diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index aa47be71df4c..9cfd6bb9198e 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2657,6 +2657,27 @@ bytes respectively. Such letter suffixes can also be entirely omitted. vmpoff= [KNL,S390] Perform z/VM CP command after power off. Format: + vsyscall= [X86-64] + Controls the behavior of vsyscalls (i.e. calls to + fixed addresses of 0xffffffffff600x00 from legacy + code). Most statically-linked binaries and older + versions of glibc use these calls. Because these + functions are at fixed addresses, they make nice + targets for exploits that can control RIP. + + emulate [default] Vsyscalls turn into traps and are + emulated reasonably safely. + + native Vsyscalls are native syscall instructions. + This is a little bit faster than trapping + and makes a few dynamic recompilers work + better than they would in emulation mode. + It also makes exploits much easier to write. + + none Vsyscalls don't work at all. This makes + them quite hard to use for exploits but + might break your system. + vt.cur_default= [VT] Default cursor shape. Format: 0xCCBBAA, where AA, BB, and CC are the same as the parameters of the [?A;B;Cc escape sequence; diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index a563c509edcb..2c224e183b52 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -17,7 +17,6 @@ * Vectors 0 ... 31 : system traps and exceptions - hardcoded events * Vectors 32 ... 127 : device interrupts * Vector 128 : legacy int80 syscall interface - * Vector 204 : legacy x86_64 vsyscall emulation * Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts * Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts * @@ -51,9 +50,6 @@ #ifdef CONFIG_X86_32 # define SYSCALL_VECTOR 0x80 #endif -#ifdef CONFIG_X86_64 -# define VSYSCALL_EMU_VECTOR 0xcc -#endif /* * Vectors 0x30-0x3f are used for ISA interrupts. diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 2bae0a513b40..0012d0902c5f 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -40,7 +40,6 @@ asmlinkage void alignment_check(void); asmlinkage void machine_check(void); #endif /* CONFIG_X86_MCE */ asmlinkage void simd_coprocessor_error(void); -asmlinkage void emulate_vsyscall(void); dotraplinkage void do_divide_error(struct pt_regs *, long); dotraplinkage void do_debug(struct pt_regs *, long); @@ -67,7 +66,6 @@ dotraplinkage void do_alignment_check(struct pt_regs *, long); dotraplinkage void do_machine_check(struct pt_regs *, long); #endif dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); -dotraplinkage void do_emulate_vsyscall(struct pt_regs *, long); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *, long); #endif diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 60107072c28b..eaea1d31f753 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -27,6 +27,12 @@ extern struct timezone sys_tz; extern void map_vsyscall(void); +/* + * Called on instruction fetch fault in vsyscall page. + * Returns true if handled. + */ +extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address); + #endif /* __KERNEL__ */ #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index e949793d6b93..46792d900018 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1123,7 +1123,6 @@ zeroentry spurious_interrupt_bug do_spurious_interrupt_bug zeroentry coprocessor_error do_coprocessor_error errorentry alignment_check do_alignment_check zeroentry simd_coprocessor_error do_simd_coprocessor_error -zeroentry emulate_vsyscall do_emulate_vsyscall /* Reload gs selector with exception handling */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index fbc097a085ca..b9b67166f9de 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -872,12 +872,6 @@ void __init trap_init(void) set_bit(SYSCALL_VECTOR, used_vectors); #endif -#ifdef CONFIG_X86_64 - BUG_ON(test_bit(VSYSCALL_EMU_VECTOR, used_vectors)); - set_system_intr_gate(VSYSCALL_EMU_VECTOR, &emulate_vsyscall); - set_bit(VSYSCALL_EMU_VECTOR, used_vectors); -#endif - /* * Should be a barrier for any external CPU state: */ diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 8f3a265476d7..0f703f10901a 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -71,7 +71,6 @@ PHDRS { text PT_LOAD FLAGS(5); /* R_E */ data PT_LOAD FLAGS(6); /* RW_ */ #ifdef CONFIG_X86_64 - user PT_LOAD FLAGS(5); /* R_E */ #ifdef CONFIG_SMP percpu PT_LOAD FLAGS(6); /* RW_ */ #endif @@ -174,38 +173,6 @@ SECTIONS . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE); -#define VSYSCALL_ADDR (-10*1024*1024) - -#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET) -#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET) - -#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0) -#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET) - - __vsyscall_0 = .; - - . = VSYSCALL_ADDR; - .vsyscall : AT(VLOAD(.vsyscall)) { - /* work around gold bug 13023 */ - __vsyscall_beginning_hack = .; - *(.vsyscall_0) - - . = __vsyscall_beginning_hack + 1024; - *(.vsyscall_1) - - . = __vsyscall_beginning_hack + 2048; - *(.vsyscall_2) - - . = __vsyscall_beginning_hack + 4096; /* Pad the whole page. */ - } :user =0xcc - . = ALIGN(__vsyscall_0 + PAGE_SIZE, PAGE_SIZE); - -#undef VSYSCALL_ADDR -#undef VLOAD_OFFSET -#undef VLOAD -#undef VVIRT_OFFSET -#undef VVIRT - #endif /* CONFIG_X86_64 */ /* Init code and data - will be freed after init */ diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index bf8e9ffee6e9..18ae83dd1cd7 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -56,6 +56,27 @@ DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), }; +static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; + +static int __init vsyscall_setup(char *str) +{ + if (str) { + if (!strcmp("emulate", str)) + vsyscall_mode = EMULATE; + else if (!strcmp("native", str)) + vsyscall_mode = NATIVE; + else if (!strcmp("none", str)) + vsyscall_mode = NONE; + else + return -EINVAL; + + return 0; + } + + return -EINVAL; +} +early_param("vsyscall", vsyscall_setup); + void update_vsyscall_tz(void) { unsigned long flags; @@ -100,7 +121,7 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", level, tsk->comm, task_pid_nr(tsk), - message, regs->ip - 2, regs->cs, + message, regs->ip, regs->cs, regs->sp, regs->ax, regs->si, regs->di); } @@ -118,45 +139,39 @@ static int addr_to_vsyscall_nr(unsigned long addr) return nr; } -void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code) +bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) { struct task_struct *tsk; unsigned long caller; int vsyscall_nr; long ret; - local_irq_enable(); + /* + * No point in checking CS -- the only way to get here is a user mode + * trap to a high address, which means that we're in 64-bit user code. + */ - if (!user_64bit_mode(regs)) { - /* - * If we trapped from kernel mode, we might as well OOPS now - * instead of returning to some random address and OOPSing - * then. - */ - BUG_ON(!user_mode(regs)); + WARN_ON_ONCE(address != regs->ip); - /* Compat mode and non-compat 32-bit CS should both segfault. */ - warn_bad_vsyscall(KERN_WARNING, regs, - "illegal int 0xcc from 32-bit mode"); - goto sigsegv; + if (vsyscall_mode == NONE) { + warn_bad_vsyscall(KERN_INFO, regs, + "vsyscall attempted with vsyscall=none"); + return false; } - /* - * x86-ism here: regs->ip points to the instruction after the int 0xcc, - * and int 0xcc is two bytes long. - */ - vsyscall_nr = addr_to_vsyscall_nr(regs->ip - 2); + vsyscall_nr = addr_to_vsyscall_nr(address); trace_emulate_vsyscall(vsyscall_nr); if (vsyscall_nr < 0) { warn_bad_vsyscall(KERN_WARNING, regs, - "illegal int 0xcc (exploit attempt?)"); + "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround"); goto sigsegv; } if (get_user(caller, (unsigned long __user *)regs->sp) != 0) { - warn_bad_vsyscall(KERN_WARNING, regs, "int 0xcc with bad stack (exploit attempt?)"); + warn_bad_vsyscall(KERN_WARNING, regs, + "vsyscall with bad stack (exploit attempt?)"); goto sigsegv; } @@ -201,13 +216,11 @@ void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code) regs->ip = caller; regs->sp += 8; - local_irq_disable(); - return; + return true; sigsegv: - regs->ip -= 2; /* The faulting instruction should be the int 0xcc. */ force_sig(SIGSEGV, current); - local_irq_disable(); + return true; } /* @@ -255,15 +268,21 @@ cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg) void __init map_vsyscall(void) { - extern char __vsyscall_0; - unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0); + extern char __vsyscall_page; + unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); extern char __vvar_page; unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page); - /* Note that VSYSCALL_MAPPED_PAGES must agree with the code below. */ - __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL); + __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall, + vsyscall_mode == NATIVE + ? PAGE_KERNEL_VSYSCALL + : PAGE_KERNEL_VVAR); + BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) != + (unsigned long)VSYSCALL_START); + __set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR); - BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != (unsigned long)VVAR_ADDRESS); + BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != + (unsigned long)VVAR_ADDRESS); } static int __init vsyscall_init(void) diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/kernel/vsyscall_emu_64.S index ffa845eae5ca..c9596a9af159 100644 --- a/arch/x86/kernel/vsyscall_emu_64.S +++ b/arch/x86/kernel/vsyscall_emu_64.S @@ -7,21 +7,31 @@ */ #include + #include +#include +#include -/* The unused parts of the page are filled with 0xcc by the linker script. */ +__PAGE_ALIGNED_DATA + .globl __vsyscall_page + .balign PAGE_SIZE, 0xcc + .type __vsyscall_page, @object +__vsyscall_page: -.section .vsyscall_0, "a" -ENTRY(vsyscall_0) - int $VSYSCALL_EMU_VECTOR -END(vsyscall_0) + mov $__NR_gettimeofday, %rax + syscall + ret -.section .vsyscall_1, "a" -ENTRY(vsyscall_1) - int $VSYSCALL_EMU_VECTOR -END(vsyscall_1) + .balign 1024, 0xcc + mov $__NR_time, %rax + syscall + ret -.section .vsyscall_2, "a" -ENTRY(vsyscall_2) - int $VSYSCALL_EMU_VECTOR -END(vsyscall_2) + .balign 1024, 0xcc + mov $__NR_getcpu, %rax + syscall + ret + + .balign 4096, 0xcc + + .size __vsyscall_page, 4096 diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index c1d018238f32..e58935c25b94 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -720,6 +720,18 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, if (is_errata100(regs, address)) return; +#ifdef CONFIG_X86_64 + /* + * Instruction fetch faults in the vsyscall page might need + * emulation. + */ + if (unlikely((error_code & PF_INSTR) && + ((address & ~0xfff) == VSYSCALL_START))) { + if (emulate_vsyscall(regs, address)) + return; + } +#endif + if (unlikely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk);