via udma100 fix

via udma100 fix

[Dan Hollis]

I don't know if anyone noticed, but the supposed udma100 fix has been
posted here:

http://www.viahardware.com/download/viatweak.shtm

At the bottom of the page.

Technical discussion of the workaround (in german):
http://home.tiscalinet.de/au-ja/review-kt133a-4.html

-Dan

Re: via udma100 fix

[Andre Hedrick]

[-- Attachment #1: Type: text/plain, Size: 767 bytes --]

On Mon, 16 Apr 2001, Dan Hollis wrote:

> I don't know if anyone noticed, but the supposed udma100 fix has been
> posted here:
> 
> http://www.viahardware.com/download/viatweak.shtm
> 
> At the bottom of the page.
> 
> Technical discussion of the workaround (in german):
> http://home.tiscalinet.de/au-ja/review-kt133a-4.html
> 
> -Dan

Hi Dan,

This was sent to me the other day, is this waht you are talking about?

Cheers,

Andre Hedrick
Linux ATA Development
ASL Kernel Development
-----------------------------------------------------------------------------
ASL, Inc.                                     Toll free: 1-877-ASL-3535
1757 Houret Court                             Fax: 1-408-941-2071
Milpitas, CA 95035                            Web: www.aslab.com

[-- Attachment #2: Type: text/plain, Size: 1532 bytes --]

--- linux-2.4.3/drivers/pci/quirks.c.kicker	Sun Apr 15 20:38:42 2001
+++ linux-2.4.3/drivers/pci/quirks.c	Sun Apr 15 21:20:49 2001
@@ -85,6 +85,29 @@
 }
 
 /*
+ *	VIA Apollo KT133 needs PCI latency patch
+ *	Made according to a windows driver based patch by George E. Breese
+ *	see PCI Latency Adjust on http://www.viahardware.com/download/viatweak.shtm
+ */
+static void __init quirk_vialatency(struct pci_dev *dev)
+{
+	u8 r70;
+
+	printk(KERN_INFO "Applying VIA PCI latency patch.\n");
+	/*
+	 *    In register 0x70, mask off bit 2 (PCI Master read caching)
+	 *    and 1 (Delay Transaction)
+	 */
+	pci_read_config_byte(dev, 0x70, &r70);
+	r70 &= 0xf9;
+	pci_write_config_byte(dev, 0x70, r70);
+	/*
+	 *    Turn off PCI Latency timeout (set to 0 clocks)
+	 */
+	pci_write_config_byte(dev, 0x75, 0x80);
+}
+
+/*
  *	VIA Apollo VP3 needs ETBF on BT848/878
  */
  
@@ -275,6 +298,7 @@
 	{ PCI_FIXUP_FINAL,	PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443BX_2, 	quirk_natoma },
 	{ PCI_FIXUP_FINAL,	PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_5597,		quirk_nopcipci },
 	{ PCI_FIXUP_FINAL,	PCI_VENDOR_ID_SI,	PCI_DEVICE_ID_SI_496,		quirk_nopcipci },
+	{ PCI_FIXUP_FINAL,	PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8363_0,	quirk_vialatency },
 	{ PCI_FIXUP_FINAL,	PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C597_0,	quirk_viaetbf },
 	{ PCI_FIXUP_HEADER,	PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C597_0,	quirk_vt82c598_id },
 	{ PCI_FIXUP_HEADER,	PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C586_3,	quirk_vt82c586_acpi },

Re: via udma100 fix

[Dan Hollis]

On Mon, 16 Apr 2001, Andre Hedrick wrote:
> On Mon, 16 Apr 2001, Dan Hollis wrote:
> > Technical discussion of the workaround (in german):
> > http://home.tiscalinet.de/au-ja/review-kt133a-4.html
> This was sent to me the other day, is this waht you are talking about?

Yes, is any of the information applicable to your via driver?

-Dan

Re: via udma100 fix

[David Balazic]

Andre Hedrick (andre@linux-ide.org) wrote :

> Hi Dan, 
> 
> This was sent to me the other day, is this waht you are talking about? 
> 
> Cheers, 

+       /*
+        *    Turn off PCI Latency timeout (set to 0 clocks)
+        */
+       pci_write_config_byte(dev, 0x75, 0x80);

Is turning off PCI Latency a good thing ?

Anyway the article (http://home.tiscalinet.de/au-ja/review-kt133a-4.html)
says that any value below 32 is good, so why not use 16 for example ?

-- 
David Balazic
--------------
"Be excellent to each other." - Bill & Ted
- - - - - - - - - - - - - - - - - - - - - -