/*
 * kexec.c - kexec_load 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.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/kexec.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/syscalls.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>

#include "kexec_internal.h"

static int copy_user_segment_list(struct kimage *image,
				  unsigned long nr_segments,
				  struct kexec_segment __user *segments)
{
	int ret;
	size_t segment_bytes;

	/* Read in the segments */
	image->nr_segments = nr_segments;
	segment_bytes = nr_segments * sizeof(*segments);
	ret = copy_from_user(image->segment, segments, segment_bytes);
	if (ret)
		ret = -EFAULT;

	return ret;
}

static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
			     unsigned long nr_segments,
			     struct kexec_segment __user *segments,
			     unsigned long flags)
{
	int ret;
	struct kimage *image;
	bool kexec_on_panic = flags & KEXEC_ON_CRASH;

	if (kexec_on_panic) {
		/* Verify we have a valid entry point */
		if ((entry < crashk_res.start) || (entry > crashk_res.end))
			return -EADDRNOTAVAIL;
	}

	/* Allocate and initialize a controlling structure */
	image = do_kimage_alloc_init();
	if (!image)
		return -ENOMEM;

	image->start = entry;

	ret = copy_user_segment_list(image, nr_segments, segments);
	if (ret)
		goto out_free_image;

	ret = sanity_check_segment_list(image);
	if (ret)
		goto out_free_image;

	 /* Enable the special crash kernel control page allocation policy. */
	if (kexec_on_panic) {
		image->control_page = crashk_res.start;
		image->type = KEXEC_TYPE_CRASH;
	}

	/*
	 * Find a location for the control code buffer, and add it
	 * the vector of segments so that it's pages will also be
	 * counted as destination pages.
	 */
	ret = -ENOMEM;
	image->control_code_page = kimage_alloc_control_pages(image,
					   get_order(KEXEC_CONTROL_PAGE_SIZE));
	if (!image->control_code_page) {
		pr_err("Could not allocate control_code_buffer\n");
		goto out_free_image;
	}

	if (!kexec_on_panic) {
		image->swap_page = kimage_alloc_control_pages(image, 0);
		if (!image->swap_page) {
			pr_err("Could not allocate swap buffer\n");
			goto out_free_control_pages;
		}
	}

	*rimage = image;
	return 0;
out_free_control_pages:
	kimage_free_page_list(&image->control_pages);
out_free_image:
	kfree(image);
	return ret;
}

/*
 * Exec Kernel system call: for obvious reasons only root may call it.
 *
 * This call breaks up into three pieces.
 * - A generic part which loads the new kernel from the current
 *   address space, and very carefully places the data in the
 *   allocated pages.
 *
 * - A generic part that interacts with the kernel and tells all of
 *   the devices to shut down.  Preventing on-going dmas, and placing
 *   the devices in a consistent state so a later kernel can
 *   reinitialize them.
 *
 * - A machine specific part that includes the syscall number
 *   and then copies the image to it's final destination.  And
 *   jumps into the image at entry.
 *
 * kexec does not sync, or unmount filesystems so if you need
 * that to happen you need to do that yourself.
 */

SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
		struct kexec_segment __user *, segments, unsigned long, flags)
{
	struct kimage **dest_image, *image;
	int result;

	/* We only trust the superuser with rebooting the system. */
	if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
		return -EPERM;

	/*
	 * Verify we have a legal set of flags
	 * This leaves us room for future extensions.
	 */
	if ((flags & KEXEC_FLAGS) != (flags & ~KEXEC_ARCH_MASK))
		return -EINVAL;

	/* Verify we are on the appropriate architecture */
	if (((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH) &&
		((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT))
		return -EINVAL;

	/* Put an artificial cap on the number
	 * of segments passed to kexec_load.
	 */
	if (nr_segments > KEXEC_SEGMENT_MAX)
		return -EINVAL;

	image = NULL;
	result = 0;

	/* Because we write directly to the reserved memory
	 * region when loading crash kernels we need a mutex here to
	 * prevent multiple crash  kernels from attempting to load
	 * simultaneously, and to prevent a crash kernel from loading
	 * over the top of a in use crash kernel.
	 *
	 * KISS: always take the mutex.
	 */
	if (!mutex_trylock(&kexec_mutex))
		return -EBUSY;

	dest_image = &kexec_image;
	if (flags & KEXEC_ON_CRASH)
		dest_image = &kexec_crash_image;
	if (nr_segments > 0) {
		unsigned long i;

		if (flags & KEXEC_ON_CRASH) {
			/*
			 * Loading another kernel to switch to if this one
			 * crashes.  Free any current crash dump kernel before
			 * we corrupt it.
			 */

			kimage_free(xchg(&kexec_crash_image, NULL));
			result = kimage_alloc_init(&image, entry, nr_segments,
						   segments, flags);
			crash_map_reserved_pages();
		} else {
			/* Loading another kernel to reboot into. */

			result = kimage_alloc_init(&image, entry, nr_segments,
						   segments, flags);
		}
		if (result)
			goto out;

		if (flags & KEXEC_PRESERVE_CONTEXT)
			image->preserve_context = 1;
		result = machine_kexec_prepare(image);
		if (result)
			goto out;

		for (i = 0; i < nr_segments; i++) {
			result = kimage_load_segment(image, &image->segment[i]);
			if (result)
				goto out;
		}
		kimage_terminate(image);
		if (flags & KEXEC_ON_CRASH)
			crash_unmap_reserved_pages();
	}
	/* Install the new kernel, and  Uninstall the old */
	image = xchg(dest_image, image);

out:
	mutex_unlock(&kexec_mutex);
	kimage_free(image);

	return result;
}

#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
		       compat_ulong_t, nr_segments,
		       struct compat_kexec_segment __user *, segments,
		       compat_ulong_t, flags)
{
	struct compat_kexec_segment in;
	struct kexec_segment out, __user *ksegments;
	unsigned long i, result;

	/* Don't allow clients that don't understand the native
	 * architecture to do anything.
	 */
	if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT)
		return -EINVAL;

	if (nr_segments > KEXEC_SEGMENT_MAX)
		return -EINVAL;

	ksegments = compat_alloc_user_space(nr_segments * sizeof(out));
	for (i = 0; i < nr_segments; i++) {
		result = copy_from_user(&in, &segments[i], sizeof(in));
		if (result)
			return -EFAULT;

		out.buf   = compat_ptr(in.buf);
		out.bufsz = in.bufsz;
		out.mem   = in.mem;
		out.memsz = in.memsz;

		result = copy_to_user(&ksegments[i], &out, sizeof(out));
		if (result)
			return -EFAULT;
	}

	return sys_kexec_load(entry, nr_segments, ksegments, flags);
}
#endif