x86/boot/64: Push correct start_cpu() return address

[linux-2.6-microblaze.git] / arch / x86 / kernel / head_64.S

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index b4421cc..b467b14 100644 (file)
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -66,13 +66,8 @@ startup_64:
         * tables and then reload them.
         */
 
-       /*
-        * Setup stack for verify_cpu(). "-8" because initial_stack is defined
-        * this way, see below. Our best guess is a NULL ptr for stack
-        * termination heuristics and we don't want to break anything which
-        * might depend on it (kgdb, ...).
-        */
-       leaq    (__end_init_task - 8)(%rip), %rsp
+       /* Set up the stack for verify_cpu(), similar to initial_stack below */
+       leaq    (__end_init_task - SIZEOF_PTREGS)(%rip), %rsp
 
        /* Sanitize CPU configuration */
        call verify_cpu
@@ -117,20 +112,20 @@ startup_64:
        movq    %rdi, %rax
        shrq    $PGDIR_SHIFT, %rax
 
-       leaq    (4096 + _KERNPG_TABLE)(%rbx), %rdx
+       leaq    (PAGE_SIZE + _KERNPG_TABLE)(%rbx), %rdx
        movq    %rdx, 0(%rbx,%rax,8)
        movq    %rdx, 8(%rbx,%rax,8)
 
-       addq    $4096, %rdx
+       addq    $PAGE_SIZE, %rdx
        movq    %rdi, %rax
        shrq    $PUD_SHIFT, %rax
        andl    $(PTRS_PER_PUD-1), %eax
-       movq    %rdx, 4096(%rbx,%rax,8)
+       movq    %rdx, PAGE_SIZE(%rbx,%rax,8)
        incl    %eax
        andl    $(PTRS_PER_PUD-1), %eax
-       movq    %rdx, 4096(%rbx,%rax,8)
+       movq    %rdx, PAGE_SIZE(%rbx,%rax,8)
 
-       addq    $8192, %rbx
+       addq    $PAGE_SIZE * 2, %rbx
        movq    %rdi, %rax
        shrq    $PMD_SHIFT, %rdi
        addq    $(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax
@@ -147,6 +142,9 @@ startup_64:
        decl    %ecx
        jnz     1b
 
+       test %rbp, %rbp
+       jz .Lskip_fixup
+
        /*
         * Fixup the kernel text+data virtual addresses. Note that
         * we might write invalid pmds, when the kernel is relocated
@@ -154,9 +152,9 @@ startup_64:
         * beyond _end.
         */
        leaq    level2_kernel_pgt(%rip), %rdi
-       leaq    4096(%rdi), %r8
+       leaq    PAGE_SIZE(%rdi), %r8
        /* See if it is a valid page table entry */
-1:     testb   $1, 0(%rdi)
+1:     testb   $_PAGE_PRESENT, 0(%rdi)
        jz      2f
        addq    %rbp, 0(%rdi)
        /* Go to the next page */
@@ -167,6 +165,7 @@ startup_64:
        /* Fixup phys_base */
        addq    %rbp, phys_base(%rip)
 
+.Lskip_fixup:
        movq    $(early_level4_pgt - __START_KERNEL_map), %rax
        jmp 1f
 ENTRY(secondary_startup_64)
@@ -265,13 +264,17 @@ ENTRY(secondary_startup_64)
        movl    $MSR_GS_BASE,%ecx
        movl    initial_gs(%rip),%eax
        movl    initial_gs+4(%rip),%edx
-       wrmsr   
+       wrmsr
 
        /* rsi is pointer to real mode structure with interesting info.
           pass it to C */
        movq    %rsi, %rdi
-       
-       /* Finally jump to run C code and to be on real kernel address
+       jmp     start_cpu
+ENDPROC(secondary_startup_64)
+
+ENTRY(start_cpu)
+       /*
+        * Jump to run C code and to be on a real kernel address.
         * Since we are running on identity-mapped space we have to jump
         * to the full 64bit address, this is only possible as indirect
         * jump.  In addition we need to ensure %cs is set so we make this
@@ -295,12 +298,14 @@ ENTRY(secondary_startup_64)
         *      REX.W + FF /5 JMP m16:64 Jump far, absolute indirect,
         *              address given in m16:64.
         */
-       movq    initial_code(%rip),%rax
-       pushq   $0              # fake return address to stop unwinder
+       pushq   $.Lafter_lret   # put return address on stack for unwinder
+       xorq    %rbp, %rbp      # clear frame pointer
+       movq    initial_code(%rip), %rax
        pushq   $__KERNEL_CS    # set correct cs
        pushq   %rax            # target address in negative space
        lretq
-ENDPROC(secondary_startup_64)
+.Lafter_lret:
+ENDPROC(start_cpu)
 
 #include "verify_cpu.S"
 
@@ -308,15 +313,11 @@ ENDPROC(secondary_startup_64)
 /*
  * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
  * up already except stack. We just set up stack here. Then call
- * start_secondary().
+ * start_secondary() via start_cpu().
  */
 ENTRY(start_cpu0)
-       movq initial_stack(%rip),%rsp
-       movq    initial_code(%rip),%rax
-       pushq   $0              # fake return address to stop unwinder
-       pushq   $__KERNEL_CS    # set correct cs
-       pushq   %rax            # target address in negative space
-       lretq
+       movq    initial_stack(%rip), %rsp
+       jmp     start_cpu
 ENDPROC(start_cpu0)
 #endif
 
@@ -328,7 +329,11 @@ ENDPROC(start_cpu0)
        GLOBAL(initial_gs)
        .quad   INIT_PER_CPU_VAR(irq_stack_union)
        GLOBAL(initial_stack)
-       .quad  init_thread_union+THREAD_SIZE-8
+       /*
+        * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
+        * unwinder reliably detect the end of the stack.
+        */
+       .quad  init_thread_union + THREAD_SIZE - SIZEOF_PTREGS
        __FINITDATA
 
 bad_address: