linux-kernel - RE: x86_mce: mce_start uses number of phsical cores instead of logical cores

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Fri, 10 May 2013 21:58:08 +0000
From:	Ming Lei <Ming.Lei@...erbed.com>
To:	"Luck, Tony" <tony.luck@...el.com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
CC:	"mchehab@...hat.com" <mchehab@...hat.com>,
	"bp@...en8.de" <bp@...en8.de>
Subject: RE: x86_mce: mce_start uses number of phsical cores instead of
 logical cores

You are right, here is the boot information confirming this:
smpboot: Booting Node   0, Processors  #1 #2 #3 #4 #5 OK
smpboot: Booting Node   1, Processors  #6 #7 #8 #9 #10 #11 OK
smpboot: Booting Node   0, Processors  #12 #13 #14 #15 #16 #17 OK
smpboot: Booting Node   1, Processors  #18 #19 #20 #21 #22 #23 OK

So only one socket gets the machine check. So is there still a problem but the fix will be different? I think the error inject creates a real machine check, but since each CPU has its own memory controller, the machine check may only send to the CPU the error happens.

Ming

-----Original Message-----
From: Luck, Tony [mailto:tony.luck@...el.com] 
Sent: Friday, May 10, 2013 2:05 PM
To: Ming Lei; linux-kernel@...r.kernel.org
Cc: mchehab@...hat.com; bp@...en8.de
Subject: RE: x86_mce: mce_start uses number of phsical cores instead of logical cores

> I used intel edac error injector and saw the same problem. I actually 
> wrote down the core numbers and I saw mce got to 0-5 and 12-17, but not the others. I have 2 sockets, 24 logical cores.

Mauro: How does the EDAC injector work on E5645 (Westmere-EP)?  Does it create a real error in memory that the processor then accesses ... tripping a machine check?

The mapping of Linux logical cpu numbers to physical socket/core/thread is somewhat as the mercy of the order that the BIOS lists things in its tables.  But those numbers look very much like you just saw the machine check on one socket.

Look at /proc/cpuinfo to be sure.  If you run "grep ^physical /proc/cpuinfo" I think you'll see output like this (confirming that only socket 0 saw the machine check):

physical id     :  0
physical id     :  0
physical id     :  0
physical id     :  0
physical id     :  0
physical id     :  0
physical id     :  1
physical id     :  1
physical id     :  1
physical id     :  1
physical id     :  1
physical id     :  1
physical id     :  0
physical id     :  0
physical id     :  0
physical id     :  0
physical id     :  0
physical id     :  0
physical id     :  1
physical id     :  1
physical id     :  1
physical id     :  1
physical id     :  1
physical id     :  1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/