ice: propagate xdp_ring onto rx_ring

With rings being split, it is now convenient to introduce a pointer to
XDP ring within the Rx ring. For XDP_TX workloads this means that
xdp_rings array access will be skipped, which was executed per each
processed frame.

Also, read the XDP prog once per NAPI and if prog is present, set up the
local xdp_ring pointer. Reading prog a single time was discussed in [1]
with some concern raised by Toke around dispatcher handling and having
the need for going through the RCU grace period in the ndo_bpf driver
callback, but ice currently is torning down NAPI instances regardless of
the prog presence on VSI.

Although the pointer to XDP ring introduced to Rx ring makes things a
lot slimmer/simpler, I still feel that single prog read per NAPI
lifetime is beneficial.

Further patch that will introduce the fallback path will also get a
profit from that as xdp_ring pointer will be set during the XDP rings
setup.

[1]: https://lore.kernel.org/bpf/87k0oseo6e.fsf@toke.dk/

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

1 files changed, 14 insertions, 11 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 08ae06d6b982..d9dfcfc2c6f9 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -452,22 +452,18 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr)
  * ice_run_xdp_zc - Executes an XDP program in zero-copy path
  * @rx_ring: Rx ring
  * @xdp: xdp_buff used as input to the XDP program
+ * @xdp_prog: XDP program to run
+ * @xdp_ring: ring to be used for XDP_TX action
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static int
-ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
+ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
 {
 	int err, result = ICE_XDP_PASS;
-	struct ice_tx_ring *xdp_ring;
-	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	/* ZC patch is enabled only when XDP program is set,
-	 * so here it can not be NULL
-	 */
-	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
-
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
 	if (likely(act == XDP_REDIRECT)) {
@@ -481,7 +477,6 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index];
 		result = ice_xmit_xdp_buff(xdp, xdp_ring);
 		if (result == ICE_XDP_CONSUMED)
 			goto out_failure;
@@ -512,9 +507,17 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
+	struct ice_tx_ring *xdp_ring;
 	unsigned int xdp_xmit = 0;
+	struct bpf_prog *xdp_prog;
 	bool failure = false;
 
+	/* ZC patch is enabled only when XDP program is set,
+	 * so here it can not be NULL
+	 */
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+	xdp_ring = rx_ring->xdp_ring;
+
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		unsigned int size, xdp_res = 0;
@@ -545,7 +548,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		xsk_buff_set_size(*xdp, size);
 		xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool);
 
-		xdp_res = ice_run_xdp_zc(rx_ring, *xdp);
+		xdp_res = ice_run_xdp_zc(rx_ring, *xdp, xdp_prog, xdp_ring);
 		if (xdp_res) {
 			if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))
 				xdp_xmit |= xdp_res;
@@ -593,7 +596,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 	if (cleaned_count >= ICE_RX_BUF_WRITE)
 		failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count);
 
-	ice_finalize_xdp_rx(rx_ring, xdp_xmit);
+	ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
 
 	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {