From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gate.crashing.org (gate.crashing.org [63.228.1.57]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id E4081B703D for ; Fri, 6 Apr 2012 08:12:49 +1000 (EST) Message-ID: <1333663961.3040.34.camel@pasglop> Subject: Re: [PATCH 03/12] powerpc: Rework runlatch code From: Benjamin Herrenschmidt To: Andreas Schwab Date: Fri, 06 Apr 2012 08:12:41 +1000 In-Reply-To: References: <1330680922-6894-1-git-send-email-benh@kernel.crashing.org> <1330680922-6894-4-git-send-email-benh__48089.0872575857$1330681158$gmane$org@kernel.crashing.org> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 Cc: linuxppc-dev@ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Thu, 2012-04-05 at 23:38 +0200, Andreas Schwab wrote: > Benjamin Herrenschmidt writes: > > > This moves the inlines into system.h and changes the runlatch > > code to use the thread local flags (non-atomic) rather than > > the TIF flags (atomic) to keep track of the latch state. > > > > The code to turn it back on in an asynchronous interrupt is > > now simplified and partially inlined. > > This breaks the X server in that it no longer receives SIGIO signals. Interesting. I have not observed that on my machine here, however I have seen on my dual G5 (and not on the quad) some occasional loss of interrupts for seconds which might be related. Have you verified that you can "fix" it with reverting just the above patch ? I would have more easily blamed the rest of my series than this specific one... Anyways, I'll have a closer look but it might have to wait for tuesday. Cheers, Ben.