From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Message-ID: <17490.43037.407086.355772@cargo.ozlabs.ibm.com> Date: Sat, 29 Apr 2006 09:41:17 +1000 From: Paul Mackerras To: Kumar Gala Subject: Re: alignment exceptionhandler sleeps in invalid context In-Reply-To: <27BDABD8-B970-4F2C-AA0A-07D55A9D3303@kernel.crashing.org> References: <20060424173246.GA22318@suse.de> <17489.63055.968862.256370@cargo.ozlabs.ibm.com> <20060428111942.GA15646@suse.de> <27BDABD8-B970-4F2C-AA0A-07D55A9D3303@kernel.crashing.org> Cc: linuxppc-dev@ozlabs.org, Olaf Hering List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Kumar Gala writes: > I was going to ask how this was actually hit. It seems odd that we > would have an alignment error in the network stack. From the oops > can we determine what the instruction was that faulted and what > address it was trying to access. No, it's not particularly odd, given that our get_unaligned() and put_unaligned() in include/asm-powerpc/unaligned.h just do a single access. That makes the common case (address is actually aligned, or cpu handles it in hardware) fast at the expense of occasionally taking an alignment exception. Paul.