diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 95ee795d9796..d8164e6abaaf 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -381,11 +381,25 @@ ENTRY(startup_64)
 	/* Save the trampoline address in RCX */
 	movq	%rax, %rcx
 
+	/* Set up 32-bit addressable stack */
+	leaq	TRAMPOLINE_32BIT_STACK_END(%rcx), %rsp
+
 	/*
-	 * Load the address of trampoline_return() into RDI.
-	 * It will be used by the trampoline to return to the main code.
+	 * Preserve live 64-bit registers on the stack: this is necessary
+	 * because the architecture does not guarantee that GPRs will retain
+	 * their full 64-bit values across a 32-bit mode switch.
+	 */
+	pushq	%rbp
+	pushq	%rbx
+	pushq	%rsi
+
+	/*
+	 * Push the 64-bit address of trampoline_return() onto the new stack.
+	 * It will be used by the trampoline to return to the main code. Due to
+	 * the 32-bit mode switch, it cannot be kept it in a register either.
 	 */
 	leaq	trampoline_return(%rip), %rdi
+	pushq	%rdi
 
 	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
 	pushq	$__KERNEL32_CS
@@ -393,6 +407,11 @@ ENTRY(startup_64)
 	pushq	%rax
 	lretq
 trampoline_return:
+	/* Restore live 64-bit registers */
+	popq	%rsi
+	popq	%rbx
+	popq	%rbp
+
 	/* Restore the stack, the 32-bit trampoline uses its own stack */
 	leaq	boot_stack_end(%rbx), %rsp
 
@@ -573,7 +592,7 @@ SYM_FUNC_END(.Lrelocated)
 /*
  * This is the 32-bit trampoline that will be copied over to low memory.
  *
- * RDI contains the return address (might be above 4G).
+ * Return address is at the top of the stack (might be above 4G).
  * ECX contains the base address of the trampoline memory.
  * Non zero RDX means trampoline needs to enable 5-level paging.
  */
@@ -583,9 +602,6 @@ ENTRY(trampoline_32bit_src)
 	movl	%eax, %ds
 	movl	%eax, %ss
 
-	/* Set up new stack */
-	leal	TRAMPOLINE_32BIT_STACK_END(%ecx), %esp
-
 	/* Disable paging */
 	movl	%cr0, %eax
 	btrl	$X86_CR0_PG_BIT, %eax
@@ -644,7 +660,7 @@ ENTRY(trampoline_32bit_src)
 	.code64
 SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled)
 	/* Return from the trampoline */
-	jmp	*%rdi
+	retq
 SYM_FUNC_END(.Lpaging_enabled)
 
 	/*