From c7ac8679bec9397afe8918f788cbcef88c38da54 Mon Sep 17 00:00:00 2001
From: Greg Rose <gregory.v.rose@intel.com>
Date: Fri, 10 Jun 2011 01:27:09 +0000
Subject: rtnetlink: Compute and store minimum ifinfo dump size
The message size allocated for rtnl ifinfo dumps was limited to
a single page. This is not enough for additional interface info
available with devices that support SR-IOV and caused a bug in
which VF info would not be displayed if more than approximately
40 VFs were created per interface.
Implement a new function pointer for the rtnl_register service that will
calculate the amount of data required for the ifinfo dump and allocate
enough data to satisfy the request.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
net/core/rtnetlink.c | 60 ++++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 49 insertions(+), 11 deletions(-)
(limited to 'net/core/rtnetlink.c')
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index abd936d8a71..a798fc6f2aa 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -56,9 +56,11 @@
struct rtnl_link {
rtnl_doit_func doit;
rtnl_dumpit_func dumpit;
+ rtnl_calcit_func calcit;
};
static DEFINE_MUTEX(rtnl_mutex);
+static u16 min_ifinfo_dump_size;
void rtnl_lock(void)
{
@@ -144,12 +146,28 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
return tab ? tab[msgindex].dumpit : NULL;
}
+static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex)
+{
+ struct rtnl_link *tab;
+
+ if (protocol <= RTNL_FAMILY_MAX)
+ tab = rtnl_msg_handlers[protocol];
+ else
+ tab = NULL;
+
+ if (tab == NULL || tab[msgindex].calcit == NULL)
+ tab = rtnl_msg_handlers[PF_UNSPEC];
+
+ return tab ? tab[msgindex].calcit : NULL;
+}
+
/**
* __rtnl_register - Register a rtnetlink message type
* @protocol: Protocol family or PF_UNSPEC
* @msgtype: rtnetlink message type
* @doit: Function pointer called for each request message
* @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
+ * @calcit: Function pointer to calc size of dump message
*
* Registers the specified function pointers (at least one of them has
* to be non-NULL) to be called whenever a request message for the
@@ -162,7 +180,8 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
* Returns 0 on success or a negative error code.
*/
int __rtnl_register(int protocol, int msgtype,
- rtnl_doit_func doit, rtnl_dumpit_func dumpit)
+ rtnl_doit_func doit, rtnl_dumpit_func dumpit,
+ rtnl_calcit_func calcit)
{
struct rtnl_link *tab;
int msgindex;
@@ -185,6 +204,9 @@ int __rtnl_register(int protocol, int msgtype,
if (dumpit)
tab[msgindex].dumpit = dumpit;
+ if (calcit)
+ tab[msgindex].calcit = calcit;
+
return 0;
}
EXPORT_SYMBOL_GPL(__rtnl_register);
@@ -199,9 +221,10 @@ EXPORT_SYMBOL_GPL(__rtnl_register);
* of memory implies no sense in continuing.
*/
void rtnl_register(int protocol, int msgtype,
- rtnl_doit_func doit, rtnl_dumpit_func dumpit)
+ rtnl_doit_func doit, rtnl_dumpit_func dumpit,
+ rtnl_calcit_func calcit)
{
- if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0)
+ if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0)
panic("Unable to register rtnetlink message handler, "
"protocol = %d, message type = %d\n",
protocol, msgtype);
@@ -1818,6 +1841,11 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
return err;
}
+static u16 rtnl_calcit(struct sk_buff *skb)
+{
+ return min_ifinfo_dump_size;
+}
+
static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
{
int idx;
@@ -1847,11 +1875,14 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
struct net *net = dev_net(dev);
struct sk_buff *skb;
int err = -ENOBUFS;
+ size_t if_info_size;
- skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
+ skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL);
if (skb == NULL)
goto errout;
+ min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size);
+
err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
@@ -1902,14 +1933,20 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
struct sock *rtnl;
rtnl_dumpit_func dumpit;
+ rtnl_calcit_func calcit;
+ u16 min_dump_alloc = 0;
dumpit = rtnl_get_dumpit(family, type);
if (dumpit == NULL)
return -EOPNOTSUPP;
+ calcit = rtnl_get_calcit(family, type);
+ if (calcit)
+ min_dump_alloc = calcit(skb);
__rtnl_unlock();
rtnl = net->rtnl;
- err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL);
+ err = netlink_dump_start(rtnl, skb, nlh, dumpit,
+ NULL, min_dump_alloc);
rtnl_lock();
return err;
}
@@ -2019,12 +2056,13 @@ void __init rtnetlink_init(void)
netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV);
register_netdevice_notifier(&rtnetlink_dev_notifier);
- rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo);
- rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL);
- rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL);
- rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink,
+ rtnl_dump_ifinfo, rtnl_calcit);
+ rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all);
- rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all);
+ rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
}
--
cgit v1.2.3-70-g09d2
From 4e985adaa504c1c1a05c8e013777ea0791a17b4d Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@infradead.org>
Date: Tue, 21 Jun 2011 03:11:20 +0000
Subject: rtnl: provide link dump consistency info
This patch adds a change sequence counter to each net namespace
which is bumped whenever a netdevice is added or removed from
the list. If such a change occurred while a link dump took place,
the dump will have the NLM_F_DUMP_INTR flag set in the first
message which has been interrupted and in all subsequent messages
of the same dump.
Note that links may still be modified or renamed while a dump is
taking place but we can guarantee for userspace to receive a
complete list of links and not miss any.
Testing:
I have added 500 VLAN netdevices to make sure the dump is split
over multiple messages. Then while continuously dumping links in
one process I also continuously deleted and re-added a dummy
netdevice in another process. Multiple dumps per seconds have
had the NLM_F_DUMP_INTR flag set.
I guess we can wait for Johannes patch to hit net-next via the
wireless tree. I just wanted to give this some testing right away.
Signed-off-by: Thomas Graf <tgraf@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/net_namespace.h | 1 +
net/core/dev.c | 10 ++++++++++
net/core/net_namespace.c | 1 +
net/core/rtnetlink.c | 4 ++++
4 files changed, 16 insertions(+)
(limited to 'net/core/rtnetlink.c')
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index aef430d779b..1ab1aec209a 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -65,6 +65,7 @@ struct net {
struct list_head dev_base_head;
struct hlist_head *dev_name_head;
struct hlist_head *dev_index_head;
+ unsigned int dev_base_seq; /* protected by rtnl_mutex */
/* core fib_rules */
struct list_head rules_ops;
diff --git a/net/core/dev.c b/net/core/dev.c
index 6b6ef14b42f..4577e6711ec 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -199,6 +199,11 @@ static struct list_head ptype_all __read_mostly; /* Taps */
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
+static inline void dev_base_seq_inc(struct net *net)
+{
+ while (++net->dev_base_seq == 0);
+}
+
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
@@ -237,6 +242,9 @@ static int list_netdevice(struct net_device *dev)
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
+
+ dev_base_seq_inc(net);
+
return 0;
}
@@ -253,6 +261,8 @@ static void unlist_netdevice(struct net_device *dev)
hlist_del_rcu(&dev->name_hlist);
hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
+
+ dev_base_seq_inc(dev_net(dev));
}
/*
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index ea489db1bc2..5bbdbf0d366 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -129,6 +129,7 @@ static __net_init int setup_net(struct net *net)
atomic_set(&net->count, 1);
atomic_set(&net->passive, 1);
+ net->dev_base_seq = 1;
#ifdef NETNS_REFCNT_DEBUG
atomic_set(&net->use_count, 0);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a798fc6f2aa..99d9e953fe3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1032,6 +1032,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
s_idx = cb->args[1];
rcu_read_lock();
+ cb->seq = net->dev_base_seq;
+
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
@@ -1043,6 +1045,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
cb->nlh->nlmsg_seq, 0,
NLM_F_MULTI) <= 0)
goto out;
+
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
--
cgit v1.2.3-70-g09d2