From 3d48b53fb2ae37158e700ffef3f45461ff15c965 Mon Sep 17 00:00:00 2001 From: Matthias Tafelmeier Date: Thu, 29 Dec 2016 21:37:21 +0100 Subject: net: dev_weight: TX/RX orthogonality Oftenly, introducing side effects on packet processing on the other half of the stack by adjusting one of TX/RX via sysctl is not desirable. There are cases of demand for asymmetric, orthogonal configurability. This holds true especially for nodes where RPS for RFS usage on top is configured and therefore use the 'old dev_weight'. This is quite a common base configuration setup nowadays, even with NICs of superior processing support (e.g. aRFS). A good example use case are nodes acting as noSQL data bases with a large number of tiny requests and rather fewer but large packets as responses. It's affordable to have large budget and rx dev_weights for the requests. But as a side effect having this large a number on TX processed in one run can overwhelm drivers. This patch therefore introduces an independent configurability via sysctl to userland. Signed-off-by: Matthias Tafelmeier Signed-off-by: David S. Miller --- net/core/dev.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 8db5a0b4b520..56818f7eab2b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3427,7 +3427,11 @@ EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; -int weight_p __read_mostly = 64; /* old backlog weight */ +int weight_p __read_mostly = 64; /* old backlog weight */ +int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ +int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ +int dev_rx_weight __read_mostly = 64; +int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -4833,7 +4837,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = weight_p; + napi->weight = dev_rx_weight; while (again) { struct sk_buff *skb; -- cgit From e7246e122aaa99ebbb8ad7da80f35a20577bd8af Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:35 -0500 Subject: net-tc: extract skip classify bit from tc_verd Packets sent by the IFB device skip subsequent tc classification. A single bit governs this state. Move it out of tc_verd in anticipation of removing that __u16 completely. The new bitfield tc_skip_classify temporarily uses one bit of a hole, until tc_verd is removed completely in a follow-up patch. Remove the bit hole comment. It could be 2, 3, 4 or 5 bits long. With that many options, little value in documenting it. Introduce a helper function to deduplicate the logic in the two sites that check this bit. The field tc_skip_classify is set only in IFB on skbs cloned in act_mirred, so original packet sources do not have to clear the bit when reusing packets (notably, pktgen and octeon). Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- drivers/net/ifb.c | 2 +- include/linux/skbuff.h | 5 ++++- include/net/sch_generic.h | 11 +++++++++++ include/uapi/linux/pkt_cls.h | 6 ------ net/core/dev.c | 10 +++------- net/sched/act_api.c | 11 ++++------- 6 files changed, 23 insertions(+), 22 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 082534e187fc..442c4c4a9606 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -81,7 +81,7 @@ static void ifb_ri_tasklet(unsigned long _txp) u32 from = G_TC_FROM(skb->tc_verd); skb->tc_verd = 0; - skb->tc_verd = SET_TC_NCLS(skb->tc_verd); + skb->tc_skip_classify = 1; u64_stats_update_begin(&txp->tsync); txp->tx_packets++; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b53c0cfd417e..570f60ec6cb4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -589,6 +589,7 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @tc_skip_classify: do not classify packet. set by IFB device * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -749,7 +750,9 @@ struct sk_buff { #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; #endif - /* 2, 4 or 5 bit hole */ +#ifdef CONFIG_NET_CLS_ACT + __u8 tc_skip_classify:1; +#endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 498f81b229a4..857356f2d74b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -418,6 +418,17 @@ static inline bool skb_at_tc_ingress(const struct sk_buff *skb) #endif } +static inline bool skb_skip_tc_classify(struct sk_buff *skb) +{ +#ifdef CONFIG_NET_CLS_ACT + if (skb->tc_skip_classify) { + skb->tc_skip_classify = 0; + return true; + } +#endif + return false; +} + /* Reset all TX qdiscs greater then index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index bba23dbb3ab6..1eed5d7509bc 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -22,8 +22,6 @@ bit 6,7: Where this packet was last seen 1: on the Ingress 2: on the Egress -bit 8: when set --> Request not to classify on ingress. - * * */ @@ -36,10 +34,6 @@ bit 8: when set --> Request not to classify on ingress. #define AT_INGRESS 0x1 #define AT_EGRESS 0x2 -#define TC_NCLS _TC_MAKEMASK1(8) -#define SET_TC_NCLS(v) ( TC_NCLS | (v & ~TC_NCLS)) -#define CLR_TC_NCLS(v) ( v & ~TC_NCLS) - #define S_TC_AT _TC_MAKE32(12) #define M_TC_AT _TC_MAKEMASK(2,S_TC_AT) #define G_TC_AT(x) _TC_GETVALUE(x,S_TC_AT,M_TC_AT) diff --git a/net/core/dev.c b/net/core/dev.c index 56818f7eab2b..e39e35d2e082 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4093,12 +4093,8 @@ another_round: goto out; } -#ifdef CONFIG_NET_CLS_ACT - if (skb->tc_verd & TC_NCLS) { - skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); - goto ncls; - } -#endif + if (skb_skip_tc_classify(skb)) + goto skip_classify; if (pfmemalloc) goto skip_taps; @@ -4128,8 +4124,8 @@ skip_taps: #endif #ifdef CONFIG_NET_CLS_ACT skb->tc_verd = 0; -ncls: #endif +skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2095c83ce773..f04715a57300 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -426,11 +426,9 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, { int ret = -1, i; - if (skb->tc_verd & TC_NCLS) { - skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); - ret = TC_ACT_OK; - goto exec_done; - } + if (skb_skip_tc_classify(skb)) + return TC_ACT_OK; + for (i = 0; i < nr_actions; i++) { const struct tc_action *a = actions[i]; @@ -439,9 +437,8 @@ repeat: if (ret == TC_ACT_REPEAT) goto repeat; /* we need a ttl - JHS */ if (ret != TC_ACT_PIPE) - goto exec_done; + break; } -exec_done: return ret; } EXPORT_SYMBOL(tcf_action_exec); -- cgit From a5135bcfba7345031df45e02cd150a45add47cf8 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:36 -0500 Subject: net-tc: convert tc_verd to integer bitfields Extract the remaining two fields from tc_verd and remove the __u16 completely. TC_AT and TC_FROM are converted to equivalent two-bit integer fields tc_at and tc_from. Where possible, use existing helper skb_at_tc_ingress when reading tc_at. Introduce helper skb_reset_tc to clear fields. Not documenting tc_from and tc_at, because they will be replaced with single bit fields in follow-on patches. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- drivers/net/ifb.c | 7 +++---- drivers/staging/octeon/ethernet-tx.c | 5 ++--- include/linux/skbuff.h | 6 ++---- include/net/sch_generic.h | 10 +++++++++- include/uapi/linux/pkt_cls.h | 31 ------------------------------- net/core/dev.c | 10 ++++------ net/core/pktgen.c | 4 +--- net/core/skbuff.c | 3 --- net/sched/act_ife.c | 7 +++---- net/sched/act_mirred.c | 9 ++++----- net/sched/sch_netem.c | 2 +- 11 files changed, 29 insertions(+), 65 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 442c4c4a9606..b73b6b6c066b 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -78,9 +78,9 @@ static void ifb_ri_tasklet(unsigned long _txp) } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { - u32 from = G_TC_FROM(skb->tc_verd); + u32 from = skb->tc_from; - skb->tc_verd = 0; + skb_reset_tc(skb); skb->tc_skip_classify = 1; u64_stats_update_begin(&txp->tsync); @@ -239,7 +239,6 @@ static void ifb_setup(struct net_device *dev) static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ifb_dev_private *dp = netdev_priv(dev); - u32 from = G_TC_FROM(skb->tc_verd); struct ifb_q_private *txp = dp->tx_private + skb_get_queue_mapping(skb); u64_stats_update_begin(&txp->rsync); @@ -247,7 +246,7 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) txp->rx_bytes += skb->len; u64_stats_update_end(&txp->rsync); - if (!(from & (AT_INGRESS|AT_EGRESS)) || !skb->skb_iif) { + if (skb->tc_from == AT_STACK || !skb->skb_iif) { dev_kfree_skb(skb); dev->stats.rx_dropped++; return NETDEV_TX_OK; diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c index 6b4c20872323..0b8053205091 100644 --- a/drivers/staging/octeon/ethernet-tx.c +++ b/drivers/staging/octeon/ethernet-tx.c @@ -23,6 +23,7 @@ #endif /* CONFIG_XFRM */ #include +#include #include @@ -369,9 +370,7 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) #ifdef CONFIG_NET_SCHED skb->tc_index = 0; -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; -#endif /* CONFIG_NET_CLS_ACT */ + skb_reset_tc(skb); #endif /* CONFIG_NET_SCHED */ #endif /* REUSE_SKBUFFS_WITHOUT_FREE */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 570f60ec6cb4..f738d09947b2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -599,7 +599,6 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index - * @tc_verd: traffic control verdict * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue @@ -752,13 +751,12 @@ struct sk_buff { #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; + __u8 tc_at:2; + __u8 tc_from:2; #endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ -#ifdef CONFIG_NET_CLS_ACT - __u16 tc_verd; /* traffic control verdict */ -#endif #endif union { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 857356f2d74b..f80dba516964 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -409,10 +409,18 @@ bool tcf_destroy(struct tcf_proto *tp, bool force); void tcf_destroy_chain(struct tcf_proto __rcu **fl); int skb_do_redirect(struct sk_buff *); +static inline void skb_reset_tc(struct sk_buff *skb) +{ +#ifdef CONFIG_NET_CLS_ACT + skb->tc_at = 0; + skb->tc_from = 0; +#endif +} + static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT - return G_TC_AT(skb->tc_verd) & AT_INGRESS; + return skb->tc_at & AT_INGRESS; #else return false; #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 1eed5d7509bc..cee753a7a40c 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -5,40 +5,9 @@ #include #ifdef __KERNEL__ -/* I think i could have done better macros ; for now this is stolen from - * some arch/mips code - jhs -*/ -#define _TC_MAKE32(x) ((x)) - -#define _TC_MAKEMASK1(n) (_TC_MAKE32(1) << _TC_MAKE32(n)) -#define _TC_MAKEMASK(v,n) (_TC_MAKE32((_TC_MAKE32(1)<<(v))-1) << _TC_MAKE32(n)) -#define _TC_MAKEVALUE(v,n) (_TC_MAKE32(v) << _TC_MAKE32(n)) -#define _TC_GETVALUE(v,n,m) ((_TC_MAKE32(v) & _TC_MAKE32(m)) >> _TC_MAKE32(n)) - -/* verdict bit breakdown - * -bit 6,7: Where this packet was last seen -0: Above the transmit example at the socket level -1: on the Ingress -2: on the Egress - - * - * */ - -#define S_TC_FROM _TC_MAKE32(6) -#define M_TC_FROM _TC_MAKEMASK(2,S_TC_FROM) -#define G_TC_FROM(x) _TC_GETVALUE(x,S_TC_FROM,M_TC_FROM) -#define V_TC_FROM(x) _TC_MAKEVALUE(x,S_TC_FROM) -#define SET_TC_FROM(v,n) ((V_TC_FROM(n)) | (v & ~M_TC_FROM)) #define AT_STACK 0x0 #define AT_INGRESS 0x1 #define AT_EGRESS 0x2 - -#define S_TC_AT _TC_MAKE32(12) -#define M_TC_AT _TC_MAKEMASK(2,S_TC_AT) -#define G_TC_AT(x) _TC_GETVALUE(x,S_TC_AT,M_TC_AT) -#define V_TC_AT(x) _TC_MAKEVALUE(x,S_TC_AT) -#define SET_TC_AT(v,n) ((V_TC_AT(n)) | (v & ~M_TC_AT)) #endif /* Action attributes */ diff --git a/net/core/dev.c b/net/core/dev.c index e39e35d2e082..8b5d6d033473 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3153,7 +3153,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) if (!cl) return skb; - /* skb->tc_verd and qdisc_skb_cb(skb)->pkt_len were already set + /* skb->tc_at and qdisc_skb_cb(skb)->pkt_len were already set * earlier by the caller. */ qdisc_bstats_cpu_update(cl->q, skb); @@ -3320,7 +3320,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); + skb->tc_at = AT_EGRESS; # ifdef CONFIG_NET_EGRESS if (static_key_false(&egress_needed)) { skb = sch_handle_egress(skb, &rc, dev); @@ -3920,7 +3920,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } qdisc_skb_cb(skb)->pkt_len = skb->len; - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); + skb->tc_at = AT_INGRESS; qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res, false)) { @@ -4122,9 +4122,7 @@ skip_taps: goto out; } #endif -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; -#endif + skb_reset_tc(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 8e69ce472236..96947f5d41e4 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3439,9 +3439,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) /* skb was 'freed' by stack, so clean few * bits and reuse it */ -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; /* reset reclass/redir ttl */ -#endif + skb_reset_tc(skb); } while (--burst > 0); goto out; /* Skips xmit_mode M_START_XMIT */ } else if (pkt_dev->xmit_mode == M_QUEUE_XMIT) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5a03730fbc1a..adec4bf807d8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -878,9 +878,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); -#ifdef CONFIG_NET_CLS_ACT - CHECK_SKB_FIELD(tc_verd); -#endif #endif } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 80b848d3f096..921fb20eaa7c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -736,12 +736,11 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, u16 metalen = ife_get_sz(skb, ife); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; unsigned int skboff = skb->dev->hard_header_len; - u32 at = G_TC_AT(skb->tc_verd); int new_len = skb->len + hdrm; bool exceed_mtu = false; int err; - if (at & AT_EGRESS) { + if (!skb_at_tc_ingress(skb)) { if (new_len > skb->dev->mtu) exceed_mtu = true; } @@ -773,7 +772,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, return TC_ACT_SHOT; } - if (!(at & AT_EGRESS)) + if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); iethh = (struct ethhdr *)skb->data; @@ -816,7 +815,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, ether_addr_copy(oethh->h_dest, iethh->h_dest); oethh->h_proto = htons(ife->eth_type); - if (!(at & AT_EGRESS)) + if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); spin_unlock(&ife->tcf_lock); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 2d9fa6e0a1b4..8543279bba49 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -170,7 +170,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, int retval, err = 0; int m_eaction; int mac_len; - u32 at; tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); @@ -191,7 +190,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, goto out; } - at = G_TC_AT(skb->tc_verd); skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) goto out; @@ -200,8 +198,9 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, * and devices expect a mac header on xmit, then mac push/pull is * needed. */ - if (at != tcf_mirred_act_direction(m_eaction) && m_mac_header_xmit) { - if (at & AT_EGRESS) { + if (skb->tc_at != tcf_mirred_act_direction(m_eaction) && + m_mac_header_xmit) { + if (!skb_at_tc_ingress(skb)) { /* caught at egress, act ingress: pull mac */ mac_len = skb_network_header(skb) - skb_mac_header(skb); skb_pull_rcsum(skb2, mac_len); @@ -213,7 +212,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, /* mirror is always swallowed */ if (tcf_mirred_is_act_redirect(m_eaction)) - skb2->tc_verd = SET_TC_FROM(skb2->tc_verd, at); + skb2->tc_from = skb2->tc_at; skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index bcfadfdea8e0..bb5c638b6852 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -626,7 +626,7 @@ deliver: * If it's at ingress let's pretend the delay is * from the network (tstamp will be updated). */ - if (G_TC_FROM(skb->tc_verd) & AT_INGRESS) + if (skb->tc_from & AT_INGRESS) skb->tstamp = 0; #endif -- cgit From 8dc07fdbf2054f157e8333f940a1ad728916c786 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:37 -0500 Subject: net-tc: convert tc_at to tc_at_ingress Field tc_at is used only within tc actions to distinguish ingress from egress processing. A single bit is sufficient for this purpose. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- include/net/sch_generic.h | 3 +-- net/core/dev.c | 8 +++----- net/sched/act_mirred.c | 12 ++++++------ 4 files changed, 12 insertions(+), 14 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f738d09947b2..fab3f87e9bd1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -590,6 +590,7 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @tc_skip_classify: do not classify packet. set by IFB device + * @tc_at_ingress: used within tc_classify to distinguish in/egress * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -751,7 +752,7 @@ struct sk_buff { #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; - __u8 tc_at:2; + __u8 tc_at_ingress:1; __u8 tc_from:2; #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f80dba516964..4bd6d5387209 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -412,7 +412,6 @@ int skb_do_redirect(struct sk_buff *); static inline void skb_reset_tc(struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT - skb->tc_at = 0; skb->tc_from = 0; #endif } @@ -420,7 +419,7 @@ static inline void skb_reset_tc(struct sk_buff *skb) static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT - return skb->tc_at & AT_INGRESS; + return skb->tc_at_ingress; #else return false; #endif diff --git a/net/core/dev.c b/net/core/dev.c index 8b5d6d033473..c143f1391117 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3153,9 +3153,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) if (!cl) return skb; - /* skb->tc_at and qdisc_skb_cb(skb)->pkt_len were already set - * earlier by the caller. - */ + /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res, false)) { @@ -3320,7 +3318,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT - skb->tc_at = AT_EGRESS; + skb->tc_at_ingress = 0; # ifdef CONFIG_NET_EGRESS if (static_key_false(&egress_needed)) { skb = sch_handle_egress(skb, &rc, dev); @@ -3920,7 +3918,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } qdisc_skb_cb(skb)->pkt_len = skb->len; - skb->tc_at = AT_INGRESS; + skb->tc_at_ingress = 1; qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res, false)) { diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 8543279bba49..e832c62fd705 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -39,15 +39,15 @@ static bool tcf_mirred_is_act_redirect(int action) return action == TCA_EGRESS_REDIR || action == TCA_INGRESS_REDIR; } -static u32 tcf_mirred_act_direction(int action) +static bool tcf_mirred_act_wants_ingress(int action) { switch (action) { case TCA_EGRESS_REDIR: case TCA_EGRESS_MIRROR: - return AT_EGRESS; + return false; case TCA_INGRESS_REDIR: case TCA_INGRESS_MIRROR: - return AT_INGRESS; + return true; default: BUG(); } @@ -198,7 +198,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, * and devices expect a mac header on xmit, then mac push/pull is * needed. */ - if (skb->tc_at != tcf_mirred_act_direction(m_eaction) && + if (skb_at_tc_ingress(skb) != tcf_mirred_act_wants_ingress(m_eaction) && m_mac_header_xmit) { if (!skb_at_tc_ingress(skb)) { /* caught at egress, act ingress: pull mac */ @@ -212,11 +212,11 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, /* mirror is always swallowed */ if (tcf_mirred_is_act_redirect(m_eaction)) - skb2->tc_from = skb2->tc_at; + skb2->tc_from = skb_at_tc_ingress(skb) ? AT_INGRESS : AT_EGRESS; skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; - if (tcf_mirred_act_direction(m_eaction) & AT_EGRESS) + if (!tcf_mirred_act_wants_ingress(m_eaction)) err = dev_queue_xmit(skb2); else err = netif_receive_skb(skb2); -- cgit From 738b35ccee1bcd7cf4af147edd76e7880533ad9f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 11 Jan 2017 21:13:02 -0800 Subject: net: core: Make netif_wake_subqueue a wrapper netif_wake_subqueue() is duplicating the same thing that netif_tx_wake_queue() does, so make it call it directly after looking up the queue from the index. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 +++++++++++++- net/core/dev.c | 22 ---------------------- 2 files changed, 13 insertions(+), 23 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ebd9e2c12f44..97ae0ac513ee 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3106,7 +3106,19 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev, return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } -void netif_wake_subqueue(struct net_device *dev, u16 queue_index); +/** + * netif_wake_subqueue - allow sending packets on subqueue + * @dev: network device + * @queue_index: sub queue index + * + * Resume individual transmit queue of a device with multiple transmit queues. + */ +static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) +{ + struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); + + netif_tx_wake_queue(txq); +} #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, diff --git a/net/core/dev.c b/net/core/dev.c index e98cc06d2577..ad5959e56116 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2408,28 +2408,6 @@ void netif_schedule_queue(struct netdev_queue *txq) } EXPORT_SYMBOL(netif_schedule_queue); -/** - * netif_wake_subqueue - allow sending packets on subqueue - * @dev: network device - * @queue_index: sub queue index - * - * Resume individual transmit queue of a device with multiple transmit queues. - */ -void netif_wake_subqueue(struct net_device *dev, u16 queue_index) -{ - struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); - - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) { - struct Qdisc *q; - - rcu_read_lock(); - q = rcu_dereference(txq->qdisc); - __netif_schedule(q); - rcu_read_unlock(); - } -} -EXPORT_SYMBOL(netif_wake_subqueue); - void netif_tx_wake_queue(struct netdev_queue *dev_queue) { if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { -- cgit From 1b7cd0044e4a9f69aaf00511870b07fcdeda591d Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 18 Jan 2017 15:02:49 -0800 Subject: net: remove duplicate code. netdev_rx_handler_register() checks to see if the handler is already busy which was recently separated into netdev_is_rx_handler_busy(). So use the same function inside register() to avoid code duplication. Essentially this change should be a no-op Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- net/core/dev.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index ad5959e56116..c8f1f67ff16c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3961,9 +3961,7 @@ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data) { - ASSERT_RTNL(); - - if (dev->rx_handler) + if (netdev_is_rx_handler_busy(dev)) return -EBUSY; /* Note: rx_handler_data must be set before rx_handler */ -- cgit From f991bb9da142ba79b54ed0757f22e756f45e2c5a Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 30 Jan 2017 06:45:38 +0100 Subject: net: Drop secpath on free after gro merge. With a followup patch, a gro merged skb can have a secpath. So drop it before freeing or reusing the skb. Signed-off-by: Steffen Klassert --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 56818f7eab2b..ef3a969477bf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4623,6 +4623,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { skb_dst_drop(skb); + secpath_reset(skb); kmem_cache_free(skbuff_head_cache, skb); } else { __kfree_skb(skb); @@ -4663,6 +4664,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); + secpath_reset(skb); napi->skb = skb; } -- cgit From b2504a5dbef3305ef41988ad270b0e8ec289331c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 31 Jan 2017 10:20:32 -0800 Subject: net: reduce skb_warn_bad_offload() noise Dmitry reported warnings occurring in __skb_gso_segment() [1] All SKB_GSO_DODGY producers can allow user space to feed packets that trigger the current check. We could prevent them from doing so, rejecting packets, but this might add regressions to existing programs. It turns out our SKB_GSO_DODGY handlers properly set up checksum information that is needed anyway when packets needs to be segmented. By checking again skb_needs_check() after skb_mac_gso_segment(), we should remove these pesky warnings, at a very minor cost. With help from Willem de Bruijn [1] WARNING: CPU: 1 PID: 6768 at net/core/dev.c:2439 skb_warn_bad_offload+0x2af/0x390 net/core/dev.c:2434 lo: caps=(0x000000a2803b7c69, 0x0000000000000000) len=138 data_len=0 gso_size=15883 gso_type=4 ip_summed=0 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 6768 Comm: syz-executor1 Not tainted 4.9.0 #5 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ffff8801c063ecd8 ffffffff82346bdf ffffffff00000001 1ffff100380c7d2e ffffed00380c7d26 0000000041b58ab3 ffffffff84b37e38 ffffffff823468f1 ffffffff84820740 ffffffff84f289c0 dffffc0000000000 ffff8801c063ee20 Call Trace: [] __dump_stack lib/dump_stack.c:15 [inline] [] dump_stack+0x2ee/0x3ef lib/dump_stack.c:51 [] panic+0x1fb/0x412 kernel/panic.c:179 [] __warn+0x1c4/0x1e0 kernel/panic.c:542 [] warn_slowpath_fmt+0xc5/0x100 kernel/panic.c:565 [] skb_warn_bad_offload+0x2af/0x390 net/core/dev.c:2434 [] __skb_gso_segment+0x482/0x780 net/core/dev.c:2706 [] skb_gso_segment include/linux/netdevice.h:3985 [inline] [] validate_xmit_skb+0x5c9/0xc20 net/core/dev.c:2969 [] __dev_queue_xmit+0xe6b/0x1e70 net/core/dev.c:3383 [] dev_queue_xmit+0x17/0x20 net/core/dev.c:3424 [] packet_snd net/packet/af_packet.c:2930 [inline] [] packet_sendmsg+0x32ed/0x4d30 net/packet/af_packet.c:2955 [] sock_sendmsg_nosec net/socket.c:621 [inline] [] sock_sendmsg+0xca/0x110 net/socket.c:631 [] ___sys_sendmsg+0x8fa/0x9f0 net/socket.c:1954 [] __sys_sendmsg+0x138/0x300 net/socket.c:1988 [] SYSC_sendmsg net/socket.c:1999 [inline] [] SyS_sendmsg+0x2d/0x50 net/socket.c:1995 [] entry_SYSCALL_64_fastpath+0x1f/0xc2 Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Cc: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/dev.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index e61528c50209..727b6fda0e8c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2658,11 +2658,12 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) { + struct sk_buff *segs; + if (unlikely(skb_needs_check(skb, tx_path))) { int err; - skb_warn_bad_offload(skb); - + /* We're going to init ->check field in TCP or UDP header */ err = skb_cow_head(skb, 0); if (err < 0) return ERR_PTR(err); @@ -2690,7 +2691,12 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, skb_reset_mac_header(skb); skb_reset_mac_len(skb); - return skb_mac_gso_segment(skb, features); + segs = skb_mac_gso_segment(skb, features); + + if (unlikely(skb_needs_check(skb, tx_path))) + skb_warn_bad_offload(skb); + + return segs; } EXPORT_SYMBOL(__skb_gso_segment); -- cgit From 79e7fff47b7bb4124ef970a13eac4fdeddd1fc25 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 2 Feb 2017 18:43:28 -0800 Subject: net: remove support for per driver ndo_busy_poll() We added generic support for busy polling in NAPI layer in linux-4.5 No network driver uses ndo_busy_poll() anymore, we can get rid of the pointer in struct net_device_ops, and its use in sk_busy_loop() Saves NETIF_F_BUSY_POLL features bit. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 -- include/linux/netdevice.h | 3 --- net/core/dev.c | 15 --------------- net/core/ethtool.c | 1 - 4 files changed, 21 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 9c6c8ef2e9e7..9a0419594e84 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -71,7 +71,6 @@ enum { 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 */ - NETIF_F_BUSY_POLL_BIT, /* Busy poll */ NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ @@ -134,7 +133,6 @@ enum { #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) -#define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) #define NETIF_F_HW_TC __NETIF_F(HW_TC) #define for_each_netdev_feature(mask_addr, bit) \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f3878fbe7786..6f18b509fb2f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1184,9 +1184,6 @@ struct net_device_ops { int (*ndo_netpoll_setup)(struct net_device *dev, struct netpoll_info *info); void (*ndo_netpoll_cleanup)(struct net_device *dev); -#endif -#ifdef CONFIG_NET_RX_BUSY_POLL - int (*ndo_busy_poll)(struct napi_struct *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); diff --git a/net/core/dev.c b/net/core/dev.c index 727b6fda0e8c..4cde8bfb9bab 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4978,7 +4978,6 @@ bool sk_busy_loop(struct sock *sk, int nonblock) { unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0; int (*napi_poll)(struct napi_struct *napi, int budget); - int (*busy_poll)(struct napi_struct *dev); void *have_poll_lock = NULL; struct napi_struct *napi; int rc; @@ -4993,17 +4992,10 @@ restart: if (!napi) goto out; - /* Note: ndo_busy_poll method is optional in linux-4.5 */ - busy_poll = napi->dev->netdev_ops->ndo_busy_poll; - preempt_disable(); for (;;) { rc = 0; local_bh_disable(); - if (busy_poll) { - rc = busy_poll(napi); - goto count; - } if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); @@ -6956,13 +6948,6 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~dev->gso_partial_features; } -#ifdef CONFIG_NET_RX_BUSY_POLL - if (dev->netdev_ops->ndo_busy_poll) - features |= NETIF_F_BUSY_POLL; - else -#endif - features &= ~NETIF_F_BUSY_POLL; - return features; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 6b3eee0834a0..d5f412b3093d 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -102,7 +102,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXFCS_BIT] = "rx-fcs", [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", - [NETIF_F_BUSY_POLL_BIT] = "busy-poll", [NETIF_F_HW_TC_BIT] = "hw-tc-offload", }; -- cgit From 6e7bc478c9a006c701c14476ec9d389a484b4864 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Feb 2017 14:29:42 -0800 Subject: net: skb_needs_check() accepts CHECKSUM_NONE for tx My recent change missed fact that UFO would perform a complete UDP checksum before segmenting in frags. In this case skb->ip_summed is set to CHECKSUM_NONE. We need to add this valid case to skb_needs_check() Fixes: b2504a5dbef3 ("net: reduce skb_warn_bad_offload() noise") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/dev.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 4cde8bfb9bab..42ba0379575a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2637,9 +2637,10 @@ EXPORT_SYMBOL(skb_mac_gso_segment); static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) - return skb->ip_summed != CHECKSUM_PARTIAL; - else - return skb->ip_summed == CHECKSUM_NONE; + return skb->ip_summed != CHECKSUM_PARTIAL && + skb->ip_summed != CHECKSUM_NONE; + + return skb->ip_summed == CHECKSUM_NONE; } /** -- cgit From 02c1602ee7b3e3d062c3eacd374d6a6e3a2ebb73 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Feb 2017 15:25:02 -0800 Subject: net: remove __napi_complete() All __napi_complete() callers have been converted to use the more standard napi_complete_done(), we can now remove this NAPI method for good. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - net/core/dev.c | 24 +++--------------------- 2 files changed, 3 insertions(+), 22 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6f18b509fb2f..014fbe256d55 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -463,7 +463,6 @@ static inline bool napi_reschedule(struct napi_struct *napi) return false; } -bool __napi_complete(struct napi_struct *n); bool napi_complete_done(struct napi_struct *n, int work_done); /** * napi_complete - NAPI processing complete diff --git a/net/core/dev.c b/net/core/dev.c index 42ba0379575a..404d2e6d5d32 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4883,23 +4883,6 @@ void __napi_schedule_irqoff(struct napi_struct *n) } EXPORT_SYMBOL(__napi_schedule_irqoff); -bool __napi_complete(struct napi_struct *n) -{ - BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); - - /* Some drivers call us directly, instead of calling - * napi_complete_done(). - */ - if (unlikely(test_bit(NAPI_STATE_IN_BUSY_POLL, &n->state))) - return false; - - list_del_init(&n->poll_list); - smp_mb__before_atomic(); - clear_bit(NAPI_STATE_SCHED, &n->state); - return true; -} -EXPORT_SYMBOL(__napi_complete); - bool napi_complete_done(struct napi_struct *n, int work_done) { unsigned long flags; @@ -4926,14 +4909,13 @@ bool napi_complete_done(struct napi_struct *n, int work_done) else napi_gro_flush(n, false); } - if (likely(list_empty(&n->poll_list))) { - WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state)); - } else { + if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); - __napi_complete(n); + list_del_init(&n->poll_list); local_irq_restore(flags); } + WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state)); return true; } EXPORT_SYMBOL(napi_complete_done); -- cgit From a8eca326151ee1beac82a4fd86d9edad3a37aaed Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 6 Feb 2017 16:20:14 +0100 Subject: net: remove ndo_neigh_{construct, destroy} from stacked devices In commit 18bfb924f000 ("net: introduce default neigh_construct/destroy ndo calls for L2 upper devices") we added these ndos to stacked devices such as team and bond, so that calls will be propagated to mlxsw. However, previous commit removed the reliance on these ndos and no new users of these ndos have appeared since above mentioned commit. We can therefore safely remove this dead code. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 -- drivers/net/team/team.c | 2 -- include/linux/netdevice.h | 4 ---- net/8021q/vlan_dev.c | 2 -- net/bridge/br_device.c | 2 -- net/core/dev.c | 44 ----------------------------------------- 6 files changed, 56 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e6af04716cf7..6321f12630c8 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4145,8 +4145,6 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_add_slave = bond_enslave, .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, - .ndo_neigh_construct = netdev_default_l2upper_neigh_construct, - .ndo_neigh_destroy = netdev_default_l2upper_neigh_destroy, .ndo_bridge_setlink = switchdev_port_bridge_setlink, .ndo_bridge_getlink = switchdev_port_bridge_getlink, .ndo_bridge_dellink = switchdev_port_bridge_dellink, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index a3711769544b..4a24b5d15f5a 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2001,8 +2001,6 @@ static const struct net_device_ops team_netdev_ops = { .ndo_add_slave = team_add_slave, .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, - .ndo_neigh_construct = netdev_default_l2upper_neigh_construct, - .ndo_neigh_destroy = netdev_default_l2upper_neigh_destroy, .ndo_change_carrier = team_change_carrier, .ndo_bridge_setlink = switchdev_port_bridge_setlink, .ndo_bridge_getlink = switchdev_port_bridge_getlink, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 014fbe256d55..58afbd1cc659 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3888,10 +3888,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info); -int netdev_default_l2upper_neigh_construct(struct net_device *dev, - struct neighbour *n); -void netdev_default_l2upper_neigh_destroy(struct net_device *dev, - struct neighbour *n); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 116455ac3db5..e97ab824e368 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -791,8 +791,6 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, - .ndo_neigh_construct = netdev_default_l2upper_neigh_construct, - .ndo_neigh_destroy = netdev_default_l2upper_neigh_destroy, .ndo_fdb_add = switchdev_port_fdb_add, .ndo_fdb_del = switchdev_port_fdb_del, .ndo_fdb_dump = switchdev_port_fdb_dump, diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 6c46d1b4cdbb..5ba0b558f8ae 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -347,8 +347,6 @@ static const struct net_device_ops br_netdev_ops = { .ndo_add_slave = br_add_slave, .ndo_del_slave = br_del_slave, .ndo_fix_features = br_fix_features, - .ndo_neigh_construct = netdev_default_l2upper_neigh_construct, - .ndo_neigh_destroy = netdev_default_l2upper_neigh_destroy, .ndo_fdb_add = br_fdb_add, .ndo_fdb_del = br_fdb_delete, .ndo_fdb_dump = br_fdb_dump, diff --git a/net/core/dev.c b/net/core/dev.c index 404d2e6d5d32..3e1a60102e64 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6111,50 +6111,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev, } EXPORT_SYMBOL(netdev_lower_state_changed); -int netdev_default_l2upper_neigh_construct(struct net_device *dev, - struct neighbour *n) -{ - struct net_device *lower_dev, *stop_dev; - struct list_head *iter; - int err; - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (!lower_dev->netdev_ops->ndo_neigh_construct) - continue; - err = lower_dev->netdev_ops->ndo_neigh_construct(lower_dev, n); - if (err) { - stop_dev = lower_dev; - goto rollback; - } - } - return 0; - -rollback: - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (lower_dev == stop_dev) - break; - if (!lower_dev->netdev_ops->ndo_neigh_destroy) - continue; - lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n); - } - return err; -} -EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_construct); - -void netdev_default_l2upper_neigh_destroy(struct net_device *dev, - struct neighbour *n) -{ - struct net_device *lower_dev; - struct list_head *iter; - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (!lower_dev->netdev_ops->ndo_neigh_destroy) - continue; - lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n); - } -} -EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_destroy); - static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; -- cgit From 722c9a0cebb88ac1a982285f15d5fd44f4140c66 Mon Sep 17 00:00:00 2001 From: tcharding Date: Thu, 9 Feb 2017 17:56:04 +1100 Subject: net: Fix checkpatch WARNING: please, no space before tabs This patch fixes multiple occurrences of space before tabs warnings. More lines of code were moved than required to keep kernel-doc comments uniform. Signed-off-by: Tobin C. Harding Signed-off-by: David S. Miller --- net/core/dev.c | 142 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 71 insertions(+), 71 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 0921609dfa81..b7c795017299 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1,5 +1,5 @@ /* - * NET3 Protocol independent device support routines. + * NET3 Protocol independent device support routines. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -7,7 +7,7 @@ * 2 of the License, or (at your option) any later version. * * Derived from the non IP parts of dev.c 1.0.19 - * Authors: Ross Biro + * Authors: Ross Biro * Fred N. van Kempen, * Mark Evans, * @@ -21,9 +21,9 @@ * * Changes: * D.J. Barrow : Fixed bug where dev->refcnt gets set - * to 2 if register_netdev gets called - * before net_dev_init & also removed a - * few lines of code in the process. + * to 2 if register_netdev gets called + * before net_dev_init & also removed a + * few lines of code in the process. * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant * stunts to keep the queue safe. @@ -36,7 +36,7 @@ * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. - * Alan Cox : Fix ETH_P_ALL echoback lengths. + * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before @@ -46,7 +46,7 @@ * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. - * Alan Cox : Fixed nasty side effect of device close + * Alan Cox : Fixed nasty side effect of device close * changes. * Rudi Cilibrasi : Pass the right thing to * set_mac_address() @@ -67,8 +67,8 @@ * Paul Rusty Russell : SIOCSIFNAME * Pekka Riikonen : Netdev boot-time settings code * Andrew Morton : Make unregister_netdevice wait - * indefinitely on dev->refcnt - * J Hadi Salim : - Backlog queue sampling + * indefinitely on dev->refcnt + * J Hadi Salim : - Backlog queue sampling * - netif_rx() feedback */ @@ -574,13 +574,13 @@ static int netdev_boot_setup_add(char *name, struct ifmap *map) } /** - * netdev_boot_setup_check - check boot time settings - * @dev: the netdevice + * netdev_boot_setup_check - check boot time settings + * @dev: the netdevice * - * Check boot time settings for the device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found, 1 if they are. + * Check boot time settings for the device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found, 1 if they are. */ int netdev_boot_setup_check(struct net_device *dev) { @@ -590,10 +590,10 @@ int netdev_boot_setup_check(struct net_device *dev) for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && !strcmp(dev->name, s[i].name)) { - dev->irq = s[i].map.irq; - dev->base_addr = s[i].map.base_addr; - dev->mem_start = s[i].map.mem_start; - dev->mem_end = s[i].map.mem_end; + dev->irq = s[i].map.irq; + dev->base_addr = s[i].map.base_addr; + dev->mem_start = s[i].map.mem_start; + dev->mem_end = s[i].map.mem_end; return 1; } } @@ -603,14 +603,14 @@ EXPORT_SYMBOL(netdev_boot_setup_check); /** - * netdev_boot_base - get address from boot time settings - * @prefix: prefix for network device - * @unit: id for network device + * netdev_boot_base - get address from boot time settings + * @prefix: prefix for network device + * @unit: id for network device * - * Check boot time settings for the base address of device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found. + * Check boot time settings for the base address of device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found. */ unsigned long netdev_boot_base(const char *prefix, int unit) { @@ -737,15 +737,15 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name) EXPORT_SYMBOL(__dev_get_by_name); /** - * dev_get_by_name_rcu - find a device by its name - * @net: the applicable net namespace - * @name: name to find + * dev_get_by_name_rcu - find a device by its name + * @net: the applicable net namespace + * @name: name to find * - * Find an interface by name. - * If the name is found a pointer to the device is returned. - * If the name is not found then %NULL is returned. - * The reference counters are not incremented so the caller must be - * careful with locks. The caller must hold RCU lock. + * Find an interface by name. + * If the name is found a pointer to the device is returned. + * If the name is not found then %NULL is returned. + * The reference counters are not incremented so the caller must be + * careful with locks. The caller must hold RCU lock. */ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) @@ -1289,8 +1289,8 @@ void netdev_state_change(struct net_device *dev) EXPORT_SYMBOL(netdev_state_change); /** - * netdev_notify_peers - notify network peers about existence of @dev - * @dev: network device + * netdev_notify_peers - notify network peers about existence of @dev + * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when @@ -1518,17 +1518,17 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, static int dev_boot_phase = 1; /** - * register_netdevice_notifier - register a network notifier block - * @nb: notifier + * register_netdevice_notifier - register a network notifier block + * @nb: notifier * - * Register a notifier to be called when network device events occur. - * The notifier passed is linked into the kernel structures and must - * not be reused until it has been unregistered. A negative errno code - * is returned on a failure. + * Register a notifier to be called when network device events occur. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. * - * When registered all registration and up events are replayed - * to the new notifier to allow device to have a race free - * view of the network device list. + * When registered all registration and up events are replayed + * to the new notifier to allow device to have a race free + * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) @@ -1585,17 +1585,17 @@ outroll: EXPORT_SYMBOL(register_netdevice_notifier); /** - * unregister_netdevice_notifier - unregister a network notifier block - * @nb: notifier + * unregister_netdevice_notifier - unregister a network notifier block + * @nb: notifier * - * Unregister a notifier previously registered by - * register_netdevice_notifier(). The notifier is unlinked into the - * kernel structures and may then be reused. A negative errno code - * is returned on a failure. + * Unregister a notifier previously registered by + * register_netdevice_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. * - * After unregistering unregister and down device events are synthesized - * for all devices on the device list to the removed notifier to remove - * the need for special case cleanup code. + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) @@ -7544,17 +7544,17 @@ void netdev_freemem(struct net_device *dev) } /** - * alloc_netdev_mqs - allocate network device - * @sizeof_priv: size of private data to allocate space for - * @name: device name format string - * @name_assign_type: origin of device name - * @setup: callback to initialize device - * @txqs: the number of TX subqueues to allocate - * @rxqs: the number of RX subqueues to allocate - * - * Allocates a struct net_device with private data area for driver use - * and performs basic initialization. Also allocates subqueue structs - * for each queue on the device. + * alloc_netdev_mqs - allocate network device + * @sizeof_priv: size of private data to allocate space for + * @name: device name format string + * @name_assign_type: origin of device name + * @setup: callback to initialize device + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate + * + * Allocates a struct net_device with private data area for driver use + * and performs basic initialization. Also allocates subqueue structs + * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, @@ -7666,13 +7666,13 @@ free_dev: EXPORT_SYMBOL(alloc_netdev_mqs); /** - * free_netdev - free network device - * @dev: device + * free_netdev - free network device + * @dev: device * - * This function does the last stage of destroying an allocated device - * interface. The reference to the device object is released. - * If this is the last reference then it will be freed. - * Must be called in process context. + * This function does the last stage of destroying an allocated device + * interface. The reference to the device object is released. If this + * is the last reference then it will be freed.Must be called in process + * context. */ void free_netdev(struct net_device *dev) { -- cgit From 643aa9cba0b688ffde28ac39aebec6f56fc2a8af Mon Sep 17 00:00:00 2001 From: tcharding Date: Thu, 9 Feb 2017 17:56:05 +1100 Subject: net: Fix checkpatch whitespace errors This patch fixes two trivial whitespace errors. Brace should be on the previous line and trailing statements should be on next line. Signed-off-by: Tobin C. Harding Signed-off-by: David S. Miller --- net/core/dev.c | 39 ++++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 19 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index b7c795017299..60a0be743cdb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -192,7 +192,8 @@ static seqcount_t devnet_rename_seq; static inline void dev_base_seq_inc(struct net *net) { - while (++net->dev_base_seq == 0); + while (++net->dev_base_seq == 0) + ; } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) @@ -274,8 +275,8 @@ EXPORT_PER_CPU_SYMBOL(softnet_data); * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */ -static const unsigned short netdev_lock_type[] = - {ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, +static const unsigned short netdev_lock_type[] = { + ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, @@ -291,22 +292,22 @@ static const unsigned short netdev_lock_type[] = ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; -static const char *const netdev_lock_name[] = - {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", - "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", - "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", - "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", - "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", - "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", - "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", - "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", - "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", - "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", - "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", - "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; +static const char *const netdev_lock_name[] = { + "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", + "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", + "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", + "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", + "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", + "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", + "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", + "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", + "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", + "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", + "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", + "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", + "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", + "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", + "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; -- cgit From eb13da1a103a808c05267816fa4d30d603bfda5e Mon Sep 17 00:00:00 2001 From: tcharding Date: Thu, 9 Feb 2017 17:56:06 +1100 Subject: net: Fix checkpatch block comments warnings Fix multiple occurrences of checkpatch warning. WARNING: Block comments use * on subsequent lines. Also make comment blocks more uniform. Signed-off-by: Tobin C. Harding Signed-off-by: David S. Miller --- net/core/dev.c | 65 +++++++++++++++++++++++++++++----------------------------- 1 file changed, 33 insertions(+), 32 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 60a0be743cdb..e583820c21be 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -353,10 +353,11 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) #endif /******************************************************************************* + * + * Protocol management and registration routines + * + *******************************************************************************/ - Protocol management and registration routines - -*******************************************************************************/ /* * Add a protocol ID to the list. Now that the input handler is @@ -539,10 +540,10 @@ void dev_remove_offload(struct packet_offload *po) EXPORT_SYMBOL(dev_remove_offload); /****************************************************************************** - - Device Boot-time Settings Routines - -*******************************************************************************/ + * + * Device Boot-time Settings Routines + * + ******************************************************************************/ /* Boot time configuration table */ static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX]; @@ -664,10 +665,10 @@ int __init netdev_boot_setup(char *str) __setup("netdev=", netdev_boot_setup); /******************************************************************************* - - Device Interface Subroutines - -*******************************************************************************/ + * + * Device Interface Subroutines + * + *******************************************************************************/ /** * dev_get_iflink - get 'iflink' value of a interface @@ -3326,16 +3327,16 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) } /* The device has no queue. Common case for software devices: - loopback, all the sorts of tunnels... + * loopback, all the sorts of tunnels... - Really, it is unlikely that netif_tx_lock protection is necessary - here. (f.e. loopback and IP tunnels are clean ignoring statistics - counters.) - However, it is possible, that they rely on protection - made by us here. + * Really, it is unlikely that netif_tx_lock protection is necessary + * here. (f.e. loopback and IP tunnels are clean ignoring statistics + * counters.) + * However, it is possible, that they rely on protection + * made by us here. - Check this and shot the lock. It is not prone from deadlocks. - Either shot noqueue qdisc, it is even simpler 8) + * Check this and shot the lock. It is not prone from deadlocks. + *Either shot noqueue qdisc, it is even simpler 8) */ if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ @@ -3397,9 +3398,9 @@ int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) EXPORT_SYMBOL(dev_queue_xmit_accel); -/*======================================================================= - Receiver routines - =======================================================================*/ +/************************************************************************* + * Receiver routines + *************************************************************************/ int netdev_max_backlog __read_mostly = 1000; EXPORT_SYMBOL(netdev_max_backlog); @@ -6359,8 +6360,8 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags) } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI - is important. Some (broken) drivers set IFF_PROMISC, when - IFF_ALLMULTI is requested not asking us and not reporting. + * is important. Some (broken) drivers set IFF_PROMISC, when + * IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { int inc = (flags & IFF_ALLMULTI) ? 1 : -1; @@ -6724,8 +6725,8 @@ static void rollback_registered_many(struct list_head *head) /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - */ + * this device. They should clean all the things. + */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); if (!dev->rtnl_link_ops || @@ -7855,12 +7856,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_shutdown(dev); /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - - Note that dev->reg_state stays at NETREG_REGISTERED. - This is wanted because this way 8021q and macvlan know - the device is just moving and can keep their slaves up. - */ + * this device. They should clean all the things. + * + * Note that dev->reg_state stays at NETREG_REGISTERED. + * This is wanted because this way 8021q and macvlan know + * the device is just moving and can keep their slaves up. + */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); -- cgit From f4563a75fb93d6a756416d97e13f0773ac373a24 Mon Sep 17 00:00:00 2001 From: tcharding Date: Thu, 9 Feb 2017 17:56:07 +1100 Subject: net: Fix checkpatch, Missing a blank line after declarations This patch fixes multiple occurrences of checkpatch WARNING: Missing a blank line after declarations. Signed-off-by: Tobin C. Harding Signed-off-by: David S. Miller --- net/core/dev.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index e583820c21be..363c44b9be63 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2498,6 +2498,7 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, if (dev->num_tc) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; qcount = dev->tc_to_txq[tc].count; } @@ -2719,9 +2720,11 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; + if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + if (PageHighMem(skb_frag_page(frag))) return 1; } @@ -2735,6 +2738,7 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr = page_to_phys(skb_frag_page(frag)); + if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) return 1; } @@ -3210,6 +3214,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { int new_index = get_xps_queue(dev, skb); + if (new_index < 0) new_index = skb_tx_hash(dev, skb); @@ -3239,6 +3244,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb, accel_priv, __netdev_pick_tx); @@ -3768,6 +3774,7 @@ static int netif_rx_internal(struct sk_buff *skb) #endif { unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); put_cpu(); } @@ -3827,6 +3834,7 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) while (clist) { struct sk_buff *skb = clist; + clist = clist->next; WARN_ON(atomic_read(&skb->users)); @@ -5663,6 +5671,7 @@ static int netdev_adjacent_sysfs_add(struct net_device *dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", adj_dev->name); return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), @@ -5673,6 +5682,7 @@ static void netdev_adjacent_sysfs_del(struct net_device *dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", name); sysfs_remove_link(&(dev->dev.kobj), linkname); @@ -5942,6 +5952,7 @@ void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { struct netdev_notifier_changeupper_info changeupper_info; + ASSERT_RTNL(); changeupper_info.upper_dev = upper_dev; @@ -6659,6 +6670,7 @@ EXPORT_SYMBOL(dev_change_xdp_fd); static int dev_new_index(struct net *net) { int ifindex = net->ifindex; + for (;;) { if (++ifindex <= 0) ifindex = 1; @@ -7072,6 +7084,7 @@ void netif_tx_stop_all_queues(struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + netif_tx_stop_queue(txq); } } -- cgit From 37fabbf4d489cc2e1cbf7cde816d9453a65ddfb7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 10 Feb 2017 05:46:46 -0800 Subject: net: busy-poll: remove LL_FLUSH_FAILED and LL_FLUSH_BUSY Commit 79e7fff47b7b ("net: remove support for per driver ndo_busy_poll()") made them obsolete. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/busy_poll.h | 4 ---- net/core/dev.c | 3 --- 2 files changed, 7 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index d73b849e29a6..b8d637225a07 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -33,10 +33,6 @@ struct napi_struct; extern unsigned int sysctl_net_busy_read __read_mostly; extern unsigned int sysctl_net_busy_poll __read_mostly; -/* return values from ndo_ll_poll */ -#define LL_FLUSH_FAILED -1 -#define LL_FLUSH_BUSY -2 - static inline bool net_busy_loop_on(void) { return sysctl_net_busy_poll; diff --git a/net/core/dev.c b/net/core/dev.c index 363c44b9be63..2f1bbe1bf67c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5008,9 +5008,6 @@ count: LINUX_MIB_BUSYPOLLRXPACKETS, rc); local_bh_enable(); - if (rc == LL_FLUSH_FAILED) - break; /* permanent failure */ - if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) || busy_loop_timeout(end_time)) break; -- cgit From 25393d3fc055b76587fcc91627aee8c345400c3a Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 15 Feb 2017 09:39:44 +0100 Subject: net: Prepare gro for packet consuming gro callbacks The upcomming IPsec ESP gro callbacks will consume the skb, so prepare for that. Signed-off-by: Steffen Klassert --- include/linux/netdevice.h | 9 +++++++++ net/core/dev.c | 7 +++++++ net/xfrm/Kconfig | 4 ++++ 3 files changed, 20 insertions(+) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f9da3acfee9a..9e5d1cd9d975 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -352,6 +352,7 @@ enum gro_result { GRO_HELD, GRO_NORMAL, GRO_DROP, + GRO_CONSUMED, }; typedef enum gro_result gro_result_t; @@ -2661,10 +2662,18 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } +#ifdef CONFIG_XFRM_OFFLOAD +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +{ + if (PTR_ERR(pp) != -EINPROGRESS) + NAPI_GRO_CB(skb)->flush |= flush; +} +#else static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } +#endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, diff --git a/net/core/dev.c b/net/core/dev.c index 3e1a60102e64..64efbb9e4436 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4505,6 +4505,11 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (&ptype->list == head) goto normal; + if (IS_ERR(pp) && PTR_ERR(pp) == -EINPROGRESS) { + ret = GRO_CONSUMED; + goto ok; + } + same_flow = NAPI_GRO_CB(skb)->same_flow; ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; @@ -4609,6 +4614,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) case GRO_HELD: case GRO_MERGED: + case GRO_CONSUMED: break; } @@ -4680,6 +4686,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, break; case GRO_MERGED: + case GRO_CONSUMED: break; } diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index bda1a13628a8..a484451c72ec 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -5,6 +5,10 @@ config XFRM bool depends on NET +config XFRM_OFFLOAD + bool + depends on XFRM + config XFRM_ALGO tristate select XFRM -- cgit From 559c59b238ebb7d39b732b6b08a59693b972e75c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Feb 2017 08:20:56 -0800 Subject: net: napi_watchdog() can use napi_schedule_irqoff() hrtimer handlers run with masked hard IRQ, we can therefore use napi_schedule_irqoff() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 05d19c6acf94..304f2deae5f9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5089,7 +5089,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) napi = container_of(timer, struct napi_struct, timer); if (napi->gro_list) - napi_schedule(napi); + napi_schedule_irqoff(napi); return HRTIMER_NORESTART; } -- cgit From 39e6c8208d7b6fb9d2047850fb3327db567b564b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Feb 2017 10:34:50 -0800 Subject: net: solve a NAPI race While playing with mlx4 hardware timestamping of RX packets, I found that some packets were received by TCP stack with a ~200 ms delay... Since the timestamp was provided by the NIC, and my probe was added in tcp_v4_rcv() while in BH handler, I was confident it was not a sender issue, or a drop in the network. This would happen with a very low probability, but hurting RPC workloads. A NAPI driver normally arms the IRQ after the napi_complete_done(), after NAPI_STATE_SCHED is cleared, so that the hard irq handler can grab it. Problem is that if another point in the stack grabs NAPI_STATE_SCHED bit while IRQ are not disabled, we might have later an IRQ firing and finding this bit set, right before napi_complete_done() clears it. This can happen with busy polling users, or if gro_flush_timeout is used. But some other uses of napi_schedule() in drivers can cause this as well. thread 1 thread 2 (could be on same cpu, or not) // busy polling or napi_watchdog() napi_schedule(); ... napi->poll() device polling: read 2 packets from ring buffer Additional 3rd packet is available. device hard irq // does nothing because NAPI_STATE_SCHED bit is owned by thread 1 napi_schedule(); napi_complete_done(napi, 2); rearm_irq(); Note that rearm_irq() will not force the device to send an additional IRQ for the packet it already signaled (3rd packet in my example) This patch adds a new NAPI_STATE_MISSED bit, that napi_schedule_prep() can set if it could not grab NAPI_STATE_SCHED Then napi_complete_done() properly reschedules the napi to make sure we do not miss something. Since we manipulate multiple bits at once, use cmpxchg() like in sk_busy_loop() to provide proper transactions. In v2, I changed napi_watchdog() to use a relaxed variant of napi_schedule_prep() : No need to set NAPI_STATE_MISSED from this point. In v3, I added more details in the changelog and clears NAPI_STATE_MISSED in busy_poll_stop() In v4, I added the ideas given by Alexander Duyck in v3 review Signed-off-by: Eric Dumazet Cc: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 29 ++++++------------ net/core/dev.c | 76 ++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 81 insertions(+), 24 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f40f0ab3847a..97456b2539e4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -330,6 +330,7 @@ struct napi_struct { enum { NAPI_STATE_SCHED, /* Poll is scheduled */ + NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ @@ -338,12 +339,13 @@ enum { }; enum { - NAPIF_STATE_SCHED = (1UL << NAPI_STATE_SCHED), - NAPIF_STATE_DISABLE = (1UL << NAPI_STATE_DISABLE), - NAPIF_STATE_NPSVC = (1UL << NAPI_STATE_NPSVC), - NAPIF_STATE_HASHED = (1UL << NAPI_STATE_HASHED), - NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL), - NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), + NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), + NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), + NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED), + NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), + NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), }; enum gro_result { @@ -414,20 +416,7 @@ static inline bool napi_disable_pending(struct napi_struct *n) return test_bit(NAPI_STATE_DISABLE, &n->state); } -/** - * napi_schedule_prep - check if NAPI can be scheduled - * @n: NAPI context - * - * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable to - * insure only one NAPI poll instance runs. We also make - * sure there is no pending NAPI disable. - */ -static inline bool napi_schedule_prep(struct napi_struct *n) -{ - return !napi_disable_pending(n) && - !test_and_set_bit(NAPI_STATE_SCHED, &n->state); -} +bool napi_schedule_prep(struct napi_struct *n); /** * napi_schedule - schedule NAPI poll diff --git a/net/core/dev.c b/net/core/dev.c index 304f2deae5f9..e63bf61b19be 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4883,6 +4883,39 @@ void __napi_schedule(struct napi_struct *n) } EXPORT_SYMBOL(__napi_schedule); +/** + * napi_schedule_prep - check if napi can be scheduled + * @n: napi context + * + * Test if NAPI routine is already running, and if not mark + * it as running. This is used as a condition variable + * insure only one NAPI poll instance runs. We also make + * sure there is no pending NAPI disable. + */ +bool napi_schedule_prep(struct napi_struct *n) +{ + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + if (unlikely(val & NAPIF_STATE_DISABLE)) + return false; + new = val | NAPIF_STATE_SCHED; + + /* Sets STATE_MISSED bit if STATE_SCHED was already set + * This was suggested by Alexander Duyck, as compiler + * emits better code than : + * if (val & NAPIF_STATE_SCHED) + * new |= NAPIF_STATE_MISSED; + */ + new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * + NAPIF_STATE_MISSED; + } while (cmpxchg(&n->state, val, new) != val); + + return !(val & NAPIF_STATE_SCHED); +} +EXPORT_SYMBOL(napi_schedule_prep); + /** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule @@ -4897,7 +4930,7 @@ EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { - unsigned long flags; + unsigned long flags, val, new; /* * 1) Don't let napi dequeue from the cpu poll list @@ -4927,7 +4960,27 @@ bool napi_complete_done(struct napi_struct *n, int work_done) list_del_init(&n->poll_list); local_irq_restore(flags); } - WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state)); + + do { + val = READ_ONCE(n->state); + + WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); + + new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED); + + /* If STATE_MISSED was set, leave STATE_SCHED set, + * because we will call napi->poll() one more time. + * This C code was suggested by Alexander Duyck to help gcc. + */ + new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * + NAPIF_STATE_SCHED; + } while (cmpxchg(&n->state, val, new) != val); + + if (unlikely(val & NAPIF_STATE_MISSED)) { + __napi_schedule(n); + return false; + } + return true; } EXPORT_SYMBOL(napi_complete_done); @@ -4953,6 +5006,16 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) { int rc; + /* Busy polling means there is a high chance device driver hard irq + * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was + * set in napi_schedule_prep(). + * Since we are about to call napi->poll() once more, we can safely + * clear NAPI_STATE_MISSED. + * + * Note: x86 could use a single "lock and ..." instruction + * to perform these two clear_bit() + */ + clear_bit(NAPI_STATE_MISSED, &napi->state); clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); @@ -5088,8 +5151,13 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) struct napi_struct *napi; napi = container_of(timer, struct napi_struct, timer); - if (napi->gro_list) - napi_schedule_irqoff(napi); + + /* Note : we use a relaxed variant of napi_schedule_prep() not setting + * NAPI_STATE_MISSED, since we do not react to a device IRQ. + */ + if (napi->gro_list && !napi_disable_pending(napi) && + !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) + __napi_schedule_irqoff(napi); return HRTIMER_NORESTART; } -- cgit From 13baa00ad01bb3a9f893e3a08cbc2d072fc0c15d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 1 Mar 2017 14:28:39 -0800 Subject: net: net_enable_timestamp() can be called from irq contexts It is now very clear that silly TCP listeners might play with enabling/disabling timestamping while new children are added to their accept queue. Meaning net_enable_timestamp() can be called from BH context while current state of the static key is not enabled. Lets play safe and allow all contexts. The work queue is scheduled only under the problematic cases, which are the static key enable/disable transition, to not slow down critical paths. This extends and improves what we did in commit 5fa8bbda38c6 ("net: use a work queue to defer net_disable_timestamp() work") Fixes: b90e5794c5bd ("net: dont call jump_label_dec from irq context") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Signed-off-by: David S. Miller --- net/core/dev.c | 35 +++++++++++++++++++++++++++++++---- 1 file changed, 31 insertions(+), 4 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index e63bf61b19be..8637b2b71f3d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1698,27 +1698,54 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue); static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL static atomic_t netstamp_needed_deferred; +static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) { int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + int wanted; - while (deferred--) - static_key_slow_dec(&netstamp_needed); + wanted = atomic_add_return(deferred, &netstamp_wanted); + if (wanted > 0) + static_key_enable(&netstamp_needed); + else + static_key_disable(&netstamp_needed); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { +#ifdef HAVE_JUMP_LABEL + int wanted; + + while (1) { + wanted = atomic_read(&netstamp_wanted); + if (wanted <= 0) + break; + if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted) + return; + } + atomic_inc(&netstamp_needed_deferred); + schedule_work(&netstamp_work); +#else static_key_slow_inc(&netstamp_needed); +#endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef HAVE_JUMP_LABEL - /* net_disable_timestamp() can be called from non process context */ - atomic_inc(&netstamp_needed_deferred); + int wanted; + + while (1) { + wanted = atomic_read(&netstamp_wanted); + if (wanted <= 1) + break; + if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted) + return; + } + atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_key_slow_dec(&netstamp_needed); -- cgit From 37c343b4f4e70e9dc328ab04903c0ec8d154c1a4 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Tue, 14 Mar 2017 08:58:08 -0400 Subject: net: Resend IGMP memberships upon peer notification. When we notify peers of potential changes, it's also good to update IGMP memberships. For example, during VM migration, updating IGMP memberships will redirect existing multicast streams to the VM at the new location. Signed-off-by: Vladislav Yasevich Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- net/core/dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 8637b2b71f3d..7869ae3837ca 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1304,6 +1304,7 @@ void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); -- cgit