Announcement

Collapse
No announcement yet.

Bisected: The Unfortunate Reason Linux 4.20 Is Running Slower

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

  • Originally posted by ryao View Post
    1. AMD is vulnerable to Spectre v2.
    Only theoretically, not practically.. Which makes a huge difference in what kind of mitigations are warranted

    Originally posted by ryao View Post
    2. This patch is written in a way that should apply this mitigation to AMD hardware, whether it needs further mitigations or not.
    No, it it is written in a way where it COULD be applied to AMD hardware(*), but shouldn't necessarily, and isn't.

    Originally posted by ryao View Post
    3. Reports contradict #2.
    Not sure what you are talking about. You are contradicting yourself so much it is hard to keep track.

    * Note, when I repeat your term "AMD hardware" here, I mean Zen. Older AMD chips have indirect branch predicators more similar to Intels and are just as vulnerable. Only the latest Zen architectures have a newer design, that is effectively immune unless someone sets up specific circumstances, or a new trick is discovered.
    Last edited by carewolf; 11-18-2018, 07:32 PM.

    Comment


    • Originally posted by TemplarGR View Post
      AMD is only *realistically* vulnerable to the milder Spectre v1 variant.
      That was the situation when the first white papers and proof-of-concept attacks were published, since then we've learned that the situation isn't quite so rosy for AMD or ARM-based CPUs.

      Intel, being the dominant player in the market, is obviously what security researchers aim for and testing to see if the exploits work on AMD and ARM is something they may or may not do after they've found the issue on Intel and got the proof-of-concept working. With the latest set of speculative execution vulnerabilities, published only last week, they didn't even test them on AMD as they simply didn't have the hardware lying around.

      Don't get me wrong, Intel definitely has cut more corners than AMD, but having been and to some extent continuing to be the dominant player in the market they're obviously going to be under more scrutiny than anyone else. This additional scrutiny will obviously make the situation look more lopsided than it actually is.
      Last edited by L_A_G; 11-19-2018, 05:54 AM.
      "Why should I want to make anything up? Life's bad enough as it is without wanting to invent any more of it."

      Comment


      • Originally posted by L_A_G View Post

        That was the situation when the first white papers and proof-of-concept attacks were published, since then we've learned that the situation isn't quite so rosy for AMD or ARM-based CPUs.

        Intel, being the dominant player in the market, is obviously what security researchers aim for and testing to see if the exploits work on AMD and ARM is something they may or may not do after they've found the issue on Intel and got the proof-of-concept working. With the latest set of speculative execution vulnerabilities, published only last week, they didn't even test them on AMD as they simply didn't have the hardware lying around.

        Don't get me wrong, Intel definitely has cut more corners than AMD, but having been and to some extent continuing to be the dominant player in the market they're obviously going to be under more scrutiny than anyone else. This additional scrutiny will obviously make the situation look more lopsided than it actually is.
        Yeah, but the attitude you purvey about these researchers is just so ignorant and stupid because it doesn't reflect reality at all. If these researchers do in fact think like you describe, and somehow in my gut feelings I doubt that very much, then they can't possibly know for sure.

        Comment

        Working...
        X