vhost/vsock: Allocate nonlinear SKBs for handling large receive buffers

When receiving a packet from a guest, vhost_vsock_handle_tx_kick()
calls vhost_vsock_alloc_linear_skb() to allocate and fill an SKB with
the receive data. Unfortunately, these are always linear allocations and
can therefore result in significant pressure on kmalloc() considering
that the maximum packet size (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE +
VIRTIO_VSOCK_SKB_HEADROOM) is a little over 64KiB, resulting in a 128KiB
allocation for each packet.

Rework the vsock SKB allocation so that, for sizes with page order
greater than PAGE_ALLOC_COSTLY_ORDER, a nonlinear SKB is allocated
instead with the packet header in the SKB and the receive data in the
fragments. Finally, add a debug warning if virtio_vsock_skb_rx_put() is
ever called on an SKB with a non-zero length, as this would be
destructive for the nonlinear case.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Will Deacon <will@kernel.org>
Message-Id: <20250717090116.11987-8-will@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 24b7547b05a6c29d26146f026d1ef099931d52b8..0679a706ebc072c91858e484bb908df25a00c970 100644 (file)
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -349,7 +349,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
                return NULL;
 
        /* len contains both payload and hdr */
-       skb = virtio_vsock_alloc_linear_skb(len, GFP_KERNEL);
+       skb = virtio_vsock_alloc_skb(len, GFP_KERNEL);
        if (!skb)
                return NULL;
 
@@ -378,10 +378,8 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
 
        virtio_vsock_skb_rx_put(skb, payload_len);
 
-       nbytes = copy_from_iter(skb->data, payload_len, &iov_iter);
-       if (nbytes != payload_len) {
-               vq_err(vq, "Expected %zu byte payload, got %zu bytes\n",
-                      payload_len, nbytes);
+       if (skb_copy_datagram_from_iter(skb, 0, &iov_iter, payload_len)) {
+               vq_err(vq, "Failed to copy %zu byte payload\n", payload_len);
                kfree_skb(skb);
                return NULL;
        }

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 36dd0cd553688861c1ab366d97b3776ccf4b4883..fa5934ea9c81ed766b4a67e91c1cc0db36c66996 100644 (file)
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -49,22 +49,48 @@ static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb)
 
 static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len)
 {
-       skb_put(skb, len);
+       DEBUG_NET_WARN_ON_ONCE(skb->len);
+
+       if (skb_is_nonlinear(skb))
+               skb->len = len;
+       else
+               skb_put(skb, len);
 }
 
 static inline struct sk_buff *
-virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask)
+__virtio_vsock_alloc_skb_with_frags(unsigned int header_len,
+                                   unsigned int data_len,
+                                   gfp_t mask)
 {
        struct sk_buff *skb;
+       int err;
 
-       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)
 {