

@@ -104,8 +104,8 @@ cat <<EOF
 EOF
 [ -n "$kcsan_barrier" ] && printf "\t${kcsan_barrier}; \\\\\n"
 cat <<EOF
-	instrument_atomic_write(__ai_ptr, ${mult}sizeof(*__ai_ptr)); \\
-	instrument_atomic_write(__ai_oldp, ${mult}sizeof(*__ai_oldp)); \\
+	instrument_atomic_read_write(__ai_ptr, ${mult}sizeof(*__ai_ptr)); \\
+	instrument_read_write(__ai_oldp, ${mult}sizeof(*__ai_oldp)); \\
 	arch_${xchg}${order}(__ai_ptr, __ai_oldp, __VA_ARGS__); \\
 })
 EOF
@@ -119,7 +119,7 @@ cat <<EOF
 EOF
 [ -n "$kcsan_barrier" ] && printf "\t${kcsan_barrier}; \\\\\n"
 cat <<EOF
-	instrument_atomic_write(__ai_ptr, ${mult}sizeof(*__ai_ptr)); \\
+	instrument_atomic_read_write(__ai_ptr, ${mult}sizeof(*__ai_ptr)); \\
 	arch_${xchg}${order}(__ai_ptr, __VA_ARGS__); \\
 })
 EOF
@@ -173,7 +173,7 @@ for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg" "try_cmpxchg64"; do
 	done
 done
 
-for xchg in "cmpxchg_local" "cmpxchg64_local" "sync_cmpxchg"; do
+for xchg in "cmpxchg_local" "cmpxchg64_local" "sync_cmpxchg" "try_cmpxchg_local" "try_cmpxchg64_local" ; do
 	gen_xchg "${xchg}" "" ""
 	printf "\n"
 done