bridge: select IP addr as source addr for querier
Subsystems (3)
PATCH v3 1/3 bridge: select IP addr as source addr for querier
From: Cong Wang <[email protected]>
Quote from Adam:
"If it is believed that the use of 0.0.0.0
as the IP address is what is causing strange behaviour on other devices then is there a good reason that a bridge rather than a router shouldn't be the active querier? If not then using the bridge IP address and having the querier enabled by default may be a reasonable solution (provided that our querier obeys the election rules and shuts up if it sees a query from a lower IP address that isn't 0.0.0.0). Just because a device is the elected querier for IGMP doesn't appear to mean it is required to perform any other routing functions."
And introduce a new troggle for it, by default we still use 0.0.0.0 as src IP.
---
v2: introduce a new troggle
net/bridge/br_multicast.c | 5 ++++- net/bridge/br_private.h | 1 + net/bridge/br_sysfs_br.c | 25 +++++++++++++++++++++++++ 3 files changed, 30 insertions(+), 1 deletions(-)
net/bridge/br_multicast.c +4 -1
@@ -23,6 +23,7 @@#include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> +#include <linux/inetdevice.h> #include <net/ip.h> #if IS_ENABLED (CONFIG_IPV6 )#include <net/ipv6.h>
@@ -381,7 +382,8 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, iph->frag_off =htons (IP_DF ); iph->ttl =1 ; iph->protocol =IPPROTO_IGMP ; - iph->saddr =0 ; + iph->saddr = br->multicast_query_zero_source ? +0 :inet_select_addr (br->dev,0 ,RT_SCOPE_LINK ); iph->daddr =htonl (INADDR_ALLHOSTS_GROUP ); ((u8 *)&iph[1 ])[0 ] =IPOPT_RA ; ((u8 *)&iph[1 ])[1 ] =4 ;
@@ -1618,6 +1620,7 @@ void br_multicast_init(struct net_bridge *br) br->multicast_router =1 ; br->multicast_querier =0 ; + br->multicast_query_zero_source =1 ; br->multicast_last_member_count =2 ; br->multicast_startup_query_count =2 ;
net/bridge/br_private.h +1 -0
@@ -249,6 +249,7 @@ struct net_bridge u8 multicast_disabled:1; u8 multicast_querier:1; + u8 multicast_query_zero_source:1;u32 hash_elasticity;u32 hash_max;
net/bridge/br_sysfs_br.c +25 -0
@@ -375,6 +375,30 @@ static ssize_t store_multicast_snooping(struct device *d, static DEVICE_ATTR(multicast_snooping, S_IRUGO | S_IWUSR, show_multicast_snooping, store_multicast_snooping); +static ssize_t show_multicast_query_zero_source (struct device *d, +struct device_attribute *attr, +char *buf) +{ +struct net_bridge *br =to_bridge (d); +return sprintf (buf,"%d\n" , br->multicast_query_zero_source); +} + +static int set_query_zero_source (struct net_bridge *br,unsigned long val) +{ + br->multicast_query_zero_source = !!val; +return 0 ; +} + +static ssize_t store_multicast_query_zero_source (struct device *d, +struct device_attribute *attr, +const char *buf,size_t len) +{ +return store_bridge_parm (d, buf, len, set_query_zero_source); +} +static DEVICE_ATTR(multicast_query_zero_source, S_IRUGO | S_IWUSR, + show_multicast_query_zero_source, + store_multicast_query_zero_source); +static ssize_t show_multicast_querier (struct device *d,struct device_attribute *attr,char *buf)
@@ -734,6 +758,7 @@ static struct attribute *bridge_attrs[] = { &dev_attr_multicast_router.attr, &dev_attr_multicast_snooping.attr, &dev_attr_multicast_querier.attr, + &dev_attr_multicast_query_zero_source.attr, &dev_attr_hash_elasticity.attr, &dev_attr_hash_max.attr, &dev_attr_multicast_last_member_count.attr,
Signature · 1 line
1.7.7.6
PATCH v3 2/3 bridge: only expire the mdb entry when query is received
From: Cong Wang <[email protected]>
Currently we arm the expire timer when the mdb entry is added, however, this causes problem when there is no querier sent out after that.
So we should only arm the timer when a corresponding query is received, as suggested by Herbert.
And "if there is no querier then group subscriptions shouldn't expire. There has to be at least one querier in the network for this thing to work. Otherwise it just degenerates into a non-snooping switch, which is OK."
---
v3: fix the code in br_multicast_leave_group()
v2: add a flag to check if timer is fired or not
net/bridge/br_multicast.c | 21 ++++++++++++--------- net/bridge/br_private.h | 1 + 2 files changed, 13 insertions(+), 9 deletions(-)
net/bridge/br_multicast.c +12 -9
@@ -617,8 +617,6 @@ rehash: mp->br = br; mp->addr = *group; -setup_timer (&mp->timer, br_multicast_group_expired, - (unsigned long )mp);hlist_add_head_rcu (&mp->hlist[mdb->ver], &mdb->mhash[hash]); mdb->size++;
@@ -656,7 +654,6 @@ static int br_multicast_add_group(struct net_bridge *br,struct net_bridge_mdb_entry *mp;struct net_bridge_port_group *p;struct net_bridge_port_group __rcu **pp; -unsigned long now = jiffies;int err;spin_lock (&br->multicast_lock);
@@ -671,7 +668,6 @@ static int br_multicast_add_group(struct net_bridge *br,if (!port) { mp->mglist = true; -mod_timer (&mp->timer, now + br->multicast_membership_interval); goto out; }
@@ -679,7 +675,7 @@ static int br_multicast_add_group(struct net_bridge *br, (p =mlock_dereference (*pp, br)) !=NULL ; pp = &p->next) {if (p->port == port) - goto found; + goto out;if ((unsigned long )p->port < (unsigned long )port)break ; }
@@ -690,8 +686,6 @@ static int br_multicast_add_group(struct net_bridge *br,rcu_assign_pointer (*pp, p);br_mdb_notify (br->dev, port, group,RTM_NEWMDB ); -found: -mod_timer (&p->timer, now + br->multicast_membership_interval); out: err =0 ;
@@ -1131,6 +1125,10 @@ static int br_ip4_multicast_query(struct net_bridge *br,if (!mp) goto out; +setup_timer (&mp->timer, br_multicast_group_expired, (unsigned long )mp); +mod_timer (&mp->timer, now + br->multicast_membership_interval); + mp->timer_armed = true; + max_delay *= br->multicast_last_member_count; if (mp->mglist &&
@@ -1205,6 +1203,10 @@ static int br_ip6_multicast_query(struct net_bridge *br,if (!mp) goto out; +setup_timer (&mp->timer, br_multicast_group_expired, (unsigned long )mp); +mod_timer (&mp->timer, now + br->multicast_membership_interval); + mp->timer_armed = true; + max_delay *= br->multicast_last_member_count; if (mp->mglist && (timer_pending(&mp->timer) ?
@@ -1263,7 +1265,7 @@ static void br_multicast_leave_group(struct net_bridge *br,call_rcu_bh (&p->rcu, br_multicast_free_pg);br_mdb_notify (br->dev, port, group,RTM_DELMDB ); -if (!mp->ports && !mp->mglist && +if (!mp->ports && !mp->mglist && mp->timer_armed &&netif_running (br->dev))mod_timer (&mp->timer, jiffies); }
@@ -1275,7 +1277,7 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval;if (!port) { -if (mp->mglist && +if (mp->mglist && mp->timer_armed && (timer_pending (&mp->timer) ?time_after (mp->timer.expires, time) :try_to_del_timer_sync (&mp->timer) >=0 )) {
@@ -1674,6 +1676,7 @@ void br_multicast_stop(struct net_bridge *br)hlist_for_each_entry_safe (mp, n, &mdb->mhash[i], hlist[ver]) {del_timer (&mp->timer); + mp->timer_armed = false;call_rcu_bh (&mp->rcu, br_multicast_free_group); } }
net/bridge/br_private.h +1 -0
@@ -112,6 +112,7 @@ struct net_bridge_mdb_entrystruct timer_list timer;struct br_ip addr;bool mglist; +bool timer_armed; };struct net_bridge_mdb_htable
Signature · 1 line
1.7.7.6
Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
net/bridge/br_multicast.c static void br_multicast_leave_group(struct net_bridge *br, · line 1283
Quoted 10 lines · Cong Wang
net/bridge/br_multicast.c +1
-1@@ -1275,7 +1277,7 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval;if (!port) { -if (mp->mglist && +if (mp->mglist && mp->timer_armed && (timer_pending (&mp->timer) ?time_after (mp->timer.expires, time) :try_to_del_timer_sync (&mp->timer) >=0 )) {
This whole section of code should now be removed since we're now only arming the timer in response to a query to that group. Of course if we were the querier and sent out a query here then you'd need to simulate the reception of a query.
Cheers,
Signature · 3 lines
Email: Herbert Xu <[email protected]> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
Quoted 5 lines · Herbert Xu
Quoted 4 lines · Cong Wang
net/bridge/br_multicast.c +0
-0@@ -1275,7 +1277,7 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval;
Quoted 11 lines
net/bridge/br_multicast.c static void br_multicast_leave_group(struct net_bridge *br, · line 1283
Quoted 6 lines
net/bridge/br_multicast.c +1
-1if (!port) { -if (mp->mglist && +if (mp->mglist && mp->timer_armed && (timer_pending (&mp->timer) ?time_after (mp->timer.expires, time) :try_to_del_timer_sync (&mp->timer) >=0 )) {This whole section of code should now be removed since we're now only arming the timer in response to a query to that group. Of course if we were the querier and sent out a query here then you'd need to simulate the reception of a query.
Hmm, this piece of code is checking if bridge itself is in the mdb entry and if it just receives a leave, which seems still necessary... What am I missing?
Thanks!
Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
Quoted 18 lines · Cong Wang
Quoted 5 lines · Herbert Xu
Quoted 4 lines · Cong Wang
net/bridge/br_multicast.c +0
-0@@ -1275,7 +1277,7 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval;Quoted 11 lines
net/bridge/br_multicast.c static void br_multicast_leave_group(struct net_bridge *br, · line 1283
Quoted 6 lines
net/bridge/br_multicast.c +1
-1if (!port) { -if (mp->mglist && +if (mp->mglist && mp->timer_armed && (timer_pending (&mp->timer) ?time_after (mp->timer.expires, time) :try_to_del_timer_sync (&mp->timer) >=0 )) {This whole section of code should now be removed since we're now only arming the timer in response to a query to that group. Of course if we were the querier and sent out a query here then you'd need to simulate the reception of a query.
Quoted 3 lines
Hmm, this piece of code is checking if bridge itself is in the mdb entry and if it just receives a leave, which seems still necessary... What am I missing?
I think I quoted the wrong hunk in the patch, I meant the code that arms the timer should no longer be in the leave_group function unless we just sent a query ourselves (and in that case the expiration should also be adjusted accordingly).
Cheers,
Signature · 3 lines
Email: Herbert Xu <[email protected]> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
Quoted 5 lines · Herbert Xu
I think I quoted the wrong hunk in the patch, I meant the code that arms the timer should no longer be in the
leave_groupfunction unless we just sent a query ourselves (and in that case the expiration should also be adjusted accordingly).
Is the following patch what you meant?
net/bridge/br_multicast.c +0 -0
@@ -1302,22 +1302,6 @@ static void br_multicast_leave_group(struct
net_bridge *br,
goto out;
}- for (p = mlock_dereference(mp->ports, br);
- p != NULL;
- p = mlock_dereference(p->next, br)) {
- if (p->port != port)
- continue;
-
- if (!hlist_unhashed(&p->mglist) &&
- (timer_pending(&p->timer) ?
- time_after(p->timer.expires, time) :
- try_to_del_timer_sync(&p->timer) >= 0)) {
- mod_timer(&p->timer, time);
- }
-
- break;
- }
-
out:
spin_unlock(&br->multicast_lock);
}
Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
Quoted 8 lines · Cong Wang
Quoted 5 lines · Herbert Xu
I think I quoted the wrong hunk in the patch, I meant the code that arms the timer should no longer be in the
leave_groupfunction unless we just sent a query ourselves (and in that case the expiration should also be adjusted accordingly).Is the following patch what you meant?
Right, but also add the corresponding timers in case we send a group-specific query since that won't loop back to ourselves.
Thanks,
Signature · 3 lines
Email: Herbert Xu <[email protected]> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
Quoted 8 lines · Herbert Xu
Quoted 7 lines · Cong Wang
Quoted 5 lines · Herbert Xu
I think I quoted the wrong hunk in the patch, I meant the code that arms the timer should no longer be in the
leave_groupfunction unless we just sent a query ourselves (and in that case the expiration should also be adjusted accordingly).
Quoted 4 lines
Quoted 1 line
Is the following patch what you meant?
Right, but also add the corresponding timers in case we send a group-specific query since that won't loop back to ourselves.
Ok, then something like below , it is a delta patch, the first piece should go to patch 3/3.
net/bridge/br_multicast.c +0 -0
@@ -1263,6 +1263,24 @@ static void br_multicast_leave_group(struct
net_bridge *br,
br->multicast_query_interval;
mod_timer(port ? &port->multicast_query_timer :
&br->multicast_query_timer, time);
+
+ time = jiffies + br->multicast_last_member_count *
+ br->multicast_last_member_interval;
+ for (p = mlock_dereference(mp->ports, br);
+ p != NULL;
+ p = mlock_dereference(p->next, br)) {
+ if (p->port != port)
+ continue;
+
+ if (!hlist_unhashed(&p->mglist) &&
+ (timer_pending(&p->timer) ?
+ time_after(p->timer.expires, time) :
+ try_to_del_timer_sync(&p->timer) >= 0)) {
+ mod_timer(&p->timer, time);
+ }
+
+ break;
+ }
}
if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
@@ -1298,24 +1316,6 @@ static void br_multicast_leave_group(struct net_bridge *br,
try_to_del_timer_sync(&mp->timer) >= 0)) {
mod_timer(&mp->timer, time);
}
-
- goto out;
- }
-
- for (p = mlock_dereference(mp->ports, br);
- p != NULL;
- p = mlock_dereference(p->next, br)) {
- if (p->port != port)
- continue;
-
- if (!hlist_unhashed(&p->mglist) &&
- (timer_pending(&p->timer) ?
- time_after(p->timer.expires, time) :
- try_to_del_timer_sync(&p->timer) >= 0)) {
- mod_timer(&p->timer, time);
- }
-
- break;
}
out:
Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
Quoted 9 lines · Cong Wang
Quoted 8 lines · Herbert Xu
Quoted 7 lines · Cong Wang
Quoted 5 lines · Herbert Xu
I think I quoted the wrong hunk in the patch, I meant the code that arms the timer should no longer be in the
leave_groupfunction unless we just sent a query ourselves (and in that case the expiration should also be adjusted accordingly).
Quoted 7 lines
Quoted 4 lines
Quoted 1 line
Is the following patch what you meant?
Right, but also add the corresponding timers in case we send a group-specific query since that won't loop back to ourselves.
Ok, then something like below , it is a delta patch, the first piece should go to patch 3/3.
Yes this looks about right. BTW, for the groups-epcific queries you should use the leave timeout values and not the startup timeout values.
Thanks,
Signature · 3 lines
Email: Herbert Xu <[email protected]> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
Quoted 5 lines · Herbert Xu
Yes this looks about right. BTW, for the groups-epcific queries you should use the leave timeout values and not the startup timeout values.
Right, something like below:
net/bridge/br_multicast.c +0 -0
@@ -1252,20 +1252,13 @@ static void br_multicast_leave_group(struct
net_bridge *br,
if (br->multicast_querier &&
!timer_pending(&br->multicast_querier_timer)) {
- u32 sent;
-
__br_multicast_send_query(br, port, &mp->addr);- sent = port ? port->multicast_startup_queries_sent :
- br->multicast_startup_queries_sent;
- time = jiffies;
- time += sent < br->multicast_startup_query_count ?
- br->multicast_startup_query_interval :
- br->multicast_query_interval;
- mod_timer(port ? &port->multicast_query_timer :
- &br->multicast_query_timer, time);
time = jiffies + br->multicast_last_member_count *
br->multicast_last_member_interval;
+ mod_timer(port ? &port->multicast_query_timer :
+ &br->multicast_query_timer, time);
+
for (p = mlock_dereference(mp->ports, br);
p != NULL;
p = mlock_dereference(p->next, br)) {Re: [Patch net-next v3 2/3] bridge: only expire the mdb entry when query is received
Quoted 8 lines · Cong Wang
Quoted 5 lines · Herbert Xu
Yes this looks about right. BTW, for the groups-epcific queries you should use the leave timeout values and not the startup timeout values.
Right, something like below:
Yes thanks!
Signature · 3 lines
Email: Herbert Xu <[email protected]> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
PATCH v3 3/3 bridge: send query as soon as leave is received
In reply to Cong WangFrom: Cong Wang <[email protected]>
Send a non-general query when leave is received, if the user marks it as a querier.
---
v3: use non-general query
v2: only send query to the port received leave
net/bridge/br_multicast.c | 15 +++++++++++++++ 1 files changed, 15 insertions(+), 0 deletions(-)
net/bridge/br_multicast.c +15 -0
@@ -1250,6 +1250,21 @@ static void br_multicast_leave_group(struct net_bridge *br,if (!mp) goto out; +if (br->multicast_querier && + !timer_pending (&br->multicast_querier_timer)) { +u32 sent; + +__br_multicast_send_query (br, port, &mp->addr); + sent = port ? port->multicast_startup_queries_sent : + br->multicast_startup_queries_sent; + time = jiffies; + time += sent < br->multicast_startup_query_count ? + br->multicast_startup_query_interval : + br->multicast_query_interval; +mod_timer (port ? &port->multicast_query_timer : + &br->multicast_query_timer, time); + } +if (port && (port->flags &BR_MULTICAST_FAST_LEAVE )) {struct net_bridge_port_group __rcu **pp;