Skip to contentSkip to conversation

via-velocity: Enable scatter/gather IO by default

PATCH Applied Simon Kagstrom 2 participants 5 messages Feb 11, 2010 – Feb 18, 2010

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 via-velocity: Enable scatter/gather IO by default

Reduces CPU utilization significantly with sendfile for example.

---
Also good to have if Krishnas tcp_sendmsg optimizations,

http://patchwork.ozlabs.org/patch/42944/

get merged.

 drivers/net/via-velocity.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)
drivers/net/via-velocity.c +1 -1
index 317aa34..18770ac 100644
@@ -2825,7 +2825,7 @@ static int __devinit velocity_found1(struct pci_dev *pdev, const struct pci_devi
 	netif_napi_add(dev, &vptr->napi, velocity_poll, VELOCITY_NAPI_WEIGHT);
 
 	dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER |
-		NETIF_F_HW_VLAN_RX | NETIF_F_IP_CSUM;
+		NETIF_F_HW_VLAN_RX | NETIF_F_IP_CSUM | NETIF_F_SG;
 
 	ret = register_netdev(dev);
 	if (ret < 0)
Signature · 1 line
1.6.0.4
maintainer
#1 lore raw

From: Simon Kagstrom <[email protected]>
Date: Thu, 11 Feb 2010 16:39:55 +0100

Quoted 3 lines

Reduces CPU utilization significantly with sendfile for example.

I think you need to have a look at this patch before making a change like this:

commit 83c98a8cd04dd0f848574370594886ba3bf56750

Author: Dave Jones <[email protected]>
Date:   Tue Jul 21 09:15:49 2009 +0000

Remove unused zero-copy code from velocity NIC driver.

This code hasn't been enabled in forever.

drivers/net/via-velocity.c +11 -66
index 42365e5..4ebe2ca 100644
@@ -976,9 +976,6 @@ static int __devinit velocity_found1(struct pci_dev *pdev, const struct pci_devi
 	dev->netdev_ops = &velocity_netdev_ops;
 	dev->ethtool_ops = &velocity_ethtool_ops;
 
-#ifdef  VELOCITY_ZERO_COPY_SUPPORT
-	dev->features |= NETIF_F_SG;
-#endif
 	dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER |
 		NETIF_F_HW_VLAN_RX;
 
@@ -1849,11 +1846,7 @@ static void velocity_free_tx_buf(struct velocity_info *vptr, struct velocity_td_
 
 		pktlen = max_t(unsigned int, skb->len, ETH_ZLEN);
 		for (i = 0; i < tdinfo->nskb_dma; i++) {
-#ifdef VELOCITY_ZERO_COPY_SUPPORT
-			pci_unmap_single(vptr->pdev, tdinfo->skb_dma[i], le16_to_cpu(td->tdesc1.len), PCI_DMA_TODEVICE);
-#else
 			pci_unmap_single(vptr->pdev, tdinfo->skb_dma[i], pktlen, PCI_DMA_TODEVICE);
-#endif
 			tdinfo->skb_dma[i] = 0;
 		}
 	}
@@ -2095,13 +2088,6 @@ static int velocity_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	len = cpu_to_le16(pktlen);
 
-#ifdef VELOCITY_ZERO_COPY_SUPPORT
-	if (skb_shinfo(skb)->nr_frags > 6 && __skb_linearize(skb)) {
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-#endif
-
 	spin_lock_irqsave(&vptr->lock, flags);
 
 	index = vptr->tx.curr[qnum];
@@ -2111,59 +2097,18 @@ static int velocity_xmit(struct sk_buff *skb, struct net_device *dev)
 	td_ptr->tdesc1.TCR = TCR0_TIC;
 	td_ptr->td_buf[0].size &= ~TD_QUEUE;
 
-#ifdef VELOCITY_ZERO_COPY_SUPPORT
-	if (skb_shinfo(skb)->nr_frags > 0) {
-		int nfrags = skb_shinfo(skb)->nr_frags;
-		tdinfo->skb = skb;
-		if (nfrags > 6) {
-			skb_copy_from_linear_data(skb, tdinfo->buf, skb->len);
-			tdinfo->skb_dma[0] = tdinfo->buf_dma;
-			td_ptr->tdesc0.len = len;
-			td_ptr->tx.buf[0].pa_low = cpu_to_le32(tdinfo->skb_dma[0]);
-			td_ptr->tx.buf[0].pa_high = 0;
-			td_ptr->tx.buf[0].size = len;	/* queue is 0 anyway */
-			tdinfo->nskb_dma = 1;
-		} else {
-			int i = 0;
-			tdinfo->nskb_dma = 0;
-			tdinfo->skb_dma[i] = pci_map_single(vptr->pdev, skb->data,
-						skb_headlen(skb), PCI_DMA_TODEVICE);
-
-			td_ptr->tdesc0.len = len;
-
-			/* FIXME: support 48bit DMA later */
-			td_ptr->tx.buf[i].pa_low = cpu_to_le32(tdinfo->skb_dma);
-			td_ptr->tx.buf[i].pa_high = 0;
-			td_ptr->tx.buf[i].size = cpu_to_le16(skb_headlen(skb));
-
-			for (i = 0; i < nfrags; i++) {
-				skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-				void *addr = (void *)page_address(frag->page) + frag->page_offset;
-
-				tdinfo->skb_dma[i + 1] = pci_map_single(vptr->pdev, addr, frag->size, PCI_DMA_TODEVICE);
-
-				td_ptr->tx.buf[i + 1].pa_low = cpu_to_le32(tdinfo->skb_dma[i + 1]);
-				td_ptr->tx.buf[i + 1].pa_high = 0;
-				td_ptr->tx.buf[i + 1].size = cpu_to_le16(frag->size);
-			}
-			tdinfo->nskb_dma = i - 1;
-		}
+	/*
+	 *	Map the linear network buffer into PCI space and
+	 *	add it to the transmit ring.
+	 */
+	tdinfo->skb = skb;
+	tdinfo->skb_dma[0] = pci_map_single(vptr->pdev, skb->data, pktlen, PCI_DMA_TODEVICE);
+	td_ptr->tdesc0.len = len;
+	td_ptr->td_buf[0].pa_low = cpu_to_le32(tdinfo->skb_dma[0]);
+	td_ptr->td_buf[0].pa_high = 0;
+	td_ptr->td_buf[0].size = len;
+	tdinfo->nskb_dma = 1;
 
-	} else
-#endif
-	{
-		/*
-		 *	Map the linear network buffer into PCI space and
-		 *	add it to the transmit ring.
-		 */
-		tdinfo->skb = skb;
-		tdinfo->skb_dma[0] = pci_map_single(vptr->pdev, skb->data, pktlen, PCI_DMA_TODEVICE);
-		td_ptr->tdesc0.len = len;
-		td_ptr->td_buf[0].pa_low = cpu_to_le32(tdinfo->skb_dma[0]);
-		td_ptr->td_buf[0].pa_high = 0;
-		td_ptr->td_buf[0].size = len;
-		tdinfo->nskb_dma = 1;
-	}
 	td_ptr->tdesc1.cmd = TCPLS_NORMAL + (tdinfo->nskb_dma + 1) * 16;
 
 	if (vptr->vlgrp && vlan_tx_tag_present(skb)) {
#2 lore raw
Quoted 7 lines · On Tue, 16 Feb 2010 16:20:15 -0800 (PST) David Miller <[email protected]>…
Quoted 3 lines

Reduces CPU utilization significantly with sendfile for example.

I think you need to have a look at this patch before making a change like this:

Quoted 7 lines

commit 83c98a8cd04dd0f848574370594886ba3bf56750

Author: Dave Jones <[email protected]>
Date:   Tue Jul 21 09:15:49 2009 +0000

Remove unused zero-copy code from velocity NIC driver.

This code hasn't been enabled in forever.

Well I reenabled it here:

http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=c79992fddee28bbd31b35ac297e1068d32930179

it was also cleaned up to remove all the #ifdefs around that code.

// Simon