From mboxrd@z Thu Jan 1 00:00:00 1970 From: Greg Kroah-Hartman Subject: [PATCH 3.15 002/139] block: virtio_blk: dont hold spin lock during world switch Date: Sat, 28 Jun 2014 10:46:03 -0700 Message-ID: <20140628174605.469557168@linuxfoundation.org> References: <20140628174605.352098823@linuxfoundation.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20140628174605.352098823@linuxfoundation.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.linux-foundation.org Errors-To: virtualization-bounces@lists.linux-foundation.org To: linux-kernel@vger.kernel.org Cc: "Michael S. Tsirkin" , Greg Kroah-Hartman , Ming Lei , stable@vger.kernel.org, virtualization@lists.linux-foundation.org, Jens Axboe List-Id: virtualization@lists.linuxfoundation.org 3.15-stable review patch. If anyone has any objections, please let me know. ------------------ From: Ming Lei commit e8edca6f7f92234202d6dd163c118ef495244d7c upstream. Firstly, it isn't necessary to hold lock of vblk->vq_lock when notifying hypervisor about queued I/O. Secondly, virtqueue_notify() will cause world switch and it may take long time on some hypervisors(such as, qemu-arm), so it isn't good to hold the lock and block other vCPUs. On arm64 quad core VM(qemu-kvm), the patch can increase I/O performance a lot with VIRTIO_RING_F_EVENT_IDX enabled: - without the patch: 14K IOPS - with the patch: 34K IOPS fio script: [global] direct=1 bsrange=4k-4k timeout=10 numjobs=4 ioengine=libaio iodepth=64 filename=/dev/vdc group_reporting=1 [f1] rw=randread Cc: Rusty Russell Cc: "Michael S. Tsirkin" Cc: virtualization@lists.linux-foundation.org Signed-off-by: Ming Lei Acked-by: Rusty Russell Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/virtio_blk.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -159,6 +159,7 @@ static int virtio_queue_rq(struct blk_mq unsigned int num; const bool last = (req->cmd_flags & REQ_END) != 0; int err; + bool notify = false; BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); @@ -211,10 +212,12 @@ static int virtio_queue_rq(struct blk_mq return BLK_MQ_RQ_QUEUE_ERROR; } - if (last) - virtqueue_kick(vblk->vq); - + if (last && virtqueue_kick_prepare(vblk->vq)) + notify = true; spin_unlock_irqrestore(&vblk->vq_lock, flags); + + if (notify) + virtqueue_notify(vblk->vq); return BLK_MQ_RQ_QUEUE_OK; }