linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jeff Garzik <jgarzik@pobox.com>
To: linux-ide@vger.kernel.org
Cc: Ricky Beam <jfbeam@bluetronic.net>,
	Linux Kernel <linux-kernel@vger.kernel.org>
Subject: [PATCH] fix sata_sil quirk
Date: Tue, 22 Jun 2004 16:22:33 -0400	[thread overview]
Message-ID: <40D89509.6010502@pobox.com> (raw)

[-- Attachment #1: Type: text/plain, Size: 727 bytes --]

Here's my suggested fix...  good catch Ricky.

Yes, unfortunately performance will be dog slow.

Silicon Image 311x is fully SATA compliant -- but it's the only 
controller that sends odd-sized packets to the SATA device.  That causes 
no end of problems, including the thing that SIL_QUIRK_MOD15WRITE 
attempts to work around.

I've got contacts at Silicon Image, and have been meaning to bug them 
for a "real fix" for a while.  It is rumored that there is a much better 
fix, which allows full performance while at the same time not killing 
your SATA drive due to odd-sized SATA frames on the wire.

Unfortunately, at this point in time, we must err on the side of caution 
and cripple performance, for stability.

	Jeff



[-- Attachment #2: patch --]
[-- Type: text/plain, Size: 1365 bytes --]

===== drivers/scsi/libata-scsi.c 1.39 vs edited =====
--- 1.39/drivers/scsi/libata-scsi.c	2004-05-12 11:46:21 -04:00
+++ edited/drivers/scsi/libata-scsi.c	2004-06-22 16:18:57 -04:00
@@ -182,7 +182,8 @@
 		 * 65534 when Jens Axboe's patch for dynamically
 		 * determining max_sectors is merged.
 		 */
-		if (dev->flags & ATA_DFLAG_LBA48) {
+		if ((dev->flags & ATA_DFLAG_LBA48) &&
+		    ((dev->flags & ATA_DFLAG_LOCK_SECTORS) == 0)) {
 			sdev->host->max_sectors = 2048;
 			blk_queue_max_sectors(sdev->request_queue, 2048);
 		}
===== drivers/scsi/sata_sil.c 1.26 vs edited =====
--- 1.26/drivers/scsi/sata_sil.c	2004-06-15 00:29:32 -04:00
+++ edited/drivers/scsi/sata_sil.c	2004-06-22 16:18:21 -04:00
@@ -302,6 +302,7 @@
 		       ap->id, dev->devno);
 		ap->host->max_sectors = 15;
 		ap->host->hostt->max_sectors = 15;
+		dev->flags |= ATA_DFLAG_LOCK_SECTORS;
 		return;
 	}
 
===== include/linux/libata.h 1.38 vs edited =====
--- 1.38/include/linux/libata.h	2004-06-22 00:54:44 -04:00
+++ edited/include/linux/libata.h	2004-06-22 16:17:44 -04:00
@@ -91,6 +91,7 @@
 	ATA_DFLAG_MASTER	= (1 << 2), /* is device 0? */
 	ATA_DFLAG_WCACHE	= (1 << 3), /* has write cache we can
 					     * (hopefully) flush? */
+	ATA_DFLAG_LOCK_SECTORS	= (1 << 4), /* don't adjust max_sectors */
 
 	ATA_DEV_UNKNOWN		= 0,	/* unknown device */
 	ATA_DEV_ATA		= 1,	/* ATA device */

             reply	other threads:[~2004-06-22 20:28 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-06-22 20:22 Jeff Garzik [this message]
2004-06-22 20:29 ` [PATCH] fix sata_sil quirk Ricky Beam
2004-06-22 20:41   ` Jeff Garzik
2004-06-22 22:12   ` Jeff Garzik
2004-06-23  0:34     ` Ricky Beam
2004-06-23  3:24 ` Paul Jakma
2004-06-23  3:39   ` Jeff Garzik
2004-06-23  3:46     ` Paul Jakma
2004-06-23  3:51       ` Jeff Garzik
2004-06-23  6:34         ` Ricky Beam
2004-06-28  1:54           ` George Georgalis
2004-09-27  3:40             ` George Georgalis

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=40D89509.6010502@pobox.com \
    --to=jgarzik@pobox.com \
    --cc=jfbeam@bluetronic.net \
    --cc=linux-ide@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).