[PATCH 1/2] net: Add layer 2 hardware acceleration operations for macvlan devices
From: Neil Horman <nhorman@tuxdriver.com>
Date: 2013-10-11 18:44:18
Subsystem:
networking drivers, networking [general], tc subsystem, the rest · Maintainers:
Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Jamal Hadi Salim, Jiri Pirko, Linus Torvalds
Add a operations structure that allows a network interface to export the fact that it supports package forwarding in hardware between physical interfaces and other mac layer devices assigned to it (such as macvlans). this operaions structure can be used by virtual mac devices to bypass software switching so that forwarding can be done in hardware more efficiently. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> CC: john.fastabend@gmail.com CC: Andy Gospodarek <andy@greyhouse.net> CC: "David S. Miller" <davem@davemloft.net> --- drivers/net/macvlan.c | 31 +++++++++++++++++++++++++++++++ include/linux/if_macvlan.h | 1 + include/linux/netdev_features.h | 2 ++ include/linux/netdevice.h | 11 ++++++++++- include/linux/skbuff.h | 4 ++-- net/core/dev.c | 18 +++++++++++++----- net/core/ethtool.c | 1 + net/sched/sch_generic.c | 2 +- 8 files changed, 61 insertions(+), 9 deletions(-)
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 9bf46bd..c5a2718 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c@@ -297,7 +297,16 @@ netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, int ret; const struct macvlan_dev *vlan = netdev_priv(dev); + if (vlan->fwd_priv) { + skb->dev = vlan->lowerdev; + ret = dev_hard_start_xmit(skb, skb->dev, NULL, vlan->fwd_priv); + + if (likely(ret == NETDEV_TX_OK)) + goto update_stats; + } + ret = macvlan_queue_xmit(skb, dev); +update_stats: if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct macvlan_pcpu_stats *pcpu_stats;
@@ -347,6 +356,18 @@ static int macvlan_open(struct net_device *dev) goto hash_add; } + if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) { + vlan->fwd_priv = lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); + /* + * If we get a NULL pointer back, or if we get an error + * then we should just fall through to the non accelerated path + */ + if (IS_ERR_OR_NULL(vlan->fwd_priv)) + vlan->fwd_priv = NULL; + else + return 0; + } + err = -EBUSY; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out;
@@ -367,6 +388,10 @@ hash_add: del_unicast: dev_uc_del(lowerdev, dev->dev_addr); out: + if (vlan->fwd_priv) { + lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->fwd_priv); + vlan->fwd_priv = NULL; + } return err; }
@@ -391,6 +416,11 @@ static int macvlan_stop(struct net_device *dev) hash_del: macvlan_hash_del(vlan, !dev->dismantle); + if (vlan->fwd_priv) { + lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->fwd_priv); + vlan->fwd_priv = NULL; + } + return 0; }
@@ -801,6 +831,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; } + port = macvlan_port_get_rtnl(lowerdev); /* Only 1 macvlan device can be created in passthru mode */
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index ddd33fd..c270285 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h@@ -61,6 +61,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; + void *fwd_priv; struct macvlan_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ);
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index a2a89a5..9d1ee76 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h@@ -60,6 +60,7 @@ enum { NETIF_F_HW_VLAN_STAG_TX_BIT, /* Transmit VLAN STAG HW acceleration */ NETIF_F_HW_VLAN_STAG_RX_BIT, /* Receive VLAN STAG HW acceleration */ NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ + NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ /* * Add your fresh new feature above and remember to update
@@ -112,6 +113,7 @@ enum { #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) #define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) +#define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3de49ac..0249179 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h@@ -1097,6 +1097,13 @@ struct net_device_ops { void (*ndo_del_vxlan_port)(struct net_device *dev, sa_family_t sa_family, __be16 port); + + void* (*ndo_dfwd_add_station)(struct net_device *pdev, + struct net_device *vdev); + void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); + + netdev_tx_t (*ndo_dfwd_start_xmit) (struct sk_buff *skb, + struct net_device *dev, void *priv); }; /*
@@ -1183,6 +1190,7 @@ struct net_device { /* Management operations */ const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; + const struct forwarding_accel_ops *fwd_ops; /* Hardware header description */ const struct header_ops *header_ops;
@@ -2383,7 +2391,8 @@ extern int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_port_id *ppid); extern int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq); + struct netdev_queue *txq, + void *accel_priv); extern int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2ddb48d..1710fdb 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h@@ -426,9 +426,9 @@ struct sk_buff { char cb[48] __aligned(8); unsigned long _skb_refdst; -#ifdef CONFIG_XFRM + struct sec_path *sp; -#endif + unsigned int len, data_len; __u16 mac_len,
diff --git a/net/core/dev.c b/net/core/dev.c
index 5c713f2..ecad8c2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c@@ -2536,7 +2536,7 @@ static inline int skb_needs_linearize(struct sk_buff *skb, } int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq) + struct netdev_queue *txq, void *accel_priv) { const struct net_device_ops *ops = dev->netdev_ops; int rc = NETDEV_TX_OK;
@@ -2602,9 +2602,13 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, dev_queue_xmit_nit(skb, dev); skb_len = skb->len; - rc = ops->ndo_start_xmit(skb, dev); + if (accel_priv) + rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv); + else + rc = ops->ndo_start_xmit(skb, dev); + trace_net_dev_xmit(skb, rc, dev, skb_len); - if (rc == NETDEV_TX_OK) + if (rc == NETDEV_TX_OK && txq) txq_trans_update(txq); return rc; }
@@ -2620,7 +2624,10 @@ gso: dev_queue_xmit_nit(nskb, dev); skb_len = nskb->len; - rc = ops->ndo_start_xmit(nskb, dev); + if (accel_priv) + rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv); + else + rc = ops->ndo_start_xmit(nskb, dev); trace_net_dev_xmit(nskb, rc, dev, skb_len); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK)
@@ -2645,6 +2652,7 @@ out_kfree_skb: out: return rc; } +EXPORT_SYMBOL_GPL(dev_hard_start_xmit); static void qdisc_pkt_len_init(struct sk_buff *skb) {
@@ -2852,7 +2860,7 @@ int dev_queue_xmit(struct sk_buff *skb) if (!netif_xmit_stopped(txq)) { __this_cpu_inc(xmit_recursion); - rc = dev_hard_start_xmit(skb, dev, txq); + rc = dev_hard_start_xmit(skb, dev, txq, NULL); __this_cpu_dec(xmit_recursion); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 78e9d92..9f0c599b 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c@@ -94,6 +94,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_LOOPBACK_BIT] = "loopback", [NETIF_F_RXFCS_BIT] = "rx-fcs", [NETIF_F_RXALL_BIT] = "rx-all", + [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", }; static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index e7121d2..8c44b1b 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c@@ -126,7 +126,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) - ret = dev_hard_start_xmit(skb, dev, txq); + ret = dev_hard_start_xmit(skb, dev, txq, NULL); HARD_TX_UNLOCK(dev, txq);
--
1.8.3.1