x86, boot: use appropriate rep string for move and clear

[pandora-kernel.git] / arch / x86 / boot / compressed / head_64.S

diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 26c3def..723c72d 100644 (file)
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -249,19 +249,26 @@ ENTRY(startup_64)
        addq    $(32768 + 18 + 4095), %rbx
        andq    $~4095, %rbx
 
+       /* Set up the stack */
+       leaq    boot_stack_end(%rbx), %rsp
+
+       /* Zero EFLAGS */
+       pushq   $0
+       popfq
+
 /*
  * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
-       leaq    _end_before_pgt(%rip), %r8
-       leaq    _end_before_pgt(%rbx), %r9
-       movq    $_end_before_pgt /* - $startup_32 */, %rcx
-1:     subq    $8, %r8
-       subq    $8, %r9
-       movq    0(%r8), %rax
-       movq    %rax, 0(%r9)
-       subq    $8, %rcx
-       jnz     1b
+       pushq   %rsi
+       leaq    (_bss-8)(%rip), %rsi
+       leaq    (_bss-8)(%rbx), %rdi
+       movq    $_bss /* - $startup_32 */, %rcx
+       shrq    $3, %rcx
+       std
+       rep     movsq
+       cld
+       popq    %rsi
 
 /*
  * Jump to the relocated address.
@@ -273,21 +280,14 @@ ENTRY(startup_64)
 relocated:
 
 /*
- * Clear BSS
+ * Clear BSS (stack is currently empty)
  */
-       xorq    %rax, %rax
-       leaq    _edata(%rbx), %rdi
-       leaq    _end_before_pgt(%rbx), %rcx
+       xorl    %eax, %eax
+       leaq    _bss(%rip), %rdi
+       leaq    _ebss(%rip), %rcx
        subq    %rdi, %rcx
-       cld
-       rep     stosb
-
-       /* Setup the stack */
-       leaq    boot_stack_end(%rip), %rsp
-
-       /* zero EFLAGS after setting rsp */
-       pushq   $0
-       popfq
+       shrq    $3, %rcx
+       rep     stosq
 
 /*
  * Do the decompression, and jump to the new kernel..
@@ -329,3 +329,11 @@ boot_heap:
 boot_stack:
        .fill BOOT_STACK_SIZE, 1, 0
 boot_stack_end:
+
+/*
+ * Space for page tables (not in .bss so not zeroed)
+ */
+       .section ".pgtable","a",@nobits
+       .balign 4096
+pgtable:
+       .fill 6*4096, 1, 0