[PATCH v2 1/1] net: fec: implement rx_copybreak to improve rx performance

* [PATCH v2 1/1] net: fec: implement rx_copybreak to improve rx performance
@ 2014-09-29  7:47 Fugang Duan
  2014-09-29 12:12 ` Eric Dumazet
  0 siblings, 1 reply; 5+ messages in thread
From: Fugang Duan @ 2014-09-29  7:47 UTC (permalink / raw)
  To: b20596, davem, romieu; +Cc: netdev, shawn.guo, B20596, bhutchings, b38611

- Copy short frames and keep the buffers mapped, re-allocate skb instead of
  memory copy for long frames.
- Add support for setting/getting rx_copybreak using generic ethtool tunable

Changes V2:
* Implements rx_copybreak
* Rx_copybreak provides module parameter to change this value
* Add tunable_ops support for rx_copybreak

Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
 drivers/net/ethernet/freescale/fec.h      |    2 +
 drivers/net/ethernet/freescale/fec_main.c |  212 ++++++++++++++++++++---------
 2 files changed, 149 insertions(+), 65 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 354a309..1d5e182 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -482,6 +482,8 @@ struct fec_enet_private {
 	unsigned int tx_pkts_itr;
 	unsigned int tx_time_itr;
 	unsigned int itr_clk_rate;
+
+	u32 rx_copybreak;
 };
 
 void fec_ptp_init(struct platform_device *pdev);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2c73434..276a0aa 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -176,6 +176,12 @@ static unsigned char macaddr[ETH_ALEN];
 module_param_array(macaddr, byte, NULL, 0);
 MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 
+#define COPYBREAK_DEFAULT 256
+static unsigned int copybreak __read_mostly = COPYBREAK_DEFAULT;
+module_param(copybreak, uint, 0644);
+MODULE_PARM_DESC(copybreak,
+		 "Maximum packet size that is copied to a new buffer on receive");
+
 #if defined(CONFIG_M5272)
 /*
  * Some hardware gets it MAC address out of local flash memory.
@@ -1322,6 +1328,50 @@ fec_enet_tx(struct net_device *ndev)
 	return;
 }
 
+static int
+fec_enet_new_rxbdp(struct net_device *ndev, struct bufdesc *bdp, struct sk_buff *skb)
+{
+	struct  fec_enet_private *fep = netdev_priv(ndev);
+	int off;
+
+	off = ((unsigned long)skb->data) & fep->rx_align;
+	if (off)
+		skb_reserve(skb, fep->rx_align + 1 - off);
+
+	bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, skb->data,
+					  FEC_ENET_RX_FRSIZE - fep->rx_align,
+					  DMA_FROM_DEVICE);
+	if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+		if (net_ratelimit())
+			netdev_err(ndev, "Rx DMA memory map failed\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static bool fec_enet_copybreak(struct net_device *ndev, struct sk_buff **skb,
+			       struct bufdesc *bdp, u32 length)
+{
+	struct  fec_enet_private *fep = netdev_priv(ndev);
+	struct sk_buff *new_skb;
+
+	if (length > fep->rx_copybreak)
+		return false;
+
+	new_skb = netdev_alloc_skb(ndev, length);
+	if (!new_skb)
+		return false;
+
+	dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
+				FEC_ENET_RX_FRSIZE - fep->rx_align,
+				DMA_FROM_DEVICE);
+	memcpy(new_skb->data, (*skb)->data, length);
+	*skb = new_skb;
+
+	return true;
+}
+
 /* During a receive, the cur_rx points to the current incoming buffer.
  * When we update through the ring, if the next incoming buffer has
  * not been given to the system, we just set the empty indicator,
@@ -1336,7 +1386,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	struct fec_enet_priv_rx_q *rxq;
 	struct bufdesc *bdp;
 	unsigned short status;
-	struct	sk_buff	*skb;
+	struct  sk_buff *skb_new = NULL;
+	struct  sk_buff *skb;
 	ushort	pkt_len;
 	__u8 *data;
 	int	pkt_received = 0;
@@ -1344,6 +1395,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 	bool	vlan_packet_rcvd = false;
 	u16	vlan_tag;
 	int	index = 0;
+	bool	is_copybreak;
 
 #ifdef CONFIG_M532x
 	flush_cache_all();
@@ -1401,11 +1453,27 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		ndev->stats.rx_bytes += pkt_len;
 
 		index = fec_enet_get_bd_index(rxq->rx_bd_base, bdp, fep);
-		data = rxq->rx_skbuff[index]->data;
-		dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
-					FEC_ENET_RX_FRSIZE - fep->rx_align,
-					DMA_FROM_DEVICE);
+		skb = rxq->rx_skbuff[index];
 
+		/* The packet length includes FCS, but we don't want to
+		 * include that when passing upstream as it messes up
+		 * bridging applications.
+		 */
+		is_copybreak = fec_enet_copybreak(ndev, &skb, bdp, pkt_len - 4);
+		if (!is_copybreak) {
+			skb_new = netdev_alloc_skb(ndev, FEC_ENET_RX_FRSIZE);
+			if (unlikely(!skb_new)) {
+				ndev->stats.rx_dropped++;
+				goto rx_processing_done;
+			}
+			dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+					 FEC_ENET_RX_FRSIZE - fep->rx_align,
+					 DMA_FROM_DEVICE);
+		}
+
+		prefetch(skb->data - NET_IP_ALIGN);
+		skb_put(skb, pkt_len - 4);
+		data = skb->data;
 		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
 			swap_buffer(data, pkt_len);
 
@@ -1422,62 +1490,48 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 			struct vlan_hdr *vlan_header =
 					(struct vlan_hdr *) (data + ETH_HLEN);
 			vlan_tag = ntohs(vlan_header->h_vlan_TCI);
-			pkt_len -= VLAN_HLEN;
 
 			vlan_packet_rcvd = true;
+
+			skb_copy_to_linear_data_offset(skb, VLAN_HLEN,
+						       data, (2 * ETH_ALEN));
+			skb_pull(skb, VLAN_HLEN);
 		}
 
-		/* This does 16 byte alignment, exactly what we need.
-		 * The packet length includes FCS, but we don't want to
-		 * include that when passing upstream as it messes up
-		 * bridging applications.
-		 */
-		skb = netdev_alloc_skb(ndev, pkt_len - 4 + NET_IP_ALIGN);
+		skb->protocol = eth_type_trans(skb, ndev);
 
-		if (unlikely(!skb)) {
-			ndev->stats.rx_dropped++;
-		} else {
-			int payload_offset = (2 * ETH_ALEN);
-			skb_reserve(skb, NET_IP_ALIGN);
-			skb_put(skb, pkt_len - 4);	/* Make room */
-
-			/* Extract the frame data without the VLAN header. */
-			skb_copy_to_linear_data(skb, data, (2 * ETH_ALEN));
-			if (vlan_packet_rcvd)
-				payload_offset = (2 * ETH_ALEN) + VLAN_HLEN;
-			skb_copy_to_linear_data_offset(skb, (2 * ETH_ALEN),
-						       data + payload_offset,
-						       pkt_len - 4 - (2 * ETH_ALEN));
-
-			skb->protocol = eth_type_trans(skb, ndev);
-
-			/* Get receive timestamp from the skb */
-			if (fep->hwts_rx_en && fep->bufdesc_ex)
-				fec_enet_hwtstamp(fep, ebdp->ts,
-						  skb_hwtstamps(skb));
-
-			if (fep->bufdesc_ex &&
-			    (fep->csum_flags & FLAG_RX_CSUM_ENABLED)) {
-				if (!(ebdp->cbd_esc & FLAG_RX_CSUM_ERROR)) {
-					/* don't check it */
-					skb->ip_summed = CHECKSUM_UNNECESSARY;
-				} else {
-					skb_checksum_none_assert(skb);
-				}
+		/* Get receive timestamp from the skb */
+		if (fep->hwts_rx_en && fep->bufdesc_ex)
+			fec_enet_hwtstamp(fep, ebdp->ts,
+					  skb_hwtstamps(skb));
+
+		if (fep->bufdesc_ex &&
+		    (fep->csum_flags & FLAG_RX_CSUM_ENABLED)) {
+			if (!(ebdp->cbd_esc & FLAG_RX_CSUM_ERROR)) {
+				/* don't check it */
+				skb->ip_summed = CHECKSUM_UNNECESSARY;
+			} else {
+				skb_checksum_none_assert(skb);
 			}
+		}
 
-			/* Handle received VLAN packets */
-			if (vlan_packet_rcvd)
-				__vlan_hwaccel_put_tag(skb,
-						       htons(ETH_P_8021Q),
-						       vlan_tag);
+		/* Handle received VLAN packets */
+		if (vlan_packet_rcvd)
+			__vlan_hwaccel_put_tag(skb,
+					       htons(ETH_P_8021Q),
+					       vlan_tag);
 
-			napi_gro_receive(&fep->napi, skb);
+		napi_gro_receive(&fep->napi, skb);
+
+		if (is_copybreak) {
+			dma_sync_single_for_device(&fep->pdev->dev, bdp->cbd_bufaddr,
+						   FEC_ENET_RX_FRSIZE - fep->rx_align,
+						   DMA_FROM_DEVICE);
+		} else {
+			rxq->rx_skbuff[index] = skb_new;
+			fec_enet_new_rxbdp(ndev, bdp, skb_new);
 		}
 
-		dma_sync_single_for_device(&fep->pdev->dev, bdp->cbd_bufaddr,
-					   FEC_ENET_RX_FRSIZE - fep->rx_align,
-					   DMA_FROM_DEVICE);
 rx_processing_done:
 		/* Clear the status flags for this buffer */
 		status &= ~BD_ENET_RX_STATS;
@@ -2392,6 +2446,44 @@ static void fec_enet_itr_coal_init(struct net_device *ndev)
 	fec_enet_set_coalesce(ndev, &ec);
 }
 
+static int fec_enet_get_tunable(struct net_device *netdev,
+				const struct ethtool_tunable *tuna,
+				void *data)
+{
+	struct fec_enet_private *fep = netdev_priv(netdev);
+	int ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)data = fep->rx_copybreak;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int fec_enet_set_tunable(struct net_device *netdev,
+				const struct ethtool_tunable *tuna,
+				const void *data)
+{
+	struct fec_enet_private *fep = netdev_priv(netdev);
+	int ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		fep->rx_copybreak = *(u32 *)data;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_settings		= fec_enet_get_settings,
 	.set_settings		= fec_enet_set_settings,
@@ -2408,6 +2500,8 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_sset_count		= fec_enet_get_sset_count,
 #endif
 	.get_ts_info		= fec_enet_get_ts_info,
+	.get_tunable		= fec_enet_get_tunable,
+	.set_tunable		= fec_enet_set_tunable,
 };
 
 static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
@@ -2553,33 +2647,20 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue)
 	struct sk_buff *skb;
 	struct bufdesc	*bdp;
 	struct fec_enet_priv_rx_q *rxq;
-	unsigned int off;
 
 	rxq = fep->rx_queue[queue];
 	bdp = rxq->rx_bd_base;
 	for (i = 0; i < rxq->rx_ring_size; i++) {
-		dma_addr_t addr;
-
 		skb = netdev_alloc_skb(ndev, FEC_ENET_RX_FRSIZE);
 		if (!skb)
 			goto err_alloc;
 
-		off = ((unsigned long)skb->data) & fep->rx_align;
-		if (off)
-			skb_reserve(skb, fep->rx_align + 1 - off);
-
-		addr = dma_map_single(&fep->pdev->dev, skb->data,
-				FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE);
-
-		if (dma_mapping_error(&fep->pdev->dev, addr)) {
+		if (fec_enet_new_rxbdp(ndev, bdp, skb)) {
 			dev_kfree_skb(skb);
-			if (net_ratelimit())
-				netdev_err(ndev, "Rx DMA memory map failed\n");
 			goto err_alloc;
 		}
 
 		rxq->rx_skbuff[i] = skb;
-		bdp->cbd_bufaddr = addr;
 		bdp->cbd_sc = BD_ENET_RX_EMPTY;
 
 		if (fep->bufdesc_ex) {
@@ -3240,6 +3321,7 @@ fec_probe(struct platform_device *pdev)
 	if (fep->bufdesc_ex && fep->ptp_clock)
 		netdev_info(ndev, "registered PHC device %d\n", fep->dev_id);
 
+	fep->rx_copybreak = copybreak;
 	INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
 	return 0;
 
-- 
1.7.8

^ permalink raw reply related	[flat|nested] 5+ messages in thread