x86_64/bug: Inline the UD1

(Ab)use the static_call infrastructure to convert all:

  call __WARN_trap

instances into the desired:

  ud1 (%edx), %rdi

eliminating the CALL/RET, but more importantly, fixing the
fact that all WARNs will have:

  RIP: 0010:__WARN_trap+0

Basically, by making it a static_call trampoline call, objtool will
collect the callsites, and then the inline rewrite will hit the
special case and replace the code with the magic instruction.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251110115758.456717741@infradead.org

arch/x86/include/asm/bug.h

diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index f192ff0..83b0fb3 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -135,9 +135,12 @@ do {									\
 #ifdef HAVE_ARCH_BUG_FORMAT_ARGS
 
 #ifndef __ASSEMBLY__
+#include <linux/static_call_types.h>
 struct bug_entry;
 extern void __WARN_trap(struct bug_entry *bug, ...);
 
+DECLARE_STATIC_CALL(WARN_trap, __WARN_trap);
+
 struct pt_regs;
 struct sysv_va_list { /* from AMD64 System V ABI */
 	unsigned int gp_offset;
@@ -169,7 +172,7 @@ extern void *__warn_args(struct arch_va_list *args, struct pt_regs *regs);
 #define __WARN_print_arg(flags, format, arg...)				\
 do {									\
 	int __flags = (flags) | BUGFLAG_WARNING | BUGFLAG_ARGS ;	\
-	__WARN_trap(__WARN_bug_entry(__flags, format), ## arg);		\
+	static_call_mod(WARN_trap)(__WARN_bug_entry(__flags, format), ## arg); \
 	asm (""); /* inhibit tail-call optimization */			\
 } while (0)
 

arch/x86/kernel/static_call.c

diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 378c388..b18c589 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -26,6 +26,11 @@ static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 };
 
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
+/*
+ * ud1    (%edx),%rdi -- see __WARN_trap() / decode_bug()
+ */
+static const u8 warninsn[] = { 0x67, 0x48, 0x0f, 0xb9, 0x3a };
+
 static u8 __is_Jcc(u8 *insn) /* Jcc.d32 */
 {
 	u8 ret = 0;
@@ -69,7 +74,12 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 			emulate = code;
 			code = &xor5rax;
 		}
-
+#ifdef HAVE_ARCH_BUG_FORMAT_ARGS
+		if (func == &__WARN_trap) {
+			emulate = code;
+			code = &warninsn;
+		}
+#endif
 		break;
 
 	case NOP:
@@ -128,7 +138,8 @@ static void __static_call_validate(u8 *insn, bool tail, bool tramp)
 	} else {
 		if (opcode == CALL_INSN_OPCODE ||
 		    !memcmp(insn, x86_nops[5], 5) ||
-		    !memcmp(insn, xor5rax, 5))
+		    !memcmp(insn, xor5rax, 5) ||
+		    !memcmp(insn, warninsn, 5))
 			return;
 	}
 

arch/x86/kernel/traps.c

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index fbbe3ab..cb324cc 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -31,6 +31,7 @@
 #include <linux/kexec.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <linux/static_call.h>
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/bug.h>
@@ -215,6 +216,9 @@ static inline unsigned long pt_regs_val(struct pt_regs *regs, int nr)
 }
 
 #ifdef HAVE_ARCH_BUG_FORMAT_ARGS
+DEFINE_STATIC_CALL(WARN_trap, __WARN_trap);
+EXPORT_STATIC_CALL_TRAMP(WARN_trap);
+
 /*
  * Create a va_list from an exception context.
  */