vmcore.c 27.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10
/*
 *	fs/proc/vmcore.c Interface for accessing the crash
 * 				 dump from the system's previous life.
 * 	Heavily borrowed from fs/proc/kcore.c
 *	Created by: Hariprasad Nellitheertha (hari@in.ibm.com)
 *	Copyright (C) IBM Corporation, 2004. All rights reserved
 *
 */

#include <linux/mm.h>
11
#include <linux/kcore.h>
12 13 14
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
15
#include <linux/export.h>
16
#include <linux/slab.h>
17
#include <linux/highmem.h>
A
Andrew Morton 已提交
18
#include <linux/printk.h>
19 20 21 22
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/crash_dump.h>
#include <linux/list.h>
23
#include <linux/vmalloc.h>
24
#include <linux/pagemap.h>
25 26
#include <asm/uaccess.h>
#include <asm/io.h>
27
#include "internal.h"
28 29 30 31 32 33 34 35 36

/* List representing chunks of contiguous memory areas and their offsets in
 * vmcore file.
 */
static LIST_HEAD(vmcore_list);

/* Stores the pointer to the buffer containing kernel elf core headers. */
static char *elfcorebuf;
static size_t elfcorebuf_sz;
37
static size_t elfcorebuf_sz_orig;
38

39 40 41
static char *elfnotes_buf;
static size_t elfnotes_sz;

42 43 44
/* Total size of vmcore file. */
static u64 vmcore_size;

45
static struct proc_dir_entry *proc_vmcore = NULL;
46

47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86
/*
 * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
 * The called function has to take care of module refcounting.
 */
static int (*oldmem_pfn_is_ram)(unsigned long pfn);

int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn))
{
	if (oldmem_pfn_is_ram)
		return -EBUSY;
	oldmem_pfn_is_ram = fn;
	return 0;
}
EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram);

void unregister_oldmem_pfn_is_ram(void)
{
	oldmem_pfn_is_ram = NULL;
	wmb();
}
EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram);

static int pfn_is_ram(unsigned long pfn)
{
	int (*fn)(unsigned long pfn);
	/* pfn is ram unless fn() checks pagetype */
	int ret = 1;

	/*
	 * Ask hypervisor if the pfn is really ram.
	 * A ballooned page contains no data and reading from such a page
	 * will cause high load in the hypervisor.
	 */
	fn = oldmem_pfn_is_ram;
	if (fn)
		ret = fn(pfn);

	return ret;
}

87 88
/* Reads a page from the oldmem device from given offset. */
static ssize_t read_from_oldmem(char *buf, size_t count,
89
				u64 *ppos, int userbuf)
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106
{
	unsigned long pfn, offset;
	size_t nr_bytes;
	ssize_t read = 0, tmp;

	if (!count)
		return 0;

	offset = (unsigned long)(*ppos % PAGE_SIZE);
	pfn = (unsigned long)(*ppos / PAGE_SIZE);

	do {
		if (count > (PAGE_SIZE - offset))
			nr_bytes = PAGE_SIZE - offset;
		else
			nr_bytes = count;

107 108 109 110 111 112 113 114 115
		/* If pfn is not ram, return zeros for sparse dump files */
		if (pfn_is_ram(pfn) == 0)
			memset(buf, 0, nr_bytes);
		else {
			tmp = copy_oldmem_page(pfn, buf, nr_bytes,
						offset, userbuf);
			if (tmp < 0)
				return tmp;
		}
116 117 118 119 120 121 122 123 124 125 126
		*ppos += nr_bytes;
		count -= nr_bytes;
		buf += nr_bytes;
		read += nr_bytes;
		++pfn;
		offset = 0;
	} while (count);

	return read;
}

127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
/*
 * Architectures may override this function to allocate ELF header in 2nd kernel
 */
int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
{
	return 0;
}

/*
 * Architectures may override this function to free header
 */
void __weak elfcorehdr_free(unsigned long long addr)
{}

/*
 * Architectures may override this function to read from ELF header
 */
ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
{
	return read_from_oldmem(buf, count, ppos, 0);
}

/*
 * Architectures may override this function to read from notes sections
 */
ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
{
	return read_from_oldmem(buf, count, ppos, 0);
}

157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180
/*
 * Architectures may override this function to map oldmem
 */
int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
				  unsigned long from, unsigned long pfn,
				  unsigned long size, pgprot_t prot)
{
	return remap_pfn_range(vma, from, pfn, size, prot);
}

/*
 * Copy to either kernel or user space
 */
static int copy_to(void *target, void *src, size_t size, int userbuf)
{
	if (userbuf) {
		if (copy_to_user((char __user *) target, src, size))
			return -EFAULT;
	} else {
		memcpy(target, src, size);
	}
	return 0;
}

181 182 183
/* Read from the ELF header and then the crash dump. On error, negative value is
 * returned otherwise number of bytes read are returned.
 */
184 185
static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
			     int userbuf)
186 187
{
	ssize_t acc = 0, tmp;
188
	size_t tsz;
189 190
	u64 start;
	struct vmcore *m = NULL;
191 192 193 194 195 196 197 198 199 200

	if (buflen == 0 || *fpos >= vmcore_size)
		return 0;

	/* trim buflen to not go beyond EOF */
	if (buflen > vmcore_size - *fpos)
		buflen = vmcore_size - *fpos;

	/* Read ELF core header */
	if (*fpos < elfcorebuf_sz) {
201
		tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
202
		if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf))
203 204 205 206 207 208 209 210 211 212 213
			return -EFAULT;
		buflen -= tsz;
		*fpos += tsz;
		buffer += tsz;
		acc += tsz;

		/* leave now if filled buffer already */
		if (buflen == 0)
			return acc;
	}

214 215 216 217 218 219
	/* Read Elf note segment */
	if (*fpos < elfcorebuf_sz + elfnotes_sz) {
		void *kaddr;

		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
		kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
220
		if (copy_to(buffer, kaddr, tsz, userbuf))
221 222 223 224 225 226 227 228 229 230 231
			return -EFAULT;
		buflen -= tsz;
		*fpos += tsz;
		buffer += tsz;
		acc += tsz;

		/* leave now if filled buffer already */
		if (buflen == 0)
			return acc;
	}

232 233
	list_for_each_entry(m, &vmcore_list, list) {
		if (*fpos < m->offset + m->size) {
234
			tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
235
			start = m->paddr + *fpos - m->offset;
236
			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
237 238 239 240 241 242 243 244 245 246
			if (tmp < 0)
				return tmp;
			buflen -= tsz;
			*fpos += tsz;
			buffer += tsz;
			acc += tsz;

			/* leave now if filled buffer already */
			if (buflen == 0)
				return acc;
247 248
		}
	}
249

250 251 252
	return acc;
}

253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
static ssize_t read_vmcore(struct file *file, char __user *buffer,
			   size_t buflen, loff_t *fpos)
{
	return __read_vmcore((__force char *) buffer, buflen, fpos, 1);
}

/*
 * The vmcore fault handler uses the page cache and fills data using the
 * standard __vmcore_read() function.
 *
 * On s390 the fault handler is used for memory regions that can't be mapped
 * directly with remap_pfn_range().
 */
static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
#ifdef CONFIG_S390
	struct address_space *mapping = vma->vm_file->f_mapping;
	pgoff_t index = vmf->pgoff;
	struct page *page;
	loff_t offset;
	char *buf;
	int rc;

	page = find_or_create_page(mapping, index, GFP_KERNEL);
	if (!page)
		return VM_FAULT_OOM;
	if (!PageUptodate(page)) {
		offset = (loff_t) index << PAGE_CACHE_SHIFT;
		buf = __va((page_to_pfn(page) << PAGE_SHIFT));
		rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0);
		if (rc < 0) {
			unlock_page(page);
			page_cache_release(page);
			return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
		}
		SetPageUptodate(page);
	}
	unlock_page(page);
	vmf->page = page;
	return 0;
#else
	return VM_FAULT_SIGBUS;
#endif
}

static const struct vm_operations_struct vmcore_mmap_ops = {
	.fault = mmap_vmcore_fault,
};

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
/**
 * alloc_elfnotes_buf - allocate buffer for ELF note segment in
 *                      vmalloc memory
 *
 * @notes_sz: size of buffer
 *
 * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap
 * the buffer to user-space by means of remap_vmalloc_range().
 *
 * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is
 * disabled and there's no need to allow users to mmap the buffer.
 */
static inline char *alloc_elfnotes_buf(size_t notes_sz)
{
#ifdef CONFIG_MMU
	return vmalloc_user(notes_sz);
#else
	return vzalloc(notes_sz);
#endif
}

/*
 * Disable mmap_vmcore() if CONFIG_MMU is not defined. MMU is
 * essential for mmap_vmcore() in order to map physically
 * non-contiguous objects (ELF header, ELF note segment and memory
 * regions in the 1st kernel pointed to by PT_LOAD entries) into
 * virtually contiguous user-space in ELF layout.
 */
330
#ifdef CONFIG_MMU
331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
	size_t size = vma->vm_end - vma->vm_start;
	u64 start, end, len, tsz;
	struct vmcore *m;

	start = (u64)vma->vm_pgoff << PAGE_SHIFT;
	end = start + size;

	if (size > vmcore_size || end > vmcore_size)
		return -EINVAL;

	if (vma->vm_flags & (VM_WRITE | VM_EXEC))
		return -EPERM;

	vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
	vma->vm_flags |= VM_MIXEDMAP;
348
	vma->vm_ops = &vmcore_mmap_ops;
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389

	len = 0;

	if (start < elfcorebuf_sz) {
		u64 pfn;

		tsz = min(elfcorebuf_sz - (size_t)start, size);
		pfn = __pa(elfcorebuf + start) >> PAGE_SHIFT;
		if (remap_pfn_range(vma, vma->vm_start, pfn, tsz,
				    vma->vm_page_prot))
			return -EAGAIN;
		size -= tsz;
		start += tsz;
		len += tsz;

		if (size == 0)
			return 0;
	}

	if (start < elfcorebuf_sz + elfnotes_sz) {
		void *kaddr;

		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
		kaddr = elfnotes_buf + start - elfcorebuf_sz;
		if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
						kaddr, tsz))
			goto fail;
		size -= tsz;
		start += tsz;
		len += tsz;

		if (size == 0)
			return 0;
	}

	list_for_each_entry(m, &vmcore_list, list) {
		if (start < m->offset + m->size) {
			u64 paddr = 0;

			tsz = min_t(size_t, m->offset + m->size - start, size);
			paddr = m->paddr + start - m->offset;
390 391 392
			if (remap_oldmem_pfn_range(vma, vma->vm_start + len,
						   paddr >> PAGE_SHIFT, tsz,
						   vma->vm_page_prot))
393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414
				goto fail;
			size -= tsz;
			start += tsz;
			len += tsz;

			if (size == 0)
				return 0;
		}
	}

	return 0;
fail:
	do_munmap(vma->vm_mm, vma->vm_start, len);
	return -EAGAIN;
}
#else
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
	return -ENOSYS;
}
#endif

415
static const struct file_operations proc_vmcore_operations = {
416
	.read		= read_vmcore,
A
Arnd Bergmann 已提交
417
	.llseek		= default_llseek,
418
	.mmap		= mmap_vmcore,
419 420 421 422
};

static struct vmcore* __init get_new_element(void)
{
423
	return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
424 425
}

426 427
static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
				  struct list_head *vc_list)
428 429
{
	u64 size;
430
	struct vmcore *m;
431

432 433 434
	size = elfsz + elfnotesegsz;
	list_for_each_entry(m, vc_list, list) {
		size += m->size;
435 436 437 438
	}
	return size;
}

439 440 441 442 443 444 445 446 447 448
/**
 * update_note_header_size_elf64 - update p_memsz member of each PT_NOTE entry
 *
 * @ehdr_ptr: ELF header
 *
 * This function updates p_memsz member of each PT_NOTE entry in the
 * program header table pointed to by @ehdr_ptr to real size of ELF
 * note segment.
 */
static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
449
{
450 451
	int i, rc=0;
	Elf64_Phdr *phdr_ptr;
452 453
	Elf64_Nhdr *nhdr_ptr;

454
	phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1);
455 456 457 458 459 460 461 462 463 464
	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		void *notes_section;
		u64 offset, max_sz, sz, real_sz = 0;
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		max_sz = phdr_ptr->p_memsz;
		offset = phdr_ptr->p_offset;
		notes_section = kmalloc(max_sz, GFP_KERNEL);
		if (!notes_section)
			return -ENOMEM;
465
		rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
466 467 468 469 470
		if (rc < 0) {
			kfree(notes_section);
			return rc;
		}
		nhdr_ptr = notes_section;
471
		while (nhdr_ptr->n_namesz != 0) {
472 473 474
			sz = sizeof(Elf64_Nhdr) +
				((nhdr_ptr->n_namesz + 3) & ~3) +
				((nhdr_ptr->n_descsz + 3) & ~3);
475 476 477 478 479
			if ((real_sz + sz) > max_sz) {
				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
				break;
			}
480 481 482 483
			real_sz += sz;
			nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
		}
		kfree(notes_section);
484
		phdr_ptr->p_memsz = real_sz;
485 486 487
		if (real_sz == 0) {
			pr_warn("Warning: Zero PT_NOTE entries found\n");
		}
488 489
	}

490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
	return 0;
}

/**
 * get_note_number_and_size_elf64 - get the number of PT_NOTE program
 * headers and sum of real size of their ELF note segment headers and
 * data.
 *
 * @ehdr_ptr: ELF header
 * @nr_ptnote: buffer for the number of PT_NOTE program headers
 * @sz_ptnote: buffer for size of unique PT_NOTE program header
 *
 * This function is used to merge multiple PT_NOTE program headers
 * into a unique single one. The resulting unique entry will have
 * @sz_ptnote in its phdr->p_mem.
 *
 * It is assumed that program headers with PT_NOTE type pointed to by
 * @ehdr_ptr has already been updated by update_note_header_size_elf64
 * and each of PT_NOTE program headers has actual ELF note segment
 * size in its p_memsz member.
 */
static int __init get_note_number_and_size_elf64(const Elf64_Ehdr *ehdr_ptr,
						 int *nr_ptnote, u64 *sz_ptnote)
{
	int i;
	Elf64_Phdr *phdr_ptr;

	*nr_ptnote = *sz_ptnote = 0;

	phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1);
	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		*nr_ptnote += 1;
		*sz_ptnote += phdr_ptr->p_memsz;
	}

	return 0;
}

/**
 * copy_notes_elf64 - copy ELF note segments in a given buffer
 *
 * @ehdr_ptr: ELF header
 * @notes_buf: buffer into which ELF note segments are copied
 *
 * This function is used to copy ELF note segment in the 1st kernel
 * into the buffer @notes_buf in the 2nd kernel. It is assumed that
 * size of the buffer @notes_buf is equal to or larger than sum of the
 * real ELF note segment headers and data.
 *
 * It is assumed that program headers with PT_NOTE type pointed to by
 * @ehdr_ptr has already been updated by update_note_header_size_elf64
 * and each of PT_NOTE program headers has actual ELF note segment
 * size in its p_memsz member.
 */
static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf)
{
	int i, rc=0;
	Elf64_Phdr *phdr_ptr;

	phdr_ptr = (Elf64_Phdr*)(ehdr_ptr + 1);

	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		u64 offset;
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		offset = phdr_ptr->p_offset;
558 559
		rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
					   &offset);
560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588
		if (rc < 0)
			return rc;
		notes_buf += phdr_ptr->p_memsz;
	}

	return 0;
}

/* Merges all the PT_NOTE headers into one. */
static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
					   char **notes_buf, size_t *notes_sz)
{
	int i, nr_ptnote=0, rc=0;
	char *tmp;
	Elf64_Ehdr *ehdr_ptr;
	Elf64_Phdr phdr;
	u64 phdr_sz = 0, note_off;

	ehdr_ptr = (Elf64_Ehdr *)elfptr;

	rc = update_note_header_size_elf64(ehdr_ptr);
	if (rc < 0)
		return rc;

	rc = get_note_number_and_size_elf64(ehdr_ptr, &nr_ptnote, &phdr_sz);
	if (rc < 0)
		return rc;

	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
589
	*notes_buf = alloc_elfnotes_buf(*notes_sz);
590 591 592 593 594 595 596
	if (!*notes_buf)
		return -ENOMEM;

	rc = copy_notes_elf64(ehdr_ptr, *notes_buf);
	if (rc < 0)
		return rc;

597 598 599 600 601
	/* Prepare merged PT_NOTE program header. */
	phdr.p_type    = PT_NOTE;
	phdr.p_flags   = 0;
	note_off = sizeof(Elf64_Ehdr) +
			(ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf64_Phdr);
602
	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
603 604 605 606 607 608 609 610 611 612 613 614 615
	phdr.p_vaddr   = phdr.p_paddr = 0;
	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
	phdr.p_align   = 0;

	/* Add merged PT_NOTE program header*/
	tmp = elfptr + sizeof(Elf64_Ehdr);
	memcpy(tmp, &phdr, sizeof(phdr));
	tmp += sizeof(phdr);

	/* Remove unwanted PT_NOTE program headers. */
	i = (nr_ptnote - 1) * sizeof(Elf64_Phdr);
	*elfsz = *elfsz - i;
	memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf64_Ehdr)-sizeof(Elf64_Phdr)));
616 617
	memset(elfptr + *elfsz, 0, i);
	*elfsz = roundup(*elfsz, PAGE_SIZE);
618 619 620 621 622 623 624

	/* Modify e_phnum to reflect merged headers. */
	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;

	return 0;
}

625 626 627 628 629 630 631 632 633 634
/**
 * update_note_header_size_elf32 - update p_memsz member of each PT_NOTE entry
 *
 * @ehdr_ptr: ELF header
 *
 * This function updates p_memsz member of each PT_NOTE entry in the
 * program header table pointed to by @ehdr_ptr to real size of ELF
 * note segment.
 */
static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
635
{
636 637
	int i, rc=0;
	Elf32_Phdr *phdr_ptr;
638 639
	Elf32_Nhdr *nhdr_ptr;

640
	phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1);
641 642 643 644 645 646 647 648 649 650
	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		void *notes_section;
		u64 offset, max_sz, sz, real_sz = 0;
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		max_sz = phdr_ptr->p_memsz;
		offset = phdr_ptr->p_offset;
		notes_section = kmalloc(max_sz, GFP_KERNEL);
		if (!notes_section)
			return -ENOMEM;
651
		rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
652 653 654 655 656
		if (rc < 0) {
			kfree(notes_section);
			return rc;
		}
		nhdr_ptr = notes_section;
657
		while (nhdr_ptr->n_namesz != 0) {
658 659 660
			sz = sizeof(Elf32_Nhdr) +
				((nhdr_ptr->n_namesz + 3) & ~3) +
				((nhdr_ptr->n_descsz + 3) & ~3);
661 662 663 664 665
			if ((real_sz + sz) > max_sz) {
				pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
					nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
				break;
			}
666 667 668 669
			real_sz += sz;
			nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
		}
		kfree(notes_section);
670
		phdr_ptr->p_memsz = real_sz;
671 672 673
		if (real_sz == 0) {
			pr_warn("Warning: Zero PT_NOTE entries found\n");
		}
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710
	}

	return 0;
}

/**
 * get_note_number_and_size_elf32 - get the number of PT_NOTE program
 * headers and sum of real size of their ELF note segment headers and
 * data.
 *
 * @ehdr_ptr: ELF header
 * @nr_ptnote: buffer for the number of PT_NOTE program headers
 * @sz_ptnote: buffer for size of unique PT_NOTE program header
 *
 * This function is used to merge multiple PT_NOTE program headers
 * into a unique single one. The resulting unique entry will have
 * @sz_ptnote in its phdr->p_mem.
 *
 * It is assumed that program headers with PT_NOTE type pointed to by
 * @ehdr_ptr has already been updated by update_note_header_size_elf32
 * and each of PT_NOTE program headers has actual ELF note segment
 * size in its p_memsz member.
 */
static int __init get_note_number_and_size_elf32(const Elf32_Ehdr *ehdr_ptr,
						 int *nr_ptnote, u64 *sz_ptnote)
{
	int i;
	Elf32_Phdr *phdr_ptr;

	*nr_ptnote = *sz_ptnote = 0;

	phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1);
	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		*nr_ptnote += 1;
		*sz_ptnote += phdr_ptr->p_memsz;
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
	return 0;
}

/**
 * copy_notes_elf32 - copy ELF note segments in a given buffer
 *
 * @ehdr_ptr: ELF header
 * @notes_buf: buffer into which ELF note segments are copied
 *
 * This function is used to copy ELF note segment in the 1st kernel
 * into the buffer @notes_buf in the 2nd kernel. It is assumed that
 * size of the buffer @notes_buf is equal to or larger than sum of the
 * real ELF note segment headers and data.
 *
 * It is assumed that program headers with PT_NOTE type pointed to by
 * @ehdr_ptr has already been updated by update_note_header_size_elf32
 * and each of PT_NOTE program headers has actual ELF note segment
 * size in its p_memsz member.
 */
static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf)
{
	int i, rc=0;
	Elf32_Phdr *phdr_ptr;

	phdr_ptr = (Elf32_Phdr*)(ehdr_ptr + 1);

	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
		u64 offset;
		if (phdr_ptr->p_type != PT_NOTE)
			continue;
		offset = phdr_ptr->p_offset;
744 745
		rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
					   &offset);
746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774
		if (rc < 0)
			return rc;
		notes_buf += phdr_ptr->p_memsz;
	}

	return 0;
}

/* Merges all the PT_NOTE headers into one. */
static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
					   char **notes_buf, size_t *notes_sz)
{
	int i, nr_ptnote=0, rc=0;
	char *tmp;
	Elf32_Ehdr *ehdr_ptr;
	Elf32_Phdr phdr;
	u64 phdr_sz = 0, note_off;

	ehdr_ptr = (Elf32_Ehdr *)elfptr;

	rc = update_note_header_size_elf32(ehdr_ptr);
	if (rc < 0)
		return rc;

	rc = get_note_number_and_size_elf32(ehdr_ptr, &nr_ptnote, &phdr_sz);
	if (rc < 0)
		return rc;

	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
775
	*notes_buf = alloc_elfnotes_buf(*notes_sz);
776 777 778 779 780 781 782
	if (!*notes_buf)
		return -ENOMEM;

	rc = copy_notes_elf32(ehdr_ptr, *notes_buf);
	if (rc < 0)
		return rc;

783 784 785 786 787
	/* Prepare merged PT_NOTE program header. */
	phdr.p_type    = PT_NOTE;
	phdr.p_flags   = 0;
	note_off = sizeof(Elf32_Ehdr) +
			(ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf32_Phdr);
788
	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
789 790 791 792 793 794 795 796 797 798 799 800 801
	phdr.p_vaddr   = phdr.p_paddr = 0;
	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
	phdr.p_align   = 0;

	/* Add merged PT_NOTE program header*/
	tmp = elfptr + sizeof(Elf32_Ehdr);
	memcpy(tmp, &phdr, sizeof(phdr));
	tmp += sizeof(phdr);

	/* Remove unwanted PT_NOTE program headers. */
	i = (nr_ptnote - 1) * sizeof(Elf32_Phdr);
	*elfsz = *elfsz - i;
	memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf32_Ehdr)-sizeof(Elf32_Phdr)));
802 803
	memset(elfptr + *elfsz, 0, i);
	*elfsz = roundup(*elfsz, PAGE_SIZE);
804 805 806 807 808 809 810

	/* Modify e_phnum to reflect merged headers. */
	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;

	return 0;
}

811 812 813 814
/* Add memory chunks represented by program headers to vmcore list. Also update
 * the new offset fields of exported program headers. */
static int __init process_ptload_program_headers_elf64(char *elfptr,
						size_t elfsz,
815
						size_t elfnotes_sz,
816 817 818 819 820 821 822 823 824 825 826
						struct list_head *vc_list)
{
	int i;
	Elf64_Ehdr *ehdr_ptr;
	Elf64_Phdr *phdr_ptr;
	loff_t vmcore_off;
	struct vmcore *new;

	ehdr_ptr = (Elf64_Ehdr *)elfptr;
	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */

827 828
	/* Skip Elf header, program headers and Elf note segment. */
	vmcore_off = elfsz + elfnotes_sz;
829 830

	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
831 832
		u64 paddr, start, end, size;

833 834 835
		if (phdr_ptr->p_type != PT_LOAD)
			continue;

836 837 838 839 840
		paddr = phdr_ptr->p_offset;
		start = rounddown(paddr, PAGE_SIZE);
		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
		size = end - start;

841 842 843 844
		/* Add this contiguous chunk of memory to vmcore list.*/
		new = get_new_element();
		if (!new)
			return -ENOMEM;
845 846
		new->paddr = start;
		new->size = size;
847 848 849
		list_add_tail(&new->list, vc_list);

		/* Update the program header offset. */
850 851
		phdr_ptr->p_offset = vmcore_off + (paddr - start);
		vmcore_off = vmcore_off + size;
852 853 854 855
	}
	return 0;
}

856 857
static int __init process_ptload_program_headers_elf32(char *elfptr,
						size_t elfsz,
858
						size_t elfnotes_sz,
859 860 861 862 863 864 865 866 867 868 869
						struct list_head *vc_list)
{
	int i;
	Elf32_Ehdr *ehdr_ptr;
	Elf32_Phdr *phdr_ptr;
	loff_t vmcore_off;
	struct vmcore *new;

	ehdr_ptr = (Elf32_Ehdr *)elfptr;
	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */

870 871
	/* Skip Elf header, program headers and Elf note segment. */
	vmcore_off = elfsz + elfnotes_sz;
872 873

	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
874 875
		u64 paddr, start, end, size;

876 877 878
		if (phdr_ptr->p_type != PT_LOAD)
			continue;

879 880 881 882 883
		paddr = phdr_ptr->p_offset;
		start = rounddown(paddr, PAGE_SIZE);
		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
		size = end - start;

884 885 886 887
		/* Add this contiguous chunk of memory to vmcore list.*/
		new = get_new_element();
		if (!new)
			return -ENOMEM;
888 889
		new->paddr = start;
		new->size = size;
890 891 892
		list_add_tail(&new->list, vc_list);

		/* Update the program header offset */
893 894
		phdr_ptr->p_offset = vmcore_off + (paddr - start);
		vmcore_off = vmcore_off + size;
895 896 897 898
	}
	return 0;
}

899
/* Sets offset fields of vmcore elements. */
900
static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
901
					   struct list_head *vc_list)
902 903 904 905
{
	loff_t vmcore_off;
	struct vmcore *m;

906 907
	/* Skip Elf header, program headers and Elf note segment. */
	vmcore_off = elfsz + elfnotes_sz;
908 909 910 911 912 913 914

	list_for_each_entry(m, vc_list, list) {
		m->offset = vmcore_off;
		vmcore_off += m->size;
	}
}

915
static void free_elfcorebuf(void)
916
{
917 918
	free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig));
	elfcorebuf = NULL;
919 920
	vfree(elfnotes_buf);
	elfnotes_buf = NULL;
921 922
}

923 924 925 926 927 928 929 930 931
static int __init parse_crash_elf64_headers(void)
{
	int rc=0;
	Elf64_Ehdr ehdr;
	u64 addr;

	addr = elfcorehdr_addr;

	/* Read Elf header */
932
	rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr);
933 934 935 936 937 938
	if (rc < 0)
		return rc;

	/* Do some basic Verification. */
	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
		(ehdr.e_type != ET_CORE) ||
939
		!vmcore_elf64_check_arch(&ehdr) ||
940 941 942 943 944 945
		ehdr.e_ident[EI_CLASS] != ELFCLASS64 ||
		ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
		ehdr.e_version != EV_CURRENT ||
		ehdr.e_ehsize != sizeof(Elf64_Ehdr) ||
		ehdr.e_phentsize != sizeof(Elf64_Phdr) ||
		ehdr.e_phnum == 0) {
A
Andrew Morton 已提交
946
		pr_warn("Warning: Core image elf header is not sane\n");
947 948 949 950
		return -EINVAL;
	}

	/* Read in all elf headers. */
951 952 953 954 955
	elfcorebuf_sz_orig = sizeof(Elf64_Ehdr) +
				ehdr.e_phnum * sizeof(Elf64_Phdr);
	elfcorebuf_sz = elfcorebuf_sz_orig;
	elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
					      get_order(elfcorebuf_sz_orig));
956 957 958
	if (!elfcorebuf)
		return -ENOMEM;
	addr = elfcorehdr_addr;
959
	rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
960 961
	if (rc < 0)
		goto fail;
962 963

	/* Merge all PT_NOTE headers into one. */
964 965
	rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz,
				      &elfnotes_buf, &elfnotes_sz);
966 967
	if (rc)
		goto fail;
968
	rc = process_ptload_program_headers_elf64(elfcorebuf, elfcorebuf_sz,
969
						  elfnotes_sz, &vmcore_list);
970 971
	if (rc)
		goto fail;
972
	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
973
	return 0;
974 975 976
fail:
	free_elfcorebuf();
	return rc;
977 978
}

979 980 981 982 983 984 985 986 987
static int __init parse_crash_elf32_headers(void)
{
	int rc=0;
	Elf32_Ehdr ehdr;
	u64 addr;

	addr = elfcorehdr_addr;

	/* Read Elf header */
988
	rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr);
989 990 991 992 993 994 995 996 997 998 999 1000 1001
	if (rc < 0)
		return rc;

	/* Do some basic Verification. */
	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
		(ehdr.e_type != ET_CORE) ||
		!elf_check_arch(&ehdr) ||
		ehdr.e_ident[EI_CLASS] != ELFCLASS32||
		ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
		ehdr.e_version != EV_CURRENT ||
		ehdr.e_ehsize != sizeof(Elf32_Ehdr) ||
		ehdr.e_phentsize != sizeof(Elf32_Phdr) ||
		ehdr.e_phnum == 0) {
A
Andrew Morton 已提交
1002
		pr_warn("Warning: Core image elf header is not sane\n");
1003 1004 1005 1006
		return -EINVAL;
	}

	/* Read in all elf headers. */
1007 1008 1009 1010
	elfcorebuf_sz_orig = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr);
	elfcorebuf_sz = elfcorebuf_sz_orig;
	elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
					      get_order(elfcorebuf_sz_orig));
1011 1012 1013
	if (!elfcorebuf)
		return -ENOMEM;
	addr = elfcorehdr_addr;
1014
	rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
1015 1016
	if (rc < 0)
		goto fail;
1017 1018

	/* Merge all PT_NOTE headers into one. */
1019 1020
	rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz,
				      &elfnotes_buf, &elfnotes_sz);
1021 1022
	if (rc)
		goto fail;
1023
	rc = process_ptload_program_headers_elf32(elfcorebuf, elfcorebuf_sz,
1024
						  elfnotes_sz, &vmcore_list);
1025 1026
	if (rc)
		goto fail;
1027
	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
1028
	return 0;
1029 1030 1031
fail:
	free_elfcorebuf();
	return rc;
1032 1033
}

1034 1035 1036 1037 1038 1039 1040
static int __init parse_crash_elf_headers(void)
{
	unsigned char e_ident[EI_NIDENT];
	u64 addr;
	int rc=0;

	addr = elfcorehdr_addr;
1041
	rc = elfcorehdr_read(e_ident, EI_NIDENT, &addr);
1042 1043 1044
	if (rc < 0)
		return rc;
	if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
A
Andrew Morton 已提交
1045
		pr_warn("Warning: Core image elf header not found\n");
1046 1047 1048 1049 1050 1051 1052
		return -EINVAL;
	}

	if (e_ident[EI_CLASS] == ELFCLASS64) {
		rc = parse_crash_elf64_headers();
		if (rc)
			return rc;
1053 1054 1055 1056
	} else if (e_ident[EI_CLASS] == ELFCLASS32) {
		rc = parse_crash_elf32_headers();
		if (rc)
			return rc;
1057
	} else {
A
Andrew Morton 已提交
1058
		pr_warn("Warning: Core image elf header is not sane\n");
1059 1060
		return -EINVAL;
	}
1061 1062 1063 1064 1065

	/* Determine vmcore size. */
	vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
				      &vmcore_list);

1066 1067 1068 1069 1070 1071 1072 1073
	return 0;
}

/* Init function for vmcore module. */
static int __init vmcore_init(void)
{
	int rc = 0;

1074 1075 1076 1077 1078 1079 1080 1081
	/* Allow architectures to allocate ELF header in 2nd kernel */
	rc = elfcorehdr_alloc(&elfcorehdr_addr, &elfcorehdr_size);
	if (rc)
		return rc;
	/*
	 * If elfcorehdr= has been passed in cmdline or created in 2nd kernel,
	 * then capture the dump.
	 */
1082
	if (!(is_vmcore_usable()))
1083 1084 1085
		return rc;
	rc = parse_crash_elf_headers();
	if (rc) {
A
Andrew Morton 已提交
1086
		pr_warn("Kdump: vmcore not initialized\n");
1087 1088
		return rc;
	}
1089 1090
	elfcorehdr_free(elfcorehdr_addr);
	elfcorehdr_addr = ELFCORE_ADDR_ERR;
1091

1092
	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
1093 1094 1095 1096
	if (proc_vmcore)
		proc_vmcore->size = vmcore_size;
	return 0;
}
1097
fs_initcall(vmcore_init);
1098 1099 1100 1101 1102 1103 1104

/* Cleanup function for vmcore module. */
void vmcore_cleanup(void)
{
	struct list_head *pos, *next;

	if (proc_vmcore) {
1105
		proc_remove(proc_vmcore);
1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116
		proc_vmcore = NULL;
	}

	/* clear the vmcore list. */
	list_for_each_safe(pos, next, &vmcore_list) {
		struct vmcore *m;

		m = list_entry(pos, struct vmcore, list);
		list_del(&m->list);
		kfree(m);
	}
1117
	free_elfcorebuf();
1118
}