linux-kernel - perf, percpu: panic in account

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-next>] [day] [month] [year] [list]

Date:	Mon, 05 Aug 2013 17:19:18 -0400
From:	Sasha Levin <sasha.levin@...cle.com>
To:	Peter Zijlstra <peterz@...radead.org>, paulus@...ba.org,
	Ingo Molnar <mingo@...nel.org>, acme@...stprotocols.net,
	Tejun Heo <tj@...nel.org>, cl@...ux-foundation.org
CC:	LKML <linux-kernel@...r.kernel.org>,
	"linux-mm@...ck.org" <linux-mm@...ck.org>, trinity@...r.kernel.org
Subject: perf, percpu: panic in account_event

Hi all,

While fuzzing with trinity inside a KVM tools guest running latest -next kernel,
I've stumbled on the following spew.

It seems to happen on the following line in account_event():

	if (event->attr.freq)
		atomic_inc(&per_cpu(perf_freq_events, cpu));  <--- here

Which was recently introduced in commit ("perf: Account freq events per cpu"). Although
the commit is new, it's very simple and straightforward - I can't see anything wrong with
it so maybe the fault is in percpu?

[ 4299.619701] BUG: unable to handle kernel paging request at 0000000f001d1ed6
[ 4299.620150] IP: [<ffffffff8120afb4>] account_event+0xe4/0x100
[ 4299.620150] PGD 5f30f067 PUD 0
[ 4299.620150] Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[ 4299.620150] Modules linked in:
[ 4299.620150] CPU: 14 PID: 15329 Comm: trinity-child56 Tainted: G        W 
3.11.0-rc4-next-20130805-sasha-00003-g07015f7 #3976
[ 4299.620150] task: ffff880176510000 ti: ffff8800c624a000 task.ti: ffff8800c624a000
[ 4299.620150] RIP: 0010:[<ffffffff8120afb4>]  [<ffffffff8120afb4>] account_event+0xe4/0x100
[ 4299.620150] RSP: 0018:ffff8800c624be68  EFLAGS: 00010212
[ 4299.620150] RAX: ffffffffffffffff RBX: 0000000000000000 RCX: 0000000000000000
[ 4299.627928] RDX: 0000000f001d1ed6 RSI: 00000000001dbbf8 RDI: ffff880179a437b0
[ 4299.627928] RBP: ffff8800c624be68 R08: 00000000e26ec8c5 R09: 0000000000000001
[ 4299.627928] R10: 0000000000000001 R11: 0000000000000000 R12: ffff880176510000
[ 4299.627928] R13: ffff880179a437b0 R14: 0000000000000000 R15: 0000000000000000
[ 4299.627928] FS:  00007fe6a0bbb700(0000) GS:ffff880226200000(0000) knlGS:0000000000000000
[ 4299.627928] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 4299.627928] CR2: 0000000f001d1ed6 CR3: 0000000059995000 CR4: 00000000000006e0
[ 4299.627928] Stack:
[ 4299.627928]  ffff8800c624bf68 ffffffff81215fe8 0000000000000000 ffff880176510610
[ 4299.627928]  0000000000000001 ffffffff81a37a00 ffff880176510610 0000000000000000
[ 4299.627928]  0000000000000000 0000014584098985 0000004000000001 0000000000000004
[ 4299.627928] Call Trace:
[ 4299.627928]  [<ffffffff81215fe8>] SYSC_perf_event_open+0x4e8/0x910
[ 4299.627928]  [<ffffffff81a37a00>] ? do_raw_spin_unlock+0xd0/0xe0
[ 4299.627928]  [<ffffffff81216419>] SyS_perf_event_open+0x9/0x10
[ 4299.627928]  [<ffffffff840a14ec>] tracesys+0xdd/0xe2
[ 4299.627928] Code: c7 c2 c0 1e 1d 00 48 03 14 cd 80 7b 60 86 f0 ff 02 f6 87 c9 00 00 00 04 74 1d 
48 98 48 c7 c2 c8 1e 1d 00 48 03 14 c5 80 7b 60 86 <f0> ff 02 66 0f 1f 84 00 00 00 00 00 c9 c3 66 66 
66 66 66 2e 0f
[ 4299.627928] RIP  [<ffffffff8120afb4>] account_event+0xe4/0x100
[ 4299.627928]  RSP <ffff8800c624be68>
[ 4299.627928] CR2: 0000000f001d1ed6


Thanks,
Sasha
--
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/