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
  ...

4 files changed, 64 insertions, 24 deletions

diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 04b90c88d164..db31fc6f4f1f 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -199,7 +199,7 @@ int virtio_device_reset_done(struct virtio_device *dev);
 size_t virtio_max_dma_size(const struct virtio_device *vdev);
 
 #define virtio_device_for_each_vq(vdev, vq) \
-	list_for_each_entry(vq, &vdev->vqs, list)
+	list_for_each_entry(vq, &(vdev)->vqs, list)
 
 /**
  * struct virtio_driver - operations for a virtio I/O driver
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 36fb3edfa403..0c67543a45c8 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -47,31 +47,50 @@ static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb)
 	VIRTIO_VSOCK_SKB_CB(skb)->tap_delivered = false;
 }
 
-static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb)
+static inline void virtio_vsock_skb_put(struct sk_buff *skb, u32 len)
 {
-	u32 len;
+	DEBUG_NET_WARN_ON_ONCE(skb->len);
 
-	len = le32_to_cpu(virtio_vsock_hdr(skb)->len);
-
-	if (len > 0)
+	if (skb_is_nonlinear(skb))
+		skb->len = len;
+	else
 		skb_put(skb, len);
 }
 
-static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask)
+static inline struct sk_buff *
+__virtio_vsock_alloc_skb_with_frags(unsigned int header_len,
+				    unsigned int data_len,
+				    gfp_t mask)
 {
 	struct sk_buff *skb;
+	int err;
 
-	if (size < VIRTIO_VSOCK_SKB_HEADROOM)
-		return NULL;
-
-	skb = alloc_skb(size, mask);
+	skb = alloc_skb_with_frags(header_len, data_len,
+				   PAGE_ALLOC_COSTLY_ORDER, &err, mask);
 	if (!skb)
 		return NULL;
 
 	skb_reserve(skb, VIRTIO_VSOCK_SKB_HEADROOM);
+	skb->data_len = data_len;
 	return skb;
 }
 
+static inline struct sk_buff *
+virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask)
+{
+	return __virtio_vsock_alloc_skb_with_frags(size, 0, mask);
+}
+
+static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask)
+{
+	if (size <= SKB_WITH_OVERHEAD(PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		return virtio_vsock_alloc_linear_skb(size, mask);
+
+	size -= VIRTIO_VSOCK_SKB_HEADROOM;
+	return __virtio_vsock_alloc_skb_with_frags(VIRTIO_VSOCK_SKB_HEADROOM,
+						   size, mask);
+}
+
 static inline void
 virtio_vsock_skb_queue_head(struct sk_buff_head *list, struct sk_buff *skb)
 {
@@ -111,7 +130,12 @@ static inline size_t virtio_vsock_skb_len(struct sk_buff *skb)
 	return (size_t)(skb_end_pointer(skb) - skb->head);
 }
 
-#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE	(1024 * 4)
+/* Dimension the RX SKB so that the entire thing fits exactly into
+ * a single 4KiB page. This avoids wasting memory due to alloc_skb()
+ * rounding up to the next page order and also means that we
+ * don't leave higher-order pages sitting around in the RX queue.
+ */
+#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE	SKB_WITH_OVERHEAD(1024 * 4)
 #define VIRTIO_VSOCK_MAX_BUF_SIZE		0xFFFFFFFFUL
 #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE		(1024 * 64)
 
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
index c3a8117dabe8..49e7cbc9697a 100644
--- a/include/linux/vringh.h
+++ b/include/linux/vringh.h
@@ -175,9 +175,6 @@ int vringh_complete_multi_user(struct vringh *vrh,
 			       const struct vring_used_elem used[],
 			       unsigned num_used);
 
-/* Pretend we've never seen descriptor (for easy error handling). */
-void vringh_abandon_user(struct vringh *vrh, unsigned int num);
-
 /* Do we need to fire the eventfd to notify the other side? */
 int vringh_need_notify_user(struct vringh *vrh);
 
@@ -235,10 +232,6 @@ int vringh_getdesc_kern(struct vringh *vrh,
 			u16 *head,
 			gfp_t gfp);
 
-ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len);
-ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
-			     const void *src, size_t len);
-void vringh_abandon_kern(struct vringh *vrh, unsigned int num);
 int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len);
 
 bool vringh_notify_enable_kern(struct vringh *vrh);
@@ -319,13 +312,8 @@ ssize_t vringh_iov_push_iotlb(struct vringh *vrh,
 			      struct vringh_kiov *wiov,
 			      const void *src, size_t len);
 
-void vringh_abandon_iotlb(struct vringh *vrh, unsigned int num);
-
 int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len);
 
-bool vringh_notify_enable_iotlb(struct vringh *vrh);
-void vringh_notify_disable_iotlb(struct vringh *vrh);
-
 int vringh_need_notify_iotlb(struct vringh *vrh);
 
 #endif /* CONFIG_VHOST_IOTLB */
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index d6ad01fbb8d2..283348b64af9 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -242,4 +242,32 @@
 #define VHOST_SET_FEATURES_ARRAY _IOW(VHOST_VIRTIO, 0x83, \
 				       struct vhost_features_array)
 
+/* fork_owner values for vhost */
+#define VHOST_FORK_OWNER_KTHREAD 0
+#define VHOST_FORK_OWNER_TASK 1
+
+/**
+ * VHOST_SET_FORK_FROM_OWNER - Set the fork_owner flag for the vhost device,
+ * This ioctl must called before VHOST_SET_OWNER.
+ * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y
+ *
+ * @param fork_owner: An 8-bit value that determines the vhost thread mode
+ *
+ * When fork_owner is set to VHOST_FORK_OWNER_TASK(default value):
+ *   - Vhost will create vhost worker as tasks forked from the owner,
+ *     inheriting all of the owner's attributes.
+ *
+ * When fork_owner is set to VHOST_FORK_OWNER_KTHREAD:
+ *   - Vhost will create vhost workers as kernel threads.
+ */
+#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x83, __u8)
+
+/**
+ * VHOST_GET_FORK_OWNER - Get the current fork_owner flag for the vhost device.
+ * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y
+ *
+ * @return: An 8-bit value indicating the current thread mode.
+ */
+#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x84, __u8)
+
 #endif