From: Jon Burgess <lkml@jburgess.uklinux.net>
To: raphael.rigo@inp-net.eu.org
Cc: linux kernel <linux-kernel@vger.kernel.org>
Subject: Re: [OOPS?] 2.6-test11 : problem about irq18.
Date: Mon, 08 Dec 2003 18:48:37 +0000 [thread overview]
Message-ID: <3FD4C785.4080306@jburgess.uklinux.net> (raw)
[-- Attachment #1: Type: text/plain, Size: 764 bytes --]
Raphaël Rigo wrote:
> Dec 7 18:27:45 pici kernel: Disabling IRQ #18
>
> I am using a P4 2.6 Ghz without HT activated
> 512 MB DDR PC3200 on an ASUS P4P800 Deluxe MB.
> HardDrive is on SATA (native mode) : Maxtor 6Y120MO.
Sounds like the known problem with an interrupt storm with the ICH5
See "Issue #2" at
http://www.ussg.iu.edu/hypermail/linux/kernel/0312.0/0597.html
> 2.4.23 doesn't have this problem but keeps using 30-50% CPU even if I
do nothing.
Try vmstat, I expect you'll see ~100k IRQ/s
You could try using the ata_piix driver (located amongst the SCSI drivers).
If that still doesn't help, you could try adding the patch attached to
drivers/scsi/libata-core.c
this should make the ata_piix driver catch the spurious interrupts
Jon
[-- Attachment #2: libata-spurious2.diff --]
[-- Type: text/plain, Size: 1322 bytes --]
--- libata-core.c-orig 2003-12-07 01:54:19.000000000 +0000
+++ libata-core.c 2003-12-07 16:25:11.961806872 +0000
@@ -2386,6 +2386,37 @@
}
/**
+ * ata_chk_spurious_int - Check for spurious interrupts
+ * @ap: port to which command is being issued
+ *
+ * Examines the DMA status registers and clears
+ * unexpected interrupts
+ *
+ * LOCKING:
+ */
+static inline void ata_chk_spurious_int(struct ata_port *ap) {
+ int host_stat;
+
+ if (ap->flags & ATA_FLAG_MMIO) {
+ void *mmio = (void *) ap->ioaddr.bmdma_addr;
+ host_stat = readb(mmio + ATA_DMA_STATUS);
+ } else
+ host_stat = inb(ap->ioaddr.bmdma_addr + ATA_DMA_STATUS);
+
+ if ((host_stat & (ATA_DMA_INTR | ATA_DMA_ERR | ATA_DMA_ACTIVE)) == ATA_DMA_INTR) {
+ if (ap->flags & ATA_FLAG_MMIO) {
+ void *mmio = (void *) ap->ioaddr.bmdma_addr;
+ writeb(host_stat & ~ATA_DMA_ERR, mmio + ATA_DMA_STATUS);
+ } else
+ outb(host_stat & ~ATA_DMA_ERR, ap->ioaddr.bmdma_addr + ATA_DMA_STATUS);
+
+ DPRINTK("ata%u: Caught spurious interrupt, status 0x%X\n", ap->id, host_stat);
+ udelay(1);
+ }
+}
+
+
+/**
* ata_interrupt -
* @irq:
* @dev_instance:
@@ -2417,6 +2448,7 @@
qc = ata_qc_from_tag(ap, ap->active_tag);
if (qc && ((qc->flags & ATA_QCFLAG_POLL) == 0))
handled += ata_host_intr(ap, qc);
+ ata_chk_spurious_int(ap);
}
}
next reply other threads:[~2003-12-08 18:48 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-12-08 18:48 Jon Burgess [this message]
[not found] ` <3FD5E454.2030404@inp-net.eu.org>
[not found] ` <3FD60552.5090903@jburgess.uklinux.net>
[not found] ` <3FD6094C.5040502@inp-net.eu.org>
[not found] ` <3FD60C5D.6010203@jburgess.uklinux.net>
[not found] ` <3FD60EC9.8040709@inp-net.eu.org>
[not found] ` <3FD614DB.7090207@jburgess.uklinux.net>
[not found] ` <3FD61615.30507@inp-net.eu.org>
[not found] ` <3FD6197B.1070704@jburgess.uklinux.net>
[not found] ` <3FD62990.80708@inp-net.eu.org>
2004-01-06 18:32 ` [2.6.1-rc2] SATA problem Jon Burgess
2004-01-06 19:01 ` Matthias Hentges
2004-01-06 20:06 ` Raphaël RIGO
-- strict thread matches above, loose matches on Subject: below --
2003-12-07 17:48 [OOPS?] 2.6-test11 : problem about irq18 Raphaël Rigo
2003-12-07 18:26 ` Zwane Mwaikambo
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=3FD4C785.4080306@jburgess.uklinux.net \
--to=lkml@jburgess.uklinux.net \
--cc=linux-kernel@vger.kernel.org \
--cc=raphael.rigo@inp-net.eu.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).