From mboxrd@z Thu Jan 1 00:00:00 1970 From: Patrick McHardy Subject: [PATCH 5/9] ipv4: ipmr: move unres_queue and timer to per-namespace data Date: Tue, 13 Apr 2010 17:03:19 +0200 Message-ID: <1271171003-11901-6-git-send-email-kaber@trash.net> References: <1271171003-11901-1-git-send-email-kaber@trash.net> Cc: netdev@vger.kernel.org To: davem@davemloft.net Return-path: Received: from stinky.trash.net ([213.144.137.162]:51255 "EHLO stinky.trash.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752342Ab0DMPD2 (ORCPT ); Tue, 13 Apr 2010 11:03:28 -0400 In-Reply-To: <1271171003-11901-1-git-send-email-kaber@trash.net> Sender: netdev-owner@vger.kernel.org List-ID: 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 --- include/net/netns/ipv4.h | 2 + net/ipv4/ipmr.c | 70 +++++++++++++++++++--------------------------- 2 files changed, 31 insertions(+), 41 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2764994..b15e518 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 9d4f6d1..d6aa65e 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) /* exhausted cache_array, show unresolved */ read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; + it->cache = &net->ipv4.mfc_unres_queue; it->ct = 0; spin_lock_bh(&mfc_unres_lock); - mfc = mfc_unres_queue; - while (mfc && !net_eq(mfc_net(mfc), net)) - mfc = mfc->next; + mfc = net->ipv4.mfc_unres_queue; if (mfc) return mfc; @@ -1892,7 +1879,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); - if (it->cache == &mfc_unres_queue) + if (it->cache == &net->ipv4.mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); else if (it->cache == net->ipv4.mfc_cache_array) read_unlock(&mrt_lock); @@ -1915,7 +1902,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) (unsigned long) mfc->mfc_origin, mfc->mfc_parent); - if (it->cache != &mfc_unres_queue) { + if (it->cache != &net->ipv4.mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->mfc_un.res.pkt, mfc->mfc_un.res.bytes, @@ -1992,6 +1979,9 @@ static int __net_init ipmr_net_init(struct net *net) goto fail_mfc_cache; } + setup_timer(&net->ipv4.ipmr_expire_timer, ipmr_expire_process, + (unsigned long)net); + #ifdef CONFIG_IP_PIMSM net->ipv4.mroute_reg_vif_num = -1; #endif @@ -2047,7 +2037,6 @@ int __init ip_mr_init(void) if (err) goto reg_pernet_fail; - setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); err = register_netdevice_notifier(&ip_mr_notifier); if (err) goto reg_notif_fail; @@ -2065,7 +2054,6 @@ add_proto_fail: unregister_netdevice_notifier(&ip_mr_notifier); #endif reg_notif_fail: - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ipmr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); -- 1.7.0.4