All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Luck, Tony" <tony.luck@intel.com>
To: Borislav Petkov <bp@alien8.de>, Jue Wang <juew@google.com>
Cc: "x86@kernel.org" <x86@kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"patches@lists.linux.dev" <patches@lists.linux.dev>
Subject: RE: [PATCH] x86/mce: Add workaround for SKX/CLX/CPX spurious machine checks
Date: Wed, 16 Feb 2022 18:41:58 +0000	[thread overview]
Message-ID: <9f402331d25c47b69349c8171bbd49c1@intel.com> (raw)
In-Reply-To: <Yg08Uhg0fZ9xZuP2@zn.tnic>

> Well, we could try to decode the instructions around rIP when the #MC
> is raised and see what caused the MCE and perhaps pick apart which insn
> caused it, is it accessing behind the buffer boundaries, etc.

Is this a case of "perfect is the enemy of good enough"?

It is a rare scenario (only a pain point for Jue because Google has billions and billions
of cores running this code).  You need:

1) An uncorrected error
2) That error must be in first cache line of a page
3) Kernel must execute page_copy from the page immediately before that page

	When all three happen, kernel crashes because we don't
	have a recover path from kernel page_copy

-Tony

  reply	other threads:[~2022-02-16 18:42 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-07  4:36 [RFC] x86/mce: Add workaround for SKX/CLX/CPX spurious machine checks Jue Wang
2022-02-07 18:23 ` Luck, Tony
2022-02-07 18:52 ` Borislav Petkov
2022-02-07 19:24   ` Luck, Tony
2022-02-07 20:27     ` Borislav Petkov
2022-02-07 21:07       ` Luck, Tony
2022-02-07 21:20         ` Borislav Petkov
2022-02-07 21:51           ` Luck, Tony
2022-02-08 15:04             ` Jue Wang
2022-02-08 15:09               ` [PATCH] " Jue Wang
2022-02-11 20:08                 ` Jue Wang
2022-02-11 20:18                   ` Borislav Petkov
2022-02-11 20:23                     ` Jue Wang
2022-02-15 18:42                 ` Luck, Tony
2022-02-15 22:08                 ` Borislav Petkov
2022-02-15 22:22                   ` Luck, Tony
2022-02-16 10:28                     ` Borislav Petkov
2022-02-16 15:50                       ` Jue Wang
2022-02-16 18:02                         ` Borislav Petkov
2022-02-16 18:41                           ` Luck, Tony [this message]
2022-02-16 18:52                             ` Borislav Petkov
2022-02-16 18:58                               ` Luck, Tony
2022-02-16 18:59                                 ` Jue Wang
2022-02-16 21:53                                   ` [PATCH] x86/mce: work around an erratum on fast string copy instructions Jue Wang
2022-02-17 16:30                                     ` Borislav Petkov
2022-02-17 16:32                                       ` Borislav Petkov
2022-02-18  1:32                                         ` [PATCH v2] " Jue Wang
2022-02-18 15:07                                           ` Borislav Petkov
2022-02-18 16:03                                             ` Jue Wang
2022-02-18 16:14                                               ` Borislav Petkov
2022-02-18 16:21                                                 ` Jue Wang
2022-02-18 17:16                                                   ` Borislav Petkov
2022-02-18 17:39                                                     ` Jue Wang
     [not found]                                                     ` <CAPcxDJ7=hCz6KRih4OBVv-k8WLcBL4n+VSpeP_zky7Uunq89zg@mail.gmail.com>
2022-02-18 22:05                                                       ` Borislav Petkov
2022-02-18 22:38                                                         ` Luck, Tony
2022-02-18 22:58                                                           ` Borislav Petkov
2022-02-18 17:58                                             ` Luck, Tony
2022-02-19 18:09                                           ` [tip: ras/core] x86/mce: Work " tip-bot2 for Jue Wang
2022-02-16  5:40                   ` [PATCH] x86/mce: Add workaround for SKX/CLX/CPX spurious machine checks Jue Wang
2022-02-16  5:56                     ` [PATCH] x86/mce: work around an erratum on fast string copy instructions Jue Wang
2022-02-16  9:04                       ` David Laight
2022-02-16 15:33                         ` Jue Wang

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=9f402331d25c47b69349c8171bbd49c1@intel.com \
    --to=tony.luck@intel.com \
    --cc=bp@alien8.de \
    --cc=juew@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=patches@lists.linux.dev \
    --cc=x86@kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.