Merge tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Introduce cmpxchg128() -- aka. the demise of cmpxchg_double()

   The cmpxchg128() family of functions is basically & functionally the
   same as cmpxchg_double(), but with a saner interface.

   Instead of a 6-parameter horror that forced u128 - u64/u64-halves
   layout details on the interface and exposed users to complexity,
   fragility & bugs, use a natural 3-parameter interface with u128
   types.

 - Restructure the generated atomic headers, and add kerneldoc comments
   for all of the generic atomic{,64,_long}_t operations.

   The generated definitions are much cleaner now, and come with
   documentation.

 - Implement lock_set_cmp_fn() on lockdep, for defining an ordering when
   taking multiple locks of the same type.

   This gets rid of one use of lockdep_set_novalidate_class() in the
   bcache code.

 - Fix raw_cpu_generic_try_cmpxchg() bug due to an unintended variable
   shadowing generating garbage code on Clang on certain ARM builds.

* tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
  locking/atomic: scripts: fix ${atomic}_dec_if_positive() kerneldoc
  percpu: Fix self-assignment of __old in raw_cpu_generic_try_cmpxchg()
  locking/atomic: treewide: delete arch_atomic_*() kerneldoc
  locking/atomic: docs: Add atomic operations to the driver basic API documentation
  locking/atomic: scripts: generate kerneldoc comments
  docs: scripts: kernel-doc: accept bitwise negation like ~@var
  locking/atomic: scripts: simplify raw_atomic*() definitions
  locking/atomic: scripts: simplify raw_atomic_long*() definitions
  locking/atomic: scripts: split pfx/name/sfx/order
  locking/atomic: scripts: restructure fallback ifdeffery
  locking/atomic: scripts: build raw_atomic_long*() directly
  locking/atomic: treewide: use raw_atomic*_<op>()
  locking/atomic: scripts: add trivial raw_atomic*_<op>()
  locking/atomic: scripts: factor out order template generation
  locking/atomic: scripts: remove leftover "${mult}"
  locking/atomic: scripts: remove bogus order parameter
  locking/atomic: xtensa: add preprocessor symbols
  locking/atomic: x86: add preprocessor symbols
  locking/atomic: sparc: add preprocessor symbols
  locking/atomic: sh: add preprocessor symbols
  ...

4 files changed, 162 insertions, 62 deletions

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index e271d6708c87..22142c71d35a 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -130,7 +130,4 @@ ATOMIC_OP(xor, ^)
 #define arch_atomic_read(v)			READ_ONCE((v)->counter)
 #define arch_atomic_set(v, i)			WRITE_ONCE(((v)->counter), (i))
 
-#define arch_atomic_xchg(ptr, v)		(arch_xchg(&(ptr)->counter, (u32)(v)))
-#define arch_atomic_cmpxchg(v, old, new)	(arch_cmpxchg(&((v)->counter), (u32)(old), (u32)(new)))
-
 #endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 71ab4ba9c25d..e076e079f6b2 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -15,21 +15,21 @@ static __always_inline void
 arch_set_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	arch_atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
+	raw_atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
 static __always_inline void
 arch_clear_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	arch_atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
+	raw_atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
 static __always_inline void
 arch_change_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	arch_atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
+	raw_atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
 static __always_inline int
@@ -39,7 +39,7 @@ arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	old = arch_atomic_long_fetch_or(mask, (atomic_long_t *)p);
+	old = raw_atomic_long_fetch_or(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
@@ -50,7 +50,7 @@ arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	old = arch_atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+	old = raw_atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
@@ -61,7 +61,7 @@ arch_test_and_change_bit(unsigned int nr, volatile unsigned long *p)
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	old = arch_atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+	old = raw_atomic_long_fetch_xor(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index 630f2f6b9595..40913516e654 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -25,7 +25,7 @@ arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *p)
 	if (READ_ONCE(*p) & mask)
 		return 1;
 
-	old = arch_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
+	old = raw_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
 
@@ -41,7 +41,7 @@ static __always_inline void
 arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
-	arch_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
+	raw_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
 /**
@@ -63,7 +63,7 @@ arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
 	p += BIT_WORD(nr);
 	old = READ_ONCE(*p);
 	old &= ~BIT_MASK(nr);
-	arch_atomic_long_set_release((atomic_long_t *)p, old);
+	raw_atomic_long_set_release((atomic_long_t *)p, old);
 }
 
 /**
@@ -83,7 +83,7 @@ static inline bool arch_clear_bit_unlock_is_negative_byte(unsigned int nr,
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	old = arch_atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+	old = raw_atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
 	return !!(old & BIT(7));
 }
 #define arch_clear_bit_unlock_is_negative_byte arch_clear_bit_unlock_is_negative_byte
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 6432a7fade91..94cbd50cc870 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -89,27 +89,35 @@ 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_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
 ({									\
-	typeof(pcp1) *__p1 = raw_cpu_ptr(&(pcp1));			\
-	typeof(pcp2) *__p2 = raw_cpu_ptr(&(pcp2));			\
-	int __ret = 0;							\
-	if (*__p1 == (oval1) && *__p2  == (oval2)) {			\
-		*__p1 = nval1;						\
-		*__p2 = nval2;						\
-		__ret = 1;						\
-	}								\
-	(__ret);							\
+	typeof(pcp) __old = (oval);					\
+	raw_cpu_generic_try_cmpxchg(pcp, &__old, nval);			\
+	__old;								\
 })
 
 #define __this_cpu_generic_read_nopreempt(pcp)				\
@@ -170,23 +178,22 @@ do {									\
 	__ret;								\
 })
 
-#define this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+#define this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)			\
 ({									\
-	typeof(pcp) __ret;						\
+	bool __ret;							\
 	unsigned long __flags;						\
 	raw_local_irq_save(__flags);					\
-	__ret = raw_cpu_generic_cmpxchg(pcp, oval, nval);		\
+	__ret = raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval);		\
 	raw_local_irq_restore(__flags);					\
 	__ret;								\
 })
 
-#define this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+#define this_cpu_generic_cmpxchg(pcp, oval, nval)			\
 ({									\
-	int __ret;							\
+	typeof(pcp) __ret;						\
 	unsigned long __flags;						\
 	raw_local_irq_save(__flags);					\
-	__ret = raw_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
-			oval1, oval2, nval1, nval2);			\
+	__ret = raw_cpu_generic_cmpxchg(pcp, oval, nval);		\
 	raw_local_irq_restore(__flags);					\
 	__ret;								\
 })
@@ -282,6 +289,62 @@ 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_try_cmpxchg64
+#ifdef raw_cpu_cmpxchg64
+#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg64)
+#else
+#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) \
+	raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+#ifndef raw_cpu_try_cmpxchg128
+#ifdef raw_cpu_cmpxchg128
+#define raw_cpu_try_cmpxchg128(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg128)
+#else
+#define raw_cpu_try_cmpxchg128(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)
@@ -299,21 +362,13 @@ do {									\
 	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
 
-#ifndef raw_cpu_cmpxchg_double_1
-#define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-#endif
-#ifndef raw_cpu_cmpxchg_double_2
-#define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-#endif
-#ifndef raw_cpu_cmpxchg_double_4
-#define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#ifndef raw_cpu_cmpxchg64
+#define raw_cpu_cmpxchg64(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
-#ifndef raw_cpu_cmpxchg_double_8
-#define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#ifndef raw_cpu_cmpxchg128
+#define raw_cpu_cmpxchg128(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
 
 #ifndef this_cpu_read_1
@@ -407,6 +462,62 @@ 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_try_cmpxchg64
+#ifdef this_cpu_cmpxchg64
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg64)
+#else
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) \
+	this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
+#endif
+#endif
+#ifndef this_cpu_try_cmpxchg128
+#ifdef this_cpu_cmpxchg128
+#define this_cpu_try_cmpxchg128(pcp, ovalp, nval) \
+	__cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg128)
+#else
+#define this_cpu_try_cmpxchg128(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)
@@ -424,21 +535,13 @@ do {									\
 	this_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
 
-#ifndef this_cpu_cmpxchg_double_1
-#define this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-#endif
-#ifndef this_cpu_cmpxchg_double_2
-#define this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-#endif
-#ifndef this_cpu_cmpxchg_double_4
-#define this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#ifndef this_cpu_cmpxchg64
+#define this_cpu_cmpxchg64(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
-#ifndef this_cpu_cmpxchg_double_8
-#define this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#ifndef this_cpu_cmpxchg128
+#define this_cpu_cmpxchg128(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
 
 #endif /* _ASM_GENERIC_PERCPU_H_ */