| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1425018776-14725-1-git-send-email-xiyou.wangcong@gmail.com>
Date: Thu, 26 Feb 2015 22:32:56 -0800
From: Cong Wang <xiyou.wangcong@...il.com>
To: netdev@...r.kernel.org
Cc: Cong Wang <xiyou.wangcong@...il.com>,
Nicolas Dichtel <nicolas.dichtel@...nd.com>,
Eric Dumazet <eric.dumazet@...il.com>
Subject: [Patch net] netns: avoid allocating idr when dumping info
We can allocate the peer netns id when creating the link
instead of when dumping the link.
This fixes the following kernel warning:
===============================
[ INFO: suspicious RCU usage. ]
3.19.0+ #805 Tainted: G W
-------------------------------
include/linux/rcupdate.h:538 Illegal context switch in RCU read-side critical section!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 0
2 locks held by ip/771:
#0: (rtnl_mutex){+.+.+.}, at: [<ffffffff8182b8f4>] netlink_dump+0x21/0x26c
#1: (rcu_read_lock){......}, at: [<ffffffff817d785b>] rcu_read_lock+0x0/0x6e
stack backtrace:
CPU: 3 PID: 771 Comm: ip Tainted: G W 3.19.0+ #805
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
0000000000000001 ffff8800d51e7718 ffffffff81a27457 0000000029e729e6
ffff8800d6108000 ffff8800d51e7748 ffffffff810b539b ffffffff820013dd
00000000000001c8 0000000000000000 ffff8800d7448088 ffff8800d51e7758
Call Trace:
[<ffffffff81a27457>] dump_stack+0x4c/0x65
[<ffffffff810b539b>] lockdep_rcu_suspicious+0x107/0x110
[<ffffffff8109796f>] rcu_preempt_sleep_check+0x45/0x47
[<ffffffff8109e457>] ___might_sleep+0x1d/0x1cb
[<ffffffff8109e67d>] __might_sleep+0x78/0x80
[<ffffffff814b9b1f>] idr_alloc+0x45/0xd1
[<ffffffff810cb7ab>] ? rcu_read_lock_held+0x3b/0x3d
[<ffffffff814b9f9d>] ? idr_for_each+0x53/0x101
[<ffffffff817c1383>] alloc_netid+0x61/0x69
[<ffffffff817c14c3>] __peernet2id+0x79/0x8d
[<ffffffff817c1ab7>] peernet2id+0x13/0x1f
[<ffffffff817d8673>] rtnl_fill_ifinfo+0xa8d/0xc20
[<ffffffff810b17d9>] ? __lock_is_held+0x39/0x52
[<ffffffff817d894f>] rtnl_dump_ifinfo+0x149/0x213
[<ffffffff8182b9c2>] netlink_dump+0xef/0x26c
[<ffffffff8182bcba>] netlink_recvmsg+0x17b/0x2c5
[<ffffffff817b0adc>] __sock_recvmsg+0x4e/0x59
[<ffffffff817b1b40>] sock_recvmsg+0x3f/0x51
[<ffffffff817b1f9a>] ___sys_recvmsg+0xf6/0x1d9
[<ffffffff8115dc67>] ? handle_pte_fault+0x6e1/0xd3d
[<ffffffff8100a3a0>] ? native_sched_clock+0x35/0x37
[<ffffffff8109f45b>] ? sched_clock_local+0x12/0x72
[<ffffffff8109f6ac>] ? sched_clock_cpu+0x9e/0xb7
[<ffffffff810cb7ab>] ? rcu_read_lock_held+0x3b/0x3d
[<ffffffff811abde8>] ? __fcheck_files+0x4c/0x58
[<ffffffff811ac556>] ? __fget_light+0x2d/0x52
[<ffffffff817b376f>] __sys_recvmsg+0x42/0x60
[<ffffffff817b379f>] SyS_recvmsg+0x12/0x1c
Fixes: commit d37512a277dfb2cef ("rtnl: add link netns id to interface messages")
Cc: Nicolas Dichtel <nicolas.dichtel@...nd.com>
Cc: Eric Dumazet <eric.dumazet@...il.com>
Signed-off-by: Cong Wang <xiyou.wangcong@...il.com>
---
include/net/net_namespace.h | 14 +++++++++++++-
net/core/net_namespace.c | 14 ++------------
net/core/rtnetlink.c | 11 +++++++++--
3 files changed, 24 insertions(+), 15 deletions(-)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 36faf49..25ac2e0 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -27,6 +27,7 @@
#include <net/netns/nftables.h>
#include <net/netns/xfrm.h>
#include <linux/ns_common.h>
+#include <uapi/linux/net_namespace.h>
struct user_namespace;
struct proc_dir_entry;
@@ -291,7 +292,18 @@ static inline struct net *read_pnet(struct net * const *pnet)
#define __net_initconst __initconst
#endif
-int peernet2id(struct net *net, struct net *peer);
+int __peernet2id(struct net *net, struct net *peer, bool alloc);
+
+/* This function returns the id of a peer netns. If no id is assigned, one will
+ * be allocated and returned.
+ */
+static inline int peernet2id(struct net *net, struct net *peer)
+{
+ int id = __peernet2id(net, peer, true);
+
+ return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
+}
+
struct net *get_net_ns_by_id(struct net *net, int id);
struct pernet_operations {
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index cb5290b..9ff2164 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -175,7 +175,7 @@ static int net_eq_idr(int id, void *net, void *peer)
return 0;
}
-static int __peernet2id(struct net *net, struct net *peer, bool alloc)
+int __peernet2id(struct net *net, struct net *peer, bool alloc)
{
int id = idr_for_each(&net->netns_ids, net_eq_idr, peer);
@@ -192,17 +192,7 @@ static int __peernet2id(struct net *net, struct net *peer, bool alloc)
return -ENOENT;
}
-
-/* This function returns the id of a peer netns. If no id is assigned, one will
- * be allocated and returned.
- */
-int peernet2id(struct net *net, struct net *peer)
-{
- int id = __peernet2id(net, peer, true);
-
- return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
-}
-EXPORT_SYMBOL(peernet2id);
+EXPORT_SYMBOL(__peernet2id);
struct net *get_net_ns_by_id(struct net *net, int id)
{
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1385de0..a4348ac 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1175,8 +1175,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
if (!net_eq(dev_net(dev), link_net)) {
- int id = peernet2id(dev_net(dev), link_net);
+ int id = __peernet2id(dev_net(dev), link_net, false);
+ if (id < 0)
+ id = NETNSA_NSID_NOT_ASSIGNED;
if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
goto nla_put_failure;
}
@@ -2142,7 +2144,12 @@ replay:
dev->ifindex = ifm->ifi_index;
if (ops->newlink) {
- err = ops->newlink(link_net ? : net, dev, tb, data);
+ struct net *src_net = link_net ?: net;
+
+ if (ops->get_link_net && !net_eq(src_net, dev_net(dev)))
+ (void)peernet2id(dev_net(dev), src_net);
+
+ err = ops->newlink(src_net, dev, tb, data);
/* Drivers should call free_netdev() in ->destructor
* and unregister it on failure after registration
* so that device could be finally freed in rtnl_unlock.
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists