From 660b26dc1a8aeb33c2a2246ebf1b3684449a74b7 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 21 Jan 2013 06:00:26 +0000 Subject: mcast: add multicast proxy support (IPv4 and IPv6) This patch add the support of proxy multicast, ie being able to build a static multicast tree. It adds the support of (*,*) and (*,G) entries. The user should define an (*,*) entry which is not used for real forwarding. This entry defines the upstream in iif and contains all interfaces from the static tree in its oifs. It will be used to forward packet upstream when they come from an interface belonging to the static tree. Hence, the user should define (*,G) entries to build its static tree. Note that upstream interface must be part of oifs: packets are sent to all oifs interfaces except the input interface. This ensures to always join the whole static tree, even if the packet is not coming from the upstream interface. Signed-off-by: Nicolas Dichtel Acked-by: David L Stevens Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 106 insertions(+), 13 deletions(-) (limited to 'net/ipv4/ipmr.c') diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a9454cbd953c..4b5e22670d44 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -828,6 +828,49 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, return NULL; } +/* Look for a (*,*,oif) entry */ +static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt, + int vifi) +{ + int line = MFC_HASH(INADDR_ANY, INADDR_ANY); + struct mfc_cache *c; + + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) + if (c->mfc_origin == INADDR_ANY && + c->mfc_mcastgrp == INADDR_ANY && + c->mfc_un.res.ttls[vifi] < 255) + return c; + + return NULL; +} + +/* Look for a (*,G) entry */ +static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, + __be32 mcastgrp, int vifi) +{ + int line = MFC_HASH(mcastgrp, INADDR_ANY); + struct mfc_cache *c, *proxy; + + if (mcastgrp == INADDR_ANY) + goto skip; + + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) + if (c->mfc_origin == INADDR_ANY && + c->mfc_mcastgrp == mcastgrp) { + if (c->mfc_un.res.ttls[vifi] < 255) + return c; + + /* It's ok if the vifi is part of the static tree */ + proxy = ipmr_cache_find_any_parent(mrt, + c->mfc_parent); + if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) + return c; + } + +skip: + return ipmr_cache_find_any_parent(mrt, vifi); +} + /* * Allocate a multicast cache entry */ @@ -1053,7 +1096,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) * MFC cache manipulation by user space mroute daemon */ -static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) +static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { int line; struct mfc_cache *c, *next; @@ -1062,7 +1105,8 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr && + (parent == -1 || parent == c->mfc_parent)) { list_del_rcu(&c->list); mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_free(c); @@ -1073,7 +1117,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) } static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, - struct mfcctl *mfc, int mrtsock) + struct mfcctl *mfc, int mrtsock, int parent) { bool found = false; int line; @@ -1086,7 +1130,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr && + (parent == -1 || parent == c->mfc_parent)) { found = true; break; } @@ -1103,7 +1148,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, return 0; } - if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) + if (mfc->mfcc_mcastgrp.s_addr != INADDR_ANY && + !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; c = ipmr_cache_alloc(); @@ -1218,7 +1264,7 @@ static void mrtsock_destruct(struct sock *sk) int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { - int ret; + int ret, parent = 0; struct vifctl vif; struct mfcctl mfc; struct net *net = sock_net(sk); @@ -1287,16 +1333,22 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi */ case MRT_ADD_MFC: case MRT_DEL_MFC: + parent = -1; + case MRT_ADD_MFC_PROXY: + case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) return -EINVAL; if (copy_from_user(&mfc, optval, sizeof(mfc))) return -EFAULT; + if (parent == 0) + parent = mfc.mfcc_parent; rtnl_lock(); - if (optname == MRT_DEL_MFC) - ret = ipmr_mfc_delete(mrt, &mfc); + if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY) + ret = ipmr_mfc_delete(mrt, &mfc, parent); else ret = ipmr_mfc_add(net, mrt, &mfc, - sk == rtnl_dereference(mrt->mroute_sk)); + sk == rtnl_dereference(mrt->mroute_sk), + parent); rtnl_unlock(); return ret; /* @@ -1749,17 +1801,28 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, { int psend = -1; int vif, ct; + int true_vifi = ipmr_find_vif(mrt, skb->dev); vif = cache->mfc_parent; cache->mfc_un.res.pkt++; cache->mfc_un.res.bytes += skb->len; + if (cache->mfc_origin == INADDR_ANY && true_vifi >= 0) { + struct mfc_cache *cache_proxy; + + /* For an (*,G) entry, we only check that the incomming + * interface is part of the static tree. + */ + cache_proxy = ipmr_cache_find_any_parent(mrt, vif); + if (cache_proxy && + cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + goto forward; + } + /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (mrt->vif_table[vif].dev != skb->dev) { - int true_vifi; - if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... @@ -1776,7 +1839,6 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, } cache->mfc_un.res.wrong_if++; - true_vifi = ipmr_find_vif(mrt, skb->dev); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -1794,15 +1856,33 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } +forward: mrt->vif_table[vif].pkt_in++; mrt->vif_table[vif].bytes_in += skb->len; /* * Forward the frame */ + if (cache->mfc_origin == INADDR_ANY && + cache->mfc_mcastgrp == INADDR_ANY) { + if (true_vifi >= 0 && + true_vifi != cache->mfc_parent && + ip_hdr(skb)->ttl > + cache->mfc_un.res.ttls[cache->mfc_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = cache->mfc_parent; + goto last_forward; + } + goto dont_forward; + } for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { - if (ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { + /* For (*,G) entry, don't forward to the incoming interface */ + if ((cache->mfc_origin != INADDR_ANY || ct != true_vifi) && + ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -1813,6 +1893,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, psend = ct; } } +last_forward: if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -1902,6 +1983,13 @@ int ip_mr_input(struct sk_buff *skb) /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); + if (cache == NULL) { + int vif = ipmr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, + vif); + } /* * No usable cache entry @@ -2107,7 +2195,12 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_lock(); cache = ipmr_cache_find(mrt, saddr, daddr); + if (cache == NULL && skb->dev) { + int vif = ipmr_find_vif(mrt, skb->dev); + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, daddr, vif); + } if (cache == NULL) { struct sk_buff *skb2; struct iphdr *iph; -- cgit v1.2.3 From 360eb5da665566a110993c58ed2a63e98f6720bf Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 22 Jan 2013 11:18:03 +0100 Subject: ipmr: fix sparse warning when testing origin or group mfc_mcastgrp and mfc_origin are __be32, thus we need to convert INADDR_ANY. Because INADDR_ANY is 0, this patch just fix sparse warnings. Reported-by: Fengguang Wu Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'net/ipv4/ipmr.c') diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 4b5e22670d44..7085b9b51e7f 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -832,12 +832,12 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt, int vifi) { - int line = MFC_HASH(INADDR_ANY, INADDR_ANY); + int line = MFC_HASH(htonl(INADDR_ANY), htonl(INADDR_ANY)); struct mfc_cache *c; list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) - if (c->mfc_origin == INADDR_ANY && - c->mfc_mcastgrp == INADDR_ANY && + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == htonl(INADDR_ANY) && c->mfc_un.res.ttls[vifi] < 255) return c; @@ -848,14 +848,14 @@ static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt, static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, __be32 mcastgrp, int vifi) { - int line = MFC_HASH(mcastgrp, INADDR_ANY); + int line = MFC_HASH(mcastgrp, htonl(INADDR_ANY)); struct mfc_cache *c, *proxy; - if (mcastgrp == INADDR_ANY) + if (mcastgrp == htonl(INADDR_ANY)) goto skip; list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) - if (c->mfc_origin == INADDR_ANY && + if (c->mfc_origin == htonl(INADDR_ANY) && c->mfc_mcastgrp == mcastgrp) { if (c->mfc_un.res.ttls[vifi] < 255) return c; @@ -1148,7 +1148,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, return 0; } - if (mfc->mfcc_mcastgrp.s_addr != INADDR_ANY && + if (mfc->mfcc_mcastgrp.s_addr != htonl(INADDR_ANY) && !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; @@ -1807,7 +1807,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, cache->mfc_un.res.pkt++; cache->mfc_un.res.bytes += skb->len; - if (cache->mfc_origin == INADDR_ANY && true_vifi >= 0) { + if (cache->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; /* For an (*,G) entry, we only check that the incomming @@ -1863,8 +1863,8 @@ forward: /* * Forward the frame */ - if (cache->mfc_origin == INADDR_ANY && - cache->mfc_mcastgrp == INADDR_ANY) { + if (cache->mfc_origin == htonl(INADDR_ANY) && + cache->mfc_mcastgrp == htonl(INADDR_ANY)) { if (true_vifi >= 0 && true_vifi != cache->mfc_parent && ip_hdr(skb)->ttl > @@ -1881,7 +1881,8 @@ forward: for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ - if ((cache->mfc_origin != INADDR_ANY || ct != true_vifi) && + if ((cache->mfc_origin != htonl(INADDR_ANY) || + ct != true_vifi) && ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); -- cgit v1.2.3 From d4beaa66add8aebf83ab16d2fde4e4de8dac36df Mon Sep 17 00:00:00 2001 From: Gao feng Date: Mon, 18 Feb 2013 01:34:54 +0000 Subject: net: proc: change proc_net_fops_create to proc_create Right now, some modules such as bonding use proc_create to create proc entries under /proc/net/, and other modules such as ipv4 use proc_net_fops_create. It looks a little chaos.this patch changes all of proc_net_fops_create to proc_create. we can remove proc_net_fops_create after this patch. Signed-off-by: Gao feng Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/ipmr.c') diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7085b9b51e7f..160a8b8e9cae 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2703,9 +2703,9 @@ static int __net_init ipmr_net_init(struct net *net) #ifdef CONFIG_PROC_FS err = -ENOMEM; - if (!proc_net_fops_create(net, "ip_mr_vif", 0, &ipmr_vif_fops)) + if (!proc_create("ip_mr_vif", 0, net->proc_net, &ipmr_vif_fops)) goto proc_vif_fail; - if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops)) + if (!proc_create("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_fops)) goto proc_cache_fail; #endif return 0; -- cgit v1.2.3 From ece31ffd539e8e2b586b1ca5f50bc4f4591e3893 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Mon, 18 Feb 2013 01:34:56 +0000 Subject: net: proc: change proc_net_remove to remove_proc_entry proc_net_remove is only used to remove proc entries that under /proc/net,it's not a general function for removing proc entries of netns. if we want to remove some proc entries which under /proc/net/stat/, we still need to call remove_proc_entry. this patch use remove_proc_entry to replace proc_net_remove. we can remove proc_net_remove after this patch. Signed-off-by: Gao feng Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4/ipmr.c') diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 160a8b8e9cae..5f95b3aa579e 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2712,7 +2712,7 @@ static int __net_init ipmr_net_init(struct net *net) #ifdef CONFIG_PROC_FS proc_cache_fail: - proc_net_remove(net, "ip_mr_vif"); + remove_proc_entry("ip_mr_vif", net->proc_net); proc_vif_fail: ipmr_rules_exit(net); #endif @@ -2723,8 +2723,8 @@ fail: static void __net_exit ipmr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove(net, "ip_mr_cache"); - proc_net_remove(net, "ip_mr_vif"); + remove_proc_entry("ip_mr_cache", net->proc_net); + remove_proc_entry("ip_mr_vif", net->proc_net); #endif ipmr_rules_exit(net); } -- cgit v1.2.3