diff options
Diffstat (limited to 'net')
109 files changed, 953 insertions, 749 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index b7889782047..c1b92cab46c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -163,7 +163,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, goto err_unlock; } - rx_stats = per_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats, + rx_stats = per_cpu_ptr(vlan_dev_info(skb->dev)->vlan_rx_stats, smp_processor_id()); rx_stats->rx_packets++; rx_stats->rx_bytes += skb->len; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 4dd873e3a1b..be1cb909d8c 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/appletalk/aarp.c b/net/appletalk/aarp.c index 9d4adfd2275..f2b3b56aa77 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -819,7 +819,7 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev, ma = &ifa->address; else { /* We need to make a copy of the entry. */ da.s_node = sa.s_node; - da.s_net = da.s_net; + da.s_net = sa.s_net; ma = &da; } diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c index bf706f83a5c..14912600ec5 100644 --- a/net/ax25/ax25_out.c +++ b/net/ax25/ax25_out.c @@ -92,6 +92,12 @@ ax25_cb *ax25_send_frame(struct sk_buff *skb, int paclen, ax25_address *src, ax2 #endif } + /* + * There is one ref for the state machine; a caller needs + * one more to put it back, just like with the existing one. + */ + ax25_cb_hold(ax25); + ax25_cb_add(ax25); ax25->state = AX25_STATE_1; diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 29b1b220d6c..ef09c7b3a85 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/hci_conn.c b/net/bluetooth/hci_conn.c index b7c4224f4e7..b10e3cdb08f 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -377,6 +377,9 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 if (acl->state == BT_CONNECTED && (sco->state == BT_OPEN || sco->state == BT_CLOSED)) { + acl->power_save = 1; + hci_conn_enter_active_mode(acl); + if (lmp_esco_capable(hdev)) hci_setup_sync(sco, acl->handle); else diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 28517bad796..592da5c909c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1699,6 +1699,7 @@ static inline void hci_sync_conn_complete_evt(struct hci_dev *hdev, struct sk_bu break; case 0x1c: /* SCO interval rejected */ + case 0x1a: /* Unsupported Remote Feature */ case 0x1f: /* Unspecified error */ if (conn->out && conn->attempt < 2) { conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) | diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 569750010fd..fc6ec1e7265 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -243,6 +243,39 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb) input_sync(dev); } +static int __hidp_send_ctrl_message(struct hidp_session *session, + unsigned char hdr, unsigned char *data, int size) +{ + struct sk_buff *skb; + + BT_DBG("session %p data %p size %d", session, data, size); + + if (!(skb = alloc_skb(size + 1, GFP_ATOMIC))) { + BT_ERR("Can't allocate memory for new frame"); + return -ENOMEM; + } + + *skb_put(skb, 1) = hdr; + if (data && size > 0) + memcpy(skb_put(skb, size), data, size); + + skb_queue_tail(&session->ctrl_transmit, skb); + + return 0; +} + +static inline int hidp_send_ctrl_message(struct hidp_session *session, + unsigned char hdr, unsigned char *data, int size) +{ + int err; + + err = __hidp_send_ctrl_message(session, hdr, data, size); + + hidp_schedule(session); + + return err; +} + static int hidp_queue_report(struct hidp_session *session, unsigned char *data, int size) { @@ -282,7 +315,9 @@ static int hidp_send_report(struct hidp_session *session, struct hid_report *rep static int hidp_output_raw_report(struct hid_device *hid, unsigned char *data, size_t count) { - if (hidp_queue_report(hid->driver_data, data, count)) + if (hidp_send_ctrl_message(hid->driver_data, + HIDP_TRANS_SET_REPORT | HIDP_DATA_RTYPE_FEATURE, + data, count)) return -ENOMEM; return count; } @@ -307,39 +342,6 @@ static inline void hidp_del_timer(struct hidp_session *session) del_timer(&session->timer); } -static int __hidp_send_ctrl_message(struct hidp_session *session, - unsigned char hdr, unsigned char *data, int size) -{ - struct sk_buff *skb; - - BT_DBG("session %p data %p size %d", session, data, size); - - if (!(skb = alloc_skb(size + 1, GFP_ATOMIC))) { - BT_ERR("Can't allocate memory for new frame"); - return -ENOMEM; - } - - *skb_put(skb, 1) = hdr; - if (data && size > 0) - memcpy(skb_put(skb, size), data, size); - - skb_queue_tail(&session->ctrl_transmit, skb); - - return 0; -} - -static inline int hidp_send_ctrl_message(struct hidp_session *session, - unsigned char hdr, unsigned char *data, int size) -{ - int err; - - err = __hidp_send_ctrl_message(session, hdr, data, size); - - hidp_schedule(session); - - return err; -} - static void hidp_process_handshake(struct hidp_session *session, unsigned char param) { @@ -701,29 +703,9 @@ static void hidp_close(struct hid_device *hid) static int hidp_parse(struct hid_device *hid) { struct hidp_session *session = hid->driver_data; - struct hidp_connadd_req *req = session->req; - unsigned char *buf; - int ret; - - buf = kmalloc(req->rd_size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (copy_from_user(buf, req->rd_data, req->rd_size)) { - kfree(buf); - return -EFAULT; - } - - ret = hid_parse_report(session->hid, buf, req->rd_size); - - kfree(buf); - - if (ret) - return ret; - session->req = NULL; - - return 0; + return hid_parse_report(session->hid, session->rd_data, + session->rd_size); } static int hidp_start(struct hid_device *hid) @@ -768,12 +750,24 @@ static int hidp_setup_hid(struct hidp_session *session, bdaddr_t src, dst; int err; + session->rd_data = kzalloc(req->rd_size, GFP_KERNEL); + if (!session->rd_data) + return -ENOMEM; + + if (copy_from_user(session->rd_data, req->rd_data, req->rd_size)) { + err = -EFAULT; + goto fault; + } + session->rd_size = req->rd_size; + hid = hid_allocate_device(); - if (IS_ERR(hid)) - return PTR_ERR(session->hid); + if (IS_ERR(hid)) { + err = PTR_ERR(hid); + goto fault; + } session->hid = hid; - session->req = req; + hid->driver_data = session; baswap(&src, &bt_sk(session->ctrl_sock->sk)->src); @@ -804,6 +798,10 @@ failed: hid_destroy_device(hid); session->hid = NULL; +fault: + kfree(session->rd_data); + session->rd_data = NULL; + return err; } @@ -898,6 +896,9 @@ unlink: session->hid = NULL; } + kfree(session->rd_data); + session->rd_data = NULL; + purge: skb_queue_purge(&session->ctrl_transmit); skb_queue_purge(&session->intr_transmit); diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index faf3d74c358..a4e215d50c1 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -154,7 +154,9 @@ struct hidp_session { struct sk_buff_head ctrl_transmit; struct sk_buff_head intr_transmit; - struct hidp_connadd_req *req; + /* Report descriptor */ + __u8 *rd_data; + uint rd_size; }; static inline void hidp_schedule(struct hidp_session *session) diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 5129b88c8e5..400efa26ddb 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; } @@ -1367,7 +1368,6 @@ static int l2cap_ertm_send(struct sock *sk) while ((skb = sk->sk_send_head) && (!l2cap_tx_window_full(sk)) && !(pi->conn_state & L2CAP_CONN_REMOTE_BUSY)) { - tx_skb = skb_clone(skb, GFP_ATOMIC); if (pi->remote_max_tx && bt_cb(skb)->retries == pi->remote_max_tx) { @@ -1375,6 +1375,8 @@ static int l2cap_ertm_send(struct sock *sk) break; } + tx_skb = skb_clone(skb, GFP_ATOMIC); + bt_cb(skb)->retries++; control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); @@ -3435,8 +3437,8 @@ 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 +3473,9 @@ 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; @@ -3517,7 +3519,6 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk struct l2cap_pinfo *pi; u16 control, len; u8 tx_seq; - int err; sk = l2cap_get_chan_by_scid(&conn->chan_list, cid); if (!sk) { @@ -3569,13 +3570,11 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk goto drop; if (__is_iframe(control)) - err = l2cap_data_channel_iframe(sk, control, skb); + l2cap_data_channel_iframe(sk, control, skb); else - err = l2cap_data_channel_sframe(sk, control, skb); + l2cap_data_channel_sframe(sk, control, skb); - if (!err) - goto done; - break; + goto done; case L2CAP_MODE_STREAMING: control = get_unaligned_le16(skb->data); @@ -3601,7 +3600,7 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk else pi->expected_tx_seq = tx_seq + 1; - err = l2cap_sar_reassembly_sdu(sk, skb, control); + l2cap_sar_reassembly_sdu(sk, skb, control); goto done; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index fc5ee3296e2..89f4a59eb82 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -252,7 +252,6 @@ static void rfcomm_session_timeout(unsigned long arg) BT_DBG("session %p state %ld", s, s->state); set_bit(RFCOMM_TIMED_OUT, &s->flags); - rfcomm_session_put(s); rfcomm_schedule(RFCOMM_SCHED_TIMEO); } @@ -1151,7 +1150,11 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) break; case BT_DISCONN: - rfcomm_session_put(s); + /* When socket is closed and we are not RFCOMM + * initiator rfcomm_process_rx already calls + * rfcomm_session_put() */ + if (s->sock->sk->sk_state != BT_CLOSED) + rfcomm_session_put(s); break; } } @@ -1920,6 +1923,7 @@ static inline void rfcomm_process_sessions(void) if (test_and_clear_bit(RFCOMM_TIMED_OUT, &s->flags)) { s->state = BT_DISCONN; rfcomm_send_disc(s, 0); + rfcomm_session_put(s); continue; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bd1c65425d4..0b7f262cd14 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/compat.c b/net/compat.c index e1a56ade803..a1fb1b079a8 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 c36a17aafcf..be9924f60ec 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4771,21 +4771,23 @@ 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 +5035,11 @@ 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 +5602,12 @@ 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/dst.c b/net/core/dst.c index 57bc4d5b8d0..cb1b3488b73 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -17,6 +17,7 @@ #include <linux/string.h> #include <linux/types.h> #include <net/net_namespace.h> +#include <linux/sched.h> #include <net/dst.h> @@ -79,6 +80,7 @@ loop: while ((dst = next) != NULL) { next = dst->next; prefetch(&next->next); + cond_resched(); if (likely(atomic_read(&dst->__refcnt))) { last->next = dst; last = dst; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a23b45f08ec..2e692afdc55 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", @@ -3519,6 +3524,7 @@ static int pktgen_thread_worker(void *arg) wait_event_interruptible_timeout(t->queue, t->control != 0, HZ/10); + try_to_freeze(); continue; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 33148a56819..794bcb897ff 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); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bfa3e7865a8..93c4e060c91 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 76ff58d43e2..e1f6f225f01 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -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; diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index f3e9ba1cfd0..ff16e9df196 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -77,34 +77,24 @@ int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, return err; } -static struct kmem_cache *ccid_kmem_cache_create(int obj_size, const char *fmt,...) +static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...) { struct kmem_cache *slab; - char slab_name_fmt[32], *slab_name; va_list args; va_start(args, fmt); - vsnprintf(slab_name_fmt, sizeof(slab_name_fmt), fmt, args); + vsnprintf(slab_name_fmt, CCID_SLAB_NAME_LENGTH, fmt, args); va_end(args); - slab_name = kstrdup(slab_name_fmt, GFP_KERNEL); - if (slab_name == NULL) - return NULL; - slab = kmem_cache_create(slab_name, sizeof(struct ccid) + obj_size, 0, + slab = kmem_cache_create(slab_name_fmt, sizeof(struct ccid) + obj_size, 0, SLAB_HWCACHE_ALIGN, NULL); - if (slab == NULL) - kfree(slab_name); return slab; } static void ccid_kmem_cache_destroy(struct kmem_cache *slab) { - if (slab != NULL) { - const char *name = kmem_cache_name(slab); - + if (slab != NULL) kmem_cache_destroy(slab); - kfree(name); - } } static int ccid_activate(struct ccid_operations *ccid_ops) @@ -113,6 +103,7 @@ static int ccid_activate(struct ccid_operations *ccid_ops) ccid_ops->ccid_hc_rx_slab = ccid_kmem_cache_create(ccid_ops->ccid_hc_rx_obj_size, + ccid_ops->ccid_hc_rx_slab_name, "ccid%u_hc_rx_sock", ccid_ops->ccid_id); if (ccid_ops->ccid_hc_rx_slab == NULL) @@ -120,6 +111,7 @@ static int ccid_activate(struct ccid_operations *ccid_ops) ccid_ops->ccid_hc_tx_slab = ccid_kmem_cache_create(ccid_ops->ccid_hc_tx_obj_size, + ccid_ops->ccid_hc_tx_slab_name, "ccid%u_hc_tx_sock", ccid_ops->ccid_id); if (ccid_ops->ccid_hc_tx_slab == NULL) diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index facedd20b53..6df6f8ac963 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -19,7 +19,9 @@ #include <linux/list.h> #include <linux/module.h> -#define CCID_MAX 255 +/* maximum value for a CCID (RFC 4340, 19.5) */ +#define CCID_MAX 255 +#define CCID_SLAB_NAME_LENGTH 32 struct tcp_info; @@ -49,6 +51,8 @@ struct ccid_operations { const char *ccid_name; struct kmem_cache *ccid_hc_rx_slab, *ccid_hc_tx_slab; + char ccid_hc_rx_slab_name[CCID_SLAB_NAME_LENGTH]; + char ccid_hc_tx_slab_name[CCID_SLAB_NAME_LENGTH]; __u32 ccid_hc_rx_obj_size, ccid_hc_tx_obj_size; /* Interface Routines */ diff --git a/net/dccp/probe.c b/net/dccp/probe.c index dc328425fa2..f5b3464f124 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: @@ -156,14 +156,13 @@ 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; - ret = register_jprobe(&dccp_send_probe); + try_then_request_module((ret = register_jprobe(&dccp_send_probe)) == 0, + "dccp"); if (ret) goto err1; @@ -172,14 +171,14 @@ 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/ipv4/Kconfig b/net/ipv4/Kconfig index 70491d9035e..0c94a1ac294 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/devinet.c b/net/ipv4/devinet.c index 5cdbc102a41..040c4f05b65 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"), diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 3323168ee52..82dbf711d6d 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(); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 76c08402c93..a42f658e756 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -946,7 +946,6 @@ int igmp_rcv(struct sk_buff *skb) break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: - case IGMPV3_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ if (skb_rtable(skb)->fl.iif == 0) break; @@ -960,6 +959,7 @@ int igmp_rcv(struct sk_buff *skb) in_dev_put(in_dev); return pim_rcv_v1(skb); #endif + case IGMPV3_HOST_MEMBERSHIP_REPORT: case IGMP_DVMRP: case IGMP_TRACE: case IGMP_HOST_LEAVE_MESSAGE: diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index bdb78dd180c..1aaa8110d84 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -368,7 +368,7 @@ static int inet_diag_bc_run(const void *bc, int len, yes = entry->sport >= op[1].no; break; case INET_DIAG_BC_S_LE: - yes = entry->dport <= op[1].no; + yes = entry->sport <= op[1].no; break; case INET_DIAG_BC_D_GE: yes = entry->dport >= op[1].no; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e34013a78ef..3451799e3db 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/ipconfig.c b/net/ipv4/ipconfig.c index 4e08b7f2331..10a6a604bf3 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/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 06632762ba5..90203e1b918 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -925,10 +925,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) if (t && !IS_ERR(t)) { struct arpt_getinfo info; const struct xt_table_info *private = t->private; - #ifdef CONFIG_COMPAT + struct xt_table_info tmp; + if (compat) { - struct xt_table_info tmp; ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(NFPROTO_ARP); private = &tmp; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 572330a552e..3ce53cf13d5 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1132,10 +1132,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) if (t && !IS_ERR(t)) { struct ipt_getinfo info; const struct xt_table_info *private = t->private; - #ifdef CONFIG_COMPAT + struct xt_table_info tmp; + if (compat) { - struct xt_table_info tmp; ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET); private = &tmp; diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 549e206cdd4..ea5cea2415c 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_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index d171b123a65..d1ea38a7c49 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -210,7 +210,7 @@ static ctl_table ip_ct_sysctl_table[] = { }, { .procname = "ip_conntrack_buckets", - .data = &nf_conntrack_htable_size, + .data = &init_net.ct.htable_size, .maxlen = sizeof(unsigned int), .mode = 0444, .proc_handler = proc_dointvec, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 8668a3defda..2fb7b76da94 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -32,7 +32,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) struct hlist_nulls_node *n; for (st->bucket = 0; - st->bucket < nf_conntrack_htable_size; + st->bucket < net->ct.htable_size; st->bucket++) { n = rcu_dereference(net->ct.hash[st->bucket].first); if (!is_a_nulls(n)) @@ -50,7 +50,7 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, head = rcu_dereference(head->next); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { - if (++st->bucket >= nf_conntrack_htable_size) + if (++st->bucket >= net->ct.htable_size) return NULL; } head = rcu_dereference(net->ct.hash[st->bucket].first); diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index fa2d6b6fc3e..331ead3ebd1 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/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index fe1a64479dd..26066a2327a 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -35,9 +35,6 @@ static DEFINE_SPINLOCK(nf_nat_lock); static struct nf_conntrack_l3proto *l3proto __read_mostly; -/* Calculated at init based on memory size */ -static unsigned int nf_nat_htable_size __read_mostly; - #define MAX_IP_NAT_PROTO 256 static const struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO] __read_mostly; @@ -72,7 +69,7 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_put); /* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int -hash_by_src(const struct nf_conntrack_tuple *tuple) +hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple) { unsigned int hash; @@ -80,7 +77,7 @@ hash_by_src(const struct nf_conntrack_tuple *tuple) hash = jhash_3words((__force u32)tuple->src.u3.ip, (__force u32)tuple->src.u.all, tuple->dst.protonum, 0); - return ((u64)hash * nf_nat_htable_size) >> 32; + return ((u64)hash * net->ipv4.nat_htable_size) >> 32; } /* Is this tuple already taken? (not by us) */ @@ -147,7 +144,7 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range *range) { - unsigned int h = hash_by_src(tuple); + unsigned int h = hash_by_src(net, tuple); const struct nf_conn_nat *nat; const struct nf_conn *ct; const struct hlist_node *n; @@ -330,7 +327,7 @@ nf_nat_setup_info(struct nf_conn *ct, if (have_to_hash) { unsigned int srchash; - srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_lock); /* nf_conntrack_alter_reply might re-allocate exntension aera */ nat = nfct_nat(ct); @@ -679,8 +676,10 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, static int __net_init nf_nat_net_init(struct net *net) { - net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, - &net->ipv4.nat_vmalloced, 0); + /* Leave them the same for the moment. */ + net->ipv4.nat_htable_size = net->ct.htable_size; + net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, + &net->ipv4.nat_vmalloced, 0); if (!net->ipv4.nat_bysource) return -ENOMEM; return 0; @@ -703,7 +702,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) nf_ct_iterate_cleanup(net, &clean_nat, NULL); synchronize_rcu(); nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced, - nf_nat_htable_size); + net->ipv4.nat_htable_size); } static struct pernet_operations nf_nat_net_ops = { @@ -724,9 +723,6 @@ static int __init nf_nat_init(void) return ret; } - /* Leave them the same for the moment. */ - nf_nat_htable_size = nf_conntrack_htable_size; - ret = register_pernet_subsys(&nf_nat_net_ops); if (ret < 0) goto cleanup_extend; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e446496f564..d62b05d3338 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -586,7 +586,9 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); +#ifdef CONFIG_NET_CLS_ROUTE remove_proc_entry("rt_acct", net->proc_net); +#endif } static struct pernet_operations ip_rt_proc_ops __net_initdata = { diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 26399ad2a28..66fd80ef247 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) @@ -340,20 +353,6 @@ 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); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 12cab7d74db..3fddc69cccc 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: @@ -5791,11 +5783,9 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* tcp_ack considers this ACK as duplicate * and does not calculate rtt. - * Fix it at least with timestamps. + * Force it here. */ - if (tp->rx_opt.saw_tstamp && - tp->rx_opt.rcv_tsecr && !tp->srtt) - tcp_ack_saw_tstamp(sk, 0); + tcp_ack_update_rtt(sk, 0, 0); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 15e96030ce4..65b8ebfd078 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1262,20 +1262,10 @@ 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 +1309,14 @@ 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 +1341,7 @@ 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 && diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 87accec8d09..f206ee5dda8 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 93316a96d82..383ce237640 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -553,7 +553,6 @@ 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 +580,18 @@ 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; @@ -2527,9 +2522,7 @@ 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) @@ -2555,8 +2548,7 @@ 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)), + sysctl_tcp_window_scaling, &rcv_wscale); tp->rx_opt.rcv_wscale = rcv_wscale; diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index bb110c5ce1d..9bc805df95d 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -39,9 +39,9 @@ static int port __read_mostly = 0; MODULE_PARM_DESC(port, "Port to match (0=all)"); module_param(port, int, 0); -static int bufsize __read_mostly = 4096; +static unsigned int bufsize __read_mostly = 4096; MODULE_PARM_DESC(bufsize, "Log buffer size in packets (4096)"); -module_param(bufsize, int, 0); +module_param(bufsize, uint, 0); static int full __read_mostly; MODULE_PARM_DESC(full, "Full log (1=every ack packet received, 0=only cwnd changes)"); @@ -75,12 +75,12 @@ static struct { static inline int tcp_probe_used(void) { - return (tcp_probe.head - tcp_probe.tail) % bufsize; + return (tcp_probe.head - tcp_probe.tail) & (bufsize - 1); } static inline int tcp_probe_avail(void) { - return bufsize - tcp_probe_used(); + return bufsize - tcp_probe_used() - 1; } /* @@ -116,7 +116,7 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, p->ssthresh = tcp_current_ssthresh(sk); p->srtt = tp->srtt >> 3; - tcp_probe.head = (tcp_probe.head + 1) % bufsize; + tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1); } tcp_probe.lastcwnd = tp->snd_cwnd; spin_unlock(&tcp_probe.lock); @@ -149,7 +149,7 @@ static int tcpprobe_open(struct inode * inode, struct file * file) static int tcpprobe_sprint(char *tbuf, int n) { const struct tcp_log *p - = tcp_probe.log + tcp_probe.tail % bufsize; + = tcp_probe.log + tcp_probe.tail; struct timespec tv = ktime_to_timespec(ktime_sub(p->tstamp, tcp_probe.start)); @@ -192,7 +192,7 @@ static ssize_t tcpprobe_read(struct file *file, char __user *buf, width = tcpprobe_sprint(tbuf, sizeof(tbuf)); if (cnt + width < len) - tcp_probe.tail = (tcp_probe.tail + 1) % bufsize; + tcp_probe.tail = (tcp_probe.tail + 1) & (bufsize - 1); spin_unlock_bh(&tcp_probe.lock); @@ -222,9 +222,10 @@ static __init int tcpprobe_init(void) init_waitqueue_head(&tcp_probe.wait); spin_lock_init(&tcp_probe.lock); - if (bufsize < 0) + if (bufsize == 0) return -EINVAL; + bufsize = roundup_pow_of_two(bufsize); tcp_probe.log = kcalloc(bufsize, sizeof(struct tcp_log), GFP_KERNEL); if (!tcp_probe.log) goto err0; @@ -236,7 +237,7 @@ static __init int tcpprobe_init(void) if (ret) goto err1; - pr_info("TCP probe registered (port=%d)\n", port); + pr_info("TCP probe registered (port=%d) bufsize=%u\n", port, bufsize); return 0; err1: proc_net_remove(&init_net, procname); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1f9534846ca..f0126fdd7e0 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); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 8c08a28d8f8..67107d63c1c 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -15,7 +15,6 @@ #include <net/xfrm.h> #include <net/ip.h> -static struct dst_ops xfrm4_dst_ops; static struct xfrm_policy_afinfo xfrm4_policy_afinfo; static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, @@ -190,8 +189,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) static inline int xfrm4_garbage_collect(struct dst_ops *ops) { - xfrm4_policy_afinfo.garbage_collect(&init_net); - return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2); + struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops); + + xfrm4_policy_afinfo.garbage_collect(net); + return (atomic_read(&ops->entries) > ops->gc_thresh * 2); } static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -268,7 +269,7 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { static struct ctl_table xfrm4_policy_table[] = { { .procname = "xfrm4_gc_thresh", - .data = &xfrm4_dst_ops.gc_thresh, + .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, @@ -295,8 +296,6 @@ static void __exit xfrm4_policy_fini(void) void __init xfrm4_init(int rt_max_size) { - xfrm4_state_init(); - xfrm4_policy_init(); /* * Select a default value for the gc_thresh based on the main route * table hash size. It seems to me the worst case scenario is when @@ -308,6 +307,9 @@ void __init xfrm4_init(int rt_max_size) * and start cleaning when were 1/2 full */ xfrm4_dst_ops.gc_thresh = rt_max_size/2; + + xfrm4_state_init(); + xfrm4_policy_init(); #ifdef CONFIG_SYSCTL sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv4_ctl_path, xfrm4_policy_table); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index df159fffe4b..4bac362b133 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -559,6 +559,11 @@ static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb) return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev); } +static inline struct net *ipv6_skb_net(struct sk_buff *skb) +{ + return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev); +} + /* Router Alert as of RFC 2711 */ static int ipv6_hop_ra(struct sk_buff *skb, int optoff) @@ -580,8 +585,8 @@ static int ipv6_hop_ra(struct sk_buff *skb, int optoff) static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); + struct net *net = ipv6_skb_net(skb); u32 pkt_len; - struct net *net = dev_net(skb_dst(skb)->dev); if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index cd48801a8d6..eb6d0972863 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/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 480d7f8c980..8a7e0f52e17 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1164,10 +1164,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat) if (t && !IS_ERR(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; - #ifdef CONFIG_COMPAT + struct xt_table_info tmp; + if (compat) { - struct xt_table_info tmp; ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 5f2ec208a8c..0956ebabbff 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 e0b9424fa1b..624a54832a7 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -63,6 +63,7 @@ struct nf_ct_frag6_queue struct inet_frag_queue q; __be32 id; /* fragment id */ + u32 user; struct in6_addr saddr; struct in6_addr daddr; @@ -168,13 +169,14 @@ 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 +561,7 @@ 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 +607,7 @@ 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/reassembly.c b/net/ipv6/reassembly.c index 4d98549a686..2cddea3bd6b 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; @@ -705,7 +708,8 @@ static void ip6_frags_ns_sysctl_unregister(struct net *net) 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; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index db3b2730389..c2bd74c5f8d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2630,6 +2630,7 @@ 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; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 5b9af508b8f..7208a06576c 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; @@ -253,21 +266,6 @@ 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, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ee9cf62458d..febfd595a40 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1169,7 +1169,6 @@ 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 +1207,7 @@ 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 && diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 7254e3f899a..dbdc696f5fc 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -24,7 +24,6 @@ #include <net/mip6.h> #endif -static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, @@ -224,8 +223,10 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) static inline int xfrm6_garbage_collect(struct dst_ops *ops) { - xfrm6_policy_afinfo.garbage_collect(&init_net); - return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2); + struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops); + + xfrm6_policy_afinfo.garbage_collect(net); + return (atomic_read(&ops->entries) > ops->gc_thresh * 2); } static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -310,7 +311,7 @@ static void xfrm6_policy_fini(void) static struct ctl_table xfrm6_policy_table[] = { { .procname = "xfrm6_gc_thresh", - .data = &xfrm6_dst_ops.gc_thresh, + .data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, @@ -326,13 +327,6 @@ int __init xfrm6_init(void) int ret; unsigned int gc_thresh; - ret = xfrm6_policy_init(); - if (ret) - goto out; - - ret = xfrm6_state_init(); - if (ret) - goto out_policy; /* * We need a good default value for the xfrm6 gc threshold. * In ipv4 we set it to the route hash table size * 8, which @@ -346,6 +340,15 @@ int __init xfrm6_init(void) */ gc_thresh = FIB6_TABLE_HASHSZ * 8; xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; + + ret = xfrm6_policy_init(); + if (ret) + goto out; + + ret = xfrm6_state_init(); + if (ret) + goto out_policy; + #ifdef CONFIG_SYSCTL sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path, xfrm6_policy_table); diff --git a/net/irda/irlap.c b/net/irda/irlap.c index 356e65b1dc4..783c5f367d2 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 c5c51959e3c..94a9884d714 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 7bf5b913828..0e7d8bde145 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 b001c361ad3..4300df35d37 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 7dea882dbb7..6b3602de359 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); @@ -700,15 +698,18 @@ dev_irnet_ioctl( /* Query PPP channel and unit number */ case PPPIOCGCHAN: + lock_kernel(); if(ap->ppp_open && !put_user(ppp_channel_index(&ap->chan), (int __user *)argp)) err = 0; + unlock_kernel(); break; case PPPIOCGUNIT: lock_kernel(); if(ap->ppp_open && !put_user(ppp_unit_number(&ap->chan), (int __user *)argp)) - err = 0; + err = 0; + unlock_kernel(); break; /* All these ioctls can be passed both directly and from ppp_generic, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 1e428863574..c18286a2167 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 3b1f5f5f8de..fd8b28361a6 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 84209fbbeb1..539f43bc97d 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; */ } @@ -3793,9 +3794,9 @@ static struct pernet_operations pfkey_net_ops = { static void __exit ipsec_pfkey_exit(void) { - unregister_pernet_subsys(&pfkey_net_ops); xfrm_unregister_km(&pfkeyv2_mgr); sock_unregister(PF_KEY); + unregister_pernet_subsys(&pfkey_net_ops); proto_unregister(&key_proto); } @@ -3806,21 +3807,22 @@ static int __init ipsec_pfkey_init(void) if (err != 0) goto out; - err = sock_register(&pfkey_family_ops); + err = register_pernet_subsys(&pfkey_net_ops); if (err != 0) goto out_unregister_key_proto; + err = sock_register(&pfkey_family_ops); + if (err != 0) + goto out_unregister_pernet; err = xfrm_register_km(&pfkeyv2_mgr); if (err != 0) goto out_sock_unregister; - err = register_pernet_subsys(&pfkey_net_ops); - if (err != 0) - goto out_xfrm_unregister_km; out: return err; -out_xfrm_unregister_km: - xfrm_unregister_km(&pfkeyv2_mgr); + out_sock_unregister: sock_unregister(PF_KEY); +out_unregister_pernet: + unregister_pernet_subsys(&pfkey_net_ops); out_unregister_key_proto: proto_unregister(&key_proto); goto out; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index a8da23905c7..0192cfdacae 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 79a69805221..f2d76238b9b 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 b95699f0054..847ffca4018 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 e55a6861d26..c37ac2d7bec 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 6182e8ea0be..3c115fc1978 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_core.c b/net/netfilter/nf_conntrack_core.c index 0e98c3282d4..4d79e3c1616 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -30,6 +30,7 @@ #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/mm.h> +#include <linux/nsproxy.h> #include <linux/rculist_nulls.h> #include <net/netfilter/nf_conntrack.h> @@ -63,8 +64,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_max); struct nf_conn nf_conntrack_untracked __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_untracked); -static struct kmem_cache *nf_conntrack_cachep __read_mostly; - static int nf_conntrack_hash_rnd_initted; static unsigned int nf_conntrack_hash_rnd; @@ -86,9 +85,10 @@ static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, return ((u64)h * size) >> 32; } -static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple) +static inline u_int32_t hash_conntrack(const struct net *net, + const struct nf_conntrack_tuple *tuple) { - return __hash_conntrack(tuple, nf_conntrack_htable_size, + return __hash_conntrack(tuple, net->ct.htable_size, nf_conntrack_hash_rnd); } @@ -296,7 +296,7 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - unsigned int hash = hash_conntrack(tuple); + unsigned int hash = hash_conntrack(net, tuple); /* Disable BHs the entire time since we normally need to disable them * at least once for the stats anyway. @@ -366,10 +366,11 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, void nf_conntrack_hash_insert(struct nf_conn *ct) { + struct net *net = nf_ct_net(ct); unsigned int hash, repl_hash; - hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); + hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); __nf_conntrack_hash_insert(ct, hash, repl_hash); } @@ -397,8 +398,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) return NF_ACCEPT; - hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); + hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); /* We're not in hash table, and we refuse to set up related connections for unconfirmed conns. But packet copies and @@ -468,7 +469,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, struct net *net = nf_ct_net(ignored_conntrack); struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - unsigned int hash = hash_conntrack(tuple); + unsigned int hash = hash_conntrack(net, tuple); /* Disable BHs the entire time since we need to disable them at * least once for the stats anyway. @@ -503,7 +504,7 @@ static noinline int early_drop(struct net *net, unsigned int hash) int dropped = 0; rcu_read_lock(); - for (i = 0; i < nf_conntrack_htable_size; i++) { + for (i = 0; i < net->ct.htable_size; i++) { hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { tmp = nf_ct_tuplehash_to_ctrack(h); @@ -523,7 +524,7 @@ static noinline int early_drop(struct net *net, unsigned int hash) if (cnt >= NF_CT_EVICTION_RANGE) break; - hash = (hash + 1) % nf_conntrack_htable_size; + hash = (hash + 1) % net->ct.htable_size; } rcu_read_unlock(); @@ -557,7 +558,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, if (nf_conntrack_max && unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { - unsigned int hash = hash_conntrack(orig); + unsigned int hash = hash_conntrack(net, orig); if (!early_drop(net, hash)) { atomic_dec(&net->ct.count); if (net_ratelimit()) @@ -572,7 +573,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, * Do not use kmem_cache_zalloc(), as this cache uses * SLAB_DESTROY_BY_RCU. */ - ct = kmem_cache_alloc(nf_conntrack_cachep, gfp); + ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp); if (ct == NULL) { pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n"); atomic_dec(&net->ct.count); @@ -611,7 +612,7 @@ void nf_conntrack_free(struct nf_conn *ct) nf_ct_ext_destroy(ct); atomic_dec(&net->ct.count); nf_ct_ext_free(ct); - kmem_cache_free(nf_conntrack_cachep, ct); + kmem_cache_free(net->ct.nf_conntrack_cachep, ct); } EXPORT_SYMBOL_GPL(nf_conntrack_free); @@ -1014,7 +1015,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), struct hlist_nulls_node *n; spin_lock_bh(&nf_conntrack_lock); - for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { + for (; *bucket < net->ct.htable_size; (*bucket)++) { hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) @@ -1113,9 +1114,12 @@ static void nf_ct_release_dying_list(struct net *net) static void nf_conntrack_cleanup_init_net(void) { + /* wait until all references to nf_conntrack_untracked are dropped */ + while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1) + schedule(); + nf_conntrack_helper_fini(); nf_conntrack_proto_fini(); - kmem_cache_destroy(nf_conntrack_cachep); } static void nf_conntrack_cleanup_net(struct net *net) @@ -1127,15 +1131,14 @@ static void nf_conntrack_cleanup_net(struct net *net) schedule(); goto i_see_dead_people; } - /* wait until all references to nf_conntrack_untracked are dropped */ - while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1) - schedule(); nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, - nf_conntrack_htable_size); + net->ct.htable_size); nf_conntrack_ecache_fini(net); nf_conntrack_acct_fini(net); nf_conntrack_expect_fini(net); + kmem_cache_destroy(net->ct.nf_conntrack_cachep); + kfree(net->ct.slabname); free_percpu(net->ct.stat); } @@ -1190,10 +1193,12 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) { int i, bucket, vmalloced, old_vmalloced; unsigned int hashsize, old_size; - int rnd; struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; + if (current->nsproxy->net_ns != &init_net) + return -EOPNOTSUPP; + /* On boot, we can set this without any fancy locking. */ if (!nf_conntrack_htable_size) return param_set_uint(val, kp); @@ -1206,33 +1211,29 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!hash) return -ENOMEM; - /* We have to rehahs for the new table anyway, so we also can - * use a newrandom seed */ - get_random_bytes(&rnd, sizeof(rnd)); - /* Lookups in the old hash might happen in parallel, which means we * might get false negatives during connection lookup. New connections * created because of a false negative won't make it into the hash * though since that required taking the lock. */ spin_lock_bh(&nf_conntrack_lock); - for (i = 0; i < nf_conntrack_htable_size; i++) { + for (i = 0; i < init_net.ct.htable_size; i++) { while (!hlist_nulls_empty(&init_net.ct.hash[i])) { h = hlist_nulls_entry(init_net.ct.hash[i].first, struct nf_conntrack_tuple_hash, hnnode); hlist_nulls_del_rcu(&h->hnnode); - bucket = __hash_conntrack(&h->tuple, hashsize, rnd); + bucket = __hash_conntrack(&h->tuple, hashsize, + nf_conntrack_hash_rnd); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } - old_size = nf_conntrack_htable_size; + old_size = init_net.ct.htable_size; old_vmalloced = init_net.ct.hash_vmalloc; old_hash = init_net.ct.hash; - nf_conntrack_htable_size = hashsize; + init_net.ct.htable_size = nf_conntrack_htable_size = hashsize; init_net.ct.hash_vmalloc = vmalloced; init_net.ct.hash = hash; - nf_conntrack_hash_rnd = rnd; spin_unlock_bh(&nf_conntrack_lock); nf_ct_free_hashtable(old_hash, old_vmalloced, old_size); @@ -1271,15 +1272,6 @@ static int nf_conntrack_init_init_net(void) NF_CONNTRACK_VERSION, nf_conntrack_htable_size, nf_conntrack_max); - nf_conntrack_cachep = kmem_cache_create("nf_conntrack", - sizeof(struct nf_conn), - 0, SLAB_DESTROY_BY_RCU, NULL); - if (!nf_conntrack_cachep) { - printk(KERN_ERR "Unable to create nf_conn slab cache\n"); - ret = -ENOMEM; - goto err_cache; - } - ret = nf_conntrack_proto_init(); if (ret < 0) goto err_proto; @@ -1288,13 +1280,19 @@ static int nf_conntrack_init_init_net(void) if (ret < 0) goto err_helper; + /* Set up fake conntrack: to never be deleted, not in any hashes */ +#ifdef CONFIG_NET_NS + nf_conntrack_untracked.ct_net = &init_net; +#endif + atomic_set(&nf_conntrack_untracked.ct_general.use, 1); + /* - and look it like as a confirmed connection */ + set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status); + return 0; err_helper: nf_conntrack_proto_fini(); err_proto: - kmem_cache_destroy(nf_conntrack_cachep); -err_cache: return ret; } @@ -1316,7 +1314,24 @@ static int nf_conntrack_init_net(struct net *net) ret = -ENOMEM; goto err_stat; } - net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, + + net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net); + if (!net->ct.slabname) { + ret = -ENOMEM; + goto err_slabname; + } + + net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname, + sizeof(struct nf_conn), 0, + SLAB_DESTROY_BY_RCU, NULL); + if (!net->ct.nf_conntrack_cachep) { + printk(KERN_ERR "Unable to create nf_conn slab cache\n"); + ret = -ENOMEM; + goto err_cache; + } + + net->ct.htable_size = nf_conntrack_htable_size; + net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, &net->ct.hash_vmalloc, 1); if (!net->ct.hash) { ret = -ENOMEM; @@ -1333,15 +1348,6 @@ static int nf_conntrack_init_net(struct net *net) if (ret < 0) goto err_ecache; - /* Set up fake conntrack: - - to never be deleted, not in any hashes */ -#ifdef CONFIG_NET_NS - nf_conntrack_untracked.ct_net = &init_net; -#endif - atomic_set(&nf_conntrack_untracked.ct_general.use, 1); - /* - and look it like as a confirmed connection */ - set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status); - return 0; err_ecache: @@ -1350,8 +1356,12 @@ err_acct: nf_conntrack_expect_fini(net); err_expect: nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, - nf_conntrack_htable_size); + net->ct.htable_size); err_hash: + kmem_cache_destroy(net->ct.nf_conntrack_cachep); +err_cache: + kfree(net->ct.slabname); +err_slabname: free_percpu(net->ct.stat); err_stat: return ret; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index fdf5d2a1d9b..2f25ff61098 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -569,7 +569,7 @@ static void exp_proc_remove(struct net *net) #endif /* CONFIG_PROC_FS */ } -module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0600); +module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400); int nf_conntrack_expect_init(struct net *net) { @@ -577,7 +577,7 @@ int nf_conntrack_expect_init(struct net *net) if (net_eq(net, &init_net)) { if (!nf_ct_expect_hsize) { - nf_ct_expect_hsize = nf_conntrack_htable_size / 256; + nf_ct_expect_hsize = net->ct.htable_size / 256; if (!nf_ct_expect_hsize) nf_ct_expect_hsize = 1; } diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 38ea7ef3ccd..f0732aa18e4 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/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 65c2a7bc3af..4b1a56bd074 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -192,7 +192,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, /* Get rid of expecteds, set helpers to NULL. */ hlist_nulls_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode) unhelp(h, me); - for (i = 0; i < nf_conntrack_htable_size; i++) { + for (i = 0; i < net->ct.htable_size; i++) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) unhelp(h, me); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 59d8064eb52..0ffe689dfe9 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -594,7 +594,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); last = (struct nf_conn *)cb->args[1]; - for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { + for (; cb->args[0] < init_net.ct.htable_size; cb->args[0]++) { restart: hlist_nulls_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]], hnnode) { @@ -1437,8 +1437,9 @@ ctnetlink_exp_dump_mask(struct sk_buff *skb, struct nlattr *nest_parms; memset(&m, 0xFF, sizeof(m)); - m.src.u.all = mask->src.u.all; memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3)); + m.src.u.all = mask->src.u.all; + m.dst.protonum = tuple->dst.protonum; nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK | NLA_F_NESTED); if (!nest_parms) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 4b572163784..023966b569b 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -376,7 +376,7 @@ int ct_sip_get_header(const struct nf_conn *ct, const char *dptr, dptr += hdr->len; else if (hdr->cname && limit - dptr >= hdr->clen + 1 && strnicmp(dptr, hdr->cname, hdr->clen) == 0 && - !isalpha(*(dptr + hdr->clen + 1))) + !isalpha(*(dptr + hdr->clen))) dptr += hdr->clen; else continue; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 028aba667ef..e310f1561bb 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -51,7 +51,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) struct hlist_nulls_node *n; for (st->bucket = 0; - st->bucket < nf_conntrack_htable_size; + st->bucket < net->ct.htable_size; st->bucket++) { n = rcu_dereference(net->ct.hash[st->bucket].first); if (!is_a_nulls(n)) @@ -69,7 +69,7 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, head = rcu_dereference(head->next); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { - if (++st->bucket >= nf_conntrack_htable_size) + if (++st->bucket >= net->ct.htable_size) return NULL; } head = rcu_dereference(net->ct.hash[st->bucket].first); @@ -355,7 +355,7 @@ static ctl_table nf_ct_sysctl_table[] = { }, { .procname = "nf_conntrack_buckets", - .data = &nf_conntrack_htable_size, + .data = &init_net.ct.htable_size, .maxlen = sizeof(unsigned int), .mode = 0444, .proc_handler = proc_dointvec, @@ -421,6 +421,7 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) goto out_kmemdup; table[1].data = &net->ct.count; + table[2].data = &net->ct.htable_size; table[3].data = &net->ct.sysctl_checksum; table[4].data = &net->ct.sysctl_log_invalid; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index eb0ceb84652..fc70a49c0af 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 7a10bbe02c1..c5d9f97ef21 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/af_netlink.c b/net/netlink/af_netlink.c index a4957bf2ca6..4c5972ba8c7 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -455,9 +455,14 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, if (nl_table[protocol].registered && try_module_get(nl_table[protocol].module)) module = nl_table[protocol].module; + else + err = -EPROTONOSUPPORT; cb_mutex = nl_table[protocol].cb_mutex; netlink_unlock_table(); + if (err < 0) + goto out; + err = __netlink_create(net, sock, cb_mutex, protocol); if (err < 0) goto out_module; diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index aacba76070f..e2e2d33cafd 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -843,12 +843,13 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) dptr = skb_push(skb, 1); *dptr = AX25_P_NETROM; - ax25s = ax25_send_frame(skb, 256, (ax25_address *)dev->dev_addr, &nr_neigh->callsign, nr_neigh->digipeat, nr_neigh->dev); - if (nr_neigh->ax25 && ax25s) { - /* We were already holding this ax25_cb */ + ax25s = nr_neigh->ax25; + nr_neigh->ax25 = ax25_send_frame(skb, 256, + (ax25_address *)dev->dev_addr, + &nr_neigh->callsign, + nr_neigh->digipeat, nr_neigh->dev); + if (ax25s) ax25_cb_put(ax25s); - } - nr_neigh->ax25 = ax25s; dev_put(dev); ret = (nr_neigh->ax25 != NULL); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 020562164b5..f126d18dbdc 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; } @@ -1030,8 +1021,20 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) status = TP_STATUS_SEND_REQUEST; err = dev_queue_xmit(skb); - if (unlikely(err > 0 && (err = net_xmit_errno(err)) != 0)) - goto out_xmit; + if (unlikely(err > 0)) { + err = net_xmit_errno(err); + if (err && __packet_get_status(po, ph) == + TP_STATUS_AVAILABLE) { + /* skb was destructed already */ + skb = NULL; + goto out_status; + } + /* + * skb was dropped but not destructed yet; + * let's treat it like congestion or err < 0 + */ + err = 0; + } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || @@ -1042,9 +1045,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) err = len_sum; goto out_put; -out_xmit: - skb->destructor = sock_wfree; - atomic_dec(&po->tx_ring.pending); out_status: __packet_set_status(po, ph, status); kfree_skb(skb); diff --git a/net/rds/ib.c b/net/rds/ib.c index 536ebe5d3f6..3b899236104 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 db224f7c293..b28fa8525b2 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_link.c b/net/rose/rose_link.c index bd86a63960c..5ef5f6988a2 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -101,13 +101,17 @@ static void rose_t0timer_expiry(unsigned long param) static int rose_send_frame(struct sk_buff *skb, struct rose_neigh *neigh) { ax25_address *rose_call; + ax25_cb *ax25s; if (ax25cmp(&rose_callsign, &null_ax25_address) == 0) rose_call = (ax25_address *)neigh->dev->dev_addr; else rose_call = &rose_callsign; + ax25s = neigh->ax25; neigh->ax25 = ax25_send_frame(skb, 260, rose_call, &neigh->callsign, neigh->digipeat, neigh->dev); + if (ax25s) + ax25_cb_put(ax25s); return (neigh->ax25 != NULL); } @@ -120,13 +124,17 @@ static int rose_send_frame(struct sk_buff *skb, struct rose_neigh *neigh) static int rose_link_up(struct rose_neigh *neigh) { ax25_address *rose_call; + ax25_cb *ax25s; if (ax25cmp(&rose_callsign, &null_ax25_address) == 0) rose_call = (ax25_address *)neigh->dev->dev_addr; else rose_call = &rose_callsign; + ax25s = neigh->ax25; neigh->ax25 = ax25_find_cb(rose_call, &neigh->callsign, neigh->digipeat, neigh->dev); + if (ax25s) + ax25_cb_put(ax25s); return (neigh->ax25 != NULL); } diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 114df6eec8c..968e8bac1b5 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/rose/rose_route.c b/net/rose/rose_route.c index 795c4b025e3..70a0b3b4b4d 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -235,6 +235,8 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh) if ((s = rose_neigh_list) == rose_neigh) { rose_neigh_list = rose_neigh->next; + if (rose_neigh->ax25) + ax25_cb_put(rose_neigh->ax25); kfree(rose_neigh->digipeat); kfree(rose_neigh); return; @@ -243,6 +245,8 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh) while (s != NULL && s->next != NULL) { if (s->next == rose_neigh) { s->next = rose_neigh->next; + if (rose_neigh->ax25) + ax25_cb_put(rose_neigh->ax25); kfree(rose_neigh->digipeat); kfree(rose_neigh); return; @@ -812,6 +816,7 @@ void rose_link_failed(ax25_cb *ax25, int reason) if (rose_neigh != NULL) { rose_neigh->ax25 = NULL; + ax25_cb_put(ax25); rose_del_route_by_neigh(rose_neigh); rose_kill_by_neigh(rose_neigh); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 929218a4762..21f9c7678aa 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -433,7 +433,7 @@ config NET_ACT_POLICE module. To compile this code as a module, choose M here: the - module will be called police. + module will be called act_police. config NET_ACT_GACT tristate "Generic actions" @@ -443,7 +443,7 @@ config NET_ACT_GACT accepting packets. To compile this code as a module, choose M here: the - module will be called gact. + module will be called act_gact. config GACT_PROB bool "Probability support" @@ -459,7 +459,7 @@ config NET_ACT_MIRRED other devices. To compile this code as a module, choose M here: the - module will be called mirred. + module will be called act_mirred. config NET_ACT_IPT tristate "IPtables targets" @@ -469,7 +469,7 @@ config NET_ACT_IPT classification. To compile this code as a module, choose M here: the - module will be called ipt. + module will be called act_ipt. config NET_ACT_NAT tristate "Stateless NAT" @@ -479,7 +479,7 @@ config NET_ACT_NAT netfilter for NAT unless you know what you are doing. To compile this code as a module, choose M here: the - module will be called nat. + module will be called act_nat. config NET_ACT_PEDIT tristate "Packet Editing" @@ -488,7 +488,7 @@ config NET_ACT_PEDIT Say Y here if you want to mangle the content of packets. To compile this code as a module, choose M here: the - module will be called pedit. + module will be called act_pedit. config NET_ACT_SIMP tristate "Simple Example (Debug)" @@ -502,7 +502,7 @@ config NET_ACT_SIMP If unsure, say N. To compile this code as a module, choose M here: the - module will be called simple. + module will be called act_simple. config NET_ACT_SKBEDIT tristate "SKB Editing" @@ -513,7 +513,7 @@ config NET_ACT_SKBEDIT If unsure, say N. To compile this code as a module, choose M here: the - module will be called skbedit. + module will be called act_skbedit. config NET_CLS_IND bool "Incoming device classification" diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2a740035aa6..64f5e328cee 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 d771cc1b777..4e4ca65cd32 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 1ef9de9bbae..47bc20d3a85 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 89ab66e5474..67fdac9d2d3 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 b94c3dd7101..769c386bd42 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 c7450c8f0a7..6dcdd251781 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 7535a7bed2f..f394fc190a4 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 fc6a43ccd95..f7a7f8380e3 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(); @@ -644,7 +644,22 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) p = gss_fill_context(p, end, ctx, gss_msg->auth->mech); if (IS_ERR(p)) { err = PTR_ERR(p); - gss_msg->msg.errno = (err == -EAGAIN) ? -EAGAIN : -EACCES; + switch (err) { + case -EACCES: + gss_msg->msg.errno = err; + err = mlen; + break; + case -EFAULT: + case -ENOMEM: + case -EINVAL: + case -ENOSYS: + gss_msg->msg.errno = -EAGAIN; + break; + default: + printk(KERN_CRIT "%s: bad return from " + "gss_fill_context: %zd\n", __func__, err); + BUG(); + } goto err_release_msg; } gss_msg->ctx = gss_get_ctx(ctx); diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index ef45eba2248..2deb0ed72ff 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -131,8 +131,10 @@ gss_import_sec_context_kerberos(const void *p, struct krb5_ctx *ctx; int tmp; - if (!(ctx = kzalloc(sizeof(*ctx), GFP_NOFS))) + if (!(ctx = kzalloc(sizeof(*ctx), GFP_NOFS))) { + p = ERR_PTR(-ENOMEM); goto out_err; + } p = simple_get_bytes(p, end, &ctx->initiate, sizeof(ctx->initiate)); if (IS_ERR(p)) diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 6efbb0cd3c7..76e4c6f4ac3 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -252,7 +252,7 @@ gss_import_sec_context(const void *input_token, size_t bufsize, struct gss_ctx **ctx_id) { if (!(*ctx_id = kzalloc(sizeof(**ctx_id), GFP_KERNEL))) - return GSS_S_FAILURE; + return -ENOMEM; (*ctx_id)->mech_type = gss_mech_get(mech); return mech->gm_ops diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 38829e20500..154034b675b 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 830faf4d999..3e3772d8eb9 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 cef74ba0666..aae6907fd54 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 8cce9218901..f438347d817 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 b845e2293df..7d1f9e928f6 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; @@ -711,7 +699,8 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) spin_unlock_bh(&pool->sp_lock); len = 0; - if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) { + if (test_bit(XPT_LISTENER, &xprt->xpt_flags) && + !test_bit(XPT_CLOSE, &xprt->xpt_flags)) { struct svc_xprt *newxpt; newxpt = xprt->xpt_ops->xpo_accept(xprt); if (newxpt) { @@ -1204,16 +1193,15 @@ 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 4a8f6558718..d8c04111449 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 fd46d42afa8..469de292c23 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 f11be72a1a8..b15e1ebb2bf 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 04732d09013..3d739e5d15d 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/wimax/op-reset.c b/net/wimax/op-reset.c index ca269178c4d..35f370091f4 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/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index cb81ca35b0d..0ecb16a9a88 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -469,16 +469,16 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total) return 0; } -void xfrm_spd_getinfo(struct xfrmk_spdinfo *si) +void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { read_lock_bh(&xfrm_policy_lock); - si->incnt = init_net.xfrm.policy_count[XFRM_POLICY_IN]; - si->outcnt = init_net.xfrm.policy_count[XFRM_POLICY_OUT]; - si->fwdcnt = init_net.xfrm.policy_count[XFRM_POLICY_FWD]; - si->inscnt = init_net.xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; - si->outscnt = init_net.xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; - si->fwdscnt = init_net.xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; - si->spdhcnt = init_net.xfrm.policy_idx_hmask; + si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN]; + si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT]; + si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD]; + si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; + si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; + si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; + si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; read_unlock_bh(&xfrm_policy_lock); } @@ -1309,15 +1309,28 @@ static inline int xfrm_get_tos(struct flowi *fl, int family) return tos; } -static inline struct xfrm_dst *xfrm_alloc_dst(int family) +static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); + struct dst_ops *dst_ops; struct xfrm_dst *xdst; if (!afinfo) return ERR_PTR(-EINVAL); - xdst = dst_alloc(afinfo->dst_ops) ?: ERR_PTR(-ENOBUFS); + switch (family) { + case AF_INET: + dst_ops = &net->xfrm.xfrm4_dst_ops; + break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case AF_INET6: + dst_ops = &net->xfrm.xfrm6_dst_ops; + break; +#endif + default: + BUG(); + } + xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS); xfrm_policy_put_afinfo(afinfo); @@ -1366,6 +1379,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct flowi *fl, struct dst_entry *dst) { + struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; struct dst_entry *dst_prev = NULL; @@ -1389,7 +1403,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_hold(dst); for (; i < nx; i++) { - struct xfrm_dst *xdst = xfrm_alloc_dst(family); + struct xfrm_dst *xdst = xfrm_alloc_dst(net, family); struct dst_entry *dst1 = &xdst->u.dst; err = PTR_ERR(xdst); @@ -1445,7 +1459,7 @@ 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); @@ -2279,6 +2293,7 @@ EXPORT_SYMBOL(xfrm_bundle_ok); int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) { + struct net *net; int err = 0; if (unlikely(afinfo == NULL)) return -EINVAL; @@ -2302,6 +2317,27 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) xfrm_policy_afinfo[afinfo->family] = afinfo; } write_unlock_bh(&xfrm_policy_afinfo_lock); + + rtnl_lock(); + for_each_net(net) { + struct dst_ops *xfrm_dst_ops; + + switch (afinfo->family) { + case AF_INET: + xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops; + break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case AF_INET6: + xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops; + break; +#endif + default: + BUG(); + } + *xfrm_dst_ops = *afinfo->dst_ops; + } + rtnl_unlock(); + return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); @@ -2332,6 +2368,22 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); +static void __net_init xfrm_dst_ops_init(struct net *net) +{ + struct xfrm_policy_afinfo *afinfo; + + read_lock_bh(&xfrm_policy_afinfo_lock); + afinfo = xfrm_policy_afinfo[AF_INET]; + if (afinfo) + net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + afinfo = xfrm_policy_afinfo[AF_INET6]; + if (afinfo) + net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops; +#endif + read_unlock_bh(&xfrm_policy_afinfo_lock); +} + static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family) { struct xfrm_policy_afinfo *afinfo; @@ -2494,6 +2546,7 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; + xfrm_dst_ops_init(net); rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d847f1a52b4..b36cc344474 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -641,11 +641,11 @@ out: } EXPORT_SYMBOL(xfrm_state_flush); -void xfrm_sad_getinfo(struct xfrmk_sadinfo *si) +void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&xfrm_state_lock); - si->sadcnt = init_net.xfrm.state_num; - si->sadhcnt = init_net.xfrm.state_hmask; + si->sadcnt = net->xfrm.state_num; + si->sadhcnt = net->xfrm.state_hmask; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&xfrm_state_lock); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1ada6186933..d5a71297600 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -781,7 +781,8 @@ static inline size_t xfrm_spdinfo_msgsize(void) + nla_total_size(sizeof(struct xfrmu_spdhinfo)); } -static int build_spdinfo(struct sk_buff *skb, u32 pid, u32 seq, u32 flags) +static int build_spdinfo(struct sk_buff *skb, struct net *net, + u32 pid, u32 seq, u32 flags) { struct xfrmk_spdinfo si; struct xfrmu_spdinfo spc; @@ -795,7 +796,7 @@ static int build_spdinfo(struct sk_buff *skb, u32 pid, u32 seq, u32 flags) f = nlmsg_data(nlh); *f = flags; - xfrm_spd_getinfo(&si); + xfrm_spd_getinfo(net, &si); spc.incnt = si.incnt; spc.outcnt = si.outcnt; spc.fwdcnt = si.fwdcnt; @@ -828,7 +829,7 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, if (r_skb == NULL) return -ENOMEM; - if (build_spdinfo(r_skb, spid, seq, *flags) < 0) + if (build_spdinfo(r_skb, net, spid, seq, *flags) < 0) BUG(); return nlmsg_unicast(net->xfrm.nlsk, r_skb, spid); @@ -841,7 +842,8 @@ static inline size_t xfrm_sadinfo_msgsize(void) + nla_total_size(4); /* XFRMA_SAD_CNT */ } -static int build_sadinfo(struct sk_buff *skb, u32 pid, u32 seq, u32 flags) +static int build_sadinfo(struct sk_buff *skb, struct net *net, + u32 pid, u32 seq, u32 flags) { struct xfrmk_sadinfo si; struct xfrmu_sadhinfo sh; @@ -854,7 +856,7 @@ static int build_sadinfo(struct sk_buff *skb, u32 pid, u32 seq, u32 flags) f = nlmsg_data(nlh); *f = flags; - xfrm_sad_getinfo(&si); + xfrm_sad_getinfo(net, &si); sh.sadhmcnt = si.sadhmcnt; sh.sadhcnt = si.sadhcnt; @@ -882,7 +884,7 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, if (r_skb == NULL) return -ENOMEM; - if (build_sadinfo(r_skb, spid, seq, *flags) < 0) + if (build_sadinfo(r_skb, net, spid, seq, *flags) < 0) BUG(); return nlmsg_unicast(net->xfrm.nlsk, r_skb, spid); |