static_call: Add call depth tracking support

When indirect calls are switched to direct calls then it has to be ensured
that the call target is not the function, but the call thunk when call
depth tracking is enabled. But static calls are available before call
thunks have been set up.

Ensure a second run through the static call patching code after call thunks
have been created. When call thunks are not enabled this has no side
effects.

Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Signed-off-by: Thomas Gleixner <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

arch/x86/include/asm/alternative.h

···
 extern void callthunks_patch_builtin_calls(void);
 extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
 					  struct module *mod);
+extern void *callthunks_translate_call_dest(void *dest);
 #else
 static __always_inline void callthunks_patch_builtin_calls(void) {}
 static __always_inline void
 callthunks_patch_module_calls(struct callthunk_sites *sites,
 			      struct module *mod) {}
+static __always_inline void *callthunks_translate_call_dest(void *dest)
+{
+	return dest;
+}
 #endif
 
 #ifdef CONFIG_SMP

arch/x86/kernel/callthunks.c

···
 #include <linux/kallsyms.h>
 #include <linux/memory.h>
 #include <linux/moduleloader.h>
+#include <linux/static_call.h>
 
 #include <asm/alternative.h>
 #include <asm/asm-offsets.h>
···
 	pr_info("Setting up call depth tracking\n");
 	mutex_lock(&text_mutex);
 	callthunks_setup(&cs, &builtin_coretext);
+	static_call_force_reinit();
 	thunks_initialized = true;
 	mutex_unlock(&text_mutex);
+}
+
+void *callthunks_translate_call_dest(void *dest)
+{
+	void *target;
+
+	lockdep_assert_held(&text_mutex);
+
+	if (!thunks_initialized || skip_addr(dest))
+		return dest;
+
+	if (!is_coretext(NULL, dest))
+		return dest;
+
+	target = patch_dest(dest, false);
+	return target ? : dest;
 }
 
 #ifdef CONFIG_MODULES

arch/x86/kernel/static_call.c

···
 
 	switch (type) {
 	case CALL:
+		func = callthunks_translate_call_dest(func);
 		code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
 		if (func == &__static_call_return0) {
 			emulate = code;

include/linux/static_call.h

···
 
 extern int __init static_call_init(void);
 
+extern void static_call_force_reinit(void);
+
 struct static_call_mod {
 	struct static_call_mod *next;
 	struct module *mod; /* for vmlinux, mod == NULL */

kernel/static_call_inline.c

···
 extern struct static_call_tramp_key __start_static_call_tramp_key[],
 				    __stop_static_call_tramp_key[];
 
-static bool static_call_initialized;
+static int static_call_initialized;
+
+/*
+ * Must be called before early_initcall() to be effective.
+ */
+void static_call_force_reinit(void)
+{
+	if (WARN_ON_ONCE(!static_call_initialized))
+		return;
+
+	static_call_initialized++;
+}
 
 /* mutex to protect key modules/sites */
 static DEFINE_MUTEX(static_call_mutex);
···
 {
 	int ret;
 
-	if (static_call_initialized)
+	/* See static_call_force_reinit(). */
+	if (static_call_initialized == 1)
 		return 0;
 
 	cpus_read_lock();
···
 		BUG();
 	}
 
-	static_call_initialized = true;
-
 #ifdef CONFIG_MODULES
-	register_module_notifier(&static_call_module_nb);
+	if (!static_call_initialized)
+		register_module_notifier(&static_call_module_nb);
 #endif
+
+	static_call_initialized = 1;
 	return 0;
 }
 early_initcall(static_call_init);