diff options
Diffstat (limited to 'arch/x86/kernel/machine_kexec_64.c')
| -rw-r--r-- | arch/x86/kernel/machine_kexec_64.c | 201 |
1 files changed, 154 insertions, 47 deletions
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index b180d8e497c3..697fb99406e6 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -28,6 +28,7 @@ #include <asm/setup.h> #include <asm/set_memory.h> #include <asm/cpu.h> +#include <asm/efi.h> #ifdef CONFIG_ACPI /* @@ -75,6 +76,19 @@ map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) static int map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) { return 0; } #endif +static int map_mmio_serial(struct x86_mapping_info *info, pgd_t *level4p) +{ + unsigned long mstart, mend; + + if (!kexec_debug_8250_mmio32) + return 0; + + mstart = kexec_debug_8250_mmio32 & PAGE_MASK; + mend = (kexec_debug_8250_mmio32 + PAGE_SIZE + 23) & PAGE_MASK; + pr_info("Map PCI serial at %lx - %lx\n", mstart, mend); + return kernel_ident_mapping_init(info, level4p, mstart, mend); +} + #ifdef CONFIG_KEXEC_FILE const struct kexec_file_ops * const kexec_file_loaders[] = { &kexec_bzImage64_ops, @@ -87,6 +101,8 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p) { #ifdef CONFIG_EFI unsigned long mstart, mend; + void *kaddr; + int ret; if (!efi_enabled(EFI_BOOT)) return 0; @@ -102,6 +118,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p) if (!mstart) return 0; + ret = kernel_ident_mapping_init(info, level4p, mstart, mend); + if (ret) + return ret; + + kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB); + if (!kaddr) { + pr_err("Could not map UEFI system table\n"); + return -ENOMEM; + } + + mstart = efi_config_table; + + if (efi_enabled(EFI_64BIT)) { + efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr; + + mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables; + } else { + efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr; + + mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables; + } + + memunmap(kaddr); + return kernel_ident_mapping_init(info, level4p, mstart, mend); #endif return 0; @@ -119,7 +159,8 @@ static void free_transition_pgtable(struct kimage *image) image->arch.pte = NULL; } -static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) +static int init_transition_pgtable(struct kimage *image, pgd_t *pgd, + unsigned long control_page) { pgprot_t prot = PAGE_KERNEL_EXEC_NOENC; unsigned long vaddr, paddr; @@ -129,8 +170,13 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) pmd_t *pmd; pte_t *pte; - vaddr = (unsigned long)relocate_kernel; - paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE); + /* + * For the transition to the identity mapped page tables, the control + * code page also needs to be mapped at the virtual address it starts + * off running from. + */ + vaddr = (unsigned long)__va(control_page); + paddr = control_page; pgd += pgd_index(vaddr); if (!pgd_present(*pgd)) { p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); @@ -189,7 +235,7 @@ static void *alloc_pgt_page(void *data) return p; } -static int init_pgtable(struct kimage *image, unsigned long start_pgtable) +static int init_pgtable(struct kimage *image, unsigned long control_page) { struct x86_mapping_info info = { .alloc_pgt_page = alloc_pgt_page, @@ -198,12 +244,12 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) .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); + image->arch.pgd = alloc_pgt_page(image); + if (!image->arch.pgd) + return -ENOMEM; if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { info.page_flag |= _PAGE_ENC; @@ -217,8 +263,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = pfn_mapped[i].start << PAGE_SHIFT; mend = pfn_mapped[i].end << PAGE_SHIFT; - result = kernel_ident_mapping_init(&info, - level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, image->arch.pgd, + mstart, mend); if (result) return result; } @@ -233,8 +279,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; - result = kernel_ident_mapping_init(&info, - level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, image->arch.pgd, + mstart, mend); if (result) return result; @@ -244,15 +290,23 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) * Prepare EFI systab and ACPI tables for kexec kernel since they are * not covered by pfn_mapped. */ - result = map_efi_systab(&info, level4p); + result = map_efi_systab(&info, image->arch.pgd); if (result) return result; - result = map_acpi_tables(&info, level4p); + result = map_acpi_tables(&info, image->arch.pgd); if (result) return result; - return init_transition_pgtable(image, level4p); + result = map_mmio_serial(&info, image->arch.pgd); + if (result) + return result; + + /* + * This must be last because the intermediate page table pages it + * allocates will not be control pages and may overlap the image. + */ + return init_transition_pgtable(image, image->arch.pgd, control_page); } static void load_segments(void) @@ -267,24 +321,58 @@ static void load_segments(void) ); } +static void prepare_debug_idt(unsigned long control_page, unsigned long vec_ofs) +{ + gate_desc idtentry = { 0 }; + int i; + + idtentry.bits.p = 1; + idtentry.bits.type = GATE_TRAP; + idtentry.segment = __KERNEL_CS; + idtentry.offset_low = (control_page & 0xFFFF) + vec_ofs; + idtentry.offset_middle = (control_page >> 16) & 0xFFFF; + idtentry.offset_high = control_page >> 32; + + for (i = 0; i < 16; i++) { + kexec_debug_idt[i] = idtentry; + idtentry.offset_low += KEXEC_DEBUG_EXC_HANDLER_SIZE; + } +} + int machine_kexec_prepare(struct kimage *image) { - unsigned long start_pgtable; + void *control_page = page_address(image->control_code_page); + unsigned long reloc_start = (unsigned long)__relocate_kernel_start; + unsigned long reloc_end = (unsigned long)__relocate_kernel_end; int result; - /* Calculate the offsets */ - start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT; - /* Setup the identity mapped 64bit page table */ - result = init_pgtable(image, start_pgtable); + result = init_pgtable(image, __pa(control_page)); if (result) return result; + kexec_va_control_page = (unsigned long)control_page; + kexec_pa_table_page = (unsigned long)__pa(image->arch.pgd); + + if (image->type == KEXEC_TYPE_DEFAULT) + kexec_pa_swap_page = page_to_pfn(image->swap_page) << PAGE_SHIFT; + + prepare_debug_idt((unsigned long)__pa(control_page), + (unsigned long)kexec_debug_exc_vectors - reloc_start); + + __memcpy(control_page, __relocate_kernel_start, reloc_end - reloc_start); + + set_memory_rox((unsigned long)control_page, 1); return 0; } void machine_kexec_cleanup(struct kimage *image) { + void *control_page = page_address(image->control_code_page); + + set_memory_nx((unsigned long)control_page, 1); + set_memory_rw((unsigned long)control_page, 1); + free_transition_pgtable(image); } @@ -292,11 +380,19 @@ void machine_kexec_cleanup(struct kimage *image) * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -void machine_kexec(struct kimage *image) +void __nocfi machine_kexec(struct kimage *image) { - unsigned long page_list[PAGES_NR]; - void *control_page; + unsigned long reloc_start = (unsigned long)__relocate_kernel_start; + relocate_kernel_fn *relocate_kernel_ptr; + unsigned int host_mem_enc_active; int save_ftrace_enabled; + void *control_page; + + /* + * This must be done before load_segments() since if call depth tracking + * is used then GS must be valid to make any function calls. + */ + host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -323,17 +419,13 @@ void machine_kexec(struct kimage *image) #endif } - control_page = page_address(image->control_code_page) + PAGE_SIZE; - __memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE); + control_page = page_address(image->control_code_page); - 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); + /* + * Allow for the possibility that relocate_kernel might not be at + * the very start of the page. + */ + relocate_kernel_ptr = control_page + (unsigned long)relocate_kernel - reloc_start; /* * The segment registers are funny things, they have both a @@ -342,23 +434,17 @@ void machine_kexec(struct kimage *image) * with from a table in memory. At no other time is the * descriptor table in memory accessed. * - * I take advantage of this here by force loading the - * segments, before I zap the gdt with an invalid value. + * Take advantage of this here by force loading the segments, + * before the GDT is zapped with an invalid value. */ load_segments(); - /* - * The gdt & idt are now invalid. - * If you want to load them you must set up your own idt & gdt. - */ - native_idt_invalidate(); - native_gdt_invalidate(); /* now call it */ - 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)); + image->start = relocate_kernel_ptr((unsigned long)image->head, + virt_to_phys(control_page), + image->start, + image->preserve_context, + host_mem_enc_active); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -539,19 +625,40 @@ static void kexec_mark_crashkres(bool protect) /* Don't touch the control code page used in crash_kexec().*/ control = PFN_PHYS(page_to_pfn(kexec_crash_image->control_code_page)); - /* Control code page is located in the 2nd page. */ - kexec_mark_range(crashk_res.start, control + PAGE_SIZE - 1, protect); + kexec_mark_range(crashk_res.start, control - 1, protect); control += KEXEC_CONTROL_PAGE_SIZE; kexec_mark_range(control, crashk_res.end, protect); } +/* make the memory storing dm crypt keys in/accessible */ +static void kexec_mark_dm_crypt_keys(bool protect) +{ + unsigned long start_paddr, end_paddr; + unsigned int nr_pages; + + if (kexec_crash_image->dm_crypt_keys_addr) { + start_paddr = kexec_crash_image->dm_crypt_keys_addr; + end_paddr = start_paddr + kexec_crash_image->dm_crypt_keys_sz - 1; + nr_pages = (PAGE_ALIGN(end_paddr) - PAGE_ALIGN_DOWN(start_paddr))/PAGE_SIZE; + if (protect) + set_memory_np((unsigned long)phys_to_virt(start_paddr), nr_pages); + else + __set_memory_prot( + (unsigned long)phys_to_virt(start_paddr), + nr_pages, + __pgprot(_PAGE_PRESENT | _PAGE_NX | _PAGE_RW)); + } +} + void arch_kexec_protect_crashkres(void) { kexec_mark_crashkres(true); + kexec_mark_dm_crypt_keys(true); } void arch_kexec_unprotect_crashkres(void) { + kexec_mark_dm_crypt_keys(false); kexec_mark_crashkres(false); } #endif |