Cc: Zhang, Yanmin <yanmin_zhang@...>, Andi Kleen <andi@...>, Matthew Wilcox <matthew@...>, LKML <linux-kernel@...>, Alexander Viro <viro@...>, Andrew Morton <akpm@...>, Thomas Gleixner <tglx@...>, H. Peter Anvin <hpa@...>
Ok, after having thought that over, and looked at the code, I think I like
your version after all. The old implementation was pretty complex due to
the need to be so extra careful about the count that could change outside
of the lock, so everything considered, a new implementation that is
simpler is probably the better choice.
Ergo, I will just pull your scheduler tree.
Linus
--
