netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: David Miller <davem@davemloft.net>
Cc: Stephen Hemminger <shemminger@vyatta.com>, netdev@vger.kernel.org
Subject: [PATCH net-next-2.6] ipv6: use RCU to walk list of network devices
Date: Thu, 12 Nov 2009 04:34:30 +0100	[thread overview]
Message-ID: <4AFB8246.6060804@gmail.com> (raw)
In-Reply-To: <20091110175647.683253741@vyatta.com>

Stephen Hemminger a écrit :
> No longer need read_lock(&dev_base_lock), use RCU instead.
> This also needs to be optimized for large number of devices.
> 
> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>

I gave a look at your patch Stephen and found we need a new
next_net_device_rcu(struct net_device *dev) as well,
as next_net_device() is not RCU safe.

(followup patch is probably needed to use it in net/ipv4/igmp.c,
after commit 61fbab77a843d2e77232 : IPV4: use rcu to walk list of devices in IGMP)

We also can avoid taking references on inet6_dev structs.

[PATCH net-next-2.6] ipv6: use RCU to walk list of network devices

No longer need read_lock(&dev_base_lock), use RCU instead.
We also can avoid taking references on inet6_dev structs.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
 include/linux/netdevice.h |   10 +++++++
 net/ipv6/anycast.c        |   29 +++++++++-----------
 net/ipv6/mcast.c          |   51 ++++++++++++++++--------------------
 3 files changed, 47 insertions(+), 43 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 083b598..2734a67 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1093,6 +1093,16 @@ static inline struct net_device *next_net_device(struct net_device *dev)
 	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
 }
 
+static inline struct net_device *next_net_device_rcu(struct net_device *dev)
+{
+	struct list_head *lh;
+	struct net *net;
+
+	net = dev_net(dev);
+	lh = rcu_dereference(dev->dev_list.next);
+	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
+}
+
 static inline struct net_device *first_net_device(struct net *net)
 {
 	return list_empty(&net->dev_base_head) ? NULL :
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 2f00ca8..f1c74c8 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -431,9 +431,9 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq)
 	struct net *net = seq_file_net(seq);
 
 	state->idev = NULL;
-	for_each_netdev(net, state->dev) {
+	for_each_netdev_rcu(net, state->dev) {
 		struct inet6_dev *idev;
-		idev = in6_dev_get(state->dev);
+		idev = __in6_dev_get(state->dev);
 		if (!idev)
 			continue;
 		read_lock_bh(&idev->lock);
@@ -443,7 +443,6 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq)
 			break;
 		}
 		read_unlock_bh(&idev->lock);
-		in6_dev_put(idev);
 	}
 	return im;
 }
@@ -454,16 +453,15 @@ static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im
 
 	im = im->aca_next;
 	while (!im) {
-		if (likely(state->idev != NULL)) {
+		if (likely(state->idev != NULL))
 			read_unlock_bh(&state->idev->lock);
-			in6_dev_put(state->idev);
-		}
-		state->dev = next_net_device(state->dev);
+
+		state->dev = next_net_device_rcu(state->dev);
 		if (!state->dev) {
 			state->idev = NULL;
 			break;
 		}
-		state->idev = in6_dev_get(state->dev);
+		state->idev = __in6_dev_get(state->dev);
 		if (!state->idev)
 			continue;
 		read_lock_bh(&state->idev->lock);
@@ -482,29 +480,30 @@ static struct ifacaddr6 *ac6_get_idx(struct seq_file *seq, loff_t pos)
 }
 
 static void *ac6_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(dev_base_lock)
+	__acquires(RCU)
 {
-	read_lock(&dev_base_lock);
+	rcu_read_lock();
 	return ac6_get_idx(seq, *pos);
 }
 
 static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct ifacaddr6 *im;
-	im = ac6_get_next(seq, v);
+	struct ifacaddr6 *im = ac6_get_next(seq, v);
+
 	++*pos;
 	return im;
 }
 
 static void ac6_seq_stop(struct seq_file *seq, void *v)
-	__releases(dev_base_lock)
+	__releases(RCU)
 {
 	struct ac6_iter_state *state = ac6_seq_private(seq);
+
 	if (likely(state->idev != NULL)) {
 		read_unlock_bh(&state->idev->lock);
-		in6_dev_put(state->idev);
+		state->idev = NULL;
 	}
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 }
 
 static int ac6_seq_show(struct seq_file *seq, void *v)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index f9fcf69..1f9c444 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2375,9 +2375,9 @@ static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq)
 	struct net *net = seq_file_net(seq);
 
 	state->idev = NULL;
-	for_each_netdev(net, state->dev) {
+	for_each_netdev_rcu(net, state->dev) {
 		struct inet6_dev *idev;
-		idev = in6_dev_get(state->dev);
+		idev = __in6_dev_get(state->dev);
 		if (!idev)
 			continue;
 		read_lock_bh(&idev->lock);
@@ -2387,7 +2387,6 @@ static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq)
 			break;
 		}
 		read_unlock_bh(&idev->lock);
-		in6_dev_put(idev);
 	}
 	return im;
 }
@@ -2398,16 +2397,15 @@ static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr
 
 	im = im->next;
 	while (!im) {
-		if (likely(state->idev != NULL)) {
+		if (likely(state->idev != NULL))
 			read_unlock_bh(&state->idev->lock);
-			in6_dev_put(state->idev);
-		}
-		state->dev = next_net_device(state->dev);
+
+		state->dev = next_net_device_rcu(state->dev);
 		if (!state->dev) {
 			state->idev = NULL;
 			break;
 		}
-		state->idev = in6_dev_get(state->dev);
+		state->idev = __in6_dev_get(state->dev);
 		if (!state->idev)
 			continue;
 		read_lock_bh(&state->idev->lock);
@@ -2426,31 +2424,31 @@ static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos)
 }
 
 static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(dev_base_lock)
+	__acquires(RCU)
 {
-	read_lock(&dev_base_lock);
+	rcu_read_lock();
 	return igmp6_mc_get_idx(seq, *pos);
 }
 
 static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct ifmcaddr6 *im;
-	im = igmp6_mc_get_next(seq, v);
+	struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v);
+
 	++*pos;
 	return im;
 }
 
 static void igmp6_mc_seq_stop(struct seq_file *seq, void *v)
-	__releases(dev_base_lock)
+	__releases(RCU)
 {
 	struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq);
+
 	if (likely(state->idev != NULL)) {
 		read_unlock_bh(&state->idev->lock);
-		in6_dev_put(state->idev);
 		state->idev = NULL;
 	}
 	state->dev = NULL;
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 }
 
 static int igmp6_mc_seq_show(struct seq_file *seq, void *v)
@@ -2507,9 +2505,9 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq)
 
 	state->idev = NULL;
 	state->im = NULL;
-	for_each_netdev(net, state->dev) {
+	for_each_netdev_rcu(net, state->dev) {
 		struct inet6_dev *idev;
-		idev = in6_dev_get(state->dev);
+		idev = __in6_dev_get(state->dev);
 		if (unlikely(idev == NULL))
 			continue;
 		read_lock_bh(&idev->lock);
@@ -2525,7 +2523,6 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq)
 			spin_unlock_bh(&im->mca_lock);
 		}
 		read_unlock_bh(&idev->lock);
-		in6_dev_put(idev);
 	}
 	return psf;
 }
@@ -2539,16 +2536,15 @@ static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_s
 		spin_unlock_bh(&state->im->mca_lock);
 		state->im = state->im->next;
 		while (!state->im) {
-			if (likely(state->idev != NULL)) {
+			if (likely(state->idev != NULL))
 				read_unlock_bh(&state->idev->lock);
-				in6_dev_put(state->idev);
-			}
-			state->dev = next_net_device(state->dev);
+
+			state->dev = next_net_device_rcu(state->dev);
 			if (!state->dev) {
 				state->idev = NULL;
 				goto out;
 			}
-			state->idev = in6_dev_get(state->dev);
+			state->idev = __in6_dev_get(state->dev);
 			if (!state->idev)
 				continue;
 			read_lock_bh(&state->idev->lock);
@@ -2573,9 +2569,9 @@ static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos)
 }
 
 static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(dev_base_lock)
+	__acquires(RCU)
 {
-	read_lock(&dev_base_lock);
+	rcu_read_lock();
 	return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
 }
 
@@ -2591,7 +2587,7 @@ static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 }
 
 static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v)
-	__releases(dev_base_lock)
+	__releases(RCU)
 {
 	struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq);
 	if (likely(state->im != NULL)) {
@@ -2600,11 +2596,10 @@ static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v)
 	}
 	if (likely(state->idev != NULL)) {
 		read_unlock_bh(&state->idev->lock);
-		in6_dev_put(state->idev);
 		state->idev = NULL;
 	}
 	state->dev = NULL;
-	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
 }
 
 static int igmp6_mcf_seq_show(struct seq_file *seq, void *v)

  parent reply	other threads:[~2009-11-12  3:34 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-11-10 17:54 [PATCH 00/10] netdev: get rid of read_lock(&dev_base_lock) usages Stephen Hemminger
2009-11-10 17:54 ` [PATCH 01/10] netdev: add netdev_continue_rcu Stephen Hemminger
2009-11-10 18:19   ` Eric Dumazet
2009-11-11  6:47     ` David Miller
2009-11-10 19:39   ` Paul E. McKenney
2009-11-10 17:54 ` [PATCH 02/10] vlan: eliminate use of dev_base_lock Stephen Hemminger
2009-11-10 18:20   ` Eric Dumazet
2009-11-11  6:47     ` David Miller
2009-11-10 17:54 ` [PATCH 03/10] net: use rcu for network scheduler API Stephen Hemminger
2009-11-10 18:20   ` Eric Dumazet
2009-11-11  6:47     ` David Miller
2009-11-10 17:54 ` [PATCH 04/10] AOE: use rcu to find network device Stephen Hemminger
2009-11-10 18:23   ` Eric Dumazet
2009-11-10 20:01   ` Ed Cashin
2009-11-10 23:06     ` Stephen Hemminger
2009-11-10 23:53       ` Stephen Hemminger
2009-11-11  6:48         ` David Miller
2009-11-12 14:33         ` Ed Cashin
2009-11-12 17:10           ` Stephen Hemminger
2009-11-12 18:07             ` Ed Cashin
2009-11-12 19:09               ` Stephen Hemminger
2009-11-18 16:49         ` Ed Cashin
2009-11-11 14:22       ` Ed Cashin
2009-11-13 21:39         ` Ed Cashin
2009-11-13 22:24           ` Stephen Hemminger
2009-11-10 17:54 ` [PATCH 05/10] parisc: use RCU " Stephen Hemminger
2009-11-10 18:26   ` Eric Dumazet
2009-11-11  6:48   ` David Miller
2009-11-10 17:54 ` [PATCH 06/10] s390: use RCU to walk list of network devices Stephen Hemminger
2009-11-10 18:27   ` Eric Dumazet
2009-11-10 18:29     ` Stephen Hemminger
2009-11-10 18:40   ` Eric Dumazet
2009-11-11  6:49     ` David Miller
2009-11-10 17:54 ` [PATCH 07/10] decnet: use RCU to find " Stephen Hemminger
2009-11-10 18:43   ` Eric Dumazet
2009-11-10 18:50     ` Stephen Hemminger
2009-11-10 18:24       ` steve
2009-11-11 17:39         ` [PATCH 1/2] decnet: add RTNL lock when reading address list Stephen Hemminger
2009-11-11 17:40           ` [PATCH 2/2] decnet: convert dndev_lock to spinlock Stephen Hemminger
2009-11-12  3:56             ` David Miller
2009-11-12  3:56           ` [PATCH 1/2] decnet: add RTNL lock when reading address list David Miller
2009-11-10 19:25       ` [PATCH 07/10] decnet: use RCU to find network devices Eric Dumazet
2009-11-11  6:49   ` David Miller
2009-11-10 17:54 ` [PATCH 08/10] ipv6: use RCU to walk list of " Stephen Hemminger
2009-11-11  6:50   ` David Miller
2009-11-12  3:34   ` Eric Dumazet [this message]
2009-11-14  4:39     ` [PATCH net-next-2.6] " David Miller
2009-11-10 17:54 ` [PATCH 09/10] IPV4: use rcu to walk list of devices in IGMP Stephen Hemminger
2009-11-10 18:47   ` Eric Dumazet
2009-11-11  6:50   ` David Miller
2009-11-10 17:54 ` [PATCH 10/10] CAN: use dev_get_by_index_rcu Stephen Hemminger
2009-11-10 18:34   ` Eric Dumazet
2009-11-11  5:54     ` Oliver Hartkopp
2009-11-11  6:50       ` David Miller
2009-11-10 18:18 ` [PATCH 00/10] netdev: get rid of read_lock(&dev_base_lock) usages Eric Dumazet
2009-11-10 18:22   ` Stephen Hemminger
2009-11-10 18:24   ` Stephen Hemminger
2009-11-10 18:39     ` Eric Dumazet
2009-11-10 18:53       ` Stephen Hemminger

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4AFB8246.6060804@gmail.com \
    --to=eric.dumazet@gmail.com \
    --cc=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    --cc=shemminger@vyatta.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).