From 5261b85e586afe6ebe54e16e0a8acc32fc6d4902 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 13 Mar 2014 11:23:39 +1030 Subject: virtio_blk: don't crash, report error if virtqueue is broken. A bad implementation of virtio might cause us to mark the virtqueue broken: we'll dev_err() in that case, and the device is useless, but let's not BUG_ON(). ENOMEM or ENOSPC implies the ring is full, and we should try again later (-ENOMEM is documented to happen, but doesn't, as we fall through to ENOSPC). EIO means it's broken. Signed-off-by: Rusty Russell --- drivers/block/virtio_blk.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'drivers/block/virtio_blk.c') diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index b1cb3f4c4db4..a2db9ed288f2 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -158,6 +158,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req) unsigned long flags; unsigned int num; const bool last = (req->cmd_flags & REQ_END) != 0; + int err; BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); @@ -198,11 +199,16 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req) } spin_lock_irqsave(&vblk->vq_lock, flags); - if (__virtblk_add_req(vblk->vq, vbr, vbr->sg, num) < 0) { + err = __virtblk_add_req(vblk->vq, vbr, vbr->sg, num); + if (err) { virtqueue_kick(vblk->vq); spin_unlock_irqrestore(&vblk->vq_lock, flags); blk_mq_stop_hw_queue(hctx); - return BLK_MQ_RQ_QUEUE_BUSY; + /* Out of mem doesn't actually happen, since we fall back + * to direct descriptors */ + if (err == -ENOMEM || err == -ENOSPC) + return BLK_MQ_RQ_QUEUE_BUSY; + return BLK_MQ_RQ_QUEUE_ERROR; } if (last) -- cgit v1.2.1 From fc4324b4597c4eb8907207e82f9a6acec84dd335 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 19 Mar 2014 17:08:24 +1030 Subject: virtio-blk: base queue-depth on virtqueue ringsize or module param Venkatash spake thus: virtio-blk set the default queue depth to 64 requests, which was insufficient for high-IOPS devices. Instead set the blk-queue depth to the device's virtqueue depth divided by two (each I/O requires at least two VQ entries). But behold, Ted added a module parameter: Also allow the queue depth to be something which can be set at module load time or via a kernel boot-time parameter, for testing/benchmarking purposes. And I rewrote it substantially, mainly to take VIRTIO_RING_F_INDIRECT_DESC into account. As QEMU sets the vq size for PCI to 128, Venkatash's patch wouldn't have made a change. This version does (since QEMU also offers VIRTIO_RING_F_INDIRECT_DESC. Inspired-by: "Theodore Ts'o" Based-on-the-true-story-of: Venkatesh Srinivas Cc: "Michael S. Tsirkin" Cc: virtio-dev@lists.oasis-open.org Cc: virtualization@lists.linux-foundation.org Cc: Frank Swiderski Signed-off-by: Rusty Russell --- drivers/block/virtio_blk.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'drivers/block/virtio_blk.c') diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index a2db9ed288f2..196222271a50 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -491,10 +491,11 @@ static struct blk_mq_ops virtio_mq_ops = { static struct blk_mq_reg virtio_mq_reg = { .ops = &virtio_mq_ops, .nr_hw_queues = 1, - .queue_depth = 64, + .queue_depth = 0, /* Set in virtblk_probe */ .numa_node = NUMA_NO_NODE, .flags = BLK_MQ_F_SHOULD_MERGE, }; +module_param_named(queue_depth, virtio_mq_reg.queue_depth, uint, 0444); static void virtblk_init_vbr(void *data, struct blk_mq_hw_ctx *hctx, struct request *rq, unsigned int nr) @@ -558,6 +559,13 @@ static int virtblk_probe(struct virtio_device *vdev) goto out_free_vq; } + /* Default queue sizing is to fill the ring. */ + if (!virtio_mq_reg.queue_depth) { + virtio_mq_reg.queue_depth = vblk->vq->num_free; + /* ... but without indirect descs, we use 2 descs per req */ + if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC)) + virtio_mq_reg.queue_depth /= 2; + } virtio_mq_reg.cmd_size = sizeof(struct virtblk_req) + sizeof(struct scatterlist) * sg_elems; -- cgit v1.2.1