From 351638e7deeed2ec8ce451b53d33921b3da68f83 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 28 May 2013 01:30:21 +0000 Subject: net: pass info struct via netdevice notifier So far, only net_device * could be passed along with netdevice notifier event. This patch provides a possibility to pass custom structure able to provide info that event listener needs to know. Signed-off-by: Jiri Pirko v2->v3: fix typo on simeth shortened dev_getter shortened notifier_info struct name v1->v2: fix notifier_call parameter in call_netdevice_notifier() Signed-off-by: David S. Miller --- net/ipv6/ndisc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6/ndisc.c') diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2712ab22a174..a0962697a257 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1568,7 +1568,7 @@ int ndisc_rcv(struct sk_buff *skb) static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct inet6_dev *idev; -- cgit v1.2.3-59-g8ed1b From 29a3cad5c6ae9e7fbf1509d01d39c3c3c38f11f9 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 28 May 2013 20:34:26 +0000 Subject: ipv6: Correct comparisons and calculations using skb->tail and skb-transport_header This corrects an regression introduced by "net: Use 16bits for *_headers fields of struct skbuff" when NET_SKBUFF_DATA_USES_OFFSET is not set. In that case skb->tail will be a pointer whereas skb->transport_header will be an offset from head. This is corrected by using wrappers that ensure that comparisons and calculations are always made using pointers. Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- net/ipv6/exthdrs_core.c | 2 +- net/ipv6/icmp.c | 2 +- net/ipv6/mcast.c | 5 +++-- net/ipv6/mip6.c | 6 ++++-- net/ipv6/ndisc.c | 9 +++++---- net/ipv6/output_core.c | 3 ++- net/ipv6/raw.c | 3 ++- net/ipv6/route.c | 2 +- 8 files changed, 19 insertions(+), 13 deletions(-) (limited to 'net/ipv6/ndisc.c') diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index c5e83fae4df4..140748debc4a 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -115,7 +115,7 @@ EXPORT_SYMBOL(ipv6_skip_exthdr); int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) { const unsigned char *nh = skb_network_header(skb); - int packet_len = skb->tail - skb->network_header; + int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); struct ipv6_opt_hdr *hdr; int len; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 1d2902e61786..4b4890bbe16d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -399,7 +399,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) int err = 0; if ((u8 *)hdr < skb->head || - (skb->network_header + sizeof(*hdr)) > skb->tail) + (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; /* diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index bfa6cc36ef2a..72c8bfe06bb4 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1409,8 +1409,9 @@ static void mld_sendpack(struct sk_buff *skb) idev = __in6_dev_get(skb->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - payload_len = (skb->tail - skb->network_header) - sizeof(*pip6); - mldlen = skb->tail - skb->transport_header; + payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - + sizeof(*pip6); + mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 0f9bdc5ee9f3..9ac01dc9402e 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -268,7 +268,8 @@ static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; @@ -404,7 +405,8 @@ static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb, struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index a0962697a257..781dd3c99680 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -693,7 +693,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; @@ -853,7 +853,7 @@ static void ndisc_recv_na(struct sk_buff *skb) const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; @@ -1069,7 +1069,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) __u8 * opt = (__u8 *)(ra_msg + 1); - optlen = (skb->tail - skb->transport_header) - sizeof(struct ra_msg); + optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - + sizeof(struct ra_msg); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); @@ -1346,7 +1347,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) u8 *hdr; struct ndisc_options ndopts; struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); - u32 ndoptlen = skb->tail - (skb->transport_header + + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); #ifdef CONFIG_IPV6_NDISC_NODETYPE diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index c2e73e647e44..ab92a3673fbb 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -40,7 +40,8 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) u16 offset = sizeof(struct ipv6hdr); struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - unsigned int packet_len = skb->tail - skb->network_header; + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index eedff8ccded5..4f8886aa8429 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1132,7 +1132,8 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) - amount = skb->tail - skb->transport_header; + amount = skb_tail_pointer(skb) - + skb_transport_header(skb); spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 194c3cde1536..2b874185ebb2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1649,7 +1649,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu int optlen, on_link; u8 *lladdr; - optlen = skb->tail - skb->transport_header; + optlen = skb_tail_pointer(skb) - skb_transport_header(skb); optlen -= sizeof(*msg); if (optlen < 0) { -- cgit v1.2.3-59-g8ed1b From f2f79cca13e36972978ffd1fb6483c8a1141b510 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Sat, 13 Jul 2013 11:26:51 +0300 Subject: ndisc: bool initializations should use true and false Signed-off-by: Daniel Baluta Signed-off-by: David S. Miller --- net/ipv6/ndisc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv6/ndisc.c') diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b3b5730b48c5..24c03396e008 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -479,7 +479,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) - override = 0; + override = false; inc_opt |= ifp->idev->cnf.force_tllao; in6_ifa_put(ifp); } else { @@ -557,7 +557,7 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, } if (ipv6_addr_any(saddr)) - inc_opt = 0; + inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev); @@ -790,7 +790,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && - inc != 0 && + inc && idev->nd_parms->proxy_delay != 0) { /* * for anycast or proxy, -- cgit v1.2.3-59-g8ed1b From 2ac3ac8f86f2fe065d746d9a9abaca867adec577 Mon Sep 17 00:00:00 2001 From: Michal Kubeček Date: Thu, 1 Aug 2013 10:04:14 +0200 Subject: ipv6: prevent fib6_run_gc() contention On a high-traffic router with many processors and many IPv6 dst entries, soft lockup in fib6_run_gc() can occur when number of entries reaches gc_thresh. This happens because fib6_run_gc() uses fib6_gc_lock to allow only one thread to run the garbage collector but ip6_dst_gc() doesn't update net->ipv6.ip6_rt_last_gc until fib6_run_gc() returns. On a system with many entries, this can take some time so that in the meantime, other threads pass the tests in ip6_dst_gc() (ip6_rt_last_gc is still not updated) and wait for the lock. They then have to run the garbage collector one after another which blocks them for quite long. Resolve this by replacing special value ~0UL of expire parameter to fib6_run_gc() by explicit "force" parameter to choose between spin_lock_bh() and spin_trylock_bh() and call fib6_run_gc() with force=false if gc_thresh is reached but not max_size. Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 2 +- net/ipv6/ip6_fib.c | 19 ++++++++----------- net/ipv6/ndisc.c | 4 ++-- net/ipv6/route.c | 4 ++-- 4 files changed, 13 insertions(+), 16 deletions(-) (limited to 'net/ipv6/ndisc.c') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 2a601e7da1bf..48ec25a7fcb6 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -300,7 +300,7 @@ extern void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info); extern void fib6_run_gc(unsigned long expires, - struct net *net); + struct net *net, bool force); extern void fib6_gc_cleanup(void); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5fc9c7a68d8d..d872553ca933 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1632,19 +1632,16 @@ static int fib6_age(struct rt6_info *rt, void *arg) static DEFINE_SPINLOCK(fib6_gc_lock); -void fib6_run_gc(unsigned long expires, struct net *net) +void fib6_run_gc(unsigned long expires, struct net *net, bool force) { - if (expires != ~0UL) { + if (force) { spin_lock_bh(&fib6_gc_lock); - gc_args.timeout = expires ? (int)expires : - net->ipv6.sysctl.ip6_rt_gc_interval; - } else { - if (!spin_trylock_bh(&fib6_gc_lock)) { - mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); - return; - } - gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval; + } else if (!spin_trylock_bh(&fib6_gc_lock)) { + mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); + return; } + gc_args.timeout = expires ? (int)expires : + net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = icmp6_dst_gc(); @@ -1661,7 +1658,7 @@ void fib6_run_gc(unsigned long expires, struct net *net) static void fib6_gc_timer_cb(unsigned long arg) { - fib6_run_gc(0, (struct net *)arg); + fib6_run_gc(0, (struct net *)arg, true); } static int __net_init fib6_net_init(struct net *net) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 24c03396e008..79aa9652ed86 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1576,7 +1576,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); idev = in6_dev_get(dev); if (!idev) break; @@ -1586,7 +1586,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a8c891aa2464..824c424f9648 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1326,7 +1326,7 @@ static int ip6_dst_gc(struct dst_ops *ops) goto out; net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net); + fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size); net->ipv6.ip6_rt_last_gc = now; entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) @@ -2827,7 +2827,7 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; proc_dointvec(ctl, write, buffer, lenp, ppos); - fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); + fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } -- cgit v1.2.3-59-g8ed1b