locking/static_keys: Add a new static_key interface

There are various problems and short-comings with the current
static_key interface:

 - static_key_{true,false}() read like a branch depending on the key
   value, instead of the actual likely/unlikely branch depending on
   init value.

 - static_key_{true,false}() are, as stated above, tied to the
   static_key init values STATIC_KEY_INIT_{TRUE,FALSE}.

 - we're limited to the 2 (out of 4) possible options that compile to
   a default NOP because that's what our arch_static_branch() assembly
   emits.

So provide a new static_key interface:

  DEFINE_STATIC_KEY_TRUE(name);
  DEFINE_STATIC_KEY_FALSE(name);

Which define a key of different types with an initial true/false
value.

Then allow:

   static_branch_likely()
   static_branch_unlikely()

to take a key of either type and emit the right instruction for the
case.

This means adding a second arch_static_branch_jump() assembly helper
which emits a JMP per default.

In order to determine the right instruction for the right state,
encode the branch type in the LSB of jump_entry::key.

This is the final step in removing the naming confusion that has led to
a stream of avoidable bugs such as:

  a833581e372a ("x86, perf: Fix static_key bug in load_mm_cr4()")

... but it also allows new static key combinations that will give us
performance enhancements in the subsequent patches.

Tested-by: Rabin Vincent <rabin@rab.in> # arm
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> # ppc
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # s390
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 139 insertions, 10 deletions

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 65f0ebac63cf..e337a1961933 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -107,12 +107,12 @@ static inline int static_key_count(struct static_key *key)
 
 static __always_inline bool static_key_false(struct static_key *key)
 {
-	return arch_static_branch(key);
+	return arch_static_branch(key, false);
 }
 
 static __always_inline bool static_key_true(struct static_key *key)
 {
-	return !static_key_false(key);
+	return !arch_static_branch(key, true);
 }
 
 extern struct jump_entry __start___jump_table[];
@@ -130,12 +130,12 @@ extern void static_key_slow_inc(struct static_key *key);
 extern void static_key_slow_dec(struct static_key *key);
 extern void jump_label_apply_nops(struct module *mod);
 
-#define STATIC_KEY_INIT_TRUE ((struct static_key)		\
+#define STATIC_KEY_INIT_TRUE					\
 	{ .enabled = ATOMIC_INIT(1),				\
-	  .entries = (void *)JUMP_TYPE_TRUE })
-#define STATIC_KEY_INIT_FALSE ((struct static_key)		\
+	  .entries = (void *)JUMP_TYPE_TRUE }
+#define STATIC_KEY_INIT_FALSE					\
 	{ .enabled = ATOMIC_INIT(0),				\
-	  .entries = (void *)JUMP_TYPE_FALSE })
+	  .entries = (void *)JUMP_TYPE_FALSE }
 
 #else  /* !HAVE_JUMP_LABEL */
 
@@ -183,10 +183,8 @@ static inline int jump_label_apply_nops(struct module *mod)
 	return 0;
 }
 
-#define STATIC_KEY_INIT_TRUE ((struct static_key) \
-		{ .enabled = ATOMIC_INIT(1) })
-#define STATIC_KEY_INIT_FALSE ((struct static_key) \
-		{ .enabled = ATOMIC_INIT(0) })
+#define STATIC_KEY_INIT_TRUE	{ .enabled = ATOMIC_INIT(1) }
+#define STATIC_KEY_INIT_FALSE	{ .enabled = ATOMIC_INIT(0) }
 
 #endif	/* HAVE_JUMP_LABEL */
 
@@ -218,6 +216,137 @@ static inline void static_key_disable(struct static_key *key)
 		static_key_slow_dec(key);
 }
 
+/* -------------------------------------------------------------------------- */
+
+/*
+ * Two type wrappers around static_key, such that we can use compile time
+ * type differentiation to emit the right code.
+ *
+ * All the below code is macros in order to play type games.
+ */
+
+struct static_key_true {
+	struct static_key key;
+};
+
+struct static_key_false {
+	struct static_key key;
+};
+
+#define STATIC_KEY_TRUE_INIT  (struct static_key_true) { .key = STATIC_KEY_INIT_TRUE,  }
+#define STATIC_KEY_FALSE_INIT (struct static_key_false){ .key = STATIC_KEY_INIT_FALSE, }
+
+#define DEFINE_STATIC_KEY_TRUE(name)	\
+	struct static_key_true name = STATIC_KEY_TRUE_INIT
+
+#define DEFINE_STATIC_KEY_FALSE(name)	\
+	struct static_key_false name = STATIC_KEY_FALSE_INIT
+
+#ifdef HAVE_JUMP_LABEL
+
+/*
+ * Combine the right initial value (type) with the right branch order
+ * to generate the desired result.
+ *
+ *
+ * type\branch|	likely (1)	      |	unlikely (0)
+ * -----------+-----------------------+------------------
+ *            |                       |
+ *  true (1)  |	   ...		      |	   ...
+ *            |    NOP		      |	   JMP L
+ *            |    <br-stmts>	      |	1: ...
+ *            |	L: ...		      |
+ *            |			      |
+ *            |			      |	L: <br-stmts>
+ *            |			      |	   jmp 1b
+ *            |                       |
+ * -----------+-----------------------+------------------
+ *            |                       |
+ *  false (0) |	   ...		      |	   ...
+ *            |    JMP L	      |	   NOP
+ *            |    <br-stmts>	      |	1: ...
+ *            |	L: ...		      |
+ *            |			      |
+ *            |			      |	L: <br-stmts>
+ *            |			      |	   jmp 1b
+ *            |                       |
+ * -----------+-----------------------+------------------
+ *
+ * The initial value is encoded in the LSB of static_key::entries,
+ * type: 0 = false, 1 = true.
+ *
+ * The branch type is encoded in the LSB of jump_entry::key,
+ * branch: 0 = unlikely, 1 = likely.
+ *
+ * This gives the following logic table:
+ *
+ *	enabled	type	branch	  instuction
+ * -----------------------------+-----------
+ *	0	0	0	| NOP
+ *	0	0	1	| JMP
+ *	0	1	0	| NOP
+ *	0	1	1	| JMP
+ *
+ *	1	0	0	| JMP
+ *	1	0	1	| NOP
+ *	1	1	0	| JMP
+ *	1	1	1	| NOP
+ *
+ * Which gives the following functions:
+ *
+ *   dynamic: instruction = enabled ^ branch
+ *   static:  instruction = type ^ branch
+ *
+ * See jump_label_type() / jump_label_init_type().
+ */
+
+extern bool ____wrong_branch_error(void);
+
+#define static_branch_likely(x)							\
+({										\
+	bool branch;								\
+	if (__builtin_types_compatible_p(typeof(*x), struct static_key_true))	\
+		branch = !arch_static_branch(&(x)->key, true);			\
+	else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \
+		branch = !arch_static_branch_jump(&(x)->key, true);		\
+	else									\
+		branch = ____wrong_branch_error();				\
+	branch;									\
+})
+
+#define static_branch_unlikely(x)						\
+({										\
+	bool branch;								\
+	if (__builtin_types_compatible_p(typeof(*x), struct static_key_true))	\
+		branch = arch_static_branch_jump(&(x)->key, false);		\
+	else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \
+		branch = arch_static_branch(&(x)->key, false);			\
+	else									\
+		branch = ____wrong_branch_error();				\
+	branch;									\
+})
+
+#else /* !HAVE_JUMP_LABEL */
+
+#define static_branch_likely(x)		likely(static_key_enabled(&(x)->key))
+#define static_branch_unlikely(x)	unlikely(static_key_enabled(&(x)->key))
+
+#endif /* HAVE_JUMP_LABEL */
+
+/*
+ * Advanced usage; refcount, branch is enabled when: count != 0
+ */
+
+#define static_branch_inc(x)		static_key_slow_inc(&(x)->key)
+#define static_branch_dec(x)		static_key_slow_dec(&(x)->key)
+
+/*
+ * Normal usage; boolean enable/disable.
+ */
+
+#define static_branch_enable(x)		static_key_enable(&(x)->key)
+#define static_branch_disable(x)	static_key_disable(&(x)->key)
+
 #endif	/* _LINUX_JUMP_LABEL_H */
 
 #endif /* __ASSEMBLY__ */