From 3a5ca857079ea022e0b1b17fc154f7ad7dbc150f Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 2 Mar 2021 13:24:23 +0100 Subject: can: dev: Move device back to init netns on owning netns delete When a non-initial netns is destroyed, the usual policy is to delete all virtual network interfaces contained, but move physical interfaces back to the initial netns. This keeps the physical interface visible on the system. CAN devices are somewhat special, as they define rtnl_link_ops even if they are physical devices. If a CAN interface is moved into a non-initial netns, destroying that netns lets the interface vanish instead of moving it back to the initial netns. default_device_exit() skips CAN interfaces due to having rtnl_link_ops set. Reproducer: ip netns add foo ip link set can0 netns foo ip netns delete foo WARNING: CPU: 1 PID: 84 at net/core/dev.c:11030 ops_exit_list+0x38/0x60 CPU: 1 PID: 84 Comm: kworker/u4:2 Not tainted 5.10.19 #1 Workqueue: netns cleanup_net [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0x94/0xa8) [] (dump_stack) from [] (__warn+0xb8/0x114) [] (__warn) from [] (warn_slowpath_fmt+0x7c/0xac) [] (warn_slowpath_fmt) from [] (ops_exit_list+0x38/0x60) [] (ops_exit_list) from [] (cleanup_net+0x230/0x380) [] (cleanup_net) from [] (process_one_work+0x1d8/0x438) [] (process_one_work) from [] (worker_thread+0x64/0x5a8) [] (worker_thread) from [] (kthread+0x148/0x14c) [] (kthread) from [] (ret_from_fork+0x14/0x2c) To properly restore physical CAN devices to the initial netns on owning netns exit, introduce a flag on rtnl_link_ops that can be set by drivers. For CAN devices setting this flag, default_device_exit() considers them non-virtual, applying the usual namespace move. The issue was introduced in the commit mentioned below, as at that time CAN devices did not have a dellink() operation. Fixes: e008b5fc8dc7 ("net: Simplfy default_device_exit and improve batching.") Link: https://lore.kernel.org/r/20210302122423.872326-1-martin@strongswan.org Signed-off-by: Martin Willi Signed-off-by: Marc Kleine-Budde --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 6c5967e80132..a142a207fc1d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -11346,7 +11346,7 @@ static void __net_exit default_device_exit(struct net *net) continue; /* Leave virtual devices for the generic cleanup */ - if (dev->rtnl_link_ops) + if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ -- cgit v1.2.3 From cb038357937ee4f589aab2469ec3896dce90f317 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Tue, 16 Mar 2021 15:36:47 -0700 Subject: net: fix race between napi kthread mode and busy poll Currently, napi_thread_wait() checks for NAPI_STATE_SCHED bit to determine if the kthread owns this napi and could call napi->poll() on it. However, if socket busy poll is enabled, it is possible that the busy poll thread grabs this SCHED bit (after the previous napi->poll() invokes napi_complete_done() and clears SCHED bit) and tries to poll on the same napi. napi_disable() could grab the SCHED bit as well. This patch tries to fix this race by adding a new bit NAPI_STATE_SCHED_THREADED in napi->state. This bit gets set in ____napi_schedule() if the threaded mode is enabled, and gets cleared in napi_complete_done(), and we only poll the napi in kthread if this bit is set. This helps distinguish the ownership of the napi between kthread and other scenarios and fixes the race issue. Fixes: 29863d41bb6e ("net: implement threaded-able napi poll loop support") Reported-by: Martin Zaharinov Suggested-by: Jakub Kicinski Signed-off-by: Wei Wang Cc: Alexander Duyck Cc: Eric Dumazet Cc: Paolo Abeni Cc: Hannes Frederic Sowa Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 19 ++++++++++++++++++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5b67ea89d5f2..87a5d186faff 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -360,6 +360,7 @@ enum { NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ + NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ }; enum { @@ -372,6 +373,7 @@ enum { NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), + NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), }; enum gro_result { diff --git a/net/core/dev.c b/net/core/dev.c index a142a207fc1d..bb568f7cb81b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4294,6 +4294,13 @@ static inline void ____napi_schedule(struct softnet_data *sd, */ thread = READ_ONCE(napi->thread); if (thread) { + /* Avoid doing set_bit() if the thread is in + * INTERRUPTIBLE state, cause napi_thread_wait() + * makes sure to proceed with napi polling + * if the thread is explicitly woken from here. + */ + if (READ_ONCE(thread->state) != TASK_INTERRUPTIBLE) + set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } @@ -6486,6 +6493,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | + NAPIF_STATE_SCHED_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, @@ -6968,16 +6976,25 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) static int napi_thread_wait(struct napi_struct *napi) { + bool woken = false; + set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop() && !napi_disable_pending(napi)) { - if (test_bit(NAPI_STATE_SCHED, &napi->state)) { + /* Testing SCHED_THREADED bit here to make sure the current + * kthread owns this napi and could poll on this napi. + * Testing SCHED bit is not enough because SCHED bit might be + * set by some other busy poll thread or by napi_disable(). + */ + if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); + /* woken being true indicates this thread owns this napi. */ + woken = true; set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); -- cgit v1.2.3 From 6c015a2256801597fadcbc11d287774c9c512fa5 Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Thu, 18 Mar 2021 04:42:53 +0100 Subject: net: check all name nodes in __dev_alloc_name __dev_alloc_name(), when supplied with a name containing '%d', will search for the first available device number to generate a unique device name. Since commit ff92741270bf8b6e78aa885f166b68c7a67ab13a ("net: introduce name_node struct to be used in hashlist") network devices may have alternate names. __dev_alloc_name() does take these alternate names into account, possibly generating a name that is already taken and failing with -ENFILE as a result. This demonstrates the bug: # rmmod dummy 2>/dev/null # ip link property add dev lo altname dummy0 # modprobe dummy numdummies=1 modprobe: ERROR: could not insert 'dummy': Too many open files in system Instead of creating a device named dummy1, modprobe fails. Fix this by checking all the names in the d->name_node list, not just d->name. Signed-off-by: Jiri Bohac Fixes: ff92741270bf ("net: introduce name_node struct to be used in hashlist") Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/dev.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index bb568f7cb81b..0f72ff5d34ba 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1184,6 +1184,18 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -ENOMEM; for_each_netdev(net, d) { + struct netdev_name_node *name_node; + list_for_each_entry(name_node, &d->name_node->list, list) { + if (!sscanf(name_node->name, name, &i)) + continue; + if (i < 0 || i >= max_netdevices) + continue; + + /* avoid cases where sscanf is not exact inverse of printf */ + snprintf(buf, IFNAMSIZ, name, i); + if (!strncmp(buf, name_node->name, IFNAMSIZ)) + set_bit(i, inuse); + } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) -- cgit v1.2.3