From owner-freebsd-scsi Mon Sep 13 13:58:52 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from duke.cs.duke.edu (duke.cs.duke.edu [152.3.140.1]) by hub.freebsd.org (Postfix) with ESMTP id B6BCB15611 for ; Mon, 13 Sep 1999 13:58:38 -0700 (PDT) (envelope-from gallatin@cs.duke.edu) Received: from grasshopper.cs.duke.edu (grasshopper.cs.duke.edu [152.3.145.30]) by duke.cs.duke.edu (8.9.1/8.9.1) with ESMTP id QAA07270; Mon, 13 Sep 1999 16:58:36 -0400 (EDT) Received: (from gallatin@localhost) by grasshopper.cs.duke.edu (8.9.3/8.9.1) id QAA14361; Mon, 13 Sep 1999 16:58:04 -0400 (EDT) (envelope-from gallatin@cs.duke.edu) From: Andrew Gallatin MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Date: Mon, 13 Sep 1999 16:58:02 -0400 (EDT) To: "Justin T. Gibbs" Cc: scsi@freebsd.org, anderson@cs.duke.edu, Don Lewis Subject: Re: data corruption when using aic7890 In-Reply-To: <199909131555.JAA14180@caspian.plutotech.com> References: <14301.2437.648605.15748@grasshopper.cs.duke.edu> <199909131555.JAA14180@caspian.plutotech.com> X-Mailer: VM 6.43 under 20.4 "Emerald" XEmacs Lucid Message-ID: <14301.23120.948268.723629@grasshopper.cs.duke.edu> Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Justin T. Gibbs writes: > > The DMA engine on these chips shouldn't require any external intervention > from the software side to deal with the FIFOs. You fire it up, and wait for > it to complete. > > Perhaps if you can better characterize how the data is corrupted I can > think of more things to check. I'll take a peek at the S/G and DMA > handling code in the firmware later today regardless. Does this help? Using the default driver settings & a more verbose test (prints every bad word) I see occasional behaviour like below -- ##error 0 page 41315 expected [0x000000000b1631b4] saw [0x00000000171b71b4] continuing ##error 1 page 41315 expected [0x000000000b1631b8] saw [0x00000000171b71b8] continuing ##error 2 page 41315 expected [0x000000000b1631bc] saw [0x00000000171b71bc] continuing ##error 3 page 41315 expected [0x000000000b1631c0] saw [0x00000000171b71c0] continuing ##error 4 page 41315 expected [0x000000000b1631c4] saw [0x00000000171b71c4] continuing ##error 5 page 41315 expected [0x000000000b1631c8] saw [0x00000000171b71c8] continuing ##error 6 page 41315 expected [0x000000000b1631cc] saw [0x00000000171b71cc] continuing ##error 7 page 41315 expected [0x000000000b1631d0] saw [0x00000000171b71d0] continuing ##error 8 page 41315 expected [0x000000000b1631d4] saw [0x00000000171b71d4] continuing ##error 9 page 41315 expected [0x000000000b1631d8] saw [0x00000000171b71d8] continuing ##error 10 page 41315 expected [0x000000000b1631dc] saw [0x00000000171b71dc] continuing ##error 11 page 41315 expected [0x000000000b1631e0] saw [0x00000000171b71e0] continuing ##error 12 page 41315 expected [0x000000000b1631e4] saw [0x00000000171b71e4] continuing ##error 13 page 41315 expected [0x000000000b1631e8] saw [0x00000000171b71e8] continuing ##error 14 page 41315 expected [0x000000000b1631ec] saw [0x00000000171b71ec] continuing ##error 15 page 41315 expected [0x000000000b1631f0] saw [0x00000000171b71f0] continuing ##error 16 page 41315 expected [0x000000000b1631f4] saw [0x00000000171b71f4] continuing ##error 17 page 41315 expected [0x000000000b1631f8] saw [0x00000000171b71f8] continuing ##error 18 page 41315 expected [0x000000000b1631fc] saw [0x00000000171b71fc] continuing This means that offsets 0x1b4 through 0x1fc are all bad, but the rest of the page is OK. The reuses buffers & doesn't prezero them, so what it found in the buffer is not really very meaningful. Thanks, Drew ------------------------------------------------------------------------------ Andrew Gallatin, Sr Systems Programmer http://www.cs.duke.edu/~gallatin Duke University Email: gallatin@cs.duke.edu Department of Computer Science Phone: (919) 660-6590 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message