Return-path: Received: from xc.sipsolutions.net ([83.246.72.84]:37087 "EHLO sipsolutions.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752838AbYKSNPp (ORCPT ); Wed, 19 Nov 2008 08:15:45 -0500 Subject: Re: [PATCH/RFT] iwlagn: fix RX skb alignment From: Johannes Berg To: Tomas Winkler Cc: John Linville , reinette chatre , Marcel Holtmann , "Luis R. Rodriguez" , "Rafael J. Wysocki" , Matt Mackall , Christophe Dumez , Zhu Yi , Jan =?UTF-8?Q?V=C4=8Del=C3=A1k?= , Thomas Witt , linux-wireless , Andres Freund In-Reply-To: <1227100347.26243.38.camel@johannes.berg> (sfid-20081119_141314_720850_5E82DA6A) References: <1226969241.4014.24.camel@johannes.berg> <1227001390.4014.43.camel@johannes.berg> <1ba2fa240811180613g48c94199s67e4334e89282e76@mail.gmail.com> <1227021904.4014.58.camel@johannes.berg> <1ba2fa240811190115i6bad0c89wb1d9c8ee281be2f8@mail.gmail.com> <1227094594.26243.6.camel@johannes.berg> <1ba2fa240811190422o4eebb26ai17ea12825ae8e708@mail.gmail.com> <1227097994.26243.33.camel@johannes.berg> <1ba2fa240811190502j274595e6lf02b957ae047b4c4@mail.gmail.com> (sfid-20081119_140215_205729_C9D74877) <1227100190.26243.36.camel@johannes.berg> (sfid-20081119_141052_748770_CFCF3F4F) <1227100347.26243.38.camel@johannes.berg> (sfid-20081119_141314_720850_5E82DA6A) Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-RLq6GQP+xmidG21+ocsp" Date: Wed, 19 Nov 2008 14:14:56 +0100 Message-Id: <1227100496.26243.40.camel@johannes.berg> (sfid-20081119_141549_012238_DE9A210C) Mime-Version: 1.0 Sender: linux-wireless-owner@vger.kernel.org List-ID: --=-RLq6GQP+xmidG21+ocsp Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Wed, 2008-11-19 at 14:12 +0100, Johannes Berg wrote: > On Wed, 2008-11-19 at 14:09 +0100, Johannes Berg wrote: > > On Wed, 2008-11-19 at 15:02 +0200, Tomas Winkler wrote: > >=20 > > > > Here's a thought: iwl_rx_queue_update_write_ptr doesn't synchronise= the > > > > pointer rxq->bd memory to the device. So if you have a platform tha= t's > > > > not cache coherent for IO devices (mine is) that might be a problem= . > > >=20 > > > Need to issue wmb() there or something like this? > >=20 > > well rb is also dma memory, no? So you'd have to use dma_sync_ or > > something, just like with skb data, no? >=20 > or maybe not? I can't look into this today, sorry. Ah, no, you don't have to because this is allocated with pci_alloc_consistent. I'm getting confused, sorry. johannes --=-RLq6GQP+xmidG21+ocsp Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Comment: Johannes Berg (powerbook) iQIcBAABAgAGBQJJJBFMAAoJEKVg1VMiehFYnKIQAJs8t6D5f/1M9BWaWi+8UlPk 3Wnbn/+w1mr63WZCNNImbtxaw5UGGVN5xuGLmRUUk+EFWrf47OHB36yyMY3W61/o A5ETxNGmboUv3JuTyhMzajg7r4FXZfmdt5y2OPDm4bHOzHzte9hzFqujT9H9Zaco KAplUYnNH4tzz4wb3EwIw884KVuO2c8/oY3ANe9zYuD97itZYFbijMdW8ZUwLrk1 227Lk8qiz3w6B1+I1ZLmjDvPfM9a28npurJFJAqkdQTaRbdGl/ovSU5DFcBhV+Hr mckmWiCeqcSw2SnESqcwmsv05zqJ6CykjVLP4m9BnIaSNSYcNMywBEYMk2VQoPhc RpoC1/AVjnmljDrRKEjBK53j5dmPSh5fn4/uTEj/jk6RDtNfJwAjANfNZLSxUqUb GuIN3U0a6RXHoYYztxsf4xopZWHciDaWbiaIZXihZRhWjV2LnhUhuWV4Dd1Vuc6+ tL8xRynGm2ZR5eYHMY20ruA/89GUoTLm7uNJbXzpi8jndVnLUIbqSweMPwbEPk13 Px+zY+E/0a+I6Azot0dP8tt1RkroK14eNmneDiTg1QXRChUtrYCK8JxR5ysuNWWb Ai4XrHZfP0+9mNkn/cCPu2Qt6iC8nN36brs6DSkN34XAzKRdtJmB6aPBhSNneYDs xpn6DLIWkzVcP7WE6xlC =ou0J -----END PGP SIGNATURE----- --=-RLq6GQP+xmidG21+ocsp--