From 10b3ad8c21bb4b135768c30dd4c51a1c744da699 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 29 Aug 2014 21:07:24 -0700 Subject: [PATCH 1/9] net: Do txq_trans_update() in netdev_start_xmit() That way we don't have to audit every call site to make sure it is doing this properly. Signed-off-by: David S. Miller --- drivers/net/wan/dlci.c | 6 ++++-- include/linux/netdevice.h | 10 ++++++++-- net/core/dev.c | 7 ++----- net/core/netpoll.c | 4 +--- net/core/pktgen.c | 3 +-- net/packet/af_packet.c | 7 ++----- net/sched/sch_teql.c | 3 +-- 7 files changed, 19 insertions(+), 21 deletions(-) diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 81b22a180aad..6427e8283419 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -192,8 +192,10 @@ static netdev_tx_t dlci_transmit(struct sk_buff *skb, struct net_device *dev) { struct dlci_local *dlp = netdev_priv(dev); - if (skb) - netdev_start_xmit(skb, dlp->slave); + if (skb) { + struct netdev_queue *txq = skb_get_tx_queue(dev, skb); + netdev_start_xmit(skb, dlp->slave, txq); + } return NETDEV_TX_OK; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 456eb1fe51e8..16171802ea7d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3437,11 +3437,17 @@ static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, return ops->ndo_start_xmit(skb, dev); } -static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev) +static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq) { const struct net_device_ops *ops = dev->netdev_ops; + int rc; - return __netdev_start_xmit(ops, skb, dev); + rc = __netdev_start_xmit(ops, skb, dev); + if (rc == NETDEV_TX_OK) + txq_trans_update(txq); + + return rc; } int netdev_class_create_file_ns(struct class_attribute *class_attr, diff --git a/net/core/dev.c b/net/core/dev.c index a6077ef56345..6392adaaa22f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2666,10 +2666,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb_len = skb->len; trace_net_dev_start_xmit(skb, dev); - rc = netdev_start_xmit(skb, dev); + rc = netdev_start_xmit(skb, dev, txq); trace_net_dev_xmit(skb, rc, dev, skb_len); - if (rc == NETDEV_TX_OK) - txq_trans_update(txq); return rc; } @@ -2685,7 +2683,7 @@ gso: skb_len = nskb->len; trace_net_dev_start_xmit(nskb, dev); - rc = netdev_start_xmit(nskb, dev); + rc = netdev_start_xmit(nskb, dev, txq); trace_net_dev_xmit(nskb, rc, dev, skb_len); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) @@ -2694,7 +2692,6 @@ gso: skb->next = nskb; return rc; } - txq_trans_update(txq); if (unlikely(netif_xmit_stopped(txq) && skb->next)) return NETDEV_TX_BUSY; } while (skb->next); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 12b1df976562..05bc57edaa81 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -91,9 +91,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, skb->vlan_tci = 0; } - status = netdev_start_xmit(skb, dev); - if (status == NETDEV_TX_OK) - txq_trans_update(txq); + status = netdev_start_xmit(skb, dev, txq); out: return status; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index d81b540096c3..34bd2ff9f121 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3335,11 +3335,10 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) goto unlock; } atomic_inc(&(pkt_dev->skb->users)); - ret = netdev_start_xmit(pkt_dev->skb, odev); + ret = netdev_start_xmit(pkt_dev->skb, odev, txq); switch (ret) { case NETDEV_TX_OK: - txq_trans_update(txq); pkt_dev->last_ok = 1; pkt_dev->sofar++; pkt_dev->seq_num++; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b7a7f5a721bd..fe305a05a8fc 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -258,11 +258,8 @@ static int packet_direct_xmit(struct sk_buff *skb) local_bh_disable(); HARD_TX_LOCK(dev, txq, smp_processor_id()); - if (!netif_xmit_frozen_or_drv_stopped(txq)) { - ret = netdev_start_xmit(skb, dev); - if (ret == NETDEV_TX_OK) - txq_trans_update(txq); - } + if (!netif_xmit_frozen_or_drv_stopped(txq)) + ret = netdev_start_xmit(skb, dev, txq); HARD_TX_UNLOCK(dev, txq); local_bh_enable(); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 64cd93ca8104..193dc2cba1ec 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -316,8 +316,7 @@ restart: unsigned int length = qdisc_pkt_len(skb); if (!netif_xmit_frozen_or_stopped(slave_txq) && - netdev_start_xmit(skb, slave) == NETDEV_TX_OK) { - txq_trans_update(slave_txq); + netdev_start_xmit(skb, slave, slave_txq) == NETDEV_TX_OK) { __netif_tx_unlock(slave_txq); master->slaves = NEXT_SLAVE(q); netif_wake_queue(dev); From 2ea255137555052655c6a646c4e48ea7481494c7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 29 Aug 2014 21:10:01 -0700 Subject: [PATCH 2/9] net: Create xmit_one() helper for dev_hard_start_xmit() Hopefully making the code a bit easier to read and digest. Signed-off-by: David S. Miller --- net/core/dev.c | 35 +++++++++++++++++++---------------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 6392adaaa22f..0fde7d2153db 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2599,11 +2599,27 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) } EXPORT_SYMBOL(netif_skb_features); +static int xmit_one(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq) +{ + unsigned int len; + int rc; + + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(skb, dev); + + len = skb->len; + trace_net_dev_start_xmit(skb, dev); + rc = netdev_start_xmit(skb, dev, txq); + trace_net_dev_xmit(skb, rc, dev, len); + + return rc; +} + int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { int rc = NETDEV_TX_OK; - unsigned int skb_len; if (likely(!skb->next)) { netdev_features_t features; @@ -2661,14 +2677,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, } } - if (!list_empty(&ptype_all)) - dev_queue_xmit_nit(skb, dev); - - skb_len = skb->len; - trace_net_dev_start_xmit(skb, dev); - rc = netdev_start_xmit(skb, dev, txq); - trace_net_dev_xmit(skb, rc, dev, skb_len); - return rc; + return xmit_one(skb, dev, txq); } gso: @@ -2678,13 +2687,7 @@ gso: skb->next = nskb->next; nskb->next = NULL; - if (!list_empty(&ptype_all)) - dev_queue_xmit_nit(nskb, dev); - - skb_len = nskb->len; - trace_net_dev_start_xmit(nskb, dev); - rc = netdev_start_xmit(nskb, dev, txq); - trace_net_dev_xmit(nskb, rc, dev, skb_len); + rc = xmit_one(nskb, dev, txq); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) goto out_kfree_gso_skb; From 7f2e870f2a48a0524a3b03b04fa019311d16a7f7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 29 Aug 2014 21:19:14 -0700 Subject: [PATCH 3/9] net: Move main gso loop out of dev_hard_start_xmit() into helper. There is a slight policy change happening here as well. The previous code would drop the entire rest of the GSO skb if any of them got, for example, a congestion notification. That makes no sense, anything NET_XMIT_MASK and below is something like congestion or policing. And in the congestion case it doesn't even mean the packet was actually dropped. Just continue until dev_xmit_complete() evaluates to false. Signed-off-by: David S. Miller --- net/core/dev.c | 48 +++++++++++++++++++++++++++++------------------- 1 file changed, 29 insertions(+), 19 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 0fde7d2153db..ab7bb809711e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2616,6 +2616,34 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, return rc; } +static struct sk_buff *xmit_list(struct sk_buff *first, struct net_device *dev, + struct netdev_queue *txq, int *ret) +{ + struct sk_buff *skb = first; + int rc = NETDEV_TX_OK; + + while (skb) { + struct sk_buff *next = skb->next; + + skb->next = NULL; + rc = xmit_one(skb, dev, txq); + if (unlikely(!dev_xmit_complete(rc))) { + skb->next = next; + goto out; + } + + skb = next; + if (netif_xmit_stopped(txq) && skb) { + rc = NETDEV_TX_BUSY; + break; + } + } + +out: + *ret = rc; + return skb; +} + int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { @@ -2681,25 +2709,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, } gso: - do { - struct sk_buff *nskb = skb->next; - - skb->next = nskb->next; - nskb->next = NULL; - - rc = xmit_one(nskb, dev, txq); - if (unlikely(rc != NETDEV_TX_OK)) { - if (rc & ~NETDEV_TX_MASK) - goto out_kfree_gso_skb; - nskb->next = skb->next; - skb->next = nskb; - return rc; - } - if (unlikely(netif_xmit_stopped(txq) && skb->next)) - return NETDEV_TX_BUSY; - } while (skb->next); - -out_kfree_gso_skb: + skb->next = xmit_list(skb->next, dev, txq, &rc); if (likely(skb->next == NULL)) { skb->destructor = DEV_GSO_CB(skb)->destructor; consume_skb(skb); From fa2dbdc253c2aee2a760c64de454cb62469ec11d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 29 Aug 2014 21:55:22 -0700 Subject: [PATCH 4/9] net: Pass a "more" indication down into netdev_start_xmit() code paths. For now it will always be false. Signed-off-by: David S. Miller --- drivers/net/wan/dlci.c | 2 +- include/linux/netdevice.h | 9 +++++---- net/atm/mpc.c | 2 +- net/core/dev.c | 2 +- net/core/netpoll.c | 2 +- net/core/pktgen.c | 2 +- net/packet/af_packet.c | 2 +- net/sched/sch_teql.c | 3 ++- 8 files changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 6427e8283419..ae6ecf401189 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -194,7 +194,7 @@ static netdev_tx_t dlci_transmit(struct sk_buff *skb, struct net_device *dev) if (skb) { struct netdev_queue *txq = skb_get_tx_queue(dev, skb); - netdev_start_xmit(skb, dlp->slave, txq); + netdev_start_xmit(skb, dlp->slave, txq, false); } return NETDEV_TX_OK; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 16171802ea7d..5050218c5b7f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3431,19 +3431,20 @@ int __init dev_proc_init(void); #endif static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, - struct sk_buff *skb, struct net_device *dev) + struct sk_buff *skb, struct net_device *dev, + bool more) { - skb->xmit_more = 0; + skb->xmit_more = more ? 1 : 0; return ops->ndo_start_xmit(skb, dev); } static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq) + struct netdev_queue *txq, bool more) { const struct net_device_ops *ops = dev->netdev_ops; int rc; - rc = __netdev_start_xmit(ops, skb, dev); + rc = __netdev_start_xmit(ops, skb, dev, more); if (rc == NETDEV_TX_OK) txq_trans_update(txq); diff --git a/net/atm/mpc.c b/net/atm/mpc.c index d662da161e5a..0e982222d425 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -599,7 +599,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb, } non_ip: - return __netdev_start_xmit(mpc->old_ops, skb, dev); + return __netdev_start_xmit(mpc->old_ops, skb, dev, false); } static int atm_mpoa_vcc_attach(struct atm_vcc *vcc, void __user *arg) diff --git a/net/core/dev.c b/net/core/dev.c index ab7bb809711e..f0ed5a611a97 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2610,7 +2610,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, len = skb->len; trace_net_dev_start_xmit(skb, dev); - rc = netdev_start_xmit(skb, dev, txq); + rc = netdev_start_xmit(skb, dev, txq, false); trace_net_dev_xmit(skb, rc, dev, len); return rc; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 05bc57edaa81..e6645b4f330a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -91,7 +91,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, skb->vlan_tci = 0; } - status = netdev_start_xmit(skb, dev, txq); + status = netdev_start_xmit(skb, dev, txq, false); out: return status; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 34bd2ff9f121..5b36a9428c59 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3335,7 +3335,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) goto unlock; } atomic_inc(&(pkt_dev->skb->users)); - ret = netdev_start_xmit(pkt_dev->skb, odev, txq); + ret = netdev_start_xmit(pkt_dev->skb, odev, txq, false); switch (ret) { case NETDEV_TX_OK: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index fe305a05a8fc..87d20f48ff06 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -259,7 +259,7 @@ static int packet_direct_xmit(struct sk_buff *skb) HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) - ret = netdev_start_xmit(skb, dev, txq); + ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); local_bh_enable(); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 193dc2cba1ec..aaa8d03ed054 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -316,7 +316,8 @@ restart: unsigned int length = qdisc_pkt_len(skb); if (!netif_xmit_frozen_or_stopped(slave_txq) && - netdev_start_xmit(skb, slave, slave_txq) == NETDEV_TX_OK) { + netdev_start_xmit(skb, slave, slave_txq, false) == + NETDEV_TX_OK) { __netif_tx_unlock(slave_txq); master->slaves = NEXT_SLAVE(q); netif_wake_queue(dev); From 95f6b3dda2a4a052f7dabe9998e4ffac491b7bc2 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 29 Aug 2014 21:57:30 -0700 Subject: [PATCH 5/9] net: Have xmit_list() signal more==true when appropriate. Signed-off-by: David S. Miller --- net/core/dev.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index f0ed5a611a97..6d82194e414b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2600,7 +2600,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) EXPORT_SYMBOL(netif_skb_features); static int xmit_one(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq) + struct netdev_queue *txq, bool more) { unsigned int len; int rc; @@ -2610,7 +2610,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, len = skb->len; trace_net_dev_start_xmit(skb, dev); - rc = netdev_start_xmit(skb, dev, txq, false); + rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); return rc; @@ -2626,7 +2626,7 @@ static struct sk_buff *xmit_list(struct sk_buff *first, struct net_device *dev, struct sk_buff *next = skb->next; skb->next = NULL; - rc = xmit_one(skb, dev, txq); + rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; goto out; @@ -2705,7 +2705,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, } } - return xmit_one(skb, dev, txq); + return xmit_one(skb, dev, txq, false); } gso: From eae3f88ee44251bcca3a085f9565257c6f9f9e69 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 30 Aug 2014 15:17:13 -0700 Subject: [PATCH 6/9] net: Separate out SKB validation logic from transmit path. dev_hard_start_xmit() does two things, it first validates and canonicalizes the SKB, then it actually sends it. Make a set of helper functions for doing the first part. Signed-off-by: David S. Miller --- net/core/dev.c | 135 ++++++++++++++++++++++++++++--------------------- 1 file changed, 76 insertions(+), 59 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 6d82194e414b..704a5434f77d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2644,80 +2644,97 @@ out: return skb; } +struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) +{ + if (vlan_tx_tag_present(skb) && + !vlan_hw_offload_capable(features, skb->vlan_proto)) { + skb = __vlan_put_tag(skb, skb->vlan_proto, + vlan_tx_tag_get(skb)); + if (skb) + skb->vlan_tci = 0; + } + return skb; +} + +static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) +{ + netdev_features_t features; + + if (skb->next) + return skb; + + /* If device doesn't need skb->dst, release it right now while + * its hot in this cpu cache + */ + if (dev->priv_flags & IFF_XMIT_DST_RELEASE) + skb_dst_drop(skb); + + features = netif_skb_features(skb); + skb = validate_xmit_vlan(skb, features); + if (unlikely(!skb)) + goto out_null; + + /* If encapsulation offload request, verify we are testing + * hardware encapsulation features instead of standard + * features for the netdev + */ + if (skb->encapsulation) + features &= dev->hw_enc_features; + + if (netif_needs_gso(skb, features)) { + if (unlikely(dev_gso_segment(skb, features))) + goto out_kfree_skb; + } else { + if (skb_needs_linearize(skb, features) && + __skb_linearize(skb)) + goto out_kfree_skb; + + /* If packet is not checksummed and device does not + * support checksumming for this protocol, complete + * checksumming here. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (skb->encapsulation) + skb_set_inner_transport_header(skb, + skb_checksum_start_offset(skb)); + else + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); + if (!(features & NETIF_F_ALL_CSUM) && + skb_checksum_help(skb)) + goto out_kfree_skb; + } + } + + return skb; + +out_kfree_skb: + kfree_skb(skb); +out_null: + return NULL; +} + int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { int rc = NETDEV_TX_OK; - if (likely(!skb->next)) { - netdev_features_t features; - - /* - * If device doesn't need skb->dst, release it right now while - * its hot in this cpu cache - */ - if (dev->priv_flags & IFF_XMIT_DST_RELEASE) - skb_dst_drop(skb); - - features = netif_skb_features(skb); - - if (vlan_tx_tag_present(skb) && - !vlan_hw_offload_capable(features, skb->vlan_proto)) { - skb = __vlan_put_tag(skb, skb->vlan_proto, - vlan_tx_tag_get(skb)); - if (unlikely(!skb)) - goto out; - - skb->vlan_tci = 0; - } - - /* If encapsulation offload request, verify we are testing - * hardware encapsulation features instead of standard - * features for the netdev - */ - if (skb->encapsulation) - features &= dev->hw_enc_features; - - if (netif_needs_gso(skb, features)) { - if (unlikely(dev_gso_segment(skb, features))) - goto out_kfree_skb; - if (skb->next) - goto gso; - } else { - if (skb_needs_linearize(skb, features) && - __skb_linearize(skb)) - goto out_kfree_skb; - - /* If packet is not checksummed and device does not - * support checksumming for this protocol, complete - * checksumming here. - */ - if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (skb->encapsulation) - skb_set_inner_transport_header(skb, - skb_checksum_start_offset(skb)); - else - skb_set_transport_header(skb, - skb_checksum_start_offset(skb)); - if (!(features & NETIF_F_ALL_CSUM) && - skb_checksum_help(skb)) - goto out_kfree_skb; - } - } + skb = validate_xmit_skb(skb, dev); + if (!skb) + return rc; + if (likely(!skb->next)) return xmit_one(skb, dev, txq, false); - } -gso: skb->next = xmit_list(skb->next, dev, txq, &rc); if (likely(skb->next == NULL)) { skb->destructor = DEV_GSO_CB(skb)->destructor; consume_skb(skb); return rc; } -out_kfree_skb: + kfree_skb(skb); -out: + return rc; } EXPORT_SYMBOL_GPL(dev_hard_start_xmit); From 50cbe9ab5f8d92d2d4a327b56e96559d8f63a1fa Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 30 Aug 2014 19:13:51 -0700 Subject: [PATCH 7/9] net: Validate xmit SKBs right when we pull them out of the qdisc. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 6 +----- net/sched/sch_generic.c | 5 ++++- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5050218c5b7f..47c49ba2dcf4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2827,6 +2827,7 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *); int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_port_id *ppid); +struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index 704a5434f77d..75bc5b068a13 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2656,7 +2656,7 @@ struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t featur return skb; } -static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) +struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) { netdev_features_t features; @@ -2719,10 +2719,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, { int rc = NETDEV_TX_OK; - skb = validate_xmit_skb(skb, dev); - if (!skb) - return rc; - if (likely(!skb->next)) return xmit_one(skb, dev, txq, false); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 05b3f5d104af..f178798a5836 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -70,8 +70,11 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q) } else skb = NULL; } else { - if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) + if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) { skb = q->dequeue(q); + if (skb) + skb = validate_xmit_skb(skb, qdisc_dev(q)); + } } return skb; From ce93718fb7cdbc064c3000ff59e4d3200bdfa744 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 30 Aug 2014 19:22:20 -0700 Subject: [PATCH 8/9] net: Don't keep around original SKB when we software segment GSO frames. Just maintain the list properly by returning the head of the remaining SKB list from dev_hard_start_xmit(). Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +- net/core/dev.c | 79 +++++++-------------------------------- net/sched/sch_generic.c | 2 +- 3 files changed, 17 insertions(+), 68 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 47c49ba2dcf4..202c25a9aadf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2828,8 +2828,8 @@ int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_port_id *ppid); struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev); -int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq); +struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq, int *ret); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index 75bc5b068a13..c89da4f306b1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2485,52 +2485,6 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) return 0; } -struct dev_gso_cb { - void (*destructor)(struct sk_buff *skb); -}; - -#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb) - -static void dev_gso_skb_destructor(struct sk_buff *skb) -{ - struct dev_gso_cb *cb; - - kfree_skb_list(skb->next); - skb->next = NULL; - - cb = DEV_GSO_CB(skb); - if (cb->destructor) - cb->destructor(skb); -} - -/** - * dev_gso_segment - Perform emulated hardware segmentation on skb. - * @skb: buffer to segment - * @features: device features as applicable to this skb - * - * This function segments the given skb and stores the list of segments - * in skb->next. - */ -static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) -{ - struct sk_buff *segs; - - segs = skb_gso_segment(skb, features); - - /* Verifying header integrity only. */ - if (!segs) - return 0; - - if (IS_ERR(segs)) - return PTR_ERR(segs); - - skb->next = segs; - DEV_GSO_CB(skb)->destructor = skb->destructor; - skb->destructor = dev_gso_skb_destructor; - - return 0; -} - /* If MPLS offload request, verify we are testing hardware MPLS features * instead of standard features for the netdev. */ @@ -2682,8 +2636,13 @@ struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) features &= dev->hw_enc_features; if (netif_needs_gso(skb, features)) { - if (unlikely(dev_gso_segment(skb, features))) - goto out_kfree_skb; + struct sk_buff *segs; + + segs = skb_gso_segment(skb, features); + kfree_skb(skb); + if (IS_ERR(segs)) + segs = NULL; + skb = segs; } else { if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) @@ -2714,26 +2673,16 @@ out_null: return NULL; } -int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq) +struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq, int *ret) { - int rc = NETDEV_TX_OK; - - if (likely(!skb->next)) - return xmit_one(skb, dev, txq, false); - - skb->next = xmit_list(skb->next, dev, txq, &rc); - if (likely(skb->next == NULL)) { - skb->destructor = DEV_GSO_CB(skb)->destructor; - consume_skb(skb); - return rc; + if (likely(!skb->next)) { + *ret = xmit_one(skb, dev, txq, false); + return skb; } - kfree_skb(skb); - - return rc; + return xmit_list(skb, dev, txq, ret); } -EXPORT_SYMBOL_GPL(dev_hard_start_xmit); static void qdisc_pkt_len_init(struct sk_buff *skb) { @@ -2945,7 +2894,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) if (!netif_xmit_stopped(txq)) { __this_cpu_inc(xmit_recursion); - rc = dev_hard_start_xmit(skb, dev, txq); + skb = dev_hard_start_xmit(skb, dev, txq, &rc); __this_cpu_dec(xmit_recursion); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index f178798a5836..a8bf9f9928bd 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -129,7 +129,7 @@ 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); + skb = dev_hard_start_xmit(skb, dev, txq, &ret); HARD_TX_UNLOCK(dev, txq); From 8dcda22a5d0abaf347b21b057655f3809b91639d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 1 Sep 2014 15:06:40 -0700 Subject: [PATCH 9/9] net: xmit_list() becomes dev_hard_start_xmit(). Now fundamentally we can process lists of SKBs as cheaply as single packets. Signed-off-by: David S. Miller --- net/core/dev.c | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index c89da4f306b1..6857d57aa294 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2570,8 +2570,8 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, return rc; } -static struct sk_buff *xmit_list(struct sk_buff *first, struct net_device *dev, - struct netdev_queue *txq, int *ret) +struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev, + struct netdev_queue *txq, int *ret) { struct sk_buff *skb = first; int rc = NETDEV_TX_OK; @@ -2673,17 +2673,6 @@ out_null: return NULL; } -struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq, int *ret) -{ - if (likely(!skb->next)) { - *ret = xmit_one(skb, dev, txq, false); - return skb; - } - - return xmit_list(skb, dev, txq, ret); -} - static void qdisc_pkt_len_init(struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb);