Date: Tue, 1 Jul 2008 14:58:53 +0200 From: =?ISO-8859-1?Q?S=F8ren_Schmidt?= <sos@FreeBSD.ORG> To: "Daniel Eriksson" <daniel_k_eriksson@telia.com> Cc: legioner.r@gmail.com, morten@lightworkings.dk, freebsd-stable@FreeBSD.ORG Subject: Re: MCP55 SATA data corruption in FreeBSD 7 Message-ID: <7ABD8B47-2ECD-457E-908D-E0BED4C6AE56@FreeBSD.ORG> In-Reply-To: <4F9C9299A10AE74E89EA580D14AA10A61A1968@royal64.emp.zapto.org> References: <4F9C9299A10AE74E89EA580D14AA10A61A1968@royal64.emp.zapto.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--Apple-Mail-1-386732697
Content-Type: text/plain;
charset=ISO-8859-1;
format=flowed;
delsp=yes
Content-Transfer-Encoding: quoted-printable
Hi
OK, the only "modern" nVidia board I have is MCP51 based, however it =20
uses the same codepath as the MCP55.
Anyhow, there has been fixes fro these in -current, thats not in any =20
of the releng's yet.
Please try the attached patch, or even better try a -current kernel.
-S=F8ren
--Apple-Mail-1-386732697
Content-Disposition: attachment;
filename=ff
Content-Type: application/octet-stream;
x-unix-mode=0644;
name="ff"
Content-Transfer-Encoding: 7bit
Index: ata-chipset.c
===================================================================
RCS file: /home/ncvs/src/sys/dev/ata/ata-chipset.c,v
retrieving revision 1.202.2.7
diff -u -r1.202.2.7 ata-chipset.c
--- ata-chipset.c 1 Apr 2008 15:20:49 -0000 1.202.2.7
+++ ata-chipset.c 1 Jul 2008 12:57:01 -0000
@@ -3147,15 +3475,23 @@
struct ata_channel *ch = device_get_softc(dev);
int offset = ctlr->chip->cfg2 & NV4 ? 0x0440 : 0x0010;
int shift = ch->unit << (ctlr->chip->cfg2 & NVQ ? 4 : 2);
- u_int32_t istatus = ATA_INL(ctlr->r_res2, offset);
+ u_int32_t istatus;
+
+ /* get interrupt status */
+ if (ctlr->chip->cfg2 & NVQ)
+ istatus = ATA_INL(ctlr->r_res2, offset);
+ else
+ istatus = ATA_INB(ctlr->r_res2, offset);
/* do we have any PHY events ? */
if (istatus & (0x0c << shift))
ata_sata_phy_check_events(dev);
/* clear interrupt(s) */
- ATA_OUTB(ctlr->r_res2, offset,
- (0x0f << shift) | (ctlr->chip->cfg2 & NVQ ? 0x00f000f0 : 0));
+ if (ctlr->chip->cfg2 & NVQ)
+ ATA_OUTL(ctlr->r_res2, offset, (0x0f << shift) | 0x00f000f0);
+ else
+ ATA_OUTB(ctlr->r_res2, offset, (0x0f << shift));
/* do we have any device action ? */
return (istatus & (0x01 << shift));
--Apple-Mail-1-386732697
Content-Type: text/plain;
charset=ISO-8859-1;
format=flowed;
delsp=yes
Content-Transfer-Encoding: quoted-printable
On 1Jul, 2008, at 11:01 , Daniel Eriksson wrote:
>
> I am having problems with silent data corruption on (some) drives
> connected to an MCP55 SATA controller.
>
> I have two servers, both running RELENG_7_0/amd64. One has the 570 =20
> Ultra
> chipset, the other has 570 SLI. Both chipsets have the MCP55 SATA
> controller.
>
> The server with 570 Ultra chipset has a bunch of older 250GB SATA-150
> drives hooked up to the MCP55 controller and it is working just fine.
> The server with 570 SLI chipset has a bunch of new SATA-300 drives
> hooked up to the MCP55 controller and it is giving me silent data
> corruption (easily detectable by running ZFS scrub, every time I run =20=
> it
> new checksum errors show up). I know the drives are good because when
> they are hooked up to another controller they work just fine.
>
> Unfortunately the drives does not have a jumper for setting SATA-150
> speed (they are Samsung 1 TB drives), and trying to force the drives =20=
> to
> SATA-150 speed with the "patch" provided by the manufacturer does not
> seem to work (the drives still negotiate SATA-300 speed). I will try =20=
> to
> get my hands on another older SATA-150 drive (or a new that can be
> jumpered) to verify if the culprit is the MCP55 revision (see below) =20=
> or
> the interface speed.
>
>
> NOT working (570 SLI)
> ---------------------
> atapci1@pci0:0:5:0: class=3D0x010185 card=3D0x72501462 =
chip=3D0x037f10de
> rev=3D0xa2 hdr=3D0x00
> vendor =3D 'Nvidia Corp'
> device =3D 'MCP55 SATA Controller'
> class =3D mass storage
> subclass =3D ATA
>
> Working (570 Ultra)
> -------------------
> atapci1@pci0:0:5:0: class=3D0x010185 card=3D0xcb8410de =
chip=3D0x037f10de
> rev=3D0xa3 hdr=3D0x00
> vendor =3D 'Nvidia Corp'
> device =3D 'MCP55 SATA Controller'
> class =3D mass storage
> subclass =3D ATA
>
> This is most likely related to kern/120296
> (http://www.freebsd.org/cgi/query-pr.cgi?pr=3Dkern/120296) and kern/=20=
> 121396
> (http://www.freebsd.org/cgi/query-pr.cgi?pr=3Dkern/121396).
>
>
> If someone else is having data corruption problems with drives =20
> connected
> to an MCP55 controller it might be worth testing if limiting the =20
> drives
> to SATA-150 makes a difference. It will most likely take me a while
> before I can verify this.
>
> ---
> Daniel Eriksson (http://www.toomuchdata.com/)
>
-S=F8ren
--Apple-Mail-1-386732697--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?7ABD8B47-2ECD-457E-908D-E0BED4C6AE56>