lkml.org 
[lkml]   [2008]   [Aug]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] seqlock: serialize against writers

On Fri, 29 Aug 2008, Gregory Haskins wrote:
>
> Yeah, ideas crossed in the mail ;)
>
> I could just force all of the seqbegins to hit the slowpath by hacking
> the code and see what happens (aside from slowing down, of course ;)
>
> Question: Which seqlock_t does userspace use? I assume it uses
> seqlock_t and not raw_seqlock_t. But the only reason that I ask is that
> I converted raw_seqlock_t to use the new style as well to be consistent,
> even though it is not strictly necessary for the same reasons. So if
> perchance userspace uses the raw variant, I could solve this issue by
> only re-working the seqlock_t variant. Kind of a long shot, but figured
> I would mention it :)

I answered this on IRC, but this is for the rest of those reading this
thread.

Userspace (vsyscalls) can only use raw_seqlock_t. And only the read
version for that matter. Since the read of raw_seqlock_t is just that, a
read, no writes, and no jumping to other functions on contention.

The vsyscalls should never use the -rt seqlock_t. Not modifying the raws
here should make us golden.

-- Steve



\
 
 \ /
  Last update: 2008-08-29 19:01    [from the cache]
©2003-2014 Jasper Spaans. Advertise on this site