Messages in this thread | | | From | Mateusz Guzik <> | Date | Sun, 3 Sep 2023 23:18:44 +0200 | Subject | Re: [PATCH v2] x86: bring back rep movsq for user access on CPUs without ERMS |
| |
On 9/3/23, Linus Torvalds <torvalds@linux-foundation.org> wrote: > On Sun, 3 Sept 2023 at 14:06, Mateusz Guzik <mjguzik@gmail.com> wrote: >> >> I don't think it is *that* bad. I did a quick sanity check on that >> front by rolling with bpftrace on cases which pass AT_EMPTY_PATH *and* >> provide a path. > > I guess you are right - nobody sane would use AT_EMPTY_PATH except if > they don't have a path. > > Of course, the only reason we're discussing this in the first place is > because people are doing insane things, which makes _that_ particular > argument very weak indeed... >
I put blame on whoever allowed non-NULL path and AT_EMPTY_PATH as a valid combination, forcing the user buf to be accessed no matter what. But I'm not going to go digging for names. ;)
-- Mateusz Guzik <mjguzik gmail.com>
| |