--- zzzz-none-000/linux-3.10.107/net/ipv4/igmp.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/ipv4/igmp.c 2021-02-04 17:41:59.000000000 +0000 @@ -88,6 +88,7 @@ #include #include #include +#include #include #include @@ -96,6 +97,7 @@ #include #include #include +#include #include #ifdef CONFIG_IP_MROUTE #include @@ -108,19 +110,23 @@ #define IP_MAX_MEMBERSHIPS 20 #define IP_MAX_MSF 10 +/* IGMP reports for link-local multicast groups are enabled by default */ +int sysctl_igmp_llm_reports __read_mostly = 1; + #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ -#define IGMP_V1_Router_Present_Timeout (400*HZ) -#define IGMP_V2_Router_Present_Timeout (400*HZ) -#define IGMP_Unsolicited_Report_Interval (10*HZ) -#define IGMP_Query_Response_Interval (10*HZ) -#define IGMP_Unsolicited_Report_Count 2 +#define IGMP_V1_ROUTER_PRESENT_TIMEOUT (400*HZ) +#define IGMP_V2_ROUTER_PRESENT_TIMEOUT (400*HZ) +#define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ) +#define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ) +#define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) +#define IGMP_QUERY_ROBUSTNESS_VARIABLE 2 -#define IGMP_Initial_Report_Delay (1) +#define IGMP_INITIAL_REPORT_DELAY (1) -/* IGMP_Initial_Report_Delay is not from IGMP specs! +/* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs! * IGMP specs require to report membership immediately after * joining a group, but we delay the first report by a * small interval. It seems more natural and still does not @@ -138,6 +144,29 @@ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) +static int unsolicited_report_interval(struct in_device *in_dev) +{ + int interval_ms, interval_jiffies; + + if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) + interval_ms = IN_DEV_CONF_GET( + in_dev, + IGMPV2_UNSOLICITED_REPORT_INTERVAL); + else /* v3 */ + interval_ms = IN_DEV_CONF_GET( + in_dev, + IGMPV3_UNSOLICITED_REPORT_INTERVAL); + + interval_jiffies = msecs_to_jiffies(interval_ms); + + /* _timer functions can't handle a delay of 0 jiffies so ensure + * we always return a positive value. + */ + if (interval_jiffies <= 0) + interval_jiffies = 1; + return interval_jiffies; +} + static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr); static void igmpv3_clear_delrec(struct in_device *in_dev); @@ -186,7 +215,7 @@ /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { - int tv = net_random() % max_delay; + int tv = prandom_u32() % max_delay; im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) @@ -195,7 +224,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev) { - int tv = net_random() % in_dev->mr_maxdelay; + int tv = prandom_u32() % in_dev->mr_maxdelay; unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && @@ -209,7 +238,7 @@ static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = net_random() % delay; + int tv = prandom_u32() % delay; if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); @@ -290,7 +319,7 @@ struct ip_sf_list *psf; int scount = 0; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; @@ -298,9 +327,7 @@ return scount; } -#define igmp_skb_size(skb) (*(unsigned int *)((skb)->cb)) - -static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) +static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; @@ -310,6 +337,7 @@ struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; + unsigned int size = mtu; while (1) { skb = alloc_skb(size + hlen + tlen, @@ -320,7 +348,7 @@ if (size < 256) return NULL; } - igmp_skb_size(skb) = size; + skb->priority = TC_PRIO_CONTROL; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, @@ -334,6 +362,7 @@ skb->dev = dev; skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); @@ -348,7 +377,7 @@ pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -368,11 +397,11 @@ static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); - const int igmplen = skb->tail - skb->transport_header; + const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); - return ip_local_out(skb); + return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) @@ -402,8 +431,7 @@ return skb; } -#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? igmp_skb_size(skb) - (skb)->len : \ - skb_tailroom(skb)) : 0) +#define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) @@ -416,6 +444,8 @@ if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; + if (ipv4_is_local_multicast(pmc->multiaddr) && !sysctl_igmp_llm_reports) + return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; @@ -442,7 +472,7 @@ } first = 1; psf_prev = NULL; - for (psf=*psf_list; psf; psf=psf_next) { + for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; @@ -475,7 +505,7 @@ if (!skb) return NULL; psrc = (__be32 *)skb_put(skb, sizeof(__be32)); - *psrc = psf->sf_inaddr; + net_hdr_word(psrc) = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { @@ -499,7 +529,7 @@ return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ - if (skb && AVAILABLE(skb)multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(pmc->multiaddr) && + !sysctl_igmp_llm_reports) + continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; @@ -555,7 +588,7 @@ struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; - for (psf=*ppsf; psf; psf = psf_next) { + for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) @@ -579,7 +612,7 @@ /* deleted MCA's */ pmc_prev = NULL; - for (pmc=in_dev->mc_tomb; pmc; pmc=pmc_next) { + for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; @@ -657,7 +690,11 @@ if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - else if (type == IGMP_HOST_LEAVE_MESSAGE) + + if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + return 0; + + if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; @@ -671,10 +708,11 @@ hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); - if (skb == NULL) { + if (!skb) { ip_rt_put(rt); return -1; } + skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); @@ -692,7 +730,7 @@ iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -705,7 +743,7 @@ ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); - return ip_local_out(skb); + return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(unsigned long data) @@ -724,7 +762,8 @@ igmpv3_send_cr(in_dev); if (in_dev->mr_ifc_count) { in_dev->mr_ifc_count--; - igmp_ifc_start_timer(in_dev, IGMP_Unsolicited_Report_Interval); + igmp_ifc_start_timer(in_dev, + unsolicited_report_interval(in_dev)); } in_dev_put(in_dev); } @@ -733,15 +772,14 @@ { if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + in_dev->mr_ifc_count = in_dev->mr_qrv ?: sysctl_igmp_qrv; igmp_ifc_start_timer(in_dev, 1); } static void igmp_timer_expire(unsigned long data) { - struct ip_mc_list *im=(struct ip_mc_list *)data; + struct ip_mc_list *im = (struct ip_mc_list *)data; struct in_device *in_dev = im->interface; spin_lock(&im->lock); @@ -749,7 +787,7 @@ if (im->unsolicit_count) { im->unsolicit_count--; - igmp_start_timer(im, IGMP_Unsolicited_Report_Interval); + igmp_start_timer(im, unsolicited_report_interval(in_dev)); } im->reporter = 1; spin_unlock(&im->lock); @@ -771,10 +809,10 @@ int i, scount; scount = 0; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; - for (i=0; isf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != @@ -802,10 +840,10 @@ /* mark INCLUDE-mode sources */ scount = 0; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; - for (i=0; isf_inaddr) { psf->sf_gsresp = 1; scount++; @@ -829,6 +867,8 @@ if (group == IGMP_ALL_HOSTS) return false; + if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { @@ -857,15 +897,15 @@ if (ih->code == 0) { /* Alas, old v1 router presents here. */ - max_delay = IGMP_Query_Response_Interval; + max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + - IGMP_V1_Router_Present_Timeout; + IGMP_V1_ROUTER_PRESENT_TIMEOUT; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + - IGMP_V2_Router_Present_Timeout; + IGMP_V2_ROUTER_PRESENT_TIMEOUT; } /* cancel the interface change timer */ in_dev->mr_ifc_count = 0; @@ -877,7 +917,7 @@ return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ - max_delay = IGMP_Query_Response_Interval; + max_delay = IGMP_QUERY_RESPONSE_INTERVAL; group = 0; } else if (IGMP_V2_SEEN(in_dev)) { /* this is a v3 query with v2 queriers present; @@ -909,7 +949,7 @@ in_dev->mr_qrv = ih3->qrv; if (!group) { /* general query */ if (ih3->nsrcs) - return false; /* no sources allowed */ + return true; /* no sources allowed */ igmp_gq_start_timer(in_dev); return false; } @@ -935,6 +975,9 @@ continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(im->multiaddr) && + !sysctl_igmp_llm_reports) + continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; @@ -959,22 +1002,14 @@ int len = skb->len; bool dropped = true; - if (in_dev == NULL) + if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (!csum_fold(skb->csum)) - break; - /* fall through */ - case CHECKSUM_NONE: - skb->csum = 0; - if (__skb_checksum_complete(skb)) - goto drop; - } + if (skb_checksum_simple_validate(skb)) + goto drop; ih = igmp_hdr(skb); switch (ih->type) { @@ -1071,8 +1106,7 @@ pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; - pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; @@ -1080,7 +1114,7 @@ pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; - for (psf=pmc->sources; psf; psf=psf->sf_next) + for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); @@ -1098,7 +1132,7 @@ spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; - for (pmc=in_dev->mc_tomb; pmc; pmc=pmc->next) { + for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; @@ -1111,7 +1145,7 @@ } spin_unlock_bh(&in_dev->mc_tomb_lock); if (pmc) { - for (psf=pmc->tomb; psf; psf=psf_next) { + for (psf = pmc->tomb; psf; psf = psf_next) { psf_next = psf->sf_next; kfree(psf); } @@ -1144,7 +1178,7 @@ psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); - for (; psf; psf=psf_next) { + for (; psf; psf = psf_next) { psf_next = psf->sf_next; kfree(psf); } @@ -1168,6 +1202,8 @@ #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; + if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + return; reporter = im->reporter; igmp_stop_timer(im); @@ -1200,19 +1236,20 @@ #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; + if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + return; if (in_dev->dead) return; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); - igmp_start_timer(im, IGMP_Initial_Report_Delay); + igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); spin_unlock_bh(&im->lock); return; } /* else, v3 */ - im->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + im->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; igmp_ifc_event(in_dev); #endif } @@ -1222,6 +1259,57 @@ * Multicast list managers */ +static u32 ip_mc_hash(const struct ip_mc_list *im) +{ + return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG); +} + +static void ip_mc_hash_add(struct in_device *in_dev, + struct ip_mc_list *im) +{ + struct ip_mc_list __rcu **mc_hash; + u32 hash; + + mc_hash = rtnl_dereference(in_dev->mc_hash); + if (mc_hash) { + hash = ip_mc_hash(im); + im->next_hash = mc_hash[hash]; + rcu_assign_pointer(mc_hash[hash], im); + return; + } + + /* do not use a hash table for small number of items */ + if (in_dev->mc_count < 4) + return; + + mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG, + GFP_KERNEL); + if (!mc_hash) + return; + + for_each_pmc_rtnl(in_dev, im) { + hash = ip_mc_hash(im); + im->next_hash = mc_hash[hash]; + RCU_INIT_POINTER(mc_hash[hash], im); + } + + rcu_assign_pointer(in_dev->mc_hash, mc_hash); +} + +static void ip_mc_hash_remove(struct in_device *in_dev, + struct ip_mc_list *im) +{ + struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash); + struct ip_mc_list *aux; + + if (!mc_hash) + return; + mc_hash += ip_mc_hash(im); + while ((aux = rtnl_dereference(*mc_hash)) != im) + mc_hash = &aux->next_hash; + *mc_hash = im->next_hash; +} + /* * A socket has joined a multicast group on device dev. @@ -1255,14 +1343,16 @@ atomic_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST - setup_timer(&im->timer, &igmp_timer_expire, (unsigned long)im); - im->unsolicit_count = IGMP_Unsolicited_Report_Count; + setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im); + im->unsolicit_count = sysctl_igmp_qrv; #endif im->next_rcu = in_dev->mc_list; in_dev->mc_count++; rcu_assign_pointer(in_dev->mc_list, im); + ip_mc_hash_add(in_dev, im); + #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im->multiaddr); #endif @@ -1274,19 +1364,188 @@ } EXPORT_SYMBOL(ip_mc_inc_group); +static int ip_mc_check_iphdr(struct sk_buff *skb) +{ + const struct iphdr *iph; + unsigned int len; + unsigned int offset = skb_network_offset(skb) + sizeof(*iph); + + if (!pskb_may_pull(skb, offset)) + return -EINVAL; + + iph = ip_hdr(skb); + + if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) + return -EINVAL; + + offset += ip_hdrlen(skb) - sizeof(*iph); + + if (!pskb_may_pull(skb, offset)) + return -EINVAL; + + iph = ip_hdr(skb); + + if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + return -EINVAL; + + len = skb_network_offset(skb) + ntohs(iph->tot_len); + if (skb->len < len || len < offset) + return -EINVAL; + + skb_set_transport_header(skb, offset); + + return 0; +} + +static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) +{ + unsigned int len = skb_transport_offset(skb); + + len += sizeof(struct igmpv3_report); + + return pskb_may_pull(skb, len) ? 0 : -EINVAL; +} + +static int ip_mc_check_igmp_query(struct sk_buff *skb) +{ + unsigned int len = skb_transport_offset(skb); + + len += sizeof(struct igmphdr); + if (skb->len < len) + return -EINVAL; + + /* IGMPv{1,2}? */ + if (skb->len != len) { + /* or IGMPv3? */ + len += sizeof(struct igmpv3_query) - sizeof(struct igmphdr); + if (skb->len < len || !pskb_may_pull(skb, len)) + return -EINVAL; + } + + /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer + * all-systems destination addresses (224.0.0.1) for general queries + */ + if (!igmp_hdr(skb)->group && + ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) + return -EINVAL; + + return 0; +} + +static int ip_mc_check_igmp_msg(struct sk_buff *skb) +{ + switch (igmp_hdr(skb)->type) { + case IGMP_HOST_LEAVE_MESSAGE: + case IGMP_HOST_MEMBERSHIP_REPORT: + case IGMPV2_HOST_MEMBERSHIP_REPORT: + /* fall through */ + return 0; + case IGMPV3_HOST_MEMBERSHIP_REPORT: + return ip_mc_check_igmp_reportv3(skb); + case IGMP_HOST_MEMBERSHIP_QUERY: + return ip_mc_check_igmp_query(skb); + default: + return -ENOMSG; + } +} + +static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb) +{ + return skb_checksum_simple_validate(skb); +} + +static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) + +{ + struct sk_buff *skb_chk; + unsigned int transport_len; + unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); + int ret = -EINVAL; + + transport_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb); + + skb_chk = skb_checksum_trimmed(skb, transport_len, + ip_mc_validate_checksum); + if (!skb_chk) + goto err; + + if (!pskb_may_pull(skb_chk, len)) + goto err; + + ret = ip_mc_check_igmp_msg(skb_chk); + if (ret) + goto err; + + if (skb_trimmed) + *skb_trimmed = skb_chk; + /* free now unneeded clone */ + else if (skb_chk != skb) + kfree_skb(skb_chk); + + ret = 0; + +err: + if (ret && skb_chk && skb_chk != skb) + kfree_skb(skb_chk); + + return ret; +} + +/** + * ip_mc_check_igmp - checks whether this is a sane IGMP packet + * @skb: the skb to validate + * @skb_trimmed: to store an skb pointer trimmed to IPv4 packet tail (optional) + * + * Checks whether an IPv4 packet is a valid IGMP packet. If so sets + * skb transport header accordingly and returns zero. + * + * -EINVAL: A broken packet was detected, i.e. it violates some internet + * standard + * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. + * -ENOMEM: A memory allocation failure happened. + * + * Optionally, an skb pointer might be provided via skb_trimmed (or set it + * to NULL): After parsing an IGMP packet successfully it will point to + * an skb which has its tail aligned to the IP packet end. This might + * either be the originally provided skb or a trimmed, cloned version if + * the skb frame had data beyond the IP packet. A cloned skb allows us + * to leave the original skb and its full frame unchanged (which might be + * desirable for layer 2 frame jugglers). + * + * Caller needs to set the skb network header and free any returned skb if it + * differs from the provided skb. + */ +int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) +{ + int ret = ip_mc_check_iphdr(skb); + + if (ret < 0) + return ret; + + if (ip_hdr(skb)->protocol != IPPROTO_IGMP) + return -ENOMSG; + + return __ip_mc_check_igmp(skb, skb_trimmed); +} +EXPORT_SYMBOL(ip_mc_check_igmp); + /* - * Resend IGMP JOIN report; used for bonding. - * Called with rcu_read_lock() + * Resend IGMP JOIN report; used by netdev notifier. */ -void ip_mc_rejoin_groups(struct in_device *in_dev) +static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; - for_each_pmc_rcu(in_dev, im) { + ASSERT_RTNL(); + + for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(im->multiaddr) && + !sysctl_igmp_llm_reports) + continue; /* a failover is happening and switches * must be notified immediately @@ -1301,7 +1560,6 @@ } #endif } -EXPORT_SYMBOL(ip_mc_rejoin_groups); /* * A socket has left a multicast group on device dev @@ -1319,6 +1577,7 @@ ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { + ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; igmp_group_dropped(i); @@ -1386,16 +1645,12 @@ { ASSERT_RTNL(); - in_dev->mc_tomb = NULL; #ifdef CONFIG_IP_MULTICAST - in_dev->mr_gq_running = 0; setup_timer(&in_dev->mr_gq_timer, igmp_gq_timer_expire, (unsigned long)in_dev); - in_dev->mr_ifc_count = 0; - in_dev->mc_count = 0; setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, (unsigned long)in_dev); - in_dev->mr_qrv = IGMP_Unsolicited_Report_Count; + in_dev->mr_qrv = sysctl_igmp_qrv; #endif spin_lock_init(&in_dev->mc_tomb_lock); @@ -1409,6 +1664,9 @@ ASSERT_RTNL(); +#ifdef CONFIG_IP_MULTICAST + in_dev->mr_qrv = sysctl_igmp_qrv; +#endif ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) @@ -1475,7 +1733,9 @@ */ int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS; int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; - +#ifdef CONFIG_IP_MULTICAST +int sysctl_igmp_qrv __read_mostly = IGMP_QUERY_ROBUSTNESS_VARIABLE; +#endif static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) @@ -1484,7 +1744,7 @@ int rv = 0; psf_prev = NULL; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1510,8 +1770,7 @@ #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + psf->sf_crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; @@ -1557,7 +1816,7 @@ pmc->sfcount[sfmode]--; } err = 0; - for (i=0; i 0; @@ -1574,10 +1833,9 @@ /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST - pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; in_dev->mr_ifc_count = pmc->crcount; - for (psf=pmc->sources; psf; psf = psf->sf_next) + for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { @@ -1598,7 +1856,7 @@ struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1626,7 +1884,7 @@ struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; - for (psf=pmc->sources; psf; psf=psf->sf_next) + for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && @@ -1643,7 +1901,7 @@ int new_in, rv; rv = 0; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; @@ -1653,7 +1911,7 @@ if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; - for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next) { + for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; @@ -1675,7 +1933,7 @@ * add or update "delete" records if an active filter * is now inactive */ - for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next) + for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { @@ -1727,7 +1985,7 @@ if (!delta) pmc->sfcount[sfmode]++; err = 0; - for (i=0; isfcount[sfmode]--; - for (j=0; jsfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST @@ -1753,10 +2011,9 @@ #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ - pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; + pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv; in_dev->mr_ifc_count = pmc->crcount; - for (psf=pmc->sources; psf; psf = psf->sf_next) + for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { @@ -1771,12 +2028,12 @@ { struct ip_sf_list *psf, *nextpsf; - for (psf=pmc->tomb; psf; psf=nextpsf) { + for (psf = pmc->tomb; psf; psf = nextpsf) { nextpsf = psf->sf_next; kfree(psf); } pmc->tomb = NULL; - for (psf=pmc->sources; psf; psf=nextpsf) { + for (psf = pmc->sources; psf; psf = nextpsf) { nextpsf = psf->sf_next; kfree(psf); } @@ -1786,30 +2043,28 @@ pmc->sfcount[MCAST_EXCLUDE] = 1; } - -/* - * Join a multicast group +/* Join a multicast group */ -int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) + +int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { - int err; __be32 addr = imr->imr_multiaddr.s_addr; - struct ip_mc_socklist *iml = NULL, *i; + struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; + int err; + + ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; - rtnl_lock(); - in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { - iml = NULL; err = -ENODEV; goto done; } @@ -1826,7 +2081,7 @@ if (count >= sysctl_igmp_max_memberships) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); - if (iml == NULL) + if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); @@ -1837,7 +2092,6 @@ ip_mc_inc_group(in_dev, addr); err = 0; done: - rtnl_unlock(); return err; } EXPORT_SYMBOL(ip_mc_join_group); @@ -1848,7 +2102,7 @@ struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; - if (psf == NULL) { + if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); @@ -1862,10 +2116,6 @@ return err; } -/* - * Ask a socket to leave a group. - */ - int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); @@ -1877,7 +2127,8 @@ u32 ifindex; int ret = -EADDRNOTAVAIL; - rtnl_lock(); + ASSERT_RTNL(); + in_dev = ip_mc_find_dev(net, imr); if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) { ret = -ENODEV; @@ -1902,7 +2153,6 @@ if (in_dev) ip_mc_dec_group(in_dev, group); - rtnl_unlock(); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); @@ -1910,7 +2160,6 @@ return 0; } out: - rtnl_unlock(); return ret; } EXPORT_SYMBOL(ip_mc_leave_group); @@ -1932,7 +2181,7 @@ if (!ipv4_is_multicast(addr)) return -EINVAL; - rtnl_lock(); + ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; @@ -1974,7 +2223,7 @@ if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; - for (i=0; isl_count; i++) { + for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) @@ -1993,7 +2242,7 @@ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); - for (j=i+1; jsl_count; j++) + for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; @@ -2019,7 +2268,7 @@ newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { - for (i=0; isl_count; i++) + for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); @@ -2029,7 +2278,7 @@ psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ - for (i=0; isl_count; i++) { + for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) @@ -2037,7 +2286,7 @@ } if (rv == 0) /* address already there is an error */ goto done; - for (j=psl->sl_count-1; j>=i; j--) + for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; @@ -2046,9 +2295,8 @@ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: - rtnl_unlock(); if (leavegroup) - return ip_mc_leave_group(sk, &imr); + err = ip_mc_leave_group(sk, &imr); return err; } @@ -2070,7 +2318,7 @@ msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; - rtnl_lock(); + ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; @@ -2132,7 +2380,6 @@ pmc->sfmode = msf->imsf_fmode; err = 0; done: - rtnl_unlock(); if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; @@ -2150,11 +2397,11 @@ struct ip_sf_socklist *psl; struct net *net = sock_net(sk); + ASSERT_RTNL(); + if (!ipv4_is_multicast(addr)) return -EINVAL; - rtnl_lock(); - imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; @@ -2175,7 +2422,6 @@ goto done; msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); - rtnl_unlock(); if (!psl) { len = 0; count = 0; @@ -2194,7 +2440,6 @@ return -EFAULT; return 0; done: - rtnl_unlock(); return err; } @@ -2208,6 +2453,8 @@ struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; + ASSERT_RTNL(); + psin = (struct sockaddr_in *)&gsf->gf_group; if (psin->sin_family != AF_INET) return -EINVAL; @@ -2215,8 +2462,6 @@ if (!ipv4_is_multicast(addr)) return -EINVAL; - rtnl_lock(); - err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { @@ -2228,7 +2473,6 @@ goto done; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); - rtnl_unlock(); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; @@ -2236,7 +2480,7 @@ copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) { return -EFAULT; } - for (i=0; isl_count; i++) { + for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } @@ -2307,7 +2550,7 @@ struct ip_mc_socklist *iml; struct net *net = sock_net(sk); - if (inet->mc_list == NULL) + if (!inet->mc_list) return; rtnl_lock(); @@ -2317,7 +2560,7 @@ inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); - if (in_dev != NULL) + if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); @@ -2327,21 +2570,34 @@ } /* called with rcu_read_lock() */ -int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 proto) +int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; + struct ip_mc_list __rcu **mc_hash; struct ip_sf_list *psf; int rv = 0; - for_each_pmc_rcu(in_dev, im) { - if (im->multiaddr == mc_addr) - break; + mc_hash = rcu_dereference(in_dev->mc_hash); + if (mc_hash) { + u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG); + + for (im = rcu_dereference(mc_hash[hash]); + im != NULL; + im = rcu_dereference(im->next_hash)) { + if (im->multiaddr == mc_addr) + break; + } + } else { + for_each_pmc_rcu(in_dev, im) { + if (im->multiaddr == mc_addr) + break; + } } if (im && proto == IPPROTO_IGMP) { rv = 1; } else if (im) { if (src_addr) { - for (psf=im->sources; psf; psf=psf->sf_next) { + for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } @@ -2463,7 +2719,7 @@ querier = "NONE"; #endif - if (rcu_dereference(state->in_dev->mc_list) == im) { + if (rcu_access_pointer(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } @@ -2521,13 +2777,13 @@ for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); - if (unlikely(idev == NULL)) + if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); - if (likely(im != NULL)) { + if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; - if (likely(psf != NULL)) { + if (likely(psf)) { state->im = im; state->idev = idev; break; @@ -2597,7 +2853,7 @@ __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); - if (likely(state->im != NULL)) { + if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } @@ -2612,11 +2868,7 @@ struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { - seq_printf(seq, - "%3s %6s " - "%10s %10s %6s %6s\n", "Idx", - "Device", "MCA", - "SRC", "INC", "EXC"); + seq_puts(seq, "Idx Device MCA SRC INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s 0x%08x " @@ -2654,6 +2906,7 @@ static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; + int err; pde = proc_create("igmp", S_IRUGO, net->proc_net, &igmp_mc_seq_fops); if (!pde) @@ -2662,8 +2915,18 @@ &igmp_mcf_seq_fops); if (!pde) goto out_mcfilter; + err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, + SOCK_DGRAM, 0, net); + if (err < 0) { + pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", + err); + goto out_sock; + } + return 0; +out_sock: + remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: @@ -2674,15 +2937,54 @@ { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); + inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; +#endif -int __init igmp_mc_proc_init(void) +static int igmp_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) { - return register_pernet_subsys(&igmp_net_ops); + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct in_device *in_dev; + + switch (event) { + case NETDEV_RESEND_IGMP: + in_dev = __in_dev_get_rtnl(dev); + if (in_dev) + ip_mc_rejoin_groups(in_dev); + break; + default: + break; + } + return NOTIFY_DONE; } + +static struct notifier_block igmp_notifier = { + .notifier_call = igmp_netdev_event, +}; + +int __init igmp_mc_init(void) +{ +#if defined(CONFIG_PROC_FS) + int err; + + err = register_pernet_subsys(&igmp_net_ops); + if (err) + return err; + err = register_netdevice_notifier(&igmp_notifier); + if (err) + goto reg_notif_fail; + return 0; + +reg_notif_fail: + unregister_pernet_subsys(&igmp_net_ops); + return err; +#else + return register_netdevice_notifier(&igmp_notifier); #endif +}