diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 66350e6a6ca5..e13027247c90 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -361,6 +361,8 @@ restore_all: TRACE_IRQS_IRET restore_all_notrace: #ifdef CONFIG_X86_ESPFIX32 + ALTERNATIVE "jmp restore_nocheck", "", X86_BUG_ESPFIX + movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS /* * Warning: PT_OLDSS(%esp) contains the wrong/random values if we @@ -387,19 +389,6 @@ ENTRY(iret_exc ) #ifdef CONFIG_X86_ESPFIX32 ldt_ss: -#ifdef CONFIG_PARAVIRT - /* - * The kernel can't run on a non-flat stack if paravirt mode - * is active. Rather than try to fixup the high bits of - * ESP, bypass this code entirely. This may break DOSemu - * and/or Wine support in a paravirt VM, although the option - * is still available to implement the setting of the high - * 16-bits in the INTERRUPT_RETURN paravirt-op. - */ - cmpl $0, pv_info+PARAVIRT_enabled - jne restore_nocheck -#endif - /* * Setup and switch to ESPFIX stack * diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6663fae71b12..d11a3aaafd96 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -286,4 +286,12 @@ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#ifdef CONFIG_X86_32 +/* + * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional + * to avoid confusion. + */ +#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#endif + #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 079d83fc6488..d8337f34b5f4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -802,6 +802,31 @@ static void detect_nopl(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_NOPL); #else set_cpu_cap(c, X86_FEATURE_NOPL); +#endif + + /* + * ESPFIX is a strange bug. All real CPUs have it. Paravirt + * systems that run Linux at CPL > 0 may or may not have the + * issue, but, even if they have the issue, there's absolutely + * nothing we can do about it because we can't use the real IRET + * instruction. + * + * NB: For the time being, only 32-bit kernels support + * X86_BUG_ESPFIX as such. 64-bit kernels directly choose + * whether to apply espfix using paravirt hooks. If any + * non-paravirt system ever shows up that does *not* have the + * ESPFIX issue, we can change this. + */ +#ifdef CONFIG_X86_32 +#ifdef CONFIG_PARAVIRT + do { + extern void native_iret(void); + if (pv_cpu_ops.iret == native_iret) + set_cpu_bug(c, X86_BUG_ESPFIX); + } while (0); +#else + set_cpu_bug(c, X86_BUG_ESPFIX); +#endif #endif }