diff options
Diffstat (limited to 'arch/x86/entry')
-rw-r--r-- | arch/x86/entry/calling.h | 68 | ||||
-rw-r--r-- | arch/x86/entry/entry_32.S | 8 | ||||
-rw-r--r-- | arch/x86/entry/entry_64.S | 42 | ||||
-rw-r--r-- | arch/x86/entry/entry_64_compat.S | 11 | ||||
-rw-r--r-- | arch/x86/entry/vdso/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/entry/vdso/vma.c | 6 |
6 files changed, 109 insertions, 28 deletions
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 993dd06c8923..806729a7172f 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -6,6 +6,8 @@ #include <asm/percpu.h> #include <asm/asm-offsets.h> #include <asm/processor-flags.h> +#include <asm/msr.h> +#include <asm/nospec-branch.h> /* @@ -146,27 +148,19 @@ For 32-bit we have the following conventions - kernel is built with .endm -.macro POP_REGS pop_rdi=1 skip_r11rcx=0 +.macro POP_REGS pop_rdi=1 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .if \skip_r11rcx - popq %rsi - .else popq %r11 - .endif popq %r10 popq %r9 popq %r8 popq %rax - .if \skip_r11rcx - popq %rsi - .else popq %rcx - .endif popq %rdx popq %rsi .if \pop_rdi @@ -317,6 +311,62 @@ For 32-bit we have the following conventions - kernel is built with #endif /* + * IBRS kernel mitigation for Spectre_v2. + * + * Assumes full context is established (PUSH_REGS, CR3 and GS) and it clobbers + * the regs it uses (AX, CX, DX). Must be called before the first RET + * instruction (NOTE! UNTRAIN_RET includes a RET instruction) + * + * The optional argument is used to save/restore the current value, + * which is used on the paranoid paths. + * + * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set. + */ +.macro IBRS_ENTER save_reg + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + rdmsr + shl $32, %rdx + or %rdx, %rax + mov %rax, \save_reg + test $SPEC_CTRL_IBRS, %eax + jz .Ldo_wrmsr_\@ + lfence + jmp .Lend_\@ +.Ldo_wrmsr_\@: +.endif + + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_\@: +.endm + +/* + * Similar to IBRS_ENTER, requires KERNEL GS,CR3 and clobbers (AX, CX, DX) + * regs. Must be called after the last RET. + */ +.macro IBRS_EXIT save_reg + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + mov \save_reg, %rdx +.else + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + andl $(~SPEC_CTRL_IBRS), %edx +.endif + + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_\@: +.endm + +/* * Mitigate Spectre v1 for conditional swapgs code paths. * * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 37d9016d4768..e6c258bf9511 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -643,7 +643,6 @@ ENTRY(__switch_to_asm) movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset #endif -#ifdef CONFIG_RETPOLINE /* * When switching from a shallower to a deeper call stack * the RSB may either underflow or use entries populated @@ -652,7 +651,6 @@ ENTRY(__switch_to_asm) * speculative execution to prevent attack. */ FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW -#endif /* restore callee-saved registers */ popfl @@ -1502,13 +1500,13 @@ ENTRY(async_page_fault) END(async_page_fault) #endif -ENTRY(rewind_stack_do_exit) +ENTRY(rewind_stack_and_make_dead) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp movl PER_CPU_VAR(cpu_current_top_of_stack), %esi leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp - call do_exit + call make_task_dead 1: jmp 1b -END(rewind_stack_do_exit) +END(rewind_stack_and_make_dead) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index ced052ddc4d7..bf08de4232e3 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -235,6 +235,10 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) /* IRQs are off. */ movq %rax, %rdi movq %rsp, %rsi + + /* clobbers %rax, make sure it is after saving the syscall nr */ + IBRS_ENTER + call do_syscall_64 /* returns with IRQs disabled */ TRACE_IRQS_IRETQ /* we're about to change IF */ @@ -311,8 +315,8 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: - /* rcx and r11 are already restored (see code above) */ - POP_REGS pop_rdi=0 skip_r11rcx=1 + IBRS_EXIT + POP_REGS pop_rdi=0 /* * Now all regs are restored except RSP and RDI. @@ -363,7 +367,6 @@ ENTRY(__switch_to_asm) movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset #endif -#ifdef CONFIG_RETPOLINE /* * When switching from a shallower to a deeper call stack * the RSB may either underflow or use entries populated @@ -372,7 +375,6 @@ ENTRY(__switch_to_asm) * speculative execution to prevent attack. */ FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW -#endif /* restore callee-saved registers */ popfq @@ -685,6 +687,7 @@ GLOBAL(retint_user) TRACE_IRQS_IRETQ GLOBAL(swapgs_restore_regs_and_return_to_usermode) + IBRS_EXIT #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates user mode. */ testb $3, CS(%rsp) @@ -1250,7 +1253,13 @@ ENTRY(paranoid_entry) */ FENCE_SWAPGS_KERNEL_ENTRY - ret + /* + * Once we have CR3 and %GS setup save and set SPEC_CTRL. Just like + * CR3 above, keep the old value in a callee saved register. + */ + IBRS_ENTER save_reg=%r15 + + RET END(paranoid_entry) /* @@ -1278,12 +1287,20 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + + /* + * Must restore IBRS state before both CR3 and %GS since we need access + * to the per-CPU x86_spec_ctrl_shadow variable. + */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit) + /* * Save all registers in pt_regs, and switch GS if needed. */ @@ -1303,6 +1320,7 @@ ENTRY(error_entry) FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER .Lerror_entry_from_usermode_after_swapgs: /* Put us onto the real thread stack. */ @@ -1367,6 +1385,7 @@ ENTRY(error_entry) SWAPGS FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER /* * Pretend that the exception came from user mode: set up pt_regs @@ -1472,6 +1491,8 @@ ENTRY(nmi) PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER + IBRS_ENTER + /* * At this point we no longer need to worry about stack damage * due to nesting -- we're on the normal thread stack and we're @@ -1695,6 +1716,9 @@ end_repeat_nmi: movq $-1, %rsi call do_nmi + /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 @@ -1735,10 +1759,10 @@ END(nmi) ENTRY(ignore_sysret) UNWIND_HINT_EMPTY mov $-ENOSYS, %eax - sysret + sysretl END(ignore_sysret) -ENTRY(rewind_stack_do_exit) +ENTRY(rewind_stack_and_make_dead) UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp @@ -1747,5 +1771,5 @@ ENTRY(rewind_stack_do_exit) leaq -PTREGS_SIZE(%rax), %rsp UNWIND_HINT_REGS - call do_exit -END(rewind_stack_do_exit) + call make_task_dead +END(rewind_stack_and_make_dead) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 40d2834a8101..85dd05de648c 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -4,7 +4,6 @@ * * Copyright 2000-2002 Andi Kleen, SuSE Labs. */ -#include "calling.h" #include <asm/asm-offsets.h> #include <asm/current.h> #include <asm/errno.h> @@ -17,6 +16,8 @@ #include <linux/linkage.h> #include <linux/err.h> +#include "calling.h" + .section .entry.text, "ax" /* @@ -106,6 +107,8 @@ ENTRY(entry_SYSENTER_compat) xorl %r15d, %r15d /* nospec r15 */ cld + IBRS_ENTER + /* * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether @@ -253,6 +256,8 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) */ TRACE_IRQS_OFF + IBRS_ENTER + movq %rsp, %rdi call do_fast_syscall_32 /* XEN PV guests always use IRET path */ @@ -262,6 +267,9 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) /* Opportunistic SYSRET */ sysret32_from_system_call: TRACE_IRQS_ON /* User mode traces as IRQs on. */ + + IBRS_EXIT + movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ @@ -403,6 +411,7 @@ ENTRY(entry_INT80_compat) * gate turned them off. */ TRACE_IRQS_OFF + IBRS_ENTER movq %rsp, %rdi call do_int80_syscall_32 diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 5bfe2243a08f..ec5d8d0bd222 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -172,7 +172,7 @@ quiet_cmd_vdso = VDSO $@ VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \ $(call ld-option, --build-id) $(call ld-option, --eh-frame-hdr) \ - -Bsymbolic + -Bsymbolic -z noexecstack GCOV_PROFILE := n # diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 46caca4d9141..a3cd828359f8 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -228,8 +228,8 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) /* Round the lowest possible end address up to a PMD boundary. */ end = (start + len + PMD_SIZE - 1) & PMD_MASK; - if (end >= TASK_SIZE_MAX) - end = TASK_SIZE_MAX; + if (end >= DEFAULT_MAP_WINDOW) + end = DEFAULT_MAP_WINDOW; end -= len; if (end > start) { @@ -329,7 +329,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) static __init int vdso_setup(char *s) { vdso64_enabled = simple_strtoul(s, NULL, 0); - return 0; + return 1; } __setup("vdso=", vdso_setup); #endif |