x86, vdso: Use asm volatile in __getcpu

commit 1ddf0b1b11aa8a90cef6706e935fc31c75c406ba upstream.

In Linux 3.18 and below, GCC hoists the lsl instructions in the
pvclock code all the way to the beginning of __vdso_clock_gettime,
slowing the non-paravirt case significantly.  For unknown reasons,
presumably related to the removal of a branch, the performance issue
is gone as of

e76b027e6408 x86,vdso: Use LSL unconditionally for vgetcpu

but I don't trust GCC enough to expect the problem to stay fixed.

There should be no correctness issue, because the __getcpu calls in
__vdso_vlock_gettime were never necessary in the first place.

Note to stable maintainers: In 3.18 and below, depending on
configuration, gcc 4.9.2 generates code like this:

     9c3:       44 0f 03 e8             lsl    %ax,%r13d
     9c7:       45 89 eb                mov    %r13d,%r11d
     9ca:       0f 03 d8                lsl    %ax,%ebx

This patch won't apply as is to any released kernel, but I'll send a
trivial backported version if needed.

[
 Backported by Andy Lutomirski.  Should apply to all affected
 versions.  This fixes a functionality bug as well as a performance
 bug: buggy kernels can infinite loop in __vdso_clock_gettime on
 affected compilers.  See, for exammple:

 https://bugzilla.redhat.com/show_bug.cgi?id=1178975
]

Fixes: 51c19b4f5927 x86: vdso: pvclock gettime support
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 2a46ca720afca5fd6f5e5010698e8eea56748837..2874be9aef0ae7f19efec928c66a4bb0394e0311 100644 (file)
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void)
                native_read_tscp(&p);
        } else {
                /* Load per CPU data from GDT */
-               asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+               asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
        }
 
        return p;