[xdp-hints] Re: [RFC bpf-next 05/23] ice: Introduce ice_xdp_buff

[Maciej Fijalkowski <maciej.fijalkowski@intel.com>]

On Thu, Aug 24, 2023 at 09:26:44PM +0200, Larysa Zaremba wrote:
> In order to use XDP hints via kfuncs we need to put
> RX descriptor and ring pointers just next to xdp_buff.
> Same as in hints implementations in other drivers, we achieve
> this through putting xdp_buff into a child structure.

Don't you mean a parent struct? xdp_buff will be 'child' of ice_xdp_buff
if i'm reading this right.

> 
> Currently, xdp_buff is stored in the ring structure,
> so replace it with union that includes child structure.
> This way enough memory is available while existing XDP code
> remains isolated from hints.
> 
> Minimum size of the new child structure (ice_xdp_buff) is exactly
> 64 bytes (single cache line). To place it at the start of a cache line,
> move 'next' field from CL1 to CL3, as it isn't used often. This still
> leaves 128 bits available in CL3 for packet context extensions.

I believe ice_xdp_buff will be beefed up in later patches, so what is the
point of moving 'next' ? We won't be able to keep ice_xdp_buff in a single
CL anyway.

> 
> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
> ---
>  drivers/net/ethernet/intel/ice/ice_txrx.c     |  7 +++--
>  drivers/net/ethernet/intel/ice/ice_txrx.h     | 26 ++++++++++++++++---
>  drivers/net/ethernet/intel/ice/ice_txrx_lib.h | 10 +++++++
>  3 files changed, 38 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
> index 40f2f6dabb81..4e6546d9cf85 100644
> --- a/drivers/net/ethernet/intel/ice/ice_txrx.c
> +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
> @@ -557,13 +557,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
>   * @xdp_prog: XDP program to run
>   * @xdp_ring: ring to be used for XDP_TX action
>   * @rx_buf: Rx buffer to store the XDP action
> + * @eop_desc: Last descriptor in packet to read metadata from
>   *
>   * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
>   */
>  static void
>  ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
>  	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
> -	    struct ice_rx_buf *rx_buf)
> +	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
>  {
>  	unsigned int ret = ICE_XDP_PASS;
>  	u32 act;
> @@ -571,6 +572,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
>  	if (!xdp_prog)
>  		goto exit;
>  
> +	ice_xdp_meta_set_desc(xdp, eop_desc);

I am currently not sure if for multi-buffer case HW repeats all the
necessary info within each descriptor for every frag? IOW shouldn't you be
using the ice_rx_ring::first_desc?

Would be good to test hints for mbuf case for sure.

> +
>  	act = bpf_prog_run_xdp(xdp_prog, xdp);
>  	switch (act) {
>  	case XDP_PASS:
> @@ -1240,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
>  		if (ice_is_non_eop(rx_ring, rx_desc))
>  			continue;
>  
> -		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
> +		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
>  		if (rx_buf->act == ICE_XDP_PASS)
>  			goto construct_skb;
>  		total_rx_bytes += xdp_get_buff_len(xdp);
> diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
> index 166413fc33f4..d0ab2c4c0c91 100644
> --- a/drivers/net/ethernet/intel/ice/ice_txrx.h
> +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
> @@ -257,6 +257,18 @@ enum ice_rx_dtype {
>  	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
>  };
>  
> +struct ice_pkt_ctx {
> +	const union ice_32b_rx_flex_desc *eop_desc;
> +};
> +
> +struct ice_xdp_buff {
> +	struct xdp_buff xdp_buff;
> +	struct ice_pkt_ctx pkt_ctx;
> +};
> +
> +/* Required for compatibility with xdp_buffs from xsk_pool */
> +static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
> +
>  /* indices into GLINT_ITR registers */
>  #define ICE_RX_ITR	ICE_IDX_ITR0
>  #define ICE_TX_ITR	ICE_IDX_ITR1
> @@ -298,7 +310,6 @@ enum ice_dynamic_itr {
>  /* descriptor ring, associated with a VSI */
>  struct ice_rx_ring {
>  	/* CL1 - 1st cacheline starts here */
> -	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
>  	void *desc;			/* Descriptor ring memory */
>  	struct device *dev;		/* Used for DMA mapping */
>  	struct net_device *netdev;	/* netdev ring maps to */
> @@ -310,12 +321,19 @@ struct ice_rx_ring {
>  	u16 count;			/* Number of descriptors */
>  	u16 reg_idx;			/* HW register index of the ring */
>  	u16 next_to_alloc;
> -	/* CL2 - 2nd cacheline starts here */
> +
>  	union {
>  		struct ice_rx_buf *rx_buf;
>  		struct xdp_buff **xdp_buf;
>  	};
> -	struct xdp_buff xdp;
> +	/* CL2 - 2nd cacheline starts here */
> +	union {
> +		struct ice_xdp_buff xdp_ext;
> +		struct {
> +			struct xdp_buff xdp;
> +			struct ice_pkt_ctx pkt_ctx;
> +		};
> +	};
>  	/* CL3 - 3rd cacheline starts here */
>  	struct bpf_prog *xdp_prog;
>  	u16 rx_offset;
> @@ -325,6 +343,8 @@ struct ice_rx_ring {
>  	u16 next_to_clean;
>  	u16 first_desc;
>  
> +	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
> +
>  	/* stats structs */
>  	struct ice_ring_stats *ring_stats;
>  
> diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> index e1d49e1235b3..145883eec129 100644
> --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> @@ -151,4 +151,14 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
>  		       struct sk_buff *skb);
>  void
>  ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
> +
> +static inline void
> +ice_xdp_meta_set_desc(struct xdp_buff *xdp,
> +		      union ice_32b_rx_flex_desc *eop_desc)
> +{
> +	struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff,
> +						    xdp_buff);
> +
> +	xdp_ext->pkt_ctx.eop_desc = eop_desc;
> +}
>  #endif /* !_ICE_TXRX_LIB_H_ */
> -- 
> 2.41.0
>