On Tue, Jan 13, 2015 at 02:44:09PM -0800, Andy Lutomirski wrote: > 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 > ] Thanks for this, I'll go queue it up. greg k-h -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html