1 files changed, 162 insertions, 59 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index a7fe2b4ce655..2a3f0834e139 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -546,19 +546,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 }
 
 /**
- * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring
- * @rx_ring: Rx ring
- */
-static void ice_bump_ntc(struct ice_rx_ring *rx_ring)
-{
-	int ntc = rx_ring->next_to_clean + 1;
-
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-	prefetch(ICE_RX_DESC(rx_ring, ntc));
-}
-
-/**
  * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
  * @rx_ring: Rx ring
  * @xdp: Pointer to XDP buffer
@@ -572,8 +559,14 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
 	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
+	struct skb_shared_info *sinfo = NULL;
 	struct sk_buff *skb;
+	u32 nr_frags = 0;
 
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+	}
 	net_prefetch(xdp->data_meta);
 
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
@@ -589,6 +582,29 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 		__skb_pull(skb, metasize);
 	}
 
+	if (likely(!xdp_buff_has_frags(xdp)))
+		goto out;
+
+	for (int i = 0; i < nr_frags; i++) {
+		struct skb_shared_info *skinfo = skb_shinfo(skb);
+		skb_frag_t *frag = &sinfo->frags[i];
+		struct page *page;
+		void *addr;
+
+		page = dev_alloc_page();
+		if (!page) {
+			dev_kfree_skb(skb);
+			return NULL;
+		}
+		addr = page_to_virt(page);
+
+		memcpy(addr, skb_frag_page(frag), skb_frag_size(frag));
+
+		__skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++,
+					   addr, 0, skb_frag_size(frag));
+	}
+
+out:
 	xsk_buff_free(xdp);
 	return skb;
 }
@@ -597,7 +613,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
  */
-static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 {
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
@@ -619,7 +635,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 	}
 
 	if (!completed_frames)
-		return;
+		return 0;
 
 	if (likely(!xdp_ring->xdp_tx_active)) {
 		xsk_frames = completed_frames;
@@ -649,6 +665,8 @@ skip:
 		xdp_ring->next_to_clean -= cnt;
 	if (xsk_frames)
 		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+
+	return completed_frames;
 }
 
 /**
@@ -666,37 +684,72 @@ skip:
 static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 			      struct ice_tx_ring *xdp_ring)
 {
+	struct skb_shared_info *sinfo = NULL;
 	u32 size = xdp->data_end - xdp->data;
 	u32 ntu = xdp_ring->next_to_use;
 	struct ice_tx_desc *tx_desc;
 	struct ice_tx_buf *tx_buf;
-	dma_addr_t dma;
-
-	if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) {
-		ice_clean_xdp_irq_zc(xdp_ring);
-		if (!ICE_DESC_UNUSED(xdp_ring)) {
-			xdp_ring->ring_stats->tx_stats.tx_busy++;
-			return ICE_XDP_CONSUMED;
-		}
+	struct xdp_buff *head;
+	u32 nr_frags = 0;
+	u32 free_space;
+	u32 frag = 0;
+
+	free_space = ICE_DESC_UNUSED(xdp_ring);
+	if (free_space < ICE_RING_QUARTER(xdp_ring))
+		free_space += ice_clean_xdp_irq_zc(xdp_ring);
+
+	if (unlikely(!free_space))
+		goto busy;
+
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+		if (free_space < nr_frags + 1)
+			goto busy;
 	}
 
-	dma = xsk_buff_xdp_get_dma(xdp);
-	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
-
-	tx_buf = &xdp_ring->tx_buf[ntu];
-	tx_buf->xdp = xdp;
-	tx_buf->type = ICE_TX_BUF_XSK_TX;
 	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
-	tx_desc->buf_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
-						      0, size, 0);
-	xdp_ring->xdp_tx_active++;
+	tx_buf = &xdp_ring->tx_buf[ntu];
+	head = xdp;
+
+	for (;;) {
+		dma_addr_t dma;
+
+		dma = xsk_buff_xdp_get_dma(xdp);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+
+		tx_buf->xdp = xdp;
+		tx_buf->type = ICE_TX_BUF_XSK_TX;
+		tx_desc->buf_addr = cpu_to_le64(dma);
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0);
+		/* account for each xdp_buff from xsk_buff_pool */
+		xdp_ring->xdp_tx_active++;
+
+		if (++ntu == xdp_ring->count)
+			ntu = 0;
+
+		if (frag == nr_frags)
+			break;
+
+		tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+		tx_buf = &xdp_ring->tx_buf[ntu];
+
+		xdp = xsk_buff_get_frag(head);
+		size = skb_frag_size(&sinfo->frags[frag]);
+		frag++;
+	}
 
-	if (++ntu == xdp_ring->count)
-		ntu = 0;
 	xdp_ring->next_to_use = ntu;
+	/* update last descriptor from a frame with EOP */
+	tx_desc->cmd_type_offset_bsz |=
+		cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S);
 
 	return ICE_XDP_TX;
+
+busy:
+	xdp_ring->ring_stats->tx_stats.tx_busy++;
+
+	return ICE_XDP_CONSUMED;
 }
 
 /**
@@ -752,6 +805,34 @@ out_failure:
 	return result;
 }
 
+static int
+ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
+		 struct xdp_buff *xdp, const unsigned int size)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first);
+
+	if (!size)
+		return 0;
+
+	if (!xdp_buff_has_frags(first)) {
+		sinfo->nr_frags = 0;
+		sinfo->xdp_frags_size = 0;
+		xdp_buff_set_frags_flag(first);
+	}
+
+	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
+		xsk_buff_free(first);
+		return -ENOMEM;
+	}
+
+	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++,
+				   virt_to_page(xdp->data_hard_start), 0, size);
+	sinfo->xdp_frags_size += size;
+	xsk_buff_add_frag(xdp);
+
+	return 0;
+}
+
 /**
  * ice_clean_rx_irq_zc - consumes packets from the hardware ring
  * @rx_ring: AF_XDP Rx ring
@@ -762,9 +843,14 @@ out_failure:
 int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+	struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
+	u32 ntc = rx_ring->next_to_clean;
+	u32 ntu = rx_ring->next_to_use;
+	struct xdp_buff *first = NULL;
 	struct ice_tx_ring *xdp_ring;
 	unsigned int xdp_xmit = 0;
 	struct bpf_prog *xdp_prog;
+	u32 cnt = rx_ring->count;
 	bool failure = false;
 	int entries_to_alloc;
 
@@ -774,6 +860,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	xdp_ring = rx_ring->xdp_ring;
 
+	if (ntc != rx_ring->first_desc)
+		first = *ice_xdp_buf(rx_ring, rx_ring->first_desc);
+
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		unsigned int size, xdp_res = 0;
@@ -783,7 +872,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		u16 vlan_tag = 0;
 		u16 rx_ptype;
 
-		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
+		rx_desc = ICE_RX_DESC(rx_ring, ntc);
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
 		if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits))
@@ -795,51 +884,61 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		if (unlikely(rx_ring->next_to_clean == rx_ring->next_to_use))
+		if (unlikely(ntc == ntu))
 			break;
 
-		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
+		xdp = *ice_xdp_buf(rx_ring, ntc);
 
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 				   ICE_RX_FLX_DESC_PKT_LEN_M;
-		if (!size) {
-			xdp->data = NULL;
-			xdp->data_end = NULL;
-			xdp->data_hard_start = NULL;
-			xdp->data_meta = NULL;
-			goto construct_skb;
-		}
 
 		xsk_buff_set_size(xdp, size);
-		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
+		xsk_buff_dma_sync_for_cpu(xdp, xsk_pool);
+
+		if (!first) {
+			first = xdp;
+			xdp_buff_clear_frags_flag(first);
+		} else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) {
+			break;
+		}
+
+		if (++ntc == cnt)
+			ntc = 0;
 
-		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring);
+		if (ice_is_non_eop(rx_ring, rx_desc))
+			continue;
+
+		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring);
 		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
 			xdp_xmit |= xdp_res;
 		} else if (xdp_res == ICE_XDP_EXIT) {
 			failure = true;
+			first = NULL;
+			rx_ring->first_desc = ntc;
 			break;
 		} else if (xdp_res == ICE_XDP_CONSUMED) {
-			xsk_buff_free(xdp);
+			xsk_buff_free(first);
 		} else if (xdp_res == ICE_XDP_PASS) {
 			goto construct_skb;
 		}
 
-		total_rx_bytes += size;
+		total_rx_bytes += xdp_get_buff_len(first);
 		total_rx_packets++;
 
-		ice_bump_ntc(rx_ring);
+		first = NULL;
+		rx_ring->first_desc = ntc;
 		continue;
 
 construct_skb:
 		/* XDP_PASS path */
-		skb = ice_construct_skb_zc(rx_ring, xdp);
+		skb = ice_construct_skb_zc(rx_ring, first);
 		if (!skb) {
 			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
 			break;
 		}
 
-		ice_bump_ntc(rx_ring);
+		first = NULL;
+		rx_ring->first_desc = ntc;
 
 		if (eth_skb_pad(skb)) {
 			skb = NULL;
@@ -858,18 +957,22 @@ construct_skb:
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 	}
 
-	entries_to_alloc = ICE_DESC_UNUSED(rx_ring);
+	rx_ring->next_to_clean = ntc;
+	entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
 	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
 		failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
 
-	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
-		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
+	if (xsk_uses_need_wakeup(xsk_pool)) {
+		/* ntu could have changed when allocating entries above, so
+		 * use rx_ring value instead of stack based one
+		 */
+		if (failure || ntc == rx_ring->next_to_use)
+			xsk_set_rx_need_wakeup(xsk_pool);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);
+			xsk_clear_rx_need_wakeup(xsk_pool);
 
 		return (int)total_rx_packets;
 	}
@@ -894,7 +997,7 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
 
 	tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
 	tx_desc->buf_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
+	tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(desc),
 						      0, desc->len, 0);
 
 	*total_bytes += desc->len;
@@ -921,7 +1024,7 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 
 		tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
 		tx_desc->buf_addr = cpu_to_le64(dma);
-		tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(&descs[i]),
 							      0, descs[i].len, 0);
 
 		*total_bytes += descs[i].len;