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, 76 insertions, 11 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 505a306e0271..aebe2c8f6a68 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -394,6 +394,23 @@ ALT_UP_B(.L0_\@)
 #endif
 	.endm
 
+/*
+ * Raw SMP data memory barrier
+ */
+	.macro	__smp_dmb mode
+#if __LINUX_ARM_ARCH__ >= 7
+	.ifeqs "\mode","arm"
+	dmb	ish
+	.else
+	W(dmb)	ish
+	.endif
+#elif __LINUX_ARM_ARCH__ == 6
+	mcr	p15, 0, r0, c7, c10, 5	@ dmb
+#else
+	.error "Incompatible SMP platform"
+#endif
+	.endm
+
 #if defined(CONFIG_CPU_V7M)
 	/*
 	 * setmode is used to assert to be in svc mode during boot. For v7-M
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index db8512d9a918..f0e3b01afa74 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -197,6 +197,16 @@ static inline int arch_atomic_fetch_##op(int i, atomic_t *v)		\
 	return val;							\
 }
 
+#define arch_atomic_add_return			arch_atomic_add_return
+#define arch_atomic_sub_return			arch_atomic_sub_return
+#define arch_atomic_fetch_add			arch_atomic_fetch_add
+#define arch_atomic_fetch_sub			arch_atomic_fetch_sub
+
+#define arch_atomic_fetch_and			arch_atomic_fetch_and
+#define arch_atomic_fetch_andnot		arch_atomic_fetch_andnot
+#define arch_atomic_fetch_or			arch_atomic_fetch_or
+#define arch_atomic_fetch_xor			arch_atomic_fetch_xor
+
 static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -210,8 +220,7 @@ static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
 
 	return ret;
 }
-
-#define arch_atomic_fetch_andnot		arch_atomic_fetch_andnot
+#define arch_atomic_cmpxchg arch_atomic_cmpxchg
 
 #endif /* __LINUX_ARM_ARCH__ */
 
@@ -240,8 +249,6 @@ ATOMIC_OPS(xor, ^=, eor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define arch_atomic_xchg(v, new) (arch_xchg(&((v)->counter), new))
-
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
 	s64 counter;
diff --git a/arch/arm/include/asm/sync_bitops.h b/arch/arm/include/asm/sync_bitops.h
index 6f5d627c44a3..f46b3c570f92 100644
--- a/arch/arm/include/asm/sync_bitops.h
+++ b/arch/arm/include/asm/sync_bitops.h
@@ -14,14 +14,35 @@
  * ops which are SMP safe even on a UP kernel.
  */
 
+/*
+ * Unordered
+ */
+
 #define sync_set_bit(nr, p)		_set_bit(nr, p)
 #define sync_clear_bit(nr, p)		_clear_bit(nr, p)
 #define sync_change_bit(nr, p)		_change_bit(nr, p)
-#define sync_test_and_set_bit(nr, p)	_test_and_set_bit(nr, p)
-#define sync_test_and_clear_bit(nr, p)	_test_and_clear_bit(nr, p)
-#define sync_test_and_change_bit(nr, p)	_test_and_change_bit(nr, p)
 #define sync_test_bit(nr, addr)		test_bit(nr, addr)
-#define arch_sync_cmpxchg		arch_cmpxchg
 
+/*
+ * Fully ordered
+ */
+
+int _sync_test_and_set_bit(int nr, volatile unsigned long * p);
+#define sync_test_and_set_bit(nr, p)	_sync_test_and_set_bit(nr, p)
+
+int _sync_test_and_clear_bit(int nr, volatile unsigned long * p);
+#define sync_test_and_clear_bit(nr, p)	_sync_test_and_clear_bit(nr, p)
+
+int _sync_test_and_change_bit(int nr, volatile unsigned long * p);
+#define sync_test_and_change_bit(nr, p)	_sync_test_and_change_bit(nr, p)
+
+#define arch_sync_cmpxchg(ptr, old, new)				\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__smp_mb__before_atomic();					\
+	__ret = arch_cmpxchg_relaxed((ptr), (old), (new));		\
+	__smp_mb__after_atomic();					\
+	__ret;								\
+})
 
 #endif
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 95bd35991288..f069d1b2318e 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -28,7 +28,7 @@ UNWIND(	.fnend		)
 ENDPROC(\name		)
 	.endm
 
-	.macro	testop, name, instr, store
+	.macro	__testop, name, instr, store, barrier
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
@@ -38,7 +38,7 @@ UNWIND(	.fnstart	)
 	mov	r0, r0, lsr #5
 	add	r1, r1, r0, lsl #2	@ Get word offset
 	mov	r3, r2, lsl r3		@ create mask
-	smp_dmb
+	\barrier
 #if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
 	.arch_extension	mp
 	ALT_SMP(W(pldw)	[r1])
@@ -50,13 +50,21 @@ UNWIND(	.fnstart	)
 	strex	ip, r2, [r1]
 	cmp	ip, #0
 	bne	1b
-	smp_dmb
+	\barrier
 	cmp	r0, #0
 	movne	r0, #1
 2:	bx	lr
 UNWIND(	.fnend		)
 ENDPROC(\name		)
 	.endm
+
+	.macro	testop, name, instr, store
+	__testop \name, \instr, \store, smp_dmb
+	.endm
+
+	.macro	sync_testop, name, instr, store
+	__testop \name, \instr, \store, __smp_dmb
+	.endm
 #else
 	.macro	bitop, name, instr
 ENTRY(	\name		)
diff --git a/arch/arm/lib/testchangebit.S b/arch/arm/lib/testchangebit.S
index 4ebecc67e6e0..f13fe9bc2399 100644
--- a/arch/arm/lib/testchangebit.S
+++ b/arch/arm/lib/testchangebit.S
@@ -10,3 +10,7 @@
                 .text
 
 testop	_test_and_change_bit, eor, str
+
+#if __LINUX_ARM_ARCH__ >= 6
+sync_testop	_sync_test_and_change_bit, eor, str
+#endif
diff --git a/arch/arm/lib/testclearbit.S b/arch/arm/lib/testclearbit.S
index 009afa0f5b4a..4d2c5ca620eb 100644
--- a/arch/arm/lib/testclearbit.S
+++ b/arch/arm/lib/testclearbit.S
@@ -10,3 +10,7 @@
                 .text
 
 testop	_test_and_clear_bit, bicne, strne
+
+#if __LINUX_ARM_ARCH__ >= 6
+sync_testop	_sync_test_and_clear_bit, bicne, strne
+#endif
diff --git a/arch/arm/lib/testsetbit.S b/arch/arm/lib/testsetbit.S
index f3192e55acc8..649dbab65d8d 100644
--- a/arch/arm/lib/testsetbit.S
+++ b/arch/arm/lib/testsetbit.S
@@ -10,3 +10,7 @@
                 .text
 
 testop	_test_and_set_bit, orreq, streq
+
+#if __LINUX_ARM_ARCH__ >= 6
+sync_testop	_sync_test_and_set_bit, orreq, streq
+#endif