From: Dave Hansen <dave.hansen@intel.com>
To: Nadav Amit <nadav.amit@gmail.com>, linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org, Nadav Amit <namit@vmware.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Andrew Cooper <andrew.cooper3@citrix.com>,
Andrew Morton <akpm@linux-foundation.org>,
Andy Lutomirski <luto@kernel.org>,
Dave Hansen <dave.hansen@linux.intel.com>,
Peter Xu <peterx@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Thomas Gleixner <tglx@linutronix.de>,
Will Deacon <will@kernel.org>, Yu Zhao <yuzhao@google.com>,
Nick Piggin <npiggin@gmail.com>,
x86@kernel.org
Subject: Re: [PATCH v2 3/5] x86/mm: check exec permissions on fault
Date: Mon, 25 Oct 2021 07:20:27 -0700 [thread overview]
Message-ID: <e55875fa-1264-7e08-3bb8-ed984f6ea5b3@intel.com> (raw)
In-Reply-To: <20211021122112.592634-4-namit@vmware.com>
On 10/21/21 5:21 AM, Nadav Amit wrote:
> access_error() currently does not check for execution permission
> violation.
Ye
> As a result, spurious page-faults due to execution permission
> violation cause SIGSEGV.
While I could totally believe that something is goofy when VMAs are
being changed underneath a page fault, I'm having trouble figuring out
why the "if (error_code & X86_PF_WRITE)" code is being modified.
> It appears not to be an issue so far, but the next patches avoid TLB
> flushes on permission promotion, which can lead to this scenario. nodejs
> for instance crashes when TLB flush is avoided on permission promotion.
Just to be clear, "promotion" is going from something like:
W=0->W=1
or
NX=1->NX=0
right? I tend to call that "relaxing" permissions.
Currently, X86_PF_WRITE faults are considered an access error unless the
VMA to which the write occurred allows writes. Returning "no access
error" permits continuing and handling the copy-on-write.
It sounds like you want to expand that. You want to add a whole class
of new faults that can be ignored: not just that some COW handling might
be necessary, but that the PTE itself might be out of date. Just like
a "COW fault" may just result in setting the PTE.W=1 and moving on with
our day, an instruction fault might now just end up with setting
PTE.NX=0 and also moving on with our day.
I'm really confused why the "error_code & X86_PF_WRITE" case is getting
modified. I would have expected it to be something like just adding:
/* read, instruction fetch */
if (error_code & X86_PF_INSN) {
/* Avoid enforcing access error if spurious: */
if (unlikely(!(vma->vm_flags & VM_EXEC)))
return 1;
return 0;
}
I'm really confused what X86_PF_WRITE and X86_PF_INSN have in common
other than both being able to (now) be generated spuriously.
next prev parent reply other threads:[~2021-10-25 14:20 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-21 12:21 [PATCH v2 0/5] mm/mprotect: avoid unnecessary TLB flushes Nadav Amit
2021-10-21 12:21 ` [PATCH v2 1/5] x86: Detection of Knights Landing A/D leak Nadav Amit
2021-10-26 15:54 ` Dave Hansen
2021-10-26 15:57 ` Nadav Amit
2021-10-21 12:21 ` [PATCH v2 2/5] mm: avoid unnecessary flush on change_huge_pmd() Nadav Amit
2021-10-25 10:52 ` Peter Zijlstra
2021-10-25 16:29 ` Nadav Amit
2021-10-26 16:06 ` Dave Hansen
2021-10-26 16:47 ` Nadav Amit
2021-10-26 16:53 ` Nadav Amit
2021-10-26 17:44 ` Nadav Amit
2021-10-26 18:44 ` Dave Hansen
2021-10-26 19:06 ` Nadav Amit
2021-10-26 19:40 ` Dave Hansen
2021-10-26 20:07 ` Nadav Amit
2021-10-26 20:47 ` Dave Hansen
2021-10-21 12:21 ` [PATCH v2 3/5] x86/mm: check exec permissions on fault Nadav Amit
2021-10-25 10:59 ` Peter Zijlstra
2021-10-25 11:13 ` Andrew Cooper
2021-10-25 14:23 ` Dave Hansen
2021-10-25 14:20 ` Dave Hansen [this message]
2021-10-25 16:19 ` Nadav Amit
2021-10-25 17:45 ` Dave Hansen
2021-10-25 17:51 ` Nadav Amit
2021-10-25 18:00 ` Dave Hansen
2021-10-21 12:21 ` [PATCH v2 4/5] mm/mprotect: use mmu_gather Nadav Amit
2021-10-21 12:21 ` [PATCH v2 5/5] mm/mprotect: do not flush on permission promotion Nadav Amit
2021-10-25 11:12 ` Peter Zijlstra
2021-10-25 16:27 ` Nadav Amit
2021-10-22 3:04 ` [PATCH v2 0/5] mm/mprotect: avoid unnecessary TLB flushes Andrew Morton
2021-10-22 21:58 ` Nadav Amit
2021-10-26 16:09 ` Dave Hansen
2021-10-25 10:50 ` Peter Zijlstra
2021-10-25 16:42 ` Nadav Amit
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=e55875fa-1264-7e08-3bb8-ed984f6ea5b3@intel.com \
--to=dave.hansen@intel.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=andrew.cooper3@citrix.com \
--cc=dave.hansen@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=nadav.amit@gmail.com \
--cc=namit@vmware.com \
--cc=npiggin@gmail.com \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=will@kernel.org \
--cc=x86@kernel.org \
--cc=yuzhao@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).