diff mbox series

[net-next,v2,5/6] bcm63xx_enet: convert to build_skb

Message ID 20201224142421.32350-6-liew.s.piaw@gmail.com (mailing list archive)
State Deferred
Delegated to: Netdev Maintainers
Headers show
Series bcm63xx_enet: major makeover of driver | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 4 maintainers not CCed: davem@davemloft.net leon@kernel.org kuba@kernel.org tangbin@cmss.chinamobile.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 81 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns WARNING: line length of 97 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/header_inline success Link
netdev/stable success Stable not CCed

Commit Message

Sieng-Piaw Liew Dec. 24, 2020, 2:24 p.m. UTC 
We can increase the efficiency of rx path by using buffers to receive
packets then build SKBs around them just before passing into the network
stack. In contrast, preallocating SKBs too early reduces CPU cache
efficiency.

Check if we're in NAPI context when refilling RX. Normally we're almost
always running in NAPI context. Dispatch to napi_alloc_frag directly
instead of relying on netdev_alloc_frag which does the same but
with the overhead of local_bh_disable/enable.

Tested on BCM6328 320 MHz and iperf3 -M 512 to measure packet/sec
performance. Included netif_receive_skb_list and NET_IP_ALIGN
optimizations.

Before:
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-10.00  sec  49.9 MBytes  41.9 Mbits/sec  197         sender
[  4]   0.00-10.00  sec  49.3 MBytes  41.3 Mbits/sec            receiver

After:
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-30.00  sec   171 MBytes  47.8 Mbits/sec  272         sender
[  4]   0.00-30.00  sec   170 MBytes  47.6 Mbits/sec            receiver

Signed-off-by: Sieng Piaw Liew <liew.s.piaw@gmail.com>
---
 drivers/net/ethernet/broadcom/bcm63xx_enet.c | 157 +++++++++----------
 drivers/net/ethernet/broadcom/bcm63xx_enet.h |  14 +-
 2 files changed, 80 insertions(+), 91 deletions(-)

Comments

Florian Fainelli Dec. 29, 2020, 3:24 a.m. UTC | #1 
On 12/24/2020 6:24 AM, Sieng Piaw Liew wrote:
> We can increase the efficiency of rx path by using buffers to receive
> packets then build SKBs around them just before passing into the network
> stack. In contrast, preallocating SKBs too early reduces CPU cache
> efficiency.
> 
> Check if we're in NAPI context when refilling RX. Normally we're almost
> always running in NAPI context. Dispatch to napi_alloc_frag directly
> instead of relying on netdev_alloc_frag which does the same but
> with the overhead of local_bh_disable/enable.
> 
> Tested on BCM6328 320 MHz and iperf3 -M 512 to measure packet/sec
> performance. Included netif_receive_skb_list and NET_IP_ALIGN
> optimizations.
> 
> Before:
> [ ID] Interval           Transfer     Bandwidth       Retr
> [  4]   0.00-10.00  sec  49.9 MBytes  41.9 Mbits/sec  197         sender
> [  4]   0.00-10.00  sec  49.3 MBytes  41.3 Mbits/sec            receiver
> 
> After:
> [ ID] Interval           Transfer     Bandwidth       Retr
> [  4]   0.00-30.00  sec   171 MBytes  47.8 Mbits/sec  272         sender
> [  4]   0.00-30.00  sec   170 MBytes  47.6 Mbits/sec            receiver

This looks good, however there are a few nits and suggestions below:

[snip]

> @@ -862,6 +868,24 @@ static void bcm_enet_adjust_link(struct net_device *dev)
>  		priv->pause_tx ? "tx" : "off");
>  }
>  
> +static void bcm_enet_free_rx_buf_ring(struct device *kdev, struct bcm_enet_priv *priv)
> +{
> +	int i;
> +
> +	for (i = 0; i < priv->rx_ring_size; i++) {
> +		struct bcm_enet_desc *desc;
> +
> +		if (!priv->rx_buf[i])
> +			continue;
> +
> +		desc = &priv->rx_desc_cpu[i];
> +		dma_unmap_single(kdev, desc->address, priv->rx_buf_size,
> +				 DMA_FROM_DEVICE);
> +		skb_free_frag(priv->rx_buf[i]);
> +	}
> +	kfree(priv->rx_buf);
> +}

This is a good helper to introduced, however I would introduce it as a
preliminary patch that way it becomes clear when you are doing the
sk_buff to buf substitution in the next patch.

[snip]

> @@ -1640,9 +1641,12 @@ static int bcm_enet_change_mtu(struct net_device *dev, int new_mtu)
>  	 * align rx buffer size to dma burst len, account FCS since
>  	 * it's appended
>  	 */
> -	priv->rx_skb_size = ALIGN(actual_mtu + ETH_FCS_LEN,
> +	priv->rx_buf_size = ALIGN(actual_mtu + ETH_FCS_LEN,
>  				  priv->dma_maxburst * 4);
>  
> +	priv->rx_frag_size = SKB_DATA_ALIGN(priv->rx_buf_offset + priv->rx_buf_size)
> +						+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));

The alignment of the second line is a bit off and you should aim for the
+ operator to be on the preceding line, and have SKB_DATA_ALIGN() start
on the opening parenthesis of the preceding line.
diff mbox series

Patch

diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 51976ed87d2d..8c2e97311a2c 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -220,7 +220,7 @@  static void bcm_enet_mdio_write_mii(struct net_device *dev, int mii_id,
 /*
  * refill rx queue
  */
-static int bcm_enet_refill_rx(struct net_device *dev)
+static int bcm_enet_refill_rx(struct net_device *dev, bool napi_mode)
 {
 	struct bcm_enet_priv *priv;
 
@@ -228,29 +228,29 @@  static int bcm_enet_refill_rx(struct net_device *dev)
 
 	while (priv->rx_desc_count < priv->rx_ring_size) {
 		struct bcm_enet_desc *desc;
-		struct sk_buff *skb;
-		dma_addr_t p;
 		int desc_idx;
 		u32 len_stat;
 
 		desc_idx = priv->rx_dirty_desc;
 		desc = &priv->rx_desc_cpu[desc_idx];
 
-		if (!priv->rx_skb[desc_idx]) {
-			if (priv->enet_is_sw)
-				skb = netdev_alloc_skb_ip_align(dev, priv->rx_skb_size);
+		if (!priv->rx_buf[desc_idx]) {
+			void *buf;
+
+			if (likely(napi_mode))
+				buf = napi_alloc_frag(priv->rx_frag_size);
 			else
-				skb = netdev_alloc_skb(dev, priv->rx_skb_size);
-			if (!skb)
+				buf = netdev_alloc_frag(priv->rx_frag_size);
+			if (unlikely(!buf))
 				break;
-			priv->rx_skb[desc_idx] = skb;
-			p = dma_map_single(&priv->pdev->dev, skb->data,
-					   priv->rx_skb_size,
-					   DMA_FROM_DEVICE);
-			desc->address = p;
+			priv->rx_buf[desc_idx] = buf;
+			desc->address = dma_map_single(&priv->pdev->dev,
+						       buf + priv->rx_buf_offset,
+						       priv->rx_buf_size,
+						       DMA_FROM_DEVICE);
 		}
 
-		len_stat = priv->rx_skb_size << DMADESC_LENGTH_SHIFT;
+		len_stat = priv->rx_buf_size << DMADESC_LENGTH_SHIFT;
 		len_stat |= DMADESC_OWNER_MASK;
 		if (priv->rx_dirty_desc == priv->rx_ring_size - 1) {
 			len_stat |= (DMADESC_WRAP_MASK >> priv->dma_desc_shift);
@@ -290,7 +290,7 @@  static void bcm_enet_refill_rx_timer(struct timer_list *t)
 	struct net_device *dev = priv->net_dev;
 
 	spin_lock(&priv->rx_lock);
-	bcm_enet_refill_rx(dev);
+	bcm_enet_refill_rx(dev, false);
 	spin_unlock(&priv->rx_lock);
 }
 
@@ -320,6 +320,7 @@  static int bcm_enet_receive_queue(struct net_device *dev, int budget)
 		int desc_idx;
 		u32 len_stat;
 		unsigned int len;
+		void *buf;
 
 		desc_idx = priv->rx_curr_desc;
 		desc = &priv->rx_desc_cpu[desc_idx];
@@ -365,16 +366,14 @@  static int bcm_enet_receive_queue(struct net_device *dev, int budget)
 		}
 
 		/* valid packet */
-		skb = priv->rx_skb[desc_idx];
+		buf = priv->rx_buf[desc_idx];
 		len = (len_stat & DMADESC_LENGTH_MASK) >> DMADESC_LENGTH_SHIFT;
 		/* don't include FCS */
 		len -= 4;
 
 		if (len < copybreak) {
-			struct sk_buff *nskb;
-
-			nskb = napi_alloc_skb(&priv->napi, len);
-			if (!nskb) {
+			skb = napi_alloc_skb(&priv->napi, len);
+			if (unlikely(!skb)) {
 				/* forget packet, just rearm desc */
 				dev->stats.rx_dropped++;
 				continue;
@@ -382,14 +381,21 @@  static int bcm_enet_receive_queue(struct net_device *dev, int budget)
 
 			dma_sync_single_for_cpu(kdev, desc->address,
 						len, DMA_FROM_DEVICE);
-			memcpy(nskb->data, skb->data, len);
+			memcpy(skb->data, buf + priv->rx_buf_offset, len);
 			dma_sync_single_for_device(kdev, desc->address,
 						   len, DMA_FROM_DEVICE);
-			skb = nskb;
 		} else {
-			dma_unmap_single(&priv->pdev->dev, desc->address,
-					 priv->rx_skb_size, DMA_FROM_DEVICE);
-			priv->rx_skb[desc_idx] = NULL;
+			dma_unmap_single(kdev, desc->address,
+					 priv->rx_buf_size, DMA_FROM_DEVICE);
+			priv->rx_buf[desc_idx] = NULL;
+
+			skb = build_skb(buf, priv->rx_frag_size);
+			if (unlikely(!skb)) {
+				skb_free_frag(buf);
+				dev->stats.rx_dropped++;
+				continue;
+			}
+			skb_reserve(skb, priv->rx_buf_offset);
 		}
 
 		skb_put(skb, len);
@@ -403,7 +409,7 @@  static int bcm_enet_receive_queue(struct net_device *dev, int budget)
 	netif_receive_skb_list(&rx_list);
 
 	if (processed || !priv->rx_desc_count) {
-		bcm_enet_refill_rx(dev);
+		bcm_enet_refill_rx(dev, true);
 
 		/* kick rx dma */
 		enet_dmac_writel(priv, priv->dma_chan_en_mask,
@@ -862,6 +868,24 @@  static void bcm_enet_adjust_link(struct net_device *dev)
 		priv->pause_tx ? "tx" : "off");
 }
 
+static void bcm_enet_free_rx_buf_ring(struct device *kdev, struct bcm_enet_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->rx_ring_size; i++) {
+		struct bcm_enet_desc *desc;
+
+		if (!priv->rx_buf[i])
+			continue;
+
+		desc = &priv->rx_desc_cpu[i];
+		dma_unmap_single(kdev, desc->address, priv->rx_buf_size,
+				 DMA_FROM_DEVICE);
+		skb_free_frag(priv->rx_buf[i]);
+	}
+	kfree(priv->rx_buf);
+}
+
 /*
  * open callback, allocate dma rings & buffers and start rx operation
  */
@@ -971,10 +995,10 @@  static int bcm_enet_open(struct net_device *dev)
 	priv->tx_curr_desc = 0;
 	spin_lock_init(&priv->tx_lock);
 
-	/* init & fill rx ring with skbs */
-	priv->rx_skb = kcalloc(priv->rx_ring_size, sizeof(struct sk_buff *),
+	/* init & fill rx ring with buffers */
+	priv->rx_buf = kcalloc(priv->rx_ring_size, sizeof(void *),
 			       GFP_KERNEL);
-	if (!priv->rx_skb) {
+	if (!priv->rx_buf) {
 		ret = -ENOMEM;
 		goto out_free_tx_skb;
 	}
@@ -991,7 +1015,7 @@  static int bcm_enet_open(struct net_device *dev)
 		enet_dmac_writel(priv, ENETDMA_BUFALLOC_FORCE_MASK | 0,
 				ENETDMAC_BUFALLOC, priv->rx_chan);
 
-	if (bcm_enet_refill_rx(dev)) {
+	if (bcm_enet_refill_rx(dev, false)) {
 		dev_err(kdev, "cannot allocate rx skb queue\n");
 		ret = -ENOMEM;
 		goto out;
@@ -1086,18 +1110,7 @@  static int bcm_enet_open(struct net_device *dev)
 	return 0;
 
 out:
-	for (i = 0; i < priv->rx_ring_size; i++) {
-		struct bcm_enet_desc *desc;
-
-		if (!priv->rx_skb[i])
-			continue;
-
-		desc = &priv->rx_desc_cpu[i];
-		dma_unmap_single(kdev, desc->address, priv->rx_skb_size,
-				 DMA_FROM_DEVICE);
-		kfree_skb(priv->rx_skb[i]);
-	}
-	kfree(priv->rx_skb);
+	bcm_enet_free_rx_buf_ring(kdev, priv);
 
 out_free_tx_skb:
 	kfree(priv->tx_skb);
@@ -1176,7 +1189,6 @@  static int bcm_enet_stop(struct net_device *dev)
 {
 	struct bcm_enet_priv *priv;
 	struct device *kdev;
-	int i;
 
 	priv = netdev_priv(dev);
 	kdev = &priv->pdev->dev;
@@ -1204,21 +1216,10 @@  static int bcm_enet_stop(struct net_device *dev)
 	/* force reclaim of all tx buffers */
 	bcm_enet_tx_reclaim(dev, 1);
 
-	/* free the rx skb ring */
-	for (i = 0; i < priv->rx_ring_size; i++) {
-		struct bcm_enet_desc *desc;
-
-		if (!priv->rx_skb[i])
-			continue;
-
-		desc = &priv->rx_desc_cpu[i];
-		dma_unmap_single(kdev, desc->address, priv->rx_skb_size,
-				 DMA_FROM_DEVICE);
-		kfree_skb(priv->rx_skb[i]);
-	}
+	/* free the rx buffer ring */
+	bcm_enet_free_rx_buf_ring(kdev, priv);
 
 	/* free remaining allocated memory */
-	kfree(priv->rx_skb);
 	kfree(priv->tx_skb);
 	dma_free_coherent(kdev, priv->rx_desc_alloc_size,
 			  priv->rx_desc_cpu, priv->rx_desc_dma);
@@ -1640,9 +1641,12 @@  static int bcm_enet_change_mtu(struct net_device *dev, int new_mtu)
 	 * align rx buffer size to dma burst len, account FCS since
 	 * it's appended
 	 */
-	priv->rx_skb_size = ALIGN(actual_mtu + ETH_FCS_LEN,
+	priv->rx_buf_size = ALIGN(actual_mtu + ETH_FCS_LEN,
 				  priv->dma_maxburst * 4);
 
+	priv->rx_frag_size = SKB_DATA_ALIGN(priv->rx_buf_offset + priv->rx_buf_size)
+						+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
 	dev->mtu = new_mtu;
 	return 0;
 }
@@ -1727,6 +1731,7 @@  static int bcm_enet_probe(struct platform_device *pdev)
 
 	priv->enet_is_sw = false;
 	priv->dma_maxburst = BCMENET_DMA_MAXBURST;
+	priv->rx_buf_offset = NET_SKB_PAD;
 
 	ret = bcm_enet_change_mtu(dev, dev->mtu);
 	if (ret)
@@ -2154,10 +2159,10 @@  static int bcm_enetsw_open(struct net_device *dev)
 	priv->tx_curr_desc = 0;
 	spin_lock_init(&priv->tx_lock);
 
-	/* init & fill rx ring with skbs */
-	priv->rx_skb = kcalloc(priv->rx_ring_size, sizeof(struct sk_buff *),
+	/* init & fill rx ring with buffers */
+	priv->rx_buf = kcalloc(priv->rx_ring_size, sizeof(void *),
 			       GFP_KERNEL);
-	if (!priv->rx_skb) {
+	if (!priv->rx_buf) {
 		dev_err(kdev, "cannot allocate rx skb queue\n");
 		ret = -ENOMEM;
 		goto out_free_tx_skb;
@@ -2205,7 +2210,7 @@  static int bcm_enetsw_open(struct net_device *dev)
 	enet_dma_writel(priv, ENETDMA_BUFALLOC_FORCE_MASK | 0,
 			ENETDMA_BUFALLOC_REG(priv->rx_chan));
 
-	if (bcm_enet_refill_rx(dev)) {
+	if (bcm_enet_refill_rx(dev, false)) {
 		dev_err(kdev, "cannot allocate rx skb queue\n");
 		ret = -ENOMEM;
 		goto out;
@@ -2305,18 +2310,7 @@  static int bcm_enetsw_open(struct net_device *dev)
 	return 0;
 
 out:
-	for (i = 0; i < priv->rx_ring_size; i++) {
-		struct bcm_enet_desc *desc;
-
-		if (!priv->rx_skb[i])
-			continue;
-
-		desc = &priv->rx_desc_cpu[i];
-		dma_unmap_single(kdev, desc->address, priv->rx_skb_size,
-				 DMA_FROM_DEVICE);
-		kfree_skb(priv->rx_skb[i]);
-	}
-	kfree(priv->rx_skb);
+	bcm_enet_free_rx_buf_ring(kdev, priv);
 
 out_free_tx_skb:
 	kfree(priv->tx_skb);
@@ -2345,7 +2339,6 @@  static int bcm_enetsw_stop(struct net_device *dev)
 {
 	struct bcm_enet_priv *priv;
 	struct device *kdev;
-	int i;
 
 	priv = netdev_priv(dev);
 	kdev = &priv->pdev->dev;
@@ -2367,21 +2360,10 @@  static int bcm_enetsw_stop(struct net_device *dev)
 	/* force reclaim of all tx buffers */
 	bcm_enet_tx_reclaim(dev, 1);
 
-	/* free the rx skb ring */
-	for (i = 0; i < priv->rx_ring_size; i++) {
-		struct bcm_enet_desc *desc;
-
-		if (!priv->rx_skb[i])
-			continue;
-
-		desc = &priv->rx_desc_cpu[i];
-		dma_unmap_single(kdev, desc->address, priv->rx_skb_size,
-				 DMA_FROM_DEVICE);
-		kfree_skb(priv->rx_skb[i]);
-	}
+	/* free the rx buffer ring */
+	bcm_enet_free_rx_buf_ring(kdev, priv);
 
 	/* free remaining allocated memory */
-	kfree(priv->rx_skb);
 	kfree(priv->tx_skb);
 	dma_free_coherent(kdev, priv->rx_desc_alloc_size,
 			  priv->rx_desc_cpu, priv->rx_desc_dma);
@@ -2678,6 +2660,7 @@  static int bcm_enetsw_probe(struct platform_device *pdev)
 	priv->rx_ring_size = BCMENET_DEF_RX_DESC;
 	priv->tx_ring_size = BCMENET_DEF_TX_DESC;
 	priv->dma_maxburst = BCMENETSW_DMA_MAXBURST;
+	priv->rx_buf_offset = NET_SKB_PAD + NET_IP_ALIGN;
 
 	pd = dev_get_platdata(&pdev->dev);
 	if (pd) {
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.h b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
index 1d3c917eb830..78f1830fb3cb 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.h
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.h
@@ -230,11 +230,17 @@  struct bcm_enet_priv {
 	/* next dirty rx descriptor to refill */
 	int rx_dirty_desc;
 
-	/* size of allocated rx skbs */
-	unsigned int rx_skb_size;
+	/* size of allocated rx buffers */
+	unsigned int rx_buf_size;
 
-	/* list of skb given to hw for rx */
-	struct sk_buff **rx_skb;
+	/* allocated rx buffer offset */
+	unsigned int rx_buf_offset;
+
+	/* size of allocated rx frag */
+	unsigned int rx_frag_size;
+
+	/* list of buffer given to hw for rx */
+	void **rx_buf;
 
 	/* used when rx skb allocation failed, so we defer rx queue
 	 * refill */