x86: Improve the trampoline in 64-bit mode

At present this leaves the stack at the pre-relocation value. This is not
ideal since we want to have U-Boot running entirely from the top of
memory.

In addition, the new global_data pointer is not actually used, since
the global_data pointer itself is relocated, then the pre-relocation value
is changed, so the effective value (after relocation) does not update.

Adjust the implementation to follow the 32-bit code more closely, with a
trampoline function which is passed the new stack and global_data pointer.
This ensures that the correct values come through even when relocating.

Signed-off-by: Simon Glass <sjg@chromium.org>
Reviewed-by: Bin Meng <bmeng.cn@gmail.com>
diff --git a/arch/x86/cpu/start64.S b/arch/x86/cpu/start64.S
index 7be8347..78e894d 100644
--- a/arch/x86/cpu/start64.S
+++ b/arch/x86/cpu/start64.S
@@ -26,3 +26,22 @@
 
 	/* Should not return here */
 	jmp	.
+
+.globl board_init_f_r_trampoline64
+.type board_init_f_r_trampoline64, @function
+board_init_f_r_trampoline64:
+	/*
+	 * SDRAM has been initialised, U-Boot code has been copied into
+	 * RAM, BSS has been cleared and relocation adjustments have been
+	 * made. It is now time to jump into the in-RAM copy of U-Boot
+	 *
+	 * %eax = Address of top of new stack
+	 */
+
+	/* Stack grows down from top of SDRAM */
+	movq	%rsi, %rsp
+
+	/* New gd is in rdi */
+
+	/* Re-enter U-Boot by calling board_init_f_r() */
+	call	board_init_f_r
diff --git a/arch/x86/include/asm/u-boot-x86.h b/arch/x86/include/asm/u-boot-x86.h
index 1d8aa32..02a8b0f 100644
--- a/arch/x86/include/asm/u-boot-x86.h
+++ b/arch/x86/include/asm/u-boot-x86.h
@@ -117,6 +117,17 @@
  */
 void __noreturn board_init_f_r(void);
 
+/*
+ * board_init_f_r_trampoline64() - jump to relocated address with new stack
+ *
+ * This is the 64-bit version
+ *
+ * @new_gd: New global_data pointer to use
+ * @sp: New stack pointer to pass on to board_init_r()
+ */
+void __noreturn board_init_f_r_trampoline64(struct global_data *new_gd,
+					    ulong sp);
+
 int arch_misc_init(void);
 
 /* Read the time stamp counter */