Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost updates from Michael Tsirkin:
 "New features, performance improvements, cleanups:

   - basic polling support for vhost
   - rework virtio to optionally use DMA API, fixing it on Xen
   - balloon stats gained a new entry
   - using the new napi_alloc_skb speeds up virtio net
   - virtio blk stats can now be read while another VCPU is busy
     inflating or deflating the balloon

  plus misc cleanups in various places"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_net: replace netdev_alloc_skb_ip_align() with napi_alloc_skb()
  vhost_net: basic polling support
  vhost: introduce vhost_vq_avail_empty()
  vhost: introduce vhost_has_work()
  virtio_balloon: Allow to resize and update the balloon stats in parallel
  virtio_balloon: Use a workqueue instead of "vballoon" kthread
  virtio/s390: size of SET_IND payload
  virtio/s390: use dev_to_virtio
  vhost: rename vhost_init_used()
  vhost: rename cross-endian helpers
  virtio_blk: VIRTIO_BLK_F_WCE->VIRTIO_BLK_F_FLUSH
  vring: Use the DMA API on Xen
  virtio_pci: Use the DMA API if enabled
  virtio_mmio: Use the DMA API if enabled
  virtio: Add improved queue allocation API
  virtio_ring: Support DMA APIs
  vring: Introduce vring_use_dma_api()
  s390/dma: Allow per device dma ops
  alpha/dma: use common noop dma ops
  dma: Provide simple noop dma ops

5 files changed, 141 insertions, 17 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9eda69e40678..f744eeb3e2b4 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -287,6 +287,43 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
 	rcu_read_unlock_bh();
 }
 
+static inline unsigned long busy_clock(void)
+{
+	return local_clock() >> 10;
+}
+
+static bool vhost_can_busy_poll(struct vhost_dev *dev,
+				unsigned long endtime)
+{
+	return likely(!need_resched()) &&
+	       likely(!time_after(busy_clock(), endtime)) &&
+	       likely(!signal_pending(current)) &&
+	       !vhost_has_work(dev);
+}
+
+static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
+				    struct vhost_virtqueue *vq,
+				    struct iovec iov[], unsigned int iov_size,
+				    unsigned int *out_num, unsigned int *in_num)
+{
+	unsigned long uninitialized_var(endtime);
+	int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
+				    out_num, in_num, NULL, NULL);
+
+	if (r == vq->num && vq->busyloop_timeout) {
+		preempt_disable();
+		endtime = busy_clock() + vq->busyloop_timeout;
+		while (vhost_can_busy_poll(vq->dev, endtime) &&
+		       vhost_vq_avail_empty(vq->dev, vq))
+			cpu_relax_lowlatency();
+		preempt_enable();
+		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
+					out_num, in_num, NULL, NULL);
+	}
+
+	return r;
+}
+
 /* 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)
@@ -331,10 +368,9 @@ static void handle_tx(struct vhost_net *net)
 			      % UIO_MAXIOV == nvq->done_idx))
 			break;
 
-		head = vhost_get_vq_desc(vq, vq->iov,
-					 ARRAY_SIZE(vq->iov),
-					 &out, &in,
-					 NULL, NULL);
+		head = vhost_net_tx_get_vq_desc(net, vq, vq->iov,
+						ARRAY_SIZE(vq->iov),
+						&out, &in);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(head < 0))
 			break;
@@ -435,6 +471,38 @@ static int peek_head_len(struct sock *sk)
 	return len;
 }
 
+static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
+{
+	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *vq = &nvq->vq;
+	unsigned long uninitialized_var(endtime);
+	int len = peek_head_len(sk);
+
+	if (!len && vq->busyloop_timeout) {
+		/* Both tx vq and rx socket were polled here */
+		mutex_lock(&vq->mutex);
+		vhost_disable_notify(&net->dev, vq);
+
+		preempt_disable();
+		endtime = busy_clock() + vq->busyloop_timeout;
+
+		while (vhost_can_busy_poll(&net->dev, endtime) &&
+		       skb_queue_empty(&sk->sk_receive_queue) &&
+		       vhost_vq_avail_empty(&net->dev, vq))
+			cpu_relax_lowlatency();
+
+		preempt_enable();
+
+		if (vhost_enable_notify(&net->dev, vq))
+			vhost_poll_queue(&vq->poll);
+		mutex_unlock(&vq->mutex);
+
+		len = peek_head_len(sk);
+	}
+
+	return len;
+}
+
 /* This is a multi-buffer version of vhost_get_desc, that works if
  *	vq has read descriptors only.
  * @vq		- the relevant virtqueue
@@ -553,7 +621,7 @@ static void handle_rx(struct vhost_net *net)
 		vq->log : NULL;
 	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
 
-	while ((sock_len = peek_head_len(sock->sk))) {
+	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
 		headcount = get_rx_bufs(vq, vq->heads, vhost_len,
@@ -917,7 +985,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 
 		vhost_net_disable_vq(n, vq);
 		vq->private_data = sock;
-		r = vhost_init_used(vq);
+		r = vhost_vq_init_access(vq);
 		if (r)
 			goto err_used;
 		r = vhost_net_enable_vq(n, vq);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 29cfc57d496e..f898686cdd93 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1274,7 +1274,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 			vq = &vs->vqs[i].vq;
 			mutex_lock(&vq->mutex);
 			vq->private_data = vs_tpg;
-			vhost_init_used(vq);
+			vhost_vq_init_access(vq);
 			mutex_unlock(&vq->mutex);
 		}
 		ret = 0;
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index f2882ac98726..388eec4e1a90 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -196,7 +196,7 @@ static long vhost_test_run(struct vhost_test *n, int test)
 		oldpriv = vq->private_data;
 		vq->private_data = priv;
 
-		r = vhost_init_used(&n->vqs[index]);
+		r = vhost_vq_init_access(&n->vqs[index]);
 
 		mutex_unlock(&vq->mutex);
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 236553e81027..669fef1e2bb6 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -43,11 +43,21 @@ enum {
 #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
 
 #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
-static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq)
+static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
 {
 	vq->user_be = !virtio_legacy_is_little_endian();
 }
 
+static void vhost_enable_cross_endian_big(struct vhost_virtqueue *vq)
+{
+	vq->user_be = true;
+}
+
+static void vhost_enable_cross_endian_little(struct vhost_virtqueue *vq)
+{
+	vq->user_be = false;
+}
+
 static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
 {
 	struct vhost_vring_state s;
@@ -62,7 +72,10 @@ static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
 	    s.num != VHOST_VRING_BIG_ENDIAN)
 		return -EINVAL;
 
-	vq->user_be = s.num;
+	if (s.num == VHOST_VRING_BIG_ENDIAN)
+		vhost_enable_cross_endian_big(vq);
+	else
+		vhost_enable_cross_endian_little(vq);
 
 	return 0;
 }
@@ -91,7 +104,7 @@ static void vhost_init_is_le(struct vhost_virtqueue *vq)
 	vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be;
 }
 #else
-static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq)
+static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
 {
 }
 
@@ -113,6 +126,11 @@ static void vhost_init_is_le(struct vhost_virtqueue *vq)
 }
 #endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */
 
+static void vhost_reset_is_le(struct vhost_virtqueue *vq)
+{
+	vq->is_le = virtio_legacy_is_little_endian();
+}
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
@@ -245,6 +263,13 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
 }
 EXPORT_SYMBOL_GPL(vhost_work_queue);
 
+/* A lockless hint for busy polling code to exit the loop */
+bool vhost_has_work(struct vhost_dev *dev)
+{
+	return !list_empty(&dev->work_list);
+}
+EXPORT_SYMBOL_GPL(vhost_has_work);
+
 void vhost_poll_queue(struct vhost_poll *poll)
 {
 	vhost_work_queue(poll->dev, &poll->work);
@@ -276,8 +301,9 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->call = NULL;
 	vq->log_ctx = NULL;
 	vq->memory = NULL;
-	vq->is_le = virtio_legacy_is_little_endian();
-	vhost_vq_reset_user_be(vq);
+	vhost_reset_is_le(vq);
+	vhost_disable_cross_endian(vq);
+	vq->busyloop_timeout = 0;
 }
 
 static int vhost_worker(void *data)
@@ -912,6 +938,19 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
 	case VHOST_GET_VRING_ENDIAN:
 		r = vhost_get_vring_endian(vq, idx, argp);
 		break;
+	case VHOST_SET_VRING_BUSYLOOP_TIMEOUT:
+		if (copy_from_user(&s, argp, sizeof(s))) {
+			r = -EFAULT;
+			break;
+		}
+		vq->busyloop_timeout = s.num;
+		break;
+	case VHOST_GET_VRING_BUSYLOOP_TIMEOUT:
+		s.index = idx;
+		s.num = vq->busyloop_timeout;
+		if (copy_to_user(argp, &s, sizeof(s)))
+			r = -EFAULT;
+		break;
 	default:
 		r = -ENOIOCTLCMD;
 	}
@@ -1152,14 +1191,14 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
 	return 0;
 }
 
-int vhost_init_used(struct vhost_virtqueue *vq)
+int vhost_vq_init_access(struct vhost_virtqueue *vq)
 {
 	__virtio16 last_used_idx;
 	int r;
 	bool is_le = vq->is_le;
 
 	if (!vq->private_data) {
-		vq->is_le = virtio_legacy_is_little_endian();
+		vhost_reset_is_le(vq);
 		return 0;
 	}
 
@@ -1182,7 +1221,7 @@ err:
 	vq->is_le = is_le;
 	return r;
 }
-EXPORT_SYMBOL_GPL(vhost_init_used);
+EXPORT_SYMBOL_GPL(vhost_vq_init_access);
 
 static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 			  struct iovec iov[], int iov_size)
@@ -1633,6 +1672,20 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev,
 }
 EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n);
 
+/* return true if we're sure that avaiable ring is empty */
+bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
+	__virtio16 avail_idx;
+	int r;
+
+	r = __get_user(avail_idx, &vq->avail->idx);
+	if (r)
+		return false;
+
+	return vhost16_to_cpu(vq, avail_idx) == vq->avail_idx;
+}
+EXPORT_SYMBOL_GPL(vhost_vq_avail_empty);
+
 /* OK, now we need to know about added descriptors. */
 bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index d3f767448a72..d36d8beb3351 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -37,6 +37,7 @@ struct vhost_poll {
 
 void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
 void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work);
+bool vhost_has_work(struct vhost_dev *dev);
 
 void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
 		     unsigned long mask, struct vhost_dev *dev);
@@ -114,6 +115,7 @@ struct vhost_virtqueue {
 	/* Ring endianness requested by userspace for cross-endian support. */
 	bool user_be;
 #endif
+	u32 busyloop_timeout;
 };
 
 struct vhost_dev {
@@ -148,7 +150,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *,
 		      struct vhost_log *log, unsigned int *log_num);
 void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
 
-int vhost_init_used(struct vhost_virtqueue *);
+int vhost_vq_init_access(struct vhost_virtqueue *);
 int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
 int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
 		     unsigned count);
@@ -158,6 +160,7 @@ void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
 			       struct vring_used_elem *heads, unsigned count);
 void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
 void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
+bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
 bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,