Re: MSI broken in libata?

[Torsten Kaiser <just.for.lkml@googlemail.com>]

On Mon, Jan 11, 2010 at 2:15 AM, Tejun Heo <tj@kernel.org> wrote:
> On 01/10/2010 01:33 PM, Torsten Kaiser wrote:
>> I did try the patch from Robert Hancock in
>> http://lkml.org/lkml/2010/1/6/417 ,but without success.
>>
>> if you need any more information, or have something for me to try,
>> please just ask. I did look at the code and the documentation about
>> enabling MSI, but did not see anything (obvious) wrong, so I don't
>> know what to try next.
>
> Can you please try the attached patch?

Yes, but as expected it does not change the result.

After applying the patch and doing a test write, I got the following
error messages:
[   89.950055] ata2.00: exception Emask 0x0 SAct 0x1 SErr 0x0 action 0x6 frozen
[   89.960910] ata2.00: failed command: WRITE FPDMA QUEUED
[   89.969853] ata2.00: cmd 61/00:00:fd:27:3e/04:00:01:00:00/40 tag 0
ncq 524288 out
[   89.969855]          res 40/00:00:00:00:00/00:00:00:00:00/00 Emask
0x4 (timeout)
[   89.992210] ata2.00: status: { DRDY }
[   89.999569] ata2: hard resetting link
[   92.190069] ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 0)
[   97.190041] ata2.00: qc timeout (cmd 0xec)
[   97.197898] ata2.00: failed to IDENTIFY (I/O error, err_mask=0x5)
[   97.207622] ata2.00: revalidation failed (errno=-5)
[   97.216094] ata2: hard resetting link
[   99.410049] ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 0)
[  109.410027] ata2.00: qc timeout (cmd 0xec)
[  109.417694] ata2.00: failed to IDENTIFY (I/O error, err_mask=0x5)
[  109.427351] ata2.00: revalidation failed (errno=-5)
[  109.435733] ata2: limiting SATA link speed to 1.5 Gbps
[  109.444384] ata2: hard resetting link
[  111.640049] ata2: SATA link up 1.5 Gbps (SStatus 113 SControl 10)
[  141.640029] ata2.00: qc timeout (cmd 0xec)
[  141.647650] ata2.00: failed to IDENTIFY (I/O error, err_mask=0x5)
[  141.657255] ata2.00: revalidation failed (errno=-5)
[  141.665577] ata2.00: disabled
[  141.671956] ata2.00: device reported invalid CHS sector 0
[  141.680792] ata2: hard resetting link
[  143.880049] ata2: SATA link up 1.5 Gbps (SStatus 113 SControl 10)
[  143.880065] ata2: EH complete
[  143.880096] sd 1:0:0:0: [sdb] Unhandled error code
[  143.880099] sd 1:0:0:0: [sdb] Result: hostbyte=DID_BAD_TARGET
driverbyte=DRIVER_OK
[  143.880106] sd 1:0:0:0: [sdb] CDB: Write(10): 2a 00 01 3e 27 fd 00 04 00 00
[  143.880121] end_request: I/O error, dev sdb, sector 20850685

The last error gets repeated for different sectors, then the xfs
filesystem shuts itself down.

Torsten