[PATCH v2 18/42] x86: Improve the trampoline in 64-bit mode

[Simon Glass]

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 at chromium.org>
---

(no changes since v1)

 arch/x86/cpu/start64.S            | 19 +++++++++++++++++++
 arch/x86/include/asm/u-boot-x86.h | 11 +++++++++++
 common/board_f.c                  | 12 +++++++-----
 3 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/arch/x86/cpu/start64.S b/arch/x86/cpu/start64.S
index 7be834788b9f..78e894d2a21a 100644
--- a/arch/x86/cpu/start64.S
+++ b/arch/x86/cpu/start64.S
@@ -26,3 +26,22 @@ _start:
 
 	/* 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 1d8aa320f535..02a8b0f15270 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_trampoline(ulong sp);
  */
 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 */
diff --git a/common/board_f.c b/common/board_f.c
index 1688e27071fc..abd589c9c996 100644
--- a/common/board_f.c
+++ b/common/board_f.c
@@ -731,8 +731,7 @@ static int fix_fdt(void)
 #endif
 
 /* ARM calls relocate_code from its crt0.S */
-#if !defined(CONFIG_ARM) && !defined(CONFIG_SANDBOX) && \
-		!CONFIG_IS_ENABLED(X86_64)
+#if !defined(CONFIG_ARM) && !defined(CONFIG_SANDBOX)
 
 static int jump_to_copy(void)
 {
@@ -754,7 +753,11 @@ static int jump_to_copy(void)
 	 * (CPU cache)
 	 */
 	arch_setup_gd(gd->new_gd);
-	board_init_f_r_trampoline(gd->start_addr_sp);
+# if CONFIG_IS_ENABLED(X86_64)
+		board_init_f_r_trampoline64(gd->new_gd, gd->start_addr_sp);
+# else
+		board_init_f_r_trampoline(gd->start_addr_sp);
+# endif
 #else
 	relocate_code(gd->start_addr_sp, gd->new_gd, gd->relocaddr);
 #endif
@@ -969,8 +972,7 @@ static const init_fnc_t init_sequence_f[] = {
 	 * watchdog device is not serviced is as small as possible.
 	 */
 	cyclic_unregister_all,
-#if !defined(CONFIG_ARM) && !defined(CONFIG_SANDBOX) && \
-		!CONFIG_IS_ENABLED(X86_64)
+#if !defined(CONFIG_ARM) && !defined(CONFIG_SANDBOX)
 	jump_to_copy,
 #endif
 	NULL,
-- 
2.40.0.634.g4ca3ef3211-goog