From 2b4aa3cec4873005a0d5155395b34641584b3a4e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:04:07 -0500 Subject: net: Remove dev_queue_xmit_sk A function with weird arguments that it will never use to accomdate a netfilter callback prototype is absolutely in the core of the networking stack. Frankly it does not make sense and it causes a lot of confusion as to why arguments that are never used are being passed to the function. As I am preparing to make a second change to arguments to the okfn even the names stops making sense. As I have removed the two callers of this function remove this confusion from the networking stack. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/core/dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 877c84834d81..dcf9ff913925 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3143,11 +3143,11 @@ out: return rc; } -int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb) +int dev_queue_xmit(struct sk_buff *skb) { return __dev_queue_xmit(skb, NULL); } -EXPORT_SYMBOL(dev_queue_xmit_sk); +EXPORT_SYMBOL(dev_queue_xmit); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) { -- cgit v1.3-14-g43fede From 04eb44890e5bb3cc855e5c0f18a05eb7311364b7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:04:15 -0500 Subject: bridge: Add br_netif_receive_skb remove netif_receive_skb_sk netif_receive_skb_sk is only called once in the bridge code, replace it with a bridge specific function that calls netif_receive_skb. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +----- net/bridge/br_input.c | 7 ++++++- net/core/dev.c | 4 ++-- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e664f87c8e4c..97ab5c9a7069 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2985,11 +2985,7 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); -int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb); -static inline int netif_receive_skb(struct sk_buff *skb) -{ - return netif_receive_skb_sk(skb->sk, skb); -} +int netif_receive_skb(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f921a5dce22d..2359c041e27c 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -26,6 +26,11 @@ br_should_route_hook_t __rcu *br_should_route_hook __read_mostly; EXPORT_SYMBOL(br_should_route_hook); +static int br_netif_receive_skb(struct sock *sk, struct sk_buff *skb) +{ + return netif_receive_skb(skb); +} + static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; @@ -57,7 +62,7 @@ static int br_pass_frame_up(struct sk_buff *skb) return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb, indev, NULL, - netif_receive_skb_sk); + br_netif_receive_skb); } static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, diff --git a/net/core/dev.c b/net/core/dev.c index dcf9ff913925..7db9b012dfb7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3982,13 +3982,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb) * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ -int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb) +int netif_receive_skb(struct sk_buff *skb) { trace_netif_receive_skb_entry(skb); return netif_receive_skb_internal(skb); } -EXPORT_SYMBOL(netif_receive_skb_sk); +EXPORT_SYMBOL(netif_receive_skb); /* Network device is going away, flush any packets still pending * Called with irqs disabled. -- cgit v1.3-14-g43fede From 0c4b51f0054ce85c0ec578ab818f0631834573eb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:04:18 -0500 Subject: netfilter: Pass net into okfn This is immediately motivated by the bridge code that chains functions that call into netfilter. Without passing net into the okfns the bridge code would need to guess about the best expression for the network namespace to process packets in. As net is frequently one of the first things computed in continuation functions after netfilter has done it's job passing in the desired network namespace is in many cases a code simplification. To support this change the function dst_output_okfn is introduced to simplify passing dst_output as an okfn. For the moment dst_output_okfn just silently drops the struct net. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- drivers/net/vrf.c | 2 +- include/linux/netdevice.h | 2 +- include/linux/netfilter.h | 26 ++++++++++++++------------ include/linux/netfilter_bridge.h | 2 +- include/net/dn_neigh.h | 6 +++--- include/net/dst.h | 4 ++++ include/net/ipv6.h | 2 +- include/net/netfilter/br_netfilter.h | 2 +- net/bridge/br_forward.c | 5 ++--- net/bridge/br_input.c | 7 ++++--- net/bridge/br_netfilter_hooks.c | 21 +++++++++------------ net/bridge/br_netfilter_ipv6.c | 3 +-- net/bridge/br_private.h | 6 +++--- net/bridge/br_stp_bpdu.c | 3 ++- net/core/dev.c | 4 +++- net/decnet/dn_neigh.c | 8 ++++---- net/decnet/dn_nsp_in.c | 3 ++- net/decnet/dn_route.c | 6 +++--- net/ipv4/arp.c | 7 +++---- net/ipv4/ip_forward.c | 3 +-- net/ipv4/ip_input.c | 7 ++----- net/ipv4/ip_output.c | 4 ++-- net/ipv4/ipmr.c | 4 ++-- net/ipv4/raw.c | 2 +- net/ipv4/xfrm4_input.c | 3 ++- net/ipv4/xfrm4_output.c | 2 +- net/ipv6/ip6_input.c | 5 ++--- net/ipv6/ip6_output.c | 7 ++++--- net/ipv6/ip6mr.c | 3 +-- net/ipv6/mcast.c | 4 ++-- net/ipv6/ndisc.c | 2 +- net/ipv6/output_core.c | 2 +- net/ipv6/raw.c | 2 +- net/ipv6/xfrm6_output.c | 2 +- net/netfilter/ipvs/ip_vs_xmit.c | 4 ++-- net/netfilter/nf_queue.c | 2 +- net/xfrm/xfrm_output.c | 12 ++++++------ 37 files changed, 95 insertions(+), 94 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 979a4db9c6bc..637e9fd1e14c 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -253,7 +253,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) } /* modelled after ip_finish_output2 */ -static int vrf_finish_output(struct sock *sk, struct sk_buff *skb) +static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 97ab5c9a7069..b791405958b4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2212,7 +2212,7 @@ int dev_open(struct net_device *dev); int dev_close(struct net_device *dev); int dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); -int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb); +int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); int register_netdevice(struct net_device *dev); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 295f2650b5dc..0b4d4560f33d 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -56,7 +56,7 @@ struct nf_hook_state { struct sock *sk; struct net *net; struct list_head *hook_list; - int (*okfn)(struct sock *, struct sk_buff *); + int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; static inline void nf_hook_state_init(struct nf_hook_state *p, @@ -67,7 +67,7 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, struct net_device *outdev, struct sock *sk, struct net *net, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { p->hook = hook; p->thresh = thresh; @@ -175,7 +175,7 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *), + int (*okfn)(struct net *, struct sock *, struct sk_buff *), int thresh) { struct list_head *hook_list = &net->nf.hooks[pf][hook]; @@ -193,7 +193,7 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return nf_hook_thresh(pf, hook, net, sk, skb, indev, outdev, okfn, INT_MIN); } @@ -219,31 +219,33 @@ static inline int NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *), int thresh) + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + int thresh) { int ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, thresh); if (ret == 1) - ret = okfn(sk, skb); + ret = okfn(net, sk, skb); return ret; } static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *), bool cond) + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) { int ret; if (!cond || ((ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, INT_MIN)) == 1)) - ret = okfn(sk, skb); + ret = okfn(net, sk, skb); return ret; } static inline int NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return NF_HOOK_THRESH(pf, hook, net, sk, skb, in, out, okfn, INT_MIN); } @@ -345,12 +347,12 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #else /* !CONFIG_NETFILTER */ -#define NF_HOOK(pf, hook, net, sk, skb, indev, outdev, okfn) (okfn)(sk, skb) -#define NF_HOOK_COND(pf, hook, net, sk, skb, indev, outdev, okfn, cond) (okfn)(sk, skb) +#define NF_HOOK(pf, hook, net, sk, skb, indev, outdev, okfn) (okfn)(net, sk, skb) +#define NF_HOOK_COND(pf, hook, net, sk, skb, indev, outdev, okfn, cond) (okfn)(net, sk, skb) static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return 1; } diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 2437b8a5d7a9..2ed40c402b5e 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -17,7 +17,7 @@ enum nf_br_hook_priorities { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); static inline void br_drop_fake_rtable(struct sk_buff *skb) { diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h index d0424269313f..5e902fc3f4eb 100644 --- a/include/net/dn_neigh.h +++ b/include/net/dn_neigh.h @@ -18,11 +18,11 @@ struct dn_neigh { void dn_neigh_init(void); void dn_neigh_cleanup(void); -int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb); -int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb); +int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb); +int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb); void dn_neigh_pointopoint_hello(struct sk_buff *skb); int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n); -int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb); +int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb); extern struct neigh_table dn_neigh_table; diff --git a/include/net/dst.h b/include/net/dst.h index c72e58474e52..df0481a07029 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -458,6 +458,10 @@ static inline int dst_output(struct sock *sk, struct sk_buff *skb) { return skb_dst(skb)->output(sk, skb); } +static inline int dst_output_okfn(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + return dst_output(sk, skb); +} /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 711cca428cc8..384a93cf07d6 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -807,7 +807,7 @@ static inline u8 ip6_tclass(__be32 flowinfo) int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); -int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb); +int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index d4c6b5f30acd..8fe266504900 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -31,7 +31,7 @@ static inline void nf_bridge_push_encap_header(struct sk_buff *skb) skb->network_header -= len; } -int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb); +int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb); static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) { diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 2dd2a23ce707..48afca729ed7 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -35,7 +35,7 @@ static inline int should_deliver(const struct net_bridge_port *p, p->state == BR_STATE_FORWARDING; } -int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb) +int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { if (!is_skb_forwardable(skb->dev, skb)) goto drop; @@ -65,9 +65,8 @@ drop: } EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); -int br_forward_finish(struct sock *sk, struct sk_buff *skb) +int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb->dev); return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, net, sk, skb, NULL, skb->dev, br_dev_queue_push_xmit); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 78fa7acd836e..223f4040d9df 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -26,7 +26,8 @@ br_should_route_hook_t __rcu *br_should_route_hook __read_mostly; EXPORT_SYMBOL(br_should_route_hook); -static int br_netif_receive_skb(struct sock *sk, struct sk_buff *skb) +static int +br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { return netif_receive_skb(skb); } @@ -125,7 +126,7 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, } /* note: already called with rcu_read_lock */ -int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb) +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const unsigned char *dest = eth_hdr(skb)->h_dest; struct net_bridge_port *p = br_port_get_rcu(skb->dev); @@ -213,7 +214,7 @@ drop: EXPORT_SYMBOL_GPL(br_handle_frame_finish); /* note: already called with rcu_read_lock */ -static int br_handle_local_finish(struct sock *sk, struct sk_buff *skb) +static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); u16 vid = 0; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 7886c9d7e23d..e6e76bbdc82f 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -256,7 +256,7 @@ void nf_bridge_update_protocol(struct sk_buff *skb) * don't, we use the neighbour framework to find out. In both cases, we make * sure that br_handle_frame_finish() is called afterwards. */ -int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) +int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb) { struct neighbour *neigh; struct dst_entry *dst; @@ -273,7 +273,7 @@ int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) if (neigh->hh.hh_len) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; - ret = br_handle_frame_finish(sk, skb); + ret = br_handle_frame_finish(net, sk, skb); } else { /* the neighbour function below overwrites the complete * MAC header, so we save the Ethernet source address and @@ -342,11 +342,10 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ -static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) +static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct iphdr *iph = ip_hdr(skb); - struct net *net = dev_net(dev); struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; @@ -536,10 +535,9 @@ static unsigned int br_nf_local_in(const struct nf_hook_ops *ops, } /* PF_BRIDGE/FORWARD *************************************************/ -static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb) +static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - struct net *net = dev_net(skb->dev); struct net_device *in; if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) { @@ -692,7 +690,7 @@ static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff __skb_push(skb, data->encap_size); nf_bridge_info_free(skb); - return br_dev_queue_push_xmit(sk, skb); + return br_dev_queue_push_xmit(net, sk, skb); } static int br_nf_push_frag_xmit_sk(struct sock *sk, struct sk_buff *skb) { @@ -728,17 +726,16 @@ static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) return 0; } -static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) +static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge; unsigned int mtu_reserved; - struct net *net = dev_net(skb_dst(skb)->dev); mtu_reserved = nf_bridge_mtu_reduction(skb); if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) { nf_bridge_info_free(skb); - return br_dev_queue_push_xmit(sk, skb); + return br_dev_queue_push_xmit(net, sk, skb); } nf_bridge = nf_bridge_info_get(skb); @@ -797,7 +794,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) } #endif nf_bridge_info_free(skb); - return br_dev_queue_push_xmit(sk, skb); + return br_dev_queue_push_xmit(net, sk, skb); drop: kfree_skb(skb); return 0; @@ -887,7 +884,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) skb->dev = nf_bridge->physindev; nf_bridge->physoutdev = NULL; - br_handle_frame_finish(NULL, skb); + br_handle_frame_finish(dev_net(skb->dev), NULL, skb); } static int br_nf_dev_xmit(struct sk_buff *skb) diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 5d19361ad5d3..e4dbbe44c724 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -161,12 +161,11 @@ br_nf_ipv6_daddr_was_changed(const struct sk_buff *skb, * for br_nf_pre_routing_finish(), same logic is used here but * equivalent IPv6 function ip6_route_input() called indirectly. */ -static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) +static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; struct net_device *dev = skb->dev; - struct net *net = dev_net(dev); const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 213baf7aaa93..74e99c75c8e4 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -413,10 +413,10 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, /* br_forward.c */ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb); -int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb); +int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb); void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, struct sk_buff *skb0); -int br_forward_finish(struct sock *sk, struct sk_buff *skb); +int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb); void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast); void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, struct sk_buff *skb2, bool unicast); @@ -434,7 +434,7 @@ void br_port_flags_change(struct net_bridge_port *port, unsigned long mask); void br_manage_promisc(struct net_bridge *br); /* br_input.c */ -int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); rx_handler_result_t br_handle_frame(struct sk_buff **pskb); static inline bool br_rx_handler_check_rcu(const struct net_device *dev) diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 8e2e8c352198..5881fbc114a9 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -30,7 +30,8 @@ #define LLC_RESERVE sizeof(struct llc_pdu_un) -static int br_send_bpdu_finish(struct sock *sk, struct sk_buff *skb) +static int br_send_bpdu_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) { return dev_queue_xmit(skb); } diff --git a/net/core/dev.c b/net/core/dev.c index 7db9b012dfb7..00dccfac8939 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2915,9 +2915,11 @@ EXPORT_SYMBOL(xmit_recursion); /** * dev_loopback_xmit - loop back @skb + * @net: network namespace this loopback is happening in + * @sk: sk needed to be a netfilter okfn * @skb: buffer to transmit */ -int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb) +int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 305ab2fe25cd..482730cd8a56 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -194,7 +194,7 @@ static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb) return err; } -static int dn_neigh_output_packet(struct sock *sk, struct sk_buff *skb) +static int dn_neigh_output_packet(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; @@ -334,7 +334,7 @@ static int dn_phase3_output(struct neighbour *neigh, struct sock *sk, dn_neigh_output_packet); } -int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb) +int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *) dst; @@ -378,7 +378,7 @@ void dn_neigh_pointopoint_hello(struct sk_buff *skb) /* * Ethernet router hello message received */ -int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb) +int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtnode_hello_message *msg = (struct rtnode_hello_message *)skb->data; @@ -440,7 +440,7 @@ int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb) /* * Endnode hello message received */ -int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb) +int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb) { struct endnode_hello_message *msg = (struct endnode_hello_message *)skb->data; struct neighbour *neigh; diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index e7b0605ca34a..7ac086d5c0c0 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -714,7 +714,8 @@ out: return ret; } -static int dn_nsp_rx_packet(struct sock *sk2, struct sk_buff *skb) +static int dn_nsp_rx_packet(struct net *net, struct sock *sk2, + struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct sock *sk = NULL; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index fefcd2e85ef9..e930321e2c1d 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -512,7 +512,7 @@ static int dn_return_long(struct sk_buff *skb) * * Returns: result of input function if route is found, error code otherwise */ -static int dn_route_rx_packet(struct sock *sk, struct sk_buff *skb) +static int dn_route_rx_packet(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dn_skb_cb *cb; int err; @@ -610,7 +610,7 @@ drop_it: return NET_RX_DROP; } -static int dn_route_discard(struct sock *sk, struct sk_buff *skb) +static int dn_route_discard(struct net *net, struct sock *sk, struct sk_buff *skb) { /* * I know we drop the packet here, but thats considered success in @@ -620,7 +620,7 @@ static int dn_route_discard(struct sock *sk, struct sk_buff *skb) return NET_RX_SUCCESS; } -static int dn_route_ptp_hello(struct sock *sk, struct sk_buff *skb) +static int dn_route_ptp_hello(struct net *net, struct sock *sk, struct sk_buff *skb) { dn_dev_hello(skb); dn_neigh_pointopoint_hello(skb); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index ae71e9ade5f9..61ff5ea31283 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -621,7 +621,7 @@ out: } EXPORT_SYMBOL(arp_create); -static int arp_xmit_finish(struct sock *sk, struct sk_buff *skb) +static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dev_queue_xmit(skb); } @@ -642,7 +642,7 @@ EXPORT_SYMBOL(arp_xmit); * Process an arp request. */ -static int arp_process(struct sock *sk, struct sk_buff *skb) +static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -654,7 +654,6 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) u16 dev_type = dev->type; int addr_type; struct neighbour *n; - struct net *net = dev_net(dev); bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device @@ -865,7 +864,7 @@ out: static void parp_redo(struct sk_buff *skb) { - arp_process(NULL, skb); + arp_process(dev_net(skb->dev), NULL, skb); } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 0a3c45a2e757..d66cfb35ba74 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -61,9 +61,8 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) } -static int ip_forward_finish(struct sock *sk, struct sk_buff *skb) +static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(net, IPSTATS_MIB_OUTFORWDATAGRAMS); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 991d082c7312..7cc9f7bb7fb7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -188,10 +188,8 @@ bool ip_call_ra_chain(struct sk_buff *skb) return false; } -static int ip_local_deliver_finish(struct sock *sk, struct sk_buff *skb) +static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb->dev); - __skb_pull(skb, skb_network_header_len(skb)); rcu_read_lock(); @@ -311,10 +309,9 @@ drop: int sysctl_ip_early_demux __read_mostly = 1; EXPORT_SYMBOL(sysctl_ip_early_demux); -static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) +static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); - struct net *net = dev_net(skb->dev); struct rtable *rt; if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4c9532259a7f..09a6b7bb7ea3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -104,7 +104,7 @@ static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) ip_send_check(iph); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, - dst_output); + dst_output_okfn); } int __ip_local_out(struct sk_buff *skb) @@ -266,7 +266,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, return ret; } -static int ip_finish_output(struct sock *sk, struct sk_buff *skb) +static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a88c0c5374ff..cfcb996ec51b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1678,10 +1678,10 @@ static void ip_encap(struct net *net, struct sk_buff *skb, nf_reset(skb); } -static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb) +static inline int ipmr_forward_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); - struct net *net = dev_net(skb_dst(skb)->dev); IP_INC_STATS_BH(net, IPSTATS_MIB_OUTFORWDATAGRAMS); IP_ADD_STATS_BH(net, IPSTATS_MIB_OUTOCTETS, skb->len); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 2045b1aaa6ef..28ef8a913130 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -413,7 +413,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, - dst_output); + dst_output_okfn); if (err > 0) err = net_xmit_errno(err); if (err) diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 5093000d3d5e..62e1e72db461 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -22,7 +22,8 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) return xfrm4_extract_header(skb); } -static inline int xfrm4_rcv_encap_finish(struct sock *sk, struct sk_buff *skb) +static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) { if (!skb_dst(skb)) { const struct iphdr *iph = ip_hdr(skb); diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index e4a85199e015..28ae2048b93a 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -80,7 +80,7 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb) return xfrm_output(sk, skb); } -static int __xfrm4_output(struct sock *sk, struct sk_buff *skb) +static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct xfrm_state *x = skb_dst(skb)->xfrm; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 583cf959c23d..9075acf081dd 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -47,7 +47,7 @@ #include #include -int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb) +int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct inet6_protocol *ipprot; @@ -199,9 +199,8 @@ drop: */ -static int ip6_input_finish(struct sock *sk, struct sk_buff *skb) +static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); const struct inet6_protocol *ipprot; struct inet6_dev *idev; unsigned int nhoff; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 96e76ddd4a44..d8d68e81d123 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -121,7 +121,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) return -EINVAL; } -static int ip6_finish_output(struct sock *sk, struct sk_buff *skb) +static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)) || @@ -225,7 +225,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, IPSTATS_MIB_OUT, skb->len); return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, - dst_output); + dst_output_okfn); } skb->dev = dst->dev; @@ -317,7 +317,8 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) return 0; } -static inline int ip6_forward_finish(struct sock *sk, struct sk_buff *skb) +static inline int ip6_forward_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) { skb_sender_cpu_clear(skb); return dst_output(sk, skb); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e830942b2090..5e5d16e7ce85 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1985,9 +1985,8 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) } #endif -static inline int ip6mr_forward2_finish(struct sock *sk, struct sk_buff *skb) +static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 124338a39e29..a8bf57ca74d3 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1646,7 +1646,7 @@ static void mld_sendpack(struct sk_buff *skb) err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, net->ipv6.igmp_sk, skb, NULL, skb->dev, - dst_output); + dst_output_okfn); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); @@ -2010,7 +2010,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb->dev, - dst_output); + dst_output_okfn); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index dd2b08d7c8d1..dde5a1e5875a 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -465,7 +465,7 @@ static void ndisc_send_skb(struct sk_buff *skb, err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, - dst_output); + dst_output_okfn); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 9cc9127fb5e7..e77102c4f804 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -151,7 +151,7 @@ static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, - dst_output); + dst_output_okfn); } int __ip6_local_out(struct sk_buff *skb) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index dc65ec198f7c..fec0151522a2 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -655,7 +655,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, - NULL, rt->dst.dev, dst_output); + NULL, rt->dst.dev, dst_output_okfn); if (err > 0) err = net_xmit_errno(err); if (err) diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 431ae2c22234..68a996f8a044 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -131,7 +131,7 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb) return xfrm_output(sk, skb); } -static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) +static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 65c996c14bca..cc7299033af8 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -574,7 +574,7 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!skb->sk) skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, ip_vs_conn_net(cp), NULL, skb, - NULL, skb_dst(skb)->dev, dst_output); + NULL, skb_dst(skb)->dev, dst_output_okfn); } else ret = NF_ACCEPT; @@ -596,7 +596,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!skb->sk) skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, ip_vs_conn_net(cp), NULL, skb, - NULL, skb_dst(skb)->dev, dst_output); + NULL, skb_dst(skb)->dev, dst_output_okfn); } else ret = NF_ACCEPT; return ret; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 96777f9a9350..9f3c3c25fa73 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -215,7 +215,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) case NF_ACCEPT: case NF_STOP: local_bh_disable(); - entry->state.okfn(entry->state.sk, skb); + entry->state.okfn(entry->state.net, entry->state.sk, skb); local_bh_enable(); break; case NF_QUEUE: diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index c21f1a02ce13..61ba99f61dc8 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -19,7 +19,7 @@ #include #include -static int xfrm_output2(struct sock *sk, struct sk_buff *skb); +static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb); static int xfrm_skb_check_space(struct sk_buff *skb) { @@ -157,12 +157,12 @@ out: } EXPORT_SYMBOL_GPL(xfrm_output_resume); -static int xfrm_output2(struct sock *sk, struct sk_buff *skb) +static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { return xfrm_output_resume(skb, 1); } -static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb) +static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb) { struct sk_buff *segs; @@ -178,7 +178,7 @@ static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb) int err; segs->next = NULL; - err = xfrm_output2(sk, segs); + err = xfrm_output2(net, sk, segs); if (unlikely(err)) { kfree_skb_list(nskb); @@ -197,7 +197,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) int err; if (skb_is_gso(skb)) - return xfrm_output_gso(sk, skb); + return xfrm_output_gso(net, sk, skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { err = skb_checksum_help(skb); @@ -208,7 +208,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) } } - return xfrm_output2(sk, skb); + return xfrm_output2(net, sk, skb); } EXPORT_SYMBOL_GPL(xfrm_output); -- cgit v1.3-14-g43fede From 27b29f63058d26c6c1742f1993338280d5a41dc6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Sep 2015 23:05:43 -0700 Subject: bpf: add bpf_redirect() helper Existing bpf_clone_redirect() helper clones skb before redirecting it to RX or TX of destination netdev. Introduce bpf_redirect() helper that does that without cloning. Benchmarked with two hosts using 10G ixgbe NICs. One host is doing line rate pktgen. Another host is configured as: $ tc qdisc add dev $dev ingress $ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \ action bpf run object-file tcbpf1_kern.o section clone_redirect_xmit drop so it receives the packet on $dev and immediately xmits it on $dev + 1 The section 'clone_redirect_xmit' in tcbpf1_kern.o file has the program that does bpf_clone_redirect() and performance is 2.0 Mpps $ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \ action bpf run object-file tcbpf1_kern.o section redirect_xmit drop which is using bpf_redirect() - 2.4 Mpps and using cls_bpf with integrated actions as: $ tc filter add dev $dev root pref 10 \ bpf run object-file tcbpf1_kern.o section redirect_xmit integ_act classid 1 performance is 2.5 Mpps To summarize: u32+act_bpf using clone_redirect - 2.0 Mpps u32+act_bpf using redirect - 2.4 Mpps cls_bpf using redirect - 2.5 Mpps For comparison linux bridge in this setup is doing 2.1 Mpps and ixgbe rx + drop in ip_rcv - 7.8 Mpps Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/net/sch_generic.h | 1 + include/uapi/linux/bpf.h | 8 ++++++++ include/uapi/linux/pkt_cls.h | 1 + net/core/dev.c | 8 ++++++++ net/core/filter.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ net/sched/act_bpf.c | 1 + net/sched/cls_bpf.c | 1 + samples/bpf/bpf_helpers.h | 4 ++++ samples/bpf/tcbpf1_kern.c | 24 +++++++++++++++++++++++- 9 files changed, 91 insertions(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index da61febb9091..4c79ce8c1f92 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -402,6 +402,7 @@ void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); 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 *); /* 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/bpf.h b/include/uapi/linux/bpf.h index 2fbd1c71fa3b..4ec0b5488294 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -272,6 +272,14 @@ enum bpf_func_id { BPF_FUNC_skb_get_tunnel_key, BPF_FUNC_skb_set_tunnel_key, BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */ + /** + * bpf_redirect(ifindex, flags) - redirect to another netdev + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: TC_ACT_REDIRECT + */ + BPF_FUNC_redirect, __BPF_FUNC_MAX_ID, }; diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 0a262a83f9d4..439873775d49 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -87,6 +87,7 @@ enum { #define TC_ACT_STOLEN 4 #define TC_ACT_QUEUED 5 #define TC_ACT_REPEAT 6 +#define TC_ACT_REDIRECT 7 #define TC_ACT_JUMP 0x10000000 /* Action type identifiers*/ diff --git a/net/core/dev.c b/net/core/dev.c index 00dccfac8939..ee0d6286f934 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3670,6 +3670,14 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, case TC_ACT_QUEUED: kfree_skb(skb); return NULL; + case TC_ACT_REDIRECT: + /* skb_mac_header check was done by cls/act_bpf, so + * we can safely push the L2 header back before + * redirecting to another netdev + */ + __skb_push(skb, skb->mac_len); + skb_do_redirect(skb); + return NULL; default: break; } diff --git a/net/core/filter.c b/net/core/filter.c index 971d6ba89758..da3f3d94d6e9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1427,6 +1427,48 @@ const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; +struct redirect_info { + u32 ifindex; + u32 flags; +}; + +static DEFINE_PER_CPU(struct redirect_info, redirect_info); +static u64 bpf_redirect(u64 ifindex, u64 flags, u64 r3, u64 r4, u64 r5) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + + ri->ifindex = ifindex; + ri->flags = flags; + return TC_ACT_REDIRECT; +} + +int skb_do_redirect(struct sk_buff *skb) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct net_device *dev; + + dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex); + ri->ifindex = 0; + if (unlikely(!dev)) { + kfree_skb(skb); + return -EINVAL; + } + + if (BPF_IS_REDIRECT_INGRESS(ri->flags)) + return dev_forward_skb(dev, skb); + + skb->dev = dev; + return dev_queue_xmit(skb); +} + +const struct bpf_func_proto bpf_redirect_proto = { + .func = bpf_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return task_get_classid((struct sk_buff *) (unsigned long) r1); @@ -1607,6 +1649,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_key_proto(); + case BPF_FUNC_redirect: + return &bpf_redirect_proto; default: return sk_filter_func_proto(func_id); } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 559bfa011bda..0bc6f912f870 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -72,6 +72,7 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, case TC_ACT_PIPE: case TC_ACT_RECLASSIFY: case TC_ACT_OK: + case TC_ACT_REDIRECT: action = filter_res; break; case TC_ACT_SHOT: diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 77b0ef148256..0590816ab7b0 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -70,6 +70,7 @@ static int cls_bpf_exec_opcode(int code) case TC_ACT_PIPE: case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_REDIRECT: case TC_ACT_UNSPEC: return code; default: diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 3a44d3a272af..21aa1b44c30c 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -33,6 +33,10 @@ static int (*bpf_get_current_comm)(void *buf, int buf_size) = (void *) BPF_FUNC_get_current_comm; static int (*bpf_perf_event_read)(void *map, int index) = (void *) BPF_FUNC_perf_event_read; +static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) = + (void *) BPF_FUNC_clone_redirect; +static int (*bpf_redirect)(int ifindex, int flags) = + (void *) BPF_FUNC_redirect; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c index 9bfb2eb34563..fa051b3d53ee 100644 --- a/samples/bpf/tcbpf1_kern.c +++ b/samples/bpf/tcbpf1_kern.c @@ -5,7 +5,7 @@ #include #include #include - +#include #include "bpf_helpers.h" /* compiler workaround */ @@ -64,4 +64,26 @@ int bpf_prog1(struct __sk_buff *skb) return 0; } +SEC("redirect_xmit") +int _redirect_xmit(struct __sk_buff *skb) +{ + return bpf_redirect(skb->ifindex + 1, 0); +} +SEC("redirect_recv") +int _redirect_recv(struct __sk_buff *skb) +{ + return bpf_redirect(skb->ifindex + 1, 1); +} +SEC("clone_redirect_xmit") +int _clone_redirect_xmit(struct __sk_buff *skb) +{ + bpf_clone_redirect(skb, skb->ifindex + 1, 0); + return TC_ACT_SHOT; +} +SEC("clone_redirect_recv") +int _clone_redirect_recv(struct __sk_buff *skb) +{ + bpf_clone_redirect(skb, skb->ifindex + 1, 1); + return TC_ACT_SHOT; +} char _license[] SEC("license") = "GPL"; -- cgit v1.3-14-g43fede From 6ea29da1d04f56e167ec8cc5ed15e927997d9d67 Mon Sep 17 00:00:00 2001 From: Michal Kubeček Date: Thu, 24 Sep 2015 10:59:05 +0200 Subject: net: remove unused argument of __netdev_find_adj() The __netdev_find_adj() helper does not use its first argument, only the device to find and list to walk through. Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- net/core/dev.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index ee0d6286f934..464c22b6261a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4865,8 +4865,7 @@ struct netdev_adjacent { struct rcu_head rcu; }; -static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, - struct net_device *adj_dev, +static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, struct list_head *adj_list) { struct netdev_adjacent *adj; @@ -4892,7 +4891,7 @@ bool netdev_has_upper_dev(struct net_device *dev, { ASSERT_RTNL(); - return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper); + return __netdev_find_adj(upper_dev, &dev->all_adj_list.upper); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -5154,7 +5153,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, struct netdev_adjacent *adj; int ret; - adj = __netdev_find_adj(dev, adj_dev, dev_list); + adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { adj->ref_nr++; @@ -5210,7 +5209,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, { struct netdev_adjacent *adj; - adj = __netdev_find_adj(dev, adj_dev, dev_list); + adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { pr_err("tried to remove device %s from %s\n", @@ -5331,10 +5330,10 @@ static int __netdev_upper_dev_link(struct net_device *dev, return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ - if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) + if (__netdev_find_adj(dev, &upper_dev->all_adj_list.upper)) return -EBUSY; - if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper)) + if (__netdev_find_adj(upper_dev, &dev->adj_list.upper)) return -EEXIST; if (master && netdev_master_upper_dev_get(dev)) @@ -5612,7 +5611,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev, if (!lower_dev) return NULL; - lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower); + lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower); if (!lower) return NULL; -- cgit v1.3-14-g43fede From 004a5d0140ce1d05c1f5fce5df4baa2717a330e0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:10 -0700 Subject: net: use sk_fullsock() in __netdev_pick_tx() SYN_RECV & TIMEWAIT sockets are not full blown, they do not have a sk_dst_cache pointer. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 1 + net/core/dev.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net/core/dev.c') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index dd423d840852..f83669460d82 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -92,6 +92,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) req->rsk_listener = sk_listener; req_to_sk(req)->sk_prot = sk_listener->sk_prot; sk_node_init(&req_to_sk(req)->sk_node); + sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; /* Following is temporary. It is coupled with debugging * helpers in reqsk_put() & reqsk_free() diff --git a/net/core/dev.c b/net/core/dev.c index 323c04edd779..a229bf0d649d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2974,6 +2974,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) new_index = skb_tx_hash(dev, skb); if (queue_index != new_index && sk && + sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); -- cgit v1.3-14-g43fede From 573c7ba006edbecff0714db651dd3602b9d0a6a0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 16 Oct 2015 14:01:22 +0200 Subject: net: introduce pre-change upper device notifier This newly introduced netdevice notifier is called before actual change upper happens. That provides a possibility for notifier handlers to know upper change will happen and react to it, including possibility to forbid the change. That is valuable for drivers which can check if the upper device linkage is supported and forbid that in case it is not. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 9 +++++++++ 2 files changed, 10 insertions(+) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b3374402c1ea..69fdd427c8cb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2106,6 +2106,7 @@ struct pcpu_sw_netstats { #define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ #define NETDEV_CHANGEINFODATA 0x0018 #define NETDEV_BONDING_INFO 0x0019 +#define NETDEV_PRECHANGEUPPER 0x001A int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); diff --git a/net/core/dev.c b/net/core/dev.c index a229bf0d649d..1225b4be8ed6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5346,6 +5346,12 @@ static int __netdev_upper_dev_link(struct net_device *dev, changeupper_info.master = master; changeupper_info.linking = true; + ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + &changeupper_info.info); + ret = notifier_to_errno(ret); + if (ret) + return ret; + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, master); if (ret) @@ -5488,6 +5494,9 @@ void netdev_upper_dev_unlink(struct net_device *dev, changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; changeupper_info.linking = false; + call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + &changeupper_info.info); + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); /* Here is the tricky part. We must remove all dev's lower -- cgit v1.3-14-g43fede From fd867d51f889aec11cca235ebb008578780d052d Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 2 Nov 2015 21:55:59 -0500 Subject: net/core: generic support for disabling netdev features down stack There are some netdev features, which when disabled on an upper device, such as a bonding master or a bridge, must be disabled and cannot be re-enabled on underlying devices. This is a rework of an earlier more heavy-handed appraoch, which simply disables and prevents re-enabling of netdev features listed in a new define in include/net/netdev_features.h, NETIF_F_UPPER_DISABLES. Any upper device that disables a flag in that feature mask, the disabling will propagate down the stack, and any lower device that has any upper device with one of those flags disabled should not be able to enable said flag. Initially, only LRO is included for proof of concept, and because this code effectively does the same thing as dev_disable_lro(), though it will also activate from the ethtool path, which was one of the goals here. [root@dell-per730-01 ~]# ethtool -k bond0 |grep large large-receive-offload: on [root@dell-per730-01 ~]# ethtool -k p5p1 |grep large large-receive-offload: on [root@dell-per730-01 ~]# ethtool -K bond0 lro off [root@dell-per730-01 ~]# ethtool -k bond0 |grep large large-receive-offload: off [root@dell-per730-01 ~]# ethtool -k p5p1 |grep large large-receive-offload: off dmesg dump: [ 1033.277986] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2. [ 1034.067949] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83 [ 1034.753612] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1. [ 1035.591019] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71 This has been successfully tested with bnx2x, qlcnic and netxen network cards as slaves in a bond interface. Turning LRO on or off on the master also turns it on or off on each of the slaves, new slaves are added with LRO in the same state as the master, and LRO can't be toggled on the slaves. Also, this should largely remove the need for dev_disable_lro(), and most, if not all, of its call sites can be replaced by simply making sure NETIF_F_LRO isn't included in the relevant device's feature flags. Note that this patch is driven by bug reports from users saying it was confusing that bonds and slaves had different settings for the same features, and while it won't be 100% in sync if a lower device doesn't support a feature like LRO, I think this is a good step in the right direction. CC: "David S. Miller" CC: Eric Dumazet CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: Jiri Pirko CC: Nikolay Aleksandrov CC: Michal Kubecek CC: Alexander Duyck CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 11 +++++++++ net/core/dev.c | 50 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) (limited to 'net/core/dev.c') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 9672781c593d..0f5837a9b1ba 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -125,6 +125,11 @@ enum { #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) +#define for_each_netdev_feature(mask_addr, feature) \ + int bit; \ + for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) \ + feature = __NETIF_F_BIT(bit); + /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ #define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \ @@ -167,6 +172,12 @@ enum { */ #define NETIF_F_ALL_FOR_ALL (NETIF_F_NOCACHE_COPY | NETIF_F_FSO) +/* + * If upper/master device has these features disabled, they must be disabled + * on all lower/slave devices as well. + */ +#define NETIF_F_UPPER_DISABLES NETIF_F_LRO + /* changeable features with no special hardware requirements */ #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) diff --git a/net/core/dev.c b/net/core/dev.c index 13f49f81ae13..c4d2b430788d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6288,6 +6288,44 @@ static void rollback_registered(struct net_device *dev) list_del(&single); } +static netdev_features_t netdev_sync_upper_features(struct net_device *lower, + struct net_device *upper, netdev_features_t features) +{ + netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; + netdev_features_t feature; + + for_each_netdev_feature(&upper_disables, feature) { + if (!(upper->wanted_features & feature) + && (features & feature)) { + netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n", + &feature, upper->name); + features &= ~feature; + } + } + + return features; +} + +static void netdev_sync_lower_features(struct net_device *upper, + struct net_device *lower, netdev_features_t features) +{ + netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; + netdev_features_t feature; + + for_each_netdev_feature(&upper_disables, feature) { + if (!(features & feature) && (lower->features & feature)) { + netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", + &feature, lower->name); + lower->wanted_features &= ~feature; + netdev_update_features(lower); + + if (unlikely(lower->features & feature)) + netdev_WARN(upper, "failed to disable %pNF on %s!\n", + &feature, lower->name); + } + } +} + static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { @@ -6357,7 +6395,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, int __netdev_update_features(struct net_device *dev) { + struct net_device *upper, *lower; netdev_features_t features; + struct list_head *iter; int err = 0; ASSERT_RTNL(); @@ -6370,6 +6410,10 @@ int __netdev_update_features(struct net_device *dev) /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); + /* some features can't be enabled if they're off an an upper device */ + netdev_for_each_upper_dev_rcu(dev, upper, iter) + features = netdev_sync_upper_features(dev, upper, features); + if (dev->features == features) return 0; @@ -6386,6 +6430,12 @@ int __netdev_update_features(struct net_device *dev) return -1; } + /* some features must be disabled on lower devices when disabled + * on an upper device (think: bonding master or bridge) + */ + netdev_for_each_lower_dev(dev, lower, iter) + netdev_sync_lower_features(dev, lower, features); + if (!err) dev->features = features; -- cgit v1.3-14-g43fede From 5ba3f7d61a3a9e6d94462b207d302931b53d8c61 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Tue, 3 Nov 2015 10:15:59 -0500 Subject: net/core: fix for_each_netdev_feature As pointed out by Nikolay and further explained by Geert, the initial for_each_netdev_feature macro was broken, as feature would get set outside of the block of code it was intended to run in, thus only ever working for the first feature bit in the mask. While less pretty this way, this is tested and confirmed functional with multiple feature bits set in NETIF_F_UPPER_DISABLES. [root@dell-per730-01 ~]# ethtool -K bond0 lro off ... [ 242.761394] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2. [ 243.552178] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83 [ 244.353978] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1. [ 245.147420] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71 [root@dell-per730-01 ~]# ethtool -K bond0 gro off ... [ 251.925645] bond0: Disabling feature 0x0000000000004000 on lower dev p5p2. [ 252.713693] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83 [ 253.499085] bond0: Disabling feature 0x0000000000004000 on lower dev p5p1. [ 254.290922] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71 Fixes: fd867d51f ("net/core: generic support for disabling netdev features down stack") CC: "David S. Miller" CC: Eric Dumazet CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: Jiri Pirko CC: Nikolay Aleksandrov CC: Michal Kubecek CC: Alexander Duyck CC: Geert Uytterhoeven CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 6 ++---- net/core/dev.c | 8 ++++++-- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 0f5837a9b1ba..f0d87347df19 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -125,10 +125,8 @@ enum { #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) -#define for_each_netdev_feature(mask_addr, feature) \ - int bit; \ - for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) \ - feature = __NETIF_F_BIT(bit); +#define for_each_netdev_feature(mask_addr, bit) \ + for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/net/core/dev.c b/net/core/dev.c index c4d2b430788d..8ce3f74cd6b9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6293,8 +6293,10 @@ static netdev_features_t netdev_sync_upper_features(struct net_device *lower, { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; + int feature_bit; - for_each_netdev_feature(&upper_disables, feature) { + for_each_netdev_feature(&upper_disables, feature_bit) { + feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n", @@ -6311,8 +6313,10 @@ static void netdev_sync_lower_features(struct net_device *upper, { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; + int feature_bit; - for_each_netdev_feature(&upper_disables, feature) { + for_each_netdev_feature(&upper_disables, feature_bit) { + feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); -- cgit v1.3-14-g43fede