/*
* kexec.c - kexec system call
* Copyright (C) 2002-2004 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/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/kexec.h>
#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
#include <linux/reboot.h>
#include <linux/syscalls.h>
#include <linux/ioport.h>
#include <linux/hardirq.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <asm/page.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/system.h>
#include <asm/semaphore.h>
/* Per cpu memory for storing cpu states in case of system crash. */
note_buf_t* crash_notes;
/* Location of the reserved area for the crash kernel */
struct resource crashk_res = {
.name = "Crash kernel",
.start = 0,
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
int kexec_should_crash(struct task_struct *p)
{
if (in_interrupt() || !p->pid || is_init(p) || panic_on_oops)
return 1;
return 0;
}
/*
* When kexec transitions to the new kernel there is a one-to-one
* mapping between physical and virtual addresses. On processors
* where you can disable the MMU this is trivial, and easy. For
* others it is still a simple predictable page table to setup.
*
* In that environment kexec copies the new kernel to its final
* resting place. This means I can only support memory whose
* physical address can fit in an unsigned long. In particular
* addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled.
* If the assembly stub has more restrictive requirements
* KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be
* defined more restrictively in <asm/kexec.h>.
*
* The code for the transition from the current kernel to the
* the new kernel is placed in the control_code_buffer, whose size
* is given by KEXEC_CONTROL_CODE_SIZE. In the best case only a single
* page of memory is necessary, but some architectures require more.
* Because this memory must be identity mapped in the transition from
* virtual to physical addresses it must live in the range
* 0 - TASK_SIZE, as only the user space mappings are arbitrarily
* modifiable.
*
* The assembly stub in the control code buffer is passed a linked list
* of descriptor pages detailing the source pages of the new kernel,
* and the destination addresses of those source pages. As this data
* structure is not used in the context of the current OS, it must
* be self-contained.
*
* The code has been made to work with highmem pages and will use a
* destination page in its final resting place (if it happens
* to allocate it). The end product of this is that most of the
* physical address space, and most of RAM can be used.
*
* Future directions include:
* - allocating a page table with the control code buffer identity
* mapped, to simplify machine_kexec and make kexec_on_panic more
* reliable.
*/
/*
* KIMAGE_NO_DEST is an impossible destination address..., for
* allocating pages whose destination address we do not care about.
*/
#define KIMAGE_NO_DEST (-1UL)
static int kimage_is_destination_range(struct kimage *image,
unsigned long start, unsigned long end);
static struct page *kimage_alloc_page(struct kimage *image,
gfp_t gfp_mask,
unsigned long dest);
static int do_kimage_alloc(struct kimage **rimage, unsigned long entry,
unsigned long nr_segments,
struct kexec_segment __user *segments)
{
size_t segment_bytes;
struct kimage *image;
unsigned long i;
int result;
/* Allocate a controlling structure */
result = -ENOMEM;
image = kzalloc(sizeof(*image), GFP_KERNEL);
if (!image)
goto out;
image->head = 0;
image->entry = &image->head;
image->last_entry = &image->head;
image->control_page = ~0; /* By default this does not apply */
image->start = entry;
image->type = KEXEC_TYPE_DEFAULT;
/* Initialize the list of control pages */
INIT_LIST_HEAD(&image->control_pages);
/* Initialize the list of destination pages */
INIT_LIST_HEAD(&image->dest_pages);
/* Initialize the list of unuseable pages */
INIT_LIST_HEAD(&image->unuseable_pages);
/* Read in the segments */
image->nr_segments = nr_segments;
segment_bytes = nr_segments * sizeof(*segments);
result = copy_from_user(image->segment, segments, segment_bytes);
if (result)
goto out;
/*
* Verify we have good destination addresses. The caller is
* responsible for making certain we don't attempt to load
* the new image into invalid or reserved areas of RAM. This
* just verifies it is an address we can use.
*
* Since the kernel does everything in page size chunks ensure
* the destination addreses are page aligned. Too many
* special cases crop of when we don't do this. The most
* insidious is getting overlapping destination addresses
* simply because addresses are changed to page size
* granularity.
*/
result = -EADDRNOTAVAIL