From: "Luck, Tony" <tony.luck@intel.com>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Joe Konno <joe.konno@linux.intel.com>,
"linux-efi@vger.kernel.org" <linux-efi@vger.kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Ard Biesheuvel <ard.biesheuvel@linaro.org>,
Matthew Garrett <matthew.garrett@nebula.com>,
Jeremy Kerr <jk@ozlabs.org>, Andi Kleen <ak@linux.intel.com>,
Matthew Garrett <mjg59@google.com>,
"Peter Jones" <pjones@redhat.com>,
Andy Lutomirski <luto@kernel.org>,
James Bottomley <james.bottomley@hansenpartnership.com>
Subject: RE: [PATCH 1/2] fs/efivarfs: restrict inode permissions
Date: Wed, 21 Feb 2018 01:05:59 +0000 [thread overview]
Message-ID: <3908561D78D1C84285E8C5FCA982C28F7B37DE1B@ORSMSX110.amr.corp.intel.com> (raw)
In-Reply-To: <CA+55aFy8JMLjpDk+sU6pirSZdVqqHtw5oocDAEC7wcHuo5Vssw@mail.gmail.com>
>> EFI[1] stinks. Reading any file in /sys/firmware/efi/efivars/ generates
>> 4 (yes FOUR!) SMIs.
> Is that actualkly the normal implementation?
I don't know if there are other implementations. This is what I see on my
lab system.
> Also, if these are just synchronous SMI's, then don't we just end up
> correctly assigning the CPU load to the reader, and it doesn't
> actually matter? Where's the DoS?
SMI are broadcast to all logical CPUs. The bigger the system the
more the pain from an SMI as code tries to rendezvous them all
(4 socket * 24 core * 2 HyperThreads = 192 CPUs on my system).
Looping reading files from efivarfs doesn't stop the system, but it
does slow to a crawl while it is happening. Not a full blown DoS,
but fairly unpleasant.
-Tony
next prev parent reply other threads:[~2018-02-21 1:06 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-15 18:22 [PATCH 0/2] efivars: reading variables can generate SMIs Joe Konno
2018-02-15 18:22 ` [PATCH 1/2] fs/efivarfs: restrict inode permissions Joe Konno
2018-02-20 19:18 ` Andy Lutomirski
2018-02-20 21:18 ` Luck, Tony
2018-02-20 21:22 ` Matthew Garrett
2018-02-20 21:32 ` Luck, Tony
2018-02-20 21:35 ` Matthew Garrett
2018-02-20 22:01 ` Linus Torvalds
2018-02-20 23:30 ` Luck, Tony
2018-02-20 23:39 ` Matthew Garrett
2018-02-20 23:50 ` Luck, Tony
2018-02-21 0:49 ` Linus Torvalds
2018-02-21 1:05 ` Luck, Tony [this message]
2018-02-21 2:16 ` Linus Torvalds
2018-02-21 9:03 ` Ard Biesheuvel
2018-02-21 18:02 ` Linus Torvalds
2018-02-21 18:21 ` Andi Kleen
2018-02-21 19:47 ` Luck, Tony
2018-02-21 19:50 ` Linus Torvalds
2018-02-21 19:58 ` Luck, Tony
2018-02-21 20:40 ` Linus Torvalds
2018-02-22 1:45 ` [PATCH] efivarfs: Limit the rate for non-root to read files Luck, Tony
2018-02-22 1:58 ` Linus Torvalds
2018-02-22 5:34 ` Luck, Tony
2018-02-22 17:10 ` Eric W. Biederman
[not found] ` <CA+55aFy0hRexJkLbN7t31LjfGr4Ae0W5g6sBMqHHJi8aYuGKeA@mail.gmail.com>
[not found] ` <612E894E-62C8-4155-AED8-D53702EDC8DC@intel.com>
[not found] ` <CA+55aFxeBaTbwvbWqx1MKYjKKzLUs=1O43Bx2=JaO8qrnY-8HA@mail.gmail.com>
2018-02-22 17:15 ` [PATCH v2] " Luck, Tony
2018-02-22 17:39 ` Linus Torvalds
2018-02-22 17:54 ` Luck, Tony
2018-02-22 18:07 ` Linus Torvalds
2018-02-22 18:08 ` Ard Biesheuvel
2018-02-23 20:34 ` Andy Lutomirski
2018-02-23 19:47 ` [PATCH] " Peter Jones
2018-02-21 19:52 ` [PATCH 1/2] fs/efivarfs: restrict inode permissions Linus Torvalds
2018-02-24 20:06 ` Alan Cox
2018-02-25 10:56 ` Ard Biesheuvel
2018-02-21 0:49 ` Peter Jones
2018-02-20 23:19 ` Andy Lutomirski
2018-02-15 18:22 ` [PATCH 2/2] efi: restrict top-level attribute permissions Joe Konno
2018-02-16 10:41 ` [PATCH 0/2] efivars: reading variables can generate SMIs Ard Biesheuvel
2018-02-16 10:55 ` Borislav Petkov
2018-02-16 10:58 ` Ard Biesheuvel
2018-02-16 11:08 ` Borislav Petkov
2018-02-16 11:18 ` Ard Biesheuvel
2018-02-16 18:48 ` Joe Konno
2018-02-16 18:58 ` Borislav Petkov
2018-02-16 19:22 ` Peter Jones
2018-02-16 19:31 ` Ard Biesheuvel
2018-02-16 19:51 ` Matthew Garrett
2018-02-16 19:32 ` Luck, Tony
2018-02-16 19:54 ` Peter Jones
2018-02-16 20:51 ` James Bottomley
2018-02-16 21:09 ` Luck, Tony
2018-02-16 21:45 ` Andy Lutomirski
2018-02-16 21:58 ` Matthew Garrett
2018-02-16 22:02 ` Luck, Tony
2018-02-16 22:03 ` Matthew Garrett
2018-02-17 18:12 ` Andy Lutomirski
2018-02-16 22:05 ` Peter Jones
2018-02-17 9:36 ` Ard Biesheuvel
2018-02-17 16:17 ` Andi Kleen
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=3908561D78D1C84285E8C5FCA982C28F7B37DE1B@ORSMSX110.amr.corp.intel.com \
--to=tony.luck@intel.com \
--cc=ak@linux.intel.com \
--cc=ard.biesheuvel@linaro.org \
--cc=james.bottomley@hansenpartnership.com \
--cc=jk@ozlabs.org \
--cc=joe.konno@linux.intel.com \
--cc=linux-efi@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=matthew.garrett@nebula.com \
--cc=mjg59@google.com \
--cc=pjones@redhat.com \
--cc=torvalds@linux-foundation.org \
/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).