From 133800d1f0288b9ddfc0d0aded10d9efa82d5b8c Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 8 Mar 2016 10:34:28 -0300 Subject: sctp: fix copying more bytes than expected in sctp_add_bind_addr Dmitry reported that sctp_add_bind_addr may read more bytes than expected in case the parameter is a IPv4 addr supplied by the user through calls such as sctp_bindx_add(), because it always copies sizeof(union sctp_addr) while the buffer may be just a struct sockaddr_in, which is smaller. This patch then fixes it by limiting the memcpy to the min between the union size and a (new parameter) provided addr size. Where possible this parameter still is the size of that union, except for reading from user-provided buffers, which then it accounts for protocol type. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/bind_addr.c | 14 ++++++++------ net/sctp/protocol.c | 1 + net/sctp/sm_make_chunk.c | 3 ++- net/sctp/socket.c | 4 +++- 4 files changed, 14 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 871cdf9567e6..401c60750b20 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -111,7 +111,8 @@ int sctp_bind_addr_dup(struct sctp_bind_addr *dest, dest->port = src->port; list_for_each_entry(addr, &src->address_list, list) { - error = sctp_add_bind_addr(dest, &addr->a, 1, gfp); + error = sctp_add_bind_addr(dest, &addr->a, sizeof(addr->a), + 1, gfp); if (error < 0) break; } @@ -150,7 +151,7 @@ void sctp_bind_addr_free(struct sctp_bind_addr *bp) /* Add an address to the bind address list in the SCTP_bind_addr structure. */ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, - __u8 addr_state, gfp_t gfp) + int new_size, __u8 addr_state, gfp_t gfp) { struct sctp_sockaddr_entry *addr; @@ -159,7 +160,7 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, if (!addr) return -ENOMEM; - memcpy(&addr->a, new, sizeof(*new)); + memcpy(&addr->a, new, min_t(size_t, sizeof(*new), new_size)); /* Fix up the port if it has not yet been set. * Both v4 and v6 have the port at the same offset. @@ -291,7 +292,8 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list, } af->from_addr_param(&addr, rawaddr, htons(port), 0); - retval = sctp_add_bind_addr(bp, &addr, SCTP_ADDR_SRC, gfp); + retval = sctp_add_bind_addr(bp, &addr, sizeof(addr), + SCTP_ADDR_SRC, gfp); if (retval) { /* Can't finish building the list, clean up. */ sctp_bind_addr_clean(bp); @@ -453,8 +455,8 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, (((AF_INET6 == addr->sa.sa_family) && (flags & SCTP_ADDR6_ALLOWED) && (flags & SCTP_ADDR6_PEERSUPP)))) - error = sctp_add_bind_addr(dest, addr, SCTP_ADDR_SRC, - gfp); + error = sctp_add_bind_addr(dest, addr, sizeof(*addr), + SCTP_ADDR_SRC, gfp); } return error; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1099e99a53c4..d3d50daa248b 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -216,6 +216,7 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, (copy_flags & SCTP_ADDR6_ALLOWED) && (copy_flags & SCTP_ADDR6_PEERSUPP)))) { error = sctp_add_bind_addr(bp, &addr->a, + sizeof(addr->a), SCTP_ADDR_SRC, GFP_ATOMIC); if (error) goto end_copy; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5d6a03fad378..7fe971e30ad6 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1830,7 +1830,8 @@ no_hmac: /* Also, add the destination address. */ if (list_empty(&retval->base.bind_addr.address_list)) { sctp_add_bind_addr(&retval->base.bind_addr, &chunk->dest, - SCTP_ADDR_SRC, GFP_ATOMIC); + sizeof(chunk->dest), SCTP_ADDR_SRC, + GFP_ATOMIC); } retval->next_tsn = retval->c.initial_tsn; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e878da0949db..0e3de0c71137 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -386,7 +386,8 @@ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) /* Add the address to the bind address list. * Use GFP_ATOMIC since BHs will be disabled. */ - ret = sctp_add_bind_addr(bp, addr, SCTP_ADDR_SRC, GFP_ATOMIC); + ret = sctp_add_bind_addr(bp, addr, af->sockaddr_len, + SCTP_ADDR_SRC, GFP_ATOMIC); /* Copy back into socket for getsockname() use. */ if (!ret) { @@ -577,6 +578,7 @@ static int sctp_send_asconf_add_ip(struct sock *sk, af = sctp_get_af_specific(addr->v4.sin_family); memcpy(&saveaddr, addr, af->sockaddr_len); retval = sctp_add_bind_addr(bp, &saveaddr, + sizeof(saveaddr), SCTP_ADDR_NEW, GFP_ATOMIC); addr_buf += af->sockaddr_len; } -- cgit v1.2.3 From abbdb5a74cead60e20b79c960c1772955f0b6b81 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 20 Mar 2016 11:27:47 -0700 Subject: net: remove a dubious unlikely() clause TCP protocol is still used these days, and TCP uses clones in its transmit path. We can not optimize linux stack assuming it is mostly used in routers, or that TCP is dead. Fixes: 795bb1c00d ("net: bulk free infrastructure for NAPI context, use napi_consume_skb") Signed-off-by: Eric Dumazet Cc: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f044f970f1a6..d04c2d1c8c87 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -815,7 +815,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget) trace_consume_skb(skb); /* if SKB is a clone, don't handle this case */ - if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) { + if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } -- cgit v1.2.3 From 07b4d6a1749422fa1e054f3c2aba444acdba39e8 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Fri, 18 Mar 2016 18:39:18 -0300 Subject: sctp: do not update a_rwnd if we are not issuing a sack The SACK can be lost pretty much elsewhere, but if its allocation fail, we know we are not sending it, so it is better to revert a_rwnd to its previous value as this may give it a chance to issue a window update later. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/sm_sideeffect.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 3c22c41a2bc2..7fe56d0acabf 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -215,10 +215,14 @@ static int sctp_gen_sack(struct sctp_association *asoc, int force, sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_SACK)); } else { + __u32 old_a_rwnd = asoc->a_rwnd; + asoc->a_rwnd = asoc->rwnd; sack = sctp_make_sack(asoc); - if (!sack) + if (!sack) { + asoc->a_rwnd = old_a_rwnd; goto nomem; + } asoc->peer.sack_needed = 0; asoc->peer.sack_cnt = 0; -- cgit v1.2.3 From 31b055ef0c6116a27e9a787304ecf87a77d34764 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Fri, 18 Mar 2016 18:39:19 -0300 Subject: sctp: do not leak chunks that are sent to unconfirmed paths Currently, if a chunk is scheduled to be sent through a transport that is currently unconfirmed, it will be leaked as it is dequeued from outq and is not re-queued nor freed. As I'm not aware of any situation that may lead to this situation, I'm fixing this by freeing the chunk and also logging a trace so that we can fix the other bug if it ever happens. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/outqueue.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index f03541d0f12d..8d3d3625130e 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -978,8 +978,12 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) (new_transport->state == SCTP_UNCONFIRMED) || (new_transport->state == SCTP_PF))) new_transport = asoc->peer.active_path; - if (new_transport->state == SCTP_UNCONFIRMED) + if (new_transport->state == SCTP_UNCONFIRMED) { + WARN_ONCE(1, "Atempt to send packet on unconfirmed path."); + sctp_chunk_fail(chunk, 0); + sctp_chunk_free(chunk); continue; + } /* Change packets if necessary. */ if (new_transport != transport) { -- cgit v1.2.3 From 3822a5ff4bc32043fa9c7b6d6f125bcdca6da39c Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Sat, 19 Mar 2016 12:17:20 -0300 Subject: sctp: align MTU to a word SCTP is a protocol that is aligned to a word (4 bytes). Thus using bare MTU can sometimes return values that are not aligned, like for loopback, which is 65536 but ipv4_mtu() limits that to 65535. This mis-alignment will cause the last non-aligned bytes to never be used and can cause issues with congestion control. So it's better to just consider a lower MTU and keep congestion control calcs saner as they are based on PMTU. Same applies to icmp frag needed messages, which is also fixed by this patch. One other effect of this is the inability to send MTU-sized packet without queueing or fragmentation and without hitting Nagle. As the check performed at sctp_packet_can_append_data(): if (chunk->skb->len + q->out_qlen >= transport->pathmtu - packet->overhead) /* Enough data queued to fill a packet */ return SCTP_XMIT_OK; with the above example of MTU, if there are no other messages queued, one cannot send a packet that just fits one packet (65532 bytes) and without causing DATA chunk fragmentation or a delay. v2: - Added WORD_TRUNC macro Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/associola.c | 3 ++- net/sctp/input.c | 3 ++- net/sctp/transport.c | 4 ++-- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/sctp/associola.c b/net/sctp/associola.c index a19b3e607703..e1849f3714ad 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1406,7 +1406,8 @@ void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc) list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->pmtu_pending && t->dst) { - sctp_transport_update_pmtu(sk, t, dst_mtu(t->dst)); + sctp_transport_update_pmtu(sk, t, + WORD_TRUNC(dst_mtu(t->dst))); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) diff --git a/net/sctp/input.c b/net/sctp/input.c index db76f1ab4ac2..00b8445364e3 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -606,7 +606,8 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) /* PMTU discovery (RFC1191) */ if (ICMP_FRAG_NEEDED == code) { - sctp_icmp_frag_needed(sk, asoc, transport, info); + sctp_icmp_frag_needed(sk, asoc, transport, + WORD_TRUNC(info)); goto out_unlock; } else { if (ICMP_PROT_UNREACH == code) { diff --git a/net/sctp/transport.c b/net/sctp/transport.c index d517153891a6..9b6b48c7524e 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -226,7 +226,7 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) } if (transport->dst) { - transport->pathmtu = dst_mtu(transport->dst); + transport->pathmtu = WORD_TRUNC(dst_mtu(transport->dst)); } else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } @@ -280,7 +280,7 @@ void sctp_transport_route(struct sctp_transport *transport, return; } if (transport->dst) { - transport->pathmtu = dst_mtu(transport->dst); + transport->pathmtu = WORD_TRUNC(dst_mtu(transport->dst)); /* Initialize sk->sk_rcv_saddr, if the transport is the * association's active path for getsockname(). -- cgit v1.2.3 From b8cba75bdf6a48ea4811bbefb11a94a5c7281b68 Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Sat, 19 Mar 2016 09:32:00 -0700 Subject: ipip: Properly mark ipip GRO packets as encapsulated. ipip encapsulated packets can be merged together by GRO but the result does not have the proper GSO type set or even marked as being encapsulated at all. Later retransmission of these packets will likely fail if the device does not support ipip offloads. This is similar to the issue resolved in IPv6 sit in feec0cb3 ("ipv6: gro: support sit protocol"). Reported-by: Patrick Boutilier Fixes: 9667e9bb ("ipip: Add gro callbacks to ipip offload") Tested-by: Patrick Boutilier Acked-by: Eric Dumazet Signed-off-by: Jesse Gross Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0cc923f83e10..965923325535 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1448,6 +1448,13 @@ out_unlock: return err; } +static int ipip_gro_complete(struct sk_buff *skb, int nhoff) +{ + skb->encapsulation = 1; + skb_shinfo(skb)->gso_type |= SKB_GSO_IPIP; + return inet_gro_complete(skb, nhoff); +} + int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net) @@ -1676,7 +1683,7 @@ static const struct net_offload ipip_offload = { .callbacks = { .gso_segment = inet_gso_segment, .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, + .gro_complete = ipip_gro_complete, }, }; -- cgit v1.2.3 From fac8e0f579695a3ecbc4d3cac369139d7f819971 Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Sat, 19 Mar 2016 09:32:01 -0700 Subject: tunnels: Don't apply GRO to multiple layers of encapsulation. When drivers express support for TSO of encapsulated packets, they only mean that they can do it for one layer of encapsulation. Supporting additional levels would mean updating, at a minimum, more IP length fields and they are unaware of this. No encapsulation device expresses support for handling offloaded encapsulated packets, so we won't generate these types of frames in the transmit path. However, GRO doesn't have a check for multiple levels of encapsulation and will attempt to build them. UDP tunnel GRO actually does prevent this situation but it only handles multiple UDP tunnels stacked on top of each other. This generalizes that solution to prevent any kind of tunnel stacking that would cause problems. Fixes: bf5a755f ("net-gre-gro: Add GRE support to the GRO stack") Signed-off-by: Jesse Gross Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- net/ipv4/af_inet.c | 15 ++++++++++++++- net/ipv4/gre_offload.c | 5 +++++ net/ipv4/udp_offload.c | 6 +++--- net/ipv6/ip6_offload.c | 15 ++++++++++++++- 5 files changed, 37 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index edb7179bc051..43c74cad25bc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4438,7 +4438,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->udp_mark = 0; + NAPI_GRO_CB(skb)->encap_mark = 0; NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 965923325535..0fefba64ee79 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1380,6 +1380,19 @@ out: return pp; } +static struct sk_buff **ipip_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->encap_mark) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + + NAPI_GRO_CB(skb)->encap_mark = 1; + + return inet_gro_receive(head, skb); +} + #define SECONDS_PER_DAY 86400 /* inet_current_timestamp - Return IP network timestamp @@ -1682,7 +1695,7 @@ static struct packet_offload ip_packet_offload __read_mostly = { static const struct net_offload ipip_offload = { .callbacks = { .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, + .gro_receive = ipip_gro_receive, .gro_complete = ipip_gro_complete, }, }; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 540866dbd27d..dd031617160a 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -126,6 +126,11 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, struct packet_offload *ptype; __be16 type; + if (NAPI_GRO_CB(skb)->encap_mark) + goto out; + + NAPI_GRO_CB(skb)->encap_mark = 1; + off = skb_gro_offset(skb); hlen = off + sizeof(*greh); greh = skb_gro_header_fast(skb, off); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 8a3405a80260..8007f73b8981 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -311,14 +311,14 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - if (NAPI_GRO_CB(skb)->udp_mark || + if (NAPI_GRO_CB(skb)->encap_mark || (skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; - /* mark that this skb passed once through the udp gro layer */ - NAPI_GRO_CB(skb)->udp_mark = 1; + /* mark that this skb passed once through the tunnel gro layer */ + NAPI_GRO_CB(skb)->encap_mark = 1; rcu_read_lock(); uo_priv = rcu_dereference(udp_offload_base); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index eeca943f12dc..82e9f3076028 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -258,6 +258,19 @@ out: return pp; } +static struct sk_buff **sit_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->encap_mark) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + + NAPI_GRO_CB(skb)->encap_mark = 1; + + return ipv6_gro_receive(head, skb); +} + static int ipv6_gro_complete(struct sk_buff *skb, int nhoff) { const struct net_offload *ops; @@ -302,7 +315,7 @@ static struct packet_offload ipv6_packet_offload __read_mostly = { static const struct net_offload sit_offload = { .callbacks = { .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, + .gro_receive = sit_gro_receive, .gro_complete = sit_gro_complete, }, }; -- cgit v1.2.3 From a09a4c8dd1ec7f830e1fb9e59eb72bddc965d168 Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Sat, 19 Mar 2016 09:32:02 -0700 Subject: tunnels: Remove encapsulation offloads on decap. If a packet is either locally encapsulated or processed through GRO it is marked with the offloads that it requires. However, when it is decapsulated these tunnel offload indications are not removed. This means that if we receive an encapsulated TCP packet, aggregate it with GRO, decapsulate, and retransmit the resulting frame on a NIC that does not support encapsulation, we won't be able to take advantage of hardware offloads even though it is just a simple TCP packet at this point. This fixes the problem by stripping off encapsulation offload indications when packets are decapsulated. The performance impacts of this bug are significant. In a test where a Geneve encapsulated TCP stream is sent to a hypervisor, GRO'ed, decapsulated, and bridged to a VM performance is improved by 60% (5Gbps->8Gbps) as a result of avoiding unnecessary segmentation at the VM tap interface. Reported-by: Ramu Ramamurthy Fixes: 68c33163 ("v4 GRE: Add TCP segmentation offload for GRE") Signed-off-by: Jesse Gross Signed-off-by: David S. Miller --- net/ipv4/fou.c | 13 +++++++++++-- net/ipv4/ip_tunnel_core.c | 3 ++- net/ipv6/sit.c | 6 ++++-- 3 files changed, 17 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 780484243e14..a0586b4a197d 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -48,7 +48,7 @@ static inline struct fou *fou_from_sock(struct sock *sk) return sk->sk_user_data; } -static void fou_recv_pull(struct sk_buff *skb, size_t len) +static int fou_recv_pull(struct sk_buff *skb, size_t len) { struct iphdr *iph = ip_hdr(skb); @@ -59,6 +59,7 @@ static void fou_recv_pull(struct sk_buff *skb, size_t len) __skb_pull(skb, len); skb_postpull_rcsum(skb, udp_hdr(skb), len); skb_reset_transport_header(skb); + return iptunnel_pull_offloads(skb); } static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) @@ -68,9 +69,14 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) if (!fou) return 1; - fou_recv_pull(skb, sizeof(struct udphdr)); + if (fou_recv_pull(skb, sizeof(struct udphdr))) + goto drop; return -fou->protocol; + +drop: + kfree_skb(skb); + return 0; } static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, @@ -170,6 +176,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); + if (iptunnel_pull_offloads(skb)) + goto drop; + return -guehdr->proto_ctype; drop: diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index d27276f6f8dd..02dd990af542 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -114,7 +114,8 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); skb_scrub_packet(skb, xnet); - return 0; + + return iptunnel_pull_offloads(skb); } EXPORT_SYMBOL_GPL(iptunnel_pull_header); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index f45b8ffc2840..83384308d032 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -681,14 +681,16 @@ static int ipip6_rcv(struct sk_buff *skb) skb->mac_header = skb->network_header; skb_reset_network_header(skb); IPCB(skb)->flags = 0; - skb->protocol = htons(ETH_P_IPV6); + skb->dev = tunnel->dev; if (packet_is_spoofed(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; goto out; } - __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); + if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6), + !net_eq(tunnel->net, dev_net(tunnel->dev)))) + goto out; err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { -- cgit v1.2.3 From b002fdcc89979ff342d4139d165a4e1d51e586ff Mon Sep 17 00:00:00 2001 From: Luis de Bethencourt Date: Sat, 19 Mar 2016 21:19:55 +0000 Subject: gen_stats.c: Add description for cpu argument Function gnet_stats_copy_basic is missing the description of the cpu argument in the documentation. Adding it. Signed-off-by: Luis de Bethencourt Signed-off-by: David S. Miller --- net/core/gen_stats.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 1e2f46a69d50..e640462ea8bf 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -140,6 +140,7 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic); /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV * @d: dumping handle + * @cpu: copy statistic per cpu * @b: basic statistics * * Appends the basic statistics to the top level TLV created by -- cgit v1.2.3 From e9fc2f052c96142e50c6ddd0a5e7432af68bd13b Mon Sep 17 00:00:00 2001 From: Luis de Bethencourt Date: Sat, 19 Mar 2016 21:31:38 +0000 Subject: net: sched: Add description for cpu_bstats argument Commit 22e0f8b9322c ("net: sched: make bstats per cpu and estimator RCU safe") added the argument cpu_bstats to functions gen_new_estimator and gen_replace_estimator and now the descriptions of these are missing for the documentation. Adding them. Signed-off-by: Luis de Bethencourt Signed-off-by: David S. Miller --- net/core/gen_estimator.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 92d886f4adcb..4573d81093fe 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -191,6 +191,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats /** * gen_new_estimator - create a new rate estimator * @bstats: basic statistics + * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @stats_lock: statistics lock * @opt: rate estimator configuration TLV @@ -287,6 +288,7 @@ EXPORT_SYMBOL(gen_kill_estimator); /** * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics + * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @stats_lock: statistics lock * @opt: rate estimator configuration TLV -- cgit v1.2.3 From ed49e650371008b0e00c8004cc2ca93055740f78 Mon Sep 17 00:00:00 2001 From: Luis de Bethencourt Date: Mon, 21 Mar 2016 16:31:14 +0000 Subject: net: add description for len argument of dev_get_phys_port_name When the function dev_get_phys_port_name was added it missed a description for it's len argument. Adding it. Fixes: db24a9044ee1 ("net: add support for phys_port_name") Signed-off-by: Luis de Bethencourt Signed-off-by: David S. Miller --- net/core/dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 43c74cad25bc..b9bcbe77d913 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6445,6 +6445,7 @@ EXPORT_SYMBOL(dev_get_phys_port_id); * dev_get_phys_port_name - Get device physical port name * @dev: device * @name: port name + * @len: limit of bytes to copy to name * * Get device physical port name */ -- cgit v1.2.3 From c70ce028e834f8e51306217dbdbd441d851c64d3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 21 Mar 2016 09:55:10 -0700 Subject: net/rtnetlink: add IFLA_GSO_MAX_SEGS and IFLA_GSO_MAX_SIZE attributes It can be useful to report dev->gso_max_segs and dev->gso_max_size so that "ip -d link" can display them to help debugging. For the moment, these attributes are read-only. Signed-off-by: Eric Dumazet Cc: Petri Gynther Cc: Stephen Hemminger Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d2d9e5ebf58e..a69cd0c097b5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -895,6 +895,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ + + nla_total_size(4) /* IFLA_MAX_GSO_SEGS */ + + nla_total_size(4) /* IFLA_MAX_GSO_SIZE */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ @@ -1223,6 +1225,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u32(skb, IFLA_GROUP, dev->group) || nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || + nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) || + nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) || #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif -- cgit v1.2.3 From ae74f10068387bb0e64d8f1c8beac5e35c1458b1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 21 Mar 2016 09:55:11 -0700 Subject: bridge: update max_gso_segs and max_gso_size It can be useful to lower max_gso_segs on NIC with very low number of TX descriptors like bcmgenet. However, this is defeated by bridge since it does not propagate the lower value of max_gso_segs and max_gso_size. Signed-off-by: Eric Dumazet Cc: Petri Gynther Cc: Stephen Hemminger Signed-off-by: David S. Miller --- net/bridge/br_if.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'net') diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index a73df3315df9..8217aecf025b 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -437,6 +437,20 @@ int br_min_mtu(const struct net_bridge *br) return mtu; } +static void br_set_gso_limits(struct net_bridge *br) +{ + unsigned int gso_max_size = GSO_MAX_SIZE; + u16 gso_max_segs = GSO_MAX_SEGS; + const struct net_bridge_port *p; + + list_for_each_entry(p, &br->port_list, list) { + gso_max_size = min(gso_max_size, p->dev->gso_max_size); + gso_max_segs = min(gso_max_segs, p->dev->gso_max_segs); + } + br->dev->gso_max_size = gso_max_size; + br->dev->gso_max_segs = gso_max_segs; +} + /* * Recomputes features using slave's features */ @@ -564,6 +578,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); dev_set_mtu(br->dev, br_min_mtu(br)); + br_set_gso_limits(br); kobject_uevent(&p->kobj, KOBJ_ADD); @@ -610,6 +625,7 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) del_nbp(p); dev_set_mtu(br->dev, br_min_mtu(br)); + br_set_gso_limits(br); spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); -- cgit v1.2.3 From 9b246841f4041f85265dec5f769c017fc36a0d33 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Mon, 21 Mar 2016 18:37:22 -0400 Subject: Make DST_CACHE a silent config option commit 911362c70d ("net: add dst_cache support") added a new kconfig option that gets selected by other networking options. It seems the intent wasn't to offer this as a user-selectable option given the lack of help text, so this patch converts it to a silent option. Signed-off-by: Dave Jones Signed-off-by: David S. Miller --- net/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/Kconfig b/net/Kconfig index e13449870d06..a8934d8c8fda 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -397,7 +397,7 @@ config LWTUNNEL with light weight tunnel state associated with fib routes. config DST_CACHE - bool "dst cache" + bool default n config NET_DEVLINK -- cgit v1.2.3 From 3ba9d300c925d89914d15beff2180064ac7ee6f6 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Mon, 21 Mar 2016 18:21:26 -0700 Subject: net: ipv4: Fix truncated timestamp returned by inet_current_timestamp() The millisecond timestamps returned by the function is converted to network byte order by making a call to htons(). htons() only returns __be16 while __be32 is required here. This was identified by the sparse warning from the buildbot: net/ipv4/af_inet.c:1405:16: sparse: incorrect type in return expression (different base types) net/ipv4/af_inet.c:1405:16: expected restricted __be32 net/ipv4/af_inet.c:1405:16: got restricted __be16 [usertype] Change the function to use htonl() to return the correct __be32 type instead so that the millisecond value doesn't get truncated. Signed-off-by: Deepa Dinamani Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: Hideaki YOSHIFUJI Cc: James Morris Cc: Patrick McHardy Cc: Arnd Bergmann Fixes: 822c868532ca ("net: ipv4: Convert IP network timestamps to be y2038 safe") Reported-by: Fengguang Wu [0-day test robot] Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0fefba64ee79..9e481992dbae 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1415,7 +1415,7 @@ __be32 inet_current_timestamp(void) msecs += (u32)ts.tv_nsec / NSEC_PER_MSEC; /* Convert to network byte order. */ - return htons(msecs); + return htonl(msecs); } EXPORT_SYMBOL(inet_current_timestamp); -- cgit v1.2.3 From 025c68186e07afaededa84143f1a22f273cd3f67 Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Mon, 21 Mar 2016 10:15:35 -0700 Subject: netlink: add support for NIC driver ioctls By returning -ENOIOCTLCMD, sock_do_ioctl() falls back to calling dev_ioctl(), which provides support for NIC driver ioctls, which includes ethtool support. This is similar to the way ioctls are handled in udp.c or tcp.c. This removes the requirement that ethtool for example be tied to the support of a specific L3 protocol (ethtool uses an AF_INET socket today). Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c8416792cce0..215fc08c02ab 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1033,6 +1033,14 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, return 0; } +static int netlink_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + /* try to hand this ioctl down to the NIC drivers. + */ + return -ENOIOCTLCMD; +} + static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) { struct sock *sock; @@ -2494,7 +2502,7 @@ static const struct proto_ops netlink_ops = { .accept = sock_no_accept, .getname = netlink_getname, .poll = datagram_poll, - .ioctl = sock_no_ioctl, + .ioctl = netlink_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = netlink_setsockopt, -- cgit v1.2.3 From ad0ea1989cc4d5905941d0a9e62c63ad6d859cef Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 22 Mar 2016 09:19:38 +0100 Subject: ipv4: fix broadcast packets reception Currently, ingress ipv4 broadcast datagrams are dropped since, in udp_v4_early_demux(), ip_check_mc_rcu() is invoked even on bcast packets. This patch addresses the issue, invoking ip_check_mc_rcu() only for mcast packets. Fixes: 6e5403093261 ("ipv4/udp: Verify multicast group is ours in upd_v4_early_demux()") Signed-off-by: Paolo Abeni Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/udp.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 836abe58a9c5..08eed5e16df0 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2070,10 +2070,14 @@ void udp_v4_early_demux(struct sk_buff *skb) if (!in_dev) return; - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return; + /* we are supposed to accept bcast packets */ + if (skb->pkt_type == PACKET_MULTICAST) { + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return; + } + sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); } else if (skb->pkt_type == PACKET_HOST) { -- cgit v1.2.3 From 4cfc86f3dae6ca38ed49cdd78f458a03d4d87992 Mon Sep 17 00:00:00 2001 From: Lance Richardson Date: Tue, 22 Mar 2016 14:56:57 -0400 Subject: ipv4: initialize flowi4_flags before calling fib_lookup() Field fl4.flowi4_flags is not initialized in fib_compute_spec_dst() before calling fib_lookup(), which means fib_table_lookup() is using non-deterministic data at this line: if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { Fix by initializing the entire fl4 structure, which will prevent similar issues as fields are added in the future by ensuring that all fields are initialized to zero unless explicitly initialized to another value. Fixes: 58189ca7b2741 ("net: Fix vti use case with oif in dst lookups") Suggested-by: David Ahern Signed-off-by: Lance Richardson Acked-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 21add552e56a..8a9246deccfe 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -280,7 +280,6 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) struct in_device *in_dev; struct fib_result res; struct rtable *rt; - struct flowi4 fl4; struct net *net; int scope; @@ -296,14 +295,13 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { - fl4.flowi4_oif = 0; - fl4.flowi4_iif = LOOPBACK_IFINDEX; - fl4.daddr = ip_hdr(skb)->saddr; - fl4.saddr = 0; - fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); - fl4.flowi4_scope = scope; - fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; - fl4.flowi4_tun_key.tun_id = 0; + struct flowi4 fl4 = { + .flowi4_iif = LOOPBACK_IFINDEX, + .daddr = ip_hdr(skb)->saddr, + .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), + .flowi4_scope = scope, + .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0, + }; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); } else { -- cgit v1.2.3 From 6f57e56a1527d58264ae126eff94fdac067744fc Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 22 Mar 2016 17:05:51 +0100 Subject: Revert "vsock: Fix blocking ops call in prepare_to_wait" This reverts commit 5988818008257ca42010d6b43a3e0e48afec9898 ("vsock: Fix blocking ops call in prepare_to_wait") The commit reverted with this patch caused us to potentially miss wakeups. Since the condition is not checked between the prepare_to_wait and the schedule(), if a wakeup happens after the condition is checked but before the sleep happens, we will miss it. ( A description of the problem can be found here: http://www.makelinux.net/ldd3/chp-6-sect-2 ). By reverting the patch, the behaviour is still incorrect (since we shouldn't sleep between the prepare_to_wait and the schedule) but at least it will not miss wakeups. The next patch in the series actually fixes the behaviour. Signed-off-by: Claudio Imbrenda Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index bbe65dcb9738..7fd1220fbfa0 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1557,6 +1557,8 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) goto out; + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + while (total_written < len) { ssize_t written; @@ -1576,9 +1578,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_wait; release_sock(sk); - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); timeout = schedule_timeout(timeout); - finish_wait(sk_sleep(sk), &wait); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); @@ -1588,6 +1588,8 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_wait; } + prepare_to_wait(sk_sleep(sk), &wait, + TASK_INTERRUPTIBLE); } /* These checks occur both as part of and after the loop @@ -1633,6 +1635,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, out_wait: if (total_written > 0) err = total_written; + finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; @@ -1713,6 +1716,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (err < 0) goto out; + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (1) { s64 ready = vsock_stream_has_data(vsk); @@ -1723,7 +1727,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, */ err = -ENOMEM; - goto out; + goto out_wait; } else if (ready > 0) { ssize_t read; @@ -1746,7 +1750,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, vsk, target, read, !(flags & MSG_PEEK), &recv_data); if (err < 0) - goto out; + goto out_wait; if (read >= target || flags & MSG_PEEK) break; @@ -1769,9 +1773,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, break; release_sock(sk); - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); timeout = schedule_timeout(timeout); - finish_wait(sk_sleep(sk), &wait); lock_sock(sk); if (signal_pending(current)) { @@ -1781,6 +1783,9 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = -EAGAIN; break; } + + prepare_to_wait(sk_sleep(sk), &wait, + TASK_INTERRUPTIBLE); } } @@ -1811,6 +1816,8 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = copied; } +out_wait: + finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; -- cgit v1.2.3 From f7f9b5e7f8eccfd68ffa7b8d74b07c478bb9e7f0 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Tue, 22 Mar 2016 17:05:52 +0100 Subject: AF_VSOCK: Shrink the area influenced by prepare_to_wait When a thread is prepared for waiting by calling prepare_to_wait, sleeping is not allowed until either the wait has taken place or finish_wait has been called. The existing code in af_vsock imposed unnecessary no-sleep assumptions to a broad list of backend functions. This patch shrinks the influence of prepare_to_wait to the area where it is strictly needed, therefore relaxing the no-sleep restriction there. Signed-off-by: Claudio Imbrenda Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 158 +++++++++++++++++++++++++---------------------- 1 file changed, 85 insertions(+), 73 deletions(-) (limited to 'net') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 7fd1220fbfa0..3dce53ebea92 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1209,10 +1209,14 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (signal_pending(current)) { err = sock_intr_errno(timeout); - goto out_wait_error; + sk->sk_state = SS_UNCONNECTED; + sock->state = SS_UNCONNECTED; + goto out_wait; } else if (timeout == 0) { err = -ETIMEDOUT; - goto out_wait_error; + sk->sk_state = SS_UNCONNECTED; + sock->state = SS_UNCONNECTED; + goto out_wait; } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); @@ -1220,20 +1224,17 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (sk->sk_err) { err = -sk->sk_err; - goto out_wait_error; - } else + sk->sk_state = SS_UNCONNECTED; + sock->state = SS_UNCONNECTED; + } else { err = 0; + } out_wait: finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; - -out_wait_error: - sk->sk_state = SS_UNCONNECTED; - sock->state = SS_UNCONNECTED; - goto out_wait; } static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) @@ -1270,18 +1271,20 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) listener->sk_err == 0) { release_sock(listener); timeout = schedule_timeout(timeout); + finish_wait(sk_sleep(listener), &wait); lock_sock(listener); if (signal_pending(current)) { err = sock_intr_errno(timeout); - goto out_wait; + goto out; } else if (timeout == 0) { err = -EAGAIN; - goto out_wait; + goto out; } prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); } + finish_wait(sk_sleep(listener), &wait); if (listener->sk_err) err = -listener->sk_err; @@ -1301,19 +1304,15 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) */ if (err) { vconnected->rejected = true; - release_sock(connected); - sock_put(connected); - goto out_wait; + } else { + newsock->state = SS_CONNECTED; + sock_graft(connected, newsock); } - newsock->state = SS_CONNECTED; - sock_graft(connected, newsock); release_sock(connected); sock_put(connected); } -out_wait: - finish_wait(sk_sleep(listener), &wait); out: release_sock(listener); return err; @@ -1557,11 +1556,11 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) goto out; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (total_written < len) { ssize_t written; + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (vsock_stream_has_space(vsk) == 0 && sk->sk_err == 0 && !(sk->sk_shutdown & SEND_SHUTDOWN) && @@ -1570,27 +1569,33 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, /* Don't wait for non-blocking sockets. */ if (timeout == 0) { err = -EAGAIN; - goto out_wait; + finish_wait(sk_sleep(sk), &wait); + goto out_err; } err = transport->notify_send_pre_block(vsk, &send_data); - if (err < 0) - goto out_wait; + if (err < 0) { + finish_wait(sk_sleep(sk), &wait); + goto out_err; + } release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); - goto out_wait; + finish_wait(sk_sleep(sk), &wait); + goto out_err; } else if (timeout == 0) { err = -EAGAIN; - goto out_wait; + finish_wait(sk_sleep(sk), &wait); + goto out_err; } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } + finish_wait(sk_sleep(sk), &wait); /* These checks occur both as part of and after the loop * conditional since we need to check before and after @@ -1598,16 +1603,16 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, */ if (sk->sk_err) { err = -sk->sk_err; - goto out_wait; + goto out_err; } else if ((sk->sk_shutdown & SEND_SHUTDOWN) || (vsk->peer_shutdown & RCV_SHUTDOWN)) { err = -EPIPE; - goto out_wait; + goto out_err; } err = transport->notify_send_pre_enqueue(vsk, &send_data); if (err < 0) - goto out_wait; + goto out_err; /* Note that enqueue will only write as many bytes as are free * in the produce queue, so we don't need to ensure len is @@ -1620,7 +1625,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, len - total_written); if (written < 0) { err = -ENOMEM; - goto out_wait; + goto out_err; } total_written += written; @@ -1628,14 +1633,13 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, err = transport->notify_send_post_enqueue( vsk, written, &send_data); if (err < 0) - goto out_wait; + goto out_err; } -out_wait: +out_err: if (total_written > 0) err = total_written; - finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; @@ -1716,21 +1720,61 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (err < 0) goto out; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (1) { - s64 ready = vsock_stream_has_data(vsk); + s64 ready; - if (ready < 0) { - /* Invalid queue pair content. XXX This should be - * changed to a connection reset in a later change. - */ + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + ready = vsock_stream_has_data(vsk); - err = -ENOMEM; - goto out_wait; - } else if (ready > 0) { + if (ready == 0) { + if (sk->sk_err != 0 || + (sk->sk_shutdown & RCV_SHUTDOWN) || + (vsk->peer_shutdown & SEND_SHUTDOWN)) { + finish_wait(sk_sleep(sk), &wait); + break; + } + /* Don't wait for non-blocking sockets. */ + if (timeout == 0) { + err = -EAGAIN; + finish_wait(sk_sleep(sk), &wait); + break; + } + + err = transport->notify_recv_pre_block( + vsk, target, &recv_data); + if (err < 0) { + finish_wait(sk_sleep(sk), &wait); + break; + } + release_sock(sk); + timeout = schedule_timeout(timeout); + lock_sock(sk); + + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + finish_wait(sk_sleep(sk), &wait); + break; + } else if (timeout == 0) { + err = -EAGAIN; + finish_wait(sk_sleep(sk), &wait); + break; + } + } else { ssize_t read; + finish_wait(sk_sleep(sk), &wait); + + if (ready < 0) { + /* Invalid queue pair content. XXX This should + * be changed to a connection reset in a later + * change. + */ + + err = -ENOMEM; + goto out; + } + err = transport->notify_recv_pre_dequeue( vsk, target, &recv_data); if (err < 0) @@ -1750,42 +1794,12 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, vsk, target, read, !(flags & MSG_PEEK), &recv_data); if (err < 0) - goto out_wait; + goto out; if (read >= target || flags & MSG_PEEK) break; target -= read; - } else { - if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN) - || (vsk->peer_shutdown & SEND_SHUTDOWN)) { - break; - } - /* Don't wait for non-blocking sockets. */ - if (timeout == 0) { - err = -EAGAIN; - break; - } - - err = transport->notify_recv_pre_block( - vsk, target, &recv_data); - if (err < 0) - break; - - release_sock(sk); - timeout = schedule_timeout(timeout); - lock_sock(sk); - - if (signal_pending(current)) { - err = sock_intr_errno(timeout); - break; - } else if (timeout == 0) { - err = -EAGAIN; - break; - } - - prepare_to_wait(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); } } @@ -1816,8 +1830,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = copied; } -out_wait: - finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; -- cgit v1.2.3 From 5197f3499c470ccc4b247db66ff883e597e3adda Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 22 Mar 2016 16:18:07 -0700 Subject: net: Reset encap_level to avoid resetting features on inner IP headers This patch corrects an oversight in which we were allowing the encap_level value to pass from the outer headers to the inner headers. As a result we were incorrectly identifying UDP or GRE tunnels as also making use of ipip or sit when the second header actually represented a tunnel encapsulated in either a UDP or GRE tunnel which already had the features masked. Fixes: 76443456227097179c1482 ("net: Move GSO csum into SKB_GSO_CB") Reported-by: Tom Herbert Signed-off-by: Alexander Duyck Acked-by: Tom Herbert Signed-off-by: David S. Miller --- net/ipv4/gre_offload.c | 1 + net/ipv4/udp_offload.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net') diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index dd031617160a..c47539d04b88 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -49,6 +49,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, /* setup inner skb. */ skb->encapsulation = 0; + SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 8007f73b8981..0ed2dafb7cc4 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -56,6 +56,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, /* setup inner skb. */ skb->encapsulation = 0; + SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); -- cgit v1.2.3 From 6579a023a881e0592ce9a98fdfcbcc0a2a096aa7 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Wed, 23 Mar 2016 17:59:51 +0800 Subject: net: ping: make ping_v6_sendmsg static As ping_v6_sendmsg is used only in this file, making it static The body of "pingv6_prot" and "pingv6_protosw" were moved at the middle of the file, to avoid having to declare some static prototypes. Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- net/ipv6/ping.c | 59 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 29 insertions(+), 30 deletions(-) (limited to 'net') diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 263a5164a6f5..c382db7a2e73 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -26,35 +26,6 @@ #include #include -struct proto pingv6_prot = { - .name = "PINGv6", - .owner = THIS_MODULE, - .init = ping_init_sock, - .close = ping_close, - .connect = ip6_datagram_connect_v6_only, - .disconnect = udp_disconnect, - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .sendmsg = ping_v6_sendmsg, - .recvmsg = ping_recvmsg, - .bind = ping_bind, - .backlog_rcv = ping_queue_rcv_skb, - .hash = ping_hash, - .unhash = ping_unhash, - .get_port = ping_get_port, - .obj_size = sizeof(struct raw6_sock), -}; -EXPORT_SYMBOL_GPL(pingv6_prot); - -static struct inet_protosw pingv6_protosw = { - .type = SOCK_DGRAM, - .protocol = IPPROTO_ICMPV6, - .prot = &pingv6_prot, - .ops = &inet6_dgram_ops, - .flags = INET_PROTOSW_REUSE, -}; - - /* Compatibility glue so we can support IPv6 when it's compiled as a module */ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) @@ -77,7 +48,7 @@ static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, return 0; } -int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) +static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -192,6 +163,34 @@ int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return len; } +struct proto pingv6_prot = { + .name = "PINGv6", + .owner = THIS_MODULE, + .init = ping_init_sock, + .close = ping_close, + .connect = ip6_datagram_connect_v6_only, + .disconnect = udp_disconnect, + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .sendmsg = ping_v6_sendmsg, + .recvmsg = ping_recvmsg, + .bind = ping_bind, + .backlog_rcv = ping_queue_rcv_skb, + .hash = ping_hash, + .unhash = ping_unhash, + .get_port = ping_get_port, + .obj_size = sizeof(struct raw6_sock), +}; +EXPORT_SYMBOL_GPL(pingv6_prot); + +static struct inet_protosw pingv6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_ICMPV6, + .prot = &pingv6_prot, + .ops = &inet6_dgram_ops, + .flags = INET_PROTOSW_REUSE, +}; + #ifdef CONFIG_PROC_FS static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos) { -- cgit v1.2.3