idpf: convert to libeth Tx buffer completion

&idpf_tx_buffer is almost identical to the previous generations, as well
as the way it's handled. Moreover, relying on dma_unmap_addr() and
!!buf->skb instead of explicit defining of buffer's type was never good.
Use the newly added libeth helpers to do it properly and reduce the
copy-paste around the Tx code.
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c

@@ -2,6 +2,7 @@
 /* Copyright (C) 2023 Intel Corporation */
 
 #include <net/libeth/rx.h>
+#include <net/libeth/tx.h>
 
 #include "idpf.h"
 
@@ -224,6 +225,7 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 		/* record length, and DMA address */
 		dma_unmap_len_set(tx_buf, len, size);
 		dma_unmap_addr_set(tx_buf, dma, dma);
+		tx_buf->type = LIBETH_SQE_FRAG;
 
 		/* align size to end of page */
 		max_data += -dma & (IDPF_TX_MAX_READ_REQ_SIZE - 1);
@@ -245,6 +247,8 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 				i = 0;
 			}
 
+			tx_q->tx_buf[i].type = LIBETH_SQE_EMPTY;
+
 			dma += max_data;
 			size -= max_data;
 
@@ -282,13 +286,13 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 	tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, offsets,
 						  size, td_tag);
 
-	IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i);
+	first->type = LIBETH_SQE_SKB;
+	first->rs_idx = i;
 
-	/* set next_to_watch value indicating a packet is present */
-	first->next_to_watch = tx_desc;
+	IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i);
 
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
-	netdev_tx_sent_queue(nq, first->bytecount);
+	netdev_tx_sent_queue(nq, first->bytes);
 
 	idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more());
 }
@@ -306,8 +310,7 @@ idpf_tx_singleq_get_ctx_desc(struct idpf_tx_queue *txq)
 	struct idpf_base_tx_ctx_desc *ctx_desc;
 	int ntu = txq->next_to_use;
 
-	memset(&txq->tx_buf[ntu], 0, sizeof(struct idpf_tx_buf));
-	txq->tx_buf[ntu].ctx_entry = true;
+	txq->tx_buf[ntu].type = LIBETH_SQE_CTX;
 
 	ctx_desc = &txq->base_ctx[ntu];
 
@@ -396,11 +399,11 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 	first->skb = skb;
 
 	if (tso) {
-		first->gso_segs = offload.tso_segs;
-		first->bytecount = skb->len + ((first->gso_segs - 1) * offload.tso_hdr_len);
+		first->packets = offload.tso_segs;
+		first->bytes = skb->len + ((first->packets - 1) * offload.tso_hdr_len);
 	} else {
-		first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
-		first->gso_segs = 1;
+		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+		first->packets = 1;
 	}
 	idpf_tx_singleq_map(tx_q, first, &offload);
 
@@ -420,10 +423,15 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 				  int *cleaned)
 {
-	unsigned int total_bytes = 0, total_pkts = 0;
+	struct libeth_sq_napi_stats ss = { };
 	struct idpf_base_tx_desc *tx_desc;
 	u32 budget = tx_q->clean_budget;
 	s16 ntc = tx_q->next_to_clean;
+	struct libeth_cq_pp cp = {
+		.dev	= tx_q->dev,
+		.ss	= &ss,
+		.napi	= napi_budget,
+	};
 	struct idpf_netdev_priv *np;
 	struct idpf_tx_buf *tx_buf;
 	struct netdev_queue *nq;
@@ -441,47 +449,23 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 		 * such. We can skip this descriptor since there is no buffer
 		 * to clean.
 		 */
-		if (tx_buf->ctx_entry) {
-			/* Clear this flag here to avoid stale flag values when
-			 * this buffer is used for actual data in the future.
-			 * There are cases where the tx_buf struct / the flags
-			 * field will not be cleared before being reused.
-			 */
-			tx_buf->ctx_entry = false;
+		if (unlikely(tx_buf->type <= LIBETH_SQE_CTX)) {
+			tx_buf->type = LIBETH_SQE_EMPTY;
 			goto fetch_next_txq_desc;
 		}
 
-		/* if next_to_watch is not set then no work pending */
-		eop_desc = (struct idpf_base_tx_desc *)tx_buf->next_to_watch;
-		if (!eop_desc)
-			break;
-
-		/* prevent any other reads prior to eop_desc */
+		/* prevent any other reads prior to type */
 		smp_rmb();
 
+		eop_desc = &tx_q->base_tx[tx_buf->rs_idx];
+
 		/* if the descriptor isn't done, no work yet to do */
 		if (!(eop_desc->qw1 &
 		      cpu_to_le64(IDPF_TX_DESC_DTYPE_DESC_DONE)))
 			break;
 
-		/* clear next_to_watch to prevent false hangs */
-		tx_buf->next_to_watch = NULL;
-
 		/* update the statistics for this packet */
-		total_bytes += tx_buf->bytecount;
-		total_pkts += tx_buf->gso_segs;
-
-		napi_consume_skb(tx_buf->skb, napi_budget);
-
-		/* unmap skb header data */
-		dma_unmap_single(tx_q->dev,
-				 dma_unmap_addr(tx_buf, dma),
-				 dma_unmap_len(tx_buf, len),
-				 DMA_TO_DEVICE);
-
-		/* clear tx_buf data */
-		tx_buf->skb = NULL;
-		dma_unmap_len_set(tx_buf, len, 0);
+		libeth_tx_complete(tx_buf, &cp);
 
 		/* unmap remaining buffers */
 		while (tx_desc != eop_desc) {
@@ -495,13 +479,7 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 			}
 
 			/* unmap any remaining paged data */
-			if (dma_unmap_len(tx_buf, len)) {
-				dma_unmap_page(tx_q->dev,
-					       dma_unmap_addr(tx_buf, dma),
-					       dma_unmap_len(tx_buf, len),
-					       DMA_TO_DEVICE);
-				dma_unmap_len_set(tx_buf, len, 0);
-			}
+			libeth_tx_complete(tx_buf, &cp);
 		}
 
 		/* update budget only if we did something */
@@ -521,11 +499,11 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 	ntc += tx_q->desc_count;
 	tx_q->next_to_clean = ntc;
 
-	*cleaned += total_pkts;
+	*cleaned += ss.packets;
 
 	u64_stats_update_begin(&tx_q->stats_sync);
-	u64_stats_add(&tx_q->q_stats.packets, total_pkts);
-	u64_stats_add(&tx_q->q_stats.bytes, total_bytes);
+	u64_stats_add(&tx_q->q_stats.packets, ss.packets);
+	u64_stats_add(&tx_q->q_stats.bytes, ss.bytes);
 	u64_stats_update_end(&tx_q->stats_sync);
 
 	np = netdev_priv(tx_q->netdev);
@@ -533,7 +511,7 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 
 	dont_wake = np->state != __IDPF_VPORT_UP ||
 		    !netif_carrier_ok(tx_q->netdev);
-	__netif_txq_completed_wake(nq, total_pkts, total_bytes,
+	__netif_txq_completed_wake(nq, ss.packets, ss.bytes,
 				   IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH,
 				   dont_wake);
 

drivers/net/ethernet/intel/idpf/idpf_txrx.h

@@ -131,7 +131,6 @@ do {								\
 	(txq)->num_completions_pending - (txq)->complq->num_completions)
 
 #define IDPF_TX_SPLITQ_COMPL_TAG_WIDTH	16
-#define IDPF_SPLITQ_TX_INVAL_COMPL_TAG	-1
 /* Adjust the generation for the completion tag and wrap if necessary */
 #define IDPF_TX_ADJ_COMPL_TAG_GEN(txq) \
 	((++(txq)->compl_tag_cur_gen) >= (txq)->compl_tag_gen_max ? \
@@ -149,47 +148,7 @@ union idpf_tx_flex_desc {
 	struct idpf_flex_tx_sched_desc flow; /* flow based scheduling */
 };
 
-/**
- * struct idpf_tx_buf
- * @next_to_watch: Next descriptor to clean
- * @skb: Pointer to the skb
- * @dma: DMA address
- * @len: DMA length
- * @bytecount: Number of bytes
- * @gso_segs: Number of GSO segments
- * @compl_tag: Splitq only, unique identifier for a buffer. Used to compare
- *	       with completion tag returned in buffer completion event.
- *	       Because the completion tag is expected to be the same in all
- *	       data descriptors for a given packet, and a single packet can
- *	       span multiple buffers, we need this field to track all
- *	       buffers associated with this completion tag independently of
- *	       the buf_id. The tag consists of a N bit buf_id and M upper
- *	       order "generation bits". See compl_tag_bufid_m and
- *	       compl_tag_gen_s in struct idpf_queue. We'll use a value of -1
- *	       to indicate the tag is not valid.
- * @ctx_entry: Singleq only. Used to indicate the corresponding entry
- *	       in the descriptor ring was used for a context descriptor and
- *	       this buffer entry should be skipped.
- */
-struct idpf_tx_buf {
-	void *next_to_watch;
-	struct sk_buff *skb;
-	DEFINE_DMA_UNMAP_ADDR(dma);
-	DEFINE_DMA_UNMAP_LEN(len);
-	unsigned int bytecount;
-	unsigned short gso_segs;
-
-	union {
-		int compl_tag;
-
-		bool ctx_entry;
-	};
-};
-
-struct idpf_tx_stash {
-	struct hlist_node hlist;
-	struct idpf_tx_buf buf;
-};
+#define idpf_tx_buf libeth_sqe
 
 /**
  * struct idpf_buf_lifo - LIFO for managing OOO completions
@@ -496,11 +455,6 @@ struct idpf_tx_queue_stats {
 	u64_stats_t dma_map_errs;
 };
 
-struct idpf_cleaned_stats {
-	u32 packets;
-	u32 bytes;
-};
-
 #define IDPF_ITR_DYNAMIC	1
 #define IDPF_ITR_MAX		0x1FE0
 #define IDPF_ITR_20K		0x0032
@@ -688,7 +642,7 @@ struct idpf_tx_queue {
 
 		void *desc_ring;
 	};
-	struct idpf_tx_buf *tx_buf;
+	struct libeth_sqe *tx_buf;
 	struct idpf_txq_group *txq_grp;
 	struct device *dev;
 	void __iomem *tail;