/* Gather all the required information to prepare elf headers for ram regions */
static void fill_up_crash_elf_data(struct crash_elf_data *ced,
struct kimage *image)
{
unsigned int nr_ranges = 0;
ced->image = image;
walk_system_ram_res(0, -1, &nr_ranges,
get_nr_ram_ranges_callback);
ced->max_nr_ranges = nr_ranges;
/*
* We don't create ELF headers for GART aperture as an attempt
* to dump this memory in second kernel leads to hang/crash.
* If gart aperture is present, one needs to exclude that region
* and that could lead to need of extra phdr.
*/
walk_iomem_res("GART", IORESOURCE_MEM, 0, -1,
ced, get_gart_ranges_callback);
/*
* If we have gart region, excluding that could potentially split
* a memory range, resulting in extra header. Account for that.
*/
if (ced->gart_end)
ced->max_nr_ranges++;
/* Exclusion of crash region could split memory ranges */
ced->max_nr_ranges++;
/* If crashk_low_res is not 0, another range split possible */
if (crashk_low_res.end != 0)
ced->max_nr_ranges++;
}
int crash_load_segments(struct kimage *image)
{
unsigned long src_start, src_sz, elf_sz;
void *elf_addr;
int ret;
/*
* Determine and load a segment for backup area. First 640K RAM
* region is backup source
*/
ret = walk_system_ram_res(KEXEC_BACKUP_SRC_START, KEXEC_BACKUP_SRC_END,
image, determine_backup_region);
/* Zero or postive return values are ok */
if (ret < 0)
return ret;
src_start = image->arch.backup_src_start;
src_sz = image->arch.backup_src_sz;
/* Add backup segment. */
if (src_sz) {
/*
* Ideally there is no source for backup segment. This is
* copied in purgatory after crash. Just add a zero filled
* segment for now to make sure checksum logic works fine.
*/
ret = kexec_add_buffer(image, (char *)&crash_zero_bytes,
sizeof(crash_zero_bytes), src_sz,
PAGE_SIZE, 0, -1, 0,
&image->arch.backup_load_addr);
if (ret)
return ret;
pr_debug("Loaded backup region at 0x%lx backup_start=0x%lx memsz=0x%lx\n",
image->arch.backup_load_addr, src_start, src_sz);
}
/* Prepare elf headers and add a segment */
ret = prepare_elf_headers(image, &elf_addr, &elf_sz);
if (ret)
return ret;
image->arch.elf_headers = elf_addr;
image->arch.elf_headers_sz = elf_sz;
ret = kexec_add_buffer(image, (char *)elf_addr, elf_sz, elf_sz,
ELF_CORE_HEADER_ALIGN, 0, -1, 0,
&image->arch.elf_load_addr);
if (ret) {
vfree((void *)image->arch.elf_headers);
return ret;
}
pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
image->arch.elf_load_addr, elf_sz, elf_sz);
return ret;
}
static int prepare_elf64_headers(struct crash_elf_data *ced,
void **addr, unsigned long *sz)
{
Elf64_Ehdr *ehdr;
Elf64_Phdr *phdr;
unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
unsigned char *buf, *bufp;
unsigned int cpu;
unsigned long long notes_addr;
int ret;
/* extra phdr for vmcoreinfo elf note */
nr_phdr = nr_cpus + 1;
nr_phdr += ced->max_nr_ranges;
/*
* kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
* area on x86_64 (ffffffff80000000 - ffffffffa0000000).
* I think this is required by tools like gdb. So same physical
* memory will be mapped in two elf headers. One will contain kernel
* text virtual addresses and other will have __va(physical) addresses.
*/
nr_phdr++;
elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
buf = vzalloc(elf_sz);
if (!buf)
return -ENOMEM;
bufp = buf;
ehdr = (Elf64_Ehdr *)bufp;
bufp += sizeof(Elf64_Ehdr);
memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
ehdr->e_ident[EI_CLASS] = ELFCLASS64;
ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
ehdr->e_ident[EI_VERSION] = EV_CURRENT;
ehdr->e_ident[EI_OSABI] = ELF_OSABI;
memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
ehdr->e_type = ET_CORE;
ehdr->e_machine = ELF_ARCH;
ehdr->e_version = EV_CURRENT;
ehdr->e_phoff = sizeof(Elf64_Ehdr);
ehdr->e_ehsize = sizeof(Elf64_Ehdr);
ehdr->e_phentsize = sizeof(Elf64_Phdr);
/* Prepare one phdr of type PT_NOTE for each present cpu */
for_each_present_cpu(cpu) {
phdr = (Elf64_Phdr *)bufp;
bufp += sizeof(Elf64_Phdr);
phdr->p_type = PT_NOTE;
notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
phdr->p_offset = phdr->p_paddr = notes_addr;
phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
(ehdr->e_phnum)++;
}
/* Prepare one PT_NOTE header for vmcoreinfo */
phdr = (Elf64_Phdr *)bufp;
bufp += sizeof(Elf64_Phdr);
phdr->p_type = PT_NOTE;
phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
(ehdr->e_phnum)++;
#ifdef CONFIG_X86_64
/* Prepare PT_LOAD type program header for kernel text region */
phdr = (Elf64_Phdr *)bufp;
bufp += sizeof(Elf64_Phdr);
phdr->p_type = PT_LOAD;
phdr->p_flags = PF_R|PF_W|PF_X;
phdr->p_vaddr = (Elf64_Addr)_text;
phdr->p_filesz = phdr->p_memsz = _end - _text;
phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
(ehdr->e_phnum)++;
#endif
/* Prepare PT_LOAD headers for system ram chunks. */
ced->ehdr = ehdr;
ced->bufp = bufp;
ret = walk_system_ram_res(0, -1, ced,
prepare_elf64_ram_headers_callback);
if (ret < 0)
return ret;
*addr = buf;
*sz = elf_sz;
return 0;
}
/*
* Helper function for placing a buffer in a kexec segment. This assumes
* that kexec_mutex is held.
*/
int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
unsigned long memsz, unsigned long buf_align,
unsigned long buf_min, unsigned long buf_max,
bool top_down, unsigned long *load_addr)
{
struct kexec_segment *ksegment;
struct kexec_buf buf, *kbuf;
int ret;
/* Currently adding segment this way is allowed only in file mode */
if (!image->file_mode)
return -EINVAL;
if (image->nr_segments >= KEXEC_SEGMENT_MAX)
return -EINVAL;
/*
* Make sure we are not trying to add buffer after allocating
* control pages. All segments need to be placed first before
* any control pages are allocated. As control page allocation
* logic goes through list of segments to make sure there are
* no destination overlaps.
*/
if (!list_empty(&image->control_pages)) {
WARN_ON(1);
return -EINVAL;
}
memset(&buf, 0, sizeof(struct kexec_buf));
kbuf = &buf;
kbuf->image = image;
kbuf->buffer = buffer;
kbuf->bufsz = bufsz;
kbuf->memsz = ALIGN(memsz, PAGE_SIZE);
kbuf->buf_align = max(buf_align, PAGE_SIZE);
kbuf->buf_min = buf_min;
kbuf->buf_max = buf_max;
kbuf->top_down = top_down;
/* Walk the RAM ranges and allocate a suitable range for the buffer */
if (image->type == KEXEC_TYPE_CRASH)
ret = walk_iomem_res_desc(crashk_res.desc,
IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
crashk_res.start, crashk_res.end, kbuf,
locate_mem_hole_callback);
else
ret = walk_system_ram_res(0, -1, kbuf,
locate_mem_hole_callback);
if (ret != 1) {
/* A suitable memory range could not be found for buffer */
return -EADDRNOTAVAIL;
}
/* Found a suitable memory range */
ksegment = &image->segment[image->nr_segments];
ksegment->kbuf = kbuf->buffer;
ksegment->bufsz = kbuf->bufsz;
ksegment->mem = kbuf->mem;
ksegment->memsz = kbuf->memsz;
image->nr_segments++;
*load_addr = ksegment->mem;
return 0;
}
