From 3891a04aafd668686239349ea58f3314ea2af86b Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 29 Apr 2014 16:46:09 -0700 Subject: x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack The IRET instruction, when returning to a 16-bit segment, only restores the bottom 16 bits of the user space stack pointer. This causes some 16-bit software to break, but it also leaks kernel state to user space. We have a software workaround for that ("espfix") for the 32-bit kernel, but it relies on a nonzero stack segment base which is not available in 64-bit mode. In checkin: b3b42ac2cbae x86-64, modify_ldt: Ban 16-bit segments on 64-bit kernels we "solved" this by forbidding 16-bit segments on 64-bit kernels, with the logic that 16-bit support is crippled on 64-bit kernels anyway (no V86 support), but it turns out that people are doing stuff like running old Win16 binaries under Wine and expect it to work. This works around this by creating percpu "ministacks", each of which is mapped 2^16 times 64K apart. When we detect that the return SS is on the LDT, we copy the IRET frame to the ministack and use the relevant alias to return to userspace. The ministacks are mapped readonly, so if IRET faults we promote #GP to #DF which is an IST vector and thus has its own stack; we then do the fixup in the #DF handler. (Making #GP an IST exception would make the msr_safe functions unsafe in NMI/MC context, and quite possibly have other effects.) Special thanks to: - Andy Lutomirski, for the suggestion of using very small stack slots and copy (as opposed to map) the IRET frame there, and for the suggestion to mark them readonly and let the fault promote to #DF. - Konrad Wilk for paravirt fixup and testing. - Borislav Petkov for testing help and useful comments. Reported-by: Brian Gerst Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/r/1398816946-3351-1-git-send-email-hpa@linux.intel.com Cc: Konrad Rzeszutek Wilk Cc: Borislav Petkov Cc: Andrew Lutomriski Cc: Linus Torvalds Cc: Dirk Hohndel Cc: Arjan van de Ven Cc: comex Cc: Alexander van Heukelum Cc: Boris Ostrovsky Cc: # consider after upstream merge --- arch/x86/include/asm/setup.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/include/asm/setup.h') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 9264f04a4c55..9e3be3329a7e 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -57,6 +57,9 @@ extern void x86_ce4100_early_setup(void); static inline void x86_ce4100_early_setup(void) { } #endif +extern void init_espfix_bsp(void); +extern void init_espfix_ap(void); + #ifndef _SETUP /* -- cgit v1.2.3 From e1fe9ed8d2a4937510d0d60e20705035c2609aea Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 1 May 2014 14:12:23 -0700 Subject: x86, espfix: Move espfix definitions into a separate header file Sparse warns that the percpu variables aren't declared before they are defined. Rather than hacking around it, move espfix definitions into a proper header file. Reported-by: Fengguang Wu Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/espfix.h | 16 ++++++++++++++++ arch/x86/include/asm/setup.h | 5 ++--- arch/x86/kernel/espfix_64.c | 1 + 3 files changed, 19 insertions(+), 3 deletions(-) create mode 100644 arch/x86/include/asm/espfix.h (limited to 'arch/x86/include/asm/setup.h') diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h new file mode 100644 index 000000000000..729051c82b02 --- /dev/null +++ b/arch/x86/include/asm/espfix.h @@ -0,0 +1,16 @@ +#ifdef _ASM_X86_ESPFIX_H +#define _ASM_X86_ESPFIX_H + +#ifdef CONFIG_X86_64 + +#include + +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +extern void init_espfix_bsp(void); +extern void init_espfix_ap(void); + +#endif /* CONFIG_X86_64 */ + +#endif /* _ASM_X86_ESPFIX_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 9e3be3329a7e..ff4e7b236e21 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -57,11 +57,10 @@ extern void x86_ce4100_early_setup(void); static inline void x86_ce4100_early_setup(void) { } #endif -extern void init_espfix_bsp(void); -extern void init_espfix_ap(void); - #ifndef _SETUP +#include + /* * This is set up by the setup-routine at boot-time */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 8a64da36310f..6afbb16e9b79 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -40,6 +40,7 @@ #include #include #include +#include /* * Note: we only need 6*8 = 48 bytes for the espfix stack, but round -- cgit v1.2.3