diff options
Diffstat (limited to 'net')
133 files changed, 1453 insertions, 1087 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 33f90e7362cc..453512266ea1 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -663,7 +663,7 @@ out: return err; } -static int vlan_init_net(struct net *net) +static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); int err; @@ -675,7 +675,7 @@ static int vlan_init_net(struct net *net) return err; } -static void vlan_exit_net(struct net *net) +static void __net_exit vlan_exit_net(struct net *net) { vlan_proc_cleanup(net); } diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index e75a2f3b10af..c0316e0ca6e8 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -14,6 +14,7 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, if (skb_bond_should_drop(skb)) goto drop; + skb->skb_iif = skb->dev->ifindex; __vlan_hwaccel_put_tag(skb, vlan_tci); skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); @@ -85,6 +86,7 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, if (skb_bond_should_drop(skb)) goto drop; + skb->skb_iif = skb->dev->ifindex; __vlan_hwaccel_put_tag(skb, vlan_tci); skb->dev = vlan_group_get_device(grp, vlan_tci & VLAN_VID_MASK); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index b7889782047e..77a49ffdd0ef 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -263,11 +263,10 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, vhdr->h_vlan_TCI = htons(vlan_tci); /* - * Set the protocol type. For a packet of type ETH_P_802_3 we - * put the length in here instead. It is up to the 802.2 - * layer to carry protocol information. + * Set the protocol type. For a packet of type ETH_P_802_3/2 we + * put the length in here instead. */ - if (type != ETH_P_802_3) + if (type != ETH_P_802_3 && type != ETH_P_802_2) vhdr->h_vlan_encapsulated_proto = htons(type); else vhdr->h_vlan_encapsulated_proto = htons(len); diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 9ec1f057c03a..afead353e215 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -140,7 +140,7 @@ void vlan_proc_cleanup(struct net *net) * Create /proc/net/vlan entries */ -int vlan_proc_init(struct net *net) +int __net_init vlan_proc_init(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 4dd873e3a1bb..be1cb909d8c0 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -42,6 +42,8 @@ #include <net/9p/client.h> #include <net/9p/transport.h> +#include <linux/syscalls.h> /* killme */ + #define P9_PORT 564 #define MAX_SOCK_BUF (64*1024) #define MAXPOLLWADDR 2 @@ -788,24 +790,41 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) static int p9_socket_open(struct p9_client *client, struct socket *csocket) { - int fd, ret; + struct p9_trans_fd *p; + int ret, fd; + + p = kmalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); + if (!p) + return -ENOMEM; csocket->sk->sk_allocation = GFP_NOIO; fd = sock_map_fd(csocket, 0); if (fd < 0) { P9_EPRINTK(KERN_ERR, "p9_socket_open: failed to map fd\n"); + sock_release(csocket); + kfree(p); return fd; } - ret = p9_fd_open(client, fd, fd); - if (ret < 0) { - P9_EPRINTK(KERN_ERR, "p9_socket_open: failed to open fd\n"); + get_file(csocket->file); + get_file(csocket->file); + p->wr = p->rd = csocket->file; + client->trans = p; + client->status = Connected; + + sys_close(fd); /* still racy */ + + p->rd->f_flags |= O_NONBLOCK; + + p->conn = p9_conn_create(client); + if (IS_ERR(p->conn)) { + ret = PTR_ERR(p->conn); + p->conn = NULL; + kfree(p); + sockfd_put(csocket); sockfd_put(csocket); return ret; } - - ((struct p9_trans_fd *)client->trans)->rd->f_flags |= O_NONBLOCK; - return 0; } @@ -883,7 +902,6 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) struct socket *csocket; struct sockaddr_in sin_server; struct p9_fd_opts opts; - struct p9_trans_fd *p = NULL; /* this gets allocated in p9_fd_open */ err = parse_opts(args, &opts); if (err < 0) @@ -897,12 +915,11 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) sin_server.sin_family = AF_INET; sin_server.sin_addr.s_addr = in_aton(addr); sin_server.sin_port = htons(opts.port); - sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &csocket); + err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &csocket); - if (!csocket) { + if (err) { P9_EPRINTK(KERN_ERR, "p9_trans_tcp: problem creating socket\n"); - err = -EIO; - goto error; + return err; } err = csocket->ops->connect(csocket, @@ -912,30 +929,11 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) P9_EPRINTK(KERN_ERR, "p9_trans_tcp: problem connecting socket to %s\n", addr); - goto error; - } - - err = p9_socket_open(client, csocket); - if (err < 0) - goto error; - - p = (struct p9_trans_fd *) client->trans; - p->conn = p9_conn_create(client); - if (IS_ERR(p->conn)) { - err = PTR_ERR(p->conn); - p->conn = NULL; - goto error; - } - - return 0; - -error: - if (csocket) sock_release(csocket); + return err; + } - kfree(p); - - return err; + return p9_socket_open(client, csocket); } static int @@ -944,49 +942,33 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) int err; struct socket *csocket; struct sockaddr_un sun_server; - struct p9_trans_fd *p = NULL; /* this gets allocated in p9_fd_open */ csocket = NULL; if (strlen(addr) > UNIX_PATH_MAX) { P9_EPRINTK(KERN_ERR, "p9_trans_unix: address too long: %s\n", addr); - err = -ENAMETOOLONG; - goto error; + return -ENAMETOOLONG; } sun_server.sun_family = PF_UNIX; strcpy(sun_server.sun_path, addr); - sock_create_kern(PF_UNIX, SOCK_STREAM, 0, &csocket); + err = sock_create_kern(PF_UNIX, SOCK_STREAM, 0, &csocket); + if (err < 0) { + P9_EPRINTK(KERN_ERR, "p9_trans_unix: problem creating socket\n"); + return err; + } err = csocket->ops->connect(csocket, (struct sockaddr *)&sun_server, sizeof(struct sockaddr_un) - 1, 0); if (err < 0) { P9_EPRINTK(KERN_ERR, "p9_trans_unix: problem connecting socket: %s: %d\n", addr, err); - goto error; - } - - err = p9_socket_open(client, csocket); - if (err < 0) - goto error; - - p = (struct p9_trans_fd *) client->trans; - p->conn = p9_conn_create(client); - if (IS_ERR(p->conn)) { - err = PTR_ERR(p->conn); - p->conn = NULL; - goto error; - } - - return 0; - -error: - if (csocket) sock_release(csocket); + return err; + } - kfree(p); - return err; + return p9_socket_open(client, csocket); } static int @@ -994,7 +976,7 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) { int err; struct p9_fd_opts opts; - struct p9_trans_fd *p = NULL; /* this get allocated in p9_fd_open */ + struct p9_trans_fd *p; parse_opts(args, &opts); @@ -1005,21 +987,19 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) err = p9_fd_open(client, opts.rfd, opts.wfd); if (err < 0) - goto error; + return err; p = (struct p9_trans_fd *) client->trans; p->conn = p9_conn_create(client); if (IS_ERR(p->conn)) { err = PTR_ERR(p->conn); p->conn = NULL; - goto error; + fput(p->rd); + fput(p->wr); + return err; } return 0; - -error: - kfree(p); - return err; } static struct p9_trans_module p9_tcp_trans = { diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 29b1b220d6cf..ef09c7b3a858 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -78,7 +78,7 @@ static struct bnep_session *__bnep_get_session(u8 *dst) static void __bnep_link_session(struct bnep_session *s) { /* It's safe to call __module_get() here because sessions are added - by the socket layer which has to hold the refference to this module. + by the socket layer which has to hold the reference to this module. */ __module_get(THIS_MODULE); list_add(&s->list, &bnep_session_list); @@ -632,7 +632,7 @@ int bnep_del_connection(struct bnep_conndel_req *req) s = __bnep_get_session(req->dst); if (s) { /* Wakeup user-space which is polling for socket errors. - * This is temporary hack untill we have shutdown in L2CAP */ + * This is temporary hack until we have shutdown in L2CAP */ s->sock->sk->sk_err = EUNATCH; /* Kill session thread */ diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index 97f8d68d574d..3487cfe74aec 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -21,7 +21,8 @@ */ #include <linux/module.h> - +#include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -516,33 +517,37 @@ static char *cmtp_procinfo(struct capi_ctr *ctrl) return "CAPI Message Transport Protocol"; } -static int cmtp_ctr_read_proc(char *page, char **start, off_t off, int count, int *eof, struct capi_ctr *ctrl) +static int cmtp_proc_show(struct seq_file *m, void *v) { + struct capi_ctr *ctrl = m->private; struct cmtp_session *session = ctrl->driverdata; struct cmtp_application *app; struct list_head *p, *n; - int len = 0; - len += sprintf(page + len, "%s\n\n", cmtp_procinfo(ctrl)); - len += sprintf(page + len, "addr %s\n", session->name); - len += sprintf(page + len, "ctrl %d\n", session->num); + seq_printf(m, "%s\n\n", cmtp_procinfo(ctrl)); + seq_printf(m, "addr %s\n", session->name); + seq_printf(m, "ctrl %d\n", session->num); list_for_each_safe(p, n, &session->applications) { app = list_entry(p, struct cmtp_application, list); - len += sprintf(page + len, "appl %d -> %d\n", app->appl, app->mapping); + seq_printf(m, "appl %d -> %d\n", app->appl, app->mapping); } - if (off + count >= len) - *eof = 1; - - if (len < off) - return 0; - - *start = page + off; + return 0; +} - return ((count < len - off) ? count : len - off); +static int cmtp_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, cmtp_proc_show, PDE(inode)->data); } +static const struct file_operations cmtp_proc_fops = { + .owner = THIS_MODULE, + .open = cmtp_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; int cmtp_attach_device(struct cmtp_session *session) { @@ -582,7 +587,7 @@ int cmtp_attach_device(struct cmtp_session *session) session->ctrl.send_message = cmtp_send_message; session->ctrl.procinfo = cmtp_procinfo; - session->ctrl.ctr_read_proc = cmtp_ctr_read_proc; + session->ctrl.proc_fops = &cmtp_proc_fops; if (attach_capi_ctr(&session->ctrl) < 0) { BT_ERR("Can't attach new controller"); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 569750010fd3..18e7f5a43dc4 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -770,7 +770,7 @@ static int hidp_setup_hid(struct hidp_session *session, hid = hid_allocate_device(); if (IS_ERR(hid)) - return PTR_ERR(session->hid); + return PTR_ERR(hid); session->hid = hid; session->req = req; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 5129b88c8e5b..1120cf14a548 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1212,6 +1212,7 @@ static void l2cap_monitor_timeout(unsigned long arg) bh_lock_sock(sk); if (l2cap_pi(sk)->retry_count >= l2cap_pi(sk)->remote_max_tx) { l2cap_send_disconn_req(l2cap_pi(sk)->conn, sk); + bh_unlock_sock(sk); return; } @@ -3435,8 +3436,8 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str (pi->unacked_frames > 0)) __mod_retrans_timer(); - l2cap_ertm_send(sk); pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + l2cap_ertm_send(sk); } break; @@ -3471,9 +3472,9 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; if (rx_control & L2CAP_CTRL_POLL) { - l2cap_retransmit_frame(sk, tx_seq); pi->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(sk); + l2cap_retransmit_frame(sk, tx_seq); l2cap_ertm_send(sk); if (pi->conn_state & L2CAP_CONN_WAIT_F) { pi->srej_save_reqseq = tx_seq; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index a2cbe61f6e65..7bc0604069c7 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -467,7 +467,7 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) return 0; } -void br_net_exit(struct net *net) +void __net_exit br_net_exit(struct net *net) { struct net_device *dev; LIST_HEAD(list); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bd1c65425d4f..0b7f262cd148 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1406,6 +1406,9 @@ static int do_ebt_set_ctl(struct sock *sk, { int ret; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + switch(cmd) { case EBT_SO_SET_ENTRIES: ret = do_replace(sock_net(sk), user, len); @@ -1425,6 +1428,9 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) struct ebt_replace tmp; struct ebt_table *t; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; diff --git a/net/can/af_can.c b/net/can/af_can.c index 51adc4c2b860..bc18b084ffdb 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -77,8 +77,8 @@ static int stats_timer __read_mostly = 1; module_param(stats_timer, int, S_IRUGO); MODULE_PARM_DESC(stats_timer, "enable timer for statistics (default:on)"); -HLIST_HEAD(can_rx_dev_list); -static struct dev_rcv_lists can_rx_alldev_list; +/* receive filters subscribed for 'all' CAN devices */ +struct dev_rcv_lists can_rx_alldev_list; static DEFINE_SPINLOCK(can_rcvlists_lock); static struct kmem_cache *rcv_cache __read_mostly; @@ -292,28 +292,10 @@ EXPORT_SYMBOL(can_send); static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev) { - struct dev_rcv_lists *d = NULL; - struct hlist_node *n; - - /* - * find receive list for this device - * - * The hlist_for_each_entry*() macros curse through the list - * using the pointer variable n and set d to the containing - * struct in each list iteration. Therefore, after list - * iteration, d is unmodified when the list is empty, and it - * points to last list element, when the list is non-empty - * but no match in the loop body is found. I.e. d is *not* - * NULL when no match is found. We can, however, use the - * cursor variable n to decide if a match was found. - */ - - hlist_for_each_entry_rcu(d, n, &can_rx_dev_list, list) { - if (d->dev == dev) - break; - } - - return n ? d : NULL; + if (!dev) + return &can_rx_alldev_list; + else + return (struct dev_rcv_lists *)dev->ml_priv; } /** @@ -468,16 +450,6 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask, EXPORT_SYMBOL(can_rx_register); /* - * can_rx_delete_device - rcu callback for dev_rcv_lists structure removal - */ -static void can_rx_delete_device(struct rcu_head *rp) -{ - struct dev_rcv_lists *d = container_of(rp, struct dev_rcv_lists, rcu); - - kfree(d); -} - -/* * can_rx_delete_receiver - rcu callback for single receiver entry removal */ static void can_rx_delete_receiver(struct rcu_head *rp) @@ -541,7 +513,6 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, "dev %s, id %03X, mask %03X\n", DNAME(dev), can_id, mask); r = NULL; - d = NULL; goto out; } @@ -552,10 +523,10 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, can_pstats.rcv_entries--; /* remove device structure requested by NETDEV_UNREGISTER */ - if (d->remove_on_zero_entries && !d->entries) - hlist_del_rcu(&d->list); - else - d = NULL; + if (d->remove_on_zero_entries && !d->entries) { + kfree(d); + dev->ml_priv = NULL; + } out: spin_unlock(&can_rcvlists_lock); @@ -563,10 +534,6 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, /* schedule the receiver item for deletion */ if (r) call_rcu(&r->rcu, can_rx_delete_receiver); - - /* schedule the device structure for deletion */ - if (d) - call_rcu(&d->rcu, can_rx_delete_device); } EXPORT_SYMBOL(can_rx_unregister); @@ -780,48 +747,35 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, case NETDEV_REGISTER: - /* - * create new dev_rcv_lists for this device - * - * N.B. zeroing the struct is the correct initialization - * for the embedded hlist_head structs. - * Another list type, e.g. list_head, would require - * explicit initialization. - */ - + /* create new dev_rcv_lists for this device */ d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) { printk(KERN_ERR "can: allocation of receive list failed\n"); return NOTIFY_DONE; } - d->dev = dev; - - spin_lock(&can_rcvlists_lock); - hlist_add_head_rcu(&d->list, &can_rx_dev_list); - spin_unlock(&can_rcvlists_lock); + BUG_ON(dev->ml_priv); + dev->ml_priv = d; break; case NETDEV_UNREGISTER: spin_lock(&can_rcvlists_lock); - d = find_dev_rcv_lists(dev); + d = dev->ml_priv; if (d) { - if (d->entries) { + if (d->entries) d->remove_on_zero_entries = 1; - d = NULL; - } else - hlist_del_rcu(&d->list); + else { + kfree(d); + dev->ml_priv = NULL; + } } else printk(KERN_ERR "can: notifier: receive list not " "found for dev %s\n", dev->name); spin_unlock(&can_rcvlists_lock); - if (d) - call_rcu(&d->rcu, can_rx_delete_device); - break; } @@ -853,21 +807,13 @@ static __init int can_init(void) { printk(banner); + memset(&can_rx_alldev_list, 0, sizeof(can_rx_alldev_list)); + rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver), 0, 0, NULL); if (!rcv_cache) return -ENOMEM; - /* - * Insert can_rx_alldev_list for reception on all devices. - * This struct is zero initialized which is correct for the - * embedded hlist heads, the dev pointer, and the entries counter. - */ - - spin_lock(&can_rcvlists_lock); - hlist_add_head_rcu(&can_rx_alldev_list.list, &can_rx_dev_list); - spin_unlock(&can_rcvlists_lock); - if (stats_timer) { /* the statistics are updated every second (timer triggered) */ setup_timer(&can_stattimer, can_stat_update, 0); @@ -887,8 +833,7 @@ static __init int can_init(void) static __exit void can_exit(void) { - struct dev_rcv_lists *d; - struct hlist_node *n, *next; + struct net_device *dev; if (stats_timer) del_timer(&can_stattimer); @@ -900,14 +845,19 @@ static __exit void can_exit(void) unregister_netdevice_notifier(&can_netdev_notifier); sock_unregister(PF_CAN); - /* remove can_rx_dev_list */ - spin_lock(&can_rcvlists_lock); - hlist_del(&can_rx_alldev_list.list); - hlist_for_each_entry_safe(d, n, next, &can_rx_dev_list, list) { - hlist_del(&d->list); - kfree(d); + /* remove created dev_rcv_lists from still registered CAN devices */ + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { + if (dev->type == ARPHRD_CAN && dev->ml_priv){ + + struct dev_rcv_lists *d = dev->ml_priv; + + BUG_ON(d->entries); + kfree(d); + dev->ml_priv = NULL; + } } - spin_unlock(&can_rcvlists_lock); + rcu_read_unlock(); rcu_barrier(); /* Wait for completion of call_rcu()'s */ diff --git a/net/can/af_can.h b/net/can/af_can.h index 18f91e37cc30..34253b84e30f 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -63,10 +63,8 @@ struct receiver { enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_EFF, RX_MAX }; +/* per device receive filters linked at dev->ml_priv */ struct dev_rcv_lists { - struct hlist_node list; - struct rcu_head rcu; - struct net_device *dev; struct hlist_head rx[RX_MAX]; struct hlist_head rx_sff[0x800]; int remove_on_zero_entries; diff --git a/net/can/proc.c b/net/can/proc.c index 9b9ad29be567..f4265cc9c3fb 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -45,6 +45,7 @@ #include <linux/proc_fs.h> #include <linux/list.h> #include <linux/rcupdate.h> +#include <linux/if_arp.h> #include <linux/can/core.h> #include "af_can.h" @@ -84,6 +85,9 @@ static const char rx_list_name[][8] = { [RX_EFF] = "rx_eff", }; +/* receive filters subscribed for 'all' CAN devices */ +extern struct dev_rcv_lists can_rx_alldev_list; + /* * af_can statistics stuff */ @@ -190,10 +194,6 @@ void can_stat_update(unsigned long data) /* * proc read functions - * - * From known use-cases we expect about 10 entries in a receive list to be - * printed in the proc_fs. So PAGE_SIZE is definitely enough space here. - * */ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, @@ -202,7 +202,6 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, struct receiver *r; struct hlist_node *n; - rcu_read_lock(); hlist_for_each_entry_rcu(r, n, rx_list, list) { char *fmt = (r->can_id & CAN_EFF_FLAG)? " %-5s %08X %08x %08x %08x %8ld %s\n" : @@ -212,7 +211,6 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, (unsigned long)r->func, (unsigned long)r->data, r->matches, r->ident); } - rcu_read_unlock(); } static void can_print_recv_banner(struct seq_file *m) @@ -346,24 +344,39 @@ static const struct file_operations can_version_proc_fops = { .release = single_release, }; +static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx, + struct net_device *dev, + struct dev_rcv_lists *d) +{ + if (!hlist_empty(&d->rx[idx])) { + can_print_recv_banner(m); + can_print_rcvlist(m, &d->rx[idx], dev); + } else + seq_printf(m, " (%s: no entry)\n", DNAME(dev)); + +} + static int can_rcvlist_proc_show(struct seq_file *m, void *v) { /* double cast to prevent GCC warning */ int idx = (int)(long)m->private; + struct net_device *dev; struct dev_rcv_lists *d; - struct hlist_node *n; seq_printf(m, "\nreceive list '%s':\n", rx_list_name[idx]); rcu_read_lock(); - hlist_for_each_entry_rcu(d, n, &can_rx_dev_list, list) { - if (!hlist_empty(&d->rx[idx])) { - can_print_recv_banner(m); - can_print_rcvlist(m, &d->rx[idx], d->dev); - } else - seq_printf(m, " (%s: no entry)\n", DNAME(d->dev)); + /* receive list for 'all' CAN devices (dev == NULL) */ + d = &can_rx_alldev_list; + can_rcvlist_proc_show_one(m, idx, NULL, d); + + /* receive list for registered CAN devices */ + for_each_netdev_rcu(&init_net, dev) { + if (dev->type == ARPHRD_CAN && dev->ml_priv) + can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv); } + rcu_read_unlock(); seq_putc(m, '\n'); @@ -383,34 +396,50 @@ static const struct file_operations can_rcvlist_proc_fops = { .release = single_release, }; +static inline void can_rcvlist_sff_proc_show_one(struct seq_file *m, + struct net_device *dev, + struct dev_rcv_lists *d) +{ + int i; + int all_empty = 1; + + /* check wether at least one list is non-empty */ + for (i = 0; i < 0x800; i++) + if (!hlist_empty(&d->rx_sff[i])) { + all_empty = 0; + break; + } + + if (!all_empty) { + can_print_recv_banner(m); + for (i = 0; i < 0x800; i++) { + if (!hlist_empty(&d->rx_sff[i])) + can_print_rcvlist(m, &d->rx_sff[i], dev); + } + } else + seq_printf(m, " (%s: no entry)\n", DNAME(dev)); +} + static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) { + struct net_device *dev; struct dev_rcv_lists *d; - struct hlist_node *n; /* RX_SFF */ seq_puts(m, "\nreceive list 'rx_sff':\n"); rcu_read_lock(); - hlist_for_each_entry_rcu(d, n, &can_rx_dev_list, list) { - int i, all_empty = 1; - /* check wether at least one list is non-empty */ - for (i = 0; i < 0x800; i++) - if (!hlist_empty(&d->rx_sff[i])) { - all_empty = 0; - break; - } - - if (!all_empty) { - can_print_recv_banner(m); - for (i = 0; i < 0x800; i++) { - if (!hlist_empty(&d->rx_sff[i])) - can_print_rcvlist(m, &d->rx_sff[i], - d->dev); - } - } else - seq_printf(m, " (%s: no entry)\n", DNAME(d->dev)); + + /* sff receive list for 'all' CAN devices (dev == NULL) */ + d = &can_rx_alldev_list; + can_rcvlist_sff_proc_show_one(m, NULL, d); + + /* sff receive list for registered CAN devices */ + for_each_netdev_rcu(&init_net, dev) { + if (dev->type == ARPHRD_CAN && dev->ml_priv) + can_rcvlist_sff_proc_show_one(m, dev, dev->ml_priv); } + rcu_read_unlock(); seq_putc(m, '\n'); diff --git a/net/compat.c b/net/compat.c index e1a56ade803b..a1fb1b079a82 100644 --- a/net/compat.c +++ b/net/compat.c @@ -754,26 +754,21 @@ asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, size_t len, asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, - struct timespec __user *timeout) + struct compat_timespec __user *timeout) { int datagrams; struct timespec ktspec; - struct compat_timespec __user *utspec; if (timeout == NULL) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, NULL); - utspec = (struct compat_timespec __user *)timeout; - if (get_user(ktspec.tv_sec, &utspec->tv_sec) || - get_user(ktspec.tv_nsec, &utspec->tv_nsec)) + if (get_compat_timespec(&ktspec, timeout)) return -EFAULT; datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, &ktspec); - if (datagrams > 0 && - (put_user(ktspec.tv_sec, &utspec->tv_sec) || - put_user(ktspec.tv_nsec, &utspec->tv_nsec))) + if (datagrams > 0 && put_compat_timespec(&ktspec, timeout)) datagrams = -EFAULT; return datagrams; diff --git a/net/core/dev.c b/net/core/dev.c index c36a17aafcf3..a008f6987a95 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1853,6 +1853,14 @@ gso: skb->next = nskb->next; nskb->next = NULL; + + /* + * If device doesnt need nskb->dst, release it right now while + * its hot in this cpu cache + */ + if (dev->priv_flags & IFF_XMIT_DST_RELEASE) + skb_dst_drop(nskb); + rc = ops->ndo_start_xmit(nskb, dev); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) @@ -2422,6 +2430,7 @@ int netif_receive_skb(struct sk_buff *skb) struct packet_type *ptype, *pt_prev; struct net_device *orig_dev; struct net_device *null_or_orig; + struct net_device *null_or_bond; int ret = NET_RX_DROP; __be16 type; @@ -2487,12 +2496,24 @@ ncls: if (!skb) goto out; + /* + * Make sure frames received on VLAN interfaces stacked on + * bonding interfaces still make their way to any base bonding + * device that may have registered for a specific ptype. The + * handler may have to adjust skb->dev and orig_dev. + */ + null_or_bond = NULL; + if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) && + (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) { + null_or_bond = vlan_dev_real_dev(skb->dev); + } + type = skb->protocol; list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && - (ptype->dev == null_or_orig || ptype->dev == skb->dev || - ptype->dev == orig_dev)) { + if (ptype->type == type && (ptype->dev == null_or_orig || + ptype->dev == skb->dev || ptype->dev == orig_dev || + ptype->dev == null_or_bond)) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -3185,7 +3206,7 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { const struct net_device_stats *stats = dev_get_stats(dev); - seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " + seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, @@ -4771,21 +4792,23 @@ static void net_set_todo(struct net_device *dev) static void rollback_registered_many(struct list_head *head) { - struct net_device *dev; + struct net_device *dev, *tmp; BUG_ON(dev_boot_phase); ASSERT_RTNL(); - list_for_each_entry(dev, head, unreg_list) { + list_for_each_entry_safe(dev, tmp, head, unreg_list) { /* Some devices call without registering - * for initialization unwind. + * for initialization unwind. Remove those + * devices and proceed with the remaining. */ if (dev->reg_state == NETREG_UNINITIALIZED) { pr_debug("unregister_netdevice: device %s/%p never " "was registered\n", dev->name, dev); WARN_ON(1); - return; + list_del(&dev->unreg_list); + continue; } BUG_ON(dev->reg_state != NETREG_REGISTERED); @@ -5033,6 +5056,11 @@ int register_netdevice(struct net_device *dev) rollback_registered(dev); dev->reg_state = NETREG_UNREGISTERED; } + /* + * Prevent userspace races by waiting until the network + * device is fully setup before sending notifications. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); out: return ret; @@ -5595,6 +5623,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); + /* + * Prevent userspace races by waiting until the network + * device is fully setup before sending notifications. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + synchronize_net(); err = 0; out: diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 02a3b2c69c1e..9a24377146bf 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -708,7 +708,7 @@ static struct notifier_block fib_rules_notifier = { .notifier_call = fib_rules_event, }; -static int fib_rules_net_init(struct net *net) +static int __net_init fib_rules_net_init(struct net *net) { INIT_LIST_HEAD(&net->rules_ops); spin_lock_init(&net->rules_mod_lock); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 0b4d0d35ef40..7aa697253765 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -407,11 +407,24 @@ static void arp_reply(struct sk_buff *skb) __be32 sip, tip; unsigned char *sha; struct sk_buff *send_skb; - struct netpoll *np = NULL; + struct netpoll *np, *tmp; + unsigned long flags; + int hits = 0; + + if (list_empty(&npinfo->rx_np)) + return; + + /* Before checking the packet, we do some early + inspection whether this is interesting at all */ + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (np->dev == skb->dev) + hits++; + } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); - if (npinfo->rx_np && npinfo->rx_np->dev == skb->dev) - np = npinfo->rx_np; - if (!np) + /* No netpoll struct is using this dev */ + if (!hits) return; /* No arp on this interface */ @@ -437,77 +450,91 @@ static void arp_reply(struct sk_buff *skb) arp_ptr += skb->dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4; - /* if we actually cared about dst hw addr, it would get copied here */ + /* If we actually cared about dst hw addr, + it would get copied here */ arp_ptr += skb->dev->addr_len; memcpy(&tip, arp_ptr, 4); /* Should we ignore arp? */ - if (tip != np->local_ip || - ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) + if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) return; size = arp_hdr_len(skb->dev); - send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev), - LL_RESERVED_SPACE(np->dev)); - if (!send_skb) - return; - - skb_reset_network_header(send_skb); - arp = (struct arphdr *) skb_put(send_skb, size); - send_skb->dev = skb->dev; - send_skb->protocol = htons(ETH_P_ARP); + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (tip != np->local_ip) + continue; - /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ptype, - sha, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - return; - } + send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev), + LL_RESERVED_SPACE(np->dev)); + if (!send_skb) + continue; - /* - * Fill out the arp protocol part. - * - * we only support ethernet device type, - * which (according to RFC 1390) should always equal 1 (Ethernet). - */ + skb_reset_network_header(send_skb); + arp = (struct arphdr *) skb_put(send_skb, size); + send_skb->dev = skb->dev; + send_skb->protocol = htons(ETH_P_ARP); - arp->ar_hrd = htons(np->dev->type); - arp->ar_pro = htons(ETH_P_IP); - arp->ar_hln = np->dev->addr_len; - arp->ar_pln = 4; - arp->ar_op = htons(type); + /* Fill the device header for the ARP frame */ + if (dev_hard_header(send_skb, skb->dev, ptype, + sha, np->dev->dev_addr, + send_skb->len) < 0) { + kfree_skb(send_skb); + continue; + } - arp_ptr=(unsigned char *)(arp + 1); - memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &tip, 4); - arp_ptr += 4; - memcpy(arp_ptr, sha, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); + /* + * Fill out the arp protocol part. + * + * we only support ethernet device type, + * which (according to RFC 1390) should + * always equal 1 (Ethernet). + */ - netpoll_send_skb(np, send_skb); + arp->ar_hrd = htons(np->dev->type); + arp->ar_pro = htons(ETH_P_IP); + arp->ar_hln = np->dev->addr_len; + arp->ar_pln = 4; + arp->ar_op = htons(type); + + arp_ptr = (unsigned char *)(arp + 1); + memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &tip, 4); + arp_ptr += 4; + memcpy(arp_ptr, sha, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &sip, 4); + + netpoll_send_skb(np, send_skb); + + /* If there are several rx_hooks for the same address, + we're fine by sending a single reply */ + break; + } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); } int __netpoll_rx(struct sk_buff *skb) { int proto, len, ulen; + int hits = 0; struct iphdr *iph; struct udphdr *uh; - struct netpoll_info *npi = skb->dev->npinfo; - struct netpoll *np = npi->rx_np; + struct netpoll_info *npinfo = skb->dev->npinfo; + struct netpoll *np, *tmp; - if (!np) + if (list_empty(&npinfo->rx_np)) goto out; + if (skb->dev->type != ARPHRD_ETHER) goto out; /* check if netpoll clients need ARP */ if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { - skb_queue_tail(&npi->arp_tx, skb); + skb_queue_tail(&npinfo->arp_tx, skb); return 1; } @@ -551,16 +578,23 @@ int __netpoll_rx(struct sk_buff *skb) goto out; if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) goto out; - if (np->local_ip && np->local_ip != iph->daddr) - goto out; - if (np->remote_ip && np->remote_ip != iph->saddr) - goto out; - if (np->local_port && np->local_port != ntohs(uh->dest)) - goto out; - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (np->local_ip && np->local_ip != iph->daddr) + continue; + if (np->remote_ip && np->remote_ip != iph->saddr) + continue; + if (np->local_port && np->local_port != ntohs(uh->dest)) + continue; + + np->rx_hook(np, ntohs(uh->source), + (char *)(uh+1), + ulen - sizeof(struct udphdr)); + hits++; + } + + if (!hits) + goto out; kfree_skb(skb); return 1; @@ -684,6 +718,7 @@ int netpoll_setup(struct netpoll *np) struct net_device *ndev = NULL; struct in_device *in_dev; struct netpoll_info *npinfo; + struct netpoll *npe, *tmp; unsigned long flags; int err; @@ -704,7 +739,7 @@ int netpoll_setup(struct netpoll *np) } npinfo->rx_flags = 0; - npinfo->rx_np = NULL; + INIT_LIST_HEAD(&npinfo->rx_np); spin_lock_init(&npinfo->rx_lock); skb_queue_head_init(&npinfo->arp_tx); @@ -785,7 +820,7 @@ int netpoll_setup(struct netpoll *np) if (np->rx_hook) { spin_lock_irqsave(&npinfo->rx_lock, flags); npinfo->rx_flags |= NETPOLL_RX_ENABLED; - npinfo->rx_np = np; + list_add_tail(&np->rx, &npinfo->rx_np); spin_unlock_irqrestore(&npinfo->rx_lock, flags); } @@ -801,9 +836,16 @@ int netpoll_setup(struct netpoll *np) return 0; release: - if (!ndev->npinfo) + if (!ndev->npinfo) { + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(npe, tmp, &npinfo->rx_np, rx) { + npe->dev = NULL; + } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); + kfree(npinfo); - np->dev = NULL; + } + dev_put(ndev); return err; } @@ -823,10 +865,11 @@ void netpoll_cleanup(struct netpoll *np) if (np->dev) { npinfo = np->dev->npinfo; if (npinfo) { - if (npinfo->rx_np == np) { + if (!list_empty(&npinfo->rx_np)) { spin_lock_irqsave(&npinfo->rx_lock, flags); - npinfo->rx_np = NULL; - npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; + list_del(&np->rx); + if (list_empty(&npinfo->rx_np)) + npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; spin_unlock_irqrestore(&npinfo->rx_lock, flags); } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a23b45f08ec9..de0c2c726420 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -250,8 +250,7 @@ struct pktgen_dev { __u64 count; /* Default No packets to send */ __u64 sofar; /* How many pkts we've sent so far */ __u64 tx_bytes; /* How many bytes we've transmitted */ - __u64 errors; /* Errors when trying to transmit, - pkts will be re-sent */ + __u64 errors; /* Errors when trying to transmit, */ /* runtime counters relating to clone_skb */ @@ -3465,6 +3464,12 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->seq_num++; pkt_dev->tx_bytes += pkt_dev->last_pkt_size; break; + case NET_XMIT_DROP: + case NET_XMIT_CN: + case NET_XMIT_POLICED: + /* skb has been consumed */ + pkt_dev->errors++; + break; default: /* Drivers are not supposed to return other values! */ if (net_ratelimit()) pr_info("pktgen: %s xmit error: %d\n", diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 33148a568199..62f3878a6010 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1364,15 +1364,15 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_UNREGISTER: rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); break; - case NETDEV_REGISTER: - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); - break; case NETDEV_UP: case NETDEV_DOWN: rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); break; + case NETDEV_POST_INIT: + case NETDEV_REGISTER: case NETDEV_CHANGE: case NETDEV_GOING_DOWN: + case NETDEV_UNREGISTER_BATCH: break; default: rtmsg_ifinfo(RTM_NEWLINK, dev, 0); @@ -1386,7 +1386,7 @@ static struct notifier_block rtnetlink_dev_notifier = { }; -static int rtnetlink_net_init(struct net *net) +static int __net_init rtnetlink_net_init(struct net *net) { struct sock *sk; sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX, @@ -1397,7 +1397,7 @@ static int rtnetlink_net_init(struct net *net) return 0; } -static void rtnetlink_net_exit(struct net *net) +static void __net_exit rtnetlink_net_exit(struct net *net) { netlink_kernel_release(net->rtnl); net->rtnl = NULL; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bfa3e7865a8c..93c4e060c91e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -93,7 +93,7 @@ static int sock_pipe_buf_steal(struct pipe_inode_info *pipe, /* Pipe buffer operations for a socket. */ -static struct pipe_buf_operations sock_pipe_buf_ops = { +static const struct pipe_buf_operations sock_pipe_buf_ops = { .can_merge = 0, .map = generic_pipe_buf_map, .unmap = generic_pipe_buf_unmap, diff --git a/net/core/sock.c b/net/core/sock.c index 76ff58d43e26..ceef50bd131b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -741,7 +741,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct timeval tm; } v; - unsigned int lv = sizeof(int); + int lv = sizeof(int); int len; if (get_user(len, optlen)) @@ -1205,6 +1205,10 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) if (newsk->sk_prot->sockets_allocated) percpu_counter_inc(newsk->sk_prot->sockets_allocated); + + if (sock_flag(newsk, SOCK_TIMESTAMP) || + sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE)) + net_enable_timestamp(); } out: return newsk; @@ -2136,13 +2140,13 @@ int sock_prot_inuse_get(struct net *net, struct proto *prot) } EXPORT_SYMBOL_GPL(sock_prot_inuse_get); -static int sock_inuse_init_net(struct net *net) +static int __net_init sock_inuse_init_net(struct net *net) { net->core.inuse = alloc_percpu(struct prot_inuse); return net->core.inuse ? 0 : -ENOMEM; } -static void sock_inuse_exit_net(struct net *net) +static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.inuse); } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index dad7bc4878e0..b195c4feaa0a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -996,7 +996,7 @@ static struct inet_protosw dccp_v4_protosw = { .flags = INET_PROTOSW_ICSK, }; -static int dccp_v4_init_net(struct net *net) +static int __net_init dccp_v4_init_net(struct net *net) { int err; @@ -1005,7 +1005,7 @@ static int dccp_v4_init_net(struct net *net) return err; } -static void dccp_v4_exit_net(struct net *net) +static void __net_exit dccp_v4_exit_net(struct net *net) { inet_ctl_sock_destroy(net->dccp.v4_ctl_sk); } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index baf05cf43c28..1aec6349e858 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1189,7 +1189,7 @@ static struct inet_protosw dccp_v6_protosw = { .flags = INET_PROTOSW_ICSK, }; -static int dccp_v6_init_net(struct net *net) +static int __net_init dccp_v6_init_net(struct net *net) { int err; @@ -1198,7 +1198,7 @@ static int dccp_v6_init_net(struct net *net) return err; } -static void dccp_v6_exit_net(struct net *net) +static void __net_exit dccp_v6_exit_net(struct net *net) { inet_ctl_sock_destroy(net->dccp.v6_ctl_sk); } diff --git a/net/dccp/probe.c b/net/dccp/probe.c index dc328425fa20..a1362dc8abb0 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -43,7 +43,7 @@ static int bufsize = 64 * 1024; static const char procname[] = "dccpprobe"; static struct { - struct kfifo *fifo; + struct kfifo fifo; spinlock_t lock; wait_queue_head_t wait; struct timespec tstart; @@ -67,7 +67,7 @@ static void printl(const char *fmt, ...) len += vscnprintf(tbuf+len, sizeof(tbuf)-len, fmt, args); va_end(args); - kfifo_put(dccpw.fifo, tbuf, len); + kfifo_in_locked(&dccpw.fifo, tbuf, len, &dccpw.lock); wake_up(&dccpw.wait); } @@ -109,7 +109,7 @@ static struct jprobe dccp_send_probe = { static int dccpprobe_open(struct inode *inode, struct file *file) { - kfifo_reset(dccpw.fifo); + kfifo_reset(&dccpw.fifo); getnstimeofday(&dccpw.tstart); return 0; } @@ -131,11 +131,11 @@ static ssize_t dccpprobe_read(struct file *file, char __user *buf, return -ENOMEM; error = wait_event_interruptible(dccpw.wait, - __kfifo_len(dccpw.fifo) != 0); + kfifo_len(&dccpw.fifo) != 0); if (error) goto out_free; - cnt = kfifo_get(dccpw.fifo, tbuf, len); + cnt = kfifo_out_locked(&dccpw.fifo, tbuf, len, &dccpw.lock); error = copy_to_user(buf, tbuf, cnt) ? -EFAULT : 0; out_free: @@ -156,10 +156,8 @@ static __init int dccpprobe_init(void) init_waitqueue_head(&dccpw.wait); spin_lock_init(&dccpw.lock); - dccpw.fifo = kfifo_alloc(bufsize, GFP_KERNEL, &dccpw.lock); - if (IS_ERR(dccpw.fifo)) - return PTR_ERR(dccpw.fifo); - + if (kfifo_alloc(&dccpw.fifo, bufsize, GFP_KERNEL)) + return ret; if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &dccpprobe_fops)) goto err0; @@ -172,14 +170,14 @@ static __init int dccpprobe_init(void) err1: proc_net_remove(&init_net, procname); err0: - kfifo_free(dccpw.fifo); + kfifo_free(&dccpw.fifo); return ret; } module_init(dccpprobe_init); static __exit void dccpprobe_exit(void) { - kfifo_free(dccpw.fifo); + kfifo_free(&dccpw.fifo); proc_net_remove(&init_net, procname); unregister_jprobe(&dccp_send_probe); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index dd3db88f8f0a..205a1c12f3c0 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -73,8 +73,8 @@ __setup("ether=", netdev_boot_setup); * @len: packet length (<= skb->len) * * - * Set the protocol type. For a packet of type ETH_P_802_3 we put the length - * in here instead. It is up to the 802.2 layer to carry protocol information. + * Set the protocol type. For a packet of type ETH_P_802_3/2 we put the length + * in here instead. */ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -82,7 +82,7 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, { struct ethhdr *eth = (struct ethhdr *)skb_push(skb, ETH_HLEN); - if (type != ETH_P_802_3) + if (type != ETH_P_802_3 && type != ETH_P_802_2) eth->h_proto = htons(type); else eth->h_proto = htons(len); diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 70491d9035eb..0c94a1ac2946 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -166,7 +166,7 @@ config IP_PNP_DHCP If unsure, say Y. Note that if you want to use DHCP, a DHCP server must be operating on your network. Read - <file:Documentation/filesystems/nfsroot.txt> for details. + <file:Documentation/filesystems/nfs/nfsroot.txt> for details. config IP_PNP_BOOTP bool "IP: BOOTP support" @@ -181,7 +181,7 @@ config IP_PNP_BOOTP does BOOTP itself, providing all necessary information on the kernel command line, you can say N here. If unsure, say Y. Note that if you want to use BOOTP, a BOOTP server must be operating on your network. - Read <file:Documentation/filesystems/nfsroot.txt> for details. + Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details. config IP_PNP_RARP bool "IP: RARP support" @@ -194,7 +194,7 @@ config IP_PNP_RARP older protocol which is being obsoleted by BOOTP and DHCP), say Y here. Note that if you want to use RARP, a RARP server must be operating on your network. Read - <file:Documentation/filesystems/nfsroot.txt> for details. + <file:Documentation/filesystems/nfs/nfsroot.txt> for details. # not yet ready.. # bool ' IP: ARP support' CONFIG_IP_PNP_ARP diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index c95cd93acf29..1940b4df7699 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -70,6 +70,7 @@ * bonding can change the skb before * sending (e.g. insert 8021q tag). * Harald Welte : convert to make use of jenkins hash + * Jesper D. Brouer: Proxy ARP PVLAN RFC 3069 support. */ #include <linux/module.h> @@ -524,12 +525,15 @@ int arp_bind_neighbour(struct dst_entry *dst) /* * Check if we can use proxy ARP for this path */ - -static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt) +static inline int arp_fwd_proxy(struct in_device *in_dev, + struct net_device *dev, struct rtable *rt) { struct in_device *out_dev; int imi, omi = -1; + if (rt->u.dst.dev == dev) + return 0; + if (!IN_DEV_PROXY_ARP(in_dev)) return 0; @@ -548,6 +552,43 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt) } /* + * Check for RFC3069 proxy arp private VLAN (allow to send back to same dev) + * + * RFC3069 supports proxy arp replies back to the same interface. This + * is done to support (ethernet) switch features, like RFC 3069, where + * the individual ports are not allowed to communicate with each + * other, BUT they are allowed to talk to the upstream router. As + * described in RFC 3069, it is possible to allow these hosts to + * communicate through the upstream router, by proxy_arp'ing. + * + * RFC 3069: "VLAN Aggregation for Efficient IP Address Allocation" + * + * This technology is known by different names: + * In RFC 3069 it is called VLAN Aggregation. + * Cisco and Allied Telesyn call it Private VLAN. + * Hewlett-Packard call it Source-Port filtering or port-isolation. + * Ericsson call it MAC-Forced Forwarding (RFC Draft). + * + */ +static inline int arp_fwd_pvlan(struct in_device *in_dev, + struct net_device *dev, struct rtable *rt, + __be32 sip, __be32 tip) +{ + /* Private VLAN is only concerned about the same ethernet segment */ + if (rt->u.dst.dev != dev) + return 0; + + /* Don't reply on self probes (often done by windowz boxes)*/ + if (sip == tip) + return 0; + + if (IN_DEV_PROXY_ARP_PVLAN(in_dev)) + return 1; + else + return 0; +} + +/* * Interface to link layer: send routine and receive handler. */ @@ -833,8 +874,11 @@ static int arp_process(struct sk_buff *skb) } goto out; } else if (IN_DEV_FORWARD(in_dev)) { - if (addr_type == RTN_UNICAST && rt->u.dst.dev != dev && - (arp_fwd_proxy(in_dev, rt) || pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) { + if (addr_type == RTN_UNICAST && + (arp_fwd_proxy(in_dev, dev, rt) || + arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || + pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) + { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); @@ -863,7 +907,8 @@ static int arp_process(struct sk_buff *skb) devices (strip is candidate) */ if (n == NULL && - arp->ar_op == htons(ARPOP_REPLY) && + (arp->ar_op == htons(ARPOP_REPLY) || + (arp->ar_op == htons(ARPOP_REQUEST) && tip == sip)) && inet_addr_type(net, sip) == RTN_UNICAST) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5cdbc102a418..cd71a3908391 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1397,6 +1397,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), + DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), @@ -1407,6 +1408,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), + DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 3323168ee52d..9b3e28ed5240 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -252,6 +252,8 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, no_addr = in_dev->ifa_list == NULL; rpf = IN_DEV_RPFILTER(in_dev); accept_local = IN_DEV_ACCEPT_LOCAL(in_dev); + if (mark && !IN_DEV_SRC_VMARK(in_dev)) + fl.mark = 0; } rcu_read_unlock(); @@ -881,7 +883,7 @@ static void nl_fib_input(struct sk_buff *skb) netlink_unicast(net->ipv4.fibnl, skb, pid, MSG_DONTWAIT); } -static int nl_fib_lookup_init(struct net *net) +static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0, @@ -1002,7 +1004,7 @@ fail: return err; } -static void __net_exit ip_fib_net_exit(struct net *net) +static void ip_fib_net_exit(struct net *net) { unsigned int i; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ed19aa6919c2..96b21011a3e4 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -62,8 +62,8 @@ static DEFINE_SPINLOCK(fib_multipath_lock); #define for_nexthops(fi) { int nhsel; const struct fib_nh * nh; \ for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) -#define change_nexthops(fi) { int nhsel; struct fib_nh * nh; \ -for (nhsel=0, nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++) +#define change_nexthops(fi) { int nhsel; struct fib_nh *nexthop_nh; \ +for (nhsel=0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nexthop_nh++, nhsel++) #else /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -72,7 +72,7 @@ for (nhsel=0, nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, #define for_nexthops(fi) { int nhsel = 0; const struct fib_nh * nh = (fi)->fib_nh; \ for (nhsel=0; nhsel < 1; nhsel++) -#define change_nexthops(fi) { int nhsel = 0; struct fib_nh * nh = (struct fib_nh *)((fi)->fib_nh); \ +#define change_nexthops(fi) { int nhsel = 0; struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ for (nhsel=0; nhsel < 1; nhsel++) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -145,9 +145,9 @@ void free_fib_info(struct fib_info *fi) return; } change_nexthops(fi) { - if (nh->nh_dev) - dev_put(nh->nh_dev); - nh->nh_dev = NULL; + if (nexthop_nh->nh_dev) + dev_put(nexthop_nh->nh_dev); + nexthop_nh->nh_dev = NULL; } endfor_nexthops(fi); fib_info_cnt--; release_net(fi->fib_net); @@ -162,9 +162,9 @@ void fib_release_info(struct fib_info *fi) if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); change_nexthops(fi) { - if (!nh->nh_dev) + if (!nexthop_nh->nh_dev) continue; - hlist_del(&nh->nh_hash); + hlist_del(&nexthop_nh->nh_hash); } endfor_nexthops(fi) fi->fib_dead = 1; fib_info_put(fi); @@ -395,19 +395,20 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (!rtnh_ok(rtnh, remaining)) return -EINVAL; - nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; - nh->nh_oif = rtnh->rtnh_ifindex; - nh->nh_weight = rtnh->rtnh_hops + 1; + nexthop_nh->nh_flags = + (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; + nexthop_nh->nh_oif = rtnh->rtnh_ifindex; + nexthop_nh->nh_weight = rtnh->rtnh_hops + 1; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); - nh->nh_gw = nla ? nla_get_be32(nla) : 0; + nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0; #ifdef CONFIG_NET_CLS_ROUTE nla = nla_find(attrs, attrlen, RTA_FLOW); - nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; + nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; #endif } @@ -738,7 +739,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_nhs = nhs; change_nexthops(fi) { - nh->nh_parent = fi; + nexthop_nh->nh_parent = fi; } endfor_nexthops(fi) if (cfg->fc_mx) { @@ -808,7 +809,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto failure; } else { change_nexthops(fi) { - if ((err = fib_check_nh(cfg, fi, nh)) != 0) + if ((err = fib_check_nh(cfg, fi, nexthop_nh)) != 0) goto failure; } endfor_nexthops(fi) } @@ -843,11 +844,11 @@ link_it: struct hlist_head *head; unsigned int hash; - if (!nh->nh_dev) + if (!nexthop_nh->nh_dev) continue; - hash = fib_devindex_hashfn(nh->nh_dev->ifindex); + hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex); head = &fib_info_devhash[hash]; - hlist_add_head(&nh->nh_hash, head); + hlist_add_head(&nexthop_nh->nh_hash, head); } endfor_nexthops(fi) spin_unlock_bh(&fib_info_lock); return fi; @@ -1080,21 +1081,21 @@ int fib_sync_down_dev(struct net_device *dev, int force) prev_fi = fi; dead = 0; change_nexthops(fi) { - if (nh->nh_flags&RTNH_F_DEAD) + if (nexthop_nh->nh_flags&RTNH_F_DEAD) dead++; - else if (nh->nh_dev == dev && - nh->nh_scope != scope) { - nh->nh_flags |= RTNH_F_DEAD; + else if (nexthop_nh->nh_dev == dev && + nexthop_nh->nh_scope != scope) { + nexthop_nh->nh_flags |= RTNH_F_DEAD; #ifdef CONFIG_IP_ROUTE_MULTIPATH spin_lock_bh(&fib_multipath_lock); - fi->fib_power -= nh->nh_power; - nh->nh_power = 0; + fi->fib_power -= nexthop_nh->nh_power; + nexthop_nh->nh_power = 0; spin_unlock_bh(&fib_multipath_lock); #endif dead++; } #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (force > 1 && nh->nh_dev == dev) { + if (force > 1 && nexthop_nh->nh_dev == dev) { dead = fi->fib_nhs; break; } @@ -1144,18 +1145,20 @@ int fib_sync_up(struct net_device *dev) prev_fi = fi; alive = 0; change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD)) { + if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) { alive++; continue; } - if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP)) + if (nexthop_nh->nh_dev == NULL || + !(nexthop_nh->nh_dev->flags&IFF_UP)) continue; - if (nh->nh_dev != dev || !__in_dev_get_rtnl(dev)) + if (nexthop_nh->nh_dev != dev || + !__in_dev_get_rtnl(dev)) continue; alive++; spin_lock_bh(&fib_multipath_lock); - nh->nh_power = 0; - nh->nh_flags &= ~RTNH_F_DEAD; + nexthop_nh->nh_power = 0; + nexthop_nh->nh_flags &= ~RTNH_F_DEAD; spin_unlock_bh(&fib_multipath_lock); } endfor_nexthops(fi) @@ -1182,9 +1185,9 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res) if (fi->fib_power <= 0) { int power = 0; change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD)) { - power += nh->nh_weight; - nh->nh_power = nh->nh_weight; + if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) { + power += nexthop_nh->nh_weight; + nexthop_nh->nh_power = nexthop_nh->nh_weight; } } endfor_nexthops(fi); fi->fib_power = power; @@ -1204,9 +1207,10 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res) w = jiffies % fi->fib_power; change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) { - if ((w -= nh->nh_power) <= 0) { - nh->nh_power--; + if (!(nexthop_nh->nh_flags&RTNH_F_DEAD) && + nexthop_nh->nh_power) { + if ((w -= nexthop_nh->nh_power) <= 0) { + nexthop_nh->nh_power--; fi->fib_power--; res->nh_sel = nhsel; spin_unlock_bh(&fib_multipath_lock); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 76c08402c933..8f5468393f01 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2603,7 +2603,7 @@ static const struct file_operations igmp_mcf_seq_fops = { .release = seq_release_net, }; -static int igmp_net_init(struct net *net) +static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; @@ -2621,7 +2621,7 @@ out_igmp: return -ENOMEM; } -static void igmp_net_exit(struct net *net) +static void __net_exit igmp_net_exit(struct net *net) { proc_net_remove(net, "mcfilter"); proc_net_remove(net, "igmp"); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index ee16475f8fc3..8da6429269dd 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -529,6 +529,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, syn_ack_recalc(req, thresh, max_retries, queue->rskq_defer_accept, &expire, &resend); + if (req->rsk_ops->syn_ack_timeout) + req->rsk_ops->syn_ack_timeout(parent, req); if (!expire && (!resend || !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 86964b353c31..891c72aea520 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -646,7 +646,7 @@ static struct ctl_table ip4_frags_ctl_table[] = { { } }; -static int ip4_frags_ns_ctl_register(struct net *net) +static int __net_init ip4_frags_ns_ctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -676,7 +676,7 @@ err_alloc: return -ENOMEM; } -static void ip4_frags_ns_ctl_unregister(struct net *net) +static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) { struct ctl_table *table; @@ -704,7 +704,7 @@ static inline void ip4_frags_ctl_register(void) } #endif -static int ipv4_frags_init_net(struct net *net) +static int __net_init ipv4_frags_init_net(struct net *net) { /* * Fragment cache limits. We will commit 256K at one time. Should we @@ -726,7 +726,7 @@ static int ipv4_frags_init_net(struct net *net) return ip4_frags_ns_ctl_register(net); } -static void ipv4_frags_exit_net(struct net *net) +static void __net_exit ipv4_frags_exit_net(struct net *net) { ip4_frags_ns_ctl_unregister(net); inet_frags_exit_net(&net->ipv4.frags, &ip4_frags); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f36ce156cac6..7631b20490f5 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1307,7 +1307,7 @@ static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head) } } -static int ipgre_init_net(struct net *net) +static int __net_init ipgre_init_net(struct net *net) { struct ipgre_net *ign = net_generic(net, ipgre_net_id); int err; @@ -1334,7 +1334,7 @@ err_alloc_dev: return err; } -static void ipgre_exit_net(struct net *net) +static void __net_exit ipgre_exit_net(struct net *net) { struct ipgre_net *ign; LIST_HEAD(list); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e34013a78ef4..3451799e3dbf 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -254,7 +254,7 @@ int ip_mc_output(struct sk_buff *skb) */ if (rt->rt_flags&RTCF_MULTICAST) { - if ((!sk || inet_sk(sk)->mc_loop) + if (sk_mc_loop(sk) #ifdef CONFIG_IP_MROUTE /* Small optimization: do not loopback not local frames, which returned after forwarding; they will be dropped diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index cafad9baff03..644dc43a55de 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -451,7 +451,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, (1<<IP_TTL) | (1<<IP_HDRINCL) | (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) | (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | - (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT))) || + (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) | + (1<<IP_MINTTL))) || optname == IP_MULTICAST_TTL || optname == IP_MULTICAST_ALL || optname == IP_MULTICAST_LOOP || @@ -936,6 +937,14 @@ mc_msf_out: inet->transparent = !!val; break; + case IP_MINTTL: + if (optlen < 1) + goto e_inval; + if (val < 0 || val > 255) + goto e_inval; + inet->min_ttl = val; + break; + default: err = -ENOPROTOOPT; break; @@ -1198,6 +1207,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_TRANSPARENT: val = inet->transparent; break; + case IP_MINTTL: + val = inet->min_ttl; + break; default: release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 4e08b7f2331c..10a6a604bf32 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1446,7 +1446,7 @@ late_initcall(ip_auto_config); /* * Decode any IP configuration options in the "ip=" or "nfsaddrs=" kernel - * command line parameter. See Documentation/filesystems/nfsroot.txt. + * command line parameter. See Documentation/filesystems/nfs/nfsroot.txt. */ static int __init ic_proto_name(char *name) { diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index eda04fed3379..95db732e542b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -130,7 +130,6 @@ struct ipip_net { struct net_device *fb_tunnel_dev; }; -static void ipip_fb_tunnel_init(struct net_device *dev); static void ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); @@ -730,7 +729,7 @@ static void ipip_tunnel_init(struct net_device *dev) ipip_tunnel_bind_dev(dev); } -static void ipip_fb_tunnel_init(struct net_device *dev) +static void __net_init ipip_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -773,7 +772,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) } } -static int ipip_init_net(struct net *net) +static int __net_init ipip_init_net(struct net *net) { struct ipip_net *ipn = net_generic(net, ipip_net_id); int err; @@ -806,7 +805,7 @@ err_alloc_dev: return err; } -static void ipip_exit_net(struct net *net) +static void __net_exit ipip_exit_net(struct net *net) { struct ipip_net *ipn = net_generic(net, ipip_net_id); LIST_HEAD(list); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 549e206cdd42..ea5cea2415c1 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -50,7 +50,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo) struct tcphdr _tcph, *tcph; __be16 oldval; - /* Not enought header? */ + /* Not enough header? */ tcph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph); if (!tcph) return false; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index fa2d6b6fc3e5..331ead3ebd1b 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -14,6 +14,7 @@ #include <net/route.h> #include <net/ip.h> +#include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv4.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> @@ -34,6 +35,20 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } +static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, + struct sk_buff *skb) +{ +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge && + skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + return IP_DEFRAG_CONNTRACK_BRIDGE_IN; +#endif + if (hooknum == NF_INET_PRE_ROUTING) + return IP_DEFRAG_CONNTRACK_IN; + else + return IP_DEFRAG_CONNTRACK_OUT; +} + static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, @@ -50,10 +65,8 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, #endif /* Gather fragments. */ if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { - if (nf_ct_ipv4_gather_frags(skb, - hooknum == NF_INET_PRE_ROUTING ? - IP_DEFRAG_CONNTRACK_IN : - IP_DEFRAG_CONNTRACK_OUT)) + enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb); + if (nf_ct_ipv4_gather_frags(skb, user)) return NF_STOLEN; } return NF_ACCEPT; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e446496f564f..1cc339441e7d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1988,8 +1988,13 @@ static int __mkroute_input(struct sk_buff *skb, if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is * invalid for proxy arp. DNAT routes are always valid. + * + * Proxy arp feature have been extended to allow, ARP + * replies back to the same interface, to support + * Private VLAN switch technologies. See arp.c. */ - if (out_dev == in_dev) { + if (out_dev == in_dev && + IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { err = -EINVAL; goto cleanup; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 26399ad2a289..5c24db4a3c91 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -277,6 +277,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + + if (tcp_opt.saw_tstamp) + cookie_check_timestamp(&tcp_opt); + ret = NULL; req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) @@ -292,6 +299,12 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; ireq->ecn_ok = 0; + ireq->snd_wscale = tcp_opt.snd_wscale; + ireq->rcv_wscale = tcp_opt.rcv_wscale; + ireq->sack_ok = tcp_opt.sack_ok; + ireq->wscale_ok = tcp_opt.wscale_ok; + ireq->tstamp_ok = tcp_opt.saw_tstamp; + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -340,26 +353,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, } } - /* check for timestamp cookie support */ - memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst); - - if (tcp_opt.saw_tstamp) - cookie_check_timestamp(&tcp_opt); - - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->rcv_wscale = tcp_opt.rcv_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - /* Try to redo what tcp_v4_send_synack did. */ req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, &req->rcv_wnd, &req->window_clamp, - ireq->wscale_ok, &rcv_wscale); + ireq->wscale_ok, &rcv_wscale, + dst_metric(&rt->u.dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b0a26bb25e2e..d5d69ea8f249 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -536,8 +536,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb) tp->nonagle &= ~TCP_NAGLE_PUSH; } -static inline void tcp_mark_urg(struct tcp_sock *tp, int flags, - struct sk_buff *skb) +static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) { if (flags & MSG_OOB) tp->snd_up = tp->write_seq; @@ -546,13 +545,13 @@ static inline void tcp_mark_urg(struct tcp_sock *tp, int flags, static inline void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle) { - struct tcp_sock *tp = tcp_sk(sk); - if (tcp_send_head(sk)) { - struct sk_buff *skb = tcp_write_queue_tail(sk); + struct tcp_sock *tp = tcp_sk(sk); + if (!(flags & MSG_MORE) || forced_push(tp)) - tcp_mark_push(tp, skb); - tcp_mark_urg(tp, flags, skb); + tcp_mark_push(tp, tcp_write_queue_tail(sk)); + + tcp_mark_urg(tp, flags); __tcp_push_pending_frames(sk, mss_now, (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle); } @@ -877,12 +876,12 @@ ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset, #define TCP_PAGE(sk) (sk->sk_sndmsg_page) #define TCP_OFF(sk) (sk->sk_sndmsg_off) -static inline int select_size(struct sock *sk) +static inline int select_size(struct sock *sk, int sg) { struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache; - if (sk->sk_route_caps & NETIF_F_SG) { + if (sg) { if (sk_can_gso(sk)) tmp = 0; else { @@ -906,7 +905,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct sk_buff *skb; int iovlen, flags; int mss_now, size_goal; - int err, copied; + int sg, err, copied; long timeo; lock_sock(sk); @@ -934,6 +933,8 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto out_err; + sg = sk->sk_route_caps & NETIF_F_SG; + while (--iovlen >= 0) { int seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; @@ -959,8 +960,9 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - skb = sk_stream_alloc_skb(sk, select_size(sk), - sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, + select_size(sk, sg), + sk->sk_allocation); if (!skb) goto wait_for_memory; @@ -997,9 +999,7 @@ new_segment: /* We can extend the last page * fragment. */ merge = 1; - } else if (i == MAX_SKB_FRAGS || - (!i && - !(sk->sk_route_caps & NETIF_F_SG))) { + } else if (i == MAX_SKB_FRAGS || !sg) { /* Need to add new fragment and cannot * do this because interface is non-SG, * or because all the page slots are diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 12cab7d74dba..28e029632493 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3727,7 +3727,7 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - u8 **hvpp, int estab, struct dst_entry *dst) + u8 **hvpp, int estab) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); @@ -3766,8 +3766,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && sysctl_tcp_window_scaling && - !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) { + !estab && sysctl_tcp_window_scaling) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > 14) { @@ -3783,8 +3782,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && sysctl_tcp_timestamps && - !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) { + (!estab && sysctl_tcp_timestamps))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -3792,8 +3790,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && sysctl_tcp_sack && - !dst_feature(dst, RTAX_FEATURE_NO_SACK)) { + !estab && sysctl_tcp_sack) { opt_rx->sack_ok = 1; tcp_sack_reset(opt_rx); } @@ -3878,7 +3875,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, if (tcp_parse_aligned_timestamp(tp, th)) return 1; } - tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1); return 1; } @@ -4133,10 +4130,8 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack && - !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack) { int mib_idx; if (before(seq, tp->rcv_nxt)) @@ -4165,15 +4160,13 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack && - !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) @@ -5428,11 +5421,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); struct tcp_cookie_values *cvp = tp->cookie_values; int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst); + tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0); if (th->ack) { /* rfc793: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 15e96030ce47..c3588b4fd979 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -742,9 +742,9 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, * This still operates on a request_sock only, not on a big * socket. */ -static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, - struct request_sock *req, - struct request_values *rvp) +static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, + struct request_sock *req, + struct request_values *rvp) { const struct inet_request_sock *ireq = inet_rsk(req); int err = -1; @@ -775,10 +775,11 @@ static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, return err; } -static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, +static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { - return __tcp_v4_send_synack(sk, NULL, req, rvp); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + return tcp_v4_send_synack(sk, NULL, req, rvp); } /* @@ -1192,10 +1193,11 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb) struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), - .rtx_syn_ack = tcp_v4_send_synack, + .rtx_syn_ack = tcp_v4_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, + .syn_ack_timeout = tcp_syn_ack_timeout, }; #ifdef CONFIG_TCP_MD5SIG @@ -1262,20 +1264,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops; #endif - ireq = inet_rsk(req); - ireq->loc_addr = daddr; - ireq->rmt_addr = saddr; - ireq->no_srccheck = inet_sk(sk)->transparent; - ireq->opt = tcp_v4_save_options(sk, skb); - - dst = inet_csk_route_req(sk, req); - if(!dst) - goto drop_and_free; - tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = TCP_MSS_DEFAULT; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && @@ -1319,8 +1311,14 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb); + ireq = inet_rsk(req); + ireq->loc_addr = daddr; + ireq->rmt_addr = saddr; + ireq->no_srccheck = inet_sk(sk)->transparent; + ireq->opt = tcp_v4_save_options(sk, skb); + if (security_inet_conn_request(sk, skb, req)) - goto drop_and_release; + goto drop_and_free; if (!want_cookie) TCP_ECN_create_request(req, tcp_hdr(skb)); @@ -1345,6 +1343,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && + (dst = inet_csk_route_req(sk, req)) != NULL && (peer = rt_get_peer((struct rtable *)dst)) != NULL && peer->v4daddr == saddr) { if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && @@ -1376,8 +1375,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) } tcp_rsk(req)->snt_isn = isn; - if (__tcp_v4_send_synack(sk, dst, req, - (struct request_values *)&tmp_ext) || + if (tcp_v4_send_synack(sk, dst, req, + (struct request_values *)&tmp_ext) || want_cookie) goto drop_and_free; @@ -1652,6 +1651,9 @@ int tcp_v4_rcv(struct sk_buff *skb) if (!sk) goto no_tcp_socket; + if (iph->ttl < inet_sk(sk)->min_ttl) + goto discard_and_relse; + process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; @@ -2428,12 +2430,12 @@ static struct tcp_seq_afinfo tcp4_seq_afinfo = { }, }; -static int tcp4_proc_init_net(struct net *net) +static int __net_init tcp4_proc_init_net(struct net *net) { return tcp_proc_register(net, &tcp4_seq_afinfo); } -static void tcp4_proc_exit_net(struct net *net) +static void __net_exit tcp4_proc_exit_net(struct net *net) { tcp_proc_unregister(net, &tcp4_seq_afinfo); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 87accec8d097..f206ee5dda80 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -95,9 +95,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); int paws_reject = 0; + tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tmp_opt.tstamp_ok = 1; - tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -526,9 +526,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); int paws_reject = 0; - if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) { - tmp_opt.tstamp_ok = 1; - tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); + tmp_opt.saw_tstamp = 0; + if (th->doff > (sizeof(struct tcphdr)>>2)) { + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 93316a96d820..4a1605d3f909 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -183,7 +183,8 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) */ void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, - int wscale_ok, __u8 *rcv_wscale) + int wscale_ok, __u8 *rcv_wscale, + __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); @@ -232,7 +233,13 @@ void tcp_select_initial_window(int __space, __u32 mss, init_cwnd = 2; else if (mss > 1460) init_cwnd = 3; - if (*rcv_wnd > init_cwnd * mss) + /* when initializing use the value from init_rcv_wnd + * rather than the default from above + */ + if (init_rcv_wnd && + (*rcv_wnd > init_rcv_wnd * mss)) + *rcv_wnd = init_rcv_wnd * mss; + else if (*rcv_wnd > init_cwnd * mss) *rcv_wnd = init_cwnd * mss; } @@ -553,7 +560,6 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_cookie_values *cvp = tp->cookie_values; - struct dst_entry *dst = __sk_dst_get(sk); unsigned remaining = MAX_TCP_OPTION_SPACE; u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? tcp_cookie_size_check(cvp->cookie_desired) : @@ -581,22 +587,18 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && - !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) && - *md5 == NULL)) { + if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sysctl_tcp_window_scaling && - !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) { + if (likely(sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sysctl_tcp_sack && - !dst_feature(dst, RTAX_FEATURE_NO_SACK))) { + if (likely(sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; @@ -1799,11 +1801,6 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { - struct sk_buff *skb = tcp_send_head(sk); - - if (!skb) - return; - /* If we are closed, the bytes will have to remain here. * In time closedown will finish, we empty the write queue and * all will be happy. @@ -2427,7 +2424,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, &req->rcv_wnd, &req->window_clamp, ireq->wscale_ok, - &rcv_wscale); + &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; } @@ -2527,9 +2525,7 @@ static void tcp_connect_init(struct sock *sk) * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr) + - (sysctl_tcp_timestamps && - (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ? - TCPOLEN_TSTAMP_ALIGNED : 0)); + (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk) != NULL) @@ -2555,9 +2551,9 @@ static void tcp_connect_init(struct sock *sk) tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - (sysctl_tcp_window_scaling && - !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)), - &rcv_wscale); + sysctl_tcp_window_scaling, + &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8816a20c2597..de7d1bf9114f 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -474,6 +474,12 @@ static void tcp_synack_timer(struct sock *sk) TCP_TIMEOUT_INIT, TCP_RTO_MAX); } +void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req) +{ + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); +} +EXPORT_SYMBOL(tcp_syn_ack_timeout); + void tcp_set_keepalive(struct sock *sk, int val) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1f9534846ca9..4f7d2122d818 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -216,9 +216,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, * force rand to be an odd multiple of UDP_HTABLE_SIZE */ rand = (rand | 1) * (udptable->mask + 1); - for (last = first + udptable->mask + 1; - first != last; - first++) { + last = first + udptable->mask + 1; + do { hslot = udp_hashslot(udptable, net, first); bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); @@ -238,7 +237,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, snum += rand; } while (snum != first); spin_unlock_bh(&hslot->lock); - } + } while (++first != last); goto fail; } else { hslot = udp_hashslot(udptable, net, snum); @@ -2028,12 +2027,12 @@ static struct udp_seq_afinfo udp4_seq_afinfo = { }, }; -static int udp4_proc_init_net(struct net *net) +static int __net_init udp4_proc_init_net(struct net *net) { return udp_proc_register(net, &udp4_seq_afinfo); } -static void udp4_proc_exit_net(struct net *net) +static void __net_exit udp4_proc_exit_net(struct net *net) { udp_proc_unregister(net, &udp4_seq_afinfo); } diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 66f79513f4a5..6610bf76369f 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -81,12 +81,12 @@ static struct udp_seq_afinfo udplite4_seq_afinfo = { }, }; -static int udplite4_proc_init_net(struct net *net) +static int __net_init udplite4_proc_init_net(struct net *net) { return udp_proc_register(net, &udplite4_seq_afinfo); } -static void udplite4_proc_exit_net(struct net *net) +static void __net_exit udplite4_proc_exit_net(struct net *net) { udp_proc_unregister(net, &udplite4_seq_afinfo); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index de7a194a64ab..1593289155ff 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3027,14 +3027,14 @@ static const struct file_operations if6_fops = { .release = seq_release_net, }; -static int if6_proc_net_init(struct net *net) +static int __net_init if6_proc_net_init(struct net *net) { if (!proc_net_fops_create(net, "if_inet6", S_IRUGO, &if6_fops)) return -ENOMEM; return 0; } -static void if6_proc_net_exit(struct net *net) +static void __net_exit if6_proc_net_exit(struct net *net) { proc_net_remove(net, "if_inet6"); } @@ -4418,7 +4418,7 @@ static void addrconf_sysctl_unregister(struct inet6_dev *idev) #endif -static int addrconf_init_net(struct net *net) +static int __net_init addrconf_init_net(struct net *net) { int err; struct ipv6_devconf *all, *dflt; @@ -4467,7 +4467,7 @@ err_alloc_all: return err; } -static void addrconf_exit_net(struct net *net) +static void __net_exit addrconf_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL __addrconf_sysctl_unregister(net->ipv6.devconf_dflt); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 12e69d364dd5..e29160ff4a0f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -999,7 +999,7 @@ err_udplite_mib: return -ENOMEM; } -static void __net_exit ipv6_cleanup_mibs(struct net *net) +static void ipv6_cleanup_mibs(struct net *net) { snmp_mib_free((void **)net->mib.udp_stats_in6); snmp_mib_free((void **)net->mib.udplite_stats_in6); @@ -1042,7 +1042,7 @@ out: #endif } -static void inet6_net_exit(struct net *net) +static void __net_exit inet6_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS udp6_proc_exit(net); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index f1c74c8ef9de..c4f6ca32fa74 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -538,7 +538,7 @@ static const struct file_operations ac6_seq_fops = { .release = seq_release_net, }; -int ac6_proc_init(struct net *net) +int __net_init ac6_proc_init(struct net *net) { if (!proc_net_fops_create(net, "anycast6", S_IRUGO, &ac6_seq_fops)) return -ENOMEM; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b7aa7c64cc4a..551882b9dfd6 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -262,7 +262,7 @@ static struct fib_rules_ops fib6_rules_ops_template = { .fro_net = &init_net, }; -static int fib6_rules_net_init(struct net *net) +static int __net_init fib6_rules_net_init(struct net *net) { struct fib_rules_ops *ops; int err = -ENOMEM; @@ -291,7 +291,7 @@ out_fib6_rules_ops: goto out; } -static void fib6_rules_net_exit(struct net *net) +static void __net_exit fib6_rules_net_exit(struct net *net) { fib_rules_unregister(net->ipv6.fib6_rules_ops); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4ae661bc3677..217dbc2e28d4 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -951,7 +951,7 @@ ctl_table ipv6_icmp_table_template[] = { { }, }; -struct ctl_table *ipv6_icmp_sysctl_init(struct net *net) +struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) { struct ctl_table *table; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0e93ca56eb69..f626ea2b304f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -239,7 +239,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) return NULL; } -static void fib6_tables_init(struct net *net) +static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); fib6_link_table(net, net->ipv6.fib6_local_tbl); @@ -262,7 +262,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl, flags); } -static void fib6_tables_init(struct net *net) +static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); } @@ -1469,7 +1469,7 @@ static void fib6_gc_timer_cb(unsigned long arg) fib6_run_gc(0, (struct net *)arg); } -static int fib6_net_init(struct net *net) +static int __net_init fib6_net_init(struct net *net) { setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 6e7bffa2205e..e41eba8aacf1 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -154,7 +154,7 @@ static void ip6_fl_gc(unsigned long dummy) write_unlock(&ip6_fl_lock); } -static void ip6_fl_purge(struct net *net) +static void __net_exit ip6_fl_purge(struct net *net) { int i; @@ -735,7 +735,7 @@ static const struct file_operations ip6fl_seq_fops = { .release = seq_release_net, }; -static int ip6_flowlabel_proc_init(struct net *net) +static int __net_init ip6_flowlabel_proc_init(struct net *net) { if (!proc_net_fops_create(net, "ip6_flowlabel", S_IRUGO, &ip6fl_seq_fops)) @@ -743,7 +743,7 @@ static int ip6_flowlabel_proc_init(struct net *net) return 0; } -static void ip6_flowlabel_proc_fini(struct net *net) +static void __net_exit ip6_flowlabel_proc_fini(struct net *net) { proc_net_remove(net, "ip6_flowlabel"); } @@ -754,11 +754,10 @@ static inline int ip6_flowlabel_proc_init(struct net *net) } static inline void ip6_flowlabel_proc_fini(struct net *net) { - return ; } #endif -static inline void ip6_flowlabel_net_exit(struct net *net) +static void __net_exit ip6_flowlabel_net_exit(struct net *net) { ip6_fl_purge(net); ip6_flowlabel_proc_fini(net); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index cd48801a8d6f..eb6d09728633 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -121,10 +121,9 @@ static int ip6_output2(struct sk_buff *skb) skb->dev = dev; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { - struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && + if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && ((mroute6_socket(dev_net(dev)) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index d453d07b0dfe..fbd786981aa9 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -74,7 +74,6 @@ MODULE_LICENSE("GPL"); (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ (HASH_SIZE - 1)) -static void ip6_fb_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); @@ -1364,7 +1363,7 @@ static void ip6_tnl_dev_init(struct net_device *dev) * Return: 0 **/ -static void ip6_fb_tnl_dev_init(struct net_device *dev) +static void __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); @@ -1388,7 +1387,7 @@ static struct xfrm6_tunnel ip6ip6_handler = { .priority = 1, }; -static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) +static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) { int h; struct ip6_tnl *t; @@ -1407,7 +1406,7 @@ static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) unregister_netdevice_many(&list); } -static int ip6_tnl_init_net(struct net *net) +static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); int err; @@ -1436,7 +1435,7 @@ err_alloc_dev: return err; } -static void ip6_tnl_exit_net(struct net *net) +static void __net_exit ip6_tnl_exit_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 1f9c44442e65..25f6cca79e6b 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2646,7 +2646,7 @@ static const struct file_operations igmp6_mcf_seq_fops = { .release = seq_release_net, }; -static int igmp6_proc_init(struct net *net) +static int __net_init igmp6_proc_init(struct net *net) { int err; @@ -2666,23 +2666,22 @@ out_proc_net_igmp6: goto out; } -static void igmp6_proc_exit(struct net *net) +static void __net_exit igmp6_proc_exit(struct net *net) { proc_net_remove(net, "mcfilter6"); proc_net_remove(net, "igmp6"); } #else -static int igmp6_proc_init(struct net *net) +static inline int igmp6_proc_init(struct net *net) { return 0; } -static void igmp6_proc_exit(struct net *net) +static inline void igmp6_proc_exit(struct net *net) { - ; } #endif -static int igmp6_net_init(struct net *net) +static int __net_init igmp6_net_init(struct net *net) { int err; @@ -2708,7 +2707,7 @@ out_sock_create: goto out; } -static void igmp6_net_exit(struct net *net) +static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); igmp6_proc_exit(net); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index c45852798092..2dfec6bb8ada 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1772,7 +1772,7 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *bu #endif -static int ndisc_net_init(struct net *net) +static int __net_init ndisc_net_init(struct net *net) { struct ipv6_pinfo *np; struct sock *sk; @@ -1797,7 +1797,7 @@ static int ndisc_net_init(struct net *net) return 0; } -static void ndisc_net_exit(struct net *net) +static void __net_exit ndisc_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.ndisc_sk); } diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 5f2ec208a8c3..0956ebabbff2 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -20,6 +20,7 @@ #include <net/ipv6.h> #include <net/inet_frag.h> +#include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> @@ -187,6 +188,21 @@ out: return nf_conntrack_confirm(skb); } +static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, + struct sk_buff *skb) +{ +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge && + skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN; +#endif + if (hooknum == NF_INET_PRE_ROUTING) + return IP6_DEFRAG_CONNTRACK_IN; + else + return IP6_DEFRAG_CONNTRACK_OUT; + +} + static unsigned int ipv6_defrag(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, @@ -199,8 +215,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (skb->nfct) return NF_ACCEPT; - reasm = nf_ct_frag6_gather(skb); - + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); /* queued */ if (reasm == NULL) return NF_STOLEN; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index e0b9424fa1b2..312c20adc83f 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -168,13 +168,14 @@ out: /* Creation primitives. */ static __inline__ struct nf_ct_frag6_queue * -fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst) +fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst) { struct inet_frag_queue *q; struct ip6_create_arg arg; unsigned int hash; arg.id = id; + arg.user = user; arg.src = src; arg.dst = dst; @@ -559,7 +560,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return 0; } -struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) +struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) { struct sk_buff *clone; struct net_device *dev = skb->dev; @@ -605,7 +606,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) if (atomic_read(&nf_init_frags.mem) > nf_init_frags.high_thresh) nf_ct_frag6_evictor(); - fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr); + fq = fq_find(fhdr->identification, user, &hdr->saddr, &hdr->daddr); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); goto ret_orig; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index c9605c3ad91f..02f20016b4c9 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -259,7 +259,7 @@ int snmp6_unregister_dev(struct inet6_dev *idev) struct net *net = dev_net(idev->dev); if (!net->mib.proc_net_devsnmp6) return -ENOENT; - if (!idev || !idev->stats.proc_dir_entry) + if (!idev->stats.proc_dir_entry) return -EINVAL; remove_proc_entry(idev->stats.proc_dir_entry->name, net->mib.proc_net_devsnmp6); @@ -267,7 +267,7 @@ int snmp6_unregister_dev(struct inet6_dev *idev) return 0; } -static int ipv6_proc_init_net(struct net *net) +static int __net_init ipv6_proc_init_net(struct net *net) { if (!proc_net_fops_create(net, "sockstat6", S_IRUGO, &sockstat6_seq_fops)) @@ -288,7 +288,7 @@ proc_dev_snmp6_fail: return -ENOMEM; } -static void ipv6_proc_exit_net(struct net *net) +static void __net_exit ipv6_proc_exit_net(struct net *net) { proc_net_remove(net, "sockstat6"); proc_net_remove(net, "dev_snmp6"); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 926ce8eeffaf..ed31c37c6e39 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1275,7 +1275,7 @@ static const struct file_operations raw6_seq_fops = { .release = seq_release_net, }; -static int raw6_init_net(struct net *net) +static int __net_init raw6_init_net(struct net *net) { if (!proc_net_fops_create(net, "raw6", S_IRUGO, &raw6_seq_fops)) return -ENOMEM; @@ -1283,7 +1283,7 @@ static int raw6_init_net(struct net *net) return 0; } -static void raw6_exit_net(struct net *net) +static void __net_exit raw6_exit_net(struct net *net) { proc_net_remove(net, "raw6"); } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 4d98549a6868..fa38fc7cc6e9 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -72,6 +72,7 @@ struct frag_queue struct inet_frag_queue q; __be32 id; /* fragment id */ + u32 user; struct in6_addr saddr; struct in6_addr daddr; @@ -141,7 +142,7 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a) struct ip6_create_arg *arg = a; fq = container_of(q, struct frag_queue, q); - return (fq->id == arg->id && + return (fq->id == arg->id && fq->user == arg->user && ipv6_addr_equal(&fq->saddr, arg->src) && ipv6_addr_equal(&fq->daddr, arg->dst)); } @@ -163,6 +164,7 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a) struct ip6_create_arg *arg = a; fq->id = arg->id; + fq->user = arg->user; ipv6_addr_copy(&fq->saddr, arg->src); ipv6_addr_copy(&fq->daddr, arg->dst); } @@ -243,6 +245,7 @@ fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst, unsigned int hash; arg.id = id; + arg.user = IP6_DEFRAG_LOCAL_DELIVER; arg.src = src; arg.dst = dst; @@ -669,7 +672,7 @@ static struct ctl_table ip6_frags_ctl_table[] = { { } }; -static int ip6_frags_ns_sysctl_register(struct net *net) +static int __net_init ip6_frags_ns_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -699,13 +702,14 @@ err_alloc: return -ENOMEM; } -static void ip6_frags_ns_sysctl_unregister(struct net *net) +static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net) { struct ctl_table *table; table = net->ipv6.sysctl.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr); - kfree(table); + if (!net_eq(net, &init_net)) + kfree(table); } static struct ctl_table_header *ip6_ctl_header; @@ -741,7 +745,7 @@ static inline void ip6_frags_sysctl_unregister(void) } #endif -static int ipv6_frags_init_net(struct net *net) +static int __net_init ipv6_frags_init_net(struct net *net) { net->ipv6.frags.high_thresh = 256 * 1024; net->ipv6.frags.low_thresh = 192 * 1024; @@ -752,7 +756,7 @@ static int ipv6_frags_init_net(struct net *net) return ip6_frags_ns_sysctl_register(net); } -static void ipv6_frags_exit_net(struct net *net) +static void __net_exit ipv6_frags_exit_net(struct net *net) { ip6_frags_ns_sysctl_unregister(net); inet_frags_exit_net(&net->ipv6.frags, &ip6_frags); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index db3b27303890..8500156f2637 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2612,7 +2612,7 @@ ctl_table ipv6_route_table_template[] = { { } }; -struct ctl_table *ipv6_route_sysctl_init(struct net *net) +struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) { struct ctl_table *table; @@ -2630,13 +2630,14 @@ struct ctl_table *ipv6_route_sysctl_init(struct net *net) table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; + table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; } return table; } #endif -static int ip6_route_net_init(struct net *net) +static int __net_init ip6_route_net_init(struct net *net) { int ret = -ENOMEM; @@ -2701,7 +2702,7 @@ out_ip6_dst_ops: goto out; } -static void ip6_route_net_exit(struct net *net) +static void __net_exit ip6_route_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS proc_net_remove(net, "ipv6_route"); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 976e68244b99..10207cc8cc0e 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -62,7 +62,6 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) -static void ipip6_fb_tunnel_init(struct net_device *dev); static void ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); @@ -1120,7 +1119,7 @@ static void ipip6_tunnel_init(struct net_device *dev) ipip6_tunnel_bind_dev(dev); } -static void ipip6_fb_tunnel_init(struct net_device *dev) +static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -1145,7 +1144,7 @@ static struct xfrm_tunnel sit_handler = { .priority = 1, }; -static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) +static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) { int prio; @@ -1162,7 +1161,7 @@ static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) } } -static int sit_init_net(struct net *net) +static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); int err; @@ -1195,7 +1194,7 @@ err_alloc_dev: return err; } -static void sit_exit_net(struct net *net) +static void __net_exit sit_exit_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); LIST_HEAD(list); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 5b9af508b8f2..34d1f0690d7e 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -185,6 +185,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + + if (tcp_opt.saw_tstamp) + cookie_check_timestamp(&tcp_opt); + ret = NULL; req = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (!req) @@ -218,6 +225,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) req->expires = 0UL; req->retrans = 0; ireq->ecn_ok = 0; + ireq->snd_wscale = tcp_opt.snd_wscale; + ireq->rcv_wscale = tcp_opt.rcv_wscale; + ireq->sack_ok = tcp_opt.sack_ok; + ireq->wscale_ok = tcp_opt.wscale_ok; + ireq->tstamp_ok = tcp_opt.saw_tstamp; + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; @@ -253,25 +266,11 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out_free; } - /* check for timestamp cookie support */ - memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0, dst); - - if (tcp_opt.saw_tstamp) - cookie_check_timestamp(&tcp_opt); - - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->rcv_wscale = tcp_opt.rcv_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, &req->rcv_wnd, &req->window_clamp, - ireq->wscale_ok, &rcv_wscale); + ireq->wscale_ok, &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index c690736885b4..f841d93bf987 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -55,7 +55,7 @@ struct ctl_path net_ipv6_ctl_path[] = { }; EXPORT_SYMBOL_GPL(net_ipv6_ctl_path); -static int ipv6_sysctl_net_init(struct net *net) +static int __net_init ipv6_sysctl_net_init(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; @@ -98,7 +98,7 @@ out_ipv6_table: goto out; } -static void ipv6_sysctl_net_exit(struct net *net) +static void __net_exit ipv6_sysctl_net_exit(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ee9cf62458d4..6963a6b6763e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -520,6 +520,13 @@ done: return err; } +static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req, + struct request_values *rvp) +{ + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + return tcp_v6_send_synack(sk, req, rvp); +} + static inline void syn_flood_warning(struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES @@ -876,7 +883,7 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) if (genhash || memcmp(hash_location, newhash, 16) != 0) { if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash %s for (%pI6, %u)->(%pI6, %u)\n", + printk(KERN_INFO "MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", genhash ? "failed" : "mismatch", &ip6h->saddr, ntohs(th->source), &ip6h->daddr, ntohs(th->dest)); @@ -890,10 +897,11 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), - .rtx_syn_ack = tcp_v6_send_synack, + .rtx_syn_ack = tcp_v6_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, - .send_reset = tcp_v6_send_reset + .send_reset = tcp_v6_send_reset, + .syn_ack_timeout = tcp_syn_ack_timeout, }; #ifdef CONFIG_TCP_MD5SIG @@ -1169,7 +1177,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct inet6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = __sk_dst_get(sk); __u32 isn = TCP_SKB_CB(skb)->when; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; @@ -1208,7 +1215,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && @@ -2106,7 +2113,7 @@ static struct tcp_seq_afinfo tcp6_seq_afinfo = { }, }; -int tcp6_proc_init(struct net *net) +int __net_init tcp6_proc_init(struct net *net) { return tcp_proc_register(net, &tcp6_seq_afinfo); } @@ -2175,18 +2182,18 @@ static struct inet_protosw tcpv6_protosw = { INET_PROTOSW_ICSK, }; -static int tcpv6_net_init(struct net *net) +static int __net_init tcpv6_net_init(struct net *net) { return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, SOCK_RAW, IPPROTO_TCP, net); } -static void tcpv6_net_exit(struct net *net) +static void __net_exit tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); } -static void tcpv6_net_exit_batch(struct list_head *net_exit_list) +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) { inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 69ebdbe78c47..34efb3589ffa 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1396,7 +1396,7 @@ static struct udp_seq_afinfo udp6_seq_afinfo = { }, }; -int udp6_proc_init(struct net *net) +int __net_init udp6_proc_init(struct net *net) { return udp_proc_register(net, &udp6_seq_afinfo); } diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 6ea6938919e6..5f48fadc27f7 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -104,12 +104,12 @@ static struct udp_seq_afinfo udplite6_seq_afinfo = { }, }; -static int udplite6_proc_init_net(struct net *net) +static int __net_init udplite6_proc_init_net(struct net *net) { return udp_proc_register(net, &udplite6_seq_afinfo); } -static void udplite6_proc_exit_net(struct net *net) +static void __net_exit udplite6_proc_exit_net(struct net *net) { udp_proc_unregister(net, &udplite6_seq_afinfo); } diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 811984d9324b..8b85d774e47f 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -496,9 +496,6 @@ static void ircomm_tty_close(struct tty_struct *tty, struct file *filp) IRDA_DEBUG(0, "%s()\n", __func__ ); - if (!tty) - return; - IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;); @@ -1007,9 +1004,6 @@ static void ircomm_tty_hangup(struct tty_struct *tty) IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;); - if (!tty) - return; - /* ircomm_tty_flush_buffer(tty); */ ircomm_tty_shutdown(self); diff --git a/net/irda/irlap.c b/net/irda/irlap.c index 356e65b1dc42..783c5f367d29 100644 --- a/net/irda/irlap.c +++ b/net/irda/irlap.c @@ -450,10 +450,10 @@ void irlap_disconnect_request(struct irlap_cb *self) /* Check if we are in the right state for disconnecting */ switch (self->state) { - case LAP_XMIT_P: /* FALLTROUGH */ - case LAP_XMIT_S: /* FALLTROUGH */ - case LAP_CONN: /* FALLTROUGH */ - case LAP_RESET_WAIT: /* FALLTROUGH */ + case LAP_XMIT_P: /* FALLTHROUGH */ + case LAP_XMIT_S: /* FALLTHROUGH */ + case LAP_CONN: /* FALLTHROUGH */ + case LAP_RESET_WAIT: /* FALLTHROUGH */ case LAP_RESET_CHECK: irlap_do_event(self, DISCONNECT_REQUEST, NULL, NULL); break; @@ -485,9 +485,9 @@ void irlap_disconnect_indication(struct irlap_cb *self, LAP_REASON reason) IRDA_DEBUG(1, "%s(), Sending reset request!\n", __func__); irlap_do_event(self, RESET_REQUEST, NULL, NULL); break; - case LAP_NO_RESPONSE: /* FALLTROUGH */ - case LAP_DISC_INDICATION: /* FALLTROUGH */ - case LAP_FOUND_NONE: /* FALLTROUGH */ + case LAP_NO_RESPONSE: /* FALLTHROUGH */ + case LAP_DISC_INDICATION: /* FALLTHROUGH */ + case LAP_FOUND_NONE: /* FALLTHROUGH */ case LAP_MEDIA_BUSY: irlmp_link_disconnect_indication(self->notify.instance, self, reason, NULL); diff --git a/net/irda/irlap_event.c b/net/irda/irlap_event.c index c5c51959e3ce..94a9884d7146 100644 --- a/net/irda/irlap_event.c +++ b/net/irda/irlap_event.c @@ -1741,7 +1741,7 @@ static int irlap_state_reset(struct irlap_cb *self, IRLAP_EVENT event, * Function irlap_state_xmit_s (event, skb, info) * * XMIT_S, The secondary station has been given the right to transmit, - * and we therefor do not expect to receive any transmissions from other + * and we therefore do not expect to receive any transmissions from other * stations. */ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event, diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index 7bf5b913828b..0e7d8bde145d 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -105,7 +105,7 @@ int __init irlmp_init(void) init_timer(&irlmp->discovery_timer); - /* Do discovery every 3 seconds, conditionaly */ + /* Do discovery every 3 seconds, conditionally */ if (sysctl_discovery) irlmp_start_discovery_timer(irlmp, sysctl_discovery_timeout*HZ); @@ -1842,7 +1842,7 @@ LM_REASON irlmp_convert_lap_reason( LAP_REASON lap_reason) reason = LM_CONNECT_FAILURE; break; default: - IRDA_DEBUG(1, "%s(), Unknow IrLAP disconnect reason %d!\n", + IRDA_DEBUG(1, "%s(), Unknown IrLAP disconnect reason %d!\n", __func__, lap_reason); reason = LM_LAP_DISCONNECT; break; diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index b001c361ad30..4300df35d37d 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -249,6 +249,7 @@ #include <linux/poll.h> #include <linux/capability.h> #include <linux/ctype.h> /* isspace() */ +#include <linux/string.h> /* skip_spaces() */ #include <asm/uaccess.h> #include <linux/init.h> diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 7dea882dbb75..156020d138b5 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -76,9 +76,8 @@ irnet_ctrl_write(irnet_socket * ap, /* Look at the next command */ start = next; - /* Scrap whitespaces before the command */ - while(isspace(*start)) - start++; + /* Scrap whitespaces before the command */ + start = skip_spaces(start); /* ',' is our command separator */ next = strchr(start, ','); @@ -133,8 +132,7 @@ irnet_ctrl_write(irnet_socket * ap, char * endp; /* Scrap whitespaces before the command */ - while(isspace(*begp)) - begp++; + begp = skip_spaces(begp); /* Convert argument to a number (last arg is the base) */ addr = simple_strtoul(begp, &endp, 16); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 1e428863574f..c18286a2167b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -221,7 +221,7 @@ static int afiucv_pm_restore_thaw(struct device *dev) return 0; } -static struct dev_pm_ops afiucv_pm_ops = { +static const struct dev_pm_ops afiucv_pm_ops = { .prepare = afiucv_pm_prepare, .complete = afiucv_pm_complete, .freeze = afiucv_pm_freeze, diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 3b1f5f5f8de7..fd8b28361a64 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -93,7 +93,7 @@ static int iucv_pm_freeze(struct device *); static int iucv_pm_thaw(struct device *); static int iucv_pm_restore(struct device *); -static struct dev_pm_ops iucv_pm_ops = { +static const struct dev_pm_ops iucv_pm_ops = { .prepare = iucv_pm_prepare, .complete = iucv_pm_complete, .freeze = iucv_pm_freeze, diff --git a/net/key/af_key.c b/net/key/af_key.c index 84209fbbeb17..4744b1f6372f 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1193,6 +1193,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, x->aalg->alg_key_len = key->sadb_key_bits; memcpy(x->aalg->alg_key, key+1, keysize); } + x->aalg->alg_trunc_len = a->uinfo.auth.icv_truncbits; x->props.aalgo = sa->sadb_sa_auth; /* x->algo.flags = sa->sadb_sa_flags; */ } @@ -3737,17 +3738,17 @@ static int __net_init pfkey_init_proc(struct net *net) return 0; } -static void pfkey_exit_proc(struct net *net) +static void __net_exit pfkey_exit_proc(struct net *net) { proc_net_remove(net, "pfkey"); } #else -static int __net_init pfkey_init_proc(struct net *net) +static inline int pfkey_init_proc(struct net *net) { return 0; } -static void pfkey_exit_proc(struct net *net) +static inline void pfkey_exit_proc(struct net *net) { } #endif diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 3a66546cad06..e35d907fba2c 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -47,6 +47,10 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); #define dprintk(args...) #endif +/* Maybe we'll add some more in the future. */ +#define LLC_CMSG_PKTINFO 1 + + /** * llc_ui_next_link_no - return the next unused link number for a sap * @sap: Address of sap to get link number from. @@ -136,6 +140,7 @@ static struct proto llc_proto = { .name = "LLC", .owner = THIS_MODULE, .obj_size = sizeof(struct llc_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, }; /** @@ -192,10 +197,8 @@ static int llc_ui_release(struct socket *sock) llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); - if (!sock_flag(sk, SOCK_ZAPPED)) { - llc_sap_put(llc->sap); + if (!sock_flag(sk, SOCK_ZAPPED)) llc_sap_remove_socket(llc->sap, sk); - } release_sock(sk); if (llc->dev) dev_put(llc->dev); @@ -255,7 +258,14 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) if (!sock_flag(sk, SOCK_ZAPPED)) goto out; rc = -ENODEV; - llc->dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); + if (sk->sk_bound_dev_if) { + llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); + if (llc->dev && addr->sllc_arphrd != llc->dev->type) { + dev_put(llc->dev); + llc->dev = NULL; + } + } else + llc->dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); if (!llc->dev) goto out; rc = -EUSERS; @@ -306,7 +316,25 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) goto out; rc = -ENODEV; rtnl_lock(); - llc->dev = dev_getbyhwaddr(&init_net, addr->sllc_arphrd, addr->sllc_mac); + if (sk->sk_bound_dev_if) { + llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); + if (llc->dev) { + if (!addr->sllc_arphrd) + addr->sllc_arphrd = llc->dev->type; + if (llc_mac_null(addr->sllc_mac)) + memcpy(addr->sllc_mac, llc->dev->dev_addr, + IFHWADDRLEN); + if (addr->sllc_arphrd != llc->dev->type || + !llc_mac_match(addr->sllc_mac, + llc->dev->dev_addr)) { + rc = -EINVAL; + dev_put(llc->dev); + llc->dev = NULL; + } + } + } else + llc->dev = dev_getbyhwaddr(&init_net, addr->sllc_arphrd, + addr->sllc_mac); rtnl_unlock(); if (!llc->dev) goto out; @@ -322,7 +350,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) rc = -EBUSY; /* some other network layer is using the sap */ if (!sap) goto out; - llc_sap_hold(sap); } else { struct llc_addr laddr, daddr; struct sock *ask; @@ -591,6 +618,20 @@ static int llc_wait_data(struct sock *sk, long timeo) return rc; } +static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) +{ + struct llc_sock *llc = llc_sk(skb->sk); + + if (llc->cmsg_flags & LLC_CMSG_PKTINFO) { + struct llc_pktinfo info; + + info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex; + llc_pdu_decode_dsap(skb, &info.lpi_sap); + llc_pdu_decode_da(skb, info.lpi_mac); + put_cmsg(msg, SOL_LLC, LLC_OPT_PKTINFO, sizeof(info), &info); + } +} + /** * llc_ui_accept - accept a new incoming connection. * @sock: Socket which connections arrive on. @@ -812,6 +853,8 @@ copy_uaddr: memcpy(uaddr, llc_ui_skb_cb(skb), sizeof(*uaddr)); msg->msg_namelen = sizeof(*uaddr); } + if (llc_sk(sk)->cmsg_flags) + llc_cmsg_rcv(msg, skb); goto out; } @@ -1030,6 +1073,12 @@ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, goto out; llc->rw = opt; break; + case LLC_OPT_PKTINFO: + if (opt) + llc->cmsg_flags |= LLC_CMSG_PKTINFO; + else + llc->cmsg_flags &= ~LLC_CMSG_PKTINFO; + break; default: rc = -ENOPROTOOPT; goto out; @@ -1083,6 +1132,9 @@ static int llc_ui_getsockopt(struct socket *sock, int level, int optname, val = llc->k; break; case LLC_OPT_RX_WIN: val = llc->rw; break; + case LLC_OPT_PKTINFO: + val = (llc->cmsg_flags & LLC_CMSG_PKTINFO) != 0; + break; default: rc = -ENOPROTOOPT; goto out; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index c6bab39b018e..a8dde9b010da 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -468,6 +468,19 @@ static int llc_exec_conn_trans_actions(struct sock *sk, return rc; } +static inline bool llc_estab_match(const struct llc_sap *sap, + const struct llc_addr *daddr, + const struct llc_addr *laddr, + const struct sock *sk) +{ + struct llc_sock *llc = llc_sk(sk); + + return llc->laddr.lsap == laddr->lsap && + llc->daddr.lsap == daddr->lsap && + llc_mac_match(llc->laddr.mac, laddr->mac) && + llc_mac_match(llc->daddr.mac, daddr->mac); +} + /** * __llc_lookup_established - Finds connection for the remote/local sap/mac * @sap: SAP @@ -484,23 +497,35 @@ static struct sock *__llc_lookup_established(struct llc_sap *sap, struct llc_addr *laddr) { struct sock *rc; - struct hlist_node *node; - - read_lock(&sap->sk_list.lock); - sk_for_each(rc, node, &sap->sk_list.list) { - struct llc_sock *llc = llc_sk(rc); - - if (llc->laddr.lsap == laddr->lsap && - llc->daddr.lsap == daddr->lsap && - llc_mac_match(llc->laddr.mac, laddr->mac) && - llc_mac_match(llc->daddr.mac, daddr->mac)) { - sock_hold(rc); + struct hlist_nulls_node *node; + int slot = llc_sk_laddr_hashfn(sap, laddr); + struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; + + rcu_read_lock(); +again: + sk_nulls_for_each_rcu(rc, node, laddr_hb) { + if (llc_estab_match(sap, daddr, laddr, rc)) { + /* Extra checks required by SLAB_DESTROY_BY_RCU */ + if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + goto again; + if (unlikely(llc_sk(rc)->sap != sap || + !llc_estab_match(sap, daddr, laddr, rc))) { + sock_put(rc); + continue; + } goto found; } } rc = NULL; + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (unlikely(get_nulls_value(node) != slot)) + goto again; found: - read_unlock(&sap->sk_list.lock); + rcu_read_unlock(); return rc; } @@ -516,6 +541,53 @@ struct sock *llc_lookup_established(struct llc_sap *sap, return sk; } +static inline bool llc_listener_match(const struct llc_sap *sap, + const struct llc_addr *laddr, + const struct sock *sk) +{ + struct llc_sock *llc = llc_sk(sk); + + return sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && + llc->laddr.lsap == laddr->lsap && + llc_mac_match(llc->laddr.mac, laddr->mac); +} + +static struct sock *__llc_lookup_listener(struct llc_sap *sap, + struct llc_addr *laddr) +{ + struct sock *rc; + struct hlist_nulls_node *node; + int slot = llc_sk_laddr_hashfn(sap, laddr); + struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; + + rcu_read_lock(); +again: + sk_nulls_for_each_rcu(rc, node, laddr_hb) { + if (llc_listener_match(sap, laddr, rc)) { + /* Extra checks required by SLAB_DESTROY_BY_RCU */ + if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + goto again; + if (unlikely(llc_sk(rc)->sap != sap || + !llc_listener_match(sap, laddr, rc))) { + sock_put(rc); + continue; + } + goto found; + } + } + rc = NULL; + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (unlikely(get_nulls_value(node) != slot)) + goto again; +found: + rcu_read_unlock(); + return rc; +} + /** * llc_lookup_listener - Finds listener for local MAC + SAP * @sap: SAP @@ -529,24 +601,12 @@ struct sock *llc_lookup_established(struct llc_sap *sap, static struct sock *llc_lookup_listener(struct llc_sap *sap, struct llc_addr *laddr) { - struct sock *rc; - struct hlist_node *node; + static struct llc_addr null_addr; + struct sock *rc = __llc_lookup_listener(sap, laddr); - read_lock(&sap->sk_list.lock); - sk_for_each(rc, node, &sap->sk_list.list) { - struct llc_sock *llc = llc_sk(rc); + if (!rc) + rc = __llc_lookup_listener(sap, &null_addr); - if (rc->sk_type == SOCK_STREAM && rc->sk_state == TCP_LISTEN && - llc->laddr.lsap == laddr->lsap && - (llc_mac_match(llc->laddr.mac, laddr->mac) || - llc_mac_null(llc->laddr.mac))) { - sock_hold(rc); - goto found; - } - } - rc = NULL; -found: - read_unlock(&sap->sk_list.lock); return rc; } @@ -647,15 +707,22 @@ static int llc_find_offset(int state, int ev_type) * @sap: SAP * @sk: socket * - * This function adds a socket to sk_list of a SAP. + * This function adds a socket to the hash tables of a SAP. */ void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk) { + struct llc_sock *llc = llc_sk(sk); + struct hlist_head *dev_hb = llc_sk_dev_hash(sap, llc->dev->ifindex); + struct hlist_nulls_head *laddr_hb = llc_sk_laddr_hash(sap, &llc->laddr); + llc_sap_hold(sap); - write_lock_bh(&sap->sk_list.lock); llc_sk(sk)->sap = sap; - sk_add_node(sk, &sap->sk_list.list); - write_unlock_bh(&sap->sk_list.lock); + + spin_lock_bh(&sap->sk_lock); + sap->sk_count++; + sk_nulls_add_node_rcu(sk, laddr_hb); + hlist_add_head(&llc->dev_hash_node, dev_hb); + spin_unlock_bh(&sap->sk_lock); } /** @@ -663,14 +730,18 @@ void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk) * @sap: SAP * @sk: socket * - * This function removes a connection from sk_list.list of a SAP if + * This function removes a connection from the hash tables of a SAP if * the connection was in this list. */ void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk) { - write_lock_bh(&sap->sk_list.lock); - sk_del_node_init(sk); - write_unlock_bh(&sap->sk_list.lock); + struct llc_sock *llc = llc_sk(sk); + + spin_lock_bh(&sap->sk_lock); + sk_nulls_del_node_init_rcu(sk); + hlist_del(&llc->dev_hash_node); + sap->sk_count--; + spin_unlock_bh(&sap->sk_lock); llc_sap_put(sap); } diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index ff4c0ab96a69..78167e81dfeb 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -23,7 +23,7 @@ #include <net/llc.h> LIST_HEAD(llc_sap_list); -DEFINE_RWLOCK(llc_sap_list_lock); +DEFINE_SPINLOCK(llc_sap_list_lock); /** * llc_sap_alloc - allocates and initializes sap. @@ -33,40 +33,19 @@ DEFINE_RWLOCK(llc_sap_list_lock); static struct llc_sap *llc_sap_alloc(void) { struct llc_sap *sap = kzalloc(sizeof(*sap), GFP_ATOMIC); + int i; if (sap) { /* sap->laddr.mac - leave as a null, it's filled by bind */ sap->state = LLC_SAP_STATE_ACTIVE; - rwlock_init(&sap->sk_list.lock); + spin_lock_init(&sap->sk_lock); + for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++) + INIT_HLIST_NULLS_HEAD(&sap->sk_laddr_hash[i], i); atomic_set(&sap->refcnt, 1); } return sap; } -/** - * llc_add_sap - add sap to station list - * @sap: Address of the sap - * - * Adds a sap to the LLC's station sap list. - */ -static void llc_add_sap(struct llc_sap *sap) -{ - list_add_tail(&sap->node, &llc_sap_list); -} - -/** - * llc_del_sap - del sap from station list - * @sap: Address of the sap - * - * Removes a sap to the LLC's station sap list. - */ -static void llc_del_sap(struct llc_sap *sap) -{ - write_lock_bh(&llc_sap_list_lock); - list_del(&sap->node); - write_unlock_bh(&llc_sap_list_lock); -} - static struct llc_sap *__llc_sap_find(unsigned char sap_value) { struct llc_sap* sap; @@ -90,13 +69,13 @@ out: */ struct llc_sap *llc_sap_find(unsigned char sap_value) { - struct llc_sap* sap; + struct llc_sap *sap; - read_lock_bh(&llc_sap_list_lock); + rcu_read_lock_bh(); sap = __llc_sap_find(sap_value); if (sap) llc_sap_hold(sap); - read_unlock_bh(&llc_sap_list_lock); + rcu_read_unlock_bh(); return sap; } @@ -117,7 +96,7 @@ struct llc_sap *llc_sap_open(unsigned char lsap, { struct llc_sap *sap = NULL; - write_lock_bh(&llc_sap_list_lock); + spin_lock_bh(&llc_sap_list_lock); if (__llc_sap_find(lsap)) /* SAP already exists */ goto out; sap = llc_sap_alloc(); @@ -125,9 +104,9 @@ struct llc_sap *llc_sap_open(unsigned char lsap, goto out; sap->laddr.lsap = lsap; sap->rcv_func = func; - llc_add_sap(sap); + list_add_tail_rcu(&sap->node, &llc_sap_list); out: - write_unlock_bh(&llc_sap_list_lock); + spin_unlock_bh(&llc_sap_list_lock); return sap; } @@ -142,8 +121,14 @@ out: */ void llc_sap_close(struct llc_sap *sap) { - WARN_ON(!hlist_empty(&sap->sk_list.list)); - llc_del_sap(sap); + WARN_ON(sap->sk_count); + + spin_lock_bh(&llc_sap_list_lock); + list_del_rcu(&sap->node); + spin_unlock_bh(&llc_sap_list_lock); + + synchronize_rcu(); + kfree(sap); } diff --git a/net/llc/llc_output.c b/net/llc/llc_output.c index 754f4fedc852..b38a1079a98e 100644 --- a/net/llc/llc_output.c +++ b/net/llc/llc_output.c @@ -33,48 +33,19 @@ int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da) { - int rc = 0; + int rc = -EINVAL; switch (skb->dev->type) { -#ifdef CONFIG_TR - case ARPHRD_IEEE802_TR: { - struct net_device *dev = skb->dev; - struct trh_hdr *trh; - - skb_push(skb, sizeof(*trh)); - skb_reset_mac_header(skb); - trh = tr_hdr(skb); - trh->ac = AC; - trh->fc = LLC_FRAME; - if (sa) - memcpy(trh->saddr, sa, dev->addr_len); - else - memset(trh->saddr, 0, dev->addr_len); - if (da) { - memcpy(trh->daddr, da, dev->addr_len); - tr_source_route(skb, trh, dev); - skb_reset_mac_header(skb); - } - break; - } -#endif + case ARPHRD_IEEE802_TR: case ARPHRD_ETHER: - case ARPHRD_LOOPBACK: { - unsigned short len = skb->len; - struct ethhdr *eth; - - skb_push(skb, sizeof(*eth)); - skb_reset_mac_header(skb); - eth = eth_hdr(skb); - eth->h_proto = htons(len); - memcpy(eth->h_dest, da, ETH_ALEN); - memcpy(eth->h_source, sa, ETH_ALEN); + case ARPHRD_LOOPBACK: + rc = dev_hard_header(skb, skb->dev, ETH_P_802_2, da, sa, + skb->len); + if (rc > 0) + rc = 0; break; - } default: - printk(KERN_WARNING "device type not supported: %d\n", - skb->dev->type); - rc = -EINVAL; + WARN(1, "device type not supported: %d\n", skb->dev->type); } return rc; } diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index be47ac427f6b..7af1ff2d1f19 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -32,21 +32,23 @@ static void llc_ui_format_mac(struct seq_file *seq, u8 *addr) static struct sock *llc_get_sk_idx(loff_t pos) { - struct list_head *sap_entry; struct llc_sap *sap; - struct hlist_node *node; struct sock *sk = NULL; - - list_for_each(sap_entry, &llc_sap_list) { - sap = list_entry(sap_entry, struct llc_sap, node); - - read_lock_bh(&sap->sk_list.lock); - sk_for_each(sk, node, &sap->sk_list.list) { - if (!pos) - goto found; - --pos; + int i; + + list_for_each_entry_rcu(sap, &llc_sap_list, node) { + spin_lock_bh(&sap->sk_lock); + for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++) { + struct hlist_nulls_head *head = &sap->sk_laddr_hash[i]; + struct hlist_nulls_node *node; + + sk_nulls_for_each(sk, node, head) { + if (!pos) + goto found; /* keep the lock */ + --pos; + } } - read_unlock_bh(&sap->sk_list.lock); + spin_unlock_bh(&sap->sk_lock); } sk = NULL; found: @@ -57,10 +59,23 @@ static void *llc_seq_start(struct seq_file *seq, loff_t *pos) { loff_t l = *pos; - read_lock_bh(&llc_sap_list_lock); + rcu_read_lock_bh(); return l ? llc_get_sk_idx(--l) : SEQ_START_TOKEN; } +static struct sock *laddr_hash_next(struct llc_sap *sap, int bucket) +{ + struct hlist_nulls_node *node; + struct sock *sk = NULL; + + while (++bucket < LLC_SK_LADDR_HASH_ENTRIES) + sk_nulls_for_each(sk, node, &sap->sk_laddr_hash[bucket]) + goto out; + +out: + return sk; +} + static void *llc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock* sk, *next; @@ -73,25 +88,23 @@ static void *llc_seq_next(struct seq_file *seq, void *v, loff_t *pos) goto out; } sk = v; - next = sk_next(sk); + next = sk_nulls_next(sk); if (next) { sk = next; goto out; } llc = llc_sk(sk); sap = llc->sap; - read_unlock_bh(&sap->sk_list.lock); - sk = NULL; - for (;;) { - if (sap->node.next == &llc_sap_list) - break; - sap = list_entry(sap->node.next, struct llc_sap, node); - read_lock_bh(&sap->sk_list.lock); - if (!hlist_empty(&sap->sk_list.list)) { - sk = sk_head(&sap->sk_list.list); - break; - } - read_unlock_bh(&sap->sk_list.lock); + sk = laddr_hash_next(sap, llc_sk_laddr_hashfn(sap, &llc->laddr)); + if (sk) + goto out; + spin_unlock_bh(&sap->sk_lock); + list_for_each_entry_continue_rcu(sap, &llc_sap_list, node) { + spin_lock_bh(&sap->sk_lock); + sk = laddr_hash_next(sap, -1); + if (sk) + break; /* keep the lock */ + spin_unlock_bh(&sap->sk_lock); } out: return sk; @@ -104,9 +117,9 @@ static void llc_seq_stop(struct seq_file *seq, void *v) struct llc_sock *llc = llc_sk(sk); struct llc_sap *sap = llc->sap; - read_unlock_bh(&sap->sk_list.lock); + spin_unlock_bh(&sap->sk_lock); } - read_unlock_bh(&llc_sap_list_lock); + rcu_read_unlock_bh(); } static int llc_seq_socket_show(struct seq_file *seq, void *v) diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 008de1fc42ca..ad6e6e1cf22f 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -297,6 +297,17 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, llc_sap_state_process(sap, skb); } +static inline bool llc_dgram_match(const struct llc_sap *sap, + const struct llc_addr *laddr, + const struct sock *sk) +{ + struct llc_sock *llc = llc_sk(sk); + + return sk->sk_type == SOCK_DGRAM && + llc->laddr.lsap == laddr->lsap && + llc_mac_match(llc->laddr.mac, laddr->mac); +} + /** * llc_lookup_dgram - Finds dgram socket for the local sap/mac * @sap: SAP @@ -309,25 +320,68 @@ static struct sock *llc_lookup_dgram(struct llc_sap *sap, const struct llc_addr *laddr) { struct sock *rc; - struct hlist_node *node; - - read_lock_bh(&sap->sk_list.lock); - sk_for_each(rc, node, &sap->sk_list.list) { - struct llc_sock *llc = llc_sk(rc); - - if (rc->sk_type == SOCK_DGRAM && - llc->laddr.lsap == laddr->lsap && - llc_mac_match(llc->laddr.mac, laddr->mac)) { - sock_hold(rc); + struct hlist_nulls_node *node; + int slot = llc_sk_laddr_hashfn(sap, laddr); + struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; + + rcu_read_lock_bh(); +again: + sk_nulls_for_each_rcu(rc, node, laddr_hb) { + if (llc_dgram_match(sap, laddr, rc)) { + /* Extra checks required by SLAB_DESTROY_BY_RCU */ + if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + goto again; + if (unlikely(llc_sk(rc)->sap != sap || + !llc_dgram_match(sap, laddr, rc))) { + sock_put(rc); + continue; + } goto found; } } rc = NULL; + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (unlikely(get_nulls_value(node) != slot)) + goto again; found: - read_unlock_bh(&sap->sk_list.lock); + rcu_read_unlock_bh(); return rc; } +static inline bool llc_mcast_match(const struct llc_sap *sap, + const struct llc_addr *laddr, + const struct sk_buff *skb, + const struct sock *sk) +{ + struct llc_sock *llc = llc_sk(sk); + + return sk->sk_type == SOCK_DGRAM && + llc->laddr.lsap == laddr->lsap && + llc->dev == skb->dev; +} + +static void llc_do_mcast(struct llc_sap *sap, struct sk_buff *skb, + struct sock **stack, int count) +{ + struct sk_buff *skb1; + int i; + + for (i = 0; i < count; i++) { + skb1 = skb_clone(skb, GFP_ATOMIC); + if (!skb1) { + sock_put(stack[i]); + continue; + } + + llc_sap_rcv(sap, skb1, stack[i]); + sock_put(stack[i]); + } +} + /** * llc_sap_mcast - Deliver multicast PDU's to all matching datagram sockets. * @sap: SAP @@ -340,32 +394,31 @@ static void llc_sap_mcast(struct llc_sap *sap, const struct llc_addr *laddr, struct sk_buff *skb) { - struct sock *sk; + int i = 0, count = 256 / sizeof(struct sock *); + struct sock *sk, *stack[count]; struct hlist_node *node; + struct llc_sock *llc; + struct hlist_head *dev_hb = llc_sk_dev_hash(sap, skb->dev->ifindex); - read_lock_bh(&sap->sk_list.lock); - sk_for_each(sk, node, &sap->sk_list.list) { - struct llc_sock *llc = llc_sk(sk); - struct sk_buff *skb1; + spin_lock_bh(&sap->sk_lock); + hlist_for_each_entry(llc, node, dev_hb, dev_hash_node) { - if (sk->sk_type != SOCK_DGRAM) - continue; + sk = &llc->sk; - if (llc->laddr.lsap != laddr->lsap) + if (!llc_mcast_match(sap, laddr, skb, sk)) continue; - if (llc->dev != skb->dev) - continue; - - skb1 = skb_clone(skb, GFP_ATOMIC); - if (!skb1) - break; - sock_hold(sk); - llc_sap_rcv(sap, skb1, sk); - sock_put(sk); + if (i < count) + stack[i++] = sk; + else { + llc_do_mcast(sap, skb, stack, i); + i = 0; + } } - read_unlock_bh(&sap->sk_list.lock); + spin_unlock_bh(&sap->sk_lock); + + llc_do_mcast(sap, skb, stack, i); } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index fbef678f64c8..2312efe04c62 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -244,7 +244,7 @@ struct mesh_path *mesh_path_lookup_by_idx(int idx, struct ieee80211_sub_if_data * @addr: destination address of the path (ETH_ALEN length) * @sdata: local subif * - * Returns: 0 on sucess + * Returns: 0 on success * * State: the initial state of the new path is set to 0 */ @@ -532,7 +532,7 @@ static void mesh_path_node_reclaim(struct rcu_head *rp) * @addr: dst address (ETH_ALEN length) * @sdata: local subif * - * Returns: 0 if succesful + * Returns: 0 if successful */ int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata) { diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 79a698052218..f2d76238b9b5 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -112,7 +112,8 @@ config IP_VS_RR module, choose M here. If unsure, say N. config IP_VS_WRR - tristate "weighted round-robin scheduling" + tristate "weighted round-robin scheduling" + select GCD ---help--- The weighted robin-robin scheduling algorithm directs network connections to different real servers based on server weights diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b95699f00545..847ffca40184 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1366,6 +1366,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, == sysctl_ip_vs_sync_threshold[0])) || ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) && ((cp->state == IP_VS_TCP_S_FIN_WAIT) || + (cp->state == IP_VS_TCP_S_CLOSE) || (cp->state == IP_VS_TCP_S_CLOSE_WAIT) || (cp->state == IP_VS_TCP_S_TIME_WAIT))))) ip_vs_sync_conn(cp); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e55a6861d26f..c37ac2d7bec4 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2077,6 +2077,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (!capable(CAP_NET_ADMIN)) return -EPERM; + if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_SET_MAX) + return -EINVAL; + if (len < 0 || len > MAX_ARG_LEN) + return -EINVAL; if (len != set_arglen[SET_CMDID(cmd)]) { pr_err("set_ctl: len %u != %u\n", len, set_arglen[SET_CMDID(cmd)]); @@ -2352,17 +2356,25 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { unsigned char arg[128]; int ret = 0; + unsigned int copylen; if (!capable(CAP_NET_ADMIN)) return -EPERM; + if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_GET_MAX) + return -EINVAL; + if (*len < get_arglen[GET_CMDID(cmd)]) { pr_err("get_ctl: len %u < %u\n", *len, get_arglen[GET_CMDID(cmd)]); return -EINVAL; } - if (copy_from_user(arg, user, get_arglen[GET_CMDID(cmd)]) != 0) + copylen = get_arglen[GET_CMDID(cmd)]; + if (copylen > 128) + return -EINVAL; + + if (copy_from_user(arg, user, copylen) != 0) return -EFAULT; if (mutex_lock_interruptible(&__ip_vs_mutex)) @@ -2714,6 +2726,8 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, if (!(nla_af && (nla_fwmark || (nla_port && nla_protocol && nla_addr)))) return -EINVAL; + memset(usvc, 0, sizeof(*usvc)); + usvc->af = nla_get_u16(nla_af); #ifdef CONFIG_IP_VS_IPV6 if (usvc->af != AF_INET && usvc->af != AF_INET6) @@ -2901,6 +2915,8 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, if (!(nla_addr && nla_port)) return -EINVAL; + memset(udest, 0, sizeof(*udest)); + nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr)); udest->port = nla_get_u16(nla_port); diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index 6182e8ea0be7..3c115fc19784 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -24,6 +24,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/net.h> +#include <linux/gcd.h> #include <net/ip_vs.h> @@ -38,20 +39,6 @@ struct ip_vs_wrr_mark { }; -/* - * Get the gcd of server weights - */ -static int gcd(int a, int b) -{ - int c; - - while ((c = a % b)) { - a = b; - b = c; - } - return b; -} - static int ip_vs_wrr_gcd_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 38ea7ef3ccd2..f0732aa18e4f 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -323,24 +323,24 @@ static void update_nl_seq(struct nf_conn *ct, u32 nl_seq, struct nf_ct_ftp_master *info, int dir, struct sk_buff *skb) { - unsigned int i, oldest = NUM_SEQ_TO_REMEMBER; + unsigned int i, oldest; /* Look for oldest: if we find exact match, we're done. */ for (i = 0; i < info->seq_aft_nl_num[dir]; i++) { if (info->seq_aft_nl[dir][i] == nl_seq) return; - - if (oldest == info->seq_aft_nl_num[dir] || - before(info->seq_aft_nl[dir][i], - info->seq_aft_nl[dir][oldest])) - oldest = i; } if (info->seq_aft_nl_num[dir] < NUM_SEQ_TO_REMEMBER) { info->seq_aft_nl[dir][info->seq_aft_nl_num[dir]++] = nl_seq; - } else if (oldest != NUM_SEQ_TO_REMEMBER && - after(nl_seq, info->seq_aft_nl[dir][oldest])) { - info->seq_aft_nl[dir][oldest] = nl_seq; + } else { + if (before(info->seq_aft_nl[dir][0], info->seq_aft_nl[dir][1])) + oldest = 0; + else + oldest = 1; + + if (after(nl_seq, info->seq_aft_nl[dir][oldest])) + info->seq_aft_nl[dir][oldest] = nl_seq; } } diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index eb0ceb846527..fc70a49c0afd 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -482,8 +482,7 @@ static ssize_t recent_old_proc_write(struct file *file, if (copy_from_user(buf, input, size)) return -EFAULT; - while (isspace(*c)) - c++; + c = skip_spaces(c); if (size - (c - buf) < 5) return c - buf; diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index 7a10bbe02c13..c5d9f97ef217 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -682,7 +682,7 @@ struct netlbl_domaddr6_map *netlbl_domhsh_getentry_af6(const char *domain, * buckets and @skip_chain entries. For each entry in the table call * @callback, if @callback returns a negative value stop 'walking' through the * table and return. Updates the values in @skip_bkt and @skip_chain on - * return. Returns zero on succcess, negative values on failure. + * return. Returns zero on success, negative values on failure. * */ int netlbl_domhsh_walk(u32 *skip_bkt, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d07ecda0a92d..a4b6e148c5de 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -681,9 +681,7 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) int chains_to_skip = cb->args[0]; int fams_to_skip = cb->args[1]; - for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { - if (i < chains_to_skip) - continue; + for (i = chains_to_skip; i < GENL_FAM_TAB_SIZE; i++) { n = 0; list_for_each_entry(rt, genl_family_chain(i), family_list) { if (!rt->netnsok && !net_eq(net, &init_net)) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 020562164b56..a97acfe7e770 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -415,7 +415,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name; - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct net_device *dev; __be16 proto = 0; int err; @@ -437,6 +437,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, */ saddr->spkt_device[13] = 0; +retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; @@ -456,58 +457,48 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, if (len > dev->mtu + dev->hard_header_len) goto out_unlock; - err = -ENOBUFS; - skb = sock_wmalloc(sk, len + LL_RESERVED_SPACE(dev), 0, GFP_KERNEL); - - /* - * If the write buffer is full, then tough. At this level the user - * gets to deal with the problem - do your own algorithmic backoffs. - * That's far more flexible. - */ - - if (skb == NULL) - goto out_unlock; - - /* - * Fill it in - */ - - /* FIXME: Save some space for broken drivers that write a - * hard header at transmission time by themselves. PPP is the - * notable one here. This should really be fixed at the driver level. - */ - skb_reserve(skb, LL_RESERVED_SPACE(dev)); - skb_reset_network_header(skb); - - /* Try to align data part correctly */ - if (dev->header_ops) { - skb->data -= dev->hard_header_len; - skb->tail -= dev->hard_header_len; - if (len < dev->hard_header_len) - skb_reset_network_header(skb); + if (!skb) { + size_t reserved = LL_RESERVED_SPACE(dev); + unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; + + rcu_read_unlock(); + skb = sock_wmalloc(sk, len + reserved, 0, GFP_KERNEL); + if (skb == NULL) + return -ENOBUFS; + /* FIXME: Save some space for broken drivers that write a hard + * header at transmission time by themselves. PPP is the notable + * one here. This should really be fixed at the driver level. + */ + skb_reserve(skb, reserved); + skb_reset_network_header(skb); + + /* Try to align data part correctly */ + if (hhlen) { + skb->data -= hhlen; + skb->tail -= hhlen; + if (len < hhlen) + skb_reset_network_header(skb); + } + err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); + if (err) + goto out_free; + goto retry; } - /* Returns -EFAULT on error */ - err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); + skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - if (err) - goto out_free; - - /* - * Now send it - */ dev_queue_xmit(skb); rcu_read_unlock(); return len; -out_free: - kfree_skb(skb); out_unlock: rcu_read_unlock(); +out_free: + kfree_skb(skb); return err; } @@ -2457,7 +2448,7 @@ static const struct file_operations packet_seq_fops = { #endif -static int packet_net_init(struct net *net) +static int __net_init packet_net_init(struct net *net) { rwlock_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); @@ -2468,7 +2459,7 @@ static int packet_net_init(struct net *net) return 0; } -static void packet_net_exit(struct net *net) +static void __net_exit packet_net_exit(struct net *net) { proc_net_remove(net, "packet"); } diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 67f072e94d00..387197b579b1 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -75,7 +75,8 @@ static int pn_sendmsg(struct kiocb *iocb, struct sock *sk, struct sk_buff *skb; int err; - if (msg->msg_flags & MSG_OOB) + if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL| + MSG_CMSG_COMPAT)) return -EOPNOTSUPP; if (msg->msg_name == NULL) @@ -119,7 +120,8 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, int rval = -EOPNOTSUPP; int copylen; - if (flags & MSG_OOB) + if (flags & ~(MSG_PEEK|MSG_TRUNC|MSG_DONTWAIT|MSG_NOSIGNAL| + MSG_CMSG_COMPAT)) goto out_nofree; if (addr_len) diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index d183509d3fa6..d01208968c83 100644 --- a/net/phonet/pep-gprs.c +++ b/net/phonet/pep-gprs.c @@ -96,11 +96,11 @@ static int gprs_recv(struct gprs_dev *gp, struct sk_buff *skb) goto drop; } - if (likely(skb_headroom(skb) & 3)) { + if (skb_headroom(skb) & 3) { struct sk_buff *rskb, *fs; int flen = 0; - /* Phonet Pipe data header is misaligned (3 bytes), + /* Phonet Pipe data header may be misaligned (3 bytes), * so wrap the IP packet as a single fragment of an head-less * socket buffer. The network stack will pull what it needs, * but at least, the whole IP payload is not memcpy'd. */ diff --git a/net/phonet/pep.c b/net/phonet/pep.c index b6356f3832f6..360cf377693e 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -354,6 +354,9 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) queue = &pn->ctrlreq_queue; goto queue; + case PNS_PIPE_ALIGNED_DATA: + __skb_pull(skb, 1); + /* fall through */ case PNS_PIPE_DATA: __skb_pull(skb, 3); /* Pipe data header */ if (!pn_flow_safe(pn->rx_fc)) { @@ -441,6 +444,7 @@ static int pep_connreq_rcv(struct sock *sk, struct sk_buff *skb) struct sockaddr_pn dst; u16 peer_type; u8 pipe_handle, enabled, n_sb; + u8 aligned = 0; if (!pskb_pull(skb, sizeof(*hdr) + 4)) return -EINVAL; @@ -479,6 +483,9 @@ static int pep_connreq_rcv(struct sock *sk, struct sk_buff *skb) return -EINVAL; peer_type = (peer_type & 0xff00) | data[0]; break; + case PN_PIPE_SB_ALIGNED_DATA: + aligned = data[0] != 0; + break; } n_sb--; } @@ -510,6 +517,7 @@ static int pep_connreq_rcv(struct sock *sk, struct sk_buff *skb) newpn->rx_credits = 0; newpn->rx_fc = newpn->tx_fc = PN_LEGACY_FLOW_CONTROL; newpn->init_enable = enabled; + newpn->aligned = aligned; BUG_ON(!skb_queue_empty(&newsk->sk_receive_queue)); skb_queue_head(&newsk->sk_receive_queue, skb); @@ -829,11 +837,15 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) return -ENOBUFS; } - skb_push(skb, 3); + skb_push(skb, 3 + pn->aligned); skb_reset_transport_header(skb); ph = pnp_hdr(skb); ph->utid = 0; - ph->message_id = PNS_PIPE_DATA; + if (pn->aligned) { + ph->message_id = PNS_PIPE_ALIGNED_DATA; + ph->data[0] = 0; /* padding */ + } else + ph->message_id = PNS_PIPE_DATA; ph->pipe_handle = pn->pipe_handle; return pn_skb_send(sk, skb, &pipe_srv); @@ -848,7 +860,9 @@ static int pep_sendmsg(struct kiocb *iocb, struct sock *sk, int flags = msg->msg_flags; int err, done; - if (msg->msg_flags & MSG_OOB || !(msg->msg_flags & MSG_EOR)) + if ((msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL| + MSG_CMSG_COMPAT)) || + !(msg->msg_flags & MSG_EOR)) return -EOPNOTSUPP; skb = sock_alloc_send_skb(sk, MAX_PNPIPE_HEADER + len, @@ -927,6 +941,9 @@ int pep_write(struct sock *sk, struct sk_buff *skb) struct sk_buff *rskb, *fs; int flen = 0; + if (pep_sk(sk)->aligned) + return pipe_skb_send(sk, skb); + rskb = alloc_skb(MAX_PNPIPE_HEADER, GFP_ATOMIC); if (!rskb) { kfree_skb(skb); @@ -966,6 +983,10 @@ static int pep_recvmsg(struct kiocb *iocb, struct sock *sk, struct sk_buff *skb; int err; + if (flags & ~(MSG_OOB|MSG_PEEK|MSG_TRUNC|MSG_DONTWAIT|MSG_WAITALL| + MSG_NOSIGNAL|MSG_CMSG_COMPAT)) + return -EOPNOTSUPP; + if (unlikely(1 << sk->sk_state & (TCPF_LISTEN | TCPF_CLOSE))) return -ENOTCONN; @@ -973,6 +994,8 @@ static int pep_recvmsg(struct kiocb *iocb, struct sock *sk, /* Dequeue and acknowledge control request */ struct pep_sock *pn = pep_sk(sk); + if (flags & MSG_PEEK) + return -EOPNOTSUPP; skb = skb_dequeue(&pn->ctrlreq_queue); if (skb) { pep_ctrlreq_error(sk, skb, PN_PIPE_NO_ERROR, diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index bc4a33bf2d3d..c597cc53a6fb 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -311,7 +311,7 @@ static struct notifier_block phonet_device_notifier = { }; /* Per-namespace Phonet devices handling */ -static int phonet_init_net(struct net *net) +static int __net_init phonet_init_net(struct net *net) { struct phonet_net *pnn = net_generic(net, phonet_net_id); @@ -324,7 +324,7 @@ static int phonet_init_net(struct net *net) return 0; } -static void phonet_exit_net(struct net *net) +static void __net_exit phonet_exit_net(struct net *net) { struct phonet_net *pnn = net_generic(net, phonet_net_id); struct net_device *dev; diff --git a/net/rds/ib.c b/net/rds/ib.c index 536ebe5d3f6b..3b8992361042 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -182,8 +182,8 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, ic = conn->c_transport_data; dev_addr = &ic->i_cm_id->route.addr.dev_addr; - ib_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid); - ib_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid); + rdma_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid); + rdma_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid); rds_ibdev = ib_get_client_data(ic->i_cm_id->device, &rds_ib_client); iinfo->max_send_wr = ic->i_send_ring.w_nr; diff --git a/net/rds/iw.c b/net/rds/iw.c index db224f7c2937..b28fa8525b24 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -184,8 +184,8 @@ static int rds_iw_conn_info_visitor(struct rds_connection *conn, ic = conn->c_transport_data; dev_addr = &ic->i_cm_id->route.addr.dev_addr; - ib_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid); - ib_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid); + rdma_addr_get_sgid(dev_addr, (union ib_gid *) &iinfo->src_gid); + rdma_addr_get_dgid(dev_addr, (union ib_gid *) &iinfo->dst_gid); rds_iwdev = ib_get_client_data(ic->i_cm_id->device, &rds_iw_client); iinfo->max_send_wr = ic->i_send_ring.w_nr; diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 114df6eec8c3..968e8bac1b5d 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -75,7 +75,7 @@ static void rose_loopback_timer(unsigned long param) lci_i = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); frametype = skb->data[2]; dest = (rose_address *)(skb->data + 4); - lci_o = 0xFFF - lci_i; + lci_o = ROSE_DEFAULT_MAXVC + 1 - lci_i; skb_reset_transport_header(skb); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2a740035aa6b..64f5e328cee9 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -598,7 +598,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, goto errout; /* compat_mode being true specifies a call that is supposed - * to add additional backward compatiblity statistic TLVs. + * to add additional backward compatibility statistic TLVs. */ if (compat_mode) { if (a->type == TCA_OLD_COMPAT) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index d771cc1b777a..4e4ca65cd320 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -717,7 +717,7 @@ static void sctp_cmd_new_state(sctp_cmd_seq_t *cmds, if (sctp_style(sk, TCP)) { /* Change the sk->sk_state of a TCP-style socket that has - * sucessfully completed a connect() call. + * successfully completed a connect() call. */ if (sctp_state(asoc, ESTABLISHED) && sctp_sstate(sk, CLOSED)) sk->sk_state = SCTP_SS_ESTABLISHED; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 1ef9de9bbae9..47bc20d3a85b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3577,7 +3577,7 @@ sctp_disposition_t sctp_sf_do_asconf(const struct sctp_endpoint *ep, * To do this properly, we'll set the destination address of the chunk * and at the transmit time, will try look up the transport to use. * Since ASCONFs may be bundled, the correct transport may not be - * created untill we process the entire packet, thus this workaround. + * created until we process the entire packet, thus this workaround. */ asconf_ack->dest = chunk->source; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(asconf_ack)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 89ab66e54740..67fdac9d2d33 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2087,8 +2087,7 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */ - if (sp->autoclose > (MAX_SCHEDULE_TIMEOUT / HZ) ) - sp->autoclose = (__u32)(MAX_SCHEDULE_TIMEOUT / HZ) ; + sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ); return 0; } diff --git a/net/socket.c b/net/socket.c index b94c3dd71015..769c386bd428 100644 --- a/net/socket.c +++ b/net/socket.c @@ -312,18 +312,6 @@ static struct file_system_type sock_fs_type = { .kill_sb = kill_anon_super, }; -static int sockfs_delete_dentry(struct dentry *dentry) -{ - /* - * At creation time, we pretended this dentry was hashed - * (by clearing DCACHE_UNHASHED bit in d_flags) - * At delete time, we restore the truth : not hashed. - * (so that dput() can proceed correctly) - */ - dentry->d_flags |= DCACHE_UNHASHED; - return 0; -} - /* * sockfs_dname() is called from d_path(). */ @@ -334,7 +322,6 @@ static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) } static const struct dentry_operations sockfs_dentry_operations = { - .d_delete = sockfs_delete_dentry, .d_dname = sockfs_dname, }; @@ -355,68 +342,55 @@ static const struct dentry_operations sockfs_dentry_operations = { * but we take care of internal coherence yet. */ -static int sock_alloc_fd(struct file **filep, int flags) +static int sock_alloc_file(struct socket *sock, struct file **f, int flags) { + struct qstr name = { .name = "" }; + struct path path; + struct file *file; int fd; fd = get_unused_fd_flags(flags); - if (likely(fd >= 0)) { - struct file *file = get_empty_filp(); - - *filep = file; - if (unlikely(!file)) { - put_unused_fd(fd); - return -ENFILE; - } - } else - *filep = NULL; - return fd; -} - -static int sock_attach_fd(struct socket *sock, struct file *file, int flags) -{ - struct dentry *dentry; - struct qstr name = { .name = "" }; + if (unlikely(fd < 0)) + return fd; - dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name); - if (unlikely(!dentry)) + path.dentry = d_alloc(sock_mnt->mnt_sb->s_root, &name); + if (unlikely(!path.dentry)) { + put_unused_fd(fd); return -ENOMEM; + } + path.mnt = mntget(sock_mnt); - dentry->d_op = &sockfs_dentry_operations; - /* - * We dont want to push this dentry into global dentry hash table. - * We pretend dentry is already hashed, by unsetting DCACHE_UNHASHED - * This permits a working /proc/$pid/fd/XXX on sockets - */ - dentry->d_flags &= ~DCACHE_UNHASHED; - d_instantiate(dentry, SOCK_INODE(sock)); + path.dentry->d_op = &sockfs_dentry_operations; + d_instantiate(path.dentry, SOCK_INODE(sock)); + SOCK_INODE(sock)->i_fop = &socket_file_ops; - sock->file = file; - init_file(file, sock_mnt, dentry, FMODE_READ | FMODE_WRITE, + file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &socket_file_ops); - SOCK_INODE(sock)->i_fop = &socket_file_ops; + if (unlikely(!file)) { + /* drop dentry, keep inode */ + atomic_inc(&path.dentry->d_inode->i_count); + path_put(&path); + put_unused_fd(fd); + return -ENFILE; + } + + sock->file = file; file->f_flags = O_RDWR | (flags & O_NONBLOCK); file->f_pos = 0; file->private_data = sock; - return 0; + *f = file; + return fd; } int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; - int fd = sock_alloc_fd(&newfile, flags); + int fd = sock_alloc_file(sock, &newfile, flags); - if (likely(fd >= 0)) { - int err = sock_attach_fd(sock, newfile, flags); - - if (unlikely(err < 0)) { - put_filp(newfile); - put_unused_fd(fd); - return err; - } + if (likely(fd >= 0)) fd_install(fd, newfile); - } + return fd; } @@ -1390,29 +1364,19 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, if (err < 0) goto out_release_both; - fd1 = sock_alloc_fd(&newfile1, flags & O_CLOEXEC); + fd1 = sock_alloc_file(sock1, &newfile1, flags); if (unlikely(fd1 < 0)) { err = fd1; goto out_release_both; } - fd2 = sock_alloc_fd(&newfile2, flags & O_CLOEXEC); + fd2 = sock_alloc_file(sock2, &newfile2, flags); if (unlikely(fd2 < 0)) { err = fd2; - put_filp(newfile1); - put_unused_fd(fd1); - goto out_release_both; - } - - err = sock_attach_fd(sock1, newfile1, flags & O_NONBLOCK); - if (unlikely(err < 0)) { - goto out_fd2; - } - - err = sock_attach_fd(sock2, newfile2, flags & O_NONBLOCK); - if (unlikely(err < 0)) { fput(newfile1); - goto out_fd1; + put_unused_fd(fd1); + sock_release(sock2); + goto out; } audit_fd_pair(fd1, fd2); @@ -1438,16 +1402,6 @@ out_release_1: sock_release(sock1); out: return err; - -out_fd2: - put_filp(newfile1); - sock_release(sock1); -out_fd1: - put_filp(newfile2); - sock_release(sock2); - put_unused_fd(fd1); - put_unused_fd(fd2); - goto out; } /* @@ -1551,17 +1505,13 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, */ __module_get(newsock->ops->owner); - newfd = sock_alloc_fd(&newfile, flags & O_CLOEXEC); + newfd = sock_alloc_file(newsock, &newfile, flags); if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); goto out_put; } - err = sock_attach_fd(newsock, newfile, flags & O_NONBLOCK); - if (err < 0) - goto out_fd_simple; - err = security_socket_accept(sock, newsock); if (err) goto out_fd; @@ -1591,11 +1541,6 @@ out_put: fput_light(sock->file, fput_needed); out: return err; -out_fd_simple: - sock_release(newsock); - put_filp(newfile); - put_unused_fd(newfd); - goto out_put; out_fd: fput(newfile); put_unused_fd(newfd); diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index c7450c8f0a7c..6dcdd2517819 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -55,16 +55,8 @@ static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, /* * RFC 4291, Section 2.2.1 - * - * To keep the result as short as possible, especially - * since we don't shorthand, we don't want leading zeros - * in each halfword, so avoid %pI6. */ - return snprintf(buf, buflen, "%x:%x:%x:%x:%x:%x:%x:%x", - ntohs(addr->s6_addr16[0]), ntohs(addr->s6_addr16[1]), - ntohs(addr->s6_addr16[2]), ntohs(addr->s6_addr16[3]), - ntohs(addr->s6_addr16[4]), ntohs(addr->s6_addr16[5]), - ntohs(addr->s6_addr16[6]), ntohs(addr->s6_addr16[7])); + return snprintf(buf, buflen, "%pI6c", addr); } static size_t rpc_ntop6(const struct sockaddr *sap, diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 7535a7bed2fa..f394fc190a49 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -123,16 +123,19 @@ rpcauth_unhash_cred_locked(struct rpc_cred *cred) clear_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags); } -static void +static int rpcauth_unhash_cred(struct rpc_cred *cred) { spinlock_t *cache_lock; + int ret; cache_lock = &cred->cr_auth->au_credcache->lock; spin_lock(cache_lock); - if (atomic_read(&cred->cr_count) == 0) + ret = atomic_read(&cred->cr_count) == 0; + if (ret) rpcauth_unhash_cred_locked(cred); spin_unlock(cache_lock); + return ret; } /* @@ -446,31 +449,35 @@ void put_rpccred(struct rpc_cred *cred) { /* Fast path for unhashed credentials */ - if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) - goto need_lock; - - if (!atomic_dec_and_test(&cred->cr_count)) + if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) == 0) { + if (atomic_dec_and_test(&cred->cr_count)) + cred->cr_ops->crdestroy(cred); return; - goto out_destroy; -need_lock: + } + if (!atomic_dec_and_lock(&cred->cr_count, &rpc_credcache_lock)) return; if (!list_empty(&cred->cr_lru)) { number_cred_unused--; list_del_init(&cred->cr_lru); } - if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0) - rpcauth_unhash_cred(cred); if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) { - cred->cr_expire = jiffies; - list_add_tail(&cred->cr_lru, &cred_unused); - number_cred_unused++; - spin_unlock(&rpc_credcache_lock); - return; + if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0) { + cred->cr_expire = jiffies; + list_add_tail(&cred->cr_lru, &cred_unused); + number_cred_unused++; + goto out_nodestroy; + } + if (!rpcauth_unhash_cred(cred)) { + /* We were hashed and someone looked us up... */ + goto out_nodestroy; + } } spin_unlock(&rpc_credcache_lock); -out_destroy: cred->cr_ops->crdestroy(cred); + return; +out_nodestroy: + spin_unlock(&rpc_credcache_lock); } EXPORT_SYMBOL_GPL(put_rpccred); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index fc6a43ccd950..3c3c50f38a1c 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -304,7 +304,7 @@ __gss_find_upcall(struct rpc_inode *rpci, uid_t uid) * to that upcall instead of adding the new upcall. */ static inline struct gss_upcall_msg * -gss_add_msg(struct gss_auth *gss_auth, struct gss_upcall_msg *gss_msg) +gss_add_msg(struct gss_upcall_msg *gss_msg) { struct rpc_inode *rpci = gss_msg->inode; struct inode *inode = &rpci->vfs_inode; @@ -445,7 +445,7 @@ gss_setup_upcall(struct rpc_clnt *clnt, struct gss_auth *gss_auth, struct rpc_cr gss_new = gss_alloc_msg(gss_auth, uid, clnt, gss_cred->gc_machine_cred); if (IS_ERR(gss_new)) return gss_new; - gss_msg = gss_add_msg(gss_auth, gss_new); + gss_msg = gss_add_msg(gss_new); if (gss_msg == gss_new) { struct inode *inode = &gss_new->inode->vfs_inode; int res = rpc_queue_upcall(inode, &gss_new->msg); @@ -485,7 +485,7 @@ gss_refresh_upcall(struct rpc_task *task) dprintk("RPC: %5u gss_refresh_upcall for uid %u\n", task->tk_pid, cred->cr_uid); gss_msg = gss_setup_upcall(task->tk_client, gss_auth, cred); - if (IS_ERR(gss_msg) == -EAGAIN) { + if (PTR_ERR(gss_msg) == -EAGAIN) { /* XXX: warning on the first, under the assumption we * shouldn't normally hit this case on a refresh. */ warn_gssd(); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 38829e20500b..154034b675bd 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -79,7 +79,7 @@ static void call_connect_status(struct rpc_task *task); static __be32 *rpc_encode_header(struct rpc_task *task); static __be32 *rpc_verify_header(struct rpc_task *task); -static int rpc_ping(struct rpc_clnt *clnt, int flags); +static int rpc_ping(struct rpc_clnt *clnt); static void rpc_register_client(struct rpc_clnt *clnt) { @@ -340,7 +340,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) return clnt; if (!(args->flags & RPC_CLNT_CREATE_NOPING)) { - int err = rpc_ping(clnt, RPC_TASK_SOFT); + int err = rpc_ping(clnt); if (err != 0) { rpc_shutdown_client(clnt); return ERR_PTR(err); @@ -528,7 +528,7 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old, clnt->cl_prog = program->number; clnt->cl_vers = version->number; clnt->cl_stats = program->stats; - err = rpc_ping(clnt, RPC_TASK_SOFT); + err = rpc_ping(clnt); if (err != 0) { rpc_shutdown_client(clnt); clnt = ERR_PTR(err); @@ -1060,7 +1060,7 @@ call_bind_status(struct rpc_task *task) goto retry_timeout; case -EPFNOSUPPORT: /* server doesn't support any rpcbind version we know of */ - dprintk("RPC: %5u remote rpcbind service unavailable\n", + dprintk("RPC: %5u unrecognized remote rpcbind service\n", task->tk_pid); break; case -EPROTONOSUPPORT: @@ -1069,6 +1069,21 @@ call_bind_status(struct rpc_task *task) task->tk_status = 0; task->tk_action = call_bind; return; + case -ECONNREFUSED: /* connection problems */ + case -ECONNRESET: + case -ENOTCONN: + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -EPIPE: + dprintk("RPC: %5u remote rpcbind unreachable: %d\n", + task->tk_pid, task->tk_status); + if (!RPC_IS_SOFTCONN(task)) { + rpc_delay(task, 5*HZ); + goto retry_timeout; + } + status = task->tk_status; + break; default: dprintk("RPC: %5u unrecognized rpcbind error (%d)\n", task->tk_pid, -task->tk_status); @@ -1180,11 +1195,25 @@ static void call_transmit_status(struct rpc_task *task) { task->tk_action = call_status; + + /* + * Common case: success. Force the compiler to put this + * test first. + */ + if (task->tk_status == 0) { + xprt_end_transmit(task); + rpc_task_force_reencode(task); + return; + } + switch (task->tk_status) { case -EAGAIN: break; default: + dprint_status(task); xprt_end_transmit(task); + rpc_task_force_reencode(task); + break; /* * Special cases: if we've been waiting on the * socket's write_space() callback, or if the @@ -1192,11 +1221,16 @@ call_transmit_status(struct rpc_task *task) * then hold onto the transport lock. */ case -ECONNREFUSED: - case -ECONNRESET: - case -ENOTCONN: case -EHOSTDOWN: case -EHOSTUNREACH: case -ENETUNREACH: + if (RPC_IS_SOFTCONN(task)) { + xprt_end_transmit(task); + rpc_exit(task, task->tk_status); + break; + } + case -ECONNRESET: + case -ENOTCONN: case -EPIPE: rpc_task_force_reencode(task); } @@ -1346,6 +1380,10 @@ call_timeout(struct rpc_task *task) dprintk("RPC: %5u call_timeout (major)\n", task->tk_pid); task->tk_timeouts++; + if (RPC_IS_SOFTCONN(task)) { + rpc_exit(task, -ETIMEDOUT); + return; + } if (RPC_IS_SOFT(task)) { if (clnt->cl_chatty) printk(KERN_NOTICE "%s: server %s not responding, timed out\n", @@ -1675,14 +1713,14 @@ static struct rpc_procinfo rpcproc_null = { .p_decode = rpcproc_decode_null, }; -static int rpc_ping(struct rpc_clnt *clnt, int flags) +static int rpc_ping(struct rpc_clnt *clnt) { struct rpc_message msg = { .rpc_proc = &rpcproc_null, }; int err; msg.rpc_cred = authnull_ops.lookup_cred(NULL, NULL, 0); - err = rpc_call_sync(clnt, &msg, flags); + err = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN); put_rpccred(msg.rpc_cred); return err; } diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 830faf4d9997..3e3772d8eb92 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -20,6 +20,7 @@ #include <linux/in6.h> #include <linux/kernel.h> #include <linux/errno.h> +#include <linux/mutex.h> #include <net/ipv6.h> #include <linux/sunrpc/clnt.h> @@ -110,6 +111,9 @@ static void rpcb_getport_done(struct rpc_task *, void *); static void rpcb_map_release(void *data); static struct rpc_program rpcb_program; +static struct rpc_clnt * rpcb_local_clnt; +static struct rpc_clnt * rpcb_local_clnt4; + struct rpcbind_args { struct rpc_xprt * r_xprt; @@ -163,21 +167,60 @@ static const struct sockaddr_in rpcb_inaddr_loopback = { .sin_port = htons(RPCBIND_PORT), }; -static struct rpc_clnt *rpcb_create_local(struct sockaddr *addr, - size_t addrlen, u32 version) +static DEFINE_MUTEX(rpcb_create_local_mutex); + +/* + * Returns zero on success, otherwise a negative errno value + * is returned. + */ +static int rpcb_create_local(void) { struct rpc_create_args args = { - .protocol = XPRT_TRANSPORT_UDP, - .address = addr, - .addrsize = addrlen, + .protocol = XPRT_TRANSPORT_TCP, + .address = (struct sockaddr *)&rpcb_inaddr_loopback, + .addrsize = sizeof(rpcb_inaddr_loopback), .servername = "localhost", .program = &rpcb_program, - .version = version, + .version = RPCBVERS_2, .authflavor = RPC_AUTH_UNIX, .flags = RPC_CLNT_CREATE_NOPING, }; + struct rpc_clnt *clnt, *clnt4; + int result = 0; + + if (rpcb_local_clnt) + return result; + + mutex_lock(&rpcb_create_local_mutex); + if (rpcb_local_clnt) + goto out; + + clnt = rpc_create(&args); + if (IS_ERR(clnt)) { + dprintk("RPC: failed to create local rpcbind " + "client (errno %ld).\n", PTR_ERR(clnt)); + result = -PTR_ERR(clnt); + goto out; + } - return rpc_create(&args); + /* + * This results in an RPC ping. On systems running portmapper, + * the v4 ping will fail. Proceed anyway, but disallow rpcb + * v4 upcalls. + */ + clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4); + if (IS_ERR(clnt4)) { + dprintk("RPC: failed to create local rpcbind v4 " + "cleint (errno %ld).\n", PTR_ERR(clnt4)); + clnt4 = NULL; + } + + rpcb_local_clnt = clnt; + rpcb_local_clnt4 = clnt4; + +out: + mutex_unlock(&rpcb_create_local_mutex); + return result; } static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr, @@ -209,22 +252,13 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr, return rpc_create(&args); } -static int rpcb_register_call(const u32 version, struct rpc_message *msg) +static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg) { - struct sockaddr *addr = (struct sockaddr *)&rpcb_inaddr_loopback; - size_t addrlen = sizeof(rpcb_inaddr_loopback); - struct rpc_clnt *rpcb_clnt; int result, error = 0; msg->rpc_resp = &result; - rpcb_clnt = rpcb_create_local(addr, addrlen, version); - if (!IS_ERR(rpcb_clnt)) { - error = rpc_call_sync(rpcb_clnt, msg, 0); - rpc_shutdown_client(rpcb_clnt); - } else - error = PTR_ERR(rpcb_clnt); - + error = rpc_call_sync(clnt, msg, RPC_TASK_SOFTCONN); if (error < 0) { dprintk("RPC: failed to contact local rpcbind " "server (errno %d).\n", -error); @@ -279,6 +313,11 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port) struct rpc_message msg = { .rpc_argp = &map, }; + int error; + + error = rpcb_create_local(); + if (error) + return error; dprintk("RPC: %sregistering (%u, %u, %d, %u) with local " "rpcbind\n", (port ? "" : "un"), @@ -288,7 +327,7 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port) if (port) msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_2, &msg); + return rpcb_register_call(rpcb_local_clnt, &msg); } /* @@ -313,7 +352,7 @@ static int rpcb_register_inet4(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - result = rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(rpcb_local_clnt4, msg); kfree(map->r_addr); return result; } @@ -340,7 +379,7 @@ static int rpcb_register_inet6(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - result = rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(rpcb_local_clnt4, msg); kfree(map->r_addr); return result; } @@ -356,7 +395,7 @@ static int rpcb_unregister_all_protofamilies(struct rpc_message *msg) map->r_addr = ""; msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - return rpcb_register_call(RPCBVERS_4, msg); + return rpcb_register_call(rpcb_local_clnt4, msg); } /** @@ -414,6 +453,13 @@ int rpcb_v4_register(const u32 program, const u32 version, struct rpc_message msg = { .rpc_argp = &map, }; + int error; + + error = rpcb_create_local(); + if (error) + return error; + if (rpcb_local_clnt4 == NULL) + return -EPROTONOSUPPORT; if (address == NULL) return rpcb_unregister_all_protofamilies(&msg); @@ -491,7 +537,7 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi .rpc_message = &msg, .callback_ops = &rpcb_getport_ops, .callback_data = map, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | RPC_TASK_SOFTCONN, }; return rpc_run_task(&task_setup_data); @@ -1027,3 +1073,15 @@ static struct rpc_program rpcb_program = { .version = rpcb_version, .stats = &rpcb_stats, }; + +/** + * cleanup_rpcb_clnt - remove xprtsock's sysctls, unregister + * + */ +void cleanup_rpcb_clnt(void) +{ + if (rpcb_local_clnt4) + rpc_shutdown_client(rpcb_local_clnt4); + if (rpcb_local_clnt) + rpc_shutdown_client(rpcb_local_clnt); +} diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index cef74ba0666c..aae6907fd546 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -210,6 +210,7 @@ void rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qnam { __rpc_init_priority_wait_queue(queue, qname, RPC_NR_PRIORITY); } +EXPORT_SYMBOL_GPL(rpc_init_priority_wait_queue); void rpc_init_wait_queue(struct rpc_wait_queue *queue, const char *qname) { @@ -385,6 +386,20 @@ static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct r } /* + * Tests whether rpc queue is empty + */ +int rpc_queue_empty(struct rpc_wait_queue *queue) +{ + int res; + + spin_lock_bh(&queue->lock); + res = queue->qlen; + spin_unlock_bh(&queue->lock); + return (res == 0); +} +EXPORT_SYMBOL_GPL(rpc_queue_empty); + +/* * Wake up a task on a specific queue */ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task) diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 8cce92189019..f438347d817b 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -24,6 +24,8 @@ extern struct cache_detail ip_map_cache, unix_gid_cache; +extern void cleanup_rpcb_clnt(void); + static int __init init_sunrpc(void) { @@ -53,6 +55,7 @@ out: static void __exit cleanup_sunrpc(void) { + cleanup_rpcb_clnt(); rpcauth_remove_module(); cleanup_socket_xprt(); svc_cleanup_xprt_sock(); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index b845e2293dfe..1c924ee0a1ef 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -16,8 +16,6 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT -#define SVC_MAX_WAKING 5 - static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); @@ -306,7 +304,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) struct svc_pool *pool; struct svc_rqst *rqstp; int cpu; - int thread_avail; if (!(xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED)))) @@ -318,6 +315,12 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) spin_lock_bh(&pool->sp_lock); + if (!list_empty(&pool->sp_threads) && + !list_empty(&pool->sp_sockets)) + printk(KERN_ERR + "svc_xprt_enqueue: " + "threads and transports both waiting??\n"); + if (test_bit(XPT_DEAD, &xprt->xpt_flags)) { /* Don't enqueue dead transports */ dprintk("svc: transport %p is dead, not enqueued\n", xprt); @@ -358,15 +361,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) } process: - /* Work out whether threads are available */ - thread_avail = !list_empty(&pool->sp_threads); /* threads are asleep */ - if (pool->sp_nwaking >= SVC_MAX_WAKING) { - /* too many threads are runnable and trying to wake up */ - thread_avail = 0; - pool->sp_stats.overloads_avoided++; - } - - if (thread_avail) { + if (!list_empty(&pool->sp_threads)) { rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, rq_list); @@ -381,8 +376,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) svc_xprt_get(xprt); rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); - rqstp->rq_waking = 1; - pool->sp_nwaking++; pool->sp_stats.threads_woken++; BUG_ON(xprt->xpt_pool != pool); wake_up(&rqstp->rq_wait); @@ -651,11 +644,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) return -EINTR; spin_lock_bh(&pool->sp_lock); - if (rqstp->rq_waking) { - rqstp->rq_waking = 0; - pool->sp_nwaking--; - BUG_ON(pool->sp_nwaking < 0); - } xprt = svc_xprt_dequeue(pool); if (xprt) { rqstp->rq_xprt = xprt; @@ -1204,16 +1192,15 @@ static int svc_pool_stats_show(struct seq_file *m, void *p) struct svc_pool *pool = p; if (p == SEQ_START_TOKEN) { - seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken overloads-avoided threads-timedout\n"); + seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken threads-timedout\n"); return 0; } - seq_printf(m, "%u %lu %lu %lu %lu %lu\n", + seq_printf(m, "%u %lu %lu %lu %lu\n", pool->sp_id, pool->sp_stats.packets, pool->sp_stats.sockets_queued, pool->sp_stats.threads_woken, - pool->sp_stats.overloads_avoided, pool->sp_stats.threads_timedout); return 0; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 4a8f6558718a..d8c041114497 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -655,23 +655,25 @@ static struct unix_gid *unix_gid_lookup(uid_t uid) return NULL; } -static int unix_gid_find(uid_t uid, struct group_info **gip, - struct svc_rqst *rqstp) +static struct group_info *unix_gid_find(uid_t uid, struct svc_rqst *rqstp) { - struct unix_gid *ug = unix_gid_lookup(uid); + struct unix_gid *ug; + struct group_info *gi; + int ret; + + ug = unix_gid_lookup(uid); if (!ug) - return -EAGAIN; - switch (cache_check(&unix_gid_cache, &ug->h, &rqstp->rq_chandle)) { + return ERR_PTR(-EAGAIN); + ret = cache_check(&unix_gid_cache, &ug->h, &rqstp->rq_chandle); + switch (ret) { case -ENOENT: - *gip = NULL; - return 0; + return ERR_PTR(-ENOENT); case 0: - *gip = ug->gi; - get_group_info(*gip); + gi = get_group_info(ug->gi); cache_put(&ug->h, &unix_gid_cache); - return 0; + return gi; default: - return -EAGAIN; + return ERR_PTR(-EAGAIN); } } @@ -681,6 +683,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) struct sockaddr_in *sin; struct sockaddr_in6 *sin6, sin6_storage; struct ip_map *ipm; + struct group_info *gi; + struct svc_cred *cred = &rqstp->rq_cred; switch (rqstp->rq_addr.ss_family) { case AF_INET: @@ -721,6 +725,17 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) ip_map_cached_put(rqstp, ipm); break; } + + gi = unix_gid_find(cred->cr_uid, rqstp); + switch (PTR_ERR(gi)) { + case -EAGAIN: + return SVC_DROP; + case -ENOENT: + break; + default: + put_group_info(cred->cr_group_info); + cred->cr_group_info = gi; + } return SVC_OK; } @@ -817,19 +832,11 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) slen = svc_getnl(argv); /* gids length */ if (slen > 16 || (len -= (slen + 2)*4) < 0) goto badcred; - if (unix_gid_find(cred->cr_uid, &cred->cr_group_info, rqstp) - == -EAGAIN) + cred->cr_group_info = groups_alloc(slen); + if (cred->cr_group_info == NULL) return SVC_DROP; - if (cred->cr_group_info == NULL) { - cred->cr_group_info = groups_alloc(slen); - if (cred->cr_group_info == NULL) - return SVC_DROP; - for (i = 0; i < slen; i++) - GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv); - } else { - for (i = 0; i < slen ; i++) - svc_getnl(argv); - } + for (i = 0; i < slen; i++) + GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv); if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; return SVC_DENIED; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index fd46d42afa89..469de292c23c 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -700,6 +700,10 @@ void xprt_connect(struct rpc_task *task) } if (!xprt_lock_write(xprt, task)) return; + + if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) + xprt->ops->close(xprt); + if (xprt_connected(xprt)) xprt_release_write(xprt, task); else { diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index f11be72a1a80..b15e1ebb2bfa 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -54,7 +54,7 @@ * Assumptions: * - head[0] is physically contiguous. * - tail[0] is physically contiguous. - * - pages[] is not physically or virtually contigous and consists of + * - pages[] is not physically or virtually contiguous and consists of * PAGE_SIZE elements. * * Output: diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 04732d09013e..3d739e5d15d8 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2019,7 +2019,7 @@ static void xs_connect(struct rpc_task *task) if (xprt_test_and_set_connecting(xprt)) return; - if (transport->sock != NULL) { + if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) { dprintk("RPC: xs_connect delayed xprt %p for %lu " "seconds\n", xprt, xprt->reestablish_timeout / HZ); diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 0b15d7250c40..53196009160a 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -71,7 +71,7 @@ static struct ctl_table_root net_sysctl_ro_root = { .permissions = net_ctl_ro_header_perms, }; -static int sysctl_net_init(struct net *net) +static int __net_init sysctl_net_init(struct net *net) { setup_sysctl_set(&net->sysctls, &net_sysctl_ro_root.default_set, @@ -79,7 +79,7 @@ static int sysctl_net_init(struct net *net) return 0; } -static void sysctl_net_exit(struct net *net) +static void __net_exit sysctl_net_exit(struct net *net) { WARN_ON(!list_empty(&net->sysctls.list)); return; diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 3b30d1130b61..dafbd533067c 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -33,6 +33,7 @@ config TIPC_ADVANCED config TIPC_ZONES int "Maximum number of zones in network" depends on TIPC_ADVANCED + range 1 255 default "3" help Max number of zones inside TIPC network. Max supported value @@ -44,10 +45,10 @@ config TIPC_ZONES config TIPC_CLUSTERS int "Maximum number of clusters in a zone" depends on TIPC_ADVANCED + range 1 1 default "1" help - ***Only 1 (one cluster in a zone) is supported by current code. - Any value set here will be overridden.*** + ***Only 1 (one cluster in a zone) is supported by current code.*** (Max number of clusters inside TIPC zone. Max supported value is 4095 clusters, minimum is 1. @@ -59,6 +60,7 @@ config TIPC_CLUSTERS config TIPC_NODES int "Maximum number of nodes in cluster" depends on TIPC_ADVANCED + range 8 2047 default "255" help Maximum number of nodes inside a TIPC cluster. Maximum @@ -70,6 +72,7 @@ config TIPC_NODES config TIPC_SLAVE_NODES int "Maximum number of slave nodes in cluster" depends on TIPC_ADVANCED + range 0 2047 default "0" help ***This capability is not supported by current code.*** @@ -83,6 +86,7 @@ config TIPC_SLAVE_NODES config TIPC_PORTS int "Maximum number of ports in a node" depends on TIPC_ADVANCED + range 217 65536 default "8191" help Maximum number of ports within a node. Maximum diff --git a/net/tipc/core.c b/net/tipc/core.c index 3256bd7d398f..52c571fedbe0 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -189,11 +189,11 @@ static int __init tipc_init(void) tipc_remote_management = 1; tipc_max_publications = 10000; tipc_max_subscriptions = 2000; - tipc_max_ports = delimit(CONFIG_TIPC_PORTS, 127, 65536); - tipc_max_zones = delimit(CONFIG_TIPC_ZONES, 1, 255); - tipc_max_clusters = delimit(CONFIG_TIPC_CLUSTERS, 1, 1); - tipc_max_nodes = delimit(CONFIG_TIPC_NODES, 8, 2047); - tipc_max_slaves = delimit(CONFIG_TIPC_SLAVE_NODES, 0, 2047); + tipc_max_ports = CONFIG_TIPC_PORTS; + tipc_max_zones = CONFIG_TIPC_ZONES; + tipc_max_clusters = CONFIG_TIPC_CLUSTERS; + tipc_max_nodes = CONFIG_TIPC_NODES; + tipc_max_slaves = CONFIG_TIPC_SLAVE_NODES; tipc_net_id = 4711; if ((res = tipc_core_start())) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f25511903115..9bc9b92bc099 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2224,7 +2224,7 @@ static const struct net_proto_family unix_family_ops = { }; -static int unix_net_init(struct net *net) +static int __net_init unix_net_init(struct net *net) { int error = -ENOMEM; @@ -2243,7 +2243,7 @@ out: return error; } -static void unix_net_exit(struct net *net) +static void __net_exit unix_net_exit(struct net *net) { unix_sysctl_unregister(net); proc_net_remove(net, "unix"); diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c index 708f5df6b7f0..d095c7be10d0 100644 --- a/net/unix/sysctl_net_unix.c +++ b/net/unix/sysctl_net_unix.c @@ -31,7 +31,7 @@ static struct ctl_path unix_path[] = { { }, }; -int unix_sysctl_register(struct net *net) +int __net_init unix_sysctl_register(struct net *net) { struct ctl_table *table; diff --git a/net/wimax/op-reset.c b/net/wimax/op-reset.c index ca269178c4d4..35f370091f4f 100644 --- a/net/wimax/op-reset.c +++ b/net/wimax/op-reset.c @@ -62,7 +62,7 @@ * Called when wanting to reset the device for any reason. Device is * taken back to power on status. * - * This call blocks; on succesful return, the device has completed the + * This call blocks; on successful return, the device has completed the * reset process and is ready to operate. */ int wimax_reset(struct wimax_dev *wimax_dev) diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk index 8316cf075ce9..3cc9e69880a8 100644 --- a/net/wireless/genregdb.awk +++ b/net/wireless/genregdb.awk @@ -26,11 +26,11 @@ BEGIN { } /^[ \t]*#/ { - /* Ignore */ + # Ignore } !active && /^[ \t]*$/ { - /* Ignore */ + # Ignore } !active && /country/ { diff --git a/net/wireless/wext-proc.c b/net/wireless/wext-proc.c index 273a7f77c834..8bafa31fa9f8 100644 --- a/net/wireless/wext-proc.c +++ b/net/wireless/wext-proc.c @@ -140,7 +140,7 @@ static const struct file_operations wireless_seq_fops = { .release = seq_release_net, }; -int wext_proc_init(struct net *net) +int __net_init wext_proc_init(struct net *net) { /* Create /proc/net/wireless entry */ if (!proc_net_fops_create(net, "wireless", S_IRUGO, &wireless_seq_fops)) @@ -149,7 +149,7 @@ int wext_proc_init(struct net *net) return 0; } -void wext_proc_exit(struct net *net) +void __net_exit wext_proc_exit(struct net *net) { proc_net_remove(net, "wireless"); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index cb81ca35b0d6..4725a549ad4d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1445,7 +1445,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (!dev) goto free_dst; - /* Copy neighbout for reachability confirmation */ + /* Copy neighbour for reachability confirmation */ dst0->neighbour = neigh_clone(dst->neighbour); xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len); diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c index 2e221f2cad7e..2c4d6cdcba49 100644 --- a/net/xfrm/xfrm_sysctl.c +++ b/net/xfrm/xfrm_sysctl.c @@ -2,7 +2,7 @@ #include <net/net_namespace.h> #include <net/xfrm.h> -static void __xfrm_sysctl_init(struct net *net) +static void __net_init __xfrm_sysctl_init(struct net *net) { net->xfrm.sysctl_aevent_etime = XFRM_AE_ETIME; net->xfrm.sysctl_aevent_rseqth = XFRM_AE_SEQT_SIZE; @@ -64,7 +64,7 @@ out_kmemdup: return -ENOMEM; } -void xfrm_sysctl_fini(struct net *net) +void __net_exit xfrm_sysctl_fini(struct net *net) { struct ctl_table *table; |