[culprit found] Re: [boot hang] 2.6.7-rc2, VIA VT8237

[culprit found] Re: [boot hang] 2.6.7-rc2, VIA VT8237

[David Ford]

[-- Attachment #1: Type: text/plain, Size: 288 bytes --]

Culprit found.  If CONFIG_IOMMU_DEBUG is enabled, the machine will hang 
on boot at the partition check when using the VIA driver.

David Ford wrote:

> Both 2.6.5 and 2.6.7 will boot using the GENERIC IDE driver.  I 
> haven't yet gotten any kernel to not lock up using the VIA driver.


[-- Attachment #2: david+challenge-response.vcf --]
[-- Type: text/x-vcard, Size: 183 bytes --]

begin:vcard
fn:David Ford
n:Ford;David
email;internet:david@blue-labs.org
title:Industrial Geek
tel;home:Ask please
tel;cell:(203) 650-3611
x-mozilla-html:TRUE
version:2.1
end:vcard

Re: [culprit found] Re: [boot hang] 2.6.7-rc2, VIA VT8237

[Andi Kleen]

David Ford <david+challenge-response@blue-labs.org> writes:

> Culprit found.  If CONFIG_IOMMU_DEBUG is enabled, the machine will
> hang on boot at the partition check when using the VIA driver.

The real culprit is buggy VIA silicon. Use this patch.

-Andi

---------------------------------------------------------------
Enable VIA softmmu workaround for iommu=force/IOMMU_DEBUG too

diff -u linux-2.6.7rc3-bk3/arch/x86_64/kernel/io_apic.c-o linux-2.6.7rc3-bk3/arch/x86_64/kernel/io_apic.c
--- linux-2.6.7rc3-bk3/arch/x86_64/kernel/io_apic.c-o	2004-06-11 03:02:42.000000000 +0200
+++ linux-2.6.7rc3-bk3/arch/x86_64/kernel/io_apic.c	2004-06-12 15:46:35.000000000 +0200
@@ -252,7 +252,8 @@
 				switch (vendor) { 
 				case PCI_VENDOR_ID_VIA:
 #ifdef CONFIG_GART_IOMMU
-					if (end_pfn >= (0xffffffff>>PAGE_SHIFT) &&
+					if ((end_pfn >= (0xffffffff>>PAGE_SHIFT) ||
+					     force_iommu) &&
 					    !iommu_aperture_allowed) {
 						printk(KERN_INFO
     "Looks like a VIA chipset. Disabling IOMMU. Overwrite with \"iommu=allowed\"\n");

Re: [culprit found] Re: [boot hang] 2.6.7-rc2, VIA VT8237

[David Ford]

[-- Attachment #1: Type: text/plain, Size: 1177 bytes --]

Yep, that patch makes this thing bootable now :)

Thank you,
David

Andi Kleen wrote:

>David Ford <david+challenge-response@blue-labs.org> writes:
>
>  
>
>>Culprit found.  If CONFIG_IOMMU_DEBUG is enabled, the machine will
>>hang on boot at the partition check when using the VIA driver.
>>    
>>
>
>The real culprit is buggy VIA silicon. Use this patch.
>
>-Andi
>
>---------------------------------------------------------------
>Enable VIA softmmu workaround for iommu=force/IOMMU_DEBUG too
>
>diff -u linux-2.6.7rc3-bk3/arch/x86_64/kernel/io_apic.c-o linux-2.6.7rc3-bk3/arch/x86_64/kernel/io_apic.c
>--- linux-2.6.7rc3-bk3/arch/x86_64/kernel/io_apic.c-o	2004-06-11 03:02:42.000000000 +0200
>+++ linux-2.6.7rc3-bk3/arch/x86_64/kernel/io_apic.c	2004-06-12 15:46:35.000000000 +0200
>@@ -252,7 +252,8 @@
> 				switch (vendor) { 
> 				case PCI_VENDOR_ID_VIA:
> #ifdef CONFIG_GART_IOMMU
>-					if (end_pfn >= (0xffffffff>>PAGE_SHIFT) &&
>+					if ((end_pfn >= (0xffffffff>>PAGE_SHIFT) ||
>+					     force_iommu) &&
> 					    !iommu_aperture_allowed) {
> 						printk(KERN_INFO
>     "Looks like a VIA chipset. Disabling IOMMU. Overwrite with \"iommu=allowed\"\n");
>
>  
>

[-- Attachment #2: david+challenge-response.vcf --]
[-- Type: text/x-vcard, Size: 183 bytes --]

begin:vcard
fn:David Ford
n:Ford;David
email;internet:david@blue-labs.org
title:Industrial Geek
tel;home:Ask please
tel;cell:(203) 650-3611
x-mozilla-html:TRUE
version:2.1
end:vcard