ixgbe, xsk: Terminate Rx side of NAPI when XSK Rx queue gets full

When XSK pool uses need_wakeup feature, correlate -ENOBUFS that was
returned from xdp_do_redirect() with a XSK Rx queue being full. In such
case, terminate the Rx processing that is being done on the current HW
Rx ring and let the user space consume descriptors from XSK Rx queue so
that there is room that driver can use later on.

Introduce new internal return code IXGBE_XDP_EXIT that will indicate case
described above.

Note that it does not affect Tx processing that is bound to the same
NAPI context, nor the other Rx rings.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220413153015.453864-8-maciej.fijalkowski@intel.com

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
index bba3fea..f1f69ce 100644 (file)
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -8,6 +8,7 @@
 #define IXGBE_XDP_CONSUMED     BIT(0)
 #define IXGBE_XDP_TX           BIT(1)
 #define IXGBE_XDP_REDIR                BIT(2)
+#define IXGBE_XDP_EXIT         BIT(3)
 
 #define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \
                       IXGBE_TXD_CMD_RS)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 85497bf..bdd70b8 100644 (file)
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -109,9 +109,13 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 
        if (likely(act == XDP_REDIRECT)) {
                err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-               if (err)
-                       goto out_failure;
-               return IXGBE_XDP_REDIR;
+               if (!err)
+                       return IXGBE_XDP_REDIR;
+               if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+                       result = IXGBE_XDP_EXIT;
+               else
+                       result = IXGBE_XDP_CONSUMED;
+               goto out_failure;
        }
 
        switch (act) {
@@ -130,16 +134,17 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
                if (result == IXGBE_XDP_CONSUMED)
                        goto out_failure;
                break;
+       case XDP_DROP:
+               result = IXGBE_XDP_CONSUMED;
+               break;
        default:
                bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
                fallthrough;
        case XDP_ABORTED:
+               result = IXGBE_XDP_CONSUMED;
 out_failure:
                trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
                fallthrough; /* handle aborts by dropping packet */
-       case XDP_DROP:
-               result = IXGBE_XDP_CONSUMED;
-               break;
        }
        return result;
 }
@@ -303,12 +308,16 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
                xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool);
                xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp);
 
-               if (likely(xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)))
+               if (likely(xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR))) {
                        xdp_xmit |= xdp_res;
-               else if (xdp_res == IXGBE_XDP_CONSUMED)
+               } else if (xdp_res == IXGBE_XDP_EXIT) {
+                       failure = true;
+                       break;
+               } else if (xdp_res == IXGBE_XDP_CONSUMED) {
                        xsk_buff_free(bi->xdp);
-               else
+               } else if (xdp_res == IXGBE_XDP_PASS) {
                        goto construct_skb;
+               }
 
                bi->xdp = NULL;
                total_rx_packets++;