Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1492273 > unrolled thread

RE: ATA failure regression

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  RE: ATA failure regression "Shah, Nehal-bakulchandra" <Nehal-bakulchandra.Shah@amd.com> - 2016-09-28 07:50 +0200
    Re: ATA failure regression "tj@kernel.org" <tj@kernel.org> - 2016-09-29 10:30 +0200
      Re: ATA failure regression Henrique de Moraes Holschuh <hmh@hmh.eng.br> - 2016-09-29 13:30 +0200
        Re: ATA failure regression "tj@kernel.org" <tj@kernel.org> - 2016-09-29 13:40 +0200

#1492273 — RE: ATA failure regression

Hi 

Can someone please help me to debug this issue?

Regards
Nehal

-----Original Message-----
From: Shah, Nehal-bakulchandra 
Sent: Monday, September 26, 2016 3:45 PM
To: 'Bharat Kumar Gogada' <bharat.kumar.gogada@xilinx.com>
Cc: Deucher, Alexander <Alexander.Deucher@amd.com>; linux-pci@vger.kernel.org; holler@ahsoftware.de; tj@kernel.org; linux-ide@vger.kernel.org; linux-kernel@vger.kernel.org
Subject: RE: ATA failure regression

Hi Bharat

Thanks for the reply. I have observed following thing

If IOMMU is enabled in BIOS and I use following option FCH SATA Debug Options --> Unused SATA Port Auto Shut Down Disabled. Issue is not happening. I have attached dmesg and lspci output with this option

Also I have attached lspci log with IOMMU disabled.

When issue is happening I am not able to take lspci logs as it stops in initramfs itself. I will try to get.


Thanks

Nehal
-----Original Message-----
From: Bharat Kumar Gogada [mailto:bharat.kumar.gogada@xilinx.com]
Sent: Friday, September 23, 2016 3:40 PM
To: Shah, Nehal-bakulchandra <Nehal-bakulchandra.Shah@amd.com>; linux-kernel@vger.kernel.org; linux-pci@vger.kernel.org; holler@ahsoftware.de; tj@kernel.org; linux-ide@vger.kernel.org
Cc: Deucher, Alexander <Alexander.Deucher@amd.com>
Subject: RE: ATA failure regression

> Hi All,
> 
> Resending this wider audience
> 
> Currently I am working on AMD future platform.  I am hitting the same 
> bug of ATA Failure Regression reported in past.
> (https://patchwork.kernel.org/patch/6875661/) or 
> http://lkml.iu.edu/hypermail/linux/kernel/1507.3/01961.html
> 
> I am newbie to this and because of this Ubuntu  16.04 is not booting. 
> If disable IOMMU and MSI obviously it works but that is not solution. 
> Even when I bisected it boiled to same place which was mentioned in past discussion.
> 
So here when you are disabling MSI, it is working with legacy interrupts or MSI-X.
Can you post the end sata device lscpi -xxx -vvv content. 

Bharat

[toc] | [next] | [standalone]

#1493197

Hello,

On Wed, Sep 28, 2016 at 05:45:08AM +0000, Shah, Nehal-bakulchandra wrote:
> Can someone please help me to debug this issue?

The only thing I can do from libata side is disbling msi on the
affected platform, but the problem doesn't seem confined to ahci, so
probably the right thing to do for now is disabling msi on the
platform?

Thanks.

-- 
tejun

[toc] | [prev] | [next] | [standalone]

#1493404

On Thu, 29 Sep 2016, tj@kernel.org wrote:
> On Wed, Sep 28, 2016 at 05:45:08AM +0000, Shah, Nehal-bakulchandra wrote:
> > Can someone please help me to debug this issue?
> 
> The only thing I can do from libata side is disbling msi on the
> affected platform, but the problem doesn't seem confined to ahci, so
> probably the right thing to do for now is disabling msi on the
> platform?

Actually, according to Shah's post from the 26th to this thread,
everything works just fine even with the IOMMU enabled, as long as the
system is configured to NOT auto-shutdown unused SATA ports.

That seems to give some extra avenues at fixing/working around the
issue, maybe?

-- 
  Henrique Holschuh

[toc] | [prev] | [next] | [standalone]

#1493414

Hello,

(cc'ing Dan, hi!)

On Thu, Sep 29, 2016 at 08:25:58AM -0300, Henrique de Moraes Holschuh wrote:
> Actually, according to Shah's post from the 26th to this thread,
> everything works just fine even with the IOMMU enabled, as long as the
> system is configured to NOT auto-shutdown unused SATA ports.
> 
> That seems to give some extra avenues at fixing/working around the
> issue, maybe?

Hmm... it could be that the multiple msix routing gets screwed when
the bios disables unoccupied ports.  Dan, can you please look into
this?  Shah is seeing ahci failing during boot on an AMD platform with
msi enabled.  If disabling of unoccupied ports is turned off in bios,
the problem goes away.  Maybe we're mapping the irqs incorrectly in
such cases?

Thanks.

-- 
tejun

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web