Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 31 Jul 2017 13:20:34 +0000
From:      bugzilla-noreply@freebsd.org
To:        freebsd-bugs@FreeBSD.org
Subject:   [Bug 219399] System panics after several hours of 14-threads-compilation orgies using poudriere on AMD Ryzen...
Message-ID:  <bug-219399-8-tgmDxZiYgw@https.bugs.freebsd.org/bugzilla/>
In-Reply-To: <bug-219399-8@https.bugs.freebsd.org/bugzilla/>
References:  <bug-219399-8@https.bugs.freebsd.org/bugzilla/>

next in thread | previous in thread | raw e-mail | index | archive | help

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=219399

--- Comment #190 from rozhuk.im@gmail.com ---
    "On AMD, the tool discovered that some processors generate
    a #UD (undefined opcode) exception prior to completing the
    instruction fetch. Per AMD specifications, a #PF (page fault)
    exception occurring during an instruction fetch should
    supersede a #UD exception, but in the instruction search,
    which places the last bytes of the instruction on a non
    -
    executable page, some processors generate the #UD before the
    final bytes are moved off of the read/write page. It appears
    that AMD discovered this at around the same time as this
    research; the newest AMD Architecture Programmer’s
    Manual (March 2017) was updated to allow this situation."
From:
https://github.com/xoreaxeaxeax/sandsifter/blob/master/references/domas_breaking_the_x86_isa_wp.pdf
Tool: https://github.com/xoreaxeaxeax/sandsifter

-- 
You are receiving this mail because:
You are the assignee for the bug.


Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-219399-8-tgmDxZiYgw>