From 6cfda7fbebe8a4fd33ea5722fa0212f98f643c35 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 5 Jan 2015 19:47:43 +0100 Subject: can: m_can: tag current CAN FD controllers as non-ISO During the CAN FD standardization process within the ISO it turned out that the failure detection capability has to be improved. The CAN in Automation organization (CiA) defined the already implemented CAN FD controllers as 'non-ISO' and the upcoming improved CAN FD controllers as 'ISO' compliant. See at http://www.can-cia.com/index.php?id=1937 Finally there will be three types of CAN FD controllers in the future: 1. ISO compliant (fixed) 2. non-ISO compliant (fixed, like the M_CAN IP v3.0.1 in m_can.c) 3. ISO/non-ISO CAN FD controllers (switchable, like the PEAK USB FD) So the current M_CAN driver for the M_CAN IP v3.0.1 has to expose its non-ISO implementation by setting the CAN_CTRLMODE_FD_NON_ISO ctrlmode at startup. As this bit cannot be switched at configuration time CAN_CTRLMODE_FD_NON_ISO must not be set in ctrlmode_supported of the current M_CAN driver. Signed-off-by: Oliver Hartkopp Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 3e4323a3918d..94ffe0c83ce7 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -98,6 +98,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */ #define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */ #define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */ +#define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */ /* * CAN device statistics -- cgit v1.2.3 From f555f3d76aaade29c7e221a37ee64fe722955c09 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jan 2015 11:37:12 +0100 Subject: genetlink: document parallel_ops The kernel-doc for the parallel_ops family struct member is missing, add it. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/net/genetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 84125088c309..2ea2c55bdc87 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -27,6 +27,8 @@ struct genl_info; * @maxattr: maximum number of attributes supported * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them + * @parallel_ops: operations can be called in parallel and aren't + * synchronized by the core genetlink code * @pre_doit: called before an operation's doit callback, it may * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may -- cgit v1.2.3 From ee1c244219fd652964710a6cc3e4f922e86aa492 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jan 2015 11:37:14 +0100 Subject: genetlink: synchronize socket closing and family removal In addition to the problem Jeff Layton reported, I looked at the code and reproduced the same warning by subscribing and removing the genl family with a socket still open. This is a fairly tricky race which originates in the fact that generic netlink allows the family to go away while sockets are still open - unlike regular netlink which has a module refcount for every open socket so in general this cannot be triggered. Trying to resolve this issue by the obvious locking isn't possible as it will result in deadlocks between unregistration and group unbind notification (which incidentally lockdep doesn't find due to the home grown locking in the netlink table.) To really resolve this, introduce a "closing socket" reference counter (for generic netlink only, as it's the only affected family) in the core netlink code and use that in generic netlink to wait for all the sockets that are being closed at the same time as a generic netlink family is removed. This fixes the race that when a socket is closed, it will should call the unbind, but if the family is removed at the same time the unbind will not find it, leading to the warning. The real problem though is that in this case the unbind could actually find a new family that is registered to have a multicast group with the same ID, and call its mcast_unbind() leading to confusing. Also remove the warning since it would still trigger, but is now no longer a problem. This also moves the code in af_netlink.c to before unreferencing the module to avoid having the same problem in the normal non-genl case. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/genetlink.h | 4 ++++ include/net/genetlink.h | 5 ++++- net/netlink/af_netlink.c | 24 +++++++++++++++++------- net/netlink/af_netlink.h | 1 + net/netlink/genetlink.c | 16 +++++++++------- 5 files changed, 35 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index 55b685719d52..09460d6d6682 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -11,6 +11,10 @@ extern void genl_unlock(void); extern int lockdep_genl_is_held(void); #endif +/* for synchronisation between af_netlink and genetlink */ +extern atomic_t genl_sk_destructing_cnt; +extern wait_queue_head_t genl_sk_destructing_waitq; + /** * rcu_dereference_genl - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 2ea2c55bdc87..6c92415311ca 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -35,7 +35,10 @@ struct genl_info; * undo operations done by pre_doit, for example release locks * @mcast_bind: a socket bound to the given multicast group (which * is given as the offset into the groups array) - * @mcast_unbind: a socket was unbound from the given multicast group + * @mcast_unbind: a socket was unbound from the given multicast group. + * Note that unbind() will not be called symmetrically if the + * generic netlink family is removed while there are still open + * sockets. * @attrbuf: buffer to store parsed attributes * @family_list: family list * @mcgrps: multicast groups used by this family (private) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 84ea76ca3f1f..02fdde28dada 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -61,6 +61,7 @@ #include #include #include +#include #include #include @@ -1095,6 +1096,8 @@ static void netlink_remove(struct sock *sk) __sk_del_bind_node(sk); netlink_update_listeners(sk); } + if (sk->sk_protocol == NETLINK_GENERIC) + atomic_inc(&genl_sk_destructing_cnt); netlink_table_ungrab(); } @@ -1211,6 +1214,20 @@ static int netlink_release(struct socket *sock) * will be purged. */ + /* must not acquire netlink_table_lock in any way again before unbind + * and notifying genetlink is done as otherwise it might deadlock + */ + if (nlk->netlink_unbind) { + int i; + + for (i = 0; i < nlk->ngroups; i++) + if (test_bit(i, nlk->groups)) + nlk->netlink_unbind(sock_net(sk), i + 1); + } + if (sk->sk_protocol == NETLINK_GENERIC && + atomic_dec_return(&genl_sk_destructing_cnt) == 0) + wake_up(&genl_sk_destructing_waitq); + sock->sk = NULL; wake_up_interruptible_all(&nlk->wait); @@ -1246,13 +1263,6 @@ static int netlink_release(struct socket *sock) netlink_table_ungrab(); } - if (nlk->netlink_unbind) { - int i; - - for (i = 0; i < nlk->ngroups; i++) - if (test_bit(i, nlk->groups)) - nlk->netlink_unbind(sock_net(sk), i + 1); - } kfree(nlk->groups); nlk->groups = NULL; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index f123a88496f8..f1c31b39aa3e 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -2,6 +2,7 @@ #define _AF_NETLINK_H #include +#include #include #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index c18d3f5624b2..ee57459fc258 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -23,6 +23,9 @@ static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static DECLARE_RWSEM(cb_lock); +atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0); +DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq); + void genl_lock(void) { mutex_lock(&genl_mutex); @@ -435,15 +438,18 @@ int genl_unregister_family(struct genl_family *family) genl_lock_all(); - genl_unregister_mc_groups(family); - list_for_each_entry(rc, genl_family_chain(family->id), family_list) { if (family->id != rc->id || strcmp(rc->name, family->name)) continue; + genl_unregister_mc_groups(family); + list_del(&rc->family_list); family->n_ops = 0; - genl_unlock_all(); + up_write(&cb_lock); + wait_event(genl_sk_destructing_waitq, + atomic_read(&genl_sk_destructing_cnt) == 0); + genl_unlock(); kfree(family->attrbuf); genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); @@ -1014,7 +1020,6 @@ static int genl_bind(struct net *net, int group) static void genl_unbind(struct net *net, int group) { int i; - bool found = false; down_read(&cb_lock); for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { @@ -1027,14 +1032,11 @@ static void genl_unbind(struct net *net, int group) if (f->mcast_unbind) f->mcast_unbind(net, fam_grp); - found = true; break; } } } up_read(&cb_lock); - - WARN_ON(!found); } static int __net_init genl_pernet_init(struct net *net) -- cgit v1.2.3