From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756348Ab1HEFjS (ORCPT ); Fri, 5 Aug 2011 01:39:18 -0400 Received: from hera.kernel.org ([140.211.167.34]:45440 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756252Ab1HEFjP (ORCPT ); Fri, 5 Aug 2011 01:39:15 -0400 Date: Fri, 5 Aug 2011 05:39:07 GMT From: tip-bot for Andy Lutomirski Message-ID: Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@redhat.com, konrad.wilk@oracle.com, luto@mit.edu, tglx@linutronix.de, hpa@linux.intel.com, luto@mit.edu Reply-To: mingo@redhat.com, hpa@zytor.com, linux-kernel@vger.kernel.org, luto@mit.edu, konrad.wilk@oracle.com, tglx@linutronix.de, hpa@linux.intel.com, luto@mit.edu In-Reply-To: References: To: linux-tip-commits@vger.kernel.org Subject: [tip:x86/vdso] x86-64: Add user_64bit_mode paravirt op Git-Commit-ID: 318f5a2a672152328c9fb4dead504b89ec738a43 X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.3 (hera.kernel.org [127.0.0.1]); Fri, 05 Aug 2011 05:39:07 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 318f5a2a672152328c9fb4dead504b89ec738a43 Gitweb: http://git.kernel.org/tip/318f5a2a672152328c9fb4dead504b89ec738a43 Author: Andy Lutomirski AuthorDate: Wed, 3 Aug 2011 09:31:53 -0400 Committer: H. Peter Anvin CommitDate: Thu, 4 Aug 2011 16:13:49 -0700 x86-64: Add user_64bit_mode paravirt op Three places in the kernel assume that the only long mode CPL 3 selector is __USER_CS. This is not true on Xen -- Xen's sysretq changes cs to the magic value 0xe033. Two of the places are corner cases, but as of "x86-64: Improve vsyscall emulation CS and RIP handling" (c9712944b2a12373cb6ff8059afcfb7e826a6c54), vsyscalls will segfault if called with Xen's extra CS selector. This causes a panic when older init builds die. It seems impossible to make Xen use __USER_CS reliably without taking a performance hit on every system call, so this fixes the tests instead with a new paravirt op. It's a little ugly because ptrace.h can't include paravirt.h. Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/f4fcb3947340d9e96ce1054a432f183f9da9db83.1312378163.git.luto@mit.edu Reported-by: Konrad Rzeszutek Wilk Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/desc.h | 4 ++-- arch/x86/include/asm/paravirt_types.h | 6 ++++++ arch/x86/include/asm/ptrace.h | 19 +++++++++++++++++++ arch/x86/kernel/paravirt.c | 4 ++++ arch/x86/kernel/step.c | 2 +- arch/x86/kernel/vsyscall_64.c | 6 +----- arch/x86/mm/fault.c | 2 +- arch/x86/xen/enlighten.c | 4 ++++ 8 files changed, 38 insertions(+), 9 deletions(-) diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 7b439d9..41935fa 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -27,8 +27,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in desc->base2 = (info->base_addr & 0xff000000) >> 24; /* - * Don't allow setting of the lm bit. It is useless anyway - * because 64bit system calls require __USER_CS: + * Don't allow setting of the lm bit. It would confuse + * user_64bit_mode and would get overridden by sysret anyway. */ desc->l = 0; } diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8288509..96a0f80 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -41,6 +41,7 @@ #include #include +#include struct page; struct thread_struct; @@ -63,6 +64,11 @@ struct paravirt_callee_save { struct pv_info { unsigned int kernel_rpl; int shared_kernel_pmd; + +#ifdef CONFIG_X86_64 + u16 extra_user_64bit_cs; /* __USER_CS if none */ +#endif + int paravirt_enabled; const char *name; }; diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 94e7618..3566454 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -131,6 +131,9 @@ struct pt_regs { #ifdef __KERNEL__ #include +#ifdef CONFIG_PARAVIRT +#include +#endif struct cpuinfo_x86; struct task_struct; @@ -187,6 +190,22 @@ static inline int v8086_mode(struct pt_regs *regs) #endif } +#ifdef CONFIG_X86_64 +static inline bool user_64bit_mode(struct pt_regs *regs) +{ +#ifndef CONFIG_PARAVIRT + /* + * On non-paravirt systems, this is the only long mode CPL 3 + * selector. We do not allow long mode selectors in the LDT. + */ + return regs->cs == __USER_CS; +#else + /* Headers are too twisted for this to go in paravirt.h. */ + return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; +#endif +} +#endif + /* * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode * when it traps. The previous stack will be directly underneath the saved diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 869e1ae..681f159 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -299,6 +299,10 @@ struct pv_info pv_info = { .paravirt_enabled = 0, .kernel_rpl = 0, .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */ + +#ifdef CONFIG_X86_64 + .extra_user_64bit_cs = __USER_CS, +#endif }; struct pv_init_ops pv_init_ops = { diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 7977f0c..c346d11 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -74,7 +74,7 @@ static int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs) #ifdef CONFIG_X86_64 case 0x40 ... 0x4f: - if (regs->cs != __USER_CS) + if (!user_64bit_mode(regs)) /* 32-bit mode: register increment */ return 0; /* 64-bit mode: REX prefix */ diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index dda7dff..1725930 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -127,11 +127,7 @@ void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code) local_irq_enable(); - /* - * Real 64-bit user mode code has cs == __USER_CS. Anything else - * is bogus. - */ - if (regs->cs != __USER_CS) { + 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 diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2dbf6bf..c1d0182 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -105,7 +105,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, * but for now it's good enough to assume that long * mode only uses well known segments or kernel. */ - return (!user_mode(regs)) || (regs->cs == __USER_CS); + return (!user_mode(regs) || user_64bit_mode(regs)); #endif case 0x60: /* 0x64 thru 0x67 are valid prefixes in all modes. */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 5525163..78fe33d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -937,6 +937,10 @@ static const struct pv_info xen_info __initconst = { .paravirt_enabled = 1, .shared_kernel_pmd = 0, +#ifdef CONFIG_X86_64 + .extra_user_64bit_cs = FLAT_USER_CS64, +#endif + .name = "Xen", };