Messages in this thread | | | Subject | Re: [PATCH 1/2] mmap.2: clarify MAP_LOCKED semantic | From | Peter Zijlstra <> | Date | Wed, 11 May 2016 13:18:05 +0200 |
| |
On 05/11/2016 01:07 PM, Peter Zijlstra wrote: > On 05/13/2015 04:38 PM, Michal Hocko wrote: >> >> This patch makes the semantic of MAP_LOCKED explicit and suggest using >> mmap + mlock as the only way to guarantee no later major page faults. >> > > URGH, this really blows chunks. It basically means MAP_LOCKED is > pointless cruft and we might as well remove it. > > Why not fix it proper?
OK; after having been pointed at this discussion, it seems I reacted rather too hasty in that I didn't read all the previous threads.
From that it appears fixing this proper is indeed rather hard, and we should indeed consider MAP_LOCKED broken. At which point I would've worded the manpage update stronger, but alas.
Sorry for the noise.
| |