[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <3908561D78D1C84285E8C5FCA982C28F192ED527@ORSMSX104.amr.corp.intel.com>
Date: Fri, 11 May 2012 16:23:06 +0000
From: "Luck, Tony" <tony.luck@...el.com>
To: Chen Gong <gong.chen@...ux.intel.com>
CC: "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...e.hu>, Borislav Petkov <bp@...64.org>,
"Huang, Ying" <ying.huang@...el.com>,
Hidetoshi Seto <seto.hidetoshi@...fujitsu.com>
Subject: RE: [PATCH 1/2] x86/mce: Only restart instruction after machine
check recovery if it is safe
> How about using following condition to decrease the execution time?
> if (mi->restartable == 0 ||
> memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0)
>
> Since restart operation is impossible, whether recovery operation can
> be avoided?
Because I still want the side-effects from memory_failure() of
marking the page as poisoned and SRAO signal to other users of
the page (or no signal at all to the others for clean LRU page).
Perhaps this deserves a comment
-Tony
Powered by blists - more mailing lists