static_call: Add inline static call infrastructure

Add infrastructure for an arch-specific CONFIG_HAVE_STATIC_CALL_INLINE
option, which is a faster version of CONFIG_HAVE_STATIC_CALL.  At
runtime, the static call sites are patched directly, rather than using
the out-of-line trampolines.

Compared to out-of-line static calls, the performance benefits are more
modest, but still measurable.  Steven Rostedt did some tracepoint
measurements:

  https://lkml.kernel.org/r/20181126155405.72b4f718@gandalf.local.home

This code is heavily inspired by the jump label code (aka "static
jumps"), as some of the concepts are very similar.

For more details, see the comments in include/linux/static_call.h.

[peterz: simplified interface; merged trampolines]

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.684334440@infradead.org

arch/Kconfig

@@ -978,6 +978,10 @@ config ARCH_HAS_VDSO_DATA
 config HAVE_STATIC_CALL
 	bool
 
+config HAVE_STATIC_CALL_INLINE
+	bool
+	depends on HAVE_STATIC_CALL
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"

include/asm-generic/vmlinux.lds.h

@@ -388,6 +388,12 @@
 	KEEP(*(__jump_table))						\
 	__stop___jump_table = .;
 
+#define STATIC_CALL_DATA						\
+	. = ALIGN(8);							\
+	__start_static_call_sites = .;					\
+	KEEP(*(.static_call_sites))					\
+	__stop_static_call_sites = .;
+
 /*
  * Allow architectures to handle ro_after_init data on their
  * own by defining an empty RO_AFTER_INIT_DATA.
@@ -398,6 +404,7 @@
 	__start_ro_after_init = .;					\
 	*(.data..ro_after_init)						\
 	JUMP_TABLE_DATA							\
+	STATIC_CALL_DATA						\
 	__end_ro_after_init = .;
 #endif
 

include/linux/module.h

@@ -25,6 +25,7 @@
 #include <linux/error-injection.h>
 #include <linux/tracepoint-defs.h>
 #include <linux/srcu.h>
+#include <linux/static_call_types.h>
 
 #include <linux/percpu.h>
 #include <asm/module.h>
@@ -498,6 +499,10 @@ struct module {
 	unsigned long *kprobe_blacklist;
 	unsigned int num_kprobe_blacklist;
 #endif
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	int num_static_call_sites;
+	struct static_call_site *static_call_sites;
+#endif
 
 #ifdef CONFIG_LIVEPATCH
 	bool klp; /* Is this a livepatch module? */

include/linux/static_call.h

@@ -95,7 +95,41 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func);
 			     STATIC_CALL_TRAMP_ADDR(name), func);	\
 })
 
-#if defined(CONFIG_HAVE_STATIC_CALL)
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+
+struct static_call_mod {
+	struct static_call_mod *next;
+	struct module *mod; /* for vmlinux, mod == NULL */
+	struct static_call_site *sites;
+};
+
+struct static_call_key {
+	void *func;
+	struct static_call_mod *mods;
+};
+
+extern void __static_call_update(struct static_call_key *key, void *tramp, void *func);
+extern int static_call_mod_init(struct module *mod);
+
+#define DEFINE_STATIC_CALL(name, _func)					\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = _func,						\
+		.mods = NULL,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
+
+#define static_call(name)	__static_call(name)
+
+#define EXPORT_STATIC_CALL(name)					\
+	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
+	EXPORT_SYMBOL(STATIC_CALL_TRAMP(name))
+
+#define EXPORT_STATIC_CALL_GPL(name)					\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name));			\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name))
+
+#elif defined(CONFIG_HAVE_STATIC_CALL)
 
 struct static_call_key {
 	void *func;

include/linux/static_call_types.h

@@ -2,14 +2,27 @@
 #ifndef _STATIC_CALL_TYPES_H
 #define _STATIC_CALL_TYPES_H
 
+#include <linux/types.h>
 #include <linux/stringify.h>
 
 #define STATIC_CALL_KEY_PREFIX		__SCK__
+#define STATIC_CALL_KEY_PREFIX_STR	__stringify(STATIC_CALL_KEY_PREFIX)
+#define STATIC_CALL_KEY_PREFIX_LEN	(sizeof(STATIC_CALL_KEY_PREFIX_STR) - 1)
 #define STATIC_CALL_KEY(name)		__PASTE(STATIC_CALL_KEY_PREFIX, name)
 
 #define STATIC_CALL_TRAMP_PREFIX	__SCT__
 #define STATIC_CALL_TRAMP_PREFIX_STR	__stringify(STATIC_CALL_TRAMP_PREFIX)
+#define STATIC_CALL_TRAMP_PREFIX_LEN	(sizeof(STATIC_CALL_TRAMP_PREFIX_STR) - 1)
 #define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
 #define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
 
+/*
+ * The static call site table needs to be created by external tooling (objtool
+ * or a compiler plugin).
+ */
+struct static_call_site {
+	s32 addr;
+	s32 key;
+};
+
 #endif /* _STATIC_CALL_TYPES_H */

kernel/Makefile

@@ -111,6 +111,7 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/
 obj-$(CONFIG_KCSAN) += kcsan/
 obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
+obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 

kernel/module.c

@@ -3274,6 +3274,11 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	mod->kprobe_blacklist = section_objs(info, "_kprobe_blacklist",
 						sizeof(unsigned long),
 						&mod->num_kprobe_blacklist);
+#endif
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	mod->static_call_sites = section_objs(info, ".static_call_sites",
+					      sizeof(*mod->static_call_sites),
+					      &mod->num_static_call_sites);
 #endif
 	mod->extable = section_objs(info, "__ex_table",
 				    sizeof(*mod->extable), &mod->num_exentries);