diff options
author | Eric Dumazet <eric.dumazet@gmail.com> | 2011-04-27 22:56:07 +0000 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2011-05-02 15:26:28 -0700 |
commit | e67f88dd12f610da98ca838822f2c9b4e7c6100e (patch) | |
tree | 6cf01b794984aaad97b6e6ff6e5103bc48d68191 /net/core/rtnetlink.c | |
parent | dcfd9cdc1222f14d6180514e533289493a0716fb (diff) | |
download | op-kernel-dev-e67f88dd12f610da98ca838822f2c9b4e7c6100e.zip op-kernel-dev-e67f88dd12f610da98ca838822f2c9b4e7c6100e.tar.gz |
net: dont hold rtnl mutex during netlink dump callbacks
Four years ago, Patrick made a change to hold rtnl mutex during netlink
dump callbacks.
I believe it was a wrong move. This slows down concurrent dumps, making
good old /proc/net/ files faster than rtnetlink in some situations.
This occurred to me because one "ip link show dev ..." was _very_ slow
on a workload adding/removing network devices in background.
All dump callbacks are able to use RCU locking now, so this patch does
roughly a revert of commits :
1c2d670f366 : [RTNETLINK]: Hold rtnl_mutex during netlink dump callbacks
6313c1e0992 : [RTNETLINK]: Remove unnecessary locking in dump callbacks
This let writers fight for rtnl mutex and readers going full speed.
It also takes care of phonet : phonet_route_get() is now called from rcu
read section. I renamed it to phonet_route_get_rcu()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Remi Denis-Courmont <remi.denis-courmont@nokia.com>
Acked-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core/rtnetlink.c')
-rw-r--r-- | net/core/rtnetlink.c | 12 |
1 files changed, 5 insertions, 7 deletions
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d7c4bb4..29633125 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1007,10 +1007,11 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) s_h = cb->args[0]; s_idx = cb->args[1]; + rcu_read_lock(); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { if (idx < s_idx) goto cont; if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, @@ -1023,6 +1024,7 @@ cont: } } out: + rcu_read_unlock(); cb->args[1] = idx; cb->args[0] = h; @@ -1879,7 +1881,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) int min_len; int family; int type; - int err; type = nlh->nlmsg_type; if (type > RTM_MAX) @@ -1906,11 +1907,8 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (dumpit == NULL) return -EOPNOTSUPP; - __rtnl_unlock(); rtnl = net->rtnl; - err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL); - rtnl_lock(); - return err; + return netlink_dump_start(rtnl, skb, nlh, dumpit, NULL); } memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *))); @@ -1980,7 +1978,7 @@ static int __net_init rtnetlink_net_init(struct net *net) { struct sock *sk; sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX, - rtnetlink_rcv, &rtnl_mutex, THIS_MODULE); + rtnetlink_rcv, NULL, THIS_MODULE); if (!sk) return -ENOMEM; net->rtnl = sk; |