From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:04 +0200
Subject: ice: Use the xsk batched rx allocation interface
Patch-mainline: v5.16-rc1
Git-commit: db804cfc21e969a5a4ada4b8142f711def5ed339
References: jsc#SLE-18375

Use the new xsk batched rx allocation interface for the zero-copy data
path. As the array of struct xdp_buff pointers kept by the driver is
really a ring that wraps, the allocation routine is modified to detect
a wrap and in that case call the allocation function twice. The
allocation function cannot deal with wrapped rings, only arrays. As we
now know exactly how many buffers we get and that there is no
wrapping, the allocation function can be simplified even more as all
if-statements in the allocation loop can be removed, improving
performance.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-5-magnus.karlsson@gmail.com
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/intel/ice/ice_xsk.c |   44 +++++++++++++------------------
 1 file changed, 19 insertions(+), 25 deletions(-)

--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -365,44 +365,38 @@ bool ice_alloc_rx_bufs_zc(struct ice_rin
 	union ice_32b_rx_flex_desc *rx_desc;
 	u16 ntu = rx_ring->next_to_use;
 	struct xdp_buff **xdp;
-	bool ok = true;
+	u32 nb_buffs, i;
 	dma_addr_t dma;
 
-	if (!count)
-		return true;
-
 	rx_desc = ICE_RX_DESC(rx_ring, ntu);
 	xdp = &rx_ring->xdp_buf[ntu];
 
-	do {
-		*xdp = xsk_buff_alloc(rx_ring->xsk_pool);
-		if (!xdp) {
-			ok = false;
-			break;
-		}
+	nb_buffs = min_t(u16, count, rx_ring->count - ntu);
+	nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs);
+	if (!nb_buffs)
+		return false;
 
+	i = nb_buffs;
+	while (i--) {
 		dma = xsk_buff_xdp_get_dma(*xdp);
 		rx_desc->read.pkt_addr = cpu_to_le64(dma);
-		rx_desc->wb.status_error0 = 0;
 
 		rx_desc++;
 		xdp++;
-		ntu++;
+	}
 
-		if (unlikely(ntu == rx_ring->count)) {
-			rx_desc = ICE_RX_DESC(rx_ring, 0);
-			xdp = rx_ring->xdp_buf;
-			ntu = 0;
-		}
-	} while (--count);
-
-	if (rx_ring->next_to_use != ntu) {
-		/* clear the status bits for the next_to_use descriptor */
-		rx_desc->wb.status_error0 = 0;
-		ice_release_rx_desc(rx_ring, ntu);
+	ntu += nb_buffs;
+	if (ntu == rx_ring->count) {
+		rx_desc = ICE_RX_DESC(rx_ring, 0);
+		xdp = rx_ring->xdp_buf;
+		ntu = 0;
 	}
 
-	return ok;
+	/* clear the status bits for the next_to_use descriptor */
+	rx_desc->wb.status_error0 = 0;
+	ice_release_rx_desc(rx_ring, ntu);
+
+	return count == nb_buffs ? true : false;
 }
 
 /**
@@ -545,7 +539,7 @@ int ice_clean_rx_irq_zc(struct ice_ring
 			break;
 
 		xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean];
-		(*xdp)->data_end = (*xdp)->data + size;
+		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);