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
  ...

7 files changed, 128 insertions, 312 deletions

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 5e754e895767..55a55ec04350 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -14,12 +14,6 @@
  * resource counting etc..
  */
 
-/**
- * arch_atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v.
- */
 static __always_inline int arch_atomic_read(const atomic_t *v)
 {
 	/*
@@ -29,25 +23,11 @@ static __always_inline int arch_atomic_read(const atomic_t *v)
 	return __READ_ONCE((v)->counter);
 }
 
-/**
- * arch_atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
 static __always_inline void arch_atomic_set(atomic_t *v, int i)
 {
 	__WRITE_ONCE(v->counter, i);
 }
 
-/**
- * arch_atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
 static __always_inline void arch_atomic_add(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
@@ -55,13 +35,6 @@ static __always_inline void arch_atomic_add(int i, atomic_t *v)
 		     : "ir" (i) : "memory");
 }
 
-/**
- * arch_atomic_sub - subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
 static __always_inline void arch_atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
@@ -69,27 +42,12 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
 		     : "ir" (i) : "memory");
 }
 
-/**
- * arch_atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
 static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i);
 }
 #define arch_atomic_sub_and_test arch_atomic_sub_and_test
 
-/**
- * arch_atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
@@ -97,12 +55,6 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
 }
 #define arch_atomic_inc arch_atomic_inc
 
-/**
- * arch_atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
@@ -110,69 +62,30 @@ static __always_inline void arch_atomic_dec(atomic_t *v)
 }
 #define arch_atomic_dec arch_atomic_dec
 
-/**
- * arch_atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
 static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
 {
 	return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e);
 }
 #define arch_atomic_dec_and_test arch_atomic_dec_and_test
 
-/**
- * arch_atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
 static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
 {
 	return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e);
 }
 #define arch_atomic_inc_and_test arch_atomic_inc_and_test
 
-/**
- * arch_atomic_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
 static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i);
 }
 #define arch_atomic_add_negative arch_atomic_add_negative
 
-/**
- * arch_atomic_add_return - add integer and return
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns @i + @v
- */
 static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
 #define arch_atomic_add_return arch_atomic_add_return
 
-/**
- * arch_atomic_sub_return - subtract integer and return
- * @v: pointer of type atomic_t
- * @i: integer value to subtract
- *
- * Atomically subtracts @i from @v and returns @v - @i
- */
 static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
 {
 	return arch_atomic_add_return(-i, v);
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 808b4eece251..3486d91b8595 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -61,30 +61,12 @@ ATOMIC64_DECL(add_unless);
 #undef __ATOMIC64_DECL
 #undef ATOMIC64_EXPORT
 
-/**
- * arch_atomic64_cmpxchg - cmpxchg atomic64 variable
- * @v: pointer to type atomic64_t
- * @o: expected value
- * @n: new value
- *
- * Atomically sets @v to @n if it was equal to @o and returns
- * the old value.
- */
-
 static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	return arch_cmpxchg64(&v->counter, o, n);
 }
 #define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
 
-/**
- * arch_atomic64_xchg - xchg atomic64 variable
- * @v: pointer to type atomic64_t
- * @n: value to assign
- *
- * Atomically xchgs the value of @v to @n and returns
- * the old value.
- */
 static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 {
 	s64 o;
@@ -97,13 +79,6 @@ static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 }
 #define arch_atomic64_xchg arch_atomic64_xchg
 
-/**
- * arch_atomic64_set - set atomic64 variable
- * @v: pointer to type atomic64_t
- * @i: value to assign
- *
- * Atomically sets the value of @v to @n.
- */
 static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned high = (unsigned)(i >> 32);
@@ -113,12 +88,6 @@ static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 			     : "eax", "edx", "memory");
 }
 
-/**
- * arch_atomic64_read - read atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically reads the value of @v and returns it.
- */
 static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	s64 r;
@@ -126,13 +95,6 @@ static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 	return r;
 }
 
-/**
- * arch_atomic64_add_return - add and return
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns @i + *@v
- */
 static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
@@ -142,9 +104,6 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_add_return arch_atomic64_add_return
 
-/*
- * Other variants with different arithmetic operators:
- */
 static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
@@ -172,13 +131,6 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 }
 #define arch_atomic64_dec_return arch_atomic64_dec_return
 
-/**
- * arch_atomic64_add - add integer to atomic64 variable
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v.
- */
 static __always_inline s64 arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
@@ -187,13 +139,6 @@ static __always_inline s64 arch_atomic64_add(s64 i, atomic64_t *v)
 	return i;
 }
 
-/**
- * arch_atomic64_sub - subtract the atomic64 variable
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v.
- */
 static __always_inline s64 arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
@@ -202,12 +147,6 @@ static __always_inline s64 arch_atomic64_sub(s64 i, atomic64_t *v)
 	return i;
 }
 
-/**
- * arch_atomic64_inc - increment atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1.
- */
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
@@ -215,12 +154,6 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
-/**
- * arch_atomic64_dec - decrement atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
@@ -228,15 +161,6 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
 }
 #define arch_atomic64_dec arch_atomic64_dec
 
-/**
- * arch_atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if the add was done, zero otherwise.
- */
 static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned low = (unsigned)u;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index c496595bf601..3165c0feedf7 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -10,37 +10,16 @@
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
-/**
- * arch_atomic64_read - read atomic64 variable
- * @v: pointer of type atomic64_t
- *
- * Atomically reads the value of @v.
- * Doesn't imply a read memory barrier.
- */
 static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	return __READ_ONCE((v)->counter);
 }
 
-/**
- * arch_atomic64_set - set atomic64 variable
- * @v: pointer to type atomic64_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
 static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	__WRITE_ONCE(v->counter, i);
 }
 
-/**
- * arch_atomic64_add - add integer to atomic64 variable
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v.
- */
 static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
@@ -48,13 +27,6 @@ static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 		     : "er" (i), "m" (v->counter) : "memory");
 }
 
-/**
- * arch_atomic64_sub - subtract the atomic64 variable
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v.
- */
 static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
@@ -62,27 +34,12 @@ static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 		     : "er" (i), "m" (v->counter) : "memory");
 }
 
-/**
- * arch_atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
 static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i);
 }
 #define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
 
-/**
- * arch_atomic64_inc - increment atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1.
- */
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
@@ -91,12 +48,6 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
-/**
- * arch_atomic64_dec - decrement atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
@@ -105,56 +56,24 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
 }
 #define arch_atomic64_dec arch_atomic64_dec
 
-/**
- * arch_atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
 static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e);
 }
 #define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
 
-/**
- * arch_atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
 static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e);
 }
 #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
 
-/**
- * arch_atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
 static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i);
 }
 #define arch_atomic64_add_negative arch_atomic64_add_negative
 
-/**
- * arch_atomic64_add_return - add and return
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns @i + @v
- */
 static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	return i + xadd(&v->counter, i);
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 540573f515b7..d53636506134 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -239,29 +239,4 @@ extern void __add_wrong_size(void)
 #define __xadd(ptr, inc, lock)	__xchg_op((ptr), (inc), xadd, lock)
 #define xadd(ptr, inc)		__xadd((ptr), (inc), LOCK_PREFIX)
 
-#define __cmpxchg_double(pfx, p1, p2, o1, o2, n1, n2)			\
-({									\
-	bool __ret;							\
-	__typeof__(*(p1)) __old1 = (o1), __new1 = (n1);			\
-	__typeof__(*(p2)) __old2 = (o2), __new2 = (n2);			\
-	BUILD_BUG_ON(sizeof(*(p1)) != sizeof(long));			\
-	BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long));			\
-	VM_BUG_ON((unsigned long)(p1) % (2 * sizeof(long)));		\
-	VM_BUG_ON((unsigned long)((p1) + 1) != (unsigned long)(p2));	\
-	asm volatile(pfx "cmpxchg%c5b %1"				\
-		     CC_SET(e)						\
-		     : CC_OUT(e) (__ret),				\
-		       "+m" (*(p1)), "+m" (*(p2)),			\
-		       "+a" (__old1), "+d" (__old2)			\
-		     : "i" (2 * sizeof(long)),				\
-		       "b" (__new1), "c" (__new2));			\
-	__ret;								\
-})
-
-#define arch_cmpxchg_double(p1, p2, o1, o2, n1, n2) \
-	__cmpxchg_double(LOCK_PREFIX, p1, p2, o1, o2, n1, n2)
-
-#define arch_cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
-	__cmpxchg_double(, p1, p2, o1, o2, n1, n2)
-
 #endif	/* ASM_X86_CMPXCHG_H */
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 6ba80ce9438d..b5731c51f0f4 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -103,6 +103,6 @@ static inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *pold, u64 new)
 
 #endif
 
-#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX8)
+#define system_has_cmpxchg64()		boot_cpu_has(X86_FEATURE_CX8)
 
 #endif /* _ASM_X86_CMPXCHG_32_H */
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 0d3beb27b7fe..44b08b53ab32 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -20,6 +20,71 @@
 	arch_try_cmpxchg((ptr), (po), (n));				\
 })
 
-#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
+union __u128_halves {
+	u128 full;
+	struct {
+		u64 low, high;
+	};
+};
+
+#define __arch_cmpxchg128(_ptr, _old, _new, _lock)			\
+({									\
+	union __u128_halves o = { .full = (_old), },			\
+			    n = { .full = (_new), };			\
+									\
+	asm volatile(_lock "cmpxchg16b %[ptr]"				\
+		     : [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high)			\
+		     : "memory");					\
+									\
+	o.full;								\
+})
+
+static __always_inline u128 arch_cmpxchg128(volatile u128 *ptr, u128 old, u128 new)
+{
+	return __arch_cmpxchg128(ptr, old, new, LOCK_PREFIX);
+}
+#define arch_cmpxchg128 arch_cmpxchg128
+
+static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old, u128 new)
+{
+	return __arch_cmpxchg128(ptr, old, new,);
+}
+#define arch_cmpxchg128_local arch_cmpxchg128_local
+
+#define __arch_try_cmpxchg128(_ptr, _oldp, _new, _lock)			\
+({									\
+	union __u128_halves o = { .full = *(_oldp), },			\
+			    n = { .full = (_new), };			\
+	bool ret;							\
+									\
+	asm volatile(_lock "cmpxchg16b %[ptr]"				\
+		     CC_SET(e)						\
+		     : CC_OUT(e) (ret),					\
+		       [ptr] "+m" (*ptr),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high)			\
+		     : "memory");					\
+									\
+	if (unlikely(!ret))						\
+		*(_oldp) = o.full;					\
+									\
+	likely(ret);							\
+})
+
+static __always_inline bool arch_try_cmpxchg128(volatile u128 *ptr, u128 *oldp, u128 new)
+{
+	return __arch_try_cmpxchg128(ptr, oldp, new, LOCK_PREFIX);
+}
+#define arch_try_cmpxchg128 arch_try_cmpxchg128
+
+static __always_inline bool arch_try_cmpxchg128_local(volatile u128 *ptr, u128 *oldp, u128 new)
+{
+	return __arch_try_cmpxchg128(ptr, oldp, new,);
+}
+#define arch_try_cmpxchg128_local arch_try_cmpxchg128_local
+
+#define system_has_cmpxchg128()		boot_cpu_has(X86_FEATURE_CX16)
 
 #endif /* _ASM_X86_CMPXCHG_64_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 13c0d63ed55e..34734d730463 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -210,6 +210,67 @@ do {									\
 	(typeof(_var))(unsigned long) pco_old__;			\
 })
 
+#if defined(CONFIG_X86_32) && !defined(CONFIG_UML)
+#define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval)		\
+({									\
+	union {								\
+		u64 var;						\
+		struct {						\
+			u32 low, high;					\
+		};							\
+	} old__, new__;							\
+									\
+	old__.var = _oval;						\
+	new__.var = _nval;						\
+									\
+	asm qual (ALTERNATIVE("leal %P[var], %%esi; call this_cpu_cmpxchg8b_emu", \
+			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		  : [var] "+m" (_var),					\
+		    "+a" (old__.low),					\
+		    "+d" (old__.high)					\
+		  : "b" (new__.low),					\
+		    "c" (new__.high)					\
+		  : "memory", "esi");					\
+									\
+	old__.var;							\
+})
+
+#define raw_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg64_op(8,         , pcp, oval, nval)
+#define this_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg64_op(8, volatile, pcp, oval, nval)
+#endif
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg_op(8,         , pcp, oval, nval);
+#define this_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval);
+
+#define percpu_cmpxchg128_op(size, qual, _var, _oval, _nval)		\
+({									\
+	union {								\
+		u128 var;						\
+		struct {						\
+			u64 low, high;					\
+		};							\
+	} old__, new__;							\
+									\
+	old__.var = _oval;						\
+	new__.var = _nval;						\
+									\
+	asm qual (ALTERNATIVE("leaq %P[var], %%rsi; call this_cpu_cmpxchg16b_emu", \
+			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		  : [var] "+m" (_var),					\
+		    "+a" (old__.low),					\
+		    "+d" (old__.high)					\
+		  : "b" (new__.low),					\
+		    "c" (new__.high)					\
+		  : "memory", "rsi");					\
+									\
+	old__.var;							\
+})
+
+#define raw_cpu_cmpxchg128(pcp, oval, nval)	percpu_cmpxchg128_op(16,         , pcp, oval, nval)
+#define this_cpu_cmpxchg128(pcp, oval, nval)	percpu_cmpxchg128_op(16, volatile, pcp, oval, nval)
+#endif
+
 /*
  * this_cpu_read() makes gcc load the percpu variable every time it is
  * accessed while this_cpu_read_stable() allows the value to be cached.
@@ -290,23 +351,6 @@ do {									\
 #define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
 
-#ifdef CONFIG_X86_CMPXCHG64
-#define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2)		\
-({									\
-	bool __ret;							\
-	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
-	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
-	asm volatile("cmpxchg8b "__percpu_arg(1)			\
-		     CC_SET(z)						\
-		     : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \
-		     : "b" (__n1), "c" (__n2));				\
-	__ret;								\
-})
-
-#define raw_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
-#define this_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
-#endif /* CONFIG_X86_CMPXCHG64 */
-
 /*
  * Per cpu atomic 64 bit operations are only available under 64 bit.
  * 32 bit must fall back to generic operations.
@@ -329,30 +373,6 @@ do {									\
 #define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, volatile, pcp, val)
 #define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(8, volatile, pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
-
-/*
- * Pretty complex macro to generate cmpxchg16 instruction.  The instruction
- * is not supported on early AMD64 processors so we must be able to emulate
- * it in software.  The address used in the cmpxchg16 instruction must be
- * aligned to a 16 byte boundary.
- */
-#define percpu_cmpxchg16b_double(pcp1, pcp2, o1, o2, n1, n2)		\
-({									\
-	bool __ret;							\
-	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
-	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
-	alternative_io("leaq %P1,%%rsi\n\tcall this_cpu_cmpxchg16b_emu\n\t", \
-		       "cmpxchg16b " __percpu_arg(1) "\n\tsetz %0\n\t",	\
-		       X86_FEATURE_CX16,				\
-		       ASM_OUTPUT2("=a" (__ret), "+m" (pcp1),		\
-				   "+m" (pcp2), "+d" (__o2)),		\
-		       "b" (__n1), "c" (__n2), "a" (__o1) : "rsi");	\
-	__ret;								\
-})
-
-#define raw_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
-#define this_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
-
 #endif
 
 static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,