On Tue, Apr 14, 2015 at 08:36:43PM +0200, Borislav Petkov wrote:
> 64MB out of how much? Does it even matter?
>
> You could turn off CONFIG_GART_IOMMU and not build aperture_64.c at all.
>
> I think then you'll fall back to swiotlb or whatever and that will most
> likely slow down DMA ... the
On Tue, Apr 14, 2015 at 08:36:43PM +0200, Borislav Petkov wrote:
64MB out of how much? Does it even matter?
You could turn off CONFIG_GART_IOMMU and not build aperture_64.c at all.
I think then you'll fall back to swiotlb or whatever and that will most
likely slow down DMA ... the story
On Tue, Apr 14, 2015 at 08:22:48PM +0200, Jörg-Volker Peetz wrote:
> thank you for the explanation. Somehow I thought I had a newer CPU w/o
> GART registers, but I misread the patch. Maybe wishful thinking, in
> the hope to save 64 MB :-(
64MB out of how much? Does it even matter?
You could turn
Hi,
Borislav Petkov wrote on 04/14/2015 13:33:
> On Tue, Apr 14, 2015 at 01:15:43PM +0200, Jörg-Volker Peetz wrote:
>> Hi,
>
> Hi,
>
> please do not top-post.
>
>> tried this patch on my HP Pavilion notebook wiht AMD Phenom II processor. The
>> BIOS has no IOMMU option.
>> With this patch I'm
On Tue, Apr 14, 2015 at 01:15:43PM +0200, Jörg-Volker Peetz wrote:
> Hi,
Hi,
please do not top-post.
> tried this patch on my HP Pavilion notebook wiht AMD Phenom II processor. The
> BIOS has no IOMMU option.
> With this patch I'm still seeing the AGP messages mention in the patch
>
Hi,
tried this patch on my HP Pavilion notebook wiht AMD Phenom II processor. The
BIOS has no IOMMU option.
With this patch I'm still seeing the AGP messages mention in the patch
description.
Is this processor affected at all? /proc/cpuinfo says "cpu family" 16. That is
10h?
Regards,
jvp.
Hi,
tried this patch on my HP Pavilion notebook wiht AMD Phenom II processor. The
BIOS has no IOMMU option.
With this patch I'm still seeing the AGP messages mention in the patch
description.
Is this processor affected at all? /proc/cpuinfo says cpu family 16. That is
10h?
Regards,
jvp.
On Tue, Apr 14, 2015 at 01:15:43PM +0200, Jörg-Volker Peetz wrote:
Hi,
Hi,
please do not top-post.
tried this patch on my HP Pavilion notebook wiht AMD Phenom II processor. The
BIOS has no IOMMU option.
With this patch I'm still seeing the AGP messages mention in the patch
description.
Hi,
Borislav Petkov wrote on 04/14/2015 13:33:
On Tue, Apr 14, 2015 at 01:15:43PM +0200, Jörg-Volker Peetz wrote:
Hi,
Hi,
please do not top-post.
tried this patch on my HP Pavilion notebook wiht AMD Phenom II processor. The
BIOS has no IOMMU option.
With this patch I'm still seeing
On Tue, Apr 14, 2015 at 08:22:48PM +0200, Jörg-Volker Peetz wrote:
thank you for the explanation. Somehow I thought I had a newer CPU w/o
GART registers, but I misread the patch. Maybe wishful thinking, in
the hope to save 64 MB :-(
64MB out of how much? Does it even matter?
You could turn
On Tue, Apr 07, 2015 at 03:34:19PM -0500, Aravind Gopalakrishnan wrote:
> On 4/7/2015 9:57 AM, Borislav Petkov wrote:
> >On Tue, Apr 07, 2015 at 09:46:26AM -0500, Aravind Gopalakrishnan wrote:
> >>Okay. I'll do that and correct the typos Ingo pointed out earlier and
> >>resend.
> >Btw, I think you
On Tue, Apr 07, 2015 at 03:34:19PM -0500, Aravind Gopalakrishnan wrote:
On 4/7/2015 9:57 AM, Borislav Petkov wrote:
On Tue, Apr 07, 2015 at 09:46:26AM -0500, Aravind Gopalakrishnan wrote:
Okay. I'll do that and correct the typos Ingo pointed out earlier and
resend.
Btw, I think you should do
On 4/7/2015 9:57 AM, Borislav Petkov wrote:
On Tue, Apr 07, 2015 at 09:46:26AM -0500, Aravind Gopalakrishnan wrote:
Okay. I'll do that and correct the typos Ingo pointed out earlier and
resend.
Btw, I think you should do the same in early_gart_iommu_check() too.
Doing the testing this way
On 4/7/2015 7:34 AM, Borislav Petkov wrote:
On Mon, Apr 06, 2015 at 06:10:22PM -0500, Aravind Gopalakrishnan wrote:
So what happens if !early_pci_allowed() but the GART is present? We'll
set amd_northbridges.flags |= AMD_NB_GART, but won't run any of the
setup code in aperture_64.c, right? Is
On Tue, Apr 07, 2015 at 09:46:26AM -0500, Aravind Gopalakrishnan wrote:
> Okay. I'll do that and correct the typos Ingo pointed out earlier and
> resend.
Btw, I think you should do the same in early_gart_iommu_check() too.
Doing the testing this way would mean that we first are testing for GART
On Mon, Apr 06, 2015 at 06:10:22PM -0500, Aravind Gopalakrishnan wrote:
> >So what happens if !early_pci_allowed() but the GART is present? We'll
> >set amd_northbridges.flags |= AMD_NB_GART, but won't run any of the
> >setup code in aperture_64.c, right? Is that a valid setup?
>
> It might be a
On Mon, Apr 06, 2015 at 06:10:22PM -0500, Aravind Gopalakrishnan wrote:
So what happens if !early_pci_allowed() but the GART is present? We'll
set amd_northbridges.flags |= AMD_NB_GART, but won't run any of the
setup code in aperture_64.c, right? Is that a valid setup?
It might be a valid
On 4/7/2015 7:34 AM, Borislav Petkov wrote:
On Mon, Apr 06, 2015 at 06:10:22PM -0500, Aravind Gopalakrishnan wrote:
So what happens if !early_pci_allowed() but the GART is present? We'll
set amd_northbridges.flags |= AMD_NB_GART, but won't run any of the
setup code in aperture_64.c, right? Is
On Tue, Apr 07, 2015 at 09:46:26AM -0500, Aravind Gopalakrishnan wrote:
Okay. I'll do that and correct the typos Ingo pointed out earlier and
resend.
Btw, I think you should do the same in early_gart_iommu_check() too.
Doing the testing this way would mean that we first are testing for GART
hw
On 4/7/2015 9:57 AM, Borislav Petkov wrote:
On Tue, Apr 07, 2015 at 09:46:26AM -0500, Aravind Gopalakrishnan wrote:
Okay. I'll do that and correct the typos Ingo pointed out earlier and
resend.
Btw, I think you should do the same in early_gart_iommu_check() too.
Doing the testing this way
On 4/2/2015 1:19 PM, Ingo Molnar wrote:
+ if (amd_gart_present())
amd_northbridges.flags |= AMD_NB_GART;
/*
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 76164e173a24..1cb170b06853 100644
--- a/arch/x86/kernel/aperture_64.c
+++
On 4/2/2015 1:19 PM, Ingo Molnar wrote:
+ if (amd_gart_present())
amd_northbridges.flags |= AMD_NB_GART;
/*
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 76164e173a24..1cb170b06853 100644
--- a/arch/x86/kernel/aperture_64.c
+++
* Borislav Petkov wrote:
> On Thu, Apr 02, 2015 at 12:04:21PM -0500, Aravind Gopalakrishnan wrote:
> > >No need - I can amend the local copy I have here.
>
> Here's what I did:
>
> ---
> From: Aravind Gopalakrishnan
> Date: Wed, 1 Apr 2015 09:32:08 -0500
> Subject: [PATCH] x86/gart: Check
On 4/2/2015 11:53 AM, Borislav Petkov wrote:
On Thu, Apr 02, 2015 at 11:23:17AM -0500, Aravind Gopalakrishnan wrote:
Sure, will do that and resend.
No need - I can amend the local copy I have here.
Okay.
Thanks!
-Aravind.
--
To unsubscribe from this list: send the line "unsubscribe
On Thu, Apr 02, 2015 at 12:04:21PM -0500, Aravind Gopalakrishnan wrote:
> >No need - I can amend the local copy I have here.
Here's what I did:
---
From: Aravind Gopalakrishnan
Date: Wed, 1 Apr 2015 09:32:08 -0500
Subject: [PATCH] x86/gart: Check for GART support before accessing GART
On Thu, Apr 02, 2015 at 11:23:17AM -0500, Aravind Gopalakrishnan wrote:
> Sure, will do that and resend.
No need - I can amend the local copy I have here.
--
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--
--
To unsubscribe from this list: send the line "unsubscribe
On 4/2/2015 11:06 AM, Ingo Molnar wrote:
We get "AGP:" messages on kernel logs like this-
[0.00] AGP: Node 0: aperture [bus addr 0x-0x01ff] (32MB)
[0.00] AGP: Your BIOS doesn't leave a aperture memory hole
[0.00] AGP: Please enable the IOMMU option in the
* Aravind Gopalakrishnan wrote:
> On 4/2/2015 5:01 AM, Ingo Molnar wrote:
> >* Aravind Gopalakrishnan wrote:
> >
> >>GART registers are not present in newer processors (Fam15h, Model 10h
> >>and later). So, avoid accesses to GART registers in PCI config
> >>space by returning early in
On 4/2/2015 5:01 AM, Ingo Molnar wrote:
* Aravind Gopalakrishnan wrote:
GART registers are not present in newer processors (Fam15h, Model 10h
and later). So, avoid accesses to GART registers in PCI config
space by returning early in early_gart_iommu_check() and
gart_iommu_hole_init() if GART
* Aravind Gopalakrishnan wrote:
> GART registers are not present in newer processors (Fam15h, Model 10h
> and later). So, avoid accesses to GART registers in PCI config
> space by returning early in early_gart_iommu_check() and
> gart_iommu_hole_init() if GART is not available.
In what fashion
On Wed, Apr 01, 2015 at 09:32:08AM -0500, Aravind Gopalakrishnan wrote:
> GART registers are not present in newer processors (Fam15h, Model 10h
> and later). So, avoid accesses to GART registers in PCI config
> space by returning early in early_gart_iommu_check() and
> gart_iommu_hole_init() if
On Wed, Apr 01, 2015 at 09:32:08AM -0500, Aravind Gopalakrishnan wrote:
GART registers are not present in newer processors (Fam15h, Model 10h
and later). So, avoid accesses to GART registers in PCI config
space by returning early in early_gart_iommu_check() and
gart_iommu_hole_init() if GART
* Aravind Gopalakrishnan aravind.gopalakrish...@amd.com wrote:
GART registers are not present in newer processors (Fam15h, Model 10h
and later). So, avoid accesses to GART registers in PCI config
space by returning early in early_gart_iommu_check() and
gart_iommu_hole_init() if GART is not
* Aravind Gopalakrishnan aravind.gopalakrish...@amd.com wrote:
On 4/2/2015 5:01 AM, Ingo Molnar wrote:
* Aravind Gopalakrishnan aravind.gopalakrish...@amd.com wrote:
GART registers are not present in newer processors (Fam15h, Model 10h
and later). So, avoid accesses to GART registers in
On 4/2/2015 5:01 AM, Ingo Molnar wrote:
* Aravind Gopalakrishnan aravind.gopalakrish...@amd.com wrote:
GART registers are not present in newer processors (Fam15h, Model 10h
and later). So, avoid accesses to GART registers in PCI config
space by returning early in early_gart_iommu_check() and
On 4/2/2015 11:06 AM, Ingo Molnar wrote:
We get AGP: messages on kernel logs like this-
[0.00] AGP: Node 0: aperture [bus addr 0x-0x01ff] (32MB)
[0.00] AGP: Your BIOS doesn't leave a aperture memory hole
[0.00] AGP: Please enable the IOMMU option in the BIOS
On Thu, Apr 02, 2015 at 11:23:17AM -0500, Aravind Gopalakrishnan wrote:
Sure, will do that and resend.
No need - I can amend the local copy I have here.
--
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--
--
To unsubscribe from this list: send the line unsubscribe
On Thu, Apr 02, 2015 at 12:04:21PM -0500, Aravind Gopalakrishnan wrote:
No need - I can amend the local copy I have here.
Here's what I did:
---
From: Aravind Gopalakrishnan aravind.gopalakrish...@amd.com
Date: Wed, 1 Apr 2015 09:32:08 -0500
Subject: [PATCH] x86/gart: Check for GART support
On 4/2/2015 11:53 AM, Borislav Petkov wrote:
On Thu, Apr 02, 2015 at 11:23:17AM -0500, Aravind Gopalakrishnan wrote:
Sure, will do that and resend.
No need - I can amend the local copy I have here.
Okay.
Thanks!
-Aravind.
--
To unsubscribe from this list: send the line unsubscribe
* Borislav Petkov b...@suse.de wrote:
On Thu, Apr 02, 2015 at 12:04:21PM -0500, Aravind Gopalakrishnan wrote:
No need - I can amend the local copy I have here.
Here's what I did:
---
From: Aravind Gopalakrishnan aravind.gopalakrish...@amd.com
Date: Wed, 1 Apr 2015 09:32:08 -0500
GART registers are not present in newer processors (Fam15h, Model 10h
and later). So, avoid accesses to GART registers in PCI config
space by returning early in early_gart_iommu_check() and
gart_iommu_hole_init() if GART is not available.
Refactoring the family check used in amd_nb into an inline
GART registers are not present in newer processors (Fam15h, Model 10h
and later). So, avoid accesses to GART registers in PCI config
space by returning early in early_gart_iommu_check() and
gart_iommu_hole_init() if GART is not available.
Refactoring the family check used in amd_nb into an inline
42 matches
Mail list logo