x86/retpoline: Ensure default return thunk isn't used at runtime

Make sure the default return thunk is not used after all return
instructions have been patched by the alternatives because the default
return thunk is insufficient when it comes to mitigating Retbleed or
SRSO.

Fix based on an earlier version by David Kaplan <david.kaplan@amd.com>.

  [ bp: Fix the compilation error of warn_thunk_thunk being an invisible
        symbol, hoist thunk macro into calling.h ]

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Co-developed-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20231010171020.462211-4-david.kaplan@amd.com
Link: https://lore.kernel.org/r/20240104132446.GEZZaxnrIgIyat0pqf@fat_crate.local

4 files changed, 72 insertions, 59 deletions

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 39e069b68c6e..bd31b2534053 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -426,3 +426,63 @@ For 32-bit we have the following conventions - kernel is built with
 .endm
 
 #endif /* CONFIG_SMP */
+
+#ifdef CONFIG_X86_64
+
+/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
+.macro THUNK name, func
+SYM_FUNC_START(\name)
+	pushq %rbp
+	movq %rsp, %rbp
+
+	pushq %rdi
+	pushq %rsi
+	pushq %rdx
+	pushq %rcx
+	pushq %rax
+	pushq %r8
+	pushq %r9
+	pushq %r10
+	pushq %r11
+
+	call \func
+
+	popq %r11
+	popq %r10
+	popq %r9
+	popq %r8
+	popq %rax
+	popq %rcx
+	popq %rdx
+	popq %rsi
+	popq %rdi
+	popq %rbp
+	RET
+SYM_FUNC_END(\name)
+	_ASM_NOKPROBE(\name)
+.endm
+
+#else /* CONFIG_X86_32 */
+
+/* put return address in eax (arg1) */
+.macro THUNK name, func, put_ret_addr_in_eax=0
+SYM_CODE_START_NOALIGN(\name)
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+
+	.if \put_ret_addr_in_eax
+	/* Place EIP in the arg1 */
+	movl 3*4(%esp), %eax
+	.endif
+
+	call \func
+	popl %edx
+	popl %ecx
+	popl %eax
+	RET
+	_ASM_NOKPROBE(\name)
+SYM_CODE_END(\name)
+	.endm
+
+#endif
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 8c8d38f0cb1d..582731f74dc8 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -7,6 +7,8 @@
 #include <linux/linkage.h>
 #include <asm/msr-index.h>
 
+#include "calling.h"
+
 .pushsection .noinstr.text, "ax"
 
 SYM_FUNC_START(entry_ibpb)
@@ -20,3 +22,5 @@ SYM_FUNC_END(entry_ibpb)
 EXPORT_SYMBOL_GPL(entry_ibpb);
 
 .popsection
+
+THUNK warn_thunk_thunk, __warn_thunk
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index 0103e103a657..da37f42f4549 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -4,33 +4,15 @@
  * Copyright 2008 by Steven Rostedt, Red Hat, Inc
  *  (inspired by Andi Kleen's thunk_64.S)
  */
-	#include <linux/export.h>
-	#include <linux/linkage.h>
-	#include <asm/asm.h>
 
-	/* put return address in eax (arg1) */
-	.macro THUNK name, func, put_ret_addr_in_eax=0
-SYM_CODE_START_NOALIGN(\name)
-	pushl %eax
-	pushl %ecx
-	pushl %edx
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
 
-	.if \put_ret_addr_in_eax
-	/* Place EIP in the arg1 */
-	movl 3*4(%esp), %eax
-	.endif
+#include "calling.h"
 
-	call \func
-	popl %edx
-	popl %ecx
-	popl %eax
-	RET
-	_ASM_NOKPROBE(\name)
-SYM_CODE_END(\name)
-	.endm
-
-	THUNK preempt_schedule_thunk, preempt_schedule
-	THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
-	EXPORT_SYMBOL(preempt_schedule_thunk)
-	EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
+THUNK preempt_schedule_thunk, preempt_schedule
+THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
+EXPORT_SYMBOL(preempt_schedule_thunk)
+EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
 
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 416b400f39db..119ebdc3d362 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -9,39 +9,6 @@
 #include "calling.h"
 #include <asm/asm.h>
 
-	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
-	.macro THUNK name, func
-SYM_FUNC_START(\name)
-	pushq %rbp
-	movq %rsp, %rbp
-
-	pushq %rdi
-	pushq %rsi
-	pushq %rdx
-	pushq %rcx
-	pushq %rax
-	pushq %r8
-	pushq %r9
-	pushq %r10
-	pushq %r11
-
-	call \func
-
-	popq %r11
-	popq %r10
-	popq %r9
-	popq %r8
-	popq %rax
-	popq %rcx
-	popq %rdx
-	popq %rsi
-	popq %rdi
-	popq %rbp
-	RET
-SYM_FUNC_END(\name)
-	_ASM_NOKPROBE(\name)
-	.endm
-
 THUNK preempt_schedule_thunk, preempt_schedule
 THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
 EXPORT_SYMBOL(preempt_schedule_thunk)