From e5a55a898720096f43bc24938f8875c0a1b34cd7 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 24 Oct 2012 08:12:57 +0000 Subject: net: create generic bridge ops The PF_BRIDGE:RTM_{GET|SET}LINK nlmsg family and type are currently embedded in the ./net/bridge module. This prohibits them from being used by other bridging devices. One example of this being hardware that has embedded bridging components. In order to use these nlmsg types more generically this patch adds two net_device_ops hooks. One to set link bridge attributes and another to dump the current bride attributes. ndo_bridge_setlink() ndo_bridge_getlink() CC: Lennert Buytenhek CC: Stephen Hemminger Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f8eda0276f03..7bf867c97043 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -887,6 +887,10 @@ struct netdev_fcoe_hbainfo { * struct net_device *dev, int idx) * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. + * + * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh) + * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, + * struct net_device *dev) */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -998,6 +1002,12 @@ struct net_device_ops { struct netlink_callback *cb, struct net_device *dev, int idx); + + int (*ndo_bridge_setlink)(struct net_device *dev, + struct nlmsghdr *nlh); + int (*ndo_bridge_getlink)(struct sk_buff *skb, + u32 pid, u32 seq, + struct net_device *dev); }; /* -- cgit v1.2.3 From 62532da9d5f47a7ced3b965aa73ffd5b1afbeb79 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Thu, 15 Nov 2012 08:49:10 +0000 Subject: net: Add generic packet offload infrastructure. Create a new data structure to contain the GRO/GSO callbacks and add a new registration mechanism. Singed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 +++++++++ net/core/dev.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 94 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7bf867c97043..d45a58db4ba3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1521,6 +1521,17 @@ struct packet_type { struct list_head list; }; +struct packet_offload { + __be16 type; /* This is really htons(ether_type). */ + struct sk_buff *(*gso_segment)(struct sk_buff *skb, + netdev_features_t features); + int (*gso_send_check)(struct sk_buff *skb); + struct sk_buff **(*gro_receive)(struct sk_buff **head, + struct sk_buff *skb); + int (*gro_complete)(struct sk_buff *skb); + struct list_head list; +}; + #include /* netdevice notifier chain. Please remember to update the rtnetlink @@ -1615,6 +1626,9 @@ extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short extern void dev_add_pack(struct packet_type *pt); extern void dev_remove_pack(struct packet_type *pt); extern void __dev_remove_pack(struct packet_type *pt); +extern void dev_add_offload(struct packet_offload *po); +extern void dev_remove_offload(struct packet_offload *po); +extern void __dev_remove_offload(struct packet_offload *po); extern struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags, unsigned short mask); diff --git a/net/core/dev.c b/net/core/dev.c index 83232a1be1e7..6884f8783bdd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -176,8 +176,10 @@ #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) static DEFINE_SPINLOCK(ptype_lock); +static DEFINE_SPINLOCK(offload_lock); static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; static struct list_head ptype_all __read_mostly; /* Taps */ +static struct list_head offload_base __read_mostly; /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -470,6 +472,82 @@ void dev_remove_pack(struct packet_type *pt) } EXPORT_SYMBOL(dev_remove_pack); + +/** + * dev_add_offload - register offload handlers + * @po: protocol offload declaration + * + * Add protocol offload handlers to the networking stack. The passed + * &proto_offload is linked into kernel lists and may not be freed until + * it has been removed from the kernel lists. + * + * This call does not sleep therefore it can not + * guarantee all CPU's that are in middle of receiving packets + * will see the new offload handlers (until the next received packet). + */ +void dev_add_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + + spin_lock(&offload_lock); + list_add_rcu(&po->list, head); + spin_unlock(&offload_lock); +} +EXPORT_SYMBOL(dev_add_offload); + +/** + * __dev_remove_offload - remove offload handler + * @po: packet offload declaration + * + * Remove a protocol offload handler that was previously added to the + * kernel offload handlers by dev_add_offload(). The passed &offload_type + * is removed from the kernel lists and can be freed or reused once this + * function returns. + * + * The packet type might still be in use by receivers + * and must not be freed until after all the CPU's have gone + * through a quiescent state. + */ +void __dev_remove_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + struct packet_offload *po1; + + spin_lock(&ptype_lock); + + list_for_each_entry(po1, head, list) { + if (po == po1) { + list_del_rcu(&po->list); + goto out; + } + } + + pr_warn("dev_remove_offload: %p not found\n", po); +out: + spin_unlock(&ptype_lock); +} +EXPORT_SYMBOL(__dev_remove_offload); + +/** + * dev_remove_offload - remove packet offload handler + * @po: packet offload declaration + * + * Remove a packet offload handler that was previously added to the kernel + * offload handlers by dev_add_offload(). The passed &offload_type is + * removed from the kernel lists and can be freed or reused once this + * function returns. + * + * This call sleeps to guarantee that no CPU is looking at the packet + * type after return. + */ +void dev_remove_offload(struct packet_offload *po) +{ + __dev_remove_offload(po); + + synchronize_net(); +} +EXPORT_SYMBOL(dev_remove_offload); + /****************************************************************************** Device Boot-time Settings Routines @@ -6661,6 +6739,8 @@ static int __init net_dev_init(void) for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); + INIT_LIST_HEAD(&offload_base); + if (register_pernet_subsys(&netdev_net_ops)) goto out; -- cgit v1.2.3 From 22061d8014455b01eb018bd6c35a1b3040ccc230 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Thu, 15 Nov 2012 08:49:11 +0000 Subject: net: Switch to using the new packet offload infrustructure Convert to using the new GSO/GRO registration mechanism and new packet offload structure. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ------ net/core/dev.c | 19 +++++++++---------- net/ipv4/af_inet.c | 5 +++++ net/ipv6/af_inet6.c | 6 ++++++ 4 files changed, 20 insertions(+), 16 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d45a58db4ba3..61bc8483031f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1509,12 +1509,6 @@ struct packet_type { struct net_device *, struct packet_type *, struct net_device *); - struct sk_buff *(*gso_segment)(struct sk_buff *skb, - netdev_features_t features); - int (*gso_send_check)(struct sk_buff *skb); - struct sk_buff **(*gro_receive)(struct sk_buff **head, - struct sk_buff *skb); - int (*gro_complete)(struct sk_buff *skb); bool (*id_match)(struct packet_type *ptype, struct sock *sk); void *af_packet_priv; diff --git a/net/core/dev.c b/net/core/dev.c index 6884f8783bdd..cf843a256cc6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2072,7 +2072,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; int vlan_depth = ETH_HLEN; int err; @@ -2101,9 +2101,8 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, } rcu_read_lock(); - list_for_each_entry_rcu(ptype, - &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && !ptype->dev && ptype->gso_segment) { + list_for_each_entry_rcu(ptype, &offload_base, list) { + if (ptype->type == type && ptype->gso_segment) { if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { err = ptype->gso_send_check(skb); segs = ERR_PTR(err); @@ -3522,9 +3521,9 @@ static void flush_backlog(void *arg) static int napi_gro_complete(struct sk_buff *skb) { - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; + struct list_head *head = &offload_base; int err = -ENOENT; if (NAPI_GRO_CB(skb)->count == 1) { @@ -3534,7 +3533,7 @@ static int napi_gro_complete(struct sk_buff *skb) rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || ptype->dev || !ptype->gro_complete) + if (ptype->type != type || !ptype->gro_complete) continue; err = ptype->gro_complete(skb); @@ -3584,9 +3583,9 @@ EXPORT_SYMBOL(napi_gro_flush); enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; + struct list_head *head = &offload_base; int same_flow; int mac_len; enum gro_result ret; @@ -3599,7 +3598,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || ptype->dev || !ptype->gro_receive) + if (ptype->type != type || !ptype->gro_receive) continue; skb_set_network_header(skb, skb_gro_offset(skb)); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 766c59658563..4c99c5fdba3f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1662,6 +1662,10 @@ static int ipv4_proc_init(void); static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, +}; + +static struct packet_offload ip_packet_offload __read_mostly = { + .type = cpu_to_be16(ETH_P_IP), .gso_send_check = inet_gso_send_check, .gso_segment = inet_gso_segment, .gro_receive = inet_gro_receive, @@ -1781,6 +1785,7 @@ static int __init inet_init(void) ipfrag_init(); + dev_add_offload(&ip_packet_offload); dev_add_pack(&ip_packet_type); rc = 0; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a974247a9ae4..6e245177608c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -938,6 +938,10 @@ out_unlock: static struct packet_type ipv6_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .func = ipv6_rcv, +}; + +static struct packet_offload ipv6_packet_offload __read_mostly = { + .type = cpu_to_be16(ETH_P_IPV6), .gso_send_check = ipv6_gso_send_check, .gso_segment = ipv6_gso_segment, .gro_receive = ipv6_gro_receive, @@ -946,6 +950,7 @@ static struct packet_type ipv6_packet_type __read_mostly = { static int __init ipv6_packet_init(void) { + dev_add_offload(&ipv6_packet_offload); dev_add_pack(&ipv6_packet_type); return 0; } @@ -953,6 +958,7 @@ static int __init ipv6_packet_init(void) static void ipv6_packet_cleanup(void) { dev_remove_pack(&ipv6_packet_type); + dev_remove_offload(&ipv6_packet_offload); } static int __net_init ipv6_init_mibs(struct net *net) -- cgit v1.2.3 From f191a1d17f227032c159e5499809f545402b6dc6 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Thu, 15 Nov 2012 08:49:23 +0000 Subject: net: Remove code duplication between offload structures Move the offload callbacks into its own structure. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 +++++++--- include/net/protocol.h | 10 +++------- net/core/dev.c | 14 +++++++------- net/ipv4/af_inet.c | 42 ++++++++++++++++++++++++------------------ net/ipv6/ip6_offload.c | 28 +++++++++++++++------------- net/ipv6/tcpv6_offload.c | 10 ++++++---- net/ipv6/udp_offload.c | 6 ++++-- 7 files changed, 66 insertions(+), 54 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 61bc8483031f..e46c830c88d8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1515,15 +1515,19 @@ struct packet_type { struct list_head list; }; -struct packet_offload { - __be16 type; /* This is really htons(ether_type). */ +struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); - struct list_head list; +}; + +struct packet_offload { + __be16 type; /* This is really htons(ether_type). */ + struct offload_callbacks callbacks; + struct list_head list; }; #include diff --git a/include/net/protocol.h b/include/net/protocol.h index 2c90794c139d..047c0476c0a0 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -29,6 +29,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include #endif +#include /* This is one larger than the largest protocol value that can be * found in an ipv4 or ipv6 header. Since in both cases the protocol @@ -63,13 +64,8 @@ struct inet6_protocol { #endif struct net_offload { - int (*gso_send_check)(struct sk_buff *skb); - struct sk_buff *(*gso_segment)(struct sk_buff *skb, - netdev_features_t features); - struct sk_buff **(*gro_receive)(struct sk_buff **head, - struct sk_buff *skb); - int (*gro_complete)(struct sk_buff *skb); - unsigned int flags; /* Flags used by IPv6 for now */ + struct offload_callbacks callbacks; + unsigned int flags; /* Flags used by IPv6 for now */ }; /* This should be set for any extension header which is compatible with GSO. */ #define INET6_PROTO_GSO_EXTHDR 0x1 diff --git a/net/core/dev.c b/net/core/dev.c index cf843a256cc6..cf105e886cca 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2102,16 +2102,16 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { - if (ptype->type == type && ptype->gso_segment) { + if (ptype->type == type && ptype->callbacks.gso_segment) { if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { - err = ptype->gso_send_check(skb); + err = ptype->callbacks.gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) break; __skb_push(skb, (skb->data - skb_network_header(skb))); } - segs = ptype->gso_segment(skb, features); + segs = ptype->callbacks.gso_segment(skb, features); break; } } @@ -3533,10 +3533,10 @@ static int napi_gro_complete(struct sk_buff *skb) rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->gro_complete) + if (ptype->type != type || !ptype->callbacks.gro_complete) continue; - err = ptype->gro_complete(skb); + err = ptype->callbacks.gro_complete(skb); break; } rcu_read_unlock(); @@ -3598,7 +3598,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->gro_receive) + if (ptype->type != type || !ptype->callbacks.gro_receive) continue; skb_set_network_header(skb, skb_gro_offset(skb)); @@ -3608,7 +3608,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; - pp = ptype->gro_receive(&napi->gro_list, skb); + pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); break; } rcu_read_unlock(); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9f2e7fd8bea8..d5e5a054123c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1276,8 +1276,8 @@ static int inet_gso_send_check(struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(inet_offloads[proto]); - if (likely(ops && ops->gso_send_check)) - err = ops->gso_send_check(skb); + if (likely(ops && ops->callbacks.gso_send_check)) + err = ops->callbacks.gso_send_check(skb); rcu_read_unlock(); out: @@ -1326,8 +1326,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, rcu_read_lock(); ops = rcu_dereference(inet_offloads[proto]); - if (likely(ops && ops->gso_segment)) - segs = ops->gso_segment(skb, features); + if (likely(ops && ops->callbacks.gso_segment)) + segs = ops->callbacks.gso_segment(skb, features); rcu_read_unlock(); if (!segs || IS_ERR(segs)) @@ -1379,7 +1379,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, rcu_read_lock(); ops = rcu_dereference(inet_offloads[proto]); - if (!ops || !ops->gro_receive) + if (!ops || !ops->callbacks.gro_receive) goto out_unlock; if (*(u8 *)iph != 0x45) @@ -1420,7 +1420,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); - pp = ops->gro_receive(head, skb); + pp = ops->callbacks.gro_receive(head, skb); out_unlock: rcu_read_unlock(); @@ -1444,10 +1444,10 @@ static int inet_gro_complete(struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(inet_offloads[proto]); - if (WARN_ON(!ops || !ops->gro_complete)) + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->gro_complete(skb); + err = ops->callbacks.gro_complete(skb); out_unlock: rcu_read_unlock(); @@ -1563,10 +1563,12 @@ static const struct net_protocol tcp_protocol = { }; static const struct net_offload tcp_offload = { - .gso_send_check = tcp_v4_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, + .callbacks = { + .gso_send_check = tcp_v4_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + }, }; static const struct net_protocol udp_protocol = { @@ -1577,8 +1579,10 @@ static const struct net_protocol udp_protocol = { }; static const struct net_offload udp_offload = { - .gso_send_check = udp4_ufo_send_check, - .gso_segment = udp4_ufo_fragment, + .callbacks = { + .gso_send_check = udp4_ufo_send_check, + .gso_segment = udp4_ufo_fragment, + }, }; static const struct net_protocol icmp_protocol = { @@ -1667,10 +1671,12 @@ static int ipv4_proc_init(void); static struct packet_offload ip_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_IP), - .gso_send_check = inet_gso_send_check, - .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, + .callbacks = { + .gso_send_check = inet_gso_send_check, + .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, + }, }; static int __init ipv4_offload_init(void) diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 63d79d9005bd..f26f0da7f095 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -70,9 +70,9 @@ static int ipv6_gso_send_check(struct sk_buff *skb) ops = rcu_dereference(inet6_offloads[ ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); - if (likely(ops && ops->gso_send_check)) { + if (likely(ops && ops->callbacks.gso_send_check)) { skb_reset_transport_header(skb); - err = ops->gso_send_check(skb); + err = ops->callbacks.gso_send_check(skb); } rcu_read_unlock(); @@ -113,9 +113,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); rcu_read_lock(); ops = rcu_dereference(inet6_offloads[proto]); - if (likely(ops && ops->gso_segment)) { + if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); - segs = ops->gso_segment(skb, features); + segs = ops->callbacks.gso_segment(skb, features); } rcu_read_unlock(); @@ -173,7 +173,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, rcu_read_lock(); proto = iph->nexthdr; ops = rcu_dereference(inet6_offloads[proto]); - if (!ops || !ops->gro_receive) { + if (!ops || !ops->callbacks.gro_receive) { __pskb_pull(skb, skb_gro_offset(skb)); proto = ipv6_gso_pull_exthdrs(skb, proto); skb_gro_pull(skb, -skb_transport_offset(skb)); @@ -181,7 +181,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, __skb_push(skb, skb_gro_offset(skb)); ops = rcu_dereference(inet6_offloads[proto]); - if (!ops || !ops->gro_receive) + if (!ops || !ops->callbacks.gro_receive) goto out_unlock; iph = ipv6_hdr(skb); @@ -220,7 +220,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, csum = skb->csum; skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); - pp = ops->gro_receive(head, skb); + pp = ops->callbacks.gro_receive(head, skb); skb->csum = csum; @@ -244,10 +244,10 @@ static int ipv6_gro_complete(struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]); - if (WARN_ON(!ops || !ops->gro_complete)) + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->gro_complete(skb); + err = ops->callbacks.gro_complete(skb); out_unlock: rcu_read_unlock(); @@ -257,10 +257,12 @@ out_unlock: static struct packet_offload ipv6_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), - .gso_send_check = ipv6_gso_send_check, - .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, - .gro_complete = ipv6_gro_complete, + .callbacks = { + .gso_send_check = ipv6_gso_send_check, + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, + }, }; static int __init ipv6_offload_init(void) diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 3a27fe685c8e..2ec6bf6a0aa0 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -81,10 +81,12 @@ static int tcp6_gro_complete(struct sk_buff *skb) } static const struct net_offload tcpv6_offload = { - .gso_send_check = tcp_v6_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, + .callbacks = { + .gso_send_check = tcp_v6_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, }; int __init tcpv6_offload_init(void) diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 979e4ab63a8b..8e01c44a987c 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -107,8 +107,10 @@ out: return segs; } static const struct net_offload udpv6_offload = { - .gso_send_check = udp6_ufo_send_check, - .gso_segment = udp6_ufo_fragment, + .callbacks = { + .gso_send_check = udp6_ufo_send_check, + .gso_segment = udp6_ufo_fragment, + }, }; int __init udp_offload_init(void) -- cgit v1.2.3 From d93cf0687c9853bf91b1b9a5124ab97ebc47e00c Mon Sep 17 00:00:00 2001 From: Adam Buchbinder Date: Wed, 19 Sep 2012 21:47:58 -0400 Subject: various: Fix spelling of "registered" in comments. Some comments misspell "registered"; this fixes them. No code changes. Signed-off-by: Adam Buchbinder Signed-off-by: Jiri Kosina --- arch/cris/include/arch-v10/arch/irq.h | 2 +- arch/cris/include/arch-v32/arch/irq.h | 2 +- include/linux/netdevice.h | 2 +- include/net/irda/irlmp.h | 2 +- net/netfilter/nf_log.c | 2 +- sound/core/seq/seq_device.c | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/arch/cris/include/arch-v10/arch/irq.h b/arch/cris/include/arch-v10/arch/irq.h index 7d345947b3ee..ca2675ae08ed 100644 --- a/arch/cris/include/arch-v10/arch/irq.h +++ b/arch/cris/include/arch-v10/arch/irq.h @@ -142,7 +142,7 @@ __asm__ ( \ * it here, we would not get the multiple_irq at all. * * The non-blocking here is based on the knowledge that the timer interrupt is - * registred as a fast interrupt (IRQF_DISABLED) so that we _know_ there will not + * registered as a fast interrupt (IRQF_DISABLED) so that we _know_ there will not * be an sti() before the timer irq handler is run to acknowledge the interrupt. */ diff --git a/arch/cris/include/arch-v32/arch/irq.h b/arch/cris/include/arch-v32/arch/irq.h index b31e9984f849..fe3cdd22bed4 100644 --- a/arch/cris/include/arch-v32/arch/irq.h +++ b/arch/cris/include/arch-v32/arch/irq.h @@ -103,7 +103,7 @@ __asm__ ( \ * if we had BLOCK'edit here, we would not get the multiple_irq at all. * * The non-blocking here is based on the knowledge that the timer interrupt is - * registred as a fast interrupt (IRQF_DISABLED) so that we _know_ there will not + * registered as a fast interrupt (IRQF_DISABLED) so that we _know_ there will not * be an sti() before the timer irq handler is run to acknowledge the interrupt. */ #define BUILD_TIMER_IRQ(nr, mask) \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f8eda0276f03..b2056e6e2acc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -369,7 +369,7 @@ typedef enum gro_result gro_result_t; * * If the rx_handler consider the skb should be ignored, it should return * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that - * are registred on exact device (ptype->dev == skb->dev). + * are registered on exact device (ptype->dev == skb->dev). * * If the rx_handler didn't changed skb->dev, but want the skb to be normally * delivered, it should return RX_HANDLER_PASS. diff --git a/include/net/irda/irlmp.h b/include/net/irda/irlmp.h index fff11b7fe8a4..591f78631f13 100644 --- a/include/net/irda/irlmp.h +++ b/include/net/irda/irlmp.h @@ -134,7 +134,7 @@ typedef struct { } CACHE_ENTRY; /* - * Information about each registred IrLAP layer + * Information about each registered IrLAP layer */ struct lap_cb { irda_queue_t queue; /* Must be first */ diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 703fb26aa48d..9e312695c818 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -32,7 +32,7 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger) return NULL; } -/* return EEXIST if the same logger is registred, 0 on success. */ +/* return EEXIST if the same logger is registered, 0 on success. */ int nf_log_register(u_int8_t pf, struct nf_logger *logger) { const struct nf_logger *llog; diff --git a/sound/core/seq/seq_device.c b/sound/core/seq/seq_device.c index 60e8fc1b3440..040c60e1da28 100644 --- a/sound/core/seq/seq_device.c +++ b/sound/core/seq/seq_device.c @@ -66,7 +66,7 @@ struct ops_list { /* operators */ struct snd_seq_dev_ops ops; - /* registred devices */ + /* registered devices */ struct list_head dev_list; /* list of devices */ int num_devices; /* number of associated devices */ int num_init_devices; /* number of initialized devices */ -- cgit v1.2.3 From c91f6df2db4972d3cc983e6988b9abf1ad02f5f9 Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Mon, 26 Nov 2012 05:21:08 +0000 Subject: sockopt: Change getsockopt() of SO_BINDTODEVICE to return an interface name Instead of having the getsockopt() of SO_BINDTODEVICE return an index, which will then require another call like if_indextoname() to get the actual interface name, have it return the name directly. This also matches the existing man page description on socket(7) which mentions the argument being an interface name. If the value has not been set, zero is returned and optlen will be set to zero to indicate there is no interface name present. Added a seqlock to protect this code path, and dev_ifname(), from someone changing the device name via dev_change_name(). v2: Added seqlock protection while copying device name. v3: Fixed word wrap in patch. Signed-off-by: Brian Haley Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 21 ++++++++++++++-- net/core/sock.c | 64 ++++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 81 insertions(+), 6 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e46c830c88d8..e9929abeb932 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1567,6 +1567,8 @@ extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern rwlock_t dev_base_lock; /* Device list lock */ +extern seqlock_t devnet_rename_seq; /* Device rename lock */ + #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) diff --git a/net/core/dev.c b/net/core/dev.c index 7304ea8a1f13..2a5f55866429 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -203,6 +203,8 @@ static struct list_head offload_base __read_mostly; DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +DEFINE_SEQLOCK(devnet_rename_seq); + static inline void dev_base_seq_inc(struct net *net) { while (++net->dev_base_seq == 0); @@ -1091,22 +1093,31 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) + write_seqlock(&devnet_rename_seq); + + if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { + write_sequnlock(&devnet_rename_seq); return 0; + } memcpy(oldname, dev->name, IFNAMSIZ); err = dev_get_valid_name(net, dev, newname); - if (err < 0) + if (err < 0) { + write_sequnlock(&devnet_rename_seq); return err; + } rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); + write_sequnlock(&devnet_rename_seq); return ret; } + write_sequnlock(&devnet_rename_seq); + write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); write_unlock_bh(&dev_base_lock); @@ -1124,6 +1135,7 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; + write_seqlock(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; } else { @@ -4148,6 +4160,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) { struct net_device *dev; struct ifreq ifr; + unsigned seq; /* * Fetch the caller's info block. @@ -4156,6 +4169,8 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; +retry: + seq = read_seqbegin(&devnet_rename_seq); rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); if (!dev) { @@ -4165,6 +4180,8 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) strcpy(ifr.ifr_name, dev->name); rcu_read_unlock(); + if (read_seqretry(&devnet_rename_seq, seq)) + goto retry; if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; diff --git a/net/core/sock.c b/net/core/sock.c index d4f7b58b3866..a692ef49c9bb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -505,7 +505,8 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) } EXPORT_SYMBOL(sk_dst_check); -static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) +static int sock_setbindtodevice(struct sock *sk, char __user *optval, + int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES @@ -562,6 +563,59 @@ out: return ret; } +static int sock_getbindtodevice(struct sock *sk, char __user *optval, + int __user *optlen, int len) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + struct net *net = sock_net(sk); + struct net_device *dev; + char devname[IFNAMSIZ]; + unsigned seq; + + if (sk->sk_bound_dev_if == 0) { + len = 0; + goto zero; + } + + ret = -EINVAL; + if (len < IFNAMSIZ) + goto out; + +retry: + seq = read_seqbegin(&devnet_rename_seq); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + ret = -ENODEV; + if (!dev) { + rcu_read_unlock(); + goto out; + } + + strcpy(devname, dev->name); + rcu_read_unlock(); + if (read_seqretry(&devnet_rename_seq, seq)) + goto retry; + + len = strlen(devname) + 1; + + ret = -EFAULT; + if (copy_to_user(optval, devname, len)) + goto out; + +zero: + ret = -EFAULT; + if (put_user(len, optlen)) + goto out; + + ret = 0; + +out: +#endif + + return ret; +} + static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) { if (valbool) @@ -589,7 +643,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, */ if (optname == SO_BINDTODEVICE) - return sock_bindtodevice(sk, optval, optlen); + return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; @@ -1075,15 +1129,17 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); break; + case SO_BINDTODEVICE: - v.val = sk->sk_bound_dev_if; - break; + return sock_getbindtodevice(sk, optval, optlen, len); + case SO_GET_FILTER: len = sk_get_filter(sk, (struct sock_filter __user *)optval, len); if (len < 0) return len; goto lenout; + default: return -ENOPROTOOPT; } -- cgit v1.2.3 From bb728820fe7c42fdb838ab2745fb5fe6b18b5ffa Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Wed, 28 Nov 2012 21:55:25 +0000 Subject: core: make GRO methods static. This patch changes three methods to be static and removes their EXPORT_SYMBOLs in core/dev.c and their external declaration in netdevice.h. The methods, dev_gro_receive(), napi_frags_finish() and napi_skb_finish(), which are in the GRO rx path, are not used outside core/dev.c. Signed-off-by: Rami Rosen Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ------ net/core/dev.c | 9 +++------ 2 files changed, 3 insertions(+), 12 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e9929abeb932..18c5dc98f6dc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2153,16 +2153,10 @@ extern void dev_kfree_skb_any(struct sk_buff *skb); extern int netif_rx(struct sk_buff *skb); extern int netif_rx_ni(struct sk_buff *skb); extern int netif_receive_skb(struct sk_buff *skb); -extern gro_result_t dev_gro_receive(struct napi_struct *napi, - struct sk_buff *skb); -extern gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb); extern gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); extern void napi_gro_flush(struct napi_struct *napi, bool flush_old); extern struct sk_buff * napi_get_frags(struct napi_struct *napi); -extern gro_result_t napi_frags_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret); extern gro_result_t napi_gro_frags(struct napi_struct *napi); static inline void napi_free_frags(struct napi_struct *napi) diff --git a/net/core/dev.c b/net/core/dev.c index 2a5f55866429..2f94df257e5a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3592,7 +3592,7 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old) } EXPORT_SYMBOL(napi_gro_flush); -enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; struct packet_offload *ptype; @@ -3683,7 +3683,6 @@ normal: ret = GRO_NORMAL; goto pull; } -EXPORT_SYMBOL(dev_gro_receive); static inline gro_result_t __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) @@ -3710,7 +3709,7 @@ __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) return dev_gro_receive(napi, skb); } -gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) +static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { case GRO_NORMAL: @@ -3736,7 +3735,6 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) return ret; } -EXPORT_SYMBOL(napi_skb_finish); static void skb_gro_reset_offset(struct sk_buff *skb) { @@ -3788,7 +3786,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); -gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, +static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) { switch (ret) { @@ -3813,7 +3811,6 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, return ret; } -EXPORT_SYMBOL(napi_frags_finish); static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { -- cgit v1.2.3 From c3c7c254b2e8cd99b0adf288c2a1bddacd7ba255 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 6 Dec 2012 13:54:59 +0000 Subject: net: gro: fix possible panic in skb_gro_receive() commit 2e71a6f8084e (net: gro: selective flush of packets) added a bug for skbs using frag_list. This part of the GRO stack is rarely used, as it needs skb not using a page fragment for their skb->head. Most drivers do use a page fragment, but some of them use GFP_KERNEL allocations for the initial fill of their RX ring buffer. napi_gro_flush() overwrite skb->prev that was used for these skb to point to the last skb in frag_list. Fix this using a separate field in struct napi_gro_cb to point to the last fragment. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ net/core/dev.c | 2 ++ net/core/skbuff.c | 6 +++--- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f8eda0276f03..a848ffc327f4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1488,6 +1488,9 @@ struct napi_gro_cb { /* Used in ipv6_gro_receive() */ int proto; + + /* used in skb_gro_receive() slow path */ + struct sk_buff *last; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) diff --git a/net/core/dev.c b/net/core/dev.c index c0946cb2b354..e5942bf45a6d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3451,6 +3451,8 @@ static int napi_gro_complete(struct sk_buff *skb) struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; int err = -ENOENT; + BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); + if (NAPI_GRO_CB(skb)->count == 1) { skb_shinfo(skb)->gso_size = 0; goto out; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4007c1437fda..3f0636cd76cd 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3004,7 +3004,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) skb_shinfo(nskb)->gso_size = pinfo->gso_size; pinfo->gso_size = 0; skb_header_release(p); - nskb->prev = p; + NAPI_GRO_CB(nskb)->last = p; nskb->data_len += p->len; nskb->truesize += p->truesize; @@ -3030,8 +3030,8 @@ merge: __skb_pull(skb, offset); - p->prev->next = skb; - p->prev = skb; + NAPI_GRO_CB(p)->last->next = skb; + NAPI_GRO_CB(p)->last = skb; skb_header_release(skb); done: -- cgit v1.2.3 From 6a674e9c75b17e7a88ff15b3c2e269eed54f7cfb Mon Sep 17 00:00:00 2001 From: Joseph Gasparakis Date: Fri, 7 Dec 2012 14:14:14 +0000 Subject: net: Add support for hardware-offloaded encapsulation This patch adds support in the kernel for offloading in the NIC Tx and Rx checksumming for encapsulated packets (such as VXLAN and IP GRE). For Tx encapsulation offload, the driver will need to set the right bits in netdev->hw_enc_features. The protocol driver will have to set the skb->encapsulation bit and populate the inner headers, so the NIC driver will use those inner headers to calculate the csum in hardware. For Rx encapsulation offload, the driver will need to set again the skb->encapsulation flag and the skb->ip_csum to CHECKSUM_UNNECESSARY. In that case the protocol driver should push the decapsulated packet up to the stack, again with CHECKSUM_UNNECESSARY. In ether case, the protocol driver should set the skb->encapsulation flag back to zero. Finally the protocol driver should have NETIF_F_RXCSUM flag set in its features. Signed-off-by: Joseph Gasparakis Signed-off-by: Peter P Waskiewicz Jr Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/ip.h | 5 +++ include/linux/ipv6.h | 5 +++ include/linux/netdevice.h | 6 +++ include/linux/skbuff.h | 95 ++++++++++++++++++++++++++++++++++++++++++++++- include/linux/tcp.h | 10 +++++ include/linux/udp.h | 5 +++ net/core/skbuff.c | 9 +++++ 7 files changed, 134 insertions(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/ip.h b/include/linux/ip.h index 58b82a22a52b..492bc6513533 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -25,6 +25,11 @@ static inline struct iphdr *ip_hdr(const struct sk_buff *skb) return (struct iphdr *)skb_network_header(skb); } +static inline struct iphdr *inner_ip_hdr(const struct sk_buff *skb) +{ + return (struct iphdr *)skb_inner_network_header(skb); +} + static inline struct iphdr *ipip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_transport_header(skb); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 12729e966dc9..faed1e357dd6 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -67,6 +67,11 @@ static inline struct ipv6hdr *ipv6_hdr(const struct sk_buff *skb) return (struct ipv6hdr *)skb_network_header(skb); } +static inline struct ipv6hdr *inner_ipv6_hdr(const struct sk_buff *skb) +{ + return (struct ipv6hdr *)skb_inner_network_header(skb); +} + static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_transport_header(skb); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 18c5dc98f6dc..c6a14d4d1396 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1063,6 +1063,12 @@ struct net_device { netdev_features_t wanted_features; /* mask of features inheritable by VLAN devices */ netdev_features_t vlan_features; + /* mask of features inherited by encapsulating devices + * This field indicates what encapsulation offloads + * the hardware is capable of doing, and drivers will + * need to set them appropriately. + */ + netdev_features_t hw_enc_features; /* Interface index. Unique device identifier */ int ifindex; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f2af494330ab..320e976d5ab8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -376,6 +376,8 @@ typedef unsigned char *sk_buff_data_t; * @mark: Generic packet mark * @dropcount: total number of sk_receive_queue overflows * @vlan_tci: vlan tag control information + * @inner_transport_header: Inner transport layer header (encapsulation) + * @inner_network_header: Network layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header @@ -471,7 +473,13 @@ struct sk_buff { __u8 wifi_acked:1; __u8 no_fcs:1; __u8 head_frag:1; - /* 8/10 bit hole (depending on ndisc_nodetype presence) */ + /* Encapsulation protocol and NIC drivers should use + * this flag to indicate to each other if the skb contains + * encapsulated packet or not and maybe use the inner packet + * headers if needed + */ + __u8 encapsulation:1; + /* 7/9 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); #ifdef CONFIG_NET_DMA @@ -486,6 +494,8 @@ struct sk_buff { __u32 avail_size; }; + sk_buff_data_t inner_transport_header; + sk_buff_data_t inner_network_header; sk_buff_data_t transport_header; sk_buff_data_t network_header; sk_buff_data_t mac_header; @@ -1435,12 +1445,53 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +static inline void skb_reset_inner_headers(struct sk_buff *skb) +{ + skb->inner_network_header = skb->network_header; + skb->inner_transport_header = skb->transport_header; +} + static inline void skb_reset_mac_len(struct sk_buff *skb) { skb->mac_len = skb->network_header - skb->mac_header; } #ifdef NET_SKBUFF_DATA_USES_OFFSET +static inline unsigned char *skb_inner_transport_header(const struct sk_buff + *skb) +{ + return skb->head + skb->inner_transport_header; +} + +static inline void skb_reset_inner_transport_header(struct sk_buff *skb) +{ + skb->inner_transport_header = skb->data - skb->head; +} + +static inline void skb_set_inner_transport_header(struct sk_buff *skb, + const int offset) +{ + skb_reset_inner_transport_header(skb); + skb->inner_transport_header += offset; +} + +static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) +{ + return skb->head + skb->inner_network_header; +} + +static inline void skb_reset_inner_network_header(struct sk_buff *skb) +{ + skb->inner_network_header = skb->data - skb->head; +} + +static inline void skb_set_inner_network_header(struct sk_buff *skb, + const int offset) +{ + skb_reset_inner_network_header(skb); + skb->inner_network_header += offset; +} + static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { return skb->head + skb->transport_header; @@ -1496,6 +1547,38 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) } #else /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline unsigned char *skb_inner_transport_header(const struct sk_buff + *skb) +{ + return skb->inner_transport_header; +} + +static inline void skb_reset_inner_transport_header(struct sk_buff *skb) +{ + skb->inner_transport_header = skb->data; +} + +static inline void skb_set_inner_transport_header(struct sk_buff *skb, + const int offset) +{ + skb->inner_transport_header = skb->data + offset; +} + +static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) +{ + return skb->inner_network_header; +} + +static inline void skb_reset_inner_network_header(struct sk_buff *skb) +{ + skb->inner_network_header = skb->data; +} + +static inline void skb_set_inner_network_header(struct sk_buff *skb, + const int offset) +{ + skb->inner_network_header = skb->data + offset; +} static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { @@ -1574,11 +1657,21 @@ static inline u32 skb_network_header_len(const struct sk_buff *skb) return skb->transport_header - skb->network_header; } +static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) +{ + return skb->inner_transport_header - skb->inner_network_header; +} + static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } +static inline int skb_inner_network_offset(const struct sk_buff *skb) +{ + return skb_inner_network_header(skb) - skb->data; +} + static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull(skb, skb_network_offset(skb) + len); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 60b7aac15e0e..4e1d2283e3cc 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -35,6 +35,16 @@ static inline unsigned int tcp_hdrlen(const struct sk_buff *skb) return tcp_hdr(skb)->doff * 4; } +static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb) +{ + return (struct tcphdr *)skb_inner_transport_header(skb); +} + +static inline unsigned int inner_tcp_hdrlen(const struct sk_buff *skb) +{ + return inner_tcp_hdr(skb)->doff * 4; +} + static inline unsigned int tcp_optlen(const struct sk_buff *skb) { return (tcp_hdr(skb)->doff - 5) * 4; diff --git a/include/linux/udp.h b/include/linux/udp.h index 0b67d7793520..9d81de123c90 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -27,6 +27,11 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) return (struct udphdr *)skb_transport_header(skb); } +static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) +{ + return (struct udphdr *)skb_inner_transport_header(skb); +} + #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) static inline int udp_hashfn(struct net *net, unsigned num, unsigned mask) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 880722e22cc5..ccbabf565732 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -682,11 +682,14 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->transport_header = old->transport_header; new->network_header = old->network_header; new->mac_header = old->mac_header; + new->inner_transport_header = old->inner_transport_header; + new->inner_network_header = old->inner_transport_header; skb_dst_copy(new, old); new->rxhash = old->rxhash; new->ooo_okay = old->ooo_okay; new->l4_rxhash = old->l4_rxhash; new->no_fcs = old->no_fcs; + new->encapsulation = old->encapsulation; #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif @@ -892,6 +895,8 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->network_header += offset; if (skb_mac_header_was_set(new)) new->mac_header += offset; + new->inner_transport_header += offset; + new->inner_network_header += offset; #endif skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; @@ -1089,6 +1094,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->network_header += off; if (skb_mac_header_was_set(skb)) skb->mac_header += off; + skb->inner_transport_header += off; + skb->inner_network_header += off; /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL) skb->csum_start += nhead; @@ -1188,6 +1195,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, n->network_header += off; if (skb_mac_header_was_set(skb)) n->mac_header += off; + n->inner_transport_header += off; + n->inner_network_header += off; #endif return n; -- cgit v1.2.3 From 30e6c9fa93cf3dbc7cc6df1d748ad25e4264545a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Dec 2012 17:25:08 +0000 Subject: net: devnet_rename_seq should be a seqcount Using a seqlock for devnet_rename_seq is not a good idea, as device_rename() can sleep. As we hold RTNL, we dont need a protection for writers, and only need a seqcount so that readers can catch a change done by a writer. Bug added in commit c91f6df2db4972d3 (sockopt: Change getsockopt() of SO_BINDTODEVICE to return an interface name) Reported-by: Dave Jones Signed-off-by: Eric Dumazet Cc: Brian Haley Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev.c | 18 +++++++++--------- net/core/sock.c | 4 ++-- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 02e0f6b156c3..c599e4782d45 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1576,7 +1576,7 @@ extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern rwlock_t dev_base_lock; /* Device list lock */ -extern seqlock_t devnet_rename_seq; /* Device rename lock */ +extern seqcount_t devnet_rename_seq; /* Device rename seq */ #define for_each_netdev(net, d) \ diff --git a/net/core/dev.c b/net/core/dev.c index d0cbc93fcf32..515473ee52cb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -203,7 +203,7 @@ static struct list_head offload_base __read_mostly; DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); -DEFINE_SEQLOCK(devnet_rename_seq); +seqcount_t devnet_rename_seq; static inline void dev_base_seq_inc(struct net *net) { @@ -1093,10 +1093,10 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - write_seqlock(&devnet_rename_seq); + write_seqcount_begin(&devnet_rename_seq); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - write_sequnlock(&devnet_rename_seq); + write_seqcount_end(&devnet_rename_seq); return 0; } @@ -1104,7 +1104,7 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_get_valid_name(net, dev, newname); if (err < 0) { - write_sequnlock(&devnet_rename_seq); + write_seqcount_end(&devnet_rename_seq); return err; } @@ -1112,11 +1112,11 @@ rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); - write_sequnlock(&devnet_rename_seq); + write_seqcount_end(&devnet_rename_seq); return ret; } - write_sequnlock(&devnet_rename_seq); + write_seqcount_end(&devnet_rename_seq); write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); @@ -1135,7 +1135,7 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - write_seqlock(&devnet_rename_seq); + write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; } else { @@ -4180,7 +4180,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) return -EFAULT; retry: - seq = read_seqbegin(&devnet_rename_seq); + seq = read_seqcount_begin(&devnet_rename_seq); rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); if (!dev) { @@ -4190,7 +4190,7 @@ retry: strcpy(ifr.ifr_name, dev->name); rcu_read_unlock(); - if (read_seqretry(&devnet_rename_seq, seq)) + if (read_seqcount_retry(&devnet_rename_seq, seq)) goto retry; if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) diff --git a/net/core/sock.c b/net/core/sock.c index a692ef49c9bb..bc131d419683 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -583,7 +583,7 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval, goto out; retry: - seq = read_seqbegin(&devnet_rename_seq); + seq = read_seqcount_begin(&devnet_rename_seq); rcu_read_lock(); dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); ret = -ENODEV; @@ -594,7 +594,7 @@ retry: strcpy(devname, dev->name); rcu_read_unlock(); - if (read_seqretry(&devnet_rename_seq, seq)) + if (read_seqcount_retry(&devnet_rename_seq, seq)) goto retry; len = strlen(devname) + 1; -- cgit v1.2.3 From d07d7507bfb4e23735c9b83e397c43e1e8a173e8 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 10 Jan 2013 23:19:10 +0000 Subject: net, wireless: overwrite default_ethtool_ops Since: commit 2c60db037034d27f8c636403355d52872da92f81 Author: Eric Dumazet Date: Sun Sep 16 09:17:26 2012 +0000 net: provide a default dev->ethtool_ops wireless core does not correctly assign ethtool_ops. After alloc_netdev*() call, some cfg80211 drivers provide they own ethtool_ops, but some do not. For them, wireless core provide generic cfg80211_ethtool_ops, which is assigned in NETDEV_REGISTER notify call: if (!dev->ethtool_ops) dev->ethtool_ops = &cfg80211_ethtool_ops; But after Eric's commit, dev->ethtool_ops is no longer NULL (on cfg80211 drivers without custom ethtool_ops), but points to &default_ethtool_ops. In order to fix the problem, provide function which will overwrite default_ethtool_ops and use it by wireless core. Signed-off-by: Stanislaw Gruszka Acked-by: Johannes Berg Acked-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ net/core/dev.c | 8 ++++++++ net/wireless/core.c | 3 +-- 3 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c599e4782d45..9ef07d0868b6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -60,6 +60,9 @@ struct wireless_dev; #define SET_ETHTOOL_OPS(netdev,ops) \ ( (netdev)->ethtool_ops = (ops) ) +extern void netdev_set_default_ethtool_ops(struct net_device *dev, + const struct ethtool_ops *ops); + /* hardware address assignment types */ #define NET_ADDR_PERM 0 /* address is permanent (default) */ #define NET_ADDR_RANDOM 1 /* address is generated randomly */ diff --git a/net/core/dev.c b/net/core/dev.c index 515473ee52cb..f64e439b4a00 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6121,6 +6121,14 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) static const struct ethtool_ops default_ethtool_ops; +void netdev_set_default_ethtool_ops(struct net_device *dev, + const struct ethtool_ops *ops) +{ + if (dev->ethtool_ops == &default_ethtool_ops) + dev->ethtool_ops = ops; +} +EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); + /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for diff --git a/net/wireless/core.c b/net/wireless/core.c index 14d990400354..b677eab55b68 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -866,8 +866,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, /* allow mac80211 to determine the timeout */ wdev->ps_timeout = -1; - if (!dev->ethtool_ops) - dev->ethtool_ops = &cfg80211_ethtool_ops; + netdev_set_default_ethtool_ops(dev, &cfg80211_ethtool_ops); if ((wdev->iftype == NL80211_IFTYPE_STATION || wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || -- cgit v1.2.3