ipv4: ipmr: move unres_queue and timer to per-namespace data

The unres_queue is currently shared between all namespaces. Following patches
will additionally allow to create multiple multicast routing tables in each
namespace. Having a single shared queue for all these users seems to excessive,
move the queue and the cleanup timer to the per-namespace data to unshare it.

As a side-effect, this fixes a bug in the seq file iteration functions: the
first entry returned is always from the current namespace, entries returned
after that may belong to any namespace.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 31 insertions, 41 deletions

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2764994c9136..b15e518f952a 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -60,6 +60,8 @@ struct netns_ipv4 {
 
 #ifdef CONFIG_IP_MROUTE
         struct sock             *mroute_sk;
+        struct timer_list       ipmr_expire_timer;
+        struct mfc_cache        *mfc_unres_queue;
         struct mfc_cache        **mfc_cache_array;
         struct vif_device       *vif_table;
         int                     maxvif;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d4f6d1340a4..d6aa65e2b08f 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -80,8 +80,6 @@ static DEFINE_RWLOCK(mrt_lock);
 
 #define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL)
 
-static struct mfc_cache *mfc_unres_queue;               /* Queue of unresolved entries */
-
 /* Special spinlock for queue of unresolved entries */
 static DEFINE_SPINLOCK(mfc_unres_lock);
 
@@ -100,8 +98,6 @@ static int ipmr_cache_report(struct net *net,
                              struct sk_buff *pkt, vifi_t vifi, int assert);
 static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm);
 
-static struct timer_list ipmr_expire_timer;
-
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
 
 static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v)
@@ -364,25 +360,26 @@ static void ipmr_destroy_unres(struct mfc_cache *c)
 }
 
 
-/* Single timer process for all the unresolved queue. */
+/* Timer process for the unresolved queue. */
 
-static void ipmr_expire_process(unsigned long dummy)
+static void ipmr_expire_process(unsigned long arg)
 {
+        struct net *net = (struct net *)arg;
         unsigned long now;
         unsigned long expires;
         struct mfc_cache *c, **cp;
 
         if (!spin_trylock(&mfc_unres_lock)) {
-                mod_timer(&ipmr_expire_timer, jiffies+HZ/10);
+                mod_timer(&net->ipv4.ipmr_expire_timer, jiffies+HZ/10);
                 return;
         }
 
-        if (mfc_unres_queue == NULL)
+        if (net->ipv4.mfc_unres_queue == NULL)
                 goto out;
 
         now = jiffies;
         expires = 10*HZ;
-        cp = &mfc_unres_queue;
+        cp = &net->ipv4.mfc_unres_queue;
 
         while ((c=*cp) != NULL) {
                 if (time_after(c->mfc_un.unres.expires, now)) {
@@ -398,8 +395,8 @@ static void ipmr_expire_process(unsigned long dummy)
                 ipmr_destroy_unres(c);
         }
 
-        if (mfc_unres_queue != NULL)
-                mod_timer(&ipmr_expire_timer, jiffies + expires);
+        if (net->ipv4.mfc_unres_queue != NULL)
+                mod_timer(&net->ipv4.ipmr_expire_timer, jiffies + expires);
 
 out:
         spin_unlock(&mfc_unres_lock);
@@ -708,9 +705,8 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
         const struct iphdr *iph = ip_hdr(skb);
 
         spin_lock_bh(&mfc_unres_lock);
-        for (c=mfc_unres_queue; c; c=c->next) {
-                if (net_eq(mfc_net(c), net) &&
-                    c->mfc_mcastgrp == iph->daddr &&
+        for (c=net->ipv4.mfc_unres_queue; c; c=c->next) {
+                if (c->mfc_mcastgrp == iph->daddr &&
                     c->mfc_origin == iph->saddr)
                         break;
         }
@@ -751,10 +747,10 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
                 }
 
                 atomic_inc(&net->ipv4.cache_resolve_queue_len);
-                c->next = mfc_unres_queue;
-                mfc_unres_queue = c;
+                c->next = net->ipv4.mfc_unres_queue;
+                net->ipv4.mfc_unres_queue = c;
 
-                mod_timer(&ipmr_expire_timer, c->mfc_un.unres.expires);
+                mod_timer(&net->ipv4.ipmr_expire_timer, c->mfc_un.unres.expires);
         }
 
         /*
@@ -849,18 +845,17 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
          *      need to send on the frames and tidy up.
          */
         spin_lock_bh(&mfc_unres_lock);
-        for (cp = &mfc_unres_queue; (uc=*cp) != NULL;
+        for (cp = &net->ipv4.mfc_unres_queue; (uc=*cp) != NULL;
              cp = &uc->next) {
-                if (net_eq(mfc_net(uc), net) &&
-                    uc->mfc_origin == c->mfc_origin &&
+                if (uc->mfc_origin == c->mfc_origin &&
                     uc->mfc_mcastgrp == c->mfc_mcastgrp) {
                         *cp = uc->next;
                         atomic_dec(&net->ipv4.cache_resolve_queue_len);
                         break;
                 }
         }
-        if (mfc_unres_queue == NULL)
-                del_timer(&ipmr_expire_timer);
+        if (net->ipv4.mfc_unres_queue == NULL)
+                del_timer(&net->ipv4.ipmr_expire_timer);
         spin_unlock_bh(&mfc_unres_lock);
 
         if (uc) {
@@ -912,14 +907,9 @@ static void mroute_clean_tables(struct net *net)
                 struct mfc_cache *c, **cp;
 
                 spin_lock_bh(&mfc_unres_lock);
-                cp = &mfc_unres_queue;
+                cp = &net->ipv4.mfc_unres_queue;
                 while ((c = *cp) != NULL) {
-                        if (!net_eq(mfc_net(c), net)) {
-                                cp = &c->next;
-                                continue;
-                        }
                         *cp = c->next;
-
                         ipmr_destroy_unres(c);
                 }
                 spin_unlock_bh(&mfc_unres_lock);
@@ -1819,11 +1809,10 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
                                 return mfc;
         read_unlock(&mrt_lock);
 
-        it->cache = &mfc_unres_queue;
+        it->cache = &net->ipv4.mfc_unres_queue;
         spin_lock_bh(&mfc_unres_lock);
-        for (mfc = mfc_unres_queue; mfc; mfc = mfc->next)
-                if (net_eq(mfc_net(mfc), net) &&
-                    pos-- == 0)
+        for (mfc = net->ipv4.mfc_unres_queue; mfc; mfc = mfc->next)
+                if (pos-- == 0)
                         return mfc;
         spin_unlock_bh(&mfc_unres_lock);
 
@@ -1857,7 +1846,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
         if (mfc->next)
                 return mfc->next;
 
-        if (it->cache == &mfc_unres_queue)
+        if (it->cache == &net->ipv4.mfc_unres_queue)
                 goto end_of_list;
 
         BUG_ON(it->cache != net->ipv4.mfc_cache_array);
@@ -1870,13 +1859,11 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)