diff options
| author | Andy Lutomirski <luto@MIT.EDU> | 2011-08-03 09:31:53 -0400 |
|---|---|---|
| committer | H. Peter Anvin <hpa@linux.intel.com> | 2011-08-04 16:13:49 -0700 |
| commit | 318f5a2a672152328c9fb4dead504b89ec738a43 (patch) | |
| tree | d37bcc93c8c1b29c057c44dac13148531706631e /arch/x86/kernel | |
| parent | 5d5791af4c0d4fd32093882357506355c3357503 (diff) | |
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 <luto@mit.edu>
Link: http://lkml.kernel.org/r/f4fcb3947340d9e96ce1054a432f183f9da9db83.1312378163.git.luto@mit.edu
Reported-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Diffstat (limited to 'arch/x86/kernel')
| -rw-r--r-- | arch/x86/kernel/paravirt.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/step.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/vsyscall_64.c | 6 |
3 files changed, 6 insertions, 6 deletions
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 869e1aeeb71..681f1599421 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 7977f0cfe33..c346d116148 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 dda7dff9cef..1725930a6f9 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 |