From 8b58a39846568dcd7d0c98b2fadc25018e59dedf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Jul 2015 23:32:12 +0200 Subject: ipv6: use flag instead of u16 for hop in inet6_skb_parm Hop was always either 0 or sizeof(struct ipv6hdr). Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 82806c60aa42..1319a6bb6b82 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -94,7 +94,6 @@ static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) struct inet6_skb_parm { int iif; __be16 ra; - __u16 hop; __u16 dst0; __u16 srcrt; __u16 dst1; @@ -111,6 +110,7 @@ struct inet6_skb_parm { #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 #define IP6SKB_FRAGMENTED 16 +#define IP6SKB_HOPBYHOP 32 }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) -- cgit v1.2.3 From 634ec36cc0ab9d8dda0f2c101fa28d2e2a61b9eb Mon Sep 17 00:00:00 2001 From: David Thomson Date: Fri, 10 Jul 2015 13:56:54 +1200 Subject: net: phy: Pass mdix ethtool setting through to phy driver Pass the mdix setting from ethtool down to the phy driver, to allow driver specific implementations of manually setting the polarity. Signed-off-by: David Thomson Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index a26c3f84b8dd..e5fb1d415961 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -424,6 +424,8 @@ struct phy_device { struct net_device *attached_dev; + u8 mdix; + void (*adjust_link)(struct net_device *dev); }; #define to_phy_device(d) container_of(d, struct phy_device, dev) -- cgit v1.2.3 From 70aa996601335ca3069190ebcdae8870828086a8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 10 Jul 2015 18:13:20 -0500 Subject: netfilter: kill nf_hooks_active The function obscures what is going on in nf_hook_thresh and it's existence requires computing the hook list twice. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 00050dfd9f23..60e89348a91d 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -150,11 +150,6 @@ static inline bool nf_hook_list_active(struct list_head *nf_hook_list, } #endif -static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) -{ - return nf_hook_list_active(&nf_hooks[pf][hook], pf, hook); -} - int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); /** @@ -172,10 +167,12 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int (*okfn)(struct sock *, struct sk_buff *), int thresh) { - if (nf_hooks_active(pf, hook)) { + struct list_head *nf_hook_list = &nf_hooks[pf][hook]; + + if (nf_hook_list_active(nf_hook_list, pf, hook)) { struct nf_hook_state state; - nf_hook_state_init(&state, &nf_hooks[pf][hook], hook, thresh, + nf_hook_state_init(&state, nf_hook_list, hook, thresh, pf, indev, outdev, sk, okfn); return nf_hook_slow(skb, &state); } -- cgit v1.2.3 From 085db2c04557d31db61541f361bd8b4de92c9939 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 10 Jul 2015 18:15:06 -0500 Subject: netfilter: Per network namespace netfilter hooks. - Add a new set of functions for registering and unregistering per network namespace hooks. - Modify the old global namespace hook functions to use the per network namespace hooks in their implementation, so their remains a single list that needs to be walked for any hook (this is important for keeping the hook priority working and for keeping the code walking the hooks simple). - Only allow registering the per netdevice hooks in the network namespace where the network device lives. - Dynamically allocate the structures in the per network namespace hook list in nf_register_net_hook, and unregister them in nf_unregister_net_hook. Dynamic allocate is required somewhere as the number of network namespaces are not fixed so we might as well allocate them in the registration function. The chain of registered hooks on any list is expected to be small so the cost of walking that list to find the entry we are unregistering should also be small. Performing the management of the dynamically allocated list entries in the registration and unregistration functions keeps the complexity from spreading. Signed-off-by: "Eric W. Biederman" --- include/linux/netfilter.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 60e89348a91d..9bbd110ec81b 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -11,6 +11,8 @@ #include #include #include +#include +#include #ifdef CONFIG_NETFILTER static inline int NF_DROP_GETERR(int verdict) @@ -118,6 +120,13 @@ struct nf_sockopt_ops { }; /* Function to register/unregister hook points. */ +int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops); +void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops); +int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n); +void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n); + int nf_register_hook(struct nf_hook_ops *reg); void nf_unregister_hook(struct nf_hook_ops *reg); int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); @@ -128,8 +137,6 @@ void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); int nf_register_sockopt(struct nf_sockopt_ops *reg); void nf_unregister_sockopt(struct nf_sockopt_ops *reg); -extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; - #ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; @@ -167,7 +174,8 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int (*okfn)(struct sock *, struct sk_buff *), int thresh) { - struct list_head *nf_hook_list = &nf_hooks[pf][hook]; + struct net *net = dev_net(indev ? indev : outdev); + struct list_head *nf_hook_list = &net->nf.hooks[pf][hook]; if (nf_hook_list_active(nf_hook_list, pf, hook)) { struct nf_hook_state state; -- cgit v1.2.3 From e7c8899f3e6f2830136cf6e115c4a55ce7a3920a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 14 Jul 2015 17:51:07 +0200 Subject: netfilter: move tee_active to core This prepares for a TEE like expression in nftables. We want to ensure only one duplicate is sent, so both will use the same percpu variable to detect duplication. The other use case is detection of recursive call to xtables, but since we don't want dependency from nft to xtables core its put into core.c instead of the x_tables core. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 9bbd110ec81b..e01da73ee6c4 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -390,4 +390,15 @@ extern struct nfq_ct_hook __rcu *nfq_ct_hook; static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif +/** + * nf_skb_duplicated - TEE target has sent a packet + * + * When a xtables target sends a packet, the OUTPUT and POSTROUTING + * hooks are traversed again, i.e. nft and xtables are invoked recursively. + * + * This is used by xtables TEE target to prevent the duplicated skb from + * being duplicated again. + */ +DECLARE_PER_CPU(bool, nf_skb_duplicated); + #endif /*__LINUX_NETFILTER_H*/ -- cgit v1.2.3 From 7814b6ec6d0d63444abdb49554166c8cfcbd063e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 14 Jul 2015 17:51:08 +0200 Subject: netfilter: xtables: don't save/restore jumpstack offset In most cases there is no reentrancy into ip/ip6tables. For skbs sent by REJECT or SYNPROXY targets, there is one level of reentrancy, but its not relevant as those targets issue an absolute verdict, i.e. the jumpstack can be clobbered since its not used after the target issues absolute verdict (ACCEPT, DROP, STOLEN, etc). So the only special case where it is relevant is the TEE target, which returns XT_CONTINUE. This patch changes ip(6)_do_table to always use the jump stack starting from 0. When we detect we're operating on an skb sent via TEE (percpu nf_skb_duplicated is 1) we switch to an alternate stack to leave the original one alone. Since there is no TEE support for arptables, it doesn't need to test if tee is active. The jump stack overflow tests are no longer needed as well -- since ->stacksize is the largest call depth we cannot exceed it. A much better alternative to the external jumpstack would be to just declare a jumps[32] stack on the local stack frame, but that would mean we'd have to reject iptables rulesets that used to work before. Another alternative would be to start rejecting rulesets with a larger call depth, e.g. 1000 -- in this case it would be feasible to allocate the entire stack in the percpu area which would avoid one dereference. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 286098a5667f..149284557ca7 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -222,7 +222,6 @@ struct xt_table_info { * @stacksize jumps (number of user chains) can possibly be made. */ unsigned int stacksize; - unsigned int __percpu *stackptr; void ***jumpstack; unsigned char entries[0] __aligned(8); -- cgit v1.2.3 From dcebd3153e0a7749bb054ab73fa4e1ca33e9d3f9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 14 Jul 2015 17:51:09 +0200 Subject: netfilter: add and use jump label for xt_tee Don't bother testing if we need to switch to alternate stack unless TEE target is used. Suggested-by: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 149284557ca7..b006b719183f 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -3,6 +3,7 @@ #include +#include #include /** @@ -280,6 +281,12 @@ void xt_free_table_info(struct xt_table_info *info); */ DECLARE_PER_CPU(seqcount_t, xt_recseq); +/* xt_tee_enabled - true if x_tables needs to handle reentrancy + * + * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. + */ +extern struct static_key xt_tee_enabled; + /** * xt_write_recseq_begin - start of a write section * -- cgit v1.2.3 From d746d707a8b1421a4ba46b497cb5d59e20161645 Mon Sep 17 00:00:00 2001 From: Anuradha Karuppiah Date: Tue, 14 Jul 2015 13:43:19 -0700 Subject: net core: Add protodown support. This patch introduces the proto_down flag that can be used by user space applications to notify switch drivers that errors have been detected on the device. The switch driver can react to protodown notification by doing a phys down on the associated switch port. Signed-off-by: Anuradha Karuppiah Signed-off-by: Andy Gospodarek Signed-off-by: Roopa Prabhu Signed-off-by: Wilson Kok Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e20979dfd6a9..45cfd797eb77 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1041,6 +1041,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. + * void (*ndo_change_proto_down)(struct net_device *dev, + * bool proto_down); + * This function is used to pass protocol port error state information + * to the switch driver. The switch driver can react to the proto_down + * by doing a phys down on the associated switch port. + * */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1211,6 +1217,8 @@ struct net_device_ops { int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); + int (*ndo_change_proto_down)(struct net_device *dev, + bool proto_down); }; /** @@ -1502,6 +1510,10 @@ enum netdev_priv_flags { * * @qdisc_tx_busylock: XXX: need comments on this one * + * @proto_down: protocol port state information can be sent to the + * switch driver and used to set the phys state of the + * switch port. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -1762,6 +1774,7 @@ struct net_device { #endif struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; + bool proto_down; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2982,6 +2995,7 @@ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); +int dev_change_proto_down(struct net_device *dev, bool proto_down); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -- cgit v1.2.3 From 0c4f691ff6791e55ac831666df0b49b1679c56e4 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sat, 18 Jul 2015 18:24:48 -0700 Subject: net: don't reforward packets already forwarded by offload device Just before queuing skb for xmit on port, check if skb has been marked by switchdev port driver as already fordwarded by device. If so, drop skb. A non-zero skb->offload_fwd_mark field is set by the switchdev port driver/device on ingress to indicate the skb has already been forwarded by the device to egress ports with matching dev->skb_mark. The switchdev port driver would assign a non-zero dev->offload_skb_mark for each device port netdev during registration, for example. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Acked-by: Roopa Prabhu Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++++ include/linux/skbuff.h | 9 ++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 45cfd797eb77..8364f29e08be 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1456,6 +1456,8 @@ enum netdev_priv_flags { * * @xps_maps: XXX: need comments on this one * + * @offload_fwd_mark: Offload device fwding mark + * * @trans_start: Time (in jiffies) of last Tx * @watchdog_timeo: Represents the timeout that is used by * the watchdog ( see dev_watchdog() ) @@ -1697,6 +1699,10 @@ struct net_device { struct xps_dev_maps __rcu *xps_maps; #endif +#ifdef CONFIG_NET_SWITCHDEV + u32 offload_fwd_mark; +#endif + /* These may be needed for future network-power-down code. */ /* diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d6cdd6e87d53..af7a09650fa2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -506,6 +506,7 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking + * @offload_fwd_mark: fwding offload mark * @mark: Generic packet mark * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information @@ -650,9 +651,15 @@ struct sk_buff { unsigned int sender_cpu; }; #endif + union { #ifdef CONFIG_NETWORK_SECMARK - __u32 secmark; + __u32 secmark; +#endif +#ifdef CONFIG_NET_SWITCHDEV + __u32 offload_fwd_mark; #endif + }; + union { __u32 mark; __u32 reserved_tailroom; -- cgit v1.2.3 From d754f98b502ad9a8c7570d494e1eaa0e6bc0350c Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sat, 18 Jul 2015 18:24:49 -0700 Subject: net: add phys ID compare helper to test if two IDs are the same Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8364f29e08be..607b5f41f46f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -766,6 +766,13 @@ struct netdev_phys_item_id { unsigned char id_len; }; +static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, + struct netdev_phys_item_id *b) +{ + return a->id_len == b->id_len && + memcmp(a->id, b->id, a->id_len) == 0; +} + typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3 From 6acc23266054a9969737b435fa012f87465dbc50 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 16 Jul 2015 21:50:50 +0200 Subject: net: remove skb_frag_add_head It's not used anywhere. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index af7a09650fa2..6bd96fe9416a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2678,12 +2678,6 @@ static inline void skb_frag_list_init(struct sk_buff *skb) skb_shinfo(skb)->frag_list = NULL; } -static inline void skb_frag_add_head(struct sk_buff *skb, struct sk_buff *frag) -{ - frag->next = skb_shinfo(skb)->frag_list; - skb_shinfo(skb)->frag_list = frag; -} - #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) -- cgit v1.2.3 From f4c190eb8b4f80b12dc98ce7d54a3bea0e4e7e69 Mon Sep 17 00:00:00 2001 From: Joachim Eastwood Date: Fri, 17 Jul 2015 00:26:12 +0200 Subject: stmmac: drop custom_* fields from plat_stmmacenet_data Both of these fields are unused and has been unused since they were added 3 and 5 years ago. Drop them since they are clearly not very useful. Signed-off-by: Joachim Eastwood Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c735f5c91eea..c86a20047cb1 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -123,8 +123,6 @@ struct plat_stmmacenet_data { void (*free)(struct platform_device *pdev, void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); - void *custom_cfg; - void *custom_data; void *bsp_priv; }; -- cgit v1.2.3 From 4e10df9a60d96ced321dd2af71da558c6b750078 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 20 Jul 2015 20:34:18 -0700 Subject: bpf: introduce bpf_skb_vlan_push/pop() helpers Allow eBPF programs attached to TC qdiscs call skb_vlan_push/pop via helper functions. These functions may change skb->data/hlen which are cached by some JITs to improve performance of ld_abs/ld_ind instructions. Therefore JITs need to recognize bpf_skb_vlan_push/pop() calls, re-compute header len and re-cache skb->data/hlen back into cpu registers. Note, skb->data/hlen are not directly accessible from the programs, so any changes to skb->data done either by these helpers or by other TC actions are safe. eBPF JIT supported by three architectures: - arm64 JIT is using bpf_load_pointer() without caching, so it's ok as-is. - x64 JIT re-caches skb->data/hlen unconditionally after vlan_push/pop calls (experiments showed that conditional re-caching is slower). - s390 JIT falls back to interpreter for now when bpf_skb_vlan_push() is present in the program (re-caching is tbd). These helpers allow more scalable handling of vlan from the programs. Instead of creating thousands of vlan netdevs on top of eth0 and attaching TC+ingress+bpf to all of them, the program can be attached to eth0 directly and manipulate vlans as necessary. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 ++ include/linux/filter.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4383476a0d48..139d6d2e123f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -192,5 +192,7 @@ extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; +extern const struct bpf_func_proto bpf_skb_vlan_push_proto; +extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; #endif /* _LINUX_BPF_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 17724f6ea983..69d00555ce35 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -411,6 +411,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); void bpf_int_jit_compile(struct bpf_prog *fp); +bool bpf_helper_changes_skb_data(void *func); #ifdef CONFIG_BPF_JIT typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); -- cgit v1.2.3 From 499a24256862714539e902c0499b67da2bb3ab72 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Tue, 21 Jul 2015 10:43:46 +0200 Subject: lwtunnel: infrastructure for handling light weight tunnels like mpls Provides infrastructure to parse/dump/store encap information for light weight tunnels like mpls. Encap information for such tunnels is associated with fib routes. This infrastructure is based on previous suggestions from Eric Biederman to follow the xfrm infrastructure. Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/lwtunnel.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/lwtunnel.h (limited to 'include/linux') diff --git a/include/linux/lwtunnel.h b/include/linux/lwtunnel.h new file mode 100644 index 000000000000..97f32f8b4ae1 --- /dev/null +++ b/include/linux/lwtunnel.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_LWTUNNEL_H_ +#define _LINUX_LWTUNNEL_H_ + +#include + +#endif /* _LINUX_LWTUNNEL_H_ */ -- cgit v1.2.3 From e3e4712ec0961ed586a8db340bd994c4ad7f5dba Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Tue, 21 Jul 2015 10:43:53 +0200 Subject: mpls: ip tunnel support This implementation uses lwtunnel infrastructure to register hooks for mpls tunnel encaps. It picks cues from iptunnel_encaps infrastructure and previous mpls iptunnel RFC patches from Eric W. Biederman and Robert Shearman Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/mpls_iptunnel.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/mpls_iptunnel.h (limited to 'include/linux') diff --git a/include/linux/mpls_iptunnel.h b/include/linux/mpls_iptunnel.h new file mode 100644 index 000000000000..ef29eb2d6dfd --- /dev/null +++ b/include/linux/mpls_iptunnel.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_MPLS_IPTUNNEL_H +#define _LINUX_MPLS_IPTUNNEL_H + +#include + +#endif /* _LINUX_MPLS_IPTUNNEL_H */ -- cgit v1.2.3 From ee122c79d4227f6ec642157834b6a90fcffa4382 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 21 Jul 2015 10:43:58 +0200 Subject: vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6bd96fe9416a..648a2c241993 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3469,5 +3469,6 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) skb_network_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ -- cgit v1.2.3 From 3985e8a3611a93bb36789f65db862e5700aab65e Mon Sep 17 00:00:00 2001 From: Erik Kline Date: Wed, 22 Jul 2015 16:38:25 +0900 Subject: ipv6: sysctl to restrict candidate source addresses Per RFC 6724, section 4, "Candidate Source Addresses": It is RECOMMENDED that the candidate source addresses be the set of unicast addresses assigned to the interface that will be used to send to the destination (the "outgoing" interface). Add a sysctl to enable this behaviour. Signed-off-by: Erik Kline Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 1319a6bb6b82..06ed637225b8 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -57,6 +57,7 @@ struct ipv6_devconf { bool initialized; struct in6_addr secret; } stable_secret; + __s32 use_oif_addrs_only; void *sysctl; }; -- cgit v1.2.3 From 3bbd14e0a2e3a988b1b5fe702a2539bd8d0ec622 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 20 Jul 2015 13:32:52 +0200 Subject: netfilter: rename local nf_hook_list to hook_list 085db2c04557 ("netfilter: Per network namespace netfilter hooks.") introduced a new nf_hook_list that is global, so let's avoid this overlap. Signed-off-by: Pablo Neira Ayuso Acked-by: "Eric W. Biederman" --- include/linux/netfilter.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index e01da73ee6c4..d788ce62d826 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -140,20 +140,20 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); #ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; -static inline bool nf_hook_list_active(struct list_head *nf_hook_list, +static inline bool nf_hook_list_active(struct list_head *hook_list, u_int8_t pf, unsigned int hook) { if (__builtin_constant_p(pf) && __builtin_constant_p(hook)) return static_key_false(&nf_hooks_needed[pf][hook]); - return !list_empty(nf_hook_list); + return !list_empty(hook_list); } #else -static inline bool nf_hook_list_active(struct list_head *nf_hook_list, +static inline bool nf_hook_list_active(struct list_head *hook_list, u_int8_t pf, unsigned int hook) { - return !list_empty(nf_hook_list); + return !list_empty(hook_list); } #endif @@ -175,12 +175,12 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int thresh) { struct net *net = dev_net(indev ? indev : outdev); - struct list_head *nf_hook_list = &net->nf.hooks[pf][hook]; + struct list_head *hook_list = &net->nf.hooks[pf][hook]; - if (nf_hook_list_active(nf_hook_list, pf, hook)) { + if (nf_hook_list_active(hook_list, pf, hook)) { struct nf_hook_state state; - nf_hook_state_init(&state, nf_hook_list, hook, thresh, + nf_hook_state_init(&state, hook_list, hook, thresh, pf, indev, outdev, sk, okfn); return nf_hook_slow(skb, &state); } -- cgit v1.2.3 From e0910bace663b78c026b73bbd711a24ccf410531 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 23 Jul 2015 15:43:56 +0200 Subject: lwtunnel: export linux/lwtunnel.h to userspace Note also that include/linux/lwtunnel.h is not needed. CC: Thomas Graf CC: Roopa Prabhu Fixes: 499a24256862 ("lwtunnel: infrastructure for handling light weight tunnels like mpls") Signed-off-by: Nicolas Dichtel Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/lwtunnel.h | 6 ------ 1 file changed, 6 deletions(-) delete mode 100644 include/linux/lwtunnel.h (limited to 'include/linux') diff --git a/include/linux/lwtunnel.h b/include/linux/lwtunnel.h deleted file mode 100644 index 97f32f8b4ae1..000000000000 --- a/include/linux/lwtunnel.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _LINUX_LWTUNNEL_H_ -#define _LINUX_LWTUNNEL_H_ - -#include - -#endif /* _LINUX_LWTUNNEL_H_ */ -- cgit v1.2.3 From 2be6967cdbc95a9960b620defedbf5e02e2af619 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 23 Jul 2015 23:35:56 +0300 Subject: net/mlx5e: Support ETH_RSS_HASH_XOR The ConnectX-4 HW implements inverted XOR8. To make it act as XOR we re-order the HW RSS indirection table. Set XOR to be the default RSS hash function and add ethtool API to control it. Signed-off-by: Saeed Mahameed Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6d2f6fee041c..c60a62bba652 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1936,9 +1936,9 @@ enum { }; enum { - MLX5_TIRC_RX_HASH_FN_HASH_NONE = 0x0, - MLX5_TIRC_RX_HASH_FN_HASH_INVERTED_XOR8 = 0x1, - MLX5_TIRC_RX_HASH_FN_HASH_TOEPLITZ = 0x2, + MLX5_RX_HASH_FN_NONE = 0x0, + MLX5_RX_HASH_FN_INVERTED_XOR8 = 0x1, + MLX5_RX_HASH_FN_TOEPLITZ = 0x2, }; enum { -- cgit v1.2.3 From 311c7c71c9bb8786c96fee353fe9886c08b017fe Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 23 Jul 2015 23:35:57 +0300 Subject: net/mlx5e: Allocate DMA coherent memory on reader NUMA node By affinity hints and XPS, each mlx5e channel is assigned a CPU core. Channel DMA coherent memory that is written by the NIC and read by SW (e.g CQ buffer) is allocated on the NUMA node of the CPU core assigned for the channel. Channel DMA coherent memory that is written by SW and read by the NIC (e.g SQ/RQ buffer) is allocated on the NUMA node of the NIC. Doorbell record (written by SW and read by the NIC) is an exception since it is accessed by SW more frequently. Signed-off-by: Saeed Mahameed Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5722d88c2429..1c0d5d062d7c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -463,6 +463,10 @@ struct mlx5_priv { /* end: mr staff */ /* start: alloc staff */ + /* protect buffer alocation according to numa node */ + struct mutex alloc_mutex; + int numa_node; + struct mutex pgdir_mutex; struct list_head pgdir_list; /* end: alloc staff */ @@ -672,6 +676,8 @@ void mlx5_health_cleanup(void); void __init mlx5_health_init(void); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); +int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, + struct mlx5_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf); struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, @@ -773,6 +779,8 @@ void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db); +int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, + int node); void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); const char *mlx5_command_str(int command); -- cgit v1.2.3 From 88a85f99e51fb2373259ab83c8bb130a9bbf3804 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Thu, 23 Jul 2015 23:35:59 +0300 Subject: net/mlx5e: TX latency optimization to save DMA reads A regular TX WQE execution involves two or more DMA reads - one to fetch the WQE, and another one per WQE gather entry. These DMA reads obviously increase the TX latency. There are two mlx5 mechanisms to bypass these DMA reads: 1) Inline WQE 2) Blue Flame (BF) An inline WQE contains a whole packet, thus saves the DMA read/s of the regular WQE gather entry/s. Inline WQE support was already added in the previous commit. A BF WQE is written directly to the device I/O mapped memory, thus enables saving the DMA read that fetches the WQE. The BF WQE I/O write must be in cache line granularity, thus uses the CPU write combining mechanism. A BF WQE I/O write acts also as a TX doorbell for notifying the device of new TX WQEs. A BF WQE is written to the same I/O mapped address as the regular TX doorbell, thus this address is being mapped twice - once by ioremap() and once by io_mapping_map_wc(). While both mechanisms reduce the TX latency, they both consume more CPU cycles than a regular WQE: - A BF WQE must still be written to host memory, in addition to being written directly to the device I/O mapped memory. - An inline WQE involves copying the SKB data into it. To handle this tradeoff, we introduce here a heuristic algorithm that strives to avoid using these two mechanisms in case the TX queue is being back-pressured by the device, and limit their usage rate otherwise. An inline WQE will always be "Blue Flamed" (written directly to the device I/O mapped memory) while a BF WQE may not be inlined (may contain gather entries). Preliminary testing using netperf UDP_RR shows that the latency goes down from 17.5us to 16.9us, while the message rate (tested with pktgen) stays the same. Signed-off-by: Achiad Shochat Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1c0d5d062d7c..5fe0cae1a515 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -380,7 +380,7 @@ struct mlx5_uar { u32 index; struct list_head bf_list; unsigned free_bf_bmap; - void __iomem *wc_map; + void __iomem *bf_map; void __iomem *map; }; @@ -435,6 +435,8 @@ struct mlx5_priv { struct mlx5_uuar_info uuari; MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock); + struct io_mapping *bf_mapping; + /* pages stuff */ struct workqueue_struct *pg_wq; struct rb_root page_root; -- cgit v1.2.3 From 77fc29c4bbbbd01ee22c50ce8260fd0f2e08c124 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Mon, 27 Jul 2015 14:46:31 +0300 Subject: net/mlx4_core: Preparations for 802.1ad VLAN support mlx4_core preparation to support hardware accelerated 802.1ad VLAN device. To allow 802.1ad accelerated device, "packet has vlan" (phv) Firmware capability should be available. Firmware without the phv capability won't behave properly and can't support 802.1ad device acceleration. The driver checks the Firmware capability and sets the phv bit accordingly in SET_PORT command. Signed-off-by: Hadar Hen Zion Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index fd13c1ce3b4a..bcbf8c72a77b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -211,6 +211,8 @@ enum { MLX4_DEV_CAP_FLAG2_ETS_CFG = 1LL << 26, MLX4_DEV_CAP_FLAG2_PORT_BEACON = 1LL << 27, MLX4_DEV_CAP_FLAG2_IGNORE_FCS = 1LL << 28, + MLX4_DEV_CAP_FLAG2_PHV_EN = 1LL << 29, + MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN = 1LL << 30, }; enum { @@ -581,6 +583,7 @@ struct mlx4_caps { u64 phys_port_id[MLX4_MAX_PORTS + 1]; int tunnel_offload_mode; u8 rx_checksum_flags_port[MLX4_MAX_PORTS + 1]; + u8 phv_bit[MLX4_MAX_PORTS + 1]; u8 alloc_res_qp_mask; u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; @@ -1332,6 +1335,8 @@ int mlx4_SET_PORT_BEACON(struct mlx4_dev *dev, u8 port, u16 time); int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port, u8 ignore_fcs_value); int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable); +int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val); +int get_phv_bit(struct mlx4_dev *dev, u8 port, int *phv); int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx); int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); -- cgit v1.2.3 From e802f8e4c54e6adf4215ef9fa3d6eea8fcb10bf9 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Mon, 27 Jul 2015 14:46:33 +0300 Subject: net/mlx4: Prepare VLAN macros for 802.1ad Hardware accelerated support To add Hardware accelerated support in 802.1ad vlan, replace Current VLAN macros to CVLAN. Replace: MLX4_WQE_CTRL_INS_VLAN MLX4_CQE_VLAN_PRESENT_MASK With: MLX4_WQE_CTRL_INS_CVLAN MLX4_CQE_CVLAN_PRESENT_MASK Signed-off-by: Hadar Hen Zion Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/cq.h | 2 +- include/linux/mlx4/qp.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h index e7ecc12a1163..899a97b20d27 100644 --- a/include/linux/mlx4/cq.h +++ b/include/linux/mlx4/cq.h @@ -88,7 +88,7 @@ struct mlx4_ts_cqe { enum { MLX4_CQE_L2_TUNNEL_IPOK = 1 << 31, - MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29, + MLX4_CQE_CVLAN_PRESENT_MASK = 1 << 29, MLX4_CQE_L2_TUNNEL = 1 << 27, MLX4_CQE_L2_TUNNEL_CSUM = 1 << 26, MLX4_CQE_L2_TUNNEL_IPV4 = 1 << 25, diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 6fed539e5456..6c619006c21f 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -272,7 +272,7 @@ enum { MLX4_WQE_CTRL_SOLICITED = 1 << 1, MLX4_WQE_CTRL_IP_CSUM = 1 << 4, MLX4_WQE_CTRL_TCP_UDP_CSUM = 1 << 5, - MLX4_WQE_CTRL_INS_VLAN = 1 << 6, + MLX4_WQE_CTRL_INS_CVLAN = 1 << 6, MLX4_WQE_CTRL_STRONG_ORDER = 1 << 7, MLX4_WQE_CTRL_FORCE_LOOPBACK = 1 << 0, }; -- cgit v1.2.3 From e38af4faf01d0b35df6995fb395e5fa4a4898289 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Mon, 27 Jul 2015 14:46:34 +0300 Subject: net/mlx4_en: Add support for hardware accelerated 802.1ad vlan To enable device support in accelerated 802.1ad vlan, the port capability "packet has vlan enable" (phv_en) should be set. Firmware won't work properly, in case phv_en is not set. The user can enable "phv_en" port capability with the new ethtool private flag phv-bit. The phv-bit private flag default value is OFF, users who are interested in 802.1ad hardware acceleration should turn ON the phv-bit private flag: $ ethtool --set-priv-flags eth1 phv-bit on Once the private flag is set, the device is ready for 802.1ad vlan acceleration. The user should also change the interface device features and turn on "tx-vlan-stag-hw-insert" which is off by default: $ ethtool -K eth1 tx-vlan-stag-hw-insert on "phv-bit" private flag setting is available only for Physical Functions(PF), the Virtual Function (VF) will be able to use the feature by setting "tx-vlan-stag-hw-insert" ethtool device feature only if the feature was enabled by the Hypervisor. Signed-off-by: Hadar Hen Zion Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/cq.h | 1 + include/linux/mlx4/qp.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h index 899a97b20d27..09cebe528488 100644 --- a/include/linux/mlx4/cq.h +++ b/include/linux/mlx4/cq.h @@ -89,6 +89,7 @@ struct mlx4_ts_cqe { enum { MLX4_CQE_L2_TUNNEL_IPOK = 1 << 31, MLX4_CQE_CVLAN_PRESENT_MASK = 1 << 29, + MLX4_CQE_SVLAN_PRESENT_MASK = 1 << 30, MLX4_CQE_L2_TUNNEL = 1 << 27, MLX4_CQE_L2_TUNNEL_CSUM = 1 << 26, MLX4_CQE_L2_TUNNEL_IPV4 = 1 << 25, diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 6c619006c21f..de45a51b3f04 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -273,6 +273,7 @@ enum { MLX4_WQE_CTRL_IP_CSUM = 1 << 4, MLX4_WQE_CTRL_TCP_UDP_CSUM = 1 << 5, MLX4_WQE_CTRL_INS_CVLAN = 1 << 6, + MLX4_WQE_CTRL_INS_SVLAN = 1 << 7, MLX4_WQE_CTRL_STRONG_ORDER = 1 << 7, MLX4_WQE_CTRL_FORCE_LOOPBACK = 1 << 0, }; -- cgit v1.2.3 From 0933328a1b8adb6c8b2b8c8b823dad0295659c40 Mon Sep 17 00:00:00 2001 From: Joachim Eastwood Date: Wed, 29 Jul 2015 00:09:02 +0200 Subject: stmmac: remove unused stmmac_of_data struct As dwmac-* drivers that need OF match have been converted to use their own internal OF match data structure this can now be removed. Signed-off-by: Joachim Eastwood Signed-off-by: David S. Miller --- include/linux/stmmac.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c86a20047cb1..b43cd56b78e9 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -125,22 +125,4 @@ struct plat_stmmacenet_data { void (*exit)(struct platform_device *pdev, void *priv); void *bsp_priv; }; - -/* of_data for SoC glue layer device tree bindings */ - -struct stmmac_of_data { - int has_gmac; - int enh_desc; - int tx_coe; - int rx_coe; - int bugged_jumbo; - int pmt; - int riwt_off; - void (*fix_mac_speed)(void *priv, unsigned int speed); - void (*bus_setup)(void __iomem *ioaddr); - void *(*setup)(struct platform_device *pdev); - void (*free)(struct platform_device *pdev, void *priv); - int (*init)(struct platform_device *pdev, void *priv); - void (*exit)(struct platform_device *pdev, void *priv); -}; #endif -- cgit v1.2.3 From 75fee59550a9899fd9438ebc0a64c972829a8dd2 Mon Sep 17 00:00:00 2001 From: Joachim Eastwood Date: Wed, 29 Jul 2015 00:09:03 +0200 Subject: stmmac: remove setup/free glue callbacks As all dwmac-* drivers have been converted to have a proper probe function the setup callback can now be removed. Also remove the free callback that wasn't used by any driver. New dwmac-* drivers should implement standard probe and remove functions to preform any needed setup and teardown. Signed-off-by: Joachim Eastwood Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index b43cd56b78e9..eead8ab93c0a 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -119,8 +119,6 @@ struct plat_stmmacenet_data { int rx_fifo_size; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); - void *(*setup)(struct platform_device *pdev); - void (*free)(struct platform_device *pdev, void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); void *bsp_priv; -- cgit v1.2.3 From 72b1e5e4cac72efa6b739b47e41f53e4520b4194 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 Jul 2015 16:21:30 +0200 Subject: netfilter: bridge: reduce nf_bridge_info to 32 bytes again We can use union for most of the temporary cruft (original ipv4/ipv6 address, source mac, physoutdev) since they're used during different stages of br netfilter traversal. Also get rid of the last two ->mask users. Shrinks struct from 48 to 32 on 64bit arch. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 12 +++++++++--- include/linux/skbuff.h | 19 +++++++++++++------ 2 files changed, 22 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 6d80fc686323..2437b8a5d7a9 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -17,9 +17,6 @@ enum nf_br_hook_priorities { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -#define BRNF_BRIDGED_DNAT 0x02 -#define BRNF_NF_BRIDGE_PREROUTING 0x08 - int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); static inline void br_drop_fake_rtable(struct sk_buff *skb) @@ -63,8 +60,17 @@ nf_bridge_get_physoutdev(const struct sk_buff *skb) { return skb->nf_bridge ? skb->nf_bridge->physoutdev : NULL; } + +static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb) +{ + return skb->nf_bridge && skb->nf_bridge->in_prerouting; +} #else #define br_drop_fake_rtable(skb) do { } while (0) +static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb) +{ + return false; +} #endif /* CONFIG_BRIDGE_NETFILTER */ #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d6cdd6e87d53..ac732e67a6c8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -173,17 +173,24 @@ struct nf_bridge_info { BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; - bool pkt_otherhost; + u8 pkt_otherhost:1; + u8 in_prerouting:1; + u8 bridged_dnat:1; __u16 frag_max_size; - unsigned int mask; struct net_device *physindev; union { - struct net_device *physoutdev; - char neigh_header[8]; - }; - union { + /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; + + /* after prerouting + nat detected: store original source + * mac since neigh resolution overwrites it, only used while + * skb is out in neigh layer. + */ + char neigh_header[8]; + + /* always valid & non-NULL from FORWARD on, for physdev match */ + struct net_device *physoutdev; }; }; #endif -- cgit v1.2.3 From 7b36f92934e40d1ee24e5617ddedb852e10086ca Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 30 Jul 2015 12:42:47 +0200 Subject: bpf: provide helper that indicates eBPF was migrated During recent discussions we had with Michael, we found that it would be useful to have an indicator that tells the JIT that an eBPF program had been migrated from classic instructions into eBPF instructions, as only in that case A and X need to be cleared in the prologue. Such eBPF programs do not set a particular type, but all have BPF_PROG_TYPE_UNSPEC. Thus, introduce a small helper for cde66c2d88da ("s390/bpf: Only clear A and X for converted BPF programs") and possibly others in future. Signed-off-by: Daniel Borkmann Cc: Michael Holzheu Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 69d00555ce35..6b025491120d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -354,6 +354,16 @@ static inline unsigned int bpf_prog_size(unsigned int proglen) offsetof(struct bpf_prog, insns[proglen])); } +static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) +{ + /* When classic BPF programs have been loaded and the arch + * does not have a classic BPF JIT (anymore), they have been + * converted via bpf_migrate_filter() to eBPF and thus always + * have an unspec program type. + */ + return prog->type == BPF_PROG_TYPE_UNSPEC; +} + #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) #ifdef CONFIG_DEBUG_SET_MODULE_RONX -- cgit v1.2.3 From b13138ef72178a13f34e33883f9f093f9e3b1bda Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 30 Jul 2015 12:42:49 +0200 Subject: bpf: also show process name/pid in bpf_jit_dump It can be useful for testing to see the actual process/pid who is loading a given filter. I was running some BPF test program and noticed unusual filter loads from time to time, triggered by some other application in the background. bpf_jit_disasm is still working after this change. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6b025491120d..fa2cab985e57 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -12,6 +12,7 @@ #include #include #include +#include #include @@ -438,8 +439,9 @@ void bpf_jit_free(struct bpf_prog *fp); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { - pr_err("flen=%u proglen=%u pass=%u image=%pK\n", - flen, proglen, pass, image); + pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen, + proglen, pass, image, current->comm, task_pid_nr(current)); + if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); -- cgit v1.2.3 From 8013d1d7eafb0589ca766db6b74026f76b7f5cb4 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 30 Jul 2015 14:28:42 +0800 Subject: net/ipv6: add sysctl option accept_ra_min_hop_limit Commit 6fd99094de2b ("ipv6: Don't reduce hop limit for an interface") disabled accept hop limit from RA if it is smaller than the current hop limit for security stuff. But this behavior kind of break the RFC definition. RFC 4861, 6.3.4. Processing Received Router Advertisements A Router Advertisement field (e.g., Cur Hop Limit, Reachable Time, and Retrans Timer) may contain a value denoting that it is unspecified. In such cases, the parameter should be ignored and the host should continue using whatever value it is already using. If the received Cur Hop Limit value is non-zero, the host SHOULD set its CurHopLimit variable to the received value. So add sysctl option accept_ra_min_hop_limit to let user choose the minimum hop limit value they can accept from RA. And set default to 1 to meet RFC standards. Signed-off-by: Hangbin Liu Acked-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 06ed637225b8..cb9dcad72372 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -29,6 +29,7 @@ struct ipv6_devconf { __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; + __s32 accept_ra_min_hop_limit; __s32 accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; -- cgit v1.2.3 From f70ea018da0631e10c26a02f5a82d626ffef5bd7 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 31 Jul 2015 16:52:10 -0700 Subject: net: Add functions to get skb->hash based on flow structures Add skb_get_hash_flowi6 and skb_get_hash_flowi4 which derive an sk_buff hash from flowi6 and flowi4 structures respectively. These functions can be called when creating a packet in the output path where the new sk_buff does not yet contain a fully formed packet that is parsable by flow dissector. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 648a2c241993..b7c1286e247d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,7 @@ #include #include #include +#include /* A. Checksumming of received packets by device. * @@ -945,6 +946,26 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->hash; } +__u32 __skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6); + +static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6) +{ + if (!skb->l4_hash && !skb->sw_hash) + __skb_get_hash_flowi6(skb, fl6); + + return skb->hash; +} + +__u32 __skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl); + +static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl4) +{ + if (!skb->l4_hash && !skb->sw_hash) + __skb_get_hash_flowi4(skb, fl4); + + return skb->hash; +} + __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) -- cgit v1.2.3 From d9eea403ca81f60cd535d354c77ada4c2bee8d66 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Tue, 4 Aug 2015 14:05:42 +0300 Subject: net/mlx5_core: Introduce access function to modify RSS/LRO params To be used by the mlx5 Eth driver in following commit. This is in preparation for netdev "light-weight" open/stop flow change described in previous commit. Signed-off-by: Achiad Shochat Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c60a62bba652..469b7bda3304 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4050,6 +4050,13 @@ struct mlx5_ifc_modify_tis_in_bits { struct mlx5_ifc_tisc_bits ctx; }; +struct mlx5_ifc_modify_tir_bitmask_bits { + u8 reserved[0x20]; + + u8 reserved1[0x1f]; + u8 lro[0x1]; +}; + struct mlx5_ifc_modify_tir_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; @@ -4071,7 +4078,7 @@ struct mlx5_ifc_modify_tir_in_bits { u8 reserved_3[0x20]; - u8 modify_bitmask[0x40]; + struct mlx5_ifc_modify_tir_bitmask_bits bitmask; u8 reserved_4[0x40]; -- cgit v1.2.3 From 5c50368f38317627421bf24a0b66b1af0d44eddc Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Tue, 4 Aug 2015 14:05:43 +0300 Subject: net/mlx5e: Light-weight netdev open/stop Create/destroy TIRs, TISs and flow tables upon PCI probe/remove rather than upon the netdev ndo_open/stop. Upon ndo_stop(), redirect all RX traffic to the (lately introduced) "Drop RQ" and then close only the RX/TX rings, leaving the TIRs, TISs and flow tables alive. Signed-off-by: Achiad Shochat Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 469b7bda3304..dd2097455a2e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4123,6 +4123,13 @@ struct mlx5_ifc_modify_rqt_out_bits { u8 reserved_1[0x40]; }; +struct mlx5_ifc_rqt_bitmask_bits { + u8 reserved[0x20]; + + u8 reserved1[0x1f]; + u8 rqn_list[0x1]; +}; + struct mlx5_ifc_modify_rqt_in_bits { u8 opcode[0x10]; u8 reserved_0[0x10]; @@ -4135,7 +4142,7 @@ struct mlx5_ifc_modify_rqt_in_bits { u8 reserved_3[0x20]; - u8 modify_bitmask[0x40]; + struct mlx5_ifc_rqt_bitmask_bits bitmask; u8 reserved_4[0x40]; -- cgit v1.2.3 From efea389d3cc6427a9a94e92b2d7bf4c862f2cfcf Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Tue, 4 Aug 2015 14:05:47 +0300 Subject: net/mlx5_core: Support physical port counters Added physical port counters in the following standard formats to ethtool statistics: - IEEE 802.3 - RFC2863 - RFC2819 Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 10 ++++++++++ include/linux/mlx5/driver.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index b943cd9e2097..250b1ff8b48d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1182,6 +1182,16 @@ enum { MLX5_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR = 0x40, }; +enum { + MLX5_IEEE_802_3_COUNTERS_GROUP = 0x0, + MLX5_RFC_2863_COUNTERS_GROUP = 0x1, + MLX5_RFC_2819_COUNTERS_GROUP = 0x2, + MLX5_RFC_3635_COUNTERS_GROUP = 0x3, + MLX5_ETHERNET_EXTENDED_COUNTERS_GROUP = 0x5, + MLX5_PER_PRIORITY_COUNTERS_GROUP = 0x10, + MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11 +}; + static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) { if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5fe0cae1a515..2039546b0ec6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -103,6 +103,7 @@ enum { MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, MLX5_REG_PAOS = 0x5006, + MLX5_REG_PPCNT = 0x5008, MLX5_REG_PMAOS = 0x5012, MLX5_REG_PUDE = 0x5009, MLX5_REG_PMPE = 0x5010, -- cgit v1.2.3 From d92cff89a0c80e7e49796366e441d97f07b5d321 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 4 Aug 2015 18:26:19 +0200 Subject: net_dbg_ratelimited: turn into no-op when !DEBUG The pr_debug family of functions turns into a no-op when -DDEBUG is not specified, opting instead to call "no_printk", which gets compiled to a no-op (but retains gcc's nice warnings about printf-style arguments). The problem with net_dbg_ratelimited is that it is defined to be a variant of net_ratelimited_function, which expands to essentially: if (net_ratelimit()) pr_debug(fmt, ...); When DEBUG is not defined, then this becomes, if (net_ratelimit()) ; This seems benign, except it isn't. Firstly, there's the obvious overhead of calling net_ratelimit needlessly, which does quite some book keeping for the rate limiting. Given that the pr_debug and net_dbg_ratelimited family of functions are sprinkled liberally through performance critical code, with developers assuming they'll be compiled out to a no-op most of the time, we certainly do not want this needless book keeping. Secondly, and most visibly, even though no debug message is printed when DEBUG is not defined, if there is a flood of invocations, dmesg winds up peppered with messages such as "net_ratelimit: 320 callbacks suppressed". This is because our aforementioned net_ratelimit() function actually prints this text in some circumstances. It's especially odd to see this when there isn't any other accompanying debug message. So, in sum, it doesn't make sense to have this function's current behavior, and instead it should match what every other debug family of functions in the kernel does with !DEBUG -- nothing. This patch replaces calls to net_dbg_ratelimited when !DEBUG with no_printk, keeping with the idiom of all the other debug print helpers. Also, though not strictly neccessary, it guards the call with an if (0) so that all evaluation of any arguments are sure to be compiled out. Signed-off-by: Jason A. Donenfeld Signed-off-by: David S. Miller --- include/linux/net.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 04aa06852771..049d4b03c4c4 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -239,8 +239,16 @@ do { \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) +#if defined(DEBUG) #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) +#else +#define net_dbg_ratelimited(fmt, ...) \ + do { \ + if (0) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + } while (0) +#endif bool __net_get_random_once(void *buf, int nbytes, bool *done, struct static_key *done_key); -- cgit v1.2.3 From 3499abb249bb5ed9d21031944bc3059ec4aa2909 Mon Sep 17 00:00:00 2001 From: Andreas Schultz Date: Wed, 5 Aug 2015 17:51:45 +0200 Subject: netfilter: nfacct: per network namespace support - Move the nfnl_acct_list into the network namespace, initialize and destroy it per namespace - Keep track of refcnt on nfacct objects, the old logic does not longer work with a per namespace list - Adjust xt_nfacct to pass the namespace when registring objects Signed-off-by: Andreas Schultz Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_acct.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h index 6ec975748742..80ca889b164e 100644 --- a/include/linux/netfilter/nfnetlink_acct.h +++ b/include/linux/netfilter/nfnetlink_acct.h @@ -2,6 +2,7 @@ #define _NFNL_ACCT_H_ #include +#include enum { NFACCT_NO_QUOTA = -1, @@ -11,7 +12,7 @@ enum { struct nf_acct; -struct nf_acct *nfnl_acct_find_get(const char *filter_name); +struct nf_acct *nfnl_acct_find_get(struct net *net, const char *filter_name); void nfnl_acct_put(struct nf_acct *acct); void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct); extern int nfnl_acct_overquota(const struct sk_buff *skb, -- cgit v1.2.3 From ffe8690c85b8426db7783064724d106702f1b1e8 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Thu, 6 Aug 2015 07:02:32 +0000 Subject: perf: add the necessary core perf APIs when accessing events counters in eBPF programs This patch add three core perf APIs: - perf_event_attrs(): export the struct perf_event_attr from struct perf_event; - perf_event_get(): get the struct perf_event from the given fd; - perf_event_read_local(): read the events counters active on the current CPU; These APIs are needed when accessing events counters in eBPF programs. The API perf_event_read_local() comes from Peter and I add the corresponding SOB. Signed-off-by: Kaixu Xia Signed-off-by: Peter Zijlstra Signed-off-by: David S. Miller --- include/linux/perf_event.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2027809433b3..092a0e8a479a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -641,6 +641,8 @@ extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); +extern struct perf_event *perf_event_get(unsigned int fd); +extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); @@ -659,6 +661,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); +extern u64 perf_event_read_local(struct perf_event *event); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -979,6 +982,12 @@ static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } +static inline struct perf_event *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } +static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) +{ + return ERR_PTR(-EINVAL); +} +static inline u64 perf_event_read_local(struct perf_event *event) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } @@ -1011,6 +1020,7 @@ static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } +static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL) -- cgit v1.2.3 From 2a36f0b92eb638dd023870574eb471b1c56be9ad Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Thu, 6 Aug 2015 07:02:33 +0000 Subject: bpf: Make the bpf_prog_array_map more generic All the map backends are of generic nature. In order to avoid adding much special code into the eBPF core, rewrite part of the bpf_prog_array map code and make it more generic. So the new perf_event_array map type can reuse most of code with bpf_prog_array map and add fewer lines of special code. Signed-off-by: Wang Nan Signed-off-by: Kaixu Xia Signed-off-by: David S. Miller --- include/linux/bpf.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 139d6d2e123f..d495211d63d1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -24,6 +24,10 @@ struct bpf_map_ops { void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); + + /* funcs called by prog_array and perf_event_array map */ + void *(*map_fd_get_ptr) (struct bpf_map *map, int fd); + void (*map_fd_put_ptr) (void *ptr); }; struct bpf_map { @@ -142,13 +146,13 @@ struct bpf_array { bool owner_jited; union { char value[0] __aligned(8); - struct bpf_prog *prog[0] __aligned(8); + void *ptrs[0] __aligned(8); }; }; #define MAX_TAIL_CALL_CNT 32 u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); -void bpf_prog_array_map_clear(struct bpf_map *map); +void bpf_fd_array_map_clear(struct bpf_map *map); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); -- cgit v1.2.3 From ea317b267e9d03a8241893aa176fba7661d07579 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Thu, 6 Aug 2015 07:02:34 +0000 Subject: bpf: Add new bpf map type to store the pointer to struct perf_event Introduce a new bpf map type 'BPF_MAP_TYPE_PERF_EVENT_ARRAY'. This map only stores the pointer to struct perf_event. The user space event FDs from perf_event_open() syscall are converted to the pointer to struct perf_event and stored in map. Signed-off-by: Kaixu Xia Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d495211d63d1..4fc1f4070789 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -10,6 +10,7 @@ #include #include #include +#include struct bpf_map; -- cgit v1.2.3 From 35578d7984003097af2b1e34502bc943d40c1804 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Thu, 6 Aug 2015 07:02:35 +0000 Subject: bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter According to the perf_event_map_fd and index, the function bpf_perf_event_read() can convert the corresponding map value to the pointer to struct perf_event and return the Hardware PMU counter value. Signed-off-by: Kaixu Xia Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4fc1f4070789..f57d7fed9ec3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -190,6 +190,7 @@ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_perf_event_read_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; -- cgit v1.2.3 From 4c96b7dc0d393f12c17e0d81db15aa4a820a6ab3 Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Wed, 12 Aug 2015 17:06:26 -0500 Subject: Add a matching set of device_ functions for determining mac/phy OF has some helper functions for parsing MAC and PHY settings. In cases where the platform is providing this information rather than the device itself, there needs to be similar functions for ACPI. These functions are slightly modified versions of the ones in of_net which can use information provided via DT or ACPI. Signed-off-by: Jeremy Linton Signed-off-by: David S. Miller --- include/linux/property.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 76ebde9c11d4..a59c6ee566c2 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -166,4 +166,8 @@ void device_add_property_set(struct device *dev, struct property_set *pset); bool device_dma_is_coherent(struct device *dev); +int device_get_phy_mode(struct device *dev); + +void *device_get_mac_address(struct device *dev, char *addr, int alen); + #endif /* _LINUX_PROPERTY_H_ */ -- cgit v1.2.3 From 35103d11173b8fea874183f8aa508ae71234d299 Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Thu, 13 Aug 2015 10:39:01 -0400 Subject: net: ipv6 sysctl option to ignore routes when nexthop link is down Like the ipv4 patch with a similar title, this adds a sysctl to allow the user to change routing behavior based on whether or not the interface associated with the nexthop was an up or down link. The default setting preserves the current behavior, but anyone that enables it will notice that nexthops on down interfaces will no longer be selected: net.ipv6.conf.all.ignore_routes_with_linkdown = 0 net.ipv6.conf.default.ignore_routes_with_linkdown = 0 net.ipv6.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, not only will link status be reported to userspace, but an indication that a nexthop is dead and will not be used is also reported. 1000::/8 via 7000::2 dev p7p1 metric 1024 dead linkdown pref medium 1000::/8 via 8000::2 dev p8p1 metric 1024 pref medium 7000::/8 dev p7p1 proto kernel metric 256 dead linkdown pref medium 8000::/8 dev p8p1 proto kernel metric 256 pref medium 9000::/8 via 8000::2 dev p8p1 metric 2048 pref medium 9000::/8 via 7000::2 dev p7p1 metric 1024 dead linkdown pref medium fe80::/64 dev p7p1 proto kernel metric 256 dead linkdown pref medium fe80::/64 dev p8p1 proto kernel metric 256 pref medium This also adds devconf support and notification when sysctl values change. v2: drop use of rt6i_nhflags since it is not needed right now Signed-off-by: Andy Gospodarek Signed-off-by: Dinesh Dutt Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index cb9dcad72372..f1f32af6d9b9 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -31,6 +31,7 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __s32 accept_ra_min_hop_limit; __s32 accept_ra_pinfo; + __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; -- cgit v1.2.3 From 4e3c89920cd3a6cfce22c6f537690747c26128dd Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:00 -0600 Subject: net: Introduce VRF related flags and helpers Add a VRF_MASTER flag for interfaces and helper functions for determining if a device is a VRF_MASTER. Add link attribute for passing VRF_TABLE id. Add vrf_ptr to netdevice. Add various macros for determining if a device is a VRF device, the index of the master VRF device and table associated with VRF device. Signed-off-by: Shrijeet Mukherjee Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 607b5f41f46f..f7a6ef2fae3a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1289,6 +1289,7 @@ enum netdev_priv_flags { IFF_XMIT_DST_RELEASE_PERM = 1<<22, IFF_IPVLAN_MASTER = 1<<23, IFF_IPVLAN_SLAVE = 1<<24, + IFF_VRF_MASTER = 1<<25, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1316,6 +1317,7 @@ enum netdev_priv_flags { #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE +#define IFF_VRF_MASTER IFF_VRF_MASTER /** * struct net_device - The DEVICE structure. @@ -1432,6 +1434,7 @@ enum netdev_priv_flags { * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data + * @vrf_ptr: VRF specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * * @last_rx: Time of last Rx @@ -1650,6 +1653,7 @@ struct net_device { struct dn_dev __rcu *dn_ptr; struct inet6_dev __rcu *ip6_ptr; void *ax25_ptr; + struct net_vrf_dev __rcu *vrf_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) @@ -3808,6 +3812,22 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_is_vrf(const struct net_device *dev) +{ + return dev->priv_flags & IFF_VRF_MASTER; +} + +static inline bool netif_index_is_vrf(struct net *net, int ifindex) +{ + struct net_device *dev = dev_get_by_index_rcu(net, ifindex); + bool rc = false; + + if (dev) + rc = netif_is_vrf(dev); + + return rc; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From 2377799c084d86d22074cd4acd20edc32024d669 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 13 Jul 2015 12:17:25 +0200 Subject: average: provide macro to create static EWMA Having the EWMA parameters stored in the runtime struct imposes memory requirements for the constant values that could just be inlined in the code. This particularly makes sense if there are a lot of such structs, for example in mac80211 in the station table where each station has a number of these in an array, and there can be many stations. Provide a macro DECLARE_EWMA() that declares the necessary struct and inline functions to access it with the parameters hard-coded; using this also means the user no longer needs to 'select AVERAGE' as it's entirely self-contained. In the mac80211 case, on x86-64, this actually slightly *reduces* code size, while also saving 80 bytes of runtime memory per sta. Signed-off-by: Johannes Berg --- include/linux/average.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/average.h b/include/linux/average.h index c6028fd742c1..60f8226c5652 100644 --- a/include/linux/average.h +++ b/include/linux/average.h @@ -27,4 +27,43 @@ static inline unsigned long ewma_read(const struct ewma *avg) return avg->internal >> avg->factor; } +#define DECLARE_EWMA(name, _factor, _weight) \ + struct ewma_##name { \ + unsigned long internal; \ + }; \ + static inline void ewma_##name##_init(struct ewma_##name *e) \ + { \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + e->internal = 0; \ + } \ + static inline unsigned long \ + ewma_##name##_read(struct ewma_##name *e) \ + { \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + return e->internal >> ilog2(_factor); \ + } \ + static inline void ewma_##name##_add(struct ewma_##name *e, \ + unsigned long val) \ + { \ + unsigned long internal = ACCESS_ONCE(e->internal); \ + unsigned long weight = ilog2(_weight); \ + unsigned long factor = ilog2(_factor); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + \ + ACCESS_ONCE(e->internal) = internal ? \ + (((internal << weight) - internal) + \ + (val << factor)) >> weight : \ + (val << factor); \ + } + #endif /* _LINUX_AVERAGE_H */ -- cgit v1.2.3 From 8f9c98df949333f08b74e5df1caacf7e2c5e8552 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 19 Jul 2015 16:09:12 +0300 Subject: mac80211: fix BIT position for TDLS WIDE extended cap The bit was not according to ieee80211 specification. Fix that. Reviewed-by: Arik Nemtsov Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b9c7897dc566..cfa906f28b7a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2074,8 +2074,8 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA5_TDLS_PROHIBITED BIT(6) #define WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED BIT(7) +#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) -#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(7) /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 -- cgit v1.2.3 From 76b733d15874128ee2d0365b4cbe7d51decd8d37 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Fri, 14 Aug 2015 22:33:30 +0200 Subject: nfc: st-nci: Remove duplicate file platform_data/st_nci.h commit "nfc: st-nci: Rename st21nfcb to st-nci" adds include/linux/platform_data/st_nci.h duplicated with include/linux/platform_data/st-nci.h. Only drivers/nfc/st-nci/i2c.c uses platform_data/st_nci.h. Cc: stable@vger.kernel.org Reported-by: Hauke Mehrtens Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/linux/platform_data/st_nci.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/platform_data/st_nci.h (limited to 'include/linux') diff --git a/include/linux/platform_data/st_nci.h b/include/linux/platform_data/st_nci.h deleted file mode 100644 index d9d400a297bd..000000000000 --- a/include/linux/platform_data/st_nci.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Driver include for ST NCI NFC chip family. - * - * Copyright (C) 2014-2015 STMicroelectronics SAS. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see . - */ - -#ifndef _ST_NCI_H_ -#define _ST_NCI_H_ - -#define ST_NCI_DRIVER_NAME "st_nci" - -struct st_nci_nfc_platform_data { - unsigned int gpio_reset; - unsigned int irq_polarity; -}; - -#endif /* _ST_NCI_H_ */ -- cgit v1.2.3 From fa8187c96471c49419c25d4ec3299d17d3f274b2 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 13 Aug 2015 19:01:06 +0200 Subject: net: declare new net_device priv_flag IFF_NO_QUEUE This private net_device flag can be set by drivers to inform that a device runs fine without a qdisc attached. This was formerly done by setting tx_queue_len to zero. Signed-off-by: Phil Sutter Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f7a6ef2fae3a..d131755516ca 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1262,6 +1262,7 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device + * @IFF_NO_QUEUE: device can run without qdisc attached */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1290,6 +1291,7 @@ enum netdev_priv_flags { IFF_IPVLAN_MASTER = 1<<23, IFF_IPVLAN_SLAVE = 1<<24, IFF_VRF_MASTER = 1<<25, + IFF_NO_QUEUE = 1<<26, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1318,6 +1320,7 @@ enum netdev_priv_flags { #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE #define IFF_VRF_MASTER IFF_VRF_MASTER +#define IFF_NO_QUEUE IFF_NO_QUEUE /** * struct net_device - The DEVICE structure. -- cgit v1.2.3 From fbaff3ef859a86dc3df2128d2de9f8a6e255a967 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 13 Aug 2015 18:34:03 -0700 Subject: net: fix endian check warning in etherdevice.h Sparse builds have been warning for a really long time now that etherdevice.h has a conversion that is unsafe. include/linux/etherdevice.h:79:32: warning: restricted __be16 degrades to integer This code change fixes the issue and generates the exact same assembly before/after (checked on x86_64) Fixes: 2c722fe1c821 (etherdevice: Optimize a few is__ether_addr functions) Signed-off-by: Jesse Brandeburg CC: Joe Perches Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 9012f8775208..eb049c622208 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -76,7 +76,7 @@ static inline bool is_link_local_ether_addr(const u8 *addr) #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | - ((a[2] ^ b[2]) & m)) == 0; + (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif -- cgit v1.2.3 From 6fa1bcab6be6e9bd93f80e345c7e9a4ec7861df9 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Sun, 16 Aug 2015 16:04:50 +0300 Subject: net/mlx5e: Ethtool link speed setting fixes - Port speed settings are applied by the device only upon port admin status transition from DOWN to UP. So we enforce this transition regardless of the port's current operation state (which may be occasionally DOWN if for example the network cable is disconnected). - Fix the PORT_UP/DOWN device interface enum - Set the local_port bit in the device PAOS register - EXPORT the PAOS (Port Administrative and Operational Status) register set/query access functions. Signed-off-by: Achiad Shochat Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2039546b0ec6..4b5d7fc88d0f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -152,8 +152,8 @@ enum mlx5_dev_event { }; enum mlx5_port_status { - MLX5_PORT_UP = 1 << 1, - MLX5_PORT_DOWN = 1 << 2, + MLX5_PORT_UP = 1, + MLX5_PORT_DOWN = 2, }; struct mlx5_uuar_info { @@ -761,9 +761,10 @@ int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, u8 local_port); int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, int proto_mask); -int mlx5_set_port_status(struct mlx5_core_dev *dev, - enum mlx5_port_status status); -int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status); +int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status); +int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status *status); int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); -- cgit v1.2.3 From 3c2d18ef22df1bdccfb11a5b85b29e4e61b9d9c6 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Sun, 16 Aug 2015 16:04:51 +0300 Subject: net/mlx5e: Support ethtool get/set_pauseparam Only rx/tx pause settings. Autoneg setting is currently not supported. Signed-off-by: Achiad Shochat Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4b5d7fc88d0f..8b6d6f2154a4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -103,6 +103,7 @@ enum { MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, MLX5_REG_PAOS = 0x5006, + MLX5_REG_PFCC = 0x5007, MLX5_REG_PPCNT = 0x5008, MLX5_REG_PMAOS = 0x5012, MLX5_REG_PUDE = 0x5009, @@ -774,6 +775,10 @@ void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, u8 *vl_hw_cap, u8 local_port); +int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); +int mlx5_query_port_pause(struct mlx5_core_dev *dev, + u32 *rx_pause, u32 *tx_pause); + int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, -- cgit v1.2.3 From 2f52bdcf6ba1bd81597b1505a222430676548b3a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 16 Aug 2015 07:49:20 -0600 Subject: net: Updates to netif_index_is_vrf As Eric noted netif_index_is_vrf is not called with rcu_read_lock held, so wrap the dev_get_by_index_rcu in rcu_read_lock and unlock. If VRF is not enabled or oif is 0 skip the device lookup. In both cases index cannot be the VRF master. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d131755516ca..8a530f930754 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3822,12 +3822,22 @@ static inline bool netif_is_vrf(const struct net_device *dev) static inline bool netif_index_is_vrf(struct net *net, int ifindex) { - struct net_device *dev = dev_get_by_index_rcu(net, ifindex); bool rc = false; +#if IS_ENABLED(CONFIG_NET_VRF) + struct net_device *dev; + + if (ifindex == 0) + return false; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = netif_is_vrf(dev); + rcu_read_unlock(); +#endif return rc; } -- cgit v1.2.3 From 808d28c468a89e8680396d98aea96024b6f5afdc Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 16 Aug 2015 10:26:49 -0600 Subject: net: Fix docbook warning for IFF_VRF_MASTER enum kbuild test robot reported: tree: git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git master head: d52736e24fe2e927c26817256f8d1a3c8b5d51a0 commit: 4e3c89920cd3a6cfce22c6f537690747c26128dd [751/762] net: Introduce VRF related flags and helpers reproduce: make htmldocs >> Warning(include/linux/netdevice.h:1293): Enum value 'IFF_VRF_MASTER' not described in enum 'netdev_priv_flags' Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8a530f930754..4bd177faa90c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1262,6 +1262,7 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device + * @IFF_VRF_MASTER: device is a VRF master * @IFF_NO_QUEUE: device can run without qdisc attached */ enum netdev_priv_flags { -- cgit v1.2.3 From 74f4e0cc61080f63f28e8d519bdf437957e64217 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 14 Aug 2015 00:21:45 +0200 Subject: bcma: switch GPIO portions to use GPIOLIB_IRQCHIP This switches the BCMA GPIO driver to use GPIOLIB_IRQCHIP to handle its interrupts instead of rolling its own copy of the irqdomain handling etc. Signed-off-by: Linus Walleij Signed-off-by: Hauke Mehrtens Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_chipcommon.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 6cceedf65ca2..cf038431a5cc 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -640,7 +640,6 @@ struct bcma_drv_cc { spinlock_t gpio_lock; #ifdef CONFIG_BCMA_DRIVER_GPIO struct gpio_chip gpio; - struct irq_domain *irq_domain; #endif }; -- cgit v1.2.3 From f4e774f55fe0bb568a0877b2eb9e1b4b5a6f5cbc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 19 Aug 2015 09:46:22 +0200 Subject: average: remove out-of-line implementation Since all users are now converted to the inline implementation, remove the out-of-line implementation entirely. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/average.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/average.h b/include/linux/average.h index 60f8226c5652..d04aa58280de 100644 --- a/include/linux/average.h +++ b/include/linux/average.h @@ -3,30 +3,6 @@ /* Exponentially weighted moving average (EWMA) */ -/* For more documentation see lib/average.c */ - -struct ewma { - unsigned long internal; - unsigned long factor; - unsigned long weight; -}; - -extern void ewma_init(struct ewma *avg, unsigned long factor, - unsigned long weight); - -extern struct ewma *ewma_add(struct ewma *avg, unsigned long val); - -/** - * ewma_read() - Get average value - * @avg: Average structure - * - * Returns the average value held in @avg. - */ -static inline unsigned long ewma_read(const struct ewma *avg) -{ - return avg->internal >> avg->factor; -} - #define DECLARE_EWMA(name, _factor, _weight) \ struct ewma_##name { \ unsigned long internal; \ -- cgit v1.2.3 From b7fe10e5ebac2a3f37e95535e616494b65fa020f Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 19 Aug 2015 17:07:32 -0700 Subject: gro: Fix remcsum offload to deal with frags in GRO The remote checksum offload GRO did not consider the case that frag0 might be in use. This patch fixes that by accessing headers using the skb_gro functions and not saving offsets relative to skb->head. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 44 ++++++++++++++++++++++++++++++++------------ 1 file changed, 32 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4bd177faa90c..6abe0d6f1e1d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2311,8 +2311,7 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb); static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) { - return (NAPI_GRO_CB(skb)->gro_remcsum_start - skb_headroom(skb) == - skb_gro_offset(skb)); + return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); } static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, @@ -2408,37 +2407,58 @@ static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) grc->delta = 0; } -static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - int start, int offset, - struct gro_remcsum *grc, - bool nopartial) +static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, + unsigned int off, size_t hdrlen, + int start, int offset, + struct gro_remcsum *grc, + bool nopartial) { __wsum delta; + size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); if (!nopartial) { - NAPI_GRO_CB(skb)->gro_remcsum_start = - ((unsigned char *)ptr + start) - skb->head; - return; + NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; + return ptr; + } + + ptr = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, off + plen)) { + ptr = skb_gro_header_slow(skb, off + plen, off); + if (!ptr) + return NULL; } - delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset); + delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, + start, offset); /* Adjust skb->csum since we changed the packet */ NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); - grc->offset = (ptr + offset) - (void *)skb->head; + grc->offset = off + hdrlen + offset; grc->delta = delta; + + return ptr; } static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, struct gro_remcsum *grc) { + void *ptr; + size_t plen = grc->offset + sizeof(u16); + if (!grc->delta) return; - remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta); + ptr = skb_gro_header_fast(skb, grc->offset); + if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { + ptr = skb_gro_header_slow(skb, plen, grc->offset); + if (!ptr) + return; + } + + remcsum_unadjust((__sum16 *)ptr, grc->delta); } static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, -- cgit v1.2.3 From 0e4ead9d7b3655d76371604abb9b0dcc4e79bb7d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 27 Aug 2015 09:31:18 +0200 Subject: net: introduce change upper device notifier change info Add info that is passed along with NETDEV_CHANGEUPPER event. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6abe0d6f1e1d..39f30daac483 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2127,6 +2127,13 @@ struct netdev_notifier_change_info { unsigned int flags_changed; }; +struct netdev_notifier_changeupper_info { + struct netdev_notifier_info info; /* must be first */ + struct net_device *upper_dev; /* new upper dev */ + bool master; /* is upper dev master */ + bool linking; /* is the nofication for link or unlink */ +}; + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { -- cgit v1.2.3 From 0894ae3f0a587bda9733ec4a4b67af7ded3a9498 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 27 Aug 2015 09:31:19 +0200 Subject: net: add netif_is_bridge_master helper Add this helper so code can easily figure out if netdev is a bridge. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 39f30daac483..be625f4754b9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3848,6 +3848,11 @@ static inline bool netif_is_vrf(const struct net_device *dev) return dev->priv_flags & IFF_VRF_MASTER; } +static inline bool netif_is_bridge_master(const struct net_device *dev) +{ + return dev->priv_flags & IFF_EBRIDGE; +} + static inline bool netif_index_is_vrf(struct net *net, int ifindex) { bool rc = false; -- cgit v1.2.3 From 35d4e1725202e6656fcfa8b88447327ad3ae0c0c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 27 Aug 2015 09:31:20 +0200 Subject: net: add netif_is_ovs_master helper with IFF_OPENVSWITCH private flag Add this helper so code can easily figure out if netdev is openswitch. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index be625f4754b9..6656a43c072d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1264,6 +1264,7 @@ struct net_device_ops { * @IFF_MACVLAN: Macvlan device * @IFF_VRF_MASTER: device is a VRF master * @IFF_NO_QUEUE: device can run without qdisc attached + * @IFF_OPENVSWITCH: device is a Open vSwitch master */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1293,6 +1294,7 @@ enum netdev_priv_flags { IFF_IPVLAN_SLAVE = 1<<24, IFF_VRF_MASTER = 1<<25, IFF_NO_QUEUE = 1<<26, + IFF_OPENVSWITCH = 1<<27, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1322,6 +1324,7 @@ enum netdev_priv_flags { #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE #define IFF_VRF_MASTER IFF_VRF_MASTER #define IFF_NO_QUEUE IFF_NO_QUEUE +#define IFF_OPENVSWITCH IFF_OPENVSWITCH /** * struct net_device - The DEVICE structure. @@ -3853,6 +3856,11 @@ static inline bool netif_is_bridge_master(const struct net_device *dev) return dev->priv_flags & IFF_EBRIDGE; } +static inline bool netif_is_ovs_master(const struct net_device *dev) +{ + return dev->priv_flags & IFF_OPENVSWITCH; +} + static inline bool netif_index_is_vrf(struct net *net, int ifindex) { bool rc = false; -- cgit v1.2.3 From 0dc1549bfd67053181415a3f7544628a6bcd2a08 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 27 Aug 2015 09:31:21 +0200 Subject: net: kill long time unused bonding private flags We don't use them for years, just kill them now. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 57 +++++++++++++++++------------------------------ 1 file changed, 21 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6656a43c072d..88a00694eda5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1240,13 +1240,8 @@ struct net_device_ops { * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device - * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active - * @IFF_MASTER_8023AD: bonding master, 802.3ad - * @IFF_MASTER_ALB: bonding master, balance-alb * @IFF_BONDING: bonding master or slave - * @IFF_SLAVE_NEEDARP: need ARPs for validation * @IFF_ISATAP: ISATAP interface (RFC4214) - * @IFF_MASTER_ARPMON: bonding master, ARP mon in use * @IFF_WAN_HDLC: WAN HDLC device * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to * release skb->dst @@ -1269,43 +1264,33 @@ struct net_device_ops { enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, IFF_EBRIDGE = 1<<1, - IFF_SLAVE_INACTIVE = 1<<2, - IFF_MASTER_8023AD = 1<<3, - IFF_MASTER_ALB = 1<<4, - IFF_BONDING = 1<<5, - IFF_SLAVE_NEEDARP = 1<<6, - IFF_ISATAP = 1<<7, - IFF_MASTER_ARPMON = 1<<8, - IFF_WAN_HDLC = 1<<9, - IFF_XMIT_DST_RELEASE = 1<<10, - IFF_DONT_BRIDGE = 1<<11, - IFF_DISABLE_NETPOLL = 1<<12, - IFF_MACVLAN_PORT = 1<<13, - IFF_BRIDGE_PORT = 1<<14, - IFF_OVS_DATAPATH = 1<<15, - IFF_TX_SKB_SHARING = 1<<16, - IFF_UNICAST_FLT = 1<<17, - IFF_TEAM_PORT = 1<<18, - IFF_SUPP_NOFCS = 1<<19, - IFF_LIVE_ADDR_CHANGE = 1<<20, - IFF_MACVLAN = 1<<21, - IFF_XMIT_DST_RELEASE_PERM = 1<<22, - IFF_IPVLAN_MASTER = 1<<23, - IFF_IPVLAN_SLAVE = 1<<24, - IFF_VRF_MASTER = 1<<25, - IFF_NO_QUEUE = 1<<26, - IFF_OPENVSWITCH = 1<<27, + IFF_BONDING = 1<<2, + IFF_ISATAP = 1<<3, + IFF_WAN_HDLC = 1<<4, + IFF_XMIT_DST_RELEASE = 1<<5, + IFF_DONT_BRIDGE = 1<<6, + IFF_DISABLE_NETPOLL = 1<<7, + IFF_MACVLAN_PORT = 1<<8, + IFF_BRIDGE_PORT = 1<<9, + IFF_OVS_DATAPATH = 1<<10, + IFF_TX_SKB_SHARING = 1<<11, + IFF_UNICAST_FLT = 1<<12, + IFF_TEAM_PORT = 1<<13, + IFF_SUPP_NOFCS = 1<<14, + IFF_LIVE_ADDR_CHANGE = 1<<15, + IFF_MACVLAN = 1<<16, + IFF_XMIT_DST_RELEASE_PERM = 1<<17, + IFF_IPVLAN_MASTER = 1<<18, + IFF_IPVLAN_SLAVE = 1<<19, + IFF_VRF_MASTER = 1<<20, + IFF_NO_QUEUE = 1<<21, + IFF_OPENVSWITCH = 1<<22, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN #define IFF_EBRIDGE IFF_EBRIDGE -#define IFF_SLAVE_INACTIVE IFF_SLAVE_INACTIVE -#define IFF_MASTER_8023AD IFF_MASTER_8023AD -#define IFF_MASTER_ALB IFF_MASTER_ALB #define IFF_BONDING IFF_BONDING -#define IFF_SLAVE_NEEDARP IFF_SLAVE_NEEDARP #define IFF_ISATAP IFF_ISATAP -#define IFF_MASTER_ARPMON IFF_MASTER_ARPMON #define IFF_WAN_HDLC IFF_WAN_HDLC #define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE #define IFF_DONT_BRIDGE IFF_DONT_BRIDGE -- cgit v1.2.3 From 2e4cfae2a8e3f9ce3925c9b6e9e865fe8476fc4f Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Thu, 27 Aug 2015 15:25:45 -0700 Subject: netfilter: Define v6ops in !CONFIG_NETFILTER case. When CONFIG_OPENVSWITCH is set, and CONFIG_NETFILTER is not set, the openvswitch IPv6 fragmentation handling cannot refer to ipv6_ops because it isn't defined. Add a dummy version to avoid #ifdefs in source files. Fixes: 7f8a436 "openvswitch: Add conntrack action" Signed-off-by: Joe Stringer Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 8b7d28f3aada..771574677e83 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -9,15 +9,6 @@ #include - -#ifdef CONFIG_NETFILTER -int ip6_route_me_harder(struct sk_buff *skb); -__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol); - -int ipv6_netfilter_init(void); -void ipv6_netfilter_fini(void); - /* * Hook functions for ipv6 to allow xt_* modules to be built-in even * if IPv6 is a module. @@ -30,6 +21,14 @@ struct nf_ipv6_ops { int (*output)(struct sock *, struct sk_buff *)); }; +#ifdef CONFIG_NETFILTER +int ip6_route_me_harder(struct sk_buff *skb); +__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol); + +int ipv6_netfilter_init(void); +void ipv6_netfilter_fini(void); + extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops; static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) { @@ -39,6 +38,7 @@ static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) #else /* CONFIG_NETFILTER */ static inline int ipv6_netfilter_init(void) { return 0; } static inline void ipv6_netfilter_fini(void) { return; } +static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) { return NULL; } #endif /* CONFIG_NETFILTER */ #endif /*__LINUX_IP6_NETFILTER_H*/ -- cgit v1.2.3 From df2cf4a78e488d26728590cb3c6b4fe4c4862c77 Mon Sep 17 00:00:00 2001 From: Philip Downey Date: Thu, 27 Aug 2015 16:46:26 +0100 Subject: IGMP: Inhibit reports for local multicast groups The range of addresses between 224.0.0.0 and 224.0.0.255 inclusive, is reserved for the use of routing protocols and other low-level topology discovery or maintenance protocols, such as gateway discovery and group membership reporting. Multicast routers should not forward any multicast datagram with destination addresses in this range, regardless of its TTL. Currently, IGMP reports are generated for this reserved range of addresses even though a router will ignore this information since it has no purpose. However, the presence of reserved group addresses in an IGMP membership report uses up network bandwidth and can also obscure addresses of interest when inspecting membership reports using packet inspection or debug messages. Although the RFCs for the various version of IGMP (e.g.RFC 3376 for v3) do not specify that the reserved addresses be excluded from membership reports, it should do no harm in doing so. In particular there should be no adverse effect in any IGMP snooping functionality since 224.0.0.x is specifically excluded as per RFC 4541 (IGMP and MLD Snooping Switches Considerations) section 2.1.2. Data Forwarding Rules: 2) Packets with a destination IP (DIP) address in the 224.0.0.X range which are not IGMP must be forwarded on all ports. IGMP reports for local multicast groups can now be optionally inhibited by means of a system control variable (by setting the value to zero) e.g.: echo 0 > /proc/sys/net/ipv4/igmp_link_local_mcast_reports To retain backwards compatibility the previous behaviour is retained by default on system boot or reverted by setting the value back to non-zero e.g.: echo 1 > /proc/sys/net/ipv4/igmp_link_local_mcast_reports Signed-off-by: Philip Downey Signed-off-by: David S. Miller --- include/linux/igmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 193ad488d3e2..908429216d9f 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -37,6 +37,7 @@ static inline struct igmpv3_query * return (struct igmpv3_query *)skb_transport_header(skb); } +extern int sysctl_igmp_llm_reports; extern int sysctl_igmp_max_memberships; extern int sysctl_igmp_max_msf; extern int sysctl_igmp_qrv; -- cgit v1.2.3 From 1a6877b9c0c2ad901d4335d909432d3bb6d3a330 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 28 Aug 2015 15:56:22 -0700 Subject: lib: introduce strncpy_from_unsafe() generalize FETCH_FUNC_NAME(memory, string) into strncpy_from_unsafe() and fix sparse warnings that were present in original implementation. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/uaccess.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ae572c138607..d6f2c2c5b043 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -129,4 +129,6 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); +extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); + #endif /* __LINUX_UACCESS_H__ */ -- cgit v1.2.3 From 5a11dd7d9649149f336ca72069d56ce52b21567f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 31 Aug 2015 15:56:46 +0200 Subject: net: phy: Allow PHY devices to identify themselves as Ethernet switches, etc. Some Ethernet MAC drivers using the PHY library require the hardcoding of link parameters when interfaced to a switch device, SFP module, switch to switch port, etc. This has typically lead to various ad-hoc implementations looking like this: - using a "fixed PHY" emulated device, which will provide link indication towards the Ethernet MAC driver and hardware - pretend there is no PHY and hardcode link parameters, ala mv643x_eth Based on that, it is desireable to have the PHY drivers advertise the correct link parameters, just like regular Ethernet PHYs towards their CPU Ethernet MAC drivers, however, Ethernet MAC drivers should be able to tell whether this link should be monitored or not. In the context of an Ethernet switch, SFP module, switch to switch link, we do not need to monitor this link since it should be always up. Signed-off-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e5fb1d415961..962387a192f1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -330,6 +330,7 @@ struct phy_c45_device_ids { * c45_ids: 802.3-c45 Device Identifers if is_c45. * is_c45: Set to true if this phy uses clause 45 addressing. * is_internal: Set to true if this phy is internal to a MAC. + * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc. * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. * state: state of the PHY for management purposes @@ -368,6 +369,7 @@ struct phy_device { struct phy_c45_device_ids c45_ids; bool is_c45; bool is_internal; + bool is_pseudo_fixed_link; bool has_fixups; bool suspended; @@ -688,6 +690,16 @@ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) { return phydev->interface >= PHY_INTERFACE_MODE_RGMII && phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID; +}; + +/* + * phy_is_pseudo_fixed_link - Convenience function for testing if this + * PHY is the CPU port facing side of an Ethernet switch, or similar. + * @phydev: the phy_device struct + */ +static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) +{ + return phydev->is_pseudo_fixed_link; } /** -- cgit v1.2.3 From a5597008dbc230876db2d344561d634f4d52ea4a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 31 Aug 2015 15:56:53 +0200 Subject: phy: fixed_phy: Add gpio to determine link up/down. An SFP module may have a link up/down status pin which can be connection to a GPIO line of the host. Add support for reading such an GPIO in the fixed_phy driver. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy_fixed.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index fe5732d53eda..2400d2ea4f34 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -13,9 +13,11 @@ struct device_node; #if IS_ENABLED(CONFIG_FIXED_PHY) extern int fixed_phy_add(unsigned int irq, int phy_id, - struct fixed_phy_status *status); + struct fixed_phy_status *status, + int link_gpio); extern struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, + int link_gpio, struct device_node *np); extern void fixed_phy_del(int phy_addr); extern int fixed_phy_set_link_update(struct phy_device *phydev, @@ -26,12 +28,14 @@ extern int fixed_phy_update_state(struct phy_device *phydev, const struct fixed_phy_status *changed); #else static inline int fixed_phy_add(unsigned int irq, int phy_id, - struct fixed_phy_status *status) + struct fixed_phy_status *status, + int link_gpio) { return -ENODEV; } static inline struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, + int gpio_link, struct device_node *np) { return ERR_PTR(-ENODEV); -- cgit v1.2.3 From e5276937ae6e654a811345f0716266f12e77bede Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 1 Sep 2015 09:24:23 -0700 Subject: flow_dissector: Move skb related functions to skbuff.h Move the flow dissector functions that are specific to skbuffs into skbuff.h out of flow_dissector.h. This makes flow_dissector.h have no dependencies on skbuff.h. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 989307f991db..8a697c673b58 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -945,6 +945,53 @@ skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) skb->hash = hash; } +void __skb_get_hash(struct sk_buff *skb); +u32 skb_get_poff(const struct sk_buff *skb); +u32 __skb_get_poff(const struct sk_buff *skb, void *data, + const struct flow_keys *keys, int hlen); +__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, + void *data, int hlen_proto); + +static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, + int thoff, u8 ip_proto) +{ + return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); +} + +void skb_flow_dissector_init(struct flow_dissector *flow_dissector, + const struct flow_dissector_key *key, + unsigned int key_count); + +bool __skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, + void *data, __be16 proto, int nhoff, int hlen); + +static inline bool skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container) +{ + return __skb_flow_dissect(skb, flow_dissector, target_container, + NULL, 0, 0, 0); +} + +static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, + struct flow_keys *flow) +{ + memset(flow, 0, sizeof(*flow)); + return __skb_flow_dissect(skb, &flow_keys_dissector, flow, + NULL, 0, 0, 0); +} + +static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow, + void *data, __be16 proto, + int nhoff, int hlen) +{ + memset(flow, 0, sizeof(*flow)); + return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow, + data, proto, nhoff, hlen); +} + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) -- cgit v1.2.3 From bcc83839ffdb063dd2b0370cd85c4f825761fc59 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 1 Sep 2015 09:24:24 -0700 Subject: skbuff: Make __skb_set_sw_hash a general function Move __skb_set_sw_hash to skbuff.h and add __skb_set_hash which is a common method (between __skb_set_sw_hash and skb_set_hash) to set the hash in an skbuff. Also, move skb_clear_hash to be closer to __skb_set_hash. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 45 +++++++++++++++++++++++++++++---------------- 1 file changed, 29 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8a697c673b58..5d2c812e725b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -937,14 +937,40 @@ enum pkt_hash_types { PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; -static inline void -skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) +static inline void skb_clear_hash(struct sk_buff *skb) { - skb->l4_hash = (type == PKT_HASH_TYPE_L4); + skb->hash = 0; skb->sw_hash = 0; + skb->l4_hash = 0; +} + +static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) +{ + if (!skb->l4_hash) + skb_clear_hash(skb); +} + +static inline void +__skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) +{ + skb->l4_hash = is_l4; + skb->sw_hash = is_sw; skb->hash = hash; } +static inline void +skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) +{ + /* Used by drivers to set hash from HW */ + __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); +} + +static inline void +__skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) +{ + __skb_set_hash(skb, hash, true, is_l4); +} + void __skb_get_hash(struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, @@ -1027,19 +1053,6 @@ static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) return skb->hash; } -static inline void skb_clear_hash(struct sk_buff *skb) -{ - skb->hash = 0; - skb->sw_hash = 0; - skb->l4_hash = 0; -} - -static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) -{ - if (!skb->l4_hash) - skb_clear_hash(skb); -} - static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; -- cgit v1.2.3 From c6cc1ca7f4d70cbb3ea3a5ca163c5dabaf155cdb Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 1 Sep 2015 09:24:25 -0700 Subject: flowi: Abstract out functions to get flow hash based on flowi Create __get_hash_from_flowi6 and __get_hash_from_flowi4 to get the flow keys and hash based on flowi structures. These are called by __skb_get_hash_flowi6 and __skb_get_hash_flowi4. Also, created get_hash_from_flowi6 and get_hash_from_flowi4 which can be called when just the hash value for a flowi is needed. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5d2c812e725b..bbe41bccfc5f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1030,8 +1030,12 @@ __u32 __skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6); static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6) { - if (!skb->l4_hash && !skb->sw_hash) - __skb_get_hash_flowi6(skb, fl6); + if (!skb->l4_hash && !skb->sw_hash) { + struct flow_keys keys; + + __skb_set_sw_hash(skb, __get_hash_from_flowi6(fl6, &keys), + flow_keys_have_l4(&keys)); + } return skb->hash; } @@ -1040,8 +1044,12 @@ __u32 __skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl); static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl4) { - if (!skb->l4_hash && !skb->sw_hash) - __skb_get_hash_flowi4(skb, fl4); + if (!skb->l4_hash && !skb->sw_hash) { + struct flow_keys keys; + + __skb_set_sw_hash(skb, __get_hash_from_flowi4(fl4, &keys), + flow_keys_have_l4(&keys)); + } return skb->hash; } -- cgit v1.2.3 From cd79a2382aa5dcefa6e21a7c59bb1bb19e53b74d Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 1 Sep 2015 09:24:27 -0700 Subject: flow_dissector: Add flags argument to skb_flow_dissector functions The flags argument will allow control of the dissection process (for instance whether to parse beyond L3). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bbe41bccfc5f..9e62687c70f3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -991,31 +991,34 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, - void *data, __be16 proto, int nhoff, int hlen); + void *data, __be16 proto, int nhoff, int hlen, + unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container) + void *target_container, unsigned int flags) { return __skb_flow_dissect(skb, flow_dissector, target_container, - NULL, 0, 0, 0); + NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, - struct flow_keys *flow) + struct flow_keys *flow, + unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(skb, &flow_keys_dissector, flow, - NULL, 0, 0, 0); + NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow, void *data, __be16 proto, - int nhoff, int hlen) + int nhoff, int hlen, + unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow, - data, proto, nhoff, hlen); + data, proto, nhoff, hlen, flags); } static inline __u32 skb_get_hash(struct sk_buff *skb) @@ -2046,7 +2049,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb, if (skb_transport_header_was_set(skb)) return; - else if (skb_flow_dissect_flow_keys(skb, &keys)) + else if (skb_flow_dissect_flow_keys(skb, &keys, 0)) skb_set_transport_header(skb, keys.control.thoff); else skb_set_transport_header(skb, offset_hint); -- cgit v1.2.3 From de4c1f8ba302ccf4f2b3b17dc614b0a0b14d351a Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 1 Sep 2015 18:11:04 -0700 Subject: flow_dissector: Fix function argument ordering dependency Commit c6cc1ca7f4d70c ("flowi: Abstract out functions to get flow hash based on flowi") introduced a bug in __skb_set_sw_hash where we require a dependency on evaluating arguments in a function in order. There is no such ordering enforced in C, so this incorrect. This patch fixes that by splitting out the arguments. This bug was found via a compiler warning that keys may be uninitialized. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9e62687c70f3..eabfb810bc62 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1035,9 +1035,9 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; + __u32 hash = __get_hash_from_flowi6(fl6, &keys); - __skb_set_sw_hash(skb, __get_hash_from_flowi6(fl6, &keys), - flow_keys_have_l4(&keys)); + __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; @@ -1049,9 +1049,9 @@ static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl4) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; + __u32 hash = __get_hash_from_flowi4(fl4, &keys); - __skb_set_sw_hash(skb, __get_hash_from_flowi4(fl4, &keys), - flow_keys_have_l4(&keys)); + __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; -- cgit v1.2.3 From 20a17bf6c04e3eca8824c930ecc55ab832558e3b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 1 Sep 2015 21:19:17 -0700 Subject: flow_dissector: Use 'const' where possible. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index eabfb810bc62..2738d355cdf9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1029,9 +1029,9 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->hash; } -__u32 __skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6); +__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6); -static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6) +static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; @@ -1043,9 +1043,9 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6) return skb->hash; } -__u32 __skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl); +__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl); -static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl4) +static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; -- cgit v1.2.3 From 62da98656b62a5ca57f22263705175af8ded5aa1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 3 Sep 2015 01:26:07 +0200 Subject: netfilter: nf_conntrack: make nf_ct_zone_dflt built-in Fengguang reported, that some randconfig generated the following linker issue with nf_ct_zone_dflt object involved: [...] CC init/version.o LD init/built-in.o net/built-in.o: In function `ipv4_conntrack_defrag': nf_defrag_ipv4.c:(.text+0x93e95): undefined reference to `nf_ct_zone_dflt' net/built-in.o: In function `ipv6_defrag': nf_defrag_ipv6_hooks.c:(.text+0xe3ffe): undefined reference to `nf_ct_zone_dflt' make: *** [vmlinux] Error 1 Given that configurations exist where we have a built-in part, which is accessing nf_ct_zone_dflt such as the two handlers nf_ct_defrag_user() and nf_ct6_defrag_user(), and a part that configures nf_conntrack as a module, we must move nf_ct_zone_dflt into a fixed, guaranteed built-in area when netfilter is configured in general. Therefore, split the more generic parts into a common header under include/linux/netfilter/ and move nf_ct_zone_dflt into the built-in section that already holds parts related to CONFIG_NF_CONNTRACK in the netfilter core. This fixes the issue on my side. Fixes: 308ac9143ee2 ("netfilter: nf_conntrack: push zone object into functions") Reported-by: Fengguang Wu Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 ++ .../linux/netfilter/nf_conntrack_zones_common.h | 23 ++++++++++++++++++++++ 2 files changed, 25 insertions(+) create mode 100644 include/linux/netfilter/nf_conntrack_zones_common.h (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d788ce62d826..36a652531791 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -368,6 +368,8 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#include + extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; diff --git a/include/linux/netfilter/nf_conntrack_zones_common.h b/include/linux/netfilter/nf_conntrack_zones_common.h new file mode 100644 index 000000000000..5d7cf36d4766 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_zones_common.h @@ -0,0 +1,23 @@ +#ifndef _NF_CONNTRACK_ZONES_COMMON_H +#define _NF_CONNTRACK_ZONES_COMMON_H + +#include + +#define NF_CT_DEFAULT_ZONE_ID 0 + +#define NF_CT_ZONE_DIR_ORIG (1 << IP_CT_DIR_ORIGINAL) +#define NF_CT_ZONE_DIR_REPL (1 << IP_CT_DIR_REPLY) + +#define NF_CT_DEFAULT_ZONE_DIR (NF_CT_ZONE_DIR_ORIG | NF_CT_ZONE_DIR_REPL) + +#define NF_CT_FLAG_MARK 1 + +struct nf_conntrack_zone { + u16 id; + u8 flags; + u8 dir; +}; + +extern const struct nf_conntrack_zone nf_ct_zone_dflt; + +#endif /* _NF_CONNTRACK_ZONES_COMMON_H */ -- cgit v1.2.3