On Tue, 1 Jul 2025 17:45:03 +0100
Will Deacon <will@xxxxxxxxxx> wrote:
> When allocating receive buffers for the vsock virtio RX virtqueue, an
> SKB is allocated with a 4140 data payload (the 44-byte packet header +
> VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE). Even when factoring in the SKB
> overhead, the resulting 8KiB allocation thanks to the rounding in
> kmalloc_reserve() is wasteful (~3700 unusable bytes) and results in a
> higher-order page allocation for the sake of a few hundred bytes of
> packet data.
>
> Limit the vsock virtio RX buffers to a page per SKB, resulting in much
> better memory utilisation and removing the need to allocate higher-order
> pages entirely.
>
> Signed-off-by: Will Deacon <will@xxxxxxxxxx>
> ---
> include/linux/virtio_vsock.h | 1 -
> net/vmw_vsock/virtio_transport.c | 7 ++++++-
> 2 files changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
> index eb6980aa19fd..1b5731186095 100644
> --- a/include/linux/virtio_vsock.h
> +++ b/include/linux/virtio_vsock.h
> @@ -109,7 +109,6 @@ 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)
> #define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL
> #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64)
>
> diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
> index 488e6ddc6ffa..3daba06ed499 100644
> --- a/net/vmw_vsock/virtio_transport.c
> +++ b/net/vmw_vsock/virtio_transport.c
> @@ -307,7 +307,12 @@ virtio_transport_cancel_pkt(struct vsock_sock *vsk)
>
> static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
> {
> - int total_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM;
> + /* Dimension the SKB so that the entire thing fits exactly into
> + * a single 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.
> + */
> + int total_len = SKB_WITH_OVERHEAD(PAGE_SIZE);
Should that be an explicit 4096?
Otherwise it is very wasteful of memory on systems with large pages.
David
> struct scatterlist pkt, *p;
> struct virtqueue *vq;
> struct sk_buff *skb;
