[PATCH] kexec: x86_64 kexec implementation

This is the x86_64 implementation of machine kexec.  32bit compatibility
support has been implemented, and machine_kexec has been enhanced to not care
about the changing internal kernel paget table structures.

From: Alexander Nyberg <alexn@dsv.su.se>

      build fix

Signed-off-by: Eric Biederman <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 143 insertions, 0 deletions

diff --git a/arch/x86_64/kernel/relocate_kernel.S b/arch/x86_64/kernel/relocate_kernel.S
new file mode 100644
index 000000000000..d24fa9b72a2b
--- /dev/null
+++ b/arch/x86_64/kernel/relocate_kernel.S
@@ -0,0 +1,143 @@
+/*
+ * relocate_kernel.S - put the kernel image in place to boot
+ * Copyright (C) 2002-2005 Eric Biederman  <ebiederm@xmission.com>
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/linkage.h>
+
+        /*
+         * Must be relocatable PIC code callable as a C function, that once
+         * it starts can not use the previous processes stack.
+         */
+        .globl relocate_new_kernel
+        .code64
+relocate_new_kernel:
+        /* %rdi page_list
+         * %rsi reboot_code_buffer
+         * %rdx start address
+         * %rcx page_table
+         * %r8  arg5
+         * %r9  arg6
+         */
+
+        /* zero out flags, and disable interrupts */
+        pushq $0
+        popfq
+
+        /* set a new stack at the bottom of our page... */
+        lea   4096(%rsi), %rsp
+
+        /* store the parameters back on the stack */
+        pushq   %rdx /* store the start address */
+
+        /* Set cr0 to a known state:
+         * 31 1 == Paging enabled
+         * 18 0 == Alignment check disabled
+         * 16 0 == Write protect disabled
+         * 3  0 == No task switch
+         * 2  0 == Don't do FP software emulation.
+         * 0  1 == Proctected mode enabled
+         */
+        movq    %cr0, %rax
+        andq    $~((1<<18)|(1<<16)|(1<<3)|(1<<2)), %rax
+        orl     $((1<<31)|(1<<0)), %eax
+        movq    %rax, %cr0
+
+        /* Set cr4 to a known state:
+         * 10 0 == xmm exceptions disabled
+         * 9  0 == xmm registers instructions disabled
+         * 8  0 == performance monitoring counter disabled
+         * 7  0 == page global disabled
+         * 6  0 == machine check exceptions disabled
+         * 5  1 == physical address extension enabled
+         * 4  0 == page size extensions disabled
+         * 3  0 == Debug extensions disabled
+         * 2  0 == Time stamp disable (disabled)
+         * 1  0 == Protected mode virtual interrupts disabled
+         * 0  0 == VME disabled
+         */
+
+        movq    $((1<<5)), %rax
+        movq    %rax, %cr4
+
+        jmp 1f
+1:
+
+        /* Switch to the identity mapped page tables,
+         * and flush the TLB.
+        */
+        movq    %rcx, %cr3
+
+        /* Do the copies */
+        movq    %rdi, %rcx      /* Put the page_list in %rcx */
+        xorq    %rdi, %rdi
+        xorq    %rsi, %rsi
+        jmp     1f
+
+0:      /* top, read another word for the indirection page */
+
+        movq    (%rbx), %rcx
+        addq    $8,     %rbx
+1:
+        testq   $0x1,   %rcx  /* is it a destination page? */
+        jz      2f
+        movq    %rcx,   %rdi
+        andq    $0xfffffffffffff000, %rdi
+        jmp     0b
+2:
+        testq   $0x2,   %rcx  /* is it an indirection page? */
+        jz      2f
+        movq    %rcx,   %rbx
+        andq    $0xfffffffffffff000, %rbx
+        jmp     0b
+2:
+        testq   $0x4,   %rcx  /* is it the done indicator? */
+        jz      2f
+        jmp     3f
+2:
+        testq   $0x8,   %rcx  /* is it the source indicator? */
+        jz      0b            /* Ignore it otherwise */
+        movq    %rcx,   %rsi  /* For ever source page do a copy */
+        andq    $0xfffffffffffff000, %rsi
+
+        movq    $512,   %rcx
+        rep ; movsq
+        jmp     0b
+3:
+
+        /* To be certain of avoiding problems with self-modifying code
+         * I need to execute a serializing instruction here.
+         * So I flush the TLB by reloading %cr3 here, it's handy,
+         * and not processor dependent.
+         */
+        movq    %cr3, %rax
+        movq    %rax, %cr3
+
+        /* set all of the registers to known values */
+        /* leave %rsp alone */
+
+        xorq    %rax, %rax
+        xorq    %rbx, %rbx
+        xorq    %rcx, %rcx
+        xorq    %rdx, %rdx
+        xorq    %rsi, %rsi
+        xorq    %rdi, %rdi
+        xorq    %rbp, %rbp
+        xorq    %r8,  %r8
+        xorq    %r9,  %r9
+        xorq    %r10, %r9
+        xorq    %r11, %r11
+        xorq    %r12, %r12
+        xorq    %r13, %r13
+        xorq    %r14, %r14
+        xorq    %r15, %r15
+
+        ret
+relocate_new_kernel_end:
+
+        .globl relocate_new_kernel_size
+relocate_new_kernel_size:
+        .quad relocate_new_kernel_end - relocate_new_kernel