Merge branch 'rx_copybreak'

Govindarajulu Varadarajan says:

====================
enic: Add support for rx_copybreak

The following series implements rx_copybreak.

dma_map_single()/dma_unmap_single() is more expensive than alloc_skb & memcpy
for smaller packets. By doing this we can reuse the dma buff which is already
mapped. This is very useful when iommu is on. The default skb copybreak value
is 256.

When iommu is on, we can go much higher than 256. All the drivers that supports
rx_copybreak provides module parameter to change this value. Since module
parameter is the least preferred way for changing driver values, this series
adds ethtool support for setting rx_copybreak.

v4:
Validate tunable length in ethtool_get_tunable, not in driver implemented
function.

Loose tunable_ops array for each tunable type. Define one function and let the
driver use switch case for each type.

Use double underscore for data type in UAPI headers.
Use const qualifier where possible.

v3:
Add tunable namespace to ethtool. Use new ethtool cmd ETHTOOL_S/GTUNABLE to
set/get rx_copybreak from userspace.

v2:
Add new ethtool_cmd for DMA buffer parameters, instead of adding new members to
existing ethtool_ringparam.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/cisco/enic/enic.h

@@ -186,6 +186,7 @@ struct enic {
 	____cacheline_aligned struct vnic_cq cq[ENIC_CQ_MAX];
 	unsigned int cq_count;
 	struct enic_rfs_flw_tbl rfs_h;
+	u32 rx_copybreak;
 };
 
 static inline struct device *enic_get_dev(struct enic *enic)

drivers/net/ethernet/cisco/enic/enic_ethtool.c

@@ -379,6 +379,43 @@ static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	return ret;
 }
 
+static int enic_get_tunable(struct net_device *dev,
+			    const struct ethtool_tunable *tuna, void *data)
+{
+	struct enic *enic = netdev_priv(dev);
+	int ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)data = enic->rx_copybreak;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int enic_set_tunable(struct net_device *dev,
+			    const struct ethtool_tunable *tuna,
+			    const void *data)
+{
+	struct enic *enic = netdev_priv(dev);
+	int ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		enic->rx_copybreak = *(u32 *)data;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 static const struct ethtool_ops enic_ethtool_ops = {
 	.get_settings = enic_get_settings,
 	.get_drvinfo = enic_get_drvinfo,
@@ -391,6 +428,8 @@ static const struct ethtool_ops enic_ethtool_ops = {
 	.get_coalesce = enic_get_coalesce,
 	.set_coalesce = enic_set_coalesce,
 	.get_rxnfc = enic_get_rxnfc,
+	.get_tunable = enic_get_tunable,
+	.set_tunable = enic_set_tunable,
 };
 
 void enic_set_ethtool_ops(struct net_device *netdev)

drivers/net/ethernet/cisco/enic/enic_main.c

@@ -66,6 +66,8 @@
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_DYN     0x0044  /* enet dynamic vnic */
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_VF      0x0071  /* enet SRIOV VF */
 
+#define RX_COPYBREAK_DEFAULT		256
+
 /* Supported devices */
 static const struct pci_device_id enic_id_table[] = {
 	{ PCI_VDEVICE(CISCO, PCI_DEVICE_ID_CISCO_VIC_ENET) },
@@ -924,6 +926,7 @@ static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
 	pci_unmap_single(enic->pdev, buf->dma_addr,
 		buf->len, PCI_DMA_FROMDEVICE);
 	dev_kfree_skb_any(buf->os_buf);
+	buf->os_buf = NULL;
 }
 
 static int enic_rq_alloc_buf(struct vnic_rq *rq)
@@ -934,7 +937,24 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq)
 	unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
 	unsigned int os_buf_index = 0;
 	dma_addr_t dma_addr;
+	struct vnic_rq_buf *buf = rq->to_use;
+
+	if (buf->os_buf) {
+		buf = buf->next;
+		rq->to_use = buf;
+		rq->ring.desc_avail--;
+		if ((buf->index & VNIC_RQ_RETURN_RATE) == 0) {
+			/* Adding write memory barrier prevents compiler and/or
+			 * CPU reordering, thus avoiding descriptor posting
+			 * before descriptor is initialized. Otherwise, hardware
+			 * can read stale descriptor fields.
+			 */
+			wmb();
+			iowrite32(buf->index, &rq->ctrl->posted_index);
+		}
 
+		return 0;
+	}
 	skb = netdev_alloc_skb_ip_align(netdev, len);
 	if (!skb)
 		return -ENOMEM;
@@ -957,6 +977,25 @@ static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
 		pkt_size->small_pkt_bytes_cnt += pkt_len;
 }
 
+static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb,
+			     struct vnic_rq_buf *buf, u16 len)
+{
+	struct enic *enic = netdev_priv(netdev);
+	struct sk_buff *new_skb;
+
+	if (len > enic->rx_copybreak)
+		return false;
+	new_skb = netdev_alloc_skb_ip_align(netdev, len);
+	if (!new_skb)
+		return false;
+	pci_dma_sync_single_for_cpu(enic->pdev, buf->dma_addr, len,
+				    DMA_FROM_DEVICE);
+	memcpy(new_skb->data, (*skb)->data, len);
+	*skb = new_skb;
+
+	return true;
+}
+
 static void enic_rq_indicate_buf(struct vnic_rq *rq,
 	struct cq_desc *cq_desc, struct vnic_rq_buf *buf,
 	int skipped, void *opaque)
@@ -978,9 +1017,6 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 		return;
 
 	skb = buf->os_buf;
-	prefetch(skb->data - NET_IP_ALIGN);
-	pci_unmap_single(enic->pdev, buf->dma_addr,
-		buf->len, PCI_DMA_FROMDEVICE);
 
 	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc,
 		&type, &color, &q_number, &completed_index,
@@ -1011,6 +1047,13 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 		/* Good receive
 		 */
 
+		if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) {
+			buf->os_buf = NULL;
+			pci_unmap_single(enic->pdev, buf->dma_addr, buf->len,
+					 PCI_DMA_FROMDEVICE);
+		}
+		prefetch(skb->data - NET_IP_ALIGN);
+
 		skb_put(skb, bytes_written);
 		skb->protocol = eth_type_trans(skb, netdev);
 		skb_record_rx_queue(skb, q_number);
@@ -2531,6 +2574,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(dev, "Cannot register net device, aborting\n");
 		goto err_out_dev_deinit;
 	}
+	enic->rx_copybreak = RX_COPYBREAK_DEFAULT;
 
 	return 0;
 

include/linux/ethtool.h

@@ -257,6 +257,10 @@ struct ethtool_ops {
 				     struct ethtool_eeprom *, u8 *);
 	int	(*get_eee)(struct net_device *, struct ethtool_eee *);
 	int	(*set_eee)(struct net_device *, struct ethtool_eee *);
+	int	(*get_tunable)(struct net_device *,
+			       const struct ethtool_tunable *, void *);
+	int	(*set_tunable)(struct net_device *,
+			       const struct ethtool_tunable *, const void *);
 
 
 };

include/uapi/linux/ethtool.h

@@ -209,6 +209,32 @@ struct ethtool_value {
 	__u32	data;
 };
 
+enum tunable_id {
+	ETHTOOL_ID_UNSPEC,
+	ETHTOOL_RX_COPYBREAK,
+};
+
+enum tunable_type_id {
+	ETHTOOL_TUNABLE_UNSPEC,
+	ETHTOOL_TUNABLE_U8,
+	ETHTOOL_TUNABLE_U16,
+	ETHTOOL_TUNABLE_U32,
+	ETHTOOL_TUNABLE_U64,
+	ETHTOOL_TUNABLE_STRING,
+	ETHTOOL_TUNABLE_S8,
+	ETHTOOL_TUNABLE_S16,
+	ETHTOOL_TUNABLE_S32,
+	ETHTOOL_TUNABLE_S64,
+};
+
+struct ethtool_tunable {
+	__u32	cmd;
+	__u32	id;
+	__u32	type_id;
+	__u32	len;
+	void	*data[0];
+};
+
 /**
  * struct ethtool_regs - hardware register dump
  * @cmd: Command number = %ETHTOOL_GREGS
@@ -1152,6 +1178,8 @@ enum ethtool_sfeatures_retval_bits {
 
 #define ETHTOOL_GRSSH		0x00000046 /* Get RX flow hash configuration */
 #define ETHTOOL_SRSSH		0x00000047 /* Set RX flow hash configuration */
+#define ETHTOOL_GTUNABLE	0x00000048 /* Get tunable configuration */
+#define ETHTOOL_STUNABLE	0x00000049 /* Set tunable configuration */
 
 /* compatibility with older code */
 #define SPARC_ETH_GSET		ETHTOOL_GSET

net/core/ethtool.c

@@ -1621,6 +1621,80 @@ static int ethtool_get_module_eeprom(struct net_device *dev,
 				      modinfo.eeprom_len);
 }
 
+static int ethtool_tunable_valid(const struct ethtool_tunable *tuna)
+{
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		if (tuna->len != sizeof(u32) ||
+		    tuna->type_id != ETHTOOL_TUNABLE_U32)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr)
+{
+	int ret;
+	struct ethtool_tunable tuna;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	void *data;
+
+	if (!ops->get_tunable)
+		return -EOPNOTSUPP;
+	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
+		return -EFAULT;
+	ret = ethtool_tunable_valid(&tuna);
+	if (ret)
+		return ret;
+	data = kmalloc(tuna.len, GFP_USER);
+	if (!data)
+		return -ENOMEM;
+	ret = ops->get_tunable(dev, &tuna, data);
+	if (ret)
+		goto out;
+	useraddr += sizeof(tuna);
+	ret = -EFAULT;
+	if (copy_to_user(useraddr, data, tuna.len))
+		goto out;
+	ret = 0;
+
+out:
+	kfree(data);
+	return ret;
+}
+
+static int ethtool_set_tunable(struct net_device *dev, void __user *useraddr)
+{
+	int ret;
+	struct ethtool_tunable tuna;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	void *data;
+
+	if (!ops->set_tunable)
+		return -EOPNOTSUPP;
+	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
+		return -EFAULT;
+	ret = ethtool_tunable_valid(&tuna);
+	if (ret)
+		return ret;
+	data = kmalloc(tuna.len, GFP_USER);
+	if (!data)
+		return -ENOMEM;
+	useraddr += sizeof(tuna);
+	ret = -EFAULT;
+	if (copy_from_user(data, useraddr, tuna.len))
+		goto out;
+	ret = ops->set_tunable(dev, &tuna, data);
+
+out:
+	kfree(data);
+	return ret;
+}
+
 /* The main entry point in this file.  Called from net/core/dev_ioctl.c */
 
 int dev_ethtool(struct net *net, struct ifreq *ifr)
@@ -1670,6 +1744,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GCHANNELS:
 	case ETHTOOL_GET_TS_INFO:
 	case ETHTOOL_GEEE:
+	case ETHTOOL_GTUNABLE:
 		break;
 	default:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -1857,6 +1932,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GMODULEEEPROM:
 		rc = ethtool_get_module_eeprom(dev, useraddr);
 		break;
+	case ETHTOOL_GTUNABLE:
+		rc = ethtool_get_tunable(dev, useraddr);
+		break;
+	case ETHTOOL_STUNABLE:
+		rc = ethtool_set_tunable(dev, useraddr);
+		break;
 	default:
 		rc = -EOPNOTSUPP;
 	}