Locking changes for v6.5:

- 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. 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.
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmSav3wRHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1gDyxAAjCHQjpolrre7fRpyiTDwqzIKT27H04vQ
 zrQVlVc42WBnn9pe8LthGy43/RvYvqlZvLoLONA4fMkuYriM6nSMsoZjeUmE+6Rs
 QAElQC74P5YvEBOa67VNY3/M7sj22ftDe7ODtVV8OrnPjMk1sQNRvaK025Cs3yig
 8MAI//hHGNmyVAp1dPYZMJNqxGCvluReLZ4SaUJFCMrg7YgUXgCBj/5Gi07TlKxn
 sT8BFCssoEW/B9FXkh59B1t6FBCZoSy4XSZfsZe0uVAUJ4XDEOO+zBgaWFCedNQT
 wP323ryBgMrkzUKA8j2/o5d3QnMA1GcBfHNNlvAl/fOfrxWXzDZnOEY26YcaLMa0
 YIuRF/JNbPZlt6DCUVBUEvMPpfNYi18dFN0rat1a6xL2L4w+tm55y3mFtSsg76Ka
 r7L2nWlRrAGXnuA+VEPqkqbSWRUSWOv5hT2Mcyb5BqqZRsxBETn6G8GVAzIO6j6v
 giyfUdA8Z9wmMZ7NtB6usxe3p1lXtnZ/shCE7ZHXm6xstyZrSXaHgOSgAnB9DcuJ
 7KpGIhhSODQSwC/h/J0KEpb9Pr/5jCWmXAQ2DWnZK6ndt1jUfFi8pfK58wm0AuAM
 o9t8Mx3o8wZjbMdt6up9OIM1HyFiMx2BSaZK+8f/bWemHQ0xwez5g4k5O5AwVOaC
 x9Nt+Tp0Ze4=
 =DsYj
 -----END PGP SIGNATURE-----

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
  ...

include/linux/context_tracking.h

@@ -119,7 +119,7 @@ extern void ct_idle_exit(void);
  */
 static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
-	return !(arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX);
+	return !(raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX);
 }
 
 /*
@@ -128,7 +128,7 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
  */
 static __always_inline unsigned long ct_state_inc(int incby)
 {
-	return arch_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state));
+	return raw_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state));
 }
 
 static __always_inline bool warn_rcu_enter(void)

include/linux/context_tracking_state.h

@@ -51,7 +51,7 @@ DECLARE_PER_CPU(struct context_tracking, context_tracking);
 #ifdef CONFIG_CONTEXT_TRACKING_USER
 static __always_inline int __ct_state(void)
 {
-	return arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK;
+	return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK;
 }
 #endif
 

include/linux/cpumask.h

@@ -1071,7 +1071,7 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
  */
 static __always_inline unsigned int num_online_cpus(void)
 {
-	return arch_atomic_read(&__num_online_cpus);
+	return raw_atomic_read(&__num_online_cpus);
 }
 #define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)

include/linux/dmar.h

@@ -202,67 +202,74 @@ static inline void detect_intel_iommu(void)
 
 struct irte {
 	union {
-		/* Shared between remapped and posted mode*/
 		struct {
-			__u64	present		: 1,  /*  0      */
-				fpd		: 1,  /*  1      */
-				__res0		: 6,  /*  2 -  6 */
-				avail		: 4,  /*  8 - 11 */
-				__res1		: 3,  /* 12 - 14 */
-				pst		: 1,  /* 15      */
-				vector		: 8,  /* 16 - 23 */
-				__res2		: 40; /* 24 - 63 */
-		};
+			union {
+				/* Shared between remapped and posted mode*/
+				struct {
+					__u64	present		: 1,  /*  0      */
+						fpd		: 1,  /*  1      */
+						__res0		: 6,  /*  2 -  6 */
+						avail		: 4,  /*  8 - 11 */
+						__res1		: 3,  /* 12 - 14 */
+						pst		: 1,  /* 15      */
+						vector		: 8,  /* 16 - 23 */
+						__res2		: 40; /* 24 - 63 */
+				};
 
-		/* Remapped mode */
-		struct {
-			__u64	r_present	: 1,  /*  0      */
-				r_fpd		: 1,  /*  1      */
-				dst_mode	: 1,  /*  2      */
-				redir_hint	: 1,  /*  3      */
-				trigger_mode	: 1,  /*  4      */
-				dlvry_mode	: 3,  /*  5 -  7 */
-				r_avail		: 4,  /*  8 - 11 */
-				r_res0		: 4,  /* 12 - 15 */
-				r_vector	: 8,  /* 16 - 23 */
-				r_res1		: 8,  /* 24 - 31 */
-				dest_id		: 32; /* 32 - 63 */
-		};
+				/* Remapped mode */
+				struct {
+					__u64	r_present	: 1,  /*  0      */
+						r_fpd		: 1,  /*  1      */
+						dst_mode	: 1,  /*  2      */
+						redir_hint	: 1,  /*  3      */
+						trigger_mode	: 1,  /*  4      */
+						dlvry_mode	: 3,  /*  5 -  7 */
+						r_avail		: 4,  /*  8 - 11 */
+						r_res0		: 4,  /* 12 - 15 */
+						r_vector	: 8,  /* 16 - 23 */
+						r_res1		: 8,  /* 24 - 31 */
+						dest_id		: 32; /* 32 - 63 */
+				};
 
-		/* Posted mode */
-		struct {
-			__u64	p_present	: 1,  /*  0      */
-				p_fpd		: 1,  /*  1      */
-				p_res0		: 6,  /*  2 -  7 */
-				p_avail		: 4,  /*  8 - 11 */
-				p_res1		: 2,  /* 12 - 13 */
-				p_urgent	: 1,  /* 14      */
-				p_pst		: 1,  /* 15      */
-				p_vector	: 8,  /* 16 - 23 */
-				p_res2		: 14, /* 24 - 37 */
-				pda_l		: 26; /* 38 - 63 */
-		};
-		__u64 low;
-	};
+				/* Posted mode */
+				struct {
+					__u64	p_present	: 1,  /*  0      */
+						p_fpd		: 1,  /*  1      */
+						p_res0		: 6,  /*  2 -  7 */
+						p_avail		: 4,  /*  8 - 11 */
+						p_res1		: 2,  /* 12 - 13 */
+						p_urgent	: 1,  /* 14      */
+						p_pst		: 1,  /* 15      */
+						p_vector	: 8,  /* 16 - 23 */
+						p_res2		: 14, /* 24 - 37 */
+						pda_l		: 26; /* 38 - 63 */
+				};
+				__u64 low;
+			};
 
-	union {
-		/* Shared between remapped and posted mode*/
-		struct {
-			__u64	sid		: 16,  /* 64 - 79  */
-				sq		: 2,   /* 80 - 81  */
-				svt		: 2,   /* 82 - 83  */
-				__res3		: 44;  /* 84 - 127 */
-		};
+			union {
+				/* Shared between remapped and posted mode*/
+				struct {
+					__u64	sid		: 16,  /* 64 - 79  */
+						sq		: 2,   /* 80 - 81  */
+						svt		: 2,   /* 82 - 83  */
+						__res3		: 44;  /* 84 - 127 */
+				};
 
-		/* Posted mode*/
-		struct {
-			__u64	p_sid		: 16,  /* 64 - 79  */
-				p_sq		: 2,   /* 80 - 81  */
-				p_svt		: 2,   /* 82 - 83  */
-				p_res3		: 12,  /* 84 - 95  */
-				pda_h		: 32;  /* 96 - 127 */
+				/* Posted mode*/
+				struct {
+					__u64	p_sid		: 16,  /* 64 - 79  */
+						p_sq		: 2,   /* 80 - 81  */
+						p_svt		: 2,   /* 82 - 83  */
+						p_res3		: 12,  /* 84 - 95  */
+						pda_h		: 32;  /* 96 - 127 */
+				};
+				__u64 high;
+			};
 		};
-		__u64 high;
+#ifdef CONFIG_IRQ_REMAP
+		__u128 irte;
+#endif
 	};
 };
 

include/linux/jump_label.h

@@ -257,7 +257,7 @@ extern enum jump_label_type jump_label_init_type(struct jump_entry *entry);
 
 static __always_inline int static_key_count(struct static_key *key)
 {
-	return arch_atomic_read(&key->enabled);
+	return raw_atomic_read(&key->enabled);
 }
 
 static __always_inline void jump_label_init(void)

include/linux/lockdep.h

@@ -447,6 +447,14 @@ extern int lockdep_is_held(const void *);
 
 #endif /* !LOCKDEP */
 
+#ifdef CONFIG_PROVE_LOCKING
+void lockdep_set_lock_cmp_fn(struct lockdep_map *, lock_cmp_fn, lock_print_fn);
+
+#define lock_set_cmp_fn(lock, ...)	lockdep_set_lock_cmp_fn(&(lock)->dep_map, __VA_ARGS__)
+#else
+#define lock_set_cmp_fn(lock, ...)	do { } while (0)
+#endif
+
 enum xhlock_context_t {
 	XHLOCK_HARD,
 	XHLOCK_SOFT,

include/linux/lockdep_types.h

@@ -85,6 +85,11 @@ struct lock_trace;
 
 #define LOCKSTAT_POINTS		4
 
+struct lockdep_map;
+typedef int (*lock_cmp_fn)(const struct lockdep_map *a,
+			   const struct lockdep_map *b);
+typedef void (*lock_print_fn)(const struct lockdep_map *map);
+
 /*
  * The lock-class itself. The order of the structure members matters.
  * reinit_class() zeroes the key member and all subsequent members.
@@ -110,6 +115,9 @@ struct lock_class {
 	struct list_head		locks_after, locks_before;
 
 	const struct lockdep_subclass_key *key;
+	lock_cmp_fn			cmp_fn;
+	lock_print_fn			print_fn;
+
 	unsigned int			subclass;
 	unsigned int			dep_gen_id;
 

include/linux/percpu-defs.h

@@ -343,31 +343,19 @@ static __always_inline void __this_cpu_preempt_check(const char *op) { }
 	pscr2_ret__;							\
 })
 
-/*
- * Special handling for cmpxchg_double.  cmpxchg_double is passed two
- * percpu variables.  The first has to be aligned to a double word
- * boundary and the second has to follow directly thereafter.
- * We enforce this on all architectures even if they don't support
- * a double cmpxchg instruction, since it's a cheap requirement, and it
- * avoids breaking the requirement for architectures with the instruction.
- */
-#define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...)		\
+#define __pcpu_size_call_return2bool(stem, variable, ...)		\
 ({									\
-	bool pdcrb_ret__;						\
-	__verify_pcpu_ptr(&(pcp1));					\
-	BUILD_BUG_ON(sizeof(pcp1) != sizeof(pcp2));			\
-	VM_BUG_ON((unsigned long)(&(pcp1)) % (2 * sizeof(pcp1)));	\
-	VM_BUG_ON((unsigned long)(&(pcp2)) !=				\
-		  (unsigned long)(&(pcp1)) + sizeof(pcp1));		\
-	switch(sizeof(pcp1)) {						\
-	case 1: pdcrb_ret__ = stem##1(pcp1, pcp2, __VA_ARGS__); break;	\
-	case 2: pdcrb_ret__ = stem##2(pcp1, pcp2, __VA_ARGS__); break;	\
-	case 4: pdcrb_ret__ = stem##4(pcp1, pcp2, __VA_ARGS__); break;	\
-	case 8: pdcrb_ret__ = stem##8(pcp1, pcp2, __VA_ARGS__); break;	\
+	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;			\
 	}								\
-	pdcrb_ret__;							\
+	pscr2_ret__;							\
 })
 
 #define __pcpu_size_call(stem, variable, ...)				\
@@ -426,9 +414,8 @@ 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_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
-
+#define raw_cpu_try_cmpxchg(pcp, ovalp, nval) \
+	__pcpu_size_call_return2bool(raw_cpu_try_cmpxchg_, pcp, ovalp, nval)
 #define raw_cpu_sub(pcp, val)		raw_cpu_add(pcp, -(val))
 #define raw_cpu_inc(pcp)		raw_cpu_add(pcp, 1)
 #define raw_cpu_dec(pcp)		raw_cpu_sub(pcp, 1)
@@ -488,11 +475,6 @@ do {									\
 	raw_cpu_cmpxchg(pcp, oval, nval);				\
 })
 
-#define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-({	__this_cpu_preempt_check("cmpxchg_double");			\
-	raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2);	\
-})
-
 #define __this_cpu_sub(pcp, val)	__this_cpu_add(pcp, -(typeof(pcp))(val))
 #define __this_cpu_inc(pcp)		__this_cpu_add(pcp, 1)
 #define __this_cpu_dec(pcp)		__this_cpu_sub(pcp, 1)
@@ -513,9 +495,8 @@ 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_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-	__pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
-
+#define this_cpu_try_cmpxchg(pcp, ovalp, nval) \
+	__pcpu_size_call_return2bool(this_cpu_try_cmpxchg_, pcp, ovalp, nval)
 #define this_cpu_sub(pcp, val)		this_cpu_add(pcp, -(typeof(pcp))(val))
 #define this_cpu_inc(pcp)		this_cpu_add(pcp, 1)
 #define this_cpu_dec(pcp)		this_cpu_sub(pcp, 1)

include/linux/slub_def.h

@@ -39,7 +39,8 @@ enum stat_item {
 	CPU_PARTIAL_FREE,	/* Refill cpu partial on free */
 	CPU_PARTIAL_NODE,	/* Refill cpu partial from node partial */
 	CPU_PARTIAL_DRAIN,	/* Drain cpu partial to node partial */
-	NR_SLUB_STAT_ITEMS };
+	NR_SLUB_STAT_ITEMS
+};
 
 #ifndef CONFIG_SLUB_TINY
 /*
@@ -47,8 +48,13 @@ enum stat_item {
  * with this_cpu_cmpxchg_double() alignment requirements.
  */
 struct kmem_cache_cpu {
-	void **freelist;	/* Pointer to next available object */
-	unsigned long tid;	/* Globally unique transaction id */
+	union {
+		struct {
+			void **freelist;	/* Pointer to next available object */
+			unsigned long tid;	/* Globally unique transaction id */
+		};
+		freelist_aba_t freelist_tid;
+	};
 	struct slab *slab;	/* The slab from which we are allocating */
 #ifdef CONFIG_SLUB_CPU_PARTIAL
 	struct slab *partial;	/* Partially allocated frozen slabs */

include/linux/types.h

@@ -10,6 +10,11 @@
 #define DECLARE_BITMAP(name,bits) \
 	unsigned long name[BITS_TO_LONGS(bits)]
 
+#ifdef __SIZEOF_INT128__
+typedef __s128 s128;
+typedef __u128 u128;
+#endif
+
 typedef u32 __kernel_dev_t;
 
 typedef __kernel_fd_set		fd_set;