kexec_core.c 39.7 KB
Newer Older
1 2 3 4 5 6 7 8
/*
 * kexec.c - kexec system call core code.
 * 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.
 */

9
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40

#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/mutex.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
#include <linux/reboot.h>
#include <linux/ioport.h>
#include <linux/hardirq.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/utsname.h>
#include <linux/numa.h>
#include <linux/suspend.h>
#include <linux/device.h>
#include <linux/freezer.h>
#include <linux/pm.h>
#include <linux/cpu.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/console.h>
#include <linux/vmalloc.h>
#include <linux/swap.h>
#include <linux/syscore_ops.h>
#include <linux/compiler.h>
#include <linux/hugetlb.h>
41
#include <linux/frame.h>
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69

#include <asm/page.h>
#include <asm/sections.h>

#include <crypto/hash.h>
#include <crypto/sha.h>
#include "kexec_internal.h"

DEFINE_MUTEX(kexec_mutex);

/* Per cpu memory for storing cpu states in case of system crash. */
note_buf_t __percpu *crash_notes;

/* vmcoreinfo stuff */
static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
size_t vmcoreinfo_size;
size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);

/* Flag to indicate we are going to kexec a new kernel */
bool kexec_in_progress = false;


/* Location of the reserved area for the crash kernel */
struct resource crashk_res = {
	.name  = "Crash kernel",
	.start = 0,
	.end   = 0,
70 71
	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
	.desc  = IORES_DESC_CRASH_KERNEL
72 73 74 75 76
};
struct resource crashk_low_res = {
	.name  = "Crash kernel",
	.start = 0,
	.end   = 0,
77 78
	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
	.desc  = IORES_DESC_CRASH_KERNEL
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98
};

int kexec_should_crash(struct task_struct *p)
{
	/*
	 * If crash_kexec_post_notifiers is enabled, don't run
	 * crash_kexec() here yet, which must be run after panic
	 * notifiers in panic().
	 */
	if (crash_kexec_post_notifiers)
		return 0;
	/*
	 * There are 4 panic() calls in do_exit() path, each of which
	 * corresponds to each of these 4 conditions.
	 */
	if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
		return 1;
	return 0;
}

99 100 101 102 103 104
int kexec_crash_loaded(void)
{
	return !!kexec_crash_image;
}
EXPORT_SYMBOL_GPL(kexec_crash_loaded);

105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
/*
 * 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_PAGE_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)
150
#define PAGE_COUNT(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT)
151 152 153 154 155 156 157

static struct page *kimage_alloc_page(struct kimage *image,
				       gfp_t gfp_mask,
				       unsigned long dest);

int sanity_check_segment_list(struct kimage *image)
{
158
	int i;
159
	unsigned long nr_segments = image->nr_segments;
160
	unsigned long total_pages = 0;
161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179

	/*
	 * 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 addresses 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.
	 */
	for (i = 0; i < nr_segments; i++) {
		unsigned long mstart, mend;

		mstart = image->segment[i].mem;
		mend   = mstart + image->segment[i].memsz;
180 181
		if (mstart > mend)
			return -EADDRNOTAVAIL;
182
		if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
183
			return -EADDRNOTAVAIL;
184
		if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
185
			return -EADDRNOTAVAIL;
186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
	}

	/* Verify our destination addresses do not overlap.
	 * If we alloed overlapping destination addresses
	 * through very weird things can happen with no
	 * easy explanation as one segment stops on another.
	 */
	for (i = 0; i < nr_segments; i++) {
		unsigned long mstart, mend;
		unsigned long j;

		mstart = image->segment[i].mem;
		mend   = mstart + image->segment[i].memsz;
		for (j = 0; j < i; j++) {
			unsigned long pstart, pend;

			pstart = image->segment[j].mem;
			pend   = pstart + image->segment[j].memsz;
			/* Do the segments overlap ? */
			if ((mend > pstart) && (mstart < pend))
206
				return -EINVAL;
207 208 209 210 211 212 213 214 215 216
		}
	}

	/* Ensure our buffer sizes are strictly less than
	 * our memory sizes.  This should always be the case,
	 * and it is easier to check up front than to be surprised
	 * later on.
	 */
	for (i = 0; i < nr_segments; i++) {
		if (image->segment[i].bufsz > image->segment[i].memsz)
217
			return -EINVAL;
218 219
	}

220 221 222 223 224 225 226 227 228 229 230 231 232 233 234
	/*
	 * Verify that no more than half of memory will be consumed. If the
	 * request from userspace is too large, a large amount of time will be
	 * wasted allocating pages, which can cause a soft lockup.
	 */
	for (i = 0; i < nr_segments; i++) {
		if (PAGE_COUNT(image->segment[i].memsz) > totalram_pages / 2)
			return -EINVAL;

		total_pages += PAGE_COUNT(image->segment[i].memsz);
	}

	if (total_pages > totalram_pages / 2)
		return -EINVAL;

235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251
	/*
	 * Verify we have good destination addresses.  Normally
	 * the caller is responsible for making certain we don't
	 * attempt to load the new image into invalid or reserved
	 * areas of RAM.  But crash kernels are preloaded into a
	 * reserved area of ram.  We must ensure the addresses
	 * are in the reserved area otherwise preloading the
	 * kernel could corrupt things.
	 */

	if (image->type == KEXEC_TYPE_CRASH) {
		for (i = 0; i < nr_segments; i++) {
			unsigned long mstart, mend;

			mstart = image->segment[i].mem;
			mend = mstart + image->segment[i].memsz - 1;
			/* Ensure we are within the crash kernel limits */
252 253
			if ((mstart < phys_to_boot_phys(crashk_res.start)) ||
			    (mend > phys_to_boot_phys(crashk_res.end)))
254
				return -EADDRNOTAVAIL;
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336
		}
	}

	return 0;
}

struct kimage *do_kimage_alloc_init(void)
{
	struct kimage *image;

	/* Allocate a controlling structure */
	image = kzalloc(sizeof(*image), GFP_KERNEL);
	if (!image)
		return NULL;

	image->head = 0;
	image->entry = &image->head;
	image->last_entry = &image->head;
	image->control_page = ~0; /* By default this does not apply */
	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 unusable pages */
	INIT_LIST_HEAD(&image->unusable_pages);

	return image;
}

int kimage_is_destination_range(struct kimage *image,
					unsigned long start,
					unsigned long end)
{
	unsigned long i;

	for (i = 0; i < image->nr_segments; i++) {
		unsigned long mstart, mend;

		mstart = image->segment[i].mem;
		mend = mstart + image->segment[i].memsz;
		if ((end > mstart) && (start < mend))
			return 1;
	}

	return 0;
}

static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
{
	struct page *pages;

	pages = alloc_pages(gfp_mask, order);
	if (pages) {
		unsigned int count, i;

		pages->mapping = NULL;
		set_page_private(pages, order);
		count = 1 << order;
		for (i = 0; i < count; i++)
			SetPageReserved(pages + i);
	}

	return pages;
}

static void kimage_free_pages(struct page *page)
{
	unsigned int order, count, i;

	order = page_private(page);
	count = 1 << order;
	for (i = 0; i < count; i++)
		ClearPageReserved(page + i);
	__free_pages(page, order);
}

void kimage_free_page_list(struct list_head *list)
{
337
	struct page *page, *next;
338

339
	list_for_each_entry_safe(page, next, list, lru) {
340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376
		list_del(&page->lru);
		kimage_free_pages(page);
	}
}

static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
							unsigned int order)
{
	/* Control pages are special, they are the intermediaries
	 * that are needed while we copy the rest of the pages
	 * to their final resting place.  As such they must
	 * not conflict with either the destination addresses
	 * or memory the kernel is already using.
	 *
	 * The only case where we really need more than one of
	 * these are for architectures where we cannot disable
	 * the MMU and must instead generate an identity mapped
	 * page table for all of the memory.
	 *
	 * At worst this runs in O(N) of the image size.
	 */
	struct list_head extra_pages;
	struct page *pages;
	unsigned int count;

	count = 1 << order;
	INIT_LIST_HEAD(&extra_pages);

	/* Loop while I can allocate a page and the page allocated
	 * is a destination page.
	 */
	do {
		unsigned long pfn, epfn, addr, eaddr;

		pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order);
		if (!pages)
			break;
377
		pfn   = page_to_boot_pfn(pages);
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462
		epfn  = pfn + count;
		addr  = pfn << PAGE_SHIFT;
		eaddr = epfn << PAGE_SHIFT;
		if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
			      kimage_is_destination_range(image, addr, eaddr)) {
			list_add(&pages->lru, &extra_pages);
			pages = NULL;
		}
	} while (!pages);

	if (pages) {
		/* Remember the allocated page... */
		list_add(&pages->lru, &image->control_pages);

		/* Because the page is already in it's destination
		 * location we will never allocate another page at
		 * that address.  Therefore kimage_alloc_pages
		 * will not return it (again) and we don't need
		 * to give it an entry in image->segment[].
		 */
	}
	/* Deal with the destination pages I have inadvertently allocated.
	 *
	 * Ideally I would convert multi-page allocations into single
	 * page allocations, and add everything to image->dest_pages.
	 *
	 * For now it is simpler to just free the pages.
	 */
	kimage_free_page_list(&extra_pages);

	return pages;
}

static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
						      unsigned int order)
{
	/* Control pages are special, they are the intermediaries
	 * that are needed while we copy the rest of the pages
	 * to their final resting place.  As such they must
	 * not conflict with either the destination addresses
	 * or memory the kernel is already using.
	 *
	 * Control pages are also the only pags we must allocate
	 * when loading a crash kernel.  All of the other pages
	 * are specified by the segments and we just memcpy
	 * into them directly.
	 *
	 * The only case where we really need more than one of
	 * these are for architectures where we cannot disable
	 * the MMU and must instead generate an identity mapped
	 * page table for all of the memory.
	 *
	 * Given the low demand this implements a very simple
	 * allocator that finds the first hole of the appropriate
	 * size in the reserved memory region, and allocates all
	 * of the memory up to and including the hole.
	 */
	unsigned long hole_start, hole_end, size;
	struct page *pages;

	pages = NULL;
	size = (1 << order) << PAGE_SHIFT;
	hole_start = (image->control_page + (size - 1)) & ~(size - 1);
	hole_end   = hole_start + size - 1;
	while (hole_end <= crashk_res.end) {
		unsigned long i;

		if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT)
			break;
		/* See if I overlap any of the segments */
		for (i = 0; i < image->nr_segments; i++) {
			unsigned long mstart, mend;

			mstart = image->segment[i].mem;
			mend   = mstart + image->segment[i].memsz - 1;
			if ((hole_end >= mstart) && (hole_start <= mend)) {
				/* Advance the hole to the end of the segment */
				hole_start = (mend + (size - 1)) & ~(size - 1);
				hole_end   = hole_start + size - 1;
				break;
			}
		}
		/* If I don't overlap any segments I have found my hole! */
		if (i == image->nr_segments) {
			pages = pfn_to_page(hole_start >> PAGE_SHIFT);
463
			image->control_page = hole_end;
464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502
			break;
		}
	}

	return pages;
}


struct page *kimage_alloc_control_pages(struct kimage *image,
					 unsigned int order)
{
	struct page *pages = NULL;

	switch (image->type) {
	case KEXEC_TYPE_DEFAULT:
		pages = kimage_alloc_normal_control_pages(image, order);
		break;
	case KEXEC_TYPE_CRASH:
		pages = kimage_alloc_crash_control_pages(image, order);
		break;
	}

	return pages;
}

static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
{
	if (*image->entry != 0)
		image->entry++;

	if (image->entry == image->last_entry) {
		kimage_entry_t *ind_page;
		struct page *page;

		page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST);
		if (!page)
			return -ENOMEM;

		ind_page = page_address(page);
503
		*image->entry = virt_to_boot_phys(ind_page) | IND_INDIRECTION;
504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
		image->entry = ind_page;
		image->last_entry = ind_page +
				      ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
	}
	*image->entry = entry;
	image->entry++;
	*image->entry = 0;

	return 0;
}

static int kimage_set_destination(struct kimage *image,
				   unsigned long destination)
{
	int result;

	destination &= PAGE_MASK;
	result = kimage_add_entry(image, destination | IND_DESTINATION);

	return result;
}


static int kimage_add_page(struct kimage *image, unsigned long page)
{
	int result;

	page &= PAGE_MASK;
	result = kimage_add_entry(image, page | IND_SOURCE);

	return result;
}


static void kimage_free_extra_pages(struct kimage *image)
{
	/* Walk through and free any extra destination pages I may have */
	kimage_free_page_list(&image->dest_pages);

	/* Walk through and free any unusable pages I have cached */
	kimage_free_page_list(&image->unusable_pages);

}
void kimage_terminate(struct kimage *image)
{
	if (*image->entry != 0)
		image->entry++;

	*image->entry = IND_DONE;
}

#define for_each_kimage_entry(image, ptr, entry) \
	for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
		ptr = (entry & IND_INDIRECTION) ? \
558
			boot_phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
559 560 561 562 563

static void kimage_free_entry(kimage_entry_t entry)
{
	struct page *page;

564
	page = boot_pfn_to_page(entry >> PAGE_SHIFT);
565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657
	kimage_free_pages(page);
}

void kimage_free(struct kimage *image)
{
	kimage_entry_t *ptr, entry;
	kimage_entry_t ind = 0;

	if (!image)
		return;

	kimage_free_extra_pages(image);
	for_each_kimage_entry(image, ptr, entry) {
		if (entry & IND_INDIRECTION) {
			/* Free the previous indirection page */
			if (ind & IND_INDIRECTION)
				kimage_free_entry(ind);
			/* Save this indirection page until we are
			 * done with it.
			 */
			ind = entry;
		} else if (entry & IND_SOURCE)
			kimage_free_entry(entry);
	}
	/* Free the final indirection page */
	if (ind & IND_INDIRECTION)
		kimage_free_entry(ind);

	/* Handle any machine specific cleanup */
	machine_kexec_cleanup(image);

	/* Free the kexec control pages... */
	kimage_free_page_list(&image->control_pages);

	/*
	 * Free up any temporary buffers allocated. This might hit if
	 * error occurred much later after buffer allocation.
	 */
	if (image->file_mode)
		kimage_file_post_load_cleanup(image);

	kfree(image);
}

static kimage_entry_t *kimage_dst_used(struct kimage *image,
					unsigned long page)
{
	kimage_entry_t *ptr, entry;
	unsigned long destination = 0;

	for_each_kimage_entry(image, ptr, entry) {
		if (entry & IND_DESTINATION)
			destination = entry & PAGE_MASK;
		else if (entry & IND_SOURCE) {
			if (page == destination)
				return ptr;
			destination += PAGE_SIZE;
		}
	}

	return NULL;
}

static struct page *kimage_alloc_page(struct kimage *image,
					gfp_t gfp_mask,
					unsigned long destination)
{
	/*
	 * Here we implement safeguards to ensure that a source page
	 * is not copied to its destination page before the data on
	 * the destination page is no longer useful.
	 *
	 * To do this we maintain the invariant that a source page is
	 * either its own destination page, or it is not a
	 * destination page at all.
	 *
	 * That is slightly stronger than required, but the proof
	 * that no problems will not occur is trivial, and the
	 * implementation is simply to verify.
	 *
	 * When allocating all pages normally this algorithm will run
	 * in O(N) time, but in the worst case it will run in O(N^2)
	 * time.   If the runtime is a problem the data structures can
	 * be fixed.
	 */
	struct page *page;
	unsigned long addr;

	/*
	 * Walk through the list of destination pages, and see if I
	 * have a match.
	 */
	list_for_each_entry(page, &image->dest_pages, lru) {
658
		addr = page_to_boot_pfn(page) << PAGE_SHIFT;
659 660 661 662 663 664 665 666 667 668 669 670 671 672
		if (addr == destination) {
			list_del(&page->lru);
			return page;
		}
	}
	page = NULL;
	while (1) {
		kimage_entry_t *old;

		/* Allocate a page, if we run out of memory give up */
		page = kimage_alloc_pages(gfp_mask, 0);
		if (!page)
			return NULL;
		/* If the page cannot be used file it away */
673
		if (page_to_boot_pfn(page) >
674 675 676 677
				(KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) {
			list_add(&page->lru, &image->unusable_pages);
			continue;
		}
678
		addr = page_to_boot_pfn(page) << PAGE_SHIFT;
679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700

		/* If it is the destination page we want use it */
		if (addr == destination)
			break;

		/* If the page is not a destination page use it */
		if (!kimage_is_destination_range(image, addr,
						  addr + PAGE_SIZE))
			break;

		/*
		 * I know that the page is someones destination page.
		 * See if there is already a source page for this
		 * destination page.  And if so swap the source pages.
		 */
		old = kimage_dst_used(image, addr);
		if (old) {
			/* If so move it */
			unsigned long old_addr;
			struct page *old_page;

			old_addr = *old & PAGE_MASK;
701
			old_page = boot_pfn_to_page(old_addr >> PAGE_SHIFT);
702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756
			copy_highpage(page, old_page);
			*old = addr | (*old & ~PAGE_MASK);

			/* The old page I have found cannot be a
			 * destination page, so return it if it's
			 * gfp_flags honor the ones passed in.
			 */
			if (!(gfp_mask & __GFP_HIGHMEM) &&
			    PageHighMem(old_page)) {
				kimage_free_pages(old_page);
				continue;
			}
			addr = old_addr;
			page = old_page;
			break;
		}
		/* Place the page on the destination list, to be used later */
		list_add(&page->lru, &image->dest_pages);
	}

	return page;
}

static int kimage_load_normal_segment(struct kimage *image,
					 struct kexec_segment *segment)
{
	unsigned long maddr;
	size_t ubytes, mbytes;
	int result;
	unsigned char __user *buf = NULL;
	unsigned char *kbuf = NULL;

	result = 0;
	if (image->file_mode)
		kbuf = segment->kbuf;
	else
		buf = segment->buf;
	ubytes = segment->bufsz;
	mbytes = segment->memsz;
	maddr = segment->mem;

	result = kimage_set_destination(image, maddr);
	if (result < 0)
		goto out;

	while (mbytes) {
		struct page *page;
		char *ptr;
		size_t uchunk, mchunk;

		page = kimage_alloc_page(image, GFP_HIGHUSER, maddr);
		if (!page) {
			result  = -ENOMEM;
			goto out;
		}
757
		result = kimage_add_page(image, page_to_boot_pfn(page)
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817
								<< PAGE_SHIFT);
		if (result < 0)
			goto out;

		ptr = kmap(page);
		/* Start with a clear page */
		clear_page(ptr);
		ptr += maddr & ~PAGE_MASK;
		mchunk = min_t(size_t, mbytes,
				PAGE_SIZE - (maddr & ~PAGE_MASK));
		uchunk = min(ubytes, mchunk);

		/* For file based kexec, source pages are in kernel memory */
		if (image->file_mode)
			memcpy(ptr, kbuf, uchunk);
		else
			result = copy_from_user(ptr, buf, uchunk);
		kunmap(page);
		if (result) {
			result = -EFAULT;
			goto out;
		}
		ubytes -= uchunk;
		maddr  += mchunk;
		if (image->file_mode)
			kbuf += mchunk;
		else
			buf += mchunk;
		mbytes -= mchunk;
	}
out:
	return result;
}

static int kimage_load_crash_segment(struct kimage *image,
					struct kexec_segment *segment)
{
	/* For crash dumps kernels we simply copy the data from
	 * user space to it's destination.
	 * We do things a page at a time for the sake of kmap.
	 */
	unsigned long maddr;
	size_t ubytes, mbytes;
	int result;
	unsigned char __user *buf = NULL;
	unsigned char *kbuf = NULL;

	result = 0;
	if (image->file_mode)
		kbuf = segment->kbuf;
	else
		buf = segment->buf;
	ubytes = segment->bufsz;
	mbytes = segment->memsz;
	maddr = segment->mem;
	while (mbytes) {
		struct page *page;
		char *ptr;
		size_t uchunk, mchunk;

818
		page = boot_pfn_to_page(maddr >> PAGE_SHIFT);
819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876
		if (!page) {
			result  = -ENOMEM;
			goto out;
		}
		ptr = kmap(page);
		ptr += maddr & ~PAGE_MASK;
		mchunk = min_t(size_t, mbytes,
				PAGE_SIZE - (maddr & ~PAGE_MASK));
		uchunk = min(ubytes, mchunk);
		if (mchunk > uchunk) {
			/* Zero the trailing part of the page */
			memset(ptr + uchunk, 0, mchunk - uchunk);
		}

		/* For file based kexec, source pages are in kernel memory */
		if (image->file_mode)
			memcpy(ptr, kbuf, uchunk);
		else
			result = copy_from_user(ptr, buf, uchunk);
		kexec_flush_icache_page(page);
		kunmap(page);
		if (result) {
			result = -EFAULT;
			goto out;
		}
		ubytes -= uchunk;
		maddr  += mchunk;
		if (image->file_mode)
			kbuf += mchunk;
		else
			buf += mchunk;
		mbytes -= mchunk;
	}
out:
	return result;
}

int kimage_load_segment(struct kimage *image,
				struct kexec_segment *segment)
{
	int result = -ENOMEM;

	switch (image->type) {
	case KEXEC_TYPE_DEFAULT:
		result = kimage_load_normal_segment(image, segment);
		break;
	case KEXEC_TYPE_CRASH:
		result = kimage_load_crash_segment(image, segment);
		break;
	}

	return result;
}

struct kimage *kexec_image;
struct kimage *kexec_crash_image;
int kexec_load_disabled;

877 878 879 880 881
/*
 * No panic_cpu check version of crash_kexec().  This function is called
 * only when panic_cpu holds the current CPU number; this is the only CPU
 * which processes crash_kexec routines.
 */
882
void __noclone __crash_kexec(struct pt_regs *regs)
883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903
{
	/* Take the kexec_mutex here to prevent sys_kexec_load
	 * running on one cpu from replacing the crash kernel
	 * we are using after a panic on a different cpu.
	 *
	 * If the crash kernel was not located in a fixed area
	 * of memory the xchg(&kexec_crash_image) would be
	 * sufficient.  But since I reuse the memory...
	 */
	if (mutex_trylock(&kexec_mutex)) {
		if (kexec_crash_image) {
			struct pt_regs fixed_regs;

			crash_setup_regs(&fixed_regs, regs);
			crash_save_vmcoreinfo();
			machine_crash_shutdown(&fixed_regs);
			machine_kexec(kexec_crash_image);
		}
		mutex_unlock(&kexec_mutex);
	}
}
904
STACK_FRAME_NON_STANDARD(__crash_kexec);
905

906 907 908 909 910 911 912 913 914 915 916 917 918
void crash_kexec(struct pt_regs *regs)
{
	int old_cpu, this_cpu;

	/*
	 * Only one CPU is allowed to execute the crash_kexec() code as with
	 * panic().  Otherwise parallel calls of panic() and crash_kexec()
	 * may stop each other.  To exclude them, we use panic_cpu here too.
	 */
	this_cpu = raw_smp_processor_id();
	old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
	if (old_cpu == PANIC_CPU_INVALID) {
		/* This is the 1st CPU which comes here, so go ahead. */
919
		printk_nmi_flush_on_panic();
920 921 922 923 924 925 926 927 928 929
		__crash_kexec(regs);

		/*
		 * Reset panic_cpu to allow another panic()/crash_kexec()
		 * call.
		 */
		atomic_set(&panic_cpu, PANIC_CPU_INVALID);
	}
}

930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946
size_t crash_get_memory_size(void)
{
	size_t size = 0;

	mutex_lock(&kexec_mutex);
	if (crashk_res.end != crashk_res.start)
		size = resource_size(&crashk_res);
	mutex_unlock(&kexec_mutex);
	return size;
}

void __weak crash_free_reserved_phys_range(unsigned long begin,
					   unsigned long end)
{
	unsigned long addr;

	for (addr = begin; addr < end; addr += PAGE_SIZE)
947
		free_reserved_page(boot_pfn_to_page(addr >> PAGE_SHIFT));
948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986
}

int crash_shrink_memory(unsigned long new_size)
{
	int ret = 0;
	unsigned long start, end;
	unsigned long old_size;
	struct resource *ram_res;

	mutex_lock(&kexec_mutex);

	if (kexec_crash_image) {
		ret = -ENOENT;
		goto unlock;
	}
	start = crashk_res.start;
	end = crashk_res.end;
	old_size = (end == 0) ? 0 : end - start + 1;
	if (new_size >= old_size) {
		ret = (new_size == old_size) ? 0 : -EINVAL;
		goto unlock;
	}

	ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL);
	if (!ram_res) {
		ret = -ENOMEM;
		goto unlock;
	}

	start = roundup(start, KEXEC_CRASH_MEM_ALIGN);
	end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN);

	crash_free_reserved_phys_range(end, crashk_res.end);

	if ((start == end) && (crashk_res.parent != NULL))
		release_resource(&crashk_res);

	ram_res->start = end;
	ram_res->end = crashk_res.end;
987
	ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055
	ram_res->name = "System RAM";

	crashk_res.end = end - 1;

	insert_resource(&iomem_resource, ram_res);

unlock:
	mutex_unlock(&kexec_mutex);
	return ret;
}

static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
			    size_t data_len)
{
	struct elf_note note;

	note.n_namesz = strlen(name) + 1;
	note.n_descsz = data_len;
	note.n_type   = type;
	memcpy(buf, &note, sizeof(note));
	buf += (sizeof(note) + 3)/4;
	memcpy(buf, name, note.n_namesz);
	buf += (note.n_namesz + 3)/4;
	memcpy(buf, data, note.n_descsz);
	buf += (note.n_descsz + 3)/4;

	return buf;
}

static void final_note(u32 *buf)
{
	struct elf_note note;

	note.n_namesz = 0;
	note.n_descsz = 0;
	note.n_type   = 0;
	memcpy(buf, &note, sizeof(note));
}

void crash_save_cpu(struct pt_regs *regs, int cpu)
{
	struct elf_prstatus prstatus;
	u32 *buf;

	if ((cpu < 0) || (cpu >= nr_cpu_ids))
		return;

	/* Using ELF notes here is opportunistic.
	 * I need a well defined structure format
	 * for the data I pass, and I need tags
	 * on the data to indicate what information I have
	 * squirrelled away.  ELF notes happen to provide
	 * all of that, so there is no need to invent something new.
	 */
	buf = (u32 *)per_cpu_ptr(crash_notes, cpu);
	if (!buf)
		return;
	memset(&prstatus, 0, sizeof(prstatus));
	prstatus.pr_pid = current->pid;
	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
	buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
			      &prstatus, sizeof(prstatus));
	final_note(buf);
}

static int __init crash_notes_memory_init(void)
{
	/* Allocate memory for saving cpu registers. */
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077
	size_t size, align;

	/*
	 * crash_notes could be allocated across 2 vmalloc pages when percpu
	 * is vmalloc based . vmalloc doesn't guarantee 2 continuous vmalloc
	 * pages are also on 2 continuous physical pages. In this case the
	 * 2nd part of crash_notes in 2nd page could be lost since only the
	 * starting address and size of crash_notes are exported through sysfs.
	 * Here round up the size of crash_notes to the nearest power of two
	 * and pass it to __alloc_percpu as align value. This can make sure
	 * crash_notes is allocated inside one physical page.
	 */
	size = sizeof(note_buf_t);
	align = min(roundup_pow_of_two(sizeof(note_buf_t)), PAGE_SIZE);

	/*
	 * Break compile if size is bigger than PAGE_SIZE since crash_notes
	 * definitely will be in 2 pages with that.
	 */
	BUILD_BUG_ON(size > PAGE_SIZE);

	crash_notes = __alloc_percpu(size, align);
1078
	if (!crash_notes) {
1079
		pr_warn("Memory allocation for saving cpu register states failed\n");
1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200
		return -ENOMEM;
	}
	return 0;
}
subsys_initcall(crash_notes_memory_init);


/*
 * parsing the "crashkernel" commandline
 *
 * this code is intended to be called from architecture specific code
 */


/*
 * This function parses command lines in the format
 *
 *   crashkernel=ramsize-range:size[,...][@offset]
 *
 * The function returns 0 on success and -EINVAL on failure.
 */
static int __init parse_crashkernel_mem(char *cmdline,
					unsigned long long system_ram,
					unsigned long long *crash_size,
					unsigned long long *crash_base)
{
	char *cur = cmdline, *tmp;

	/* for each entry of the comma-separated list */
	do {
		unsigned long long start, end = ULLONG_MAX, size;

		/* get the start of the range */
		start = memparse(cur, &tmp);
		if (cur == tmp) {
			pr_warn("crashkernel: Memory value expected\n");
			return -EINVAL;
		}
		cur = tmp;
		if (*cur != '-') {
			pr_warn("crashkernel: '-' expected\n");
			return -EINVAL;
		}
		cur++;

		/* if no ':' is here, than we read the end */
		if (*cur != ':') {
			end = memparse(cur, &tmp);
			if (cur == tmp) {
				pr_warn("crashkernel: Memory value expected\n");
				return -EINVAL;
			}
			cur = tmp;
			if (end <= start) {
				pr_warn("crashkernel: end <= start\n");
				return -EINVAL;
			}
		}

		if (*cur != ':') {
			pr_warn("crashkernel: ':' expected\n");
			return -EINVAL;
		}
		cur++;

		size = memparse(cur, &tmp);
		if (cur == tmp) {
			pr_warn("Memory value expected\n");
			return -EINVAL;
		}
		cur = tmp;
		if (size >= system_ram) {
			pr_warn("crashkernel: invalid size\n");
			return -EINVAL;
		}

		/* match ? */
		if (system_ram >= start && system_ram < end) {
			*crash_size = size;
			break;
		}
	} while (*cur++ == ',');

	if (*crash_size > 0) {
		while (*cur && *cur != ' ' && *cur != '@')
			cur++;
		if (*cur == '@') {
			cur++;
			*crash_base = memparse(cur, &tmp);
			if (cur == tmp) {
				pr_warn("Memory value expected after '@'\n");
				return -EINVAL;
			}
		}
	}

	return 0;
}

/*
 * That function parses "simple" (old) crashkernel command lines like
 *
 *	crashkernel=size[@offset]
 *
 * It returns 0 on success and -EINVAL on failure.
 */
static int __init parse_crashkernel_simple(char *cmdline,
					   unsigned long long *crash_size,
					   unsigned long long *crash_base)
{
	char *cur = cmdline;

	*crash_size = memparse(cmdline, &cur);
	if (cmdline == cur) {
		pr_warn("crashkernel: memory value expected\n");
		return -EINVAL;
	}

	if (*cur == '@')
		*crash_base = memparse(cur+1, &cur);
	else if (*cur != ' ' && *cur != '\0') {
1201
		pr_warn("crashkernel: unrecognized char: %c\n", *cur);
1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237
		return -EINVAL;
	}

	return 0;
}

#define SUFFIX_HIGH 0
#define SUFFIX_LOW  1
#define SUFFIX_NULL 2
static __initdata char *suffix_tbl[] = {
	[SUFFIX_HIGH] = ",high",
	[SUFFIX_LOW]  = ",low",
	[SUFFIX_NULL] = NULL,
};

/*
 * That function parses "suffix"  crashkernel command lines like
 *
 *	crashkernel=size,[high|low]
 *
 * It returns 0 on success and -EINVAL on failure.
 */
static int __init parse_crashkernel_suffix(char *cmdline,
					   unsigned long long	*crash_size,
					   const char *suffix)
{
	char *cur = cmdline;

	*crash_size = memparse(cmdline, &cur);
	if (cmdline == cur) {
		pr_warn("crashkernel: memory value expected\n");
		return -EINVAL;
	}

	/* check with suffix */
	if (strncmp(cur, suffix, strlen(suffix))) {
1238
		pr_warn("crashkernel: unrecognized char: %c\n", *cur);
1239 1240 1241 1242
		return -EINVAL;
	}
	cur += strlen(suffix);
	if (*cur != ' ' && *cur != '\0') {
1243
		pr_warn("crashkernel: unrecognized char: %c\n", *cur);
1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399
		return -EINVAL;
	}

	return 0;
}

static __init char *get_last_crashkernel(char *cmdline,
			     const char *name,
			     const char *suffix)
{
	char *p = cmdline, *ck_cmdline = NULL;

	/* find crashkernel and use the last one if there are more */
	p = strstr(p, name);
	while (p) {
		char *end_p = strchr(p, ' ');
		char *q;

		if (!end_p)
			end_p = p + strlen(p);

		if (!suffix) {
			int i;

			/* skip the one with any known suffix */
			for (i = 0; suffix_tbl[i]; i++) {
				q = end_p - strlen(suffix_tbl[i]);
				if (!strncmp(q, suffix_tbl[i],
					     strlen(suffix_tbl[i])))
					goto next;
			}
			ck_cmdline = p;
		} else {
			q = end_p - strlen(suffix);
			if (!strncmp(q, suffix, strlen(suffix)))
				ck_cmdline = p;
		}
next:
		p = strstr(p+1, name);
	}

	if (!ck_cmdline)
		return NULL;

	return ck_cmdline;
}

static int __init __parse_crashkernel(char *cmdline,
			     unsigned long long system_ram,
			     unsigned long long *crash_size,
			     unsigned long long *crash_base,
			     const char *name,
			     const char *suffix)
{
	char	*first_colon, *first_space;
	char	*ck_cmdline;

	BUG_ON(!crash_size || !crash_base);
	*crash_size = 0;
	*crash_base = 0;

	ck_cmdline = get_last_crashkernel(cmdline, name, suffix);

	if (!ck_cmdline)
		return -EINVAL;

	ck_cmdline += strlen(name);

	if (suffix)
		return parse_crashkernel_suffix(ck_cmdline, crash_size,
				suffix);
	/*
	 * if the commandline contains a ':', then that's the extended
	 * syntax -- if not, it must be the classic syntax
	 */
	first_colon = strchr(ck_cmdline, ':');
	first_space = strchr(ck_cmdline, ' ');
	if (first_colon && (!first_space || first_colon < first_space))
		return parse_crashkernel_mem(ck_cmdline, system_ram,
				crash_size, crash_base);

	return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
}

/*
 * That function is the entry point for command line parsing and should be
 * called from the arch-specific code.
 */
int __init parse_crashkernel(char *cmdline,
			     unsigned long long system_ram,
			     unsigned long long *crash_size,
			     unsigned long long *crash_base)
{
	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
					"crashkernel=", NULL);
}

int __init parse_crashkernel_high(char *cmdline,
			     unsigned long long system_ram,
			     unsigned long long *crash_size,
			     unsigned long long *crash_base)
{
	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
				"crashkernel=", suffix_tbl[SUFFIX_HIGH]);
}

int __init parse_crashkernel_low(char *cmdline,
			     unsigned long long system_ram,
			     unsigned long long *crash_size,
			     unsigned long long *crash_base)
{
	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
				"crashkernel=", suffix_tbl[SUFFIX_LOW]);
}

static void update_vmcoreinfo_note(void)
{
	u32 *buf = vmcoreinfo_note;

	if (!vmcoreinfo_size)
		return;
	buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
			      vmcoreinfo_size);
	final_note(buf);
}

void crash_save_vmcoreinfo(void)
{
	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
	update_vmcoreinfo_note();
}

void vmcoreinfo_append_str(const char *fmt, ...)
{
	va_list args;
	char buf[0x50];
	size_t r;

	va_start(args, fmt);
	r = vscnprintf(buf, sizeof(buf), fmt, args);
	va_end(args);

	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);

	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);

	vmcoreinfo_size += r;
}

/*
 * provide an empty default implementation here -- architecture
 * code may override this
 */
void __weak arch_crash_save_vmcoreinfo(void)
{}

1400
phys_addr_t __weak paddr_vmcoreinfo_note(void)
1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434
{
	return __pa((unsigned long)(char *)&vmcoreinfo_note);
}

static int __init crash_save_vmcoreinfo_init(void)
{
	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
	VMCOREINFO_PAGESIZE(PAGE_SIZE);

	VMCOREINFO_SYMBOL(init_uts_ns);
	VMCOREINFO_SYMBOL(node_online_map);
#ifdef CONFIG_MMU
	VMCOREINFO_SYMBOL(swapper_pg_dir);
#endif
	VMCOREINFO_SYMBOL(_stext);
	VMCOREINFO_SYMBOL(vmap_area_list);

#ifndef CONFIG_NEED_MULTIPLE_NODES
	VMCOREINFO_SYMBOL(mem_map);
	VMCOREINFO_SYMBOL(contig_page_data);
#endif
#ifdef CONFIG_SPARSEMEM
	VMCOREINFO_SYMBOL(mem_section);
	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
	VMCOREINFO_STRUCT_SIZE(mem_section);
	VMCOREINFO_OFFSET(mem_section, section_mem_map);
#endif
	VMCOREINFO_STRUCT_SIZE(page);
	VMCOREINFO_STRUCT_SIZE(pglist_data);
	VMCOREINFO_STRUCT_SIZE(zone);
	VMCOREINFO_STRUCT_SIZE(free_area);
	VMCOREINFO_STRUCT_SIZE(list_head);
	VMCOREINFO_SIZE(nodemask_t);
	VMCOREINFO_OFFSET(page, flags);
1435
	VMCOREINFO_OFFSET(page, _refcount);
1436 1437 1438 1439
	VMCOREINFO_OFFSET(page, mapping);
	VMCOREINFO_OFFSET(page, lru);
	VMCOREINFO_OFFSET(page, _mapcount);
	VMCOREINFO_OFFSET(page, private);
1440 1441
	VMCOREINFO_OFFSET(page, compound_dtor);
	VMCOREINFO_OFFSET(page, compound_order);
1442
	VMCOREINFO_OFFSET(page, compound_head);
1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471
	VMCOREINFO_OFFSET(pglist_data, node_zones);
	VMCOREINFO_OFFSET(pglist_data, nr_zones);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
	VMCOREINFO_OFFSET(pglist_data, node_mem_map);
#endif
	VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
	VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
	VMCOREINFO_OFFSET(pglist_data, node_id);
	VMCOREINFO_OFFSET(zone, free_area);
	VMCOREINFO_OFFSET(zone, vm_stat);
	VMCOREINFO_OFFSET(zone, spanned_pages);
	VMCOREINFO_OFFSET(free_area, free_list);
	VMCOREINFO_OFFSET(list_head, next);
	VMCOREINFO_OFFSET(list_head, prev);
	VMCOREINFO_OFFSET(vmap_area, va_start);
	VMCOREINFO_OFFSET(vmap_area, list);
	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
	log_buf_kexec_setup();
	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
	VMCOREINFO_NUMBER(NR_FREE_PAGES);
	VMCOREINFO_NUMBER(PG_lru);
	VMCOREINFO_NUMBER(PG_private);
	VMCOREINFO_NUMBER(PG_swapcache);
	VMCOREINFO_NUMBER(PG_slab);
#ifdef CONFIG_MEMORY_FAILURE
	VMCOREINFO_NUMBER(PG_hwpoison);
#endif
	VMCOREINFO_NUMBER(PG_head_mask);
	VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
1472 1473 1474
#ifdef CONFIG_X86
	VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
#endif
1475 1476
#ifdef CONFIG_HUGETLB_PAGE
	VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576
#endif

	arch_crash_save_vmcoreinfo();
	update_vmcoreinfo_note();

	return 0;
}

subsys_initcall(crash_save_vmcoreinfo_init);

/*
 * Move into place and start executing a preloaded standalone
 * executable.  If nothing was preloaded return an error.
 */
int kernel_kexec(void)
{
	int error = 0;

	if (!mutex_trylock(&kexec_mutex))
		return -EBUSY;
	if (!kexec_image) {
		error = -EINVAL;
		goto Unlock;
	}

#ifdef CONFIG_KEXEC_JUMP
	if (kexec_image->preserve_context) {
		lock_system_sleep();
		pm_prepare_console();
		error = freeze_processes();
		if (error) {
			error = -EBUSY;
			goto Restore_console;
		}
		suspend_console();
		error = dpm_suspend_start(PMSG_FREEZE);
		if (error)
			goto Resume_console;
		/* At this point, dpm_suspend_start() has been called,
		 * but *not* dpm_suspend_end(). We *must* call
		 * dpm_suspend_end() now.  Otherwise, drivers for
		 * some devices (e.g. interrupt controllers) become
		 * desynchronized with the actual state of the
		 * hardware at resume time, and evil weirdness ensues.
		 */
		error = dpm_suspend_end(PMSG_FREEZE);
		if (error)
			goto Resume_devices;
		error = disable_nonboot_cpus();
		if (error)
			goto Enable_cpus;
		local_irq_disable();
		error = syscore_suspend();
		if (error)
			goto Enable_irqs;
	} else
#endif
	{
		kexec_in_progress = true;
		kernel_restart_prepare(NULL);
		migrate_to_reboot_cpu();

		/*
		 * migrate_to_reboot_cpu() disables CPU hotplug assuming that
		 * no further code needs to use CPU hotplug (which is true in
		 * the reboot case). However, the kexec path depends on using
		 * CPU hotplug again; so re-enable it here.
		 */
		cpu_hotplug_enable();
		pr_emerg("Starting new kernel\n");
		machine_shutdown();
	}

	machine_kexec(kexec_image);

#ifdef CONFIG_KEXEC_JUMP
	if (kexec_image->preserve_context) {
		syscore_resume();
 Enable_irqs:
		local_irq_enable();
 Enable_cpus:
		enable_nonboot_cpus();
		dpm_resume_start(PMSG_RESTORE);
 Resume_devices:
		dpm_resume_end(PMSG_RESTORE);
 Resume_console:
		resume_console();
		thaw_processes();
 Restore_console:
		pm_restore_console();
		unlock_system_sleep();
	}
#endif

 Unlock:
	mutex_unlock(&kexec_mutex);
	return error;
}

/*
1577 1578
 * Protection mechanism for crashkernel reserved memory after
 * the kdump kernel is loaded.
1579 1580 1581 1582
 *
 * Provide an empty default implementation here -- architecture
 * code may override this
 */
1583 1584 1585 1586 1587
void __weak arch_kexec_protect_crashkres(void)
{}

void __weak arch_kexec_unprotect_crashkres(void)
{}