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

Pull virtio updates from Michael Tsirkin:

 - vhost can now support legacy threading if enabled in Kconfig

 - vsock memory allocation strategies for large buffers have been
   improved, reducing pressure on kmalloc

 - vhost now supports the in-order feature. guest bits missed the merge
   window.

 - fixes, cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (30 commits)
  vsock/virtio: Allocate nonlinear SKBs for handling large transmit buffers
  vsock/virtio: Rename virtio_vsock_skb_rx_put()
  vhost/vsock: Allocate nonlinear SKBs for handling large receive buffers
  vsock/virtio: Move SKB allocation lower-bound check to callers
  vsock/virtio: Rename virtio_vsock_alloc_skb()
  vsock/virtio: Resize receive buffers so that each SKB fits in a 4K page
  vsock/virtio: Move length check to callers of virtio_vsock_skb_rx_put()
  vsock/virtio: Validate length in packet header before skb_put()
  vhost/vsock: Avoid allocating arbitrarily-sized SKBs
  vhost_net: basic in_order support
  vhost: basic in order support
  vhost: fail early when __vhost_add_used() fails
  vhost: Reintroduce kthread API and add mode selection
  vdpa: Fix IDR memory leak in VDUSE module exit
  vdpa/mlx5: Fix release of uninitialized resources on error path
  vhost-scsi: Fix check for inline_sg_cnt exceeding preallocated limit
  virtio: virtio_dma_buf: fix missing parameter documentation
  vhost: Fix typos
  vhost: vringh: Remove unused functions
  vhost: vringh: Remove unused iotlb functions
  ...

Author: torvalds

drivers/gpu/drm/virtio/virtgpu_drv.c

@@ -130,10 +130,10 @@ static void virtio_gpu_remove(struct virtio_device *vdev)
 
 static void virtio_gpu_shutdown(struct virtio_device *vdev)
 {
-	/*
-	 * drm does its own synchronization on shutdown.
-	 * Do nothing here, opt out of device reset.
-	 */
+	struct drm_device *dev = vdev->priv;
+
+	/* stop talking to the device */
+	drm_dev_unplug(dev);
 }
 
 static void virtio_gpu_config_changed(struct virtio_device *vdev)

drivers/vdpa/mlx5/core/mr.c

@@ -908,6 +908,9 @@ void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
 {
 	struct mlx5_vdpa_mr_resources *mres = &mvdev->mres;
 
+	if (!mres->wq_gc)
+		return;
+
 	atomic_set(&mres->shutdown, 1);
 
 	flush_delayed_work(&mres->gc_dwork_ent);

drivers/vdpa/mlx5/net/mlx5_vnet.c

@@ -2491,7 +2491,7 @@ static void mlx5_vdpa_set_vq_num(struct vdpa_device *vdev, u16 idx, u32 num)
         }
 
 	mvq = &ndev->vqs[idx];
-	ndev->needs_teardown = num != mvq->num_ent;
+	ndev->needs_teardown |= num != mvq->num_ent;
 	mvq->num_ent = num;
 }
 
@@ -3432,15 +3432,17 @@ static void mlx5_vdpa_free(struct vdpa_device *vdev)
 
 	ndev = to_mlx5_vdpa_ndev(mvdev);
 
+	/* Functions called here should be able to work with
+	 * uninitialized resources.
+	 */
 	free_fixed_resources(ndev);
 	mlx5_vdpa_clean_mrs(mvdev);
 	mlx5_vdpa_destroy_mr_resources(&ndev->mvdev);
-	mlx5_cmd_cleanup_async_ctx(&mvdev->async_ctx);
-
 	if (!is_zero_ether_addr(ndev->config.mac)) {
 		pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev));
 		mlx5_mpfs_del_mac(pfmdev, ndev->config.mac);
 	}
+	mlx5_cmd_cleanup_async_ctx(&mvdev->async_ctx);
 	mlx5_vdpa_free_resources(&ndev->mvdev);
 	free_irqs(ndev);
 	kfree(ndev->event_cbs);
@@ -3888,6 +3890,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	mvdev->actual_features =
 			(device_features & BIT_ULL(VIRTIO_F_VERSION_1));
 
+	mlx5_cmd_init_async_ctx(mdev, &mvdev->async_ctx);
+
 	ndev->vqs = kcalloc(max_vqs, sizeof(*ndev->vqs), GFP_KERNEL);
 	ndev->event_cbs = kcalloc(max_vqs + 1, sizeof(*ndev->event_cbs), GFP_KERNEL);
 	if (!ndev->vqs || !ndev->event_cbs) {
@@ -3960,8 +3964,6 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 		ndev->rqt_size = 1;
 	}
 
-	mlx5_cmd_init_async_ctx(mdev, &mvdev->async_ctx);
-
 	ndev->mvdev.mlx_features = device_features;
 	mvdev->vdev.dma_dev = &mdev->pdev->dev;
 	err = mlx5_vdpa_alloc_resources(&ndev->mvdev);

drivers/vdpa/vdpa_user/vduse_dev.c

@@ -2216,6 +2216,7 @@ static void vduse_exit(void)
 	cdev_del(&vduse_ctrl_cdev);
 	unregister_chrdev_region(vduse_major, VDUSE_DEV_MAX);
 	class_unregister(&vduse_class);
+	idr_destroy(&vduse_idr);
 }
 module_exit(vduse_exit);
 

drivers/vhost/Kconfig

@@ -95,4 +95,22 @@ config VHOST_CROSS_ENDIAN_LEGACY
 
 	  If unsure, say "N".
 
+config VHOST_ENABLE_FORK_OWNER_CONTROL
+	bool "Enable VHOST_ENABLE_FORK_OWNER_CONTROL"
+	default y
+	help
+	  This option enables two IOCTLs: VHOST_SET_FORK_FROM_OWNER and
+	  VHOST_GET_FORK_FROM_OWNER. These allow userspace applications
+	  to modify the vhost worker mode for vhost devices.
+
+	  Also expose module parameter 'fork_from_owner_default' to allow users
+	  to configure the default mode for vhost workers.
+
+	  By default, `VHOST_ENABLE_FORK_OWNER_CONTROL` is set to `y`,
+	  users can change the worker thread mode as needed.
+	  If this config is disabled (n),the related IOCTLs and parameters will
+	  be unavailable.
+
+	  If unsure, say "Y".
+
 endif

drivers/vhost/net.c

@@ -74,7 +74,8 @@ static const u64 vhost_net_features[VIRTIO_FEATURES_DWORDS] = {
 	(1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
 	(1ULL << VIRTIO_NET_F_MRG_RXBUF) |
 	(1ULL << VIRTIO_F_ACCESS_PLATFORM) |
-	(1ULL << VIRTIO_F_RING_RESET),
+	(1ULL << VIRTIO_F_RING_RESET) |
+	(1ULL << VIRTIO_F_IN_ORDER),
 	VIRTIO_BIT(VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO) |
 	VIRTIO_BIT(VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO),
 };
@@ -376,7 +377,8 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net,
 	while (j) {
 		add = min(UIO_MAXIOV - nvq->done_idx, j);
 		vhost_add_used_and_signal_n(vq->dev, vq,
-					    &vq->heads[nvq->done_idx], add);
+					    &vq->heads[nvq->done_idx],
+					    NULL, add);
 		nvq->done_idx = (nvq->done_idx + add) % UIO_MAXIOV;
 		j -= add;
 	}
@@ -451,15 +453,17 @@ static int vhost_net_enable_vq(struct vhost_net *n,
 	return vhost_poll_start(poll, sock->file);
 }
 
-static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq)
+static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq,
+				  unsigned int count)
 {
 	struct vhost_virtqueue *vq = &nvq->vq;
 	struct vhost_dev *dev = vq->dev;
 
 	if (!nvq->done_idx)
 		return;
 
-	vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
+	vhost_add_used_and_signal_n(dev, vq, vq->heads,
+				    vq->nheads, count);
 	nvq->done_idx = 0;
 }
 
@@ -468,13 +472,20 @@ static void vhost_tx_batch(struct vhost_net *net,
 			   struct socket *sock,
 			   struct msghdr *msghdr)
 {
+	struct vhost_virtqueue *vq = &nvq->vq;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
 	struct tun_msg_ctl ctl = {
 		.type = TUN_MSG_PTR,
 		.num = nvq->batched_xdp,
 		.ptr = nvq->xdp,
 	};
 	int i, err;
 
+	if (in_order) {
+		vq->heads[0].len = 0;
+		vq->nheads[0] = nvq->done_idx;
+	}
+
 	if (nvq->batched_xdp == 0)
 		goto signal_used;
 
@@ -496,7 +507,7 @@ static void vhost_tx_batch(struct vhost_net *net,
 	}
 
 signal_used:
-	vhost_net_signal_used(nvq);
+	vhost_net_signal_used(nvq, in_order ? 1 : nvq->done_idx);
 	nvq->batched_xdp = 0;
 }
 
@@ -750,6 +761,7 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 	int sent_pkts = 0;
 	bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX);
 	bool busyloop_intr;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
 
 	do {
 		busyloop_intr = false;
@@ -786,11 +798,13 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 				break;
 			}
 
-			/* We can't build XDP buff, go for single
-			 * packet path but let's flush batched
-			 * packets.
-			 */
-			vhost_tx_batch(net, nvq, sock, &msg);
+			if (nvq->batched_xdp) {
+				/* We can't build XDP buff, go for single
+				 * packet path but let's flush batched
+				 * packets.
+				 */
+				vhost_tx_batch(net, nvq, sock, &msg);
+			}
 			msg.msg_control = NULL;
 		} else {
 			if (tx_can_batch(vq, total_len))
@@ -811,8 +825,12 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 			pr_debug("Truncated TX packet: len %d != %zd\n",
 				 err, len);
 done:
-		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
-		vq->heads[nvq->done_idx].len = 0;
+		if (in_order) {
+			vq->heads[0].id = cpu_to_vhost32(vq, head);
+		} else {
+			vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
+			vq->heads[nvq->done_idx].len = 0;
+		}
 		++nvq->done_idx;
 	} while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 
@@ -991,7 +1009,7 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk)
 }
 
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
-				      bool *busyloop_intr)
+				      bool *busyloop_intr, unsigned int count)
 {
 	struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
 	struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
@@ -1001,7 +1019,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 
 	if (!len && rvq->busyloop_timeout) {
 		/* Flush batched heads first */
-		vhost_net_signal_used(rnvq);
+		vhost_net_signal_used(rnvq, count);
 		/* Both tx vq and rx socket were polled here */
 		vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, true);
 
@@ -1013,22 +1031,25 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 
 /* This is a multi-buffer version of vhost_get_desc, that works if
  *	vq has read descriptors only.
- * @vq		- the relevant virtqueue
+ * @nvq		- the relevant vhost_net virtqueue
  * @datalen	- data length we'll be reading
  * @iovcount	- returned count of io vectors we fill
  * @log		- vhost log
  * @log_num	- log offset
  * @quota       - headcount quota, 1 for big buffer
  *	returns number of buffer heads allocated, negative on error
  */
-static int get_rx_bufs(struct vhost_virtqueue *vq,
+static int get_rx_bufs(struct vhost_net_virtqueue *nvq,
 		       struct vring_used_elem *heads,
+		       u16 *nheads,
 		       int datalen,
 		       unsigned *iovcount,
 		       struct vhost_log *log,
 		       unsigned *log_num,
 		       unsigned int quota)
 {
+	struct vhost_virtqueue *vq = &nvq->vq;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
 	unsigned int out, in;
 	int seg = 0;
 	int headcount = 0;
@@ -1065,14 +1086,16 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 			nlogs += *log_num;
 			log += *log_num;
 		}
-		heads[headcount].id = cpu_to_vhost32(vq, d);
 		len = iov_length(vq->iov + seg, in);
-		heads[headcount].len = cpu_to_vhost32(vq, len);
-		datalen -= len;
+		if (!in_order) {
+			heads[headcount].id = cpu_to_vhost32(vq, d);
+			heads[headcount].len = cpu_to_vhost32(vq, len);
+		}
 		++headcount;
+		datalen -= len;
 		seg += in;
 	}
-	heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen);
+
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
@@ -1082,6 +1105,15 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 		r = UIO_MAXIOV + 1;
 		goto err;
 	}
+
+	if (!in_order)
+		heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen);
+	else {
+		heads[0].len = cpu_to_vhost32(vq, len + datalen);
+		heads[0].id = cpu_to_vhost32(vq, d);
+		nheads[0] = headcount;
+	}
+
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);
@@ -1094,6 +1126,8 @@ static void handle_rx(struct vhost_net *net)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_RX];
 	struct vhost_virtqueue *vq = &nvq->vq;
+	bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
+	unsigned int count = 0;
 	unsigned in, log;
 	struct vhost_log *vq_log;
 	struct msghdr msg = {
@@ -1141,12 +1175,13 @@ static void handle_rx(struct vhost_net *net)
 
 	do {
 		sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
-						      &busyloop_intr);
+						      &busyloop_intr, count);
 		if (!sock_len)
 			break;
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
-		headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
+		headcount = get_rx_bufs(nvq, vq->heads + count,
+					vq->nheads + count,
 					vhost_len, &in, vq_log, &log,
 					likely(mergeable) ? UIO_MAXIOV : 1);
 		/* On error, stop handling until the next kick. */
@@ -1222,8 +1257,11 @@ static void handle_rx(struct vhost_net *net)
 			goto out;
 		}
 		nvq->done_idx += headcount;
-		if (nvq->done_idx > VHOST_NET_BATCH)
-			vhost_net_signal_used(nvq);
+		count += in_order ? 1 : headcount;
+		if (nvq->done_idx > VHOST_NET_BATCH) {
+			vhost_net_signal_used(nvq, count);
+			count = 0;
+		}
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len,
 					vq->iov, in);
@@ -1235,7 +1273,7 @@ static void handle_rx(struct vhost_net *net)
 	else if (!sock_len)
 		vhost_net_enable_vq(net, vq);
 out:
-	vhost_net_signal_used(nvq);
+	vhost_net_signal_used(nvq, count);
 	mutex_unlock(&vq->mutex);
 }