[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1455045314-8305-1-git-send-email-dave@stgolabs.net>
Date: Tue, 9 Feb 2016 11:15:12 -0800
From: Davidlohr Bueso <dave@...olabs.net>
To: Mel Gorman <mgorman@...hsingularity.net>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...nel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Chris Mason <clm@...com>, Darren Hart <dvhart@...ux.intel.com>,
Hugh Dickins <hughd@...gle.com>, dave@...olabs.net,
linux-kernel@...r.kernel.org
Subject: [PATCH v6 0/2] futex: lockless get_futex_key
This is the continuation of the original patch, except with Ingo's
feedback about the ordering comments we have and how we reference
them throughout the code. Please consider for v4.6.
Thanks!
Changes from v5:
- Added patch 1 (Ingo).
Changes from v4:
- Integrated feedback from Hugh, specifically:
* check for page->mapping change with page lock held when
detecting shm race.
* move inode assign, if the mapping still matches what
we expect should we have a valid inode.
* move iput out of rcu lock.
Changes from v3:
- Redo mapping sanity check, now do not halt the kernel.
Changes from v2:
- Minor adjustments by peterz.
- Applies on top of -next-20160118
Changes from v1:
- Remove unnecesary mb, as atomic_inc returning does what we need.
- Fix bogus mapping load.
- Minor code cleanups/comments.
Davidlohr Bueso (2):
futex: Rename barrier references in ordering guarantees
futex: Remove requirement for lock_page in get_futex_key
kernel/futex.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++-----------
1 file changed, 107 insertions(+), 24 deletions(-)
--
2.1.4
Powered by blists - more mailing lists