From patchwork Fri Sep 17 10:03:26 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Krishna Kumar X-Patchwork-Id: 187752 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter1.kernel.org (8.14.4/8.14.3) with ESMTP id o8HA43Nm006100 for ; Fri, 17 Sep 2010 10:04:03 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752942Ab0IQKDc (ORCPT ); Fri, 17 Sep 2010 06:03:32 -0400 Received: from e28smtp08.in.ibm.com ([122.248.162.8]:46256 "EHLO e28smtp08.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752871Ab0IQKDb (ORCPT ); Fri, 17 Sep 2010 06:03:31 -0400 Received: from d28relay03.in.ibm.com (d28relay03.in.ibm.com [9.184.220.60]) by e28smtp08.in.ibm.com (8.14.4/8.13.1) with ESMTP id o8H9hs3c005539; Fri, 17 Sep 2010 15:13:54 +0530 Received: from d28av01.in.ibm.com (d28av01.in.ibm.com [9.184.220.63]) by d28relay03.in.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id o8HA3SBC3875030; Fri, 17 Sep 2010 15:33:28 +0530 Received: from d28av01.in.ibm.com (loopback [127.0.0.1]) by d28av01.in.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id o8HA3Rx8012472; Fri, 17 Sep 2010 15:33:28 +0530 Received: from krkumar2.in.ibm.com ([9.124.220.25]) by d28av01.in.ibm.com (8.14.4/8.13.1/NCO v10.0 AVin) with ESMTP id o8HA3Qma012453; Fri, 17 Sep 2010 15:33:26 +0530 From: Krishna Kumar To: rusty@rustcorp.com.au, davem@davemloft.net, mst@redhat.com Cc: kvm@vger.kernel.org, arnd@arndb.de, netdev@vger.kernel.org, avi@redhat.com, anthony@codemonkey.ws, Krishna Kumar Date: Fri, 17 Sep 2010 15:33:26 +0530 Message-Id: <20100917100326.21276.63142.sendpatchset@krkumar2.in.ibm.com> In-Reply-To: <20100917100307.21276.79185.sendpatchset@krkumar2.in.ibm.com> References: <20100917100307.21276.79185.sendpatchset@krkumar2.in.ibm.com> Subject: [v2 RFC PATCH 3/4] Changes for vhost Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter1.kernel.org [140.211.167.41]); Fri, 17 Sep 2010 10:04:03 +0000 (UTC) diff -ruNp org2/drivers/vhost/vhost.h tx_only2/drivers/vhost/vhost.h --- org2/drivers/vhost/vhost.h 2010-08-03 08:49:31.000000000 +0530 +++ tx_only2/drivers/vhost/vhost.h 2010-09-16 15:24:01.000000000 +0530 @@ -40,11 +40,11 @@ struct vhost_poll { wait_queue_t wait; struct vhost_work work; unsigned long mask; - struct vhost_dev *dev; + struct vhost_virtqueue *vq; /* points back to vq */ }; void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, - unsigned long mask, struct vhost_dev *dev); + unsigned long mask, struct vhost_virtqueue *vq); void vhost_poll_start(struct vhost_poll *poll, struct file *file); void vhost_poll_stop(struct vhost_poll *poll); void vhost_poll_flush(struct vhost_poll *poll); @@ -110,6 +110,10 @@ struct vhost_virtqueue { /* Log write descriptors */ void __user *log_base; struct vhost_log log[VHOST_NET_MAX_SG]; + struct task_struct *worker; /* vhost for this vq, shared btwn RX/TX */ + spinlock_t *work_lock; + struct list_head *work_list; + int qnum; /* 0 for RX, 1 -> n-1 for TX */ }; struct vhost_dev { @@ -124,11 +128,13 @@ struct vhost_dev { int nvqs; struct file *log_file; struct eventfd_ctx *log_ctx; - spinlock_t work_lock; - struct list_head work_list; - struct task_struct *worker; + spinlock_t *work_lock; + struct list_head *work_list; }; +int vhost_setup_vqs(struct vhost_dev *dev, int numtxqs); +void vhost_free_vqs(struct vhost_dev *dev); +int vhost_get_num_threads(int nvqs); long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs); long vhost_dev_check_owner(struct vhost_dev *); long vhost_dev_reset_owner(struct vhost_dev *); diff -ruNp org2/drivers/vhost/net.c tx_only2/drivers/vhost/net.c --- org2/drivers/vhost/net.c 2010-08-05 14:48:06.000000000 +0530 +++ tx_only2/drivers/vhost/net.c 2010-09-16 15:24:01.000000000 +0530 @@ -33,12 +33,6 @@ * Using this limit prevents one virtqueue from starving others. */ #define VHOST_NET_WEIGHT 0x80000 -enum { - VHOST_NET_VQ_RX = 0, - VHOST_NET_VQ_TX = 1, - VHOST_NET_VQ_MAX = 2, -}; - enum vhost_net_poll_state { VHOST_NET_POLL_DISABLED = 0, VHOST_NET_POLL_STARTED = 1, @@ -47,12 +41,13 @@ enum vhost_net_poll_state { struct vhost_net { struct vhost_dev dev; - struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX]; - struct vhost_poll poll[VHOST_NET_VQ_MAX]; + struct vhost_virtqueue *vqs; + struct vhost_poll *poll; + struct socket **socks; /* Tells us whether we are polling a socket for TX. * We only do this when socket buffer fills up. * Protected by tx vq lock. */ - enum vhost_net_poll_state tx_poll_state; + enum vhost_net_poll_state *tx_poll_state; }; /* Pop first len bytes from iovec. Return number of segments used. */ @@ -92,28 +87,28 @@ static void copy_iovec_hdr(const struct } /* Caller must have TX VQ lock */ -static void tx_poll_stop(struct vhost_net *net) +static void tx_poll_stop(struct vhost_net *net, int qnum) { - if (likely(net->tx_poll_state != VHOST_NET_POLL_STARTED)) + if (likely(net->tx_poll_state[qnum] != VHOST_NET_POLL_STARTED)) return; - vhost_poll_stop(net->poll + VHOST_NET_VQ_TX); - net->tx_poll_state = VHOST_NET_POLL_STOPPED; + vhost_poll_stop(&net->poll[qnum]); + net->tx_poll_state[qnum] = VHOST_NET_POLL_STOPPED; } /* Caller must have TX VQ lock */ -static void tx_poll_start(struct vhost_net *net, struct socket *sock) +static void tx_poll_start(struct vhost_net *net, struct socket *sock, int qnum) { - if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED)) + if (unlikely(net->tx_poll_state[qnum] != VHOST_NET_POLL_STOPPED)) return; - vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file); - net->tx_poll_state = VHOST_NET_POLL_STARTED; + vhost_poll_start(&net->poll[qnum], sock->file); + net->tx_poll_state[qnum] = VHOST_NET_POLL_STARTED; } /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ -static void handle_tx(struct vhost_net *net) +static void handle_tx(struct vhost_virtqueue *vq) { - struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX]; + struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); unsigned out, in, s; int head; struct msghdr msg = { @@ -134,7 +129,7 @@ static void handle_tx(struct vhost_net * wmem = atomic_read(&sock->sk->sk_wmem_alloc); if (wmem >= sock->sk->sk_sndbuf) { mutex_lock(&vq->mutex); - tx_poll_start(net, sock); + tx_poll_start(net, sock, vq->qnum); mutex_unlock(&vq->mutex); return; } @@ -144,7 +139,7 @@ static void handle_tx(struct vhost_net * vhost_disable_notify(vq); if (wmem < sock->sk->sk_sndbuf / 2) - tx_poll_stop(net); + tx_poll_stop(net, vq->qnum); hdr_size = vq->vhost_hlen; for (;;) { @@ -159,7 +154,7 @@ static void handle_tx(struct vhost_net * if (head == vq->num) { wmem = atomic_read(&sock->sk->sk_wmem_alloc); if (wmem >= sock->sk->sk_sndbuf * 3 / 4) { - tx_poll_start(net, sock); + tx_poll_start(net, sock, vq->qnum); set_bit(SOCK_ASYNC_NOSPACE, &sock->flags); break; } @@ -189,7 +184,7 @@ static void handle_tx(struct vhost_net * err = sock->ops->sendmsg(NULL, sock, &msg, len); if (unlikely(err < 0)) { vhost_discard_vq_desc(vq, 1); - tx_poll_start(net, sock); + tx_poll_start(net, sock, vq->qnum); break; } if (err != len) @@ -282,9 +277,9 @@ err: /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ -static void handle_rx_big(struct vhost_net *net) +static void handle_rx_big(struct vhost_virtqueue *vq, + struct vhost_net *net) { - struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX]; unsigned out, in, log, s; int head; struct vhost_log *vq_log; @@ -393,9 +388,9 @@ static void handle_rx_big(struct vhost_n /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ -static void handle_rx_mergeable(struct vhost_net *net) +static void handle_rx_mergeable(struct vhost_virtqueue *vq, + struct vhost_net *net) { - struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX]; unsigned uninitialized_var(in), log; struct vhost_log *vq_log; struct msghdr msg = { @@ -500,96 +495,181 @@ static void handle_rx_mergeable(struct v unuse_mm(net->dev.mm); } -static void handle_rx(struct vhost_net *net) +static void handle_rx(struct vhost_virtqueue *vq) { + struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); + if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF)) - handle_rx_mergeable(net); + handle_rx_mergeable(vq, net); else - handle_rx_big(net); + handle_rx_big(vq, net); } static void handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); - struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); - handle_tx(net); + handle_tx(vq); } static void handle_rx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); - struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); - handle_rx(net); + handle_rx(vq); } static void handle_tx_net(struct vhost_work *work) { - struct vhost_net *net = container_of(work, struct vhost_net, - poll[VHOST_NET_VQ_TX].work); - handle_tx(net); + struct vhost_virtqueue *vq = container_of(work, struct vhost_poll, + work)->vq; + + handle_tx(vq); } static void handle_rx_net(struct vhost_work *work) { - struct vhost_net *net = container_of(work, struct vhost_net, - poll[VHOST_NET_VQ_RX].work); - handle_rx(net); + struct vhost_virtqueue *vq = container_of(work, struct vhost_poll, + work)->vq; + + handle_rx(vq); } -static int vhost_net_open(struct inode *inode, struct file *f) +void vhost_free_vqs(struct vhost_dev *dev) { - struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL); - struct vhost_dev *dev; - int r; + struct vhost_net *n = container_of(dev, struct vhost_net, dev); - if (!n) - return -ENOMEM; + kfree(dev->work_list); + kfree(dev->work_lock); + kfree(n->socks); + kfree(n->tx_poll_state); + kfree(n->poll); + kfree(n->vqs); - dev = &n->dev; - n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick; - n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick; - r = vhost_dev_init(dev, n->vqs, VHOST_NET_VQ_MAX); - if (r < 0) { - kfree(n); - return r; + /* + * Reset so that vhost_net_release (after vhost_dev_set_owner call) + * will notice. + */ + n->vqs = NULL; + n->poll = NULL; + n->socks = NULL; + n->tx_poll_state = NULL; + dev->work_lock = NULL; + dev->work_list = NULL; +} + +int vhost_setup_vqs(struct vhost_dev *dev, int numtxqs) +{ + struct vhost_net *n = container_of(dev, struct vhost_net, dev); + int num_threads; + int i, nvqs; + int ret; + + if (numtxqs < 0) + return -EINVAL; + + if (numtxqs == 0) { + /* Old qemu doesn't pass arguments to set_owner, use 1 txq */ + numtxqs = 1; + } + + /* Total number of virtqueues is 1 + numtxqs */ + nvqs = numtxqs + 1; + + /* Total number of vhost threads */ + num_threads = vhost_get_num_threads(nvqs); + + n->vqs = kmalloc(nvqs * sizeof(*n->vqs), GFP_KERNEL); + n->poll = kmalloc(nvqs * sizeof(*n->poll), GFP_KERNEL); + n->socks = kmalloc(nvqs * sizeof(*n->socks), GFP_KERNEL); + n->tx_poll_state = kmalloc(nvqs * sizeof(*n->tx_poll_state), + GFP_KERNEL); + dev->work_lock = kmalloc(num_threads * sizeof(*dev->work_lock), + GFP_KERNEL); + dev->work_list = kmalloc(num_threads * sizeof(*dev->work_list), + GFP_KERNEL); + + if (!n->vqs || !n->poll || !n->socks || !n->tx_poll_state || + !dev->work_lock || !dev->work_list) { + ret = -ENOMEM; + goto err; } - vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev); - vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev); - n->tx_poll_state = VHOST_NET_POLL_DISABLED; + /* 1 RX, followed by 'numtxqs' TX queues */ + n->vqs[0].handle_kick = handle_rx_kick; - f->private_data = n; + for (i = 1; i < nvqs; i++) + n->vqs[i].handle_kick = handle_tx_kick; + + ret = vhost_dev_init(dev, n->vqs, nvqs); + if (ret < 0) + goto err; + + vhost_poll_init(&n->poll[0], handle_rx_net, POLLIN, &n->vqs[0]); + + for (i = 1; i < nvqs; i++) { + vhost_poll_init(&n->poll[i], handle_tx_net, POLLOUT, + &n->vqs[i]); + n->tx_poll_state[i] = VHOST_NET_POLL_DISABLED; + } return 0; + +err: + /* Free all pointers that may have been allocated */ + vhost_free_vqs(dev); + + return ret; +} + +static int vhost_net_open(struct inode *inode, struct file *f) +{ + struct vhost_net *n = kzalloc(sizeof *n, GFP_KERNEL); + int ret = ENOMEM; + + if (n) { + struct vhost_dev *dev = &n->dev; + + f->private_data = n; + mutex_init(&dev->mutex); + + /* Defer all other initialization till user does SET_OWNER */ + ret = 0; + } + + return ret; } static void vhost_net_disable_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { + int qnum = vq->qnum; + if (!vq->private_data) return; - if (vq == n->vqs + VHOST_NET_VQ_TX) { - tx_poll_stop(n); - n->tx_poll_state = VHOST_NET_POLL_DISABLED; + if (qnum) { /* TX */ + tx_poll_stop(n, qnum); + n->tx_poll_state[qnum] = VHOST_NET_POLL_DISABLED; } else - vhost_poll_stop(n->poll + VHOST_NET_VQ_RX); + vhost_poll_stop(&n->poll[qnum]); } static void vhost_net_enable_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct socket *sock = vq->private_data; + int qnum = vq->qnum; + if (!sock) return; - if (vq == n->vqs + VHOST_NET_VQ_TX) { - n->tx_poll_state = VHOST_NET_POLL_STOPPED; - tx_poll_start(n, sock); + + if (qnum) { /* TX */ + n->tx_poll_state[qnum] = VHOST_NET_POLL_STOPPED; + tx_poll_start(n, sock, qnum); } else - vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file); + vhost_poll_start(&n->poll[qnum], sock->file); } static struct socket *vhost_net_stop_vq(struct vhost_net *n, @@ -605,11 +685,12 @@ static struct socket *vhost_net_stop_vq( return sock; } -static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock, - struct socket **rx_sock) +static void vhost_net_stop(struct vhost_net *n) { - *tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX); - *rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX); + int i; + + for (i = n->dev.nvqs - 1; i >= 0; i--) + n->socks[i] = vhost_net_stop_vq(n, &n->vqs[i]); } static void vhost_net_flush_vq(struct vhost_net *n, int index) @@ -620,26 +701,33 @@ static void vhost_net_flush_vq(struct vh static void vhost_net_flush(struct vhost_net *n) { - vhost_net_flush_vq(n, VHOST_NET_VQ_TX); - vhost_net_flush_vq(n, VHOST_NET_VQ_RX); + int i; + + for (i = n->dev.nvqs - 1; i >= 0; i--) + vhost_net_flush_vq(n, i); } static int vhost_net_release(struct inode *inode, struct file *f) { struct vhost_net *n = f->private_data; - struct socket *tx_sock; - struct socket *rx_sock; + struct vhost_dev *dev = &n->dev; + int i; - vhost_net_stop(n, &tx_sock, &rx_sock); + vhost_net_stop(n); vhost_net_flush(n); - vhost_dev_cleanup(&n->dev); - if (tx_sock) - fput(tx_sock->file); - if (rx_sock) - fput(rx_sock->file); + vhost_dev_cleanup(dev); + + for (i = n->dev.nvqs - 1; i >= 0; i--) + if (n->socks[i]) + fput(n->socks[i]->file); + /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ vhost_net_flush(n); + + /* Free all old pointers */ + vhost_free_vqs(dev); + kfree(n); return 0; } @@ -717,7 +805,7 @@ static long vhost_net_set_backend(struct if (r) goto err; - if (index >= VHOST_NET_VQ_MAX) { + if (index >= n->dev.nvqs) { r = -ENOBUFS; goto err; } @@ -762,22 +850,25 @@ err: static long vhost_net_reset_owner(struct vhost_net *n) { - struct socket *tx_sock = NULL; - struct socket *rx_sock = NULL; long err; + int i; + mutex_lock(&n->dev.mutex); err = vhost_dev_check_owner(&n->dev); - if (err) - goto done; - vhost_net_stop(n, &tx_sock, &rx_sock); + if (err) { + mutex_unlock(&n->dev.mutex); + return err; + } + + vhost_net_stop(n); vhost_net_flush(n); err = vhost_dev_reset_owner(&n->dev); -done: mutex_unlock(&n->dev.mutex); - if (tx_sock) - fput(tx_sock->file); - if (rx_sock) - fput(rx_sock->file); + + for (i = n->dev.nvqs - 1; i >= 0; i--) + if (n->socks[i]) + fput(n->socks[i]->file); + return err; } @@ -806,7 +897,7 @@ static int vhost_net_set_features(struct } n->dev.acked_features = features; smp_wmb(); - for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { + for (i = 0; i < n->dev.nvqs; ++i) { mutex_lock(&n->vqs[i].mutex); n->vqs[i].vhost_hlen = vhost_hlen; n->vqs[i].sock_hlen = sock_hlen; diff -ruNp org2/drivers/vhost/vhost.c tx_only2/drivers/vhost/vhost.c --- org2/drivers/vhost/vhost.c 2010-09-10 16:34:07.000000000 +0530 +++ tx_only2/drivers/vhost/vhost.c 2010-09-16 16:35:29.000000000 +0530 @@ -71,12 +71,12 @@ static void vhost_work_init(struct vhost /* Init poll structure */ void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, - unsigned long mask, struct vhost_dev *dev) + unsigned long mask, struct vhost_virtqueue *vq) { init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup); init_poll_funcptr(&poll->table, vhost_poll_func); poll->mask = mask; - poll->dev = dev; + poll->vq = vq; vhost_work_init(&poll->work, fn); } @@ -98,25 +98,25 @@ void vhost_poll_stop(struct vhost_poll * remove_wait_queue(poll->wqh, &poll->wait); } -static void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work) +static void vhost_work_flush(struct vhost_poll *poll, struct vhost_work *work) { unsigned seq; int left; int flushing; - spin_lock_irq(&dev->work_lock); + spin_lock_irq(poll->vq->work_lock); seq = work->queue_seq; work->flushing++; - spin_unlock_irq(&dev->work_lock); + spin_unlock_irq(poll->vq->work_lock); wait_event(work->done, ({ - spin_lock_irq(&dev->work_lock); + spin_lock_irq(poll->vq->work_lock); left = seq - work->done_seq <= 0; - spin_unlock_irq(&dev->work_lock); + spin_unlock_irq(poll->vq->work_lock); left; })); - spin_lock_irq(&dev->work_lock); + spin_lock_irq(poll->vq->work_lock); flushing = --work->flushing; - spin_unlock_irq(&dev->work_lock); + spin_unlock_irq(poll->vq->work_lock); BUG_ON(flushing < 0); } @@ -124,26 +124,26 @@ static void vhost_work_flush(struct vhos * locks that are also used by the callback. */ void vhost_poll_flush(struct vhost_poll *poll) { - vhost_work_flush(poll->dev, &poll->work); + vhost_work_flush(poll, &poll->work); } -static inline void vhost_work_queue(struct vhost_dev *dev, +static inline void vhost_work_queue(struct vhost_virtqueue *vq, struct vhost_work *work) { unsigned long flags; - spin_lock_irqsave(&dev->work_lock, flags); + spin_lock_irqsave(vq->work_lock, flags); if (list_empty(&work->node)) { - list_add_tail(&work->node, &dev->work_list); + list_add_tail(&work->node, vq->work_list); work->queue_seq++; - wake_up_process(dev->worker); + wake_up_process(vq->worker); } - spin_unlock_irqrestore(&dev->work_lock, flags); + spin_unlock_irqrestore(vq->work_lock, flags); } void vhost_poll_queue(struct vhost_poll *poll) { - vhost_work_queue(poll->dev, &poll->work); + vhost_work_queue(poll->vq, &poll->work); } static void vhost_vq_reset(struct vhost_dev *dev, @@ -174,7 +174,7 @@ static void vhost_vq_reset(struct vhost_ static int vhost_worker(void *data) { - struct vhost_dev *dev = data; + struct vhost_virtqueue *vq = data; struct vhost_work *work = NULL; unsigned uninitialized_var(seq); @@ -182,7 +182,7 @@ static int vhost_worker(void *data) /* mb paired w/ kthread_stop */ set_current_state(TASK_INTERRUPTIBLE); - spin_lock_irq(&dev->work_lock); + spin_lock_irq(vq->work_lock); if (work) { work->done_seq = seq; if (work->flushing) @@ -190,18 +190,18 @@ static int vhost_worker(void *data) } if (kthread_should_stop()) { - spin_unlock_irq(&dev->work_lock); + spin_unlock_irq(vq->work_lock); __set_current_state(TASK_RUNNING); return 0; } - if (!list_empty(&dev->work_list)) { - work = list_first_entry(&dev->work_list, + if (!list_empty(vq->work_list)) { + work = list_first_entry(vq->work_list, struct vhost_work, node); list_del_init(&work->node); seq = work->queue_seq; } else work = NULL; - spin_unlock_irq(&dev->work_lock); + spin_unlock_irq(vq->work_lock); if (work) { __set_current_state(TASK_RUNNING); @@ -212,9 +212,22 @@ static int vhost_worker(void *data) } } +/* + * Maximum number of vhost threads to handle RX/TX. First thread handles + * RX, next threads handle TX[0-n], where the number of threads is bound + * by MAX_VHOST_THREADS. + */ +#define MAX_VHOST_THREADS 2 + +int vhost_get_num_threads(int nvqs) +{ + return min_t(int, nvqs - 1, MAX_VHOST_THREADS); +} + long vhost_dev_init(struct vhost_dev *dev, struct vhost_virtqueue *vqs, int nvqs) { + int num_threads = vhost_get_num_threads(nvqs); int i; dev->vqs = vqs; @@ -224,17 +237,32 @@ long vhost_dev_init(struct vhost_dev *de dev->log_file = NULL; dev->memory = NULL; dev->mm = NULL; - spin_lock_init(&dev->work_lock); - INIT_LIST_HEAD(&dev->work_list); - dev->worker = NULL; for (i = 0; i < dev->nvqs; ++i) { - dev->vqs[i].dev = dev; - mutex_init(&dev->vqs[i].mutex); + struct vhost_virtqueue *vq = &dev->vqs[i]; + + if (i < num_threads) { + spin_lock_init(&dev->work_lock[i]); + INIT_LIST_HEAD(&dev->work_list[i]); + + vq->work_lock = &dev->work_lock[i]; + vq->work_list = &dev->work_list[i]; + } else { + int j = i % num_threads; + + /* Share work with another RX/TX thread */ + vq->work_lock = &dev->work_lock[j]; + vq->work_list = &dev->work_list[j]; + } + + vq->worker = NULL; + vq->dev = dev; + vq->qnum = i; + mutex_init(&vq->mutex); vhost_vq_reset(dev, dev->vqs + i); - if (dev->vqs[i].handle_kick) - vhost_poll_init(&dev->vqs[i].poll, - dev->vqs[i].handle_kick, POLLIN, dev); + if (vq->handle_kick) + vhost_poll_init(&vq->poll, vq->handle_kick, POLLIN, + vq); } return 0; @@ -260,46 +288,98 @@ static void vhost_attach_cgroups_work(st s->ret = cgroup_attach_task_all(s->owner, current); } -static int vhost_attach_cgroups(struct vhost_dev *dev) +static int vhost_attach_cgroups(struct vhost_virtqueue *vq) { struct vhost_attach_cgroups_struct attach; attach.owner = current; vhost_work_init(&attach.work, vhost_attach_cgroups_work); - vhost_work_queue(dev, &attach.work); - vhost_work_flush(dev, &attach.work); + vhost_work_queue(vq, &attach.work); + vhost_work_flush(&vq->poll, &attach.work); return attach.ret; } +static void __vhost_stop_workers(struct vhost_dev *dev, int num_threads) +{ + int i; + + for (i = 0; i < num_threads; i++) { + WARN_ON(!list_empty(dev->vqs[i].work_list)); + if (dev->vqs[i].worker) { + kthread_stop(dev->vqs[i].worker); + dev->vqs[i].worker = NULL; + } + } +} + +static void vhost_stop_workers(struct vhost_dev *dev) +{ + __vhost_stop_workers(dev, vhost_get_num_threads(dev->nvqs)); +} + +static int vhost_start_workers(struct vhost_dev *dev) +{ + int num_threads = vhost_get_num_threads(dev->nvqs); + int i, err; + + for (i = 0; i < dev->nvqs; ++i) { + struct vhost_virtqueue *vq = &dev->vqs[i]; + + if (i < num_threads) { + vq->worker = kthread_create(vhost_worker, vq, + "vhost-%d-%d", + current->pid, i); + if (IS_ERR(vq->worker)) { + i--; /* no thread to clean at this index */ + err = PTR_ERR(vq->worker); + goto err; + } + + wake_up_process(vq->worker); + + /* avoid contributing to loadavg */ + err = vhost_attach_cgroups(vq); + if (err) + goto err; + } else { + int j = i % num_threads; + struct vhost_virtqueue *share_vq = &dev->vqs[j]; + + vq->worker = share_vq->worker; + } + } + return 0; + +err: + __vhost_stop_workers(dev, i); + return err; +} + /* Caller should have device mutex */ -static long vhost_dev_set_owner(struct vhost_dev *dev) +static long vhost_dev_set_owner(struct vhost_dev *dev, int numtxqs) { - struct task_struct *worker; int err; /* Is there an owner already? */ if (dev->mm) { err = -EBUSY; goto err_mm; } + + err = vhost_setup_vqs(dev, numtxqs); + if (err) + goto err_mm; + /* No owner, become one */ dev->mm = get_task_mm(current); - worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid); - if (IS_ERR(worker)) { - err = PTR_ERR(worker); - goto err_worker; - } - - dev->worker = worker; - wake_up_process(worker); /* avoid contributing to loadavg */ - err = vhost_attach_cgroups(dev); + /* Start threads */ + err = vhost_start_workers(dev); if (err) - goto err_cgroup; + goto free_vqs; return 0; -err_cgroup: - kthread_stop(worker); - dev->worker = NULL; -err_worker: + +free_vqs: + vhost_free_vqs(dev); if (dev->mm) mmput(dev->mm); dev->mm = NULL; @@ -358,11 +438,7 @@ void vhost_dev_cleanup(struct vhost_dev mmput(dev->mm); dev->mm = NULL; - WARN_ON(!list_empty(&dev->work_list)); - if (dev->worker) { - kthread_stop(dev->worker); - dev->worker = NULL; - } + vhost_stop_workers(dev); } static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz) @@ -713,7 +789,7 @@ long vhost_dev_ioctl(struct vhost_dev *d /* If you are not the owner, you can become one */ if (ioctl == VHOST_SET_OWNER) { - r = vhost_dev_set_owner(d); + r = vhost_dev_set_owner(d, arg); goto done; }