Merge branch 'dpaa2-eth-Driver-updates'

Ioana Ciocoi Radulescu says:

====================
dpaa2-eth: Driver updates

First patch moves the driver to a page-per-frame memory model.
The others are minor tweaks and optimizations.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c

@@ -86,16 +86,16 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 	for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) {
 		addr = dpaa2_sg_get_addr(&sgt[i]);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
 			       DMA_BIDIRECTIONAL);
 
-		skb_free_frag(sg_vaddr);
+		free_pages((unsigned long)sg_vaddr, 0);
 		if (dpaa2_sg_is_final(&sgt[i]))
 			break;
 	}
 
 free_buf:
-	skb_free_frag(vaddr);
+	free_pages((unsigned long)vaddr, 0);
 }
 
 /* Build a linear skb based on a single-buffer frame descriptor */
@@ -109,7 +109,7 @@ static struct sk_buff *build_linear_skb(struct dpaa2_eth_channel *ch,
 
 	ch->buf_count--;
 
-	skb = build_skb(fd_vaddr, DPAA2_ETH_SKB_SIZE);
+	skb = build_skb(fd_vaddr, DPAA2_ETH_RX_BUF_RAW_SIZE);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -144,19 +144,19 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 		/* Get the address and length from the S/G entry */
 		sg_addr = dpaa2_sg_get_addr(sge);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
-		dma_unmap_single(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
 			       DMA_BIDIRECTIONAL);
 
 		sg_length = dpaa2_sg_get_len(sge);
 
 		if (i == 0) {
 			/* We build the skb around the first data buffer */
-			skb = build_skb(sg_vaddr, DPAA2_ETH_SKB_SIZE);
+			skb = build_skb(sg_vaddr, DPAA2_ETH_RX_BUF_RAW_SIZE);
 			if (unlikely(!skb)) {
 				/* Free the first SG entry now, since we already
 				 * unmapped it and obtained the virtual address
 				 */
-				skb_free_frag(sg_vaddr);
+				free_pages((unsigned long)sg_vaddr, 0);
 
 				/* We still need to subtract the buffers used
 				 * by this FD from our software counter
@@ -211,9 +211,9 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 
 	for (i = 0; i < count; i++) {
 		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_single(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
 			       DMA_BIDIRECTIONAL);
-		skb_free_frag(vaddr);
+		free_pages((unsigned long)vaddr, 0);
 	}
 }
 
@@ -264,9 +264,7 @@ static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
 
 	fq = &priv->fq[queue_id];
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = dpaa2_io_service_enqueue_qd(fq->channel->dpio,
-						  priv->tx_qdid, 0,
-						  fq->tx_qdbin, fd);
+		err = priv->enqueue(priv, fq, fd, 0);
 		if (err != -EBUSY)
 			break;
 	}
@@ -378,16 +376,16 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			return;
 		}
 
-		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
 			       DMA_BIDIRECTIONAL);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
 
-		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
 			       DMA_BIDIRECTIONAL);
 		skb = build_frag_skb(priv, ch, buf_data);
-		skb_free_frag(vaddr);
+		free_pages((unsigned long)vaddr, 0);
 		percpu_extras->rx_sg_frames++;
 		percpu_extras->rx_sg_bytes += dpaa2_fd_get_len(fd);
 	} else {
@@ -657,7 +655,7 @@ static int build_single_fd(struct dpaa2_eth_priv *priv,
  * dpaa2_eth_tx().
  */
 static void free_tx_fd(const struct dpaa2_eth_priv *priv,
-		       const struct dpaa2_fd *fd)
+		       const struct dpaa2_fd *fd, bool in_napi)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	dma_addr_t fd_addr;
@@ -712,7 +710,7 @@ static void free_tx_fd(const struct dpaa2_eth_priv *priv,
 		skb_free_frag(skbh);
 
 	/* Move on with skb release */
-	dev_kfree_skb(skb);
+	napi_consume_skb(skb, in_napi);
 }
 
 static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
@@ -785,9 +783,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	queue_mapping = skb_get_queue_mapping(skb);
 	fq = &priv->fq[queue_mapping];
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = dpaa2_io_service_enqueue_qd(fq->channel->dpio,
-						  priv->tx_qdid, 0,
-						  fq->tx_qdbin, &fd);
+		err = priv->enqueue(priv, fq, &fd, 0);
 		if (err != -EBUSY)
 			break;
 	}
@@ -795,7 +791,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	if (unlikely(err < 0)) {
 		percpu_stats->tx_errors++;
 		/* Clean up everything, including freeing the skb */
-		free_tx_fd(priv, &fd);
+		free_tx_fd(priv, &fd, false);
 	} else {
 		fd_len = dpaa2_fd_get_len(&fd);
 		percpu_stats->tx_packets++;
@@ -837,7 +833,7 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
 
 	/* Check frame errors in the FD field */
 	fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK;
-	free_tx_fd(priv, fd);
+	free_tx_fd(priv, fd, true);
 
 	if (likely(!fd_errors))
 		return;
@@ -903,7 +899,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	u64 buf_array[DPAA2_ETH_BUFS_PER_CMD];
-	void *buf;
+	struct page *page;
 	dma_addr_t addr;
 	int i, err;
 
@@ -911,13 +907,15 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		/* Allocate buffer visible to WRIOP + skb shared info +
 		 * alignment padding
 		 */
-		buf = napi_alloc_frag(dpaa2_eth_buf_raw_size(priv));
-		if (unlikely(!buf))
+		/* allocate one page for each Rx buffer. WRIOP sees
+		 * the entire page except for a tailroom reserved for
+		 * skb shared info
+		 */
+		page = dev_alloc_pages(0);
+		if (!page)
 			goto err_alloc;
 
-		buf = PTR_ALIGN(buf, priv->rx_buf_align);
-
-		addr = dma_map_single(dev, buf, DPAA2_ETH_RX_BUF_SIZE,
+		addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE,
 				    DMA_BIDIRECTIONAL);
 		if (unlikely(dma_mapping_error(dev, addr)))
 			goto err_map;
@@ -926,7 +924,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 
 		/* tracing point */
 		trace_dpaa2_eth_buf_seed(priv->net_dev,
-					 buf, dpaa2_eth_buf_raw_size(priv),
+					 page, DPAA2_ETH_RX_BUF_RAW_SIZE,
 					 addr, DPAA2_ETH_RX_BUF_SIZE,
 					 bpid);
 	}
@@ -948,7 +946,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 	return i;
 
 err_map:
-	skb_free_frag(buf);
+	__free_pages(page, 0);
 err_alloc:
 	/* If we managed to allocate at least some buffers,
 	 * release them to hardware
@@ -2134,6 +2132,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	struct dpni_buffer_layout buf_layout = {0};
+	u16 rx_buf_align;
 	int err;
 
 	/* We need to check for WRIOP version 1.0.0, but depending on the MC
@@ -2142,9 +2141,9 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	 */
 	if (priv->dpni_attrs.wriop_version == DPAA2_WRIOP_VERSION(0, 0, 0) ||
 	    priv->dpni_attrs.wriop_version == DPAA2_WRIOP_VERSION(1, 0, 0))
-		priv->rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN_REV1;
+		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN_REV1;
 	else
-		priv->rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
+		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
 
 	/* tx buffer */
 	buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE;
@@ -2184,7 +2183,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	/* rx buffer */
 	buf_layout.pass_frame_status = true;
 	buf_layout.pass_parser_result = true;
-	buf_layout.data_align = priv->rx_buf_align;
+	buf_layout.data_align = rx_buf_align;
 	buf_layout.data_head_room = dpaa2_eth_rx_head_room(priv);
 	buf_layout.private_data_size = 0;
 	buf_layout.options = DPNI_BUF_LAYOUT_OPT_PARSER_RESULT |
@@ -2202,6 +2201,36 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	return 0;
 }
 
+#define DPNI_ENQUEUE_FQID_VER_MAJOR	7
+#define DPNI_ENQUEUE_FQID_VER_MINOR	9
+
+static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv,
+				       struct dpaa2_eth_fq *fq,
+				       struct dpaa2_fd *fd, u8 prio)
+{
+	return dpaa2_io_service_enqueue_qd(fq->channel->dpio,
+					   priv->tx_qdid, prio,
+					   fq->tx_qdbin, fd);
+}
+
+static inline int dpaa2_eth_enqueue_fq(struct dpaa2_eth_priv *priv,
+				       struct dpaa2_eth_fq *fq,
+				       struct dpaa2_fd *fd,
+				       u8 prio __always_unused)
+{
+	return dpaa2_io_service_enqueue_fq(fq->channel->dpio,
+					   fq->tx_fqid, fd);
+}
+
+static void set_enqueue_mode(struct dpaa2_eth_priv *priv)
+{
+	if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_ENQUEUE_FQID_VER_MAJOR,
+				   DPNI_ENQUEUE_FQID_VER_MINOR) < 0)
+		priv->enqueue = dpaa2_eth_enqueue_qd;
+	else
+		priv->enqueue = dpaa2_eth_enqueue_fq;
+}
+
 /* Configure the DPNI object this interface is associated with */
 static int setup_dpni(struct fsl_mc_device *ls_dev)
 {
@@ -2255,6 +2284,8 @@ static int setup_dpni(struct fsl_mc_device *ls_dev)
 	if (err)
 		goto close;
 
+	set_enqueue_mode(priv);
+
 	priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) *
 				       dpaa2_eth_fs_count(priv), GFP_KERNEL);
 	if (!priv->cls_rules)
@@ -2339,6 +2370,7 @@ static int setup_tx_flow(struct dpaa2_eth_priv *priv,
 	}
 
 	fq->tx_qdbin = qid.qdbin;
+	fq->tx_fqid = qid.fqid;
 
 	err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
 			     DPNI_QUEUE_TX_CONFIRM, 0, fq->flowid,

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h

@@ -53,7 +53,8 @@
  */
 #define DPAA2_ETH_MAX_FRAMES_PER_QUEUE	(DPAA2_ETH_TAILDROP_THRESH / 64)
 #define DPAA2_ETH_NUM_BUFS		(DPAA2_ETH_MAX_FRAMES_PER_QUEUE + 256)
-#define DPAA2_ETH_REFILL_THRESH		DPAA2_ETH_MAX_FRAMES_PER_QUEUE
+#define DPAA2_ETH_REFILL_THRESH \
+	(DPAA2_ETH_NUM_BUFS - DPAA2_ETH_BUFS_PER_CMD)
 
 /* Maximum number of buffers that can be acquired/released through a single
  * QBMan command
@@ -63,9 +64,11 @@
 /* Hardware requires alignment for ingress/egress buffer addresses */
 #define DPAA2_ETH_TX_BUF_ALIGN		64
 
-#define DPAA2_ETH_RX_BUF_SIZE		2048
-#define DPAA2_ETH_SKB_SIZE \
-	(DPAA2_ETH_RX_BUF_SIZE + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define DPAA2_ETH_RX_BUF_RAW_SIZE	PAGE_SIZE
+#define DPAA2_ETH_RX_BUF_TAILROOM \
+	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
+#define DPAA2_ETH_RX_BUF_SIZE \
+	(DPAA2_ETH_RX_BUF_RAW_SIZE - DPAA2_ETH_RX_BUF_TAILROOM)
 
 /* Hardware annotation area in RX/TX buffers */
 #define DPAA2_ETH_RX_HWA_SIZE		64
@@ -274,6 +277,7 @@ struct dpaa2_eth_priv;
 struct dpaa2_eth_fq {
 	u32 fqid;
 	u32 tx_qdbin;
+	u32 tx_fqid;
 	u16 flowid;
 	int target_cpu;
 	u32 dq_frames;
@@ -326,6 +330,9 @@ struct dpaa2_eth_priv {
 
 	u8 num_fqs;
 	struct dpaa2_eth_fq fq[DPAA2_ETH_MAX_QUEUES];
+	int (*enqueue)(struct dpaa2_eth_priv *priv,
+		       struct dpaa2_eth_fq *fq,
+		       struct dpaa2_fd *fd, u8 prio);
 
 	u8 num_channels;
 	struct dpaa2_eth_channel *channel[DPAA2_ETH_MAX_DPCONS];
@@ -343,7 +350,6 @@ struct dpaa2_eth_priv {
 	bool rx_tstamp; /* Rx timestamping enabled */
 
 	u16 tx_qdid;
-	u16 rx_buf_align;
 	struct fsl_mc_io *mc_io;
 	/* Cores which have an affine DPIO/DPCON.
 	 * This is the cpu set on which Rx and Tx conf frames are processed
@@ -418,15 +424,6 @@ enum dpaa2_eth_rx_dist {
 	DPAA2_ETH_RX_DIST_CLS
 };
 
-/* Hardware only sees DPAA2_ETH_RX_BUF_SIZE, but the skb built around
- * the buffer also needs space for its shared info struct, and we need
- * to allocate enough to accommodate hardware alignment restrictions
- */
-static inline unsigned int dpaa2_eth_buf_raw_size(struct dpaa2_eth_priv *priv)
-{
-	return DPAA2_ETH_SKB_SIZE + priv->rx_buf_align;
-}
-
 static inline
 unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
 				       struct sk_buff *skb)
@@ -451,8 +448,7 @@ unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
  */
 static inline unsigned int dpaa2_eth_rx_head_room(struct dpaa2_eth_priv *priv)
 {
-	return priv->tx_data_offset + DPAA2_ETH_TX_BUF_ALIGN -
-	       DPAA2_ETH_RX_HWA_SIZE;
+	return priv->tx_data_offset - DPAA2_ETH_RX_HWA_SIZE;
 }
 
 int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags);