From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Garzik Subject: Re: [RFT] sata_promise: intermittent errors bug hunting Date: Tue, 27 Feb 2007 18:16:11 -0500 Message-ID: <45E4BBBB.90504@garzik.org> References: <200702272225.l1RMPfSt021674@harpo.it.uu.se> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from srv5.dvmed.net ([207.36.208.214]:55873 "EHLO mail.dvmed.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752027AbXB0XQO (ORCPT ); Tue, 27 Feb 2007 18:16:14 -0500 In-Reply-To: <200702272225.l1RMPfSt021674@harpo.it.uu.se> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Mikael Pettersson Cc: linux-ide@vger.kernel.org Mikael Pettersson wrote: > + if (hp->flags & PDC_FLAG_GEN_II) { > + /* record ASIC rev */ > + pci_read_config_byte(pdev, PCI_REVISION_ID, &hp->asic_rev); > + > +#if 1 > + /* set cache line size = 1 */ > + pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &tmp); > + printk("%s: changing pci_cache_line_size from %#02x to 0x01\n", > + __FUNCTION__, tmp); > + pci_write_config_byte(pdev, PCI_CACHE_LINE_SIZE, 0x01); > +#endif This bit strikes me as somewhat dubious. If this proves to actually fix something, I would start by exporting pci_set_cacheline_size() in drivers/pci/pci.c, using it, and seeing if that helps. Jeff