Commit 318f5a2a authored by Andy Lutomirski's avatar Andy Lutomirski Committed by H. Peter Anvin
Browse files

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"
(c9712944), 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: default avatarAndy Lutomirski <luto@mit.edu>
Link: http://lkml.kernel.org/r/f4fcb3947340d9e96ce1054a432f183f9da9db83.1312378163.git.luto@mit.edu


Reported-by: default avatarKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: default avatarH. Peter Anvin <hpa@linux.intel.com>
parent 5d5791af

arch/x86/include/asm/desc.h

+2 −2
Original line number Diff line number Diff line
@@ -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;

}

arch/x86/include/asm/paravirt_types.h

+6 −0
Original line number Diff line number Diff line
@@ -41,6 +41,7 @@ 


#include <asm/desc_defs.h>

#include <asm/kmap_types.h>

#include <asm/pgtable_types.h>



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;

};

arch/x86/include/asm/ptrace.h

+19 −0
Original line number Diff line number Diff line
@@ -131,6 +131,9 @@ struct pt_regs { 
#ifdef __KERNEL__



#include <linux/init.h>

#ifdef CONFIG_PARAVIRT

#include <asm/paravirt_types.h>

#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

arch/x86/kernel/paravirt.c

+4 −0
Original line number Diff line number Diff line
@@ -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 = {

arch/x86/kernel/step.c

+1 −1
Original line number Diff line number Diff line
@@ -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 */

CRA Git | Maintained and supported by SUSTech CRA and CCSE