[PATCH v7 09/22] x86/decompressor: Call trampoline as a normal function

[Ard Biesheuvel]

Move the long return to switch to 32-bit mode into the trampoline code
so it can be called as an ordinary function. This will allow it to be
called directly from C code in a subsequent patch.

Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx>
---
 arch/x86/boot/compressed/head_64.S | 46 ++++++++++----------
 arch/x86/boot/compressed/pgtable.h |  2 +-
 2 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 2ccddec2220ce914..1892679be2b6897a 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -446,29 +446,9 @@ SYM_CODE_START(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 and push it onto
-	 * the stack so it will survive 32-bit truncation due to the 32-bit
-	 * protected mode switch. It will be used by the trampoline to return
-	 * to the main code.
-	 */
-	leaq	trampoline_return(%rip), %rdi
-	pushq	%rdi
-
-	/* Preserve other live 64-bit registers */
-	pushq	%r15
-	pushq	%rbp
-	pushq	%rbx
-
-	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
-	pushq	$__KERNEL32_CS
 	leaq	TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax
-	pushq	%rax
-	lretq
-trampoline_return:
+	call	*%rax
+
 	/* Restore the stack, the 32-bit trampoline uses its own stack */
 	leaq	rva(boot_stack_end)(%rbx), %rsp
 
@@ -551,15 +531,33 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 	jmp	*%rax
 SYM_FUNC_END(.Lrelocated)
 
-	.code32
 /*
  * This is the 32-bit trampoline that will be copied over to low memory.
  *
- * RDI contains the return address (might be above 4G).
  * ECX contains the base address of the trampoline memory.
  * Non zero RDX means trampoline needs to enable 5-level paging.
  */
 SYM_CODE_START(trampoline_32bit_src)
+	/* Grab return address */
+	movq	(%rsp), %rax
+
+	/* Set up 32-bit addressable stack */
+	leaq	TRAMPOLINE_32BIT_STACK_END(%rcx), %rsp
+
+	/* Preserve return address and other live 64-bit registers */
+	pushq	%rax
+	pushq	%r15
+	pushq	%rbp
+	pushq	%rbx
+
+	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
+	pushq	$__KERNEL32_CS
+	leaq	0f(%rip), %rax
+	pushq	%rax
+	lretq
+
+	.code32
+0:
 	/* Set up data and stack segments */
 	movl	$__KERNEL_DS, %eax
 	movl	%eax, %ds
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
index cc9b2529a08634b4..91dbb99203fbce2d 100644
--- a/arch/x86/boot/compressed/pgtable.h
+++ b/arch/x86/boot/compressed/pgtable.h
@@ -6,7 +6,7 @@
 #define TRAMPOLINE_32BIT_PGTABLE_OFFSET	0
 
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0x80
+#define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
 
 #define TRAMPOLINE_32BIT_STACK_END	TRAMPOLINE_32BIT_SIZE
 
-- 
2.39.2