diff options
Diffstat (limited to 'net')
107 files changed, 1758 insertions, 1394 deletions
diff --git a/net/802/fddi.c b/net/802/fddi.c index f1611a1e06a..539e6064e6d 100644 --- a/net/802/fddi.c +++ b/net/802/fddi.c @@ -215,3 +215,5 @@ struct net_device *alloc_fddidev(int sizeof_priv) return alloc_netdev(sizeof_priv, "fddi%d", fddi_setup); } EXPORT_SYMBOL(alloc_fddidev); + +MODULE_LICENSE("GPL"); diff --git a/net/802/tr.c b/net/802/tr.c index e7eb13084d7..e874447ad14 100644 --- a/net/802/tr.c +++ b/net/802/tr.c @@ -561,6 +561,9 @@ static int rif_seq_show(struct seq_file *seq, void *v) } seq_putc(seq, '\n'); } + + if (dev) + dev_put(dev); } return 0; } diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 2b7390e377b..d1e10546eb8 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -492,6 +492,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, continue; dev_change_flags(vlandev, flgs & ~IFF_UP); + vlan_transfer_operstate(dev, vlandev); } break; @@ -507,6 +508,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, continue; dev_change_flags(vlandev, flgs | IFF_UP); + vlan_transfer_operstate(dev, vlandev); } break; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 654e45f5719..c67fe6f7565 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -121,8 +121,10 @@ int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, if (!skb) return NET_RX_DROP; - if (netpoll_rx_on(skb)) + if (netpoll_rx_on(skb)) { + skb->protocol = eth_type_trans(skb, skb->dev); return vlan_hwaccel_receive_skb(skb, grp, vlan_tci); + } return napi_frags_finish(napi, skb, vlan_gro_common(napi, grp, vlan_tci, skb)); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 1b34135cf99..b4b9068e55a 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -462,6 +462,7 @@ static int vlan_dev_open(struct net_device *dev) if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_join(dev); + netif_carrier_on(dev); return 0; clear_allmulti: @@ -471,6 +472,7 @@ del_unicast: if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) dev_unicast_delete(real_dev, dev->dev_addr, ETH_ALEN); out: + netif_carrier_off(dev); return err; } @@ -492,6 +494,7 @@ static int vlan_dev_stop(struct net_device *dev) if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) dev_unicast_delete(real_dev, dev->dev_addr, dev->addr_len); + netif_carrier_off(dev); return 0; } @@ -612,6 +615,8 @@ static int vlan_dev_init(struct net_device *dev) struct net_device *real_dev = vlan_dev_info(dev)->real_dev; int subclass = 0; + netif_carrier_off(dev); + /* IFF_BROADCAST|IFF_MULTICAST; ??? */ dev->flags = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI); dev->iflink = real_dev->ifindex; @@ -668,7 +673,8 @@ static int vlan_ethtool_get_settings(struct net_device *dev, const struct vlan_dev_info *vlan = vlan_dev_info(dev); struct net_device *real_dev = vlan->real_dev; - if (!real_dev->ethtool_ops->get_settings) + if (!real_dev->ethtool_ops || + !real_dev->ethtool_ops->get_settings) return -EOPNOTSUPP; return real_dev->ethtool_ops->get_settings(real_dev, cmd); diff --git a/net/9p/client.c b/net/9p/client.c index 1eb580c38fb..dd43a8289b0 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -203,7 +203,6 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag) p9pdu_reset(req->tc); p9pdu_reset(req->rc); - req->flush_tag = 0; req->tc->tag = tag-1; req->status = REQ_STATUS_ALLOC; @@ -324,35 +323,9 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r) */ void p9_client_cb(struct p9_client *c, struct p9_req_t *req) { - struct p9_req_t *other_req; - unsigned long flags; - P9_DPRINTK(P9_DEBUG_MUX, " tag %d\n", req->tc->tag); - - if (req->status == REQ_STATUS_ERROR) - wake_up(req->wq); - - if (req->flush_tag) { /* flush receive path */ - P9_DPRINTK(P9_DEBUG_9P, "<<< RFLUSH %d\n", req->tc->tag); - spin_lock_irqsave(&c->lock, flags); - other_req = p9_tag_lookup(c, req->flush_tag); - if (other_req->status != REQ_STATUS_FLSH) /* stale flush */ - spin_unlock_irqrestore(&c->lock, flags); - else { - other_req->status = REQ_STATUS_FLSHD; - spin_unlock_irqrestore(&c->lock, flags); - wake_up(other_req->wq); - } - p9_free_req(c, req); - } else { /* normal receive path */ - P9_DPRINTK(P9_DEBUG_MUX, "normal: tag %d\n", req->tc->tag); - spin_lock_irqsave(&c->lock, flags); - if (req->status != REQ_STATUS_FLSHD) - req->status = REQ_STATUS_RCVD; - spin_unlock_irqrestore(&c->lock, flags); - wake_up(req->wq); - P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag); - } + wake_up(req->wq); + P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag); } EXPORT_SYMBOL(p9_client_cb); @@ -486,9 +459,15 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq) if (IS_ERR(req)) return PTR_ERR(req); - req->flush_tag = oldtag; - /* we don't free anything here because RPC isn't complete */ + /* if we haven't received a response for oldreq, + remove it from the list. */ + spin_lock(&c->lock); + if (oldreq->status == REQ_STATUS_FLSH) + list_del(&oldreq->req_list); + spin_unlock(&c->lock); + + p9_free_req(c, req); return 0; } @@ -509,7 +488,6 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) struct p9_req_t *req; unsigned long flags; int sigpending; - int flushed = 0; P9_DPRINTK(P9_DEBUG_MUX, "client %p op %d\n", c, type); @@ -546,42 +524,28 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) goto reterr; } - /* if it was a flush we just transmitted, return our tag */ - if (type == P9_TFLUSH) - return req; -again: P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d\n", req->wq, tag); err = wait_event_interruptible(*req->wq, req->status >= REQ_STATUS_RCVD); - P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d returned %d (flushed=%d)\n", - req->wq, tag, err, flushed); + P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d returned %d\n", + req->wq, tag, err); if (req->status == REQ_STATUS_ERROR) { P9_DPRINTK(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); err = req->t_err; - } else if (err == -ERESTARTSYS && flushed) { - P9_DPRINTK(P9_DEBUG_MUX, "flushed - going again\n"); - goto again; - } else if (req->status == REQ_STATUS_FLSHD) { - P9_DPRINTK(P9_DEBUG_MUX, "flushed - erestartsys\n"); - err = -ERESTARTSYS; } - if ((err == -ERESTARTSYS) && (c->status == Connected) && (!flushed)) { + if ((err == -ERESTARTSYS) && (c->status == Connected)) { P9_DPRINTK(P9_DEBUG_MUX, "flushing\n"); - spin_lock_irqsave(&c->lock, flags); - if (req->status == REQ_STATUS_SENT) - req->status = REQ_STATUS_FLSH; - spin_unlock_irqrestore(&c->lock, flags); sigpending = 1; - flushed = 1; clear_thread_flag(TIF_SIGPENDING); - if (c->trans_mod->cancel(c, req)) { - err = p9_client_flush(c, req); - if (err == 0) - goto again; - } + if (c->trans_mod->cancel(c, req)) + p9_client_flush(c, req); + + /* if we received the response anyway, don't signal error */ + if (req->status == REQ_STATUS_RCVD) + err = 0; } if (sigpending) { @@ -1244,19 +1208,53 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) ret->name, ret->uid, ret->gid, ret->muid, ret->extension, ret->n_uid, ret->n_gid, ret->n_muid); + p9_free_req(clnt, req); + return ret; + free_and_error: p9_free_req(clnt, req); error: - return ret; + kfree(ret); + return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_stat); +static int p9_client_statsize(struct p9_wstat *wst, int optional) +{ + int ret; + + /* size[2] type[2] dev[4] qid[13] */ + /* mode[4] atime[4] mtime[4] length[8]*/ + /* name[s] uid[s] gid[s] muid[s] */ + ret = 2+2+4+13+4+4+4+8+2+2+2+2; + + if (wst->name) + ret += strlen(wst->name); + if (wst->uid) + ret += strlen(wst->uid); + if (wst->gid) + ret += strlen(wst->gid); + if (wst->muid) + ret += strlen(wst->muid); + + if (optional) { + ret += 2+4+4+4; /* extension[s] n_uid[4] n_gid[4] n_muid[4] */ + if (wst->extension) + ret += strlen(wst->extension); + } + + return ret; +} + int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) { int err; struct p9_req_t *req; struct p9_client *clnt; + err = 0; + clnt = fid->clnt; + wst->size = p9_client_statsize(wst, clnt->dotu); P9_DPRINTK(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid); P9_DPRINTK(P9_DEBUG_9P, " sz=%x type=%x dev=%x qid=%x.%llx.%x\n" @@ -1268,10 +1266,8 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) wst->atime, wst->mtime, (unsigned long long)wst->length, wst->name, wst->uid, wst->gid, wst->muid, wst->extension, wst->n_uid, wst->n_gid, wst->n_muid); - err = 0; - clnt = fid->clnt; - req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, 0, wst); + req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size, wst); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index c613ed08a5e..a2a1814c7a8 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -213,8 +213,8 @@ static void p9_conn_cancel(struct p9_conn *m, int err) spin_unlock_irqrestore(&m->client->lock, flags); list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { - list_del(&req->req_list); P9_DPRINTK(P9_DEBUG_ERROR, "call back req %p\n", req); + list_del(&req->req_list); p9_client_cb(m->client, req); } } @@ -336,7 +336,8 @@ static void p9_read_work(struct work_struct *work) "mux %p pkt: size: %d bytes tag: %d\n", m, n, tag); m->req = p9_tag_lookup(m->client, tag); - if (!m->req) { + if (!m->req || (m->req->status != REQ_STATUS_SENT && + m->req->status != REQ_STATUS_FLSH)) { P9_DPRINTK(P9_DEBUG_ERROR, "Unexpected packet tag %d\n", tag); err = -EIO; @@ -361,10 +362,11 @@ static void p9_read_work(struct work_struct *work) if ((m->req) && (m->rpos == m->rsize)) { /* packet is read in */ P9_DPRINTK(P9_DEBUG_TRANS, "got new packet\n"); spin_lock(&m->client->lock); + if (m->req->status != REQ_STATUS_ERROR) + m->req->status = REQ_STATUS_RCVD; list_del(&m->req->req_list); spin_unlock(&m->client->lock); p9_client_cb(m->client, m->req); - m->rbuf = NULL; m->rpos = 0; m->rsize = 0; @@ -454,6 +456,7 @@ static void p9_write_work(struct work_struct *work) req = list_entry(m->unsent_req_list.next, struct p9_req_t, req_list); req->status = REQ_STATUS_SENT; + P9_DPRINTK(P9_DEBUG_TRANS, "move req %p\n", req); list_move_tail(&req->req_list, &m->req_list); m->wbuf = req->tc->sdata; @@ -683,12 +686,13 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req) P9_DPRINTK(P9_DEBUG_TRANS, "client %p req %p\n", client, req); spin_lock(&client->lock); - list_del(&req->req_list); if (req->status == REQ_STATUS_UNSENT) { + list_del(&req->req_list); req->status = REQ_STATUS_FLSHD; ret = 0; - } + } else if (req->status == REQ_STATUS_SENT) + req->status = REQ_STATUS_FLSH; spin_unlock(&client->lock); diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 7fa0eb20b2f..ac4990041eb 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -295,6 +295,7 @@ handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma, goto err_out; req->rc = c->rc; + req->status = REQ_STATUS_RCVD; p9_client_cb(client, req); return; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 2d7781ec663..bb8579a141a 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -134,6 +134,7 @@ static void req_done(struct virtqueue *vq) P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc); P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag); req = p9_tag_lookup(chan->client, rc->tag); + req->status = REQ_STATUS_RCVD; p9_client_cb(chan->client, req); } } diff --git a/net/Kconfig b/net/Kconfig index ec93e7e38b3..ce77db4fcec 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -140,7 +140,7 @@ config NETFILTER_ADVANCED default y help If you say Y here you can select between all the netfilter modules. - If you say N the more ununsual ones will not be shown and the + If you say N the more unusual ones will not be shown and the basic ones needed by most people will default to 'M'. If unsure, say Y. diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c index 162199a2d74..fd8e0847b25 100644 --- a/net/appletalk/atalk_proc.c +++ b/net/appletalk/atalk_proc.c @@ -281,7 +281,6 @@ int __init atalk_proc_init(void) atalk_proc_dir = proc_mkdir("atalk", init_net.proc_net); if (!atalk_proc_dir) goto out; - atalk_proc_dir->owner = THIS_MODULE; p = proc_create("interface", S_IRUGO, atalk_proc_dir, &atalk_seq_interface_fops); diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 334fcd4a4ea..3100a8940af 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -549,6 +549,7 @@ static void br2684_setup(struct net_device *netdev) struct br2684_dev *brdev = BRPRIV(netdev); ether_setup(netdev); + brdev->net_dev = netdev; netdev->netdev_ops = &br2684_netdev_ops; diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 4990541ef5d..1a0f5ccea9c 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -281,7 +281,6 @@ int mpc_proc_init(void) printk(KERN_ERR "Unable to initialize /proc/atm/%s\n", STAT_FILE_NAME); return -ENOMEM; } - p->owner = THIS_MODULE; return 0; } diff --git a/net/atm/proc.c b/net/atm/proc.c index 49487b313f2..e7b3b273907 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -476,7 +476,6 @@ int __init atm_proc_init(void) atm_proc_root, e->proc_fops); if (!dirent) goto err_out_remove; - dirent->owner = THIS_MODULE; e->dirent = dirent; } ret = 0; diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c index 57aeba729ba..832bcf092a0 100644 --- a/net/ax25/ax25_uid.c +++ b/net/ax25/ax25_uid.c @@ -148,9 +148,13 @@ static void *ax25_uid_seq_start(struct seq_file *seq, loff_t *pos) { struct ax25_uid_assoc *pt; struct hlist_node *node; - int i = 0; + int i = 1; read_lock(&ax25_uid_lock); + + if (*pos == 0) + return SEQ_START_TOKEN; + ax25_uid_for_each(pt, node, &ax25_uid_list) { if (i == *pos) return pt; @@ -162,8 +166,10 @@ static void *ax25_uid_seq_start(struct seq_file *seq, loff_t *pos) static void *ax25_uid_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; - - return hlist_entry(((ax25_uid_assoc *)v)->uid_node.next, + if (v == SEQ_START_TOKEN) + return ax25_uid_list.first; + else + return hlist_entry(((ax25_uid_assoc *)v)->uid_node.next, ax25_uid_assoc, uid_node); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 1181db08d9d..61309b26f27 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -215,6 +215,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) conn->state = BT_OPEN; conn->power_save = 1; + conn->disc_timeout = HCI_DISCONN_TIMEOUT; switch (type) { case ACL_LINK: @@ -247,6 +248,8 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_ADD); + hci_conn_init_sysfs(conn); + tasklet_enable(&hdev->tx_task); return conn; @@ -424,12 +427,9 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (sec_level == BT_SECURITY_SDP) return 1; - if (sec_level == BT_SECURITY_LOW) { - if (conn->ssp_mode > 0 && conn->hdev->ssp_mode > 0) - return hci_conn_auth(conn, sec_level, auth_type); - else - return 1; - } + if (sec_level == BT_SECURITY_LOW && + (!conn->ssp_mode || !conn->hdev->ssp_mode)) + return 1; if (conn->link_mode & HCI_LM_ENCRYPT) return hci_conn_auth(conn, sec_level, auth_type); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 55534244c3a..4e7cb88e5da 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -866,8 +866,16 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); - if (!conn) - goto unlock; + if (!conn) { + if (ev->link_type != SCO_LINK) + goto unlock; + + conn = hci_conn_hash_lookup_ba(hdev, ESCO_LINK, &ev->bdaddr); + if (!conn) + goto unlock; + + conn->type = SCO_LINK; + } if (!ev->status) { conn->handle = __le16_to_cpu(ev->handle); @@ -875,6 +883,7 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; hci_conn_hold(conn); + conn->disc_timeout = HCI_DISCONN_TIMEOUT; } else conn->state = BT_CONNECTED; @@ -1055,9 +1064,14 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s hci_proto_connect_cfm(conn, ev->status); hci_conn_put(conn); } - } else + } else { hci_auth_cfm(conn, ev->status); + hci_conn_hold(conn); + conn->disc_timeout = HCI_DISCONN_TIMEOUT; + hci_conn_put(conn); + } + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) { if (!ev->status) { struct hci_cp_set_conn_encrypt cp; @@ -1471,7 +1485,21 @@ static inline void hci_mode_change_evt(struct hci_dev *hdev, struct sk_buff *skb static inline void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { + struct hci_ev_pin_code_req *ev = (void *) skb->data; + struct hci_conn *conn; + BT_DBG("%s", hdev->name); + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); + if (conn) { + hci_conn_hold(conn); + conn->disc_timeout = HCI_PAIRING_TIMEOUT; + hci_conn_put(conn); + } + + hci_dev_unlock(hdev); } static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -1481,7 +1509,21 @@ static inline void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff static inline void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) { + struct hci_ev_link_key_notify *ev = (void *) skb->data; + struct hci_conn *conn; + BT_DBG("%s", hdev->name); + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); + if (conn) { + hci_conn_hold(conn); + conn->disc_timeout = HCI_DISCONN_TIMEOUT; + hci_conn_put(conn); + } + + hci_dev_unlock(hdev); } static inline void hci_clock_offset_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -1646,20 +1688,28 @@ static inline void hci_sync_conn_complete_evt(struct hci_dev *hdev, struct sk_bu conn->type = SCO_LINK; } - if (conn->out && ev->status == 0x1c && conn->attempt < 2) { - conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) | - (hdev->esco_type & EDR_ESCO_MASK); - hci_setup_sync(conn, conn->link->handle); - goto unlock; - } - - if (!ev->status) { + switch (ev->status) { + case 0x00: conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; hci_conn_add_sysfs(conn); - } else + break; + + case 0x1c: /* SCO interval rejected */ + case 0x1f: /* Unspecified error */ + if (conn->out && conn->attempt < 2) { + conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) | + (hdev->esco_type & EDR_ESCO_MASK); + hci_setup_sync(conn, conn->link->handle); + goto unlock; + } + /* fall through */ + + default: conn->state = BT_CLOSED; + break; + } hci_proto_connect_cfm(conn, ev->status); if (ev->status) diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index ed82796d4a0..582d8877078 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -9,8 +9,7 @@ struct class *bt_class = NULL; EXPORT_SYMBOL_GPL(bt_class); -static struct workqueue_struct *btaddconn; -static struct workqueue_struct *btdelconn; +static struct workqueue_struct *bt_workq; static inline char *link_typetostr(int type) { @@ -88,9 +87,10 @@ static struct device_type bt_link = { static void add_conn(struct work_struct *work) { - struct hci_conn *conn = container_of(work, struct hci_conn, work); + struct hci_conn *conn = container_of(work, struct hci_conn, work_add); - flush_workqueue(btdelconn); + /* ensure previous del is complete */ + flush_work(&conn->work_del); if (device_add(&conn->dev) < 0) { BT_ERR("Failed to register connection device"); @@ -98,27 +98,6 @@ static void add_conn(struct work_struct *work) } } -void hci_conn_add_sysfs(struct hci_conn *conn) -{ - struct hci_dev *hdev = conn->hdev; - - BT_DBG("conn %p", conn); - - conn->dev.type = &bt_link; - conn->dev.class = bt_class; - conn->dev.parent = &hdev->dev; - - dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); - - dev_set_drvdata(&conn->dev, conn); - - device_initialize(&conn->dev); - - INIT_WORK(&conn->work, add_conn); - - queue_work(btaddconn, &conn->work); -} - /* * The rfcomm tty device will possibly retain even when conn * is down, and sysfs doesn't support move zombie device, @@ -131,9 +110,15 @@ static int __match_tty(struct device *dev, void *data) static void del_conn(struct work_struct *work) { - struct hci_conn *conn = container_of(work, struct hci_conn, work); + struct hci_conn *conn = container_of(work, struct hci_conn, work_del); struct hci_dev *hdev = conn->hdev; + /* ensure previous add is complete */ + flush_work(&conn->work_add); + + if (!device_is_registered(&conn->dev)) + return; + while (1) { struct device *dev; @@ -149,16 +134,40 @@ static void del_conn(struct work_struct *work) hci_dev_put(hdev); } -void hci_conn_del_sysfs(struct hci_conn *conn) +void hci_conn_init_sysfs(struct hci_conn *conn) { + struct hci_dev *hdev = conn->hdev; + BT_DBG("conn %p", conn); - if (!device_is_registered(&conn->dev)) - return; + conn->dev.type = &bt_link; + conn->dev.class = bt_class; + conn->dev.parent = &hdev->dev; + + dev_set_drvdata(&conn->dev, conn); + + device_initialize(&conn->dev); + + INIT_WORK(&conn->work_add, add_conn); + INIT_WORK(&conn->work_del, del_conn); +} + +void hci_conn_add_sysfs(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + + BT_DBG("conn %p", conn); - INIT_WORK(&conn->work, del_conn); + dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); - queue_work(btdelconn, &conn->work); + queue_work(bt_workq, &conn->work_add); +} + +void hci_conn_del_sysfs(struct hci_conn *conn) +{ + BT_DBG("conn %p", conn); + + queue_work(bt_workq, &conn->work_del); } static inline char *host_typetostr(int type) @@ -435,20 +444,13 @@ void hci_unregister_sysfs(struct hci_dev *hdev) int __init bt_sysfs_init(void) { - btaddconn = create_singlethread_workqueue("btaddconn"); - if (!btaddconn) + bt_workq = create_singlethread_workqueue("bluetooth"); + if (!bt_workq) return -ENOMEM; - btdelconn = create_singlethread_workqueue("btdelconn"); - if (!btdelconn) { - destroy_workqueue(btaddconn); - return -ENOMEM; - } - bt_class = class_create(THIS_MODULE, "bluetooth"); if (IS_ERR(bt_class)) { - destroy_workqueue(btdelconn); - destroy_workqueue(btaddconn); + destroy_workqueue(bt_workq); return PTR_ERR(bt_class); } @@ -457,8 +459,7 @@ int __init bt_sysfs_init(void) void bt_sysfs_cleanup(void) { - destroy_workqueue(btaddconn); - destroy_workqueue(btdelconn); + destroy_workqueue(bt_workq); class_destroy(bt_class); } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 1d0fb0f23c6..374536e050a 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1194,6 +1194,8 @@ void rfcomm_dlc_accept(struct rfcomm_dlc *d) rfcomm_send_ua(d->session, d->dlci); + rfcomm_dlc_clear_timer(d); + rfcomm_dlc_lock(d); d->state = BT_CONNECTED; d->state_change(d, 0); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index abdc703a11d..cab71ea2796 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -1093,11 +1093,6 @@ static void rfcomm_tty_hangup(struct tty_struct *tty) } } -static int rfcomm_tty_read_proc(char *buf, char **start, off_t offset, int len, int *eof, void *unused) -{ - return 0; -} - static int rfcomm_tty_tiocmget(struct tty_struct *tty, struct file *filp) { struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data; @@ -1156,7 +1151,6 @@ static const struct tty_operations rfcomm_ops = { .send_xchar = rfcomm_tty_send_xchar, .hangup = rfcomm_tty_hangup, .wait_until_sent = rfcomm_tty_wait_until_sent, - .read_proc = rfcomm_tty_read_proc, .tiocmget = rfcomm_tty_tiocmget, .tiocmset = rfcomm_tty_tiocmset, }; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 3953ac4214c..e4a418fcb35 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -788,15 +788,23 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff *skb, return NF_STOLEN; } +#if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE) static int br_nf_dev_queue_xmit(struct sk_buff *skb) { - if (skb->protocol == htons(ETH_P_IP) && + if (skb->nfct != NULL && + (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) && skb->len > skb->dev->mtu && !skb_is_gso(skb)) return ip_fragment(skb, br_dev_queue_push_xmit); else return br_dev_queue_push_xmit(skb); } +#else +static int br_nf_dev_queue_xmit(struct sk_buff *skb) +{ + return br_dev_queue_push_xmit(skb); +} +#endif /* PF_BRIDGE/POST_ROUTING ********************************************/ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, diff --git a/net/can/af_can.c b/net/can/af_can.c index 547bafc79e2..10f0528c3bf 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -674,8 +674,8 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, rcu_read_unlock(); - /* free the skbuff allocated by the netdevice driver */ - kfree_skb(skb); + /* consume the skbuff allocated by the netdevice driver */ + consume_skb(skb); if (matches > 0) { can_stats.matches++; diff --git a/net/can/bcm.c b/net/can/bcm.c index b7c7d465113..95d7f32643a 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1604,10 +1604,6 @@ static int __init bcm_module_init(void) /* create /proc/net/can-bcm directory */ proc_dir = proc_mkdir("can-bcm", init_net.proc_net); - - if (proc_dir) - proc_dir->owner = THIS_MODULE; - return 0; } diff --git a/net/can/proc.c b/net/can/proc.c index 520fef5e539..1463653dbe3 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -473,8 +473,6 @@ void can_init_proc(void) return; } - can_dir->owner = THIS_MODULE; - /* own procfs entries from the AF_CAN core */ pde_version = can_create_proc_readentry(CAN_PROC_VERSION, 0644, can_proc_read_version, NULL); diff --git a/net/core/datagram.c b/net/core/datagram.c index d0de644b378..b01a76abe1d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -64,13 +64,25 @@ static inline int connection_based(struct sock *sk) return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM; } +static int receiver_wake_function(wait_queue_t *wait, unsigned mode, int sync, + void *key) +{ + unsigned long bits = (unsigned long)key; + + /* + * Avoid a wakeup if event not interesting for us + */ + if (bits && !(bits & (POLLIN | POLLERR))) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} /* * Wait for a packet.. */ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) { int error; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, receiver_wake_function); prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); diff --git a/net/core/dev.c b/net/core/dev.c index 52fea5b28ca..e2e9e4af3ac 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1336,7 +1336,12 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype; +#ifdef CONFIG_NET_CLS_ACT + if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS))) + net_timestamp(skb); +#else net_timestamp(skb); +#endif rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_all, list) { @@ -1430,7 +1435,7 @@ void netif_device_detach(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { - netif_stop_queue(dev); + netif_tx_stop_all_queues(dev); } } EXPORT_SYMBOL(netif_device_detach); @@ -1445,7 +1450,7 @@ void netif_device_attach(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { - netif_wake_queue(dev); + netif_tx_wake_all_queues(dev); __netdev_watchdog_up(dev); } } @@ -1730,11 +1735,12 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) { u32 hash; - if (skb_rx_queue_recorded(skb)) { - hash = skb_get_rx_queue(skb); - } else if (skb->sk && skb->sk->sk_hash) { + if (skb_rx_queue_recorded(skb)) + return skb_get_rx_queue(skb) % dev->real_num_tx_queues; + + if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; - } else + else hash = skb->protocol; hash = jhash_1word(hash, skb_tx_hashrnd); @@ -2328,8 +2334,10 @@ static int napi_gro_complete(struct sk_buff *skb) struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; int err = -ENOENT; - if (NAPI_GRO_CB(skb)->count == 1) + if (NAPI_GRO_CB(skb)->count == 1) { + skb_shinfo(skb)->gso_size = 0; goto out; + } rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { @@ -2348,7 +2356,6 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - skb_shinfo(skb)->gso_size = 0; return netif_receive_skb(skb); } @@ -2472,8 +2479,9 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) return GRO_NORMAL; for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = !compare_ether_header( - skb_mac_header(p), skb_gro_mac_header(skb)); + NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev) + && !compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); NAPI_GRO_CB(p)->flush = 0; } @@ -2538,9 +2546,9 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi, } BUG_ON(info->nr_frags > MAX_SKB_FRAGS); - frag = &info->frags[info->nr_frags - 1]; + frag = info->frags; - for (i = skb_shinfo(skb)->nr_frags; i < info->nr_frags; i++) { + for (i = 0; i < info->nr_frags; i++) { skb_fill_page_desc(skb, i, frag->page, frag->page_offset, frag->size); frag++; @@ -4398,7 +4406,7 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; #ifdef CONFIG_COMPAT_NET_DEV_OPS - /* Netdevice_ops API compatiability support. + /* Netdevice_ops API compatibility support. * This is temporary until all network devices are converted. */ if (dev->netdev_ops) { @@ -4409,7 +4417,7 @@ int register_netdevice(struct net_device *dev) dev->name, netdev_drivername(dev, drivername, 64)); /* This works only because net_device_ops and the - compatiablity structure are the same. */ + compatibility structure are the same. */ dev->netdev_ops = (void *) &(dev->init); } #endif diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 244ca56dffa..d9d5160610d 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -261,8 +261,7 @@ static int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr) ret = 0; err_out: - if (rule_buf) - kfree(rule_buf); + kfree(rule_buf); return ret; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 755414cd49d..b5873bdff61 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -345,8 +345,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) udph->dest = htons(np->remote_port); udph->len = htons(udp_len); udph->check = 0; - udph->check = csum_tcpudp_magic(htonl(np->local_ip), - htonl(np->remote_ip), + udph->check = csum_tcpudp_magic(np->local_ip, + np->remote_ip, udp_len, IPPROTO_UDP, csum_partial(udph, udp_len, 0)); if (udph->check == 0) @@ -365,8 +365,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) iph->ttl = 64; iph->protocol = IPPROTO_UDP; iph->check = 0; - put_unaligned(htonl(np->local_ip), &(iph->saddr)); - put_unaligned(htonl(np->remote_ip), &(iph->daddr)); + put_unaligned(np->local_ip, &(iph->saddr)); + put_unaligned(np->remote_ip, &(iph->daddr)); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); @@ -424,7 +424,7 @@ static void arp_reply(struct sk_buff *skb) memcpy(&tip, arp_ptr, 4); /* Should we ignore arp? */ - if (tip != htonl(np->local_ip) || + if (tip != np->local_ip || ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) return; @@ -533,9 +533,9 @@ int __netpoll_rx(struct sk_buff *skb) goto out; if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) goto out; - if (np->local_ip && np->local_ip != ntohl(iph->daddr)) + if (np->local_ip && np->local_ip != iph->daddr) goto out; - if (np->remote_ip && np->remote_ip != ntohl(iph->saddr)) + if (np->remote_ip && np->remote_ip != iph->saddr) goto out; if (np->local_port && np->local_port != ntohs(uh->dest)) goto out; @@ -560,14 +560,14 @@ void netpoll_print_options(struct netpoll *np) { printk(KERN_INFO "%s: local port %d\n", np->name, np->local_port); - printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n", - np->name, HIPQUAD(np->local_ip)); + printk(KERN_INFO "%s: local IP %pI4\n", + np->name, &np->local_ip); printk(KERN_INFO "%s: interface %s\n", np->name, np->dev_name); printk(KERN_INFO "%s: remote port %d\n", np->name, np->remote_port); - printk(KERN_INFO "%s: remote IP %d.%d.%d.%d\n", - np->name, HIPQUAD(np->remote_ip)); + printk(KERN_INFO "%s: remote IP %pI4\n", + np->name, &np->remote_ip); printk(KERN_INFO "%s: remote ethernet address %pM\n", np->name, np->remote_mac); } @@ -589,7 +589,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->local_ip = ntohl(in_aton(cur)); + np->local_ip = in_aton(cur); cur = delim; } cur++; @@ -618,7 +618,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->remote_ip = ntohl(in_aton(cur)); + np->remote_ip = in_aton(cur); cur = delim + 1; if (*cur != 0) { @@ -759,10 +759,9 @@ int netpoll_setup(struct netpoll *np) goto release; } - np->local_ip = ntohl(in_dev->ifa_list->ifa_local); + np->local_ip = in_dev->ifa_list->ifa_local; rcu_read_unlock(); - printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n", - np->name, HIPQUAD(np->local_ip)); + printk(KERN_INFO "%s: local IP %pI4\n", np->name, &np->local_ip); } if (np->rx_hook) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 32d419f5ac9..3779c1438c1 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3806,7 +3806,6 @@ static int __init pg_init(void) pg_proc_dir = proc_mkdir(PG_PROC_DIR, init_net.proc_net); if (!pg_proc_dir) return -ENODEV; - pg_proc_dir->owner = THIS_MODULE; pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops); if (pe == NULL) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6acbf9e79eb..f091a5a845c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1365,9 +1365,8 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) static inline struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, - struct sk_buff *skb) + struct sk_buff *skb, struct sock *sk) { - struct sock *sk = skb->sk; struct page *p = sk->sk_sndmsg_page; unsigned int off; @@ -1405,13 +1404,14 @@ new_page: */ static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page, unsigned int *len, unsigned int offset, - struct sk_buff *skb, int linear) + struct sk_buff *skb, int linear, + struct sock *sk) { if (unlikely(spd->nr_pages == PIPE_BUFFERS)) return 1; if (linear) { - page = linear_to_page(page, len, &offset, skb); + page = linear_to_page(page, len, &offset, skb, sk); if (!page) return 1; } else @@ -1442,7 +1442,8 @@ static inline void __segment_seek(struct page **page, unsigned int *poff, static inline int __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct sk_buff *skb, - struct splice_pipe_desc *spd, int linear) + struct splice_pipe_desc *spd, int linear, + struct sock *sk) { if (!*len) return 1; @@ -1465,7 +1466,7 @@ static inline int __splice_segment(struct page *page, unsigned int poff, /* the linear region may spread across several pages */ flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - if (spd_fill_page(spd, page, &flen, poff, skb, linear)) + if (spd_fill_page(spd, page, &flen, poff, skb, linear, sk)) return 1; __segment_seek(&page, &poff, &plen, flen); @@ -1481,8 +1482,8 @@ static inline int __splice_segment(struct page *page, unsigned int poff, * pipe is full or if we already spliced the requested length. */ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, - unsigned int *len, - struct splice_pipe_desc *spd) + unsigned int *len, struct splice_pipe_desc *spd, + struct sock *sk) { int seg; @@ -1492,7 +1493,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, 1)) + offset, len, skb, spd, 1, sk)) return 1; /* @@ -1502,7 +1503,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (__splice_segment(f->page, f->page_offset, f->size, - offset, len, skb, spd, 0)) + offset, len, skb, spd, 0, sk)) return 1; } @@ -1528,12 +1529,13 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, }; + struct sock *sk = skb->sk; /* * __skb_splice_bits() only fails if the output has no room left, * so no point in going over the frag_list for the error case. */ - if (__skb_splice_bits(skb, &offset, &tlen, &spd)) + if (__skb_splice_bits(skb, &offset, &tlen, &spd, sk)) goto done; else if (!tlen) goto done; @@ -1545,14 +1547,13 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct sk_buff *list = skb_shinfo(skb)->frag_list; for (; list && tlen; list = list->next) { - if (__skb_splice_bits(list, &offset, &tlen, &spd)) + if (__skb_splice_bits(list, &offset, &tlen, &spd, sk)) break; } } done: if (spd.nr_pages) { - struct sock *sk = skb->sk; int ret; /* @@ -2579,7 +2580,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) skb_network_header_len(skb)); skb_copy_from_linear_data(skb, nskb->data, doffset); - if (pos >= offset + len) + if (fskb != skb_shinfo(skb)->frag_list) continue; if (!sg) { diff --git a/net/core/sock.c b/net/core/sock.c index 0620046e4eb..7dbf3ffb35c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1677,7 +1677,7 @@ static void sock_def_error_report(struct sock *sk) { read_lock(&sk->sk_callback_lock); if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible_poll(sk->sk_sleep, POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); read_unlock(&sk->sk_callback_lock); } @@ -1686,7 +1686,8 @@ static void sock_def_readable(struct sock *sk, int len) { read_lock(&sk->sk_callback_lock); if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN | + POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); read_unlock(&sk->sk_callback_lock); } @@ -1700,7 +1701,8 @@ static void sock_def_write_space(struct sock *sk) */ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + POLLWRNORM | POLLWRBAND); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 35c5f6a5cb7..831fe1879dc 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -253,9 +253,9 @@ unsigned int arpt_do_table(struct sk_buff *skb, indev = in ? in->name : nulldevname; outdev = out ? out->name : nulldevname; - rcu_read_lock(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); back = get_entry(table_base, private->underflow[hook]); @@ -273,6 +273,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) + (2 * skb->dev->addr_len); + ADD_COUNTER(e->counters, hdr_len, 1); t = arpt_get_target(e); @@ -328,8 +329,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, e = (void *)e + e->next_offset; } } while (!hotdrop); - - rcu_read_unlock(); + xt_info_rdunlock_bh(); if (hotdrop) return NF_DROP; @@ -711,9 +711,12 @@ static void get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters * with data used by 'current' CPU - * We dont care about preemption here. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; ARPT_ENTRY_ITERATE(t->entries[curcpu], @@ -726,73 +729,22 @@ static void get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); ARPT_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } -} - - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct arpt_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - ARPT_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } -static inline int -zero_entry_counter(struct arpt_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - ARPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters *alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -802,30 +754,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; - - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ + return ERR_PTR(-ENOMEM); - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); - - xt_free_table_info(info); + get_counters(private, counters); return counters; - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); } static int copy_entries_to_user(unsigned int total_size, @@ -1094,8 +1027,9 @@ static int __do_replace(struct net *net, const char *name, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1165,10 +1099,23 @@ static int do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct arpt_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} + static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1224,26 +1171,26 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len, goto free; } - mutex_lock(&t->lock); + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[smp_processor_id()]; + curcpu = smp_processor_id(); + loc_cpu_entry = private->entries[curcpu]; + xt_info_wrlock(curcpu); ARPT_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); unlock_up_free: - mutex_unlock(&t->lock); - + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 82ee7c9049f..2ec8d7290c4 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -338,10 +338,9 @@ ipt_do_table(struct sk_buff *skb, tgpar.hooknum = hook; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - - rcu_read_lock(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); @@ -436,8 +435,7 @@ ipt_do_table(struct sk_buff *skb, e = (void *)e + e->next_offset; } } while (!hotdrop); - - rcu_read_unlock(); + xt_info_rdunlock_bh(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -896,10 +894,13 @@ get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters - * with data used by 'current' CPU - * We dont care about preemption here. + * with data used by 'current' CPU. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; IPT_ENTRY_ITERATE(t->entries[curcpu], @@ -912,74 +913,22 @@ get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); IPT_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } - -} - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct ipt_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - IPT_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } - -static inline int -zero_entry_counter(struct ipt_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - IPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters * alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -988,30 +937,11 @@ static struct xt_counters * alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; + return ERR_PTR(-ENOMEM); - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ - - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); - - xt_free_table_info(info); + get_counters(private, counters); return counters; - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); } static int @@ -1306,8 +1236,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1377,11 +1308,23 @@ do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct ipt_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1437,25 +1380,26 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, int compat goto free; } - mutex_lock(&t->lock); + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[raw_smp_processor_id()]; + curcpu = smp_processor_id(); + loc_cpu_entry = private->entries[curcpu]; + xt_info_wrlock(curcpu); IPT_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); unlock_up_free: - mutex_unlock(&t->lock); + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index fe65187810f..3229e0a81ba 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -211,7 +211,8 @@ find_best_ips_proto(struct nf_conntrack_tuple *tuple, minip = ntohl(range->min_ip); maxip = ntohl(range->max_ip); j = jhash_2words((__force u32)tuple->src.u3.ip, - (__force u32)tuple->dst.u3.ip, 0); + range->flags & IP_NAT_RANGE_PERSISTENT ? + (__force u32)tuple->dst.u3.ip : 0, 0); j = ((u64)j * (maxip - minip + 1)) >> 32; *var_ipp = htonl(minip + j); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c40debe51b3..c4c60e9f068 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3397,7 +3397,7 @@ int __init ip_rt_init(void) 0, &rt_hash_log, &rt_hash_mask, - 0); + rhash_entries ? 0 : 512 * 1024); memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket)); rt_hash_lock_init(); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2451aeb5ac2..1d7f49c6f0c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1081,8 +1081,7 @@ out_err: * this, no blocking and very strange errors 8) */ -static int tcp_recv_urg(struct sock *sk, long timeo, - struct msghdr *msg, int len, int flags) +static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) { struct tcp_sock *tp = tcp_sk(sk); @@ -1697,7 +1696,7 @@ out: return err; recv_urg: - err = tcp_recv_urg(sk, timeo, msg, len, flags); + err = tcp_recv_urg(sk, msg, len, flags); goto out; } @@ -2512,6 +2511,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) struct sk_buff *p; struct tcphdr *th; struct tcphdr *th2; + unsigned int len; unsigned int thlen; unsigned int flags; unsigned int mss = 1; @@ -2532,6 +2532,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) skb_gro_pull(skb, thlen); + len = skb_gro_len(skb); flags = tcp_flag_word(th); for (; (p = *head); head = &p->next) { @@ -2562,7 +2563,7 @@ found: mss = skb_shinfo(p)->gso_size; - flush |= (skb_gro_len(skb) > mss) | !skb_gro_len(skb); + flush |= (len > mss) | !len; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); if (flush || skb_gro_receive(head, skb)) { @@ -2575,7 +2576,7 @@ found: tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH); out_check_final: - flush = skb_gro_len(skb) < mss; + flush = len < mss; flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2bc8e27a163..eec3e6f9956 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -597,16 +597,6 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) tcp_grow_window(sk, skb); } -static u32 tcp_rto_min(struct sock *sk) -{ - struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = TCP_RTO_MIN; - - if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) - rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); - return rto_min; -} - /* Called to compute a smoothed rtt estimate. The data fed to this * routine either comes from timestamps, or from segments that were * known _not_ to have been retransmitted [see Karn/Partridge @@ -928,6 +918,8 @@ static void tcp_init_metrics(struct sock *sk) tcp_set_rto(sk); if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp) goto reset; + +cwnd: tp->snd_cwnd = tcp_init_cwnd(tp, dst); tp->snd_cwnd_stamp = tcp_time_stamp; return; @@ -942,6 +934,7 @@ reset: tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT; inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; } + goto cwnd; } static void tcp_update_reordering(struct sock *sk, const int metric, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c1f259d2d33..59aec609cec 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -754,6 +754,36 @@ static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb, tp->fackets_out -= decr; } +/* Pcount in the middle of the write queue got changed, we need to do various + * tweaks to fix counters + */ +static void tcp_adjust_pcount(struct sock *sk, struct sk_buff *skb, int decr) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tp->packets_out -= decr; + + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) + tp->sacked_out -= decr; + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) + tp->retrans_out -= decr; + if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) + tp->lost_out -= decr; + + /* Reno case is special. Sigh... */ + if (tcp_is_reno(tp) && decr > 0) + tp->sacked_out -= min_t(u32, tp->sacked_out, decr); + + tcp_adjust_fackets_out(sk, skb, decr); + + if (tp->lost_skb_hint && + before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && + (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))) + tp->lost_cnt_hint -= decr; + + tcp_verify_left_out(tp); +} + /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. @@ -836,28 +866,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, int diff = old_factor - tcp_skb_pcount(skb) - tcp_skb_pcount(buff); - tp->packets_out -= diff; - - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) - tp->sacked_out -= diff; - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) - tp->retrans_out -= diff; - - if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) - tp->lost_out -= diff; - - /* Adjust Reno SACK estimate. */ - if (tcp_is_reno(tp) && diff > 0) { - tcp_dec_pcount_approx_int(&tp->sacked_out, diff); - tcp_verify_left_out(tp); - } - tcp_adjust_fackets_out(sk, skb, diff); - - if (tp->lost_skb_hint && - before(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(tp->lost_skb_hint)->seq) && - (tcp_is_fack(tp) || TCP_SKB_CB(skb)->sacked)) - tp->lost_cnt_hint -= diff; + if (diff) + tcp_adjust_pcount(sk, skb, diff); } /* Link BUFF into the send queue. */ @@ -1768,22 +1778,14 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) * packet counting does not break. */ TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS; - if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_RETRANS) - tp->retrans_out -= tcp_skb_pcount(next_skb); - if (TCP_SKB_CB(next_skb)->sacked & TCPCB_LOST) - tp->lost_out -= tcp_skb_pcount(next_skb); - /* Reno case is special. Sigh... */ - if (tcp_is_reno(tp) && tp->sacked_out) - tcp_dec_pcount_approx(&tp->sacked_out, next_skb); - - tcp_adjust_fackets_out(sk, next_skb, tcp_skb_pcount(next_skb)); - tp->packets_out -= tcp_skb_pcount(next_skb); /* changed transmit queue under us so clear hints */ tcp_clear_retrans_hints_partial(tp); if (next_skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = skb; + tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb)); + sk_wmem_free_skb(sk, next_skb); } @@ -1891,7 +1893,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (tcp_fragment(sk, skb, cur_mss, cur_mss)) return -ENOMEM; /* We'll try again later. */ } else { - tcp_init_tso_segs(sk, skb, cur_mss); + int oldpcount = tcp_skb_pcount(skb); + + if (unlikely(oldpcount > 1)) { + tcp_init_tso_segs(sk, skb, cur_mss); + tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb)); + } } tcp_retrans_try_collapse(sk, skb, cur_mss); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index bda08a09357..7a1d1ce22e6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -222,7 +222,7 @@ fail: return error; } -int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) +static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) { struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); @@ -1823,7 +1823,6 @@ EXPORT_SYMBOL(udp_lib_getsockopt); EXPORT_SYMBOL(udp_lib_setsockopt); EXPORT_SYMBOL(udp_poll); EXPORT_SYMBOL(udp_lib_get_port); -EXPORT_SYMBOL(ipv4_rcv_saddr_equal); #ifdef CONFIG_PROC_FS EXPORT_SYMBOL(udp_proc_register); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ec992159b5f..ca8cb326d1d 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -22,17 +22,17 @@ menuconfig IPV6 if IPV6 config IPV6_PRIVACY - bool "IPv6: Privacy Extensions support" + bool "IPv6: Privacy Extensions (RFC 3041) support" ---help--- Privacy Extensions for Stateless Address Autoconfiguration in IPv6 - support. With this option, additional periodically-alter - pseudo-random global-scope unicast address(es) will assigned to + support. With this option, additional periodically-altered + pseudo-random global-scope unicast address(es) will be assigned to your interface(s). - We use our standard pseudo random algorithm to generate randomized - interface identifier, instead of one described in RFC 3041. + We use our standard pseudo-random algorithm to generate the + randomized interface identifier, instead of one described in RFC 3041. - By default, kernel do not generate temporary addresses. + By default the kernel does not generate temporary addresses. To use temporary addresses, do echo 2 >/proc/sys/net/ipv6/conf/all/use_tempaddr @@ -43,9 +43,9 @@ config IPV6_ROUTER_PREF bool "IPv6: Router Preference (RFC 4191) support" ---help--- Router Preference is an optional extension to the Router - Advertisement message to improve the ability of hosts - to pick more appropriate router, especially when the hosts - is placed in a multi-homed network. + Advertisement message which improves the ability of hosts + to pick an appropriate router, especially when the hosts + are placed in a multi-homed network. If unsure, say N. diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d31df0f4bc9..a7fdf9a27f1 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -380,10 +380,6 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, default: goto sticky_done; } - - if ((rthdr->hdrlen & 1) || - (rthdr->hdrlen >> 1) != rthdr->segments_left) - goto sticky_done; } retv = 0; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e89cfa3a8f2..219e165aea1 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -365,9 +365,9 @@ ip6t_do_table(struct sk_buff *skb, IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - rcu_read_lock(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); @@ -466,7 +466,7 @@ ip6t_do_table(struct sk_buff *skb, #ifdef CONFIG_NETFILTER_DEBUG ((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON; #endif - rcu_read_unlock(); + xt_info_rdunlock_bh(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -926,9 +926,12 @@ get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters * with data used by 'current' CPU - * We dont care about preemption here. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; IP6T_ENTRY_ITERATE(t->entries[curcpu], @@ -941,72 +944,22 @@ get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); IP6T_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } -} - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct ip6t_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - IP6T_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } -static inline int -zero_entry_counter(struct ip6t_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - IP6T_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters *alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -1015,28 +968,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; - - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ + return ERR_PTR(-ENOMEM); - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); + get_counters(private, counters); - xt_free_table_info(info); - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); + return counters; } static int @@ -1332,8 +1268,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1403,11 +1340,24 @@ do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct ip6t_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} + static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1463,25 +1413,28 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, goto free; } - mutex_lock(&t->lock); + + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[raw_smp_processor_id()]; + curcpu = smp_processor_id(); + xt_info_wrlock(curcpu); + loc_cpu_entry = private->entries[curcpu]; IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); + unlock_up_free: - mutex_unlock(&t->lock); + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6842dd2edd5..8905712cfbb 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -53,6 +53,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); + __be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; + __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); int addr_type = ipv6_addr_type(sk_rcv_saddr6); @@ -60,7 +62,9 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) /* if both are mapped, treat as IPv4 */ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) - return ipv4_rcv_saddr_equal(sk, sk2); + return (!sk2_ipv6only && + (!sk_rcv_saddr || !sk2_rcv_saddr || + sk_rcv_saddr == sk2_rcv_saddr)); if (addr_type2 == IPV6_ADDR_ANY && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 0af823cf7f1..5ee5a031bc9 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -72,6 +72,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) #endif skb->protocol = htons(ETH_P_IPV6); + skb->local_df = 1; return x->outer_mode->output2(x, skb); } diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 086d5ef098f..811984d9324 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -34,6 +34,7 @@ #include <linux/module.h> #include <linux/fs.h> #include <linux/sched.h> +#include <linux/seq_file.h> #include <linux/termios.h> #include <linux/tty.h> #include <linux/interrupt.h> @@ -72,8 +73,7 @@ static int ircomm_tty_control_indication(void *instance, void *sap, static void ircomm_tty_flow_indication(void *instance, void *sap, LOCAL_FLOW cmd); #ifdef CONFIG_PROC_FS -static int ircomm_tty_read_proc(char *buf, char **start, off_t offset, int len, - int *eof, void *unused); +static const struct file_operations ircomm_tty_proc_fops; #endif /* CONFIG_PROC_FS */ static struct tty_driver *driver; @@ -98,7 +98,7 @@ static const struct tty_operations ops = { .hangup = ircomm_tty_hangup, .wait_until_sent = ircomm_tty_wait_until_sent, #ifdef CONFIG_PROC_FS - .read_proc = ircomm_tty_read_proc, + .proc_fops = &ircomm_tty_proc_fops, #endif /* CONFIG_PROC_FS */ }; @@ -1245,150 +1245,170 @@ static void ircomm_tty_flow_indication(void *instance, void *sap, } #ifdef CONFIG_PROC_FS -static int ircomm_tty_line_info(struct ircomm_tty_cb *self, char *buf) +static void ircomm_tty_line_info(struct ircomm_tty_cb *self, struct seq_file *m) { - int ret=0; + char sep; - ret += sprintf(buf+ret, "State: %s\n", ircomm_tty_state[self->state]); + seq_printf(m, "State: %s\n", ircomm_tty_state[self->state]); - ret += sprintf(buf+ret, "Service type: "); + seq_puts(m, "Service type: "); if (self->service_type & IRCOMM_9_WIRE) - ret += sprintf(buf+ret, "9_WIRE"); + seq_puts(m, "9_WIRE"); else if (self->service_type & IRCOMM_3_WIRE) - ret += sprintf(buf+ret, "3_WIRE"); + seq_puts(m, "3_WIRE"); else if (self->service_type & IRCOMM_3_WIRE_RAW) - ret += sprintf(buf+ret, "3_WIRE_RAW"); + seq_puts(m, "3_WIRE_RAW"); else - ret += sprintf(buf+ret, "No common service type!\n"); - ret += sprintf(buf+ret, "\n"); - - ret += sprintf(buf+ret, "Port name: %s\n", self->settings.port_name); - - ret += sprintf(buf+ret, "DTE status: "); - if (self->settings.dte & IRCOMM_RTS) - ret += sprintf(buf+ret, "RTS|"); - if (self->settings.dte & IRCOMM_DTR) - ret += sprintf(buf+ret, "DTR|"); - if (self->settings.dte) - ret--; /* remove the last | */ - ret += sprintf(buf+ret, "\n"); - - ret += sprintf(buf+ret, "DCE status: "); - if (self->settings.dce & IRCOMM_CTS) - ret += sprintf(buf+ret, "CTS|"); - if (self->settings.dce & IRCOMM_DSR) - ret += sprintf(buf+ret, "DSR|"); - if (self->settings.dce & IRCOMM_CD) - ret += sprintf(buf+ret, "CD|"); - if (self->settings.dce & IRCOMM_RI) - ret += sprintf(buf+ret, "RI|"); - if (self->settings.dce) - ret--; /* remove the last | */ - ret += sprintf(buf+ret, "\n"); - - ret += sprintf(buf+ret, "Configuration: "); + seq_puts(m, "No common service type!\n"); + seq_putc(m, '\n'); + + seq_printf(m, "Port name: %s\n", self->settings.port_name); + + seq_printf(m, "DTE status:"); + sep = ' '; + if (self->settings.dte & IRCOMM_RTS) { + seq_printf(m, "%cRTS", sep); + sep = '|'; + } + if (self->settings.dte & IRCOMM_DTR) { + seq_printf(m, "%cDTR", sep); + sep = '|'; + } + seq_putc(m, '\n'); + + seq_puts(m, "DCE status:"); + sep = ' '; + if (self->settings.dce & IRCOMM_CTS) { + seq_printf(m, "%cCTS", sep); + sep = '|'; + } + if (self->settings.dce & IRCOMM_DSR) { + seq_printf(m, "%cDSR", sep); + sep = '|'; + } + if (self->settings.dce & IRCOMM_CD) { + seq_printf(m, "%cCD", sep); + sep = '|'; + } + if (self->settings.dce & IRCOMM_RI) { + seq_printf(m, "%cRI", sep); + sep = '|'; + } + seq_putc(m, '\n'); + + seq_puts(m, "Configuration: "); if (!self->settings.null_modem) - ret += sprintf(buf+ret, "DTE <-> DCE\n"); + seq_puts(m, "DTE <-> DCE\n"); else - ret += sprintf(buf+ret, - "DTE <-> DTE (null modem emulation)\n"); - - ret += sprintf(buf+ret, "Data rate: %d\n", self->settings.data_rate); - - ret += sprintf(buf+ret, "Flow control: "); - if (self->settings.flow_control & IRCOMM_XON_XOFF_IN) - ret += sprintf(buf+ret, "XON_XOFF_IN|"); - if (self->settings.flow_control & IRCOMM_XON_XOFF_OUT) - ret += sprintf(buf+ret, "XON_XOFF_OUT|"); - if (self->settings.flow_control & IRCOMM_RTS_CTS_IN) - ret += sprintf(buf+ret, "RTS_CTS_IN|"); - if (self->settings.flow_control & IRCOMM_RTS_CTS_OUT) - ret += sprintf(buf+ret, "RTS_CTS_OUT|"); - if (self->settings.flow_control & IRCOMM_DSR_DTR_IN) - ret += sprintf(buf+ret, "DSR_DTR_IN|"); - if (self->settings.flow_control & IRCOMM_DSR_DTR_OUT) - ret += sprintf(buf+ret, "DSR_DTR_OUT|"); - if (self->settings.flow_control & IRCOMM_ENQ_ACK_IN) - ret += sprintf(buf+ret, "ENQ_ACK_IN|"); - if (self->settings.flow_control & IRCOMM_ENQ_ACK_OUT) - ret += sprintf(buf+ret, "ENQ_ACK_OUT|"); - if (self->settings.flow_control) - ret--; /* remove the last | */ - ret += sprintf(buf+ret, "\n"); - - ret += sprintf(buf+ret, "Flags: "); - if (self->flags & ASYNC_CTS_FLOW) - ret += sprintf(buf+ret, "ASYNC_CTS_FLOW|"); - if (self->flags & ASYNC_CHECK_CD) - ret += sprintf(buf+ret, "ASYNC_CHECK_CD|"); - if (self->flags & ASYNC_INITIALIZED) - ret += sprintf(buf+ret, "ASYNC_INITIALIZED|"); - if (self->flags & ASYNC_LOW_LATENCY) - ret += sprintf(buf+ret, "ASYNC_LOW_LATENCY|"); - if (self->flags & ASYNC_CLOSING) - ret += sprintf(buf+ret, "ASYNC_CLOSING|"); - if (self->flags & ASYNC_NORMAL_ACTIVE) - ret += sprintf(buf+ret, "ASYNC_NORMAL_ACTIVE|"); - if (self->flags) - ret--; /* remove the last | */ - ret += sprintf(buf+ret, "\n"); - - ret += sprintf(buf+ret, "Role: %s\n", self->client ? - "client" : "server"); - ret += sprintf(buf+ret, "Open count: %d\n", self->open_count); - ret += sprintf(buf+ret, "Max data size: %d\n", self->max_data_size); - ret += sprintf(buf+ret, "Max header size: %d\n", self->max_header_size); + seq_puts(m, "DTE <-> DTE (null modem emulation)\n"); + + seq_printf(m, "Data rate: %d\n", self->settings.data_rate); + + seq_puts(m, "Flow control:"); + sep = ' '; + if (self->settings.flow_control & IRCOMM_XON_XOFF_IN) { + seq_printf(m, "%cXON_XOFF_IN", sep); + sep = '|'; + } + if (self->settings.flow_control & IRCOMM_XON_XOFF_OUT) { + seq_printf(m, "%cXON_XOFF_OUT", sep); + sep = '|'; + } + if (self->settings.flow_control & IRCOMM_RTS_CTS_IN) { + seq_printf(m, "%cRTS_CTS_IN", sep); + sep = '|'; + } + if (self->settings.flow_control & IRCOMM_RTS_CTS_OUT) { + seq_printf(m, "%cRTS_CTS_OUT", sep); + sep = '|'; + } + if (self->settings.flow_control & IRCOMM_DSR_DTR_IN) { + seq_printf(m, "%cDSR_DTR_IN", sep); + sep = '|'; + } + if (self->settings.flow_control & IRCOMM_DSR_DTR_OUT) { + seq_printf(m, "%cDSR_DTR_OUT", sep); + sep = '|'; + } + if (self->settings.flow_control & IRCOMM_ENQ_ACK_IN) { + seq_printf(m, "%cENQ_ACK_IN", sep); + sep = '|'; + } + if (self->settings.flow_control & IRCOMM_ENQ_ACK_OUT) { + seq_printf(m, "%cENQ_ACK_OUT", sep); + sep = '|'; + } + seq_putc(m, '\n'); + + seq_puts(m, "Flags:"); + sep = ' '; + if (self->flags & ASYNC_CTS_FLOW) { + seq_printf(m, "%cASYNC_CTS_FLOW", sep); + sep = '|'; + } + if (self->flags & ASYNC_CHECK_CD) { + seq_printf(m, "%cASYNC_CHECK_CD", sep); + sep = '|'; + } + if (self->flags & ASYNC_INITIALIZED) { + seq_printf(m, "%cASYNC_INITIALIZED", sep); + sep = '|'; + } + if (self->flags & ASYNC_LOW_LATENCY) { + seq_printf(m, "%cASYNC_LOW_LATENCY", sep); + sep = '|'; + } + if (self->flags & ASYNC_CLOSING) { + seq_printf(m, "%cASYNC_CLOSING", sep); + sep = '|'; + } + if (self->flags & ASYNC_NORMAL_ACTIVE) { + seq_printf(m, "%cASYNC_NORMAL_ACTIVE", sep); + sep = '|'; + } + seq_putc(m, '\n'); + + seq_printf(m, "Role: %s\n", self->client ? "client" : "server"); + seq_printf(m, "Open count: %d\n", self->open_count); + seq_printf(m, "Max data size: %d\n", self->max_data_size); + seq_printf(m, "Max header size: %d\n", self->max_header_size); if (self->tty) - ret += sprintf(buf+ret, "Hardware: %s\n", + seq_printf(m, "Hardware: %s\n", self->tty->hw_stopped ? "Stopped" : "Running"); - - ret += sprintf(buf+ret, "\n"); - return ret; } - -/* - * Function ircomm_tty_read_proc (buf, start, offset, len, eof, unused) - * - * - * - */ -static int ircomm_tty_read_proc(char *buf, char **start, off_t offset, int len, - int *eof, void *unused) +static int ircomm_tty_proc_show(struct seq_file *m, void *v) { struct ircomm_tty_cb *self; - int count = 0, l; - off_t begin = 0; unsigned long flags; spin_lock_irqsave(&ircomm_tty->hb_spinlock, flags); self = (struct ircomm_tty_cb *) hashbin_get_first(ircomm_tty); - while ((self != NULL) && (count < 4000)) { + while (self != NULL) { if (self->magic != IRCOMM_TTY_MAGIC) break; - l = ircomm_tty_line_info(self, buf + count); - count += l; - if (count+begin > offset+len) - goto done; - if (count+begin < offset) { - begin += count; - count = 0; - } - + ircomm_tty_line_info(self, m); self = (struct ircomm_tty_cb *) hashbin_get_next(ircomm_tty); } - *eof = 1; -done: spin_unlock_irqrestore(&ircomm_tty->hb_spinlock, flags); + return 0; +} - if (offset >= count+begin) - return 0; - *start = buf + (offset-begin); - return ((len < begin+count-offset) ? len : begin+count-offset); +static int ircomm_tty_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, ircomm_tty_proc_show, NULL); } + +static const struct file_operations ircomm_tty_proc_fops = { + .owner = THIS_MODULE, + .open = ircomm_tty_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif /* CONFIG_PROC_FS */ MODULE_AUTHOR("Dag Brattli <dagb@cs.uit.no>"); diff --git a/net/irda/irproc.c b/net/irda/irproc.c index 88e80a31273..8ff1861649e 100644 --- a/net/irda/irproc.c +++ b/net/irda/irproc.c @@ -70,7 +70,6 @@ void __init irda_proc_register(void) proc_irda = proc_mkdir("irda", init_net.proc_net); if (proc_irda == NULL) return; - proc_irda->owner = THIS_MODULE; for (i = 0; i < ARRAY_SIZE(irda_dirs); i++) d = proc_create(irda_dirs[i].name, 0, proc_irda, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 49e786535dc..b51c9187c34 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -172,6 +172,7 @@ static void iucv_sock_close(struct sock *sk) err = iucv_sock_wait_state(sk, IUCV_CLOSED, 0, timeo); } + case IUCV_CLOSING: /* fall through */ sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); @@ -224,6 +225,8 @@ static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio) spin_lock_init(&iucv_sk(sk)->message_q.lock); skb_queue_head_init(&iucv_sk(sk)->backlog_skb_q); iucv_sk(sk)->send_tag = 0; + iucv_sk(sk)->path = NULL; + memset(&iucv_sk(sk)->src_user_id , 0, 32); sk->sk_destruct = iucv_sock_destruct; sk->sk_sndtimeo = IUCV_CONN_TIMEOUT; @@ -811,6 +814,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + /* receive/dequeue next skb: + * the function understands MSG_PEEK and, thus, does not dequeue skb */ skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -858,9 +863,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, iucv_process_message_q(sk); spin_unlock_bh(&iucv->message_q.lock); } - - } else - skb_queue_head(&sk->sk_receive_queue, skb); + } done: return err ? : copied; @@ -934,6 +937,9 @@ static int iucv_sock_shutdown(struct socket *sock, int how) lock_sock(sk); switch (sk->sk_state) { + case IUCV_DISCONN: + case IUCV_CLOSING: + case IUCV_SEVERED: case IUCV_CLOSED: err = -ENOTCONN; goto fail; @@ -1113,8 +1119,12 @@ static void iucv_callback_rx(struct iucv_path *path, struct iucv_message *msg) struct sock_msg_q *save_msg; int len; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (sk->sk_shutdown & RCV_SHUTDOWN) { + iucv_message_reject(path, msg); return; + } + + spin_lock(&iucv->message_q.lock); if (!list_empty(&iucv->message_q.list) || !skb_queue_empty(&iucv->backlog_skb_q)) @@ -1129,9 +1139,8 @@ static void iucv_callback_rx(struct iucv_path *path, struct iucv_message *msg) if (!skb) goto save_message; - spin_lock(&iucv->message_q.lock); iucv_process_message(sk, skb, path, msg); - spin_unlock(&iucv->message_q.lock); + goto out_unlock; return; @@ -1142,8 +1151,9 @@ save_message: save_msg->path = path; save_msg->msg = *msg; - spin_lock(&iucv->message_q.lock); list_add_tail(&save_msg->list, &iucv->message_q.list); + +out_unlock: spin_unlock(&iucv->message_q.lock); } diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index b58bd7c6cdf..d208b3396d9 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -236,7 +236,6 @@ int __init llc_proc_init(void) llc_proc_dir = proc_mkdir("llc", init_net.proc_net); if (!llc_proc_dir) goto out; - llc_proc_dir->owner = THIS_MODULE; p = proc_create("socket", S_IRUGO, llc_proc_dir, &llc_seq_socket_fops); if (!p) diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 60c16162474..ecc3faf9f11 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -33,7 +33,7 @@ choice ---help--- This option selects the default rate control algorithm mac80211 will use. Note that this default can still be - overriden through the ieee80211_default_rc_algo module + overridden through the ieee80211_default_rc_algo module parameter if different algorithms are available. config MAC80211_RC_DEFAULT_PID @@ -202,10 +202,3 @@ config MAC80211_DEBUG_COUNTERS and show them in debugfs. If unsure, say N. - -config MAC80211_VERBOSE_SPECT_MGMT_DEBUG - bool "Verbose Spectrum Management (IEEE 802.11h)debugging" - depends on MAC80211_DEBUG_MENU - ---help--- - Say Y here to print out verbose Spectrum Management (IEEE 802.11h) - debug messages. diff --git a/net/mac80211/main.c b/net/mac80211/main.c index a6f1d8a869b..14134193cd1 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -258,7 +258,7 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) (chan->max_power - local->power_constr_level) : chan->max_power; - if (local->user_power_level) + if (local->user_power_level >= 0) power = min(power, local->user_power_level); if (local->hw.conf.power_level != power) { @@ -757,6 +757,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.conf.long_frame_max_tx_count = 4; local->hw.conf.short_frame_max_tx_count = 7; local->hw.conf.radio_enabled = true; + local->user_power_level = -1; INIT_LIST_HEAD(&local->interfaces); mutex_init(&local->iflist_mtx); @@ -909,6 +910,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (result < 0) goto fail_sta_info; + result = ieee80211_wep_init(local); + if (result < 0) { + printk(KERN_DEBUG "%s: Failed to initialize wep: %d\n", + wiphy_name(local->hw.wiphy), result); + goto fail_wep; + } + rtnl_lock(); result = dev_alloc_name(local->mdev, local->mdev->name); if (result < 0) @@ -930,14 +938,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) goto fail_rate; } - result = ieee80211_wep_init(local); - - if (result < 0) { - printk(KERN_DEBUG "%s: Failed to initialize wep: %d\n", - wiphy_name(local->hw.wiphy), result); - goto fail_wep; - } - /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION)) { result = ieee80211_if_add(local, "wlan%d", NULL, @@ -967,13 +967,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) return 0; -fail_wep: - rate_control_deinitialize(local); fail_rate: unregister_netdevice(local->mdev); local->mdev = NULL; fail_dev: rtnl_unlock(); + ieee80211_wep_free(local); +fail_wep: sta_info_stop(local); fail_sta_info: debugfs_hw_del(local); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 7ecda9d59d8..132938b073d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -441,6 +441,9 @@ static bool ieee80211_check_tim(struct ieee802_11_elems *elems, u16 aid) u8 index, indexn1, indexn2; struct ieee80211_tim_ie *tim = (struct ieee80211_tim_ie *) elems->tim; + if (unlikely(!tim || elems->tim_len < 4)) + return false; + aid &= 0x3fff; index = aid / 8; mask = 1 << (aid & 7); @@ -945,9 +948,13 @@ void ieee80211_beacon_loss_work(struct work_struct *work) u.mgd.beacon_loss_work); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - printk(KERN_DEBUG "%s: driver reports beacon loss from AP %pM " - "- sending probe request\n", sdata->dev->name, - sdata->u.mgd.bssid); +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG + if (net_ratelimit()) { + printk(KERN_DEBUG "%s: driver reports beacon loss from AP %pM " + "- sending probe request\n", sdata->dev->name, + sdata->u.mgd.bssid); + } +#endif ifmgd->flags |= IEEE80211_STA_PROBEREQ_POLL; ieee80211_send_probe_req(sdata, ifmgd->bssid, ifmgd->ssid, @@ -1007,9 +1014,13 @@ static void ieee80211_associated(struct ieee80211_sub_if_data *sdata) (local->hw.conf.flags & IEEE80211_CONF_PS)) && time_after(jiffies, ifmgd->last_beacon + IEEE80211_MONITORING_INTERVAL)) { - printk(KERN_DEBUG "%s: beacon loss from AP %pM " - "- sending probe request\n", - sdata->dev->name, ifmgd->bssid); +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG + if (net_ratelimit()) { + printk(KERN_DEBUG "%s: beacon loss from AP %pM " + "- sending probe request\n", + sdata->dev->name, ifmgd->bssid); + } +#endif ifmgd->flags |= IEEE80211_STA_PROBEREQ_POLL; ieee80211_send_probe_req(sdata, ifmgd->bssid, ifmgd->ssid, ifmgd->ssid_len, NULL, 0); @@ -1355,7 +1366,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, for (i = 0; i < elems.ext_supp_rates_len; i++) { int rate = (elems.ext_supp_rates[i] & 0x7f) * 5; - bool is_basic = !!(elems.supp_rates[i] & 0x80); + bool is_basic = !!(elems.ext_supp_rates[i] & 0x80); if (rate > 110) have_higher_than_11mbit = true; @@ -1902,9 +1913,17 @@ static void ieee80211_sta_work(struct work_struct *work) static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) { - if (sdata->vif.type == NL80211_IFTYPE_STATION) + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + /* + * Need to update last_beacon to avoid beacon loss + * test to trigger. + */ + sdata->u.mgd.last_beacon = jiffies; + + queue_work(sdata->local->hw.workqueue, &sdata->u.mgd.work); + } } /* interface setup */ @@ -2105,12 +2124,13 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work) struct ieee80211_local *local = container_of(work, struct ieee80211_local, dynamic_ps_enable_work); + /* XXX: using scan_sdata is completely broken! */ struct ieee80211_sub_if_data *sdata = local->scan_sdata; if (local->hw.conf.flags & IEEE80211_CONF_PS) return; - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) + if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK && sdata) ieee80211_send_nullfunc(local, sdata, 1); local->hw.conf.flags |= IEEE80211_CONF_PS; diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 02730232649..81985d27cbd 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -156,8 +156,19 @@ int __ieee80211_resume(struct ieee80211_hw *hw) case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_AP: case NL80211_IFTYPE_MESH_POINT: - WARN_ON(ieee80211_if_config(sdata, changed)); - ieee80211_bss_info_change_notify(sdata, ~0); + /* + * Driver's config_interface can fail if rfkill is + * enabled. Accommodate this return code. + * FIXME: When mac80211 has knowledge of rfkill + * state the code below can change back to: + * WARN(ieee80211_if_config(sdata, changed)); + * ieee80211_bss_info_change_notify(sdata, ~0); + */ + if (ieee80211_if_config(sdata, changed)) + printk(KERN_DEBUG "%s: failed to configure interface during resume\n", + sdata->dev->name); + else + ieee80211_bss_info_change_notify(sdata, ~0); break; case NL80211_IFTYPE_WDS: break; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 64ebe664eff..9776f73c51a 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -29,6 +29,7 @@ static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *skb, + struct ieee80211_rx_status *status, u16 mpdu_seq_num, int bar_req); /* @@ -1396,7 +1397,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) * mac80211. That also explains the __skb_push() * below. */ - align = (unsigned long)skb->data & 4; + align = (unsigned long)skb->data & 3; if (align) { if (WARN_ON(skb_headroom(skb) < 3)) { dev_kfree_skb(skb); @@ -1688,7 +1689,7 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx) /* manage reordering buffer according to requested */ /* sequence number */ rcu_read_lock(); - ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, NULL, + ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, NULL, NULL, start_seq_num, 1); rcu_read_unlock(); return RX_DROP_UNUSABLE; @@ -2293,6 +2294,7 @@ static inline u16 seq_sub(u16 sq1, u16 sq2) static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *skb, + struct ieee80211_rx_status *rxstatus, u16 mpdu_seq_num, int bar_req) { @@ -2374,6 +2376,8 @@ static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, /* put the frame in the reordering buffer */ tid_agg_rx->reorder_buf[index] = skb; + memcpy(tid_agg_rx->reorder_buf[index]->cb, rxstatus, + sizeof(*rxstatus)); tid_agg_rx->stored_mpdu_num++; /* release the buffer until next missing frame */ index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) @@ -2399,7 +2403,8 @@ static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, } static u8 ieee80211_rx_reorder_ampdu(struct ieee80211_local *local, - struct sk_buff *skb) + struct sk_buff *skb, + struct ieee80211_rx_status *status) { struct ieee80211_hw *hw = &local->hw; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -2448,7 +2453,7 @@ static u8 ieee80211_rx_reorder_ampdu(struct ieee80211_local *local, /* according to mpdu sequence number deal with reordering buffer */ mpdu_seq_num = (sc & IEEE80211_SCTL_SEQ) >> 4; - ret = ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, skb, + ret = ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, skb, status, mpdu_seq_num, 0); end_reorder: return ret; @@ -2512,7 +2517,7 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb, return; } - if (!ieee80211_rx_reorder_ampdu(local, skb)) + if (!ieee80211_rx_reorder_ampdu(local, skb, status)) __ieee80211_rx_handle_packet(hw, skb, status, rate); rcu_read_unlock(); diff --git a/net/mac80211/wext.c b/net/mac80211/wext.c index deb4ecec122..959aa8379cc 100644 --- a/net/mac80211/wext.c +++ b/net/mac80211/wext.c @@ -417,6 +417,7 @@ static int ieee80211_ioctl_siwtxpower(struct net_device *dev, { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_channel* chan = local->hw.conf.channel; + bool reconf = false; u32 reconf_flags = 0; int new_power_level; @@ -427,14 +428,38 @@ static int ieee80211_ioctl_siwtxpower(struct net_device *dev, if (!chan) return -EINVAL; - if (data->txpower.fixed) - new_power_level = min(data->txpower.value, chan->max_power); - else /* Automatic power level setting */ - new_power_level = chan->max_power; + /* only change when not disabling */ + if (!data->txpower.disabled) { + if (data->txpower.fixed) { + if (data->txpower.value < 0) + return -EINVAL; + new_power_level = data->txpower.value; + /* + * Debatable, but we cannot do a fixed power + * level above the regulatory constraint. + * Use "iwconfig wlan0 txpower 15dBm" instead. + */ + if (new_power_level > chan->max_power) + return -EINVAL; + } else { + /* + * Automatic power level setting, max being the value + * passed in from userland. + */ + if (data->txpower.value < 0) + new_power_level = -1; + else + new_power_level = data->txpower.value; + } + + reconf = true; - local->user_power_level = new_power_level; - if (local->hw.conf.power_level != new_power_level) - reconf_flags |= IEEE80211_CONF_CHANGE_POWER; + /* + * ieee80211_hw_config() will limit to the channel's + * max power and possibly power constraint from AP. + */ + local->user_power_level = new_power_level; + } if (local->hw.conf.radio_enabled != !(data->txpower.disabled)) { local->hw.conf.radio_enabled = !(data->txpower.disabled); @@ -442,7 +467,7 @@ static int ieee80211_ioctl_siwtxpower(struct net_device *dev, ieee80211_led_radio(local, local->hw.conf.radio_enabled); } - if (reconf_flags) + if (reconf || reconf_flags) ieee80211_hw_config(local, reconf_flags); return 0; @@ -530,7 +555,7 @@ static int ieee80211_ioctl_giwfrag(struct net_device *dev, struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); frag->value = local->fragmentation_threshold; - frag->disabled = (frag->value >= IEEE80211_MAX_RTS_THRESHOLD); + frag->disabled = (frag->value >= IEEE80211_MAX_FRAG_THRESHOLD); frag->fixed = 1; return 0; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 2c967e4f706..cb3ad741ebf 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -52,7 +52,7 @@ config NF_CT_ACCT Please note that currently this option only sets a default state. You may change it at boot time with nf_conntrack.acct=0/1 kernel - paramater or by loading the nf_conntrack module with acct=0/1. + parameter or by loading the nf_conntrack module with acct=0/1. You may also disable/enable it on a running system with: sysctl net.netfilter.nf_conntrack_acct=0/1 @@ -275,6 +275,8 @@ config NF_CT_NETLINK help This option enables support for a netlink-based userspace interface +endif # NF_CONNTRACK + # transparent proxy support config NETFILTER_TPROXY tristate "Transparent proxying support (EXPERIMENTAL)" @@ -290,8 +292,6 @@ config NETFILTER_TPROXY To compile it as a module, choose M here. If unsure, say N. -endif # NF_CONNTRACK - config NETFILTER_XTABLES tristate "Netfilter Xtables support (required for ip_tables)" default m if NETFILTER_ADVANCED=n @@ -374,7 +374,7 @@ config NETFILTER_XT_TARGET_HL config NETFILTER_XT_TARGET_LED tristate '"LED" target support' - depends on LEDS_CLASS && LED_TRIGGERS + depends on LEDS_CLASS && LEDS_TRIGGERS depends on NETFILTER_ADVANCED help This option adds a `LED' target, which allows you to blink LEDs in @@ -837,6 +837,7 @@ config NETFILTER_XT_MATCH_SOCKET depends on NETFILTER_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED + depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DEFRAG_IPV4 help This option adds a `socket' match, which can be used to match diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 3940f996a2e..afde8f99164 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -372,7 +372,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) struct net *net = nf_ct_exp_net(expect); struct hlist_node *n; unsigned int h; - int ret = 0; + int ret = 1; if (!master_help->helper) { ret = -ESHUTDOWN; @@ -412,41 +412,23 @@ out: return ret; } -int nf_ct_expect_related(struct nf_conntrack_expect *expect) +int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, + u32 pid, int report) { int ret; spin_lock_bh(&nf_conntrack_lock); ret = __nf_ct_expect_check(expect); - if (ret < 0) + if (ret <= 0) goto out; + ret = 0; nf_ct_expect_insert(expect); - atomic_inc(&expect->use); - spin_unlock_bh(&nf_conntrack_lock); - nf_ct_expect_event(IPEXP_NEW, expect); - nf_ct_expect_put(expect); - return ret; -out: spin_unlock_bh(&nf_conntrack_lock); + nf_ct_expect_event_report(IPEXP_NEW, expect, pid, report); return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_expect_related); - -int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, - u32 pid, int report) -{ - int ret; - - spin_lock_bh(&nf_conntrack_lock); - ret = __nf_ct_expect_check(expect); - if (ret < 0) - goto out; - nf_ct_expect_insert(expect); out: spin_unlock_bh(&nf_conntrack_lock); - if (ret == 0) - nf_ct_expect_event_report(IPEXP_NEW, expect, pid, report); return ret; } EXPORT_SYMBOL_GPL(nf_ct_expect_related_report); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 30b8e9009f9..0fa5a422959 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -176,7 +176,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, } /* Get rid of expecteds, set helpers to NULL. */ - hlist_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode) + hlist_nulls_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode) unhelp(h, me); for (i = 0; i < nf_conntrack_htable_size; i++) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 409c8be58e7..8bd98c84f77 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -66,7 +66,7 @@ static const char *const dccprotos[] = { * ad_beg_p returns pointer to first byte of addr data * ad_end_p returns pointer to last byte of addr data */ -static int parse_dcc(char *data, const char *data_end, u_int32_t *ip, +static int parse_dcc(char *data, const char *data_end, __be32 *ip, u_int16_t *port, char **ad_beg_p, char **ad_end_p) { char *tmp; @@ -85,7 +85,7 @@ static int parse_dcc(char *data, const char *data_end, u_int32_t *ip, return -1; *ad_beg_p = data; - *ip = simple_strtoul(data, &data, 10); + *ip = cpu_to_be32(simple_strtoul(data, &data, 10)); /* skip blanks between ip and port */ while (*data == ' ') { @@ -112,7 +112,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, int dir = CTINFO2DIR(ctinfo); struct nf_conntrack_expect *exp; struct nf_conntrack_tuple *tuple; - u_int32_t dcc_ip; + __be32 dcc_ip; u_int16_t dcc_port; __be16 port; int i, ret = NF_ACCEPT; @@ -177,13 +177,14 @@ static int help(struct sk_buff *skb, unsigned int protoff, pr_debug("unable to parse dcc command\n"); continue; } - pr_debug("DCC bound ip/port: %u.%u.%u.%u:%u\n", - HIPQUAD(dcc_ip), dcc_port); + + pr_debug("DCC bound ip/port: %pI4:%u\n", + &dcc_ip, dcc_port); /* dcc_ip can be the internal OR external (NAT'ed) IP */ tuple = &ct->tuplehash[dir].tuple; - if (tuple->src.u3.ip != htonl(dcc_ip) && - tuple->dst.u3.ip != htonl(dcc_ip)) { + if (tuple->src.u3.ip != dcc_ip && + tuple->dst.u3.ip != dcc_ip) { if (net_ratelimit()) printk(KERN_WARNING "Forged DCC command from %pI4: %pI4:%u\n", diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c6439c77953..f13fc57e1ec 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -512,7 +512,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, skb = ctnetlink_alloc_skb(tuple(ct, IP_CT_DIR_ORIGINAL), GFP_ATOMIC); if (!skb) - return NOTIFY_DONE; + goto errout; b = skb->tail; @@ -591,8 +591,9 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, nla_put_failure: rcu_read_unlock(); nlmsg_failure: - nfnetlink_set_err(0, group, -ENOBUFS); kfree_skb(skb); +errout: + nfnetlink_set_err(0, group, -ENOBUFS); return NOTIFY_DONE; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ @@ -987,7 +988,7 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nlattr *cda[]) { struct nf_conntrack_helper *helper; struct nf_conn_help *help = nfct_help(ct); - char *helpname; + char *helpname = NULL; int err; /* don't change helper of sibling connections */ @@ -1230,7 +1231,7 @@ ctnetlink_create_conntrack(struct nlattr *cda[], rcu_read_lock(); if (cda[CTA_HELP]) { - char *helpname; + char *helpname = NULL; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname); if (err < 0) @@ -1564,7 +1565,7 @@ static int ctnetlink_expect_event(struct notifier_block *this, skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb) - return NOTIFY_DONE; + goto errout; b = skb->tail; @@ -1589,8 +1590,9 @@ static int ctnetlink_expect_event(struct notifier_block *this, nla_put_failure: rcu_read_unlock(); nlmsg_failure: - nfnetlink_set_err(0, 0, -ENOBUFS); kfree_skb(skb); +errout: + nfnetlink_set_err(0, 0, -ENOBUFS); return NOTIFY_DONE; } #endif diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 50dac8dbe7d..8e757dd5339 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -633,6 +633,8 @@ static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, if (!nest_parms) goto nla_put_failure; NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state); + NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_ROLE, + ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]); nla_nest_end(skb, nest_parms); read_unlock_bh(&dccp_lock); return 0; @@ -644,6 +646,7 @@ nla_put_failure: static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = { [CTA_PROTOINFO_DCCP_STATE] = { .type = NLA_U8 }, + [CTA_PROTOINFO_DCCP_ROLE] = { .type = NLA_U8 }, }; static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) @@ -661,11 +664,21 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) return err; if (!tb[CTA_PROTOINFO_DCCP_STATE] || - nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) + !tb[CTA_PROTOINFO_DCCP_ROLE] || + nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) > CT_DCCP_ROLE_MAX || + nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) { return -EINVAL; + } write_lock_bh(&dccp_lock); ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]); + if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) { + ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; + ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER; + } else { + ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER; + ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT; + } write_unlock_bh(&dccp_lock); return 0; } @@ -777,6 +790,7 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { .print_conntrack = dccp_print_conntrack, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nlattr = dccp_to_nlattr, + .nlattr_size = dccp_nlattr_size, .from_nlattr = nlattr_to_dccp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 4614696c1b8..0badedc542d 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -204,6 +204,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = .error = udplite_error, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, + .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 8bb998fe098..beb37311e1a 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -36,10 +36,14 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger) int nf_log_register(u_int8_t pf, struct nf_logger *logger) { const struct nf_logger *llog; + int i; if (pf >= ARRAY_SIZE(nf_loggers)) return -EINVAL; + for (i = 0; i < ARRAY_SIZE(logger->list); i++) + INIT_LIST_HEAD(&logger->list[i]); + mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 2785d66a7e3..b8ab37ad7ed 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -203,7 +203,7 @@ static int __init nfnetlink_init(void) nfnetlink_rcv, NULL, THIS_MODULE); if (!nfnl) { printk(KERN_ERR "cannot initialize nfnetlink!\n"); - return -1; + return -ENOMEM; } return 0; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 509a95621f9..150e5cf62f8 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -625,20 +625,6 @@ void xt_free_table_info(struct xt_table_info *info) } EXPORT_SYMBOL(xt_free_table_info); -void xt_table_entry_swap_rcu(struct xt_table_info *oldinfo, - struct xt_table_info *newinfo) -{ - unsigned int cpu; - - for_each_possible_cpu(cpu) { - void *p = oldinfo->entries[cpu]; - rcu_assign_pointer(oldinfo->entries[cpu], newinfo->entries[cpu]); - newinfo->entries[cpu] = p; - } - -} -EXPORT_SYMBOL_GPL(xt_table_entry_swap_rcu); - /* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) @@ -676,32 +662,43 @@ void xt_compat_unlock(u_int8_t af) EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif +DEFINE_PER_CPU(struct xt_info_lock, xt_info_locks); +EXPORT_PER_CPU_SYMBOL_GPL(xt_info_locks); + + struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { - struct xt_table_info *oldinfo, *private; + struct xt_table_info *private; /* Do the substitution. */ - mutex_lock(&table->lock); + local_bh_disable(); private = table->private; + /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { duprintf("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); - mutex_unlock(&table->lock); + local_bh_enable(); *error = -EAGAIN; return NULL; } - oldinfo = private; - rcu_assign_pointer(table->private, newinfo); - newinfo->initial_entries = oldinfo->initial_entries; - mutex_unlock(&table->lock); - synchronize_net(); - return oldinfo; + table->private = newinfo; + newinfo->initial_entries = private->initial_entries; + + /* + * Even though table entries have now been swapped, other CPU's + * may still be using the old entries. This is okay, because + * resynchronization happens because of the locking done + * during the get_counters() routine. + */ + local_bh_enable(); + + return private; } EXPORT_SYMBOL_GPL(xt_replace_table); @@ -734,7 +731,6 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table *table, /* Simplifies replace_table code. */ table->private = bootstrap; - mutex_init(&table->lock); if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; @@ -1147,7 +1143,14 @@ static struct pernet_operations xt_net_ops = { static int __init xt_init(void) { - int i, rv; + unsigned int i; + int rv; + + for_each_possible_cpu(i) { + struct xt_info_lock *lock = &per_cpu(xt_info_locks, i); + spin_lock_init(&lock->lock); + lock->readers = 0; + } xt = kmalloc(sizeof(struct xt_af) * NFPROTO_NUMPROTO, GFP_KERNEL); if (!xt) diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index ad5bd890e4e..6c4847662b8 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -58,6 +58,13 @@ xt_cluster_hash(const struct nf_conn *ct, } static inline bool +xt_cluster_ipv6_is_multicast(const struct in6_addr *addr) +{ + __be32 st = addr->s6_addr32[0]; + return ((st & htonl(0xFF000000)) == htonl(0xFF000000)); +} + +static inline bool xt_cluster_is_multicast_addr(const struct sk_buff *skb, u_int8_t family) { bool is_multicast = false; @@ -67,8 +74,8 @@ xt_cluster_is_multicast_addr(const struct sk_buff *skb, u_int8_t family) is_multicast = ipv4_is_multicast(ip_hdr(skb)->daddr); break; case NFPROTO_IPV6: - is_multicast = ipv6_addr_type(&ipv6_hdr(skb)->daddr) & - IPV6_ADDR_MULTICAST; + is_multicast = + xt_cluster_ipv6_is_multicast(&ipv6_hdr(skb)->daddr); break; default: WARN_ON(1); diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 791e030ea90..eb0ceb84652 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -474,7 +474,7 @@ static ssize_t recent_old_proc_write(struct file *file, struct recent_table *t = pde->data; struct recent_entry *e; char buf[sizeof("+255.255.255.255")], *c = buf; - __be32 addr; + union nf_inet_addr addr = {}; int add; if (size > sizeof(buf)) @@ -506,14 +506,13 @@ static ssize_t recent_old_proc_write(struct file *file, add = 1; break; } - addr = in_aton(c); + addr.ip = in_aton(c); spin_lock_bh(&recent_lock); - e = recent_entry_lookup(t, (const void *)&addr, NFPROTO_IPV4, 0); + e = recent_entry_lookup(t, &addr, NFPROTO_IPV4, 0); if (e == NULL) { if (add) - recent_entry_init(t, (const void *)&addr, - NFPROTO_IPV4, 0); + recent_entry_init(t, &addr, NFPROTO_IPV4, 0); } else { if (add) recent_entry_update(t, e); diff --git a/net/netlabel/netlabel_addrlist.c b/net/netlabel/netlabel_addrlist.c index 834c6eb7f48..c0519139679 100644 --- a/net/netlabel/netlabel_addrlist.c +++ b/net/netlabel/netlabel_addrlist.c @@ -256,13 +256,11 @@ struct netlbl_af4list *netlbl_af4list_remove(__be32 addr, __be32 mask, { struct netlbl_af4list *entry; - entry = netlbl_af4list_search(addr, head); - if (entry != NULL && entry->addr == addr && entry->mask == mask) { - netlbl_af4list_remove_entry(entry); - return entry; - } - - return NULL; + entry = netlbl_af4list_search_exact(addr, mask, head); + if (entry == NULL) + return NULL; + netlbl_af4list_remove_entry(entry); + return entry; } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) @@ -299,15 +297,11 @@ struct netlbl_af6list *netlbl_af6list_remove(const struct in6_addr *addr, { struct netlbl_af6list *entry; - entry = netlbl_af6list_search(addr, head); - if (entry != NULL && - ipv6_addr_equal(&entry->addr, addr) && - ipv6_addr_equal(&entry->mask, mask)) { - netlbl_af6list_remove_entry(entry); - return entry; - } - - return NULL; + entry = netlbl_af6list_search_exact(addr, mask, head); + if (entry == NULL) + return NULL; + netlbl_af6list_remove_entry(entry); + return entry; } #endif /* IPv6 */ diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 4e705f87969..3be0e016ab7 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1084,8 +1084,10 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, /* Build a packet - the conventional user limit is 236 bytes. We can do ludicrously large NetROM frames but must not overflow */ - if (len > 65536) - return -EMSGSIZE; + if (len > 65536) { + err = -EMSGSIZE; + goto out; + } SOCK_DEBUG(sk, "NET/ROM: sendto: building packet.\n"); size = len + NR_NETWORK_LEN + NR_TRANSPORT_LEN; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 74776de523e..f546e81acc4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1758,8 +1758,9 @@ static void free_pg_vec(char **pg_vec, unsigned int order, unsigned int len) static inline char *alloc_one_pg_vec_page(unsigned long order) { - return (char *) __get_free_pages(GFP_KERNEL | __GFP_COMP | __GFP_ZERO, - order); + gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN; + + return (char *) __get_free_pages(gfp_flags, order); } static char **alloc_pg_vec(struct tpacket_req *req, int order) diff --git a/net/phonet/Kconfig b/net/phonet/Kconfig index 51a5669573f..6ec7d55b176 100644 --- a/net/phonet/Kconfig +++ b/net/phonet/Kconfig @@ -6,7 +6,7 @@ config PHONET tristate "Phonet protocols family" help The Phone Network protocol (PhoNet) is a packet-oriented - communication protocol developped by Nokia for use with its modems. + communication protocol developed by Nokia for use with its modems. This is required for Maemo to use cellular data connectivity (if supported). It can also be used to control Nokia phones diff --git a/net/rds/ib.c b/net/rds/ib.c index 06a7b798d9a..4933b380985 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -51,6 +51,7 @@ MODULE_PARM_DESC(fmr_message_size, " Max size of a RDMA transfer"); struct list_head rds_ib_devices; +/* NOTE: if also grabbing ibdev lock, grab this first */ DEFINE_SPINLOCK(ib_nodev_conns_lock); LIST_HEAD(ib_nodev_conns); @@ -137,7 +138,7 @@ void rds_ib_remove_one(struct ib_device *device) kfree(i_ipaddr); } - rds_ib_remove_conns(rds_ibdev); + rds_ib_destroy_conns(rds_ibdev); if (rds_ibdev->mr_pool) rds_ib_destroy_mr_pool(rds_ibdev->mr_pool); @@ -249,7 +250,7 @@ static int rds_ib_laddr_check(__be32 addr) void rds_ib_exit(void) { rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); - rds_ib_remove_nodev_conns(); + rds_ib_destroy_nodev_conns(); ib_unregister_client(&rds_ib_client); rds_ib_sysctl_exit(); rds_ib_recv_exit(); diff --git a/net/rds/ib.h b/net/rds/ib.h index 8be563a1363..069206cae73 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -108,7 +108,12 @@ struct rds_ib_connection { /* sending acks */ unsigned long i_ack_flags; +#ifdef KERNEL_HAS_ATOMIC64 + atomic64_t i_ack_next; /* next ACK to send */ +#else + spinlock_t i_ack_lock; /* protect i_ack_next */ u64 i_ack_next; /* next ACK to send */ +#endif struct rds_header *i_ack; struct ib_send_wr i_ack_wr; struct ib_sge i_ack_sge; @@ -267,9 +272,17 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, /* ib_rdma.c */ int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr); -int rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn); -void rds_ib_remove_nodev_conns(void); -void rds_ib_remove_conns(struct rds_ib_device *rds_ibdev); +void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn); +void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn); +void __rds_ib_destroy_conns(struct list_head *list, spinlock_t *list_lock); +static inline void rds_ib_destroy_nodev_conns(void) +{ + __rds_ib_destroy_conns(&ib_nodev_conns, &ib_nodev_conns_lock); +} +static inline void rds_ib_destroy_conns(struct rds_ib_device *rds_ibdev) +{ + __rds_ib_destroy_conns(&rds_ibdev->conn_list, &rds_ibdev->spinlock); +} struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *); void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo); void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *); @@ -355,13 +368,4 @@ rds_ib_data_sge(struct rds_ib_connection *ic, struct ib_sge *sge) return &sge[1]; } -static inline void rds_ib_set_64bit(u64 *ptr, u64 val) -{ -#if BITS_PER_LONG == 64 - *ptr = val; -#else - set_64bit(ptr, val); -#endif -} - #endif diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 0532237bd12..f8e40e1a603 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -126,9 +126,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even err = rds_ib_update_ipaddr(rds_ibdev, conn->c_laddr); if (err) printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n", err); - err = rds_ib_add_conn(rds_ibdev, conn); - if (err) - printk(KERN_ERR "rds_ib_add_conn failed (%d)\n", err); + rds_ib_add_conn(rds_ibdev, conn); /* If the peer gave us the last packet it saw, process this as if * we had received a regular ACK. */ @@ -616,18 +614,8 @@ void rds_ib_conn_shutdown(struct rds_connection *conn) /* * Move connection back to the nodev list. */ - if (ic->rds_ibdev) { - - spin_lock_irq(&ic->rds_ibdev->spinlock); - BUG_ON(list_empty(&ic->ib_node)); - list_del(&ic->ib_node); - spin_unlock_irq(&ic->rds_ibdev->spinlock); - - spin_lock_irq(&ib_nodev_conns_lock); - list_add_tail(&ic->ib_node, &ib_nodev_conns); - spin_unlock_irq(&ib_nodev_conns_lock); - ic->rds_ibdev = NULL; - } + if (ic->rds_ibdev) + rds_ib_remove_conn(ic->rds_ibdev, conn); ic->i_cm_id = NULL; ic->i_pd = NULL; @@ -648,7 +636,11 @@ void rds_ib_conn_shutdown(struct rds_connection *conn) /* Clear the ACK state */ clear_bit(IB_ACK_IN_FLIGHT, &ic->i_ack_flags); - rds_ib_set_64bit(&ic->i_ack_next, 0); +#ifdef KERNEL_HAS_ATOMIC64 + atomic64_set(&ic->i_ack_next, 0); +#else + ic->i_ack_next = 0; +#endif ic->i_ack_recv = 0; /* Clear flow control state */ @@ -681,6 +673,9 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) INIT_LIST_HEAD(&ic->ib_node); mutex_init(&ic->i_recv_mutex); +#ifndef KERNEL_HAS_ATOMIC64 + spin_lock_init(&ic->i_ack_lock); +#endif /* * rds_ib_conn_shutdown() waits for these to be emptied so they @@ -701,11 +696,27 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) return 0; } +/* + * Free a connection. Connection must be shut down and not set for reconnect. + */ void rds_ib_conn_free(void *arg) { struct rds_ib_connection *ic = arg; + spinlock_t *lock_ptr; + rdsdebug("ic %p\n", ic); + + /* + * Conn is either on a dev's list or on the nodev list. + * A race with shutdown() or connect() would cause problems + * (since rds_ibdev would change) but that should never happen. + */ + lock_ptr = ic->rds_ibdev ? &ic->rds_ibdev->spinlock : &ib_nodev_conns_lock; + + spin_lock_irq(lock_ptr); list_del(&ic->ib_node); + spin_unlock_irq(lock_ptr); + kfree(ic); } diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 69a6289ed67..81033af9302 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -139,7 +139,7 @@ int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr) return rds_ib_add_ipaddr(rds_ibdev, ipaddr); } -int rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn) +void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn) { struct rds_ib_connection *ic = conn->c_transport_data; @@ -148,45 +148,44 @@ int rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn BUG_ON(list_empty(&ib_nodev_conns)); BUG_ON(list_empty(&ic->ib_node)); list_del(&ic->ib_node); - spin_unlock_irq(&ib_nodev_conns_lock); spin_lock_irq(&rds_ibdev->spinlock); list_add_tail(&ic->ib_node, &rds_ibdev->conn_list); spin_unlock_irq(&rds_ibdev->spinlock); + spin_unlock_irq(&ib_nodev_conns_lock); ic->rds_ibdev = rds_ibdev; - - return 0; } -void rds_ib_remove_nodev_conns(void) +void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn) { - struct rds_ib_connection *ic, *_ic; - LIST_HEAD(tmp_list); + struct rds_ib_connection *ic = conn->c_transport_data; - /* avoid calling conn_destroy with irqs off */ - spin_lock_irq(&ib_nodev_conns_lock); - list_splice(&ib_nodev_conns, &tmp_list); - INIT_LIST_HEAD(&ib_nodev_conns); - spin_unlock_irq(&ib_nodev_conns_lock); + /* place conn on nodev_conns_list */ + spin_lock(&ib_nodev_conns_lock); - list_for_each_entry_safe(ic, _ic, &tmp_list, ib_node) { - if (ic->conn->c_passive) - rds_conn_destroy(ic->conn->c_passive); - rds_conn_destroy(ic->conn); - } + spin_lock_irq(&rds_ibdev->spinlock); + BUG_ON(list_empty(&ic->ib_node)); + list_del(&ic->ib_node); + spin_unlock_irq(&rds_ibdev->spinlock); + + list_add_tail(&ic->ib_node, &ib_nodev_conns); + + spin_unlock(&ib_nodev_conns_lock); + + ic->rds_ibdev = NULL; } -void rds_ib_remove_conns(struct rds_ib_device *rds_ibdev) +void __rds_ib_destroy_conns(struct list_head *list, spinlock_t *list_lock) { struct rds_ib_connection *ic, *_ic; LIST_HEAD(tmp_list); /* avoid calling conn_destroy with irqs off */ - spin_lock_irq(&rds_ibdev->spinlock); - list_splice(&rds_ibdev->conn_list, &tmp_list); - INIT_LIST_HEAD(&rds_ibdev->conn_list); - spin_unlock_irq(&rds_ibdev->spinlock); + spin_lock_irq(list_lock); + list_splice(list, &tmp_list); + INIT_LIST_HEAD(list); + spin_unlock_irq(list_lock); list_for_each_entry_safe(ic, _ic, &tmp_list, ib_node) { if (ic->conn->c_passive) diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 5061b550216..36d931573ff 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -395,10 +395,37 @@ void rds_ib_recv_init_ack(struct rds_ib_connection *ic) * room for it beyond the ring size. Send completion notices its special * wr_id and avoids working with the ring in that case. */ +#ifndef KERNEL_HAS_ATOMIC64 static void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq, int ack_required) { - rds_ib_set_64bit(&ic->i_ack_next, seq); + unsigned long flags; + + spin_lock_irqsave(&ic->i_ack_lock, flags); + ic->i_ack_next = seq; + if (ack_required) + set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); + spin_unlock_irqrestore(&ic->i_ack_lock, flags); +} + +static u64 rds_ib_get_ack(struct rds_ib_connection *ic) +{ + unsigned long flags; + u64 seq; + + clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); + + spin_lock_irqsave(&ic->i_ack_lock, flags); + seq = ic->i_ack_next; + spin_unlock_irqrestore(&ic->i_ack_lock, flags); + + return seq; +} +#else +static void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq, + int ack_required) +{ + atomic64_set(&ic->i_ack_next, seq); if (ack_required) { smp_mb__before_clear_bit(); set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); @@ -410,8 +437,10 @@ static u64 rds_ib_get_ack(struct rds_ib_connection *ic) clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); smp_mb__after_clear_bit(); - return ic->i_ack_next; + return atomic64_read(&ic->i_ack_next); } +#endif + static void rds_ib_send_ack(struct rds_ib_connection *ic, unsigned int adv_credits) { @@ -464,6 +493,10 @@ static void rds_ib_send_ack(struct rds_ib_connection *ic, unsigned int adv_credi * - i_ack_next, which is the last sequence number we received * * Potentially, send queue and receive queue handlers can run concurrently. + * It would be nice to not have to use a spinlock to synchronize things, + * but the one problem that rules this out is that 64bit updates are + * not atomic on all platforms. Things would be a lot simpler if + * we had atomic64 or maybe cmpxchg64 everywhere. * * Reconnecting complicates this picture just slightly. When we * reconnect, we may be seeing duplicate packets. The peer diff --git a/net/rds/iw.c b/net/rds/iw.c index 1b56905c4c0..b732efb5b63 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -51,6 +51,7 @@ MODULE_PARM_DESC(fastreg_message_size, " Max size of a RDMA transfer (fastreg MR struct list_head rds_iw_devices; +/* NOTE: if also grabbing iwdev lock, grab this first */ DEFINE_SPINLOCK(iw_nodev_conns_lock); LIST_HEAD(iw_nodev_conns); @@ -145,7 +146,7 @@ void rds_iw_remove_one(struct ib_device *device) } spin_unlock_irq(&rds_iwdev->spinlock); - rds_iw_remove_conns(rds_iwdev); + rds_iw_destroy_conns(rds_iwdev); if (rds_iwdev->mr_pool) rds_iw_destroy_mr_pool(rds_iwdev->mr_pool); @@ -258,7 +259,7 @@ static int rds_iw_laddr_check(__be32 addr) void rds_iw_exit(void) { rds_info_deregister_func(RDS_INFO_IWARP_CONNECTIONS, rds_iw_ic_info); - rds_iw_remove_nodev_conns(); + rds_iw_destroy_nodev_conns(); ib_unregister_client(&rds_iw_client); rds_iw_sysctl_exit(); rds_iw_recv_exit(); diff --git a/net/rds/iw.h b/net/rds/iw.h index 0ddda34f2a1..b4fb2725289 100644 --- a/net/rds/iw.h +++ b/net/rds/iw.h @@ -131,7 +131,12 @@ struct rds_iw_connection { /* sending acks */ unsigned long i_ack_flags; +#ifdef KERNEL_HAS_ATOMIC64 + atomic64_t i_ack_next; /* next ACK to send */ +#else + spinlock_t i_ack_lock; /* protect i_ack_next */ u64 i_ack_next; /* next ACK to send */ +#endif struct rds_header *i_ack; struct ib_send_wr i_ack_wr; struct ib_sge i_ack_sge; @@ -294,9 +299,17 @@ void rds_iw_cm_connect_complete(struct rds_connection *conn, /* ib_rdma.c */ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_id); -int rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn); -void rds_iw_remove_nodev_conns(void); -void rds_iw_remove_conns(struct rds_iw_device *rds_iwdev); +void rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn); +void rds_iw_remove_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn); +void __rds_iw_destroy_conns(struct list_head *list, spinlock_t *list_lock); +static inline void rds_iw_destroy_nodev_conns(void) +{ + __rds_iw_destroy_conns(&iw_nodev_conns, &iw_nodev_conns_lock); +} +static inline void rds_iw_destroy_conns(struct rds_iw_device *rds_iwdev) +{ + __rds_iw_destroy_conns(&rds_iwdev->conn_list, &rds_iwdev->spinlock); +} struct rds_iw_mr_pool *rds_iw_create_mr_pool(struct rds_iw_device *); void rds_iw_get_mr_info(struct rds_iw_device *rds_iwdev, struct rds_info_rdma_connection *iinfo); void rds_iw_destroy_mr_pool(struct rds_iw_mr_pool *); @@ -383,13 +396,4 @@ rds_iw_data_sge(struct rds_iw_connection *ic, struct ib_sge *sge) return &sge[1]; } -static inline void rds_iw_set_64bit(u64 *ptr, u64 val) -{ -#if BITS_PER_LONG == 64 - *ptr = val; -#else - set_64bit(ptr, val); -#endif -} - #endif diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c index 57ecb3d4b8a..a416b0d492b 100644 --- a/net/rds/iw_cm.c +++ b/net/rds/iw_cm.c @@ -86,9 +86,7 @@ void rds_iw_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even err = rds_iw_update_cm_id(rds_iwdev, ic->i_cm_id); if (err) printk(KERN_ERR "rds_iw_update_ipaddr failed (%d)\n", err); - err = rds_iw_add_conn(rds_iwdev, conn); - if (err) - printk(KERN_ERR "rds_iw_add_conn failed (%d)\n", err); + rds_iw_add_conn(rds_iwdev, conn); /* If the peer gave us the last packet it saw, process this as if * we had received a regular ACK. */ @@ -637,19 +635,8 @@ void rds_iw_conn_shutdown(struct rds_connection *conn) * Move connection back to the nodev list. * Remove cm_id from the device cm_id list. */ - if (ic->rds_iwdev) { - - spin_lock_irq(&ic->rds_iwdev->spinlock); - BUG_ON(list_empty(&ic->iw_node)); - list_del(&ic->iw_node); - spin_unlock_irq(&ic->rds_iwdev->spinlock); - - spin_lock_irq(&iw_nodev_conns_lock); - list_add_tail(&ic->iw_node, &iw_nodev_conns); - spin_unlock_irq(&iw_nodev_conns_lock); - rds_iw_remove_cm_id(ic->rds_iwdev, ic->i_cm_id); - ic->rds_iwdev = NULL; - } + if (ic->rds_iwdev) + rds_iw_remove_conn(ic->rds_iwdev, conn); rdma_destroy_id(ic->i_cm_id); @@ -672,7 +659,11 @@ void rds_iw_conn_shutdown(struct rds_connection *conn) /* Clear the ACK state */ clear_bit(IB_ACK_IN_FLIGHT, &ic->i_ack_flags); - rds_iw_set_64bit(&ic->i_ack_next, 0); +#ifdef KERNEL_HAS_ATOMIC64 + atomic64_set(&ic->i_ack_next, 0); +#else + ic->i_ack_next = 0; +#endif ic->i_ack_recv = 0; /* Clear flow control state */ @@ -706,6 +697,9 @@ int rds_iw_conn_alloc(struct rds_connection *conn, gfp_t gfp) INIT_LIST_HEAD(&ic->iw_node); mutex_init(&ic->i_recv_mutex); +#ifndef KERNEL_HAS_ATOMIC64 + spin_lock_init(&ic->i_ack_lock); +#endif /* * rds_iw_conn_shutdown() waits for these to be emptied so they @@ -726,11 +720,27 @@ int rds_iw_conn_alloc(struct rds_connection *conn, gfp_t gfp) return 0; } +/* + * Free a connection. Connection must be shut down and not set for reconnect. + */ void rds_iw_conn_free(void *arg) { struct rds_iw_connection *ic = arg; + spinlock_t *lock_ptr; + rdsdebug("ic %p\n", ic); + + /* + * Conn is either on a dev's list or on the nodev list. + * A race with shutdown() or connect() would cause problems + * (since rds_iwdev would change) but that should never happen. + */ + lock_ptr = ic->rds_iwdev ? &ic->rds_iwdev->spinlock : &iw_nodev_conns_lock; + + spin_lock_irq(lock_ptr); list_del(&ic->iw_node); + spin_unlock_irq(lock_ptr); + kfree(ic); } diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index 1c02a8f952d..dcdb37da80f 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -196,7 +196,7 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i return rds_iw_add_cm_id(rds_iwdev, cm_id); } -int rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn) +void rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn) { struct rds_iw_connection *ic = conn->c_transport_data; @@ -205,45 +205,45 @@ int rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn BUG_ON(list_empty(&iw_nodev_conns)); BUG_ON(list_empty(&ic->iw_node)); list_del(&ic->iw_node); - spin_unlock_irq(&iw_nodev_conns_lock); spin_lock_irq(&rds_iwdev->spinlock); list_add_tail(&ic->iw_node, &rds_iwdev->conn_list); spin_unlock_irq(&rds_iwdev->spinlock); + spin_unlock_irq(&iw_nodev_conns_lock); ic->rds_iwdev = rds_iwdev; - - return 0; } -void rds_iw_remove_nodev_conns(void) +void rds_iw_remove_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn) { - struct rds_iw_connection *ic, *_ic; - LIST_HEAD(tmp_list); + struct rds_iw_connection *ic = conn->c_transport_data; - /* avoid calling conn_destroy with irqs off */ - spin_lock_irq(&iw_nodev_conns_lock); - list_splice(&iw_nodev_conns, &tmp_list); - INIT_LIST_HEAD(&iw_nodev_conns); - spin_unlock_irq(&iw_nodev_conns_lock); + /* place conn on nodev_conns_list */ + spin_lock(&iw_nodev_conns_lock); - list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node) { - if (ic->conn->c_passive) - rds_conn_destroy(ic->conn->c_passive); - rds_conn_destroy(ic->conn); - } + spin_lock_irq(&rds_iwdev->spinlock); + BUG_ON(list_empty(&ic->iw_node)); + list_del(&ic->iw_node); + spin_unlock_irq(&rds_iwdev->spinlock); + + list_add_tail(&ic->iw_node, &iw_nodev_conns); + + spin_unlock(&iw_nodev_conns_lock); + + rds_iw_remove_cm_id(ic->rds_iwdev, ic->i_cm_id); + ic->rds_iwdev = NULL; } -void rds_iw_remove_conns(struct rds_iw_device *rds_iwdev) +void __rds_iw_destroy_conns(struct list_head *list, spinlock_t *list_lock) { struct rds_iw_connection *ic, *_ic; LIST_HEAD(tmp_list); /* avoid calling conn_destroy with irqs off */ - spin_lock_irq(&rds_iwdev->spinlock); - list_splice(&rds_iwdev->conn_list, &tmp_list); - INIT_LIST_HEAD(&rds_iwdev->conn_list); - spin_unlock_irq(&rds_iwdev->spinlock); + spin_lock_irq(list_lock); + list_splice(list, &tmp_list); + INIT_LIST_HEAD(list); + spin_unlock_irq(list_lock); list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node) { if (ic->conn->c_passive) diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c index a1931f0027a..fde470fa50d 100644 --- a/net/rds/iw_recv.c +++ b/net/rds/iw_recv.c @@ -395,10 +395,37 @@ void rds_iw_recv_init_ack(struct rds_iw_connection *ic) * room for it beyond the ring size. Send completion notices its special * wr_id and avoids working with the ring in that case. */ +#ifndef KERNEL_HAS_ATOMIC64 static void rds_iw_set_ack(struct rds_iw_connection *ic, u64 seq, int ack_required) { - rds_iw_set_64bit(&ic->i_ack_next, seq); + unsigned long flags; + + spin_lock_irqsave(&ic->i_ack_lock, flags); + ic->i_ack_next = seq; + if (ack_required) + set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); + spin_unlock_irqrestore(&ic->i_ack_lock, flags); +} + +static u64 rds_iw_get_ack(struct rds_iw_connection *ic) +{ + unsigned long flags; + u64 seq; + + clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); + + spin_lock_irqsave(&ic->i_ack_lock, flags); + seq = ic->i_ack_next; + spin_unlock_irqrestore(&ic->i_ack_lock, flags); + + return seq; +} +#else +static void rds_iw_set_ack(struct rds_iw_connection *ic, u64 seq, + int ack_required) +{ + atomic64_set(&ic->i_ack_next, seq); if (ack_required) { smp_mb__before_clear_bit(); set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); @@ -410,8 +437,10 @@ static u64 rds_iw_get_ack(struct rds_iw_connection *ic) clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); smp_mb__after_clear_bit(); - return ic->i_ack_next; + return atomic64_read(&ic->i_ack_next); } +#endif + static void rds_iw_send_ack(struct rds_iw_connection *ic, unsigned int adv_credits) { @@ -464,6 +493,10 @@ static void rds_iw_send_ack(struct rds_iw_connection *ic, unsigned int adv_credi * - i_ack_next, which is the last sequence number we received * * Potentially, send queue and receive queue handlers can run concurrently. + * It would be nice to not have to use a spinlock to synchronize things, + * but the one problem that rules this out is that 64bit updates are + * not atomic on all platforms. Things would be a lot simpler if + * we had atomic64 or maybe cmpxchg64 everywhere. * * Reconnecting complicates this picture just slightly. When we * reconnect, we may be seeing duplicate packets. The peer diff --git a/net/rds/rds.h b/net/rds/rds.h index 06040070497..71794449ca4 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -28,6 +28,10 @@ */ #define RDS_PORT 18634 +#ifdef ATOMIC64_INIT +#define KERNEL_HAS_ATOMIC64 +#endif + #ifdef DEBUG #define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args) #else @@ -634,7 +638,7 @@ struct rds_message *rds_send_get_message(struct rds_connection *, void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force); /* stats.c */ -DECLARE_PER_CPU(struct rds_statistics, rds_stats); +DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); #define rds_stats_inc_which(which, member) do { \ per_cpu(which, get_cpu()).member++; \ put_cpu(); \ diff --git a/net/rds/send.c b/net/rds/send.c index 1b37364656f..104fe033203 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -615,7 +615,7 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) { struct rds_message *rm, *tmp; struct rds_connection *conn; - unsigned long flags; + unsigned long flags, flags2; LIST_HEAD(list); int wake = 0; @@ -651,9 +651,9 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) list_for_each_entry(rm, &list, m_sock_item) { /* We do this here rather than in the loop above, so that * we don't have to nest m_rs_lock under rs->rs_lock */ - spin_lock(&rm->m_rs_lock); + spin_lock_irqsave(&rm->m_rs_lock, flags2); rm->m_rs = NULL; - spin_unlock(&rm->m_rs_lock); + spin_unlock_irqrestore(&rm->m_rs_lock, flags2); /* * If we see this flag cleared then we're *sure* that someone diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 0f36e8d59b2..877a7f65f70 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1072,10 +1072,6 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, unsigned char *asmptr; int n, size, qbit = 0; - /* ROSE empty frame has no meaning : don't send */ - if (len == 0) - return 0; - if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_CMSG_COMPAT)) return -EINVAL; @@ -1273,12 +1269,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, skb_reset_transport_header(skb); copied = skb->len; - /* ROSE empty frame has no meaning : ignore it */ - if (copied == 0) { - skb_free_datagram(sk, skb); - return copied; - } - if (copied > size) { copied = size; msg->msg_flags |= MSG_TRUNC; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 173fcc4b050..0759f32e9dc 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -254,7 +254,7 @@ replay: } tp->ops = tp_ops; tp->protocol = protocol; - tp->prio = nprio ? : tcf_auto_prio(*back); + tp->prio = nprio ? : TC_H_MAJ(tcf_auto_prio(*back)); tp->q = q; tp->classify = tp_ops->classify; tp->classid = parent; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 72cf86e3c09..fad596bf32d 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -176,8 +176,10 @@ META_COLLECTOR(var_dev) META_COLLECTOR(int_vlan_tag) { - unsigned short uninitialized_var(tag); - if (vlan_get_tag(skb, &tag) < 0) + unsigned short tag; + + tag = vlan_tx_tag_get(skb); + if (!tag && __vlan_get_tag(skb, &tag)) *err = -1; else dst->value = tag; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index d876b873484..2b88295cb7b 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -280,6 +280,14 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) if (unlikely(!skb)) return NULL; +#ifdef CONFIG_NET_CLS_ACT + /* + * If it's at ingress let's pretend the delay is + * from the network (tstamp will be updated). + */ + if (G_TC_FROM(skb->tc_verd) & AT_INGRESS) + skb->tstamp.tv64 = 0; +#endif pr_debug("netem_dequeue: return skb=%p\n", skb); sch->q.qlen--; return skb; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index cb198af8887..8eb3e61cb70 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -106,12 +106,8 @@ static __init int sctp_proc_init(void) goto out_nomem; #ifdef CONFIG_PROC_FS if (!proc_net_sctp) { - struct proc_dir_entry *ent; - ent = proc_mkdir("sctp", init_net.proc_net); - if (ent) { - ent->owner = THIS_MODULE; - proc_net_sctp = ent; - } else + proc_net_sctp = proc_mkdir("sctp", init_net.proc_net); + if (!proc_net_sctp) goto out_free_percpu; } diff --git a/net/socket.c b/net/socket.c index 91d0c0254ff..791d71a36a9 100644 --- a/net/socket.c +++ b/net/socket.c @@ -493,8 +493,7 @@ static struct socket *sock_alloc(void) inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - get_cpu_var(sockets_in_use)++; - put_cpu_var(sockets_in_use); + percpu_add(sockets_in_use, 1); return sock; } @@ -536,8 +535,7 @@ void sock_release(struct socket *sock) if (sock->fasync_list) printk(KERN_ERR "sock_release: fasync list not empty!\n"); - get_cpu_var(sockets_in_use)--; - put_cpu_var(sockets_in_use); + percpu_sub(sockets_in_use, 1); if (!sock->file) { iput(SOCK_INODE(sock)); return; diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 5592883e1e4..443c161eb8b 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -17,28 +17,6 @@ config SUNRPC_XPRT_RDMA If unsure, say N. -config SUNRPC_REGISTER_V4 - bool "Register local RPC services via rpcbind v4 (EXPERIMENTAL)" - depends on SUNRPC && EXPERIMENTAL - default n - help - Sun added support for registering RPC services at an IPv6 - address by creating two new versions of the rpcbind protocol - (RFC 1833). - - This option enables support in the kernel RPC server for - registering kernel RPC services via version 4 of the rpcbind - protocol. If you enable this option, you must run a portmapper - daemon that supports rpcbind protocol version 4. - - Serving NFS over IPv6 from knfsd (the kernel's NFS server) - requires that you enable this option and use a portmapper that - supports rpcbind version 4. - - If unsure, say N to get traditional behavior (register kernel - RPC services using only rpcbind version 2). Distributions - using the legacy Linux portmapper daemon must say N here. - config RPCSEC_GSS_KRB5 tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)" depends on SUNRPC && EXPERIMENTAL @@ -69,7 +47,7 @@ config RPCSEC_GSS_SPKM3 select CRYPTO_CBC help Choose Y here to enable Secure RPC using the SPKM3 public key - GSS-API mechansim (RFC 2025). + GSS-API mechanism (RFC 2025). Secure RPC calls with SPKM3 require an auxiliary userspace daemon which may be found in the Linux nfs-utils package diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 4735caad26e..20029a79a5d 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -313,7 +313,6 @@ static int create_cache_proc_entries(struct cache_detail *cd) cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc); if (cd->proc_ent == NULL) goto out_nomem; - cd->proc_ent->owner = cd->owner; cd->channel_ent = cd->content_ent = NULL; p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, @@ -321,7 +320,6 @@ static int create_cache_proc_entries(struct cache_detail *cd) cd->flush_ent = p; if (p == NULL) goto out_nomem; - p->owner = cd->owner; if (cd->cache_request || cd->cache_parse) { p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, @@ -329,7 +327,6 @@ static int create_cache_proc_entries(struct cache_detail *cd) cd->channel_ent = p; if (p == NULL) goto out_nomem; - p->owner = cd->owner; } if (cd->cache_show) { p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, @@ -337,7 +334,6 @@ static int create_cache_proc_entries(struct cache_detail *cd) cd->content_ent = p; if (p == NULL) goto out_nomem; - p->owner = cd->owner; } return 0; out_nomem: diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 836f15c0c4a..5abab094441 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1032,27 +1032,20 @@ call_connect_status(struct rpc_task *task) dprint_status(task); task->tk_status = 0; - if (status >= 0) { + if (status >= 0 || status == -EAGAIN) { clnt->cl_stats->netreconn++; task->tk_action = call_transmit; return; } - /* Something failed: remote service port may have changed */ - rpc_force_rebind(clnt); - switch (status) { - case -ENOTCONN: - case -EAGAIN: - task->tk_action = call_bind; - if (!RPC_IS_SOFT(task)) - return; /* if soft mounted, test if we've timed out */ case -ETIMEDOUT: task->tk_action = call_timeout; - return; + break; + default: + rpc_exit(task, -EIO); } - rpc_exit(task, -EIO); } /* @@ -1105,14 +1098,26 @@ static void call_transmit_status(struct rpc_task *task) { task->tk_action = call_status; - /* - * Special case: if we've been waiting on the socket's write_space() - * callback, then don't call xprt_end_transmit(). - */ - if (task->tk_status == -EAGAIN) - return; - xprt_end_transmit(task); - rpc_task_force_reencode(task); + switch (task->tk_status) { + case -EAGAIN: + break; + default: + xprt_end_transmit(task); + /* + * Special cases: if we've been waiting on the + * socket's write_space() callback, or if the + * socket just returned a connection error, + * then hold onto the transport lock. + */ + case -ECONNREFUSED: + case -ECONNRESET: + case -ENOTCONN: + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -EPIPE: + rpc_task_force_reencode(task); + } } /* @@ -1152,9 +1157,12 @@ call_status(struct rpc_task *task) xprt_conditional_disconnect(task->tk_xprt, req->rq_connect_cookie); break; + case -ECONNRESET: case -ECONNREFUSED: - case -ENOTCONN: rpc_force_rebind(clnt); + rpc_delay(task, 3*HZ); + case -EPIPE: + case -ENOTCONN: task->tk_action = call_bind; break; case -EAGAIN: diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 03ae007641e..beee6da3303 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -63,9 +63,16 @@ enum { * r_owner * * The "owner" is allowed to unset a service in the rpcbind database. - * We always use the following (arbitrary) fixed string. + * + * For AF_LOCAL SET/UNSET requests, rpcbind treats this string as a + * UID which it maps to a local user name via a password lookup. + * In all other cases it is ignored. + * + * For SET/UNSET requests, user space provides a value, even for + * network requests, and GETADDR uses an empty string. We follow + * those precedents here. */ -#define RPCB_OWNER_STRING "rpcb" +#define RPCB_OWNER_STRING "0" #define RPCB_MAXOWNERLEN sizeof(RPCB_OWNER_STRING) static void rpcb_getport_done(struct rpc_task *, void *); @@ -124,12 +131,6 @@ static const struct sockaddr_in rpcb_inaddr_loopback = { .sin_port = htons(RPCBIND_PORT), }; -static const struct sockaddr_in6 rpcb_in6addr_loopback = { - .sin6_family = AF_INET6, - .sin6_addr = IN6ADDR_LOOPBACK_INIT, - .sin6_port = htons(RPCBIND_PORT), -}; - static struct rpc_clnt *rpcb_create_local(struct sockaddr *addr, size_t addrlen, u32 version) { @@ -176,9 +177,10 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr, return rpc_create(&args); } -static int rpcb_register_call(struct sockaddr *addr, size_t addrlen, - u32 version, struct rpc_message *msg) +static int rpcb_register_call(const u32 version, 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; @@ -192,7 +194,7 @@ static int rpcb_register_call(struct sockaddr *addr, size_t addrlen, error = PTR_ERR(rpcb_clnt); if (error < 0) { - printk(KERN_WARNING "RPC: failed to contact local rpcbind " + dprintk("RPC: failed to contact local rpcbind " "server (errno %d).\n", -error); return error; } @@ -254,25 +256,23 @@ 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((struct sockaddr *)&rpcb_inaddr_loopback, - sizeof(rpcb_inaddr_loopback), - RPCBVERS_2, &msg); + return rpcb_register_call(RPCBVERS_2, &msg); } /* * Fill in AF_INET family-specific arguments to register */ -static int rpcb_register_netid4(struct sockaddr_in *address_to_register, - struct rpc_message *msg) +static int rpcb_register_inet4(const struct sockaddr *sap, + struct rpc_message *msg) { + const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; - unsigned short port = ntohs(address_to_register->sin_port); + unsigned short port = ntohs(sin->sin_port); char buf[32]; /* Construct AF_INET universal address */ snprintf(buf, sizeof(buf), "%pI4.%u.%u", - &address_to_register->sin_addr.s_addr, - port >> 8, port & 0xff); + &sin->sin_addr.s_addr, port >> 8, port & 0xff); map->r_addr = buf; dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " @@ -284,29 +284,27 @@ static int rpcb_register_netid4(struct sockaddr_in *address_to_register, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback, - sizeof(rpcb_inaddr_loopback), - RPCBVERS_4, msg); + return rpcb_register_call(RPCBVERS_4, msg); } /* * Fill in AF_INET6 family-specific arguments to register */ -static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register, - struct rpc_message *msg) +static int rpcb_register_inet6(const struct sockaddr *sap, + struct rpc_message *msg) { + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; - unsigned short port = ntohs(address_to_register->sin6_port); + unsigned short port = ntohs(sin6->sin6_port); char buf[64]; /* Construct AF_INET6 universal address */ - if (ipv6_addr_any(&address_to_register->sin6_addr)) + if (ipv6_addr_any(&sin6->sin6_addr)) snprintf(buf, sizeof(buf), "::.%u.%u", port >> 8, port & 0xff); else snprintf(buf, sizeof(buf), "%pI6.%u.%u", - &address_to_register->sin6_addr, - port >> 8, port & 0xff); + &sin6->sin6_addr, port >> 8, port & 0xff); map->r_addr = buf; dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " @@ -318,9 +316,21 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call((struct sockaddr *)&rpcb_in6addr_loopback, - sizeof(rpcb_in6addr_loopback), - RPCBVERS_4, msg); + return rpcb_register_call(RPCBVERS_4, msg); +} + +static int rpcb_unregister_all_protofamilies(struct rpc_message *msg) +{ + struct rpcbind_args *map = msg->rpc_argp; + + dprintk("RPC: unregistering [%u, %u, '%s'] with " + "local rpcbind\n", + map->r_prog, map->r_vers, map->r_netid); + + map->r_addr = ""; + msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; + + return rpcb_register_call(RPCBVERS_4, msg); } /** @@ -340,10 +350,11 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register, * invoke this function once for each [program, version, address, * netid] tuple they wish to advertise. * - * Callers may also unregister RPC services that are no longer - * available by setting the port number in the passed-in address - * to zero. Callers pass a netid of "" to unregister all - * transport netids associated with [program, version, address]. + * Callers may also unregister RPC services that are registered at a + * specific address by setting the port number in @address to zero. + * They may unregister all registered protocol families at once for + * a service by passing a NULL @address argument. If @netid is "" + * then all netids for [program, version, address] are unregistered. * * This function uses rpcbind protocol version 4 to contact the * local rpcbind daemon. The local rpcbind daemon must support @@ -378,13 +389,14 @@ int rpcb_v4_register(const u32 program, const u32 version, .rpc_argp = &map, }; + if (address == NULL) + return rpcb_unregister_all_protofamilies(&msg); + switch (address->sa_family) { case AF_INET: - return rpcb_register_netid4((struct sockaddr_in *)address, - &msg); + return rpcb_register_inet4(address, &msg); case AF_INET6: - return rpcb_register_netid6((struct sockaddr_in6 *)address, - &msg); + return rpcb_register_inet6(address, &msg); } return -EAFNOSUPPORT; @@ -579,7 +591,7 @@ void rpcb_getport_async(struct rpc_task *task) map->r_xprt = xprt_get(xprt); map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR); - map->r_owner = RPCB_OWNER_STRING; /* ignored for GETADDR */ + map->r_owner = ""; map->r_status = -EIO; child = rpcb_call_async(rpcb_clnt, map, proc); @@ -703,11 +715,16 @@ static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p, *portp = 0; addr_len = ntohl(*p++); + if (addr_len == 0) { + dprintk("RPC: rpcb_decode_getaddr: " + "service is not registered\n"); + return 0; + } + /* - * Simple sanity check. The smallest possible universal - * address is an IPv4 address string containing 11 bytes. + * Simple sanity check. */ - if (addr_len < 11 || addr_len > RPCBIND_MAXUADDRLEN) + if (addr_len > RPCBIND_MAXUADDRLEN) goto out_err; /* diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 085372ef4fe..1ef6e46d9da 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -262,14 +262,8 @@ void rpc_proc_init(void) { dprintk("RPC: registering /proc/net/rpc\n"); - if (!proc_net_rpc) { - struct proc_dir_entry *ent; - ent = proc_mkdir("rpc", init_net.proc_net); - if (ent) { - ent->owner = THIS_MODULE; - proc_net_rpc = ent; - } - } + if (!proc_net_rpc) + proc_net_rpc = proc_mkdir("rpc", init_net.proc_net); } void diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index c51fed4d1af..8847add6ca1 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -312,13 +312,12 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx) switch (m->mode) { case SVC_POOL_PERCPU: { - set_cpus_allowed_ptr(task, &cpumask_of_cpu(node)); + set_cpus_allowed_ptr(task, cpumask_of(node)); break; } case SVC_POOL_PERNODE: { - node_to_cpumask_ptr(nodecpumask, node); - set_cpus_allowed_ptr(task, nodecpumask); + set_cpus_allowed_ptr(task, cpumask_of_node(node)); break; } } @@ -359,7 +358,7 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu) */ static struct svc_serv * __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, - sa_family_t family, void (*shutdown)(struct svc_serv *serv)) + void (*shutdown)(struct svc_serv *serv)) { struct svc_serv *serv; unsigned int vers; @@ -368,7 +367,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; - serv->sv_family = family; serv->sv_name = prog->pg_name; serv->sv_program = prog; serv->sv_nrthreads = 1; @@ -427,21 +425,21 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, struct svc_serv * svc_create(struct svc_program *prog, unsigned int bufsize, - sa_family_t family, void (*shutdown)(struct svc_serv *serv)) + void (*shutdown)(struct svc_serv *serv)) { - return __svc_create(prog, bufsize, /*npools*/1, family, shutdown); + return __svc_create(prog, bufsize, /*npools*/1, shutdown); } EXPORT_SYMBOL_GPL(svc_create); struct svc_serv * svc_create_pooled(struct svc_program *prog, unsigned int bufsize, - sa_family_t family, void (*shutdown)(struct svc_serv *serv), + void (*shutdown)(struct svc_serv *serv), svc_thread_fn func, struct module *mod) { struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); - serv = __svc_create(prog, bufsize, npools, family, shutdown); + serv = __svc_create(prog, bufsize, npools, shutdown); if (serv != NULL) { serv->sv_function = func; @@ -719,8 +717,6 @@ svc_exit_thread(struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_exit_thread); -#ifdef CONFIG_SUNRPC_REGISTER_V4 - /* * Register an "inet" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. @@ -735,12 +731,13 @@ static int __svc_rpcb_register4(const u32 program, const u32 version, const unsigned short protocol, const unsigned short port) { - struct sockaddr_in sin = { + const struct sockaddr_in sin = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), .sin_port = htons(port), }; - char *netid; + const char *netid; + int error; switch (protocol) { case IPPROTO_UDP: @@ -750,13 +747,23 @@ static int __svc_rpcb_register4(const u32 program, const u32 version, netid = RPCBIND_NETID_TCP; break; default: - return -EPROTONOSUPPORT; + return -ENOPROTOOPT; } - return rpcb_v4_register(program, version, - (struct sockaddr *)&sin, netid); + error = rpcb_v4_register(program, version, + (const struct sockaddr *)&sin, netid); + + /* + * User space didn't support rpcbind v4, so retry this + * registration request with the legacy rpcbind v2 protocol. + */ + if (error == -EPROTONOSUPPORT) + error = rpcb_register(program, version, protocol, port); + + return error; } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) /* * Register an "inet6" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. @@ -771,12 +778,13 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, const unsigned short protocol, const unsigned short port) { - struct sockaddr_in6 sin6 = { + const struct sockaddr_in6 sin6 = { .sin6_family = AF_INET6, .sin6_addr = IN6ADDR_ANY_INIT, .sin6_port = htons(port), }; - char *netid; + const char *netid; + int error; switch (protocol) { case IPPROTO_UDP: @@ -786,12 +794,22 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, netid = RPCBIND_NETID_TCP6; break; default: - return -EPROTONOSUPPORT; + return -ENOPROTOOPT; } - return rpcb_v4_register(program, version, - (struct sockaddr *)&sin6, netid); + error = rpcb_v4_register(program, version, + (const struct sockaddr *)&sin6, netid); + + /* + * User space didn't support rpcbind version 4, so we won't + * use a PF_INET6 listener. + */ + if (error == -EPROTONOSUPPORT) + error = -EAFNOSUPPORT; + + return error; } +#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ /* * Register a kernel RPC service via rpcbind version 4. @@ -799,69 +817,43 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, * Returns zero on success; a negative errno value is returned * if any error occurs. */ -static int __svc_register(const u32 program, const u32 version, - const sa_family_t family, +static int __svc_register(const char *progname, + const u32 program, const u32 version, + const int family, const unsigned short protocol, const unsigned short port) { - int error; + int error = -EAFNOSUPPORT; switch (family) { - case AF_INET: - return __svc_rpcb_register4(program, version, + case PF_INET: + error = __svc_rpcb_register4(program, version, protocol, port); - case AF_INET6: + break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case PF_INET6: error = __svc_rpcb_register6(program, version, protocol, port); - if (error < 0) - return error; - - /* - * Work around bug in some versions of Linux rpcbind - * which don't allow registration of both inet and - * inet6 netids. - * - * Error return ignored for now. - */ - __svc_rpcb_register4(program, version, - protocol, port); - return 0; +#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ } - return -EAFNOSUPPORT; -} - -#else /* CONFIG_SUNRPC_REGISTER_V4 */ - -/* - * Register a kernel RPC service via rpcbind version 2. - * - * Returns zero on success; a negative errno value is returned - * if any error occurs. - */ -static int __svc_register(const u32 program, const u32 version, - sa_family_t family, - const unsigned short protocol, - const unsigned short port) -{ - if (family != AF_INET) - return -EAFNOSUPPORT; - - return rpcb_register(program, version, protocol, port); + if (error < 0) + printk(KERN_WARNING "svc: failed to register %sv%u RPC " + "service (errno %d).\n", progname, version, -error); + return error; } -#endif /* CONFIG_SUNRPC_REGISTER_V4 */ - /** * svc_register - register an RPC service with the local portmapper * @serv: svc_serv struct for the service to register + * @family: protocol family of service's listener socket * @proto: transport protocol number to advertise * @port: port to advertise * - * Service is registered for any address in serv's address family + * Service is registered for any address in the passed-in protocol family */ -int svc_register(const struct svc_serv *serv, const unsigned short proto, - const unsigned short port) +int svc_register(const struct svc_serv *serv, const int family, + const unsigned short proto, const unsigned short port) { struct svc_program *progp; unsigned int i; @@ -879,15 +871,15 @@ int svc_register(const struct svc_serv *serv, const unsigned short proto, i, proto == IPPROTO_UDP? "udp" : "tcp", port, - serv->sv_family, + family, progp->pg_vers[i]->vs_hidden? " (but not telling portmap)" : ""); if (progp->pg_vers[i]->vs_hidden) continue; - error = __svc_register(progp->pg_prog, i, - serv->sv_family, proto, port); + error = __svc_register(progp->pg_name, progp->pg_prog, + i, family, proto, port); if (error < 0) break; } @@ -896,38 +888,31 @@ int svc_register(const struct svc_serv *serv, const unsigned short proto, return error; } -#ifdef CONFIG_SUNRPC_REGISTER_V4 - +/* + * If user space is running rpcbind, it should take the v4 UNSET + * and clear everything for this [program, version]. If user space + * is running portmap, it will reject the v4 UNSET, but won't have + * any "inet6" entries anyway. So a PMAP_UNSET should be sufficient + * in this case to clear all existing entries for [program, version]. + */ static void __svc_unregister(const u32 program, const u32 version, const char *progname) { - struct sockaddr_in6 sin6 = { - .sin6_family = AF_INET6, - .sin6_addr = IN6ADDR_ANY_INIT, - .sin6_port = 0, - }; int error; - error = rpcb_v4_register(program, version, - (struct sockaddr *)&sin6, ""); - dprintk("svc: %s(%sv%u), error %d\n", - __func__, progname, version, error); -} - -#else /* CONFIG_SUNRPC_REGISTER_V4 */ + error = rpcb_v4_register(program, version, NULL, ""); -static void __svc_unregister(const u32 program, const u32 version, - const char *progname) -{ - int error; + /* + * User space didn't support rpcbind v4, so retry this + * request with the legacy rpcbind v2 protocol. + */ + if (error == -EPROTONOSUPPORT) + error = rpcb_register(program, version, 0, 0); - error = rpcb_register(program, version, 0, 0); dprintk("svc: %s(%sv%u), error %d\n", __func__, progname, version, error); } -#endif /* CONFIG_SUNRPC_REGISTER_V4 */ - /* * All netids, bind addresses and ports registered for [program, version] * are removed from the local rpcbind database (if the service is not @@ -1023,6 +1008,8 @@ svc_process(struct svc_rqst *rqstp) rqstp->rq_res.tail[0].iov_len = 0; /* Will be turned off only in gss privacy case: */ rqstp->rq_splice_ok = 1; + /* Will be turned off only when NFSv4 Sessions are used */ + rqstp->rq_usedeferral = 1; /* Setup reply header */ rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); @@ -1093,7 +1080,6 @@ svc_process(struct svc_rqst *rqstp) procp = versp->vs_proc + proc; if (proc >= versp->vs_nproc || !procp->pc_func) goto err_bad_proc; - rqstp->rq_server = serv; rqstp->rq_procinfo = procp; /* Syntactic check complete */ diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index e588df5d6b3..c200d92e57e 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -14,6 +14,8 @@ #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); @@ -161,7 +163,9 @@ EXPORT_SYMBOL_GPL(svc_xprt_init); static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, struct svc_serv *serv, - unsigned short port, int flags) + const int family, + const unsigned short port, + int flags) { struct sockaddr_in sin = { .sin_family = AF_INET, @@ -176,12 +180,12 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, struct sockaddr *sap; size_t len; - switch (serv->sv_family) { - case AF_INET: + switch (family) { + case PF_INET: sap = (struct sockaddr *)&sin; len = sizeof(sin); break; - case AF_INET6: + case PF_INET6: sap = (struct sockaddr *)&sin6; len = sizeof(sin6); break; @@ -192,7 +196,8 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, return xcl->xcl_ops->xpo_create(serv, sap, len, flags); } -int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port, +int svc_create_xprt(struct svc_serv *serv, const char *xprt_name, + const int family, const unsigned short port, int flags) { struct svc_xprt_class *xcl; @@ -209,7 +214,7 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port, goto err; spin_unlock(&svc_xprt_class_lock); - newxprt = __svc_xpo_create(xcl, serv, port, flags); + newxprt = __svc_xpo_create(xcl, serv, family, port, flags); if (IS_ERR(newxprt)) { module_put(xcl->xcl_owner); return PTR_ERR(newxprt); @@ -298,6 +303,7 @@ 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)))) @@ -309,18 +315,14 @@ 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); goto out_unlock; } + pool->sp_stats.packets++; + /* Mark transport as busy. It will remain in this state until * the provider calls svc_xprt_received. We update XPT_BUSY * atomically because it also guards against trying to enqueue @@ -353,7 +355,15 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) } process: - if (!list_empty(&pool->sp_threads)) { + /* 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) { rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, rq_list); @@ -368,11 +378,15 @@ 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); } else { dprintk("svc: transport %p put into queue\n", xprt); list_add_tail(&xprt->xpt_ready, &pool->sp_sockets); + pool->sp_stats.sockets_queued++; BUG_ON(xprt->xpt_pool != pool); } @@ -585,6 +599,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) int pages; struct xdr_buf *arg; DECLARE_WAITQUEUE(wait, current); + long time_left; dprintk("svc: server %p waiting for data (to = %ld)\n", rqstp, timeout); @@ -633,6 +648,11 @@ 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; @@ -665,12 +685,14 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) add_wait_queue(&rqstp->rq_wait, &wait); spin_unlock_bh(&pool->sp_lock); - schedule_timeout(timeout); + time_left = schedule_timeout(timeout); try_to_freeze(); spin_lock_bh(&pool->sp_lock); remove_wait_queue(&rqstp->rq_wait, &wait); + if (!time_left) + pool->sp_stats.threads_timedout++; xprt = rqstp->rq_xprt; if (!xprt) { @@ -955,7 +977,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle); struct svc_deferred_req *dr; - if (rqstp->rq_arg.page_len) + if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral) return NULL; /* if more than a page, give up FIXME */ if (rqstp->rq_deferred) { dr = rqstp->rq_deferred; @@ -1033,7 +1055,13 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) return dr; } -/* +/** + * svc_find_xprt - find an RPC transport instance + * @serv: pointer to svc_serv to search + * @xcl_name: C string containing transport's class name + * @af: Address family of transport's local address + * @port: transport's IP port number + * * Return the transport instance pointer for the endpoint accepting * connections/peer traffic from the specified transport class, * address family and port. @@ -1042,14 +1070,14 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) * wild-card, and will result in matching the first transport in the * service's list that has a matching class name. */ -struct svc_xprt *svc_find_xprt(struct svc_serv *serv, char *xcl_name, - int af, int port) +struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, + const sa_family_t af, const unsigned short port) { struct svc_xprt *xprt; struct svc_xprt *found = NULL; /* Sanity check the args */ - if (!serv || !xcl_name) + if (serv == NULL || xcl_name == NULL) return found; spin_lock_bh(&serv->sv_lock); @@ -1058,7 +1086,7 @@ struct svc_xprt *svc_find_xprt(struct svc_serv *serv, char *xcl_name, continue; if (af != AF_UNSPEC && af != xprt->xpt_local.ss_family) continue; - if (port && port != svc_xprt_local_port(xprt)) + if (port != 0 && port != svc_xprt_local_port(xprt)) continue; found = xprt; svc_xprt_get(xprt); @@ -1103,3 +1131,93 @@ int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen) return totlen; } EXPORT_SYMBOL_GPL(svc_xprt_names); + + +/*----------------------------------------------------------------------------*/ + +static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos) +{ + unsigned int pidx = (unsigned int)*pos; + struct svc_serv *serv = m->private; + + dprintk("svc_pool_stats_start, *pidx=%u\n", pidx); + + lock_kernel(); + /* bump up the pseudo refcount while traversing */ + svc_get(serv); + unlock_kernel(); + + if (!pidx) + return SEQ_START_TOKEN; + return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]); +} + +static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos) +{ + struct svc_pool *pool = p; + struct svc_serv *serv = m->private; + + dprintk("svc_pool_stats_next, *pos=%llu\n", *pos); + + if (p == SEQ_START_TOKEN) { + pool = &serv->sv_pools[0]; + } else { + unsigned int pidx = (pool - &serv->sv_pools[0]); + if (pidx < serv->sv_nrpools-1) + pool = &serv->sv_pools[pidx+1]; + else + pool = NULL; + } + ++*pos; + return pool; +} + +static void svc_pool_stats_stop(struct seq_file *m, void *p) +{ + struct svc_serv *serv = m->private; + + lock_kernel(); + /* this function really, really should have been called svc_put() */ + svc_destroy(serv); + unlock_kernel(); +} + +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"); + return 0; + } + + seq_printf(m, "%u %lu %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; +} + +static const struct seq_operations svc_pool_stats_seq_ops = { + .start = svc_pool_stats_start, + .next = svc_pool_stats_next, + .stop = svc_pool_stats_stop, + .show = svc_pool_stats_show, +}; + +int svc_pool_stats_open(struct svc_serv *serv, struct file *file) +{ + int err; + + err = seq_open(file, &svc_pool_stats_seq_ops); + if (!err) + ((struct seq_file *) file->private_data)->private = serv; + return err; +} +EXPORT_SYMBOL(svc_pool_stats_open); + +/*----------------------------------------------------------------------------*/ diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5763e6460fe..af3198814c1 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -345,7 +345,6 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd, lock_sock(sock->sk); sock->sk->sk_sndbuf = snd * 2; sock->sk->sk_rcvbuf = rcv * 2; - sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK; release_sock(sock->sk); #endif } @@ -797,23 +796,6 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags), test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)); - if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags)) - /* sndbuf needs to have room for one request - * per thread, otherwise we can stall even when the - * network isn't a bottleneck. - * - * We count all threads rather than threads in a - * particular pool, which provides an upper bound - * on the number of threads which will access the socket. - * - * rcvbuf just needs to be able to hold a few requests. - * Normally they will be removed from the queue - * as soon a a complete request arrives. - */ - svc_sock_setbufsize(svsk->sk_sock, - (serv->sv_nrthreads+3) * serv->sv_max_mesg, - 3 * serv->sv_max_mesg); - clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* Receive data. If we haven't got the record length yet, get @@ -1061,15 +1043,6 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; - /* initialise setting must have enough space to - * receive and respond to one request. - * svc_tcp_recvfrom will re-adjust if necessary - */ - svc_sock_setbufsize(svsk->sk_sock, - 3 * svsk->sk_xprt.xpt_server->sv_max_mesg, - 3 * svsk->sk_xprt.xpt_server->sv_max_mesg); - - set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); if (sk->sk_state != TCP_ESTABLISHED) set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); @@ -1110,7 +1083,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, struct svc_sock *svsk; struct sock *inet; int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); - int val; dprintk("svc: svc_setup_socket %p\n", sock); if (!(svsk = kzalloc(sizeof(*svsk), GFP_KERNEL))) { @@ -1122,7 +1094,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, /* Register socket with portmapper */ if (*errp >= 0 && pmap_register) - *errp = svc_register(serv, inet->sk_protocol, + *errp = svc_register(serv, inet->sk_family, inet->sk_protocol, ntohs(inet_sk(inet)->sport)); if (*errp < 0) { @@ -1140,20 +1112,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, /* Initialize the socket */ if (sock->type == SOCK_DGRAM) svc_udp_init(svsk, serv); - else + else { + /* initialise setting must have enough space to + * receive and respond to one request. + */ + svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg, + 4 * serv->sv_max_mesg); svc_tcp_init(svsk, serv); - - /* - * We start one listener per sv_serv. We want AF_INET - * requests to be automatically shunted to our AF_INET6 - * listener using a mapped IPv4 address. Make sure - * no-one starts an equivalent IPv4 listener, which - * would steal our incoming connections. - */ - val = 0; - if (serv->sv_family == AF_INET6) - kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY, - (char *)&val, sizeof(val)); + } dprintk("svc: svc_setup_socket created %p (inet %p)\n", svsk, svsk->sk_sk); @@ -1222,6 +1188,8 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, struct sockaddr_storage addr; struct sockaddr *newsin = (struct sockaddr *)&addr; int newlen; + int family; + int val; RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); dprintk("svc: svc_create_socket(%s, %d, %s)\n", @@ -1233,14 +1201,35 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, "sockets supported\n"); return ERR_PTR(-EINVAL); } + type = (protocol == IPPROTO_UDP)? SOCK_DGRAM : SOCK_STREAM; + switch (sin->sa_family) { + case AF_INET6: + family = PF_INET6; + break; + case AF_INET: + family = PF_INET; + break; + default: + return ERR_PTR(-EINVAL); + } - error = sock_create_kern(sin->sa_family, type, protocol, &sock); + error = sock_create_kern(family, type, protocol, &sock); if (error < 0) return ERR_PTR(error); svc_reclassify_socket(sock); + /* + * If this is an PF_INET6 listener, we want to avoid + * getting requests from IPv4 remotes. Those should + * be shunted to a PF_INET listener via rpcbind. + */ + val = 1; + if (family == PF_INET6) + kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY, + (char *)&val, sizeof(val)); + if (type == SOCK_STREAM) sock->sk->sk_reuse = 1; /* allow address reuse */ error = kernel_bind(sock, sin, len); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 62098d101a1..06ca058572f 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -152,6 +152,37 @@ out: EXPORT_SYMBOL_GPL(xprt_unregister_transport); /** + * xprt_load_transport - load a transport implementation + * @transport_name: transport to load + * + * Returns: + * 0: transport successfully loaded + * -ENOENT: transport module not available + */ +int xprt_load_transport(const char *transport_name) +{ + struct xprt_class *t; + char module_name[sizeof t->name + 5]; + int result; + + result = 0; + spin_lock(&xprt_list_lock); + list_for_each_entry(t, &xprt_list, list) { + if (strcmp(t->name, transport_name) == 0) { + spin_unlock(&xprt_list_lock); + goto out; + } + } + spin_unlock(&xprt_list_lock); + strcpy(module_name, "xprt"); + strncat(module_name, transport_name, sizeof t->name); + result = request_module(module_name); +out: + return result; +} +EXPORT_SYMBOL_GPL(xprt_load_transport); + +/** * xprt_reserve_xprt - serialize write access to transports * @task: task that is requesting access to the transport * @@ -580,7 +611,7 @@ void xprt_disconnect_done(struct rpc_xprt *xprt) dprintk("RPC: disconnected transport %p\n", xprt); spin_lock_bh(&xprt->transport_lock); xprt_clear_connected(xprt); - xprt_wake_pending_tasks(xprt, -ENOTCONN); + xprt_wake_pending_tasks(xprt, -EAGAIN); spin_unlock_bh(&xprt->transport_lock); } EXPORT_SYMBOL_GPL(xprt_disconnect_done); @@ -598,7 +629,7 @@ void xprt_force_disconnect(struct rpc_xprt *xprt) /* Try to schedule an autoclose RPC call */ if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(rpciod_workqueue, &xprt->task_cleanup); - xprt_wake_pending_tasks(xprt, -ENOTCONN); + xprt_wake_pending_tasks(xprt, -EAGAIN); spin_unlock_bh(&xprt->transport_lock); } @@ -625,7 +656,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie) /* Try to schedule an autoclose RPC call */ if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(rpciod_workqueue, &xprt->task_cleanup); - xprt_wake_pending_tasks(xprt, -ENOTCONN); + xprt_wake_pending_tasks(xprt, -EAGAIN); out: spin_unlock_bh(&xprt->transport_lock); } @@ -641,10 +672,8 @@ xprt_init_autodisconnect(unsigned long data) if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) goto out_abort; spin_unlock(&xprt->transport_lock); - if (xprt_connecting(xprt)) - xprt_release_write(xprt, NULL); - else - queue_work(rpciod_workqueue, &xprt->task_cleanup); + set_bit(XPRT_CONNECTION_CLOSE, &xprt->state); + queue_work(rpciod_workqueue, &xprt->task_cleanup); return; out_abort: spin_unlock(&xprt->transport_lock); @@ -695,9 +724,8 @@ static void xprt_connect_status(struct rpc_task *task) } switch (task->tk_status) { - case -ENOTCONN: - dprintk("RPC: %5u xprt_connect_status: connection broken\n", - task->tk_pid); + case -EAGAIN: + dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid); break; case -ETIMEDOUT: dprintk("RPC: %5u xprt_connect_status: connect attempt timed " @@ -818,15 +846,8 @@ int xprt_prepare_transmit(struct rpc_task *task) err = req->rq_received; goto out_unlock; } - if (!xprt->ops->reserve_xprt(task)) { + if (!xprt->ops->reserve_xprt(task)) err = -EAGAIN; - goto out_unlock; - } - - if (!xprt_connected(xprt)) { - err = -ENOTCONN; - goto out_unlock; - } out_unlock: spin_unlock_bh(&xprt->transport_lock); return err; @@ -870,32 +891,26 @@ void xprt_transmit(struct rpc_task *task) req->rq_connect_cookie = xprt->connect_cookie; req->rq_xtime = jiffies; status = xprt->ops->send_request(task); - if (status == 0) { - dprintk("RPC: %5u xmit complete\n", task->tk_pid); - spin_lock_bh(&xprt->transport_lock); + if (status != 0) { + task->tk_status = status; + return; + } - xprt->ops->set_retrans_timeout(task); + dprintk("RPC: %5u xmit complete\n", task->tk_pid); + spin_lock_bh(&xprt->transport_lock); - xprt->stat.sends++; - xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs; - xprt->stat.bklog_u += xprt->backlog.qlen; + xprt->ops->set_retrans_timeout(task); - /* Don't race with disconnect */ - if (!xprt_connected(xprt)) - task->tk_status = -ENOTCONN; - else if (!req->rq_received) - rpc_sleep_on(&xprt->pending, task, xprt_timer); - spin_unlock_bh(&xprt->transport_lock); - return; - } + xprt->stat.sends++; + xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs; + xprt->stat.bklog_u += xprt->backlog.qlen; - /* Note: at this point, task->tk_sleeping has not yet been set, - * hence there is no danger of the waking up task being put on - * schedq, and being picked up by a parallel run of rpciod(). - */ - task->tk_status = status; - if (status == -ECONNREFUSED) - rpc_sleep_on(&xprt->sending, task, NULL); + /* Don't race with disconnect */ + if (!xprt_connected(xprt)) + task->tk_status = -ENOTCONN; + else if (!req->rq_received) + rpc_sleep_on(&xprt->pending, task, xprt_timer); + spin_unlock_bh(&xprt->transport_lock); } static inline void do_xprt_reserve(struct rpc_task *task) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 14106d26bb9..e5e28d1946a 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -310,6 +310,19 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) __func__, pad, destp, rqst->rq_slen, curlen); copy_len = rqst->rq_snd_buf.page_len; + + if (rqst->rq_snd_buf.tail[0].iov_len) { + curlen = rqst->rq_snd_buf.tail[0].iov_len; + if (destp + copy_len != rqst->rq_snd_buf.tail[0].iov_base) { + memmove(destp + copy_len, + rqst->rq_snd_buf.tail[0].iov_base, curlen); + r_xprt->rx_stats.pullup_copy_count += curlen; + } + dprintk("RPC: %s: tail destp 0x%p len %d\n", + __func__, destp + copy_len, curlen); + rqst->rq_svec[0].iov_len += curlen; + } + r_xprt->rx_stats.pullup_copy_count += copy_len; npages = PAGE_ALIGN(rqst->rq_snd_buf.page_base+copy_len) >> PAGE_SHIFT; for (i = 0; copy_len && i < npages; i++) { @@ -332,17 +345,6 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) destp += curlen; copy_len -= curlen; } - if (rqst->rq_snd_buf.tail[0].iov_len) { - curlen = rqst->rq_snd_buf.tail[0].iov_len; - if (destp != rqst->rq_snd_buf.tail[0].iov_base) { - memcpy(destp, - rqst->rq_snd_buf.tail[0].iov_base, curlen); - r_xprt->rx_stats.pullup_copy_count += curlen; - } - dprintk("RPC: %s: tail destp 0x%p len %d curlen %d\n", - __func__, destp, copy_len, curlen); - rqst->rq_svec[0].iov_len += curlen; - } /* header now contains entire send message */ return pad; } @@ -656,7 +658,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) if (curlen > rqst->rq_rcv_buf.tail[0].iov_len) curlen = rqst->rq_rcv_buf.tail[0].iov_len; if (rqst->rq_rcv_buf.tail[0].iov_base != srcp) - memcpy(rqst->rq_rcv_buf.tail[0].iov_base, srcp, curlen); + memmove(rqst->rq_rcv_buf.tail[0].iov_base, srcp, curlen); dprintk("RPC: %s: tail srcp 0x%p len %d curlen %d\n", __func__, srcp, copy_len, curlen); rqst->rq_rcv_buf.tail[0].iov_len = curlen; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index a3334e3b73c..6c26a675435 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -191,7 +191,6 @@ static int map_xdr(struct svcxprt_rdma *xprt, struct xdr_buf *xdr, struct svc_rdma_req_map *vec) { - int sge_max = (xdr->len+PAGE_SIZE-1) / PAGE_SIZE + 3; int sge_no; u32 sge_bytes; u32 page_bytes; @@ -235,7 +234,11 @@ static int map_xdr(struct svcxprt_rdma *xprt, sge_no++; } - BUG_ON(sge_no > sge_max); + dprintk("svcrdma: map_xdr: sge_no %d page_no %d " + "page_base %u page_len %u head_len %zu tail_len %zu\n", + sge_no, page_no, xdr->page_base, xdr->page_len, + xdr->head[0].iov_len, xdr->tail[0].iov_len); + vec->count = sge_no; return 0; } @@ -579,7 +582,6 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->sge[page_no+1].length = 0; } BUG_ON(sge_no > rdma->sc_max_sge); - BUG_ON(sge_no > ctxt->count); memset(&send_wr, 0, sizeof send_wr); ctxt->wr_op = IB_WR_SEND; send_wr.wr_id = (unsigned long)ctxt; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 568330eebbf..e1859614601 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -49,6 +49,9 @@ unsigned int xprt_tcp_slot_table_entries = RPC_DEF_SLOT_TABLE; unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT; unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT; +#define XS_TCP_LINGER_TO (15U * HZ) +static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; + /* * We can register our own files under /proc/sys/sunrpc by * calling register_sysctl_table() again. The files in that @@ -117,6 +120,14 @@ static ctl_table xs_tunables_table[] = { .extra2 = &xprt_max_resvport_limit }, { + .procname = "tcp_fin_timeout", + .data = &xs_tcp_fin_timeout, + .maxlen = sizeof(xs_tcp_fin_timeout), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = sysctl_jiffies + }, + { .ctl_name = 0, }, }; @@ -521,11 +532,12 @@ static void xs_nospace_callback(struct rpc_task *task) * @task: task to put to sleep * */ -static void xs_nospace(struct rpc_task *task) +static int xs_nospace(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + int ret = 0; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", task->tk_pid, req->rq_slen - req->rq_bytes_sent, @@ -537,6 +549,7 @@ static void xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) { + ret = -EAGAIN; /* * Notify TCP that we're limited by the application * window size @@ -548,10 +561,11 @@ static void xs_nospace(struct rpc_task *task) } } else { clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); - task->tk_status = -ENOTCONN; + ret = -ENOTCONN; } spin_unlock_bh(&xprt->transport_lock); + return ret; } /** @@ -594,6 +608,8 @@ static int xs_udp_send_request(struct rpc_task *task) /* Still some bytes left; set up for a retry later. */ status = -EAGAIN; } + if (!transport->sock) + goto out; switch (status) { case -ENOTSOCK: @@ -601,21 +617,19 @@ static int xs_udp_send_request(struct rpc_task *task) /* Should we call xs_close() here? */ break; case -EAGAIN: - xs_nospace(task); + status = xs_nospace(task); break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); case -ENETUNREACH: case -EPIPE: case -ECONNREFUSED: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); - break; - default: - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); } - +out: return status; } @@ -697,6 +711,8 @@ static int xs_tcp_send_request(struct rpc_task *task) status = -EAGAIN; break; } + if (!transport->sock) + goto out; switch (status) { case -ENOTSOCK: @@ -704,23 +720,19 @@ static int xs_tcp_send_request(struct rpc_task *task) /* Should we call xs_close() here? */ break; case -EAGAIN: - xs_nospace(task); + status = xs_nospace(task); break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); case -ECONNRESET: + case -EPIPE: xs_tcp_shutdown(xprt); case -ECONNREFUSED: case -ENOTCONN: - case -EPIPE: - status = -ENOTCONN; - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); - break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); - xs_tcp_shutdown(xprt); } - +out: return status; } @@ -767,23 +779,13 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s sk->sk_error_report = transport->old_error_report; } -/** - * xs_close - close a socket - * @xprt: transport - * - * This is used when all requests are complete; ie, no DRC state remains - * on the server we want to save. - */ -static void xs_close(struct rpc_xprt *xprt) +static void xs_reset_transport(struct sock_xprt *transport) { - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct socket *sock = transport->sock; struct sock *sk = transport->inet; - if (!sk) - goto clear_close_wait; - - dprintk("RPC: xs_close xprt %p\n", xprt); + if (sk == NULL) + return; write_lock_bh(&sk->sk_callback_lock); transport->inet = NULL; @@ -797,14 +799,42 @@ static void xs_close(struct rpc_xprt *xprt) sk->sk_no_check = 0; sock_release(sock); -clear_close_wait: +} + +/** + * xs_close - close a socket + * @xprt: transport + * + * This is used when all requests are complete; ie, no DRC state remains + * on the server we want to save. + * + * The caller _must_ be holding XPRT_LOCKED in order to avoid issues with + * xs_reset_transport() zeroing the socket from underneath a writer. + */ +static void xs_close(struct rpc_xprt *xprt) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + + dprintk("RPC: xs_close xprt %p\n", xprt); + + xs_reset_transport(transport); + smp_mb__before_clear_bit(); + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); smp_mb__after_clear_bit(); xprt_disconnect_done(xprt); } +static void xs_tcp_close(struct rpc_xprt *xprt) +{ + if (test_and_clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state)) + xs_close(xprt); + else + xs_tcp_shutdown(xprt); +} + /** * xs_destroy - prepare to shutdown a transport * @xprt: doomed transport @@ -1126,6 +1156,47 @@ out: read_unlock(&sk->sk_callback_lock); } +/* + * Do the equivalent of linger/linger2 handling for dealing with + * broken servers that don't close the socket in a timely + * fashion + */ +static void xs_tcp_schedule_linger_timeout(struct rpc_xprt *xprt, + unsigned long timeout) +{ + struct sock_xprt *transport; + + if (xprt_test_and_set_connecting(xprt)) + return; + set_bit(XPRT_CONNECTION_ABORT, &xprt->state); + transport = container_of(xprt, struct sock_xprt, xprt); + queue_delayed_work(rpciod_workqueue, &transport->connect_worker, + timeout); +} + +static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt) +{ + struct sock_xprt *transport; + + transport = container_of(xprt, struct sock_xprt, xprt); + + if (!test_bit(XPRT_CONNECTION_ABORT, &xprt->state) || + !cancel_delayed_work(&transport->connect_worker)) + return; + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); + xprt_clear_connecting(xprt); +} + +static void xs_sock_mark_closed(struct rpc_xprt *xprt) +{ + smp_mb__before_clear_bit(); + clear_bit(XPRT_CLOSE_WAIT, &xprt->state); + clear_bit(XPRT_CLOSING, &xprt->state); + smp_mb__after_clear_bit(); + /* Mark transport as closed and wake up all pending tasks */ + xprt_disconnect_done(xprt); +} + /** * xs_tcp_state_change - callback to handle TCP socket state changes * @sk: socket whose state has changed @@ -1158,7 +1229,7 @@ static void xs_tcp_state_change(struct sock *sk) transport->tcp_flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; - xprt_wake_pending_tasks(xprt, 0); + xprt_wake_pending_tasks(xprt, -EAGAIN); } spin_unlock_bh(&xprt->transport_lock); break; @@ -1171,10 +1242,10 @@ static void xs_tcp_state_change(struct sock *sk) clear_bit(XPRT_CONNECTED, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); smp_mb__after_clear_bit(); + xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout); break; case TCP_CLOSE_WAIT: /* The server initiated a shutdown of the socket */ - set_bit(XPRT_CLOSING, &xprt->state); xprt_force_disconnect(xprt); case TCP_SYN_SENT: xprt->connect_cookie++; @@ -1187,40 +1258,35 @@ static void xs_tcp_state_change(struct sock *sk) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; break; case TCP_LAST_ACK: + set_bit(XPRT_CLOSING, &xprt->state); + xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout); smp_mb__before_clear_bit(); clear_bit(XPRT_CONNECTED, &xprt->state); smp_mb__after_clear_bit(); break; case TCP_CLOSE: - smp_mb__before_clear_bit(); - clear_bit(XPRT_CLOSE_WAIT, &xprt->state); - clear_bit(XPRT_CLOSING, &xprt->state); - smp_mb__after_clear_bit(); - /* Mark transport as closed and wake up all pending tasks */ - xprt_disconnect_done(xprt); + xs_tcp_cancel_linger_timeout(xprt); + xs_sock_mark_closed(xprt); } out: read_unlock(&sk->sk_callback_lock); } /** - * xs_tcp_error_report - callback mainly for catching RST events + * xs_error_report - callback mainly for catching socket errors * @sk: socket */ -static void xs_tcp_error_report(struct sock *sk) +static void xs_error_report(struct sock *sk) { struct rpc_xprt *xprt; read_lock(&sk->sk_callback_lock); - if (sk->sk_err != ECONNRESET || sk->sk_state != TCP_ESTABLISHED) - goto out; if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: %s client %p...\n" "RPC: error %d\n", __func__, xprt, sk->sk_err); - - xprt_force_disconnect(xprt); + xprt_wake_pending_tasks(xprt, -EAGAIN); out: read_unlock(&sk->sk_callback_lock); } @@ -1494,6 +1560,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; + sk->sk_error_report = xs_error_report; sk->sk_no_check = UDP_CSUM_NORCV; sk->sk_allocation = GFP_ATOMIC; @@ -1526,9 +1593,10 @@ static void xs_udp_connect_worker4(struct work_struct *work) goto out; /* Start by resetting any existing state */ - xs_close(xprt); + xs_reset_transport(transport); - if ((err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) { + err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + if (err < 0) { dprintk("RPC: can't create UDP transport socket (%d).\n", -err); goto out; } @@ -1545,8 +1613,8 @@ static void xs_udp_connect_worker4(struct work_struct *work) xs_udp_finish_connecting(xprt, sock); status = 0; out: - xprt_wake_pending_tasks(xprt, status); xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, status); } /** @@ -1567,9 +1635,10 @@ static void xs_udp_connect_worker6(struct work_struct *work) goto out; /* Start by resetting any existing state */ - xs_close(xprt); + xs_reset_transport(transport); - if ((err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) { + err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock); + if (err < 0) { dprintk("RPC: can't create UDP transport socket (%d).\n", -err); goto out; } @@ -1586,18 +1655,17 @@ static void xs_udp_connect_worker6(struct work_struct *work) xs_udp_finish_connecting(xprt, sock); status = 0; out: - xprt_wake_pending_tasks(xprt, status); xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, status); } /* * We need to preserve the port number so the reply cache on the server can * find our cached RPC replies when we get around to reconnecting. */ -static void xs_tcp_reuse_connection(struct rpc_xprt *xprt) +static void xs_abort_connection(struct rpc_xprt *xprt, struct sock_xprt *transport) { int result; - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct sockaddr any; dprintk("RPC: disconnecting xprt %p to reuse port\n", xprt); @@ -1609,11 +1677,24 @@ static void xs_tcp_reuse_connection(struct rpc_xprt *xprt) memset(&any, 0, sizeof(any)); any.sa_family = AF_UNSPEC; result = kernel_connect(transport->sock, &any, sizeof(any), 0); - if (result) + if (!result) + xs_sock_mark_closed(xprt); + else dprintk("RPC: AF_UNSPEC connect return code %d\n", result); } +static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *transport) +{ + unsigned int state = transport->inet->sk_state; + + if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) + return; + if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) + return; + xs_abort_connection(xprt, transport); +} + static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1629,7 +1710,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_tcp_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; - sk->sk_error_report = xs_tcp_error_report; + sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; /* socket options */ @@ -1657,37 +1738,42 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) } /** - * xs_tcp_connect_worker4 - connect a TCP socket to a remote endpoint - * @work: RPC transport to connect + * xs_tcp_setup_socket - create a TCP socket and connect to a remote endpoint + * @xprt: RPC transport to connect + * @transport: socket transport to connect + * @create_sock: function to create a socket of the correct type * * Invoked by a work queue tasklet. */ -static void xs_tcp_connect_worker4(struct work_struct *work) +static void xs_tcp_setup_socket(struct rpc_xprt *xprt, + struct sock_xprt *transport, + struct socket *(*create_sock)(struct rpc_xprt *, + struct sock_xprt *)) { - struct sock_xprt *transport = - container_of(work, struct sock_xprt, connect_worker.work); - struct rpc_xprt *xprt = &transport->xprt; struct socket *sock = transport->sock; - int err, status = -EIO; + int status = -EIO; if (xprt->shutdown) goto out; if (!sock) { - /* start from scratch */ - if ((err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) { - dprintk("RPC: can't create TCP transport socket (%d).\n", -err); + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); + sock = create_sock(xprt, transport); + if (IS_ERR(sock)) { + status = PTR_ERR(sock); goto out; } - xs_reclassify_socket4(sock); + } else { + int abort_and_exit; - if (xs_bind4(transport, sock) < 0) { - sock_release(sock); - goto out; - } - } else + abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT, + &xprt->state); /* "close" the socket, preserving the local port */ - xs_tcp_reuse_connection(xprt); + xs_tcp_reuse_connection(xprt, transport); + + if (abort_and_exit) + goto out_eagain; + } dprintk("RPC: worker connecting xprt %p to address: %s\n", xprt, xprt->address_strings[RPC_DISPLAY_ALL]); @@ -1696,83 +1782,109 @@ static void xs_tcp_connect_worker4(struct work_struct *work) dprintk("RPC: %p connect status %d connected %d sock state %d\n", xprt, -status, xprt_connected(xprt), sock->sk->sk_state); - if (status < 0) { - switch (status) { - case -EINPROGRESS: - case -EALREADY: - goto out_clear; - case -ECONNREFUSED: - case -ECONNRESET: - /* retry with existing socket, after a delay */ - break; - default: - /* get rid of existing socket, and retry */ - xs_tcp_shutdown(xprt); - } + switch (status) { + default: + printk("%s: connect returned unhandled error %d\n", + __func__, status); + case -EADDRNOTAVAIL: + /* We're probably in TIME_WAIT. Get rid of existing socket, + * and retry + */ + set_bit(XPRT_CONNECTION_CLOSE, &xprt->state); + xprt_force_disconnect(xprt); + case -ECONNREFUSED: + case -ECONNRESET: + case -ENETUNREACH: + /* retry with existing socket, after a delay */ + case 0: + case -EINPROGRESS: + case -EALREADY: + xprt_clear_connecting(xprt); + return; } +out_eagain: + status = -EAGAIN; out: - xprt_wake_pending_tasks(xprt, status); -out_clear: xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, status); +} + +static struct socket *xs_create_tcp_sock4(struct rpc_xprt *xprt, + struct sock_xprt *transport) +{ + struct socket *sock; + int err; + + /* start from scratch */ + err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + if (err < 0) { + dprintk("RPC: can't create TCP transport socket (%d).\n", + -err); + goto out_err; + } + xs_reclassify_socket4(sock); + + if (xs_bind4(transport, sock) < 0) { + sock_release(sock); + goto out_err; + } + return sock; +out_err: + return ERR_PTR(-EIO); } /** - * xs_tcp_connect_worker6 - connect a TCP socket to a remote endpoint + * xs_tcp_connect_worker4 - connect a TCP socket to a remote endpoint * @work: RPC transport to connect * * Invoked by a work queue tasklet. */ -static void xs_tcp_connect_worker6(struct work_struct *work) +static void xs_tcp_connect_worker4(struct work_struct *work) { struct sock_xprt *transport = container_of(work, struct sock_xprt, connect_worker.work); struct rpc_xprt *xprt = &transport->xprt; - struct socket *sock = transport->sock; - int err, status = -EIO; - if (xprt->shutdown) - goto out; + xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock4); +} - if (!sock) { - /* start from scratch */ - if ((err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) { - dprintk("RPC: can't create TCP transport socket (%d).\n", -err); - goto out; - } - xs_reclassify_socket6(sock); +static struct socket *xs_create_tcp_sock6(struct rpc_xprt *xprt, + struct sock_xprt *transport) +{ + struct socket *sock; + int err; + + /* start from scratch */ + err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock); + if (err < 0) { + dprintk("RPC: can't create TCP transport socket (%d).\n", + -err); + goto out_err; + } + xs_reclassify_socket6(sock); - if (xs_bind6(transport, sock) < 0) { - sock_release(sock); - goto out; - } - } else - /* "close" the socket, preserving the local port */ - xs_tcp_reuse_connection(xprt); + if (xs_bind6(transport, sock) < 0) { + sock_release(sock); + goto out_err; + } + return sock; +out_err: + return ERR_PTR(-EIO); +} - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); +/** + * xs_tcp_connect_worker6 - connect a TCP socket to a remote endpoint + * @work: RPC transport to connect + * + * Invoked by a work queue tasklet. + */ +static void xs_tcp_connect_worker6(struct work_struct *work) +{ + struct sock_xprt *transport = + container_of(work, struct sock_xprt, connect_worker.work); + struct rpc_xprt *xprt = &transport->xprt; - status = xs_tcp_finish_connecting(xprt, sock); - dprintk("RPC: %p connect status %d connected %d sock state %d\n", - xprt, -status, xprt_connected(xprt), sock->sk->sk_state); - if (status < 0) { - switch (status) { - case -EINPROGRESS: - case -EALREADY: - goto out_clear; - case -ECONNREFUSED: - case -ECONNRESET: - /* retry with existing socket, after a delay */ - break; - default: - /* get rid of existing socket, and retry */ - xs_tcp_shutdown(xprt); - } - } -out: - xprt_wake_pending_tasks(xprt, status); -out_clear: - xprt_clear_connecting(xprt); + xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock6); } /** @@ -1817,9 +1929,6 @@ static void xs_tcp_connect(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_xprt; - /* Initiate graceful shutdown of the socket if not already done */ - if (test_bit(XPRT_CONNECTED, &xprt->state)) - xs_tcp_shutdown(xprt); /* Exit if we need to wait for socket shutdown to complete */ if (test_bit(XPRT_CLOSING, &xprt->state)) return; @@ -1901,7 +2010,7 @@ static struct rpc_xprt_ops xs_tcp_ops = { .buf_free = rpc_free, .send_request = xs_tcp_send_request, .set_retrans_timeout = xprt_set_retrans_timeout_def, - .close = xs_tcp_shutdown, + .close = xs_tcp_close, .destroy = xs_destroy, .print_stats = xs_tcp_print_stats, }; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index baac91049b0..9dcc6e7f96e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -832,7 +832,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * All right, let's create it. */ mode = S_IFSOCK | - (SOCK_INODE(sock)->i_mode & ~current->fs->umask); + (SOCK_INODE(sock)->i_mode & ~current_umask()); err = mnt_want_write(nd.path.mnt); if (err) goto out_mknod_dput; diff --git a/net/wimax/Kconfig b/net/wimax/Kconfig index 18495cdcd10..1b46747a5f5 100644 --- a/net/wimax/Kconfig +++ b/net/wimax/Kconfig @@ -8,7 +8,7 @@ # # As well, enablement of the RFKILL code means we need the INPUT layer # support to inject events coming from hw rfkill switches. That -# dependency could be killed if input.h provided appropiate means to +# dependency could be killed if input.h provided appropriate means to # work when input is disabled. comment "WiMAX Wireless Broadband support requires CONFIG_INPUT enabled" diff --git a/net/wireless/core.h b/net/wireless/core.h index d43daa236ef..0a592e4295f 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -90,7 +90,7 @@ struct cfg80211_internal_bss { struct rb_node rbn; unsigned long ts; struct kref ref; - bool hold; + bool hold, ies_allocated; /* must be last because of priv member */ struct cfg80211_bss pub; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 353e1a4ece8..2456e4ee445 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3334,7 +3334,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (!msg) return; @@ -3353,7 +3353,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, return; } - genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, GFP_KERNEL); + genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, GFP_ATOMIC); return; nla_put_failure: diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 6327e1617ac..6c1993d9990 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2095,11 +2095,12 @@ int set_regdom(const struct ieee80211_regdomain *rd) /* Caller must hold cfg80211_mutex */ void reg_device_remove(struct wiphy *wiphy) { - struct wiphy *request_wiphy; + struct wiphy *request_wiphy = NULL; assert_cfg80211_lock(); - request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); + if (last_request) + request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); kfree(wiphy->regd); if (!last_request || !request_wiphy) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 2a00e362f5f..2ae65b39b52 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -58,6 +58,10 @@ static void bss_release(struct kref *ref) bss = container_of(ref, struct cfg80211_internal_bss, ref); if (bss->pub.free_priv) bss->pub.free_priv(&bss->pub); + + if (bss->ies_allocated) + kfree(bss->pub.information_elements); + kfree(bss); } @@ -360,19 +364,41 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, found = rb_find_bss(dev, res); - if (found && overwrite) { - list_replace(&found->list, &res->list); - rb_replace_node(&found->rbn, &res->rbn, - &dev->bss_tree); - kref_put(&found->ref, bss_release); - found = res; - } else if (found) { + if (found) { kref_get(&found->ref); found->pub.beacon_interval = res->pub.beacon_interval; found->pub.tsf = res->pub.tsf; found->pub.signal = res->pub.signal; found->pub.capability = res->pub.capability; found->ts = res->ts; + + /* overwrite IEs */ + if (overwrite) { + size_t used = dev->wiphy.bss_priv_size + sizeof(*res); + size_t ielen = res->pub.len_information_elements; + + if (ksize(found) >= used + ielen) { + memcpy(found->pub.information_elements, + res->pub.information_elements, ielen); + found->pub.len_information_elements = ielen; + } else { + u8 *ies = found->pub.information_elements; + + if (found->ies_allocated) { + if (ksize(ies) < ielen) + ies = krealloc(ies, ielen, + GFP_ATOMIC); + } else + ies = kmalloc(ielen, GFP_ATOMIC); + + if (ies) { + memcpy(ies, res->pub.information_elements, ielen); + found->ies_allocated = true; + found->pub.information_elements = ies; + } + } + } + kref_put(&res->ref, bss_release); } else { /* this "consumes" the reference */ diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 82271720d97..5f1f86565f1 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -794,7 +794,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, { static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); - unsigned int h; + unsigned int h, h_wildcard; struct hlist_node *entry; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; @@ -819,8 +819,8 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, if (best) goto found; - h = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) { if (x->props.family == family && x->props.reqid == tmpl->reqid && !(x->props.flags & XFRM_STATE_WILDRECV) && |