static_call: Add static_call_cond()

Extend the static_call infrastructure to optimize the following common
pattern:

	if (func_ptr)
		func_ptr(args...)

For the trampoline (which is in effect a tail-call), we patch the
JMP.d32 into a RET, which then directly consumes the trampoline call.

For the in-line sites we replace the CALL with a NOP5.

NOTE: this is 'obviously' limited to functions with a 'void' return type.

NOTE: DEFINE_STATIC_COND_CALL() only requires a typename, as opposed
      to a full function.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.042977182@infradead.org

include/linux/static_call.h

@@ -16,7 +16,9 @@
  *
  *   DECLARE_STATIC_CALL(name, func);
  *   DEFINE_STATIC_CALL(name, func);
+ *   DEFINE_STATIC_CALL_NULL(name, typename);
  *   static_call(name)(args...);
+ *   static_call_cond(name)(args...);
  *   static_call_update(name, func);
  *
  * Usage example:
@@ -52,6 +54,43 @@
  *   rather than calling through the trampoline.  This requires objtool or a
  *   compiler plugin to detect all the static_call() sites and annotate them
  *   in the .static_call_sites section.
+ *
+ *
+ * Notes on NULL function pointers:
+ *
+ *   Static_call()s support NULL functions, with many of the caveats that
+ *   regular function pointers have.
+ *
+ *   Clearly calling a NULL function pointer is 'BAD', so too for
+ *   static_call()s (although when HAVE_STATIC_CALL it might not be immediately
+ *   fatal). A NULL static_call can be the result of:
+ *
+ *     DECLARE_STATIC_CALL_NULL(my_static_call, void (*)(int));
+ *
+ *   which is equivalent to declaring a NULL function pointer with just a
+ *   typename:
+ *
+ *     void (*my_func_ptr)(int arg1) = NULL;
+ *
+ *   or using static_call_update() with a NULL function. In both cases the
+ *   HAVE_STATIC_CALL implementation will patch the trampoline with a RET
+ *   instruction, instead of an immediate tail-call JMP. HAVE_STATIC_CALL_INLINE
+ *   architectures can patch the trampoline call to a NOP.
+ *
+ *   In all cases, any argument evaluation is unconditional. Unlike a regular
+ *   conditional function pointer call:
+ *
+ *     if (my_func_ptr)
+ *         my_func_ptr(arg1)
+ *
+ *   where the argument evaludation also depends on the pointer value.
+ *
+ *   When calling a static_call that can be NULL, use:
+ *
+ *     static_call_cond(name)(arg1);
+ *
+ *   which will include the required value tests to avoid NULL-pointer
+ *   dereferences.
  */
 
 #include <linux/types.h>
@@ -120,7 +159,16 @@ extern int static_call_text_reserved(void *start, void *end);
 	};								\
 	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+		.type = 1,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
 #define static_call(name)	__static_call(name)
+#define static_call_cond(name)	(void)__static_call(name)
 
 #define EXPORT_STATIC_CALL(name)					\
 	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
@@ -143,7 +191,15 @@ struct static_call_key {
 	};								\
 	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
 #define static_call(name)	__static_call(name)
+#define static_call_cond(name)	(void)__static_call(name)
 
 static inline
 void __static_call_update(struct static_call_key *key, void *tramp, void *func)
@@ -179,9 +235,39 @@ struct static_call_key {
 		.func = _func,						\
 	}
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+	}
+
 #define static_call(name)						\
 	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
 
+static inline void __static_call_nop(void) { }
+
+/*
+ * This horrific hack takes care of two things:
+ *
+ *  - it ensures the compiler will only load the function pointer ONCE,
+ *    which avoids a reload race.
+ *
+ *  - it ensures the argument evaluation is unconditional, similar
+ *    to the HAVE_STATIC_CALL variant.
+ *
+ * Sadly current GCC/Clang (10 for both) do not optimize this properly
+ * and will emit an indirect call for the NULL case :-(
+ */
+#define __static_call_cond(name)					\
+({									\
+	void *func = READ_ONCE(STATIC_CALL_KEY(name).func);		\
+	if (!func)							\
+		func = &__static_call_nop;				\
+	(typeof(STATIC_CALL_TRAMP(name))*)func;				\
+})
+
+#define static_call_cond(name)	(void)__static_call_cond(name)
+
 static inline
 void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 {