#define pr_fmt(fmt) "kexec: " fmt
#include <linux/mm.h>
#include <linux/kexec.h>
#include <linux/string.h>
#include <linux/gfp.h>
#include <linux/reboot.h>
#include <linux/numa.h>
#include <linux/ftrace.h>
#include <linux/io.h>
#include <linux/suspend.h>
#include <linux/vmalloc.h>
#include <linux/efi.h>
#include <linux/cc_platform.h>
#include <asm/init.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/io_apic.h>
#include <asm/debugreg.h>
#include <asm/kexec-bzimage64.h>
#include <asm/setup.h>
#include <asm/set_memory.h>
#include <asm/cpu.h>
#ifdef CONFIG_ACPI
struct init_pgtable_data {
struct x86_mapping_info *info;
pgd_t *level4p;
};
static int mem_region_callback(struct resource *res, void *arg)
{
struct init_pgtable_data *data = arg;
unsigned long mstart, mend;
mstart = res->start;
mend = mstart + resource_size(res) - 1;
return kernel_ident_mapping_init(data->info, data->level4p, mstart, mend);
}
static int
map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p)
{
struct init_pgtable_data data;
unsigned long flags;
int ret;
data.info = info;
data.level4p = level4p;
flags = IORESOURCE_MEM | IORESOURCE_BUSY;
ret = walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1,
&data, mem_region_callback);
if (ret && ret != -EINVAL)
return ret;
ret = walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1,
&data, mem_region_callback);
if (ret && ret != -EINVAL)
return ret;
return 0;
}
#else
static int map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) { return 0; }
#endif
#ifdef CONFIG_KEXEC_FILE
const struct kexec_file_ops * const kexec_file_loaders[] = {
&kexec_bzImage64_ops,
NULL
};
#endif
static int
map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
{
#ifdef CONFIG_EFI
unsigned long mstart, mend;
if (!efi_enabled(EFI_BOOT))
return 0;
mstart = (boot_params.efi_info.efi_systab |
((u64)boot_params.efi_info.efi_systab_hi<<32));
if (efi_enabled(EFI_64BIT))
mend = mstart + sizeof(efi_system_table_64_t);
else
mend = mstart + sizeof(efi_system_table_32_t);
if (!mstart)
return 0;
return kernel_ident_mapping_init(info, level4p, mstart, mend);
#endif
return 0;
}
static void free_transition_pgtable(struct kimage *image)
{
free_page((unsigned long)image->arch.p4d);
image->arch.p4d = NULL;
free_page((unsigned long)image->arch.pud);
image->arch.pud = NULL;
free_page((unsigned long)image->arch.pmd);
image->arch.pmd = NULL;
free_page((unsigned long)image->arch.pte);
image->arch.pte = NULL;
}
static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
{
pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
unsigned long vaddr, paddr;
int result = -ENOMEM;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
vaddr = (unsigned long)relocate_kernel;
paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
pgd += pgd_index(vaddr);
if (!pgd_present(*pgd)) {
p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL);
if (!p4d)
goto err;
image->arch.p4d = p4d;
set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
}
p4d = p4d_offset(pgd, vaddr);
if (!p4d_present(*p4d)) {
pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
if (!pud)
goto err;
image->arch.pud = pud;
set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
}
pud = pud_offset(p4d, vaddr);
if (!pud_present(*pud)) {
pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
if (!pmd)
goto err;
image->arch.pmd = pmd;
set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
}
pmd = pmd_offset(pud, vaddr);
if (!pmd_present(*pmd)) {
pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
if (!pte)
goto err;
image->arch.pte = pte;
set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
}
pte = pte_offset_kernel(pmd, vaddr);
if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
prot = PAGE_KERNEL_EXEC;
set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
return 0;
err:
return result;
}
static void *alloc_pgt_page(void *data)
{
struct kimage *image = (struct kimage *)data;
struct page *page;
void *p = NULL;
page = kimage_alloc_control_pages(image, 0);
if (page) {
p = page_address(page);
clear_page(p);
}
return p;
}
static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
{
struct x86_mapping_info info = {
.alloc_pgt_page = alloc_pgt_page,
.context = image,
.page_flag = __PAGE_KERNEL_LARGE_EXEC,
.kernpg_flag = _KERNPG_TABLE_NOENC,
};
unsigned long mstart, mend;
pgd_t *level4p;
int result;
int i;
level4p = (pgd_t *)__va(start_pgtable);
clear_page(level4p);
if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
info.page_flag |= _PAGE_ENC;
info.kernpg_flag |= _PAGE_ENC;
}
if (direct_gbpages)
info.direct_gbpages = true;
for (i = 0; i < nr_pfn_mapped; i++) {
mstart = pfn_mapped[i].start << PAGE_SHIFT;
mend = pfn_mapped[i].end << PAGE_SHIFT;
result = kernel_ident_mapping_init(&info,
level4p, mstart, mend);
if (result)
return result;
}
for (i = 0; i < image->nr_segments; i++) {
mstart = image->segment[i].mem;
mend = mstart + image->segment[i].memsz;
result = kernel_ident_mapping_init(&info,
level4p, mstart, mend);
if (result)
return result;
}
result = map_efi_systab(&info, level4p);
if (result)
return result;
result = map_acpi_tables(&info, level4p);
if (result)
return result;
return init_transition_pgtable(image, level4p);
}
static void load_segments(void)
{
__asm__ __volatile__ (
"\tmovl %0,%%ds\n"
"\tmovl %0,%%es\n"
"\tmovl %0,%%ss\n"
"\tmovl %0,%%fs\n"
"\tmovl %0,%%gs\n"
: : "a" (__KERNEL_DS) : "memory"
);
}
int machine_kexec_prepare(struct kimage *image)
{
unsigned long start_pgtable;
int result;
start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT;
result = init_pgtable(image, start_pgtable);
if (result)
return result;
return 0;
}
void machine_kexec_cleanup(struct kimage *image)
{
free_transition_pgtable(image);
}
void machine_kexec(struct kimage *image)
{
unsigned long page_list[PAGES_NR];
void *control_page;
int save_ftrace_enabled;
#ifdef CONFIG_KEXEC_JUMP
if (image->preserve_context)
save_processor_state();
#endif
save_ftrace_enabled = __ftrace_enabled_save();
local_irq_disable();
hw_breakpoint_disable();
cet_disable();
if (image->preserve_context) {
#ifdef CONFIG_X86_IO_APIC
clear_IO_APIC();
restore_boot_irq_mode();
#endif
}
control_page = page_address(image->control_code_page) + PAGE_SIZE;
__memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);
page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page);
page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
page_list[PA_TABLE_PAGE] =
(unsigned long)__pa(page_address(image->control_code_page));
if (image->type == KEXEC_TYPE_DEFAULT)
page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
<< PAGE_SHIFT);
load_segments();
native_idt_invalidate();
native_gdt_invalidate();
image->start = relocate_kernel((unsigned long)image->head,
(unsigned long)page_list,
image->start,
image->preserve_context,
cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT));
#ifdef CONFIG_KEXEC_JUMP
if (image->preserve_context)
restore_processor_state();
#endif
__ftrace_enabled_restore(save_ftrace_enabled);
}
#ifdef CONFIG_KEXEC_FILE
int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
Elf_Shdr *section, const Elf_Shdr *relsec,
const Elf_Shdr *symtabsec)
{
unsigned int i;
Elf64_Rela *rel;
Elf64_Sym *sym;
void *location;
unsigned long address, sec_base, value;
const char *strtab, *name, *shstrtab;
const Elf_Shdr *sechdrs;
sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
strtab = (char *)pi->ehdr + sechdrs[symtabsec->sh_link].sh_offset;
shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset;
rel = (void *)pi->ehdr + relsec->sh_offset;
pr_debug("Applying relocate section %s to %u\n",
shstrtab + relsec->sh_name, relsec->sh_info);
for (i = 0; i < relsec->sh_size / sizeof(*rel); i++) {
location = pi->purgatory_buf;
location += section->sh_offset;
location += rel[i].r_offset;
address = section->sh_addr + rel[i].r_offset;
sym = (void *)pi->ehdr + symtabsec->sh_offset;
sym += ELF64_R_SYM(rel[i].r_info);
if (sym->st_name)
name = strtab + sym->st_name;
else
name = shstrtab + sechdrs[sym->st_shndx].sh_name;
pr_debug("Symbol: %s info: %02x shndx: %02x value=%llx size: %llx\n",
name, sym->st_info, sym->st_shndx, sym->st_value,
sym->st_size);
if (sym->st_shndx == SHN_UNDEF) {
pr_err("Undefined symbol: %s\n", name);
return -ENOEXEC;
}
if (sym->st_shndx == SHN_COMMON) {
pr_err("symbol '%s' in common section\n", name);
return -ENOEXEC;
}
if (sym->st_shndx == SHN_ABS)
sec_base = 0;
else if (sym->st_shndx >= pi->ehdr->e_shnum) {
pr_err("Invalid section %d for symbol %s\n",
sym->st_shndx, name);
return -ENOEXEC;
} else
sec_base = pi->sechdrs[sym->st_shndx].sh_addr;
value = sym->st_value;
value += sec_base;
value += rel[i].r_addend;
switch (ELF64_R_TYPE(rel[i].r_info)) {
case R_X86_64_NONE:
break;
case R_X86_64_64:
*(u64 *)location = value;
break;
case R_X86_64_32:
*(u32 *)location = value;
if (value != *(u32 *)location)
goto overflow;
break;
case R_X86_64_32S:
*(s32 *)location = value;
if ((s64)value != *(s32 *)location)
goto overflow;
break;
case R_X86_64_PC32:
case R_X86_64_PLT32:
value -= (u64)address;
*(u32 *)location = value;
break;
default:
pr_err("Unknown rela relocation: %llu\n",
ELF64_R_TYPE(rel[i].r_info));
return -ENOEXEC;
}
}
return 0;
overflow:
pr_err("Overflow in relocation type %d value 0x%lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), value);
return -ENOEXEC;
}
int arch_kimage_file_post_load_cleanup(struct kimage *image)
{
vfree(image->elf_headers);
image->elf_headers = NULL;
image->elf_headers_sz = 0;
return kexec_image_post_load_cleanup_default(image);
}
#endif /* CONFIG_KEXEC_FILE */
static int
kexec_mark_range(unsigned long start, unsigned long end, bool protect)
{
struct page *page;
unsigned int nr_pages;
if (!end || start > end)
return 0;
page = pfn_to_page(start >> PAGE_SHIFT);
nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
if (protect)
return set_pages_ro(page, nr_pages);
else
return set_pages_rw(page, nr_pages);
}
static void kexec_mark_crashkres(bool protect)
{
unsigned long control;
kexec_mark_range(crashk_low_res.start, crashk_low_res.end, protect);
control = PFN_PHYS(page_to_pfn(kexec_crash_image->control_code_page));
kexec_mark_range(crashk_res.start, control + PAGE_SIZE - 1, protect);
control += KEXEC_CONTROL_PAGE_SIZE;
kexec_mark_range(control, crashk_res.end, protect);
}
void arch_kexec_protect_crashkres(void)
{
kexec_mark_crashkres(true);
}
void arch_kexec_unprotect_crashkres(void)
{
kexec_mark_crashkres(false);
}
int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
{
if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
return 0;
return set_memory_decrypted((unsigned long)vaddr, pages);
}
void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
{
if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
return;
set_memory_encrypted((unsigned long)vaddr, pages);
}