From d02f51cbcf12b09ab945873e35046045875eed9a Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Sat, 3 Mar 2018 03:03:46 +0100 Subject: bpf: fix bpf_skb_adjust_net/bpf_skb_proto_xlat to deal with gso sctp skbs SCTP GSO skbs have a gso_size of GSO_BY_FRAGS, so any sort of unconditionally mangling of that will result in nonsense value and would corrupt the skb later on. Therefore, i) add two helpers skb_increase_gso_size() and skb_decrease_gso_size() that would throw a one time warning and bail out for such skbs and ii) refuse and return early with an error in those BPF helpers that are affected. We do need to bail out as early as possible from there before any changes on the skb have been performed. Fixes: 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper") Co-authored-by: Daniel Borkmann Signed-off-by: Daniel Axtens Cc: Marcelo Ricardo Leitner Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- net/core/filter.c | 60 ++++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 42 insertions(+), 18 deletions(-) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index 0c121adbdbaa..48aa7c7320db 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2087,6 +2087,10 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -2096,19 +2100,21 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV4 needs to be changed into * SKB_GSO_TCPV6. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV4; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; + if (shinfo->gso_type & SKB_GSO_TCPV4) { + shinfo->gso_type &= ~SKB_GSO_TCPV4; + shinfo->gso_type |= SKB_GSO_TCPV6; } /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); @@ -2123,6 +2129,10 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -2132,19 +2142,21 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV6 needs to be changed into * SKB_GSO_TCPV4. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV6; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + if (shinfo->gso_type & SKB_GSO_TCPV6) { + shinfo->gso_type &= ~SKB_GSO_TCPV6; + shinfo->gso_type |= SKB_GSO_TCPV4; } /* Due to IPv4 header, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); @@ -2243,6 +2255,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -2252,11 +2268,13 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header grow, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; @@ -2267,6 +2285,10 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -2276,11 +2298,13 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header shrink, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; -- cgit v1.2.3 From b51f26b14683838825170387457176c1ffaea9f5 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 6 Mar 2018 17:27:44 -0500 Subject: net: don't unnecessarily load kernel modules in dev_ioctl() Starting with v4.16-rc1 we've been seeing a higher than usual number of requests for the kernel to load networking modules, even on events which shouldn't trigger a module load (e.g. ioctl(TCGETS)). Stephen Smalley suggested the problem may lie in commit 44c02a2c3dc5 ("dev_ioctl(): move copyin/copyout to callers") which moves changes the network dev_ioctl() function to always call dev_load(), regardless of the requested ioctl. This patch moves the dev_load() calls back into the individual ioctls while preserving the rest of the original patch. Reported-by: Dominick Grift Suggested-by: Stephen Smalley Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- net/core/dev_ioctl.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 0ab1af04296c..a04e1e88bf3a 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -402,8 +402,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c if (colon) *colon = 0; - dev_load(net, ifr->ifr_name); - /* * See which interface the caller is talking about. */ @@ -423,6 +421,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGIFMAP: case SIOCGIFINDEX: case SIOCGIFTXQLEN: + dev_load(net, ifr->ifr_name); rcu_read_lock(); ret = dev_ifsioc_locked(net, ifr, cmd); rcu_read_unlock(); @@ -431,6 +430,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c return ret; case SIOCETHTOOL: + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ethtool(net, ifr); rtnl_unlock(); @@ -447,6 +447,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSIFNAME: + dev_load(net, ifr->ifr_name); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); @@ -494,6 +495,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c /* fall through */ case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ifsioc(net, ifr, cmd); rtnl_unlock(); @@ -518,6 +520,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c cmd == SIOCGHWTSTAMP || (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ifsioc(net, ifr, cmd); rtnl_unlock(); -- cgit v1.2.3 From 1dd27cde30e85774c77349c804229431616d594a Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Fri, 9 Mar 2018 14:06:09 +1100 Subject: net: use skb_is_gso_sctp() instead of open-coding As well as the basic conversion, I noticed that a lot of the SCTP code checks gso_type without first checking skb_is_gso() so I have added that where appropriate. Also, document the helper. Cc: Daniel Borkmann Cc: Marcelo Ricardo Leitner Signed-off-by: Daniel Axtens Signed-off-by: David S. Miller --- Documentation/networking/segmentation-offloads.txt | 5 ++++- net/core/skbuff.c | 2 +- net/sched/act_csum.c | 2 +- net/sctp/input.c | 8 ++++---- net/sctp/inqueue.c | 2 +- net/sctp/offload.c | 2 +- 6 files changed, 12 insertions(+), 9 deletions(-) (limited to 'net/core') diff --git a/Documentation/networking/segmentation-offloads.txt b/Documentation/networking/segmentation-offloads.txt index fc0c949e7f9c..aca542ec125c 100644 --- a/Documentation/networking/segmentation-offloads.txt +++ b/Documentation/networking/segmentation-offloads.txt @@ -155,7 +155,10 @@ Therefore, any code in the core networking stack must be aware of the possibility that gso_size will be GSO_BY_FRAGS and handle that case appropriately. -There are a couple of helpers to make this easier: +There are some helpers to make this easier: + + - skb_is_gso(skb) && skb_is_gso_sctp(skb) is the best way to see if + an skb is an SCTP GSO skb. - For size checks, the skb_gso_validate_*_len family of helpers correctly considers GSO_BY_FRAGS. diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0bb0d8877954..baf990528943 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4904,7 +4904,7 @@ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); - } else if (unlikely(shinfo->gso_type & SKB_GSO_SCTP)) { + } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } /* UFO sets gso_size to the size of the fragmentation diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b7ba9b06b147..24b2e8e681cf 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -350,7 +350,7 @@ static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, { struct sctphdr *sctph; - if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); diff --git a/net/sctp/input.c b/net/sctp/input.c index 0247cc432e02..b381d78548ac 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -106,6 +106,7 @@ int sctp_rcv(struct sk_buff *skb) int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); + bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb); if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -123,8 +124,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && - skb_linearize(skb)) || + if ((!is_gso && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; @@ -135,7 +135,7 @@ int sctp_rcv(struct sk_buff *skb) if (skb_csum_unnecessary(skb)) __skb_decr_checksum_unnecessary(skb); else if (!sctp_checksum_disable && - !(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + !is_gso && sctp_rcv_checksum(net, skb) < 0) goto discard_it; skb->csum_valid = 1; @@ -1218,7 +1218,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, * issue as packets hitting this are mostly INIT or INIT-ACK and * those cannot be on GSO-style anyway. */ - if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return NULL; ch = (struct sctp_chunkhdr *)skb->data; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 48392552ee7c..23ebc5318edc 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -170,7 +170,7 @@ next_chunk: chunk = list_entry(entry, struct sctp_chunk, list); - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { + if (skb_is_gso(chunk->skb) && skb_is_gso_sctp(chunk->skb)) { /* GSO-marked skbs but without frags, handle * them normally */ diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 35bc7106d182..123e9f2dc226 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -45,7 +45,7 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); struct sctphdr *sh; - if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP)) + if (!skb_is_gso_sctp(skb)) goto out; sh = sctp_hdr(skb); -- cgit v1.2.3 From bf2ae2e4bf9360e07c0cdfa166bcdc0afd92f4ce Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 10 Mar 2018 18:57:50 +0800 Subject: sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca Acked-by: Marcelo Ricardo Leitner Acked-by: Phil Sutter Acked-by: Sabrina Dubroca Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/net.h | 1 + include/net/sock.h | 1 + net/core/sock.c | 21 +++++++++++++++++++++ net/core/sock_diag.c | 12 ++++-------- net/ipv4/inet_diag.c | 3 +-- net/socket.c | 5 +++++ 6 files changed, 33 insertions(+), 10 deletions(-) (limited to 'net/core') diff --git a/include/linux/net.h b/include/linux/net.h index 91216b16feb7..2a0391eea05c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -222,6 +222,7 @@ enum { int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); +bool sock_is_registered(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); diff --git a/include/net/sock.h b/include/net/sock.h index 169c92afcafa..ae23f3b389ca 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1137,6 +1137,7 @@ struct proto { int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); +int sock_load_diag_module(int family, int protocol); #ifdef SOCK_REFCNT_DEBUG static inline void sk_refcnt_debug_inc(struct sock *sk) diff --git a/net/core/sock.c b/net/core/sock.c index c501499a04fe..85b0b64e7f9d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3261,6 +3261,27 @@ void proto_unregister(struct proto *prot) } EXPORT_SYMBOL(proto_unregister); +int sock_load_diag_module(int family, int protocol) +{ + if (!protocol) { + if (!sock_is_registered(family)) + return -ENOENT; + + return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family); + } + +#ifdef CONFIG_INET + if (family == AF_INET && + !rcu_access_pointer(inet_protos[protocol])) + return -ENOENT; +#endif + + return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family, protocol); +} +EXPORT_SYMBOL(sock_load_diag_module); + #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 146b50e30659..c37b5be7c5e4 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -220,8 +220,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; if (sock_diag_handlers[req->sdiag_family] == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, req->sdiag_family); + sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; @@ -247,8 +246,7 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) @@ -281,14 +279,12 @@ static int sock_diag_bind(struct net *net, int group) case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET6); + sock_load_diag_module(AF_INET6, 0); break; } return 0; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a383f299ce24..4e5bc4b2f14e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -53,8 +53,7 @@ static DEFINE_MUTEX(inet_diag_table_mutex); static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { if (!inet_diag_table[proto]) - request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET, proto); + sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); if (!inet_diag_table[proto]) diff --git a/net/socket.c b/net/socket.c index a93c99b518ca..08847c3b8c39 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2587,6 +2587,11 @@ void sock_unregister(int family) } EXPORT_SYMBOL(sock_unregister); +bool sock_is_registered(int family) +{ + return family < NPROTO && rcu_access_pointer(net_families[family]); +} + static int __init sock_init(void) { int err; -- cgit v1.2.3 From 4dcb31d4649df36297296b819437709f5407059c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 14 Mar 2018 09:04:16 -0700 Subject: net: use skb_to_full_sk() in skb_update_prio() Andrei Vagin reported a KASAN: slab-out-of-bounds error in skb_update_prio() Since SYNACK might be attached to a request socket, we need to get back to the listener socket. Since this listener is manipulated without locks, add const qualifiers to sock_cgroup_prioidx() so that the const can also be used in skb_update_prio() Also add the const qualifier to sock_cgroup_classid() for consistency. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Reported-by: Andrei Vagin Signed-off-by: David S. Miller --- include/linux/cgroup-defs.h | 4 ++-- net/core/dev.c | 22 +++++++++++++++------- 2 files changed, 17 insertions(+), 9 deletions(-) (limited to 'net/core') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 9f242b876fde..f8e76d01a5ad 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -755,13 +755,13 @@ struct sock_cgroup_data { * updaters and return part of the previous pointer as the prioidx or * classid. Such races are short-lived and the result isn't critical. */ -static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd) +static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { /* fallback to 1 which is always the ID of the root cgroup */ return (skcd->is_data & 1) ? skcd->prioidx : 1; } -static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd) +static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { /* fallback to 0 which is the unconfigured default classid */ return (skcd->is_data & 1) ? skcd->classid : 0; diff --git a/net/core/dev.c b/net/core/dev.c index 2cedf520cb28..12be20535714 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3278,15 +3278,23 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { - struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); + const struct netprio_map *map; + const struct sock *sk; + unsigned int prioidx; - if (!skb->priority && skb->sk && map) { - unsigned int prioidx = - sock_cgroup_prioidx(&skb->sk->sk_cgrp_data); + if (skb->priority) + return; + map = rcu_dereference_bh(skb->dev->priomap); + if (!map) + return; + sk = skb_to_full_sk(skb); + if (!sk) + return; - if (prioidx < map->priomap_len) - skb->priority = map->priomap[prioidx]; - } + prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) -- cgit v1.2.3 From 4bbb3e0e8239f9079bf1fe20b3c0cb598714ae61 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 13 Mar 2018 14:51:27 +0900 Subject: net: Fix vlan untag for bridge and vlan_dev with reorder_hdr off When we have a bridge with vlan_filtering on and a vlan device on top of it, packets would be corrupted in skb_vlan_untag() called from br_dev_xmit(). The problem sits in skb_reorder_vlan_header() used in skb_vlan_untag(), which makes use of skb->mac_len. In this function mac_len is meant for handling rx path with vlan devices with reorder_header disabled, but in tx path mac_len is typically 0 and cannot be used, which is the problem in this case. The current code even does not properly handle rx path (skb_vlan_untag() called from __netif_receive_skb_core()) with reorder_header off actually. In rx path single tag case, it works as follows: - Before skb_reorder_vlan_header() mac_header data v v +-------------------+-------------+------+---- | ETH | VLAN | ETH | | ADDRS | TPID | TCI | TYPE | +-------------------+-------------+------+---- <-------- mac_len ---------> <-------------> to be removed - After skb_reorder_vlan_header() mac_header data v v +-------------------+------+---- | ETH | ETH | | ADDRS | TYPE | +-------------------+------+---- <-------- mac_len ---------> This is ok, but in rx double tag case, it corrupts packets: - Before skb_reorder_vlan_header() mac_header data v v +-------------------+-------------+-------------+------+---- | ETH | VLAN | VLAN | ETH | | ADDRS | TPID | TCI | TPID | TCI | TYPE | +-------------------+-------------+-------------+------+---- <--------------- mac_len ----------------> <-------------> should be removed <---------------------------> actually will be removed - After skb_reorder_vlan_header() mac_header data v v +-------------------+------+---- | ETH | ETH | | ADDRS | TYPE | +-------------------+------+---- <--------------- mac_len ----------------> So, two of vlan tags are both removed while only inner one should be removed and mac_header (and mac_len) is broken. skb_vlan_untag() is meant for removing the vlan header at (skb->data - 2), so use skb->data and skb->mac_header to calculate the right offset. Reported-by: Brandon Carpenter Fixes: a6e18ff11170 ("vlan: Fix untag operations of stacked vlans with REORDER_HEADER off") Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 1 + net/core/skbuff.c | 7 +++++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 8bbbcb5cd94b..820de5d222d2 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -30,6 +30,7 @@ */ #define ETH_ALEN 6 /* Octets in one ethernet addr */ +#define ETH_TLEN 2 /* Octets in ethernet type field */ #define ETH_HLEN 14 /* Total octets in header. */ #define ETH_ZLEN 60 /* Min. octets in frame sans FCS */ #define ETH_DATA_LEN 1500 /* Max. octets in payload */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index baf990528943..b103f46ec512 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5020,13 +5020,16 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { + int mac_len; + if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN, - 2 * ETH_ALEN); + mac_len = skb->data - skb_mac_header(skb); + memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), + mac_len - VLAN_HLEN - ETH_TLEN); skb->mac_header += VLAN_HLEN; return skb; } -- cgit v1.2.3 From 6e5d58fdc9bedd0255a8781b258f10bbdc63e975 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 14 Mar 2018 13:32:09 -0700 Subject: skbuff: Fix not waking applications when errors are enqueued When errors are enqueued to the error queue via sock_queue_err_skb() function, it is possible that the waiting application is not notified. Calling 'sk->sk_data_ready()' would not notify applications that selected only POLLERR events in poll() (for example). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Randy E. Witt Reviewed-by: Eric Dumazet Signed-off-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b103f46ec512..1e7acdc30732 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4179,7 +4179,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + sk->sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); -- cgit v1.2.3 From 7fe4d6dcbcb43fe0282d4213fc52be178bb30e91 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Sun, 18 Mar 2018 17:37:22 +0200 Subject: devlink: Remove redundant free on error path The current code performs unneeded free. Remove the redundant skb freeing during the error path. Fixes: 1555d204e743 ("devlink: Support for pipeline debug (dpipe)") Signed-off-by: Arkadi Sharshevsky Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/devlink.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'net/core') diff --git a/net/core/devlink.c b/net/core/devlink.c index 2f2307d94787..effd4848c2b4 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1798,7 +1798,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } @@ -1807,7 +1807,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: -err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; @@ -2073,7 +2072,7 @@ static int devlink_dpipe_entries_fill(struct genl_info *info, table->counters_enabled, &dump_ctx); if (err) - goto err_entries_dump; + return err; send_done: nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, @@ -2081,16 +2080,10 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(dump_ctx.skb, info); - -err_entries_dump: -err_skb_send_alloc: - genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr); - nlmsg_free(dump_ctx.skb); - return err; } static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, @@ -2229,7 +2222,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(skb, info); @@ -2237,7 +2230,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: -err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; -- cgit v1.2.3