From 3868204d6b89ea373a273e760609cb08020beb1a Mon Sep 17 00:00:00 2001 From: "fan.du" Date: Sun, 1 Dec 2013 16:28:48 +0800 Subject: {pktgen, xfrm} Update IPv4 header total len and checksum after tranformation commit a553e4a6317b2cfc7659542c10fe43184ffe53da ("[PKTGEN]: IPSEC support") tried to support IPsec ESP transport transformation for pktgen, but acctually this doesn't work at all for two reasons(The orignal transformed packet has bad IPv4 checksum value, as well as wrong auth value, reported by wireshark) - After transpormation, IPv4 header total length needs update, because encrypted payload's length is NOT same as that of plain text. - After transformation, IPv4 checksum needs re-caculate because of payload has been changed. With this patch, armmed pktgen with below cofiguration, Wireshark is able to decrypted ESP packet generated by pktgen without any IPv4 checksum error or auth value error. pgset "flag IPSEC" pgset "flows 1" Signed-off-by: Fan Du Signed-off-by: David S. Miller --- net/core/pktgen.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/core') diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 261357a6630..a797fff7f22 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2527,6 +2527,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, if (x) { int ret; __u8 *eth; + struct iphdr *iph; + nhead = x->props.header_len - skb_headroom(skb); if (nhead > 0) { ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); @@ -2548,6 +2550,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, eth = (__u8 *) skb_push(skb, ETH_HLEN); memcpy(eth, pkt_dev->hh, 12); *(u16 *) ð[12] = protocol; + + /* Update IPv4 header len as well as checksum value */ + iph = ip_hdr(skb); + iph->tot_len = htons(skb->len - ETH_HLEN); + ip_send_check(iph); } } return 1; -- cgit v1.2.3-70-g09d2 From 239c78db9c41a8f524cce60507440d72229d73bc Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 5 Dec 2013 23:29:19 +0100 Subject: net: clear local_df when passing skb between namespaces We must clear local_df when passing the skb between namespaces as the packet is not local to the new namespace any more and thus may not get fragmented by local rules. Fred Templin noticed that other namespaces do fragment IPv6 packets while forwarding. Instead they should have send back a PTB. The same problem should be present when forwarding DF-IPv4 packets between namespaces. Reported-by: Templin, Fred L Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/core/skbuff.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2718fed53d8..06e72d3cdf6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3584,6 +3584,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; + skb->local_df = 0; skb_dst_drop(skb); skb->mark = 0; secpath_reset(skb); -- cgit v1.2.3-70-g09d2 From d323e92cc3f4edd943610557c9ea1bb4bb5056e8 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Sun, 8 Dec 2013 09:36:56 -0500 Subject: net: drop_monitor: fix the value of maxattr maxattr in genl_family should be used to save the max attribute type, but not the max command type. Drop monitor doesn't support any attributes, so we should leave it as zero. Signed-off-by: David S. Miller --- net/core/drop_monitor.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net/core') diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 95897183226..e70301eb7a4 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = { .hdrsize = 0, .name = "NET_DM", .version = 2, - .maxattr = NET_DM_CMD_MAX, }; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); -- cgit v1.2.3-70-g09d2 From 12663bfc97c8b3fdb292428105dd92d563164050 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Sat, 7 Dec 2013 17:26:27 -0500 Subject: net: unix: allow set_peek_off to fail unix_dgram_recvmsg() will hold the readlock of the socket until recv is complete. In the same time, we may try to setsockopt(SO_PEEK_OFF) which will hang until unix_dgram_recvmsg() will complete (which can take a while) without allowing us to break out of it, triggering a hung task spew. Instead, allow set_peek_off to fail, this way userspace will not hang. Signed-off-by: Sasha Levin Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- net/core/sock.c | 2 +- net/unix/af_unix.c | 8 ++++++-- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/include/linux/net.h b/include/linux/net.h index 4bcee94cef9..69be3e6079c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -181,7 +181,7 @@ struct proto_ops { int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); - void (*set_peek_off)(struct sock *sk, int val); + int (*set_peek_off)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ diff --git a/net/core/sock.c b/net/core/sock.c index ab20ed9b0f3..5393b4b719d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -882,7 +882,7 @@ set_rcvbuf: case SO_PEEK_OFF: if (sock->ops->set_peek_off) - sock->ops->set_peek_off(sk, val); + ret = sock->ops->set_peek_off(sk, val); else ret = -EOPNOTSUPP; break; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 01625ccc3ae..a0ca162e5bd 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -530,13 +530,17 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, int); -static void unix_set_peek_off(struct sock *sk, int val) +static int unix_set_peek_off(struct sock *sk, int val) { struct unix_sock *u = unix_sk(sk); - mutex_lock(&u->readlock); + if (mutex_lock_interruptible(&u->readlock)) + return -EINTR; + sk->sk_peek_off = val; mutex_unlock(&u->readlock); + + return 0; } -- cgit v1.2.3-70-g09d2 From 53385d2d1de84f4036a0919ec46964c4e81b83f5 Mon Sep 17 00:00:00 2001 From: Bob Gilligan Date: Sun, 15 Dec 2013 13:39:56 -0800 Subject: neigh: Netlink notification for administrative NUD state change The neighbour code sends up an RTM_NEWNEIGH netlink notification if the NUD state of a neighbour cache entry is changed by a timer (e.g. from REACHABLE to STALE), even if the lladdr of the entry has not changed. But an administrative change to the the NUD state of a neighbour cache entry that does not change the lladdr (e.g. via "ip -4 neigh change ... nud ...") does not trigger a netlink notification. This means that netlink listeners will not hear about administrative NUD state changes such as from a resolved state to PERMANENT. This patch changes the neighbor code to generate an RTM_NEWNEIGH message when the NUD state of an entry is changed administratively. Signed-off-by: Bob Gilligan Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/core/neighbour.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ca15f32821f..36b1443f9ae 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1161,6 +1161,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->parms->reachable_time : 0))); neigh->nud_state = new; + notify = 1; } if (lladdr != neigh->ha) { -- cgit v1.2.3-70-g09d2 From 85328240c625f322af9f69c7b60e619717101d77 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 26 Nov 2013 06:33:52 +0000 Subject: net: allow netdev_all_upper_get_next_dev_rcu with rtnl lock held It is useful to be able to walk all upper devices when bringing a device online where the RTNL lock is held. In this case it is safe to walk the all_adj_list because the RTNL lock is used to protect the write side as well. This patch adds a check to see if the rtnl lock is held before throwing a warning in netdev_all_upper_get_next_dev_rcu(). Also because we now have a call site for lockdep_rtnl_is_held() outside COFIG_LOCK_PROVING an inline definition returning 1 is needed. Similar to the rcu_read_lock_is_held(). Fixes: 2a47fa45d4df ("ixgbe: enable l2 forwarding acceleration for macvlans") CC: Veaceslav Falico Reported-by: Yuanhan Liu Signed-off-by: John Fastabend Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- include/linux/rtnetlink.h | 5 +++++ net/core/dev.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 939428ad25a..8e3e66ac0a5 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -24,6 +24,11 @@ extern int rtnl_trylock(void); extern int rtnl_is_locked(void); #ifdef CONFIG_PROVE_LOCKING extern int lockdep_rtnl_is_held(void); +#else +static inline int lockdep_rtnl_is_held(void) +{ + return 1; +} #endif /* #ifdef CONFIG_PROVE_LOCKING */ /** diff --git a/net/core/dev.c b/net/core/dev.c index ba3b7ea5ebb..4fc17221545 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4500,7 +4500,7 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, { struct netdev_adjacent *upper; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); -- cgit v1.2.3-70-g09d2