From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mx0b-0031df01.pphosted.com (mx0b-0031df01.pphosted.com [205.220.180.131]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B665B3C0A19 for ; Fri, 9 Oct 2026 04:17:43 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=205.220.180.131 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791519481; cv=none; b=fSpgeeEL0YYlhqA7m3rewPBKY34+h5gqgU3/UU0CcccmHAUFIiIEKXPYB1zgmZGF2NsREHpjjoiZoIaMV4hrUwJjrjxvs1Zv82Js80ra9lMOisfNAhS9v1SmQKy3IDXlVvKCbHcItYYV++t5jAIhP1zlni4HUuSy78sKask1qvk= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791519481; c=relaxed/simple; bh=MwrjLO9ocEkHCKOzW5F5st6I1YEQTq9yIO5viJj9tAY=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=fHjKQ8cmzqemdR/rEZnHRgZtBCgCHaV+nNZ5OGXM00reH75trSWwtoDpXdzQLRE1bBkzr2fYXIuA8YIHlytpeaYFzCF1jAeVbUSSYf4ymBgAlH5DXMF5Y0fchGszZbiv1rmfzc3zJ7xI42o40OZYgutDWu3HAdE/zQ1hfhrnQ9c= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=oss.qualcomm.com; spf=pass smtp.mailfrom=oss.qualcomm.com; dkim=pass (2048-bit key) header.d=qualcomm.com header.i=@qualcomm.com header.b=oZrICXkW; dkim=pass (2048-bit key) header.d=oss.qualcomm.com header.i=@oss.qualcomm.com header.b=SaB45Udu; arc=none smtp.client-ip=205.220.180.131 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=oss.qualcomm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=oss.qualcomm.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=qualcomm.com header.i=@qualcomm.com header.b="oZrICXkW"; dkim=pass (2048-bit key) header.d=oss.qualcomm.com header.i=@oss.qualcomm.com header.b="SaB45Udu" Received: from pps.filterd (m0279868.ppops.net [127.0.0.1]) by mx0a-0031df01.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id 6993I3Fx251918 for ; Fri, 9 Oct 2026 04:17:42 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=qualcomm.com; h= cc:content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to; s=qcppdkim1; bh= 9d3VzjhcQcny6UxQSqI2Ryo36ZCHGGG8qlbCADHXZa0=; b=oZrICXkW3pUgJ98s 2BaGfe1p2HGbPlgFhIp/POX4Bf+UrKR1DQFwOrrAQOHkcWERnMOy2Re51lo5MhUF 6pesuhAbMb0PjEaTulrNP4IQv7yJdehmxJMLY4KWAg88zdfOVgzb37gpuboaZTXk jDYktHfL6/0OiTtKtGSzak+PFXBDLSP+rKR8tT3frqCfKEnFV1i2jEY+bPaxyZ0o tgibKWm7BlqCo5YKlMUG3HRjZSMNQcvFTXos4d5/BVIQHtZKbu6Y5LcMyAfxmV/U dfoMi74hD3aO5F6y6dMRQ9Bh/aZVD6CSkGGgo9GpRJVsKzTOR+YyoGQsA2+AvDuv Znxr4w== Received: from mail-dy1-f199.google.com (mail-dy1-f199.google.com [74.125.82.199]) by mx0a-0031df01.pphosted.com (PPS) with ESMTPS id 4h6fmqsxkj-1 (version=TLSv1.3 cipher=TLS_AES_128_GCM_SHA256 bits=128 verify=NOT) for ; Fri, 09 Oct 2026 04:17:42 +0000 (GMT) Received: by mail-dy1-f199.google.com with SMTP id 5a478bee46e88-35158d674e1so2652108eec.1 for ; Thu, 08 Oct 2026 21:17:42 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=oss.qualcomm.com; s=google; t=1791519461; x=1792124261; darn=lists.linux.dev; h=content-transfer-encoding:content-type:mime-version:references :in-reply-to:message-id:date:subject:cc:to:from:from:to:cc:subject :date:message-id:reply-to:content-type; bh=9d3VzjhcQcny6UxQSqI2Ryo36ZCHGGG8qlbCADHXZa0=; b=SaB45Udu+zUrlUITWvYQ5jKlBX964H30kepVOevVDwUUVsLbw2qr3BvDpGqH2IRldK t0oTG0NW3wu1oaiH8Ut8K4hHZMS7ChGVZOnmgKCTepaufV7SFQw7eZR+0n+1YT1lLIRV LIZfx4hu2+Z1sXA2+RCFBdb4c126f1fSxaKqSAfaLgSDl9iiI1Yxv0ACceZq82zemJL2 boenOTPGiutW95lvmkXsMQ2siQOsQ99VcalShk/l3JFinQKrJ7veFoca1tktbnMTIQjC +gsdNWQsVIJb2LrMALSu/iOcjBhN9hRiTeWWyPwkLV6zfJ0lpcsYIlXGdykBkI6a+d2j JTdg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1791519461; x=1792124261; h=content-transfer-encoding:content-type:mime-version:references :in-reply-to:message-id:date:subject:cc:to:from:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=9d3VzjhcQcny6UxQSqI2Ryo36ZCHGGG8qlbCADHXZa0=; b=e20ue/REuMqzD06LmUcOPGtL4ndrWLBpNGQn/n9QjFH4w7KuW3GtifU9sj9jtXzVJo WI7EPrwKFgoFjlNaYePEf39w0Ak62vuSWawFHMEVlna4ZxFPi7LTMBAZmr3H6XFl1weZ lY5q0KReokgV0TXooDiisQryugF/cIVD4iRTk/hxKTQr1JM3eNzAQr8CX73WeGIIxqbc J3667pilURnOrV4BVEITOK/yT6TV/12vEdccseq+vmzx/n1nkrw0nPghhyEOcTRFy31r Gq7uPWaJLvlOtdM+8ebrGEzjljOBgKT6CjpYsyr6l0OQ6L//3arJzwoNEYjURq7IApoV fcLQ== X-Forwarded-Encrypted: i=1; AKwUvBxdkxdJsvqBB+m4Fk+UwjD5oIs/CC1UKLg0yFUfUTecSjtcuBRfgDMcaf2AIxaTVsQBDEP4XyMOPU7dUQGiZg==@lists.linux.dev X-Gm-Message-State: AFq9FYIWjw71pKDf8LMb+luWvRgnae58EJZU1cdMLH60PCJU29gIznPU ixKyhBCMuVDpPAs7N8VnM+QL2afXlluIY4oNx1VijxU6VIa5IVwEJNBvFmmXYB3QIpkB3SyZlGi hiifRIoa++k30kLVhi6jGGly0UCteHHX24BSTyC2/s3byxP/izWuz5yPL71f4E1PUQTm8/g== X-Gm-Gg: AYBFou1IuJSZF/NnuY2ZsPbJKjWatFgNPqCDg2BNMANgKFp+toNqTS+75AShe2dcumK HcLvDutc6l9sCQQTuOxAtK7rooEY2imtF3k/a4z6uVIy07+uQCNvuJ8yyhmHZRajp5Ic7dJWWes ytu25Fz2EohZVG7hfb4CXIomehIaYw7iXbvtwEgNrU+a2DLmexW9U8uNwCqLl9giRuiT8lkbMaU Ip+A24Su0966ekBV7KYkQR1UDtdhRLMmPXJzmtidOVNG2101FeTxExZ2K4KXxDQdcJw+1s6Wtjz sp9UczGSQH9LfgSnARRuO03ihlGNfKACkE2tjF3085mgZCZG2t0vO9FkhyqqTkcik2W8l6QGAA1 IxARi53GT8EQQQsylsnaOww4ShdBFCtCNHr27jh1IO6xNZ9eV56pWlfvyEQ== X-Received: by 2002:a05:7301:1806:b0:342:d7a0:2f40 with SMTP id 5a478bee46e88-3537df8cdf4mr1161676eec.7.1791519460897; Thu, 08 Oct 2026 21:17:40 -0700 (PDT) X-Received: by 2002:a05:7301:1806:b0:342:d7a0:2f40 with SMTP id 5a478bee46e88-3537df8cdf4mr1161639eec.7.1791519460097; Thu, 08 Oct 2026 21:17:40 -0700 (PDT) Received: from u24-san1p10108.qualcomm.com (i-global254.qualcomm.com. [199.106.103.254]) by smtp.gmail.com with ESMTPSA id 5a478bee46e88-3537c61eaa0sm3530749eec.0.2026.10.08.21.17.39 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 08 Oct 2026 21:17:39 -0700 (PDT) From: Linlin Zhang To: mst@redhat.com, jasowangio@gmail.com, axboe@kernel.dk, ebiggers@kernel.org, stefanha@redhat.com Cc: pbonzini@redhat.com, eperezma@redhat.com, xuanzhuo@linux.alibaba.com, virtualization@lists.linux.dev, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH v4 1/2] virtio_blk: Add control virtqueue support Date: Thu, 8 Oct 2026 21:17:13 -0700 Message-ID: <20261009041727.3170811-2-linlin.zhang@oss.qualcomm.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20261009041727.3170811-1-linlin.zhang@oss.qualcomm.com> References: <20261009041727.3170811-1-linlin.zhang@oss.qualcomm.com> Precedence: bulk X-Mailing-List: virtualization@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-Proofpoint-Spam-Info: AW1haW4tMjYxMDA5MDAxNiBTYWx0ZWRfX26z/SX+JIjms SRJDSAjcdUDJBP0v+zm75SmpTDWI4WVRq/RSIHbyyZFkrHqdrvlU7aJx0dHt6t3u5qpbG496qNu egC1d/8HwmmgZnGElK/aSYxF4VKRLxM= X-Proofpoint-Spam-Details-Enc: AW1haW4tMjYxMDA5MDAxNiBTYWx0ZWRfX/fDA4b3YMp9P 4CJa9nLkx2zu5bJDriNABksRBsKyUrtyXLZXWoQb5SpRX1C/LYNIYF53c4xcLA5MdCF5PtGJPjR EsykYQ5mKa3lB68WlnEI6Oc8w4ubvdZBnlcJeaWO1zyUZ2ojV3cD+fK2QtcnhPoHkDSDkgOGeKa Y/ZggftSrqrBGNTRAXgfz3ROobGVvIFs2wwj3joDNZqS5SLW5wqrJqBd1bmLG/G6+Eqs1jORxjH 0k+Ra2fc11qnqIl9biw3jBvatO33N/QQ2P14Z9dEyFf+kHZ/6cWO/9Q15hd1N81gztWWH4/7EGw PTptqAhZR3ZWkSEYc5FpKwlVsDjEye+DNlwXSH8ReRs7gL9wI5iwwTNiAx1WfIUXoW98Mv0lARy 0ZJ+9dIBbjPRebiGW6DkBg5AihC7okRXGvE80NzRylgdrNhpBpjvAQsLdYD/+kv6cdacVrSVAIM gKuUCWmmU3ErlJ0uKKA== X-Proofpoint-GUID: RYTddRaPm2aLZ3Q5dmRCQ8Lnozv_ibwZ X-Proofpoint-ORIG-GUID: RYTddRaPm2aLZ3Q5dmRCQ8Lnozv_ibwZ X-Authority-Analysis: v=2.4 cv=IqCL47/g c=1 sm=1 tr=0 ts=6ac86ae6 cx=c_pps a=cFYjgdjTJScbgFmBucgdfQ==:117 a=JYp8KDb2vCoCEuGobkYCKw==:17 a=IkcTkHD0fZMA:10 a=660iZSQnnn4A:10 a=s4-Qcg_JpJYA:10 a=VkNPw1HP01LnGYTKEx00:22 a=u7WPNUs3qKkmUXheDGA7:22 a=ZpdpYltYx_vBUK5n70dp:22 a=EUspDBNiAAAA:8 a=mWMrKjBDJ3x8XhIyD1MA:9 a=3ZKOabzyN94A:10 a=QEXdDO2ut3YA:10 a=scEy_gLbYbu1JhEsrz4S:22 X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.293,Aquarius:18.0.1176,Hydra:6.1.134,FMLib:17.12.100.49 definitions=2026-10-09_02,2026-10-08_01,2025-10-01_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 malwarescore=0 phishscore=0 bulkscore=0 clxscore=1015 suspectscore=0 adultscore=0 impostorscore=0 priorityscore=1501 lowpriorityscore=0 spamscore=0 classifier=typeunknown authscore=0 authtc= authcc= route=outbound adjust=0 reason=mlx scancount=1 engine=8.22.0-2610020000 definitions=main-2610090016 Add support for the optional virtio-blk control virtqueue. If control queue feature bit is negotiated, this allows the driver to manage control-queue requests independently from the data path and to safely handle outstanding requests during device removal and suspend. No control command is submitted by this change. The control virtqueue will be used by a subsequent inline encryption implementation. Signed-off-by: Linlin Zhang --- drivers/block/virtio_blk.c | 244 +++++++++++++++++++++++++++++++- include/uapi/linux/virtio_blk.h | 1 + 2 files changed, 241 insertions(+), 4 deletions(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 32bf3ba07a9d..6e9729134efa 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -52,6 +53,15 @@ struct virtio_blk_vq { char name[VQ_NAME_LEN]; } ____cacheline_aligned_in_smp; +struct virtio_blk_ctrl_vq { + struct virtqueue *vq; + struct mutex mutex; + spinlock_t lock; + unsigned int inflight; + bool dead; + struct completion drained; +}; + struct virtio_blk { /* * This mutex must be held by anything that may run after @@ -83,6 +93,9 @@ struct virtio_blk { /* For zoned device */ unsigned int zone_sectors; + + /* Control virtqueue state. */ + struct virtio_blk_ctrl_vq ctrl_vq; }; struct virtblk_req { @@ -110,6 +123,27 @@ struct virtblk_req { struct scatterlist sg[]; }; +/* + * Software-only completion state for a control-queue request. + */ +struct virtblk_ctrl_completion { + struct completion done; + /* + * Set when virtblk_ctrl_vq_request()'s waiter timed out and moved on + * without freeing this request. Whichever of virtblk_ctrlq_callback() + * or virtblk_ctrl_vq_drain() later retrieves the buffer must free + * this struct and the request instead of calling complete() on it. + */ + bool abandoned; +}; + +struct virtblk_ctrl_request { + __virtio32 type; + u8 status; + + struct virtblk_ctrl_completion *compl; +}; + static inline blk_status_t virtblk_result(u8 status) { switch (status) { @@ -863,11 +897,181 @@ static int virtblk_getgeo(struct gendisk *disk, struct hd_geometry *geo) return ret; } +#define VIRTBLK_CTRL_VQ_TIMEOUT (10 * HZ) + +/* Prevent new submissions and wait for in-flight requests to complete. */ +static void virtblk_ctrl_vq_quiesce(struct virtio_blk *vblk) +{ + unsigned long flags; + bool need_wait; + + if (!vblk->ctrl_vq.vq) + return; + + init_completion(&vblk->ctrl_vq.drained); + + spin_lock_irqsave(&vblk->ctrl_vq.lock, flags); + vblk->ctrl_vq.dead = true; + need_wait = vblk->ctrl_vq.inflight != 0; + spin_unlock_irqrestore(&vblk->ctrl_vq.lock, flags); + + if (need_wait && + !wait_for_completion_timeout(&vblk->ctrl_vq.drained, + VIRTBLK_CTRL_VQ_TIMEOUT)) + dev_warn(&vblk->vdev->dev, + "timed out waiting for control queue requests to complete\n"); +} + +/* Fail requests left in the control queue after reset. */ +static void virtblk_ctrl_vq_drain(struct virtio_blk *vblk) +{ + struct virtblk_ctrl_request *creq; + unsigned long flags; + + if (!vblk->ctrl_vq.vq) + return; + + spin_lock_irqsave(&vblk->ctrl_vq.lock, flags); + while ((creq = virtqueue_detach_unused_buf(vblk->ctrl_vq.vq)) != NULL) { + bool abandoned = creq->compl->abandoned; + + if (!WARN_ON_ONCE(!vblk->ctrl_vq.inflight)) + vblk->ctrl_vq.inflight--; + + if (abandoned) { + kfree(creq->compl); + kfree(creq); + } else { + creq->status = VIRTIO_BLK_S_IOERR; + complete(&creq->compl->done); + } + } + spin_unlock_irqrestore(&vblk->ctrl_vq.lock, flags); +} + +static void virtblk_ctrlq_callback(struct virtqueue *vq) +{ + struct virtio_blk *vblk = vq->vdev->priv; + struct virtblk_ctrl_request *creq; + unsigned long flags; + unsigned int len; + + spin_lock_irqsave(&vblk->ctrl_vq.lock, flags); + do { + virtqueue_disable_cb(vq); + while ((creq = virtqueue_get_buf(vq, &len)) != NULL) { + bool drained = false; + bool abandoned = creq->compl->abandoned; + + /* + * Skip the inflight decrement/drained check when + * inflight was already 0 (a bug, hence WARN_ON_ONCE) + * — but always fall through to resolve @creq below + * regardless. Never leave a synchronous caller + * blocked because the accounting state was already + * inconsistent. + */ + if (!WARN_ON_ONCE(!vblk->ctrl_vq.inflight) && + --vblk->ctrl_vq.inflight == 0 && vblk->ctrl_vq.dead) + drained = true; + + /* + * Decide and act on @abandoned without dropping the lock + * to avoid the memory leakage of @creq and its completion + * in the race condition that virtblk_ctrl_vq_request() + * wakes up from the timeout, and the callback resumes at + * the same time. + */ + if (abandoned) { + kfree(creq->compl); + kfree(creq); + } else { + complete(&creq->compl->done); + } + if (drained) + complete(&vblk->ctrl_vq.drained); + } + } while (!virtqueue_enable_cb(vq)); + spin_unlock_irqrestore(&vblk->ctrl_vq.lock, flags); +} + +/* Submit a control-queue request and wait for completion. */ +static int virtblk_ctrl_vq_request(struct virtio_blk *vblk, + struct virtblk_ctrl_request *creq, + struct scatterlist *sgs[], + unsigned int out_sgs, unsigned int in_sgs) +{ + struct virtblk_ctrl_completion *comp; + unsigned long flags; + int err; + + /* + * GFP_NOIO: this may be reached on the bio-submission path + * (memory reclaim writing back dirty pages to this same device), + * so GFP_KERNEL could self-deadlock. + */ + comp = kmalloc_obj(*comp, GFP_NOIO); + if (!comp) + return -ENOMEM; + init_completion(&comp->done); + comp->abandoned = false; + + mutex_lock(&vblk->ctrl_vq.mutex); + creq->compl = comp; + + spin_lock_irqsave(&vblk->ctrl_vq.lock, flags); + if (vblk->ctrl_vq.dead) { + spin_unlock_irqrestore(&vblk->ctrl_vq.lock, flags); + mutex_unlock(&vblk->ctrl_vq.mutex); + kfree(comp); + creq->compl = NULL; + return -ENODEV; + } + err = virtqueue_add_sgs(vblk->ctrl_vq.vq, sgs, out_sgs, in_sgs, creq, GFP_ATOMIC); + if (!err) { + vblk->ctrl_vq.inflight++; + virtqueue_kick(vblk->ctrl_vq.vq); + } + spin_unlock_irqrestore(&vblk->ctrl_vq.lock, flags); + if (err) { + mutex_unlock(&vblk->ctrl_vq.mutex); + kfree(comp); + creq->compl = NULL; + return err; + } + + if (wait_for_completion_timeout(&comp->done, VIRTBLK_CTRL_VQ_TIMEOUT)) { + mutex_unlock(&vblk->ctrl_vq.mutex); + kfree(comp); + creq->compl = NULL; + return 0; + } + + /* + * The host hasn't responded within the timeout. @creq is still + * owned by the device, so don't touch its DMA-target fields or + * free it here. Mark it abandoned and hand ownership of both @creq + * and @comp to whichever of virtblk_ctrlq_callback() or + * virtblk_ctrl_vq_drain() retrieves the buffer later; unlock the + * mutex so subsequent requests aren't serialized behind an + * unresponsive host. + */ + spin_lock_irqsave(&vblk->ctrl_vq.lock, flags); + comp->abandoned = true; + spin_unlock_irqrestore(&vblk->ctrl_vq.lock, flags); + mutex_unlock(&vblk->ctrl_vq.mutex); + + dev_warn(&vblk->vdev->dev, + "control queue request timed out, abandoning\n"); + return -ETIMEDOUT; +} + static void virtblk_free_disk(struct gendisk *disk) { struct virtio_blk *vblk = disk->private_data; ida_free(&vd_index_ida, vblk->index); + mutex_destroy(&vblk->ctrl_vq.mutex); mutex_destroy(&vblk->vdev_mutex); kfree(vblk); } @@ -965,6 +1169,8 @@ static int init_vq(struct virtio_blk *vblk) struct virtqueue **vqs; unsigned short num_vqs; unsigned short num_poll_vqs; + unsigned short total_vqs; + bool has_ctrl_vq; struct virtio_device *vdev = vblk->vdev; struct irq_affinity desc = { 0, }; @@ -993,12 +1199,19 @@ static int init_vq(struct virtio_blk *vblk) vblk->io_queues[HCTX_TYPE_READ], vblk->io_queues[HCTX_TYPE_POLL]); + /* + * The control vq is appended after the data vqs whenever + * F_CTRL_VQ is negotiated. + */ + has_ctrl_vq = virtio_has_feature(vdev, VIRTIO_BLK_F_CTRL_VQ); + total_vqs = num_vqs + (has_ctrl_vq ? 1 : 0); + vblk->vqs = kmalloc_objs(*vblk->vqs, num_vqs); if (!vblk->vqs) return -ENOMEM; - vqs_info = kzalloc_objs(*vqs_info, num_vqs); - vqs = kmalloc_objs(*vqs, num_vqs); + vqs_info = kzalloc_objs(*vqs_info, total_vqs); + vqs = kmalloc_objs(*vqs, total_vqs); if (!vqs_info || !vqs) { err = -ENOMEM; goto out; @@ -1015,8 +1228,13 @@ static int init_vq(struct virtio_blk *vblk) vqs_info[i].name = vblk->vqs[i].name; } + if (has_ctrl_vq) { + vqs_info[num_vqs].callback = virtblk_ctrlq_callback; + vqs_info[num_vqs].name = "control"; + } + /* Discover virtqueues and write information to configuration. */ - err = virtio_find_vqs(vdev, num_vqs, vqs, vqs_info, &desc); + err = virtio_find_vqs(vdev, total_vqs, vqs, vqs_info, &desc); if (err) goto out; @@ -1025,6 +1243,9 @@ static int init_vq(struct virtio_blk *vblk) vblk->vqs[i].vq = vqs[i]; } vblk->num_vqs = num_vqs; + vblk->ctrl_vq.vq = has_ctrl_vq ? vqs[num_vqs] : NULL; + vblk->ctrl_vq.dead = false; + vblk->ctrl_vq.inflight = 0; out: kfree(vqs); @@ -1464,14 +1685,18 @@ static int virtblk_probe(struct virtio_device *vdev) } mutex_init(&vblk->vdev_mutex); + mutex_init(&vblk->ctrl_vq.mutex); + spin_lock_init(&vblk->ctrl_vq.lock); vblk->vdev = vdev; INIT_WORK(&vblk->config_work, virtblk_config_changed_work); err = init_vq(vblk); - if (err) + if (err) { + dev_err(&vdev->dev, "init virt queue failed: err = %d\n", err); goto out_free_vblk; + } /* Default queue sizing is to fill the ring. */ if (!virtblk_queue_depth) { @@ -1553,6 +1778,7 @@ static int virtblk_probe(struct virtio_device *vdev) out_free_vq: vdev->config->del_vqs(vdev); kfree(vblk->vqs); + vblk->ctrl_vq.vq = NULL; out_free_vblk: kfree(vblk); out_free_index: @@ -1571,16 +1797,21 @@ static void virtblk_remove(struct virtio_device *vdev) del_gendisk(vblk->disk); blk_mq_free_tag_set(&vblk->tag_set); + virtblk_ctrl_vq_quiesce(vblk); + mutex_lock(&vblk->vdev_mutex); /* Stop all the virtqueues. */ virtio_reset_device(vdev); + virtblk_ctrl_vq_drain(vblk); /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ vblk->vdev = NULL; vdev->config->del_vqs(vdev); kfree(vblk->vqs); + vblk->vqs = NULL; + vblk->ctrl_vq.vq = NULL; mutex_unlock(&vblk->vdev_mutex); @@ -1598,8 +1829,11 @@ static int virtblk_freeze_priv(struct virtio_device *vdev) blk_mq_quiesce_queue_nowait(q); blk_mq_unfreeze_queue(q, memflags); + virtblk_ctrl_vq_quiesce(vblk); + /* Ensure we don't receive any more interrupts */ virtio_reset_device(vdev); + virtblk_ctrl_vq_drain(vblk); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); @@ -1612,6 +1846,7 @@ static int virtblk_freeze_priv(struct virtio_device *vdev) * pointers safely. */ vblk->vqs = NULL; + vblk->ctrl_vq.vq = NULL; return 0; } @@ -1672,6 +1907,7 @@ static unsigned int features[] = { VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES, VIRTIO_BLK_F_SECURE_ERASE, VIRTIO_BLK_F_ZONED, + VIRTIO_BLK_F_CTRL_VQ, }; static struct virtio_driver virtio_blk = { diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 3744e4da1b2a..1daddd259249 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -42,6 +42,7 @@ #define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */ #define VIRTIO_BLK_F_SECURE_ERASE 16 /* Secure Erase is supported */ #define VIRTIO_BLK_F_ZONED 17 /* Zoned block device */ +#define VIRTIO_BLK_F_CTRL_VQ 20 /* Control queue */ /* Legacy feature bits */ #ifndef VIRTIO_BLK_NO_LEGACY -- 2.34.1