From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754878AbbBTNsC (ORCPT ); Fri, 20 Feb 2015 08:48:02 -0500 Received: from mail-we0-f181.google.com ([74.125.82.181]:44385 "EHLO mail-we0-f181.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754246AbbBTNr6 (ORCPT ); Fri, 20 Feb 2015 08:47:58 -0500 Date: Fri, 20 Feb 2015 14:47:52 +0100 From: Ingo Molnar To: Linus Torvalds Cc: linux-kernel@vger.kernel.org, Borislav Petkov , Thomas Gleixner , "H. Peter Anvin" , Peter Zijlstra , Andrew Morton Subject: [GIT PULL] x86 fixes Message-ID: <20150220134752.GA31370@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Linus, Please pull the latest x86-urgent-for-linus git tree from: git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus # HEAD: 570e1aa84c376ff39809442f09c7606ddf62cfd1 x86/mm/ASLR: Avoid PAGE_SIZE redefinition for UML subarch This tree contains: - EFI fixes - a boot printout fix - ASLR/kASLR fixes - intel microcode driver fixes - other misc fixes Most of the linecount comes from an EFI revert. out-of-topic modifications in x86-urgent-for-linus: ----------------------------------------------------- drivers/firmware/efi/libstub/efi-stub-helper.c# 43a9f69692b2: Revert "efi/libstub: Call ge fs/binfmt_elf.c # 4e7c22d447bb: x86, mm/ASLR: Fix stack rand Thanks, Ingo ------------------> Alexander Kuleshov (1): Documentation/x86: Fix path in zero-page.txt Dave Hansen (1): x86/mm/init: Fix incorrect page size in init_memory_mapping() printks Hector Marco-Gisbert (1): x86, mm/ASLR: Fix stack randomization on 64-bit systems Jiri Kosina (2): x86/mm/ASLR: Propagate base load address calculation x86/mm/ASLR: Avoid PAGE_SIZE redefinition for UML subarch Matt Fleming (2): x86/efi: Avoid triple faults during EFI mixed mode calls Revert "efi/libstub: Call get_memory_map() to obtain map and desc sizes" Quentin Casasnovas (2): x86/microcode/intel: Guard against stack overflow in the loader x86/microcode/intel: Handle truncated microcode images more robustly Ricardo Ribalda Delgado (1): x86/apic: Fix the devicetree build in certain configs Documentation/x86/zero-page.txt | 2 +- arch/x86/boot/compressed/Makefile | 1 + arch/x86/boot/compressed/aslr.c | 34 ++++- arch/x86/boot/compressed/efi_stub_64.S | 25 ---- arch/x86/boot/compressed/efi_thunk_64.S | 196 +++++++++++++++++++++++++ arch/x86/boot/compressed/misc.c | 3 +- arch/x86/boot/compressed/misc.h | 6 +- arch/x86/include/asm/apic.h | 8 + arch/x86/include/asm/page_types.h | 2 + arch/x86/include/uapi/asm/bootparam.h | 1 + arch/x86/kernel/cpu/microcode/intel.c | 5 + arch/x86/kernel/cpu/microcode/intel_early.c | 6 +- arch/x86/kernel/module.c | 10 +- arch/x86/kernel/setup.c | 22 ++- arch/x86/mm/init.c | 28 +++- arch/x86/mm/mmap.c | 6 +- arch/x86/platform/efi/efi_stub_64.S | 161 -------------------- arch/x86/platform/efi/efi_thunk_64.S | 121 ++++++++++++--- drivers/firmware/efi/libstub/efi-stub-helper.c | 16 +- fs/binfmt_elf.c | 5 +- 20 files changed, 419 insertions(+), 239 deletions(-) create mode 100644 arch/x86/boot/compressed/efi_thunk_64.S diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt index 199f453cb4de..82fbdbc1e0b0 100644 --- a/Documentation/x86/zero-page.txt +++ b/Documentation/x86/zero-page.txt @@ -3,7 +3,7 @@ protocol of kernel. These should be filled by bootloader or 16-bit real-mode setup code of the kernel. References/settings to it mainly are in: - arch/x86/include/asm/bootparam.h + arch/x86/include/uapi/asm/bootparam.h Offset Proto Name Meaning diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index ad754b4411f7..8bd44e8ee6e2 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -49,6 +49,7 @@ $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \ $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o $(obj)/vmlinux: $(vmlinux-objs-y) FORCE $(call if_changed,ld) diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index bb1376381985..7083c16cccba 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -14,6 +14,13 @@ static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; +struct kaslr_setup_data { + __u64 next; + __u32 type; + __u32 len; + __u8 data[1]; +} kaslr_setup_data; + #define I8254_PORT_CONTROL 0x43 #define I8254_PORT_COUNTER0 0x40 #define I8254_CMD_READBACK 0xC0 @@ -295,7 +302,29 @@ static unsigned long find_random_addr(unsigned long minimum, return slots_fetch_random(); } -unsigned char *choose_kernel_location(unsigned char *input, +static void add_kaslr_setup_data(struct boot_params *params, __u8 enabled) +{ + struct setup_data *data; + + kaslr_setup_data.type = SETUP_KASLR; + kaslr_setup_data.len = 1; + kaslr_setup_data.next = 0; + kaslr_setup_data.data[0] = enabled; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + if (data) + data->next = (unsigned long)&kaslr_setup_data; + else + params->hdr.setup_data = (unsigned long)&kaslr_setup_data; + +} + +unsigned char *choose_kernel_location(struct boot_params *params, + unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size) @@ -306,14 +335,17 @@ unsigned char *choose_kernel_location(unsigned char *input, #ifdef CONFIG_HIBERNATION if (!cmdline_find_option_bool("kaslr")) { debug_putstr("KASLR disabled by default...\n"); + add_kaslr_setup_data(params, 0); goto out; } #else if (cmdline_find_option_bool("nokaslr")) { debug_putstr("KASLR disabled by cmdline...\n"); + add_kaslr_setup_data(params, 0); goto out; } #endif + add_kaslr_setup_data(params, 1); /* Record the various known unsafe memory ranges. */ mem_avoid_init((unsigned long)input, input_size, diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S index 7ff3632806b1..99494dff2113 100644 --- a/arch/x86/boot/compressed/efi_stub_64.S +++ b/arch/x86/boot/compressed/efi_stub_64.S @@ -3,28 +3,3 @@ #include #include "../../platform/efi/efi_stub_64.S" - -#ifdef CONFIG_EFI_MIXED - .code64 - .text -ENTRY(efi64_thunk) - push %rbp - push %rbx - - subq $16, %rsp - leaq efi_exit32(%rip), %rax - movl %eax, 8(%rsp) - leaq efi_gdt64(%rip), %rax - movl %eax, 4(%rsp) - movl %eax, 2(%rax) /* Fixup the gdt base address */ - leaq efi32_boot_gdt(%rip), %rax - movl %eax, (%rsp) - - call __efi64_thunk - - addq $16, %rsp - pop %rbx - pop %rbp - ret -ENDPROC(efi64_thunk) -#endif /* CONFIG_EFI_MIXED */ diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S new file mode 100644 index 000000000000..630384a4c14a --- /dev/null +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -0,0 +1,196 @@ +/* + * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming + * + * Early support for invoking 32-bit EFI services from a 64-bit kernel. + * + * Because this thunking occurs before ExitBootServices() we have to + * restore the firmware's 32-bit GDT before we make EFI serivce calls, + * since the firmware's 32-bit IDT is still currently installed and it + * needs to be able to service interrupts. + * + * On the plus side, we don't have to worry about mangling 64-bit + * addresses into 32-bits because we're executing with an identify + * mapped pagetable and haven't transitioned to 64-bit virtual addresses + * yet. + */ + +#include +#include +#include +#include +#include + + .code64 + .text +ENTRY(efi64_thunk) + push %rbp + push %rbx + + subq $8, %rsp + leaq efi_exit32(%rip), %rax + movl %eax, 4(%rsp) + leaq efi_gdt64(%rip), %rax + movl %eax, (%rsp) + movl %eax, 2(%rax) /* Fixup the gdt base address */ + + movl %ds, %eax + push %rax + movl %es, %eax + push %rax + movl %ss, %eax + push %rax + + /* + * Convert x86-64 ABI params to i386 ABI + */ + subq $32, %rsp + movl %esi, 0x0(%rsp) + movl %edx, 0x4(%rsp) + movl %ecx, 0x8(%rsp) + movq %r8, %rsi + movl %esi, 0xc(%rsp) + movq %r9, %rsi + movl %esi, 0x10(%rsp) + + sgdt save_gdt(%rip) + + leaq 1f(%rip), %rbx + movq %rbx, func_rt_ptr(%rip) + + /* + * Switch to gdt with 32-bit segments. This is the firmware GDT + * that was installed when the kernel started executing. This + * pointer was saved at the EFI stub entry point in head_64.S. + */ + leaq efi32_boot_gdt(%rip), %rax + lgdt (%rax) + + pushq $__KERNEL_CS + leaq efi_enter32(%rip), %rax + pushq %rax + lretq + +1: addq $32, %rsp + + lgdt save_gdt(%rip) + + pop %rbx + movl %ebx, %ss + pop %rbx + movl %ebx, %es + pop %rbx + movl %ebx, %ds + + /* + * Convert 32-bit status code into 64-bit. + */ + test %rax, %rax + jz 1f + movl %eax, %ecx + andl $0x0fffffff, %ecx + andl $0xf0000000, %eax + shl $32, %rax + or %rcx, %rax +1: + addq $8, %rsp + pop %rbx + pop %rbp + ret +ENDPROC(efi64_thunk) + +ENTRY(efi_exit32) + movq func_rt_ptr(%rip), %rax + push %rax + mov %rdi, %rax + ret +ENDPROC(efi_exit32) + + .code32 +/* + * EFI service pointer must be in %edi. + * + * The stack should represent the 32-bit calling convention. + */ +ENTRY(efi_enter32) + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %es + movl %eax, %ss + + /* Reload pgtables */ + movl %cr3, %eax + movl %eax, %cr3 + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Disable long mode via EFER */ + movl $MSR_EFER, %ecx + rdmsr + btrl $_EFER_LME, %eax + wrmsr + + call *%edi + + /* We must preserve return value */ + movl %eax, %edi + + /* + * Some firmware will return with interrupts enabled. Be sure to + * disable them before we switch GDTs. + */ + cli + + movl 56(%esp), %eax + movl %eax, 2(%eax) + lgdtl (%eax) + + movl %cr4, %eax + btsl $(X86_CR4_PAE_BIT), %eax + movl %eax, %cr4 + + movl %cr3, %eax + movl %eax, %cr3 + + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + + xorl %eax, %eax + lldt %ax + + movl 60(%esp), %eax + pushl $__KERNEL_CS + pushl %eax + + /* Enable paging */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + lret +ENDPROC(efi_enter32) + + .data + .balign 8 + .global efi32_boot_gdt +efi32_boot_gdt: .word 0 + .quad 0 + +save_gdt: .word 0 + .quad 0 +func_rt_ptr: .quad 0 + + .global efi_gdt64 +efi_gdt64: + .word efi_gdt64_end - efi_gdt64 + .long 0 /* Filled out by user */ + .word 0 + .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x00af9a000000ffff /* __KERNEL_CS */ + .quad 0x00cf92000000ffff /* __KERNEL_DS */ + .quad 0x0080890000000000 /* TS descriptor */ + .quad 0x0000000000000000 /* TS continued */ +efi_gdt64_end: diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index a950864a64da..5903089c818f 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -401,7 +401,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, * the entire decompressed kernel plus relocation table, or the * entire decompressed kernel plus .bss and .brk sections. */ - output = choose_kernel_location(input_data, input_len, output, + output = choose_kernel_location(real_mode, input_data, input_len, + output, output_len > run_size ? output_len : run_size); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 24e3e569a13c..6d6730743024 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -56,7 +56,8 @@ int cmdline_find_option_bool(const char *option); #if CONFIG_RANDOMIZE_BASE /* aslr.c */ -unsigned char *choose_kernel_location(unsigned char *input, +unsigned char *choose_kernel_location(struct boot_params *params, + unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size); @@ -64,7 +65,8 @@ unsigned char *choose_kernel_location(unsigned char *input, bool has_cpuflag(int flag); #else static inline -unsigned char *choose_kernel_location(unsigned char *input, +unsigned char *choose_kernel_location(struct boot_params *params, + unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size) diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 92003f3c8a42..efc3b22d896e 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -213,7 +213,15 @@ void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); extern void setup_secondary_APIC_clock(void); extern int APIC_init_uniprocessor(void); + +#ifdef CONFIG_X86_64 +static inline int apic_force_enable(unsigned long addr) +{ + return -1; +} +#else extern int apic_force_enable(unsigned long addr); +#endif extern int apic_bsp_setup(bool upmode); extern void apic_ap_setup(void); diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index f97fbe3abb67..95e11f79f123 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -51,6 +51,8 @@ extern int devmem_is_allowed(unsigned long pagenr); extern unsigned long max_low_pfn_mapped; extern unsigned long max_pfn_mapped; +extern bool kaslr_enabled; + static inline phys_addr_t get_max_mapped(void) { return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT; diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 225b0988043a..44e6dd7e36a2 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -7,6 +7,7 @@ #define SETUP_DTB 2 #define SETUP_PCI 3 #define SETUP_EFI 4 +#define SETUP_KASLR 5 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index c6826d1e8082..746e7fd08aad 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -196,6 +196,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, struct microcode_header_intel mc_header; unsigned int mc_size; + if (leftover < sizeof(mc_header)) { + pr_err("error! Truncated header in microcode data file\n"); + break; + } + if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header))) break; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index ec9df6f9cd47..420eb933189c 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -321,7 +321,11 @@ get_matching_model_microcode(int cpu, unsigned long start, unsigned int mc_saved_count = mc_saved_data->mc_saved_count; int i; - while (leftover) { + while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) { + + if (leftover < sizeof(mc_header)) + break; + mc_header = (struct microcode_header_intel *)ucode_ptr; mc_size = get_totalsize(mc_header); diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index e69f9882bf95..ef00116e8270 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -46,21 +46,13 @@ do { \ #ifdef CONFIG_RANDOMIZE_BASE static unsigned long module_load_offset; -static int randomize_modules = 1; /* Mutex protects the module_load_offset. */ static DEFINE_MUTEX(module_kaslr_mutex); -static int __init parse_nokaslr(char *p) -{ - randomize_modules = 0; - return 0; -} -early_param("nokaslr", parse_nokaslr); - static unsigned long int get_module_load_offset(void) { - if (randomize_modules) { + if (kaslr_enabled) { mutex_lock(&module_kaslr_mutex); /* * Calculate the module_load_offset the first time this diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c4648adadd7d..0d8071d7addb 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -121,6 +121,8 @@ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; +bool __read_mostly kaslr_enabled = false; + #ifdef CONFIG_DMI RESERVE_BRK(dmi_alloc, 65536); #endif @@ -424,6 +426,11 @@ static void __init reserve_initrd(void) } #endif /* CONFIG_BLK_DEV_INITRD */ +static void __init parse_kaslr_setup(u64 pa_data, u32 data_len) +{ + kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data)); +} + static void __init parse_setup_data(void) { struct setup_data *data; @@ -449,6 +456,9 @@ static void __init parse_setup_data(void) case SETUP_EFI: parse_efi_setup(pa_data, data_len); break; + case SETUP_KASLR: + parse_kaslr_setup(pa_data, data_len); + break; default: break; } @@ -831,10 +841,14 @@ static void __init trim_low_memory_range(void) static int dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) { - pr_emerg("Kernel Offset: 0x%lx from 0x%lx " - "(relocation range: 0x%lx-0x%lx)\n", - (unsigned long)&_text - __START_KERNEL, __START_KERNEL, - __START_KERNEL_map, MODULES_VADDR-1); + if (kaslr_enabled) + pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n", + (unsigned long)&_text - __START_KERNEL, + __START_KERNEL, + __START_KERNEL_map, + MODULES_VADDR-1); + else + pr_emerg("Kernel Offset: disabled\n"); return 0; } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 079c3b6a3ff1..7ff24240d863 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -238,6 +238,31 @@ static void __init_refok adjust_range_page_size_mask(struct map_range *mr, } } +static const char *page_size_string(struct map_range *mr) +{ + static const char str_1g[] = "1G"; + static const char str_2m[] = "2M"; + static const char str_4m[] = "4M"; + static const char str_4k[] = "4k"; + + if (mr->page_size_mask & (1<page_size_mask & (1<page_size_mask & (1<flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT; + max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT; } return max; diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 5fcda7272550..86d0f9e08dd9 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -91,167 +91,6 @@ ENTRY(efi_call) ret ENDPROC(efi_call) -#ifdef CONFIG_EFI_MIXED - -/* - * We run this function from the 1:1 mapping. - * - * This function must be invoked with a 1:1 mapped stack. - */ -ENTRY(__efi64_thunk) - movl %ds, %eax - push %rax - movl %es, %eax - push %rax - movl %ss, %eax - push %rax - - subq $32, %rsp - movl %esi, 0x0(%rsp) - movl %edx, 0x4(%rsp) - movl %ecx, 0x8(%rsp) - movq %r8, %rsi - movl %esi, 0xc(%rsp) - movq %r9, %rsi - movl %esi, 0x10(%rsp) - - sgdt save_gdt(%rip) - - leaq 1f(%rip), %rbx - movq %rbx, func_rt_ptr(%rip) - - /* Switch to gdt with 32-bit segments */ - movl 64(%rsp), %eax - lgdt (%rax) - - leaq efi_enter32(%rip), %rax - pushq $__KERNEL_CS - pushq %rax - lretq - -1: addq $32, %rsp - - lgdt save_gdt(%rip) - - pop %rbx - movl %ebx, %ss - pop %rbx - movl %ebx, %es - pop %rbx - movl %ebx, %ds - - /* - * Convert 32-bit status code into 64-bit. - */ - test %rax, %rax - jz 1f - movl %eax, %ecx - andl $0x0fffffff, %ecx - andl $0xf0000000, %eax - shl $32, %rax - or %rcx, %rax -1: - ret -ENDPROC(__efi64_thunk) - -ENTRY(efi_exit32) - movq func_rt_ptr(%rip), %rax - push %rax - mov %rdi, %rax - ret -ENDPROC(efi_exit32) - - .code32 -/* - * EFI service pointer must be in %edi. - * - * The stack should represent the 32-bit calling convention. - */ -ENTRY(efi_enter32) - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %ss - - /* Reload pgtables */ - movl %cr3, %eax - movl %eax, %cr3 - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - /* Disable long mode via EFER */ - movl $MSR_EFER, %ecx - rdmsr - btrl $_EFER_LME, %eax - wrmsr - - call *%edi - - /* We must preserve return value */ - movl %eax, %edi - - /* - * Some firmware will return with interrupts enabled. Be sure to - * disable them before we switch GDTs. - */ - cli - - movl 68(%esp), %eax - movl %eax, 2(%eax) - lgdtl (%eax) - - movl %cr4, %eax - btsl $(X86_CR4_PAE_BIT), %eax - movl %eax, %cr4 - - movl %cr3, %eax - movl %eax, %cr3 - - movl $MSR_EFER, %ecx - rdmsr - btsl $_EFER_LME, %eax - wrmsr - - xorl %eax, %eax - lldt %ax - - movl 72(%esp), %eax - pushl $__KERNEL_CS - pushl %eax - - /* Enable paging */ - movl %cr0, %eax - btsl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - lret -ENDPROC(efi_enter32) - - .data - .balign 8 - .global efi32_boot_gdt -efi32_boot_gdt: .word 0 - .quad 0 - -save_gdt: .word 0 - .quad 0 -func_rt_ptr: .quad 0 - - .global efi_gdt64 -efi_gdt64: - .word efi_gdt64_end - efi_gdt64 - .long 0 /* Filled out by user */ - .word 0 - .quad 0x0000000000000000 /* NULL descriptor */ - .quad 0x00af9a000000ffff /* __KERNEL_CS */ - .quad 0x00cf92000000ffff /* __KERNEL_DS */ - .quad 0x0080890000000000 /* TS descriptor */ - .quad 0x0000000000000000 /* TS continued */ -efi_gdt64_end: -#endif /* CONFIG_EFI_MIXED */ - .data ENTRY(efi_scratch) .fill 3,8,0 diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 8806fa73e6e6..ff85d28c50f2 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -1,9 +1,26 @@ /* * Copyright (C) 2014 Intel Corporation; author Matt Fleming + * + * Support for invoking 32-bit EFI runtime services from a 64-bit + * kernel. + * + * The below thunking functions are only used after ExitBootServices() + * has been called. This simplifies things considerably as compared with + * the early EFI thunking because we can leave all the kernel state + * intact (GDT, IDT, etc) and simply invoke the the 32-bit EFI runtime + * services from __KERNEL32_CS. This means we can continue to service + * interrupts across an EFI mixed mode call. + * + * We do however, need to handle the fact that we're running in a full + * 64-bit virtual address space. Things like the stack and instruction + * addresses need to be accessible by the 32-bit firmware, so we rely on + * using the identity mappings in the EFI page table to access the stack + * and kernel text (see efi_setup_page_tables()). */ #include #include +#include .text .code64 @@ -33,14 +50,6 @@ ENTRY(efi64_thunk) leaq efi_exit32(%rip), %rbx subq %rax, %rbx movl %ebx, 8(%rsp) - leaq efi_gdt64(%rip), %rbx - subq %rax, %rbx - movl %ebx, 2(%ebx) - movl %ebx, 4(%rsp) - leaq efi_gdt32(%rip), %rbx - subq %rax, %rbx - movl %ebx, 2(%ebx) - movl %ebx, (%rsp) leaq __efi64_thunk(%rip), %rbx subq %rax, %rbx @@ -52,14 +61,92 @@ ENTRY(efi64_thunk) retq ENDPROC(efi64_thunk) - .data -efi_gdt32: - .word efi_gdt32_end - efi_gdt32 - .long 0 /* Filled out above */ - .word 0 - .quad 0x0000000000000000 /* NULL descriptor */ - .quad 0x00cf9a000000ffff /* __KERNEL_CS */ - .quad 0x00cf93000000ffff /* __KERNEL_DS */ -efi_gdt32_end: +/* + * We run this function from the 1:1 mapping. + * + * This function must be invoked with a 1:1 mapped stack. + */ +ENTRY(__efi64_thunk) + movl %ds, %eax + push %rax + movl %es, %eax + push %rax + movl %ss, %eax + push %rax + + subq $32, %rsp + movl %esi, 0x0(%rsp) + movl %edx, 0x4(%rsp) + movl %ecx, 0x8(%rsp) + movq %r8, %rsi + movl %esi, 0xc(%rsp) + movq %r9, %rsi + movl %esi, 0x10(%rsp) + + leaq 1f(%rip), %rbx + movq %rbx, func_rt_ptr(%rip) + + /* Switch to 32-bit descriptor */ + pushq $__KERNEL32_CS + leaq efi_enter32(%rip), %rax + pushq %rax + lretq + +1: addq $32, %rsp + + pop %rbx + movl %ebx, %ss + pop %rbx + movl %ebx, %es + pop %rbx + movl %ebx, %ds + /* + * Convert 32-bit status code into 64-bit. + */ + test %rax, %rax + jz 1f + movl %eax, %ecx + andl $0x0fffffff, %ecx + andl $0xf0000000, %eax + shl $32, %rax + or %rcx, %rax +1: + ret +ENDPROC(__efi64_thunk) + +ENTRY(efi_exit32) + movq func_rt_ptr(%rip), %rax + push %rax + mov %rdi, %rax + ret +ENDPROC(efi_exit32) + + .code32 +/* + * EFI service pointer must be in %edi. + * + * The stack should represent the 32-bit calling convention. + */ +ENTRY(efi_enter32) + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %es + movl %eax, %ss + + call *%edi + + /* We must preserve return value */ + movl %eax, %edi + + movl 72(%esp), %eax + pushl $__KERNEL_CS + pushl %eax + + lret +ENDPROC(efi_enter32) + + .data + .balign 8 +func_rt_ptr: .quad 0 efi_saved_sp: .quad 0 diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index d073e3946383..9bd9fbb5bea8 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -66,29 +66,25 @@ efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, unsigned long key; u32 desc_version; - *map_size = 0; - *desc_size = 0; - key = 0; - status = efi_call_early(get_memory_map, map_size, NULL, - &key, desc_size, &desc_version); - if (status != EFI_BUFFER_TOO_SMALL) - return EFI_LOAD_ERROR; - + *map_size = sizeof(*m) * 32; +again: /* * Add an additional efi_memory_desc_t because we're doing an * allocation which may be in a new descriptor region. */ - *map_size += *desc_size; + *map_size += sizeof(*m); status = efi_call_early(allocate_pool, EFI_LOADER_DATA, *map_size, (void **)&m); if (status != EFI_SUCCESS) goto fail; + *desc_size = 0; + key = 0; status = efi_call_early(get_memory_map, map_size, m, &key, desc_size, &desc_version); if (status == EFI_BUFFER_TOO_SMALL) { efi_call_early(free_pool, m); - return EFI_LOAD_ERROR; + goto again; } if (status != EFI_SUCCESS) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 02b16910f4c9..995986b8e36b 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -645,11 +645,12 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, static unsigned long randomize_stack_top(unsigned long stack_top) { - unsigned int random_variable = 0; + unsigned long random_variable = 0; if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - random_variable = get_random_int() & STACK_RND_MASK; + random_variable = (unsigned long) get_random_int(); + random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP