x86: Use a simple jump into long mode

With the 64-bit descriptor we can use a jump instruction, rather than
pushing things on the stack.

Since the processor is in 64-bit mode by this point, pop a 64-bit value
from the stack, containing the target address.

This simplifies the code slightly, in particular its use of the stack.

Signed-off-by: Simon Glass <sjg@chromium.org>

diff --git a/arch/x86/cpu/i386/call64.S b/arch/x86/cpu/i386/call64.S
index c722acb..a9d3f16 100644 (file)
--- a/arch/x86/cpu/i386/call64.S
+++ b/arch/x86/cpu/i386/call64.S
@@ -22,6 +22,7 @@ cpu_call64:
         * ecx - target
         */
        cli
+       pushl   $0              /* top 64-bits of target */
        push    %ecx            /* arg2 = target */
        push    %edx            /* arg1 = setup_base */
        mov     %eax, %ebx
@@ -32,7 +33,8 @@ cpu_call64:
        movl    %eax, %cr0
 
        /* Enable PAE mode */
-       movl    $(X86_CR4_PAE), %eax
+       movl    %cr4, %eax
+       orl     $X86_CR4_PAE, %eax
        movl    %eax, %cr4
 
        /* Enable the boot page tables */
@@ -57,23 +59,18 @@ cpu_call64:
         */
        pop     %esi                    /* setup_base */
 
-       pushl   $(X86_GDT_ENTRY_64BIT_CS * X86_GDT_ENTRY_SIZE)
-       leal    lret_target, %eax
-       pushl   %eax
-
        /* Enter paged protected Mode, activating Long Mode */
        movl    %cr0, %eax
        orl     $X86_CR0_PG, %eax
        movl    %eax, %cr0
 
        /* Jump from 32bit compatibility mode into 64bit mode. */
-       lret
+       ljmp    $(X86_GDT_ENTRY_64BIT_CS * X86_GDT_ENTRY_SIZE), $lret_target
 
-code64:
+.code64
 lret_target:
-       pop     %eax                    /* target */
-       mov     %eax, %eax              /* Clear bits 63:32 */
-       jmp     *%eax                   /* Jump to the 64-bit target */
+       pop     %rax                    /* target */
+       jmp     *%rax                   /* Jump to the 64-bit target */
 
 .globl call64_stub_size
 call64_stub_size: