From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jarek Poplawski Subject: Re: rib_trie / Fix inflate_threshold_root. Now=15 size=11 bits Date: Sun, 28 Jun 2009 23:36:02 +0200 Message-ID: <20090628213602.GA4584@ami.dom.local> References: <19012.37515.146191.198843@robur.slu.se> <20090627192057.GA5041@ami.dom.local> <19015.20051.432572.460207@robur.slu.se> <20090628143511.GA20541@ami.dom.local> <4A478D02.10805@itcare.pl> <4A4790C3.508@itcare.pl> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-2 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Robert Olsson , Robert Olsson , "Jorge Boncompte [DTI2]" , Eric Dumazet , Robert Olsson , Linux Network Development list To: =?iso-8859-2?Q?Pawe=B3?= Staszewski , David Miller Return-path: Received: from mail-bw0-f213.google.com ([209.85.218.213]:49788 "EHLO mail-bw0-f213.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751018AbZF1Vg2 (ORCPT ); Sun, 28 Jun 2009 17:36:28 -0400 Received: by bwz9 with SMTP id 9so2938634bwz.37 for ; Sun, 28 Jun 2009 14:36:30 -0700 (PDT) Content-Disposition: inline In-Reply-To: <4A4790C3.508@itcare.pl> Sender: netdev-owner@vger.kernel.org List-ID: To David Miller: since among patches tested negatively by Pawel are current 2 fixes from 2.6.31-rc, I hope they weren't sent to -stable yet. Otherwise, please withdraw them until they are tested alone. Thanks. To Pawel: On Sun, Jun 28, 2009 at 05:48:19PM +0200, Pawe=B3 Staszewski wrote: > > After apply this patch something is wrong > > Traffic is not forwarded > no info in dmesg / no info from bgp > and also i can't connect to bgpd process > > I revert kernel to past version with first Jarek patch > Since checking this can take time I attach here a patch with only changes which are currently in 2.6.31-rc. Of course, this part can be broken as well, so it's up to you: if you could try it with caution somewhere it would be very helpful; otherwise don't bother. It could be applied to 2.6.29 with or without this currently working patch. Thanks, Jarek P. --- (for 2.6.29.x, .28 or .27) diff -Nurp a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c --- a/net/ipv4/fib_trie.c 2009-06-27 20:25:06.000000000 +0200 +++ b/net/ipv4/fib_trie.c 2009-06-28 23:06:02.000000000 +0200 @@ -123,6 +123,7 @@ struct tnode { union { struct rcu_head rcu; struct work_struct work; + struct tnode *tnode_free; }; struct node *child[0]; }; @@ -161,6 +162,8 @@ static void tnode_put_child_reorg(struct static struct node *resize(struct trie *t, struct tnode *tn); static struct tnode *inflate(struct trie *t, struct tnode *tn); static struct tnode *halve(struct trie *t, struct tnode *tn); +/* tnodes to free after resize(); protected by RTNL */ +static struct tnode *tnode_free_head; =20 static struct kmem_cache *fn_alias_kmem __read_mostly; static struct kmem_cache *trie_leaf_kmem __read_mostly; @@ -385,6 +388,24 @@ static inline void tnode_free(struct tno call_rcu(&tn->rcu, __tnode_free_rcu); } =20 +static void tnode_free_safe(struct tnode *tn) +{ + BUG_ON(IS_LEAF(tn)); + tn->tnode_free =3D tnode_free_head; + tnode_free_head =3D tn; +} + +static void tnode_free_flush(void) +{ + struct tnode *tn; + + while ((tn =3D tnode_free_head)) { + tnode_free_head =3D tn->tnode_free; + tn->tnode_free =3D NULL; + tnode_free(tn); + } +} + static struct leaf *leaf_new(void) { struct leaf *l =3D kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); @@ -495,7 +516,7 @@ static struct node *resize(struct trie * =20 /* No children */ if (tn->empty_children =3D=3D tnode_child_length(tn)) { - tnode_free(tn); + tnode_free_safe(tn); return NULL; } /* One child */ @@ -509,7 +530,7 @@ static struct node *resize(struct trie * =20 /* compress one level */ node_set_parent(n, NULL); - tnode_free(tn); + tnode_free_safe(tn); return n; } /* @@ -670,7 +691,7 @@ static struct node *resize(struct trie * /* compress one level */ =20 node_set_parent(n, NULL); - tnode_free(tn); + tnode_free_safe(tn); return n; } =20 @@ -756,7 +777,7 @@ static struct tnode *inflate(struct trie put_child(t, tn, 2*i, inode->child[0]); put_child(t, tn, 2*i+1, inode->child[1]); =20 - tnode_free(inode); + tnode_free_safe(inode); continue; } =20 @@ -801,9 +822,9 @@ static struct tnode *inflate(struct trie put_child(t, tn, 2*i, resize(t, left)); put_child(t, tn, 2*i+1, resize(t, right)); =20 - tnode_free(inode); + tnode_free_safe(inode); } - tnode_free(oldtnode); + tnode_free_safe(oldtnode); return tn; nomem: { @@ -885,7 +906,7 @@ static struct tnode *halve(struct trie * put_child(t, newBinNode, 1, right); put_child(t, tn, i/2, resize(t, newBinNode)); } - tnode_free(oldtnode); + tnode_free_safe(oldtnode); return tn; nomem: { @@ -983,12 +1004,14 @@ fib_find_node(struct trie *t, u32 key) return NULL; } =20 -static struct node *trie_rebalance(struct trie *t, struct tnode *tn) +static void trie_rebalance(struct trie *t, struct tnode *tn) { int wasfull; - t_key cindex, key =3D tn->key; + t_key cindex, key; struct tnode *tp; =20 + key =3D tn->key; + while (tn !=3D NULL && (tp =3D node_parent((struct node *)tn)) !=3D N= ULL) { cindex =3D tkey_extract_bits(key, tp->pos, tp->bits); wasfull =3D tnode_full(tp, tnode_get_child(tp, cindex)); @@ -998,6 +1021,7 @@ static struct node *trie_rebalance(struc (struct node *)tn, wasfull); =20 tp =3D node_parent((struct node *) tn); + tnode_free_flush(); if (!tp) break; tn =3D tp; @@ -1007,7 +1031,10 @@ static struct node *trie_rebalance(struc if (IS_TNODE(tn)) tn =3D (struct tnode *)resize(t, (struct tnode *)tn); =20 - return (struct node *)tn; + rcu_assign_pointer(t->trie, (struct node *)tn); + tnode_free_flush(); + + return; } =20 /* only used from updater-side */ @@ -1155,7 +1182,7 @@ static struct list_head *fib_insert_node =20 /* Rebalance the trie */ =20 - rcu_assign_pointer(t->trie, trie_rebalance(t, tp)); + trie_rebalance(t, tp); done: return fa_head; } @@ -1575,7 +1602,7 @@ static void trie_leaf_remove(struct trie if (tp) { t_key cindex =3D tkey_extract_bits(l->key, tp->pos, tp->bits); put_child(t, (struct tnode *)tp, cindex, NULL); - rcu_assign_pointer(t->trie, trie_rebalance(t, tp)); + trie_rebalance(t, tp); } else rcu_assign_pointer(t->trie, NULL); =20