Announcement

Collapse
No announcement yet.

Qualcomm's Open Kernel Driver Leads To A Dirty Mess

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • Qualcomm's Open Kernel Driver Leads To A Dirty Mess

    Phoronix: Qualcomm's Open Kernel Driver Leads To A Dirty Mess

    Well, it sounded nice when Qualcomm announced an open-source 2D/3D kernel driver for their Snapdragon platform that's used by phones like the Nexus One and Dell Streak, but it turns out that their user-space Linux driver that hooks into this kernel driver is currently a closed-source blob. This has led to the eternal debate about open-source kernel components but with only closed-source components...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    I just can't understand. Why is it worth to pay a few people to make a closed source driver than releasing the source and get a much better driver for almost free...?

    Comment


    • #3
      Originally posted by balihb View Post
      I just can't understand. Why is it worth to pay a few people to make a closed source driver than releasing the source and get a much better driver for almost free...?
      Because the rule of thumb is that your chances of getting a good GPU driver are proportional to your willingness to hire skilled people to write one.

      Comment


      • #4
        As it should be. Props to David!

        Comment


        • #5
          Wait, can I actually overwrite my passwd file to gain 5 FPS in games??? Why NOBODY told me?

          Comment


          • #6
            Originally posted by yotambien View Post
            Wait, can I actually overwrite my passwd file to gain 5 FPS in games??? Why NOBODY told me?
            I was actually wondering how a command executed by the GPU could possibly modify a file on a FS, but that might just be me...

            Comment


            • #7
              @Qaridarium

              Maybe you always try too experimental driver combinations. Use Kanotix

              Comment


              • #8
                Originally posted by V!NCENT View Post
                I was actually wondering how a command executed by the GPU could possibly modify a file on a FS, but that might just be me...
                I'm pretty sure Dave was being facetious in that particular spot (using that as an absurd example of sacrificing a core goal like security/reliability). As he alludes to later in the message, though, an insecure GPU driver could potentially be used to read/write arbitrary RAM with DMA operations, which means that an attacker could modify/replace privileged code. The DRM driver might inspect these operations and reject ones that go out of the appropriate bounds, but again it might be hard to know whether that's happening (or happening correctly) if they're trying to keep the GPU programming details a secret.

                Comment


                • #9
                  Originally posted by Ex-Cyber View Post
                  I'm pretty sure Dave was being facetious in that particular spot (using that as an absurd example of sacrificing a core goal like security/reliability).
                  Uuuh, you never know. Sometimes there are hidden bugs/features where least expected.

                  Comment


                  • #10
                    Originally posted by Ex-Cyber View Post
                    I'm pretty sure Dave was being facetious in that particular spot (using that as an absurd example of sacrificing a core goal like security/reliability). As he alludes to later in the message, though, an insecure GPU driver could potentially be used to read/write arbitrary RAM with DMA operations, which means that an attacker could modify/replace privileged code. The DRM driver might inspect these operations and reject ones that go out of the appropriate bounds, but again it might be hard to know whether that's happening (or happening correctly) if they're trying to keep the GPU programming details a secret.
                    Got it in one. There's a reason RagePRO doesn't have 3D support without DIY intervention- it's because there's no way to do this very safeguarding even WITH the info to drive it with.

                    What surprises me is that Dave names 6 players in the ARM space for 3D, naming a few that I know for a fact are buying other people's 3D cores. Yes, there's 6 games in town right at the moment, all closed.

                    The list I know about is:

                    Imagination Technologies
                    Qualcomm
                    ARM
                    DMP
                    NVIDIA

                    To be sure, there might be a few more, but Freescale, Samsung, and Marvell are just buying cores from someone else (like TI's doing)- in most of the cases they're buying from ImgTec.

                    I honestly wish someone would wise up and realize that it is better to hand us most of the keys to the kingdom and flourish than to fight with us and languish. The first credible player to have a fully open decently performing FOSS 3D stack wins and wins big. I think there might be behind the scenes pressure on at least 2-3 of those on the list to make things much, much more open, based on some of my rumor grapevine info. We'll just have to see, won't we?

                    Comment

                    Working...
                    X