From 220815a9665f7deca98a09ecca655044f94cfa44 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Nov 2013 18:17:04 +0100 Subject: genetlink: fix genlmsg_multicast() bug Unfortunately, I introduced a tremendously stupid bug into genlmsg_multicast() when doing all those multicast group changes: it adjusts the group number, but then passes it to genlmsg_multicast_netns() which does that again. Somehow, my tests failed to catch this, so add a warning into genlmsg_multicast_netns() and remove the offending group ID adjustment. Also add a warning to the similar code in other functions so people who misuse them are more loudly warned. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/genetlink.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index ace4abf118d7..771af09e90eb 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -265,7 +265,7 @@ static inline int genlmsg_multicast_netns(struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { - if (group >= family->n_mcgrps) + if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return nlmsg_multicast(net->genl_sock, skb, portid, group, flags); @@ -283,9 +283,6 @@ static inline int genlmsg_multicast(struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { - if (group >= family->n_mcgrps) - return -EINVAL; - group = family->mcgrp_offset + group; return genlmsg_multicast_netns(family, &init_net, skb, portid, group, flags); } -- cgit v1.2.3 From 91398a0992c8aa18eb7749060b75761ece5ddc57 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Nov 2013 18:20:28 +0100 Subject: genetlink: fix genl_set_err() group ID Fix another really stupid bug - I introduced genl_set_err() precisely to be able to adjust the group and reject invalid ones, but then forgot to do so. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/genetlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 771af09e90eb..1b177ed803b7 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -384,6 +384,9 @@ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags) static inline int genl_set_err(struct genl_family *family, struct net *net, u32 portid, u32 group, int code) { + if (WARN_ON_ONCE(group >= family->n_mcgrps)) + return -EINVAL; + group = family->mcgrp_offset + group; return netlink_set_err(net->genl_sock, portid, group, code); } -- cgit v1.2.3 From 85fbaa75037d0b6b786ff18658ddf0b4014ce2a4 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sat, 23 Nov 2013 00:46:12 +0100 Subject: inet: fix addr_len/msg->msg_namelen assignment in recv_error and rxpmtu functions Commit bceaa90240b6019ed73b49965eac7d167610be69 ("inet: prevent leakage of uninitialized memory to user in recv syscalls") conditionally updated addr_len if the msg_name is written to. The recv_error and rxpmtu functions relied on the recvmsg functions to set up addr_len before. As this does not happen any more we have to pass addr_len to those functions as well and set it to the size of the corresponding sockaddr length. This broke traceroute and such. Fixes: bceaa90240b6 ("inet: prevent leakage of uninitialized memory to user in recv syscalls") Reported-by: Brad Spengler Reported-by: Tom Labanowski Cc: mpb Cc: David S. Miller Cc: Eric Dumazet Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- include/net/ipv6.h | 6 ++++-- include/net/ping.h | 3 ++- 3 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index 217bc5bfc6c6..5a25f36fe3a7 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -473,7 +473,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)); -int ip_recv_error(struct sock *sk, struct msghdr *msg, int len); +int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 2a5f668cd683..eb198acaac1d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -776,8 +776,10 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len); -int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len); +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); diff --git a/include/net/ping.h b/include/net/ping.h index 3f67704f3747..90f48417b03d 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -31,7 +31,8 @@ /* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { - int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len); + int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); int (*ip6_datagram_recv_ctl)(struct sock *sk, struct msghdr *msg, struct sk_buff *skb); int (*icmpv6_err_convert)(u8 type, u8 code, int *err); -- cgit v1.2.3 From 6eabca54d6781f61c7318517c1463a098acb7a87 Mon Sep 17 00:00:00 2001 From: Xufeng Zhang Date: Mon, 25 Nov 2013 11:26:57 +0800 Subject: sctp: Restore 'resent' bit to avoid retransmitted chunks for RTT measurements Currently retransmitted DATA chunks could also be used for RTT measurements since there are no flag to identify whether the transmitted DATA chunk is a new one or a retransmitted one. This problem is introduced by commit ae19c5486 ("sctp: remove 'resent' bit from the chunk") which inappropriately removed the 'resent' bit completely, instead of doing this, we should set the resent bit only for the retransmitted DATA chunks. Signed-off-by: Xufeng Zhang Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 2174d8da0770..ea0ca5f6e629 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -629,6 +629,7 @@ struct sctp_chunk { #define SCTP_NEED_FRTX 0x1 #define SCTP_DONT_FRTX 0x2 __u16 rtt_in_progress:1, /* This chunk used for RTT calc? */ + resent:1, /* Has this chunk ever been resent. */ has_tsn:1, /* Does this chunk have a TSN yet? */ has_ssn:1, /* Does this chunk have a SSN yet? */ singleton:1, /* Only chunk in the packet? */ -- cgit v1.2.3 From 1431fb31ecbaba1b5718006128f0f2ed0b94e1c3 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Tue, 3 Dec 2013 17:39:29 +0000 Subject: xen-netback: fix fragment detection in checksum setup The code to detect fragments in checksum_setup() was missing for IPv4 and too eager for IPv6. (It transpires that Windows seems to send IPv6 packets with a fragment header even if they are not a fragment - i.e. offset is zero, and M bit is not set). This patch also incorporates a fix to callers of maybe_pull_tail() where skb->network_header was being erroneously added to the length argument. Signed-off-by: Paul Durrant Signed-off-by: Zoltan Kiss Cc: Wei Liu Cc: Ian Campbell Cc: David Vrabel cc: David Miller Acked-by: Wei Liu Signed-off-by: David S. Miller --- include/net/ipv6.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index eb198acaac1d..488316e339a1 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -110,7 +110,8 @@ struct frag_hdr { __be32 identification; }; -#define IP6_MF 0x0001 +#define IP6_MF 0x0001 +#define IP6_OFFSET 0xFFF8 #include -- cgit v1.2.3 From 7f2cbdc28c034ef2c3be729681f631d5744e3cd5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Dec 2013 20:12:04 -0800 Subject: tcp_memcontrol: Cleanup/fix cg_proto->memory_pressure handling. kill memcg_tcp_enter_memory_pressure. The only function of memcg_tcp_enter_memory_pressure was to reduce deal with the unnecessary abstraction that was tcp_memcontrol. Now that struct tcp_memcontrol is gone remove this unnecessary function, the unnecessary function pointer, and modify sk_enter_memory_pressure to set this field directly, just as sk_leave_memory_pressure cleas this field directly. This fixes a small bug I intruduced when killing struct tcp_memcontrol that caused memcg_tcp_enter_memory_pressure to never be called and thus failed to ever set cg_proto->memory_pressure. Remove the cg_proto enter_memory_pressure function as it now serves no useful purpose. Don't test cg_proto->memory_presser in sk_leave_memory_pressure before clearing it. The test was originally there to ensure that the pointer was non-NULL. Now that cg_proto is not a pointer the pointer does not matter. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/sock.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index e3a18ff0c38b..2ef3c3eca47a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1035,7 +1035,6 @@ enum cg_proto_flags { }; struct cg_proto { - void (*enter_memory_pressure)(struct sock *sk); struct res_counter memory_allocated; /* Current allocated memory. */ struct percpu_counter sockets_allocated; /* Current number of sockets. */ int memory_pressure; @@ -1155,8 +1154,7 @@ static inline void sk_leave_memory_pressure(struct sock *sk) struct proto *prot = sk->sk_prot; for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - if (cg_proto->memory_pressure) - cg_proto->memory_pressure = 0; + cg_proto->memory_pressure = 0; } } @@ -1171,7 +1169,7 @@ static inline void sk_enter_memory_pressure(struct sock *sk) struct proto *prot = sk->sk_prot; for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - cg_proto->enter_memory_pressure(sk); + cg_proto->memory_pressure = 1; } sk->sk_prot->enter_memory_pressure(sk); -- cgit v1.2.3 From 9f70f46bd4c7267d48ef461a1d613ec9ec0d520c Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 10 Dec 2013 06:48:15 -0500 Subject: sctp: properly latch and use autoclose value from sock to association Currently, sctp associations latch a sockets autoclose value to an association at association init time, subject to capping constraints from the max_autoclose sysctl value. This leads to an odd situation where an application may set a socket level autoclose timeout, but sliently sctp will limit the autoclose timeout to something less than that. Fix this by modifying the autoclose setsockopt function to check the limit, cap it and warn the user via syslog that the timeout is capped. This will allow getsockopt to return valid autoclose timeout values that reflect what subsequent associations actually use. While were at it, also elimintate the assoc->autoclose variable, it duplicates whats in the timeout array, which leads to multiple sources for the same information, that may differ (as the former isn't subject to any capping). This gives us the timeout information in a canonical place and saves some space in the association structure as well. Signed-off-by: Neil Horman Acked-by: Vlad Yasevich CC: Wang Weidong CC: David Miller CC: Vlad Yasevich CC: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ea0ca5f6e629..67b5d0068273 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1726,12 +1726,6 @@ struct sctp_association { /* How many duplicated TSNs have we seen? */ int numduptsns; - /* Number of seconds of idle time before an association is closed. - * In the association context, this is really used as a boolean - * since the real timeout is stored in the timeouts array - */ - __u32 autoclose; - /* These are to support * "SCTP Extensions for Dynamic Reconfiguration of IP Addresses * and Enforcement of Flow and Message Limits" -- cgit v1.2.3