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

Pull virtio updates from Michael Tsirkin:

 - new virtio CAN driver

 - support for LoongArch architecture in fw_cfg

 - support for firmware notifications in vdpa/octeon_ep

 - support for VFs in virtio core

 - fixes, cleanups all over the place, notably:

    - vhost: fix vhost_get_avail_idx for a non empty ring
      fixing an significant old perf regression

    - READ_ONCE() annotations mean virtio ring is now
      free of KCSAN warnings

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (37 commits)
  can: virtio: Fix comment in UAPI header
  can: virtio: Add virtio CAN driver
  virtio: add num_vf callback to virtio_bus
  fw_cfg: Add support for LoongArch architecture
  vdpa/octeon_ep: fix IRQ-to-ring mapping in interrupt handler
  vdpa/octeon_ep: Add vDPA device event handling for firmware notifications
  vdpa/octeon_ep: Use 4 bytes for mailbox signature
  vdpa/octeon_ep: Fix PF->VF mailbox data address calculation
  vhost_task_create: kill unnecessary .exit_signal initialization
  vhost: remove unnecessary module_init/exit functions
  vdpa/mlx5: Use kvzalloc_flex() for MTT command memory
  vdpa_sim_net: switch to dynamic root device
  vdpa_sim_blk: switch to dynamic root device
  virtio-mem: Destroy mutex before freeing virtio_mem
  virtio-balloon: Destroy mutex before freeing virtio_balloon
  tools/virtio: fix build for kmalloc_obj API and missing stubs
  virtio_ring: Add READ_ONCE annotations for device-writable fields
  vduse: fix compat handling for VDUSE_IOTLB_GET_FD/VDUSE_VQ_GET_INFO
  tools/virtio: check mmap return value in vringh_test
  vhost/net: complete zerocopy ubufs only once
  ...

4 files changed, 56 insertions, 27 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index db341c922673..77b59f49bddb 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -399,13 +399,20 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net,
 static void vhost_zerocopy_complete(struct sk_buff *skb,
 				    struct ubuf_info *ubuf_base, bool success)
 {
-	struct ubuf_info_msgzc *ubuf = uarg_to_msgzc(ubuf_base);
-	struct vhost_net_ubuf_ref *ubufs = ubuf->ctx;
-	struct vhost_virtqueue *vq = ubufs->vq;
+	struct ubuf_info_msgzc *ubuf;
+	struct vhost_net_ubuf_ref *ubufs;
+	struct vhost_virtqueue *vq;
 	int cnt;
 
-	rcu_read_lock_bh();
+	/* Only the final cloned skb reference completes the vhost descriptor. */
+	if (!refcount_dec_and_test(&ubuf_base->refcnt))
+		return;
+
+	ubuf = uarg_to_msgzc(ubuf_base);
+	ubufs = ubuf->ctx;
+	vq = ubufs->vq;
 
+	rcu_read_lock_bh();
 	/* set len to mark this desc buffers done DMA */
 	vq->heads[ubuf->desc].len = success ?
 		VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 692564b1bcbb..ac55275fa0d0 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -1482,16 +1482,32 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep)
 }
 
 #ifdef CONFIG_MMU
-static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf)
+static int
+vhost_vdpa_get_vq_notification(struct vhost_vdpa *v, unsigned long index,
+			       struct vdpa_notification_area *notify)
 {
-	struct vhost_vdpa *v = vmf->vma->vm_file->private_data;
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+
+	if (index > 65535 || index >= v->nvqs)
+		return -EINVAL;
+
+	index = array_index_nospec(index, v->nvqs);
+
+	*notify = ops->get_vq_notification(vdpa, index);
+
+	return 0;
+}
+
+static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf)
+{
+	struct vhost_vdpa *v = vmf->vma->vm_file->private_data;
 	struct vdpa_notification_area notify;
 	struct vm_area_struct *vma = vmf->vma;
-	u16 index = vma->vm_pgoff;
+	unsigned long index = vma->vm_pgoff;
 
-	notify = ops->get_vq_notification(vdpa, index);
+	if (vhost_vdpa_get_vq_notification(v, index, &notify))
+		return VM_FAULT_SIGBUS;
 
 	return vmf_insert_pfn(vma, vmf->address & PAGE_MASK, PFN_DOWN(notify.addr));
 }
@@ -1514,8 +1530,6 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EINVAL;
 	if (vma->vm_flags & VM_READ)
 		return -EINVAL;
-	if (index > 65535)
-		return -EINVAL;
 	if (!ops->get_vq_notification)
 		return -ENOTSUPP;
 
@@ -1523,7 +1537,8 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma)
 	 * support the doorbell which sits on the page boundary and
 	 * does not share the page with other registers.
 	 */
-	notify = ops->get_vq_notification(vdpa, index);
+	if (vhost_vdpa_get_vq_notification(v, index, &notify))
+		return -EINVAL;
 	if (notify.addr & (PAGE_SIZE - 1))
 		return -EINVAL;
 	if (vma->vm_end - vma->vm_start != notify.size)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 2f2c45d20883..4c525b3e16ea 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1522,6 +1522,7 @@ static void vhost_dev_unlock_vqs(struct vhost_dev *d)
 static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq)
 {
 	__virtio16 idx;
+	u16 avail_idx;
 	int r;
 
 	r = vhost_get_avail(vq, idx, &vq->avail->idx);
@@ -1532,17 +1533,19 @@ static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq)
 	}
 
 	/* Check it isn't doing very strange thing with available indexes */
-	vq->avail_idx = vhost16_to_cpu(vq, idx);
-	if (unlikely((u16)(vq->avail_idx - vq->last_avail_idx) > vq->num)) {
+	avail_idx = vhost16_to_cpu(vq, idx);
+	if (unlikely((u16)(avail_idx - vq->last_avail_idx) > vq->num)) {
 		vq_err(vq, "Invalid available index change from %u to %u",
-		       vq->last_avail_idx, vq->avail_idx);
+		       vq->last_avail_idx, avail_idx);
 		return -EINVAL;
 	}
 
 	/* We're done if there is nothing new */
-	if (vq->avail_idx == vq->last_avail_idx)
+	if (avail_idx == vq->avail_idx)
 		return 0;
 
+	vq->avail_idx = avail_idx;
+
 	/*
 	 * We updated vq->avail_idx so we need a memory barrier between
 	 * the index read above and the caller reading avail ring entries.
@@ -3321,18 +3324,6 @@ void vhost_set_backend_features(struct vhost_dev *dev, u64 features)
 }
 EXPORT_SYMBOL_GPL(vhost_set_backend_features);
 
-static int __init vhost_init(void)
-{
-	return 0;
-}
-
-static void __exit vhost_exit(void)
-{
-}
-
-module_init(vhost_init);
-module_exit(vhost_exit);
-
 MODULE_VERSION("0.0.1");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Michael S. Tsirkin");
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 1d8ec6bed53e..9aaab6bb8061 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -302,6 +302,22 @@ vhost_transport_send_pkt(struct sk_buff *skb, struct net *net)
 		return -ENODEV;
 	}
 
+	/* Fast-fail if the guest hasn't enabled the RX vq yet. Queuing the packet
+	 * and making the caller wait is pointless: even if the guest manages to init
+	 * within the timeout, it'll immediately reply with RST, because there's no
+	 * listener on the port yet.
+	 *
+	 * vhost_vq_get_backend() without vq->mutex is acceptable here: locking
+	 * the mutex would be too expensive in this hot path, and we already have
+	 * all the outcomes covered: if the backend becomes NULL right after the check,
+	 * vhost_transport_do_send_pkt() will check it under the mutex anyway.
+	 */
+	if (unlikely(!data_race(vhost_vq_get_backend(&vsock->vqs[VSOCK_VQ_RX])))) {
+		rcu_read_unlock();
+		kfree_skb(skb);
+		return -EHOSTUNREACH;
+	}
+
 	if (virtio_vsock_skb_reply(skb))
 		atomic_inc(&vsock->queued_replies);