From patchwork Fri Jan 27 23:32:16 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Douglas Miller X-Patchwork-Id: 9542923 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id DA72C602A7 for ; Sat, 28 Jan 2017 01:18:23 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id BFBB928319 for ; Sat, 28 Jan 2017 01:18:23 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id B3FA52831C; Sat, 28 Jan 2017 01:18:23 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=unavailable version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 401002836B for ; Sat, 28 Jan 2017 01:18:22 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1750767AbdA1BSW (ORCPT ); Fri, 27 Jan 2017 20:18:22 -0500 Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:46034 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1750775AbdA1BSV (ORCPT ); Fri, 27 Jan 2017 20:18:21 -0500 Received: from pps.filterd (m0098420.ppops.net [127.0.0.1]) by mx0b-001b2d01.pphosted.com (8.16.0.20/8.16.0.20) with SMTP id v0RNTGAX019024 for ; Fri, 27 Jan 2017 18:32:24 -0500 Received: from e32.co.us.ibm.com (e32.co.us.ibm.com [32.97.110.150]) by mx0b-001b2d01.pphosted.com with ESMTP id 288e8gat6f-1 (version=TLSv1.2 cipher=AES256-SHA bits=256 verify=NOT) for ; Fri, 27 Jan 2017 18:32:24 -0500 Received: from localhost by e32.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 27 Jan 2017 16:32:24 -0700 Received: from d03dlp03.boulder.ibm.com (9.17.202.179) by e32.co.us.ibm.com (192.168.1.132) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Fri, 27 Jan 2017 16:32:21 -0700 Received: from b03cxnp07029.gho.boulder.ibm.com (b03cxnp07029.gho.boulder.ibm.com [9.17.130.16]) by d03dlp03.boulder.ibm.com (Postfix) with ESMTP id 6114619D8042; Fri, 27 Jan 2017 16:31:36 -0700 (MST) Received: from b03ledav004.gho.boulder.ibm.com (b03ledav004.gho.boulder.ibm.com [9.17.130.235]) by b03cxnp07029.gho.boulder.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id v0RNWKCK15663454; Fri, 27 Jan 2017 16:32:21 -0700 Received: from b03ledav004.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 3B8DA78057; Fri, 27 Jan 2017 16:32:21 -0700 (MST) Received: from oc5780617838.ibm.com (unknown [9.80.98.47]) by b03ledav004.gho.boulder.ibm.com (Postfix) with ESMTP id 3E83E7804D; Fri, 27 Jan 2017 16:32:20 -0700 (MST) From: Douglas Miller To: linux-kernel@vger.kernel.org, Christoph Lameter , Tejun Heo Cc: linux-block@vger.kernel.org, Douglas Miller , Guilherme Piccoli Subject: [PATCH V2 1/1] percpu-refcount: fix reference leak during percpu-atomic transition Date: Fri, 27 Jan 2017 17:32:16 -0600 X-Mailer: git-send-email 1.7.1 In-Reply-To: <1485559936-14133-1-git-send-email-dougmill@linux.vnet.ibm.com> References: <1485559936-14133-1-git-send-email-dougmill@linux.vnet.ibm.com> X-TM-AS-GCONF: 00 X-Content-Scanned: Fidelis XPS MAILER x-cbid: 17012723-0004-0000-0000-00001168AB79 X-IBM-SpamModules-Scores: X-IBM-SpamModules-Versions: BY=3.00006509; HX=3.00000240; KW=3.00000007; PH=3.00000004; SC=3.00000201; SDB=6.00813654; UDB=6.00396948; IPR=6.00591069; BA=6.00005093; NDR=6.00000001; ZLA=6.00000005; ZF=6.00000009; ZB=6.00000000; ZP=6.00000000; ZH=6.00000000; ZU=6.00000002; MB=3.00014080; XFM=3.00000011; UTC=2017-01-27 23:32:23 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 17012723-0005-0000-0000-00007C8D274F Message-Id: <1485559936-14133-2-git-send-email-dougmill@linux.vnet.ibm.com> X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:, , definitions=2017-01-27_17:, , signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 spamscore=0 suspectscore=0 malwarescore=0 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1612050000 definitions=main-1701270228 Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP percpu_ref_tryget() and percpu_ref_tryget_live() should return "true" IFF they acquire a reference. But the return value from atomic_long_inc_not_zero() is a long and may have high bits set, e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines is bool so the reference may actually be acquired but the routines return "false" which results in a reference leak since the caller assumes it does not need to do a corresponding percpu_ref_put(). This was seen when performing CPU hotplug during I/O, as hangs in blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start) raced with percpu_ref_tryget (blk_mq_timeout_work). Sample stack trace: __switch_to+0x2c0/0x450 __schedule+0x2f8/0x970 schedule+0x48/0xc0 blk_mq_freeze_queue_wait+0x94/0x120 blk_mq_queue_reinit_work+0xb8/0x180 blk_mq_queue_reinit_prepare+0x84/0xa0 cpuhp_invoke_callback+0x17c/0x600 cpuhp_up_callbacks+0x58/0x150 _cpu_up+0xf0/0x1c0 do_cpu_up+0x120/0x150 cpu_subsys_online+0x64/0xe0 device_online+0xb4/0x120 online_store+0xb4/0xc0 dev_attr_store+0x68/0xa0 sysfs_kf_write+0x80/0xb0 kernfs_fop_write+0x17c/0x250 __vfs_write+0x6c/0x1e0 vfs_write+0xd0/0x270 SyS_write+0x6c/0x110 system_call+0x38/0xe0 Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS, and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests. However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0 and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set. The fix is to make the tryget routines return an actual boolean instead of the atomic long result truncated to a bool. Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751 Signed-off-by: Douglas Miller Reviewed-by: Jens Axboe --- include/linux/percpu-refcount.h | 4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 1c7eec0..ac3518a 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -212,7 +212,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) this_cpu_inc(*percpu_count); ret = true; } else { - ret = atomic_long_inc_not_zero(&ref->count); + ret = atomic_long_inc_not_zero(&ref->count) != 0; } rcu_read_unlock_sched(); @@ -246,7 +246,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { - ret = atomic_long_inc_not_zero(&ref->count); + ret = atomic_long_inc_not_zero(&ref->count) != 0; } rcu_read_unlock_sched();