diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-12-11 14:27:06 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-12-11 14:27:06 -0800 |
commit | 70e71ca0af244f48a5dcf56dc435243792e3a495 (patch) | |
tree | f7d9c4c4d9a857a00043e9bf6aa2d6f533a34778 /net/ipv4 | |
parent | bae41e45b7400496b9bf0c70c6004419d9987819 (diff) | |
parent | 00c83b01d58068dfeb2e1351cca6fccf2a83fa8f (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) New offloading infrastructure and example 'rocker' driver for
offloading of switching and routing to hardware.
This work was done by a large group of dedicated individuals, not
limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu
2) Start making the networking operate on IOV iterators instead of
modifying iov objects in-situ during transfers. Thanks to Al Viro
and Herbert Xu.
3) A set of new netlink interfaces for the TIPC stack, from Richard
Alpe.
4) Remove unnecessary looping during ipv6 routing lookups, from Martin
KaFai Lau.
5) Add PAUSE frame generation support to gianfar driver, from Matei
Pavaluca.
6) Allow for larger reordering levels in TCP, which are easily
achievable in the real world right now, from Eric Dumazet.
7) Add a variable of napi_schedule that doesn't need to disable cpu
interrupts, from Eric Dumazet.
8) Use a doubly linked list to optimize neigh_parms_release(), from
Nicolas Dichtel.
9) Various enhancements to the kernel BPF verifier, and allow eBPF
programs to actually be attached to sockets. From Alexei
Starovoitov.
10) Support TSO/LSO in sunvnet driver, from David L Stevens.
11) Allow controlling ECN usage via routing metrics, from Florian
Westphal.
12) Remote checksum offload, from Tom Herbert.
13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
driver, from Thomas Lendacky.
14) Add MPLS support to openvswitch, from Simon Horman.
15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
Klassert.
16) Do gro flushes on a per-device basis using a timer, from Eric
Dumazet. This tries to resolve the conflicting goals between the
desired handling of bulk vs. RPC-like traffic.
17) Allow userspace to ask for the CPU upon what a packet was
received/steered, via SO_INCOMING_CPU. From Eric Dumazet.
18) Limit GSO packets to half the current congestion window, from Eric
Dumazet.
19) Add a generic helper so that all drivers set their RSS keys in a
consistent way, from Eric Dumazet.
20) Add xmit_more support to enic driver, from Govindarajulu
Varadarajan.
21) Add VLAN packet scheduler action, from Jiri Pirko.
22) Support configurable RSS hash functions via ethtool, from Eyal
Perry.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
Fix race condition between vxlan_sock_add and vxlan_sock_release
net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
net/mlx4: Add support for A0 steering
net/mlx4: Refactor QUERY_PORT
net/mlx4_core: Add explicit error message when rule doesn't meet configuration
net/mlx4: Add A0 hybrid steering
net/mlx4: Add mlx4_bitmap zone allocator
net/mlx4: Add a check if there are too many reserved QPs
net/mlx4: Change QP allocation scheme
net/mlx4_core: Use tasklet for user-space CQ completion events
net/mlx4_core: Mask out host side virtualization features for guests
net/mlx4_en: Set csum level for encapsulated packets
be2net: Export tunnel offloads only when a VxLAN tunnel is created
gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
net: fec: only enable mdio interrupt before phy device link up
net: fec: clear all interrupt events to support i.MX6SX
net: fec: reset fep link status in suspend function
net: sock: fix access via invalid file descriptor
net: introduce helper macro for_each_cmsghdr
...
Diffstat (limited to 'net/ipv4')
40 files changed, 1175 insertions, 561 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index e682b48e0709..bd2901604842 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -322,6 +322,15 @@ config NET_FOU network mechanisms and optimizations for UDP (such as ECMP and RSS) can be leveraged to provide better service. +config NET_FOU_IP_TUNNELS + bool "IP: FOU encapsulation of IP tunnels" + depends on NET_IPIP || NET_IPGRE || IPV6_SIT + select NET_FOU + ---help--- + Allow configuration of FOU or GUE encapsulation for IP tunnels. + When this option is enabled IP tunnels can be configured to use + FOU or GUE encapsulation. + config GENEVE tristate "Generic Network Virtualization Encapsulation (Geneve)" depends on INET diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e67da4e6c324..a44773c8346c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1222,7 +1222,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_TCPV6 | SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM | - SKB_GSO_MPLS | + SKB_GSO_TUNNEL_REMCSUM | 0))) goto out; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 16acb59d665e..205e1472aa78 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1292,7 +1292,7 @@ static int arp_proc_init(void); void __init arp_init(void) { - neigh_table_init(&arp_tbl); + neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl); dev_add_pack(&arp_packet_type); arp_proc_init(); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 4715f25dfe03..5160c710f2eb 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -50,7 +50,7 @@ #include <net/netlabel.h> #include <net/cipso_ipv4.h> #include <linux/atomic.h> -#include <asm/bug.h> +#include <linux/bug.h> #include <asm/unaligned.h> /* List of available DOI definitions */ @@ -72,6 +72,7 @@ struct cipso_v4_map_cache_bkt { u32 size; struct list_head list; }; + struct cipso_v4_map_cache_entry { u32 hash; unsigned char *key; @@ -82,7 +83,8 @@ struct cipso_v4_map_cache_entry { u32 activity; struct list_head list; }; -static struct cipso_v4_map_cache_bkt *cipso_v4_cache = NULL; + +static struct cipso_v4_map_cache_bkt *cipso_v4_cache; /* Restricted bitmap (tag #1) flags */ int cipso_v4_rbm_optfmt = 0; @@ -539,7 +541,7 @@ doi_add_return: /** * cipso_v4_doi_free - Frees a DOI definition - * @entry: the entry's RCU field + * @doi_def: the DOI definition * * Description: * This function frees all of the memory associated with a DOI definition. diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 360b565918c4..60173d4d3a0e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -392,8 +392,10 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) if (elen <= 0) goto out; - if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + err = skb_cow_data(skb, 0, &trailer); + if (err < 0) goto out; + nfrags = err; assoclen = sizeof(*esph); @@ -601,12 +603,12 @@ static int esp_init_authenc(struct xfrm_state *x) BUG_ON(!aalg_desc); err = -EINVAL; - if (aalg_desc->uinfo.auth.icv_fullbits/8 != + if (aalg_desc->uinfo.auth.icv_fullbits / 8 != crypto_aead_authsize(aead)) { - NETDEBUG(KERN_INFO "ESP: %s digestsize %u != %hu\n", - x->aalg->alg_name, - crypto_aead_authsize(aead), - aalg_desc->uinfo.auth.icv_fullbits/8); + pr_info("ESP: %s digestsize %u != %hu\n", + x->aalg->alg_name, + crypto_aead_authsize(aead), + aalg_desc->uinfo.auth.icv_fullbits / 8); goto free_key; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 606c520ffd5a..b986298a7ba3 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -38,21 +38,17 @@ static inline struct fou *fou_from_sock(struct sock *sk) return sk->sk_user_data; } -static int fou_udp_encap_recv_deliver(struct sk_buff *skb, - u8 protocol, size_t len) +static void fou_recv_pull(struct sk_buff *skb, size_t len) { struct iphdr *iph = ip_hdr(skb); /* Remove 'len' bytes from the packet (UDP header and - * FOU header if present), modify the protocol to the one - * we found, and then call rcv_encap. + * FOU header if present). */ iph->tot_len = htons(ntohs(iph->tot_len) - len); __skb_pull(skb, len); skb_postpull_rcsum(skb, udp_hdr(skb), len); skb_reset_transport_header(skb); - - return -protocol; } static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) @@ -62,16 +58,56 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) if (!fou) return 1; - return fou_udp_encap_recv_deliver(skb, fou->protocol, - sizeof(struct udphdr)); + fou_recv_pull(skb, sizeof(struct udphdr)); + + return -fou->protocol; +} + +static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, + void *data, size_t hdrlen, u8 ipproto) +{ + __be16 *pd = data; + size_t start = ntohs(pd[0]); + size_t offset = ntohs(pd[1]); + size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); + __wsum delta; + + if (skb->remcsum_offload) { + /* Already processed in GRO path */ + skb->remcsum_offload = 0; + return guehdr; + } + + if (!pskb_may_pull(skb, plen)) + return NULL; + guehdr = (struct guehdr *)&udp_hdr(skb)[1]; + + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) + __skb_checksum_complete(skb); + + delta = remcsum_adjust((void *)guehdr + hdrlen, + skb->csum, start, offset); + + /* Adjust skb->csum since we changed the packet */ + skb->csum = csum_add(skb->csum, delta); + + return guehdr; +} + +static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr) +{ + /* No support yet */ + kfree_skb(skb); + return 0; } static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) { struct fou *fou = fou_from_sock(sk); - size_t len; + size_t len, optlen, hdrlen; struct guehdr *guehdr; - struct udphdr *uh; + void *data; + u16 doffset = 0; if (!fou) return 1; @@ -80,25 +116,58 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) if (!pskb_may_pull(skb, len)) goto drop; - uh = udp_hdr(skb); - guehdr = (struct guehdr *)&uh[1]; + guehdr = (struct guehdr *)&udp_hdr(skb)[1]; + + optlen = guehdr->hlen << 2; + len += optlen; - len += guehdr->hlen << 2; if (!pskb_may_pull(skb, len)) goto drop; - uh = udp_hdr(skb); - guehdr = (struct guehdr *)&uh[1]; + /* guehdr may change after pull */ + guehdr = (struct guehdr *)&udp_hdr(skb)[1]; - if (guehdr->version != 0) - goto drop; + hdrlen = sizeof(struct guehdr) + optlen; - if (guehdr->flags) { - /* No support yet */ + if (guehdr->version != 0 || validate_gue_flags(guehdr, optlen)) goto drop; + + hdrlen = sizeof(struct guehdr) + optlen; + + ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len); + + /* Pull csum through the guehdr now . This can be used if + * there is a remote checksum offload. + */ + skb_postpull_rcsum(skb, udp_hdr(skb), len); + + data = &guehdr[1]; + + if (guehdr->flags & GUE_FLAG_PRIV) { + __be32 flags = *(__be32 *)(data + doffset); + + doffset += GUE_LEN_PRIV; + + if (flags & GUE_PFLAG_REMCSUM) { + guehdr = gue_remcsum(skb, guehdr, data + doffset, + hdrlen, guehdr->proto_ctype); + if (!guehdr) + goto drop; + + data = &guehdr[1]; + + doffset += GUE_PLEN_REMCSUM; + } } - return fou_udp_encap_recv_deliver(skb, guehdr->next_hdr, len); + if (unlikely(guehdr->control)) + return gue_control_message(skb, guehdr); + + __skb_pull(skb, sizeof(struct udphdr) + hdrlen); + skb_reset_transport_header(skb); + + return -guehdr->proto_ctype; + drop: kfree_skb(skb); return 0; @@ -149,6 +218,41 @@ out_unlock: return err; } +static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, + struct guehdr *guehdr, void *data, + size_t hdrlen, u8 ipproto) +{ + __be16 *pd = data; + size_t start = ntohs(pd[0]); + size_t offset = ntohs(pd[1]); + size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); + __wsum delta; + + if (skb->remcsum_offload) + return guehdr; + + if (!NAPI_GRO_CB(skb)->csum_valid) + return NULL; + + /* Pull checksum that will be written */ + if (skb_gro_header_hard(skb, off + plen)) { + guehdr = skb_gro_header_slow(skb, off + plen, off); + if (!guehdr) + return NULL; + } + + delta = remcsum_adjust((void *)guehdr + hdrlen, + NAPI_GRO_CB(skb)->csum, start, offset); + + /* Adjust skb->csum since we changed the packet */ + skb->csum = csum_add(skb->csum, delta); + NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); + + skb->remcsum_offload = 1; + + return guehdr; +} + static struct sk_buff **gue_gro_receive(struct sk_buff **head, struct sk_buff *skb) { @@ -156,38 +260,64 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, const struct net_offload *ops; struct sk_buff **pp = NULL; struct sk_buff *p; - u8 proto; struct guehdr *guehdr; - unsigned int hlen, guehlen; - unsigned int off; + size_t len, optlen, hdrlen, off; + void *data; + u16 doffset = 0; int flush = 1; off = skb_gro_offset(skb); - hlen = off + sizeof(*guehdr); + len = off + sizeof(*guehdr); + guehdr = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - guehdr = skb_gro_header_slow(skb, hlen, off); + if (skb_gro_header_hard(skb, len)) { + guehdr = skb_gro_header_slow(skb, len, off); if (unlikely(!guehdr)) goto out; } - proto = guehdr->next_hdr; + optlen = guehdr->hlen << 2; + len += optlen; - rcu_read_lock(); - offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; - ops = rcu_dereference(offloads[proto]); - if (WARN_ON(!ops || !ops->callbacks.gro_receive)) - goto out_unlock; + if (skb_gro_header_hard(skb, len)) { + guehdr = skb_gro_header_slow(skb, len, off); + if (unlikely(!guehdr)) + goto out; + } - guehlen = sizeof(*guehdr) + (guehdr->hlen << 2); + if (unlikely(guehdr->control) || guehdr->version != 0 || + validate_gue_flags(guehdr, optlen)) + goto out; - hlen = off + guehlen; - if (skb_gro_header_hard(skb, hlen)) { - guehdr = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!guehdr)) - goto out_unlock; + hdrlen = sizeof(*guehdr) + optlen; + + /* Adjust NAPI_GRO_CB(skb)->csum to account for guehdr, + * this is needed if there is a remote checkcsum offload. + */ + skb_gro_postpull_rcsum(skb, guehdr, hdrlen); + + data = &guehdr[1]; + + if (guehdr->flags & GUE_FLAG_PRIV) { + __be32 flags = *(__be32 *)(data + doffset); + + doffset += GUE_LEN_PRIV; + + if (flags & GUE_PFLAG_REMCSUM) { + guehdr = gue_gro_remcsum(skb, off, guehdr, + data + doffset, hdrlen, + guehdr->proto_ctype); + if (!guehdr) + goto out; + + data = &guehdr[1]; + + doffset += GUE_PLEN_REMCSUM; + } } + skb_gro_pull(skb, hdrlen); + flush = 0; for (p = *head; p; p = p->next) { @@ -199,7 +329,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, guehdr2 = (struct guehdr *)(p->data + off); /* Compare base GUE header to be equal (covers - * hlen, version, next_hdr, and flags. + * hlen, version, proto_ctype, and flags. */ if (guehdr->word != guehdr2->word) { NAPI_GRO_CB(p)->same_flow = 0; @@ -214,10 +344,11 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, } } - skb_gro_pull(skb, guehlen); - - /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ - skb_gro_postpull_rcsum(skb, guehdr, guehlen); + rcu_read_lock(); + offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; + ops = rcu_dereference(offloads[guehdr->proto_ctype]); + if (WARN_ON(!ops || !ops->callbacks.gro_receive)) + goto out_unlock; pp = ops->callbacks.gro_receive(head, skb); @@ -238,7 +369,7 @@ static int gue_gro_complete(struct sk_buff *skb, int nhoff) u8 proto; int err = -ENOENT; - proto = guehdr->next_hdr; + proto = guehdr->proto_ctype; guehlen = sizeof(*guehdr) + (guehdr->hlen << 2); @@ -489,6 +620,200 @@ static const struct genl_ops fou_nl_ops[] = { }, }; +size_t fou_encap_hlen(struct ip_tunnel_encap *e) +{ + return sizeof(struct udphdr); +} +EXPORT_SYMBOL(fou_encap_hlen); + +size_t gue_encap_hlen(struct ip_tunnel_encap *e) +{ + size_t len; + bool need_priv = false; + + len = sizeof(struct udphdr) + sizeof(struct guehdr); + + if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) { + len += GUE_PLEN_REMCSUM; + need_priv = true; + } + + len += need_priv ? GUE_LEN_PRIV : 0; + + return len; +} +EXPORT_SYMBOL(gue_encap_hlen); + +static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, + struct flowi4 *fl4, u8 *protocol, __be16 sport) +{ + struct udphdr *uh; + + skb_push(skb, sizeof(struct udphdr)); + skb_reset_transport_header(skb); + + uh = udp_hdr(skb); + + uh->dest = e->dport; + uh->source = sport; + uh->len = htons(skb->len); + uh->check = 0; + udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb, + fl4->saddr, fl4->daddr, skb->len); + + *protocol = IPPROTO_UDP; +} + +int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4) +{ + bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM); + int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; + __be16 sport; + + skb = iptunnel_handle_offloads(skb, csum, type); + + if (IS_ERR(skb)) + return PTR_ERR(skb); + + sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev), + skb, 0, 0, false); + fou_build_udp(skb, e, fl4, protocol, sport); + + return 0; +} +EXPORT_SYMBOL(fou_build_header); + +int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4) +{ + bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM); + int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; + struct guehdr *guehdr; + size_t hdrlen, optlen = 0; + __be16 sport; + void *data; + bool need_priv = false; + + if ((e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + csum = false; + optlen += GUE_PLEN_REMCSUM; + type |= SKB_GSO_TUNNEL_REMCSUM; + need_priv = true; + } + + optlen += need_priv ? GUE_LEN_PRIV : 0; + + skb = iptunnel_handle_offloads(skb, csum, type); + + if (IS_ERR(skb)) + return PTR_ERR(skb); + + /* Get source port (based on flow hash) before skb_push */ + sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev), + skb, 0, 0, false); + + hdrlen = sizeof(struct guehdr) + optlen; + + skb_push(skb, hdrlen); + + guehdr = (struct guehdr *)skb->data; + + guehdr->control = 0; + guehdr->version = 0; + guehdr->hlen = optlen >> 2; + guehdr->flags = 0; + guehdr->proto_ctype = *protocol; + + data = &guehdr[1]; + + if (need_priv) { + __be32 *flags = data; + + guehdr->flags |= GUE_FLAG_PRIV; + *flags = 0; + data += GUE_LEN_PRIV; + + if (type & SKB_GSO_TUNNEL_REMCSUM) { + u16 csum_start = skb_checksum_start_offset(skb); + __be16 *pd = data; + + if (csum_start < hdrlen) + return -EINVAL; + + csum_start -= hdrlen; + pd[0] = htons(csum_start); + pd[1] = htons(csum_start + skb->csum_offset); + + if (!skb_is_gso(skb)) { + skb->ip_summed = CHECKSUM_NONE; + skb->encapsulation = 0; + } + + *flags |= GUE_PFLAG_REMCSUM; + data += GUE_PLEN_REMCSUM; + } + + } + + fou_build_udp(skb, e, fl4, protocol, sport); + + return 0; +} +EXPORT_SYMBOL(gue_build_header); + +#ifdef CONFIG_NET_FOU_IP_TUNNELS + +static const struct ip_tunnel_encap_ops __read_mostly fou_iptun_ops = { + .encap_hlen = fou_encap_hlen, + .build_header = fou_build_header, +}; + +static const struct ip_tunnel_encap_ops __read_mostly gue_iptun_ops = { + .encap_hlen = gue_encap_hlen, + .build_header = gue_build_header, +}; + +static int ip_tunnel_encap_add_fou_ops(void) +{ + int ret; + + ret = ip_tunnel_encap_add_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); + if (ret < 0) { + pr_err("can't add fou ops\n"); + return ret; + } + + ret = ip_tunnel_encap_add_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE); + if (ret < 0) { + pr_err("can't add gue ops\n"); + ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); + return ret; + } + + return 0; +} + +static void ip_tunnel_encap_del_fou_ops(void) +{ + ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); + ip_tunnel_encap_del_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE); +} + +#else + +static int ip_tunnel_encap_add_fou_ops(void) +{ + return 0; +} + +static void ip_tunnel_encap_del_fou_ops(void) +{ +} + +#endif + static int __init fou_init(void) { int ret; @@ -496,6 +821,14 @@ static int __init fou_init(void) ret = genl_register_family_with_ops(&fou_nl_family, fou_nl_ops); + if (ret < 0) + goto exit; + + ret = ip_tunnel_encap_add_fou_ops(); + if (ret < 0) + genl_unregister_family(&fou_nl_family); + +exit: return ret; } @@ -503,6 +836,8 @@ static void __exit fou_fini(void) { struct fou *fou, *next; + ip_tunnel_encap_del_fou_ops(); + genl_unregister_family(&fou_nl_family); /* Close all the FOU sockets */ diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c index dedb21e99914..a457232f0131 100644 --- a/net/ipv4/geneve.c +++ b/net/ipv4/geneve.c @@ -104,7 +104,7 @@ static void geneve_build_header(struct genevehdr *geneveh, memcpy(geneveh->options, options, options_len); } -/* Transmit a fully formated Geneve frame. +/* Transmit a fully formatted Geneve frame. * * When calling this function. The skb->data should point * to the geneve header which is fully formed. @@ -131,15 +131,9 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, if (unlikely(err)) return err; - if (vlan_tx_tag_present(skb)) { - if (unlikely(!__vlan_put_tag(skb, - skb->vlan_proto, - vlan_tx_tag_get(skb)))) { - err = -ENOMEM; - return err; - } - skb->vlan_tci = 0; - } + skb = vlan_hwaccel_push_inside(skb); + if (unlikely(!skb)) + return -ENOMEM; gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index bb5947b0ce2d..51973ddc05a6 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -247,6 +247,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); rcu_read_unlock(); + + skb_set_inner_mac_header(skb, nhoff + grehlen); + return err; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5882f584910e..36f5584d93c5 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -190,7 +190,7 @@ EXPORT_SYMBOL(icmp_err_convert); */ struct icmp_control { - void (*handler)(struct sk_buff *skb); + bool (*handler)(struct sk_buff *skb); short error; /* This ICMP is classed as an error message */ }; @@ -746,7 +746,7 @@ static bool icmp_tag_validation(int proto) * ICMP_PARAMETERPROB. */ -static void icmp_unreach(struct sk_buff *skb) +static bool icmp_unreach(struct sk_buff *skb) { const struct iphdr *iph; struct icmphdr *icmph; @@ -784,8 +784,8 @@ static void icmp_unreach(struct sk_buff *skb) */ switch (net->ipv4.sysctl_ip_no_pmtu_disc) { default: - LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"), - &iph->daddr); + net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n", + &iph->daddr); break; case 2: goto out; @@ -798,8 +798,8 @@ static void icmp_unreach(struct sk_buff *skb) } break; case ICMP_SR_FAILED: - LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: Source Route Failed\n"), - &iph->daddr); + net_dbg_ratelimited("%pI4: Source Route Failed\n", + &iph->daddr); break; default: break; @@ -839,10 +839,10 @@ static void icmp_unreach(struct sk_buff *skb) icmp_socket_deliver(skb, info); out: - return; + return true; out_err: ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); - goto out; + return false; } @@ -850,17 +850,20 @@ out_err: * Handle ICMP_REDIRECT. */ -static void icmp_redirect(struct sk_buff *skb) +static bool icmp_redirect(struct sk_buff *skb) { if (skb->len < sizeof(struct iphdr)) { ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS); - return; + return false; } - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - return; + if (!pskb_may_pull(skb, sizeof(struct iphdr))) { + /* there aught to be a stat */ + return false; + } icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway); + return true; } /* @@ -875,7 +878,7 @@ static void icmp_redirect(struct sk_buff *skb) * See also WRT handling of options once they are done and working. */ -static void icmp_echo(struct sk_buff *skb) |