#include #include #include #include #include #include #include #include #include #include int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { int err; struct socket *sock = NULL; struct sockaddr_in udp_addr; err = sock_create_kern(net, AF_INET, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->local_ip; udp_addr.sin_port = cfg->local_udp_port; err = kernel_bind(sock, (struct sockaddr *)&udp_addr, sizeof(udp_addr)); if (err < 0) goto error; if (cfg->peer_udp_port) { udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->peer_ip; udp_addr.sin_port = cfg->peer_udp_port; err = kernel_connect(sock, (struct sockaddr *)&udp_addr, sizeof(udp_addr), 0); if (err < 0) goto error; } sock->sk->sk_no_check_tx = !cfg->use_udp_checksums; *sockp = sock; return 0; error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } *sockp = NULL; return err; } EXPORT_SYMBOL(udp_sock_create4); void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *cfg) { struct sock *sk = sock->sk; /* Disable multicast loopback */ inet_sk(sk)->mc_loop = 0; /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ inet_inc_convert_csum(sk); rcu_assign_sk_user_data(sk, cfg->sk_user_data); udp_sk(sk)->encap_type = cfg->encap_type; udp_sk(sk)->encap_rcv = cfg->encap_rcv; udp_sk(sk)->encap_destroy = cfg->encap_destroy; udp_sk(sk)->gro_receive = cfg->gro_receive; udp_sk(sk)->gro_complete = cfg->gro_complete; udp_tunnel_encap_enable(sock); } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct udp_tunnel_info ti; if (!dev->netdev_ops->ndo_udp_tunnel_add) return; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti); } EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port); /* Notify netdevs that UDP port started listening */ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct udp_tunnel_info ti; struct net_device *dev; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (!dev->netdev_ops->ndo_udp_tunnel_add) continue; dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port); /* Notify netdevs that UDP port is no more listening */ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct udp_tunnel_info ti; struct net_device *dev; ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (!dev->netdev_ops->ndo_udp_tunnel_del) continue; dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port); void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck) { struct udphdr *uh; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); udp_set_csum(nocheck, skb, src, dst, skb->len); iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); } EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); void udp_tunnel_sock_release(struct socket *sock) { rcu_assign_sk_user_data(sock->sk, NULL); kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; if (family == AF_INET) tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size); else tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size); if (!tun_dst) return NULL; info = &tun_dst->u.tun_info; info->key.tp_src = udp_hdr(skb)->source; info->key.tp_dst = udp_hdr(skb)->dest; if (udp_hdr(skb)->check) info->key.tun_flags |= TUNNEL_CSUM; return tun_dst; } EXPORT_SYMBOL_GPL(udp_tun_rx_dst); MODULE_LICENSE("GPL"); ht'>2017-01-28 07:49:42 -0500 commit966d2b04e070bc040319aaebfec09e0144dc3341 (patch) tree4b96156e3d1dd4dfd6039b7c219c9dc4616da52d /net/6lowpan/nhc_ghc_ext_route.c parent1b1bc42c1692e9b62756323c675a44cb1a1f9dbd (diff)
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return "true" IFF they acquire a reference. But the return value from atomic_long_inc_not_zero() is a long and may have high bits set, e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines is bool so the reference may actually be acquired but the routines return "false" which results in a reference leak since the caller assumes it does not need to do a corresponding percpu_ref_put(). This was seen when performing CPU hotplug during I/O, as hangs in blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start) raced with percpu_ref_tryget (blk_mq_timeout_work). Sample stack trace: __switch_to+0x2c0/0x450 __schedule+0x2f8/0x970 schedule+0x48/0xc0 blk_mq_freeze_queue_wait+0x94/0x120 blk_mq_queue_reinit_work+0xb8/0x180 blk_mq_queue_reinit_prepare+0x84/0xa0 cpuhp_invoke_callback+0x17c/0x600 cpuhp_up_callbacks+0x58/0x150 _cpu_up+0xf0/0x1c0 do_cpu_up+0x120/0x150 cpu_subsys_online+0x64/0xe0 device_online+0xb4/0x120 online_store+0xb4/0xc0 dev_attr_store+0x68/0xa0 sysfs_kf_write+0x80/0xb0 kernfs_fop_write+0x17c/0x250 __vfs_write+0x6c/0x1e0 vfs_write+0xd0/0x270 SyS_write+0x6c/0x110 system_call+0x38/0xe0 Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS, and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests. However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0 and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set. The fix is to make the tryget routines use an actual boolean internally instead of the atomic long result truncated to a int. Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751 Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com> Reviewed-by: Jens Axboe <axboe@fb.com> Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints") Cc: stable@vger.kernel.org # v3.18+
Diffstat (limited to 'net/6lowpan/nhc_ghc_ext_route.c')