Announcement

Collapse
No announcement yet.

Further Analyzing The Intel CPU "x86 PTI Issue" On More Systems

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

  • Further Analyzing The Intel CPU "x86 PTI Issue" On More Systems

    Phoronix: Further Analyzing The Intel CPU "x86 PTI Issue" On More Systems

    2018 has been off to a busy start with all the testing around the Linux x86 PTI (Page Table Isolation) patches for this "Intel CPU bug" that potentially dates back to the Pentium days but has yet to be fully disclosed. Here is the latest.

    http://www.phoronix.com/vr.php?view=25772

  • #2
    Intel made a public statement - https://newsroom.intel.com/news/inte...arch-findings/

    Comment


    • #3
      Hmm, seems Intel is saying that the bug isn't only in their chips. That part about working with AMD and ARM could be taken as implying that they have problems as well. There's more weasels in that short press release than in most large pet stores.

      Comment


      • #4
        It's already been fixed in macOS 10.13.2 and was the first vendor to 'fix' the issue.

        https://www.macrumors.com/2018/01/03...macos-10-13-2/

        Comment


        • #5
          Originally posted by Awesome Donkey View Post
          It's already been fixed in macOS 10.13.2 and was the first vendor to 'fix' the issue.

          https://www.macrumors.com/2018/01/03...macos-10-13-2/
          What a stupid propaganda:

          According to The Register, which first shared details on the vulnerability, Windows and Linux machines will see a 5 to 30 percent slowdown once a fix is in place. It appears Macs may not be hit as heavily, as no noticeable performance slowdowns have been reported since the launch of macOS 10.13.2.
          And as article says 'it was partially addressed by Apple'. No wonder if performance drop isn't so high in this case. Furthermore, who has to report those slowdowns for Apple?

          Comment


          • #6
            Originally posted by willmore View Post
            There's more weasels in that short press release than in most large pet stores.
            They are coute, you have to admit .

            Comment


            • #7
              What kernel boot option did you use

              From the latest git document it is PTI=on,off
              I tested a model of mine and it showed no difference in operation. So either cpu-bound are not impacted (would align with IO-bound showing issues) or I was using the wrong switch

              Comment


              • #8
                Originally posted by willmore View Post
                Hmm, seems Intel is saying that the bug isn't only in their chips. That part about working with AMD and ARM could be taken as implying that they have problems as well. There's more weasels in that short press release than in most large pet stores.
                It's security hardening feature, which could be enabled on AMD and ARM-based silicons. It's not a workaround for silicon bug, it's a security feature which is now being enabled by default. Only Intel was proven to have issue in their silicon design, but in general it's a good security feature that could be enabled for more than Intel. The problem as mentioned is the cost of it while entering/exiting syscall or interrupt.

                Comment


                • #9
                  Originally posted by willmore View Post
                  Hmm, seems Intel is saying that the bug isn't only in their chips. That part about working with AMD and ARM could be taken as implying that they have problems as well. There's more weasels in that short press release than in most large pet stores.
                  https://www.youtube.com/watch?v=osSMJRyxG0k

                  Comment


                  • #10
                    Originally posted by davidlt View Post
                    It's security hardening feature, which could be enabled on AMD and ARM-based silicons. It's not a workaround for silicon bug, it's a security feature which is now being enabled by default. Only Intel was proven to have issue in their silicon design, but in general it's a good security feature that could be enabled for more than Intel. The problem as mentioned is the cost of it while entering/exiting syscall or interrupt.
                    Great way for Intel to spin the press, they aren't the bad guys of course (sarcasm)... meanwhile datacenters around the world have to deal with capacity issues.

                    Comment

                    Working...
                    X