diff options
Diffstat (limited to 'net')
211 files changed, 7242 insertions, 2697 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a1f16303703a..8836575f9d79 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -330,12 +330,13 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id); } - new_dev = alloc_netdev(sizeof(struct vlan_dev_info), name, - vlan_setup); + new_dev = alloc_netdev_mq(sizeof(struct vlan_dev_info), name, + vlan_setup, real_dev->num_tx_queues); if (new_dev == NULL) return -ENOBUFS; + new_dev->real_num_tx_queues = real_dev->real_num_tx_queues; dev_net_set(new_dev, net); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. @@ -391,6 +392,9 @@ static void vlan_transfer_features(struct net_device *dev, vlandev->features &= ~dev->vlan_features; vlandev->features |= dev->features & dev->vlan_features; vlandev->gso_max_size = dev->gso_max_size; +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) + vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; +#endif if (old_features != vlandev->features) netdev_features_change(vlandev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 96bad8f233e2..4198ec5c8abc 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -288,10 +288,14 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, return rc; } -static int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, + struct net_device *dev) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + int i = skb_get_queue_mapping(skb); + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); + unsigned int len; + int ret; /* Handle non-VLAN frames if they are sent to us, for example by DHCP. * @@ -317,29 +321,43 @@ static int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) vlan_dev_info(dev)->cnt_inc_headroom_on_tx++; } - txq->tx_packets++; - txq->tx_bytes += skb->len; skb->dev = vlan_dev_info(dev)->real_dev; - dev_queue_xmit(skb); + len = skb->len; + ret = dev_queue_xmit(skb); + + if (likely(ret == NET_XMIT_SUCCESS)) { + txq->tx_packets++; + txq->tx_bytes += len; + } else + txq->tx_dropped++; + return NETDEV_TX_OK; } -static int vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, - struct net_device *dev) +static netdev_tx_t vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, + struct net_device *dev) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + int i = skb_get_queue_mapping(skb); + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); u16 vlan_tci; + unsigned int len; + int ret; vlan_tci = vlan_dev_info(dev)->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb); skb = __vlan_hwaccel_put_tag(skb, vlan_tci); - txq->tx_packets++; - txq->tx_bytes += skb->len; - skb->dev = vlan_dev_info(dev)->real_dev; - dev_queue_xmit(skb); + len = skb->len; + ret = dev_queue_xmit(skb); + + if (likely(ret == NET_XMIT_SUCCESS)) { + txq->tx_packets++; + txq->tx_bytes += len; + } else + txq->tx_dropped++; + return NETDEV_TX_OK; } @@ -561,6 +579,55 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa) return err; } +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) +static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid, + struct scatterlist *sgl, unsigned int sgc) +{ + struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + const struct net_device_ops *ops = real_dev->netdev_ops; + int rc = 0; + + if (ops->ndo_fcoe_ddp_setup) + rc = ops->ndo_fcoe_ddp_setup(real_dev, xid, sgl, sgc); + + return rc; +} + +static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid) +{ + struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + const struct net_device_ops *ops = real_dev->netdev_ops; + int len = 0; + + if (ops->ndo_fcoe_ddp_done) + len = ops->ndo_fcoe_ddp_done(real_dev, xid); + + return len; +} + +static int vlan_dev_fcoe_enable(struct net_device *dev) +{ + struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + const struct net_device_ops *ops = real_dev->netdev_ops; + int rc = -EINVAL; + + if (ops->ndo_fcoe_enable) + rc = ops->ndo_fcoe_enable(real_dev); + return rc; +} + +static int vlan_dev_fcoe_disable(struct net_device *dev) +{ + struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + const struct net_device_ops *ops = real_dev->netdev_ops; + int rc = -EINVAL; + + if (ops->ndo_fcoe_disable) + rc = ops->ndo_fcoe_disable(real_dev); + return rc; +} +#endif + static void vlan_dev_change_rx_flags(struct net_device *dev, int change) { struct net_device *real_dev = vlan_dev_info(dev)->real_dev; @@ -635,6 +702,10 @@ static int vlan_dev_init(struct net_device *dev) if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) + dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid; +#endif + if (real_dev->features & NETIF_F_HW_VLAN_TX) { dev->header_ops = real_dev->header_ops; dev->hard_header_len = real_dev->hard_header_len; @@ -715,6 +786,12 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_do_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) + .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, + .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, + .ndo_fcoe_enable = vlan_dev_fcoe_enable, + .ndo_fcoe_disable = vlan_dev_fcoe_disable, +#endif }; static const struct net_device_ops vlan_netdev_accel_ops = { @@ -731,6 +808,12 @@ static const struct net_device_ops vlan_netdev_accel_ops = { .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_do_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) + .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, + .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, + .ndo_fcoe_enable = vlan_dev_fcoe_enable, + .ndo_fcoe_disable = vlan_dev_fcoe_disable, +#endif }; void vlan_setup(struct net_device *dev) diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index e9c91dcecc9b..343146e1bceb 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -100,6 +100,25 @@ static int vlan_changelink(struct net_device *dev, return 0; } +static int vlan_get_tx_queues(struct net *net, + struct nlattr *tb[], + unsigned int *num_tx_queues, + unsigned int *real_num_tx_queues) +{ + struct net_device *real_dev; + + if (!tb[IFLA_LINK]) + return -EINVAL; + + real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK])); + if (!real_dev) + return -ENODEV; + + *num_tx_queues = real_dev->num_tx_queues; + *real_num_tx_queues = real_dev->real_num_tx_queues; + return 0; +} + static int vlan_newlink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { @@ -216,6 +235,7 @@ struct rtnl_link_ops vlan_link_ops __read_mostly = { .maxtype = IFLA_VLAN_MAX, .policy = vlan_policy, .priv_size = sizeof(struct vlan_dev_info), + .get_tx_queues = vlan_get_tx_queues, .setup = vlan_setup, .validate = vlan_validate, .newlink = vlan_newlink, diff --git a/net/9p/client.c b/net/9p/client.c index dd43a8289b0d..787ccddb85ea 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -117,9 +117,6 @@ static int parse_opts(char *opts, struct p9_client *clnt) } } - if (!clnt->trans_mod) - clnt->trans_mod = v9fs_get_default_trans(); - kfree(options); return ret; } @@ -689,6 +686,9 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) if (err < 0) goto error; + if (!clnt->trans_mod) + clnt->trans_mod = v9fs_get_default_trans(); + if (clnt->trans_mod == NULL) { err = -EPROTONOSUPPORT; P9_DPRINTK(P9_DEBUG_ERROR, @@ -1098,7 +1098,6 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, if (data) { memmove(data, dataptr, count); - data += count; } if (udata) { @@ -1192,9 +1191,9 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) err = p9pdu_readf(req->rc, clnt->dotu, "wS", &ignored, ret); if (err) { - ret = ERR_PTR(err); p9pdu_dump(1, req->rc); - goto free_and_error; + p9_free_req(clnt, req); + goto error; } P9_DPRINTK(P9_DEBUG_9P, @@ -1211,8 +1210,6 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) p9_free_req(clnt, req); return ret; -free_and_error: - p9_free_req(clnt, req); error: kfree(ret); return ERR_PTR(err); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 590b83963622..0d42d5da50ad 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -54,6 +54,7 @@ #include <linux/capability.h> #include <linux/module.h> #include <linux/if_arp.h> +#include <linux/smp_lock.h> #include <linux/termios.h> /* For TIOCOUTQ/INQ */ #include <net/datalink.h> #include <net/psnap.h> @@ -1237,6 +1238,7 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, return -ENOBUFS; *uaddr_len = sizeof(struct sockaddr_at); + memset(&sat.sat_zero, 0, sizeof(sat.sat_zero)); if (peer) { if (sk->sk_state != TCP_ESTABLISHED) @@ -1398,7 +1400,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, __u16 len_hops; if (!net_eq(dev_net(dev), &init_net)) - goto freeit; + goto drop; /* Don't mangle buffer if shared */ if (!(skb = skb_share_check(skb, GFP_ATOMIC))) @@ -1406,7 +1408,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, /* Size check and make sure header is contiguous */ if (!pskb_may_pull(skb, sizeof(*ddp))) - goto freeit; + goto drop; ddp = ddp_hdr(skb); @@ -1424,7 +1426,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, if (skb->len < sizeof(*ddp) || skb->len < (len_hops & 1023)) { pr_debug("AppleTalk: dropping corrupted frame (deh_len=%u, " "skb->len=%u)\n", len_hops & 1023, skb->len); - goto freeit; + goto drop; } /* @@ -1434,7 +1436,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, if (ddp->deh_sum && atalk_checksum(skb, len_hops & 1023) != ddp->deh_sum) /* Not a valid AppleTalk frame - dustbin time */ - goto freeit; + goto drop; /* Check the packet is aimed at us */ if (!ddp->deh_dnet) /* Net 0 is 'this network' */ @@ -1447,7 +1449,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, * AppleTalk iface */ atalk_route_packet(skb, dev, ddp, len_hops, origlen); - goto out; + return NET_RX_SUCCESS; } /* if IP over DDP is not selected this code will be optimized out */ @@ -1463,18 +1465,21 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, sock = atalk_search_socket(&tosat, atif); if (!sock) /* But not one of our sockets */ - goto freeit; + goto drop; /* Queue packet (standard) */ skb->sk = sock; if (sock_queue_rcv_skb(sock, skb) < 0) - goto freeit; -out: - return 0; -freeit: + goto drop; + + return NET_RX_SUCCESS; + +drop: kfree_skb(skb); - goto out; +out: + return NET_RX_DROP; + } /* diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 848af113ba2a..26a646d4eb32 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -69,7 +69,7 @@ struct br2684_vcc { struct net_device *device; /* keep old push, pop functions for chaining */ void (*old_push) (struct atm_vcc * vcc, struct sk_buff * skb); - /* void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); */ + void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); enum br2684_encaps encaps; struct list_head brvccs; #ifdef CONFIG_ATM_BR2684_IPFILTER @@ -142,6 +142,22 @@ static struct net_device *br2684_find_dev(const struct br2684_if_spec *s) return NULL; } +/* chained vcc->pop function. Check if we should wake the netif_queue */ +static void br2684_pop(struct atm_vcc *vcc, struct sk_buff *skb) +{ + struct br2684_vcc *brvcc = BR2684_VCC(vcc); + struct net_device *net_dev = skb->dev; + + pr_debug("br2684_pop(vcc %p ; net_dev %p )\n", vcc, net_dev); + brvcc->old_pop(vcc, skb); + + if (!net_dev) + return; + + if (atm_may_send(vcc, 0)) + netif_wake_queue(net_dev); + +} /* * Send a packet out a particular vcc. Not to useful right now, but paves * the way for multiple vcc's per itf. Returns true if we can send, @@ -200,20 +216,19 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); - if (!atm_may_send(atmvcc, skb->truesize)) { - /* - * We free this here for now, because we cannot know in a higher - * layer whether the skb pointer it supplied wasn't freed yet. - * Now, it always is. - */ - dev_kfree_skb(skb); - return 0; - } atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = atmvcc->atm_options; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; atmvcc->send(atmvcc, skb); + + if (!atm_may_send(atmvcc, 0)) { + netif_stop_queue(brvcc->device); + /*check for race with br2684_pop*/ + if (atm_may_send(atmvcc, 0)) + netif_start_queue(brvcc->device); + } + return 1; } @@ -223,7 +238,8 @@ static inline struct br2684_vcc *pick_outgoing_vcc(const struct sk_buff *skb, return list_empty(&brdev->brvccs) ? NULL : list_entry_brvcc(brdev->brvccs.next); /* 1 vcc/dev right now */ } -static int br2684_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t br2684_start_xmit(struct sk_buff *skb, + struct net_device *dev) { struct br2684_dev *brdev = BRPRIV(dev); struct br2684_vcc *brvcc; @@ -503,8 +519,10 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) atmvcc->user_back = brvcc; brvcc->encaps = (enum br2684_encaps)be.encaps; brvcc->old_push = atmvcc->push; + brvcc->old_pop = atmvcc->pop; barrier(); atmvcc->push = br2684_push; + atmvcc->pop = br2684_pop; __skb_queue_head_init(&queue); rq = &sk_atm(atmvcc)->sk_receive_queue; diff --git a/net/atm/clip.c b/net/atm/clip.c index 64910bb86089..64629c354343 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -267,7 +267,7 @@ static void clip_neigh_error(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); } -static struct neigh_ops clip_neigh_ops = { +static const struct neigh_ops clip_neigh_ops = { .family = AF_INET, .solicit = clip_neigh_solicit, .error_report = clip_neigh_error, @@ -360,7 +360,8 @@ static int clip_encap(struct atm_vcc *vcc, int mode) return 0; } -static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t clip_start_xmit(struct sk_buff *skb, + struct net_device *dev) { struct clip_priv *clip_priv = PRIV(dev); struct atmarp_entry *entry; diff --git a/net/atm/lec.c b/net/atm/lec.c index 8e723c2654cb..b2d644560323 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -59,7 +59,8 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 }; */ static int lec_open(struct net_device *dev); -static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t lec_start_xmit(struct sk_buff *skb, + struct net_device *dev); static int lec_close(struct net_device *dev); static void lec_init(struct net_device *dev); static struct lec_arp_table *lec_arp_find(struct lec_priv *priv, @@ -247,7 +248,8 @@ static void lec_tx_timeout(struct net_device *dev) netif_wake_queue(dev); } -static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t lec_start_xmit(struct sk_buff *skb, + struct net_device *dev) { struct sk_buff *skb2; struct lec_priv *priv = netdev_priv(dev); diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 1ac4b94bf626..38a6cb0863f0 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -73,7 +73,8 @@ static void mpoad_close(struct atm_vcc *vcc); static int msg_from_mpoad(struct atm_vcc *vcc, struct sk_buff *skb); static void mpc_push(struct atm_vcc *vcc, struct sk_buff *skb); -static int mpc_send_packet(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t mpc_send_packet(struct sk_buff *skb, + struct net_device *dev); static int mpoa_event_listener(struct notifier_block *mpoa_notifier, unsigned long event, void *dev); static void mpc_timer_refresh(void); static void mpc_cache_check( unsigned long checking_time ); @@ -528,7 +529,8 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc) /* * Probably needs some error checks and locking, not sure... */ -static int mpc_send_packet(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t mpc_send_packet(struct sk_buff *skb, + struct net_device *dev) { struct mpoa_client *mpc; struct ethhdr *eth; diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 59fdb1d2e8ed..ed371684c133 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -34,6 +34,7 @@ menuconfig BT config BT_L2CAP tristate "L2CAP protocol support" depends on BT + select CRC16 help L2CAP (Logical Link Control and Adaptation Protocol) provides connection oriented and connection-less data transport. L2CAP diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index 9c42990126a0..26fb831ef7e0 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -165,7 +165,8 @@ static inline int bnep_net_proto_filter(struct sk_buff *skb, struct bnep_session } #endif -static int bnep_net_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t bnep_net_xmit(struct sk_buff *skb, + struct net_device *dev) { struct bnep_session *s = netdev_priv(dev); struct sock *sk = s->sock->sk; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index fa47d5d84f5c..a9750984f772 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -246,6 +246,8 @@ 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); + atomic_set(&conn->devref, 0); + hci_conn_init_sysfs(conn); tasklet_enable(&hdev->tx_task); @@ -288,7 +290,7 @@ int hci_conn_del(struct hci_conn *conn) skb_queue_purge(&conn->data_q); - hci_conn_del_sysfs(conn); + hci_conn_put_device(conn); hci_dev_put(hdev); @@ -583,6 +585,19 @@ void hci_conn_check_pending(struct hci_dev *hdev) hci_dev_unlock(hdev); } +void hci_conn_hold_device(struct hci_conn *conn) +{ + atomic_inc(&conn->devref); +} +EXPORT_SYMBOL(hci_conn_hold_device); + +void hci_conn_put_device(struct hci_conn *conn) +{ + if (atomic_dec_and_test(&conn->devref)) + hci_conn_del_sysfs(conn); +} +EXPORT_SYMBOL(hci_conn_put_device); + int hci_get_conn_list(void __user *arg) { struct hci_conn_list_req req, *cl; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 406ad07cdea1..e1da8f68759c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -911,7 +911,7 @@ int hci_register_dev(struct hci_dev *hdev) hdev->reassembly[i] = NULL; init_waitqueue_head(&hdev->req_wait_q); - init_MUTEX(&hdev->req_lock); + mutex_init(&hdev->req_lock); inquiry_cache_init(hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 184ba0a88ec0..e99fe385fba2 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -887,6 +887,7 @@ static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *s } else conn->state = BT_CONNECTED; + hci_conn_hold_device(conn); hci_conn_add_sysfs(conn); if (test_bit(HCI_AUTH, &hdev->flags)) @@ -1693,6 +1694,7 @@ static inline void hci_sync_conn_complete_evt(struct hci_dev *hdev, struct sk_bu conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; + hci_conn_hold_device(conn); hci_conn_add_sysfs(conn); break; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index b18676870d55..09bedeb5579c 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -40,6 +40,7 @@ #include <linux/input.h> #include <linux/hid.h> +#include <linux/hidraw.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -92,10 +93,14 @@ static void __hidp_link_session(struct hidp_session *session) { __module_get(THIS_MODULE); list_add(&session->list, &hidp_session_list); + + hci_conn_hold_device(session->conn); } static void __hidp_unlink_session(struct hidp_session *session) { + hci_conn_put_device(session->conn); + list_del(&session->list); module_put(THIS_MODULE); } @@ -374,6 +379,7 @@ static void hidp_process_hid_control(struct hidp_session *session, /* Kill session thread */ atomic_inc(&session->terminate); + hidp_schedule(session); } } @@ -573,7 +579,11 @@ static int hidp_session(void *arg) if (session->hid) { if (session->hid->claimed & HID_CLAIMED_INPUT) hidinput_disconnect(session->hid); + if (session->hid->claimed & HID_CLAIMED_HIDRAW) + hidraw_disconnect(session->hid); + hid_destroy_device(session->hid); + session->hid = NULL; } /* Wakeup user-space polling for socket errors */ @@ -601,25 +611,27 @@ static struct device *hidp_get_device(struct hidp_session *session) { bdaddr_t *src = &bt_sk(session->ctrl_sock->sk)->src; bdaddr_t *dst = &bt_sk(session->ctrl_sock->sk)->dst; + struct device *device = NULL; struct hci_dev *hdev; - struct hci_conn *conn; hdev = hci_get_route(dst, src); if (!hdev) return NULL; - conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); + session->conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); + if (session->conn) + device = &session->conn->dev; hci_dev_put(hdev); - return conn ? &conn->dev : NULL; + return device; } static int hidp_setup_input(struct hidp_session *session, struct hidp_connadd_req *req) { struct input_dev *input; - int i; + int err, i; input = input_allocate_device(); if (!input) @@ -666,7 +678,13 @@ static int hidp_setup_input(struct hidp_session *session, input->event = hidp_input_event; - return input_register_device(input); + err = input_register_device(input); + if (err < 0) { + hci_conn_put_device(session->conn); + return err; + } + + return 0; } static int hidp_open(struct hid_device *hid) @@ -748,13 +766,11 @@ static int hidp_setup_hid(struct hidp_session *session, { struct hid_device *hid; bdaddr_t src, dst; - int ret; + int err; hid = hid_allocate_device(); - if (IS_ERR(hid)) { - ret = PTR_ERR(session->hid); - goto err; - } + if (IS_ERR(hid)) + return PTR_ERR(session->hid); session->hid = hid; session->req = req; @@ -776,16 +792,17 @@ static int hidp_setup_hid(struct hidp_session *session, hid->dev.parent = hidp_get_device(session); hid->ll_driver = &hidp_hid_driver; - ret = hid_add_device(hid); - if (ret) - goto err_hid; + err = hid_add_device(hid); + if (err < 0) + goto failed; return 0; -err_hid: + +failed: hid_destroy_device(hid); session->hid = NULL; -err: - return ret; + + return err; } int hidp_add_connection(struct hidp_connadd_req *req, struct socket *ctrl_sock, struct socket *intr_sock) @@ -835,13 +852,13 @@ int hidp_add_connection(struct hidp_connadd_req *req, struct socket *ctrl_sock, if (req->rd_size > 0) { err = hidp_setup_hid(session, req); if (err && err != -ENODEV) - goto err_skb; + goto purge; } if (!session->hid) { err = hidp_setup_input(session, req); if (err < 0) - goto err_skb; + goto purge; } __hidp_link_session(session); @@ -869,13 +886,20 @@ unlink: __hidp_unlink_session(session); - if (session->input) + if (session->input) { input_unregister_device(session->input); - if (session->hid) + session->input = NULL; + } + + if (session->hid) { hid_destroy_device(session->hid); -err_skb: + session->hid = NULL; + } + +purge: skb_queue_purge(&session->ctrl_transmit); skb_queue_purge(&session->intr_transmit); + failed: up_write(&hidp_session_sem); diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index e503c89057ad..faf3d74c3586 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -126,6 +126,8 @@ int hidp_get_conninfo(struct hidp_conninfo *ci); struct hidp_session { struct list_head list; + struct hci_conn *conn; + struct socket *ctrl_sock; struct socket *intr_sock; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index bd0a4c1bced0..b03012564647 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -41,6 +41,7 @@ #include <linux/list.h> #include <linux/device.h> #include <linux/uaccess.h> +#include <linux/crc16.h> #include <net/sock.h> #include <asm/system.h> @@ -50,7 +51,9 @@ #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> -#define VERSION "2.13" +#define VERSION "2.14" + +static int enable_ertm = 0; static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN; static u8 l2cap_fixed_chan[8] = { 0x02, }; @@ -331,6 +334,48 @@ static inline int l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 return hci_send_acl(conn->hcon, skb, 0); } +static inline int l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control) +{ + struct sk_buff *skb; + struct l2cap_hdr *lh; + struct l2cap_conn *conn = pi->conn; + int count, hlen = L2CAP_HDR_SIZE + 2; + + if (pi->fcs == L2CAP_FCS_CRC16) + hlen += 2; + + BT_DBG("pi %p, control 0x%2.2x", pi, control); + + count = min_t(unsigned int, conn->mtu, hlen); + control |= L2CAP_CTRL_FRAME_TYPE; + + skb = bt_skb_alloc(count, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh->len = cpu_to_le16(hlen - L2CAP_HDR_SIZE); + lh->cid = cpu_to_le16(pi->dcid); + put_unaligned_le16(control, skb_put(skb, 2)); + + if (pi->fcs == L2CAP_FCS_CRC16) { + u16 fcs = crc16(0, (u8 *)lh, count - 2); + put_unaligned_le16(fcs, skb_put(skb, 2)); + } + + return hci_send_acl(pi->conn->hcon, skb, 0); +} + +static inline int l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control) +{ + if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) + control |= L2CAP_SUPER_RCV_NOT_READY; + else + control |= L2CAP_SUPER_RCV_READY; + + return l2cap_send_sframe(pi, control); +} + static void l2cap_do_start(struct sock *sk) { struct l2cap_conn *conn = l2cap_pi(sk)->conn; @@ -364,6 +409,16 @@ static void l2cap_do_start(struct sock *sk) } } +static void l2cap_send_disconn_req(struct l2cap_conn *conn, struct sock *sk) +{ + struct l2cap_disconn_req req; + + req.dcid = cpu_to_le16(l2cap_pi(sk)->dcid); + req.scid = cpu_to_le16(l2cap_pi(sk)->scid); + l2cap_send_cmd(conn, l2cap_get_ident(conn), + L2CAP_DISCONN_REQ, sizeof(req), &req); +} + /* ---- L2CAP connections ---- */ static void l2cap_conn_start(struct l2cap_conn *conn) { @@ -648,15 +703,10 @@ static void __l2cap_sock_close(struct sock *sk, int reason) case BT_CONFIG: if (sk->sk_type == SOCK_SEQPACKET) { struct l2cap_conn *conn = l2cap_pi(sk)->conn; - struct l2cap_disconn_req req; sk->sk_state = BT_DISCONN; l2cap_sock_set_timer(sk, sk->sk_sndtimeo); - - req.dcid = cpu_to_le16(l2cap_pi(sk)->dcid); - req.scid = cpu_to_le16(l2cap_pi(sk)->scid); - l2cap_send_cmd(conn, l2cap_get_ident(conn), - L2CAP_DISCONN_REQ, sizeof(req), &req); + l2cap_send_disconn_req(conn, sk); } else l2cap_chan_del(sk, reason); break; @@ -715,12 +765,16 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) pi->imtu = l2cap_pi(parent)->imtu; pi->omtu = l2cap_pi(parent)->omtu; + pi->mode = l2cap_pi(parent)->mode; + pi->fcs = l2cap_pi(parent)->fcs; pi->sec_level = l2cap_pi(parent)->sec_level; pi->role_switch = l2cap_pi(parent)->role_switch; pi->force_reliable = l2cap_pi(parent)->force_reliable; } else { pi->imtu = L2CAP_DEFAULT_MTU; pi->omtu = 0; + pi->mode = L2CAP_MODE_BASIC; + pi->fcs = L2CAP_FCS_CRC16; pi->sec_level = BT_SECURITY_LOW; pi->role_switch = 0; pi->force_reliable = 0; @@ -956,6 +1010,19 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al goto done; } + switch (l2cap_pi(sk)->mode) { + case L2CAP_MODE_BASIC: + break; + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + if (enable_ertm) + break; + /* fall through */ + default: + err = -ENOTSUPP; + goto done; + } + switch (sk->sk_state) { case BT_CONNECT: case BT_CONNECT2: @@ -1007,6 +1074,19 @@ static int l2cap_sock_listen(struct socket *sock, int backlog) goto done; } + switch (l2cap_pi(sk)->mode) { + case L2CAP_MODE_BASIC: + break; + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + if (enable_ertm) + break; + /* fall through */ + default: + err = -ENOTSUPP; + goto done; + } + if (!l2cap_pi(sk)->psm) { bdaddr_t *src = &bt_sk(sk)->src; u16 psm; @@ -1117,39 +1197,219 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *l return 0; } -static inline int l2cap_do_send(struct sock *sk, struct msghdr *msg, int len) +static void l2cap_monitor_timeout(unsigned long arg) { - struct l2cap_conn *conn = l2cap_pi(sk)->conn; - struct sk_buff *skb, **frag; - int err, hlen, count, sent = 0; - struct l2cap_hdr *lh; + struct sock *sk = (void *) arg; + u16 control; - BT_DBG("sk %p len %d", sk, len); + bh_lock_sock(sk); + if (l2cap_pi(sk)->retry_count >= l2cap_pi(sk)->remote_max_tx) { + l2cap_send_disconn_req(l2cap_pi(sk)->conn, sk); + return; + } - /* First fragment (with L2CAP header) */ - if (sk->sk_type == SOCK_DGRAM) - hlen = L2CAP_HDR_SIZE + 2; - else - hlen = L2CAP_HDR_SIZE; + l2cap_pi(sk)->retry_count++; + __mod_monitor_timer(); - count = min_t(unsigned int, (conn->mtu - hlen), len); + control = L2CAP_CTRL_POLL; + l2cap_send_rr_or_rnr(l2cap_pi(sk), control); + bh_unlock_sock(sk); +} - skb = bt_skb_send_alloc(sk, hlen + count, - msg->msg_flags & MSG_DONTWAIT, &err); - if (!skb) - return err; +static void l2cap_retrans_timeout(unsigned long arg) +{ + struct sock *sk = (void *) arg; + u16 control; - /* Create L2CAP header */ - lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); - lh->cid = cpu_to_le16(l2cap_pi(sk)->dcid); - lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE)); + bh_lock_sock(sk); + l2cap_pi(sk)->retry_count = 1; + __mod_monitor_timer(); + + l2cap_pi(sk)->conn_state |= L2CAP_CONN_WAIT_F; + + control = L2CAP_CTRL_POLL; + l2cap_send_rr_or_rnr(l2cap_pi(sk), control); + bh_unlock_sock(sk); +} + +static void l2cap_drop_acked_frames(struct sock *sk) +{ + struct sk_buff *skb; + + while ((skb = skb_peek(TX_QUEUE(sk)))) { + if (bt_cb(skb)->tx_seq == l2cap_pi(sk)->expected_ack_seq) + break; + + skb = skb_dequeue(TX_QUEUE(sk)); + kfree_skb(skb); + + l2cap_pi(sk)->unacked_frames--; + } + + if (!l2cap_pi(sk)->unacked_frames) + del_timer(&l2cap_pi(sk)->retrans_timer); - if (sk->sk_type == SOCK_DGRAM) - put_unaligned(l2cap_pi(sk)->psm, (__le16 *) skb_put(skb, 2)); + return; +} + +static inline int l2cap_do_send(struct sock *sk, struct sk_buff *skb) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + int err; + + BT_DBG("sk %p, skb %p len %d", sk, skb, skb->len); + + err = hci_send_acl(pi->conn->hcon, skb, 0); + if (err < 0) + kfree_skb(skb); + + return err; +} + +static int l2cap_streaming_send(struct sock *sk) +{ + struct sk_buff *skb, *tx_skb; + struct l2cap_pinfo *pi = l2cap_pi(sk); + u16 control, fcs; + int err; + + while ((skb = sk->sk_send_head)) { + tx_skb = skb_clone(skb, GFP_ATOMIC); + + control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); + control |= pi->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT; + put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); + + if (l2cap_pi(sk)->fcs == L2CAP_FCS_CRC16) { + fcs = crc16(0, (u8 *)tx_skb->data, tx_skb->len - 2); + put_unaligned_le16(fcs, tx_skb->data + tx_skb->len - 2); + } + + err = l2cap_do_send(sk, tx_skb); + if (err < 0) { + l2cap_send_disconn_req(pi->conn, sk); + return err; + } + + pi->next_tx_seq = (pi->next_tx_seq + 1) % 64; + + if (skb_queue_is_last(TX_QUEUE(sk), skb)) + sk->sk_send_head = NULL; + else + sk->sk_send_head = skb_queue_next(TX_QUEUE(sk), skb); + + skb = skb_dequeue(TX_QUEUE(sk)); + kfree_skb(skb); + } + return 0; +} + +static int l2cap_retransmit_frame(struct sock *sk, u8 tx_seq) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + struct sk_buff *skb, *tx_skb; + u16 control, fcs; + int err; + + skb = skb_peek(TX_QUEUE(sk)); + do { + if (bt_cb(skb)->tx_seq != tx_seq) { + if (skb_queue_is_last(TX_QUEUE(sk), skb)) + break; + skb = skb_queue_next(TX_QUEUE(sk), skb); + continue; + } + + if (pi->remote_max_tx && + bt_cb(skb)->retries == pi->remote_max_tx) { + l2cap_send_disconn_req(pi->conn, sk); + break; + } + + tx_skb = skb_clone(skb, GFP_ATOMIC); + bt_cb(skb)->retries++; + control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); + control |= (pi->req_seq << L2CAP_CTRL_REQSEQ_SHIFT) + | (tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); + put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); + + if (l2cap_pi(sk)->fcs == L2CAP_FCS_CRC16) { + fcs = crc16(0, (u8 *)tx_skb->data, tx_skb->len - 2); + put_unaligned_le16(fcs, tx_skb->data + tx_skb->len - 2); + } + + err = l2cap_do_send(sk, tx_skb); + if (err < 0) { + l2cap_send_disconn_req(pi->conn, sk); + return err; + } + break; + } while(1); + return 0; +} + +static int l2cap_ertm_send(struct sock *sk) +{ + struct sk_buff *skb, *tx_skb; + struct l2cap_pinfo *pi = l2cap_pi(sk); + u16 control, fcs; + int err; + + if (pi->conn_state & L2CAP_CONN_WAIT_F) + return 0; + + while ((skb = sk->sk_send_head) && (!l2cap_tx_window_full(sk)) + && !(pi->conn_state & L2CAP_CONN_REMOTE_BUSY)) { + tx_skb = skb_clone(skb, GFP_ATOMIC); + + if (pi->remote_max_tx && + bt_cb(skb)->retries == pi->remote_max_tx) { + l2cap_send_disconn_req(pi->conn, sk); + break; + } + + bt_cb(skb)->retries++; + + control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); + control |= (pi->req_seq << L2CAP_CTRL_REQSEQ_SHIFT) + | (pi->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); + put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); + + + if (l2cap_pi(sk)->fcs == L2CAP_FCS_CRC16) { + fcs = crc16(0, (u8 *)skb->data, tx_skb->len - 2); + put_unaligned_le16(fcs, skb->data + tx_skb->len - 2); + } + + err = l2cap_do_send(sk, tx_skb); + if (err < 0) { + l2cap_send_disconn_req(pi->conn, sk); + return err; + } + __mod_retrans_timer(); + + bt_cb(skb)->tx_seq = pi->next_tx_seq; + pi->next_tx_seq = (pi->next_tx_seq + 1) % 64; + + pi->unacked_frames++; + + if (skb_queue_is_last(TX_QUEUE(sk), skb)) + sk->sk_send_head = NULL; + else + sk->sk_send_head = skb_queue_next(TX_QUEUE(sk), skb); + } + + return 0; +} + +static inline int l2cap_skbuff_fromiovec(struct sock *sk, struct msghdr *msg, int len, int count, struct sk_buff *skb) +{ + struct l2cap_conn *conn = l2cap_pi(sk)->conn; + struct sk_buff **frag; + int err, sent = 0; if (memcpy_fromiovec(skb_put(skb, count), msg->msg_iov, count)) { - err = -EFAULT; - goto fail; + return -EFAULT; } sent += count; @@ -1162,33 +1422,173 @@ static inline int l2cap_do_send(struct sock *sk, struct msghdr *msg, int len) *frag = bt_skb_send_alloc(sk, count, msg->msg_flags & MSG_DONTWAIT, &err); if (!*frag) - goto fail; - - if (memcpy_fromiovec(skb_put(*frag, count), msg->msg_iov, count)) { - err = -EFAULT; - goto fail; - } + return -EFAULT; + if (memcpy_fromiovec(skb_put(*frag, count), msg->msg_iov, count)) + return -EFAULT; sent += count; len -= count; frag = &(*frag)->next; } - err = hci_send_acl(conn->hcon, skb, 0); - if (err < 0) - goto fail; return sent; +} -fail: - kfree_skb(skb); - return err; +static struct sk_buff *l2cap_create_connless_pdu(struct sock *sk, struct msghdr *msg, size_t len) +{ + struct l2cap_conn *conn = l2cap_pi(sk)->conn; + struct sk_buff *skb; + int err, count, hlen = L2CAP_HDR_SIZE + 2; + struct l2cap_hdr *lh; + + BT_DBG("sk %p len %d", sk, (int)len); + + count = min_t(unsigned int, (conn->mtu - hlen), len); + skb = bt_skb_send_alloc(sk, count + hlen, + msg->msg_flags & MSG_DONTWAIT, &err); + if (!skb) + return ERR_PTR(-ENOMEM); + + /* Create L2CAP header */ + lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh->cid = cpu_to_le16(l2cap_pi(sk)->dcid); + lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE)); + put_unaligned_le16(l2cap_pi(sk)->psm, skb_put(skb, 2)); + + err = l2cap_skbuff_fromiovec(sk, msg, len, count, skb); + if (unlikely(err < 0)) { + kfree_skb(skb); + return ERR_PTR(err); + } + return skb; +} + +static struct sk_buff *l2cap_create_basic_pdu(struct sock *sk, struct msghdr *msg, size_t len) +{ + struct l2cap_conn *conn = l2cap_pi(sk)->conn; + struct sk_buff *skb; + int err, count, hlen = L2CAP_HDR_SIZE; + struct l2cap_hdr *lh; + + BT_DBG("sk %p len %d", sk, (int)len); + + count = min_t(unsigned int, (conn->mtu - hlen), len); + skb = bt_skb_send_alloc(sk, count + hlen, + msg->msg_flags & MSG_DONTWAIT, &err); + if (!skb) + return ERR_PTR(-ENOMEM); + + /* Create L2CAP header */ + lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh->cid = cpu_to_le16(l2cap_pi(sk)->dcid); + lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE)); + + err = l2cap_skbuff_fromiovec(sk, msg, len, count, skb); + if (unlikely(err < 0)) { + kfree_skb(skb); + return ERR_PTR(err); + } + return skb; +} + +static struct sk_buff *l2cap_create_iframe_pdu(struct sock *sk, struct msghdr *msg, size_t len, u16 control, u16 sdulen) +{ + struct l2cap_conn *conn = l2cap_pi(sk)->conn; + struct sk_buff *skb; + int err, count, hlen = L2CAP_HDR_SIZE + 2; + struct l2cap_hdr *lh; + + BT_DBG("sk %p len %d", sk, (int)len); + + if (sdulen) + hlen += 2; + + if (l2cap_pi(sk)->fcs == L2CAP_FCS_CRC16) + hlen += 2; + + count = min_t(unsigned int, (conn->mtu - hlen), len); + skb = bt_skb_send_alloc(sk, count + hlen, + msg->msg_flags & MSG_DONTWAIT, &err); + if (!skb) + return ERR_PTR(-ENOMEM); + + /* Create L2CAP header */ + lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh->cid = cpu_to_le16(l2cap_pi(sk)->dcid); + lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE)); + put_unaligned_le16(control, skb_put(skb, 2)); + if (sdulen) + put_unaligned_le16(sdulen, skb_put(skb, 2)); + + err = l2cap_skbuff_fromiovec(sk, msg, len, count, skb); + if (unlikely(err < 0)) { + kfree_skb(skb); + return ERR_PTR(err); + } + + if (l2cap_pi(sk)->fcs == L2CAP_FCS_CRC16) + put_unaligned_le16(0, skb_put(skb, 2)); + + bt_cb(skb)->retries = 0; + return skb; +} + +static inline int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, size_t len) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + struct sk_buff *skb; + struct sk_buff_head sar_queue; + u16 control; + size_t size = 0; + + __skb_queue_head_init(&sar_queue); + control = L2CAP_SDU_START; + skb = l2cap_create_iframe_pdu(sk, msg, pi->max_pdu_size, control, len); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + __skb_queue_tail(&sar_queue, skb); + len -= pi->max_pdu_size; + size +=pi->max_pdu_size; + control = 0; + + while (len > 0) { + size_t buflen; + + if (len > pi->max_pdu_size) { + control |= L2CAP_SDU_CONTINUE; + buflen = pi->max_pdu_size; + } else { + control |= L2CAP_SDU_END; + buflen = len; + } + + skb = l2cap_create_iframe_pdu(sk, msg, buflen, control, 0); + if (IS_ERR(skb)) { + skb_queue_purge(&sar_queue); + return PTR_ERR(skb); + } + + __skb_queue_tail(&sar_queue, skb); + len -= buflen; + size += buflen; + control = 0; + } + skb_queue_splice_tail(&sar_queue, TX_QUEUE(sk)); + if (sk->sk_send_head == NULL) + sk->sk_send_head = sar_queue.next; + + return size; } static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - int err = 0; + struct l2cap_pinfo *pi = l2cap_pi(sk); + struct sk_buff *skb; + u16 control; + int err; BT_DBG("sock %p, sk %p", sock, sk); @@ -1200,16 +1600,73 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms return -EOPNOTSUPP; /* Check outgoing MTU */ - if (sk->sk_type != SOCK_RAW && len > l2cap_pi(sk)->omtu) + if (sk->sk_type == SOCK_SEQPACKET && pi->mode == L2CAP_MODE_BASIC + && len > pi->omtu) return -EINVAL; lock_sock(sk); - if (sk->sk_state == BT_CONNECTED) - err = l2cap_do_send(sk, msg, len); - else + if (sk->sk_state != BT_CONNECTED) { err = -ENOTCONN; + goto done; + } + + /* Connectionless channel */ + if (sk->sk_type == SOCK_DGRAM) { + skb = l2cap_create_connless_pdu(sk, msg, len); + err = l2cap_do_send(sk, skb); + goto done; + } + + switch (pi->mode) { + case L2CAP_MODE_BASIC: + /* Create a basic PDU */ + skb = l2cap_create_basic_pdu(sk, msg, len); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + goto done; + } + + err = l2cap_do_send(sk, skb); + if (!err) + err = len; + break; + + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + /* Entire SDU fits into one PDU */ + if (len <= pi->max_pdu_size) { + control = L2CAP_SDU_UNSEGMENTED; + skb = l2cap_create_iframe_pdu(sk, msg, len, control, 0); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + goto done; + } + __skb_queue_tail(TX_QUEUE(sk), skb); + if (sk->sk_send_head == NULL) + sk->sk_send_head = skb; + } else { + /* Segment SDU into multiples PDUs */ + err = l2cap_sar_segment_sdu(sk, msg, len); + if (err < 0) + goto done; + } + + if (pi->mode == L2CAP_MODE_STREAMING) + err = l2cap_streaming_send(sk); + else + err = l2cap_ertm_send(sk); + + if (!err) + err = len; + break; + + default: + BT_DBG("bad state %1.1x", pi->mode); + err = -EINVAL; + } +done: release_sock(sk); return err; } @@ -1257,7 +1714,8 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us opts.imtu = l2cap_pi(sk)->imtu; opts.omtu = l2cap_pi(sk)->omtu; opts.flush_to = l2cap_pi(sk)->flush_to; - opts.mode = L2CAP_MODE_BASIC; + opts.mode = l2cap_pi(sk)->mode; + opts.fcs = l2cap_pi(sk)->fcs; len = min_t(unsigned int, sizeof(opts), optlen); if (copy_from_user((char *) &opts, optval, len)) { @@ -1265,8 +1723,10 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us break; } - l2cap_pi(sk)->imtu = opts.imtu; - l2cap_pi(sk)->omtu = opts.omtu; + l2cap_pi(sk)->imtu = opts.imtu; + l2cap_pi(sk)->omtu = opts.omtu; + l2cap_pi(sk)->mode = opts.mode; + l2cap_pi(sk)->fcs = opts.fcs; break; case L2CAP_LM: @@ -1379,7 +1839,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us opts.imtu = l2cap_pi(sk)->imtu; opts.omtu = l2cap_pi(sk)->omtu; opts.flush_to = l2cap_pi(sk)->flush_to; - opts.mode = L2CAP_MODE_BASIC; + opts.mode = l2cap_pi(sk)->mode; + opts.fcs = l2cap_pi(sk)->fcs; len = min_t(unsigned int, len, sizeof(opts)); if (copy_to_user(optval, (char *) &opts, len)) @@ -1708,16 +2169,108 @@ static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val) *ptr += L2CAP_CONF_OPT_SIZE + len; } +static int l2cap_mode_supported(__u8 mode, __u32 feat_mask) +{ + u32 local_feat_mask = l2cap_feat_mask; + if (enable_ertm) + local_feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING; + + switch (mode) { + case L2CAP_MODE_ERTM: + return L2CAP_FEAT_ERTM & feat_mask & local_feat_mask; + case L2CAP_MODE_STREAMING: + return L2CAP_FEAT_STREAMING & feat_mask & local_feat_mask; + default: + return 0x00; + } +} + +static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask) +{ + switch (mode) { + case L2CAP_MODE_STREAMING: + case L2CAP_MODE_ERTM: + if (l2cap_mode_supported(mode, remote_feat_mask)) + return mode; + /* fall through */ + default: + return L2CAP_MODE_BASIC; + } +} + static int l2cap_build_conf_req(struct sock *sk, void *data) { struct l2cap_pinfo *pi = l2cap_pi(sk); struct l2cap_conf_req *req = data; + struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_ERTM }; void *ptr = req->data; BT_DBG("sk %p", sk); - if (pi->imtu != L2CAP_DEFAULT_MTU) - l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->imtu); + if (pi->num_conf_req || pi->num_conf_rsp) + goto done; + + switch (pi->mode) { + case L2CAP_MODE_STREAMING: + case L2CAP_MODE_ERTM: + pi->conf_state |= L2CAP_CONF_STATE2_DEVICE; + if (!l2cap_mode_supported(pi->mode, pi->conn->feat_mask)) + l2cap_send_disconn_req(pi->conn, sk); + break; + default: + pi->mode = l2cap_select_mode(rfc.mode, pi->conn->feat_mask); + break; + } + +done: + switch (pi->mode) { + case L2CAP_MODE_BASIC: + if (pi->imtu != L2CAP_DEFAULT_MTU) + l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->imtu); + break; + + case L2CAP_MODE_ERTM: + rfc.mode = L2CAP_MODE_ERTM; + rfc.txwin_size = L2CAP_DEFAULT_TX_WINDOW; + rfc.max_transmit = L2CAP_DEFAULT_MAX_TX; + rfc.retrans_timeout = 0; + rfc.monitor_timeout = 0; + rfc.max_pdu_size = cpu_to_le16(L2CAP_DEFAULT_MAX_PDU_SIZE); + + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, + sizeof(rfc), (unsigned long) &rfc); + + if (!(pi->conn->feat_mask & L2CAP_FEAT_FCS)) + break; + + if (pi->fcs == L2CAP_FCS_NONE || + pi->conf_state & L2CAP_CONF_NO_FCS_RECV) { + pi->fcs = L2CAP_FCS_NONE; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1, pi->fcs); + } + break; + + case L2CAP_MODE_STREAMING: + rfc.mode = L2CAP_MODE_STREAMING; + rfc.txwin_size = 0; + rfc.max_transmit = 0; + rfc.retrans_timeout = 0; + rfc.monitor_timeout = 0; + rfc.max_pdu_size = cpu_to_le16(L2CAP_DEFAULT_MAX_PDU_SIZE); + + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, + sizeof(rfc), (unsigned long) &rfc); + + if (!(pi->conn->feat_mask & L2CAP_FEAT_FCS)) + break; + + if (pi->fcs == L2CAP_FCS_NONE || + pi->conf_state & L2CAP_CONF_NO_FCS_RECV) { + pi->fcs = L2CAP_FCS_NONE; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1, pi->fcs); + } + break; + } /* FIXME: Need actual value of the flush timeout */ //if (flush_to != L2CAP_DEFAULT_FLUSH_TO) @@ -1767,6 +2320,12 @@ static int l2cap_parse_conf_req(struct sock *sk, void *data) memcpy(&rfc, (void *) val, olen); break; + case L2CAP_CONF_FCS: + if (val == L2CAP_FCS_NONE) + pi->conf_state |= L2CAP_CONF_NO_FCS_RECV; + + break; + default: if (hint) break; @@ -1777,30 +2336,83 @@ static int l2cap_parse_conf_req(struct sock *sk, void *data) } } + if (pi->num_conf_rsp || pi->num_conf_req) + goto done; + + switch (pi->mode) { + case L2CAP_MODE_STREAMING: + case L2CAP_MODE_ERTM: + pi->conf_state |= L2CAP_CONF_STATE2_DEVICE; + if (!l2cap_mode_supported(pi->mode, pi->conn->feat_mask)) + return -ECONNREFUSED; + break; + default: + pi->mode = l2cap_select_mode(rfc.mode, pi->conn->feat_mask); + break; + } + +done: + if (pi->mode != rfc.mode) { + result = L2CAP_CONF_UNACCEPT; + rfc.mode = pi->mode; + + if (pi->num_conf_rsp == 1) + return -ECONNREFUSED; + + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, + sizeof(rfc), (unsigned long) &rfc); + } + + if (result == L2CAP_CONF_SUCCESS) { /* Configure output options and let the other side know * which ones we don't like. */ - if (rfc.mode == L2CAP_MODE_BASIC) { - if (mtu < pi->omtu) - result = L2CAP_CONF_UNACCEPT; - else { - pi->omtu = mtu; - pi->conf_state |= L2CAP_CONF_OUTPUT_DONE; - } + if (mtu < L2CAP_DEFAULT_MIN_MTU) + result = L2CAP_CONF_UNACCEPT; + else { + pi->omtu = mtu; + pi->conf_state |= L2CAP_CONF_MTU_DONE; + } + l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->omtu); - l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->omtu); - } else { + switch (rfc.mode) { + case L2CAP_MODE_BASIC: + pi->fcs = L2CAP_FCS_NONE; + pi->conf_state |= L2CAP_CONF_MODE_DONE; + break; + + case L2CAP_MODE_ERTM: + pi->remote_tx_win = rfc.txwin_size; + pi->remote_max_tx = rfc.max_transmit; + pi->max_pdu_size = rfc.max_pdu_size; + + rfc.retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; + rfc.monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; + + pi->conf_state |= L2CAP_CONF_MODE_DONE; + break; + + case L2CAP_MODE_STREAMING: + pi->remote_tx_win = rfc.txwin_size; + pi->max_pdu_size = rfc.max_pdu_size; + + pi->conf_state |= L2CAP_CONF_MODE_DONE; + break; + + default: result = L2CAP_CONF_UNACCEPT; memset(&rfc, 0, sizeof(rfc)); - rfc.mode = L2CAP_MODE_BASIC; - - l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, - sizeof(rfc), (unsigned long) &rfc); + rfc.mode = pi->mode; } - } + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, + sizeof(rfc), (unsigned long) &rfc); + + if (result == L2CAP_CONF_SUCCESS) + pi->conf_state |= L2CAP_CONF_OUTPUT_DONE; + } rsp->scid = cpu_to_le16(pi->dcid); rsp->result = cpu_to_le16(result); rsp->flags = cpu_to_le16(0x0000); @@ -1808,6 +2420,73 @@ static int l2cap_parse_conf_req(struct sock *sk, void *data) return ptr - data; } +static int l2cap_parse_conf_rsp(struct sock *sk, void *rsp, int len, void *data, u16 *result) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + struct l2cap_conf_req *req = data; + void *ptr = req->data; + int type, olen; + unsigned long val; + struct l2cap_conf_rfc rfc; + + BT_DBG("sk %p, rsp %p, len %d, req %p", sk, rsp, len, data); + + while (len >= L2CAP_CONF_OPT_SIZE) { + len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); + + switch (type) { + case L2CAP_CONF_MTU: + if (val < L2CAP_DEFAULT_MIN_MTU) { + *result = L2CAP_CONF_UNACCEPT; + pi->omtu = L2CAP_DEFAULT_MIN_MTU; + } else + pi->omtu = val; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->omtu); + break; + + case L2CAP_CONF_FLUSH_TO: + pi->flush_to = val; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_FLUSH_TO, + 2, pi->flush_to); + break; + + case L2CAP_CONF_RFC: + if (olen == sizeof(rfc)) + memcpy(&rfc, (void *)val, olen); + + if ((pi->conf_state & L2CAP_CONF_STATE2_DEVICE) && + rfc.mode != pi->mode) + return -ECONNREFUSED; + + pi->mode = rfc.mode; + pi->fcs = 0; + + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, + sizeof(rfc), (unsigned long) &rfc); + break; + } + } + + if (*result == L2CAP_CONF_SUCCESS) { + switch (rfc.mode) { + case L2CAP_MODE_ERTM: + pi->remote_tx_win = rfc.txwin_size; + pi->retrans_timeout = rfc.retrans_timeout; + pi->monitor_timeout = rfc.monitor_timeout; + pi->max_pdu_size = le16_to_cpu(rfc.max_pdu_size); + break; + case L2CAP_MODE_STREAMING: + pi->max_pdu_size = le16_to_cpu(rfc.max_pdu_size); + break; + } + } + + req->dcid = cpu_to_le16(pi->dcid); + req->flags = cpu_to_le16(0x0000); + + return ptr - data; +} + static int l2cap_build_conf_rsp(struct sock *sk, void *data, u16 result, u16 flags) { struct l2cap_conf_rsp *rsp = data; @@ -1994,6 +2673,7 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, l2cap_build_conf_req(sk, req), req); + l2cap_pi(sk)->num_conf_req++; break; case L2CAP_CR_PEND: @@ -2052,10 +2732,13 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr /* Complete config. */ len = l2cap_parse_conf_req(sk, rsp); - if (len < 0) + if (len < 0) { + l2cap_send_disconn_req(conn, sk); goto unlock; + } l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, len, rsp); + l2cap_pi(sk)->num_conf_rsp++; /* Reset config buffer. */ l2cap_pi(sk)->conf_len = 0; @@ -2064,7 +2747,22 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr goto unlock; if (l2cap_pi(sk)->conf_state & L2CAP_CONF_INPUT_DONE) { + if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) + || l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) + l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16; + sk->sk_state = BT_CONNECTED; + l2cap_pi(sk)->next_tx_seq = 0; + l2cap_pi(sk)->expected_ack_seq = 0; + l2cap_pi(sk)->unacked_frames = 0; + + setup_timer(&l2cap_pi(sk)->retrans_timer, + l2cap_retrans_timeout, (unsigned long) sk); + setup_timer(&l2cap_pi(sk)->monitor_timer, + l2cap_monitor_timeout, (unsigned long) sk); + + __skb_queue_head_init(TX_QUEUE(sk)); + __skb_queue_head_init(SREJ_QUEUE(sk)); l2cap_chan_ready(sk); goto unlock; } @@ -2073,6 +2771,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr u8 buf[64]; l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, l2cap_build_conf_req(sk, buf), buf); + l2cap_pi(sk)->num_conf_req++; } unlock: @@ -2102,29 +2801,32 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr break; case L2CAP_CONF_UNACCEPT: - if (++l2cap_pi(sk)->conf_retry < L2CAP_CONF_MAX_RETRIES) { - char req[128]; - /* It does not make sense to adjust L2CAP parameters - * that are currently defined in the spec. We simply - * resend config request that we sent earlier. It is - * stupid, but it helps qualification testing which - * expects at least some response from us. */ - l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, - l2cap_build_conf_req(sk, req), req); - goto done; + if (l2cap_pi(sk)->num_conf_rsp <= L2CAP_CONF_MAX_CONF_RSP) { + int len = cmd->len - sizeof(*rsp); + char req[64]; + + /* throw out any old stored conf requests */ + result = L2CAP_CONF_SUCCESS; + len = l2cap_parse_conf_rsp(sk, rsp->data, + len, req, &result); + if (len < 0) { + l2cap_send_disconn_req(conn, sk); + goto done; + } + + l2cap_send_cmd(conn, l2cap_get_ident(conn), + L2CAP_CONF_REQ, len, req); + l2cap_pi(sk)->num_conf_req++; + if (result != L2CAP_CONF_SUCCESS) + goto done; + break; } default: sk->sk_state = BT_DISCONN; sk->sk_err = ECONNRESET; l2cap_sock_set_timer(sk, HZ * 5); - { - struct l2cap_disconn_req req; - req.dcid = cpu_to_le16(l2cap_pi(sk)->dcid); - req.scid = cpu_to_le16(l2cap_pi(sk)->scid); - l2cap_send_cmd(conn, l2cap_get_ident(conn), - L2CAP_DISCONN_REQ, sizeof(req), &req); - } + l2cap_send_disconn_req(conn, sk); goto done; } @@ -2134,7 +2836,16 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr l2cap_pi(sk)->conf_state |= L2CAP_CONF_INPUT_DONE; if (l2cap_pi(sk)->conf_state & L2CAP_CONF_OUTPUT_DONE) { + if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) + || l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) + l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16; + sk->sk_state = BT_CONNECTED; + l2cap_pi(sk)->expected_tx_seq = 0; + l2cap_pi(sk)->buffer_seq = 0; + l2cap_pi(sk)->num_to_ack = 0; + __skb_queue_head_init(TX_QUEUE(sk)); + __skb_queue_head_init(SREJ_QUEUE(sk)); l2cap_chan_ready(sk); } @@ -2165,6 +2876,11 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd sk->sk_shutdown = SHUTDOWN_MASK; + skb_queue_purge(TX_QUEUE(sk)); + skb_queue_purge(SREJ_QUEUE(sk)); + del_timer(&l2cap_pi(sk)->retrans_timer); + del_timer(&l2cap_pi(sk)->monitor_timer); + l2cap_chan_del(sk, ECONNRESET); bh_unlock_sock(sk); @@ -2187,6 +2903,11 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd if (!sk) return 0; + skb_queue_purge(TX_QUEUE(sk)); + skb_queue_purge(SREJ_QUEUE(sk)); + del_timer(&l2cap_pi(sk)->retrans_timer); + del_timer(&l2cap_pi(sk)->monitor_timer); + l2cap_chan_del(sk, 0); bh_unlock_sock(sk); @@ -2205,10 +2926,14 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, struct l2cap_cm if (type == L2CAP_IT_FEAT_MASK) { u8 buf[8]; + u32 feat_mask = l2cap_feat_mask; struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf; rsp->type = cpu_to_le16(L2CAP_IT_FEAT_MASK); rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS); - put_unaligned(cpu_to_le32(l2cap_feat_mask), (__le32 *) rsp->data); + if (enable_ertm) + feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING + | L2CAP_FEAT_FCS; + put_unaligned_le32(feat_mask, rsp->data); l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf), buf); } else if (type == L2CAP_IT_FIXED_CHAN) { @@ -2359,9 +3084,374 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, struct sk_buff *sk kfree_skb(skb); } +static int l2cap_check_fcs(struct l2cap_pinfo *pi, struct sk_buff *skb) +{ + u16 our_fcs, rcv_fcs; + int hdr_size = L2CAP_HDR_SIZE + 2; + + if (pi->fcs == L2CAP_FCS_CRC16) { + skb_trim(skb, skb->len - 2); + rcv_fcs = get_unaligned_le16(skb->data + skb->len); + our_fcs = crc16(0, skb->data - hdr_size, skb->len + hdr_size); + + if (our_fcs != rcv_fcs) + return -EINVAL; + } + return 0; +} + +static void l2cap_add_to_srej_queue(struct sock *sk, struct sk_buff *skb, u8 tx_seq, u8 sar) +{ + struct sk_buff *next_skb; + + bt_cb(skb)->tx_seq = tx_seq; + bt_cb(skb)->sar = sar; + + next_skb = skb_peek(SREJ_QUEUE(sk)); + if (!next_skb) { + __skb_queue_tail(SREJ_QUEUE(sk), skb); + return; + } + + do { + if (bt_cb(next_skb)->tx_seq > tx_seq) { + __skb_queue_before(SREJ_QUEUE(sk), next_skb, skb); + return; + } + + if (skb_queue_is_last(SREJ_QUEUE(sk), next_skb)) + break; + + } while((next_skb = skb_queue_next(SREJ_QUEUE(sk), next_skb))); + + __skb_queue_tail(SREJ_QUEUE(sk), skb); +} + +static int l2cap_sar_reassembly_sdu(struct sock *sk, struct sk_buff *skb, u16 control) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + struct sk_buff *_skb; + int err = -EINVAL; + + switch (control & L2CAP_CTRL_SAR) { + case L2CAP_SDU_UNSEGMENTED: + if (pi->conn_state & L2CAP_CONN_SAR_SDU) { + kfree_skb(pi->sdu); + break; + } + + err = sock_queue_rcv_skb(sk, skb); + if (!err) + return 0; + + break; + + case L2CAP_SDU_START: + if (pi->conn_state & L2CAP_CONN_SAR_SDU) { + kfree_skb(pi->sdu); + break; + } + + pi->sdu_len = get_unaligned_le16(skb->data); + skb_pull(skb, 2); + + pi->sdu = bt_skb_alloc(pi->sdu_len, GFP_ATOMIC); + if (!pi->sdu) { + err = -ENOMEM; + break; + } + + memcpy(skb_put(pi->sdu, skb->len), skb->data, skb->len); + + pi->conn_state |= L2CAP_CONN_SAR_SDU; + pi->partial_sdu_len = skb->len; + err = 0; + break; + + case L2CAP_SDU_CONTINUE: + if (!(pi->conn_state & L2CAP_CONN_SAR_SDU)) + break; + + memcpy(skb_put(pi->sdu, skb->len), skb->data, skb->len); + + pi->partial_sdu_len += skb->len; + if (pi->partial_sdu_len > pi->sdu_len) + kfree_skb(pi->sdu); + else + err = 0; + + break; + + case L2CAP_SDU_END: + if (!(pi->conn_state & L2CAP_CONN_SAR_SDU)) + break; + + memcpy(skb_put(pi->sdu, skb->len), skb->data, skb->len); + + pi->conn_state &= ~L2CAP_CONN_SAR_SDU; + pi->partial_sdu_len += skb->len; + + if (pi->partial_sdu_len == pi->sdu_len) { + _skb = skb_clone(pi->sdu, GFP_ATOMIC); + err = sock_queue_rcv_skb(sk, _skb); + if (err < 0) + kfree_skb(_skb); + } + kfree_skb(pi->sdu); + err = 0; + + break; + } + + kfree_skb(skb); + return err; +} + +static void l2cap_check_srej_gap(struct sock *sk, u8 tx_seq) +{ + struct sk_buff *skb; + u16 control = 0; + + while((skb = skb_peek(SREJ_QUEUE(sk)))) { + if (bt_cb(skb)->tx_seq != tx_seq) + break; + + skb = skb_dequeue(SREJ_QUEUE(sk)); + control |= bt_cb(skb)->sar << L2CAP_CTRL_SAR_SHIFT; + l2cap_sar_reassembly_sdu(sk, skb, control); + l2cap_pi(sk)->buffer_seq_srej = + (l2cap_pi(sk)->buffer_seq_srej + 1) % 64; + tx_seq++; + } +} + +static void l2cap_resend_srejframe(struct sock *sk, u8 tx_seq) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + struct srej_list *l, *tmp; + u16 control; + + list_for_each_entry_safe(l,tmp, SREJ_LIST(sk), list) { + if (l->tx_seq == tx_seq) { + list_del(&l->list); + kfree(l); + return; + } + control = L2CAP_SUPER_SELECT_REJECT; + control |= l->tx_seq << L2CAP_CTRL_REQSEQ_SHIFT; + l2cap_send_sframe(pi, control); + list_del(&l->list); + list_add_tail(&l->list, SREJ_LIST(sk)); + } +} + +static void l2cap_send_srejframe(struct sock *sk, u8 tx_seq) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + struct srej_list *new; + u16 control; + + while (tx_seq != pi->expected_tx_seq) { + control = L2CAP_SUPER_SELECT_REJECT; + control |= pi->expected_tx_seq << L2CAP_CTRL_REQSEQ_SHIFT; + if (pi->conn_state & L2CAP_CONN_SEND_PBIT) { + control |= L2CAP_CTRL_POLL; + pi->conn_state &= ~L2CAP_CONN_SEND_PBIT; + } + l2cap_send_sframe(pi, control); + + new = kzalloc(sizeof(struct srej_list), GFP_ATOMIC); + new->tx_seq = pi->expected_tx_seq++; + list_add_tail(&new->list, SREJ_LIST(sk)); + } + pi->expected_tx_seq++; +} + +static inline int l2cap_data_channel_iframe(struct sock *sk, u16 rx_control, struct sk_buff *skb) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + u8 tx_seq = __get_txseq(rx_control); + u16 tx_control = 0; + u8 sar = rx_control >> L2CAP_CTRL_SAR_SHIFT; + int err = 0; + + BT_DBG("sk %p rx_control 0x%4.4x len %d", sk, rx_control, skb->len); + + if (tx_seq == pi->expected_tx_seq) + goto expected; + + if (pi->conn_state & L2CAP_CONN_SREJ_SENT) { + struct srej_list *first; + + first = list_first_entry(SREJ_LIST(sk), + struct srej_list, list); + if (tx_seq == first->tx_seq) { + l2cap_add_to_srej_queue(sk, skb, tx_seq, sar); + l2cap_check_srej_gap(sk, tx_seq); + + list_del(&first->list); + kfree(first); + + if (list_empty(SREJ_LIST(sk))) { + pi->buffer_seq = pi->buffer_seq_srej; + pi->conn_state &= ~L2CAP_CONN_SREJ_SENT; + } + } else { + struct srej_list *l; + l2cap_add_to_srej_queue(sk, skb, tx_seq, sar); + + list_for_each_entry(l, SREJ_LIST(sk), list) { + if (l->tx_seq == tx_seq) { + l2cap_resend_srejframe(sk, tx_seq); + return 0; + } + } + l2cap_send_srejframe(sk, tx_seq); + } + } else { + pi->conn_state |= L2CAP_CONN_SREJ_SENT; + + INIT_LIST_HEAD(SREJ_LIST(sk)); + pi->buffer_seq_srej = pi->buffer_seq; + + __skb_queue_head_init(SREJ_QUEUE(sk)); + l2cap_add_to_srej_queue(sk, skb, tx_seq, sar); + + pi->conn_state |= L2CAP_CONN_SEND_PBIT; + + l2cap_send_srejframe(sk, tx_seq); + } + return 0; + +expected: + pi->expected_tx_seq = (pi->expected_tx_seq + 1) % 64; + + if (pi->conn_state & L2CAP_CONN_SREJ_SENT) { + l2cap_add_to_srej_queue(sk, skb, tx_seq, sar); + return 0; + } + + pi->buffer_seq = (pi->buffer_seq + 1) % 64; + + err = l2cap_sar_reassembly_sdu(sk, skb, rx_control); + if (err < 0) + return err; + + pi->num_to_ack = (pi->num_to_ack + 1) % L2CAP_DEFAULT_NUM_TO_ACK; + if (pi->num_to_ack == L2CAP_DEFAULT_NUM_TO_ACK - 1) { + tx_control |= L2CAP_SUPER_RCV_READY; + tx_control |= pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; + l2cap_send_sframe(pi, tx_control); + } + return 0; +} + +static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, struct sk_buff *skb) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + u8 tx_seq = __get_reqseq(rx_control); + + BT_DBG("sk %p rx_control 0x%4.4x len %d", sk, rx_control, skb->len); + + switch (rx_control & L2CAP_CTRL_SUPERVISE) { + case L2CAP_SUPER_RCV_READY: + if (rx_control & L2CAP_CTRL_POLL) { + u16 control = L2CAP_CTRL_FINAL; + control |= L2CAP_SUPER_RCV_READY | + (pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT); + l2cap_send_sframe(l2cap_pi(sk), control); + pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + + } else if (rx_control & L2CAP_CTRL_FINAL) { + pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + pi->expected_ack_seq = tx_seq; + l2cap_drop_acked_frames(sk); + + if (!(pi->conn_state & L2CAP_CONN_WAIT_F)) + break; + + pi->conn_state &= ~L2CAP_CONN_WAIT_F; + del_timer(&pi->monitor_timer); + + if (pi->unacked_frames > 0) + __mod_retrans_timer(); + } else { + pi->expected_ack_seq = tx_seq; + l2cap_drop_acked_frames(sk); + + if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) + && (pi->unacked_frames > 0)) + __mod_retrans_timer(); + + l2cap_ertm_send(sk); + pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + } + break; + + case L2CAP_SUPER_REJECT: + pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + + pi->expected_ack_seq = __get_reqseq(rx_control); + l2cap_drop_acked_frames(sk); + + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + + l2cap_ertm_send(sk); + + break; + + case L2CAP_SUPER_SELECT_REJECT: + pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + + if (rx_control & L2CAP_CTRL_POLL) { + l2cap_retransmit_frame(sk, tx_seq); + pi->expected_ack_seq = tx_seq; + l2cap_drop_acked_frames(sk); + l2cap_ertm_send(sk); + if (pi->conn_state & L2CAP_CONN_WAIT_F) { + pi->srej_save_reqseq = tx_seq; + pi->conn_state |= L2CAP_CONN_SREJ_ACT; + } + } else if (rx_control & L2CAP_CTRL_FINAL) { + if ((pi->conn_state & L2CAP_CONN_SREJ_ACT) && + pi->srej_save_reqseq == tx_seq) + pi->srej_save_reqseq &= ~L2CAP_CONN_SREJ_ACT; + else + l2cap_retransmit_frame(sk, tx_seq); + } + else { + l2cap_retransmit_frame(sk, tx_seq); + if (pi->conn_state & L2CAP_CONN_WAIT_F) { + pi->srej_save_reqseq = tx_seq; + pi->conn_state |= L2CAP_CONN_SREJ_ACT; + } + } + break; + + case L2CAP_SUPER_RCV_NOT_READY: + pi->conn_state |= L2CAP_CONN_REMOTE_BUSY; + pi->expected_ack_seq = tx_seq; + l2cap_drop_acked_frames(sk); + + del_timer(&l2cap_pi(sk)->retrans_timer); + if (rx_control & L2CAP_CTRL_POLL) { + u16 control = L2CAP_CTRL_FINAL; + l2cap_send_rr_or_rnr(l2cap_pi(sk), control); + } + break; + } + + return 0; +} + static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk_buff *skb) { struct sock *sk; + struct l2cap_pinfo *pi; + u16 control, len; + u8 tx_seq; + int err; sk = l2cap_get_chan_by_scid(&conn->chan_list, cid); if (!sk) { @@ -2369,22 +3459,91 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk goto drop; } + pi = l2cap_pi(sk); + BT_DBG("sk %p, len %d", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; - if (l2cap_pi(sk)->imtu < skb->len) - goto drop; + switch (pi->mode) { + case L2CAP_MODE_BASIC: + /* If socket recv buffers overflows we drop data here + * which is *bad* because L2CAP has to be reliable. + * But we don't have any other choice. L2CAP doesn't + * provide flow control mechanism. */ - /* If socket recv buffers overflows we drop data here - * which is *bad* because L2CAP has to be reliable. - * But we don't have any other choice. L2CAP doesn't - * provide flow control mechanism. */ + if (pi->imtu < skb->len) + goto drop; + + if (!sock_queue_rcv_skb(sk, skb)) + goto done; + break; + + case L2CAP_MODE_ERTM: + control = get_unaligned_le16(skb->data); + skb_pull(skb, 2); + len = skb->len; + + if (__is_sar_start(control)) + len -= 2; + + if (pi->fcs == L2CAP_FCS_CRC16) + len -= 2; + + /* + * We can just drop the corrupted I-frame here. + * Receiver will miss it and start proper recovery + * procedures and ask retransmission. + */ + if (len > L2CAP_DEFAULT_MAX_PDU_SIZE) + goto drop; + + if (l2cap_check_fcs(pi, skb)) + goto drop; + + if (__is_iframe(control)) + err = l2cap_data_channel_iframe(sk, control, skb); + else + err = l2cap_data_channel_sframe(sk, control, skb); + + if (!err) + goto done; + break; + + case L2CAP_MODE_STREAMING: + control = get_unaligned_le16(skb->data); + skb_pull(skb, 2); + len = skb->len; + + if (__is_sar_start(control)) + len -= 2; + + if (pi->fcs == L2CAP_FCS_CRC16) + len -= 2; + + if (len > L2CAP_DEFAULT_MAX_PDU_SIZE || __is_sframe(control)) + goto drop; + + if (l2cap_check_fcs(pi, skb)) + goto drop; + + tx_seq = __get_txseq(control); + + if (pi->expected_tx_seq == tx_seq) + pi->expected_tx_seq = (pi->expected_tx_seq + 1) % 64; + else + pi->expected_tx_seq = tx_seq + 1; + + err = l2cap_sar_reassembly_sdu(sk, skb, control); - if (!sock_queue_rcv_skb(sk, skb)) goto done; + default: + BT_DBG("sk %p: bad mode 0x%2.2x", sk, l2cap_pi(sk)->mode); + break; + } + drop: kfree_skb(skb); @@ -2433,6 +3592,11 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) cid = __le16_to_cpu(lh->cid); len = __le16_to_cpu(lh->len); + if (len != skb->len) { + kfree_skb(skb); + return; + } + BT_DBG("len %d, cid 0x%4.4x", len, cid); switch (cid) { @@ -2441,7 +3605,7 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) break; case L2CAP_CID_CONN_LESS: - psm = get_unaligned((__le16 *) skb->data); + psm = get_unaligned_le16(skb->data); skb_pull(skb, 2); l2cap_conless_channel(conn, psm, skb); break; @@ -2828,6 +3992,9 @@ EXPORT_SYMBOL(l2cap_load); module_init(l2cap_init); module_exit(l2cap_exit); +module_param(enable_ertm, bool, 0644); +MODULE_PARM_DESC(enable_ertm, "Enable enhanced retransmission mode"); + MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth L2CAP ver " VERSION); MODULE_VERSION(VERSION); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index e50566ebf9f9..25692bc0a342 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -244,6 +244,33 @@ static inline int rfcomm_check_security(struct rfcomm_dlc *d) auth_type); } +static void rfcomm_session_timeout(unsigned long arg) +{ + struct rfcomm_session *s = (void *) arg; + + BT_DBG("session %p state %ld", s, s->state); + + set_bit(RFCOMM_TIMED_OUT, &s->flags); + rfcomm_session_put(s); + rfcomm_schedule(RFCOMM_SCHED_TIMEO); +} + +static void rfcomm_session_set_timer(struct rfcomm_session *s, long timeout) +{ + BT_DBG("session %p state %ld timeout %ld", s, s->state, timeout); + + if (!mod_timer(&s->timer, jiffies + timeout)) + rfcomm_session_hold(s); +} + +static void rfcomm_session_clear_timer(struct rfcomm_session *s) +{ + BT_DBG("session %p state %ld", s, s->state); + + if (timer_pending(&s->timer) && del_timer(&s->timer)) + rfcomm_session_put(s); +} + /* ---- RFCOMM DLCs ---- */ static void rfcomm_dlc_timeout(unsigned long arg) { @@ -320,6 +347,7 @@ static void rfcomm_dlc_link(struct rfcomm_session *s, struct rfcomm_dlc *d) rfcomm_session_hold(s); + rfcomm_session_clear_timer(s); rfcomm_dlc_hold(d); list_add(&d->list, &s->dlcs); d->session = s; @@ -335,6 +363,9 @@ static void rfcomm_dlc_unlink(struct rfcomm_dlc *d) d->session = NULL; rfcomm_dlc_put(d); + if (list_empty(&s->dlcs)) + rfcomm_session_set_timer(s, RFCOMM_IDLE_TIMEOUT); + rfcomm_session_put(s); } @@ -567,6 +598,8 @@ static struct rfcomm_session *rfcomm_session_add(struct socket *sock, int state) BT_DBG("session %p sock %p", s, sock); + setup_timer(&s->timer, rfcomm_session_timeout, (unsigned long) s); + INIT_LIST_HEAD(&s->dlcs); s->state = state; s->sock = sock; @@ -598,6 +631,7 @@ static void rfcomm_session_del(struct rfcomm_session *s) if (state == BT_CONNECTED) rfcomm_send_disc(s, 0); + rfcomm_session_clear_timer(s); sock_release(s->sock); kfree(s); @@ -639,6 +673,7 @@ static void rfcomm_session_close(struct rfcomm_session *s, int err) __rfcomm_dlc_close(d, err); } + rfcomm_session_clear_timer(s); rfcomm_session_put(s); } @@ -1879,6 +1914,12 @@ static inline void rfcomm_process_sessions(void) struct rfcomm_session *s; s = list_entry(p, struct rfcomm_session, list); + if (test_and_clear_bit(RFCOMM_TIMED_OUT, &s->flags)) { + s->state = BT_DISCONN; + rfcomm_send_disc(s, 0); + continue; + } + if (s->state == BT_LISTEN) { rfcomm_accept_connection(s); continue; @@ -2080,28 +2121,43 @@ static CLASS_ATTR(rfcomm_dlc, S_IRUGO, rfcomm_dlc_sysfs_show, NULL); /* ---- Initialization ---- */ static int __init rfcomm_init(void) { + int err; + l2cap_load(); hci_register_cb(&rfcomm_cb); rfcomm_thread = kthread_run(rfcomm_run, NULL, "krfcommd"); if (IS_ERR(rfcomm_thread)) { - hci_unregister_cb(&rfcomm_cb); - return PTR_ERR(rfcomm_thread); + err = PTR_ERR(rfcomm_thread); + goto unregister; } if (class_create_file(bt_class, &class_attr_rfcomm_dlc) < 0) BT_ERR("Failed to create RFCOMM info file"); - rfcomm_init_sockets(); + err = rfcomm_init_ttys(); + if (err < 0) + goto stop; -#ifdef CONFIG_BT_RFCOMM_TTY - rfcomm_init_ttys(); -#endif + err = rfcomm_init_sockets(); + if (err < 0) + goto cleanup; BT_INFO("RFCOMM ver %s", VERSION); return 0; + +cleanup: + rfcomm_cleanup_ttys(); + +stop: + kthread_stop(rfcomm_thread); + +unregister: + hci_unregister_cb(&rfcomm_cb); + + return err; } static void __exit rfcomm_exit(void) @@ -2112,9 +2168,7 @@ static void __exit rfcomm_exit(void) kthread_stop(rfcomm_thread); -#ifdef CONFIG_BT_RFCOMM_TTY rfcomm_cleanup_ttys(); -#endif rfcomm_cleanup_sockets(); } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 7f482784e9f7..0b85e8116859 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -1132,7 +1132,7 @@ error: return err; } -void __exit rfcomm_cleanup_sockets(void) +void rfcomm_cleanup_sockets(void) { class_remove_file(bt_class, &class_attr_rfcomm); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 51ae0c3e470a..13c27f17192c 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -359,20 +359,9 @@ static void sco_sock_kill(struct sock *sk) sock_put(sk); } -/* Close socket. - * Must be called on unlocked socket. - */ -static void sco_sock_close(struct sock *sk) +static void __sco_sock_close(struct sock *sk) { - struct sco_conn *conn; - - sco_sock_clear_timer(sk); - - lock_sock(sk); - - conn = sco_pi(sk)->conn; - - BT_DBG("sk %p state %d conn %p socket %p", sk, sk->sk_state, conn, sk->sk_socket); + BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); switch (sk->sk_state) { case BT_LISTEN: @@ -390,9 +379,15 @@ static void sco_sock_close(struct sock *sk) sock_set_flag(sk, SOCK_ZAPPED); break; } +} +/* Must be called on unlocked socket. */ +static void sco_sock_close(struct sock *sk) +{ + sco_sock_clear_timer(sk); + lock_sock(sk); + __sco_sock_close(sk); release_sock(sk); - sco_sock_kill(sk); } @@ -748,6 +743,30 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char return err; } +static int sco_sock_shutdown(struct socket *sock, int how) +{ + struct sock *sk = sock->sk; + int err = 0; + + BT_DBG("sock %p, sk %p", sock, sk); + + if (!sk) + return 0; + + lock_sock(sk); + if (!sk->sk_shutdown) { + sk->sk_shutdown = SHUTDOWN_MASK; + sco_sock_clear_timer(sk); + __sco_sock_close(sk); + + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + err = bt_sock_wait_state(sk, BT_CLOSED, + sk->sk_lingertime); + } + release_sock(sk); + return err; +} + static int sco_sock_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -969,7 +988,7 @@ static const struct proto_ops sco_sock_ops = { .ioctl = bt_sock_ioctl, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, - .shutdown = sock_no_shutdown, + .shutdown = sco_sock_shutdown, .setsockopt = sco_sock_setsockopt, .getsockopt = sco_sock_getsockopt }; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 15d43ba86b53..07a07770c8b6 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -20,7 +20,7 @@ #include "br_private.h" /* net device transmit always called with no BH (preempt_disabled) */ -int br_dev_xmit(struct sk_buff *skb, struct net_device *dev) +netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); const unsigned char *dest = skb->data; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index d2c27c808d3b..bc1704ac6cd9 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -22,7 +22,8 @@ static inline int should_deliver(const struct net_bridge_port *p, const struct sk_buff *skb) { - return (skb->dev != p->dev && p->state == BR_STATE_FORWARDING); + return (((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && + p->state == BR_STATE_FORWARDING); } static inline unsigned packet_length(const struct sk_buff *skb) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index eb404dc3ed6e..e486f1fc3632 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -256,6 +256,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, p->path_cost = port_cost(dev); p->priority = 0x8000 >> BR_PORT_BITS; p->port_no = index; + p->flags = 0; br_init_port(p); p->state = BR_STATE_DISABLED; br_stp_port_timer_init(p); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d5b5537272b4..2114e45682ea 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -81,6 +81,9 @@ struct net_bridge_port struct timer_list message_age_timer; struct kobject kobj; struct rcu_head rcu; + + unsigned long flags; +#define BR_HAIRPIN_MODE 0x00000001 }; struct net_bridge @@ -140,7 +143,8 @@ static inline int br_is_root_bridge(const struct net_bridge *br) /* br_device.c */ extern void br_dev_setup(struct net_device *dev); -extern int br_dev_xmit(struct sk_buff *skb, struct net_device *dev); +extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, + struct net_device *dev); /* br_fdb.c */ extern int br_fdb_init(void); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 4a3cdf8f3813..820643a3ba9c 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -143,6 +143,22 @@ static ssize_t store_flush(struct net_bridge_port *p, unsigned long v) } static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush); +static ssize_t show_hairpin_mode(struct net_bridge_port *p, char *buf) +{ + int hairpin_mode = (p->flags & BR_HAIRPIN_MODE) ? 1 : 0; + return sprintf(buf, "%d\n", hairpin_mode); +} +static ssize_t store_hairpin_mode(struct net_bridge_port *p, unsigned long v) +{ + if (v) + p->flags |= BR_HAIRPIN_MODE; + else + p->flags &= ~BR_HAIRPIN_MODE; + return 0; +} +static BRPORT_ATTR(hairpin_mode, S_IRUGO | S_IWUSR, + show_hairpin_mode, store_hairpin_mode); + static struct brport_attribute *brport_attrs[] = { &brport_attr_path_cost, &brport_attr_priority, @@ -159,6 +175,7 @@ static struct brport_attribute *brport_attrs[] = { &brport_attr_forward_delay_timer, &brport_attr_hold_timer, &brport_attr_flush, + &brport_attr_hairpin_mode, NULL }; diff --git a/net/can/af_can.c b/net/can/af_can.c index e733725b11d4..ef1c43a2ed56 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -651,12 +651,16 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, struct can_frame *cf = (struct can_frame *)skb->data; int matches; - if (dev->type != ARPHRD_CAN || !net_eq(dev_net(dev), &init_net)) { - kfree_skb(skb); - return 0; - } + if (!net_eq(dev_net(dev), &init_net)) + goto drop; - BUG_ON(skb->len != sizeof(struct can_frame) || cf->can_dlc > 8); + if (WARN_ONCE(dev->type != ARPHRD_CAN || + skb->len != sizeof(struct can_frame) || + cf->can_dlc > 8, + "PF_CAN: dropped non conform skbuf: " + "dev type %d, len %d, can_dlc %d\n", + dev->type, skb->len, cf->can_dlc)) + goto drop; /* update statistics */ can_stats.rx_frames++; @@ -682,7 +686,11 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, can_stats.matches_delta++; } - return 0; + return NET_RX_SUCCESS; + +drop: + kfree_skb(skb); + return NET_RX_DROP; } /* diff --git a/net/can/bcm.c b/net/can/bcm.c index 72720c710351..597da4f8f888 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -46,6 +46,7 @@ #include <linux/hrtimer.h> #include <linux/list.h> #include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/netdevice.h> @@ -146,23 +147,18 @@ static char *bcm_proc_getifname(int ifindex) return "???"; } -static int bcm_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) +static int bcm_proc_show(struct seq_file *m, void *v) { - int len = 0; - struct sock *sk = (struct sock *)data; + struct sock *sk = (struct sock *)m->private; struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; - len += snprintf(page + len, PAGE_SIZE - len, ">>> socket %p", - sk->sk_socket); - len += snprintf(page + len, PAGE_SIZE - len, " / sk %p", sk); - len += snprintf(page + len, PAGE_SIZE - len, " / bo %p", bo); - len += snprintf(page + len, PAGE_SIZE - len, " / dropped %lu", - bo->dropped_usr_msgs); - len += snprintf(page + len, PAGE_SIZE - len, " / bound %s", - bcm_proc_getifname(bo->ifindex)); - len += snprintf(page + len, PAGE_SIZE - len, " <<<\n"); + seq_printf(m, ">>> socket %p", sk->sk_socket); + seq_printf(m, " / sk %p", sk); + seq_printf(m, " / bo %p", bo); + seq_printf(m, " / dropped %lu", bo->dropped_usr_msgs); + seq_printf(m, " / bound %s", bcm_proc_getifname(bo->ifindex)); + seq_printf(m, " <<<\n"); list_for_each_entry(op, &bo->rx_ops, list) { @@ -172,71 +168,62 @@ static int bcm_read_proc(char *page, char **start, off_t off, if (!op->frames_abs) continue; - len += snprintf(page + len, PAGE_SIZE - len, - "rx_op: %03X %-5s ", + seq_printf(m, "rx_op: %03X %-5s ", op->can_id, bcm_proc_getifname(op->ifindex)); - len += snprintf(page + len, PAGE_SIZE - len, "[%d]%c ", - op->nframes, + seq_printf(m, "[%d]%c ", op->nframes, (op->flags & RX_CHECK_DLC)?'d':' '); if (op->kt_ival1.tv64) - len += snprintf(page + len, PAGE_SIZE - len, - "timeo=%lld ", + seq_printf(m, "timeo=%lld ", (long long) ktime_to_us(op->kt_ival1)); if (op->kt_ival2.tv64) - len += snprintf(page + len, PAGE_SIZE - len, - "thr=%lld ", + seq_printf(m, "thr=%lld ", (long long) ktime_to_us(op->kt_ival2)); - len += snprintf(page + len, PAGE_SIZE - len, - "# recv %ld (%ld) => reduction: ", + seq_printf(m, "# recv %ld (%ld) => reduction: ", op->frames_filtered, op->frames_abs); reduction = 100 - (op->frames_filtered * 100) / op->frames_abs; - len += snprintf(page + len, PAGE_SIZE - len, "%s%ld%%\n", + seq_printf(m, "%s%ld%%\n", (reduction == 100)?"near ":"", reduction); - - if (len > PAGE_SIZE - 200) { - /* mark output cut off */ - len += snprintf(page + len, PAGE_SIZE - len, "(..)\n"); - break; - } } list_for_each_entry(op, &bo->tx_ops, list) { - len += snprintf(page + len, PAGE_SIZE - len, - "tx_op: %03X %s [%d] ", + seq_printf(m, "tx_op: %03X %s [%d] ", op->can_id, bcm_proc_getifname(op->ifindex), op->nframes); if (op->kt_ival1.tv64) - len += snprintf(page + len, PAGE_SIZE - len, "t1=%lld ", + seq_printf(m, "t1=%lld ", (long long) ktime_to_us(op->kt_ival1)); if (op->kt_ival2.tv64) - len += snprintf(page + len, PAGE_SIZE - len, "t2=%lld ", + seq_printf(m, "t2=%lld ", (long long) ktime_to_us(op->kt_ival2)); - len += snprintf(page + len, PAGE_SIZE - len, "# sent %ld\n", - op->frames_abs); - - if (len > PAGE_SIZE - 100) { - /* mark output cut off */ - len += snprintf(page + len, PAGE_SIZE - len, "(..)\n"); - break; - } + seq_printf(m, "# sent %ld\n", op->frames_abs); } + seq_putc(m, '\n'); + return 0; +} - len += snprintf(page + len, PAGE_SIZE - len, "\n"); - - *eof = 1; - return len; +static int bcm_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, bcm_proc_show, PDE(inode)->data); } +static const struct file_operations bcm_proc_fops = { + .owner = THIS_MODULE, + .open = bcm_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + /* * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface * of the given bcm tx op @@ -1515,9 +1502,9 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, if (proc_dir) { /* unique socket address as filename */ sprintf(bo->procname, "%p", sock); - bo->bcm_proc_read = create_proc_read_entry(bo->procname, 0644, - proc_dir, - bcm_read_proc, sk); + bo->bcm_proc_read = proc_create_data(bo->procname, 0644, + proc_dir, + &bcm_proc_fops, sk); } return 0; diff --git a/net/can/proc.c b/net/can/proc.c index 1463653dbe34..9b9ad29be567 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -196,8 +196,8 @@ void can_stat_update(unsigned long data) * */ -static int can_print_rcvlist(char *page, int len, struct hlist_head *rx_list, - struct net_device *dev) +static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, + struct net_device *dev) { struct receiver *r; struct hlist_node *n; @@ -208,199 +208,188 @@ static int can_print_rcvlist(char *page, int len, struct hlist_head *rx_list, " %-5s %08X %08x %08x %08x %8ld %s\n" : " %-5s %03X %08x %08lx %08lx %8ld %s\n"; - len += snprintf(page + len, PAGE_SIZE - len, fmt, - DNAME(dev), r->can_id, r->mask, + seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask, (unsigned long)r->func, (unsigned long)r->data, r->matches, r->ident); - - /* does a typical line fit into the current buffer? */ - - /* 100 Bytes before end of buffer */ - if (len > PAGE_SIZE - 100) { - /* mark output cut off */ - len += snprintf(page + len, PAGE_SIZE - len, - " (..)\n"); - break; - } } rcu_read_unlock(); - - return len; } -static int can_print_recv_banner(char *page, int len) +static void can_print_recv_banner(struct seq_file *m) { /* * can1. 00000000 00000000 00000000 * ....... 0 tp20 */ - len += snprintf(page + len, PAGE_SIZE - len, - " device can_id can_mask function" + seq_puts(m, " device can_id can_mask function" " userdata matches ident\n"); - - return len; } -static int can_proc_read_stats(char *page, char **start, off_t off, - int count, int *eof, void *data) +static int can_stats_proc_show(struct seq_file *m, void *v) { - int len = 0; + seq_putc(m, '\n'); + seq_printf(m, " %8ld transmitted frames (TXF)\n", can_stats.tx_frames); + seq_printf(m, " %8ld received frames (RXF)\n", can_stats.rx_frames); + seq_printf(m, " %8ld matched frames (RXMF)\n", can_stats.matches); - len += snprintf(page + len, PAGE_SIZE - len, "\n"); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld transmitted frames (TXF)\n", - can_stats.tx_frames); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld received frames (RXF)\n", can_stats.rx_frames); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld matched frames (RXMF)\n", can_stats.matches); - - len += snprintf(page + len, PAGE_SIZE - len, "\n"); + seq_putc(m, '\n'); if (can_stattimer.function == can_stat_update) { - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld %% total match ratio (RXMR)\n", + seq_printf(m, " %8ld %% total match ratio (RXMR)\n", can_stats.total_rx_match_ratio); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld frames/s total tx rate (TXR)\n", + seq_printf(m, " %8ld frames/s total tx rate (TXR)\n", can_stats.total_tx_rate); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld frames/s total rx rate (RXR)\n", + seq_printf(m, " %8ld frames/s total rx rate (RXR)\n", can_stats.total_rx_rate); - len += snprintf(page + len, PAGE_SIZE - len, "\n"); + seq_putc(m, '\n'); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld %% current match ratio (CRXMR)\n", + seq_printf(m, " %8ld %% current match ratio (CRXMR)\n", can_stats.current_rx_match_ratio); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld frames/s current tx rate (CTXR)\n", + seq_printf(m, " %8ld frames/s current tx rate (CTXR)\n", can_stats.current_tx_rate); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld frames/s current rx rate (CRXR)\n", + seq_printf(m, " %8ld frames/s current rx rate (CRXR)\n", can_stats.current_rx_rate); - len += snprintf(page + len, PAGE_SIZE - len, "\n"); + seq_putc(m, '\n'); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld %% max match ratio (MRXMR)\n", + seq_printf(m, " %8ld %% max match ratio (MRXMR)\n", can_stats.max_rx_match_ratio); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld frames/s max tx rate (MTXR)\n", + seq_printf(m, " %8ld frames/s max tx rate (MTXR)\n", can_stats.max_tx_rate); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld frames/s max rx rate (MRXR)\n", + seq_printf(m, " %8ld frames/s max rx rate (MRXR)\n", can_stats.max_rx_rate); - len += snprintf(page + len, PAGE_SIZE - len, "\n"); + seq_putc(m, '\n'); } - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld current receive list entries (CRCV)\n", + seq_printf(m, " %8ld current receive list entries (CRCV)\n", can_pstats.rcv_entries); - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld maximum receive list entries (MRCV)\n", + seq_printf(m, " %8ld maximum receive list entries (MRCV)\n", can_pstats.rcv_entries_max); if (can_pstats.stats_reset) - len += snprintf(page + len, PAGE_SIZE - len, - "\n %8ld statistic resets (STR)\n", + seq_printf(m, "\n %8ld statistic resets (STR)\n", can_pstats.stats_reset); if (can_pstats.user_reset) - len += snprintf(page + len, PAGE_SIZE - len, - " %8ld user statistic resets (USTR)\n", + seq_printf(m, " %8ld user statistic resets (USTR)\n", can_pstats.user_reset); - len += snprintf(page + len, PAGE_SIZE - len, "\n"); - - *eof = 1; - return len; + seq_putc(m, '\n'); + return 0; } -static int can_proc_read_reset_stats(char *page, char **start, off_t off, - int count, int *eof, void *data) +static int can_stats_proc_open(struct inode *inode, struct file *file) { - int len = 0; + return single_open(file, can_stats_proc_show, NULL); +} + +static const struct file_operations can_stats_proc_fops = { + .owner = THIS_MODULE, + .open = can_stats_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +static int can_reset_stats_proc_show(struct seq_file *m, void *v) +{ user_reset = 1; if (can_stattimer.function == can_stat_update) { - len += snprintf(page + len, PAGE_SIZE - len, - "Scheduled statistic reset #%ld.\n", + seq_printf(m, "Scheduled statistic reset #%ld.\n", can_pstats.stats_reset + 1); } else { if (can_stats.jiffies_init != jiffies) can_init_stats(); - len += snprintf(page + len, PAGE_SIZE - len, - "Performed statistic reset #%ld.\n", + seq_printf(m, "Performed statistic reset #%ld.\n", can_pstats.stats_reset); } + return 0; +} - *eof = 1; - return len; +static int can_reset_stats_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, can_reset_stats_proc_show, NULL); } -static int can_proc_read_version(char *page, char **start, off_t off, - int count, int *eof, void *data) +static const struct file_operations can_reset_stats_proc_fops = { + .owner = THIS_MODULE, + .open = can_reset_stats_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int can_version_proc_show(struct seq_file *m, void *v) { - int len = 0; + seq_printf(m, "%s\n", CAN_VERSION_STRING); + return 0; +} - len += snprintf(page + len, PAGE_SIZE - len, "%s\n", - CAN_VERSION_STRING); - *eof = 1; - return len; +static int can_version_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, can_version_proc_show, NULL); } -static int can_proc_read_rcvlist(char *page, char **start, off_t off, - int count, int *eof, void *data) +static const struct file_operations can_version_proc_fops = { + .owner = THIS_MODULE, + .open = can_version_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int can_rcvlist_proc_show(struct seq_file *m, void *v) { /* double cast to prevent GCC warning */ - int idx = (int)(long)data; - int len = 0; + int idx = (int)(long)m->private; struct dev_rcv_lists *d; struct hlist_node *n; - len += snprintf(page + len, PAGE_SIZE - len, - "\nreceive list '%s':\n", rx_list_name[idx]); + seq_printf(m, "\nreceive list '%s':\n", rx_list_name[idx]); rcu_read_lock(); hlist_for_each_entry_rcu(d, n, &can_rx_dev_list, list) { if (!hlist_empty(&d->rx[idx])) { - len = can_print_recv_banner(page, len); - len = can_print_rcvlist(page, len, &d->rx[idx], d->dev); + can_print_recv_banner(m); + can_print_rcvlist(m, &d->rx[idx], d->dev); } else - len += snprintf(page + len, PAGE_SIZE - len, - " (%s: no entry)\n", DNAME(d->dev)); - - /* exit on end of buffer? */ - if (len > PAGE_SIZE - 100) - break; + seq_printf(m, " (%s: no entry)\n", DNAME(d->dev)); } rcu_read_unlock(); - len += snprintf(page + len, PAGE_SIZE - len, "\n"); + seq_putc(m, '\n'); + return 0; +} - *eof = 1; - return len; +static int can_rcvlist_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, can_rcvlist_proc_show, PDE(inode)->data); } -static int can_proc_read_rcvlist_sff(char *page, char **start, off_t off, - int count, int *eof, void *data) +static const struct file_operations can_rcvlist_proc_fops = { + .owner = THIS_MODULE, + .open = can_rcvlist_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) { - int len = 0; struct dev_rcv_lists *d; struct hlist_node *n; /* RX_SFF */ - len += snprintf(page + len, PAGE_SIZE - len, - "\nreceive list 'rx_sff':\n"); + seq_puts(m, "\nreceive list 'rx_sff':\n"); rcu_read_lock(); hlist_for_each_entry_rcu(d, n, &can_rx_dev_list, list) { @@ -413,46 +402,38 @@ static int can_proc_read_rcvlist_sff(char *page, char **start, off_t off, } if (!all_empty) { - len = can_print_recv_banner(page, len); + can_print_recv_banner(m); for (i = 0; i < 0x800; i++) { - if (!hlist_empty(&d->rx_sff[i]) && - len < PAGE_SIZE - 100) - len = can_print_rcvlist(page, len, - &d->rx_sff[i], - d->dev); + if (!hlist_empty(&d->rx_sff[i])) + can_print_rcvlist(m, &d->rx_sff[i], + d->dev); } } else - len += snprintf(page + len, PAGE_SIZE - len, - " (%s: no entry)\n", DNAME(d->dev)); - - /* exit on end of buffer? */ - if (len > PAGE_SIZE - 100) - break; + seq_printf(m, " (%s: no entry)\n", DNAME(d->dev)); } rcu_read_unlock(); - len += snprintf(page + len, PAGE_SIZE - len, "\n"); + seq_putc(m, '\n'); + return 0; +} - *eof = 1; - return len; +static int can_rcvlist_sff_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, can_rcvlist_sff_proc_show, NULL); } +static const struct file_operations can_rcvlist_sff_proc_fops = { + .owner = THIS_MODULE, + .open = can_rcvlist_sff_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + /* * proc utility functions */ -static struct proc_dir_entry *can_create_proc_readentry(const char *name, - mode_t mode, - read_proc_t *read_proc, - void *data) -{ - if (can_dir) - return create_proc_read_entry(name, mode, can_dir, read_proc, - data); - else - return NULL; -} - static void can_remove_proc_readentry(const char *name) { if (can_dir) @@ -474,24 +455,24 @@ void can_init_proc(void) } /* own procfs entries from the AF_CAN core */ - pde_version = can_create_proc_readentry(CAN_PROC_VERSION, 0644, - can_proc_read_version, NULL); - pde_stats = can_create_proc_readentry(CAN_PROC_STATS, 0644, - can_proc_read_stats, NULL); - pde_reset_stats = can_create_proc_readentry(CAN_PROC_RESET_STATS, 0644, - can_proc_read_reset_stats, NULL); - pde_rcvlist_err = can_create_proc_readentry(CAN_PROC_RCVLIST_ERR, 0644, - can_proc_read_rcvlist, (void *)RX_ERR); - pde_rcvlist_all = can_create_proc_readentry(CAN_PROC_RCVLIST_ALL, 0644, - can_proc_read_rcvlist, (void *)RX_ALL); - pde_rcvlist_fil = can_create_proc_readentry(CAN_PROC_RCVLIST_FIL, 0644, - can_proc_read_rcvlist, (void *)RX_FIL); - pde_rcvlist_inv = can_create_proc_readentry(CAN_PROC_RCVLIST_INV, 0644, - can_proc_read_rcvlist, (void *)RX_INV); - pde_rcvlist_eff = can_create_proc_readentry(CAN_PROC_RCVLIST_EFF, 0644, - can_proc_read_rcvlist, (void *)RX_EFF); - pde_rcvlist_sff = can_create_proc_readentry(CAN_PROC_RCVLIST_SFF, 0644, - can_proc_read_rcvlist_sff, NULL); + pde_version = proc_create(CAN_PROC_VERSION, 0644, can_dir, + &can_version_proc_fops); + pde_stats = proc_create(CAN_PROC_STATS, 0644, can_dir, + &can_stats_proc_fops); + pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644, can_dir, + &can_reset_stats_proc_fops); + pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644, can_dir, + &can_rcvlist_proc_fops, (void *)RX_ERR); + pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644, can_dir, + &can_rcvlist_proc_fops, (void *)RX_ALL); + pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644, can_dir, + &can_rcvlist_proc_fops, (void *)RX_FIL); + pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, can_dir, + &can_rcvlist_proc_fops, (void *)RX_INV); + pde_rcvlist_eff = proc_create_data(CAN_PROC_RCVLIST_EFF, 0644, can_dir, + &can_rcvlist_proc_fops, (void *)RX_EFF); + pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, can_dir, + &can_rcvlist_sff_proc_fops); } /* diff --git a/net/can/raw.c b/net/can/raw.c index f4cc44548bda..db3152df7d2b 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -401,6 +401,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, if (peer) return -EOPNOTSUPP; + memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = ro->ifindex; diff --git a/net/core/datagram.c b/net/core/datagram.c index b0fe69211eef..1c6cf3a1a4f6 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -55,6 +55,7 @@ #include <net/checksum.h> #include <net/sock.h> #include <net/tcp_states.h> +#include <trace/events/skb.h> /* * Is a socket 'connection oriented' ? @@ -284,6 +285,8 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, int i, copy = start - offset; struct sk_buff *frag_iter; + trace_skb_copy_datagram_iovec(skb, len); + /* Copy header. */ if (copy > 0) { if (copy > len) diff --git a/net/core/dev.c b/net/core/dev.c index a0bc087616a4..1a6561b1eb90 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -191,7 +191,6 @@ static struct list_head ptype_all __read_mostly; /* Taps */ * semaphore held. */ DEFINE_RWLOCK(dev_base_lock); - EXPORT_SYMBOL(dev_base_lock); #define NETDEV_HASHBITS 8 @@ -248,6 +247,7 @@ static RAW_NOTIFIER_HEAD(netdev_chain); */ DEFINE_PER_CPU(struct softnet_data, softnet_data); +EXPORT_PER_CPU_SYMBOL(softnet_data); #ifdef CONFIG_LOCKDEP /* @@ -269,7 +269,7 @@ static const unsigned short netdev_lock_type[] = ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, - ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_IEEE802154_PHY, + ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = @@ -287,7 +287,7 @@ static const char *const netdev_lock_name[] = "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", - "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_IEEE802154_PHY", + "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -381,6 +381,7 @@ void dev_add_pack(struct packet_type *pt) } spin_unlock_bh(&ptype_lock); } +EXPORT_SYMBOL(dev_add_pack); /** * __dev_remove_pack - remove packet handler @@ -418,6 +419,8 @@ void __dev_remove_pack(struct packet_type *pt) out: spin_unlock_bh(&ptype_lock); } +EXPORT_SYMBOL(__dev_remove_pack); + /** * dev_remove_pack - remove packet handler * @pt: packet type declaration @@ -436,6 +439,7 @@ void dev_remove_pack(struct packet_type *pt) synchronize_net(); } +EXPORT_SYMBOL(dev_remove_pack); /****************************************************************************** @@ -499,6 +503,7 @@ int netdev_boot_setup_check(struct net_device *dev) } return 0; } +EXPORT_SYMBOL(netdev_boot_setup_check); /** @@ -591,6 +596,7 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name) } return NULL; } +EXPORT_SYMBOL(__dev_get_by_name); /** * dev_get_by_name - find a device by its name @@ -615,6 +621,7 @@ struct net_device *dev_get_by_name(struct net *net, const char *name) read_unlock(&dev_base_lock); return dev; } +EXPORT_SYMBOL(dev_get_by_name); /** * __dev_get_by_index - find a device by its ifindex @@ -640,6 +647,7 @@ struct net_device *__dev_get_by_index(struct net *net, int ifindex) } return NULL; } +EXPORT_SYMBOL(__dev_get_by_index); /** @@ -664,6 +672,7 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) read_unlock(&dev_base_lock); return dev; } +EXPORT_SYMBOL(dev_get_by_index); /** * dev_getbyhwaddr - find a device by its hardware address @@ -693,7 +702,6 @@ struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *h return NULL; } - EXPORT_SYMBOL(dev_getbyhwaddr); struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) @@ -707,7 +715,6 @@ struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) return NULL; } - EXPORT_SYMBOL(__dev_getfirstbyhwtype); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) @@ -721,7 +728,6 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) rtnl_unlock(); return dev; } - EXPORT_SYMBOL(dev_getfirstbyhwtype); /** @@ -736,7 +742,8 @@ EXPORT_SYMBOL(dev_getfirstbyhwtype); * dev_put to indicate they have finished with it. */ -struct net_device * dev_get_by_flags(struct net *net, unsigned short if_flags, unsigned short mask) +struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags, + unsigned short mask) { struct net_device *dev, *ret; @@ -752,6 +759,7 @@ struct net_device * dev_get_by_flags(struct net *net, unsigned short if_flags, u read_unlock(&dev_base_lock); return ret; } +EXPORT_SYMBOL(dev_get_by_flags); /** * dev_valid_name - check if name is okay for network device @@ -777,6 +785,7 @@ int dev_valid_name(const char *name) } return 1; } +EXPORT_SYMBOL(dev_valid_name); /** * __dev_alloc_name - allocate a name for a device @@ -870,6 +879,7 @@ int dev_alloc_name(struct net_device *dev, const char *name) strlcpy(dev->name, buf, IFNAMSIZ); return ret; } +EXPORT_SYMBOL(dev_alloc_name); /** @@ -906,8 +916,7 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_alloc_name(dev, newname); if (err < 0) return err; - } - else if (__dev_get_by_name(net, newname)) + } else if (__dev_get_by_name(net, newname)) return -EEXIST; else strlcpy(dev->name, newname, IFNAMSIZ); @@ -970,7 +979,7 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return 0; } - dev->ifalias = krealloc(dev->ifalias, len+1, GFP_KERNEL); + dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); if (!dev->ifalias) return -ENOMEM; @@ -1006,6 +1015,7 @@ void netdev_state_change(struct net_device *dev) rtmsg_ifinfo(RTM_NEWLINK, dev, 0); } } +EXPORT_SYMBOL(netdev_state_change); void netdev_bonding_change(struct net_device *dev) { @@ -1034,6 +1044,7 @@ void dev_load(struct net *net, const char *name) if (!dev && capable(CAP_SYS_MODULE)) request_module("%s", name); } +EXPORT_SYMBOL(dev_load); /** * dev_open - prepare an interface for use. @@ -1118,6 +1129,7 @@ int dev_open(struct net_device *dev) return ret; } +EXPORT_SYMBOL(dev_open); /** * dev_close - shutdown an interface. @@ -1184,6 +1196,7 @@ int dev_close(struct net_device *dev) return 0; } +EXPORT_SYMBOL(dev_close); /** @@ -1279,6 +1292,7 @@ rollback: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } +EXPORT_SYMBOL(register_netdevice_notifier); /** * unregister_netdevice_notifier - unregister a network notifier block @@ -1299,6 +1313,7 @@ int unregister_netdevice_notifier(struct notifier_block *nb) rtnl_unlock(); return err; } +EXPORT_SYMBOL(unregister_netdevice_notifier); /** * call_netdevice_notifiers - call all network notifier blocks @@ -1321,11 +1336,13 @@ void net_enable_timestamp(void) { atomic_inc(&netstamp_needed); } +EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { atomic_dec(&netstamp_needed); } +EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp(struct sk_buff *skb) { @@ -1359,7 +1376,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) if ((ptype->dev == dev || !ptype->dev) && (ptype->af_packet_priv == NULL || (struct sock *)ptype->af_packet_priv != skb->sk)) { - struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC); + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) break; @@ -1527,6 +1544,7 @@ out_set_summed: out: return ret; } +EXPORT_SYMBOL(skb_checksum_help); /** * skb_gso_segment - Perform segmentation on skb. @@ -1589,7 +1607,6 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) return segs; } - EXPORT_SYMBOL(skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ @@ -1755,7 +1772,7 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); - while (unlikely (hash >= dev->real_num_tx_queues)) + while (unlikely(hash >= dev->real_num_tx_queues)) hash -= dev->real_num_tx_queues; return hash; } @@ -1890,7 +1907,7 @@ gso: q = rcu_dereference(txq->qdisc); #ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS); + skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); #endif if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); @@ -1917,7 +1934,7 @@ gso: HARD_TX_LOCK(dev, txq, cpu); if (!netif_tx_queue_stopped(txq)) { - rc = 0; + rc = NET_XMIT_SUCCESS; if (!dev_hard_start_xmit(skb, dev, txq)) { HARD_TX_UNLOCK(dev, txq); goto out; @@ -1946,6 +1963,7 @@ out: rcu_read_unlock_bh(); return rc; } +EXPORT_SYMBOL(dev_queue_xmit); /*======================================================================= @@ -2012,6 +2030,7 @@ enqueue: kfree_skb(skb); return NET_RX_DROP; } +EXPORT_SYMBOL(netif_rx); int netif_rx_ni(struct sk_buff *skb) { @@ -2025,7 +2044,6 @@ int netif_rx_ni(struct sk_buff *skb) return err; } - EXPORT_SYMBOL(netif_rx_ni); static void net_tx_action(struct softirq_action *h) @@ -2358,6 +2376,7 @@ out: rcu_read_unlock(); return ret; } +EXPORT_SYMBOL(netif_receive_skb); /* Network device is going away, flush any packets still pending */ static void flush_backlog(void *arg) @@ -2874,7 +2893,7 @@ softnet_break: goto out; } -static gifconf_func_t * gifconf_list [NPROTO]; +static gifconf_func_t *gifconf_list[NPROTO]; /** * register_gifconf - register a SIOCGIF handler @@ -2885,13 +2904,14 @@ static gifconf_func_t * gifconf_list [NPROTO]; * that is passed must not be freed or reused until it has been replaced * by another handler. */ -int register_gifconf(unsigned int family, gifconf_func_t * gifconf) +int register_gifconf(unsigned int family, gifconf_func_t *gifconf) { if (family >= NPROTO) return -EINVAL; gifconf_list[family] = gifconf; return 0; } +EXPORT_SYMBOL(register_gifconf); /* @@ -3102,7 +3122,7 @@ static int softnet_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", s->total, s->dropped, s->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ - s->cpu_collision ); + s->cpu_collision); return 0; } @@ -3338,6 +3358,7 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); return 0; } +EXPORT_SYMBOL(netdev_set_master); static void dev_change_rx_flags(struct net_device *dev, int flags) { @@ -3416,6 +3437,7 @@ int dev_set_promiscuity(struct net_device *dev, int inc) dev_set_rx_mode(dev); return err; } +EXPORT_SYMBOL(dev_set_promiscuity); /** * dev_set_allmulti - update allmulti count on a device @@ -3459,6 +3481,7 @@ int dev_set_allmulti(struct net_device *dev, int inc) } return 0; } +EXPORT_SYMBOL(dev_set_allmulti); /* * Upload unicast and multicast address lists to device and @@ -3887,10 +3910,12 @@ int dev_unicast_delete(struct net_device *dev, void *addr) ASSERT_RTNL(); + netif_addr_lock_bh(dev); err = __hw_addr_del(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_unicast_delete); @@ -3911,10 +3936,12 @@ int dev_unicast_add(struct net_device *dev, void *addr) ASSERT_RTNL(); + netif_addr_lock_bh(dev); err = __hw_addr_add(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_unicast_add); @@ -3973,7 +4000,8 @@ EXPORT_SYMBOL_GPL(__dev_addr_unsync); * @from: source device * * Add newly added addresses to the destination device and release - * addresses that have no users left. + * addresses that have no users left. The source device must be + * locked by netif_tx_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. @@ -3982,14 +4010,14 @@ int dev_unicast_sync(struct net_device *to, struct net_device *from) { int err = 0; - ASSERT_RTNL(); - if (to->addr_len != from->addr_len) return -EINVAL; + netif_addr_lock_bh(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); + netif_addr_unlock_bh(to); return err; } EXPORT_SYMBOL(dev_unicast_sync); @@ -4005,27 +4033,27 @@ EXPORT_SYMBOL(dev_unicast_sync); */ void dev_unicast_unsync(struct net_device *to, struct net_device *from) { - ASSERT_RTNL(); - if (to->addr_len != from->addr_len) return; + netif_addr_lock_bh(from); + netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_unicast_unsync); static void dev_unicast_flush(struct net_device *dev) { - /* rtnl_mutex must be held here */ - + netif_addr_lock_bh(dev); __hw_addr_flush(&dev->uc); + netif_addr_unlock_bh(dev); } static void dev_unicast_init(struct net_device *dev) { - /* rtnl_mutex must be held here */ - __hw_addr_init(&dev->uc); } @@ -4083,6 +4111,7 @@ unsigned dev_get_flags(const struct net_device *dev) return flags; } +EXPORT_SYMBOL(dev_get_flags); /** * dev_change_flags - change device settings @@ -4133,12 +4162,13 @@ int dev_change_flags(struct net_device *dev, unsigned flags) } if (dev->flags & IFF_UP && - ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI | + ((old_flags ^ dev->flags) & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) call_netdevice_notifiers(NETDEV_CHANGE, dev); if ((flags ^ dev->gflags) & IFF_PROMISC) { - int inc = (flags & IFF_PROMISC) ? +1 : -1; + int inc = (flags & IFF_PROMISC) ? 1 : -1; + dev->gflags ^= IFF_PROMISC; dev_set_promiscuity(dev, inc); } @@ -4148,7 +4178,8 @@ int dev_change_flags(struct net_device *dev, unsigned flags) IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { - int inc = (flags & IFF_ALLMULTI) ? +1 : -1; + int inc = (flags & IFF_ALLMULTI) ? 1 : -1; + dev->gflags ^= IFF_ALLMULTI; dev_set_allmulti(dev, inc); } @@ -4160,6 +4191,7 @@ int dev_change_flags(struct net_device *dev, unsigned flags) return ret; } +EXPORT_SYMBOL(dev_change_flags); /** * dev_set_mtu - Change maximum transfer unit @@ -4193,6 +4225,7 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); return err; } +EXPORT_SYMBOL(dev_set_mtu); /** * dev_set_mac_address - Change Media Access Control Address @@ -4217,6 +4250,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } +EXPORT_SYMBOL(dev_set_mac_address); /* * Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock) @@ -4230,56 +4264,56 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm return -ENODEV; switch (cmd) { - case SIOCGIFFLAGS: /* Get interface flags */ - ifr->ifr_flags = (short) dev_get_flags(dev); - return 0; + case SIOCGIFFLAGS: /* Get interface flags */ + ifr->ifr_flags = (short) dev_get_flags(dev); + return 0; - case SIOCGIFMETRIC: /* Get the metric on the interface - (currently unused) */ - ifr->ifr_metric = 0; - return 0; + case SIOCGIFMETRIC: /* Get the metric on the interface + (currently unused) */ + ifr->ifr_metric = 0; + return 0; - case SIOCGIFMTU: /* Get the MTU of a device */ - ifr->ifr_mtu = dev->mtu; - return 0; + case SIOCGIFMTU: /* Get the MTU of a device */ + ifr->ifr_mtu = dev->mtu; + return 0; - case SIOCGIFHWADDR: - if (!dev->addr_len) - memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); - else - memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - ifr->ifr_hwaddr.sa_family = dev->type; - return 0; + case SIOCGIFHWADDR: + if (!dev->addr_len) + memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); + else + memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + ifr->ifr_hwaddr.sa_family = dev->type; + return 0; - case SIOCGIFSLAVE: - err = -EINVAL; - break; + case SIOCGIFSLAVE: + err = -EINVAL; + break; - case SIOCGIFMAP: - ifr->ifr_map.mem_start = dev->mem_start; - ifr->ifr_map.mem_end = dev->mem_end; - ifr->ifr_map.base_addr = dev->base_addr; - ifr->ifr_map.irq = dev->irq; - ifr->ifr_map.dma = dev->dma; - ifr->ifr_map.port = dev->if_port; - return 0; + case SIOCGIFMAP: + ifr->ifr_map.mem_start = dev->mem_start; + ifr->ifr_map.mem_end = dev->mem_end; + ifr->ifr_map.base_addr = dev->base_addr; + ifr->ifr_map.irq = dev->irq; + ifr->ifr_map.dma = dev->dma; + ifr->ifr_map.port = dev->if_port; + return 0; - case SIOCGIFINDEX: - ifr->ifr_ifindex = dev->ifindex; - return 0; + case SIOCGIFINDEX: + ifr->ifr_ifindex = dev->ifindex; + return 0; - case SIOCGIFTXQLEN: - ifr->ifr_qlen = dev->tx_queue_len; - return 0; + case SIOCGIFTXQLEN: + ifr->ifr_qlen = dev->tx_queue_len; + return 0; - default: - /* dev_ioctl() should ensure this case - * is never reached - */ - WARN_ON(1); - err = -EINVAL; - break; + default: + /* dev_ioctl() should ensure this case + * is never reached + */ + WARN_ON(1); + err = -EINVAL; + break; } return err; @@ -4300,92 +4334,91 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) ops = dev->netdev_ops; switch (cmd) { - case SIOCSIFFLAGS: /* Set interface flags */ - return dev_change_flags(dev, ifr->ifr_flags); - - case SIOCSIFMETRIC: /* Set the metric on the interface - (currently unused) */ - return -EOPNOTSUPP; + case SIOCSIFFLAGS: /* Set interface flags */ + return dev_change_flags(dev, ifr->ifr_flags); - case SIOCSIFMTU: /* Set the MTU of a device */ - return dev_set_mtu(dev, ifr->ifr_mtu); + case SIOCSIFMETRIC: /* Set the metric on the interface + (currently unused) */ + return -EOPNOTSUPP; - case SIOCSIFHWADDR: - return dev_set_mac_address(dev, &ifr->ifr_hwaddr); + case SIOCSIFMTU: /* Set the MTU of a device */ + return dev_set_mtu(dev, ifr->ifr_mtu); - case SIOCSIFHWBROADCAST: - if (ifr->ifr_hwaddr.sa_family != dev->type) - return -EINVAL; - memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return 0; - - case SIOCSIFMAP: - if (ops->ndo_set_config) { - if (!netif_device_present(dev)) - return -ENODEV; - return ops->ndo_set_config(dev, &ifr->ifr_map); - } - return -EOPNOTSUPP; + case SIOCSIFHWADDR: + return dev_set_mac_address(dev, &ifr->ifr_hwaddr); - case SIOCADDMULTI: - if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); + case SIOCSIFHWBROADCAST: + if (ifr->ifr_hwaddr.sa_family != dev->type) + return -EINVAL; + memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return 0; - case SIOCDELMULTI: - if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; + case SIOCSIFMAP: + if (ops->ndo_set_config) { if (!netif_device_present(dev)) return -ENODEV; - return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); + return ops->ndo_set_config(dev, &ifr->ifr_map); + } + return -EOPNOTSUPP; - case SIOCSIFTXQLEN: - if (ifr->ifr_qlen < 0) - return -EINVAL; - dev->tx_queue_len = ifr->ifr_qlen; - return 0; + case SIOCADDMULTI: + if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data, + dev->addr_len, 1); + + case SIOCDELMULTI: + if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data, + dev->addr_len, 1); - case SIOCSIFNAME: - ifr->ifr_newname[IFNAMSIZ-1] = '\0'; - return dev_change_name(dev, ifr->ifr_newname); + case SIOCSIFTXQLEN: + if (ifr->ifr_qlen < 0) + return -EINVAL; + dev->tx_queue_len = ifr->ifr_qlen; + return 0; - /* - * Unknown or private ioctl - */ + case SIOCSIFNAME: + ifr->ifr_newname[IFNAMSIZ-1] = '\0'; + return dev_change_name(dev, ifr->ifr_newname); - default: - if ((cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15) || - cmd == SIOCBONDENSLAVE || - cmd == SIOCBONDRELEASE || - cmd == SIOCBONDSETHWADDR || - cmd == SIOCBONDSLAVEINFOQUERY || - cmd == SIOCBONDINFOQUERY || - cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCGMIIPHY || - cmd == SIOCGMIIREG || - cmd == SIOCSMIIREG || - cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF || - cmd == SIOCSHWTSTAMP || - cmd == SIOCWANDEV) { - err = -EOPNOTSUPP; - if (ops->ndo_do_ioctl) { - if (netif_device_present(dev)) - err = ops->ndo_do_ioctl(dev, ifr, cmd); - else - err = -ENODEV; - } - } else - err = -EINVAL; + /* + * Unknown or private ioctl + */ + default: + if ((cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15) || + cmd == SIOCBONDENSLAVE || + cmd == SIOCBONDRELEASE || + cmd == SIOCBONDSETHWADDR || + cmd == SIOCBONDSLAVEINFOQUERY || + cmd == SIOCBONDINFOQUERY || + cmd == SIOCBONDCHANGEACTIVE || + cmd == SIOCGMIIPHY || + cmd == SIOCGMIIREG || + cmd == SIOCSMIIREG || + cmd == SIOCBRADDIF || + cmd == SIOCBRDELIF || + cmd == SIOCSHWTSTAMP || + cmd == SIOCWANDEV) { + err = -EOPNOTSUPP; + if (ops->ndo_do_ioctl) { + if (netif_device_present(dev)) + err = ops->ndo_do_ioctl(dev, ifr, cmd); + else + err = -ENODEV; + } + } else + err = -EINVAL; } return err; @@ -4442,135 +4475,135 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) */ switch (cmd) { - /* - * These ioctl calls: - * - can be done by all. - * - atomic and do not require locking. - * - return a value - */ - case SIOCGIFFLAGS: - case SIOCGIFMETRIC: - case SIOCGIFMTU: - case SIOCGIFHWADDR: - case SIOCGIFSLAVE: - case SIOCGIFMAP: - case SIOCGIFINDEX: - case SIOCGIFTXQLEN: - dev_load(net, ifr.ifr_name); - read_lock(&dev_base_lock); - ret = dev_ifsioc_locked(net, &ifr, cmd); - read_unlock(&dev_base_lock); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; + /* + * These ioctl calls: + * - can be done by all. + * - atomic and do not require locking. + * - return a value + */ + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFHWADDR: + case SIOCGIFSLAVE: + case SIOCGIFMAP: + case SIOCGIFINDEX: + case SIOCGIFTXQLEN: + dev_load(net, ifr.ifr_name); + read_lock(&dev_base_lock); + ret = dev_ifsioc_locked(net, &ifr, cmd); + read_unlock(&dev_base_lock); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; - case SIOCETHTOOL: - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ethtool(net, &ifr); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; + case SIOCETHTOOL: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ethtool(net, &ifr); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - return a value - */ - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSIFNAME: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - return a value + */ + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSIFNAME: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - do not return a value - */ - case SIOCSIFFLAGS: - case SIOCSIFMETRIC: - case SIOCSIFMTU: - case SIOCSIFMAP: - case SIOCSIFHWADDR: - case SIOCSIFSLAVE: - case SIOCADDMULTI: - case SIOCDELMULTI: - case SIOCSIFHWBROADCAST: - case SIOCSIFTXQLEN: - case SIOCSMIIREG: - case SIOCBONDENSLAVE: - case SIOCBONDRELEASE: - case SIOCBONDSETHWADDR: - case SIOCBONDCHANGEACTIVE: - case SIOCBRADDIF: - case SIOCBRDELIF: - case SIOCSHWTSTAMP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - /* fall through */ - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFFLAGS: + case SIOCSIFMETRIC: + case SIOCSIFMTU: + case SIOCSIFMAP: + case SIOCSIFHWADDR: + case SIOCSIFSLAVE: + case SIOCADDMULTI: + case SIOCDELMULTI: + case SIOCSIFHWBROADCAST: + case SIOCSIFTXQLEN: + case SIOCSMIIREG: + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: + case SIOCBRADDIF: + case SIOCBRDELIF: + case SIOCSHWTSTAMP: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + return ret; + + case SIOCGIFMEM: + /* Get the per device memory space. We can add this but + * currently do not support it */ + case SIOCSIFMEM: + /* Set the per device memory buffer space. + * Not applicable in our case */ + case SIOCSIFLINK: + return -EINVAL; + + /* + * Unknown or private ioctl. + */ + default: + if (cmd == SIOCWANDEV || + (cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr.ifr_name); rtnl_lock(); ret = dev_ifsioc(net, &ifr, cmd); rtnl_unlock(); + if (!ret && copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; return ret; - - case SIOCGIFMEM: - /* Get the per device memory space. We can add this but - * currently do not support it */ - case SIOCSIFMEM: - /* Set the per device memory buffer space. - * Not applicable in our case */ - case SIOCSIFLINK: - return -EINVAL; - - /* - * Unknown or private ioctl. - */ - default: - if (cmd == SIOCWANDEV || - (cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15)) { - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret && copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - return ret; - } - /* Take care of Wireless Extensions */ - if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) - return wext_handle_ioctl(net, &ifr, cmd, arg); - return -EINVAL; + } + /* Take care of Wireless Extensions */ + if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) + return wext_handle_ioctl(net, &ifr, cmd, arg); + return -EINVAL; } } @@ -4835,6 +4868,7 @@ err_uninit: dev->netdev_ops->ndo_uninit(dev); goto out; } +EXPORT_SYMBOL(register_netdevice); /** * init_dummy_netdev - init a dummy network device for NAPI @@ -5187,6 +5221,7 @@ void free_netdev(struct net_device *dev) /* will free via device release */ put_device(&dev->dev); } +EXPORT_SYMBOL(free_netdev); /** * synchronize_net - Synchronize with packet receive processing @@ -5199,6 +5234,7 @@ void synchronize_net(void) might_sleep(); synchronize_rcu(); } +EXPORT_SYMBOL(synchronize_net); /** * unregister_netdevice - remove device from the kernel @@ -5219,6 +5255,7 @@ void unregister_netdevice(struct net_device *dev) /* Finish processing unregister after unlock */ net_set_todo(dev); } +EXPORT_SYMBOL(unregister_netdevice); /** * unregister_netdev - remove device from the kernel @@ -5237,7 +5274,6 @@ void unregister_netdev(struct net_device *dev) unregister_netdevice(dev); rtnl_unlock(); } - EXPORT_SYMBOL(unregister_netdev); /** @@ -5427,7 +5463,7 @@ unsigned long netdev_increment_features(unsigned long all, unsigned long one, unsigned long mask) { /* If device needs checksumming, downgrade to it. */ - if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) + if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM); else if (mask & NETIF_F_ALL_CSUM) { /* If one device supports v4/v6 checksumming, set for all. */ @@ -5653,41 +5689,3 @@ static int __init initialize_hashrnd(void) late_initcall_sync(initialize_hashrnd); -EXPORT_SYMBOL(__dev_get_by_index); -EXPORT_SYMBOL(__dev_get_by_name); -EXPORT_SYMBOL(__dev_remove_pack); -EXPORT_SYMBOL(dev_valid_name); -EXPORT_SYMBOL(dev_add_pack); -EXPORT_SYMBOL(dev_alloc_name); -EXPORT_SYMBOL(dev_close); -EXPORT_SYMBOL(dev_get_by_flags); -EXPORT_SYMBOL(dev_get_by_index); -EXPORT_SYMBOL(dev_get_by_name); -EXPORT_SYMBOL(dev_open); -EXPORT_SYMBOL(dev_queue_xmit); -EXPORT_SYMBOL(dev_remove_pack); -EXPORT_SYMBOL(dev_set_allmulti); -EXPORT_SYMBOL(dev_set_promiscuity); -EXPORT_SYMBOL(dev_change_flags); -EXPORT_SYMBOL(dev_set_mtu); -EXPORT_SYMBOL(dev_set_mac_address); -EXPORT_SYMBOL(free_netdev); -EXPORT_SYMBOL(netdev_boot_setup_check); -EXPORT_SYMBOL(netdev_set_master); -EXPORT_SYMBOL(netdev_state_change); -EXPORT_SYMBOL(netif_receive_skb); -EXPORT_SYMBOL(netif_rx); -EXPORT_SYMBOL(register_gifconf); -EXPORT_SYMBOL(register_netdevice); -EXPORT_SYMBOL(register_netdevice_notifier); -EXPORT_SYMBOL(skb_checksum_help); -EXPORT_SYMBOL(synchronize_net); -EXPORT_SYMBOL(unregister_netdevice); -EXPORT_SYMBOL(unregister_netdevice_notifier); -EXPORT_SYMBOL(net_enable_timestamp); -EXPORT_SYMBOL(net_disable_timestamp); -EXPORT_SYMBOL(dev_get_flags); - -EXPORT_SYMBOL(dev_load); - -EXPORT_PER_CPU_SYMBOL(softnet_data); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 9d66fa953ab7..0a113f26bc9f 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -52,6 +52,7 @@ struct per_cpu_dm_data { struct dm_hw_stat_delta { struct net_device *dev; + unsigned long last_rx; struct list_head list; struct rcu_head rcu; unsigned long last_drop_val; @@ -180,17 +181,25 @@ static void trace_napi_poll_hit(struct napi_struct *napi) struct dm_hw_stat_delta *new_stat; /* - * Ratelimit our check time to dm_hw_check_delta jiffies + * Don't check napi structures with no associated device */ - if (!time_after(jiffies, napi->dev->last_rx + dm_hw_check_delta)) + if (!napi->dev) return; rcu_read_lock(); list_for_each_entry_rcu(new_stat, &hw_stats_list, list) { + /* + * only add a note to our monitor buffer if: + * 1) this is the dev we received on + * 2) its after the last_rx delta + * 3) our rx_dropped count has gone up + */ if ((new_stat->dev == napi->dev) && + (time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) && (napi->dev->stats.rx_dropped != new_stat->last_drop_val)) { trace_drop_common(NULL, NULL); new_stat->last_drop_val = napi->dev->stats.rx_dropped; + new_stat->last_rx = jiffies; break; } } @@ -286,6 +295,7 @@ static int dropmon_net_event(struct notifier_block *ev_block, goto out; new_stat->dev = dev; + new_stat->last_rx = jiffies; INIT_RCU_HEAD(&new_stat->rcu); spin_lock(&trace_state_lock); list_add_rcu(&new_stat->list, &hw_stats_list); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 44e571111d3a..4c12ddb5f5ee 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -898,6 +898,19 @@ static int ethtool_set_value(struct net_device *dev, char __user *useraddr, return actor(dev, edata.data); } +static int ethtool_flash_device(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_flash efl; + + if (copy_from_user(&efl, useraddr, sizeof(efl))) + return -EFAULT; + + if (!dev->ethtool_ops->flash_device) + return -EOPNOTSUPP; + + return dev->ethtool_ops->flash_device(dev, &efl); +} + /* The main entry point in this file. Called from net/core/dev.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) @@ -1111,6 +1124,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SGRO: rc = ethtool_set_gro(dev, useraddr); break; + case ETHTOOL_FLASHDEV: + rc = ethtool_flash_device(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 78e5bfc454ae..493775f4f2f1 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -81,7 +81,7 @@ struct gen_estimator { struct list_head list; - struct gnet_stats_basic *bstats; + struct gnet_stats_basic_packed *bstats; struct gnet_stats_rate_est *rate_est; spinlock_t *stats_lock; int ewma_log; @@ -165,7 +165,7 @@ static void gen_add_node(struct gen_estimator *est) } static -struct gen_estimator *gen_find_node(const struct gnet_stats_basic *bstats, +struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est *rate_est) { struct rb_node *p = est_root.rb_node; @@ -202,7 +202,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic *bstats, * * NOTE: Called under rtnl_mutex */ -int gen_new_estimator(struct gnet_stats_basic *bstats, +int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct nlattr *opt) @@ -262,7 +262,7 @@ static void __gen_kill_estimator(struct rcu_head *head) * * NOTE: Called under rtnl_mutex */ -void gen_kill_estimator(struct gnet_stats_basic *bstats, +void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est) { struct gen_estimator *e; @@ -292,7 +292,7 @@ EXPORT_SYMBOL(gen_kill_estimator); * * Returns 0 on success or a negative error code. */ -int gen_replace_estimator(struct gnet_stats_basic *bstats, +int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct nlattr *opt) { @@ -308,7 +308,7 @@ EXPORT_SYMBOL(gen_replace_estimator); * * Returns true if estimator is active, and false if not. */ -bool gen_estimator_active(const struct gnet_stats_basic *bstats, +bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est *rate_est) { ASSERT_RTNL(); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index c3d0ffeac243..8569310268ab 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -106,16 +106,21 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic *b) +gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) { if (d->compat_tc_stats) { d->tc_stats.bytes = b->bytes; d->tc_stats.packets = b->packets; } - if (d->tail) - return gnet_stats_copy(d, TCA_STATS_BASIC, b, sizeof(*b)); + if (d->tail) { + struct gnet_stats_basic sb; + memset(&sb, 0, sizeof(sb)); + sb.bytes = b->bytes; + sb.packets = b->packets; + return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb)); + } return 0; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index ddd2cd2b1775..1c1af2756f38 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -517,7 +517,7 @@ int net_assign_generic(struct net *net, int id, void *data) */ ng->len = id; - memcpy(&ng->ptr, &old_ng->ptr, old_ng->len); + memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); rcu_assign_pointer(net->gen, ng); call_rcu(&old_ng->rcu, net_generic_release); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 0ac309154b0d..0b4d0d35ef40 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -323,6 +323,11 @@ static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) udelay(USEC_PER_POLL); } + + WARN_ONCE(!irqs_disabled(), + "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n", + dev->name, ops->ndo_start_xmit); + local_irq_restore(flags); } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 19b8c20e98a4..0bcecbf06581 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -131,6 +131,7 @@ #include <linux/ioport.h> #include <linux/interrupt.h> #include <linux/capability.h> +#include <linux/hrtimer.h> #include <linux/freezer.h> #include <linux/delay.h> #include <linux/timer.h> @@ -162,14 +163,13 @@ #include <asm/byteorder.h> #include <linux/rcupdate.h> #include <linux/bitops.h> -#include <asm/io.h> +#include <linux/io.h> +#include <linux/timex.h> +#include <linux/uaccess.h> #include <asm/dma.h> -#include <asm/uaccess.h> #include <asm/div64.h> /* do_div */ -#include <asm/timex.h> - -#define VERSION "pktgen v2.70: Packet Generator for packet performance testing.\n" +#define VERSION "2.72" #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ #define MPLS_STACK_BOTTOM htonl(0x00000100) @@ -206,7 +206,7 @@ #define PKTGEN_MAGIC 0xbe9be955 #define PG_PROC_DIR "pktgen" #define PGCTRL "pgctrl" -static struct proc_dir_entry *pg_proc_dir = NULL; +static struct proc_dir_entry *pg_proc_dir; #define MAX_CFLOWS 65536 @@ -231,9 +231,9 @@ struct pktgen_dev { */ struct proc_dir_entry *entry; /* proc file */ struct pktgen_thread *pg_thread;/* the owner */ - struct list_head list; /* Used for chaining in the thread's run-queue */ + struct list_head list; /* chaining in the thread's run-queue */ - int running; /* if this changes to false, the test will stop */ + int running; /* if false, the test will stop */ /* If min != max, then we will either do a linear iteration, or * we will do a random selection from within the range. @@ -246,33 +246,37 @@ struct pktgen_dev { int max_pkt_size; /* = ETH_ZLEN; */ int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */ int nfrags; - __u32 delay_us; /* Default delay */ - __u32 delay_ns; + u64 delay; /* nano-seconds */ + __u64 count; /* Default No packets to send */ __u64 sofar; /* How many pkts we've sent so far */ __u64 tx_bytes; /* How many bytes we've transmitted */ - __u64 errors; /* Errors when trying to transmit, pkts will be re-sent */ + __u64 errors; /* Errors when trying to transmit, + pkts will be re-sent */ /* runtime counters relating to clone_skb */ - __u64 next_tx_us; /* timestamp of when to tx next */ - __u32 next_tx_ns; __u64 allocated_skbs; __u32 clone_count; int last_ok; /* Was last skb sent? - * Or a failed transmit of some sort? This will keep - * sequence numbers in order, for example. + * Or a failed transmit of some sort? + * This will keep sequence numbers in order */ - __u64 started_at; /* micro-seconds */ - __u64 stopped_at; /* micro-seconds */ - __u64 idle_acc; /* micro-seconds */ + ktime_t next_tx; + ktime_t started_at; + ktime_t stopped_at; + u64 idle_acc; /* nano-seconds */ + __u32 seq_num; - int clone_skb; /* Use multiple SKBs during packet gen. If this number - * is greater than 1, then that many copies of the same - * packet will be sent before a new packet is allocated. - * For instance, if you want to send 1024 identical packets - * before creating a new packet, set clone_skb to 1024. + int clone_skb; /* + * Use multiple SKBs during packet gen. + * If this number is greater than 1, then + * that many copies of the same packet will be + * sent before a new packet is allocated. + * If you want to send 1024 identical packets + * before creating a new packet, + * set clone_skb to 1024. */ char dst_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ @@ -304,8 +308,10 @@ struct pktgen_dev { __u16 udp_dst_max; /* exclusive, dest UDP port */ /* DSCP + ECN */ - __u8 tos; /* six most significant bits of (former) IPv4 TOS are for dscp codepoint */ - __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6 (see RFC 3260, sec. 4) */ + __u8 tos; /* six MSB of (former) IPv4 TOS + are for dscp codepoint */ + __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6 + (see RFC 3260, sec. 4) */ /* MPLS */ unsigned nr_labels; /* Depth of stack, 0 = no MPLS */ @@ -346,15 +352,17 @@ struct pktgen_dev { */ __u16 pad; /* pad out the hh struct to an even 16 bytes */ - struct sk_buff *skb; /* skb we are to transmit next, mainly used for when we + struct sk_buff *skb; /* skb we are to transmit next, used for when we * are transmitting the same one multiple times */ - struct net_device *odev; /* The out-going device. Note that the device should - * have it's pg_info pointer pointing back to this - * device. This will be set when the user specifies - * the out-going device name (not when the inject is - * started as it used to do.) - */ + struct net_device *odev; /* The out-going device. + * Note that the device should have it's + * pg_info pointer pointing back to this + * device. + * Set when the user specifies the out-going + * device name (not when the inject is + * started as it used to do.) + */ struct flow_state *flows; unsigned cflows; /* Concurrent flows (config) */ unsigned lflow; /* Flow length (config) */ @@ -379,13 +387,14 @@ struct pktgen_hdr { }; struct pktgen_thread { - spinlock_t if_lock; + spinlock_t if_lock; /* for list of devices */ struct list_head if_list; /* All device here */ struct list_head th_list; struct task_struct *tsk; char result[512]; - /* Field for thread to receive "posted" events terminate, stop ifs etc. */ + /* Field for thread to receive "posted" events terminate, + stop ifs etc. */ u32 control; int cpu; @@ -397,24 +406,22 @@ struct pktgen_thread { #define REMOVE 1 #define FIND 0 -/** Convert to micro-seconds */ -static inline __u64 tv_to_us(const struct timeval *tv) +static inline ktime_t ktime_now(void) { - __u64 us = tv->tv_usec; - us += (__u64) tv->tv_sec * (__u64) 1000000; - return us; + struct timespec ts; + ktime_get_ts(&ts); + + return timespec_to_ktime(ts); } -static __u64 getCurUs(void) +/* This works even if 32 bit because of careful byte order choice */ +static inline int ktime_lt(const ktime_t cmp1, const ktime_t cmp2) { - struct timeval tv; - do_gettimeofday(&tv); - return tv_to_us(&tv); + return cmp1.tv64 < cmp2.tv64; } -/* old include end */ - -static char version[] __initdata = VERSION; +static const char version[] = + "pktgen " VERSION ": Packet Generator for packet performance testing.\n"; static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); @@ -424,7 +431,7 @@ static int pktgen_device_event(struct notifier_block *, unsigned long, void *); static void pktgen_run_all_threads(void); static void pktgen_reset_all_threads(void); static void pktgen_stop_all_threads_ifs(void); -static int pktgen_stop_device(struct pktgen_dev *pkt_dev); + static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); @@ -432,10 +439,10 @@ static unsigned int scan_ip6(const char *s, char ip[16]); static unsigned int fmt_ip6(char *s, const char ip[16]); /* Module parameters, defaults. */ -static int pg_count_d = 1000; /* 1000 pkts by default */ -static int pg_delay_d; -static int pg_clone_skb_d; -static int debug; +static int pg_count_d __read_mostly = 1000; +static int pg_delay_d __read_mostly; +static int pg_clone_skb_d __read_mostly; +static int debug __read_mostly; static DEFINE_MUTEX(pktgen_thread_lock); static LIST_HEAD(pktgen_threads); @@ -451,12 +458,12 @@ static struct notifier_block pktgen_notifier_block = { static int pgctrl_show(struct seq_file *seq, void *v) { - seq_puts(seq, VERSION); + seq_puts(seq, version); return 0; } -static ssize_t pgctrl_write(struct file *file, const char __user * buf, - size_t count, loff_t * ppos) +static ssize_t pgctrl_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) { int err = 0; char data[128]; @@ -509,10 +516,9 @@ static const struct file_operations pktgen_fops = { static int pktgen_if_show(struct seq_file *seq, void *v) { - struct pktgen_dev *pkt_dev = seq->private; - __u64 sa; - __u64 stopped; - __u64 now = getCurUs(); + const struct pktgen_dev *pkt_dev = seq->private; + ktime_t stopped; + u64 idle; seq_printf(seq, "Params: count %llu min_pkt_size: %u max_pkt_size: %u\n", @@ -520,9 +526,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->max_pkt_size); seq_printf(seq, - " frags: %d delay: %u clone_skb: %d ifname: %s\n", - pkt_dev->nfrags, - 1000 * pkt_dev->delay_us + pkt_dev->delay_ns, + " frags: %d delay: %llu clone_skb: %d ifname: %s\n", + pkt_dev->nfrags, (unsigned long long) pkt_dev->delay, pkt_dev->clone_skb, pkt_dev->odev->name); seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, @@ -549,11 +554,14 @@ static int pktgen_if_show(struct seq_file *seq, void *v) " daddr: %s min_daddr: %s max_daddr: %s\n", b1, b2, b3); - } else + } else { + seq_printf(seq, + " dst_min: %s dst_max: %s\n", + pkt_dev->dst_min, pkt_dev->dst_max); seq_printf(seq, - " dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n", - pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min, - pkt_dev->src_max); + " src_min: %s src_max: %s\n", + pkt_dev->src_min, pkt_dev->src_max); + } seq_puts(seq, " src_mac: "); @@ -565,7 +573,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_printf(seq, "%pM\n", pkt_dev->dst_mac); seq_printf(seq, - " udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n", + " udp_src_min: %d udp_src_max: %d" + " udp_dst_min: %d udp_dst_max: %d\n", pkt_dev->udp_src_min, pkt_dev->udp_src_max, pkt_dev->udp_dst_min, pkt_dev->udp_dst_max); @@ -581,23 +590,21 @@ static int pktgen_if_show(struct seq_file *seq, void *v) i == pkt_dev->nr_labels-1 ? "\n" : ", "); } - if (pkt_dev->vlan_id != 0xffff) { + if (pkt_dev->vlan_id != 0xffff) seq_printf(seq, " vlan_id: %u vlan_p: %u vlan_cfi: %u\n", - pkt_dev->vlan_id, pkt_dev->vlan_p, pkt_dev->vlan_cfi); - } + pkt_dev->vlan_id, pkt_dev->vlan_p, + pkt_dev->vlan_cfi); - if (pkt_dev->svlan_id != 0xffff) { + if (pkt_dev->svlan_id != 0xffff) seq_printf(seq, " svlan_id: %u vlan_p: %u vlan_cfi: %u\n", - pkt_dev->svlan_id, pkt_dev->svlan_p, pkt_dev->svlan_cfi); - } + pkt_dev->svlan_id, pkt_dev->svlan_p, + pkt_dev->svlan_cfi); - if (pkt_dev->tos) { + if (pkt_dev->tos) seq_printf(seq, " tos: 0x%02x\n", pkt_dev->tos); - } - if (pkt_dev->traffic_class) { + if (pkt_dev->traffic_class) seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class); - } seq_printf(seq, " Flags: "); @@ -654,17 +661,21 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_puts(seq, "\n"); - sa = pkt_dev->started_at; - stopped = pkt_dev->stopped_at; - if (pkt_dev->running) - stopped = now; /* not really stopped, more like last-running-at */ + /* not really stopped, more like last-running-at */ + stopped = pkt_dev->running ? ktime_now() : pkt_dev->stopped_at; + idle = pkt_dev->idle_acc; + do_div(idle, NSEC_PER_USEC); seq_printf(seq, - "Current:\n pkts-sofar: %llu errors: %llu\n started: %lluus stopped: %lluus idle: %lluus\n", + "Current:\n pkts-sofar: %llu errors: %llu\n", (unsigned long long)pkt_dev->sofar, - (unsigned long long)pkt_dev->errors, (unsigned long long)sa, - (unsigned long long)stopped, - (unsigned long long)pkt_dev->idle_acc); + (unsigned long long)pkt_dev->errors); + + seq_printf(seq, + " started: %lluus stopped: %lluus idle: %lluus\n", + (unsigned long long) ktime_to_us(pkt_dev->started_at), + (unsigned long long) ktime_to_us(stopped), + (unsigned long long) idle); seq_printf(seq, " seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n", @@ -696,7 +707,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v) } -static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, __u32 *num) +static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, + __u32 *num) { int i = 0; *num = 0; @@ -846,9 +858,9 @@ static ssize_t pktgen_if_write(struct file *file, /* Read variable name */ len = strn_len(&user_buffer[i], sizeof(name) - 1); - if (len < 0) { + if (len < 0) return len; - } + memset(name, 0, sizeof(name)); if (copy_from_user(name, &user_buffer[i], len)) return -EFAULT; @@ -872,9 +884,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "min_pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; @@ -889,9 +901,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "max_pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; @@ -908,9 +920,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; @@ -925,9 +937,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "debug")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; debug = value; sprintf(pg_result, "OK: debug=%u", debug); @@ -936,9 +948,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "frags")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->nfrags = value; sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags); @@ -946,26 +958,24 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "delay")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; - if (value == 0x7FFFFFFF) { - pkt_dev->delay_us = 0x7FFFFFFF; - pkt_dev->delay_ns = 0; - } else { - pkt_dev->delay_us = value / 1000; - pkt_dev->delay_ns = value % 1000; - } - sprintf(pg_result, "OK: delay=%u", - 1000 * pkt_dev->delay_us + pkt_dev->delay_ns); + if (value == 0x7FFFFFFF) + pkt_dev->delay = ULLONG_MAX; + else + pkt_dev->delay = (u64)value * NSEC_PER_USEC; + + sprintf(pg_result, "OK: delay=%llu", + (unsigned long long) pkt_dev->delay); return count; } if (!strcmp(name, "udp_src_min")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value != pkt_dev->udp_src_min) { pkt_dev->udp_src_min = value; @@ -976,9 +986,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "udp_dst_min")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value != pkt_dev->udp_dst_min) { pkt_dev->udp_dst_min = value; @@ -989,9 +999,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "udp_src_max")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value != pkt_dev->udp_src_max) { pkt_dev->udp_src_max = value; @@ -1002,9 +1012,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "udp_dst_max")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value != pkt_dev->udp_dst_max) { pkt_dev->udp_dst_max = value; @@ -1015,9 +1025,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "clone_skb")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->clone_skb = value; @@ -1026,9 +1036,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->count = value; sprintf(pg_result, "OK: count=%llu", @@ -1037,9 +1047,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "src_mac_count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (pkt_dev->src_mac_count != value) { pkt_dev->src_mac_count = value; @@ -1051,9 +1061,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "dst_mac_count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (pkt_dev->dst_mac_count != value) { pkt_dev->dst_mac_count = value; @@ -1067,9 +1077,9 @@ static ssize_t pktgen_if_write(struct file *file, char f[32]; memset(f, 0, 32); len = strn_len(&user_buffer[i], sizeof(f) - 1); - if (len < 0) { + if (len < 0) return len; - } + if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; i += len; @@ -1168,9 +1178,8 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "dst_min") || !strcmp(name, "dst")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_min) - 1); - if (len < 0) { + if (len < 0) return len; - } if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; @@ -1190,9 +1199,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "dst_max")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_max) - 1); - if (len < 0) { + if (len < 0) return len; - } + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; @@ -1303,9 +1312,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "src_min")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_min) - 1); - if (len < 0) { + if (len < 0) return len; - } + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; buf[len] = 0; @@ -1324,9 +1333,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "src_max")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_max) - 1); - if (len < 0) { + if (len < 0) return len; - } + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; buf[len] = 0; @@ -1350,9 +1359,9 @@ static ssize_t pktgen_if_write(struct file *file, memcpy(old_dmac, pkt_dev->dst_mac, ETH_ALEN); len = strn_len(&user_buffer[i], sizeof(valstr) - 1); - if (len < 0) { + if (len < 0) return len; - } + memset(valstr, 0, sizeof(valstr)); if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; @@ -1392,9 +1401,9 @@ static ssize_t pktgen_if_write(struct file *file, memcpy(old_smac, pkt_dev->src_mac, ETH_ALEN); len = strn_len(&user_buffer[i], sizeof(valstr) - 1); - if (len < 0) { + if (len < 0) return len; - } + memset(valstr, 0, sizeof(valstr)); if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; @@ -1435,9 +1444,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "flows")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value > MAX_CFLOWS) value = MAX_CFLOWS; @@ -1449,9 +1458,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "flowlen")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->lflow = value; sprintf(pg_result, "OK: flowlen=%u", pkt_dev->lflow); @@ -1460,9 +1469,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "queue_map_min")) { len = num_arg(&user_buffer[i], 5, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->queue_map_min = value; sprintf(pg_result, "OK: queue_map_min=%u", pkt_dev->queue_map_min); @@ -1471,9 +1480,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "queue_map_max")) { len = num_arg(&user_buffer[i], 5, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->queue_map_max = value; sprintf(pg_result, "OK: queue_map_max=%u", pkt_dev->queue_map_max); @@ -1505,9 +1514,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "vlan_id")) { len = num_arg(&user_buffer[i], 4, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value <= 4095) { pkt_dev->vlan_id = value; /* turn on VLAN */ @@ -1532,9 +1541,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "vlan_p")) { len = num_arg(&user_buffer[i], 1, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) { pkt_dev->vlan_p = value; @@ -1547,9 +1556,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "vlan_cfi")) { len = num_arg(&user_buffer[i], 1, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) { pkt_dev->vlan_cfi = value; @@ -1562,9 +1571,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "svlan_id")) { len = num_arg(&user_buffer[i], 4, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) { pkt_dev->svlan_id = value; /* turn on SVLAN */ @@ -1589,9 +1598,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "svlan_p")) { len = num_arg(&user_buffer[i], 1, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) { pkt_dev->svlan_p = value; @@ -1604,9 +1613,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "svlan_cfi")) { len = num_arg(&user_buffer[i], 1, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) { pkt_dev->svlan_cfi = value; @@ -1620,9 +1629,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "tos")) { __u32 tmp_value = 0; len = hex32_arg(&user_buffer[i], 2, &tmp_value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (len == 2) { pkt_dev->tos = tmp_value; @@ -1636,9 +1645,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "traffic_class")) { __u32 tmp_value = 0; len = hex32_arg(&user_buffer[i], 2, &tmp_value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (len == 2) { pkt_dev->traffic_class = tmp_value; @@ -1670,7 +1679,7 @@ static const struct file_operations pktgen_if_fops = { static int pktgen_thread_show(struct seq_file *seq, void *v) { struct pktgen_thread *t = seq->private; - struct pktgen_dev *pkt_dev; + const struct pktgen_dev *pkt_dev; BUG_ON(!t); @@ -1873,8 +1882,10 @@ static void pktgen_change_name(struct net_device *dev) remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); - pkt_dev->entry = create_proc_entry(dev->name, 0600, - pg_proc_dir); + pkt_dev->entry = proc_create_data(dev->name, 0600, + pg_proc_dir, + &pktgen_if_fops, + pkt_dev); if (!pkt_dev->entry) printk(KERN_ERR "pktgen: can't move proc " " entry for '%s'\n", dev->name); @@ -1908,13 +1919,14 @@ static int pktgen_device_event(struct notifier_block *unused, return NOTIFY_DONE; } -static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, const char *ifname) +static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, + const char *ifname) { char b[IFNAMSIZ+5]; int i = 0; - for(i=0; ifname[i] != '@'; i++) { - if(i == IFNAMSIZ) + for (i = 0; ifname[i] != '@'; i++) { + if (i == IFNAMSIZ) break; b[i] = ifname[i]; @@ -1981,7 +1993,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) printk(KERN_WARNING "pktgen: WARNING: Requested " "queue_map_min (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", - pkt_dev->queue_map_min, (ntxq ?: 1)- 1, ntxq, + pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, pkt_dev->odev->name); pkt_dev->queue_map_min = ntxq - 1; } @@ -1989,7 +2001,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) printk(KERN_WARNING "pktgen: WARNING: Requested " "queue_map_max (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", - pkt_dev->queue_map_max, (ntxq ?: 1)- 1, ntxq, + pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, pkt_dev->odev->name); pkt_dev->queue_map_max = ntxq - 1; } @@ -2030,7 +2042,8 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) */ rcu_read_lock(); - if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) { + idev = __in6_dev_get(pkt_dev->odev); + if (idev) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); @@ -2089,27 +2102,40 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) pkt_dev->nflows = 0; } -static void spin(struct pktgen_dev *pkt_dev, __u64 spin_until_us) + +static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) { - __u64 start; - __u64 now; + ktime_t start; + s32 remaining; + struct hrtimer_sleeper t; + + hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_set_expires(&t.timer, spin_until); + + remaining = ktime_to_us(hrtimer_expires_remaining(&t.timer)); + if (remaining <= 0) + return; - start = now = getCurUs(); - while (now < spin_until_us) { - /* TODO: optimize sleeping behavior */ - if (spin_until_us - now > jiffies_to_usecs(1) + 1) - schedule_timeout_interruptible(1); - else if (spin_until_us - now > 100) { - if (!pkt_dev->running) - return; - if (need_resched()) + start = ktime_now(); + if (remaining < 100) + udelay(remaining); /* really small just spin */ + else { + /* see do_nanosleep */ + hrtimer_init_sleeper(&t, current); + do { + set_current_state(TASK_INTERRUPTIBLE); + hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); + if (!hrtimer_active(&t.timer)) + t.task = NULL; + + if (likely(t.task)) schedule(); - } - now = getCurUs(); + hrtimer_cancel(&t.timer); + } while (t.task && pkt_dev->running && !signal_pending(current)); + __set_current_state(TASK_RUNNING); } - - pkt_dev->idle_acc += now - start; + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), start)); } static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) @@ -2120,13 +2146,9 @@ static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev); } -static inline int f_seen(struct pktgen_dev *pkt_dev, int flow) +static inline int f_seen(const struct pktgen_dev *pkt_dev, int flow) { - - if (pkt_dev->flows[flow].flags & F_INIT) - return 1; - else - return 0; + return !!(pkt_dev->flows[flow].flags & F_INIT); } static inline int f_pick(struct pktgen_dev *pkt_dev) @@ -2174,7 +2196,7 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) if (x) { pkt_dev->flows[flow].x = x; set_pkt_overhead(pkt_dev); - pkt_dev->pkt_overhead+=x->props.header_len; + pkt_dev->pkt_overhead += x->props.header_len; } } @@ -2313,18 +2335,18 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (!(pkt_dev->flags & F_IPV6)) { - if ((imn = ntohl(pkt_dev->saddr_min)) < (imx = - ntohl(pkt_dev-> - saddr_max))) { + imn = ntohl(pkt_dev->saddr_min); + imx = ntohl(pkt_dev->saddr_max); + if (imn < imx) { __u32 t; if (pkt_dev->flags & F_IPSRC_RND) t = random32() % (imx - imn) + imn; else { t = ntohl(pkt_dev->cur_saddr); t++; - if (t > imx) { + if (t > imx) t = imn; - } + } pkt_dev->cur_saddr = htonl(t); } @@ -2435,14 +2457,14 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) if (err) goto error; - x->curlft.bytes +=skb->len; + x->curlft.bytes += skb->len; x->curlft.packets++; error: spin_unlock(&x->lock); return err; } -static inline void free_SAs(struct pktgen_dev *pkt_dev) +static void free_SAs(struct pktgen_dev *pkt_dev) { if (pkt_dev->cflows) { /* let go of the SAs if we have them */ @@ -2457,7 +2479,7 @@ static inline void free_SAs(struct pktgen_dev *pkt_dev) } } -static inline int process_ipsec(struct pktgen_dev *pkt_dev, +static int process_ipsec(struct pktgen_dev *pkt_dev, struct sk_buff *skb, __be16 protocol) { if (pkt_dev->flags & F_IPSEC_ON) { @@ -2467,11 +2489,11 @@ static inline int process_ipsec(struct pktgen_dev *pkt_dev, int ret; __u8 *eth; nhead = x->props.header_len - skb_headroom(skb); - if (nhead >0) { + if (nhead > 0) { ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); if (ret < 0) { printk(KERN_ERR "Error expanding " - "ipsec packet %d\n",ret); + "ipsec packet %d\n", ret); goto err; } } @@ -2481,13 +2503,13 @@ static inline int process_ipsec(struct pktgen_dev *pkt_dev, ret = pktgen_output_ipsec(skb, pkt_dev); if (ret) { printk(KERN_ERR "Error creating ipsec " - "packet %d\n",ret); + "packet %d\n", ret); goto err; } /* restore ll */ eth = (__u8 *) skb_push(skb, ETH_HLEN); memcpy(eth, pkt_dev->hh, 12); - *(u16 *) & eth[12] = protocol; + *(u16 *) ð[12] = protocol; } } return 1; @@ -2500,9 +2522,9 @@ err: static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev) { unsigned i; - for (i = 0; i < pkt_dev->nr_labels; i++) { + for (i = 0; i < pkt_dev->nr_labels; i++) *mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM; - } + mpls--; *mpls |= MPLS_STACK_BOTTOM; } @@ -2543,8 +2565,9 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mod_cur_headers(pkt_dev); datalen = (odev->hard_header_len + 16) & ~0xf; - skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + datalen + - pkt_dev->pkt_overhead, GFP_ATOMIC); + skb = __netdev_alloc_skb(odev, + pkt_dev->cur_pkt_size + 64 + + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -2668,8 +2691,9 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, } } - /* Stamp the time, and sequence number, convert them to network byte order */ - + /* Stamp the time, and sequence number, + * convert them to network byte order + */ if (pgh) { struct timeval timestamp; @@ -2882,8 +2906,9 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, queue_map = pkt_dev->cur_queue_map; mod_cur_headers(pkt_dev); - skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16 + - pkt_dev->pkt_overhead, GFP_ATOMIC); + skb = __netdev_alloc_skb(odev, + pkt_dev->cur_pkt_size + 64 + + 16 + pkt_dev->pkt_overhead, GFP_NOWAIT); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -2922,7 +2947,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, udph = udp_hdr(skb); memcpy(eth, pkt_dev->hh, 12); - *(__be16 *) & eth[12] = protocol; + *(__be16 *) ð[12] = protocol; /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - @@ -3016,8 +3041,10 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, } } - /* Stamp the time, and sequence number, convert them to network byte order */ - /* should we update cloned packets too ? */ + /* Stamp the time, and sequence number, + * convert them to network byte order + * should we update cloned packets too ? + */ if (pgh) { struct timeval timestamp; @@ -3033,8 +3060,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, return skb; } -static inline struct sk_buff *fill_packet(struct net_device *odev, - struct pktgen_dev *pkt_dev) +static struct sk_buff *fill_packet(struct net_device *odev, + struct pktgen_dev *pkt_dev) { if (pkt_dev->flags & F_IPV6) return fill_packet_ipv6(odev, pkt_dev); @@ -3072,9 +3099,9 @@ static void pktgen_run(struct pktgen_thread *t) pktgen_clear_counters(pkt_dev); pkt_dev->running = 1; /* Cranke yeself! */ pkt_dev->skb = NULL; - pkt_dev->started_at = getCurUs(); - pkt_dev->next_tx_us = getCurUs(); /* Transmit immediately */ - pkt_dev->next_tx_ns = 0; + pkt_dev->started_at = + pkt_dev->next_tx = ktime_now(); + set_pkt_overhead(pkt_dev); strcpy(pkt_dev->result, "Starting"); @@ -3101,17 +3128,14 @@ static void pktgen_stop_all_threads_ifs(void) mutex_unlock(&pktgen_thread_lock); } -static int thread_is_running(struct pktgen_thread *t) +static int thread_is_running(const struct pktgen_thread *t) { - struct pktgen_dev *pkt_dev; - int res = 0; + const struct pktgen_dev *pkt_dev; list_for_each_entry(pkt_dev, &t->if_list, list) - if (pkt_dev->running) { - res = 1; - break; - } - return res; + if (pkt_dev->running) + return 1; + return 0; } static int pktgen_wait_thread_run(struct pktgen_thread *t) @@ -3168,7 +3192,8 @@ static void pktgen_run_all_threads(void) mutex_unlock(&pktgen_thread_lock); - schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ + /* Propagate thread->control */ + schedule_timeout_interruptible(msecs_to_jiffies(125)); pktgen_wait_all_threads_run(); } @@ -3186,35 +3211,29 @@ static void pktgen_reset_all_threads(void) mutex_unlock(&pktgen_thread_lock); - schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ + /* Propagate thread->control */ + schedule_timeout_interruptible(msecs_to_jiffies(125)); pktgen_wait_all_threads_run(); } static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) { - __u64 total_us, bps, mbps, pps, idle; + __u64 bps, mbps, pps; char *p = pkt_dev->result; - - total_us = pkt_dev->stopped_at - pkt_dev->started_at; - - idle = pkt_dev->idle_acc; - - p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", - (unsigned long long)total_us, - (unsigned long long)(total_us - idle), - (unsigned long long)idle, + ktime_t elapsed = ktime_sub(pkt_dev->stopped_at, + pkt_dev->started_at); + ktime_t idle = ns_to_ktime(pkt_dev->idle_acc); + + p += sprintf(p, "OK: %llu(c%llu+d%llu) nsec, %llu (%dbyte,%dfrags)\n", + (unsigned long long)ktime_to_us(elapsed), + (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)), + (unsigned long long)ktime_to_us(idle), (unsigned long long)pkt_dev->sofar, pkt_dev->cur_pkt_size, nr_frags); - pps = pkt_dev->sofar * USEC_PER_SEC; - - while ((total_us >> 32) != 0) { - pps >>= 1; - total_us >>= 1; - } - - do_div(pps, total_us); + pps = div64_u64(pkt_dev->sofar * NSEC_PER_SEC, + ktime_to_ns(elapsed)); bps = pps * 8 * pkt_dev->cur_pkt_size; @@ -3228,7 +3247,6 @@ static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) } /* Set stopped-at timer, remove from running list, do counters & statistics */ - static int pktgen_stop_device(struct pktgen_dev *pkt_dev) { int nr_frags = pkt_dev->skb ? skb_shinfo(pkt_dev->skb)->nr_frags : -1; @@ -3239,7 +3257,9 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) return -EINVAL; } - pkt_dev->stopped_at = getCurUs(); + kfree_skb(pkt_dev->skb); + pkt_dev->skb = NULL; + pkt_dev->stopped_at = ktime_now(); pkt_dev->running = 0; show_results(pkt_dev, nr_frags); @@ -3258,7 +3278,7 @@ static struct pktgen_dev *next_to_run(struct pktgen_thread *t) continue; if (best == NULL) best = pkt_dev; - else if (pkt_dev->next_tx_us < best->next_tx_us) + else if (ktime_lt(pkt_dev->next_tx, best->next_tx)) best = pkt_dev; } if_unlock(t); @@ -3275,9 +3295,6 @@ static void pktgen_stop(struct pktgen_thread *t) list_for_each_entry(pkt_dev, &t->if_list, list) { pktgen_stop_device(pkt_dev); - kfree_skb(pkt_dev->skb); - - pkt_dev->skb = NULL; } if_unlock(t); @@ -3348,30 +3365,37 @@ static void pktgen_rem_thread(struct pktgen_thread *t) mutex_unlock(&pktgen_thread_lock); } -static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) +static void idle(struct pktgen_dev *pkt_dev) +{ + ktime_t idle_start = ktime_now(); + + if (need_resched()) + schedule(); + else + cpu_relax(); + + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start)); +} + + +static void pktgen_xmit(struct pktgen_dev *pkt_dev) { struct net_device *odev = pkt_dev->odev; - int (*xmit)(struct sk_buff *, struct net_device *) + netdev_tx_t (*xmit)(struct sk_buff *, struct net_device *) = odev->netdev_ops->ndo_start_xmit; struct netdev_queue *txq; - __u64 idle_start = 0; u16 queue_map; int ret; - if (pkt_dev->delay_us || pkt_dev->delay_ns) { - u64 now; - - now = getCurUs(); - if (now < pkt_dev->next_tx_us) - spin(pkt_dev, pkt_dev->next_tx_us); + if (pkt_dev->delay) { + spin(pkt_dev, pkt_dev->next_tx); /* This is max DELAY, this has special meaning of * "never transmit" */ - if (pkt_dev->delay_us == 0x7FFFFFFF) { - pkt_dev->next_tx_us = getCurUs() + pkt_dev->delay_us; - pkt_dev->next_tx_ns = pkt_dev->delay_ns; - goto out; + if (pkt_dev->delay == ULLONG_MAX) { + pkt_dev->next_tx = ktime_add_ns(ktime_now(), ULONG_MAX); + return; } } @@ -3383,47 +3407,32 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) } txq = netdev_get_tx_queue(odev, queue_map); - if (netif_tx_queue_stopped(txq) || - netif_tx_queue_frozen(txq) || - need_resched()) { - idle_start = getCurUs(); - - if (!netif_running(odev)) { + /* Did we saturate the queue already? */ + if (netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq)) { + /* If device is down, then all queues are permnantly frozen */ + if (netif_running(odev)) + idle(pkt_dev); + else pktgen_stop_device(pkt_dev); - kfree_skb(pkt_dev->skb); - pkt_dev->skb = NULL; - goto out; - } - if (need_resched()) - schedule(); - - pkt_dev->idle_acc += getCurUs() - idle_start; - - if (netif_tx_queue_stopped(txq) || - netif_tx_queue_frozen(txq)) { - pkt_dev->next_tx_us = getCurUs(); /* TODO */ - pkt_dev->next_tx_ns = 0; - goto out; /* Try the next interface */ - } + return; } - if (pkt_dev->last_ok || !pkt_dev->skb) { - if ((++pkt_dev->clone_count >= pkt_dev->clone_skb) - || (!pkt_dev->skb)) { - /* build a new pkt */ - kfree_skb(pkt_dev->skb); + if (!pkt_dev->skb || (pkt_dev->last_ok && + ++pkt_dev->clone_count >= pkt_dev->clone_skb)) { + /* build a new pkt */ + kfree_skb(pkt_dev->skb); - pkt_dev->skb = fill_packet(odev, pkt_dev); - if (pkt_dev->skb == NULL) { - printk(KERN_ERR "pktgen: ERROR: couldn't " - "allocate skb in fill_packet.\n"); - schedule(); - pkt_dev->clone_count--; /* back out increment, OOM */ - goto out; - } - pkt_dev->allocated_skbs++; - pkt_dev->clone_count = 0; /* reset counter */ + pkt_dev->skb = fill_packet(odev, pkt_dev); + if (pkt_dev->skb == NULL) { + printk(KERN_ERR "pktgen: ERROR: couldn't " + "allocate skb in fill_packet.\n"); + schedule(); + pkt_dev->clone_count--; /* back out increment, OOM */ + return; } + + pkt_dev->allocated_skbs++; + pkt_dev->clone_count = 0; /* reset counter */ } /* fill_packet() might have changed the queue */ @@ -3431,73 +3440,53 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) txq = netdev_get_tx_queue(odev, queue_map); __netif_tx_lock_bh(txq); - if (!netif_tx_queue_stopped(txq) && - !netif_tx_queue_frozen(txq)) { - + if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) + pkt_dev->last_ok = 0; + else { atomic_inc(&(pkt_dev->skb->users)); - retry_now: + + retry_now: ret = (*xmit)(pkt_dev->skb, odev); - if (likely(ret == NETDEV_TX_OK)) { + switch (ret) { + case NETDEV_TX_OK: txq_trans_update(txq); pkt_dev->last_ok = 1; pkt_dev->sofar++; pkt_dev->seq_num++; pkt_dev->tx_bytes += pkt_dev->cur_pkt_size; - - } else if (ret == NETDEV_TX_LOCKED - && (odev->features & NETIF_F_LLTX)) { + break; + case NETDEV_TX_LOCKED: cpu_relax(); goto retry_now; - } else { /* Retry it next time */ - - atomic_dec(&(pkt_dev->skb->users)); - - if (debug && net_ratelimit()) - printk(KERN_INFO "pktgen: Hard xmit error\n"); - + default: /* Drivers are not supposed to return other values! */ + if (net_ratelimit()) + pr_info("pktgen: %s xmit error: %d\n", + odev->name, ret); pkt_dev->errors++; + /* fallthru */ + case NETDEV_TX_BUSY: + /* Retry it next time */ + atomic_dec(&(pkt_dev->skb->users)); pkt_dev->last_ok = 0; } - pkt_dev->next_tx_us = getCurUs(); - pkt_dev->next_tx_ns = 0; - - pkt_dev->next_tx_us += pkt_dev->delay_us; - pkt_dev->next_tx_ns += pkt_dev->delay_ns; - - if (pkt_dev->next_tx_ns > 1000) { - pkt_dev->next_tx_us++; - pkt_dev->next_tx_ns -= 1000; - } + if (pkt_dev->delay) + pkt_dev->next_tx = ktime_add_ns(ktime_now(), + pkt_dev->delay); } - - else { /* Retry it next time */ - pkt_dev->last_ok = 0; - pkt_dev->next_tx_us = getCurUs(); /* TODO */ - pkt_dev->next_tx_ns = 0; - } - __netif_tx_unlock_bh(txq); /* If pkt_dev->count is zero, then run forever */ if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) { - if (atomic_read(&(pkt_dev->skb->users)) != 1) { - idle_start = getCurUs(); - while (atomic_read(&(pkt_dev->skb->users)) != 1) { - if (signal_pending(current)) { - break; - } - schedule(); - } - pkt_dev->idle_acc += getCurUs() - idle_start; + while (atomic_read(&(pkt_dev->skb->users)) != 1) { + if (signal_pending(current)) + break; + idle(pkt_dev); } /* Done with this */ pktgen_stop_device(pkt_dev); - kfree_skb(pkt_dev->skb); - pkt_dev->skb = NULL; } -out:; } /* @@ -3516,7 +3505,8 @@ static int pktgen_thread_worker(void *arg) init_waitqueue_head(&t->queue); complete(&t->start_done); - pr_debug("pktgen: starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current)); + pr_debug("pktgen: starting pktgen/%d: pid=%d\n", + cpu, task_pid_nr(current)); set_current_state(TASK_INTERRUPTIBLE); @@ -3651,8 +3641,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->max_pkt_size = ETH_ZLEN; pkt_dev->nfrags = 0; pkt_dev->clone_skb = pg_clone_skb_d; - pkt_dev->delay_us = pg_delay_d / 1000; - pkt_dev->delay_ns = pg_delay_d % 1000; + pkt_dev->delay = pg_delay_d; pkt_dev->count = pg_count_d; pkt_dev->sofar = 0; pkt_dev->udp_src_min = 9; /* sink port */ @@ -3864,10 +3853,15 @@ static void __exit pg_cleanup(void) module_init(pg_init); module_exit(pg_cleanup); -MODULE_AUTHOR("Robert Olsson <robert.olsson@its.uu.se"); +MODULE_AUTHOR("Robert Olsson <robert.olsson@its.uu.se>"); MODULE_DESCRIPTION("Packet Generator tool"); MODULE_LICENSE("GPL"); +MODULE_VERSION(VERSION); module_param(pg_count_d, int, 0); +MODULE_PARM_DESC(pg_count_d, "Default number of packets to inject"); module_param(pg_delay_d, int, 0); +MODULE_PARM_DESC(pg_delay_d, "Default delay between packets (nanoseconds)"); module_param(pg_clone_skb_d, int, 0); +MODULE_PARM_DESC(pg_clone_skb_d, "Default number of copies of the same packet"); module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Enable debugging of pktgen module"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b44775f9f2bf..eb42873f2a3a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -606,7 +606,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags) { - struct netdev_queue *txq; struct ifinfomsg *ifm; struct nlmsghdr *nlh; const struct net_device_stats *stats; @@ -637,9 +636,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (dev->master) NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex); - txq = netdev_get_tx_queue(dev, 0); - if (txq->qdisc_sleeping) - NLA_PUT_STRING(skb, IFLA_QDISC, txq->qdisc_sleeping->ops->id); + if (dev->qdisc) + NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc->ops->id); if (dev->ifalias) NLA_PUT_STRING(skb, IFLA_IFALIAS, dev->ifalias); @@ -974,12 +972,20 @@ struct net_device *rtnl_create_link(struct net *net, char *ifname, { int err; struct net_device *dev; + unsigned int num_queues = 1; + unsigned int real_num_queues = 1; + if (ops->get_tx_queues) { + err = ops->get_tx_queues(net, tb, &num_queues, &real_num_queues); + if (err) + goto err; + } err = -ENOMEM; - dev = alloc_netdev(ops->priv_size, ifname, ops->setup); + dev = alloc_netdev_mq(ops->priv_size, ifname, ops->setup, num_queues); if (!dev) goto err; + dev->real_num_tx_queues = real_num_queues; if (strchr(dev->name, '%')) { err = dev_alloc_name(dev, dev->name); if (err < 0) diff --git a/net/core/sock.c b/net/core/sock.c index 3ac34ea6ec05..30d5446512f9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1035,6 +1035,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, sk->sk_prot = sk->sk_prot_creator = prot; sock_lock_init(sk); sock_net_set(sk, get_net(net)); + atomic_set(&sk->sk_wmem_alloc, 1); } return sk; @@ -1882,7 +1883,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) */ smp_wmb(); atomic_set(&sk->sk_refcnt, 1); - atomic_set(&sk->sk_wmem_alloc, 1); atomic_set(&sk->sk_drops, 0); } EXPORT_SYMBOL(sock_init_data); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 8379496de82b..e0879bfb7dd5 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -64,6 +64,7 @@ static struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { [DCB_ATTR_CAP] = {.type = NLA_NESTED}, [DCB_ATTR_PFC_STATE] = {.type = NLA_U8}, [DCB_ATTR_BCN] = {.type = NLA_NESTED}, + [DCB_ATTR_APP] = {.type = NLA_NESTED}, }; /* DCB priority flow control to User Priority nested attributes */ @@ -158,6 +159,13 @@ static struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = { [DCB_BCN_ATTR_ALL] = {.type = NLA_FLAG}, }; +/* DCB APP nested attributes. */ +static struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = { + [DCB_APP_ATTR_IDTYPE] = {.type = NLA_U8}, + [DCB_APP_ATTR_ID] = {.type = NLA_U16}, + [DCB_APP_ATTR_PRIORITY] = {.type = NLA_U8}, +}; + /* standard netlink reply call */ static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid, u32 seq, u16 flags) @@ -536,6 +544,120 @@ static int dcbnl_setpfcstate(struct net_device *netdev, struct nlattr **tb, return ret; } +static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + struct sk_buff *dcbnl_skb; + struct nlmsghdr *nlh; + struct dcbmsg *dcb; + struct nlattr *app_nest; + struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; + u16 id; + u8 up, idtype; + int ret = -EINVAL; + + if (!tb[DCB_ATTR_APP] || !netdev->dcbnl_ops->getapp) + goto out; + + ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], + dcbnl_app_nest); + if (ret) + goto out; + + ret = -EINVAL; + /* all must be non-null */ + if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || + (!app_tb[DCB_APP_ATTR_ID])) + goto out; + + /* either by eth type or by socket number */ + idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); + if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && + (idtype != DCB_APP_IDTYPE_PORTNUM)) + goto out; + + id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); + up = netdev->dcbnl_ops->getapp(netdev, idtype, id); + + /* send this back */ + dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!dcbnl_skb) + goto out; + + nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); + dcb = NLMSG_DATA(nlh); + dcb->dcb_family = AF_UNSPEC; + dcb->cmd = DCB_CMD_GAPP; + + app_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_APP); + ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_IDTYPE, idtype); + if (ret) + goto out_cancel; + + ret = nla_put_u16(dcbnl_skb, DCB_APP_ATTR_ID, id); + if (ret) + goto out_cancel; + + ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_PRIORITY, up); + if (ret) + goto out_cancel; + + nla_nest_end(dcbnl_skb, app_nest); + nlmsg_end(dcbnl_skb, nlh); + + ret = rtnl_unicast(dcbnl_skb, &init_net, pid); + if (ret) + goto nlmsg_failure; + + goto out; + +out_cancel: + nla_nest_cancel(dcbnl_skb, app_nest); +nlmsg_failure: + kfree_skb(dcbnl_skb); +out: + return ret; +} + +static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + int ret = -EINVAL; + u16 id; + u8 up, idtype; + struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; + + if (!tb[DCB_ATTR_APP] || !netdev->dcbnl_ops->setapp) + goto out; + + ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], + dcbnl_app_nest); + if (ret) + goto out; + + ret = -EINVAL; + /* all must be non-null */ + if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || + (!app_tb[DCB_APP_ATTR_ID]) || + (!app_tb[DCB_APP_ATTR_PRIORITY])) + goto out; + + /* either by eth type or by socket number */ + idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); + if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && + (idtype != DCB_APP_IDTYPE_PORTNUM)) + goto out; + + id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); + up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]); + + ret = dcbnl_reply(netdev->dcbnl_ops->setapp(netdev, idtype, id, up), + RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP, + pid, seq, flags); +out: + return ret; +} + static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb, u32 pid, u32 seq, u16 flags, int dir) { @@ -1093,6 +1215,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ret = dcbnl_bcn_setcfg(netdev, tb, pid, nlh->nlmsg_seq, nlh->nlmsg_flags); goto out; + case DCB_CMD_GAPP: + ret = dcbnl_getapp(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); + goto out; + case DCB_CMD_SAPP: + ret = dcbnl_setapp(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); + goto out; default: goto errout; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index a0a36c9e6cce..d01c00de1ad0 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -880,7 +880,7 @@ discard_and_relse: goto discard_it; } -static struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { +static const struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { .queue_xmit = ip_queue_xmit, .send_check = dccp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 3e70faab2989..64f011cc4491 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -35,8 +35,8 @@ /* The per-net dccp.v6_ctl_sk is used for sending RSTs and ACKs */ -static struct inet_connection_sock_af_ops dccp_ipv6_mapped; -static struct inet_connection_sock_af_ops dccp_ipv6_af_ops; +static const struct inet_connection_sock_af_ops dccp_ipv6_mapped; +static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops; static void dccp_v6_hash(struct sock *sk) { @@ -1055,7 +1055,7 @@ failure: return err; } -static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { +static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { .queue_xmit = inet6_csk_xmit, .send_check = dccp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, @@ -1076,7 +1076,7 @@ static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { /* * DCCP over IPv4 via INET6 API */ -static struct inet_connection_sock_af_ops dccp_ipv6_mapped = { +static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = dccp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 37b3b4293ef4..923db06c7e55 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1066,7 +1066,7 @@ static int __init dccp_init(void) (dccp_hashinfo.ehash_size - 1)) dccp_hashinfo.ehash_size--; dccp_hashinfo.ehash = (struct inet_ehash_bucket *) - __get_free_pages(GFP_ATOMIC, ehash_order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order); } while (!dccp_hashinfo.ehash && --ehash_order > 0); if (!dccp_hashinfo.ehash) { @@ -1091,7 +1091,7 @@ static int __init dccp_init(void) bhash_order > 0) continue; dccp_hashinfo.bhash = (struct inet_bind_hashbucket *) - __get_free_pages(GFP_ATOMIC, bhash_order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order); } while (!dccp_hashinfo.bhash && --bhash_order >= 0); if (!dccp_hashinfo.bhash) { @@ -1159,6 +1159,7 @@ static void __exit dccp_fini(void) kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); + percpu_counter_destroy(&dccp_orphan_count); } module_init(dccp_init); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 923786bd6d01..794b5bf95af1 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -59,7 +59,7 @@ static int dn_phase3_output(struct sk_buff *); /* * For talking to broadcast devices: Ethernet & PPP */ -static struct neigh_ops dn_long_ops = { +static const struct neigh_ops dn_long_ops = { .family = AF_DECnet, .error_report = dn_long_error_report, .output = dn_long_output, @@ -71,7 +71,7 @@ static struct neigh_ops dn_long_ops = { /* * For talking to pointopoint and multidrop devices: DDCMP and X.25 */ -static struct neigh_ops dn_short_ops = { +static const struct neigh_ops dn_short_ops = { .family = AF_DECnet, .error_report = dn_short_error_report, .output = dn_short_output, @@ -83,7 +83,7 @@ static struct neigh_ops dn_short_ops = { /* * For talking to DECnet phase III nodes */ -static struct neigh_ops dn_phase3_ops = { +static const struct neigh_ops dn_phase3_ops = { .family = AF_DECnet, .error_report = dn_short_error_report, /* Can use short version here */ .output = dn_phase3_output, diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 41055f33d28a..4b0ea0540442 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -169,13 +169,13 @@ struct net_device *dsa_slave_create(struct dsa_switch *ds, int port, char *name); /* tag_dsa.c */ -int dsa_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev); /* tag_edsa.c */ -int edsa_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev); /* tag_trailer.c */ -int trailer_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev); #endif diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 8fa25bafe6ca..cdf2d28a0297 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -15,7 +15,7 @@ #define DSA_HLEN 4 -int dsa_xmit(struct sk_buff *skb, struct net_device *dev) +netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); u8 *dsa_header; diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 815607bd286f..8f53948cff4f 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -16,7 +16,7 @@ #define DSA_HLEN 4 #define EDSA_HLEN 8 -int edsa_xmit(struct sk_buff *skb, struct net_device *dev) +netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); u8 *edsa_header; diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 1c3e30c38b86..a85c829853c0 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -13,7 +13,7 @@ #include <linux/netdevice.h> #include "dsa_priv.h" -int trailer_xmit(struct sk_buff *skb, struct net_device *dev) +netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); struct sk_buff *nskb; diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index e114da7ca9b8..0e0254fd767d 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -520,6 +520,7 @@ static int econet_getname(struct socket *sock, struct sockaddr *uaddr, if (peer) return -EOPNOTSUPP; + memset(sec, 0, sizeof(*sec)); mutex_lock(&econet_mutex); sk = sock->sk; diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index f99338a26100..4068a9f5113e 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -1,4 +1,4 @@ -obj-$(CONFIG_IEEE802154) += nl802154.o af_802154.o +obj-$(CONFIG_IEEE802154) += nl802154.o af_802154.o wpan-class.o nl802154-y := netlink.o nl_policy.o af_802154-y := af_ieee802154.o raw.o dgram.o diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 69c8d9207aa7..cd949d5e451b 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -136,7 +136,7 @@ static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, unsigned int cmd) { struct ifreq ifr; - int ret = -EINVAL; + int ret = -ENOIOCTLCMD; struct net_device *dev; if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) @@ -146,8 +146,8 @@ static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, dev_load(sock_net(sk), ifr.ifr_name); dev = dev_get_by_name(sock_net(sk), ifr.ifr_name); - if (dev->type == ARPHRD_IEEE802154 || - dev->type == ARPHRD_IEEE802154_PHY) + + if (dev->type == ARPHRD_IEEE802154 && dev->netdev_ops->ndo_do_ioctl) ret = dev->netdev_ops->ndo_do_ioctl(dev, &ifr, cmd); if (!ret && copy_to_user(arg, &ifr, sizeof(struct ifreq))) diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 53dd912d52b4..77ae6852b93d 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -40,9 +40,11 @@ static DEFINE_RWLOCK(dgram_lock); struct dgram_sock { struct sock sk; - int bound; struct ieee802154_addr src_addr; struct ieee802154_addr dst_addr; + + unsigned bound:1; + unsigned want_ack:1; }; static inline struct dgram_sock *dgram_sk(const struct sock *sk) @@ -50,7 +52,6 @@ static inline struct dgram_sock *dgram_sk(const struct sock *sk) return container_of(sk, struct dgram_sock, sk); } - static void dgram_hash(struct sock *sk) { write_lock_bh(&dgram_lock); @@ -73,6 +74,7 @@ static int dgram_init(struct sock *sk) ro->dst_addr.addr_type = IEEE802154_ADDR_LONG; ro->dst_addr.pan_id = 0xffff; + ro->want_ack = 1; memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr)); return 0; } @@ -86,18 +88,18 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) { struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; struct dgram_sock *ro = dgram_sk(sk); - int err = 0; + int err = -EINVAL; struct net_device *dev; + lock_sock(sk); + ro->bound = 0; if (len < sizeof(*addr)) - return -EINVAL; + goto out; if (addr->family != AF_IEEE802154) - return -EINVAL; - - lock_sock(sk); + goto out; dev = ieee802154_get_dev(sock_net(sk), &addr->addr); if (!dev) { @@ -113,6 +115,7 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) memcpy(&ro->src_addr, &addr->addr, sizeof(struct ieee802154_addr)); ro->bound = 1; + err = 0; out_put: dev_put(dev); out: @@ -235,7 +238,10 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, skb_reset_network_header(skb); - mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA | MAC_CB_FLAG_ACKREQ; + mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA; + if (ro->want_ack) + mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; + mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev); err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &ro->dst_addr, ro->bound ? &ro->src_addr : NULL, size); @@ -377,6 +383,64 @@ int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) return ret; } +static int dgram_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct dgram_sock *ro = dgram_sk(sk); + + int val, len; + + if (level != SOL_IEEE802154) + return -EOPNOTSUPP; + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(unsigned int, len, sizeof(int)); + + switch (optname) { + case WPAN_WANTACK: + val = ro->want_ack; + break; + default: + return -ENOPROTOOPT; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; +} + +static int dgram_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user optlen) +{ + struct dgram_sock *ro = dgram_sk(sk); + int val; + int err = 0; + + if (optlen < sizeof(int)) + return -EINVAL; + + if (get_user(val, (int __user *)optval)) + return -EFAULT; + + lock_sock(sk); + + switch (optname) { + case WPAN_WANTACK: + ro->want_ack = !!val; + break; + default: + err = -ENOPROTOOPT; + break; + } + + release_sock(sk); + return err; +} + struct proto ieee802154_dgram_prot = { .name = "IEEE-802.15.4-MAC", .owner = THIS_MODULE, @@ -391,5 +455,7 @@ struct proto ieee802154_dgram_prot = { .connect = dgram_connect, .disconnect = dgram_disconnect, .ioctl = dgram_ioctl, + .getsockopt = dgram_getsockopt, + .setsockopt = dgram_setsockopt, }; diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index a615b9d13212..2106ecbf0308 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -19,6 +19,7 @@ * Written by: * Sergey Lapin <slapin@ossfans.org> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + * Maxim Osipov <maxim.osipov@siemens.com> */ #include <linux/kernel.h> @@ -26,9 +27,11 @@ #include <linux/netdevice.h> #include <net/netlink.h> #include <net/genetlink.h> +#include <net/sock.h> #include <linux/nl802154.h> #include <net/af_ieee802154.h> #include <net/nl802154.h> +#include <net/ieee802154.h> #include <net/ieee802154_netdev.h> static unsigned int ieee802154_seq_num; @@ -73,7 +76,7 @@ static int ieee802154_nl_finish(struct sk_buff *msg) /* XXX: nlh is right at the start of msg */ void *hdr = genlmsg_data(NLMSG_DATA(msg->data)); - if (!genlmsg_end(msg, hdr)) + if (genlmsg_end(msg, hdr) < 0) goto out; return genlmsg_multicast(msg, 0, ieee802154_coord_mcgrp.id, @@ -229,7 +232,7 @@ nla_put_failure: EXPORT_SYMBOL(ieee802154_nl_beacon_indic); int ieee802154_nl_scan_confirm(struct net_device *dev, - u8 status, u8 scan_type, u32 unscanned, + u8 status, u8 scan_type, u32 unscanned, u8 page, u8 *edl/* , struct list_head *pan_desc_list */) { struct sk_buff *msg; @@ -248,6 +251,7 @@ int ieee802154_nl_scan_confirm(struct net_device *dev, NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); NLA_PUT_U8(msg, IEEE802154_ATTR_SCAN_TYPE, scan_type); NLA_PUT_U32(msg, IEEE802154_ATTR_CHANNELS, unscanned); + NLA_PUT_U8(msg, IEEE802154_ATTR_PAGE, page); if (edl) NLA_PUT(msg, IEEE802154_ATTR_ED_LIST, 27, edl); @@ -260,6 +264,60 @@ nla_put_failure: } EXPORT_SYMBOL(ieee802154_nl_scan_confirm); +int ieee802154_nl_start_confirm(struct net_device *dev, u8 status) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_START_CONF); + if (!msg) + return -ENOBUFS; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + + NLA_PUT_U8(msg, IEEE802154_ATTR_STATUS, status); + + return ieee802154_nl_finish(msg); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_start_confirm); + +static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 pid, + u32 seq, int flags, struct net_device *dev) +{ + void *hdr; + + pr_debug("%s\n", __func__); + + hdr = genlmsg_put(msg, 0, seq, &ieee802154_coordinator_family, flags, + IEEE802154_LIST_IFACE); + if (!hdr) + goto out; + + NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); + NLA_PUT_U32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex); + + NLA_PUT(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, + dev->dev_addr); + NLA_PUT_U16(msg, IEEE802154_ATTR_SHORT_ADDR, + ieee802154_mlme_ops(dev)->get_short_addr(dev)); + NLA_PUT_U16(msg, IEEE802154_ATTR_PAN_ID, + ieee802154_mlme_ops(dev)->get_pan_id(dev)); + return genlmsg_end(msg, hdr); + +nla_put_failure: + genlmsg_cancel(msg, hdr); +out: + return -EMSGSIZE; +} + /* Requests from userspace */ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) { @@ -272,7 +330,7 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) dev = dev_get_by_name(&init_net, name); } else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) dev = dev_get_by_index(&init_net, - nla_get_u32(info->attrs[IEEE802154_ATTR_DEV_INDEX])); + nla_get_u32(info->attrs[IEEE802154_ATTR_DEV_INDEX])); else return NULL; @@ -292,6 +350,7 @@ static int ieee802154_associate_req(struct sk_buff *skb, { struct net_device *dev; struct ieee802154_addr addr; + u8 page; int ret = -EINVAL; if (!info->attrs[IEEE802154_ATTR_CHANNEL] || @@ -317,8 +376,14 @@ static int ieee802154_associate_req(struct sk_buff *skb, } addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + if (info->attrs[IEEE802154_ATTR_PAGE]) + page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); + else + page = 0; + ret = ieee802154_mlme_ops(dev)->assoc_req(dev, &addr, nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]), + page, nla_get_u8(info->attrs[IEEE802154_ATTR_CAPABILITY])); dev_put(dev); @@ -401,6 +466,7 @@ static int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) struct ieee802154_addr addr; u8 channel, bcn_ord, sf_ord; + u8 page; int pan_coord, blx, coord_realign; int ret; @@ -431,7 +497,19 @@ static int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) blx = nla_get_u8(info->attrs[IEEE802154_ATTR_BAT_EXT]); coord_realign = nla_get_u8(info->attrs[IEEE802154_ATTR_COORD_REALIGN]); - ret = ieee802154_mlme_ops(dev)->start_req(dev, &addr, channel, + if (info->attrs[IEEE802154_ATTR_PAGE]) + page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); + else + page = 0; + + + if (addr.short_addr == IEEE802154_ADDR_BROADCAST) { + ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS); + dev_put(dev); + return -EINVAL; + } + + ret = ieee802154_mlme_ops(dev)->start_req(dev, &addr, channel, page, bcn_ord, sf_ord, pan_coord, blx, coord_realign); dev_put(dev); @@ -445,6 +523,7 @@ static int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) u8 type; u32 channels; u8 duration; + u8 page; if (!info->attrs[IEEE802154_ATTR_SCAN_TYPE] || !info->attrs[IEEE802154_ATTR_CHANNELS] || @@ -459,13 +538,80 @@ static int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) channels = nla_get_u32(info->attrs[IEEE802154_ATTR_CHANNELS]); duration = nla_get_u8(info->attrs[IEEE802154_ATTR_DURATION]); - ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels, + if (info->attrs[IEEE802154_ATTR_PAGE]) + page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); + else + page = 0; + + + ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels, page, duration); dev_put(dev); return ret; } +static int ieee802154_list_iface(struct sk_buff *skb, + struct genl_info *info) +{ + /* Request for interface name, index, type, IEEE address, + PAN Id, short address */ + struct sk_buff *msg; + struct net_device *dev = NULL; + int rc = -ENOBUFS; + + pr_debug("%s\n", __func__); + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + goto out_dev; + + rc = ieee802154_nl_fill_iface(msg, info->snd_pid, info->snd_seq, + 0, dev); + if (rc < 0) + goto out_free; + + dev_put(dev); + + return genlmsg_unicast(&init_net, msg, info->snd_pid); +out_free: + nlmsg_free(msg); +out_dev: + dev_put(dev); + return rc; + +} + +static int ieee802154_dump_iface(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int idx; + int s_idx = cb->args[0]; + + pr_debug("%s\n", __func__); + + idx = 0; + for_each_netdev(net, dev) { + if (idx < s_idx || (dev->type != ARPHRD_IEEE802154)) + goto cont; + + if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, dev) < 0) + break; +cont: + idx++; + } + cb->args[0] = idx; + + return skb->len; +} + #define IEEE802154_OP(_cmd, _func) \ { \ .cmd = _cmd, \ @@ -475,12 +621,22 @@ static int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) .flags = GENL_ADMIN_PERM, \ } +#define IEEE802154_DUMP(_cmd, _func, _dump) \ + { \ + .cmd = _cmd, \ + .policy = ieee802154_policy, \ + .doit = _func, \ + .dumpit = _dump, \ + } + static struct genl_ops ieee802154_coordinator_ops[] = { IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req), IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp), IEEE802154_OP(IEEE802154_DISASSOCIATE_REQ, ieee802154_disassociate_req), IEEE802154_OP(IEEE802154_SCAN_REQ, ieee802154_scan_req), IEEE802154_OP(IEEE802154_START_REQ, ieee802154_start_req), + IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface, + ieee802154_dump_iface), }; static int __init ieee802154_nl_init(void) diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index c7d71d1adcac..2363ebee02e7 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -24,7 +24,7 @@ #define NLA_HW_ADDR NLA_U64 -struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { +const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_DEV_NAME] = { .type = NLA_STRING, }, [IEEE802154_ATTR_DEV_INDEX] = { .type = NLA_U32, }, @@ -33,6 +33,7 @@ struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, }, [IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, }, + [IEEE802154_ATTR_PAGE] = { .type = NLA_U8, }, [IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, }, [IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_COORD_PAN_ID] = { .type = NLA_U16, }, @@ -50,3 +51,4 @@ struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_DURATION] = { .type = NLA_U8, }, [IEEE802154_ATTR_ED_LIST] = { .len = 27 }, }; + diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index ea8d1f15206e..4681501aae93 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -74,8 +74,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int len) goto out; } - if (dev->type != ARPHRD_IEEE802154_PHY && - dev->type != ARPHRD_IEEE802154) { + if (dev->type != ARPHRD_IEEE802154) { err = -ENODEV; goto out_put; } @@ -238,6 +237,18 @@ void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb) read_unlock(&raw_lock); } +static int raw_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + return -EOPNOTSUPP; +} + +static int raw_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user optlen) +{ + return -EOPNOTSUPP; +} + struct proto ieee802154_raw_prot = { .name = "IEEE-802.15.4-RAW", .owner = THIS_MODULE, @@ -250,5 +261,7 @@ struct proto ieee802154_raw_prot = { .unhash = raw_unhash, .connect = raw_connect, .disconnect = raw_disconnect, + .getsockopt = raw_getsockopt, + .setsockopt = raw_setsockopt, }; diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c new file mode 100644 index 000000000000..f306604da67a --- /dev/null +++ b/net/ieee802154/wpan-class.c @@ -0,0 +1,159 @@ +/* + * Copyright (C) 2007, 2008, 2009 Siemens AG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> + +#include <net/wpan-phy.h> + +#define MASTER_SHOW_COMPLEX(name, format_string, args...) \ +static ssize_t name ## _show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); \ + int ret; \ + \ + mutex_lock(&phy->pib_lock); \ + ret = sprintf(buf, format_string "\n", args); \ + mutex_unlock(&phy->pib_lock); \ + return ret; \ +} + +#define MASTER_SHOW(field, format_string) \ + MASTER_SHOW_COMPLEX(field, format_string, phy->field) + +MASTER_SHOW(current_channel, "%d"); +MASTER_SHOW(current_page, "%d"); +MASTER_SHOW(channels_supported, "%#x"); +MASTER_SHOW_COMPLEX(transmit_power, "%d +- %d dB", + ((signed char) (phy->transmit_power << 2)) >> 2, + (phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1 ); +MASTER_SHOW(cca_mode, "%d"); + +static struct device_attribute pmib_attrs[] = { + __ATTR_RO(current_channel), + __ATTR_RO(current_page), + __ATTR_RO(channels_supported), + __ATTR_RO(transmit_power), + __ATTR_RO(cca_mode), + {}, +}; + +static void wpan_phy_release(struct device *d) +{ + struct wpan_phy *phy = container_of(d, struct wpan_phy, dev); + kfree(phy); +} + +static struct class wpan_phy_class = { + .name = "ieee802154", + .dev_release = wpan_phy_release, + .dev_attrs = pmib_attrs, +}; + +static DEFINE_MUTEX(wpan_phy_mutex); +static int wpan_phy_idx; + +static int wpan_phy_match(struct device *dev, void *data) +{ + return !strcmp(dev_name(dev), (const char *)data); +} + +struct wpan_phy *wpan_phy_find(const char *str) +{ + struct device *dev; + + if (WARN_ON(!str)) + return NULL; + + dev = class_find_device(&wpan_phy_class, NULL, + (void *)str, wpan_phy_match); + if (!dev) + return NULL; + + return container_of(dev, struct wpan_phy, dev); +} +EXPORT_SYMBOL(wpan_phy_find); + +static int wpan_phy_idx_valid(int idx) +{ + return idx >= 0; +} + +struct wpan_phy *wpan_phy_alloc(size_t priv_size) +{ + struct wpan_phy *phy = kzalloc(sizeof(*phy) + priv_size, + GFP_KERNEL); + + mutex_lock(&wpan_phy_mutex); + phy->idx = wpan_phy_idx++; + if (unlikely(!wpan_phy_idx_valid(phy->idx))) { + wpan_phy_idx--; + mutex_unlock(&wpan_phy_mutex); + kfree(phy); + return NULL; + } + mutex_unlock(&wpan_phy_mutex); + + mutex_init(&phy->pib_lock); + + device_initialize(&phy->dev); + dev_set_name(&phy->dev, "wpan-phy%d", phy->idx); + + phy->dev.class = &wpan_phy_class; + + return phy; +} +EXPORT_SYMBOL(wpan_phy_alloc); + +int wpan_phy_register(struct device *parent, struct wpan_phy *phy) +{ + phy->dev.parent = parent; + + return device_add(&phy->dev); +} +EXPORT_SYMBOL(wpan_phy_register); + +void wpan_phy_unregister(struct wpan_phy *phy) +{ + device_del(&phy->dev); +} +EXPORT_SYMBOL(wpan_phy_unregister); + +void wpan_phy_free(struct wpan_phy *phy) +{ + put_device(&phy->dev); +} +EXPORT_SYMBOL(wpan_phy_free); + +static int __init wpan_phy_class_init(void) +{ + return class_register(&wpan_phy_class); +} +subsys_initcall(wpan_phy_class_init); + +static void __exit wpan_phy_class_exit(void) +{ + class_unregister(&wpan_phy_class); +} +module_exit(wpan_phy_class_exit); + +MODULE_DESCRIPTION("IEEE 802.15.4 device class"); +MODULE_LICENSE("GPL v2"); + diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 197d024b2536..6c30a73f03f5 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -124,7 +124,6 @@ static struct list_head inetsw[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw_lock); struct ipv4_config ipv4_config; - EXPORT_SYMBOL(ipv4_config); /* New destruction routine */ @@ -139,12 +138,12 @@ void inet_sock_destruct(struct sock *sk) sk_mem_reclaim(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) { - printk("Attempt to release TCP socket in state %d %p\n", + pr_err("Attempt to release TCP socket in state %d %p\n", sk->sk_state, sk); return; } if (!sock_flag(sk, SOCK_DEAD)) { - printk("Attempt to release alive inet socket %p\n", sk); + pr_err("Attempt to release alive inet socket %p\n", sk); return; } @@ -157,6 +156,7 @@ void inet_sock_destruct(struct sock *sk) dst_release(sk->sk_dst_cache); sk_refcnt_debug_dec(sk); } +EXPORT_SYMBOL(inet_sock_destruct); /* * The routines beyond this point handle the behaviour of an AF_INET @@ -219,6 +219,7 @@ out: release_sock(sk); return err; } +EXPORT_SYMBOL(inet_listen); u32 inet_ehash_secret __read_mostly; EXPORT_SYMBOL(inet_ehash_secret); @@ -435,9 +436,11 @@ int inet_release(struct socket *sock) } return 0; } +EXPORT_SYMBOL(inet_release); /* It is off by default, see below. */ int sysctl_ip_nonlocal_bind __read_mostly; +EXPORT_SYMBOL(sysctl_ip_nonlocal_bind); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { @@ -519,6 +522,7 @@ out_release_sock: out: return err; } +EXPORT_SYMBOL(inet_bind); int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr, int addr_len, int flags) @@ -532,6 +536,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr, return -EAGAIN; return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len); } +EXPORT_SYMBOL(inet_dgram_connect); static long inet_wait_for_connect(struct sock *sk, long timeo) { @@ -641,6 +646,7 @@ sock_error: sock->state = SS_DISCONNECTING; goto out; } +EXPORT_SYMBOL(inet_stream_connect); /* * Accept a pending connection. The TCP layer now gives BSD semantics. @@ -668,6 +674,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags) do_err: return err; } +EXPORT_SYMBOL(inet_accept); /* @@ -699,6 +706,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, *uaddr_len = sizeof(*sin); return 0; } +EXPORT_SYMBOL(inet_getname); int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size) @@ -711,9 +719,11 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, return sk->sk_prot->sendmsg(iocb, sk, msg, size); } +EXPORT_SYMBOL(inet_sendmsg); -static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) +static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, + size_t size, int flags) { struct sock *sk = sock->sk; @@ -780,6 +790,7 @@ int inet_shutdown(struct socket *sock, int how) release_sock(sk); return err; } +EXPORT_SYMBOL(inet_shutdown); /* * ioctl() calls you can issue on an INET socket. Most of these are @@ -798,44 +809,45 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) struct net *net = sock_net(sk); switch (cmd) { - case SIOCGSTAMP: - err = sock_get_timestamp(sk, (struct timeval __user *)arg); - break; - case SIOCGSTAMPNS: - err = sock_get_timestampns(sk, (struct timespec __user *)arg); - break; - case SIOCADDRT: - case SIOCDELRT: - case SIOCRTMSG: - err = ip_rt_ioctl(net, cmd, (void __user *)arg); - break; - case SIOCDARP: - case SIOCGARP: - case SIOCSARP: - err = arp_ioctl(net, cmd, (void __user *)arg); - break; - case SIOCGIFADDR: - case SIOCSIFADDR: - case SIOCGIFBRDADDR: - case SIOCSIFBRDADDR: - case SIOCGIFNETMASK: - case SIOCSIFNETMASK: - case SIOCGIFDSTADDR: - case SIOCSIFDSTADDR: - case SIOCSIFPFLAGS: - case SIOCGIFPFLAGS: - case SIOCSIFFLAGS: - err = devinet_ioctl(net, cmd, (void __user *)arg); - break; - default: - if (sk->sk_prot->ioctl) - err = sk->sk_prot->ioctl(sk, cmd, arg); - else - err = -ENOIOCTLCMD; - break; + case SIOCGSTAMP: + err = sock_get_timestamp(sk, (struct timeval __user *)arg); + break; + case SIOCGSTAMPNS: + err = sock_get_timestampns(sk, (struct timespec __user *)arg); + break; + case SIOCADDRT: + case SIOCDELRT: + case SIOCRTMSG: + err = ip_rt_ioctl(net, cmd, (void __user *)arg); + break; + case SIOCDARP: + case SIOCGARP: + case SIOCSARP: + err = arp_ioctl(net, cmd, (void __user *)arg); + break; + case SIOCGIFADDR: + case SIOCSIFADDR: + case SIOCGIFBRDADDR: + case SIOCSIFBRDADDR: + case SIOCGIFNETMASK: + case SIOCSIFNETMASK: + case SIOCGIFDSTADDR: + case SIOCSIFDSTADDR: + case SIOCSIFPFLAGS: + case SIOCGIFPFLAGS: + case SIOCSIFFLAGS: + err = devinet_ioctl(net, cmd, (void __user *)arg); + break; + default: + if (sk->sk_prot->ioctl) + err = sk->sk_prot->ioctl(sk, cmd, arg); + else + err = -ENOIOCTLCMD; + break; } return err; } +EXPORT_SYMBOL(inet_ioctl); const struct proto_ops inet_stream_ops = { .family = PF_INET, @@ -862,6 +874,7 @@ const struct proto_ops inet_stream_ops = { .compat_getsockopt = compat_sock_common_getsockopt, #endif }; +EXPORT_SYMBOL(inet_stream_ops); const struct proto_ops inet_dgram_ops = { .family = PF_INET, @@ -887,6 +900,7 @@ const struct proto_ops inet_dgram_ops = { .compat_getsockopt = compat_sock_common_getsockopt, #endif }; +EXPORT_SYMBOL(inet_dgram_ops); /* * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without @@ -1016,6 +1030,7 @@ out_illegal: p->type); goto out; } +EXPORT_SYMBOL(inet_register_protosw); void inet_unregister_protosw(struct inet_protosw *p) { @@ -1031,6 +1046,7 @@ void inet_unregister_protosw(struct inet_protosw *p) synchronize_net(); } } +EXPORT_SYMBOL(inet_unregister_protosw); /* * Shall we try to damage output packets if routing dev changes? @@ -1141,7 +1157,6 @@ int inet_sk_rebuild_header(struct sock *sk) return err; } - EXPORT_SYMBOL(inet_sk_rebuild_header); static int inet_gso_send_check(struct sk_buff *skb) @@ -1369,7 +1384,6 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, } return rc; } - EXPORT_SYMBOL_GPL(inet_ctl_sock_create); unsigned long snmp_fold_field(void *mib[], int offt) @@ -1676,19 +1690,3 @@ static int __init ipv4_proc_init(void) MODULE_ALIAS_NETPROTO(PF_INET); -EXPORT_SYMBOL(inet_accept); -EXPORT_SYMBOL(inet_bind); -EXPORT_SYMBOL(inet_dgram_connect); -EXPORT_SYMBOL(inet_dgram_ops); -EXPORT_SYMBOL(inet_getname); -EXPORT_SYMBOL(inet_ioctl); -EXPORT_SYMBOL(inet_listen); -EXPORT_SYMBOL(inet_register_protosw); -EXPORT_SYMBOL(inet_release); -EXPORT_SYMBOL(inet_sendmsg); -EXPORT_SYMBOL(inet_shutdown); -EXPORT_SYMBOL(inet_sock_destruct); -EXPORT_SYMBOL(inet_stream_connect); -EXPORT_SYMBOL(inet_stream_ops); -EXPORT_SYMBOL(inet_unregister_protosw); -EXPORT_SYMBOL(sysctl_ip_nonlocal_bind); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 090e9991ac2a..4e80f336c0cf 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -130,7 +130,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); static void parp_redo(struct sk_buff *skb); -static struct neigh_ops arp_generic_ops = { +static const struct neigh_ops arp_generic_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, @@ -140,7 +140,7 @@ static struct neigh_ops arp_generic_ops = { .queue_xmit = dev_queue_xmit, }; -static struct neigh_ops arp_hh_ops = { +static const struct neigh_ops arp_hh_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, @@ -150,7 +150,7 @@ static struct neigh_ops arp_hh_ops = { .queue_xmit = dev_queue_xmit, }; -static struct neigh_ops arp_direct_ops = { +static const struct neigh_ops arp_direct_ops = { .family = AF_INET, .output = dev_queue_xmit, .connected_output = dev_queue_xmit, @@ -158,7 +158,7 @@ static struct neigh_ops arp_direct_ops = { .queue_xmit = dev_queue_xmit, }; -struct neigh_ops arp_broken_ops = { +const struct neigh_ops arp_broken_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index fe3c846b99a6..291bdf50a21f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -48,7 +48,7 @@ * Patrick McHardy <kaber@trash.net> */ -#define VERSION "0.408" +#define VERSION "0.409" #include <asm/uaccess.h> #include <asm/system.h> @@ -325,10 +325,7 @@ static inline void check_tnode(const struct tnode *tn) static const int halve_threshold = 25; static const int inflate_threshold = 50; static const int halve_threshold_root = 15; -static const int inflate_threshold_root = 25; - -static int inflate_threshold_root_fix; -#define INFLATE_FIX_MAX 10 /* a comment in resize() */ +static const int inflate_threshold_root = 30; static void __alias_free_mem(struct rcu_head *head) { @@ -516,14 +513,14 @@ static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, rcu_assign_pointer(tn->child[i], n); } +#define MAX_WORK 10 static struct node *resize(struct trie *t, struct tnode *tn) { int i; - int err = 0; struct tnode *old_tn; int inflate_threshold_use; int halve_threshold_use; - int max_resize; + int max_work; if (!tn) return NULL; @@ -538,18 +535,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) } /* One child */ if (tn->empty_children == tnode_child_length(tn) - 1) - for (i = 0; i < tnode_child_length(tn); i++) { - struct node *n; - - n = tn->child[i]; - if (!n) - continue; - - /* compress one level */ - node_set_parent(n, NULL); - tnode_free_safe(tn); - return n; - } + goto one_child; /* * Double as long as the resulting node has a number of * nonempty nodes that are above the threshold. @@ -618,15 +604,17 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* Keep root node larger */ - if (!tn->parent) - inflate_threshold_use = inflate_threshold_root + - inflate_threshold_root_fix; - else + if (!node_parent((struct node*) tn)) { + inflate_threshold_use = inflate_threshold_root; + halve_threshold_use = halve_threshold_root; + } + else { inflate_threshold_use = inflate_threshold; + halve_threshold_use = halve_threshold; + } - err = 0; - max_resize = 10; - while ((tn->full_children > 0 && max_resize-- && + max_work = MAX_WORK; + while ((tn->full_children > 0 && max_work-- && 50 * (tn->full_children + tnode_child_length(tn) - tn->empty_children) >= inflate_threshold_use * tnode_child_length(tn))) { @@ -643,47 +631,19 @@ static struct node *resize(struct trie *t, struct tnode *tn) } } - if (max_resize < 0) { - if (!tn->parent) { - /* - * It was observed that during large updates even - * inflate_threshold_root = 35 might be needed to avoid - * this warning; but it should be temporary, so let's - * try to handle this automatically. - */ - if (inflate_threshold_root_fix < INFLATE_FIX_MAX) - inflate_threshold_root_fix++; - else - pr_warning("Fix inflate_threshold_root." - " Now=%d size=%d bits fix=%d\n", - inflate_threshold_root, tn->bits, - inflate_threshold_root_fix); - } else { - pr_warning("Fix inflate_threshold." - " Now=%d size=%d bits\n", - inflate_threshold, tn->bits); - } - } else if (max_resize > 3 && !tn->parent && inflate_threshold_root_fix) - inflate_threshold_root_fix--; - check_tnode(tn); + /* Return if at least one inflate is run */ + if( max_work != MAX_WORK) + return (struct node *) tn; + /* * Halve as long as the number of empty children in this * node is above threshold. */ - - /* Keep root node larger */ - - if (!tn->parent) - halve_threshold_use = halve_threshold_root; - else - halve_threshold_use = halve_threshold; - - err = 0; - max_resize = 10; - while (tn->bits > 1 && max_resize-- && + max_work = MAX_WORK; + while (tn->bits > 1 && max_work-- && 100 * (tnode_child_length(tn) - tn->empty_children) < halve_threshold_use * tnode_child_length(tn)) { @@ -698,19 +658,10 @@ static struct node *resize(struct trie *t, struct tnode *tn) } } - if (max_resize < 0) { - if (!tn->parent) - pr_warning("Fix halve_threshold_root." - " Now=%d size=%d bits\n", - halve_threshold_root, tn->bits); - else - pr_warning("Fix halve_threshold." - " Now=%d size=%d bits\n", - halve_threshold, tn->bits); - } /* Only one child remains */ - if (tn->empty_children == tnode_child_length(tn) - 1) + if (tn->empty_children == tnode_child_length(tn) - 1) { +one_child: for (i = 0; i < tnode_child_length(tn); i++) { struct node *n; @@ -724,7 +675,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) tnode_free_safe(tn); return n; } - + } return (struct node *) tn; } diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 61283f928825..13f0781f35cd 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -218,8 +218,8 @@ void inet_twdr_hangman(unsigned long data) /* We purged the entire slot, anything left? */ if (twdr->tw_count) need_timer = 1; + twdr->slot = ((twdr->slot + 1) & (INET_TWDR_TWKILL_SLOTS - 1)); } - twdr->slot = ((twdr->slot + 1) & (INET_TWDR_TWKILL_SLOTS - 1)); if (need_timer) mod_timer(&twdr->tw_timer, jiffies + twdr->period); out: diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index b902ef55be7f..533afaadefd4 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -662,7 +662,7 @@ drop_nolock: return(0); } -static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net_device_stats *stats = &tunnel->dev->stats; @@ -951,7 +951,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) addend += 4; } dev->needed_headroom = addend + hlen; - mtu -= dev->hard_header_len - addend; + mtu -= dev->hard_header_len + addend; if (mtu < 68) mtu = 68; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7d0821054729..afae0cbabbf9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1302,7 +1302,7 @@ int ip_push_pending_frames(struct sock *sk) err = ip_local_out(skb); if (err) { if (err > 0) - err = inet->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 98075b6d619c..62548cb0923c 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -387,7 +387,7 @@ static int ipip_rcv(struct sk_buff *skb) * and that skb is filled properly by that function. */ -static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net_device_stats *stats = &tunnel->dev->stats; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 06c33fb6b321..65d421cf5bc7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -201,7 +201,7 @@ failure: #ifdef CONFIG_IP_PIMSM -static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index ea50da0649fd..a2e5fc0a15e1 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -22,26 +22,11 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ - -#include <asm/uaccess.h> -#include <asm/system.h> +#include <linux/cache.h> #include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/inet.h> #include <linux/netdevice.h> -#include <linux/timer.h> -#include <net/ip.h> +#include <linux/spinlock.h> #include <net/protocol.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/ipip.h> -#include <linux/igmp.h> struct net_protocol *inet_protos[MAX_INET_PROTOS] ____cacheline_aligned_in_smp; static DEFINE_SPINLOCK(inet_proto_lock); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 2979f14bb188..ebb1e5848bc6 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -375,7 +375,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, err = NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) - err = inet->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; out: @@ -386,6 +386,8 @@ error_fault: kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); + if (err == -ENOBUFS && !inet->recverr) + err = 0; return err; } @@ -576,8 +578,11 @@ back_from_confirm: &ipc, &rt, msg->msg_flags); if (err) ip_flush_pending_frames(sk); - else if (!(msg->msg_flags & MSG_MORE)) + else if (!(msg->msg_flags & MSG_MORE)) { err = ip_push_pending_frames(sk); + if (err == -ENOBUFS && !inet->recverr) + err = 0; + } release_sock(sk); } done: diff --git a/net/ipv4/route.c b/net/ipv4/route.c index fafbe163e2b5..91867d3e6328 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1514,13 +1514,17 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) void ip_rt_send_redirect(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); - struct in_device *in_dev = in_dev_get(rt->u.dst.dev); + struct in_device *in_dev; + int log_martians; - if (!in_dev) + rcu_read_lock(); + in_dev = __in_dev_get_rcu(rt->u.dst.dev); + if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) { + rcu_read_unlock(); return; - - if (!IN_DEV_TX_REDIRECTS(in_dev)) - goto out; + } + log_martians = IN_DEV_LOG_MARTIANS(in_dev); + rcu_read_unlock(); /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. @@ -1533,7 +1537,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) */ if (rt->u.dst.rate_tokens >= ip_rt_redirect_number) { rt->u.dst.rate_last = jiffies; - goto out; + return; } /* Check for load limit; set rate_last to the latest sent @@ -1547,7 +1551,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) rt->u.dst.rate_last = jiffies; ++rt->u.dst.rate_tokens; #ifdef CONFIG_IP_ROUTE_VERBOSE - if (IN_DEV_LOG_MARTIANS(in_dev) && + if (log_martians && rt->u.dst.rate_tokens == ip_rt_redirect_number && net_ratelimit()) printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n", @@ -1555,8 +1559,6 @@ void ip_rt_send_redirect(struct sk_buff *skb) &rt->rt_dst, &rt->rt_gateway); #endif } -out: - in_dev_put(in_dev); } static int ip_error(struct sk_buff *skb) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 91145244ea63..edeea060db44 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1839,7 +1839,7 @@ void tcp_close(struct sock *sk, long timeout) /* Unread data was tossed, zap the connection. */ NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_KERNEL); + tcp_send_active_reset(sk, sk->sk_allocation); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -2336,13 +2336,13 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = !!(tp->nonagle&TCP_NAGLE_CORK); break; case TCP_KEEPIDLE: - val = (tp->keepalive_time ? : sysctl_tcp_keepalive_time) / HZ; + val = keepalive_time_when(tp) / HZ; break; case TCP_KEEPINTVL: - val = (tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl) / HZ; + val = keepalive_intvl_when(tp) / HZ; break; case TCP_KEEPCNT: - val = tp->keepalive_probes ? : sysctl_tcp_keepalive_probes; + val = keepalive_probes(tp); break; case TCP_SYNCNT: val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; @@ -2658,7 +2658,7 @@ void tcp_free_md5sig_pool(void) EXPORT_SYMBOL(tcp_free_md5sig_pool); -static struct tcp_md5sig_pool **__tcp_alloc_md5sig_pool(void) +static struct tcp_md5sig_pool **__tcp_alloc_md5sig_pool(struct sock *sk) { int cpu; struct tcp_md5sig_pool **pool; @@ -2671,7 +2671,7 @@ static struct tcp_md5sig_pool **__tcp_alloc_md5sig_pool(void) struct tcp_md5sig_pool *p; struct crypto_hash *hash; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc(sizeof(*p), sk->sk_allocation); if (!p) goto out_free; *per_cpu_ptr(pool, cpu) = p; @@ -2688,7 +2688,7 @@ out_free: return NULL; } -struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(void) +struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(struct sock *sk) { struct tcp_md5sig_pool **pool; int alloc = 0; @@ -2709,7 +2709,7 @@ retry: if (alloc) { /* we cannot hold spinlock here because this may sleep. */ - struct tcp_md5sig_pool **p = __tcp_alloc_md5sig_pool(); + struct tcp_md5sig_pool **p = __tcp_alloc_md5sig_pool(sk); spin_lock_bh(&tcp_md5sig_pool_lock); if (!p) { tcp_md5sig_users--; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2bdb0da237e6..af6d6fa00db1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -685,7 +685,7 @@ static inline void tcp_set_rto(struct sock *sk) * is invisible. Actually, Linux-2.4 also generates erratic * ACKs in some circumstances. */ - inet_csk(sk)->icsk_rto = (tp->srtt >> 3) + tp->rttvar; + inet_csk(sk)->icsk_rto = __tcp_set_rto(tp); /* 2. Fixups made earlier cannot be right. * If we do not estimate RTO correctly without them, @@ -696,8 +696,7 @@ static inline void tcp_set_rto(struct sock *sk) /* NOTE: clamping at TCP_RTO_MIN is not required, current algo * guarantees that rto is higher. */ - if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) - inet_csk(sk)->icsk_rto = TCP_RTO_MAX; + tcp_bound_rto(sk); } /* Save metrics learned by this TCP session. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6d88219c5e22..0543561da999 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -328,26 +328,29 @@ static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) * */ -void tcp_v4_err(struct sk_buff *skb, u32 info) +void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) { - struct iphdr *iph = (struct iphdr *)skb->data; - struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); + struct iphdr *iph = (struct iphdr *)icmp_skb->data; + struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2)); + struct inet_connection_sock *icsk; struct tcp_sock *tp; struct inet_sock *inet; - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; + const int type = icmp_hdr(icmp_skb)->type; + const int code = icmp_hdr(icmp_skb)->code; struct sock *sk; + struct sk_buff *skb; __u32 seq; + __u32 remaining; int err; - struct net *net = dev_net(skb->dev); + struct net *net = dev_net(icmp_skb->dev); - if (skb->len < (iph->ihl << 2) + 8) { + if (icmp_skb->len < (iph->ihl << 2) + 8) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest, - iph->saddr, th->source, inet_iif(skb)); + iph->saddr, th->source, inet_iif(icmp_skb)); if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; @@ -367,6 +370,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) if (sk->sk_state == TCP_CLOSE) goto out; + icsk = inet_csk(sk); tp = tcp_sk(sk); seq = ntohl(th->seq); if (sk->sk_state != TCP_LISTEN && @@ -393,6 +397,39 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) } err = icmp_err_convert[code].errno; + /* check if icmp_skb allows revert of backoff + * (see draft-zimmermann-tcp-lcd) */ + if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH) + break; + if (seq != tp->snd_una || !icsk->icsk_retransmits || + !icsk->icsk_backoff) + break; + + icsk->icsk_backoff--; + inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) << + icsk->icsk_backoff; + tcp_bound_rto(sk); + + skb = tcp_write_queue_head(sk); + BUG_ON(!skb); + + remaining = icsk->icsk_rto - min(icsk->icsk_rto, + tcp_time_stamp - TCP_SKB_CB(skb)->when); + + if (remaining) { + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + remaining, TCP_RTO_MAX); + } else if (sock_owned_by_user(sk)) { + /* RTO revert clocked out retransmission, + * but socket is locked. Will defer. */ + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + HZ/20, TCP_RTO_MAX); + } else { + /* RTO revert clocked out retransmission. + * Will retransmit now */ + tcp_retransmit_timer(sk); + } + break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; @@ -849,7 +886,7 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, } sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } - if (tcp_alloc_md5sig_pool() == NULL) { + if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); return -ENOMEM; } @@ -970,8 +1007,9 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (!tcp_sk(sk)->md5sig_info) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_md5sig_info *p = kzalloc(sizeof(*p), GFP_KERNEL); + struct tcp_md5sig_info *p; + p = kzalloc(sizeof(*p), sk->sk_allocation); if (!p) return -EINVAL; @@ -979,7 +1017,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } - newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation); if (!newkey) return -ENOMEM; return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr, @@ -1158,7 +1196,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { +static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .md5_lookup = tcp_v4_reqsk_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, }; @@ -1717,7 +1755,7 @@ int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw) return 0; } -struct inet_connection_sock_af_ops ipv4_specific = { +const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, @@ -1737,7 +1775,7 @@ struct inet_connection_sock_af_ops ipv4_specific = { }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_sock_af_ops tcp_sock_ipv4_specific = { +static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_add = tcp_v4_md5_add_func, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f8d67ccc64f3..e48c37d74d77 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -322,7 +322,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (key != NULL) { memcpy(&tcptw->tw_md5_key, key->key, key->keylen); tcptw->tw_md5_keylen = key->keylen; - if (tcp_alloc_md5sig_pool() == NULL) + if (tcp_alloc_md5sig_pool(sk) == NULL) BUG(); } } while (0); @@ -657,29 +657,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); if (child == NULL) goto listen_overflow; -#ifdef CONFIG_TCP_MD5SIG - else { - /* Copy over the MD5 key from the original socket */ - struct tcp_md5sig_key *key; - struct tcp_sock *tp = tcp_sk(sk); - key = tp->af_specific->md5_lookup(sk, child); - if (key != NULL) { - /* - * We're using one, so create a matching key on the - * newsk structure. If we fail to get memory then we - * end up not copying the key across. Shucks. - */ - char *newkey = kmemdup(key->key, key->keylen, - GFP_ATOMIC); - if (newkey) { - if (!tcp_alloc_md5sig_pool()) - BUG(); - tp->af_specific->md5_add(child, child, newkey, - key->keylen); - } - } - } -#endif inet_csk_reqsk_queue_unlink(sk, req, prev); inet_csk_reqsk_queue_removed(sk, req); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4e004424d400..5200aab0ca97 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2135,7 +2135,8 @@ void tcp_send_fin(struct sock *sk) } else { /* Socket is locked, keep trying until memory is available. */ for (;;) { - skb = alloc_skb_fclone(MAX_TCP_HEADER, GFP_KERNEL); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk->sk_allocation); if (skb) break; yield(); @@ -2388,7 +2389,7 @@ int tcp_connect(struct sock *sk) sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); tp->packets_out += tcp_skb_pcount(buff); - tcp_transmit_skb(sk, buff, 1, GFP_KERNEL); + tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b144a26359bc..cdb2ca7684d4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -137,13 +137,14 @@ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int retry_until; + bool do_reset; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) dst_negative_advice(&sk->sk_dst_cache); retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; } else { - if (icsk->icsk_retransmits >= sysctl_tcp_retries1) { + if (retransmits_timed_out(sk, sysctl_tcp_retries1)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); @@ -155,13 +156,15 @@ static int tcp_write_timeout(struct sock *sk) const int alive = (icsk->icsk_rto < TCP_RTO_MAX); retry_until = tcp_orphan_retries(sk, alive); + do_reset = alive || + !retransmits_timed_out(sk, retry_until); - if (tcp_out_of_resources(sk, alive || icsk->icsk_retransmits < retry_until)) + if (tcp_out_of_resources(sk, do_reset)) return 1; } } - if (icsk->icsk_retransmits >= retry_until) { + if (retransmits_timed_out(sk, retry_until)) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; @@ -279,7 +282,7 @@ static void tcp_probe_timer(struct sock *sk) * The TCP retransmit timer. */ -static void tcp_retransmit_timer(struct sock *sk) +void tcp_retransmit_timer(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -385,7 +388,7 @@ static void tcp_retransmit_timer(struct sock *sk) out_reset_timer: icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - if (icsk->icsk_retransmits > sysctl_tcp_retries1) + if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1)) __sk_dst_reset(sk); out:; @@ -499,8 +502,7 @@ static void tcp_keepalive_timer (unsigned long data) elapsed = tcp_time_stamp - tp->rcv_tstamp; if (elapsed >= keepalive_time_when(tp)) { - if ((!tp->keepalive_probes && icsk->icsk_probes_out >= sysctl_tcp_keepalive_probes) || - (tp->keepalive_probes && icsk->icsk_probes_out >= tp->keepalive_probes)) { + if (icsk->icsk_probes_out >= keepalive_probes(tp)) { tcp_send_active_reset(sk, GFP_ATOMIC); tcp_write_err(sk); goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 29ebb0d27a1e..ebaaa7f973d7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -561,12 +561,18 @@ static int udp_push_pending_frames(struct sock *sk) send: err = ip_push_pending_frames(sk); + if (err) { + if (err == -ENOBUFS && !inet->recverr) { + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); + err = 0; + } + } else + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); out: up->len = 0; up->pending = 0; - if (!err) - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index bf85d5f97032..a123a328aeb3 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -306,8 +306,10 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) v4addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && - chk_addr_ret != RTN_BROADCAST) + chk_addr_ret != RTN_BROADCAST) { + err = -EADDRNOTAVAIL; goto out; + } } else { if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index eab62a7a8f06..e2325f6a05fb 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -323,7 +323,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - int hlimit, tclass; + int hlimit; int err = 0; if ((u8 *)hdr < skb->head || @@ -469,10 +469,6 @@ route_done: if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - msg.skb = skb; msg.offset = skb_network_offset(skb); msg.type = type; @@ -488,8 +484,8 @@ route_done: err = ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), - hlimit, tclass, NULL, &fl, (struct rt6_info*)dst, + sizeof(struct icmp6hdr), hlimit, + np->tclass, NULL, &fl, (struct rt6_info*)dst, MSG_DONTWAIT); if (err) { ip6_flush_pending_frames(sk); @@ -522,7 +518,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct dst_entry *dst; int err = 0; int hlimit; - int tclass; saddr = &ipv6_hdr(skb)->daddr; @@ -562,10 +557,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - idev = in6_dev_get(skb->dev); msg.skb = skb; @@ -573,7 +564,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.type = ICMPV6_ECHO_REPLY; err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl, + sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl, (struct rt6_info*)dst, MSG_DONTWAIT); if (err) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 93beee944657..cd48801a8d6f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -194,7 +194,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct ipv6hdr *hdr; u8 proto = fl->proto; int seg_len = skb->len; - int hlimit, tclass; + int hlimit = -1; + int tclass = 0; u32 mtu; if (opt) { @@ -237,19 +238,13 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, /* * Fill in the IPv6 header */ - - hlimit = -1; - if (np) + if (np) { + tclass = np->tclass; hlimit = np->hop_limit; + } if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = -1; - if (np) - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; hdr->payload_len = htons(seg_len); @@ -1516,7 +1511,7 @@ int ip6_push_pending_frames(struct sock *sk) err = ip6_local_out(skb); if (err) { if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; } @@ -1525,6 +1520,7 @@ out: ip6_cork_release(inet, np); return err; error: + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); goto out; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a1d6045c4694..7d25bbe32110 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1036,7 +1036,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) return 0; } -static int +static netdev_tx_t ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 07ded5075b33..5c8d73730c75 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -204,7 +204,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations ip6mr_vif_seq_ops = { +static const struct seq_operations ip6mr_vif_seq_ops = { .start = ip6mr_vif_seq_start, .next = ip6mr_vif_seq_next, .stop = ip6mr_vif_seq_stop, @@ -217,7 +217,7 @@ static int ip6mr_vif_open(struct inode *inode, struct file *file) sizeof(struct ipmr_vif_iter)); } -static struct file_operations ip6mr_vif_fops = { +static const struct file_operations ip6mr_vif_fops = { .owner = THIS_MODULE, .open = ip6mr_vif_open, .read = seq_read, @@ -341,7 +341,7 @@ static int ipmr_mfc_open(struct inode *inode, struct file *file) sizeof(struct ipmr_mfc_iter)); } -static struct file_operations ip6mr_mfc_fops = { +static const struct file_operations ip6mr_mfc_fops = { .owner = THIS_MODULE, .open = ipmr_mfc_open, .read = seq_read, @@ -416,7 +416,8 @@ static struct inet6_protocol pim6_protocol = { /* Service routines creating virtual interfaces: PIMREG */ -static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, + struct net_device *dev) { struct net *net = dev_net(dev); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a7fdf9a27f15..f5e0682b402d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -315,6 +315,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, goto e_inval; if (val < -1 || val > 0xff) goto e_inval; + /* RFC 3542, 6.5: default traffic class of 0x0 */ + if (val == -1) + val = 0; np->tclass = val; retv = 0; break; @@ -1037,8 +1040,6 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_TCLASS: val = np->tclass; - if (val < 0) - val = 0; break; case IPV6_RECVTCLASS: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9eb68e92cc18..7015478797f6 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -98,7 +98,7 @@ static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); -static struct neigh_ops ndisc_generic_ops = { +static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, @@ -108,7 +108,7 @@ static struct neigh_ops ndisc_generic_ops = { .queue_xmit = dev_queue_xmit, }; -static struct neigh_ops ndisc_hh_ops = { +static const struct neigh_ops ndisc_hh_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, @@ -119,7 +119,7 @@ static struct neigh_ops ndisc_hh_ops = { }; -static struct neigh_ops ndisc_direct_ops = { +static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, .output = dev_queue_xmit, .connected_output = dev_queue_xmit, @@ -955,8 +955,8 @@ static void ndisc_recv_na(struct sk_buff *skb) */ if (skb->pkt_type != PACKET_LOOPBACK) ND_PRINTK1(KERN_WARNING - "ICMPv6 NA: someone advertises our address on %s!\n", - ifp->idev->dev->name); + "ICMPv6 NA: someone advertises our address %pI6 on %s!\n", + &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return; } @@ -1151,10 +1151,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) skb->dev->name); return; } - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) { - in6_dev_put(in6_dev); - return; - } if (!ndisc_parse_options(opt, optlen, &ndopts)) { in6_dev_put(in6_dev); @@ -1163,6 +1159,10 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } + /* skip route and link configuration on routers */ + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) + goto skip_linkparms; + #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) @@ -1283,9 +1283,7 @@ skip_defrtr: } } -#ifdef CONFIG_IPV6_NDISC_NODETYPE skip_linkparms: -#endif /* * Process options. @@ -1312,6 +1310,10 @@ skip_linkparms: NEIGH_UPDATE_F_ISROUTER); } + /* skip route and link configuration on routers */ + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) + goto out; + #ifdef CONFIG_IPV6_ROUTE_INFO if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 9ab789159913..568864f722ca 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -20,20 +20,9 @@ * - Removed unused variable 'inet6_protocol_base' * - Modified inet6_del_protocol() to correctly maintain copy bit. */ - -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/net.h> -#include <linux/in6.h> +#include <linux/module.h> #include <linux/netdevice.h> -#include <linux/if_arp.h> - -#include <net/sock.h> -#include <net/snmp.h> - -#include <net/ipv6.h> +#include <linux/spinlock.h> #include <net/protocol.h> struct inet6_protocol *inet6_protos[MAX_INET_PROTOS]; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d6c3c1c34b2d..7d675b8d82d3 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -642,7 +642,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; out: @@ -653,6 +653,8 @@ error_fault: kfree_skb(skb); error: IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); + if (err == -ENOBUFS && !np->recverr) + err = 0; return err; } @@ -877,11 +879,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, hlimit = ip6_dst_hoplimit(dst); } - if (tclass < 0) { + if (tclass < 0) tclass = np->tclass; - if (tclass < 0) - tclass = 0; - } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1473ee0a1f51..9ccfef345560 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -665,7 +665,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad net->ipv6.sysctl.ip6_rt_gc_elasticity = 1; net->ipv6.sysctl.ip6_rt_gc_min_interval = 0; - ip6_dst_gc(net->ipv6.ip6_dst_ops); + ip6_dst_gc(&net->ipv6.ip6_dst_ops); net->ipv6.sysctl.ip6_rt_gc_elasticity = saved_rt_elasticity; @@ -970,7 +970,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (unlikely(idev == NULL)) return NULL; - rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (unlikely(rt == NULL)) { in6_dev_put(idev); goto out; @@ -1060,7 +1060,7 @@ static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), static int ip6_dst_gc(struct dst_ops *ops) { unsigned long now = jiffies; - struct net *net = ops->dst_net; + struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; @@ -1154,7 +1154,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (rt == NULL) { err = -ENOMEM; @@ -1643,7 +1643,7 @@ out: static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) { struct net *net = dev_net(ort->rt6i_dev); - struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); + struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (rt) { rt->u.dst.input = ort->u.dst.input; @@ -1923,7 +1923,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, int anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops); + struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); struct neighbour *neigh; if (rt == NULL) @@ -2501,7 +2501,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) net->ipv6.rt6_stats->fib_rt_alloc, net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, - atomic_read(&net->ipv6.ip6_dst_ops->entries), + atomic_read(&net->ipv6.ip6_dst_ops.entries), net->ipv6.rt6_stats->fib_discarded_routes); return 0; @@ -2637,7 +2637,7 @@ struct ctl_table *ipv6_route_sysctl_init(struct net *net) if (table) { table[0].data = &net->ipv6.sysctl.flush_delay; - table[1].data = &net->ipv6.ip6_dst_ops->gc_thresh; + table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.ip6_rt_max_size; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; @@ -2655,12 +2655,8 @@ static int ip6_route_net_init(struct net *net) { int ret = -ENOMEM; - net->ipv6.ip6_dst_ops = kmemdup(&ip6_dst_ops_template, - sizeof(*net->ipv6.ip6_dst_ops), - GFP_KERNEL); - if (!net->ipv6.ip6_dst_ops) - goto out; - net->ipv6.ip6_dst_ops->dst_net = hold_net(net); + memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, + sizeof(net->ipv6.ip6_dst_ops)); net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), @@ -2669,7 +2665,7 @@ static int ip6_route_net_init(struct net *net) goto out_ip6_dst_ops; net->ipv6.ip6_null_entry->u.dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; - net->ipv6.ip6_null_entry->u.dst.ops = net->ipv6.ip6_dst_ops; + net->ipv6.ip6_null_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, @@ -2679,7 +2675,7 @@ static int ip6_route_net_init(struct net *net) goto out_ip6_null_entry; net->ipv6.ip6_prohibit_entry->u.dst.path = (struct dst_entry *)net->ipv6.ip6_prohibit_entry; - net->ipv6.ip6_prohibit_entry->u.dst.ops = net->ipv6.ip6_dst_ops; + net->ipv6.ip6_prohibit_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), @@ -2688,7 +2684,7 @@ static int ip6_route_net_init(struct net *net) goto out_ip6_prohibit_entry; net->ipv6.ip6_blk_hole_entry->u.dst.path = (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; - net->ipv6.ip6_blk_hole_entry->u.dst.ops = net->ipv6.ip6_dst_ops; + net->ipv6.ip6_blk_hole_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; #endif net->ipv6.sysctl.flush_delay = 0; @@ -2717,8 +2713,6 @@ out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif out_ip6_dst_ops: - release_net(net->ipv6.ip6_dst_ops->dst_net); - kfree(net->ipv6.ip6_dst_ops); goto out; } @@ -2733,8 +2727,6 @@ static void ip6_route_net_exit(struct net *net) kfree(net->ipv6.ip6_prohibit_entry); kfree(net->ipv6.ip6_blk_hole_entry); #endif - release_net(net->ipv6.ip6_dst_ops->dst_net); - kfree(net->ipv6.ip6_dst_ops); } static struct pernet_operations ip6_route_net_ops = { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index d335a306a4db..0ae4f6448187 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -609,7 +609,8 @@ static inline __be32 try_6to4(struct in6_addr *v6dst) * and that skb is filled properly by that function. */ -static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net_device_stats *stats = &tunnel->dev->stats; @@ -778,7 +779,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) iph->version = 4; iph->ihl = sizeof(struct iphdr)>>2; if (mtu > IPV6_MIN_MTU) - iph->frag_off = htons(IP_DF); + iph->frag_off = tiph->frag_off; else iph->frag_off = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d849dd53b788..3aae0f217d61 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -75,11 +75,11 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); -static struct inet_connection_sock_af_ops ipv6_mapped; -static struct inet_connection_sock_af_ops ipv6_specific; +static const struct inet_connection_sock_af_ops ipv6_mapped; +static const struct inet_connection_sock_af_ops ipv6_specific; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_sock_af_ops tcp_sock_ipv6_specific; -static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; +static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; +static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #else static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, struct in6_addr *addr) @@ -591,7 +591,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, } sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } - if (tcp_alloc_md5sig_pool() == NULL) { + if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); return -ENOMEM; } @@ -894,7 +894,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = { }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { +static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .md5_lookup = tcp_v6_reqsk_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, }; @@ -1003,6 +1003,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); t1 = (struct tcphdr *) skb_push(buff, tot_len); + skb_reset_transport_header(skb); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); @@ -1760,7 +1761,7 @@ static int tcp_v6_remember_stamp(struct sock *sk) return 0; } -static struct inet_connection_sock_af_ops ipv6_specific = { +static const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, @@ -1780,7 +1781,7 @@ static struct inet_connection_sock_af_ops ipv6_specific = { }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_sock_af_ops tcp_sock_ipv6_specific = { +static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, .md5_add = tcp_v6_md5_add_func, @@ -1792,7 +1793,7 @@ static struct tcp_sock_af_ops tcp_sock_ipv6_specific = { * TCP over IPv4 via INET6 API */ -static struct inet_connection_sock_af_ops ipv6_mapped = { +static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, @@ -1812,7 +1813,7 @@ static struct inet_connection_sock_af_ops ipv6_mapped = { }; #ifdef CONFIG_TCP_MD5SIG -static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { +static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_add = tcp_v6_md5_add_func, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d79fa6724451..164040613c2e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -724,12 +724,18 @@ static int udp_v6_push_pending_frames(struct sock *sk) send: err = ip6_push_pending_frames(sk); + if (err) { + if (err == -ENOBUFS && !inet6_sk(sk)->recverr) { + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); + err = 0; + } + } else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); out: up->len = 0; up->pending = 0; - if (!err) - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } @@ -946,11 +952,8 @@ do_udp_sendmsg: hlimit = ip6_dst_hoplimit(dst); } - if (tclass < 0) { + if (tclass < 0) tclass = np->tclass; - if (tclass < 0) - tclass = 0; - } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 417b0e309495..f1118d92a191 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -41,6 +41,7 @@ #include <linux/netdevice.h> #include <linux/uio.h> #include <linux/skbuff.h> +#include <linux/smp_lock.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/string.h> diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index cb762c8723ea..50b43c57d5d8 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -45,6 +45,7 @@ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> +#include <linux/smp_lock.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/init.h> @@ -714,6 +715,7 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); + memset(&saddr, 0, sizeof(saddr)); if (peer) { if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index 64230cffcfee..7b6b631f647f 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -41,7 +41,8 @@ static int irlan_eth_open(struct net_device *dev); static int irlan_eth_close(struct net_device *dev); -static int irlan_eth_xmit(struct sk_buff *skb, struct net_device *dev); +static netdev_tx_t irlan_eth_xmit(struct sk_buff *skb, + struct net_device *dev); static void irlan_eth_set_multicast_list( struct net_device *dev); static struct net_device_stats *irlan_eth_get_stats(struct net_device *dev); @@ -162,7 +163,8 @@ static int irlan_eth_close(struct net_device *dev) * Transmits ethernet frames over IrDA link. * */ -static int irlan_eth_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t irlan_eth_xmit(struct sk_buff *skb, + struct net_device *dev) { struct irlan_cb *self = netdev_priv(dev); int ret; diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index bccf4d0059f0..b001c361ad30 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -241,7 +241,6 @@ #include <linux/module.h> #include <linux/kernel.h> -#include <linux/smp_lock.h> #include <linux/skbuff.h> #include <linux/tty.h> #include <linux/proc_fs.h> diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 6d8ae03c14f5..68cbcb19cbd8 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -13,6 +13,7 @@ * 2) as a control channel (write commands, read events) */ +#include <linux/smp_lock.h> #include "irnet_ppp.h" /* Private header */ /* Please put other headers in irnet.h - Thanks */ diff --git a/net/irda/irnet/irnet_ppp.h b/net/irda/irnet/irnet_ppp.h index d9f8bd4ebd05..b5df2418f90c 100644 --- a/net/irda/irnet/irnet_ppp.h +++ b/net/irda/irnet/irnet_ppp.h @@ -95,7 +95,7 @@ static int /**************************** VARIABLES ****************************/ /* Filesystem callbacks (to call us) */ -static struct file_operations irnet_device_fops = +static const struct file_operations irnet_device_fops = { .owner = THIS_MODULE, .read = dev_irnet_read, diff --git a/net/irda/irproc.c b/net/irda/irproc.c index 8ff1861649e8..318766e5dbdf 100644 --- a/net/irda/irproc.c +++ b/net/irda/irproc.c @@ -34,21 +34,21 @@ #include <net/irda/irlap.h> #include <net/irda/irlmp.h> -extern struct file_operations discovery_seq_fops; -extern struct file_operations irlap_seq_fops; -extern struct file_operations irlmp_seq_fops; -extern struct file_operations irttp_seq_fops; -extern struct file_operations irias_seq_fops; +extern const struct file_operations discovery_seq_fops; +extern const struct file_operations irlap_seq_fops; +extern const struct file_operations irlmp_seq_fops; +extern const struct file_operations irttp_seq_fops; +extern const struct file_operations irias_seq_fops; struct irda_entry { const char *name; - struct file_operations *fops; + const struct file_operations *fops; }; struct proc_dir_entry *proc_irda; EXPORT_SYMBOL(proc_irda); -static struct irda_entry irda_dirs[] = { +static const struct irda_entry irda_dirs[] = { {"discovery", &discovery_seq_fops}, {"irttp", &irttp_seq_fops}, {"irlmp", &irlmp_seq_fops}, diff --git a/net/key/af_key.c b/net/key/af_key.c index dba9abd27f90..4e98193dfa0f 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3705,7 +3705,7 @@ static void pfkey_seq_stop(struct seq_file *f, void *v) read_unlock(&pfkey_table_lock); } -static struct seq_operations pfkey_seq_ops = { +static const struct seq_operations pfkey_seq_ops = { .start = pfkey_seq_start, .next = pfkey_seq_next, .stop = pfkey_seq_stop, @@ -3718,7 +3718,7 @@ static int pfkey_seq_open(struct inode *inode, struct file *file) sizeof(struct seq_net_private)); } -static struct file_operations pfkey_proc_ops = { +static const struct file_operations pfkey_proc_ops = { .open = pfkey_seq_open, .read = seq_read, .llseek = seq_lseek, diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 9208cf5f2bd5..c45eee1c0e8d 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -914,6 +914,7 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, struct llc_sock *llc = llc_sk(sk); int rc = 0; + memset(&sllc, 0, sizeof(sllc)); lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) goto out; diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 7dd77b6d4c9a..4d5543af3123 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -13,8 +13,7 @@ config MAC80211 comment "CFG80211 needs to be enabled for MAC80211" depends on CFG80211=n -menu "Rate control algorithm selection" - depends on MAC80211 != n +if MAC80211 != n config MAC80211_RC_PID bool "PID controller based rate control algorithm" if EMBEDDED @@ -61,17 +60,17 @@ config MAC80211_RC_DEFAULT default "pid" if MAC80211_RC_DEFAULT_PID default "" -endmenu +endif config MAC80211_MESH bool "Enable mac80211 mesh networking (pre-802.11s) support" depends on MAC80211 && EXPERIMENTAL - depends on BROKEN ---help--- This options enables support of Draft 802.11s mesh networking. - The implementation is based on Draft 1.08 of the Mesh Networking - amendment. For more information visit http://o11s.org/. - + The implementation is based on Draft 2.08 of the Mesh Networking + amendment. However, no compliance with that draft is claimed or even + possible, as drafts leave a number of identifiers to be defined after + ratification. For more information visit http://o11s.org/. config MAC80211_LEDS bool "Enable LED triggers" diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 1958c7c42cd9..bd765f30dba2 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -381,6 +381,14 @@ static void ieee80211_agg_splice_packets(struct ieee80211_local *local, &local->hw, queue, IEEE80211_QUEUE_STOP_REASON_AGGREGATION); + if (!(sta->ampdu_mlme.tid_state_tx[tid] & HT_ADDBA_REQUESTED_MSK)) + return; + + if (WARN(!sta->ampdu_mlme.tid_tx[tid], + "TID %d gone but expected when splicing aggregates from" + "the pending queue\n", tid)) + return; + if (!skb_queue_empty(&sta->ampdu_mlme.tid_tx[tid]->pending)) { spin_lock_irqsave(&local->queue_stop_reason_lock, flags); /* copy over remaining packets */ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4bbf5007799b..5608f6c68413 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -323,6 +323,8 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = sta->sdata; + sinfo->generation = sdata->local->sta_generation; + sinfo->filled = STATION_INFO_INACTIVE_TIME | STATION_INFO_RX_BYTES | STATION_INFO_TX_BYTES | @@ -909,6 +911,8 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, else memset(next_hop, 0, ETH_ALEN); + pinfo->generation = mesh_paths_generation; + pinfo->filled = MPATH_INFO_FRAME_QLEN | MPATH_INFO_DSN | MPATH_INFO_METRIC | diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index e9ec6cae2d39..61234e79022b 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -116,6 +116,8 @@ IEEE80211_IF_FILE(peer, u.wds.remote_addr, MAC); #ifdef CONFIG_MAC80211_MESH /* Mesh stats attributes */ +IEEE80211_IF_FILE(fwded_mcast, u.mesh.mshstats.fwded_mcast, DEC); +IEEE80211_IF_FILE(fwded_unicast, u.mesh.mshstats.fwded_unicast, DEC); IEEE80211_IF_FILE(fwded_frames, u.mesh.mshstats.fwded_frames, DEC); IEEE80211_IF_FILE(dropped_frames_ttl, u.mesh.mshstats.dropped_frames_ttl, DEC); IEEE80211_IF_FILE(dropped_frames_no_route, @@ -205,6 +207,8 @@ static void add_mesh_stats(struct ieee80211_sub_if_data *sdata) { sdata->mesh_stats_dir = debugfs_create_dir("mesh_stats", sdata->debugfsdir); + MESHSTATS_ADD(fwded_mcast); + MESHSTATS_ADD(fwded_unicast); MESHSTATS_ADD(fwded_frames); MESHSTATS_ADD(dropped_frames_ttl); MESHSTATS_ADD(dropped_frames_no_route); @@ -327,6 +331,8 @@ static void del_monitor_files(struct ieee80211_sub_if_data *sdata) static void del_mesh_stats(struct ieee80211_sub_if_data *sdata) { + MESHSTATS_DEL(fwded_mcast); + MESHSTATS_DEL(fwded_unicast); MESHSTATS_DEL(fwded_frames); MESHSTATS_DEL(dropped_frames_ttl); MESHSTATS_DEL(dropped_frames_no_route); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 4100c361a99d..020a94a31106 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -12,7 +12,11 @@ static inline int drv_tx(struct ieee80211_local *local, struct sk_buff *skb) static inline int drv_start(struct ieee80211_local *local) { - int ret = local->ops->start(&local->hw); + int ret; + + local->started = true; + smp_mb(); + ret = local->ops->start(&local->hw); trace_drv_start(local, ret); return ret; } @@ -21,6 +25,14 @@ static inline void drv_stop(struct ieee80211_local *local) { local->ops->stop(&local->hw); trace_drv_stop(local); + + /* sync away all work on the tasklet before clearing started */ + tasklet_disable(&local->tasklet); + tasklet_enable(&local->tasklet); + + barrier(); + + local->started = false; } static inline int drv_add_interface(struct ieee80211_local *local, @@ -55,16 +67,32 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local, trace_drv_bss_info_changed(local, vif, info, changed); } +static inline u64 drv_prepare_multicast(struct ieee80211_local *local, + int mc_count, + struct dev_addr_list *mc_list) +{ + u64 ret = 0; + + if (local->ops->prepare_multicast) + ret = local->ops->prepare_multicast(&local->hw, mc_count, + mc_list); + + trace_drv_prepare_multicast(local, mc_count, ret); + + return ret; +} + static inline void drv_configure_filter(struct ieee80211_local *local, unsigned int changed_flags, unsigned int *total_flags, - int mc_count, - struct dev_addr_list *mc_list) + u64 multicast) { + might_sleep(); + local->ops->configure_filter(&local->hw, changed_flags, total_flags, - mc_count, mc_list); + multicast); trace_drv_configure_filter(local, changed_flags, total_flags, - mc_count); + multicast); } static inline int drv_set_tim(struct ieee80211_local *local, diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index 5a10da2d70fd..37b9051afcf3 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -191,31 +191,55 @@ TRACE_EVENT(drv_bss_info_changed, ) ); +TRACE_EVENT(drv_prepare_multicast, + TP_PROTO(struct ieee80211_local *local, int mc_count, u64 ret), + + TP_ARGS(local, mc_count, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(int, mc_count) + __field(u64, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->mc_count = mc_count; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT " prepare mc (%d): %llx", + LOCAL_PR_ARG, __entry->mc_count, + (unsigned long long) __entry->ret + ) +); + TRACE_EVENT(drv_configure_filter, TP_PROTO(struct ieee80211_local *local, unsigned int changed_flags, unsigned int *total_flags, - int mc_count), + u64 multicast), - TP_ARGS(local, changed_flags, total_flags, mc_count), + TP_ARGS(local, changed_flags, total_flags, multicast), TP_STRUCT__entry( LOCAL_ENTRY __field(unsigned int, changed) __field(unsigned int, total) - __field(int, mc) + __field(u64, multicast) ), TP_fast_assign( LOCAL_ASSIGN; __entry->changed = changed_flags; __entry->total = *total_flags; - __entry->mc = mc_count; + __entry->multicast = multicast; ), TP_printk( - LOCAL_PR_FMT " changed:%#x total:%#x mc:%d", - LOCAL_PR_ARG, __entry->changed, __entry->total, __entry->mc + LOCAL_PR_FMT " changed:%#x total:%#x", + LOCAL_PR_ARG, __entry->changed, __entry->total ) ); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 630a438180fd..588005c84a6d 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -212,7 +212,9 @@ struct ieee80211_if_vlan { }; struct mesh_stats { - __u32 fwded_frames; /* Mesh forwarded frames */ + __u32 fwded_mcast; /* Mesh forwarded multicast frames */ + __u32 fwded_unicast; /* Mesh forwarded unicast frames */ + __u32 fwded_frames; /* Mesh total forwarded frames */ __u32 dropped_frames_ttl; /* Not transmitted since mesh_ttl == 0*/ __u32 dropped_frames_no_route; /* Not transmitted, no route found */ atomic_t estab_plinks; @@ -284,6 +286,7 @@ struct ieee80211_if_managed { struct mutex mtx; struct ieee80211_bss *associated; + struct ieee80211_mgd_work *old_associate_work; struct list_head work_list; u8 bssid[ETH_ALEN]; @@ -354,7 +357,7 @@ struct ieee80211_if_mesh { unsigned long timers_running; - bool housekeeping; + unsigned long wrkq_flags; u8 mesh_id[IEEE80211_MAX_MESH_ID_LEN]; size_t mesh_id_len; @@ -364,6 +367,10 @@ struct ieee80211_if_mesh { u8 mesh_pm_id[4]; /* Congestion Control Mode Identifier */ u8 mesh_cc_id[4]; + /* Synchronization Protocol Identifier */ + u8 mesh_sp_id[4]; + /* Authentication Protocol Identifier */ + u8 mesh_auth_id[4]; /* Local mesh Destination Sequence Number */ u32 dsn; /* Last used PREQ ID */ @@ -505,6 +512,8 @@ struct ieee80211_sub_if_data { #ifdef CONFIG_MAC80211_MESH struct dentry *mesh_stats_dir; struct { + struct dentry *fwded_mcast; + struct dentry *fwded_unicast; struct dentry *fwded_frames; struct dentry *dropped_frames_ttl; struct dentry *dropped_frames_no_route; @@ -635,6 +644,9 @@ struct ieee80211_local { /* protects the aggregated multicast list and filter calls */ spinlock_t filter_lock; + /* used for uploading changed mc list */ + struct work_struct reconfig_filter; + /* aggregated multicast list */ struct dev_addr_list *mc_list; int mc_count; @@ -655,6 +667,9 @@ struct ieee80211_local { */ bool quiescing; + /* device is started */ + bool started; + int tx_headroom; /* required headroom for hardware/radiotap */ /* Tasklet and skb queue to process calls from IRQ mode. All frames @@ -677,6 +692,7 @@ struct ieee80211_local { struct list_head sta_list; struct sta_info *sta_hash[STA_HASH_SIZE]; struct timer_list sta_cleanup; + int sta_generation; struct sk_buff_head pending[IEEE80211_MAX_QUEUES]; struct tasklet_struct tx_pending_tasklet; @@ -713,7 +729,7 @@ struct ieee80211_local { struct mutex scan_mtx; unsigned long scanning; struct cfg80211_ssid scan_ssid; - struct cfg80211_scan_request int_scan_req; + struct cfg80211_scan_request *int_scan_req; struct cfg80211_scan_request *scan_req; struct ieee80211_channel *scan_channel; const u8 *orig_ies; @@ -1034,8 +1050,10 @@ void ieee80211_recalc_idle(struct ieee80211_local *local); /* tx handling */ void ieee80211_clear_tx_pending(struct ieee80211_local *local); void ieee80211_tx_pending(unsigned long data); -int ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); -int ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, + struct net_device *dev); +netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, + struct net_device *dev); /* HT */ void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_supported_band *sband, @@ -1073,6 +1091,7 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, /* Suspend/resume and hw reconfiguration */ int ieee80211_reconfig(struct ieee80211_local *local); +void ieee80211_stop_device(struct ieee80211_local *local); #ifdef CONFIG_PM int __ieee80211_suspend(struct ieee80211_hw *hw); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index e8fb03b91a44..f6005adcbf90 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -227,9 +227,7 @@ static int ieee80211_open(struct net_device *dev) if (sdata->u.mntr_flags & MONITOR_FLAG_OTHER_BSS) local->fif_other_bss++; - spin_lock_bh(&local->filter_lock); ieee80211_configure_filter(local); - spin_unlock_bh(&local->filter_lock); break; default: conf.vif = &sdata->vif; @@ -241,17 +239,13 @@ static int ieee80211_open(struct net_device *dev) if (ieee80211_vif_is_mesh(&sdata->vif)) { local->fif_other_bss++; - spin_lock_bh(&local->filter_lock); ieee80211_configure_filter(local); - spin_unlock_bh(&local->filter_lock); ieee80211_start_mesh(sdata); } else if (sdata->vif.type == NL80211_IFTYPE_AP) { local->fif_pspoll++; - spin_lock_bh(&local->filter_lock); ieee80211_configure_filter(local); - spin_unlock_bh(&local->filter_lock); } changed |= ieee80211_reset_erp_info(sdata); @@ -283,11 +277,6 @@ static int ieee80211_open(struct net_device *dev) } } - if (local->open_count == 0) { - tasklet_enable(&local->tx_pending_tasklet); - tasklet_enable(&local->tasklet); - } - /* * set_multicast_list will be invoked by the networking core * which will check whether any increments here were done in @@ -404,10 +393,11 @@ static int ieee80211_stop(struct net_device *dev) spin_lock_bh(&local->filter_lock); __dev_addr_unsync(&local->mc_list, &local->mc_count, &dev->mc_list, &dev->mc_count); - ieee80211_configure_filter(local); spin_unlock_bh(&local->filter_lock); netif_addr_unlock_bh(dev); + ieee80211_configure_filter(local); + del_timer_sync(&local->dynamic_ps_timer); cancel_work_sync(&local->dynamic_ps_enable_work); @@ -458,9 +448,7 @@ static int ieee80211_stop(struct net_device *dev) if (sdata->u.mntr_flags & MONITOR_FLAG_OTHER_BSS) local->fif_other_bss--; - spin_lock_bh(&local->filter_lock); ieee80211_configure_filter(local); - spin_unlock_bh(&local->filter_lock); break; case NL80211_IFTYPE_STATION: del_timer_sync(&sdata->u.mgd.chswitch_timer); @@ -503,38 +491,14 @@ static int ieee80211_stop(struct net_device *dev) local->fif_other_bss--; atomic_dec(&local->iff_allmultis); - spin_lock_bh(&local->filter_lock); ieee80211_configure_filter(local); - spin_unlock_bh(&local->filter_lock); ieee80211_stop_mesh(sdata); } /* fall through */ default: - if (local->scan_sdata == sdata) { - if (!local->ops->hw_scan) - cancel_delayed_work_sync(&local->scan_work); - /* - * The software scan can no longer run now, so we can - * clear out the scan_sdata reference. However, the - * hardware scan may still be running. The complete - * function must be prepared to handle a NULL value. - */ - local->scan_sdata = NULL; - /* - * The memory barrier guarantees that another CPU - * that is hardware-scanning will now see the fact - * that this interface is gone. - */ - smp_mb(); - /* - * If software scanning, complete the scan but since - * the scan_sdata is NULL already don't send out a - * scan event to userspace -- the scan is incomplete. - */ - if (test_bit(SCAN_SW_SCANNING, &local->scanning)) - ieee80211_scan_completed(&local->hw, true); - } + if (local->scan_sdata == sdata) + ieee80211_scan_cancel(local); /* * Disable beaconing for AP and mesh, IBSS can't @@ -561,14 +525,8 @@ static int ieee80211_stop(struct net_device *dev) ieee80211_recalc_ps(local, -1); if (local->open_count == 0) { - drv_stop(local); - - ieee80211_led_radio(local, false); - - flush_workqueue(local->workqueue); - - tasklet_disable(&local->tx_pending_tasklet); - tasklet_disable(&local->tasklet); + ieee80211_clear_tx_pending(local); + ieee80211_stop_device(local); /* no reconfiguring after stop! */ hw_reconf_flags = 0; @@ -622,8 +580,8 @@ static void ieee80211_set_multicast_list(struct net_device *dev) spin_lock_bh(&local->filter_lock); __dev_addr_sync(&local->mc_list, &local->mc_count, &dev->mc_list, &dev->mc_count); - ieee80211_configure_filter(local); spin_unlock_bh(&local->filter_lock); + ieee80211_queue_work(&local->hw, &local->reconfig_filter); } /* diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 0c4f8e122ed6..797f53942e5f 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -50,9 +50,9 @@ struct ieee80211_tx_status_rtap_hdr { } __attribute__ ((packed)); -/* must be called under mdev tx lock */ void ieee80211_configure_filter(struct ieee80211_local *local) { + u64 mc; unsigned int changed_flags; unsigned int new_flags = 0; @@ -62,7 +62,7 @@ void ieee80211_configure_filter(struct ieee80211_local *local) if (atomic_read(&local->iff_allmultis)) new_flags |= FIF_ALLMULTI; - if (local->monitors) + if (local->monitors || local->scanning) new_flags |= FIF_BCN_PRBRESP_PROMISC; if (local->fif_fcsfail) @@ -80,20 +80,30 @@ void ieee80211_configure_filter(struct ieee80211_local *local) if (local->fif_pspoll) new_flags |= FIF_PSPOLL; + spin_lock_bh(&local->filter_lock); changed_flags = local->filter_flags ^ new_flags; + mc = drv_prepare_multicast(local, local->mc_count, local->mc_list); + spin_unlock_bh(&local->filter_lock); + /* be a bit nasty */ new_flags |= (1<<31); - drv_configure_filter(local, changed_flags, &new_flags, - local->mc_count, - local->mc_list); + drv_configure_filter(local, changed_flags, &new_flags, mc); WARN_ON(new_flags & (1<<31)); local->filter_flags = new_flags & ~(1<<31); } +static void ieee80211_reconfig_filter(struct work_struct *work) +{ + struct ieee80211_local *local = + container_of(work, struct ieee80211_local, reconfig_filter); + + ieee80211_configure_filter(local); +} + int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) { struct ieee80211_channel *chan, *scan_chan; @@ -231,9 +241,6 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, drv_bss_info_changed(local, &sdata->vif, &sdata->vif.bss_conf, changed); - - /* DEPRECATED */ - local->hw.conf.beacon_int = sdata->vif.bss_conf.beacon_int; } u32 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata) @@ -475,6 +482,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) } rate_control_tx_status(local, sband, sta, skb); + if (ieee80211_vif_is_mesh(&sta->sdata->vif)) + ieee80211s_update_metric(local, sta, skb); } rcu_read_unlock(); @@ -677,7 +686,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.max_rates = 1; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; - local->hw.conf.radio_enabled = true; local->user_power_level = -1; INIT_LIST_HEAD(&local->interfaces); @@ -692,6 +700,8 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, INIT_WORK(&local->restart_work, ieee80211_restart_work); + INIT_WORK(&local->reconfig_filter, ieee80211_reconfig_filter); + INIT_WORK(&local->dynamic_ps_enable_work, ieee80211_dynamic_ps_enable_work); INIT_WORK(&local->dynamic_ps_disable_work, @@ -705,12 +715,10 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, skb_queue_head_init(&local->pending[i]); tasklet_init(&local->tx_pending_tasklet, ieee80211_tx_pending, (unsigned long)local); - tasklet_disable(&local->tx_pending_tasklet); tasklet_init(&local->tasklet, ieee80211_tasklet_handler, (unsigned long) local); - tasklet_disable(&local->tasklet); skb_queue_head_init(&local->skb_queue); skb_queue_head_init(&local->skb_queue_unreliable); @@ -765,9 +773,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_ht = supp_ht || sband->ht_cap.ht_supported; } - local->int_scan_req.n_channels = channels; - local->int_scan_req.channels = kzalloc(sizeof(void *) * channels, GFP_KERNEL); - if (!local->int_scan_req.channels) + local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) + + sizeof(void *) * channels, GFP_KERNEL); + if (!local->int_scan_req) return -ENOMEM; /* if low-level driver supports AP, we also support VLAN */ @@ -882,13 +890,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) /* alloc internal scan request */ i = 0; - local->int_scan_req.ssids = &local->scan_ssid; - local->int_scan_req.n_ssids = 1; + local->int_scan_req->ssids = &local->scan_ssid; + local->int_scan_req->n_ssids = 1; for (band = 0; band < IEEE80211_NUM_BANDS; band++) { if (!hw->wiphy->bands[band]) continue; for (j = 0; j < hw->wiphy->bands[band]->n_channels; j++) { - local->int_scan_req.channels[i] = + local->int_scan_req->channels[i] = &hw->wiphy->bands[band]->channels[j]; i++; } @@ -920,7 +928,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) fail_workqueue: wiphy_unregister(local->hw.wiphy); fail_wiphy_register: - kfree(local->int_scan_req.channels); + kfree(local->int_scan_req); return result; } EXPORT_SYMBOL(ieee80211_register_hw); @@ -946,6 +954,8 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) rtnl_unlock(); + cancel_work_sync(&local->reconfig_filter); + ieee80211_clear_tx_pending(local); sta_info_stop(local); rate_control_deinitialize(local); @@ -962,7 +972,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) wiphy_unregister(local->hw.wiphy); ieee80211_wep_free(local); ieee80211_led_exit(local); - kfree(local->int_scan_req.channels); + kfree(local->int_scan_req); } EXPORT_SYMBOL(ieee80211_unregister_hw); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 2f4f518ab45c..f7364e56f1ee 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -18,8 +18,11 @@ #define PP_OFFSET 1 /* Path Selection Protocol */ #define PM_OFFSET 5 /* Path Selection Metric */ #define CC_OFFSET 9 /* Congestion Control Mode */ -#define CAPAB_OFFSET 17 -#define ACCEPT_PLINKS 0x80 +#define SP_OFFSET 13 /* Synchronization Protocol */ +#define AUTH_OFFSET 17 /* Authentication Protocol */ +#define CAPAB_OFFSET 22 +#define CAPAB_ACCEPT_PLINKS 0x80 +#define CAPAB_FORWARDING 0x10 #define TMR_RUNNING_HK 0 #define TMR_RUNNING_MP 1 @@ -47,14 +50,14 @@ static void ieee80211_mesh_housekeeping_timer(unsigned long data) struct ieee80211_local *local = sdata->local; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - ifmsh->housekeeping = true; + ifmsh->wrkq_flags |= MESH_WORK_HOUSEKEEPING; if (local->quiescing) { set_bit(TMR_RUNNING_HK, &ifmsh->timers_running); return; } - ieee80211_queue_work(local->hw.workqueue, &ifmsh->work); + ieee80211_queue_work(&local->hw, &ifmsh->work); } /** @@ -84,7 +87,9 @@ bool mesh_matches_local(struct ieee802_11_elems *ie, struct ieee80211_sub_if_dat memcmp(ifmsh->mesh_id, ie->mesh_id, ie->mesh_id_len) == 0 && memcmp(ifmsh->mesh_pp_id, ie->mesh_config + PP_OFFSET, 4) == 0 && memcmp(ifmsh->mesh_pm_id, ie->mesh_config + PM_OFFSET, 4) == 0 && - memcmp(ifmsh->mesh_cc_id, ie->mesh_config + CC_OFFSET, 4) == 0) + memcmp(ifmsh->mesh_cc_id, ie->mesh_config + CC_OFFSET, 4) == 0 && + memcmp(ifmsh->mesh_sp_id, ie->mesh_config + SP_OFFSET, 4) == 0 && + memcmp(ifmsh->mesh_auth_id, ie->mesh_config + AUTH_OFFSET, 4) == 0) return true; return false; @@ -97,7 +102,7 @@ bool mesh_matches_local(struct ieee802_11_elems *ie, struct ieee80211_sub_if_dat */ bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie) { - return (*(ie->mesh_config + CAPAB_OFFSET) & ACCEPT_PLINKS) != 0; + return (*(ie->mesh_config + CAPAB_OFFSET) & CAPAB_ACCEPT_PLINKS) != 0; } /** @@ -123,11 +128,18 @@ void mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata) void mesh_ids_set_default(struct ieee80211_if_mesh *sta) { - u8 def_id[4] = {0x00, 0x0F, 0xAC, 0xff}; - - memcpy(sta->mesh_pp_id, def_id, 4); - memcpy(sta->mesh_pm_id, def_id, 4); - memcpy(sta->mesh_cc_id, def_id, 4); + u8 oui[3] = {0x00, 0x0F, 0xAC}; + + memcpy(sta->mesh_pp_id, oui, sizeof(oui)); + memcpy(sta->mesh_pm_id, oui, sizeof(oui)); + memcpy(sta->mesh_cc_id, oui, sizeof(oui)); + memcpy(sta->mesh_sp_id, oui, sizeof(oui)); + memcpy(sta->mesh_auth_id, oui, sizeof(oui)); + sta->mesh_pp_id[sizeof(oui)] = 0; + sta->mesh_pm_id[sizeof(oui)] = 0; + sta->mesh_cc_id[sizeof(oui)] = 0xff; + sta->mesh_sp_id[sizeof(oui)] = 0xff; + sta->mesh_auth_id[sizeof(oui)] = 0x0; } int mesh_rmc_init(struct ieee80211_sub_if_data *sdata) @@ -245,7 +257,7 @@ void mesh_mgmt_ies_add(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) if (sdata->u.mesh.mesh_id_len) memcpy(pos, sdata->u.mesh.mesh_id, sdata->u.mesh.mesh_id_len); - pos = skb_put(skb, 21); + pos = skb_put(skb, 2 + IEEE80211_MESH_CONFIG_LEN); *pos++ = WLAN_EID_MESH_CONFIG; *pos++ = IEEE80211_MESH_CONFIG_LEN; /* Version */ @@ -263,15 +275,22 @@ void mesh_mgmt_ies_add(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) memcpy(pos, sdata->u.mesh.mesh_cc_id, 4); pos += 4; - /* Channel precedence: - * Not running simple channel unification protocol - */ - memset(pos, 0x00, 4); + /* Synchronization protocol identifier */ + memcpy(pos, sdata->u.mesh.mesh_sp_id, 4); pos += 4; + /* Authentication Protocol identifier */ + memcpy(pos, sdata->u.mesh.mesh_auth_id, 4); + pos += 4; + + /* Mesh Formation Info */ + memset(pos, 0x00, 1); + pos += 1; + /* Mesh capability */ sdata->u.mesh.accepting_plinks = mesh_plink_availables(sdata); - *pos++ = sdata->u.mesh.accepting_plinks ? ACCEPT_PLINKS : 0x00; + *pos = CAPAB_FORWARDING; + *pos++ |= sdata->u.mesh.accepting_plinks ? CAPAB_ACCEPT_PLINKS : 0x00; *pos++ = 0x00; return; @@ -320,30 +339,6 @@ struct mesh_table *mesh_table_alloc(int size_order) return newtbl; } -static void __mesh_table_free(struct mesh_table *tbl) -{ - kfree(tbl->hash_buckets); - kfree(tbl->hashwlock); - kfree(tbl); -} - -void mesh_table_free(struct mesh_table *tbl, bool free_leafs) -{ - struct hlist_head *mesh_hash; - struct hlist_node *p, *q; - int i; - - mesh_hash = tbl->hash_buckets; - for (i = 0; i <= tbl->hash_mask; i++) { - spin_lock(&tbl->hashwlock[i]); - hlist_for_each_safe(p, q, &mesh_hash[i]) { - tbl->free_node(p, free_leafs); - atomic_dec(&tbl->entries); - } - spin_unlock(&tbl->hashwlock[i]); - } - __mesh_table_free(tbl); -} static void ieee80211_mesh_path_timer(unsigned long data) { @@ -357,63 +352,79 @@ static void ieee80211_mesh_path_timer(unsigned long data) return; } - ieee80211_queue_work(local->hw.workqueue, &ifmsh->work); + ieee80211_queue_work(&local->hw, &ifmsh->work); } -struct mesh_table *mesh_table_grow(struct mesh_table *tbl) -{ - struct mesh_table *newtbl; - struct hlist_head *oldhash; - struct hlist_node *p, *q; - int i; - - if (atomic_read(&tbl->entries) - < tbl->mean_chain_len * (tbl->hash_mask + 1)) - goto endgrow; - - newtbl = mesh_table_alloc(tbl->size_order + 1); - if (!newtbl) - goto endgrow; - - newtbl->free_node = tbl->free_node; - newtbl->mean_chain_len = tbl->mean_chain_len; - newtbl->copy_node = tbl->copy_node; - atomic_set(&newtbl->entries, atomic_read(&tbl->entries)); - - oldhash = tbl->hash_buckets; - for (i = 0; i <= tbl->hash_mask; i++) - hlist_for_each(p, &oldhash[i]) - if (tbl->copy_node(p, newtbl) < 0) - goto errcopy; - - return newtbl; - -errcopy: - for (i = 0; i <= newtbl->hash_mask; i++) { - hlist_for_each_safe(p, q, &newtbl->hash_buckets[i]) - tbl->free_node(p, 0); +/** + * ieee80211_fill_mesh_addresses - fill addresses of a locally originated mesh frame + * @hdr: 802.11 frame header + * @fc: frame control field + * @meshda: destination address in the mesh + * @meshsa: source address address in the mesh. Same as TA, as frame is + * locally originated. + * + * Return the length of the 802.11 (does not include a mesh control header) + */ +int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, char + *meshda, char *meshsa) { + if (is_multicast_ether_addr(meshda)) { + *fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); + /* DA TA SA */ + memcpy(hdr->addr1, meshda, ETH_ALEN); + memcpy(hdr->addr2, meshsa, ETH_ALEN); + memcpy(hdr->addr3, meshsa, ETH_ALEN); + return 24; + } else { + *fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | + IEEE80211_FCTL_TODS); + /* RA TA DA SA */ + memset(hdr->addr1, 0, ETH_ALEN); /* RA is resolved later */ + memcpy(hdr->addr2, meshsa, ETH_ALEN); + memcpy(hdr->addr3, meshda, ETH_ALEN); + memcpy(hdr->addr4, meshsa, ETH_ALEN); + return 30; } - __mesh_table_free(newtbl); -endgrow: - return NULL; } /** * ieee80211_new_mesh_header - create a new mesh header * @meshhdr: uninitialized mesh header * @sdata: mesh interface to be used + * @addr4: addr4 of the mesh frame (1st in ae header) + * may be NULL + * @addr5: addr5 of the mesh frame (1st or 2nd in ae header) + * may be NULL unless addr6 is present + * @addr6: addr6 of the mesh frame (2nd or 3rd in ae header) + * may be NULL unless addr5 is present * * Return the header length. */ int ieee80211_new_mesh_header(struct ieee80211s_hdr *meshhdr, - struct ieee80211_sub_if_data *sdata) + struct ieee80211_sub_if_data *sdata, char *addr4, + char *addr5, char *addr6) { - meshhdr->flags = 0; + int aelen = 0; + memset(meshhdr, 0, sizeof(meshhdr)); meshhdr->ttl = sdata->u.mesh.mshcfg.dot11MeshTTL; put_unaligned(cpu_to_le32(sdata->u.mesh.mesh_seqnum), &meshhdr->seqnum); sdata->u.mesh.mesh_seqnum++; - - return 6; + if (addr4) { + meshhdr->flags |= MESH_FLAGS_AE_A4; + aelen += ETH_ALEN; + memcpy(meshhdr->eaddr1, addr4, ETH_ALEN); + } + if (addr5 && addr6) { + meshhdr->flags |= MESH_FLAGS_AE_A5_A6; + aelen += 2 * ETH_ALEN; + if (!addr4) { + memcpy(meshhdr->eaddr1, addr5, ETH_ALEN); + memcpy(meshhdr->eaddr2, addr6, ETH_ALEN); + } else { + memcpy(meshhdr->eaddr2, addr5, ETH_ALEN); + memcpy(meshhdr->eaddr3, addr6, ETH_ALEN); + } + } + return 6 + aelen; } static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata, @@ -433,7 +444,6 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata, if (free_plinks != sdata->u.mesh.accepting_plinks) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); - ifmsh->housekeeping = false; mod_timer(&ifmsh->housekeeping_timer, round_jiffies(jiffies + IEEE80211_MESH_HOUSEKEEPING_INTERVAL)); } @@ -470,10 +480,12 @@ void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_local *local = sdata->local; - ifmsh->housekeeping = true; - ieee80211_queue_work(local->hw.workqueue, &ifmsh->work); + ifmsh->wrkq_flags |= MESH_WORK_HOUSEKEEPING; + ieee80211_queue_work(&local->hw, &ifmsh->work); + sdata->vif.bss_conf.beacon_int = MESH_DEFAULT_BEACON_INTERVAL; ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON | - BSS_CHANGED_BEACON_ENABLED); + BSS_CHANGED_BEACON_ENABLED | + BSS_CHANGED_BEACON_INT); } void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) @@ -608,7 +620,13 @@ static void ieee80211_mesh_work(struct work_struct *work) ifmsh->last_preq + msecs_to_jiffies(ifmsh->mshcfg.dot11MeshHWMPpreqMinInterval))) mesh_path_start_discovery(sdata); - if (ifmsh->housekeeping) + if (test_and_clear_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags)) + mesh_mpath_table_grow(); + + if (test_and_clear_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags)) + mesh_mpp_table_grow(); + + if (test_and_clear_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags)) ieee80211_mesh_housekeeping(sdata, ifmsh); } @@ -619,7 +637,7 @@ void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) rcu_read_lock(); list_for_each_entry_rcu(sdata, &local->interfaces, list) if (ieee80211_vif_is_mesh(&sdata->vif)) - ieee80211_queue_work(local->hw.workqueue, &sdata->u.mesh.work); + ieee80211_queue_work(&local->hw, &sdata->u.mesh.work); rcu_read_unlock(); } @@ -692,7 +710,7 @@ ieee80211_mesh_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) case IEEE80211_STYPE_PROBE_RESP: case IEEE80211_STYPE_BEACON: skb_queue_tail(&ifmsh->skb_queue, skb); - ieee80211_queue_work(local->hw.workqueue, &ifmsh->work); + ieee80211_queue_work(&local->hw, &ifmsh->work); return RX_QUEUED; } diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 2a2ed182cb7e..dd1c19319f0a 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -44,6 +44,23 @@ enum mesh_path_flags { }; /** + * enum mesh_deferred_task_flags - mac80211 mesh deferred tasks + * + * + * + * @MESH_WORK_HOUSEKEEPING: run the periodic mesh housekeeping tasks + * @MESH_WORK_GROW_MPATH_TABLE: the mesh path table is full and needs + * to grow. + * @MESH_WORK_GROW_MPP_TABLE: the mesh portals table is full and needs to + * grow + */ +enum mesh_deferred_task_flags { + MESH_WORK_HOUSEKEEPING, + MESH_WORK_GROW_MPATH_TABLE, + MESH_WORK_GROW_MPP_TABLE, +}; + +/** * struct mesh_path - mac80211 mesh path structure * * @dst: mesh path destination mac address @@ -61,7 +78,7 @@ enum mesh_path_flags { * retry * @discovery_retries: number of discovery retries * @flags: mesh path flags, as specified on &enum mesh_path_flags - * @state_lock: mesh pat state lock + * @state_lock: mesh path state lock * * * The combination of dst and sdata is unique in the mesh path table. Since the @@ -174,6 +191,7 @@ struct mesh_rmc { */ #define MESH_PATH_REFRESH_TIME 1000 #define MESH_MIN_DISCOVERY_TIMEOUT (2 * MESH_DIAM_TRAVERSAL_TIME) +#define MESH_DEFAULT_BEACON_INTERVAL 1000 /* in 1024 us units */ #define MESH_MAX_PREQ_RETRIES 4 #define MESH_PATH_EXPIRE (600 * HZ) @@ -193,8 +211,11 @@ struct mesh_rmc { /* Public interfaces */ /* Various */ +int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, + char *da, char *sa); int ieee80211_new_mesh_header(struct ieee80211s_hdr *meshhdr, - struct ieee80211_sub_if_data *sdata); + struct ieee80211_sub_if_data *sdata, char *addr4, + char *addr5, char *addr6); int mesh_rmc_check(u8 *addr, struct ieee80211s_hdr *mesh_hdr, struct ieee80211_sub_if_data *sdata); bool mesh_matches_local(struct ieee802_11_elems *ie, @@ -205,6 +226,8 @@ void mesh_mgmt_ies_add(struct sk_buff *skb, void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); +void ieee80211s_update_metric(struct ieee80211_local *local, + struct sta_info *stainfo, struct sk_buff *skb); void ieee80211s_stop(void); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); ieee80211_rx_result @@ -246,7 +269,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, /* Mesh tables */ struct mesh_table *mesh_table_alloc(int size_order); void mesh_table_free(struct mesh_table *tbl, bool free_leafs); -struct mesh_table *mesh_table_grow(struct mesh_table *tbl); +void mesh_mpath_table_grow(void); +void mesh_mpp_table_grow(void); u32 mesh_table_hash(u8 *addr, struct ieee80211_sub_if_data *sdata, struct mesh_table *tbl); /* Mesh paths */ @@ -265,6 +289,8 @@ void mesh_path_discard_frame(struct sk_buff *skb, void mesh_path_quiesce(struct ieee80211_sub_if_data *sdata); void mesh_path_restart(struct ieee80211_sub_if_data *sdata); +extern int mesh_paths_generation; + #ifdef CONFIG_MAC80211_MESH extern int mesh_allocated; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 11ab71a68ff9..e12a786e26b8 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -201,6 +201,24 @@ int mesh_path_error_tx(u8 *dst, __le32 dst_dsn, u8 *ra, return 0; } +void ieee80211s_update_metric(struct ieee80211_local *local, + struct sta_info *stainfo, struct sk_buff *skb) +{ + struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + int failed; + + if (!ieee80211_is_data(hdr->frame_control)) + return; + + failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK); + + /* moving average, scaled to 100 */ + stainfo->fail_avg = ((80 * stainfo->fail_avg + 5) / 100 + 20 * failed); + if (stainfo->fail_avg > 95) + mesh_plink_broken(stainfo); +} + static u32 airtime_link_metric_get(struct ieee80211_local *local, struct sta_info *sta) { @@ -397,7 +415,8 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, - u8 *preq_elem, u32 metric) { + u8 *preq_elem, u32 metric) +{ struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct mesh_path *mpath; u8 *dst_addr, *orig_addr; @@ -430,7 +449,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, if ((!(mpath->flags & MESH_PATH_DSN_VALID)) || DSN_LT(mpath->dsn, dst_dsn)) { mpath->dsn = dst_dsn; - mpath->flags &= MESH_PATH_DSN_VALID; + mpath->flags |= MESH_PATH_DSN_VALID; } else if ((!(dst_flags & MP_F_DO)) && (mpath->flags & MESH_PATH_ACTIVE)) { reply = true; @@ -478,6 +497,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, hopcount, ttl, cpu_to_le32(lifetime), cpu_to_le32(metric), cpu_to_le32(preq_id), sdata); + ifmsh->mshstats.fwded_mcast++; ifmsh->mshstats.fwded_frames++; } } @@ -536,6 +556,8 @@ static void hwmp_prep_frame_process(struct ieee80211_sub_if_data *sdata, cpu_to_le32(lifetime), cpu_to_le32(metric), 0, sdata); rcu_read_unlock(); + + sdata->u.mesh.mshstats.fwded_unicast++; sdata->u.mesh.mshstats.fwded_frames++; return; @@ -660,14 +682,14 @@ static void mesh_queue_preq(struct mesh_path *mpath, u8 flags) spin_unlock(&ifmsh->mesh_preq_queue_lock); if (time_after(jiffies, ifmsh->last_preq + min_preq_int_jiff(sdata))) - ieee80211_queue_work(sdata->local->hw.workqueue, &ifmsh->work); + ieee80211_queue_work(&sdata->local->hw, &ifmsh->work); else if (time_before(jiffies, ifmsh->last_preq)) { /* avoid long wait if did not send preqs for a long time * and jiffies wrapped around */ ifmsh->last_preq = jiffies - min_preq_int_jiff(sdata) - 1; - ieee80211_queue_work(sdata->local->hw.workqueue, &ifmsh->work); + ieee80211_queue_work(&sdata->local->hw, &ifmsh->work); } else mod_timer(&ifmsh->mesh_path_timer, ifmsh->last_preq + min_preq_int_jiff(sdata)); @@ -791,7 +813,7 @@ int mesh_nexthop_lookup(struct sk_buff *skb, } if (mpath->flags & MESH_PATH_ACTIVE) { - if (time_after(jiffies, mpath->exp_time - + if (time_after(jiffies, mpath->exp_time + msecs_to_jiffies(sdata->u.mesh.mshcfg.path_refresh_time)) && !memcmp(sdata->dev->dev_addr, hdr->addr4, ETH_ALEN) @@ -810,10 +832,8 @@ int mesh_nexthop_lookup(struct sk_buff *skb, } if (skb_queue_len(&mpath->frame_queue) >= - MESH_FRAME_QUEUE_LEN) { - skb_to_free = mpath->frame_queue.next; - skb_unlink(skb_to_free, &mpath->frame_queue); - } + MESH_FRAME_QUEUE_LEN) + skb_to_free = skb_dequeue(&mpath->frame_queue); info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; skb_queue_tail(&mpath->frame_queue, skb); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 04b9e4d61b8e..751c4d0e2b36 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -38,6 +38,71 @@ struct mpath_node { static struct mesh_table *mesh_paths; static struct mesh_table *mpp_paths; /* Store paths for MPP&MAP */ +int mesh_paths_generation; +static void __mesh_table_free(struct mesh_table *tbl) +{ + kfree(tbl->hash_buckets); + kfree(tbl->hashwlock); + kfree(tbl); +} + +void mesh_table_free(struct mesh_table *tbl, bool free_leafs) +{ + struct hlist_head *mesh_hash; + struct hlist_node *p, *q; + int i; + + mesh_hash = tbl->hash_buckets; + for (i = 0; i <= tbl->hash_mask; i++) { + spin_lock(&tbl->hashwlock[i]); + hlist_for_each_safe(p, q, &mesh_hash[i]) { + tbl->free_node(p, free_leafs); + atomic_dec(&tbl->entries); + } + spin_unlock(&tbl->hashwlock[i]); + } + __mesh_table_free(tbl); +} + +static struct mesh_table *mesh_table_grow(struct mesh_table *tbl) +{ + struct mesh_table *newtbl; + struct hlist_head *oldhash; + struct hlist_node *p, *q; + int i; + + if (atomic_read(&tbl->entries) + < tbl->mean_chain_len * (tbl->hash_mask + 1)) + goto endgrow; + + newtbl = mesh_table_alloc(tbl->size_order + 1); + if (!newtbl) + goto endgrow; + + newtbl->free_node = tbl->free_node; + newtbl->mean_chain_len = tbl->mean_chain_len; + newtbl->copy_node = tbl->copy_node; + atomic_set(&newtbl->entries, atomic_read(&tbl->entries)); + + oldhash = tbl->hash_buckets; + for (i = 0; i <= tbl->hash_mask; i++) + hlist_for_each(p, &oldhash[i]) + if (tbl->copy_node(p, newtbl) < 0) + goto errcopy; + + return newtbl; + +errcopy: + for (i = 0; i <= newtbl->hash_mask; i++) { + hlist_for_each_safe(p, q, &newtbl->hash_buckets[i]) + tbl->free_node(p, 0); + } + __mesh_table_free(newtbl); +endgrow: + return NULL; +} + + /* This lock will have the grow table function as writer and add / delete nodes * as readers. When reading the table (i.e. doing lookups) we are well protected * by RCU @@ -185,6 +250,8 @@ struct mesh_path *mesh_path_lookup_by_idx(int idx, struct ieee80211_sub_if_data */ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) { + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + struct ieee80211_local *local = sdata->local; struct mesh_path *mpath, *new_mpath; struct mpath_node *node, *new_node; struct hlist_head *bucket; @@ -193,8 +260,6 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) int err = 0; u32 hash_idx; - might_sleep(); - if (memcmp(dst, sdata->dev->dev_addr, ETH_ALEN) == 0) /* never add ourselves as neighbours */ return -ENOTSUPP; @@ -206,11 +271,11 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) return -ENOSPC; err = -ENOMEM; - new_mpath = kzalloc(sizeof(struct mesh_path), GFP_KERNEL); + new_mpath = kzalloc(sizeof(struct mesh_path), GFP_ATOMIC); if (!new_mpath) goto err_path_alloc; - new_node = kmalloc(sizeof(struct mpath_node), GFP_KERNEL); + new_node = kmalloc(sizeof(struct mpath_node), GFP_ATOMIC); if (!new_node) goto err_node_alloc; @@ -243,23 +308,13 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) mesh_paths->mean_chain_len * (mesh_paths->hash_mask + 1)) grow = 1; + mesh_paths_generation++; + spin_unlock(&mesh_paths->hashwlock[hash_idx]); read_unlock(&pathtbl_resize_lock); if (grow) { - struct mesh_table *oldtbl, *newtbl; - - write_lock(&pathtbl_resize_lock); - oldtbl = mesh_paths; - newtbl = mesh_table_grow(mesh_paths); - if (!newtbl) { - write_unlock(&pathtbl_resize_lock); - return 0; - } - rcu_assign_pointer(mesh_paths, newtbl); - write_unlock(&pathtbl_resize_lock); - - synchronize_rcu(); - mesh_table_free(oldtbl, false); + set_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags); + ieee80211_queue_work(&local->hw, &ifmsh->work); } return 0; @@ -274,9 +329,46 @@ err_path_alloc: return err; } +void mesh_mpath_table_grow(void) +{ + struct mesh_table *oldtbl, *newtbl; + + write_lock(&pathtbl_resize_lock); + oldtbl = mesh_paths; + newtbl = mesh_table_grow(mesh_paths); + if (!newtbl) { + write_unlock(&pathtbl_resize_lock); + return; + } + rcu_assign_pointer(mesh_paths, newtbl); + write_unlock(&pathtbl_resize_lock); + + synchronize_rcu(); + mesh_table_free(oldtbl, false); +} + +void mesh_mpp_table_grow(void) +{ + struct mesh_table *oldtbl, *newtbl; + + write_lock(&pathtbl_resize_lock); + oldtbl = mpp_paths; + newtbl = mesh_table_grow(mpp_paths); + if (!newtbl) { + write_unlock(&pathtbl_resize_lock); + return; + } + rcu_assign_pointer(mpp_paths, newtbl); + write_unlock(&pathtbl_resize_lock); + + synchronize_rcu(); + mesh_table_free(oldtbl, false); +} int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) { + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + struct ieee80211_local *local = sdata->local; struct mesh_path *mpath, *new_mpath; struct mpath_node *node, *new_node; struct hlist_head *bucket; @@ -285,8 +377,6 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) int err = 0; u32 hash_idx; - might_sleep(); - if (memcmp(dst, sdata->dev->dev_addr, ETH_ALEN) == 0) /* never add ourselves as neighbours */ return -ENOTSUPP; @@ -295,11 +385,11 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) return -ENOTSUPP; err = -ENOMEM; - new_mpath = kzalloc(sizeof(struct mesh_path), GFP_KERNEL); + new_mpath = kzalloc(sizeof(struct mesh_path), GFP_ATOMIC); if (!new_mpath) goto err_path_alloc; - new_node = kmalloc(sizeof(struct mpath_node), GFP_KERNEL); + new_node = kmalloc(sizeof(struct mpath_node), GFP_ATOMIC); if (!new_node) goto err_node_alloc; @@ -333,20 +423,8 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) spin_unlock(&mpp_paths->hashwlock[hash_idx]); read_unlock(&pathtbl_resize_lock); if (grow) { - struct mesh_table *oldtbl, *newtbl; - - write_lock(&pathtbl_resize_lock); - oldtbl = mpp_paths; - newtbl = mesh_table_grow(mpp_paths); - if (!newtbl) { - write_unlock(&pathtbl_resize_lock); - return 0; - } - rcu_assign_pointer(mpp_paths, newtbl); - write_unlock(&pathtbl_resize_lock); - - synchronize_rcu(); - mesh_table_free(oldtbl, false); + set_bit(MESH_WORK_GROW_MPP_TABLE, &ifmsh->wrkq_flags); + ieee80211_queue_work(&local->hw, &ifmsh->work); } return 0; @@ -484,6 +562,7 @@ int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata) err = -ENXIO; enddel: + mesh_paths_generation++; spin_unlock(&mesh_paths->hashwlock[hash_idx]); read_unlock(&pathtbl_resize_lock); return err; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index cb14253587f1..ffcbad75e09b 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -409,7 +409,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m baselen = (u8 *) mgmt->u.action.u.plink_action.variable - (u8 *) mgmt; if (mgmt->u.action.u.plink_action.action_code == PLINK_CONFIRM) { baseaddr += 4; - baselen -= 4; + baselen += 4; } ieee802_11_parse_elems(baseaddr, len - baselen, &elems); if (!elems.peer_link) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 6d5a1ee0445f..97a278a2f48e 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -880,10 +880,11 @@ static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, } static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, - struct ieee80211_bss *bss, + struct ieee80211_mgd_work *wk, u32 bss_info_changed) { struct ieee80211_local *local = sdata->local; + struct ieee80211_bss *bss = wk->bss; bss_info_changed |= BSS_CHANGED_ASSOC; /* set timing information */ @@ -896,6 +897,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, bss->cbss.capability, bss->has_erp_value, bss->erp_value); sdata->u.mgd.associated = bss; + sdata->u.mgd.old_associate_work = wk; memcpy(sdata->u.mgd.bssid, bss->cbss.bssid, ETH_ALEN); /* just to be sure */ @@ -1010,7 +1012,8 @@ ieee80211_authenticate(struct ieee80211_sub_if_data *sdata, return RX_MGMT_NONE; } -static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata) +static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, + bool deauth) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; @@ -1028,6 +1031,16 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata) ifmgd->associated = NULL; memset(ifmgd->bssid, 0, ETH_ALEN); + if (deauth) { + kfree(ifmgd->old_associate_work); + ifmgd->old_associate_work = NULL; + } else { + struct ieee80211_mgd_work *wk = ifmgd->old_associate_work; + + wk->state = IEEE80211_MGD_STATE_IDLE; + list_add(&wk->list, &ifmgd->work_list); + } + /* * we need to commit the associated = NULL change because the * scan code uses that to determine whether this iface should @@ -1345,7 +1358,7 @@ ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, sdata->dev->name, bssid, reason_code); if (!wk) { - ieee80211_set_disassoc(sdata); + ieee80211_set_disassoc(sdata, true); } else { list_del(&wk->list); kfree(wk); @@ -1378,7 +1391,7 @@ ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, printk(KERN_DEBUG "%s: disassociated (Reason: %u)\n", sdata->dev->name, reason_code); - ieee80211_set_disassoc(sdata); + ieee80211_set_disassoc(sdata, false); return RX_MGMT_CFG80211_DISASSOC; } @@ -1581,7 +1594,8 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, * ieee80211_set_associated() will tell the driver */ bss_conf->aid = aid; bss_conf->assoc_capability = capab_info; - ieee80211_set_associated(sdata, wk->bss, changed); + /* this will take ownership of wk */ + ieee80211_set_associated(sdata, wk, changed); /* * Start timer to probe the connection to the AP now. @@ -1590,7 +1604,6 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, ieee80211_sta_rx_notify(sdata, (struct ieee80211_hdr *)mgmt); mod_beacon_timer(sdata); - kfree(wk); return RX_MGMT_CFG80211_ASSOC; } @@ -2096,7 +2109,7 @@ static void ieee80211_sta_work(struct work_struct *work) printk(KERN_DEBUG "No probe response from AP %pM" " after %dms, disconnecting.\n", bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ); - ieee80211_set_disassoc(sdata); + ieee80211_set_disassoc(sdata, true); mutex_unlock(&ifmgd->mtx); /* * must be outside lock due to cfg80211, @@ -2110,25 +2123,9 @@ static void ieee80211_sta_work(struct work_struct *work) } } - list_for_each_entry(wk, &ifmgd->work_list, list) { - if (wk->state != IEEE80211_MGD_STATE_IDLE) { - anybusy = true; - break; - } - } ieee80211_recalc_idle(local); - if (!anybusy) { - mutex_unlock(&ifmgd->mtx); - - if (test_and_clear_bit(IEEE80211_STA_REQ_SCAN, &ifmgd->request)) - ieee80211_queue_delayed_work(&local->hw, - &local->scan_work, - round_jiffies_relative(0)); - return; - } - list_for_each_entry_safe(wk, tmp, &ifmgd->work_list, list) { if (time_is_after_jiffies(wk->timeout)) { /* @@ -2174,6 +2171,18 @@ static void ieee80211_sta_work(struct work_struct *work) } } + list_for_each_entry(wk, &ifmgd->work_list, list) { + if (wk->state != IEEE80211_MGD_STATE_IDLE) { + anybusy = true; + break; + } + } + if (!anybusy && + test_and_clear_bit(IEEE80211_STA_REQ_SCAN, &ifmgd->request)) + ieee80211_queue_delayed_work(&local->hw, + &local->scan_work, + round_jiffies_relative(0)); + mutex_unlock(&ifmgd->mtx); list_for_each_entry_safe(wk, tmp, &free_work, list) { @@ -2500,7 +2509,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, if (ifmgd->associated && &ifmgd->associated->cbss == req->bss) { bssid = req->bss->bssid; - ieee80211_set_disassoc(sdata); + ieee80211_set_disassoc(sdata, true); } else list_for_each_entry(wk, &ifmgd->work_list, list) { if (&wk->bss->cbss == req->bss) { bssid = req->bss->bssid; @@ -2552,7 +2561,7 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, return -ENOLINK; } - ieee80211_set_disassoc(sdata); + ieee80211_set_disassoc(sdata, false); mutex_unlock(&ifmgd->mtx); diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index a5d2f1fb4417..e535f1c988fe 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -107,17 +107,8 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) } /* stop hardware - this must stop RX */ - if (local->open_count) { - ieee80211_led_radio(local, false); - drv_stop(local); - } - - /* - * flush again, in case driver queued work -- it - * shouldn't be doing (or cancel everything in the - * stop callback) that but better safe than sorry. - */ - flush_workqueue(local->workqueue); + if (local->open_count) + ieee80211_stop_device(local); local->suspended = true; /* need suspended to be visible before quiescing is false */ diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index 869fe0ef951d..38bf4168fc3a 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -33,7 +33,6 @@ struct minstrel_rate { /* per-rate throughput */ u32 cur_tp; - u32 throughput; u64 succ_hist; u64 att_hist; diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c index 98f480708050..a715d9454f64 100644 --- a/net/mac80211/rc80211_minstrel_debugfs.c +++ b/net/mac80211/rc80211_minstrel_debugfs.c @@ -83,7 +83,7 @@ minstrel_stats_open(struct inode *inode, struct file *file) p += sprintf(p, "%3u%s", mr->bitrate / 2, (mr->bitrate & 1 ? ".5" : " ")); - tp = ((mr->cur_tp * 96) / 18000) >> 10; + tp = mr->cur_tp / ((18000 << 10) / 96); prob = mr->cur_prob / 18; eprob = mr->probability / 18; @@ -139,7 +139,7 @@ minstrel_stats_release(struct inode *inode, struct file *file) return 0; } -static struct file_operations minstrel_stat_fops = { +static const struct file_operations minstrel_stat_fops = { .owner = THIS_MODULE, .open = minstrel_stats_open, .read = minstrel_stats_read, diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c index 8c053be9dc24..699d3ed869c4 100644 --- a/net/mac80211/rc80211_pid_algo.c +++ b/net/mac80211/rc80211_pid_algo.c @@ -169,19 +169,9 @@ static void rate_control_pid_sample(struct rc_pid_info *pinfo, * still a good measurement and copy it. */ if (unlikely(spinfo->tx_num_xmit == 0)) pf = spinfo->last_pf; - else { - /* XXX: BAD HACK!!! */ - struct sta_info *si = container_of(sta, struct sta_info, sta); - + else pf = spinfo->tx_num_failed * 100 / spinfo->tx_num_xmit; - if (ieee80211_vif_is_mesh(&si->sdata->vif) && pf == 100) - mesh_plink_broken(si); - pf <<= RC_PID_ARITH_SHIFT; - si->fail_avg = ((pf + (spinfo->last_pf << 3)) / 9) - >> RC_PID_ARITH_SHIFT; - } - spinfo->tx_num_xmit = 0; spinfo->tx_num_failed = 0; @@ -311,7 +301,6 @@ rate_control_pid_rate_init(void *priv, struct ieee80211_supported_band *sband, struct rc_pid_sta_info *spinfo = priv_sta; struct rc_pid_info *pinfo = priv; struct rc_pid_rateinfo *rinfo = pinfo->rinfo; - struct sta_info *si; int i, j, tmp; bool s; @@ -348,9 +337,6 @@ rate_control_pid_rate_init(void *priv, struct ieee80211_supported_band *sband, } spinfo->txrate_idx = rate_lowest_index(sband, sta); - /* HACK */ - si = container_of(sta, struct sta_info, sta); - si->fail_avg = 0; } static void *rate_control_pid_alloc(struct ieee80211_hw *hw, diff --git a/net/mac80211/rc80211_pid_debugfs.c b/net/mac80211/rc80211_pid_debugfs.c index a08a9b530347..a59043fbb0ff 100644 --- a/net/mac80211/rc80211_pid_debugfs.c +++ b/net/mac80211/rc80211_pid_debugfs.c @@ -198,7 +198,7 @@ static ssize_t rate_control_pid_events_read(struct file *file, char __user *buf, #undef RC_PID_PRINT_BUF_SIZE -static struct file_operations rc_pid_fop_events = { +static const struct file_operations rc_pid_fop_events = { .owner = THIS_MODULE, .read = rate_control_pid_events_read, .poll = rate_control_pid_events_poll, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 25a669c86e14..c01588f9d453 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -489,12 +489,21 @@ ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; unsigned int hdrlen = ieee80211_hdrlen(hdr->frame_control); + char *dev_addr = rx->dev->dev_addr; if (ieee80211_is_data(hdr->frame_control)) { - if (!ieee80211_has_a4(hdr->frame_control)) - return RX_DROP_MONITOR; - if (memcmp(hdr->addr4, rx->dev->dev_addr, ETH_ALEN) == 0) - return RX_DROP_MONITOR; + if (is_multicast_ether_addr(hdr->addr1)) { + if (ieee80211_has_tods(hdr->frame_control) || + !ieee80211_has_fromds(hdr->frame_control)) + return RX_DROP_MONITOR; + if (memcmp(hdr->addr3, dev_addr, ETH_ALEN) == 0) + return RX_DROP_MONITOR; + } else { + if (!ieee80211_has_a4(hdr->frame_control)) + return RX_DROP_MONITOR; + if (memcmp(hdr->addr4, dev_addr, ETH_ALEN) == 0) + return RX_DROP_MONITOR; + } } /* If there is not an established peer link and this is not a peer link @@ -527,7 +536,7 @@ ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) if (ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && - mesh_rmc_check(hdr->addr4, msh_h_get(hdr, hdrlen), rx->sdata)) + mesh_rmc_check(hdr->addr3, msh_h_get(hdr, hdrlen), rx->sdata)) return RX_DROP_MONITOR; #undef msh_h_get @@ -1495,7 +1504,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) /* illegal frame */ return RX_DROP_MONITOR; - if (mesh_hdr->flags & MESH_FLAGS_AE_A5_A6){ + if (!is_multicast_ether_addr(hdr->addr1) && + (mesh_hdr->flags & MESH_FLAGS_AE_A5_A6)) { struct mesh_path *mppath; rcu_read_lock(); @@ -1512,7 +1522,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) rcu_read_unlock(); } - if (compare_ether_addr(rx->dev->dev_addr, hdr->addr3) == 0) + /* Frame has reached destination. Don't forward */ + if (!is_multicast_ether_addr(hdr->addr1) && + compare_ether_addr(rx->dev->dev_addr, hdr->addr3) == 0) return RX_CONTINUE; mesh_hdr->ttl--; @@ -1532,27 +1544,32 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) rx->dev->name); fwd_hdr = (struct ieee80211_hdr *) fwd_skb->data; - /* - * Save TA to addr1 to send TA a path error if a - * suitable next hop is not found - */ - memcpy(fwd_hdr->addr1, fwd_hdr->addr2, ETH_ALEN); memcpy(fwd_hdr->addr2, rx->dev->dev_addr, ETH_ALEN); info = IEEE80211_SKB_CB(fwd_skb); memset(info, 0, sizeof(*info)); info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; info->control.vif = &rx->sdata->vif; ieee80211_select_queue(local, fwd_skb); - if (is_multicast_ether_addr(fwd_hdr->addr3)) - memcpy(fwd_hdr->addr1, fwd_hdr->addr3, - ETH_ALEN); + if (is_multicast_ether_addr(fwd_hdr->addr1)) + IEEE80211_IFSTA_MESH_CTR_INC(&sdata->u.mesh, + fwded_mcast); else { - int err = mesh_nexthop_lookup(fwd_skb, sdata); + int err; + /* + * Save TA to addr1 to send TA a path error if a + * suitable next hop is not found + */ + memcpy(fwd_hdr->addr1, fwd_hdr->addr2, + ETH_ALEN); + err = mesh_nexthop_lookup(fwd_skb, sdata); /* Failed to immediately resolve next hop: * fwded frame was dropped or will be added * later to the pending skb queue. */ if (err) return RX_DROP_MONITOR; + + IEEE80211_IFSTA_MESH_CTR_INC(&sdata->u.mesh, + fwded_unicast); } IEEE80211_IFSTA_MESH_CTR_INC(&sdata->u.mesh, fwded_frames); @@ -1560,7 +1577,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) } } - if (is_multicast_ether_addr(hdr->addr3) || + if (is_multicast_ether_addr(hdr->addr1) || rx->dev->flags & IFF_PROMISC) return RX_CONTINUE; else @@ -2423,24 +2440,20 @@ static u8 ieee80211_rx_reorder_ampdu(struct ieee80211_local *local, * This is the receive path handler. It is called by a low level driver when an * 802.11 MPDU is received from the hardware. */ -void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) +void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_rate *rate = NULL; struct ieee80211_supported_band *sband; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - if (status->band < 0 || - status->band >= IEEE80211_NUM_BANDS) { - WARN_ON(1); - return; - } + if (WARN_ON(status->band < 0 || + status->band >= IEEE80211_NUM_BANDS)) + goto drop; sband = local->hw.wiphy->bands[status->band]; - if (!sband) { - WARN_ON(1); - return; - } + if (WARN_ON(!sband)) + goto drop; /* * If we're suspending, it is possible although not too likely @@ -2449,16 +2462,21 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) * that might, for example, cause stations to be added or other * driver callbacks be invoked. */ - if (unlikely(local->quiescing || local->suspended)) { - kfree_skb(skb); - return; - } + if (unlikely(local->quiescing || local->suspended)) + goto drop; + + /* + * The same happens when we're not even started, + * but that's worth a warning. + */ + if (WARN_ON(!local->started)) + goto drop; if (status->flag & RX_FLAG_HT) { /* rate_idx is MCS index */ if (WARN_ON(status->rate_idx < 0 || status->rate_idx >= 76)) - return; + goto drop; /* HT rates are not in the table - use the highest legacy rate * for now since other parts of mac80211 may not yet be fully * MCS aware. */ @@ -2466,7 +2484,7 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) } else { if (WARN_ON(status->rate_idx < 0 || status->rate_idx >= sband->n_bitrates)) - return; + goto drop; rate = &sband->bitrates[status->rate_idx]; } @@ -2505,8 +2523,12 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) __ieee80211_rx_handle_packet(hw, skb, rate); rcu_read_unlock(); + + return; + drop: + kfree_skb(skb); } -EXPORT_SYMBOL(__ieee80211_rx); +EXPORT_SYMBOL(ieee80211_rx); /* This is a version of the rx handler that can be called from hard irq * context. Post the skb on the queue and schedule the tasklet */ diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 244f53f3c8b4..039901109fa1 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -277,9 +277,10 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) if (test_bit(SCAN_HW_SCANNING, &local->scanning)) ieee80211_restore_scan_ies(local); - if (local->scan_req != &local->int_scan_req) + if (local->scan_req != local->int_scan_req) cfg80211_scan_done(local->scan_req, aborted); local->scan_req = NULL; + local->scan_sdata = NULL; was_hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning); local->scanning = 0; @@ -292,13 +293,7 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) if (was_hw_scan) goto done; - spin_lock_bh(&local->filter_lock); - local->filter_flags &= ~FIF_BCN_PRBRESP_PROMISC; - drv_configure_filter(local, FIF_BCN_PRBRESP_PROMISC, - &local->filter_flags, - local->mc_count, - local->mc_list); - spin_unlock_bh(&local->filter_lock); + ieee80211_configure_filter(local); drv_sw_scan_complete(local); @@ -376,13 +371,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; - spin_lock_bh(&local->filter_lock); - local->filter_flags |= FIF_BCN_PRBRESP_PROMISC; - drv_configure_filter(local, FIF_BCN_PRBRESP_PROMISC, - &local->filter_flags, - local->mc_count, - local->mc_list); - spin_unlock_bh(&local->filter_lock); + ieee80211_configure_filter(local); /* TODO: start scan as soon as all nullfunc frames are ACKed */ ieee80211_queue_delayed_work(&local->hw, @@ -423,7 +412,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, local->scan_req = req; local->scan_sdata = sdata; - if (req != &local->int_scan_req && + if (req != local->int_scan_req && sdata->vif.type == NL80211_IFTYPE_STATION && !list_empty(&ifmgd->work_list)) { /* actually wait for the work it's doing to finish/time out */ @@ -672,6 +661,7 @@ void ieee80211_scan_work(struct work_struct *work) int rc; local->scan_req = NULL; + local->scan_sdata = NULL; rc = __ieee80211_start_scan(sdata, req); mutex_unlock(&local->scan_mtx); @@ -743,10 +733,10 @@ int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, if (local->scan_req) goto unlock; - memcpy(local->int_scan_req.ssids[0].ssid, ssid, IEEE80211_MAX_SSID_LEN); - local->int_scan_req.ssids[0].ssid_len = ssid_len; + memcpy(local->int_scan_req->ssids[0].ssid, ssid, IEEE80211_MAX_SSID_LEN); + local->int_scan_req->ssids[0].ssid_len = ssid_len; - ret = __ieee80211_start_scan(sdata, &sdata->local->int_scan_req); + ret = __ieee80211_start_scan(sdata, sdata->local->int_scan_req); unlock: mutex_unlock(&local->scan_mtx); return ret; @@ -754,7 +744,7 @@ int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, void ieee80211_scan_cancel(struct ieee80211_local *local) { - bool swscan; + bool abortscan; cancel_delayed_work_sync(&local->scan_work); @@ -763,9 +753,10 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) * queued -- mostly at suspend under RTNL. */ mutex_lock(&local->scan_mtx); - swscan = test_bit(SCAN_SW_SCANNING, &local->scanning); + abortscan = test_bit(SCAN_SW_SCANNING, &local->scanning) || + (!local->scanning && local->scan_req); mutex_unlock(&local->scan_mtx); - if (swscan) + if (abortscan) ieee80211_scan_completed(&local->hw, true); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index a360bceeba59..eec001491e66 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -349,6 +349,7 @@ int sta_info_insert(struct sta_info *sta) goto out_free; } list_add(&sta->list, &local->sta_list); + local->sta_generation++; local->num_sta++; sta_info_hash_add(local, sta); @@ -485,6 +486,7 @@ static void __sta_info_unlink(struct sta_info **sta) } local->num_sta--; + local->sta_generation++; if (local->ops->sta_notify) { if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 7cffaa046b33..5143d203256b 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -317,30 +317,30 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (!atomic_read(&tx->sdata->bss->num_sta_ps)) return TX_CONTINUE; + /* buffered in hardware */ + if (!(tx->local->hw.flags & IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING)) { + info->flags |= IEEE80211_TX_CTL_SEND_AFTER_DTIM; + + return TX_CONTINUE; + } + /* buffered in mac80211 */ - if (tx->local->hw.flags & IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING) { - if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) - purge_old_ps_buffers(tx->local); - if (skb_queue_len(&tx->sdata->bss->ps_bc_buf) >= - AP_MAX_BC_BUFFER) { + if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) + purge_old_ps_buffers(tx->local); + + if (skb_queue_len(&tx->sdata->bss->ps_bc_buf) >= AP_MAX_BC_BUFFER) { #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: BC TX buffer full - " - "dropping the oldest frame\n", - tx->dev->name); - } + if (net_ratelimit()) + printk(KERN_DEBUG "%s: BC TX buffer full - dropping the oldest frame\n", + tx->dev->name); #endif - dev_kfree_skb(skb_dequeue(&tx->sdata->bss->ps_bc_buf)); - } else - tx->local->total_ps_buffered++; - skb_queue_tail(&tx->sdata->bss->ps_bc_buf, tx->skb); - return TX_QUEUED; - } + dev_kfree_skb(skb_dequeue(&tx->sdata->bss->ps_bc_buf)); + } else + tx->local->total_ps_buffered++; - /* buffered in hardware */ - info->flags |= IEEE80211_TX_CTL_SEND_AFTER_DTIM; + skb_queue_tail(&tx->sdata->bss->ps_bc_buf, tx->skb); - return TX_CONTINUE; + return TX_QUEUED; } static int ieee80211_use_mfp(__le16 fc, struct sta_info *sta, @@ -700,7 +700,6 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) /* for pure STA mode without beacons, we can do it */ hdr->seq_ctrl = cpu_to_le16(tx->sdata->sequence_number); tx->sdata->sequence_number += 0x10; - tx->sdata->sequence_number &= IEEE80211_SCTL_SEQ; return TX_CONTINUE; } @@ -844,6 +843,23 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) } static ieee80211_tx_result debug_noinline +ieee80211_tx_h_stats(struct ieee80211_tx_data *tx) +{ + struct sk_buff *skb = tx->skb; + + if (!tx->sta) + return TX_CONTINUE; + + tx->sta->tx_packets++; + do { + tx->sta->tx_fragments++; + tx->sta->tx_bytes += skb->len; + } while ((skb = skb->next)); + + return TX_CONTINUE; +} + +static ieee80211_tx_result debug_noinline ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx) { if (!tx->key) @@ -887,23 +903,6 @@ ieee80211_tx_h_calculate_duration(struct ieee80211_tx_data *tx) return TX_CONTINUE; } -static ieee80211_tx_result debug_noinline -ieee80211_tx_h_stats(struct ieee80211_tx_data *tx) -{ - struct sk_buff *skb = tx->skb; - - if (!tx->sta) - return TX_CONTINUE; - - tx->sta->tx_packets++; - do { - tx->sta->tx_fragments++; - tx->sta->tx_bytes += skb->len; - } while ((skb = skb->next)); - - return TX_CONTINUE; -} - /* actual transmit path */ /* @@ -1154,6 +1153,9 @@ static int __ieee80211_tx(struct ieee80211_local *local, next = skb->next; len = skb->len; + if (next) + info->flags |= IEEE80211_TX_CTL_MORE_FRAMES; + sdata = vif_to_sdata(info->control.vif); switch (sdata->vif.type) { @@ -1210,9 +1212,9 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx) CALL_TXH(ieee80211_tx_h_sequence) CALL_TXH(ieee80211_tx_h_fragment) /* handlers after fragment must be aware of tx info fragmentation! */ + CALL_TXH(ieee80211_tx_h_stats) CALL_TXH(ieee80211_tx_h_encrypt) CALL_TXH(ieee80211_tx_h_calculate_duration) - CALL_TXH(ieee80211_tx_h_stats) #undef CALL_TXH txh_done: @@ -1410,16 +1412,7 @@ static void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; - if (ieee80211_vif_is_mesh(&sdata->vif) && - ieee80211_is_data(hdr->frame_control)) { - if (is_multicast_ether_addr(hdr->addr3)) - memcpy(hdr->addr1, hdr->addr3, ETH_ALEN); - else - if (mesh_nexthop_lookup(skb, sdata)) { - dev_put(sdata->dev); - return; - } - } else if (unlikely(sdata->vif.type == NL80211_IFTYPE_MONITOR)) { + if (unlikely(sdata->vif.type == NL80211_IFTYPE_MONITOR)) { int hdrlen; u16 len_rthdr; @@ -1476,13 +1469,22 @@ static void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, info->control.vif = &sdata->vif; + if (ieee80211_vif_is_mesh(&sdata->vif) && + ieee80211_is_data(hdr->frame_control) && + !is_multicast_ether_addr(hdr->addr1)) + if (mesh_nexthop_lookup(skb, sdata)) { + /* skb queued: don't free */ + dev_put(sdata->dev); + return; + } + ieee80211_select_queue(local, skb); ieee80211_tx(sdata, skb, false); dev_put(sdata->dev); } -int ieee80211_monitor_start_xmit(struct sk_buff *skb, - struct net_device *dev) +netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, + struct net_device *dev) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_channel *chan = local->hw.conf.channel; @@ -1566,8 +1568,8 @@ fail: * encapsulated packet will then be passed to master interface, wlan#.11, for * transmission (through low-level driver). */ -int ieee80211_subif_start_xmit(struct sk_buff *skb, - struct net_device *dev) +netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, + struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -1617,52 +1619,58 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: - fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); if (!sdata->u.mesh.mshcfg.dot11MeshTTL) { /* Do not send frames with mesh_ttl == 0 */ sdata->u.mesh.mshstats.dropped_frames_ttl++; ret = NETDEV_TX_OK; goto fail; } - memset(&mesh_hdr, 0, sizeof(mesh_hdr)); if (compare_ether_addr(dev->dev_addr, skb->data + ETH_ALEN) == 0) { - /* RA TA DA SA */ - memset(hdr.addr1, 0, ETH_ALEN); - memcpy(hdr.addr2, dev->dev_addr, ETH_ALEN); - memcpy(hdr.addr3, skb->data, ETH_ALEN); - memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN); - meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata); + hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, + skb->data, skb->data + ETH_ALEN); + meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, + sdata, NULL, NULL, NULL); } else { /* packet from other interface */ struct mesh_path *mppath; + int is_mesh_mcast = 1; + char *mesh_da; - memset(hdr.addr1, 0, ETH_ALEN); - memcpy(hdr.addr2, dev->dev_addr, ETH_ALEN); - memcpy(hdr.addr4, dev->dev_addr, ETH_ALEN); - + rcu_read_lock(); if (is_multicast_ether_addr(skb->data)) - memcpy(hdr.addr3, skb->data, ETH_ALEN); + /* DA TA mSA AE:SA */ + mesh_da = skb->data; else { - rcu_read_lock(); mppath = mpp_path_lookup(skb->data, sdata); - if (mppath) - memcpy(hdr.addr3, mppath->mpp, ETH_ALEN); - else - memset(hdr.addr3, 0xff, ETH_ALEN); - rcu_read_unlock(); + if (mppath) { + /* RA TA mDA mSA AE:DA SA */ + mesh_da = mppath->mpp; + is_mesh_mcast = 0; + } else + /* DA TA mSA AE:SA */ + mesh_da = dev->broadcast; } + hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, + mesh_da, dev->dev_addr); + rcu_read_unlock(); + if (is_mesh_mcast) + meshhdrlen = + ieee80211_new_mesh_header(&mesh_hdr, + sdata, + skb->data + ETH_ALEN, + NULL, + NULL); + else + meshhdrlen = + ieee80211_new_mesh_header(&mesh_hdr, + sdata, + NULL, + skb->data, + skb->data + ETH_ALEN); - mesh_hdr.flags |= MESH_FLAGS_AE_A5_A6; - mesh_hdr.ttl = sdata->u.mesh.mshcfg.dot11MeshTTL; - put_unaligned(cpu_to_le32(sdata->u.mesh.mesh_seqnum), &mesh_hdr.seqnum); - memcpy(mesh_hdr.eaddr1, skb->data, ETH_ALEN); - memcpy(mesh_hdr.eaddr2, skb->data + ETH_ALEN, ETH_ALEN); - sdata->u.mesh.mesh_seqnum++; - meshhdrlen = 18; } - hdrlen = 30; break; #endif case NL80211_IFTYPE_STATION: diff --git a/net/mac80211/util.c b/net/mac80211/util.c index e55d57f559ec..dd6564321369 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1007,6 +1007,16 @@ u32 ieee80211_sta_get_rates(struct ieee80211_local *local, return supp_rates; } +void ieee80211_stop_device(struct ieee80211_local *local) +{ + ieee80211_led_radio(local, false); + + cancel_work_sync(&local->reconfig_filter); + drv_stop(local); + + flush_workqueue(local->workqueue); +} + int ieee80211_reconfig(struct ieee80211_local *local) { struct ieee80211_hw *hw = &local->hw; @@ -1076,9 +1086,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* reconfigure hardware */ ieee80211_hw_config(local, ~0); - spin_lock_bh(&local->filter_lock); ieee80211_configure_filter(local); - spin_unlock_bh(&local->filter_lock); /* Finally also reconfigure all the BSS information */ list_for_each_entry(sdata, &local->interfaces, list) { diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 43f5676b1af4..d80b8192e0d4 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -74,7 +74,7 @@ static unsigned int xt_rateest_tg(struct sk_buff *skb, const struct xt_target_param *par) { const struct xt_rateest_target_info *info = par->targinfo; - struct gnet_stats_basic *stats = &info->est->bstats; + struct gnet_stats_basic_packed *stats = &info->est->bstats; spin_lock_bh(&info->est->lock); stats->bytes += skb->len; diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c index 98fc190e8f0e..390b7d09fe51 100644 --- a/net/netfilter/xt_quota.c +++ b/net/netfilter/xt_quota.c @@ -52,7 +52,7 @@ static bool quota_mt_check(const struct xt_mtchk_param *par) q->master = kmalloc(sizeof(*q->master), GFP_KERNEL); if (q->master == NULL) - return -ENOMEM; + return false; q->master->quota = q->quota; return true; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 575c64341508..66f6ba0bab11 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -136,7 +136,7 @@ int genl_register_mc_group(struct genl_family *family, { int id; unsigned long *new_groups; - int err; + int err = 0; BUG_ON(grp->name[0] == '\0'); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ce51ce012cda..ce1a34b99c23 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -847,6 +847,7 @@ static int nr_getname(struct socket *sock, struct sockaddr *uaddr, sax->fsa_ax25.sax25_family = AF_NETROM; sax->fsa_ax25.sax25_ndigis = 1; sax->fsa_ax25.sax25_call = nr->user_addr; + memset(sax->fsa_digipeater, 0, sizeof(sax->fsa_digipeater)); sax->fsa_digipeater[0] = nr->dest_addr; *uaddr_len = sizeof(struct full_sockaddr_ax25); } else { diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index c7b7838a0519..7aa11b01b2e2 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -169,7 +169,7 @@ static int nr_close(struct net_device *dev) return 0; } -static int nr_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t nr_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_device_stats *stats = &dev->stats; unsigned int len = skb->len; diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index e943c16552a2..4eb1ac9a7679 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -630,23 +630,23 @@ out: return dev; } -static ax25_digi *nr_call_to_digi(int ndigis, ax25_address *digipeaters) +static ax25_digi *nr_call_to_digi(ax25_digi *digi, int ndigis, + ax25_address *digipeaters) { - static ax25_digi ax25_digi; int i; if (ndigis == 0) return NULL; for (i = 0; i < ndigis; i++) { - ax25_digi.calls[i] = digipeaters[i]; - ax25_digi.repeated[i] = 0; + digi->calls[i] = digipeaters[i]; + digi->repeated[i] = 0; } - ax25_digi.ndigi = ndigis; - ax25_digi.lastrepeat = -1; + digi->ndigi = ndigis; + digi->lastrepeat = -1; - return &ax25_digi; + return digi; } /* @@ -656,6 +656,7 @@ int nr_rt_ioctl(unsigned int cmd, void __user *arg) { struct nr_route_struct nr_route; struct net_device *dev; + ax25_digi digi; int ret; switch (cmd) { @@ -673,13 +674,15 @@ int nr_rt_ioctl(unsigned int cmd, void __user *arg) ret = nr_add_node(&nr_route.callsign, nr_route.mnemonic, &nr_route.neighbour, - nr_call_to_digi(nr_route.ndigis, nr_route.digipeaters), + nr_call_to_digi(&digi, nr_route.ndigis, + nr_route.digipeaters), dev, nr_route.quality, nr_route.obs_count); break; case NETROM_NEIGH: ret = nr_add_neigh(&nr_route.callsign, - nr_call_to_digi(nr_route.ndigis, nr_route.digipeaters), + nr_call_to_digi(&digi, nr_route.ndigis, + nr_route.digipeaters), dev, nr_route.quality); break; default: diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index 4667af51ed71..d183509d3fa6 100644 --- a/net/phonet/pep-gprs.c +++ b/net/phonet/pep-gprs.c @@ -183,7 +183,7 @@ static int gprs_close(struct net_device *dev) return 0; } -static int gprs_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t gprs_xmit(struct sk_buff *skb, struct net_device *dev) { struct gprs_dev *gp = netdev_priv(dev); struct sock *sk = gp->sk; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index aa1617a7f265..7a4ee397d2f7 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -413,6 +413,7 @@ found: } EXPORT_SYMBOL(pn_sock_get_port); +#ifdef CONFIG_PROC_FS static struct sock *pn_sock_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); @@ -498,7 +499,8 @@ static const struct seq_operations pn_sock_seq_ops = { static int pn_sock_open(struct inode *inode, struct file *file) { - return seq_open(file, &pn_sock_seq_ops); + return seq_open_net(inode, file, &pn_sock_seq_ops, + sizeof(struct seq_net_private)); } const struct file_operations pn_sock_seq_fops = { @@ -506,5 +508,6 @@ const struct file_operations pn_sock_seq_fops = { .open = pn_sock_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; +#endif diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 796773b5df9b..ec753b3ae72a 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -1,14 +1,28 @@ config RDS - tristate "Reliable Datagram Sockets (RDS) (EXPERIMENTAL)" - depends on INET && INFINIBAND_IPOIB && EXPERIMENTAL - depends on INFINIBAND && INFINIBAND_ADDR_TRANS + tristate "The RDS Protocol (EXPERIMENTAL)" + depends on INET && EXPERIMENTAL ---help--- - RDS provides reliable, sequenced delivery of datagrams - over Infiniband. + The RDS (Reliable Datagram Sockets) protocol provides reliable, + sequenced delivery of datagrams over Infiniband, iWARP, + or TCP. + +config RDS_RDMA + tristate "RDS over Infiniband and iWARP" + depends on RDS && INFINIBAND && INFINIBAND_ADDR_TRANS + ---help--- + Allow RDS to use Infiniband and iWARP as a transport. + This transport supports RDMA operations. + +config RDS_TCP + tristate "RDS over TCP" + depends on RDS + ---help--- + Allow RDS to use TCP as a transport. + This transport does not support RDMA operations. config RDS_DEBUG - bool "Debugging messages" + bool "RDS debugging messages" depends on RDS default n diff --git a/net/rds/Makefile b/net/rds/Makefile index 51f27585fa08..b46eca109688 100644 --- a/net/rds/Makefile +++ b/net/rds/Makefile @@ -1,13 +1,20 @@ obj-$(CONFIG_RDS) += rds.o rds-y := af_rds.o bind.o cong.o connection.o info.o message.o \ recv.o send.o stats.o sysctl.o threads.o transport.o \ - loop.o page.o rdma.o \ - rdma_transport.o \ + loop.o page.o rdma.o + +obj-$(CONFIG_RDS_RDMA) += rds_rdma.o +rds_rdma-objs := rdma_transport.o \ ib.o ib_cm.o ib_recv.o ib_ring.o ib_send.o ib_stats.o \ ib_sysctl.o ib_rdma.o \ iw.o iw_cm.o iw_recv.o iw_ring.o iw_send.o iw_stats.o \ iw_sysctl.o iw_rdma.o + +obj-$(CONFIG_RDS_TCP) += rds_tcp.o +rds_tcp-objs := tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \ + tcp_send.o tcp_stats.o + ifeq ($(CONFIG_RDS_DEBUG), y) EXTRA_CFLAGS += -DDEBUG endif diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index b11e7e527864..108ed2e671c5 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -39,7 +39,6 @@ #include "rds.h" #include "rdma.h" -#include "rdma_transport.h" /* this is just used for stats gathering :/ */ static DEFINE_SPINLOCK(rds_sock_lock); @@ -509,7 +508,6 @@ out: static void __exit rds_exit(void) { - rds_rdma_exit(); sock_unregister(rds_family_ops.family); proto_unregister(&rds_proto); rds_conn_exit(); @@ -549,14 +547,8 @@ static int __init rds_init(void) rds_info_register_func(RDS_INFO_SOCKETS, rds_sock_info); rds_info_register_func(RDS_INFO_RECV_MESSAGES, rds_sock_inc_info); - /* ib/iwarp transports currently compiled-in */ - ret = rds_rdma_init(); - if (ret) - goto out_sock; goto out; -out_sock: - sock_unregister(rds_family_ops.family); out_proto: proto_unregister(&rds_proto); out_stats: diff --git a/net/rds/bind.c b/net/rds/bind.c index c17cc39160ce..5d95fc007f1a 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -187,6 +187,9 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (trans == NULL) { ret = -EADDRNOTAVAIL; rds_remove_bound(rs); + if (printk_ratelimit()) + printk(KERN_INFO "RDS: rds_bind() could not find a transport, " + "load rds_tcp or rds_rdma?\n"); goto out; } diff --git a/net/rds/cong.c b/net/rds/cong.c index 710e4599d76c..dd2711df640b 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -254,6 +254,7 @@ void rds_cong_map_updated(struct rds_cong_map *map, uint64_t portmask) read_unlock_irqrestore(&rds_cong_monitor_lock, flags); } } +EXPORT_SYMBOL_GPL(rds_cong_map_updated); int rds_cong_updated_since(unsigned long *recent) { diff --git a/net/rds/connection.c b/net/rds/connection.c index b420a20d84fd..cc8b568c0c84 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -255,12 +255,14 @@ struct rds_connection *rds_conn_create(__be32 laddr, __be32 faddr, { return __rds_conn_create(laddr, faddr, trans, gfp, 0); } +EXPORT_SYMBOL_GPL(rds_conn_create); struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp) { return __rds_conn_create(laddr, faddr, trans, gfp, 1); } +EXPORT_SYMBOL_GPL(rds_conn_create_outgoing); void rds_conn_destroy(struct rds_connection *conn) { @@ -303,6 +305,7 @@ void rds_conn_destroy(struct rds_connection *conn) rds_conn_count--; } +EXPORT_SYMBOL_GPL(rds_conn_destroy); static void rds_conn_message_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, @@ -406,6 +409,7 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len, spin_unlock_irqrestore(&rds_conn_lock, flags); } +EXPORT_SYMBOL_GPL(rds_for_each_conn_info); static int rds_conn_info_visitor(struct rds_connection *conn, void *buffer) @@ -481,6 +485,7 @@ void rds_conn_drop(struct rds_connection *conn) atomic_set(&conn->c_state, RDS_CONN_ERROR); queue_work(rds_wq, &conn->c_down_w); } +EXPORT_SYMBOL_GPL(rds_conn_drop); /* * An error occurred on the connection diff --git a/net/rds/ib.c b/net/rds/ib.c index 868559ac42d7..536ebe5d3f6b 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -282,6 +282,7 @@ struct rds_transport rds_ib_transport = { .flush_mrs = rds_ib_flush_mrs, .t_owner = THIS_MODULE, .t_name = "infiniband", + .t_type = RDS_TRANS_IB }; int __init rds_ib_init(void) diff --git a/net/rds/info.c b/net/rds/info.c index 62aeef37aefe..814a91a6f4a7 100644 --- a/net/rds/info.c +++ b/net/rds/info.c @@ -79,6 +79,7 @@ void rds_info_register_func(int optname, rds_info_func func) rds_info_funcs[offset] = func; spin_unlock(&rds_info_lock); } +EXPORT_SYMBOL_GPL(rds_info_register_func); void rds_info_deregister_func(int optname, rds_info_func func) { @@ -91,6 +92,7 @@ void rds_info_deregister_func(int optname, rds_info_func func) rds_info_funcs[offset] = NULL; spin_unlock(&rds_info_lock); } +EXPORT_SYMBOL_GPL(rds_info_deregister_func); /* * Typically we hold an atomic kmap across multiple rds_info_copy() calls @@ -137,6 +139,7 @@ void rds_info_copy(struct rds_info_iterator *iter, void *data, } } } +EXPORT_SYMBOL_GPL(rds_info_copy); /* * @optval points to the userspace buffer that the information snapshot diff --git a/net/rds/iw.c b/net/rds/iw.c index f5e9a29a80a7..db224f7c2937 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -284,6 +284,7 @@ struct rds_transport rds_iw_transport = { .flush_mrs = rds_iw_flush_mrs, .t_owner = THIS_MODULE, .t_name = "iwarp", + .t_type = RDS_TRANS_IWARP, .t_prefer_loopback = 1, }; diff --git a/net/rds/message.c b/net/rds/message.c index 5a15dc8d0cd7..ca50a8ec9742 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -50,6 +50,7 @@ void rds_message_addref(struct rds_message *rm) rdsdebug("addref rm %p ref %d\n", rm, atomic_read(&rm->m_refcount)); atomic_inc(&rm->m_refcount); } +EXPORT_SYMBOL_GPL(rds_message_addref); /* * This relies on dma_map_sg() not touching sg[].page during merging. @@ -92,6 +93,7 @@ void rds_message_put(struct rds_message *rm) kfree(rm); } } +EXPORT_SYMBOL_GPL(rds_message_put); void rds_message_inc_free(struct rds_incoming *inc) { @@ -108,6 +110,7 @@ void rds_message_populate_header(struct rds_header *hdr, __be16 sport, hdr->h_sequence = cpu_to_be64(seq); hdr->h_exthdr[0] = RDS_EXTHDR_NONE; } +EXPORT_SYMBOL_GPL(rds_message_populate_header); int rds_message_add_extension(struct rds_header *hdr, unsigned int type, const void *data, unsigned int len) @@ -133,6 +136,7 @@ int rds_message_add_extension(struct rds_header *hdr, dst[len] = RDS_EXTHDR_NONE; return 1; } +EXPORT_SYMBOL_GPL(rds_message_add_extension); /* * If a message has extension headers, retrieve them here. @@ -208,6 +212,7 @@ int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 o ext_hdr.h_rdma_offset = cpu_to_be32(offset); return rds_message_add_extension(hdr, RDS_EXTHDR_RDMA_DEST, &ext_hdr, sizeof(ext_hdr)); } +EXPORT_SYMBOL_GPL(rds_message_add_rdma_dest_extension); struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp) { @@ -399,4 +404,5 @@ void rds_message_unmapped(struct rds_message *rm) if (waitqueue_active(&rds_message_flush_waitq)) wake_up(&rds_message_flush_waitq); } +EXPORT_SYMBOL_GPL(rds_message_unmapped); diff --git a/net/rds/page.c b/net/rds/page.c index c460743a89ad..55c21efdb62e 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -81,6 +81,7 @@ int rds_page_copy_user(struct page *page, unsigned long offset, return 0; } +EXPORT_SYMBOL_GPL(rds_page_copy_user); /* * Message allocation uses this to build up regions of a message. diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 7a6c748cb56c..9ece910ea394 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -203,6 +203,7 @@ err_iw_init: out: return ret; } +module_init(rds_rdma_init); void rds_rdma_exit(void) { @@ -211,4 +212,9 @@ void rds_rdma_exit(void) rds_ib_exit(); rds_iw_exit(); } +module_exit(rds_rdma_exit); + +MODULE_AUTHOR("Oracle Corporation <rds-devel@oss.oracle.com>"); +MODULE_DESCRIPTION("RDS: IB/iWARP transport"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/net/rds/rds.h b/net/rds/rds.h index 290566c69d28..85d6f897ecc7 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -311,11 +311,17 @@ struct rds_notifier { * flag and header. */ +#define RDS_TRANS_IB 0 +#define RDS_TRANS_IWARP 1 +#define RDS_TRANS_TCP 2 +#define RDS_TRANS_COUNT 3 + struct rds_transport { char t_name[TRANSNAMSIZ]; struct list_head t_item; struct module *t_owner; unsigned int t_prefer_loopback:1; + unsigned int t_type; int (*laddr_check)(__be32 addr); int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp); diff --git a/net/rds/recv.c b/net/rds/recv.c index 86bc1a06ebbd..fdff33c7b432 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -46,12 +46,14 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, inc->i_saddr = saddr; inc->i_rdma_cookie = 0; } +EXPORT_SYMBOL_GPL(rds_inc_init); void rds_inc_addref(struct rds_incoming *inc) { rdsdebug("addref inc %p ref %d\n", inc, atomic_read(&inc->i_refcount)); atomic_inc(&inc->i_refcount); } +EXPORT_SYMBOL_GPL(rds_inc_addref); void rds_inc_put(struct rds_incoming *inc) { @@ -62,6 +64,7 @@ void rds_inc_put(struct rds_incoming *inc) inc->i_conn->c_trans->inc_free(inc); } } +EXPORT_SYMBOL_GPL(rds_inc_put); static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk, struct rds_cong_map *map, @@ -237,6 +240,7 @@ out: if (rs) rds_sock_put(rs); } +EXPORT_SYMBOL_GPL(rds_recv_incoming); /* * be very careful here. This is being called as the condition in diff --git a/net/rds/send.c b/net/rds/send.c index a4a7f428cd76..28c88ff3d038 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -439,6 +439,7 @@ void rds_rdma_send_complete(struct rds_message *rm, int status) sock_put(rds_rs_to_sk(rs)); } } +EXPORT_SYMBOL_GPL(rds_rdma_send_complete); /* * This is the same as rds_rdma_send_complete except we @@ -494,6 +495,7 @@ out: return found; } +EXPORT_SYMBOL_GPL(rds_send_get_message); /* * This removes messages from the socket's list if they're on it. The list @@ -610,6 +612,7 @@ void rds_send_drop_acked(struct rds_connection *conn, u64 ack, /* now remove the messages from the sock list as needed */ rds_send_remove_from_sock(&list, RDS_RDMA_SUCCESS); } +EXPORT_SYMBOL_GPL(rds_send_drop_acked); void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) { diff --git a/net/rds/stats.c b/net/rds/stats.c index 91d8c58b8335..7598eb07cfb1 100644 --- a/net/rds/stats.c +++ b/net/rds/stats.c @@ -37,6 +37,7 @@ #include "rds.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); +EXPORT_PER_CPU_SYMBOL_GPL(rds_stats); /* :.,$s/unsigned long\>.*\<s_\(.*\);/"\1",/g */ @@ -90,6 +91,7 @@ void rds_stats_info_copy(struct rds_info_iterator *iter, rds_info_copy(iter, &ctr, sizeof(ctr)); } } +EXPORT_SYMBOL_GPL(rds_stats_info_copy); /* * This gives global counters across all the transports. The strings diff --git a/net/rds/tcp.c b/net/rds/tcp.c new file mode 100644 index 000000000000..b5198aee45d3 --- /dev/null +++ b/net/rds/tcp.c @@ -0,0 +1,320 @@ +/* + * Copyright (c) 2006 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#include <linux/kernel.h> +#include <linux/in.h> +#include <net/tcp.h> + +#include "rds.h" +#include "tcp.h" + +/* only for info exporting */ +static DEFINE_SPINLOCK(rds_tcp_tc_list_lock); +static LIST_HEAD(rds_tcp_tc_list); +unsigned int rds_tcp_tc_count; + +/* Track rds_tcp_connection structs so they can be cleaned up */ +static DEFINE_SPINLOCK(rds_tcp_conn_lock); +static LIST_HEAD(rds_tcp_conn_list); + +static struct kmem_cache *rds_tcp_conn_slab; + +#define RDS_TCP_DEFAULT_BUFSIZE (128 * 1024) + +/* doing it this way avoids calling tcp_sk() */ +void rds_tcp_nonagle(struct socket *sock) +{ + mm_segment_t oldfs = get_fs(); + int val = 1; + + set_fs(KERNEL_DS); + sock->ops->setsockopt(sock, SOL_TCP, TCP_NODELAY, (char __user *)&val, + sizeof(val)); + set_fs(oldfs); +} + +void rds_tcp_tune(struct socket *sock) +{ + struct sock *sk = sock->sk; + + rds_tcp_nonagle(sock); + + /* + * We're trying to saturate gigabit with the default, + * see svc_sock_setbufsize(). + */ + lock_sock(sk); + sk->sk_sndbuf = RDS_TCP_DEFAULT_BUFSIZE; + sk->sk_rcvbuf = RDS_TCP_DEFAULT_BUFSIZE; + sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK; + release_sock(sk); +} + +u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc) +{ + return tcp_sk(tc->t_sock->sk)->snd_nxt; +} + +u32 rds_tcp_snd_una(struct rds_tcp_connection *tc) +{ + return tcp_sk(tc->t_sock->sk)->snd_una; +} + +void rds_tcp_restore_callbacks(struct socket *sock, + struct rds_tcp_connection *tc) +{ + rdsdebug("restoring sock %p callbacks from tc %p\n", sock, tc); + write_lock_bh(&sock->sk->sk_callback_lock); + + /* done under the callback_lock to serialize with write_space */ + spin_lock(&rds_tcp_tc_list_lock); + list_del_init(&tc->t_list_item); + rds_tcp_tc_count--; + spin_unlock(&rds_tcp_tc_list_lock); + + tc->t_sock = NULL; + + sock->sk->sk_write_space = tc->t_orig_write_space; + sock->sk->sk_data_ready = tc->t_orig_data_ready; + sock->sk->sk_state_change = tc->t_orig_state_change; + sock->sk->sk_user_data = NULL; + + write_unlock_bh(&sock->sk->sk_callback_lock); +} + +/* + * This is the only path that sets tc->t_sock. Send and receive trust that + * it is set. The RDS_CONN_CONNECTED bit protects those paths from being + * called while it isn't set. + */ +void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn) +{ + struct rds_tcp_connection *tc = conn->c_transport_data; + + rdsdebug("setting sock %p callbacks to tc %p\n", sock, tc); + write_lock_bh(&sock->sk->sk_callback_lock); + + /* done under the callback_lock to serialize with write_space */ + spin_lock(&rds_tcp_tc_list_lock); + list_add_tail(&tc->t_list_item, &rds_tcp_tc_list); + rds_tcp_tc_count++; + spin_unlock(&rds_tcp_tc_list_lock); + + /* accepted sockets need our listen data ready undone */ + if (sock->sk->sk_data_ready == rds_tcp_listen_data_ready) + sock->sk->sk_data_ready = sock->sk->sk_user_data; + + tc->t_sock = sock; + tc->conn = conn; + tc->t_orig_data_ready = sock->sk->sk_data_ready; + tc->t_orig_write_space = sock->sk->sk_write_space; + tc->t_orig_state_change = sock->sk->sk_state_change; + + sock->sk->sk_user_data = conn; + sock->sk->sk_data_ready = rds_tcp_data_ready; + sock->sk->sk_write_space = rds_tcp_write_space; + sock->sk->sk_state_change = rds_tcp_state_change; + + write_unlock_bh(&sock->sk->sk_callback_lock); +} + +static void rds_tcp_tc_info(struct socket *sock, unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens) +{ + struct rds_info_tcp_socket tsinfo; + struct rds_tcp_connection *tc; + unsigned long flags; + struct sockaddr_in sin; + int sinlen; + + spin_lock_irqsave(&rds_tcp_tc_list_lock, flags); + + if (len / sizeof(tsinfo) < rds_tcp_tc_count) + goto out; + + list_for_each_entry(tc, &rds_tcp_tc_list, t_list_item) { + + sock->ops->getname(sock, (struct sockaddr *)&sin, &sinlen, 0); + tsinfo.local_addr = sin.sin_addr.s_addr; + tsinfo.local_port = sin.sin_port; + sock->ops->getname(sock, (struct sockaddr *)&sin, &sinlen, 1); + tsinfo.peer_addr = sin.sin_addr.s_addr; + tsinfo.peer_port = sin.sin_port; + + tsinfo.hdr_rem = tc->t_tinc_hdr_rem; + tsinfo.data_rem = tc->t_tinc_data_rem; + tsinfo.last_sent_nxt = tc->t_last_sent_nxt; + tsinfo.last_expected_una = tc->t_last_expected_una; + tsinfo.last_seen_una = tc->t_last_seen_una; + + rds_info_copy(iter, &tsinfo, sizeof(tsinfo)); + } + +out: + lens->nr = rds_tcp_tc_count; + lens->each = sizeof(tsinfo); + + spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); +} + +static int rds_tcp_laddr_check(__be32 addr) +{ + if (inet_addr_type(&init_net, addr) == RTN_LOCAL) + return 0; + return -EADDRNOTAVAIL; +} + +static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp) +{ + struct rds_tcp_connection *tc; + + tc = kmem_cache_alloc(rds_tcp_conn_slab, gfp); + if (tc == NULL) + return -ENOMEM; + + tc->t_sock = NULL; + tc->t_tinc = NULL; + tc->t_tinc_hdr_rem = sizeof(struct rds_header); + tc->t_tinc_data_rem = 0; + + conn->c_transport_data = tc; + + spin_lock_irq(&rds_tcp_conn_lock); + list_add_tail(&tc->t_tcp_node, &rds_tcp_conn_list); + spin_unlock_irq(&rds_tcp_conn_lock); + + rdsdebug("alloced tc %p\n", conn->c_transport_data); + return 0; +} + +static void rds_tcp_conn_free(void *arg) +{ + struct rds_tcp_connection *tc = arg; + rdsdebug("freeing tc %p\n", tc); + kmem_cache_free(rds_tcp_conn_slab, tc); +} + +static void rds_tcp_destroy_conns(void) +{ + struct rds_tcp_connection *tc, *_tc; + LIST_HEAD(tmp_list); + + /* avoid calling conn_destroy with irqs off */ + spin_lock_irq(&rds_tcp_conn_lock); + list_splice(&rds_tcp_conn_list, &tmp_list); + INIT_LIST_HEAD(&rds_tcp_conn_list); + spin_unlock_irq(&rds_tcp_conn_lock); + + list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) { + if (tc->conn->c_passive) + rds_conn_destroy(tc->conn->c_passive); + rds_conn_destroy(tc->conn); + } +} + +void rds_tcp_exit(void) +{ + rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); + rds_tcp_listen_stop(); + rds_tcp_destroy_conns(); + rds_trans_unregister(&rds_tcp_transport); + rds_tcp_recv_exit(); + kmem_cache_destroy(rds_tcp_conn_slab); +} +module_exit(rds_tcp_exit); + +struct rds_transport rds_tcp_transport = { + .laddr_check = rds_tcp_laddr_check, + .xmit_prepare = rds_tcp_xmit_prepare, + .xmit_complete = rds_tcp_xmit_complete, + .xmit_cong_map = rds_tcp_xmit_cong_map, + .xmit = rds_tcp_xmit, + .recv = rds_tcp_recv, + .conn_alloc = rds_tcp_conn_alloc, + .conn_free = rds_tcp_conn_free, + .conn_connect = rds_tcp_conn_connect, + .conn_shutdown = rds_tcp_conn_shutdown, + .inc_copy_to_user = rds_tcp_inc_copy_to_user, + .inc_purge = rds_tcp_inc_purge, + .inc_free = rds_tcp_inc_free, + .stats_info_copy = rds_tcp_stats_info_copy, + .exit = rds_tcp_exit, + .t_owner = THIS_MODULE, + .t_name = "tcp", + .t_type = RDS_TRANS_TCP, + .t_prefer_loopback = 1, +}; + +int __init rds_tcp_init(void) +{ + int ret; + + rds_tcp_conn_slab = kmem_cache_create("rds_tcp_connection", + sizeof(struct rds_tcp_connection), + 0, 0, NULL); + if (rds_tcp_conn_slab == NULL) { + ret = -ENOMEM; + goto out; + } + + ret = rds_tcp_recv_init(); + if (ret) + goto out_slab; + + ret = rds_trans_register(&rds_tcp_transport); + if (ret) + goto out_recv; + + ret = rds_tcp_listen_init(); + if (ret) + goto out_register; + + rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); + + goto out; + +out_register: + rds_trans_unregister(&rds_tcp_transport); +out_recv: + rds_tcp_recv_exit(); +out_slab: + kmem_cache_destroy(rds_tcp_conn_slab); +out: + return ret; +} +module_init(rds_tcp_init); + +MODULE_AUTHOR("Oracle Corporation <rds-devel@oss.oracle.com>"); +MODULE_DESCRIPTION("RDS: TCP transport"); +MODULE_LICENSE("Dual BSD/GPL"); + diff --git a/net/rds/tcp.h b/net/rds/tcp.h new file mode 100644 index 000000000000..844fa6b9cf5a --- /dev/null +++ b/net/rds/tcp.h @@ -0,0 +1,93 @@ +#ifndef _RDS_TCP_H +#define _RDS_TCP_H + +#define RDS_TCP_PORT 16385 + +struct rds_tcp_incoming { + struct rds_incoming ti_inc; + struct sk_buff_head ti_skb_list; +}; + +struct rds_tcp_connection { + + struct list_head t_tcp_node; + struct rds_connection *conn; + struct socket *t_sock; + void *t_orig_write_space; + void *t_orig_data_ready; + void *t_orig_state_change; + + struct rds_tcp_incoming *t_tinc; + size_t t_tinc_hdr_rem; + size_t t_tinc_data_rem; + + /* XXX error report? */ + struct work_struct t_conn_w; + struct work_struct t_send_w; + struct work_struct t_down_w; + struct work_struct t_recv_w; + + /* for info exporting only */ + struct list_head t_list_item; + u32 t_last_sent_nxt; + u32 t_last_expected_una; + u32 t_last_seen_una; +}; + +struct rds_tcp_statistics { + uint64_t s_tcp_data_ready_calls; + uint64_t s_tcp_write_space_calls; + uint64_t s_tcp_sndbuf_full; + uint64_t s_tcp_connect_raced; + uint64_t s_tcp_listen_closed_stale; +}; + +/* tcp.c */ +int __init rds_tcp_init(void); +void rds_tcp_exit(void); +void rds_tcp_tune(struct socket *sock); +void rds_tcp_nonagle(struct socket *sock); +void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn); +void rds_tcp_restore_callbacks(struct socket *sock, + struct rds_tcp_connection *tc); +u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc); +u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); +u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); +extern struct rds_transport rds_tcp_transport; + +/* tcp_connect.c */ +int rds_tcp_conn_connect(struct rds_connection *conn); +void rds_tcp_conn_shutdown(struct rds_connection *conn); +void rds_tcp_state_change(struct sock *sk); + +/* tcp_listen.c */ +int __init rds_tcp_listen_init(void); +void rds_tcp_listen_stop(void); +void rds_tcp_listen_data_ready(struct sock *sk, int bytes); + +/* tcp_recv.c */ +int __init rds_tcp_recv_init(void); +void rds_tcp_recv_exit(void); +void rds_tcp_data_ready(struct sock *sk, int bytes); +int rds_tcp_recv(struct rds_connection *conn); +void rds_tcp_inc_purge(struct rds_incoming *inc); +void rds_tcp_inc_free(struct rds_incoming *inc); +int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov, + size_t size); + +/* tcp_send.c */ +void rds_tcp_xmit_prepare(struct rds_connection *conn); +void rds_tcp_xmit_complete(struct rds_connection *conn); +int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, + unsigned int hdr_off, unsigned int sg, unsigned int off); +void rds_tcp_write_space(struct sock *sk); +int rds_tcp_xmit_cong_map(struct rds_connection *conn, + struct rds_cong_map *map, unsigned long offset); + +/* tcp_stats.c */ +DECLARE_PER_CPU(struct rds_tcp_statistics, rds_tcp_stats); +#define rds_tcp_stats_inc(member) rds_stats_inc_which(rds_tcp_stats, member) +unsigned int rds_tcp_stats_info_copy(struct rds_info_iterator *iter, + unsigned int avail); + +#endif diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c new file mode 100644 index 000000000000..211522f9a9a2 --- /dev/null +++ b/net/rds/tcp_connect.c @@ -0,0 +1,153 @@ +/* + * Copyright (c) 2006 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#include <linux/kernel.h> +#include <linux/in.h> +#include <net/tcp.h> + +#include "rds.h" +#include "tcp.h" + +void rds_tcp_state_change(struct sock *sk) +{ + void (*state_change)(struct sock *sk); + struct rds_connection *conn; + struct rds_tcp_connection *tc; + + read_lock(&sk->sk_callback_lock); + conn = sk->sk_user_data; + if (conn == NULL) { + state_change = sk->sk_state_change; + goto out; + } + tc = conn->c_transport_data; + state_change = tc->t_orig_state_change; + + rdsdebug("sock %p state_change to %d\n", tc->t_sock, sk->sk_state); + + switch(sk->sk_state) { + /* ignore connecting sockets as they make progress */ + case TCP_SYN_SENT: + case TCP_SYN_RECV: + break; + case TCP_ESTABLISHED: + rds_connect_complete(conn); + break; + case TCP_CLOSE: + rds_conn_drop(conn); + default: + break; + } +out: + read_unlock(&sk->sk_callback_lock); + state_change(sk); +} + +int rds_tcp_conn_connect(struct rds_connection *conn) +{ + struct socket *sock = NULL; + struct sockaddr_in src, dest; + int ret; + + ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + if (ret < 0) + goto out; + + rds_tcp_tune(sock); + + src.sin_family = AF_INET; + src.sin_addr.s_addr = (__force u32)conn->c_laddr; + src.sin_port = (__force u16)htons(0); + + ret = sock->ops->bind(sock, (struct sockaddr *)&src, sizeof(src)); + if (ret) { + rdsdebug("bind failed with %d at address %u.%u.%u.%u\n", + ret, NIPQUAD(conn->c_laddr)); + goto out; + } + + dest.sin_family = AF_INET; + dest.sin_addr.s_addr = (__force u32)conn->c_faddr; + dest.sin_port = (__force u16)htons(RDS_TCP_PORT); + + /* + * once we call connect() we can start getting callbacks and they + * own the socket + */ + rds_tcp_set_callbacks(sock, conn); + ret = sock->ops->connect(sock, (struct sockaddr *)&dest, sizeof(dest), + O_NONBLOCK); + sock = NULL; + + rdsdebug("connect to address %u.%u.%u.%u returned %d\n", + NIPQUAD(conn->c_faddr), ret); + if (ret == -EINPROGRESS) + ret = 0; + +out: + if (sock) + sock_release(sock); + return ret; +} + +/* + * Before killing the tcp socket this needs to serialize with callbacks. The + * caller has already grabbed the sending sem so we're serialized with other + * senders. + * + * TCP calls the callbacks with the sock lock so we hold it while we reset the + * callbacks to those set by TCP. Our callbacks won't execute again once we + * hold the sock lock. + */ +void rds_tcp_conn_shutdown(struct rds_connection *conn) +{ + struct rds_tcp_connection *tc = conn->c_transport_data; + struct socket *sock = tc->t_sock; + + rdsdebug("shutting down conn %p tc %p sock %p\n", conn, tc, sock); + + if (sock) { + sock->ops->shutdown(sock, RCV_SHUTDOWN | SEND_SHUTDOWN); + lock_sock(sock->sk); + rds_tcp_restore_callbacks(sock, tc); /* tc->tc_sock = NULL */ + + release_sock(sock->sk); + sock_release(sock); + }; + + if (tc->t_tinc) { + rds_inc_put(&tc->t_tinc->ti_inc); + tc->t_tinc = NULL; + } + tc->t_tinc_hdr_rem = sizeof(struct rds_header); + tc->t_tinc_data_rem = 0; +} diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c new file mode 100644 index 000000000000..24b743eb0b1b --- /dev/null +++ b/net/rds/tcp_listen.c @@ -0,0 +1,199 @@ +/* + * Copyright (c) 2006 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#include <linux/kernel.h> +#include <linux/in.h> +#include <net/tcp.h> + +#include "rds.h" +#include "tcp.h" + +/* + * cheesy, but simple.. + */ +static void rds_tcp_accept_worker(struct work_struct *work); +static DECLARE_WORK(rds_tcp_listen_work, rds_tcp_accept_worker); +static struct socket *rds_tcp_listen_sock; + +static int rds_tcp_accept_one(struct socket *sock) +{ + struct socket *new_sock = NULL; + struct rds_connection *conn; + int ret; + struct inet_sock *inet; + + ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type, + sock->sk->sk_protocol, &new_sock); + if (ret) + goto out; + + new_sock->type = sock->type; + new_sock->ops = sock->ops; + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + if (ret < 0) + goto out; + + rds_tcp_tune(new_sock); + + inet = inet_sk(new_sock->sk); + + rdsdebug("accepted tcp %u.%u.%u.%u:%u -> %u.%u.%u.%u:%u\n", + NIPQUAD(inet->saddr), ntohs(inet->sport), + NIPQUAD(inet->daddr), ntohs(inet->dport)); + + conn = rds_conn_create(inet->saddr, inet->daddr, &rds_tcp_transport, + GFP_KERNEL); + if (IS_ERR(conn)) { + ret = PTR_ERR(conn); + goto out; + } + + /* + * see the comment above rds_queue_delayed_reconnect() + */ + if (!rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING)) { + if (rds_conn_state(conn) == RDS_CONN_UP) + rds_tcp_stats_inc(s_tcp_listen_closed_stale); + else + rds_tcp_stats_inc(s_tcp_connect_raced); + rds_conn_drop(conn); + ret = 0; + goto out; + } + + rds_tcp_set_callbacks(new_sock, conn); + rds_connect_complete(conn); + new_sock = NULL; + ret = 0; + +out: + if (new_sock) + sock_release(new_sock); + return ret; +} + +static void rds_tcp_accept_worker(struct work_struct *work) +{ + while (rds_tcp_accept_one(rds_tcp_listen_sock) == 0) + cond_resched(); +} + +void rds_tcp_listen_data_ready(struct sock *sk, int bytes) +{ + void (*ready)(struct sock *sk, int bytes); + + rdsdebug("listen data ready sk %p\n", sk); + + read_lock(&sk->sk_callback_lock); + ready = sk->sk_user_data; + if (ready == NULL) { /* check for teardown race */ + ready = sk->sk_data_ready; + goto out; + } + + /* + * ->sk_data_ready is also called for a newly established child socket + * before it has been accepted and the accepter has set up their + * data_ready.. we only want to queue listen work for our listening + * socket + */ + if (sk->sk_state == TCP_LISTEN) + queue_work(rds_wq, &rds_tcp_listen_work); + +out: + read_unlock(&sk->sk_callback_lock); + ready(sk, bytes); +} + +int __init rds_tcp_listen_init(void) +{ + struct sockaddr_in sin; + struct socket *sock = NULL; + int ret; + + ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + if (ret < 0) + goto out; + + sock->sk->sk_reuse = 1; + rds_tcp_nonagle(sock); + + write_lock_bh(&sock->sk->sk_callback_lock); + sock->sk->sk_user_data = sock->sk->sk_data_ready; + sock->sk->sk_data_ready = rds_tcp_listen_data_ready; + write_unlock_bh(&sock->sk->sk_callback_lock); + + sin.sin_family = PF_INET, + sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY); + sin.sin_port = (__force u16)htons(RDS_TCP_PORT); + + ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin)); + if (ret < 0) + goto out; + + ret = sock->ops->listen(sock, 64); + if (ret < 0) + goto out; + + rds_tcp_listen_sock = sock; + sock = NULL; +out: + if (sock) + sock_release(sock); + return ret; +} + +void rds_tcp_listen_stop(void) +{ + struct socket *sock = rds_tcp_listen_sock; + struct sock *sk; + + if (sock == NULL) + return; + + sk = sock->sk; + + /* serialize with and prevent further callbacks */ + lock_sock(sk); + write_lock_bh(&sk->sk_callback_lock); + if (sk->sk_user_data) { + sk->sk_data_ready = sk->sk_user_data; + sk->sk_user_data = NULL; + } + write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); + + /* wait for accepts to stop and close the socket */ + flush_workqueue(rds_wq); + sock_release(sock); + rds_tcp_listen_sock = NULL; +} diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c new file mode 100644 index 000000000000..c00dafffbb5a --- /dev/null +++ b/net/rds/tcp_recv.c @@ -0,0 +1,356 @@ +/* + * Copyright (c) 2006 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#include <linux/kernel.h> +#include <net/tcp.h> + +#include "rds.h" +#include "tcp.h" + +static struct kmem_cache *rds_tcp_incoming_slab; + +void rds_tcp_inc_purge(struct rds_incoming *inc) +{ + struct rds_tcp_incoming *tinc; + tinc = container_of(inc, struct rds_tcp_incoming, ti_inc); + rdsdebug("purging tinc %p inc %p\n", tinc, inc); + skb_queue_purge(&tinc->ti_skb_list); +} + +void rds_tcp_inc_free(struct rds_incoming *inc) +{ + struct rds_tcp_incoming *tinc; + tinc = container_of(inc, struct rds_tcp_incoming, ti_inc); + rds_tcp_inc_purge(inc); + rdsdebug("freeing tinc %p inc %p\n", tinc, inc); + kmem_cache_free(rds_tcp_incoming_slab, tinc); +} + +/* + * this is pretty lame, but, whatever. + */ +int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iovec *first_iov, + size_t size) +{ + struct rds_tcp_incoming *tinc; + struct iovec *iov, tmp; + struct sk_buff *skb; + unsigned long to_copy, skb_off; + int ret = 0; + + if (size == 0) + goto out; + + tinc = container_of(inc, struct rds_tcp_incoming, ti_inc); + iov = first_iov; + tmp = *iov; + + skb_queue_walk(&tinc->ti_skb_list, skb) { + skb_off = 0; + while (skb_off < skb->len) { + while (tmp.iov_len == 0) { + iov++; + tmp = *iov; + } + + to_copy = min(tmp.iov_len, size); + to_copy = min(to_copy, skb->len - skb_off); + + rdsdebug("ret %d size %zu skb %p skb_off %lu " + "skblen %d iov_base %p iov_len %zu cpy %lu\n", + ret, size, skb, skb_off, skb->len, + tmp.iov_base, tmp.iov_len, to_copy); + + /* modifies tmp as it copies */ + if (skb_copy_datagram_iovec(skb, skb_off, &tmp, + to_copy)) { + ret = -EFAULT; + goto out; + } + + size -= to_copy; + ret += to_copy; + skb_off += to_copy; + if (size == 0) + goto out; + } + } +out: + return ret; +} + +/* + * We have a series of skbs that have fragmented pieces of the congestion + * bitmap. They must add up to the exact size of the congestion bitmap. We + * use the skb helpers to copy those into the pages that make up the in-memory + * congestion bitmap for the remote address of this connection. We then tell + * the congestion core that the bitmap has been changed so that it can wake up + * sleepers. + * + * This is racing with sending paths which are using test_bit to see if the + * bitmap indicates that their recipient is congested. + */ + +static void rds_tcp_cong_recv(struct rds_connection *conn, + struct rds_tcp_incoming *tinc) +{ + struct sk_buff *skb; + unsigned int to_copy, skb_off; + unsigned int map_off; + unsigned int map_page; + struct rds_cong_map *map; + int ret; + + /* catch completely corrupt packets */ + if (be32_to_cpu(tinc->ti_inc.i_hdr.h_len) != RDS_CONG_MAP_BYTES) + return; + + map_page = 0; + map_off = 0; + map = conn->c_fcong; + + skb_queue_walk(&tinc->ti_skb_list, skb) { + skb_off = 0; + while (skb_off < skb->len) { + to_copy = min_t(unsigned int, PAGE_SIZE - map_off, + skb->len - skb_off); + + BUG_ON(map_page >= RDS_CONG_MAP_PAGES); + + /* only returns 0 or -error */ + ret = skb_copy_bits(skb, skb_off, + (void *)map->m_page_addrs[map_page] + map_off, + to_copy); + BUG_ON(ret != 0); + + skb_off += to_copy; + map_off += to_copy; + if (map_off == PAGE_SIZE) { + map_off = 0; + map_page++; + } + } + } + + rds_cong_map_updated(map, ~(u64) 0); +} + +struct rds_tcp_desc_arg { + struct rds_connection *conn; + gfp_t gfp; + enum km_type km; +}; + +static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, + unsigned int offset, size_t len) +{ + struct rds_tcp_desc_arg *arg = desc->arg.data; + struct rds_connection *conn = arg->conn; + struct rds_tcp_connection *tc = conn->c_transport_data; + struct rds_tcp_incoming *tinc = tc->t_tinc; + struct sk_buff *clone; + size_t left = len, to_copy; + + rdsdebug("tcp data tc %p skb %p offset %u len %zu\n", tc, skb, offset, + len); + + /* + * tcp_read_sock() interprets partial progress as an indication to stop + * processing. + */ + while (left) { + if (tinc == NULL) { + tinc = kmem_cache_alloc(rds_tcp_incoming_slab, + arg->gfp); + if (tinc == NULL) { + desc->error = -ENOMEM; + goto out; + } + tc->t_tinc = tinc; + rdsdebug("alloced tinc %p\n", tinc); + rds_inc_init(&tinc->ti_inc, conn, conn->c_faddr); + /* + * XXX * we might be able to use the __ variants when + * we've already serialized at a higher level. + */ + skb_queue_head_init(&tinc->ti_skb_list); + } + + if (left && tc->t_tinc_hdr_rem) { + to_copy = min(tc->t_tinc_hdr_rem, left); + rdsdebug("copying %zu header from skb %p\n", to_copy, + skb); + skb_copy_bits(skb, offset, + (char *)&tinc->ti_inc.i_hdr + + sizeof(struct rds_header) - + tc->t_tinc_hdr_rem, + to_copy); + tc->t_tinc_hdr_rem -= to_copy; + left -= to_copy; + offset += to_copy; + + if (tc->t_tinc_hdr_rem == 0) { + /* could be 0 for a 0 len message */ + tc->t_tinc_data_rem = + be32_to_cpu(tinc->ti_inc.i_hdr.h_len); + } + } + + if (left && tc->t_tinc_data_rem) { + clone = skb_clone(skb, arg->gfp); + if (clone == NULL) { + desc->error = -ENOMEM; + goto out; + } + + to_copy = min(tc->t_tinc_data_rem, left); + pskb_pull(clone, offset); + pskb_trim(clone, to_copy); + skb_queue_tail(&tinc->ti_skb_list, clone); + + rdsdebug("skb %p data %p len %d off %u to_copy %zu -> " + "clone %p data %p len %d\n", + skb, skb->data, skb->len, offset, to_copy, + clone, clone->data, clone->len); + + tc->t_tinc_data_rem -= to_copy; + left -= to_copy; + offset += to_copy; + } + + if (tc->t_tinc_hdr_rem == 0 && tc->t_tinc_data_rem == 0) { + if (tinc->ti_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) + rds_tcp_cong_recv(conn, tinc); + else + rds_recv_incoming(conn, conn->c_faddr, + conn->c_laddr, &tinc->ti_inc, + arg->gfp, arg->km); + + tc->t_tinc_hdr_rem = sizeof(struct rds_header); + tc->t_tinc_data_rem = 0; + tc->t_tinc = NULL; + rds_inc_put(&tinc->ti_inc); + tinc = NULL; + } + } +out: + rdsdebug("returning len %zu left %zu skb len %d rx queue depth %d\n", + len, left, skb->len, + skb_queue_len(&tc->t_sock->sk->sk_receive_queue)); + return len - left; +} + +/* the caller has to hold the sock lock */ +int rds_tcp_read_sock(struct rds_connection *conn, gfp_t gfp, enum km_type km) +{ + struct rds_tcp_connection *tc = conn->c_transport_data; + struct socket *sock = tc->t_sock; + read_descriptor_t desc; + struct rds_tcp_desc_arg arg; + + /* It's like glib in the kernel! */ + arg.conn = conn; + arg.gfp = gfp; + arg.km = km; + desc.arg.data = &arg; + desc.error = 0; + desc.count = 1; /* give more than one skb per call */ + + tcp_read_sock(sock->sk, &desc, rds_tcp_data_recv); + rdsdebug("tcp_read_sock for tc %p gfp 0x%x returned %d\n", tc, gfp, + desc.error); + + return desc.error; +} + +/* + * We hold the sock lock to serialize our rds_tcp_recv->tcp_read_sock from + * data_ready. + * + * if we fail to allocate we're in trouble.. blindly wait some time before + * trying again to see if the VM can free up something for us. + */ +int rds_tcp_recv(struct rds_connection *conn) +{ + struct rds_tcp_connection *tc = conn->c_transport_data; + struct socket *sock = tc->t_sock; + int ret = 0; + + rdsdebug("recv worker conn %p tc %p sock %p\n", conn, tc, sock); + + lock_sock(sock->sk); + ret = rds_tcp_read_sock(conn, GFP_KERNEL, KM_USER0); + release_sock(sock->sk); + + return ret; +} + +void rds_tcp_data_ready(struct sock *sk, int bytes) +{ + void (*ready)(struct sock *sk, int bytes); + struct rds_connection *conn; + struct rds_tcp_connection *tc; + + rdsdebug("data ready sk %p bytes %d\n", sk, bytes); + + read_lock(&sk->sk_callback_lock); + conn = sk->sk_user_data; + if (conn == NULL) { /* check for teardown race */ + ready = sk->sk_data_ready; + goto out; + } + + tc = conn->c_transport_data; + ready = tc->t_orig_data_ready; + rds_tcp_stats_inc(s_tcp_data_ready_calls); + + if (rds_tcp_read_sock(conn, GFP_ATOMIC, KM_SOFTIRQ0) == -ENOMEM) + queue_delayed_work(rds_wq, &conn->c_recv_w, 0); +out: + read_unlock(&sk->sk_callback_lock); + ready(sk, bytes); +} + +int __init rds_tcp_recv_init(void) +{ + rds_tcp_incoming_slab = kmem_cache_create("rds_tcp_incoming", + sizeof(struct rds_tcp_incoming), + 0, 0, NULL); + if (rds_tcp_incoming_slab == NULL) + return -ENOMEM; + return 0; +} + +void rds_tcp_recv_exit(void) +{ + kmem_cache_destroy(rds_tcp_incoming_slab); +} diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c new file mode 100644 index 000000000000..ab545e0cd5d6 --- /dev/null +++ b/net/rds/tcp_send.c @@ -0,0 +1,263 @@ +/* + * Copyright (c) 2006 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#include <linux/kernel.h> +#include <linux/in.h> +#include <net/tcp.h> + +#include "rds.h" +#include "tcp.h" + +static void rds_tcp_cork(struct socket *sock, int val) +{ + mm_segment_t oldfs; + + oldfs = get_fs(); + set_fs(KERNEL_DS); + sock->ops->setsockopt(sock, SOL_TCP, TCP_CORK, (char __user *)&val, + sizeof(val)); + set_fs(oldfs); +} + +void rds_tcp_xmit_prepare(struct rds_connection *conn) +{ + struct rds_tcp_connection *tc = conn->c_transport_data; + + rds_tcp_cork(tc->t_sock, 1); +} + +void rds_tcp_xmit_complete(struct rds_connection *conn) +{ + struct rds_tcp_connection *tc = conn->c_transport_data; + + rds_tcp_cork(tc->t_sock, 0); +} + +/* the core send_sem serializes this with other xmit and shutdown */ +int rds_tcp_sendmsg(struct socket *sock, void *data, unsigned int len) +{ + struct kvec vec = { + .iov_base = data, + .iov_len = len, + }; + struct msghdr msg = { + .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL, + }; + + return kernel_sendmsg(sock, &msg, &vec, 1, vec.iov_len); +} + +/* the core send_sem serializes this with other xmit and shutdown */ +int rds_tcp_xmit_cong_map(struct rds_connection *conn, + struct rds_cong_map *map, unsigned long offset) +{ + static struct rds_header rds_tcp_map_header = { + .h_flags = RDS_FLAG_CONG_BITMAP, + }; + struct rds_tcp_connection *tc = conn->c_transport_data; + unsigned long i; + int ret; + int copied = 0; + + /* Some problem claims cpu_to_be32(constant) isn't a constant. */ + rds_tcp_map_header.h_len = cpu_to_be32(RDS_CONG_MAP_BYTES); + + if (offset < sizeof(struct rds_header)) { + ret = rds_tcp_sendmsg(tc->t_sock, + (void *)&rds_tcp_map_header + offset, + sizeof(struct rds_header) - offset); + if (ret <= 0) + return ret; + offset += ret; + copied = ret; + if (offset < sizeof(struct rds_header)) + return ret; + } + + offset -= sizeof(struct rds_header); + i = offset / PAGE_SIZE; + offset = offset % PAGE_SIZE; + BUG_ON(i >= RDS_CONG_MAP_PAGES); + + do { + ret = tc->t_sock->ops->sendpage(tc->t_sock, + virt_to_page(map->m_page_addrs[i]), + offset, PAGE_SIZE - offset, + MSG_DONTWAIT); + if (ret <= 0) + break; + copied += ret; + offset += ret; + if (offset == PAGE_SIZE) { + offset = 0; + i++; + } + } while (i < RDS_CONG_MAP_PAGES); + + return copied ? copied : ret; +} + +/* the core send_sem serializes this with other xmit and shutdown */ +int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm, + unsigned int hdr_off, unsigned int sg, unsigned int off) +{ + struct rds_tcp_connection *tc = conn->c_transport_data; + int done = 0; + int ret = 0; + + if (hdr_off == 0) { + /* + * m_ack_seq is set to the sequence number of the last byte of + * header and data. see rds_tcp_is_acked(). + */ + tc->t_last_sent_nxt = rds_tcp_snd_nxt(tc); + rm->m_ack_seq = tc->t_last_sent_nxt + + sizeof(struct rds_header) + + be32_to_cpu(rm->m_inc.i_hdr.h_len) - 1; + smp_mb__before_clear_bit(); + set_bit(RDS_MSG_HAS_ACK_SEQ, &rm->m_flags); + tc->t_last_expected_una = rm->m_ack_seq + 1; + + rdsdebug("rm %p tcp nxt %u ack_seq %llu\n", + rm, rds_tcp_snd_nxt(tc), + (unsigned long long)rm->m_ack_seq); + } + + if (hdr_off < sizeof(struct rds_header)) { + /* see rds_tcp_write_space() */ + set_bit(SOCK_NOSPACE, &tc->t_sock->sk->sk_socket->flags); + + ret = rds_tcp_sendmsg(tc->t_sock, + (void *)&rm->m_inc.i_hdr + hdr_off, + sizeof(rm->m_inc.i_hdr) - hdr_off); + if (ret < 0) + goto out; + done += ret; + if (hdr_off + done != sizeof(struct rds_header)) + goto out; + } + + while (sg < rm->m_nents) { + ret = tc->t_sock->ops->sendpage(tc->t_sock, + sg_page(&rm->m_sg[sg]), + rm->m_sg[sg].offset + off, + rm->m_sg[sg].length - off, + MSG_DONTWAIT|MSG_NOSIGNAL); + rdsdebug("tcp sendpage %p:%u:%u ret %d\n", (void *)sg_page(&rm->m_sg[sg]), + rm->m_sg[sg].offset + off, rm->m_sg[sg].length - off, + ret); + if (ret <= 0) + break; + + off += ret; + done += ret; + if (off == rm->m_sg[sg].length) { + off = 0; + sg++; + } + } + +out: + if (ret <= 0) { + /* write_space will hit after EAGAIN, all else fatal */ + if (ret == -EAGAIN) { + rds_tcp_stats_inc(s_tcp_sndbuf_full); + ret = 0; + } else { + printk(KERN_WARNING "RDS/tcp: send to %u.%u.%u.%u " + "returned %d, disconnecting and reconnecting\n", + NIPQUAD(conn->c_faddr), ret); + rds_conn_drop(conn); + } + } + if (done == 0) + done = ret; + return done; +} + +/* + * rm->m_ack_seq is set to the tcp sequence number that corresponds to the + * last byte of the message, including the header. This means that the + * entire message has been received if rm->m_ack_seq is "before" the next + * unacked byte of the TCP sequence space. We have to do very careful + * wrapping 32bit comparisons here. + */ +static int rds_tcp_is_acked(struct rds_message *rm, uint64_t ack) +{ + if (!test_bit(RDS_MSG_HAS_ACK_SEQ, &rm->m_flags)) + return 0; + return (__s32)((u32)rm->m_ack_seq - (u32)ack) < 0; +} + +void rds_tcp_write_space(struct sock *sk) +{ + void (*write_space)(struct sock *sk); + struct rds_connection *conn; + struct rds_tcp_connection *tc; + + read_lock(&sk->sk_callback_lock); + conn = sk->sk_user_data; + if (conn == NULL) { + write_space = sk->sk_write_space; + goto out; + } + + tc = conn->c_transport_data; + rdsdebug("write_space for tc %p\n", tc); + write_space = tc->t_orig_write_space; + rds_tcp_stats_inc(s_tcp_write_space_calls); + + rdsdebug("tcp una %u\n", rds_tcp_snd_una(tc)); + tc->t_last_seen_una = rds_tcp_snd_una(tc); + rds_send_drop_acked(conn, rds_tcp_snd_una(tc), rds_tcp_is_acked); + + queue_delayed_work(rds_wq, &conn->c_send_w, 0); +out: + read_unlock(&sk->sk_callback_lock); + + /* + * write_space is only called when data leaves tcp's send queue if + * SOCK_NOSPACE is set. We set SOCK_NOSPACE every time we put + * data in tcp's send queue because we use write_space to parse the + * sequence numbers and notice that rds messages have been fully + * received. + * + * tcp's write_space clears SOCK_NOSPACE if the send queue has more + * than a certain amount of space. So we need to set it again *after* + * we call tcp's write_space or else we might only get called on the + * first of a series of incoming tcp acks. + */ + write_space(sk); + + if (sk->sk_socket) + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +} diff --git a/net/rds/tcp_stats.c b/net/rds/tcp_stats.c new file mode 100644 index 000000000000..d5898d03cd68 --- /dev/null +++ b/net/rds/tcp_stats.c @@ -0,0 +1,74 @@ +/* + * Copyright (c) 2006 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#include <linux/percpu.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> + +#include "rds.h" +#include "tcp.h" + +DEFINE_PER_CPU(struct rds_tcp_statistics, rds_tcp_stats) + ____cacheline_aligned; + +static const char const *rds_tcp_stat_names[] = { + "tcp_data_ready_calls", + "tcp_write_space_calls", + "tcp_sndbuf_full", + "tcp_connect_raced", + "tcp_listen_closed_stale", +}; + +unsigned int rds_tcp_stats_info_copy(struct rds_info_iterator *iter, + unsigned int avail) +{ + struct rds_tcp_statistics stats = {0, }; + uint64_t *src; + uint64_t *sum; + size_t i; + int cpu; + + if (avail < ARRAY_SIZE(rds_tcp_stat_names)) + goto out; + + for_each_online_cpu(cpu) { + src = (uint64_t *)&(per_cpu(rds_tcp_stats, cpu)); + sum = (uint64_t *)&stats; + for (i = 0; i < sizeof(stats) / sizeof(uint64_t); i++) + *(sum++) += *(src++); + } + + rds_stats_info_copy(iter, (uint64_t *)&stats, rds_tcp_stat_names, + ARRAY_SIZE(rds_tcp_stat_names)); +out: + return ARRAY_SIZE(rds_tcp_stat_names); +} diff --git a/net/rds/threads.c b/net/rds/threads.c index 828a1bf9ea92..dd7e0cad1e7c 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -68,6 +68,7 @@ * (TCP, IB/RDMA) to provide the necessary synchronisation. */ struct workqueue_struct *rds_wq; +EXPORT_SYMBOL_GPL(rds_wq); void rds_connect_complete(struct rds_connection *conn) { @@ -89,6 +90,7 @@ void rds_connect_complete(struct rds_connection *conn) queue_delayed_work(rds_wq, &conn->c_send_w, 0); queue_delayed_work(rds_wq, &conn->c_recv_w, 0); } +EXPORT_SYMBOL_GPL(rds_connect_complete); /* * This random exponential backoff is relied on to eventually resolve racing diff --git a/net/rds/transport.c b/net/rds/transport.c index 767da61ad2f3..7e1067901353 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -37,7 +37,7 @@ #include "rds.h" #include "loop.h" -static LIST_HEAD(rds_transports); +static struct rds_transport *transports[RDS_TRANS_COUNT]; static DECLARE_RWSEM(rds_trans_sem); int rds_trans_register(struct rds_transport *trans) @@ -46,36 +46,44 @@ int rds_trans_register(struct rds_transport *trans) down_write(&rds_trans_sem); - list_add_tail(&trans->t_item, &rds_transports); - printk(KERN_INFO "Registered RDS/%s transport\n", trans->t_name); + if (transports[trans->t_type]) + printk(KERN_ERR "RDS Transport type %d already registered\n", + trans->t_type); + else { + transports[trans->t_type] = trans; + printk(KERN_INFO "Registered RDS/%s transport\n", trans->t_name); + } up_write(&rds_trans_sem); return 0; } +EXPORT_SYMBOL_GPL(rds_trans_register); void rds_trans_unregister(struct rds_transport *trans) { down_write(&rds_trans_sem); - list_del_init(&trans->t_item); + transports[trans->t_type] = NULL; printk(KERN_INFO "Unregistered RDS/%s transport\n", trans->t_name); up_write(&rds_trans_sem); } +EXPORT_SYMBOL_GPL(rds_trans_unregister); struct rds_transport *rds_trans_get_preferred(__be32 addr) { - struct rds_transport *trans; struct rds_transport *ret = NULL; + int i; if (IN_LOOPBACK(ntohl(addr))) return &rds_loop_transport; down_read(&rds_trans_sem); - list_for_each_entry(trans, &rds_transports, t_item) { - if (trans->laddr_check(addr) == 0) { - ret = trans; + for (i = 0; i < RDS_TRANS_COUNT; i++) + { + if (transports[i] && (transports[i]->laddr_check(addr) == 0)) { + ret = transports[i]; break; } } @@ -97,12 +105,15 @@ unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, struct rds_transport *trans; unsigned int total = 0; unsigned int part; + int i; rds_info_iter_unmap(iter); down_read(&rds_trans_sem); - list_for_each_entry(trans, &rds_transports, t_item) { - if (trans->stats_info_copy == NULL) + for (i = 0; i < RDS_TRANS_COUNT; i++) + { + trans = transports[i]; + if (!trans || !trans->stats_info_copy) continue; part = trans->stats_info_copy(iter, avail); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index f0a76f6bca71..e5f478ca3d61 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -954,6 +954,7 @@ static int rose_getname(struct socket *sock, struct sockaddr *uaddr, struct rose_sock *rose = rose_sk(sk); int n; + memset(srose, 0, sizeof(*srose)); if (peer != 0) { if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c index c711e2edf5ce..424b893d1450 100644 --- a/net/rose/rose_dev.c +++ b/net/rose/rose_dev.c @@ -131,7 +131,7 @@ static int rose_close(struct net_device *dev) return 0; } -static int rose_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t rose_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_device_stats *stats = &dev->stats; diff --git a/net/sched/Makefile b/net/sched/Makefile index 54d950cd4b8d..f14e71bfa58f 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -2,7 +2,7 @@ # Makefile for the Linux Traffic Control Unit. # -obj-y := sch_generic.o +obj-y := sch_generic.o sch_mq.o obj-$(CONFIG_NET_SCHED) += sch_api.o sch_blackhole.o obj-$(CONFIG_NET_CLS) += cls_api.o diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 09cdcdfe7e91..6a536949cdc0 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -168,8 +168,7 @@ replay: /* Find qdisc */ if (!parent) { - struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0); - q = dev_queue->qdisc_sleeping; + q = dev->qdisc; parent = q->handle; } else { q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent)); @@ -181,6 +180,9 @@ replay: if ((cops = q->ops->cl_ops) == NULL) return -EINVAL; + if (cops->tcf_chain == NULL) + return -EOPNOTSUPP; + /* Do we search for filter, attached to class? */ if (TC_H_MIN(parent)) { cl = cops->get(q, parent); @@ -405,7 +407,6 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - struct netdev_queue *dev_queue; int t; int s_t; struct net_device *dev; @@ -424,15 +425,16 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if ((dev = dev_get_by_index(&init_net, tcm->tcm_ifindex)) == NULL) return skb->len; - dev_queue = netdev_get_tx_queue(dev, 0); if (!tcm->tcm_parent) - q = dev_queue->qdisc_sleeping; + q = dev->qdisc; else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); if (!q) goto out; if ((cops = q->ops->cl_ops) == NULL) goto errout; + if (cops->tcf_chain == NULL) + goto errout; if (TC_H_MIN(tcm->tcm_parent)) { cl = cops->get(q, tcm->tcm_parent); if (cl == 0) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 24d17ce9c294..3af106140f35 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -207,7 +207,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) static void qdisc_list_add(struct Qdisc *q) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) - list_add_tail(&q->list, &qdisc_root_sleeping(q)->list); + list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list); } void qdisc_list_del(struct Qdisc *q) @@ -219,17 +219,11 @@ EXPORT_SYMBOL(qdisc_list_del); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { - unsigned int i; struct Qdisc *q; - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - struct Qdisc *txq_root = txq->qdisc_sleeping; - - q = qdisc_match_from_root(txq_root, handle); - if (q) - goto out; - } + q = qdisc_match_from_root(dev->qdisc, handle); + if (q) + goto out; q = qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle); out: @@ -616,32 +610,6 @@ static u32 qdisc_alloc_handle(struct net_device *dev) return i>0 ? autohandle : 0; } -/* Attach toplevel qdisc to device queue. */ - -static struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, - struct Qdisc *qdisc) -{ - struct Qdisc *oqdisc = dev_queue->qdisc_sleeping; - spinlock_t *root_lock; - - root_lock = qdisc_lock(oqdisc); - spin_lock_bh(root_lock); - - /* Prune old scheduler */ - if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1) - qdisc_reset(oqdisc); - - /* ... and graft new one */ - if (qdisc == NULL) - qdisc = &noop_qdisc; - dev_queue->qdisc_sleeping = qdisc; - rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); - - spin_unlock_bh(root_lock); - - return oqdisc; -} - void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) { const struct Qdisc_class_ops *cops; @@ -710,6 +678,11 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (dev->flags & IFF_UP) dev_deactivate(dev); + if (new && new->ops->attach) { + new->ops->attach(new); + num_q = 0; + } + for (i = 0; i < num_q; i++) { struct netdev_queue *dev_queue = &dev->rx_queue; @@ -720,22 +693,27 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (new && i > 0) atomic_inc(&new->refcnt); - notify_and_destroy(skb, n, classid, old, new); + qdisc_destroy(old); } + notify_and_destroy(skb, n, classid, dev->qdisc, new); + if (new && !new->ops->attach) + atomic_inc(&new->refcnt); + dev->qdisc = new ? : &noop_qdisc; + if (dev->flags & IFF_UP) dev_activate(dev); } else { const struct Qdisc_class_ops *cops = parent->ops->cl_ops; - err = -EINVAL; - - if (cops) { + err = -EOPNOTSUPP; + if (cops && cops->graft) { unsigned long cl = cops->get(parent, classid); if (cl) { err = cops->graft(parent, cl, new, &old); cops->put(parent, cl); - } + } else + err = -ENOENT; } if (!err) notify_and_destroy(skb, n, classid, old, new); @@ -755,7 +733,8 @@ static struct lock_class_key qdisc_rx_lock; static struct Qdisc * qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, - u32 parent, u32 handle, struct nlattr **tca, int *errp) + struct Qdisc *p, u32 parent, u32 handle, + struct nlattr **tca, int *errp) { int err; struct nlattr *kind = tca[TCA_KIND]; @@ -832,24 +811,21 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, if (tca[TCA_RATE]) { spinlock_t *root_lock; + err = -EOPNOTSUPP; + if (sch->flags & TCQ_F_MQROOT) + goto err_out4; + if ((sch->parent != TC_H_ROOT) && - !(sch->flags & TCQ_F_INGRESS)) + !(sch->flags & TCQ_F_INGRESS) && + (!p || !(p->flags & TCQ_F_MQROOT))) root_lock = qdisc_root_sleeping_lock(sch); else root_lock = qdisc_lock(sch); err = gen_new_estimator(&sch->bstats, &sch->rate_est, root_lock, tca[TCA_RATE]); - if (err) { - /* - * Any broken qdiscs that would require - * a ops->reset() here? The qdisc was never - * in action so it shouldn't be necessary. - */ - if (ops->destroy) - ops->destroy(sch); - goto err_out3; - } + if (err) + goto err_out4; } qdisc_list_add(sch); @@ -865,6 +841,15 @@ err_out2: err_out: *errp = err; return NULL; + +err_out4: + /* + * Any broken qdiscs that would require a ops->reset() here? + * The qdisc was never in action so it shouldn't be necessary. + */ + if (ops->destroy) + ops->destroy(sch); + goto err_out3; } static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) @@ -889,13 +874,16 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) qdisc_put_stab(sch->stab); sch->stab = stab; - if (tca[TCA_RATE]) + if (tca[TCA_RATE]) { /* NB: ignores errors from replace_estimator because change can't be undone. */ + if (sch->flags & TCQ_F_MQROOT) + goto out; gen_replace_estimator(&sch->bstats, &sch->rate_est, qdisc_root_sleeping_lock(sch), tca[TCA_RATE]); - + } +out: return 0; } @@ -974,9 +962,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) q = dev->rx_queue.qdisc_sleeping; } } else { - struct netdev_queue *dev_queue; - dev_queue = netdev_get_tx_queue(dev, 0); - q = dev_queue->qdisc_sleeping; + q = dev->qdisc; } if (!q) return -ENOENT; @@ -1044,9 +1030,7 @@ replay: q = dev->rx_queue.qdisc_sleeping; } } else { - struct netdev_queue *dev_queue; - dev_queue = netdev_get_tx_queue(dev, 0); - q = dev_queue->qdisc_sleeping; + q = dev->qdisc; } /* It may be default qdisc, ignore it */ @@ -1123,13 +1107,19 @@ create_n_graft: if (!(n->nlmsg_flags&NLM_F_CREATE)) return -ENOENT; if (clid == TC_H_INGRESS) - q = qdisc_create(dev, &dev->rx_queue, + q = qdisc_create(dev, &dev->rx_queue, p, tcm->tcm_parent, tcm->tcm_parent, tca, &err); - else - q = qdisc_create(dev, netdev_get_tx_queue(dev, 0), + else { + unsigned int ntx = 0; + + if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue) + ntx = p->ops->cl_ops->select_queue(p, tcm); + + q = qdisc_create(dev, netdev_get_tx_queue(dev, ntx), p, tcm->tcm_parent, tcm->tcm_handle, tca, &err); + } if (q == NULL) { if (err == -EAGAIN) goto replay; @@ -1291,8 +1281,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) s_q_idx = 0; q_idx = 0; - dev_queue = netdev_get_tx_queue(dev, 0); - if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0) + if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx) < 0) goto done; dev_queue = &dev->rx_queue; @@ -1323,7 +1312,6 @@ done: static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { struct net *net = sock_net(skb->sk); - struct netdev_queue *dev_queue; struct tcmsg *tcm = NLMSG_DATA(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; @@ -1361,7 +1349,6 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) /* Step 1. Determine qdisc handle X:0 */ - dev_queue = netdev_get_tx_queue(dev, 0); if (pid != TC_H_ROOT) { u32 qid1 = TC_H_MAJ(pid); @@ -1372,7 +1359,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) } else if (qid1) { qid = qid1; } else if (qid == 0) - qid = dev_queue->qdisc_sleeping->handle; + qid = dev->qdisc->handle; /* Now qid is genuine qdisc handle consistent both with parent and child. @@ -1383,7 +1370,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) pid = TC_H_MAKE(qid, pid); } else { if (qid == 0) - qid = dev_queue->qdisc_sleeping->handle; + qid = dev->qdisc->handle; } /* OK. Locate qdisc */ @@ -1417,7 +1404,9 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) goto out; break; case RTM_DELTCLASS: - err = cops->delete(q, cl); + err = -EOPNOTSUPP; + if (cops->delete) + err = cops->delete(q, cl); if (err == 0) tclass_notify(skb, n, q, cl, RTM_DELTCLASS); goto out; @@ -1431,7 +1420,9 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) } new_cl = cl; - err = cops->change(q, clid, pid, tca, &new_cl); + err = -EOPNOTSUPP; + if (cops->change) + err = cops->change(q, clid, pid, tca, &new_cl); if (err == 0) tclass_notify(skb, n, q, new_cl, RTM_NEWTCLASS); @@ -1584,8 +1575,7 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; t = 0; - dev_queue = netdev_get_tx_queue(dev, 0); - if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0) goto done; dev_queue = &dev->rx_queue; @@ -1705,6 +1695,7 @@ static int __init pktsched_init(void) { register_qdisc(&pfifo_qdisc_ops); register_qdisc(&bfifo_qdisc_ops); + register_qdisc(&mq_qdisc_ops); proc_net_fops_create(&init_net, "psched", 0, &psched_fops); rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 2a8b83af7c47..ab82f145f689 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -49,7 +49,7 @@ struct atm_flow_data { struct socket *sock; /* for closing */ u32 classid; /* x:y type ID */ int ref; /* reference count */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct atm_flow_data *next; struct atm_flow_data *excess; /* flow for excess traffic; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 23a167670fd5..5b132c473264 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -128,7 +128,7 @@ struct cbq_class long avgidle; long deficit; /* Saved deficit for WRR */ psched_time_t penalized; - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct tc_cbq_xstats xstats; @@ -1621,29 +1621,25 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, { struct cbq_class *cl = (struct cbq_class*)arg; - if (cl) { - if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, - cl->common.classid); - if (new == NULL) - return -ENOBUFS; - } else { + if (new == NULL) { + new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + &pfifo_qdisc_ops, cl->common.classid); + if (new == NULL) + return -ENOBUFS; + } else { #ifdef CONFIG_NET_CLS_ACT - if (cl->police == TC_POLICE_RECLASSIFY) - new->reshape_fail = cbq_reshape_fail; + if (cl->police == TC_POLICE_RECLASSIFY) + new->reshape_fail = cbq_reshape_fail; #endif - } - sch_tree_lock(sch); - *old = cl->q; - cl->q = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - - return 0; } - return -ENOENT; + sch_tree_lock(sch); + *old = cl->q; + cl->q = new; + qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); + qdisc_reset(*old); + sch_tree_unlock(sch); + + return 0; } static struct Qdisc * @@ -1651,7 +1647,7 @@ cbq_leaf(struct Qdisc *sch, unsigned long arg) { struct cbq_class *cl = (struct cbq_class*)arg; - return cl ? cl->q : NULL; + return cl->q; } static void cbq_qlen_notify(struct Qdisc *sch, unsigned long arg) diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 7597fe146866..12b2fb04b29b 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -22,7 +22,7 @@ struct drr_class { unsigned int refcnt; unsigned int filter_cnt; - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct list_head alist; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 693df7ae33d8..4ae6aa562f2b 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -406,18 +406,38 @@ static const u8 prio2band[TC_PRIO_MAX+1] = #define PFIFO_FAST_BANDS 3 -static inline struct sk_buff_head *prio2list(struct sk_buff *skb, - struct Qdisc *qdisc) +/* + * Private data for a pfifo_fast scheduler containing: + * - queues for the three band + * - bitmap indicating which of the bands contain skbs + */ +struct pfifo_fast_priv { + u32 bitmap; + struct sk_buff_head q[PFIFO_FAST_BANDS]; +}; + +/* + * Convert a bitmap to the first band number where an skb is queued, where: + * bitmap=0 means there are no skbs on any band. + * bitmap=1 means there is an skb on band 0. + * bitmap=7 means there are skbs on all 3 bands, etc. + */ +static const int bitmap2band[] = {-1, 0, 1, 0, 2, 0, 1, 0}; + +static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv, + int band) { - struct sk_buff_head *list = qdisc_priv(qdisc); - return list + prio2band[skb->priority & TC_PRIO_MAX]; + return priv->q + band; } static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) { - struct sk_buff_head *list = prio2list(skb, qdisc); + if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) { + int band = prio2band[skb->priority & TC_PRIO_MAX]; + struct pfifo_fast_priv *priv = qdisc_priv(qdisc); + struct sk_buff_head *list = band2list(priv, band); - if (skb_queue_len(list) < qdisc_dev(qdisc)->tx_queue_len) { + priv->bitmap |= (1 << band); qdisc->q.qlen++; return __qdisc_enqueue_tail(skb, qdisc, list); } @@ -427,14 +447,18 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) { - int prio; - struct sk_buff_head *list = qdisc_priv(qdisc); + struct pfifo_fast_priv *priv = qdisc_priv(qdisc); + int band = bitmap2band[priv->bitmap]; - for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { - if (!skb_queue_empty(list + prio)) { - qdisc->q.qlen--; - return __qdisc_dequeue_head(qdisc, list + prio); - } + if (likely(band >= 0)) { + struct sk_buff_head *list = band2list(priv, band); + struct sk_buff *skb = __qdisc_dequeue_head(qdisc, list); + + qdisc->q.qlen--; + if (skb_queue_empty(list)) + priv->bitmap &= ~(1 << band); + + return skb; } return NULL; @@ -442,12 +466,13 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc) { - int prio; - struct sk_buff_head *list = qdisc_priv(qdisc); + struct pfifo_fast_priv *priv = qdisc_priv(qdisc); + int band = bitmap2band[priv->bitmap]; + + if (band >= 0) { + struct sk_buff_head *list = band2list(priv, band); - for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { - if (!skb_queue_empty(list + prio)) - return skb_peek(list + prio); + return skb_peek(list); } return NULL; @@ -456,11 +481,12 @@ static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc) static void pfifo_fast_reset(struct Qdisc* qdisc) { int prio; - struct sk_buff_head *list = qdisc_priv(qdisc); + struct pfifo_fast_priv *priv = qdisc_priv(qdisc); for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) - __qdisc_reset_queue(qdisc, list + prio); + __qdisc_reset_queue(qdisc, band2list(priv, prio)); + priv->bitmap = 0; qdisc->qstats.backlog = 0; qdisc->q.qlen = 0; } @@ -480,17 +506,17 @@ nla_put_failure: static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt) { int prio; - struct sk_buff_head *list = qdisc_priv(qdisc); + struct pfifo_fast_priv *priv = qdisc_priv(qdisc); for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) - skb_queue_head_init(list + prio); + skb_queue_head_init(band2list(priv, prio)); return 0; } -static struct Qdisc_ops pfifo_fast_ops __read_mostly = { +struct Qdisc_ops pfifo_fast_ops __read_mostly = { .id = "pfifo_fast", - .priv_size = PFIFO_FAST_BANDS * sizeof(struct sk_buff_head), + .priv_size = sizeof(struct pfifo_fast_priv), .enqueue = pfifo_fast_enqueue, .dequeue = pfifo_fast_dequeue, .peek = pfifo_fast_peek, @@ -597,17 +623,29 @@ void qdisc_destroy(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_destroy); -static bool dev_all_qdisc_sleeping_noop(struct net_device *dev) +/* Attach toplevel qdisc to device queue. */ +struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, + struct Qdisc *qdisc) { - unsigned int i; + struct Qdisc *oqdisc = dev_queue->qdisc_sleeping; + spinlock_t *root_lock; - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + root_lock = qdisc_lock(oqdisc); + spin_lock_bh(root_lock); - if (txq->qdisc_sleeping != &noop_qdisc) - return false; - } - return true; + /* Prune old scheduler */ + if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1) + qdisc_reset(oqdisc); + + /* ... and graft new one */ + if (qdisc == NULL) + qdisc = &noop_qdisc; + dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); + + spin_unlock_bh(root_lock); + + return oqdisc; } static void attach_one_default_qdisc(struct net_device *dev, @@ -632,6 +670,26 @@ static void attach_one_default_qdisc(struct net_device *dev, dev_queue->qdisc_sleeping = qdisc; } +static void attach_default_qdiscs(struct net_device *dev) +{ + struct netdev_queue *txq; + struct Qdisc *qdisc; + + txq = netdev_get_tx_queue(dev, 0); + + if (!netif_is_multiqueue(dev) || dev->tx_queue_len == 0) { + netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); + dev->qdisc = txq->qdisc_sleeping; + atomic_inc(&dev->qdisc->refcnt); + } else { + qdisc = qdisc_create_dflt(dev, txq, &mq_qdisc_ops, TC_H_ROOT); + if (qdisc) { + qdisc->ops->attach(qdisc); + dev->qdisc = qdisc; + } + } +} + static void transition_one_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_need_watchdog) @@ -659,8 +717,8 @@ void dev_activate(struct net_device *dev) virtual interfaces */ - if (dev_all_qdisc_sleeping_noop(dev)) - netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); + if (dev->qdisc == &noop_qdisc) + attach_default_qdiscs(dev); if (!netif_carrier_ok(dev)) /* Delay activation until next carrier-on event */ @@ -751,6 +809,7 @@ static void dev_init_scheduler_queue(struct net_device *dev, void dev_init_scheduler(struct net_device *dev) { + dev->qdisc = &noop_qdisc; netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); dev_init_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc); @@ -776,5 +835,8 @@ void dev_shutdown(struct net_device *dev) { netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); shutdown_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc); + qdisc_destroy(dev->qdisc); + dev->qdisc = &noop_qdisc; + WARN_ON(timer_pending(&dev->watchdog_timer)); } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 362c2811b2df..375d64cb1a3d 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -116,7 +116,7 @@ struct hfsc_class struct Qdisc_class_common cl_common; unsigned int refcnt; /* usage count */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; unsigned int level; /* class level in hierarchy */ @@ -1203,8 +1203,6 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, { struct hfsc_class *cl = (struct hfsc_class *)arg; - if (cl == NULL) - return -ENOENT; if (cl->level > 0) return -EINVAL; if (new == NULL) { @@ -1228,7 +1226,7 @@ hfsc_class_leaf(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; - if (cl != NULL && cl->level == 0) + if (cl->level == 0) return cl->qdisc; return NULL; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 88cd02626621..85acab9dc6fd 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -74,7 +74,7 @@ enum htb_cmode { struct htb_class { struct Qdisc_class_common common; /* general class parameters */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct tc_htb_xstats xstats; /* our special stats */ @@ -1117,30 +1117,29 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, { struct htb_class *cl = (struct htb_class *)arg; - if (cl && !cl->level) { - if (new == NULL && - (new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, - cl->common.classid)) - == NULL) - return -ENOBUFS; - sch_tree_lock(sch); - *old = cl->un.leaf.q; - cl->un.leaf.q = new; - if (*old != NULL) { - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - } - sch_tree_unlock(sch); - return 0; + if (cl->level) + return -EINVAL; + if (new == NULL && + (new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + &pfifo_qdisc_ops, + cl->common.classid)) == NULL) + return -ENOBUFS; + + sch_tree_lock(sch); + *old = cl->un.leaf.q; + cl->un.leaf.q = new; + if (*old != NULL) { + qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); + qdisc_reset(*old); } - return -ENOENT; + sch_tree_unlock(sch); + return 0; } static struct Qdisc *htb_leaf(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - return (cl && !cl->level) ? cl->un.leaf.q : NULL; + return !cl->level ? cl->un.leaf.q : NULL; } static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 4a2b77374358..a9e646bdb605 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -22,12 +22,6 @@ struct ingress_qdisc_data { /* ------------------------- Class/flow operations ------------------------- */ -static int ingress_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old) -{ - return -EOPNOTSUPP; -} - static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; @@ -48,12 +42,6 @@ static void ingress_put(struct Qdisc *sch, unsigned long cl) { } -static int ingress_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg) -{ - return 0; -} - static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker) { return; @@ -123,11 +111,9 @@ nla_put_failure: } static const struct Qdisc_class_ops ingress_class_ops = { - .graft = ingress_graft, .leaf = ingress_leaf, .get = ingress_get, .put = ingress_put, - .change = ingress_change, .walk = ingress_walk, .tcf_chain = ingress_find_tcf, .bind_tcf = ingress_bind_filter, diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c new file mode 100644 index 000000000000..dd5ee022f1f7 --- /dev/null +++ b/net/sched/sch_mq.c @@ -0,0 +1,235 @@ +/* + * net/sched/sch_mq.c Classful multiqueue dummy scheduler + * + * Copyright (c) 2009 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> + +struct mq_sched { + struct Qdisc **qdiscs; +}; + +static void mq_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct mq_sched *priv = qdisc_priv(sch); + unsigned int ntx; + + if (!priv->qdiscs) + return; + for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) + qdisc_destroy(priv->qdiscs[ntx]); + kfree(priv->qdiscs); +} + +static int mq_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct net_device *dev = qdisc_dev(sch); + struct mq_sched *priv = qdisc_priv(sch); + struct netdev_queue *dev_queue; + struct Qdisc *qdisc; + unsigned int ntx; + + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!netif_is_multiqueue(dev)) + return -EOPNOTSUPP; + + /* pre-allocate qdiscs, attachment can't fail */ + priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), + GFP_KERNEL); + if (priv->qdiscs == NULL) + return -ENOMEM; + + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + dev_queue = netdev_get_tx_queue(dev, ntx); + qdisc = qdisc_create_dflt(dev, dev_queue, &pfifo_fast_ops, + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(ntx + 1))); + if (qdisc == NULL) + goto err; + qdisc->flags |= TCQ_F_CAN_BYPASS; + priv->qdiscs[ntx] = qdisc; + } + + sch->flags |= TCQ_F_MQROOT; + return 0; + +err: + mq_destroy(sch); + return -ENOMEM; +} + +static void mq_attach(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct mq_sched *priv = qdisc_priv(sch); + struct Qdisc *qdisc; + unsigned int ntx; + + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + qdisc = priv->qdiscs[ntx]; + qdisc = dev_graft_qdisc(qdisc->dev_queue, qdisc); + if (qdisc) + qdisc_destroy(qdisc); + } + kfree(priv->qdiscs); + priv->qdiscs = NULL; +} + +static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *qdisc; + unsigned int ntx; + + sch->q.qlen = 0; + memset(&sch->bstats, 0, sizeof(sch->bstats)); + memset(&sch->qstats, 0, sizeof(sch->qstats)); + + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; + spin_lock_bh(qdisc_lock(qdisc)); + sch->q.qlen += qdisc->q.qlen; + sch->bstats.bytes += qdisc->bstats.bytes; + sch->bstats.packets += qdisc->bstats.packets; + sch->qstats.qlen += qdisc->qstats.qlen; + sch->qstats.backlog += qdisc->qstats.backlog; + sch->qstats.drops += qdisc->qstats.drops; + sch->qstats.requeues += qdisc->qstats.requeues; + sch->qstats.overlimits += qdisc->qstats.overlimits; + spin_unlock_bh(qdisc_lock(qdisc)); + } + return 0; +} + +static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx = cl - 1; + + if (ntx >= dev->num_tx_queues) + return NULL; + return netdev_get_tx_queue(dev, ntx); +} + +static unsigned int mq_select_queue(struct Qdisc *sch, struct tcmsg *tcm) +{ + unsigned int ntx = TC_H_MIN(tcm->tcm_parent); + + if (!mq_queue_get(sch, ntx)) + return 0; + return ntx - 1; +} + +static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, + struct Qdisc **old) +{ + struct netdev_queue *dev_queue = mq_queue_get(sch, cl); + struct net_device *dev = qdisc_dev(sch); + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + + *old = dev_graft_qdisc(dev_queue, new); + + if (dev->flags & IFF_UP) + dev_activate(dev); + return 0; +} + +static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl) +{ + struct netdev_queue *dev_queue = mq_queue_get(sch, cl); + + return dev_queue->qdisc_sleeping; +} + +static unsigned long mq_get(struct Qdisc *sch, u32 classid) +{ + unsigned int ntx = TC_H_MIN(classid); + + if (!mq_queue_get(sch, ntx)) + return 0; + return ntx; +} + +static void mq_put(struct Qdisc *sch, unsigned long cl) +{ + return; +} + +static int mq_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct netdev_queue *dev_queue = mq_queue_get(sch, cl); + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle |= TC_H_MIN(cl); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + return 0; +} + +static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) +{ + struct netdev_queue *dev_queue = mq_queue_get(sch, cl); + + sch = dev_queue->qdisc_sleeping; + if (gnet_stats_copy_basic(d, &sch->bstats) < 0 || + gnet_stats_copy_queue(d, &sch->qstats) < 0) + return -1; + return 0; +} + +static void mq_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx; + + if (arg->stop) + return; + + arg->count = arg->skip; + for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { + if (arg->fn(sch, ntx + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static const struct Qdisc_class_ops mq_class_ops = { + .select_queue = mq_select_queue, + .graft = mq_graft, + .leaf = mq_leaf, + .get = mq_get, + .put = mq_put, + .walk = mq_walk, + .dump = mq_dump_class, + .dump_stats = mq_dump_class_stats, +}; + +struct Qdisc_ops mq_qdisc_ops __read_mostly = { + .cl_ops = &mq_class_ops, + .id = "mq", + .priv_size = sizeof(struct mq_sched), + .init = mq_init, + .destroy = mq_destroy, + .attach = mq_attach, + .dump = mq_dump, + .owner = THIS_MODULE, +}; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 912731203047..069f81c97277 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -298,9 +298,6 @@ static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct multiq_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; - if (band >= q->bands) - return -EINVAL; - if (new == NULL) new = &noop_qdisc; @@ -320,9 +317,6 @@ multiq_leaf(struct Qdisc *sch, unsigned long arg) struct multiq_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; - if (band >= q->bands) - return NULL; - return q->queues[band]; } @@ -348,36 +342,13 @@ static void multiq_put(struct Qdisc *q, unsigned long cl) return; } -static int multiq_change(struct Qdisc *sch, u32 handle, u32 parent, - struct nlattr **tca, unsigned long *arg) -{ - unsigned long cl = *arg; - struct multiq_sched_data *q = qdisc_priv(sch); - - if (cl - 1 > q->bands) - return -ENOENT; - return 0; -} - -static int multiq_delete(struct Qdisc *sch, unsigned long cl) -{ - struct multiq_sched_data *q = qdisc_priv(sch); - if (cl - 1 > q->bands) - return -ENOENT; - return 0; -} - - static int multiq_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct multiq_sched_data *q = qdisc_priv(sch); - if (cl - 1 > q->bands) - return -ENOENT; tcm->tcm_handle |= TC_H_MIN(cl); - if (q->queues[cl-1]) - tcm->tcm_info = q->queues[cl-1]->handle; + tcm->tcm_info = q->queues[cl-1]->handle; return 0; } @@ -430,8 +401,6 @@ static const struct Qdisc_class_ops multiq_class_ops = { .leaf = multiq_leaf, .get = multiq_get, .put = multiq_put, - .change = multiq_change, - .delete = multiq_delete, .walk = multiq_walk, .tcf_chain = multiq_find_tcf, .bind_tcf = multiq_bind, diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 94cecef70145..0f73c412d04b 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -262,9 +262,6 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct prio_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; - if (band >= q->bands) - return -EINVAL; - if (new == NULL) new = &noop_qdisc; @@ -284,9 +281,6 @@ prio_leaf(struct Qdisc *sch, unsigned long arg) struct prio_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; - if (band >= q->bands) - return NULL; - return q->queues[band]; } @@ -311,35 +305,13 @@ static void prio_put(struct Qdisc *q, unsigned long cl) return; } -static int prio_change(struct Qdisc *sch, u32 handle, u32 parent, struct nlattr **tca, unsigned long *arg) -{ - unsigned long cl = *arg; - struct prio_sched_data *q = qdisc_priv(sch); - - if (cl - 1 > q->bands) - return -ENOENT; - return 0; -} - -static int prio_delete(struct Qdisc *sch, unsigned long cl) -{ - struct prio_sched_data *q = qdisc_priv(sch); - if (cl - 1 > q->bands) - return -ENOENT; - return 0; -} - - static int prio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct prio_sched_data *q = qdisc_priv(sch); - if (cl - 1 > q->bands) - return -ENOENT; tcm->tcm_handle |= TC_H_MIN(cl); - if (q->queues[cl-1]) - tcm->tcm_info = q->queues[cl-1]->handle; + tcm->tcm_info = q->queues[cl-1]->handle; return 0; } @@ -392,8 +364,6 @@ static const struct Qdisc_class_ops prio_class_ops = { .leaf = prio_leaf, .get = prio_get, .put = prio_put, - .change = prio_change, - .delete = prio_delete, .walk = prio_walk, .tcf_chain = prio_find_tcf, .bind_tcf = prio_bind, diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 2bdf241f6315..072cdf442f8e 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -268,8 +268,6 @@ static int red_dump_class(struct Qdisc *sch, unsigned long cl, { struct red_sched_data *q = qdisc_priv(sch); - if (cl != 1) - return -ENOENT; tcm->tcm_handle |= TC_H_MIN(1); tcm->tcm_info = q->qdisc->handle; return 0; @@ -308,17 +306,6 @@ static void red_put(struct Qdisc *sch, unsigned long arg) return; } -static int red_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) -{ - return -ENOSYS; -} - -static int red_delete(struct Qdisc *sch, unsigned long cl) -{ - return -ENOSYS; -} - static void red_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { @@ -331,20 +318,12 @@ static void red_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto **red_find_tcf(struct Qdisc *sch, unsigned long cl) -{ - return NULL; -} - static const struct Qdisc_class_ops red_class_ops = { .graft = red_graft, .leaf = red_leaf, .get = red_get, .put = red_put, - .change = red_change_class, - .delete = red_delete, .walk = red_walk, - .tcf_chain = red_find_tcf, .dump = red_dump_class, }; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 8706920a6d45..cb21380c0605 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -496,12 +496,6 @@ nla_put_failure: return -1; } -static int sfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) -{ - return -EOPNOTSUPP; -} - static unsigned long sfq_get(struct Qdisc *sch, u32 classid) { return 0; @@ -560,7 +554,6 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) static const struct Qdisc_class_ops sfq_class_ops = { .get = sfq_get, - .change = sfq_change_class, .tcf_chain = sfq_find_tcf, .dump = sfq_dump_class, .dump_stats = sfq_dump_class_stats, diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index e22dfe85e43e..8fb8107ab188 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -368,9 +368,6 @@ static int tbf_dump_class(struct Qdisc *sch, unsigned long cl, { struct tbf_sched_data *q = qdisc_priv(sch); - if (cl != 1) /* only one class */ - return -ENOENT; - tcm->tcm_handle |= TC_H_MIN(1); tcm->tcm_info = q->qdisc->handle; @@ -410,17 +407,6 @@ static void tbf_put(struct Qdisc *sch, unsigned long arg) { } -static int tbf_change_class(struct Qdisc *sch, u32 classid, u32 parentid, - struct nlattr **tca, unsigned long *arg) -{ - return -ENOSYS; -} - -static int tbf_delete(struct Qdisc *sch, unsigned long arg) -{ - return -ENOSYS; -} - static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { @@ -433,21 +419,13 @@ static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto **tbf_find_tcf(struct Qdisc *sch, unsigned long cl) -{ - return NULL; -} - static const struct Qdisc_class_ops tbf_class_ops = { .graft = tbf_graft, .leaf = tbf_leaf, .get = tbf_get, .put = tbf_put, - .change = tbf_change_class, - .delete = tbf_delete, .walk = tbf_walk, - .tcf_chain = tbf_find_tcf, .dump = tbf_dump_class, }; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 12434b6c2042..5a002c247231 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -268,7 +268,7 @@ static inline int teql_resolve(struct sk_buff *skb, return __teql_resolve(skb, skb_res, dev); } -static int teql_master_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) { struct teql_master *master = netdev_priv(dev); struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); @@ -307,7 +307,7 @@ restart: if (!netif_tx_queue_stopped(slave_txq) && !netif_tx_queue_frozen(slave_txq) && - slave_ops->ndo_start_xmit(skb, slave) == 0) { + slave_ops->ndo_start_xmit(skb, slave) == NETDEV_TX_OK) { txq_trans_update(slave_txq); __netif_tx_unlock(slave_txq); master->slaves = NEXT_SLAVE(q); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 525864bf4f07..8450960df24f 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -112,6 +112,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->cookie_life.tv_usec = (sp->assocparams.sasoc_cookie_life % 1000) * 1000; asoc->frag_point = 0; + asoc->user_frag = sp->user_frag; /* Set the association max_retrans and RTO values from the * socket values. @@ -202,6 +203,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->a_rwnd = asoc->rwnd; asoc->rwnd_over = 0; + asoc->rwnd_press = 0; /* Use my own max window until I learn something better. */ asoc->peer.rwnd = SCTP_DEFAULT_MAXWINDOW; @@ -582,6 +584,33 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, asoc->addip_last_asconf->transport == peer) asoc->addip_last_asconf->transport = NULL; + /* If we have something on the transmitted list, we have to + * save it off. The best place is the active path. + */ + if (!list_empty(&peer->transmitted)) { + struct sctp_transport *active = asoc->peer.active_path; + struct sctp_chunk *ch; + + /* Reset the transport of each chunk on this list */ + list_for_each_entry(ch, &peer->transmitted, + transmitted_list) { + ch->transport = NULL; + ch->rtt_in_progress = 0; + } + + list_splice_tail_init(&peer->transmitted, + &active->transmitted); + + /* Start a T3 timer here in case it wasn't running so + * that these migrated packets have a chance to get + * retrnasmitted. + */ + if (!timer_pending(&active->T3_rtx_timer)) + if (!mod_timer(&active->T3_rtx_timer, + jiffies + active->rto)) + sctp_transport_hold(active); + } + asoc->peer.transport_count--; sctp_transport_free(peer); @@ -651,13 +680,15 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, */ peer->param_flags = asoc->param_flags; + sctp_transport_route(peer, NULL, sp); + /* Initialize the pmtu of the transport. */ - if (peer->param_flags & SPP_PMTUD_ENABLE) - sctp_transport_pmtu(peer); - else if (asoc->pathmtu) - peer->pathmtu = asoc->pathmtu; - else - peer->pathmtu = SCTP_DEFAULT_MAXSEGMENT; + if (peer->param_flags & SPP_PMTUD_DISABLE) { + if (asoc->pathmtu) + peer->pathmtu = asoc->pathmtu; + else + peer->pathmtu = SCTP_DEFAULT_MAXSEGMENT; + } /* If this is the first transport addr on this association, * initialize the association PMTU to the peer's PMTU. @@ -673,7 +704,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, "%d\n", asoc, asoc->pathmtu); peer->pmtu_pending = 0; - asoc->frag_point = sctp_frag_point(sp, asoc->pathmtu); + asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); /* The asoc->peer.port might not be meaningful yet, but * initialize the packet structure anyway. @@ -810,11 +841,16 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, break; case SCTP_TRANSPORT_DOWN: - /* if the transort was never confirmed, do not transition it - * to inactive state. + /* If the transport was never confirmed, do not transition it + * to inactive state. Also, release the cached route since + * there may be a better route next time. */ if (transport->state != SCTP_UNCONFIRMED) transport->state = SCTP_INACTIVE; + else { + dst_release(transport->dst); + transport->dst = NULL; + } spc_state = SCTP_ADDR_UNREACHABLE; break; @@ -1324,9 +1360,8 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc) } if (pmtu) { - struct sctp_sock *sp = sctp_sk(asoc->base.sk); asoc->pathmtu = pmtu; - asoc->frag_point = sctp_frag_point(sp, pmtu); + asoc->frag_point = sctp_frag_point(asoc, pmtu); } SCTP_DEBUG_PRINTK("%s: asoc:%p, pmtu:%d, frag_point:%d\n", @@ -1369,6 +1404,17 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned len) asoc->rwnd += len; } + /* If we had window pressure, start recovering it + * once our rwnd had reached the accumulated pressure + * threshold. The idea is to recover slowly, but up + * to the initial advertised window. + */ + if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { + int change = min(asoc->pathmtu, asoc->rwnd_press); + asoc->rwnd += change; + asoc->rwnd_press -= change; + } + SCTP_DEBUG_PRINTK("%s: asoc %p rwnd increased by %d to (%u, %u) " "- %u\n", __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, asoc->a_rwnd); @@ -1401,17 +1447,38 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned len) /* Decrease asoc's rwnd by len. */ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned len) { + int rx_count; + int over = 0; + SCTP_ASSERT(asoc->rwnd, "rwnd zero", return); SCTP_ASSERT(!asoc->rwnd_over, "rwnd_over not zero", return); + + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); + + /* If we've reached or overflowed our receive buffer, announce + * a 0 rwnd if rwnd would still be positive. Store the + * the pottential pressure overflow so that the window can be restored + * back to original value. + */ + if (rx_count >= asoc->base.sk->sk_rcvbuf) + over = 1; + if (asoc->rwnd >= len) { asoc->rwnd -= len; + if (over) { + asoc->rwnd_press = asoc->rwnd; + asoc->rwnd = 0; + } } else { asoc->rwnd_over = len - asoc->rwnd; asoc->rwnd = 0; } - SCTP_DEBUG_PRINTK("%s: asoc %p rwnd decreased by %d to (%u, %u)\n", + SCTP_DEBUG_PRINTK("%s: asoc %p rwnd decreased by %d to (%u, %u, %u)\n", __func__, asoc, len, asoc->rwnd, - asoc->rwnd_over); + asoc->rwnd_over, asoc->rwnd_press); } /* Build the bind address list for the association based on info from the diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 6d5944a745d4..13a6fba41077 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -510,9 +510,28 @@ int sctp_in_scope(const union sctp_addr *addr, sctp_scope_t scope) * of requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. + * + * Address scoping can be selectively controlled via sysctl + * option */ - if (addr_scope <= scope) + switch (sctp_scope_policy) { + case SCTP_SCOPE_POLICY_DISABLE: return 1; + case SCTP_SCOPE_POLICY_ENABLE: + if (addr_scope <= scope) + return 1; + break; + case SCTP_SCOPE_POLICY_PRIVATE: + if (addr_scope <= scope || SCTP_SCOPE_PRIVATE == addr_scope) + return 1; + break; + case SCTP_SCOPE_POLICY_LINK: + if (addr_scope <= scope || SCTP_SCOPE_LINK == addr_scope) + return 1; + break; + default: + break; + } return 0; } diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 1748ef90950c..acf7c4d128f7 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -59,6 +59,7 @@ static void sctp_datamsg_init(struct sctp_datamsg *msg) msg->can_abandon = 0; msg->expires_at = 0; INIT_LIST_HEAD(&msg->chunks); + msg->msg_size = 0; } /* Allocate and initialize datamsg. */ @@ -73,6 +74,19 @@ SCTP_STATIC struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp) return msg; } +void sctp_datamsg_free(struct sctp_datamsg *msg) +{ + struct sctp_chunk *chunk; + + /* This doesn't have to be a _safe vairant because + * sctp_chunk_free() only drops the refs. + */ + list_for_each_entry(chunk, &msg->chunks, frag_list) + sctp_chunk_free(chunk); + + sctp_datamsg_put(msg); +} + /* Final destructruction of datamsg memory. */ static void sctp_datamsg_destroy(struct sctp_datamsg *msg) { @@ -142,6 +156,7 @@ static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chu { sctp_datamsg_hold(msg); chunk->msg = msg; + msg->msg_size += chunk->skb->len; } @@ -158,6 +173,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, { int max, whole, i, offset, over, err; int len, first_len; + int max_data; struct sctp_chunk *chunk; struct sctp_datamsg *msg; struct list_head *pos, *temp; @@ -179,8 +195,14 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, __func__, msg, msg->expires_at, jiffies); } - max = asoc->frag_point; + /* This is the biggest possible DATA chunk that can fit into + * the packet + */ + max_data = asoc->pathmtu - + sctp_sk(asoc->base.sk)->pf->af->net_header_len - + sizeof(struct sctphdr) - sizeof(struct sctp_data_chunk); + max = asoc->frag_point; /* If the the peer requested that we authenticate DATA chunks * we need to accound for bundling of the AUTH chunks along with * DATA. @@ -189,23 +211,41 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc); if (hmac_desc) - max -= WORD_ROUND(sizeof(sctp_auth_chunk_t) + + max_data -= WORD_ROUND(sizeof(sctp_auth_chunk_t) + hmac_desc->hmac_len); } + /* Now, check if we need to reduce our max */ + if (max > max_data) + max = max_data; + whole = 0; first_len = max; + /* Check to see if we have a pending SACK and try to let it be bundled + * with this message. Do this if we don't have any data queued already. + * To check that, look at out_qlen and retransmit list. + * NOTE: we will not reduce to account for SACK, if the message would + * not have been fragmented. + */ + if (timer_pending(&asoc->timers[SCTP_EVENT_TIMEOUT_SACK]) && + asoc->outqueue.out_qlen == 0 && + list_empty(&asoc->outqueue.retransmit) && + msg_len > max) + max_data -= WORD_ROUND(sizeof(sctp_sack_chunk_t)); + /* Encourage Cookie-ECHO bundling. */ - if (asoc->state < SCTP_STATE_COOKIE_ECHOED) { - whole = msg_len / (max - SCTP_ARBITRARY_COOKIE_ECHO_LEN); - - /* Account for the DATA to be bundled with the COOKIE-ECHO. */ - if (whole) { - first_len = max - SCTP_ARBITRARY_COOKIE_ECHO_LEN; - msg_len -= first_len; - whole = 1; - } + if (asoc->state < SCTP_STATE_COOKIE_ECHOED) + max_data -= SCTP_ARBITRARY_COOKIE_ECHO_LEN; + + /* Now that we adjusted completely, reset first_len */ + if (first_len > max_data) + first_len = max_data; + + /* Account for a different sized first fragment */ + if (msg_len >= first_len) { + msg_len -= first_len; + whole = 1; } /* How many full sized? How many bytes leftover? */ diff --git a/net/sctp/output.c b/net/sctp/output.c index b94c21190566..5cbda8f1ddfd 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -61,8 +61,24 @@ #include <net/sctp/checksum.h> /* Forward declarations for private helpers. */ -static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, +static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, struct sctp_chunk *chunk); +static void sctp_packet_append_data(struct sctp_packet *packet, + struct sctp_chunk *chunk); +static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, + struct sctp_chunk *chunk, + u16 chunk_len); + +static void sctp_packet_reset(struct sctp_packet *packet) +{ + packet->size = packet->overhead; + packet->has_cookie_echo = 0; + packet->has_sack = 0; + packet->has_data = 0; + packet->has_auth = 0; + packet->ipfragok = 0; + packet->auth = NULL; +} /* Config a packet. * This appears to be a followup set of initializations. @@ -75,13 +91,8 @@ struct sctp_packet *sctp_packet_config(struct sctp_packet *packet, SCTP_DEBUG_PRINTK("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); + sctp_packet_reset(packet); packet->vtag = vtag; - packet->has_cookie_echo = 0; - packet->has_sack = 0; - packet->has_auth = 0; - packet->has_data = 0; - packet->ipfragok = 0; - packet->auth = NULL; if (ecn_capable && sctp_packet_empty(packet)) { chunk = sctp_get_ecne_prepend(packet->transport->asoc); @@ -119,15 +130,9 @@ struct sctp_packet *sctp_packet_init(struct sctp_packet *packet, } overhead += sizeof(struct sctphdr); packet->overhead = overhead; - packet->size = overhead; + sctp_packet_reset(packet); packet->vtag = 0; - packet->has_cookie_echo = 0; - packet->has_sack = 0; - packet->has_auth = 0; - packet->has_data = 0; - packet->ipfragok = 0; packet->malloced = 0; - packet->auth = NULL; return packet; } @@ -204,7 +209,7 @@ static sctp_xmit_t sctp_packet_bundle_auth(struct sctp_packet *pkt, /* See if this is an auth chunk we are bundling or if * auth is already bundled. */ - if (chunk->chunk_hdr->type == SCTP_CID_AUTH || pkt->auth) + if (chunk->chunk_hdr->type == SCTP_CID_AUTH || pkt->has_auth) return retval; /* if the peer did not request this chunk to be authenticated, @@ -234,18 +239,19 @@ static sctp_xmit_t sctp_packet_bundle_sack(struct sctp_packet *pkt, if (sctp_chunk_is_data(chunk) && !pkt->has_sack && !pkt->has_cookie_echo) { struct sctp_association *asoc; + struct timer_list *timer; asoc = pkt->transport->asoc; + timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; - if (asoc->a_rwnd > asoc->rwnd) { + /* If the SACK timer is running, we have a pending SACK */ + if (timer_pending(timer)) { struct sctp_chunk *sack; asoc->a_rwnd = asoc->rwnd; sack = sctp_make_sack(asoc); if (sack) { - struct timer_list *timer; retval = sctp_packet_append_chunk(pkt, sack); asoc->peer.sack_needed = 0; - timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) sctp_association_put(asoc); } } @@ -261,13 +267,20 @@ sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *packet, { sctp_xmit_t retval = SCTP_XMIT_OK; __u16 chunk_len = WORD_ROUND(ntohs(chunk->chunk_hdr->length)); - size_t psize; - size_t pmtu; - int too_big; SCTP_DEBUG_PRINTK("%s: packet:%p chunk:%p\n", __func__, packet, chunk); + /* Data chunks are special. Before seeing what else we can + * bundle into this packet, check to see if we are allowed to + * send this DATA. + */ + if (sctp_chunk_is_data(chunk)) { + retval = sctp_packet_can_append_data(packet, chunk); + if (retval != SCTP_XMIT_OK) + goto finish; + } + /* Try to bundle AUTH chunk */ retval = sctp_packet_bundle_auth(packet, chunk); if (retval != SCTP_XMIT_OK) @@ -278,51 +291,16 @@ sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *packet, if (retval != SCTP_XMIT_OK) goto finish; - psize = packet->size; - pmtu = ((packet->transport->asoc) ? - (packet->transport->asoc->pathmtu) : - (packet->transport->pathmtu)); - - too_big = (psize + chunk_len > pmtu); - - /* Decide if we need to fragment or resubmit later. */ - if (too_big) { - /* It's OK to fragmet at IP level if any one of the following - * is true: - * 1. The packet is empty (meaning this chunk is greater - * the MTU) - * 2. The chunk we are adding is a control chunk - * 3. The packet doesn't have any data in it yet and data - * requires authentication. - */ - if (sctp_packet_empty(packet) || !sctp_chunk_is_data(chunk) || - (!packet->has_data && chunk->auth)) { - /* We no longer do re-fragmentation. - * Just fragment at the IP layer, if we - * actually hit this condition - */ - packet->ipfragok = 1; - goto append; - - } else { - retval = SCTP_XMIT_PMTU_FULL; - goto finish; - } - } - -append: - /* We believe that this chunk is OK to add to the packet (as - * long as we have the cwnd for it). - */ + /* Check to see if this chunk will fit into the packet */ + retval = sctp_packet_will_fit(packet, chunk, chunk_len); + if (retval != SCTP_XMIT_OK) + goto finish; - /* DATA is a special case since we must examine both rwnd and cwnd - * before we send DATA. - */ + /* We believe that this chunk is OK to add to the packet */ switch (chunk->chunk_hdr->type) { case SCTP_CID_DATA: - retval = sctp_packet_append_data(packet, chunk); - if (SCTP_XMIT_OK != retval) - goto finish; + /* Account for the data being in the packet */ + sctp_packet_append_data(packet, chunk); /* Disallow SACK bundling after DATA. */ packet->has_sack = 1; /* Disallow AUTH bundling after DATA */ @@ -598,7 +576,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) (*tp->af_specific->sctp_xmit)(nskb, tp); out: - packet->size = packet->overhead; + sctp_packet_reset(packet); return err; no_route: kfree_skb(nskb); @@ -632,16 +610,15 @@ nomem: * 2nd Level Abstractions ********************************************************************/ -/* This private function handles the specifics of appending DATA chunks. */ -static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, +/* This private function check to see if a chunk can be added */ +static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, struct sctp_chunk *chunk) { sctp_xmit_t retval = SCTP_XMIT_OK; - size_t datasize, rwnd, inflight; + size_t datasize, rwnd, inflight, flight_size; struct sctp_transport *transport = packet->transport; __u32 max_burst_bytes; struct sctp_association *asoc = transport->asoc; - struct sctp_sock *sp = sctp_sk(asoc->base.sk); struct sctp_outq *q = &asoc->outqueue; /* RFC 2960 6.1 Transmission of DATA Chunks @@ -658,7 +635,8 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, */ rwnd = asoc->peer.rwnd; - inflight = asoc->outqueue.outstanding_bytes; + inflight = q->outstanding_bytes; + flight_size = transport->flight_size; datasize = sctp_data_size(chunk); @@ -681,8 +659,8 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, * cwnd = flightsize + Max.Burst * MTU */ max_burst_bytes = asoc->max_burst * asoc->pathmtu; - if ((transport->flight_size + max_burst_bytes) < transport->cwnd) { - transport->cwnd = transport->flight_size + max_burst_bytes; + if ((flight_size + max_burst_bytes) < transport->cwnd) { + transport->cwnd = flight_size + max_burst_bytes; SCTP_DEBUG_PRINTK("%s: cwnd limited by max_burst: " "transport: %p, cwnd: %d, " "ssthresh: %d, flight_size: %d, " @@ -707,7 +685,7 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, * ignore the value of cwnd and SHOULD NOT delay retransmission. */ if (chunk->fast_retransmit != SCTP_NEED_FRTX) - if (transport->flight_size >= transport->cwnd) { + if (flight_size >= transport->cwnd) { retval = SCTP_XMIT_RWND_FULL; goto finish; } @@ -717,20 +695,36 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, * if any previously transmitted data on the connection remains * unacknowledged. */ - if (!sp->nodelay && sctp_packet_empty(packet) && - q->outstanding_bytes && sctp_state(asoc, ESTABLISHED)) { - unsigned len = datasize + q->out_qlen; + if (!sctp_sk(asoc->base.sk)->nodelay && sctp_packet_empty(packet) && + inflight && sctp_state(asoc, ESTABLISHED)) { + unsigned max = transport->pathmtu - packet->overhead; + unsigned len = chunk->skb->len + q->out_qlen; /* Check whether this chunk and all the rest of pending * data will fit or delay in hopes of bundling a full * sized packet. + * Don't delay large message writes that may have been + * fragmeneted into small peices. */ - if (len < asoc->frag_point) { + if ((len < max) && (chunk->msg->msg_size < max)) { retval = SCTP_XMIT_NAGLE_DELAY; goto finish; } } +finish: + return retval; +} + +/* This private function does management things when adding DATA chunk */ +static void sctp_packet_append_data(struct sctp_packet *packet, + struct sctp_chunk *chunk) +{ + struct sctp_transport *transport = packet->transport; + size_t datasize = sctp_data_size(chunk); + struct sctp_association *asoc = transport->asoc; + u32 rwnd = asoc->peer.rwnd; + /* Keep track of how many bytes are in flight over this transport. */ transport->flight_size += datasize; @@ -753,7 +747,45 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, /* Has been accepted for transmission. */ if (!asoc->peer.prsctp_capable) chunk->msg->can_abandon = 0; +} + +static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, + struct sctp_chunk *chunk, + u16 chunk_len) +{ + size_t psize; + size_t pmtu; + int too_big; + sctp_xmit_t retval = SCTP_XMIT_OK; + + psize = packet->size; + pmtu = ((packet->transport->asoc) ? + (packet->transport->asoc->pathmtu) : + (packet->transport->pathmtu)); + + too_big = (psize + chunk_len > pmtu); + + /* Decide if we need to fragment or resubmit later. */ + if (too_big) { + /* It's OK to fragmet at IP level if any one of the following + * is true: + * 1. The packet is empty (meaning this chunk is greater + * the MTU) + * 2. The chunk we are adding is a control chunk + * 3. The packet doesn't have any data in it yet and data + * requires authentication. + */ + if (sctp_packet_empty(packet) || !sctp_chunk_is_data(chunk) || + (!packet->has_data && chunk->auth)) { + /* We no longer do re-fragmentation. + * Just fragment at the IP layer, if we + * actually hit this condition + */ + packet->ipfragok = 1; + } else { + retval = SCTP_XMIT_PMTU_FULL; + } + } -finish: return retval; } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index d765fc53e74d..c9f20e28521b 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -406,8 +406,9 @@ void sctp_retransmit_mark(struct sctp_outq *q, * not be retransmitted */ if (!chunk->tsn_gap_acked) { - chunk->transport->flight_size -= - sctp_data_size(chunk); + if (chunk->transport) + chunk->transport->flight_size -= + sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); q->asoc->peer.rwnd += (sctp_data_size(chunk) + sizeof(struct sk_buff)); @@ -443,7 +444,8 @@ void sctp_retransmit_mark(struct sctp_outq *q, q->asoc->peer.rwnd += (sctp_data_size(chunk) + sizeof(struct sk_buff)); q->outstanding_bytes -= sctp_data_size(chunk); - transport->flight_size -= sctp_data_size(chunk); + if (chunk->transport) + transport->flight_size -= sctp_data_size(chunk); /* sctpimpguide-05 Section 2.8.2 * M5) If a T3-rtx timer expires, the @@ -1310,6 +1312,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, __u32 rtt; __u8 restart_timer = 0; int bytes_acked = 0; + int migrate_bytes = 0; /* These state variables are for coherent debug output. --xguo */ @@ -1343,8 +1346,9 @@ static void sctp_check_transmitted(struct sctp_outq *q, * considering it as 'outstanding'. */ if (!tchunk->tsn_gap_acked) { - tchunk->transport->flight_size -= - sctp_data_size(tchunk); + if (tchunk->transport) + tchunk->transport->flight_size -= + sctp_data_size(tchunk); q->outstanding_bytes -= sctp_data_size(tchunk); } continue; @@ -1378,6 +1382,20 @@ static void sctp_check_transmitted(struct sctp_outq *q, rtt); } } + + /* If the chunk hasn't been marked as ACKED, + * mark it and account bytes_acked if the + * chunk had a valid transport (it will not + * have a transport if ASCONF had deleted it + * while DATA was outstanding). + */ + if (!tchunk->tsn_gap_acked) { + tchunk->tsn_gap_acked = 1; + bytes_acked += sctp_data_size(tchunk); + if (!tchunk->transport) + migrate_bytes += sctp_data_size(tchunk); + } + if (TSN_lte(tsn, sack_ctsn)) { /* RFC 2960 6.3.2 Retransmission Timer Rules * @@ -1391,8 +1409,6 @@ static void sctp_check_transmitted(struct sctp_outq *q, restart_timer = 1; if (!tchunk->tsn_gap_acked) { - tchunk->tsn_gap_acked = 1; - bytes_acked += sctp_data_size(tchunk); /* * SFR-CACC algorithm: * 2) If the SACK contains gap acks @@ -1432,10 +1448,6 @@ static void sctp_check_transmitted(struct sctp_outq *q, * older than that newly acknowledged DATA * chunk, are qualified as 'Stray DATA chunks'. */ - if (!tchunk->tsn_gap_acked) { - tchunk->tsn_gap_acked = 1; - bytes_acked += sctp_data_size(tchunk); - } list_add_tail(lchunk, &tlist); } @@ -1491,7 +1503,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, tsn); tchunk->tsn_gap_acked = 0; - bytes_acked -= sctp_data_size(tchunk); + if (tchunk->transport) + bytes_acked -= sctp_data_size(tchunk); /* RFC 2960 6.3.2 Retransmission Timer Rules * @@ -1561,6 +1574,14 @@ static void sctp_check_transmitted(struct sctp_outq *q, #endif /* SCTP_DEBUG */ if (transport) { if (bytes_acked) { + /* We may have counted DATA that was migrated + * to this transport due to DEL-IP operation. + * Subtract those bytes, since the were never + * send on this transport and shouldn't be + * credited to this transport. + */ + bytes_acked -= migrate_bytes; + /* 8.2. When an outstanding TSN is acknowledged, * the endpoint shall clear the error counter of * the destination transport address to which the @@ -1589,7 +1610,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, transport->flight_size -= bytes_acked; if (transport->flight_size == 0) transport->partial_bytes_acked = 0; - q->outstanding_bytes -= bytes_acked; + q->outstanding_bytes -= bytes_acked + migrate_bytes; } else { /* RFC 2960 6.1, sctpimpguide-06 2.15.2 * When a sender is doing zero window probing, it diff --git a/net/sctp/proc.c b/net/sctp/proc.c index f268910620be..d093cbfeaac4 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -512,10 +512,8 @@ int __init sctp_remaddr_proc_init(void) { struct proc_dir_entry *p; - p = create_proc_entry("remaddr", S_IRUGO, proc_net_sctp); + p = proc_create("remaddr", S_IRUGO, proc_net_sctp, &sctp_remaddr_seq_fops); if (!p) return -ENOMEM; - p->proc_fops = &sctp_remaddr_seq_fops; - return 0; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 79cbd47f4df7..60093be8385d 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -160,6 +160,7 @@ static void sctp_proc_exit(void) remove_proc_entry("sctp", init_net.proc_net); } #endif + percpu_counter_destroy(&sctp_sockets_allocated); } /* Private helper to extract ipv4 address and stash them in @@ -430,16 +431,14 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) * of requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. + * + * IPv4 scoping can be controlled through sysctl option + * net.sctp.addr_scope_policy */ static sctp_scope_t sctp_v4_scope(union sctp_addr *addr) { sctp_scope_t retval; - /* Should IPv4 scoping be a sysctl configurable option - * so users can turn it off (default on) for certain - * unconventional networking environments? - */ - /* Check for unusable SCTP addresses. */ if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_UNUSABLE; @@ -1258,6 +1257,9 @@ SCTP_STATIC __init int sctp_init(void) /* Disable AUTH by default. */ sctp_auth_enable = 0; + /* Set SCOPE policy to enabled */ + sctp_scope_policy = SCTP_SCOPE_POLICY_ENABLE; + sctp_sysctl_register(); INIT_LIST_HEAD(&sctp_address_families); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 61cc6075b0df..9d881a61ac02 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2861,6 +2861,11 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, addr_param = (union sctp_addr_param *) ((void *)asconf_param + sizeof(sctp_addip_param_t)); + if (asconf_param->param_hdr.type != SCTP_PARAM_ADD_IP && + asconf_param->param_hdr.type != SCTP_PARAM_DEL_IP && + asconf_param->param_hdr.type != SCTP_PARAM_SET_PRIMARY) + return SCTP_ERROR_UNKNOWN_PARAM; + switch (addr_param->v4.param_hdr.type) { case SCTP_PARAM_IPV6_ADDRESS: if (!asoc->peer.ipv6_address) @@ -2958,9 +2963,6 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, sctp_assoc_set_primary(asoc, peer); break; - default: - return SCTP_ERROR_UNKNOWN_PARAM; - break; } return SCTP_ERROR_NO_ERROR; @@ -3104,7 +3106,7 @@ done: } /* Process a asconf parameter that is successfully acked. */ -static int sctp_asconf_param_success(struct sctp_association *asoc, +static void sctp_asconf_param_success(struct sctp_association *asoc, sctp_addip_param_t *asconf_param) { struct sctp_af *af; @@ -3113,7 +3115,6 @@ static int sctp_asconf_param_success(struct sctp_association *asoc, union sctp_addr_param *addr_param; struct sctp_transport *transport; struct sctp_sockaddr_entry *saddr; - int retval = 0; addr_param = (union sctp_addr_param *) ((void *)asconf_param + sizeof(sctp_addip_param_t)); @@ -3133,10 +3134,18 @@ static int sctp_asconf_param_success(struct sctp_association *asoc, saddr->state = SCTP_ADDR_SRC; } local_bh_enable(); + list_for_each_entry(transport, &asoc->peer.transport_addr_list, + transports) { + if (transport->state == SCTP_ACTIVE) + continue; + dst_release(transport->dst); + sctp_transport_route(transport, NULL, + sctp_sk(asoc->base.sk)); + } break; case SCTP_PARAM_DEL_IP: local_bh_disable(); - retval = sctp_del_bind_addr(bp, &addr); + sctp_del_bind_addr(bp, &addr); local_bh_enable(); list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { @@ -3148,8 +3157,6 @@ static int sctp_asconf_param_success(struct sctp_association *asoc, default: break; } - - return retval; } /* Get the corresponding ASCONF response error code from the ASCONF_ACK chunk @@ -3266,7 +3273,7 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, switch (err_code) { case SCTP_ERROR_NO_ERROR: - retval = sctp_asconf_param_success(asoc, asconf_param); + sctp_asconf_param_success(asoc, asconf_param); break; case SCTP_ERROR_RSRC_LOW: diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 86426aac1600..8674d4919556 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -440,14 +440,26 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, /* The check for association's overall error counter exceeding the * threshold is done in the state function. */ - /* When probing UNCONFIRMED addresses, the association overall - * error count is NOT incremented + /* We are here due to a timer expiration. If the timer was + * not a HEARTBEAT, then normal error tracking is done. + * If the timer was a heartbeat, we only increment error counts + * when we already have an outstanding HEARTBEAT that has not + * been acknowledged. + * Additionaly, some tranport states inhibit error increments. */ - if (transport->state != SCTP_UNCONFIRMED) + if (!is_hb) { asoc->overall_error_count++; + if (transport->state != SCTP_INACTIVE) + transport->error_count++; + } else if (transport->hb_sent) { + if (transport->state != SCTP_UNCONFIRMED) + asoc->overall_error_count++; + if (transport->state != SCTP_INACTIVE) + transport->error_count++; + } if (transport->state != SCTP_INACTIVE && - (transport->error_count++ >= transport->pathmaxrxt)) { + (transport->error_count > transport->pathmaxrxt)) { SCTP_DEBUG_PRINTK_IPADDR("transport_strike:association %p", " transport IP: port:%d failed.\n", asoc, @@ -931,6 +943,27 @@ static void sctp_cmd_t1_timer_update(struct sctp_association *asoc, } +/* Send the whole message, chunk by chunk, to the outqueue. + * This way the whole message is queued up and bundling if + * encouraged for small fragments. + */ +static int sctp_cmd_send_msg(struct sctp_association *asoc, + struct sctp_datamsg *msg) +{ + struct sctp_chunk *chunk; + int error = 0; + + list_for_each_entry(chunk, &msg->chunks, frag_list) { + error = sctp_outq_tail(&asoc->outqueue, chunk); + if (error) + break; + } + + return error; +} + + + /* These three macros allow us to pull the debugging code out of the * main flow of sctp_do_sm() to keep attention focused on the real * functionality there. @@ -1500,7 +1533,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_PROCESS_CTSN: /* Dummy up a SACK for processing. */ sackh.cum_tsn_ack = cmd->obj.be32; - sackh.a_rwnd = 0; + sackh.a_rwnd = asoc->peer.rwnd + + asoc->outqueue.outstanding_bytes; sackh.num_gap_ack_blocks = 0; sackh.num_dup_tsns = 0; sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_SACK, @@ -1575,7 +1609,13 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_UPDATE_INITTAG: asoc->peer.i.init_tag = cmd->obj.u32; break; - + case SCTP_CMD_SEND_MSG: + if (!asoc->outqueue.cork) { + sctp_outq_cork(&asoc->outqueue); + local_cork = 1; + } + error = sctp_cmd_send_msg(asoc, cmd->obj.msg); + break; default: printk(KERN_WARNING "Impossible command: %u, %p\n", cmd->verb, cmd->obj.ptr); @@ -1593,9 +1633,9 @@ out: */ if (asoc && SCTP_EVENT_T_CHUNK == event_type && chunk) { if (chunk->end_of_packet || chunk->singleton) - sctp_outq_uncork(&asoc->outqueue); + error = sctp_outq_uncork(&asoc->outqueue); } else if (local_cork) - sctp_outq_uncork(&asoc->outqueue); + error = sctp_outq_uncork(&asoc->outqueue); return error; nomem: error = -ENOMEM; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7288192f7df5..c8fae1983dd1 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -334,6 +334,15 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, if (!sctp_chunk_length_valid(chunk, sizeof(sctp_init_chunk_t))) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + /* If the INIT is coming toward a closing socket, we'll send back + * and ABORT. Essentially, this catches the race of INIT being + * backloged to the socket at the same time as the user isses close(). + * Since the socket and all its associations are going away, we + * can treat this OOTB + */ + if (sctp_sstate(ep->base.sk, CLOSING)) + return sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands); + /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(asoc, chunk->chunk_hdr->type, @@ -962,7 +971,7 @@ sctp_disposition_t sctp_sf_sendbeat_8_3(const struct sctp_endpoint *ep, { struct sctp_transport *transport = (struct sctp_transport *) arg; - if (asoc->overall_error_count > asoc->max_retrans) { + if (asoc->overall_error_count >= asoc->max_retrans) { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ @@ -1106,7 +1115,8 @@ sctp_disposition_t sctp_sf_backbeat_8_3(const struct sctp_endpoint *ep, return sctp_sf_pdiscard(ep, asoc, type, arg, commands); /* Make sure that the HEARTBEAT-ACK chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_heartbeat_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t) + + sizeof(sctp_sender_hb_info_t))) return sctp_sf_violation_chunklen(ep, asoc, type, arg, commands); @@ -2561,6 +2571,12 @@ sctp_disposition_t sctp_sf_do_9_2_shutdown(const struct sctp_endpoint *ep, chunk->subh.shutdown_hdr = sdh; ctsn = ntohl(sdh->cum_tsn_ack); + if (TSN_lt(ctsn, asoc->ctsn_ack_point)) { + SCTP_DEBUG_PRINTK("ctsn %x\n", ctsn); + SCTP_DEBUG_PRINTK("ctsn_ack_point %x\n", asoc->ctsn_ack_point); + return SCTP_DISPOSITION_DISCARD; + } + /* If Cumulative TSN Ack beyond the max tsn currently * send, terminating the association and respond to the * sender with an ABORT. @@ -2624,6 +2640,7 @@ sctp_disposition_t sctp_sf_do_9_2_shut_ctsn(const struct sctp_endpoint *ep, { struct sctp_chunk *chunk = arg; sctp_shutdownhdr_t *sdh; + __u32 ctsn; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); @@ -2635,12 +2652,19 @@ sctp_disposition_t sctp_sf_do_9_2_shut_ctsn(const struct sctp_endpoint *ep, commands); sdh = (sctp_shutdownhdr_t *)chunk->skb->data; + ctsn = ntohl(sdh->cum_tsn_ack); + + if (TSN_lt(ctsn, asoc->ctsn_ack_point)) { + SCTP_DEBUG_PRINTK("ctsn %x\n", ctsn); + SCTP_DEBUG_PRINTK("ctsn_ack_point %x\n", asoc->ctsn_ack_point); + return SCTP_DISPOSITION_DISCARD; + } /* If Cumulative TSN Ack beyond the max tsn currently * send, terminating the association and respond to the * sender with an ABORT. */ - if (!TSN_lt(ntohl(sdh->cum_tsn_ack), asoc->next_tsn)) + if (!TSN_lt(ctsn, asoc->next_tsn)) return sctp_sf_violation_ctsn(ep, asoc, type, arg, commands); /* verify, by checking the Cumulative TSN Ack field of the @@ -2867,6 +2891,9 @@ sctp_disposition_t sctp_sf_eat_data_6_2(const struct sctp_endpoint *ep, goto discard_force; case SCTP_IERROR_NO_DATA: goto consume; + case SCTP_IERROR_PROTO_VIOLATION: + return sctp_sf_abort_violation(ep, asoc, chunk, commands, + (u8 *)chunk->subh.data_hdr, sizeof(sctp_datahdr_t)); default: BUG(); } @@ -2977,6 +3004,9 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(const struct sctp_endpoint *ep, break; case SCTP_IERROR_NO_DATA: goto consume; + case SCTP_IERROR_PROTO_VIOLATION: + return sctp_sf_abort_violation(ep, asoc, chunk, commands, + (u8 *)chunk->subh.data_hdr, sizeof(sctp_datahdr_t)); default: BUG(); } @@ -3519,6 +3549,12 @@ sctp_disposition_t sctp_sf_do_asconf(const struct sctp_endpoint *ep, asconf_ack = sctp_assoc_lookup_asconf_ack(asoc, hdr->serial); if (!asconf_ack) return SCTP_DISPOSITION_DISCARD; + + /* Reset the transport so that we select the correct one + * this time around. This is to make sure that we don't + * accidentally use a stale transport that's been removed. + */ + asconf_ack->transport = NULL; } else { /* ADDIP 5.2 E5) Otherwise, the ASCONF Chunk is discarded since * it must be either a stale packet or from an attacker. @@ -4546,9 +4582,9 @@ sctp_disposition_t sctp_sf_do_prm_send(const struct sctp_endpoint *ep, void *arg, sctp_cmd_seq_t *commands) { - struct sctp_chunk *chunk = arg; + struct sctp_datamsg *msg = arg; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(chunk)); + sctp_add_cmd_sf(commands, SCTP_CMD_SEND_MSG, SCTP_DATAMSG(msg)); return SCTP_DISPOSITION_CONSUME; } @@ -5847,6 +5883,9 @@ static int sctp_eat_data(const struct sctp_association *asoc, __u32 tsn; struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; struct sock *sk = asoc->base.sk; + u16 ssn; + u16 sid; + u8 ordered = 0; data_hdr = chunk->subh.data_hdr = (sctp_datahdr_t *)chunk->skb->data; skb_pull(chunk->skb, sizeof(sctp_datahdr_t)); @@ -5986,8 +6025,10 @@ static int sctp_eat_data(const struct sctp_association *asoc, */ if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) SCTP_INC_STATS(SCTP_MIB_INUNORDERCHUNKS); - else + else { SCTP_INC_STATS(SCTP_MIB_INORDERCHUNKS); + ordered = 1; + } /* RFC 2960 6.5 Stream Identifier and Stream Sequence Number * @@ -5997,7 +6038,8 @@ static int sctp_eat_data(const struct sctp_association *asoc, * with cause set to "Invalid Stream Identifier" (See Section 3.3.10) * and discard the DATA chunk. */ - if (ntohs(data_hdr->stream) >= asoc->c.sinit_max_instreams) { + sid = ntohs(data_hdr->stream); + if (sid >= asoc->c.sinit_max_instreams) { /* Mark tsn as received even though we drop it */ sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn)); @@ -6010,6 +6052,18 @@ static int sctp_eat_data(const struct sctp_association *asoc, return SCTP_IERROR_BAD_STREAM; } + /* Check to see if the SSN is possible for this TSN. + * The biggest gap we can record is 4K wide. Since SSNs wrap + * at an unsigned short, there is no way that an SSN can + * wrap and for a valid TSN. We can simply check if the current + * SSN is smaller then the next expected one. If it is, it wrapped + * and is invalid. + */ + ssn = ntohs(data_hdr->ssn); + if (ordered && SSN_lt(ssn, sctp_ssn_peek(&asoc->ssnmap->in, sid))) { + return SCTP_IERROR_PROTO_VIOLATION; + } + /* Send the data up to the user. Note: Schedule the * SCTP_CMD_CHUNK_ULP cmd before the SCTP_CMD_GEN_SACK, as the SACK * chunk needs the updated rwnd. diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 971890dbfea0..89af37a6c871 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1361,6 +1361,7 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) sctp_lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; + sk->sk_state = SCTP_SS_CLOSING; ep = sctp_sk(sk)->ep; @@ -1813,20 +1814,22 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, sctp_set_owner_w(chunk); chunk->transport = chunk_tp; - - /* Send it to the lower layers. Note: all chunks - * must either fail or succeed. The lower layer - * works that way today. Keep it that way or this - * breaks. - */ - err = sctp_primitive_SEND(asoc, chunk); - /* Did the lower layer accept the chunk? */ - if (err) - sctp_chunk_free(chunk); - SCTP_DEBUG_PRINTK("We sent primitively.\n"); } - sctp_datamsg_put(datamsg); + /* Send it to the lower layers. Note: all chunks + * must either fail or succeed. The lower layer + * works that way today. Keep it that way or this + * breaks. + */ + err = sctp_primitive_SEND(asoc, datamsg); + /* Did the lower layer accept the chunk? */ + if (err) + sctp_datamsg_free(datamsg); + else + sctp_datamsg_put(datamsg); + + SCTP_DEBUG_PRINTK("We sent primitively.\n"); + if (err) goto out_free; else @@ -2240,7 +2243,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, sctp_assoc_sync_pmtu(asoc); } else if (asoc) { asoc->pathmtu = params->spp_pathmtu; - sctp_frag_point(sp, params->spp_pathmtu); + sctp_frag_point(asoc, params->spp_pathmtu); } else { sp->pathmtu = params->spp_pathmtu; } @@ -2877,15 +2880,10 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optl val -= sizeof(struct sctphdr) + sizeof(struct sctp_data_chunk); } - - asoc->frag_point = val; + asoc->user_frag = val; + asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); } else { sp->user_frag = val; - - /* Update the frag_point of the existing associations. */ - list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { - asoc->frag_point = sctp_frag_point(sp, asoc->pathmtu); - } } return 0; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 63eabbc71298..ab7151da120f 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -51,6 +51,7 @@ static int timer_max = 86400000; /* ms in one day */ static int int_max = INT_MAX; static int sack_timer_min = 1; static int sack_timer_max = 500; +static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ extern int sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; @@ -272,6 +273,17 @@ static ctl_table sctp_table[] = { .proc_handler = proc_dointvec, .strategy = sysctl_intvec }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "addr_scope_policy", + .data = &sctp_scope_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &addr_scope_max, + }, { .ctl_name = 0 } }; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index e5dde45c79d3..c256e4839316 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -503,6 +503,9 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, transport->ssthresh = max(transport->cwnd/2, 4*transport->asoc->pathmtu); transport->cwnd = transport->asoc->pathmtu; + + /* T3-rtx also clears fast recovery on the transport */ + transport->fast_recovery = 0; break; case SCTP_LOWER_CWND_FAST_RTX: diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 5bc2f45bddf0..ebfcf9b89909 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -28,7 +28,6 @@ #include <linux/kallsyms.h> #include <linux/mm.h> #include <linux/slab.h> -#include <linux/smp_lock.h> #include <linux/utsname.h> #include <linux/workqueue.h> #include <linux/in6.h> diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 1102ce1251f7..8f459abe97cf 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -16,7 +16,6 @@ #include <linux/slab.h> #include <linux/mempool.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/spinlock.h> #include <linux/mutex.h> diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 6f33d33cc064..27d44332f017 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -5,6 +5,7 @@ */ #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/errno.h> #include <linux/freezer.h> #include <linux/kthread.h> diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a7a36779b9b3..327011fcc407 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -119,7 +119,7 @@ int tipc_register_media(u32 media_type, warn("Media <%s> rejected, no broadcast address\n", name); goto exit; } - if ((bearer_priority < TIPC_MIN_LINK_PRI) && + if ((bearer_priority < TIPC_MIN_LINK_PRI) || (bearer_priority > TIPC_MAX_LINK_PRI)) { warn("Media <%s> rejected, illegal priority (%u)\n", name, bearer_priority); diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 466e2d22d256..258daa80ad92 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -48,6 +48,7 @@ #include <linux/kernel.h> #include <linux/module.h> /* support for loadable modules */ #include <linux/slab.h> /* kmalloc(), kfree() */ +#include <linux/smp_lock.h> #include <linux/mm.h> #include <linux/string.h> /* inline mem*, str* functions */ diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index c6031d5b135f..abf7ca3f9ff9 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -1,6 +1,15 @@ config CFG80211 - tristate "Improved wireless configuration API" + tristate "cfg80211 - wireless configuration API" depends on RFKILL || !RFKILL + ---help--- + cfg80211 is the Linux wireless LAN (802.11) configuration API. + Enable this if you have a wireless device. + + For more information refer to documentation on the wireless wiki: + + http://wireless.kernel.org/en/developers/Documentation/cfg80211 + + When built as a module it will be called cfg80211. config NL80211_TESTMODE bool "nl80211 testmode command" @@ -17,12 +26,33 @@ config NL80211_TESTMODE Say N. +config CFG80211_DEVELOPER_WARNINGS + bool "enable developer warnings" + depends on CFG80211 + default n + help + This option enables some additional warnings that help + cfg80211 developers and driver developers, but that can + trigger due to races with userspace. + + For example, when a driver reports that it was disconnected + from the AP, but the user disconnects manually at the same + time, the warning might trigger spuriously due to races. + + Say Y only if you are developing cfg80211 or a driver based + on it (or mac80211). + + config CFG80211_REG_DEBUG bool "cfg80211 regulatory debugging" depends on CFG80211 default n ---help--- You can enable this if you want to debug regulatory changes. + For more information on cfg80211 regulatory refer to the wireless + wiki: + + http://wireless.kernel.org/en/developers/Regulatory If unsure, say N. diff --git a/net/wireless/Makefile b/net/wireless/Makefile index d74cc77fa57a..3ecaa9179977 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -5,7 +5,8 @@ obj-$(CONFIG_LIB80211_CRYPT_WEP) += lib80211_crypt_wep.o obj-$(CONFIG_LIB80211_CRYPT_CCMP) += lib80211_crypt_ccmp.o obj-$(CONFIG_LIB80211_CRYPT_TKIP) += lib80211_crypt_tkip.o -cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o mlme.o ibss.o sme.o +cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o +cfg80211-y += mlme.o ibss.o sme.o chan.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_WIRELESS_EXT) += wext-compat.o wext-sme.o diff --git a/net/wireless/chan.c b/net/wireless/chan.c new file mode 100644 index 000000000000..a46ac6c9b365 --- /dev/null +++ b/net/wireless/chan.c @@ -0,0 +1,89 @@ +/* + * This file contains helper code to handle channel + * settings and keeping track of what is possible at + * any point in time. + * + * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + */ + +#include <net/cfg80211.h> +#include "core.h" + +struct ieee80211_channel * +rdev_fixed_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *for_wdev) +{ + struct wireless_dev *wdev; + struct ieee80211_channel *result = NULL; + + WARN_ON(!mutex_is_locked(&rdev->devlist_mtx)); + + list_for_each_entry(wdev, &rdev->netdev_list, list) { + if (wdev == for_wdev) + continue; + + /* + * Lock manually to tell lockdep about allowed + * nesting here if for_wdev->mtx is held already. + * This is ok as it's all under the rdev devlist + * mutex and as such can only be done once at any + * given time. + */ + mutex_lock_nested(&wdev->mtx, SINGLE_DEPTH_NESTING); + if (wdev->current_bss) + result = wdev->current_bss->pub.channel; + wdev_unlock(wdev); + + if (result) + break; + } + + return result; +} + +int rdev_set_freq(struct cfg80211_registered_device *rdev, + struct wireless_dev *for_wdev, + int freq, enum nl80211_channel_type channel_type) +{ + struct ieee80211_channel *chan; + struct ieee80211_sta_ht_cap *ht_cap; + int result; + + if (rdev_fixed_channel(rdev, for_wdev)) + return -EBUSY; + + if (!rdev->ops->set_channel) + return -EOPNOTSUPP; + + chan = ieee80211_get_channel(&rdev->wiphy, freq); + + /* Primary channel not allowed */ + if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) + return -EINVAL; + + if (channel_type == NL80211_CHAN_HT40MINUS && + chan->flags & IEEE80211_CHAN_NO_HT40MINUS) + return -EINVAL; + else if (channel_type == NL80211_CHAN_HT40PLUS && + chan->flags & IEEE80211_CHAN_NO_HT40PLUS) + return -EINVAL; + + ht_cap = &rdev->wiphy.bands[chan->band]->ht_cap; + + if (channel_type != NL80211_CHAN_NO_HT) { + if (!ht_cap->ht_supported) + return -EINVAL; + + if (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) || + ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT) + return -EINVAL; + } + + result = rdev->ops->set_channel(&rdev->wiphy, chan, channel_type); + if (result) + return result; + + rdev->channel = chan; + + return 0; +} diff --git a/net/wireless/core.c b/net/wireless/core.c index 1e189306560d..45b2be3274db 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -12,6 +12,7 @@ #include <linux/debugfs.h> #include <linux/notifier.h> #include <linux/device.h> +#include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/genetlink.h> #include <net/cfg80211.h> @@ -32,6 +33,7 @@ MODULE_DESCRIPTION("wireless configuration support"); * only read the list, and that can happen quite * often because we need to do it for each command */ LIST_HEAD(cfg80211_rdev_list); +int cfg80211_rdev_list_generation; /* * This is used to protect the cfg80211_rdev_list @@ -292,68 +294,17 @@ static void cfg80211_rfkill_sync_work(struct work_struct *work) cfg80211_rfkill_set_block(rdev, rfkill_blocked(rdev->rfkill)); } -static void cfg80211_process_events(struct wireless_dev *wdev) -{ - struct cfg80211_event *ev; - unsigned long flags; - - spin_lock_irqsave(&wdev->event_lock, flags); - while (!list_empty(&wdev->event_list)) { - ev = list_first_entry(&wdev->event_list, - struct cfg80211_event, list); - list_del(&ev->list); - spin_unlock_irqrestore(&wdev->event_lock, flags); - - wdev_lock(wdev); - switch (ev->type) { - case EVENT_CONNECT_RESULT: - __cfg80211_connect_result( - wdev->netdev, ev->cr.bssid, - ev->cr.req_ie, ev->cr.req_ie_len, - ev->cr.resp_ie, ev->cr.resp_ie_len, - ev->cr.status, - ev->cr.status == WLAN_STATUS_SUCCESS, - NULL); - break; - case EVENT_ROAMED: - __cfg80211_roamed(wdev, ev->rm.bssid, - ev->rm.req_ie, ev->rm.req_ie_len, - ev->rm.resp_ie, ev->rm.resp_ie_len); - break; - case EVENT_DISCONNECTED: - __cfg80211_disconnected(wdev->netdev, - ev->dc.ie, ev->dc.ie_len, - ev->dc.reason, true); - break; - case EVENT_IBSS_JOINED: - __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid); - break; - } - wdev_unlock(wdev); - - kfree(ev); - - spin_lock_irqsave(&wdev->event_lock, flags); - } - spin_unlock_irqrestore(&wdev->event_lock, flags); -} - static void cfg80211_event_work(struct work_struct *work) { struct cfg80211_registered_device *rdev; - struct wireless_dev *wdev; rdev = container_of(work, struct cfg80211_registered_device, event_work); rtnl_lock(); cfg80211_lock_rdev(rdev); - mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) - cfg80211_process_events(wdev); - - mutex_unlock(&rdev->devlist_mtx); + cfg80211_process_rdev_events(rdev); cfg80211_unlock_rdev(rdev); rtnl_unlock(); } @@ -411,6 +362,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) rdev->wiphy.dev.class = &ieee80211_class; rdev->wiphy.dev.platform_data = rdev; + rdev->wiphy.ps_default = CONFIG_CFG80211_DEFAULT_PS_VALUE; + wiphy_net_set(&rdev->wiphy, &init_net); rdev->rfkill_ops.set_block = cfg80211_rfkill_set_block; @@ -427,6 +380,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) INIT_WORK(&rdev->conn_work, cfg80211_conn_work); INIT_WORK(&rdev->event_work, cfg80211_event_work); + init_waitqueue_head(&rdev->dev_wait); + /* * Initialize wiphy parameters to IEEE 802.11 MIB default values. * Fragmentation and RTS threshold are disabled by default with the @@ -511,6 +466,7 @@ int wiphy_register(struct wiphy *wiphy) wiphy_update_regulatory(wiphy, NL80211_REGDOM_SET_BY_CORE); list_add(&rdev->list, &cfg80211_rdev_list); + cfg80211_rdev_list_generation++; mutex_unlock(&cfg80211_mutex); @@ -570,7 +526,23 @@ void wiphy_unregister(struct wiphy *wiphy) /* protect the device list */ mutex_lock(&cfg80211_mutex); + wait_event(rdev->dev_wait, ({ + int __count; + mutex_lock(&rdev->devlist_mtx); + __count = rdev->opencount; + mutex_unlock(&rdev->devlist_mtx); + __count == 0;})); + + mutex_lock(&rdev->devlist_mtx); BUG_ON(!list_empty(&rdev->netdev_list)); + mutex_unlock(&rdev->devlist_mtx); + + /* + * First remove the hardware from everywhere, this makes + * it impossible to find from userspace. + */ + cfg80211_debugfs_rdev_del(rdev); + list_del(&rdev->list); /* * Try to grab rdev->mtx. If a command is still in progress, @@ -578,29 +550,26 @@ void wiphy_unregister(struct wiphy *wiphy) * down the device already. We wait for this command to complete * before unlinking the item from the list. * Note: as codified by the BUG_ON above we cannot get here if - * a virtual interface is still associated. Hence, we can only - * get to lock contention here if userspace issues a command - * that identified the hardware by wiphy index. + * a virtual interface is still present. Hence, we can only get + * to lock contention here if userspace issues a command that + * identified the hardware by wiphy index. */ - mutex_lock(&rdev->mtx); - /* unlock again before freeing */ - mutex_unlock(&rdev->mtx); - - cfg80211_debugfs_rdev_del(rdev); + cfg80211_lock_rdev(rdev); + /* nothing */ + cfg80211_unlock_rdev(rdev); /* If this device got a regulatory hint tell core its * free to listen now to a new shiny device regulatory hint */ reg_device_remove(wiphy); - list_del(&rdev->list); + cfg80211_rdev_list_generation++; device_del(&rdev->wiphy.dev); debugfs_remove(rdev->wiphy.debugfsdir); mutex_unlock(&cfg80211_mutex); + flush_work(&rdev->scan_done_wk); cancel_work_sync(&rdev->conn_work); - cancel_work_sync(&rdev->scan_done_wk); - kfree(rdev->scan_req); flush_work(&rdev->event_work); } EXPORT_SYMBOL(wiphy_unregister); @@ -631,6 +600,31 @@ void wiphy_rfkill_set_hw_state(struct wiphy *wiphy, bool blocked) } EXPORT_SYMBOL(wiphy_rfkill_set_hw_state); +static void wdev_cleanup_work(struct work_struct *work) +{ + struct wireless_dev *wdev; + struct cfg80211_registered_device *rdev; + + wdev = container_of(work, struct wireless_dev, cleanup_work); + rdev = wiphy_to_dev(wdev->wiphy); + + cfg80211_lock_rdev(rdev); + + if (WARN_ON(rdev->scan_req && rdev->scan_req->dev == wdev->netdev)) { + rdev->scan_req->aborted = true; + ___cfg80211_scan_done(rdev, true); + } + + cfg80211_unlock_rdev(rdev); + + mutex_lock(&rdev->devlist_mtx); + rdev->opencount--; + mutex_unlock(&rdev->devlist_mtx); + wake_up(&rdev->dev_wait); + + dev_put(wdev->netdev); +} + static int cfg80211_netdev_notifier_call(struct notifier_block * nb, unsigned long state, void *ndev) @@ -648,11 +642,18 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, switch (state) { case NETDEV_REGISTER: + /* + * NB: cannot take rdev->mtx here because this may be + * called within code protected by it when interfaces + * are added with nl80211. + */ mutex_init(&wdev->mtx); + INIT_WORK(&wdev->cleanup_work, wdev_cleanup_work); INIT_LIST_HEAD(&wdev->event_list); spin_lock_init(&wdev->event_lock); mutex_lock(&rdev->devlist_mtx); list_add(&wdev->list, &rdev->netdev_list); + rdev->devlist_generation++; /* can only change netns with wiphy */ dev->features |= NETIF_F_NETNS_LOCAL; @@ -670,7 +671,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, wdev->wext.default_key = -1; wdev->wext.default_mgmt_key = -1; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; - wdev->wext.ps = CONFIG_CFG80211_DEFAULT_PS_VALUE; + wdev->wext.ps = wdev->wiphy->ps_default; wdev->wext.ps_timeout = 100; if (rdev->ops->set_power_mgmt) if (rdev->ops->set_power_mgmt(wdev->wiphy, dev, @@ -703,9 +704,26 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, break; } break; + case NETDEV_DOWN: + dev_hold(dev); + schedule_work(&wdev->cleanup_work); + break; case NETDEV_UP: + /* + * If we have a really quick DOWN/UP succession we may + * have this work still pending ... cancel it and see + * if it was pending, in which case we need to account + * for some of the work it would have done. + */ + if (cancel_work_sync(&wdev->cleanup_work)) { + mutex_lock(&rdev->devlist_mtx); + rdev->opencount--; + mutex_unlock(&rdev->devlist_mtx); + dev_put(dev); + } #ifdef CONFIG_WIRELESS_EXT cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: @@ -718,10 +736,17 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, break; } wdev_unlock(wdev); + rdev->opencount++; + mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); #endif break; case NETDEV_UNREGISTER: + /* + * NB: cannot take rdev->mtx here because this may be + * called within code protected by it when interfaces + * are removed with nl80211. + */ mutex_lock(&rdev->devlist_mtx); /* * It is possible to get NETDEV_UNREGISTER @@ -733,7 +758,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, if (!list_empty(&wdev->list)) { sysfs_remove_link(&dev->dev.kobj, "phy80211"); list_del_init(&wdev->list); - mutex_destroy(&wdev->mtx); + rdev->devlist_generation++; #ifdef CONFIG_WIRELESS_EXT kfree(wdev->wext.keys); #endif diff --git a/net/wireless/core.h b/net/wireless/core.h index 325c17e6198c..2a33d8bc886b 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -49,6 +49,9 @@ struct cfg80211_registered_device { /* associate netdev list */ struct mutex devlist_mtx; struct list_head netdev_list; + int devlist_generation; + int opencount; /* also protected by devlist_mtx */ + wait_queue_head_t dev_wait; /* BSSes/scanning */ spinlock_t bss_lock; @@ -101,6 +104,7 @@ bool wiphy_idx_valid(int wiphy_idx) extern struct mutex cfg80211_mutex; extern struct list_head cfg80211_rdev_list; +extern int cfg80211_rdev_list_generation; #define assert_cfg80211_lock() WARN_ON(!mutex_is_locked(&cfg80211_mutex)) @@ -335,7 +339,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, int __cfg80211_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *connect, - struct cfg80211_cached_keys *connkeys); + struct cfg80211_cached_keys *connkeys, + const u8 *prev_bssid); int cfg80211_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *connect, @@ -353,6 +358,7 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_conn_work(struct work_struct *work); +bool cfg80211_sme_failed_reassoc(struct wireless_dev *wdev); /* internal helpers */ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, @@ -364,6 +370,29 @@ void cfg80211_sme_scan_done(struct net_device *dev); void cfg80211_sme_rx_auth(struct net_device *dev, const u8 *buf, size_t len); void cfg80211_sme_disassoc(struct net_device *dev, int idx); void __cfg80211_scan_done(struct work_struct *wk); +void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak); void cfg80211_upload_connect_keys(struct wireless_dev *wdev); +int cfg80211_change_iface(struct cfg80211_registered_device *rdev, + struct net_device *dev, enum nl80211_iftype ntype, + u32 *flags, struct vif_params *params); +void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev); + +struct ieee80211_channel * +rdev_fixed_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *for_wdev); +int rdev_set_freq(struct cfg80211_registered_device *rdev, + struct wireless_dev *for_wdev, + int freq, enum nl80211_channel_type channel_type); + +#ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS +#define CFG80211_DEV_WARN_ON(cond) WARN_ON(cond) +#else +/* + * Trick to enable using it as a condition, + * and also not give a warning when it's + * not used that way. + */ +#define CFG80211_DEV_WARN_ON(cond) ({bool __r = (cond); __r; }) +#endif #endif /* __NET_WIRELESS_CORE_H */ diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 4d7a084b35e2..c88338911979 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -22,7 +22,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) return; - if (WARN_ON(!wdev->ssid_len)) + if (!wdev->ssid_len) return; bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, @@ -58,6 +58,8 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) struct cfg80211_event *ev; unsigned long flags; + CFG80211_DEV_WARN_ON(!wdev->ssid_len); + ev = kzalloc(sizeof(*ev), gfp); if (!ev) return; @@ -78,10 +80,15 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, struct cfg80211_cached_keys *connkeys) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct ieee80211_channel *chan; int err; ASSERT_WDEV_LOCK(wdev); + chan = rdev_fixed_channel(rdev, wdev); + if (chan && chan != params->channel) + return -EBUSY; + if (wdev->ssid_len) return -EALREADY; @@ -112,9 +119,11 @@ int cfg80211_join_ibss(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev = dev->ieee80211_ptr; int err; + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); err = __cfg80211_join_ibss(rdev, dev, params, connkeys); wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); return err; } @@ -264,27 +273,32 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, int cfg80211_ibss_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra) + struct iw_freq *wextfreq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct ieee80211_channel *chan; - int err; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct ieee80211_channel *chan = NULL; + int err, freq; /* call only for ibss! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) return -EINVAL; - if (!wiphy_to_dev(wdev->wiphy)->ops->join_ibss) + if (!rdev->ops->join_ibss) return -EOPNOTSUPP; - chan = cfg80211_wext_freq(wdev->wiphy, freq); - if (chan && IS_ERR(chan)) - return PTR_ERR(chan); + freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); + if (freq < 0) + return freq; - if (chan && - (chan->flags & IEEE80211_CHAN_NO_IBSS || - chan->flags & IEEE80211_CHAN_DISABLED)) - return -EINVAL; + if (freq) { + chan = ieee80211_get_channel(wdev->wiphy, freq); + if (!chan) + return -EINVAL; + if (chan->flags & IEEE80211_CHAN_NO_IBSS || + chan->flags & IEEE80211_CHAN_DISABLED) + return -EINVAL; + } if (wdev->wext.ibss.channel == chan) return 0; @@ -292,8 +306,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, wdev_lock(wdev); err = 0; if (wdev->ssid_len) - err = __cfg80211_leave_ibss(wiphy_to_dev(wdev->wiphy), - dev, true); + err = __cfg80211_leave_ibss(rdev, dev, true); wdev_unlock(wdev); if (err) @@ -307,9 +320,11 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, wdev->wext.ibss.channel_fixed = false; } + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); - err = cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); + err = cfg80211_ibss_wext_join(rdev, wdev); wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); return err; } @@ -347,6 +362,7 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); size_t len = data->length; int err; @@ -354,14 +370,13 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) return -EINVAL; - if (!wiphy_to_dev(wdev->wiphy)->ops->join_ibss) + if (!rdev->ops->join_ibss) return -EOPNOTSUPP; wdev_lock(wdev); err = 0; if (wdev->ssid_len) - err = __cfg80211_leave_ibss(wiphy_to_dev(wdev->wiphy), - dev, true); + err = __cfg80211_leave_ibss(rdev, dev, true); wdev_unlock(wdev); if (err) @@ -375,9 +390,11 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev, memcpy(wdev->wext.ibss.ssid, ssid, len); wdev->wext.ibss.ssid_len = len; + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); - err = cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); + err = cfg80211_ibss_wext_join(rdev, wdev); wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); return err; } @@ -414,6 +431,7 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); u8 *bssid = ap_addr->sa_data; int err; @@ -421,7 +439,7 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) return -EINVAL; - if (!wiphy_to_dev(wdev->wiphy)->ops->join_ibss) + if (!rdev->ops->join_ibss) return -EOPNOTSUPP; if (ap_addr->sa_family != ARPHRD_ETHER) @@ -443,8 +461,7 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev, wdev_lock(wdev); err = 0; if (wdev->ssid_len) - err = __cfg80211_leave_ibss(wiphy_to_dev(wdev->wiphy), - dev, true); + err = __cfg80211_leave_ibss(rdev, dev, true); wdev_unlock(wdev); if (err) @@ -456,9 +473,11 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev, } else wdev->wext.ibss.bssid = NULL; + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); - err = cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); + err = cfg80211_ibss_wext_join(rdev, wdev); wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); return err; } diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 525e8e247b30..79d2eec54cec 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -67,6 +67,16 @@ void cfg80211_send_rx_assoc(struct net_device *dev, const u8 *buf, size_t len) status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code); + /* + * This is a bit of a hack, we don't notify userspace of + * a (re-)association reply if we tried to send a reassoc + * and got a reject -- we only try again with an assoc + * frame instead of reassoc. + */ + if (status_code != WLAN_STATUS_SUCCESS && wdev->conn && + cfg80211_sme_failed_reassoc(wdev)) + goto out; + nl80211_send_rx_assoc(rdev, dev, buf, len, GFP_KERNEL); if (status_code == WLAN_STATUS_SUCCESS) { @@ -86,6 +96,15 @@ void cfg80211_send_rx_assoc(struct net_device *dev, const u8 *buf, size_t len) WARN_ON(!bss); } + if (!wdev->conn && wdev->sme_state == CFG80211_SME_IDLE) { + /* + * This is for the userspace SME, the CONNECTING + * state will be changed to CONNECTED by + * __cfg80211_connect_result() below. + */ + wdev->sme_state = CFG80211_SME_CONNECTING; + } + /* this consumes one bss reference (unless bss is NULL) */ __cfg80211_connect_result(dev, mgmt->bssid, NULL, 0, ie, len - ieoffs, status_code, @@ -97,6 +116,7 @@ void cfg80211_send_rx_assoc(struct net_device *dev, const u8 *buf, size_t len) cfg80211_put_bss(&bss->pub); } + out: wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_rx_assoc); @@ -149,7 +169,7 @@ static void __cfg80211_send_deauth(struct net_device *dev, reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); - from_ap = memcmp(mgmt->da, dev->dev_addr, ETH_ALEN) == 0; + from_ap = memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) != 0; __cfg80211_disconnected(dev, NULL, 0, reason_code, from_ap); } else if (wdev->sme_state == CFG80211_SME_CONNECTING) { __cfg80211_connect_result(dev, mgmt->bssid, NULL, 0, NULL, 0, @@ -198,7 +218,7 @@ static void __cfg80211_send_disassoc(struct net_device *dev, return; if (wdev->current_bss && - memcmp(wdev->current_bss, bssid, ETH_ALEN) == 0) { + memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) { for (i = 0; i < MAX_AUTH_BSSES; i++) { if (wdev->authtry_bsses[i] || wdev->auth_bsses[i]) continue; @@ -215,7 +235,7 @@ static void __cfg80211_send_disassoc(struct net_device *dev, reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); - from_ap = memcmp(mgmt->da, dev->dev_addr, ETH_ALEN) == 0; + from_ap = memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) != 0; __cfg80211_disconnected(dev, NULL, 0, reason_code, from_ap); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0cd548267d4a..eddab097435c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -408,6 +408,9 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, dev->wiphy_idx); NLA_PUT_STRING(msg, NL80211_ATTR_WIPHY_NAME, wiphy_name(&dev->wiphy)); + NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, + cfg80211_rdev_list_generation); + NLA_PUT_U8(msg, NL80211_ATTR_WIPHY_RETRY_SHORT, dev->wiphy.retry_short); NLA_PUT_U8(msg, NL80211_ATTR_WIPHY_RETRY_LONG, @@ -701,15 +704,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - struct ieee80211_channel *chan; - struct ieee80211_sta_ht_cap *ht_cap; u32 freq; - if (!rdev->ops->set_channel) { - result = -EOPNOTSUPP; - goto bad_res; - } - result = -EINVAL; if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { @@ -723,42 +719,12 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); - chan = ieee80211_get_channel(&rdev->wiphy, freq); - /* Primary channel not allowed */ - if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) - goto bad_res; - - if (channel_type == NL80211_CHAN_HT40MINUS && - (chan->flags & IEEE80211_CHAN_NO_HT40MINUS)) - goto bad_res; - else if (channel_type == NL80211_CHAN_HT40PLUS && - (chan->flags & IEEE80211_CHAN_NO_HT40PLUS)) - goto bad_res; - - /* - * At this point we know if that if HT40 was requested - * we are allowed to use it and the extension channel - * exists. - */ - - ht_cap = &rdev->wiphy.bands[chan->band]->ht_cap; - - /* no HT capabilities or intolerant */ - if (channel_type != NL80211_CHAN_NO_HT) { - if (!ht_cap->ht_supported) - goto bad_res; - if (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) || - (ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT)) - goto bad_res; - } - - result = rdev->ops->set_channel(&rdev->wiphy, chan, - channel_type); + mutex_lock(&rdev->devlist_mtx); + result = rdev_set_freq(rdev, NULL, freq, channel_type); + mutex_unlock(&rdev->devlist_mtx); if (result) goto bad_res; - - rdev->channel = chan; } changed = 0; @@ -862,6 +828,11 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); NLA_PUT_STRING(msg, NL80211_ATTR_IFNAME, dev->name); NLA_PUT_U32(msg, NL80211_ATTR_IFTYPE, dev->ieee80211_ptr->iftype); + + NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, + rdev->devlist_generation ^ + (cfg80211_rdev_list_generation << 2)); + return genlmsg_end(msg, hdr); nla_put_failure: @@ -875,12 +846,12 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * int if_idx = 0; int wp_start = cb->args[0]; int if_start = cb->args[1]; - struct cfg80211_registered_device *dev; + struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; mutex_lock(&cfg80211_mutex); - list_for_each_entry(dev, &cfg80211_rdev_list, list) { - if (!net_eq(wiphy_net(&dev->wiphy), sock_net(skb->sk))) + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + if (!net_eq(wiphy_net(&rdev->wiphy), sock_net(skb->sk))) continue; if (wp_idx < wp_start) { wp_idx++; @@ -888,21 +859,21 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * } if_idx = 0; - mutex_lock(&dev->devlist_mtx); - list_for_each_entry(wdev, &dev->netdev_list, list) { + mutex_lock(&rdev->devlist_mtx); + list_for_each_entry(wdev, &rdev->netdev_list, list) { if (if_idx < if_start) { if_idx++; continue; } if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - dev, wdev->netdev) < 0) { - mutex_unlock(&dev->devlist_mtx); + rdev, wdev->netdev) < 0) { + mutex_unlock(&rdev->devlist_mtx); goto out; } if_idx++; } - mutex_unlock(&dev->devlist_mtx); + mutex_unlock(&rdev->devlist_mtx); wp_idx++; } @@ -1006,12 +977,6 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) } } - if (!rdev->ops->change_virtual_intf || - !(rdev->wiphy.interface_modes & (1 << ntype))) { - err = -EOPNOTSUPP; - goto unlock; - } - if (info->attrs[NL80211_ATTR_MESH_ID]) { if (ntype != NL80211_IFTYPE_MESH_POINT) { err = -EINVAL; @@ -1037,18 +1002,10 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) } if (change) - err = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, - ntype, flags, ¶ms); + err = cfg80211_change_iface(rdev, dev, ntype, flags, ¶ms); else err = 0; - WARN_ON(!err && dev->ieee80211_ptr->iftype != ntype); - - if (!err && (ntype != otype)) { - if (otype == NL80211_IFTYPE_ADHOC) - cfg80211_clear_ibss(dev, false); - } - unlock: dev_put(dev); cfg80211_unlock_rdev(rdev); @@ -1653,6 +1610,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr); + NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, sinfo->generation); + sinfoattr = nla_nest_start(msg, NL80211_ATTR_STA_INFO); if (!sinfoattr) goto nla_put_failure; @@ -2138,6 +2097,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, dst); NLA_PUT(msg, NL80211_ATTR_MPATH_NEXT_HOP, ETH_ALEN, next_hop); + NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, pinfo->generation); + pinfoattr = nla_nest_start(msg, NL80211_ATTR_MPATH_INFO); if (!pinfoattr) goto nla_put_failure; @@ -2220,7 +2181,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, if (netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) { err = -EOPNOTSUPP; - goto out; + goto out_err; } while (1) { @@ -3027,10 +2988,9 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) goto out; } - request->channels = (void *)((char *)request + sizeof(*request)); request->n_channels = n_channels; if (n_ssids) - request->ssids = (void *)(request->channels + n_channels); + request->ssids = (void *)&request->channels[n_channels]; request->n_ssids = n_ssids; if (ie_len) { if (request->ssids) @@ -3127,8 +3087,7 @@ static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (!hdr) return -1; - NLA_PUT_U32(msg, NL80211_ATTR_SCAN_GENERATION, - rdev->bss_generation); + NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, rdev->bss_generation); NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, wdev->netdev->ifindex); bss = nla_nest_start(msg, NL80211_ATTR_BSS); @@ -3453,7 +3412,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev; struct net_device *dev; struct cfg80211_crypto_settings crypto; - struct ieee80211_channel *chan; + struct ieee80211_channel *chan, *fixedchan; const u8 *bssid, *ssid, *ie = NULL, *prev_bssid = NULL; int err, ssid_len, ie_len = 0; bool use_mfp = false; @@ -3496,6 +3455,15 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto out; } + mutex_lock(&rdev->devlist_mtx); + fixedchan = rdev_fixed_channel(rdev, NULL); + if (fixedchan && chan != fixedchan) { + err = -EBUSY; + mutex_unlock(&rdev->devlist_mtx); + goto out; + } + mutex_unlock(&rdev->devlist_mtx); + ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index b3ac0aace0e5..f256dfffbf46 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1018,7 +1018,6 @@ static void handle_channel(struct wiphy *wiphy, enum ieee80211_band band, map_regdom_flags(reg_rule->flags) | bw_flags; chan->max_antenna_gain = chan->orig_mag = (int) MBI_TO_DBI(power_rule->max_antenna_gain); - chan->max_bandwidth = KHZ_TO_MHZ(desired_bw_khz); chan->max_power = chan->orig_mpwr = (int) MBM_TO_DBM(power_rule->max_eirp); return; @@ -1027,7 +1026,6 @@ static void handle_channel(struct wiphy *wiphy, enum ieee80211_band band, chan->flags = flags | bw_flags | map_regdom_flags(reg_rule->flags); chan->max_antenna_gain = min(chan->orig_mag, (int) MBI_TO_DBI(power_rule->max_antenna_gain)); - chan->max_bandwidth = KHZ_TO_MHZ(desired_bw_khz); if (chan->orig_mpwr) chan->max_power = min(chan->orig_mpwr, (int) MBM_TO_DBM(power_rule->max_eirp)); @@ -1095,17 +1093,18 @@ static void handle_reg_beacon(struct wiphy *wiphy, chan->beacon_found = true; + if (wiphy->disable_beacon_hints) + return; + chan_before.center_freq = chan->center_freq; chan_before.flags = chan->flags; - if ((chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) && - !(chan->orig_flags & IEEE80211_CHAN_PASSIVE_SCAN)) { + if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) { chan->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN; channel_changed = true; } - if ((chan->flags & IEEE80211_CHAN_NO_IBSS) && - !(chan->orig_flags & IEEE80211_CHAN_NO_IBSS)) { + if (chan->flags & IEEE80211_CHAN_NO_IBSS) { chan->flags &= ~IEEE80211_CHAN_NO_IBSS; channel_changed = true; } @@ -1328,7 +1327,6 @@ static void handle_channel_custom(struct wiphy *wiphy, chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags; chan->max_antenna_gain = (int) MBI_TO_DBI(power_rule->max_antenna_gain); - chan->max_bandwidth = KHZ_TO_MHZ(desired_bw_khz); chan->max_power = (int) MBM_TO_DBM(power_rule->max_eirp); } @@ -1426,7 +1424,7 @@ static int ignore_request(struct wiphy *wiphy, if (last_wiphy != wiphy) { /* * Two cards with two APs claiming different - * different Country IE alpha2s. We could + * Country IE alpha2s. We could * intersect them, but that seems unlikely * to be correct. Reject second one for now. */ diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 662a9dad76d5..3362c7c069b2 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -30,7 +30,8 @@ int set_regdom(const struct ieee80211_regdomain *rd); * non-radar 5 GHz channels. * * Drivers do not need to call this, cfg80211 will do it for after a scan - * on a newly found BSS. + * on a newly found BSS. If you cannot make use of this feature you can + * set the wiphy->disable_beacon_hints to true. */ int regulatory_hint_found_beacon(struct wiphy *wiphy, struct ieee80211_channel *beacon_chan, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 67714d7ed5b4..4c210c2debc6 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -18,21 +18,21 @@ #define IEEE80211_SCAN_RESULT_EXPIRE (15 * HZ) -void __cfg80211_scan_done(struct work_struct *wk) +void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) { - struct cfg80211_registered_device *rdev; struct cfg80211_scan_request *request; struct net_device *dev; #ifdef CONFIG_WIRELESS_EXT union iwreq_data wrqu; #endif - rdev = container_of(wk, struct cfg80211_registered_device, - scan_done_wk); + ASSERT_RDEV_LOCK(rdev); - mutex_lock(&rdev->mtx); request = rdev->scan_req; + if (!request) + return; + dev = request->dev; /* @@ -43,9 +43,9 @@ void __cfg80211_scan_done(struct work_struct *wk) cfg80211_sme_scan_done(dev); if (request->aborted) - nl80211_send_scan_aborted(wiphy_to_dev(request->wiphy), dev); + nl80211_send_scan_aborted(rdev, dev); else - nl80211_send_scan_done(wiphy_to_dev(request->wiphy), dev); + nl80211_send_scan_done(rdev, dev); #ifdef CONFIG_WIRELESS_EXT if (!request->aborted) { @@ -57,9 +57,30 @@ void __cfg80211_scan_done(struct work_struct *wk) dev_put(dev); + rdev->scan_req = NULL; + + /* + * OK. If this is invoked with "leak" then we can't + * free this ... but we've cleaned it up anyway. The + * driver failed to call the scan_done callback, so + * all bets are off, it might still be trying to use + * the scan request or not ... if it accesses the dev + * in there (it shouldn't anyway) then it may crash. + */ + if (!leak) + kfree(request); +} + +void __cfg80211_scan_done(struct work_struct *wk) +{ + struct cfg80211_registered_device *rdev; + + rdev = container_of(wk, struct cfg80211_registered_device, + scan_done_wk); + + cfg80211_lock_rdev(rdev); + ___cfg80211_scan_done(rdev, false); cfg80211_unlock_rdev(rdev); - wiphy_to_dev(request->wiphy)->scan_req = NULL; - kfree(request); } void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) @@ -120,7 +141,7 @@ void cfg80211_bss_expire(struct cfg80211_registered_device *dev) dev->bss_generation++; } -static u8 *find_ie(u8 num, u8 *ies, size_t len) +static u8 *find_ie(u8 num, u8 *ies, int len) { while (len > 2 && ies[0] != num) { len -= ies[1] + 2; @@ -141,7 +162,7 @@ static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2) if (!ie1 && !ie2) return 0; - if (!ie1) + if (!ie1 || !ie2) return -1; r = memcmp(ie1 + 2, ie2 + 2, min(ie1[1], ie2[1])); @@ -194,6 +215,8 @@ static bool is_mesh(struct cfg80211_bss *a, ie = find_ie(WLAN_EID_MESH_CONFIG, a->information_elements, a->len_information_elements); + if (!ie) + return false; if (ie[1] != IEEE80211_MESH_CONFIG_LEN) return false; @@ -560,6 +583,7 @@ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub) spin_lock_bh(&dev->bss_lock); list_del(&bss->list); + dev->bss_generation++; rb_erase(&bss->rbn, &dev->bss_tree); spin_unlock_bh(&dev->bss_lock); @@ -583,6 +607,9 @@ int cfg80211_wext_siwscan(struct net_device *dev, if (!netif_running(dev)) return -ENETDOWN; + if (wrqu->data.length == sizeof(struct iw_scan_req)) + wreq = (struct iw_scan_req *)extra; + rdev = cfg80211_get_dev_from_ifindex(dev_net(dev), dev->ifindex); if (IS_ERR(rdev)) @@ -595,9 +622,14 @@ int cfg80211_wext_siwscan(struct net_device *dev, wiphy = &rdev->wiphy; - for (band = 0; band < IEEE80211_NUM_BANDS; band++) - if (wiphy->bands[band]) - n_channels += wiphy->bands[band]->n_channels; + /* Determine number of channels, needed to allocate creq */ + if (wreq && wreq->num_channels) + n_channels = wreq->num_channels; + else { + for (band = 0; band < IEEE80211_NUM_BANDS; band++) + if (wiphy->bands[band]) + n_channels += wiphy->bands[band]->n_channels; + } creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) + n_channels * sizeof(void *), @@ -609,27 +641,46 @@ int cfg80211_wext_siwscan(struct net_device *dev, creq->wiphy = wiphy; creq->dev = dev; - creq->ssids = (void *)(creq + 1); - creq->channels = (void *)(creq->ssids + 1); + /* SSIDs come after channels */ + creq->ssids = (void *)&creq->channels[n_channels]; creq->n_channels = n_channels; creq->n_ssids = 1; - /* all channels */ + /* translate "Scan on frequencies" request */ i = 0; for (band = 0; band < IEEE80211_NUM_BANDS; band++) { int j; if (!wiphy->bands[band]) continue; for (j = 0; j < wiphy->bands[band]->n_channels; j++) { + + /* If we have a wireless request structure and the + * wireless request specifies frequencies, then search + * for the matching hardware channel. + */ + if (wreq && wreq->num_channels) { + int k; + int wiphy_freq = wiphy->bands[band]->channels[j].center_freq; + for (k = 0; k < wreq->num_channels; k++) { + int wext_freq = wreq->channel_list[k].m / 100000; + if (wext_freq == wiphy_freq) + goto wext_freq_found; + } + goto wext_freq_not_found; + } + + wext_freq_found: creq->channels[i] = &wiphy->bands[band]->channels[j]; i++; + wext_freq_not_found: ; } } - /* translate scan request */ - if (wrqu->data.length == sizeof(struct iw_scan_req)) { - wreq = (struct iw_scan_req *)extra; + /* Set real number of channels specified in creq->channels[] */ + creq->n_channels = i; + /* translate "Scan for SSID" request */ + if (wreq) { if (wrqu->data.flags & IW_SCAN_THIS_ESSID) { if (wreq->essid_len > IEEE80211_MAX_SSID_LEN) return -EINVAL; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 8a7dcbf90602..68307883ec87 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -27,10 +27,10 @@ struct cfg80211_conn { CFG80211_CONN_ASSOCIATE_NEXT, CFG80211_CONN_ASSOCIATING, } state; - u8 bssid[ETH_ALEN]; + u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; u8 *ie; size_t ie_len; - bool auto_auth; + bool auto_auth, prev_bssid_valid; }; @@ -65,7 +65,6 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) if (!request) return -ENOMEM; - request->channels = (void *)((char *)request + sizeof(*request)); if (wdev->conn->params.channel) request->channels[0] = wdev->conn->params.channel; else { @@ -82,7 +81,7 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) } } request->n_channels = n_channels; - request->ssids = (void *)(request->channels + n_channels); + request->ssids = (void *)&request->channels[n_channels]; request->n_ssids = 1; memcpy(request->ssids[0].ssid, wdev->conn->params.ssid, @@ -110,6 +109,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); struct cfg80211_connect_params *params; + const u8 *prev_bssid = NULL; int err; ASSERT_WDEV_LOCK(wdev); @@ -135,15 +135,11 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) case CFG80211_CONN_ASSOCIATE_NEXT: BUG_ON(!rdev->ops->assoc); wdev->conn->state = CFG80211_CONN_ASSOCIATING; - /* - * We could, later, implement roaming here and then actually - * set prev_bssid to non-NULL. But then we need to be aware - * that some APs don't like that -- so we'd need to retry - * the association. - */ + if (wdev->conn->prev_bssid_valid) + prev_bssid = wdev->conn->prev_bssid; err = __cfg80211_mlme_assoc(rdev, wdev->netdev, params->channel, params->bssid, - NULL, + prev_bssid, params->ssid, params->ssid_len, params->ie, params->ie_len, false, ¶ms->crypto); @@ -256,9 +252,11 @@ void cfg80211_sme_scan_done(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; + mutex_lock(&wiphy_to_dev(wdev->wiphy)->devlist_mtx); wdev_lock(wdev); __cfg80211_sme_scan_done(dev); wdev_unlock(wdev); + mutex_unlock(&wiphy_to_dev(wdev->wiphy)->devlist_mtx); } void cfg80211_sme_rx_auth(struct net_device *dev, @@ -314,6 +312,28 @@ void cfg80211_sme_rx_auth(struct net_device *dev, } } +bool cfg80211_sme_failed_reassoc(struct wireless_dev *wdev) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + if (WARN_ON(!wdev->conn)) + return false; + + if (!wdev->conn->prev_bssid_valid) + return false; + + /* + * Some stupid APs don't accept reassoc, so we + * need to fall back to trying regular assoc. + */ + wdev->conn->prev_bssid_valid = false; + wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; + schedule_work(&rdev->conn_work); + + return true; +} + void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, size_t resp_ie_len, @@ -331,15 +351,13 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return; - if (wdev->sme_state == CFG80211_SME_CONNECTED) - nl80211_send_roamed(wiphy_to_dev(wdev->wiphy), dev, + if (wdev->sme_state != CFG80211_SME_CONNECTING) + return; + + nl80211_send_connect_result(wiphy_to_dev(wdev->wiphy), dev, bssid, req_ie, req_ie_len, - resp_ie, resp_ie_len, GFP_KERNEL); - else - nl80211_send_connect_result(wiphy_to_dev(wdev->wiphy), dev, - bssid, req_ie, req_ie_len, - resp_ie, resp_ie_len, - status, GFP_KERNEL); + resp_ie, resp_ie_len, + status, GFP_KERNEL); #ifdef CONFIG_WIRELESS_EXT if (wextev) { @@ -357,8 +375,11 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; - if (bssid && status == WLAN_STATUS_SUCCESS) + if (bssid && status == WLAN_STATUS_SUCCESS) { memcpy(wrqu.ap_addr.sa_data, bssid, ETH_ALEN); + memcpy(wdev->wext.prev_bssid, bssid, ETH_ALEN); + wdev->wext.prev_bssid_valid = true; + } wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); } #endif @@ -369,18 +390,13 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, wdev->current_bss = NULL; } - if (status == WLAN_STATUS_SUCCESS && - wdev->sme_state == CFG80211_SME_IDLE) - goto success; - - if (wdev->sme_state != CFG80211_SME_CONNECTING) - return; - if (wdev->conn) wdev->conn->state = CFG80211_CONN_IDLE; if (status != WLAN_STATUS_SUCCESS) { wdev->sme_state = CFG80211_SME_IDLE; + if (wdev->conn) + kfree(wdev->conn->ie); kfree(wdev->conn); wdev->conn = NULL; kfree(wdev->connect_keys); @@ -389,7 +405,6 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, return; } - success: if (!bss) bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, wdev->ssid, wdev->ssid_len, @@ -430,12 +445,15 @@ void cfg80211_connect_result(struct net_device *dev, const u8 *bssid, struct cfg80211_event *ev; unsigned long flags; + CFG80211_DEV_WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTING); + ev = kzalloc(sizeof(*ev) + req_ie_len + resp_ie_len, gfp); if (!ev) return; ev->type = EVENT_CONNECT_RESULT; - memcpy(ev->cr.bssid, bssid, ETH_ALEN); + if (bssid) + memcpy(ev->cr.bssid, bssid, ETH_ALEN); ev->cr.req_ie = ((u8 *)ev) + sizeof(*ev); ev->cr.req_ie_len = req_ie_len; memcpy((void *)ev->cr.req_ie, req_ie, req_ie_len); @@ -465,7 +483,7 @@ void __cfg80211_roamed(struct wireless_dev *wdev, const u8 *bssid, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return; - if (WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTED)) + if (wdev->sme_state != CFG80211_SME_CONNECTED) return; /* internal error -- how did we get to CONNECTED w/o BSS? */ @@ -509,6 +527,8 @@ void __cfg80211_roamed(struct wireless_dev *wdev, const u8 *bssid, memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; memcpy(wrqu.ap_addr.sa_data, bssid, ETH_ALEN); + memcpy(wdev->wext.prev_bssid, bssid, ETH_ALEN); + wdev->wext.prev_bssid_valid = true; wireless_send_event(wdev->netdev, SIOCGIWAP, &wrqu, NULL); #endif } @@ -522,6 +542,8 @@ void cfg80211_roamed(struct net_device *dev, const u8 *bssid, struct cfg80211_event *ev; unsigned long flags; + CFG80211_DEV_WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTED); + ev = kzalloc(sizeof(*ev) + req_ie_len + resp_ie_len, gfp); if (!ev) return; @@ -557,7 +579,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return; - if (WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTED)) + if (wdev->sme_state != CFG80211_SME_CONNECTED) return; if (wdev->current_bss) { @@ -570,10 +592,30 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, wdev->ssid_len = 0; if (wdev->conn) { + const u8 *bssid; + int ret; + kfree(wdev->conn->ie); wdev->conn->ie = NULL; kfree(wdev->conn); wdev->conn = NULL; + + /* + * If this disconnect was due to a disassoc, we + * we might still have an auth BSS around. For + * the userspace SME that's currently expected, + * but for the kernel SME (nl80211 CONNECT or + * wireless extensions) we want to clear up all + * state. + */ + for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (!wdev->auth_bsses[i]) + continue; + bssid = wdev->auth_bsses[i]->pub.bssid; + ret = __cfg80211_mlme_deauth(rdev, dev, bssid, NULL, 0, + WLAN_REASON_DEAUTH_LEAVING); + WARN(ret, "deauth failed: %d\n", ret); + } } nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); @@ -601,6 +643,8 @@ void cfg80211_disconnected(struct net_device *dev, u16 reason, struct cfg80211_event *ev; unsigned long flags; + CFG80211_DEV_WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTED); + ev = kzalloc(sizeof(*ev) + ie_len, gfp); if (!ev) return; @@ -621,9 +665,11 @@ EXPORT_SYMBOL(cfg80211_disconnected); int __cfg80211_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *connect, - struct cfg80211_cached_keys *connkeys) + struct cfg80211_cached_keys *connkeys, + const u8 *prev_bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct ieee80211_channel *chan; int err; ASSERT_WDEV_LOCK(wdev); @@ -631,6 +677,10 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, if (wdev->sme_state != CFG80211_SME_IDLE) return -EALREADY; + chan = rdev_fixed_channel(rdev, wdev); + if (chan && chan != connect->channel) + return -EBUSY; + if (WARN_ON(wdev->connect_keys)) { kfree(wdev->connect_keys); wdev->connect_keys = NULL; @@ -638,14 +688,28 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, if (connkeys && connkeys->def >= 0) { int idx; + u32 cipher; idx = connkeys->def; + cipher = connkeys->params[idx].cipher; /* If given a WEP key we may need it for shared key auth */ - if (connkeys->params[idx].cipher == WLAN_CIPHER_SUITE_WEP40 || - connkeys->params[idx].cipher == WLAN_CIPHER_SUITE_WEP104) { + if (cipher == WLAN_CIPHER_SUITE_WEP40 || + cipher == WLAN_CIPHER_SUITE_WEP104) { connect->key_idx = idx; connect->key = connkeys->params[idx].key; connect->key_len = connkeys->params[idx].key_len; + + /* + * If ciphers are not set (e.g. when going through + * iwconfig), we have to set them appropriately here. + */ + if (connect->crypto.cipher_group == 0) + connect->crypto.cipher_group = cipher; + + if (connect->crypto.n_ciphers_pairwise == 0) { + connect->crypto.n_ciphers_pairwise = 1; + connect->crypto.ciphers_pairwise[0] = cipher; + } } } @@ -701,6 +765,11 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, wdev->sme_state = CFG80211_SME_CONNECTING; wdev->connect_keys = connkeys; + if (prev_bssid) { + memcpy(wdev->conn->prev_bssid, prev_bssid, ETH_ALEN); + wdev->conn->prev_bssid_valid = true; + } + /* we're good if we have both BSSID and channel */ if (wdev->conn->params.bssid && wdev->conn->params.channel) { wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; @@ -719,6 +788,7 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, } } if (err) { + kfree(wdev->conn->ie); kfree(wdev->conn); wdev->conn = NULL; wdev->sme_state = CFG80211_SME_IDLE; @@ -751,9 +821,11 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, { int err; + mutex_lock(&rdev->devlist_mtx); wdev_lock(dev->ieee80211_ptr); - err = __cfg80211_connect(rdev, dev, connect, connkeys); + err = __cfg80211_connect(rdev, dev, connect, connkeys, NULL); wdev_unlock(dev->ieee80211_ptr); + mutex_unlock(&rdev->devlist_mtx); return err; } @@ -786,6 +858,7 @@ int __cfg80211_disconnect(struct cfg80211_registered_device *rdev, (wdev->conn->state == CFG80211_CONN_SCANNING || wdev->conn->state == CFG80211_CONN_SCAN_AGAIN)) { wdev->sme_state = CFG80211_SME_IDLE; + kfree(wdev->conn->ie); kfree(wdev->conn); wdev->conn = NULL; wdev->ssid_len = 0; diff --git a/net/wireless/util.c b/net/wireless/util.c index ba387d85dcfd..3fc2df86278f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -274,11 +274,11 @@ static int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) switch (ae) { case 0: return 6; - case 1: + case MESH_FLAGS_AE_A4: return 12; - case 2: + case MESH_FLAGS_AE_A5_A6: return 18; - case 3: + case (MESH_FLAGS_AE_A4 | MESH_FLAGS_AE_A5_A6): return 24; default: return 6; @@ -333,10 +333,18 @@ int ieee80211_data_to_8023(struct sk_buff *skb, u8 *addr, } break; case cpu_to_le16(IEEE80211_FCTL_FROMDS): - if (iftype != NL80211_IFTYPE_STATION || + if ((iftype != NL80211_IFTYPE_STATION && + iftype != NL80211_IFTYPE_MESH_POINT) || (is_multicast_ether_addr(dst) && !compare_ether_addr(src, addr))) return -1; + if (iftype == NL80211_IFTYPE_MESH_POINT) { + struct ieee80211s_hdr *meshdr = + (struct ieee80211s_hdr *) (skb->data + hdrlen); + hdrlen += ieee80211_get_mesh_hdrlen(meshdr); + if (meshdr->flags & MESH_FLAGS_AE_A4) + memcpy(src, meshdr->eaddr1, ETH_ALEN); + } break; case cpu_to_le16(0): if (iftype != NL80211_IFTYPE_ADHOC) @@ -566,3 +574,111 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev) kfree(wdev->connect_keys); wdev->connect_keys = NULL; } + +static void cfg80211_process_wdev_events(struct wireless_dev *wdev) +{ + struct cfg80211_event *ev; + unsigned long flags; + const u8 *bssid = NULL; + + spin_lock_irqsave(&wdev->event_lock, flags); + while (!list_empty(&wdev->event_list)) { + ev = list_first_entry(&wdev->event_list, + struct cfg80211_event, list); + list_del(&ev->list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + + wdev_lock(wdev); + switch (ev->type) { + case EVENT_CONNECT_RESULT: + if (!is_zero_ether_addr(ev->cr.bssid)) + bssid = ev->cr.bssid; + __cfg80211_connect_result( + wdev->netdev, bssid, + ev->cr.req_ie, ev->cr.req_ie_len, + ev->cr.resp_ie, ev->cr.resp_ie_len, + ev->cr.status, + ev->cr.status == WLAN_STATUS_SUCCESS, + NULL); + break; + case EVENT_ROAMED: + __cfg80211_roamed(wdev, ev->rm.bssid, + ev->rm.req_ie, ev->rm.req_ie_len, + ev->rm.resp_ie, ev->rm.resp_ie_len); + break; + case EVENT_DISCONNECTED: + __cfg80211_disconnected(wdev->netdev, + ev->dc.ie, ev->dc.ie_len, + ev->dc.reason, true); + break; + case EVENT_IBSS_JOINED: + __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid); + break; + } + wdev_unlock(wdev); + + kfree(ev); + + spin_lock_irqsave(&wdev->event_lock, flags); + } + spin_unlock_irqrestore(&wdev->event_lock, flags); +} + +void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev) +{ + struct wireless_dev *wdev; + + ASSERT_RTNL(); + ASSERT_RDEV_LOCK(rdev); + + mutex_lock(&rdev->devlist_mtx); + + list_for_each_entry(wdev, &rdev->netdev_list, list) + cfg80211_process_wdev_events(wdev); + + mutex_unlock(&rdev->devlist_mtx); +} + +int cfg80211_change_iface(struct cfg80211_registered_device *rdev, + struct net_device *dev, enum nl80211_iftype ntype, + u32 *flags, struct vif_params *params) +{ + int err; + enum nl80211_iftype otype = dev->ieee80211_ptr->iftype; + + ASSERT_RDEV_LOCK(rdev); + + /* don't support changing VLANs, you just re-create them */ + if (otype == NL80211_IFTYPE_AP_VLAN) + return -EOPNOTSUPP; + + if (!rdev->ops->change_virtual_intf || + !(rdev->wiphy.interface_modes & (1 << ntype))) + return -EOPNOTSUPP; + + if (ntype != otype) { + switch (otype) { + case NL80211_IFTYPE_ADHOC: + cfg80211_leave_ibss(rdev, dev, false); + break; + case NL80211_IFTYPE_STATION: + cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, true); + break; + case NL80211_IFTYPE_MESH_POINT: + /* mesh should be handled? */ + break; + default: + break; + } + + cfg80211_process_rdev_events(rdev); + } + + err = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, + ntype, flags, params); + + WARN_ON(!err && dev->ieee80211_ptr->iftype != ntype); + + return err; +} diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index e4e90e249bab..429dd06a4ecc 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -70,18 +70,8 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, enum nl80211_iftype type; int ret; - if (!wdev) - return -EOPNOTSUPP; - rdev = wiphy_to_dev(wdev->wiphy); - if (!rdev->ops->change_virtual_intf) - return -EOPNOTSUPP; - - /* don't support changing VLANs, you just re-create them */ - if (wdev->iftype == NL80211_IFTYPE_AP_VLAN) - return -EOPNOTSUPP; - switch (*mode) { case IW_MODE_INFRA: type = NL80211_IFTYPE_STATION; @@ -104,9 +94,9 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, memset(&vifparams, 0, sizeof(vifparams)); - ret = rdev->ops->change_virtual_intf(wdev->wiphy, dev, type, - NULL, &vifparams); - WARN_ON(!ret && wdev->iftype != type); + cfg80211_lock_rdev(rdev); + ret = cfg80211_change_iface(rdev, dev, type, NULL, &vifparams); + cfg80211_unlock_rdev(rdev); return ret; } @@ -267,39 +257,26 @@ EXPORT_SYMBOL_GPL(cfg80211_wext_giwrange); * @wiphy: the wiphy * @freq: the wext freq encoding * - * Returns a channel, %NULL for auto, or an ERR_PTR for errors! + * Returns a frequency, or a negative error code, or 0 for auto. */ -struct ieee80211_channel *cfg80211_wext_freq(struct wiphy *wiphy, - struct iw_freq *freq) +int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq) { - struct ieee80211_channel *chan; - int f; - /* - * Parse frequency - return NULL for auto and + * Parse frequency - return 0 for auto and * -EINVAL for impossible things. */ if (freq->e == 0) { if (freq->m < 0) - return NULL; - f = ieee80211_channel_to_frequency(freq->m); + return 0; + return ieee80211_channel_to_frequency(freq->m); } else { int i, div = 1000000; for (i = 0; i < freq->e; i++) div /= 10; if (div <= 0) - return ERR_PTR(-EINVAL); - f = freq->m / div; + return -EINVAL; + return freq->m / div; } - - /* - * Look up channel struct and return -EINVAL when - * it cannot be found. - */ - chan = ieee80211_get_channel(wiphy, f); - if (!chan) - return ERR_PTR(-EINVAL); - return chan; } int cfg80211_wext_siwrts(struct net_device *dev, @@ -761,30 +738,27 @@ EXPORT_SYMBOL_GPL(cfg80211_wext_giwencode); int cfg80211_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra) + struct iw_freq *wextfreq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); - struct ieee80211_channel *chan; - int err; + int freq, err; switch (wdev->iftype) { case NL80211_IFTYPE_STATION: - return cfg80211_mgd_wext_siwfreq(dev, info, freq, extra); + return cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); case NL80211_IFTYPE_ADHOC: - return cfg80211_ibss_wext_siwfreq(dev, info, freq, extra); + return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); default: - chan = cfg80211_wext_freq(wdev->wiphy, freq); - if (!chan) + freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); + if (freq < 0) + return freq; + if (freq == 0) return -EINVAL; - if (IS_ERR(chan)) - return PTR_ERR(chan); - err = rdev->ops->set_channel(wdev->wiphy, chan, - NL80211_CHAN_NO_HT); - if (err) - return err; - rdev->channel = chan; - return 0; + mutex_lock(&rdev->devlist_mtx); + err = rdev_set_freq(rdev, NULL, freq, NL80211_CHAN_NO_HT); + mutex_unlock(&rdev->devlist_mtx); + return err; } } EXPORT_SYMBOL_GPL(cfg80211_wext_siwfreq); diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h index 9a3774749589..20b3daef6964 100644 --- a/net/wireless/wext-compat.h +++ b/net/wireless/wext-compat.h @@ -42,8 +42,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *ssid); -struct ieee80211_channel *cfg80211_wext_freq(struct wiphy *wiphy, - struct iw_freq *freq); +int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq); extern const struct iw_handler_def cfg80211_wext_handler; diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 7bacbd1c2af6..d16cd9ea4d00 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -15,6 +15,7 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { struct cfg80211_cached_keys *ck = NULL; + const u8 *prev_bssid = NULL; int err, i; ASSERT_RDEV_LOCK(rdev); @@ -42,8 +43,12 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, for (i = 0; i < 6; i++) ck->params[i].key = ck->data[i]; } + + if (wdev->wext.prev_bssid_valid) + prev_bssid = wdev->wext.prev_bssid; + err = __cfg80211_connect(rdev, wdev->netdev, - &wdev->wext.connect, ck); + &wdev->wext.connect, ck, prev_bssid); if (err) kfree(ck); @@ -52,25 +57,31 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, int cfg80211_mgd_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra) + struct iw_freq *wextfreq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); - struct ieee80211_channel *chan; - int err; + struct ieee80211_channel *chan = NULL; + int err, freq; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; - chan = cfg80211_wext_freq(wdev->wiphy, freq); - if (chan && IS_ERR(chan)) - return PTR_ERR(chan); + freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); + if (freq < 0) + return freq; - if (chan && (chan->flags & IEEE80211_CHAN_DISABLED)) - return -EINVAL; + if (freq) { + chan = ieee80211_get_channel(wdev->wiphy, freq); + if (!chan) + return -EINVAL; + if (chan->flags & IEEE80211_CHAN_DISABLED) + return -EINVAL; + } cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); if (wdev->sme_state != CFG80211_SME_IDLE) { @@ -84,9 +95,8 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev, /* if SSID set, we'll try right again, avoid event */ if (wdev->wext.connect.ssid_len) event = false; - err = __cfg80211_disconnect(wiphy_to_dev(wdev->wiphy), - dev, WLAN_REASON_DEAUTH_LEAVING, - event); + err = __cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, event); if (err) goto out; } @@ -95,17 +105,15 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev, wdev->wext.connect.channel = chan; /* SSID is not set, we just want to switch channel */ - if (wdev->wext.connect.ssid_len && chan) { - err = -EOPNOTSUPP; - if (rdev->ops->set_channel) - err = rdev->ops->set_channel(wdev->wiphy, chan, - NL80211_CHAN_NO_HT); + if (chan && !wdev->wext.connect.ssid_len) { + err = rdev_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); goto out; } - err = cfg80211_mgd_wext_connect(wiphy_to_dev(wdev->wiphy), wdev); + err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); return err; } @@ -143,6 +151,7 @@ int cfg80211_mgd_wext_siwessid(struct net_device *dev, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); size_t len = data->length; int err; @@ -157,7 +166,8 @@ int cfg80211_mgd_wext_siwessid(struct net_device *dev, if (len > 0 && ssid[len - 1] == '\0') len--; - cfg80211_lock_rdev(wiphy_to_dev(wdev->wiphy)); + cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); err = 0; @@ -173,23 +183,24 @@ int cfg80211_mgd_wext_siwessid(struct net_device *dev, /* if SSID set now, we'll try to connect, avoid event */ if (len) event = false; - err = __cfg80211_disconnect(wiphy_to_dev(wdev->wiphy), - dev, WLAN_REASON_DEAUTH_LEAVING, - event); + err = __cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, event); if (err) goto out; } + wdev->wext.prev_bssid_valid = false; wdev->wext.connect.ssid = wdev->wext.ssid; memcpy(wdev->wext.ssid, ssid, len); wdev->wext.connect.ssid_len = len; wdev->wext.connect.crypto.control_port = false; - err = cfg80211_mgd_wext_connect(wiphy_to_dev(wdev->wiphy), wdev); + err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); - cfg80211_unlock_rdev(wiphy_to_dev(wdev->wiphy)); + mutex_unlock(&rdev->devlist_mtx); + cfg80211_unlock_rdev(rdev); return err; } @@ -206,7 +217,15 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, data->flags = 0; wdev_lock(wdev); - if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { + if (wdev->current_bss) { + const u8 *ie = ieee80211_bss_get_ie(&wdev->current_bss->pub, + WLAN_EID_SSID); + if (ie) { + data->flags = 1; + data->length = ie[1]; + memcpy(ssid, ie + 2, data->length); + } + } else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { data->flags = 1; data->length = wdev->wext.connect.ssid_len; memcpy(ssid, wdev->wext.connect.ssid, data->length); @@ -222,6 +241,7 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); u8 *bssid = ap_addr->sa_data; int err; @@ -236,7 +256,8 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev, if (is_zero_ether_addr(bssid) || is_broadcast_ether_addr(bssid)) bssid = NULL; - cfg80211_lock_rdev(wiphy_to_dev(wdev->wiphy)); + cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->devlist_mtx); wdev_lock(wdev); if (wdev->sme_state != CFG80211_SME_IDLE) { @@ -250,9 +271,8 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev, compare_ether_addr(bssid, wdev->wext.connect.bssid) == 0) goto out; - err = __cfg80211_disconnect(wiphy_to_dev(wdev->wiphy), - dev, WLAN_REASON_DEAUTH_LEAVING, - false); + err = __cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, false); if (err) goto out; } @@ -263,10 +283,11 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev, } else wdev->wext.connect.bssid = NULL; - err = cfg80211_mgd_wext_connect(wiphy_to_dev(wdev->wiphy), wdev); + err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); - cfg80211_unlock_rdev(wiphy_to_dev(wdev->wiphy)); + mutex_unlock(&rdev->devlist_mtx); + cfg80211_unlock_rdev(rdev); return err; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 21cdc872004e..5e6c072c64d3 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -40,6 +40,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/net.h> diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h index d401dc8f05ed..e5195c99f71e 100644 --- a/net/xfrm/xfrm_hash.h +++ b/net/xfrm/xfrm_hash.h @@ -16,7 +16,7 @@ static inline unsigned int __xfrm6_addr_hash(xfrm_address_t *addr) static inline unsigned int __xfrm4_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) { - return ntohl(daddr->a4 ^ saddr->a4); + return ntohl(daddr->a4 + saddr->a4); } static inline unsigned int __xfrm6_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index a2adb51849a9..fef8db553e8d 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -60,7 +60,7 @@ static int xfrm_statistics_seq_open(struct inode *inode, struct file *file) return single_open_net(inode, file, xfrm_statistics_seq_show); } -static struct file_operations xfrm_statistics_seq_fops = { +static const struct file_operations xfrm_statistics_seq_fops = { .owner = THIS_MODULE, .open = xfrm_statistics_seq_open, .read = seq_read, |