From d04a48b06d63b6d6e9289ca8a5e6e84ebfe39bfd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 May 2012 17:01:57 -0600 Subject: userns: Convert __dev_set_promiscuity to use kuids in audit logs Cc: Klaus Heinrich Kiwi Cc: Eric Paris Acked-by: David S. Miller Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- net/core/dev.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 0cb3fe8d8e7..026bb4a3766 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4492,8 +4492,8 @@ static void dev_change_rx_flags(struct net_device *dev, int flags) static int __dev_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; ASSERT_RTNL(); @@ -4525,7 +4525,8 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), audit_get_loginuid(current), - uid, gid, + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } -- cgit v1.2.3-70-g09d2 From 748e2d9396a18c3fd3d07d47c1b41320acf1fbf4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Aug 2012 21:50:59 +0000 Subject: net: reinstate rtnl in call_netdevice_notifiers() Eric Biederman pointed out that not holding RTNL while calling call_netdevice_notifiers() was racy. This patch is a direct transcription his feedback against commit 0115e8e30d6fc (net: remove delay at device dismantle) Thanks Eric ! Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Mahesh Bandewar Cc: "Eric W. Biederman" Cc: Gao feng Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/core/dev.c | 9 +++++++-- net/core/fib_rules.c | 3 +-- net/ipv4/devinet.c | 6 +----- net/ipv4/fib_frontend.c | 7 ++----- net/ipv6/addrconf.c | 6 +----- 5 files changed, 12 insertions(+), 19 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 0640d2a859c..bc857fead8c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1466,8 +1466,7 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - if (val != NETDEV_UNREGISTER_FINAL) - ASSERT_RTNL(); + ASSERT_RTNL(); return raw_notifier_call_chain(&netdev_chain, val, dev); } EXPORT_SYMBOL(call_netdevice_notifiers); @@ -5782,7 +5781,11 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + + __rtnl_unlock(); rcu_barrier(); + rtnl_lock(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { @@ -5855,7 +5858,9 @@ void netdev_run_todo(void) = list_first_entry(&list, struct net_device, todo_list); list_del(&dev->todo_list); + rtnl_lock(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + __rtnl_unlock(); if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { pr_err("network todo '%s' but state %d\n", diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 585093755c2..ab7db83236c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -711,16 +711,15 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, struct net *net = dev_net(dev); struct fib_rules_ops *ops; + ASSERT_RTNL(); switch (event) { case NETDEV_REGISTER: - ASSERT_RTNL(); list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break; case NETDEV_UNREGISTER: - ASSERT_RTNL(); list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6a5e6e4b142..adf273f8ad2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1147,12 +1147,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; - struct in_device *in_dev; - - if (event == NETDEV_UNREGISTER_FINAL) - goto out; + struct in_device *in_dev = __in_dev_get_rtnl(dev); - in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index fd7d9ae64f1..acdee325d97 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1050,9 +1050,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo return NOTIFY_DONE; } - if (event == NETDEV_UNREGISTER_FINAL) - return NOTIFY_DONE; - in_dev = __in_dev_get_rtnl(dev); switch (event) { @@ -1064,14 +1061,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(net, -1); break; case NETDEV_DOWN: fib_disable_ip(dev, 0, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(net, 0); break; } return NOTIFY_DONE; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e581009cb09..6bc85f7c31e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2566,14 +2566,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, void *data) { struct net_device *dev = (struct net_device *) data; - struct inet6_dev *idev; + struct inet6_dev *idev = __in6_dev_get(dev); int run_pending = 0; int err; - if (event == NETDEV_UNREGISTER_FINAL) - return NOTIFY_DONE; - - idev = __in6_dev_get(dev); switch (event) { case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { -- cgit v1.2.3-70-g09d2 From 8f4cccbbd92f2ad0ddbbc498ef7cee2a1c3defe9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 20 Aug 2012 22:16:51 +0100 Subject: net: Set device operstate at registration time The operstate of a device is initially IF_OPER_UNKNOWN and is updated asynchronously by linkwatch after each change of carrier state reported by the driver. The default carrier state of a net device is on, and this will never be changed on drivers that do not support carrier detection, thus the operstate remains IF_OPER_UNKNOWN. For devices that do support carrier detection, the driver must set the carrier state to off initially, then poll the hardware state when the device is opened. However, we must not activate linkwatch for a unregistered device, and commit b473001 ('net: Do not fire linkwatch events until the device is registered.') ensured that we don't. But this means that the operstate for many devices that support carrier detection remains IF_OPER_UNKNOWN when it should be IF_OPER_DOWN. The same issue exists with the dormant state. The proper initialisation sequence, avoiding a race with opening of the device, is: rtnl_lock(); rc = register_netdevice(dev); if (rc) goto out_unlock; netif_carrier_off(dev); /* or netif_dormant_on(dev) */ rtnl_unlock(); but it seems silly that this should have to be repeated in so many drivers. Further, the operstate seen immediately after opening the device may still be IF_OPER_UNKNOWN due to the asynchronous nature of linkwatch. Commit 22604c8 ('net: Fix for initial link state in 2.6.28') attempted to fix this by setting the operstate synchronously, but it was reverted as it could lead to deadlock. This initialises the operstate synchronously at registration time only. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 2 ++ net/core/link_watch.c | 8 ++++++++ 3 files changed, 11 insertions(+) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ad7fa8c10e..ccac82e6160 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2227,6 +2227,7 @@ static inline void dev_hold(struct net_device *dev) * kind of lower layer not just hardware media. */ +extern void linkwatch_init_dev(struct net_device *dev); extern void linkwatch_fire_event(struct net_device *dev); extern void linkwatch_forget_dev(struct net_device *dev); diff --git a/net/core/dev.c b/net/core/dev.c index bc857fead8c..2f25d0cac51 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5648,6 +5648,8 @@ int register_netdevice(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); + linkwatch_init_dev(dev); + dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index c3519c6d1b1..a01922219a2 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -76,6 +76,14 @@ static void rfc2863_policy(struct net_device *dev) } +void linkwatch_init_dev(struct net_device *dev) +{ + /* Handle pre-registration link state changes */ + if (!netif_carrier_ok(dev) || netif_dormant(dev)) + rfc2863_policy(dev); +} + + static bool linkwatch_urgent_event(struct net_device *dev) { if (!netif_running(dev)) -- cgit v1.2.3-70-g09d2 From 6549dd43c04327071571edf7aea4465b16539422 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Thu, 23 Aug 2012 15:36:55 +0000 Subject: net: dev: fix the incorrect hold of net namespace's lo device When moving a net device from one net namespace to another net namespace,dev_change_net_namespace calls NETDEV_DOWN event,so the original net namespace's dst entries which beloned to this net device will be put into dst_garbage list. then dev_change_net_namespace will set this net device's net to the new net namespace. If we unregister this net device's driver, this will trigger the NETDEV_UNREGISTER_FINAL event, dst_ifdown will be called, and get this net device's dst entries from dst_garbage list, put these entries' dev to the new net namespace's lo device. It's not what we want,actually we need these dst entries hold the original net namespace's lo device,this incorrect device holding will trigger emg message like below. unregister_netdevice: waiting for lo to become free. Usage count = 1 so we should call NETDEV_UNREGISTER_FINAL event in dev_change_net_namespace too,in order to make sure dst entries already in the dst_garbage list, we need rcu_barrier before we call NETDEV_UNREGISTER_FINAL event. With help form Eric Dumazet. Signed-off-by: Gao feng Cc: Eric Dumazet Cc: "Eric W. Biederman" Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 3401e2dab7c..a5fc3e301cf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6259,6 +6259,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + rcu_barrier(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); /* -- cgit v1.2.3-70-g09d2 From d1a53dfd114a6c53464de116cdab88d934bfe92f Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Mon, 27 Aug 2012 23:39:24 +0000 Subject: net: fix documentation of skb_needs_linearize(). skb_needs_linearize() does not check highmem DMA as it does not call illegal_highdma() anymore, so there is no need to mention highmem DMA here. (Indeed, ~NETIF_F_SG flag, which is checked in skb_needs_linearize(), can be set when illegal_highdma() returns true, and we are assured that illegal_highdma() is invoked prior to skb_needs_linearize() as skb_needs_linearize() is a static method called only once. But ~NETIF_F_SG can be set not only there in this same invocation path. It can also be set when can_checksum_protocol() returns false). see commit 02932ce9e2c136e6fab2571c8e0dd69ae8ec9853, Convert skb_need_linearize() to use precomputed features. Signed-off-by: Rami Rosen Signed-off-by: David S. Miller --- net/core/dev.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index a5fc3e301cf..b1e6d638551 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2184,9 +2184,7 @@ EXPORT_SYMBOL(netif_skb_features); /* * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or - * 2. skb is fragmented and the device does not support SG, or if - * at least one of fragments is in highmem and device does not - * support DMA from it. + * 2. skb is fragmented and the device does not support SG. */ static inline int skb_needs_linearize(struct sk_buff *skb, int features) -- cgit v1.2.3-70-g09d2