This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

HiPCIe SATA reset issue

Hi,

I am using DM8168 processor with EZSDK version of 5_05_02_00 and my Linux version is linux-2.6.37-psp04.04.00.01.

I am trying to SATA disk through PCIe. While writing some more than 100 MB, the SATA disk is resetting and I am getting below error message:

ata1.00: exception Emask 0x0 SAct 0x1 SErr 0x0 action 0x6 frozen
ata1.00: failed command: WRITE FPDMA QUEUED
ata1.00: cmd 61/08:00:00:00:00/00:00:00:00:00/40 tag 0 ncq 4096 out
         res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
ata1.00: status: { DRDY }
ata1: hard resetting link
ata1: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
ata1.00: configured for UDMA/100
ata1.00: device reported invalid CHS sector 0
ata1: EH complete

Please let me know, what might be reason for this issue?

Thanks in advance.

Regards,
Salih

  • Salih,

    Have you tried with the latest linux kernel code base?

     http://arago-project.org/git/projects/?p=linux-omap3.git;a=shortlog;h=refs/heads/ti81xx-master

    Regards,
    Pavel

  • Hi Pavel,

    I am using the kernel linux-2.6.37-psp04.04.00.01 and the SDK is ti-ezsdk_dm816x-evm_5_05_02_00. 

    Any other latest kernel is available for this platform after this release?

    And also let me how to download that kernel from git link given by you in the above post

    arago-project.org/.../projects;a=shortlog;h=refs/heads/ti81xx-master

    Thank in advance.

    Regards,

    Salih

  • Muhammad Salih said:

    I am using the kernel linux-2.6.37-psp04.04.00.01 and the SDK is ti-ezsdk_dm816x-evm_5_05_02_00. 

    Any other latest kernel is available for this platform after this release?

    Yes, the one I provided to you.

    processors.wiki.ti.com/.../TI81XX_Linux_PSP_Releases

    Muhammad Salih said:

    And also let me how to download that kernel from git link given by you in the above post

    arago-project.org/.../projects;a=shortlog;h=refs/heads/ti81xx-master

     Click on the upper right "snapshot" button, then save/download the linux-omap3-97101e6c43c0e956dbc2863bd3e50ab70f987a91.tar.gz file.

    BR
    Pavel

  • hi Pavel,

    I am not seeing the "snapshot" button with your post. Still I am not clear on how to download the source code.

    Please help me out for the same.

    Thanks in advance.

    Regards,
    Salih
  • Muhammad Salih said:
    I am not seeing the "snapshot" button with your post.

    The "snapshot" button is not in my post, but in the link I have provided to you. The one below:

    Regards,
    Pavel

  • Hi Pavel,

    I am not seeing the file (linux-omap3-97101e6c43c0e956dbc2863bd3e50ab70f987a91.tar.gz) which the link you given above.

    The page screen shot is attached with this post.

    /cfs-file/__key/communityserver-discussions-components-files/791/4276.screenshot.9.jpg.zip

    Regards,
    Salih

  • Salih,

    Muhammad Salih said:

    This screenshot is not from the link I have provided to you.

    The screenshot from the link I have provided is attached:

    BR
    Pavel

  • Hi Pavel,

    Is there any changes done in the source code regarding PCIe-SATA.

    I have downloaded the source code and tested with the same. Getting the same issue.

    My PCIe-SATA device is 6Gbps. Whenver I am trying to partition it, I am getting this issue.

    And also I can able to write upto 10MB file at the instant. If it crosses, more than that, I am getting this reset error messages.

    ata1.00: exception Emask 0x0 SAct 0x1 SErr 0x0 action 0x6 frozen
    ata1.00: failed command: WRITE FPDMA QUEUED
    ata1.00: cmd 61/08:00:00:00:00/00:00:00:00:00/40 tag 0 ncq 4096 out
             res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
    ata1.00: status: { DRDY }
    ata1: hard resetting link
    ata1: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
    ata1.00: configured for UDMA/100
    ata1.00: device reported invalid CHS sector 0
    ata1: EH complete
    ata1.00: exception Emask 0x0 SAct 0x1 SErr 0x0 action 0x6 frozen
    ata1.00: failed command: WRITE FPDMA QUEUED
    ata1.00: cmd 61/08:00:00:00:00/00:00:00:00:00/40 tag 0 ncq 4096 out
             res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
    ata1.00: status: { DRDY }
    ata1: hard resetting link
    ata1: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
    ata1.00: qc timeout (cmd 0xec)
    ata1.00: failed to IDENTIFY (I/O error, err_mask=0x4)
    ata1.00: revalidation failed (errno=-5)
    ata1: hard resetting link
    ata1: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
    ata1.00: qc timeout (cmd 0xec)
    ata1.00: failed to IDENTIFY (I/O error, err_mask=0x4)
    ata1.00: revalidation failed (errno=-5)
    ata1: limiting SATA link speed to 3.0 Gbps
    ata1: hard resetting link
    ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 320)
    ata1.00: qc timeout (cmd 0xec)
    ata1.00: failed to IDENTIFY (I/O error, err_mask=0x4)
    ata1.00: revalidation failed (errno=-5)
    ata1.00: disabled
    ata1.00: device reported invalid CHS sector 0
    ata1: hard resetting link
    ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 320)
    ata1: EH complete
    sd 0:0:0:0: [sda] Unhandled error code
    sd 0:0:0:0: [sda]  Result: hostbyte=0x04 driverbyte=0x00
    sd 0:0:0:0: [sda] CDB: cdb[0]=0x2a: 2a 00 00 00 00 00 00 00 08 00
    end_request: I/O error, dev sda, sector 0
    Buffer I/O error on device sda, logical block 0
    lost page write due to I/O error on sda
    sd 0:0:0:0: [sda] READ CAPACITY(16) failed
    sd 0:0:0:0: [sda]  Result: hostbyte=0x04 driverbyte=0x00
    sd 0:0:0:0: [sda] Sense not available.
    sd 0:0:0:0: [sda] READ CAPACITY failed
    sd 0:0:0:0: [sda]  Result: hostbyte=0x04 driverbyte=0x00
    sd 0:0:0:0: [sda] Sense not available.
    sd 0:0:0:0: [sda] Asking for cache data failed
    sd 0:0:0:0: [sda] Assuming drive cache: write through
    sda: detected capacity change from 15013748736 to 0

    I am struggling with for long time. Please give me any solution to solve this issue.

    Thanks in advance.

    Regards,
    Salih

  • Muhammad Salih said:
    Is there any changes done in the source code regarding PCIe-SATA.

    Yes

    Muhammad Salih said:
    My PCIe-SATA device is 6Gbps.

    The SATA subsystem supports up to 3Gbps SATA devices. Can you test with 3Gbps SATA, do you have the same?

    See the below pointers for more info:

    Regards,
    Pavel

  • Hi Pavel,

    Thanks for your inputs. If my PCIe-SATA device is 6 Gbps, whether the controller will switch the Speed of the device to 3Gbps.
    If not, is it possible to change the speed of SATA in the Source code?.

    Please let me know the suggestions for the same.

    Thanks in advance.

    Regards
    Salih
  • Salih,

    The TI8168 PCIe (Peripheral Component Interconnect Express) module is a multi-lane I/O interconnect that provides low pin count, high reliability, and high-speed data transfer at rates of up to 5.0 Gbps per lane per direction, for serial links on backplanes and printed wiring boards. It is a 3rd Generation I/O Interconnect technology succeeding PCI and ISA bus that is designed to be used as a general-purpose serial I/O interconnect in multiple market segments, including desktop, mobile, server, storage and embedded communications. It is also used as a bridge to other interconnects like SATA, USB2/3.0, EMAC, etc.

    Have you tried with connecting this SATA disk to the DM816x SATA peripheral directly (not to the DM816x PCIe peripheral)?

    See if the below e2e threads will be in help:

    Regards,
    Pavel

  • Hi Pavel,

    Thanks for your inputs. I have tried the SATA with directly connected to SATA interface.

    But those SATA device speed is 3 Gbps and I am not facing any issue with that device.

    But whatever I am having the PCIe-SATA device which 6 Gbps is in speed. Here, I want to know whether this issue related to SATA driver or related PCIe.

    If it is related SATA, then no issues I can manage with some EP device in PCIe. In case of PCIe, I have to fix that issue.

    That is the reason I am asking the suggestion from e2e to switch the PCIe-SATA device to Gen2.


    Thanks in advance.

    Regards,
    Salih

  • Hi,

    I have tested with the Kernel which you provided in the above post. I am getting the same issue.

    I want to know in which register, have I to set the Speed of PCIe-SATA device. In case of auto detection in the Speed, I have to disable it in the source code.

    If you tell me the changes where I have to do in the source code, it will be easy for me to finalize this issue.

    I want to change my PCIe_SATA device speed from 6 Gbps to 3 Gbps in the driver.

    Thanks in advance.

    Regards,
    Salih

  • Hi,

    Any updates on this query?. I am keep on waiting for your valuable response. It is bottleneck for me to solve this issue.

    I need to release it to my Customer, as they are keep on waiting for my response in this issue.

    Please provide your inputs as soon as possible.

    Thanks in advance.

    Regards,
    Salih

  • Hi,

    Any updates on this query. I am keep on waiting for your response.

    Please at least do some response for this query irrespective of giving solution.

    Thanks in advance.

    Regards,
    Salih

  • Salih,

    I am checking this with the PCIe experts. I will update this thread but there will be delay. Sorry about that.

    Regards,
    Pavel
  • Hi,

    Any updates on this?

    Regards,
    Salih
  • Salih,

    The feedback from the team is this is unknown problem.

    Regards,
    Pavel
  • Hi Pavel,

    At least can I get the solution on how to set the Speed of the device to 3Gbps?

    Did TI test the same scenario in this processor?

    Thanks in advance.

    Regards,
    Salih
  • Haven't seen answer for this as reached with the unattended SATA resets with different mSATA types.
    Seems this is not related to device speeds nor their internal hw-buffering.
    Have someone diggt out the relation with the bus CRC Errors ?
    Some of the devices have reported enormous amounts of them.

    -niilo