From patchwork Mon May 18 17:36:35 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Greg KH X-Patchwork-Id: 11555961 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 13B341391 for ; Mon, 18 May 2020 17:40:44 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E18CD207FB for ; Mon, 18 May 2020 17:40:43 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1589823644; bh=k6R50BJnSJAsdfMITjdQB0gK2h+S7nINXG3Eh7ugscQ=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=XAtEPKSAV9A8VqSMX/Cvs4RPzzBcDVDguyrIPJTrSvGhtDhl1lz/EG65TMH7ZrZqj ICKXhQXafAAgY4+/HeO84Iy1hJTPt/ZQkp7N7B1MOGcpdQtB/UZjHi00fyTZWMyJX+ XSbdf6KE16bd5tKgSOhoja+fsp8qNtSRQmK+VKL8= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729131AbgERRkm (ORCPT ); Mon, 18 May 2020 13:40:42 -0400 Received: from mail.kernel.org ([198.145.29.99]:36444 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729121AbgERRkl (ORCPT ); Mon, 18 May 2020 13:40:41 -0400 Received: from localhost (83-86-89-107.cable.dynamic.v4.ziggo.nl [83.86.89.107]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 0910120829; Mon, 18 May 2020 17:40:39 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1589823640; bh=k6R50BJnSJAsdfMITjdQB0gK2h+S7nINXG3Eh7ugscQ=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=GXpADY6vy9s4UQi6L/KhuyR2wbWI6ct01c0fpk3+Eh7JGO7/6QRjfNypyOfqDyWIZ WZyc5uR3VuN+y5FZ16nUv4HKLiW3PFU6aTbIiUm/qyf0Sggs6P8ysAvvEVTN2dSAwR BMAGpBk3fTf53729ytaRhNNoTWb++RzJST5gJgEA= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Gabriel Krisman Bertazi , Brian King , Keith Busch , linux-nvme@lists.infradead.org, linux-block@vger.kernel.org, Christoph Hellwig , Jens Axboe , Giuliano Procida Subject: [PATCH 4.4 64/86] blk-mq: Allow timeouts to run while queue is freezing Date: Mon, 18 May 2020 19:36:35 +0200 Message-Id: <20200518173503.327209969@linuxfoundation.org> X-Mailer: git-send-email 2.26.2 In-Reply-To: <20200518173450.254571947@linuxfoundation.org> References: <20200518173450.254571947@linuxfoundation.org> User-Agent: quilt/0.66 MIME-Version: 1.0 Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org From: Gabriel Krisman Bertazi commit 71f79fb3179e69b0c1448a2101a866d871c66e7f upstream. In case a submitted request gets stuck for some reason, the block layer can prevent the request starvation by starting the scheduled timeout work. If this stuck request occurs at the same time another thread has started a queue freeze, the blk_mq_timeout_work will not be able to acquire the queue reference and will return silently, thus not issuing the timeout. But since the request is already holding a q_usage_counter reference and is unable to complete, it will never release its reference, preventing the queue from completing the freeze started by first thread. This puts the request_queue in a hung state, forever waiting for the freeze completion. This was observed while running IO to a NVMe device at the same time we toggled the CPU hotplug code. Eventually, once a request got stuck requiring a timeout during a queue freeze, we saw the CPU Hotplug notification code get stuck inside blk_mq_freeze_queue_wait, as shown in the trace below. [c000000deaf13690] [c000000deaf13738] 0xc000000deaf13738 (unreliable) [c000000deaf13860] [c000000000015ce8] __switch_to+0x1f8/0x350 [c000000deaf138b0] [c000000000ade0e4] __schedule+0x314/0x990 [c000000deaf13940] [c000000000ade7a8] schedule+0x48/0xc0 [c000000deaf13970] [c0000000005492a4] blk_mq_freeze_queue_wait+0x74/0x110 [c000000deaf139e0] [c00000000054b6a8] blk_mq_queue_reinit_notify+0x1a8/0x2e0 [c000000deaf13a40] [c0000000000e7878] notifier_call_chain+0x98/0x100 [c000000deaf13a90] [c0000000000b8e08] cpu_notify_nofail+0x48/0xa0 [c000000deaf13ac0] [c0000000000b92f0] _cpu_down+0x2a0/0x400 [c000000deaf13b90] [c0000000000b94a8] cpu_down+0x58/0xa0 [c000000deaf13bc0] [c0000000006d5dcc] cpu_subsys_offline+0x2c/0x50 [c000000deaf13bf0] [c0000000006cd244] device_offline+0x104/0x140 [c000000deaf13c30] [c0000000006cd40c] online_store+0x6c/0xc0 [c000000deaf13c80] [c0000000006c8c78] dev_attr_store+0x68/0xa0 [c000000deaf13cc0] [c0000000003974d0] sysfs_kf_write+0x80/0xb0 [c000000deaf13d00] [c0000000003963e8] kernfs_fop_write+0x188/0x200 [c000000deaf13d50] [c0000000002e0f6c] __vfs_write+0x6c/0xe0 [c000000deaf13d90] [c0000000002e1ca0] vfs_write+0xc0/0x230 [c000000deaf13de0] [c0000000002e2cdc] SyS_write+0x6c/0x110 [c000000deaf13e30] [c000000000009204] system_call+0x38/0xb4 The fix is to allow the timeout work to execute in the window between dropping the initial refcount reference and the release of the last reference, which actually marks the freeze completion. This can be achieved with percpu_refcount_tryget, which does not require the counter to be alive. This way the timeout work can do it's job and terminate a stuck request even during a freeze, returning its reference and avoiding the deadlock. Allowing the timeout to run is just a part of the fix, since for some devices, we might get stuck again inside the device driver's timeout handler, should it attempt to allocate a new request in that path - which is a quite common action for Abort commands, which need to be sent after a timeout. In NVMe, for instance, we call blk_mq_alloc_request from inside the timeout handler, which will fail during a freeze, since it also tries to acquire a queue reference. I considered a similar change to blk_mq_alloc_request as a generic solution for further device driver hangs, but we can't do that, since it would allow new requests to disturb the freeze process. I thought about creating a new function in the block layer to support unfreezable requests for these occasions, but after working on it for a while, I feel like this should be handled in a per-driver basis. I'm now experimenting with changes to the NVMe timeout path, but I'm open to suggestions of ways to make this generic. Signed-off-by: Gabriel Krisman Bertazi Cc: Brian King Cc: Keith Busch Cc: linux-nvme@lists.infradead.org Cc: linux-block@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Giuliano Procida Signed-off-by: Greg Kroah-Hartman --- block/blk-mq.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -628,7 +628,20 @@ static void blk_mq_rq_timer(unsigned lon }; int i; - if (blk_queue_enter(q, GFP_NOWAIT)) + /* A deadlock might occur if a request is stuck requiring a + * timeout at the same time a queue freeze is waiting + * completion, since the timeout code would not be able to + * acquire the queue reference here. + * + * That's why we don't use blk_queue_enter here; instead, we use + * percpu_ref_tryget directly, because we need to be able to + * obtain a reference even in the short window between the queue + * starting to freeze, by dropping the first reference in + * blk_mq_freeze_queue_start, and the moment the last request is + * consumed, marked by the instant q_usage_counter reaches + * zero. + */ + if (!percpu_ref_tryget(&q->q_usage_counter)) return; blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);