linux-kernel - not seeing PMIs on AMD 16h family processor with 3.4 or 3.15

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>] [day] [month] [year] [list]

Date:	Thu, 8 May 2014 15:41:48 -0700
From:	Prasad Koya <prasad.koya@...il.com>
To:	LKML <linux-kernel@...r.kernel.org>
Subject: not seeing PMIs on AMD 16h family processor with 3.4 or 3.15

Hi

We are not seeing performance monitoring interrupts on AMD eKabini CPU
(family 16h processor). Tried both 3.4 and 3.15 kernels. If there is
more relevant group for this, I could post it there.

When I write to 0xc001_0004 (as given in AMD spec for core perf
counters) counter I see that it overflows fine and it starts counting
back from 0. However I don't see any NMI after oerflow. I also checked
0xc001_0000 and its value is 0x530076, which shows that the NMI is
enabled.

On 3.15 kernel I see this message on console:

[67044.084213] perf interrupt took too long (2529 > 2500), lowering
kernel.perf_event_max_sample_rate to 50000
[146301.023898] Uhhuh. NMI received for unknown reason 31 on CPU 1.
[146301.023952] Do you have a strange power saving mode enabled?
[146301.023991] Dazed and confused, but trying to continue

Anyone else seeing this?

Thank you.
--
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/