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 <redacted>; 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