From mboxrd@z Thu Jan 1 00:00:00 1970 From: Matt Helsley Subject: Re: suspend blockers & Android integration Date: Sun, 6 Jun 2010 07:43:22 -0700 Message-ID: <20100606144322.GC21016@count0.beaverton.ibm.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org To: Thomas Gleixner Cc: Arve =?iso-8859-1?B?SGr4bm5lduVn?= , "Rafael J. Wysocki" , Peter Zijlstra , Ingo Molnar , tytso@mit.edu, Brian Swetland , Neil Brown , Alan Stern , Felipe Balbi , LKML , Florian Mickler , Linux OMAP Mailing List , Linux PM , Alan Cox , James Bottomley , Linus Torvalds , Kevin Hilman , "H. Peter Anvin" , Arjan van de Ven List-Id: linux-omap@vger.kernel.org On Sun, Jun 06, 2010 at 12:36:21PM +0200, Thomas Gleixner wrote: > On Sat, 5 Jun 2010, Arve Hj=F8nnev=E5g wrote: > > events like input event go though a single thread in our system > > process, while other events like network packets (which are also > > wakeup events) goes directly to the app. If you want to wake up cgroup-frozen tasks for these fds perhaps your framework can fcnt(fd, F_SETOWN, ) to send SIGIO to a userspace-suspend-blocker thread/process/process group. When IO comes i= n, the suspend blocker is signalled which then unfreezes the cgroup of the fro= zen untrusted task. SIGIO works on pipes, fifos, sockets, ttys, and ptys -- many of which are precisely the kinds of things that would connect [tru= sted and untrusted] apps. Notably absent (last I checked): inotify fds, sign= alfd, timerfd, eventfd, filesystem fds and likely more. Incidentally, this is just to show that it's not impossible to implemen= t "wakeups" for cgroup-frozen tasks in userspace. Cheers, -Matt Helsley