Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1307527
| From | Davidlohr Bueso <dave@stgolabs.net> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH] rbtree: use READ_ONCE in RB_EMPTY_ROOT |
| Date | 2016-01-12 16:20 +0100 |
| Message-ID | <qQ8TM-2LK-21@gated-at.bofh.it> (permalink) |
| References | <qPPo6-67U-19@gated-at.bofh.it> <qQ37I-7fJ-11@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
On Tue, 12 Jan 2016, Peter Zijlstra wrote: >On Mon, Jan 11, 2016 at 10:22:43AM -0800, Davidlohr Bueso wrote: >> With d72da4a4d97 (rbtree: Make lockless searches non-fatal) our rbtrees >> provide weak guarantees that allows us to do lockless (and very speculative) >> reads of the tree. Such readers cannot see partial stores on nodes, ie >> left/right as well as root. As such, similar to the WRITE_ONCE semantics when >> doing rotations, use READ_ONCE when checking the root node in RB_EMPTY_ROOT. > >No objection, but is this actually used anywhere? I found this because I wanted to use the waiter check in rtmutexes in a lockless fashion (ie rt_mutex_has_waiters). > >Or is this a just-in-case completeness thing? This too. Thanks, Davidlohr
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH] rbtree: use READ_ONCE in RB_EMPTY_ROOT Davidlohr Bueso <dave@stgolabs.net> - 2016-01-11 19:30 +0100
Re: [PATCH] rbtree: use READ_ONCE in RB_EMPTY_ROOT Peter Zijlstra <peterz@infradead.org> - 2016-01-12 10:10 +0100
Re: [PATCH] rbtree: use READ_ONCE in RB_EMPTY_ROOT Davidlohr Bueso <dave@stgolabs.net> - 2016-01-12 16:20 +0100
Re: [PATCH] rbtree: use READ_ONCE in RB_EMPTY_ROOT Peter Zijlstra <peterz@infradead.org> - 2016-01-12 17:00 +0100
csiph-web