[Intel-wired-lan] [PATCH bpf-next v4 09/11] samples/bpf: add buffer recycling for unaligned chunks to xdpsock

[Jonathan Lemon]

On 30 Jul 2019, at 1:53, Kevin Laatz wrote:

> This patch adds buffer recycling support for unaligned buffers. Since 
> we
> don't mask the addr to 2k at umem_reg in unaligned mode, we need to 
> make
> sure we give back the correct (original) addr to the fill queue. We 
> achieve
> this using the new descriptor format and associated masks. The new 
> format
> uses the upper 16-bits for the offset and the lower 48-bits for the 
> addr.
> Since we have a field for the offset, we no longer need to modify the
> actual address. As such, all we have to do to get back the original 
> address
> is mask for the lower 48 bits (i.e. strip the offset and we get the 
> address
> on it's own).
>
> Signed-off-by: Kevin Laatz <kevin.laatz at intel.com>
> Signed-off-by: Bruce Richardson <bruce.richardson at intel.com>
>
> ---
> v2:
>   - Removed unused defines
>   - Fix buffer recycling for unaligned case
>   - Remove --buf-size (--frame-size merged before this)
>   - Modifications to use the new descriptor format for buffer 
> recycling
> ---
>  samples/bpf/xdpsock_user.c | 24 +++++++++++++++---------
>  1 file changed, 15 insertions(+), 9 deletions(-)
>
> diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
> index 756b00eb1afe..62b2059cd0e3 100644
> --- a/samples/bpf/xdpsock_user.c
> +++ b/samples/bpf/xdpsock_user.c
> @@ -475,6 +475,7 @@ static void kick_tx(struct xsk_socket_info *xsk)
>
>  static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk)
>  {
> +	struct xsk_umem_info *umem = xsk->umem;
>  	u32 idx_cq = 0, idx_fq = 0;
>  	unsigned int rcvd;
>  	size_t ndescs;
> @@ -487,22 +488,21 @@ static inline void complete_tx_l2fwd(struct 
> xsk_socket_info *xsk)
>  		xsk->outstanding_tx;
>
>  	/* re-add completed Tx buffers */
> -	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, ndescs, &idx_cq);
> +	rcvd = xsk_ring_cons__peek(&umem->cq, ndescs, &idx_cq);
>  	if (rcvd > 0) {
>  		unsigned int i;
>  		int ret;
>
> -		ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
> +		ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
>  		while (ret != rcvd) {
>  			if (ret < 0)
>  				exit_with_error(-ret);
> -			ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd,
> -						     &idx_fq);
> +			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
>  		}
> +
>  		for (i = 0; i < rcvd; i++)
> -			*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) =
> -				*xsk_ring_cons__comp_addr(&xsk->umem->cq,
> -							  idx_cq++);
> +			*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) =
> +				*xsk_ring_cons__comp_addr(&umem->cq, idx_cq++);
>
>  		xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
>  		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
> @@ -549,7 +549,11 @@ static void rx_drop(struct xsk_socket_info *xsk)
>  	for (i = 0; i < rcvd; i++) {
>  		u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
>  		u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len;
> -		char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr);
> +		u64 offset = addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
> +
> +		addr &= XSK_UNALIGNED_BUF_ADDR_MASK;
> +		char *pkt = xsk_umem__get_data(xsk->umem->buffer,
> +				addr + offset);

The mask constants should not be part of the api - this should be
hidden behind an accessor.

Something like:
   u64 addr = xsk_umem__get_addr(xsk->umem, handle);




>  		hex_dump(pkt, len, addr);
>  		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = addr;
> @@ -655,7 +659,9 @@ static void l2fwd(struct xsk_socket_info *xsk)
>  							  idx_rx)->addr;
>  			u32 len = xsk_ring_cons__rx_desc(&xsk->rx,
>  							 idx_rx++)->len;
> -			char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr);
> +			u64 offset = addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
> +			char *pkt = xsk_umem__get_data(xsk->umem->buffer,
> +				(addr & XSK_UNALIGNED_BUF_ADDR_MASK) + offset);
>
>  			swap_mac_addresses(pkt);
>
> -- 
> 2.17.1