From: Borislav Petkov <[email protected]> Map EFI runtime services 1:1 into the trampoline pgd so that all those functions can be used in a kexec kernel. As we all know, the braindead design of SetVirtualAddressMap() doesn't allow a subsequent call to this function to reestablish virtual mappings, leading us to do all kinds of crazy dances in the kernel.
64-bit only for now. Signed-off-by: Borislav Petkov <[email protected]> --- arch/x86/include/asm/efi.h | 2 + arch/x86/platform/efi/efi.c | 84 +++++++++++++++++++++++++++---------- arch/x86/platform/efi/efi_stub_64.S | 39 +++++++++++++++++ 3 files changed, 102 insertions(+), 23 deletions(-) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 60c89f30c727..3ed4b8c51548 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -39,6 +39,8 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #else /* !CONFIG_X86_32 */ +extern pgd_t *efi_pgt; + #define EFI_LOADER_SIGNATURE "EL64" extern u64 efi_call0(void *fp); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 4b70be21fe0a..9e45eac3c33a 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -649,15 +649,24 @@ static int __init efi_runtime_init(void) pr_err("Could not map the runtime service table!\n"); return -ENOMEM; } - /* - * We will only need *early* access to the following - * two EFI runtime services before set_virtual_address_map - * is invoked. - */ - efi_phys.get_time = (efi_get_time_t *)runtime->get_time; - efi_phys.set_virtual_address_map = - (efi_set_virtual_address_map_t *) - runtime->set_virtual_address_map; + +#define efi_phys_assign(f) \ + efi_phys.f = (efi_ ##f## _t *)runtime->f + + efi_phys_assign(get_time); + efi_phys_assign(set_time); + efi_phys_assign(get_wakeup_time); + efi_phys_assign(set_wakeup_time); + efi_phys_assign(get_variable); + efi_phys_assign(get_next_variable); + efi_phys_assign(set_variable); + efi_phys_assign(get_next_high_mono_count); + efi_phys_assign(reset_system); + efi_phys_assign(set_virtual_address_map); + efi_phys_assign(query_variable_info); + efi_phys_assign(update_capsule); + efi_phys_assign(query_capsule_caps); + /* * Make efi_get_time can be called before entering * virtual mode. @@ -845,9 +854,10 @@ void efi_memory_uc(u64 addr, unsigned long size) */ void __init efi_enter_virtual_mode(void) { + pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); efi_memory_desc_t *md, *prev_md = NULL; efi_status_t status; - unsigned long size; + unsigned long size, page_flags; u64 end, systab, start_pfn, end_pfn; void *p, *va, *new_memmap = NULL; int count = 0; @@ -895,7 +905,8 @@ void __init efi_enter_virtual_mode(void) md = p; if (!(md->attribute & EFI_MEMORY_RUNTIME) && md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) + md->type != EFI_BOOT_SERVICES_DATA && + md->type != EFI_CONVENTIONAL_MEMORY) continue; size = md->num_pages << EFI_PAGE_SHIFT; @@ -920,11 +931,26 @@ void __init efi_enter_virtual_mode(void) continue; } + page_flags = 0; + + if (md->type == EFI_RUNTIME_SERVICES_DATA || + md->type == EFI_BOOT_SERVICES_DATA) + page_flags = _PAGE_NX; + + if (!(md->attribute & EFI_MEMORY_WB)) + page_flags |= _PAGE_PCD; + + kernel_map_pages_in_pgd(pgd, md->phys_addr, + md->num_pages, page_flags); + systab = (u64) (unsigned long) efi_phys.systab; if (md->phys_addr <= systab && systab < end) { systab += md->virt_addr - md->phys_addr; efi.systab = (efi_system_table_t *) (unsigned long) systab; } + + md->virt_addr = md->phys_addr; + new_memmap = krealloc(new_memmap, (count + 1) * memmap.desc_size, GFP_KERNEL); @@ -935,6 +961,8 @@ void __init efi_enter_virtual_mode(void) BUG_ON(!efi.systab); + efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd; + status = phys_efi_set_virtual_address_map( memmap.desc_size * count, memmap.desc_size, @@ -947,6 +975,9 @@ void __init efi_enter_virtual_mode(void) panic("EFI call to SetVirtualAddressMap() failed!"); } + efi.systab->runtime = kzalloc(sizeof(efi_runtime_services_t), GFP_KERNEL); + BUG_ON(!efi.systab->runtime); + /* * Now that EFI is in virtual mode, update the function * pointers in the runtime service table to the new virtual addresses. @@ -954,19 +985,26 @@ void __init efi_enter_virtual_mode(void) * Call EFI services through wrapper functions. */ efi.runtime_version = efi_systab.hdr.revision; - efi.get_time = virt_efi_get_time; - efi.set_time = virt_efi_set_time; - efi.get_wakeup_time = virt_efi_get_wakeup_time; - efi.set_wakeup_time = virt_efi_set_wakeup_time; - efi.get_variable = virt_efi_get_variable; - efi.get_next_variable = virt_efi_get_next_variable; - efi.set_variable = virt_efi_set_variable; - efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count; - efi.reset_system = virt_efi_reset_system; + + +#define efi_assign(efi, f) \ + efi.f = virt_efi_##f; \ + efi.systab->runtime->f = (unsigned long)efi_phys.f + + efi_assign(efi, get_time); + efi_assign(efi, set_time); + efi_assign(efi, get_wakeup_time); + efi_assign(efi, set_wakeup_time); + efi_assign(efi, get_variable); + efi_assign(efi, get_next_variable); + efi_assign(efi, set_variable); + efi_assign(efi, get_next_high_mono_count); + efi_assign(efi, reset_system); efi.set_virtual_address_map = NULL; - efi.query_variable_info = virt_efi_query_variable_info; - efi.update_capsule = virt_efi_update_capsule; - efi.query_capsule_caps = virt_efi_query_capsule_caps; + efi_assign(efi, query_variable_info); + efi_assign(efi, update_capsule); + efi_assign(efi, query_capsule_caps); + if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 4c07ccab8146..eec8d6d02c17 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -34,10 +34,34 @@ mov %rsi, %cr0; \ mov (%rsp), %rsp +/* happily stolen from gcc, see __flush_tlb_global() */ +#define FLUSH_TLB_ALL \ + movq %cr4, %r14; \ + movq %r14, %r13; \ + and $0x7f, %r13b; \ + movq %r13, %cr4; \ + movq %r14, %cr4 + +/* + * %r15 is a non-volatile register and is preserved by UEFI so use + * it for stashing previous PGD in there. + */ +#define SWITCH_PGT \ + movq %cr3, %r15; \ + movq efi_pgt, %rax; \ + movq %rax, %cr3; \ + FLUSH_TLB_ALL + +#define RESTORE_PGT \ + movq %r15, %cr3; \ + FLUSH_TLB_ALL + ENTRY(efi_call0) SAVE_XMM subq $32, %rsp + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -47,7 +71,9 @@ ENTRY(efi_call1) SAVE_XMM subq $32, %rsp mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -57,7 +83,9 @@ ENTRY(efi_call2) SAVE_XMM subq $32, %rsp mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -68,7 +96,9 @@ ENTRY(efi_call3) subq $32, %rsp mov %rcx, %r8 mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -80,7 +110,9 @@ ENTRY(efi_call4) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $32, %rsp RESTORE_XMM ret @@ -93,7 +125,9 @@ ENTRY(efi_call5) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $48, %rsp RESTORE_XMM ret @@ -109,8 +143,13 @@ ENTRY(efi_call6) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx + SWITCH_PGT call *%rdi + RESTORE_PGT addq $48, %rsp RESTORE_XMM ret ENDPROC(efi_call6) + +GLOBAL(efi_pgt) + .quad 0 -- 1.8.2.135.g7b592fa -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
