2 Replies Latest reply on Dec 16, 2015 11:26 AM by naimc

    HD4600 BSODs after wake from monitor sleep

    naimc

      Intel,  We have been trying to find the root cause of BSOD's that are occurring on 1000+ computers that have a i7-4765T with the HD4600 iGPU. OS is Windows 8.1 Enterprise x64 running the intel video driver versions 10.18.14.4170 or  10.18.14.4080.

       

      After collecting  500 GB worth of BSOD dumps we hired OSR to look at the dumps in order to find the root cause of the crashing. Here are the findings :

       

      "The systems are experiencing a wide variety of system crashes, though they appear to all trace back to a very consistent memory corruption pattern. Specifically, we are consistently seeing one of two values "randomly" appear in memory:

       

      •    0x00000010`00000004

      •    0x00000010`00400004

       

      Interestingly, when the corruption is discovered the value appears at physical memory page offset 0xFD8 (most common) or 0xD70 (less common).

       

      For example, in one crash the problem was that the MRXSMB20 image file is corrupted:

       

      3: kd> !chkimg -d mrxsmb20

      fffff800826a6fd8-fffff800826a6fdd  6 bytes - mrxsmb20!Smb2UpdateFileInfoCacheEntry+4c8

          [ 89 7d 18 49 89 45:04 00 00 00 10 00 ]

          fffff800826a6fdf - mrxsmb20!Smb2UpdateFileInfoCacheEntry+4cf (+0x07)

          [ e8:00 ]

      7 errors : mrxsmb20 (fffff800826a6fd8-fffff800826a6fdf)

       

      Dumping the start of the corrupted range, we see our offset and value:

       

      3: kd> dq fffff800826a6fd8

      fffff800`826a6fd8  00000010`00000004 4c2b894c`0000e99c

      fffff800`826a6fe8  ade901b6`41986d8b 850f02f8`83fffffd

      fffff800`826a6ff8  8bc03345`fffffbb5 445e15ff`ce8b49d7

      fffff800`826a7008  fb9f850f`c0840002 03fffffe`fee9ffff

       

      In another crash a pool header is corrupted:

       

      2: kd> !pool ffffc00089adcd70

      Pool page ffffc00089adcd70 region is Paged pool

      ...

      ffffc00089adcc00 size:  170 previous size:  b0  (Free )  MPsc

       

      ffffc00089adcd70 doesn't look like a valid small pool allocation, checking to see

      if the entire page is actually part of a large page allocation...

       

      2: kd> dq ffffc00089adcd70

      ffffc000`89adcd70  00000010`00000004 8d5eb149`4b83d33a

      ffffc000`89adcd80  00000000`00000000 ffffe000`bdecfec0

      ffffc000`89adcd90  ffffe000`bc728860 ffffc000`89adcd98

       

      Due to the fact that the crash appears at random in different virtual address ranges, we believe that the corruption must be generated by a device in the system (or by the platform)."

       

       

      The team as OSR also discovered that our "memory scribble" BSOD were mostly occurring around "power transitions states" on our computers. Examples just after a wake event; User logs-on move mouse or keyboard, Monitor wakes up from sleep BSOD.

       

      We disabled the monitor inactivity time-out sleep from all our 1000+ computers with the i7-4765T with the HD4600 iGPU. and the BSOD stopped ! (All our systems are on the windows high performance power profile with the idle monitor power-off disabled.)

       

      While reading the release notes for the new driver version  15.36.26.4294 I found this in the fixed section :

            " - Set monitor to turn off after 1 min. Unplug DVI monitor once monitor is off. System hang seen when DVI monitor is plugged back. - Windows 7 / 8"

       

      Would it be possible to have details regarding the nature of these systems hangs as we would like to know if they fit with the BSOD's types we have collected.


      Thank you.

        • 1. Re: HD4600 BSODs after wake from monitor sleep
          allan_intel

          Are you getting same BSOD with driver version 4332?

           

          Please try the driver linked below and let me know your findings:

          Download Intel® Graphics Driver for Windows 7/8.1* [15.36.28.4332]

           

          Allan.

          • 2. Re: HD4600 BSODs after wake from monitor sleep
            naimc

            Allan.

             

            No we have not tried 4332. I was not even aware it was released.  But reading the release notes it is apparent that our setup is different.

            * BSOD / Lockup when hot-plugging HDMI display to laptop after undocking it from tri-extended mode, reported against 5th Gen Graphics running Windows* 7 – 64 bit.  Issue resolved by adding registry key to ensure set mode call by OS is properly performed.

             

            Our monitors have DVI connection, connected to a DVI to Displayport adapter then going to a Display port on our computers.

             

            A discussion thread was started on OSR forum  :  OSR's ntdev List: Memory Corruption Mystery: Any Ideas? about the source of corruption pattern 0x00000010`00000004 and we all wondering if this could be coming from anything related to the HD4600; driver vbios etc.

            Its a long process to deploy a new driver versionto 1000+ computers, Re-enabled Monitor sleep in the windows power profile, then wait to see if the BSOD's return.  We are reluctant to make changes without the high likely hood of a positive outcome given that the BSOD's have now stopped

             

            thank you for the suggestion

             

            Naim.