From 318f5a2a672152328c9fb4dead504b89ec738a43 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 3 Aug 2011 09:31:53 -0400 Subject: 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 +++++++++++++++++++ 3 files changed, 27 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 7b439d9aea2a..41935fadfdfc 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 82885099c869..96a0f80407b8 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 94e7618fcac8..35664547125b 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 -- cgit v1.2.1 From fce8dc06423d6fb2709469dc5c55b04e09c1d126 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 10 Aug 2011 11:15:31 -0400 Subject: x86-64: Wire up getcpu syscall getcpu is available as a vdso entry and an emulated vsyscall. Programs that for some reason don't want to use the vdso should still be able to call getcpu without relying on the slow emulated vsyscall. It costs almost nothing to expose it as a real syscall. We also need this for the following patch in vsyscall=native mode. Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/6b19f55bdb06a0c32c2fa6dba9b6f222e1fde999.1312988155.git.luto@mit.edu Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/unistd_64.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 705bf139288c..d92641cc7acc 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -681,6 +681,8 @@ __SYSCALL(__NR_syncfs, sys_syncfs) __SYSCALL(__NR_sendmmsg, sys_sendmmsg) #define __NR_setns 308 __SYSCALL(__NR_setns, sys_setns) +#define __NR_getcpu 309 +__SYSCALL(__NR_getcpu, sys_getcpu) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR -- cgit v1.2.1 From 3ae36655b97a03fa1decf72f04078ef945647c1a Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 10 Aug 2011 11:15:32 -0400 Subject: x86-64: Rework vsyscall emulation and add vsyscall= parameter There are three choices: vsyscall=native: Vsyscalls are native code that issues the corresponding syscalls. vsyscall=emulate (default): Vsyscalls are emulated by instruction fault traps, tested in the bad_area path. The actual contents of the vsyscall page is the same as the vsyscall=native case except that it's marked NX. This way programs that make assumptions about what the code in the page does will not be confused when they read that code. vsyscall=none: Trying to execute a vsyscall will segfault. Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/8449fb3abf89851fd6b2260972666a6f82542284.1312988155.git.luto@mit.edu Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/irq_vectors.h | 4 ---- arch/x86/include/asm/traps.h | 2 -- arch/x86/include/asm/vsyscall.h | 6 ++++++ 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/x86/include') 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 */ -- cgit v1.2.1