From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 13 Apr 2022 17:30:06 +0200
Subject: ice, xsk: Terminate Rx side of NAPI when XSK Rx queue gets full
Patch-mainline: v5.19-rc1
Git-commit: 50ae066480738e0d3ce72a90c8c0f4d9de6092e0
References: jsc#PED-376

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 ICE_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/20220413153015.453864-6-maciej.fijalkowski@intel.com
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/intel/ice/ice_txrx.h |    1 +
 drivers/net/ethernet/intel/ice/ice_xsk.c  |   29 +++++++++++++++++++----------
 2 files changed, 20 insertions(+), 10 deletions(-)

--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -133,6 +133,7 @@ static inline int ice_skb_pad(void)
 #define ICE_XDP_CONSUMED	BIT(0)
 #define ICE_XDP_TX		BIT(1)
 #define ICE_XDP_REDIR		BIT(2)
+#define ICE_XDP_EXIT		BIT(3)
 
 #define ICE_RX_DMA_ATTR \
 	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -545,9 +545,13 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ri
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		if (err)
-			goto out_failure;
-		return ICE_XDP_REDIR;
+		if (!err)
+			return ICE_XDP_REDIR;
+		if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+			result = ICE_XDP_EXIT;
+		else
+			result = ICE_XDP_CONSUMED;
+		goto out_failure;
 	}
 
 	switch (act) {
@@ -558,15 +562,16 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ri
 		if (result == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
+	case XDP_DROP:
+		result = ICE_XDP_CONSUMED;
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_ABORTED:
+		result = ICE_XDP_CONSUMED;
 out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
-		fallthrough;
-	case XDP_DROP:
-		result = ICE_XDP_CONSUMED;
 		break;
 	}
 
@@ -634,12 +639,16 @@ int ice_clean_rx_irq_zc(struct ice_rx_ri
 		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
 
 		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring);
-		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)))
+		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
 			xdp_xmit |= xdp_res;
-		else if (xdp_res == ICE_XDP_CONSUMED)
+		} else if (xdp_res == ICE_XDP_EXIT) {
+			failure = true;
+			break;
+		} else if (xdp_res == ICE_XDP_CONSUMED) {
 			xsk_buff_free(xdp);
-		else
+		} else if (xdp_res == ICE_XDP_PASS) {
 			goto construct_skb;
+		}
 
 		total_rx_bytes += size;
 		total_rx_packets++;
@@ -674,7 +683,7 @@ construct_skb:
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 	}
 
-	failure = !ice_alloc_rx_bufs_zc(rx_ring, ICE_DESC_UNUSED(rx_ring));
+	failure |= !ice_alloc_rx_bufs_zc(rx_ring, ICE_DESC_UNUSED(rx_ring));
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);