diff options
author | Frederic Weisbecker <fweisbec@gmail.com> | 2009-12-07 07:28:35 +0100 |
---|---|---|
committer | Frederic Weisbecker <fweisbec@gmail.com> | 2009-12-07 07:29:22 +0100 |
commit | 6548698f929814375fa5d62ae1db96959b0418c1 (patch) | |
tree | 340924ae82cb0946aa15045b2b72186de52a8146 /net | |
parent | 1d2c6cfd40b2dece3bb958cbbc405a2c1536ab75 (diff) | |
parent | 22763c5cf3690a681551162c15d34d935308c8d7 (diff) |
Merge commit 'v2.6.32' into reiserfs/kill-bkl
Merge-reason: The tree was based 2.6.31. It's better to be up to date
with 2.6.32. Although no conflicting changes were made in between,
it gives benchmarking results closer to the lastest kernel behaviour.
Diffstat (limited to 'net')
437 files changed, 21383 insertions, 10124 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index fe649081fbd..a29c5ab5815 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -225,12 +225,6 @@ int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id) return -EOPNOTSUPP; } - /* The real device must be up and operating in order to - * assosciate a VLAN device with it. - */ - if (!(real_dev->flags & IFF_UP)) - return -ENETDOWN; - if (__find_vlan_dev(real_dev, vlan_id) != NULL) return -EEXIST; @@ -287,8 +281,11 @@ out_uninit_applicant: if (ngrp) vlan_gvrp_uninit_applicant(real_dev); out_free_group: - if (ngrp) - vlan_group_free(ngrp); + if (ngrp) { + hlist_del_rcu(&ngrp->hlist); + /* Free the group, after all cpu's are done. */ + call_rcu(&ngrp->rcu, vlan_rcu_free); + } return err; } @@ -336,12 +333,13 @@ 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. @@ -397,6 +395,9 @@ 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); @@ -468,6 +469,19 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, } break; + case NETDEV_CHANGEMTU: + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + vlandev = vlan_group_get_device(grp, i); + if (!vlandev) + continue; + + if (vlandev->mtu <= dev->mtu) + continue; + + dev_set_mtu(vlandev, dev->mtu); + } + break; + case NETDEV_FEAT_CHANGE: /* Propagate device features to underlying device */ for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 96bad8f233e..4198ec5c8ab 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 e9c91dcecc9..a9150485019 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[]) { @@ -150,6 +169,7 @@ static size_t vlan_get_size(const struct net_device *dev) struct vlan_dev_info *vlan = vlan_dev_info(dev); return nla_total_size(2) + /* IFLA_VLAN_ID */ + sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */ vlan_qos_map_size(vlan->nr_ingress_mappings) + vlan_qos_map_size(vlan->nr_egress_mappings); } @@ -216,6 +236,7 @@ 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/8021q/vlanproc.c b/net/8021q/vlanproc.c index b55a091a33d..6262c335f3c 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -107,7 +107,7 @@ static const struct file_operations vlandev_fops = { */ /* Strings */ -static const char *vlan_name_type_str[VLAN_NAME_TYPE_HIGHEST] = { +static const char *const vlan_name_type_str[VLAN_NAME_TYPE_HIGHEST] = { [VLAN_NAME_TYPE_RAW_PLUS_VID] = "VLAN_NAME_TYPE_RAW_PLUS_VID", [VLAN_NAME_TYPE_PLUS_VID_NO_PAD] = "VLAN_NAME_TYPE_PLUS_VID_NO_PAD", [VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD] = "VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD", diff --git a/net/9p/client.c b/net/9p/client.c index 5bf5f227dbe..8af95b2dddd 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -582,11 +582,9 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt) memset(&fid->qid, 0, sizeof(struct p9_qid)); fid->mode = -1; - fid->rdir_fpos = 0; fid->uid = current_fsuid(); fid->clnt = clnt; - fid->aux = NULL; - + fid->rdir = NULL; spin_lock_irqsave(&clnt->lock, flags); list_add(&fid->flist, &clnt->fidlist); spin_unlock_irqrestore(&clnt->lock, flags); @@ -609,6 +607,7 @@ static void p9_fid_destroy(struct p9_fid *fid) spin_lock_irqsave(&clnt->lock, flags); list_del(&fid->flist); spin_unlock_irqrestore(&clnt->lock, flags); + kfree(fid->rdir); kfree(fid); } diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 9bf0b737aa5..ea1e3daabef 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -200,7 +200,7 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req) req->status = REQ_STATUS_SENT; - if (chan->vq->vq_ops->add_buf(chan->vq, chan->sg, out, in, req->tc)) { + if (chan->vq->vq_ops->add_buf(chan->vq, chan->sg, out, in, req->tc) < 0) { P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio rpc add_buf returned failure"); return -EIO; @@ -334,8 +334,6 @@ static void p9_virtio_remove(struct virtio_device *vdev) } } -#define VIRTIO_ID_9P 9 - static struct virtio_device_id id_table[] = { { VIRTIO_ID_9P, VIRTIO_DEV_ANY_ID }, { 0 }, diff --git a/net/Kconfig b/net/Kconfig index 7051b971067..041c35edb76 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -23,6 +23,26 @@ menuconfig NET if NET +config WANT_COMPAT_NETLINK_MESSAGES + bool + help + This option can be selected by other options that need compat + netlink messages. + +config COMPAT_NETLINK_MESSAGES + def_bool y + depends on COMPAT + depends on WIRELESS_EXT || WANT_COMPAT_NETLINK_MESSAGES + help + This option makes it possible to send different netlink messages + to tasks depending on whether the task is a compat task or not. To + achieve this, you need to set skb_shinfo(skb)->frag_list to the + compat skb before sending the skb, the netlink code will sort out + which message to actually pass to the task. + + Newly written code should NEVER need this option but do + compat-independent messages instead! + menu "Networking options" source "net/packet/Kconfig" diff --git a/net/Makefile b/net/Makefile index ba324aefda7..1542e7268a7 100644 --- a/net/Makefile +++ b/net/Makefile @@ -24,7 +24,6 @@ obj-y += ipv6/ endif obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ -obj-$(CONFIG_NET_SCHED) += sched/ obj-$(CONFIG_BRIDGE) += bridge/ obj-$(CONFIG_NET_DSA) += dsa/ obj-$(CONFIG_IPX) += ipx/ diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 89f99d3beb6..9d4adfd2275 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -599,7 +599,7 @@ int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb, /* Non ELAP we cannot do. */ if (dev->type != ARPHRD_ETHER) - return -1; + goto free_it; skb->dev = dev; skb->protocol = htons(ETH_P_ATALK); @@ -634,7 +634,7 @@ int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb, if (!a) { /* Whoops slipped... good job it's an unreliable protocol 8) */ write_unlock_bh(&aarp_lock); - return -1; + goto free_it; } /* Set up the queue */ @@ -663,15 +663,21 @@ out_unlock: write_unlock_bh(&aarp_lock); /* Tell the ddp layer we have taken over for this frame. */ - return 0; + goto sent; sendit: if (skb->sk) skb->priority = skb->sk->sk_priority; - dev_queue_xmit(skb); + if (dev_queue_xmit(skb)) + goto drop; sent: - return 1; + return NET_XMIT_SUCCESS; +free_it: + kfree_skb(skb); +drop: + return NET_XMIT_DROP; } +EXPORT_SYMBOL(aarp_send_ddp); /* * An entry in the aarp unresolved queue has become resolved. Send diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 875eda5dbad..b1a4290996b 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1270,8 +1270,10 @@ static int handle_ip_over_ddp(struct sk_buff *skb) struct net_device_stats *stats; /* This needs to be able to handle ipddp"N" devices */ - if (!dev) - return -ENODEV; + if (!dev) { + kfree_skb(skb); + return NET_RX_DROP; + } skb->protocol = htons(ETH_P_IP); skb_pull(skb, 13); @@ -1281,8 +1283,7 @@ static int handle_ip_over_ddp(struct sk_buff *skb) stats = netdev_priv(dev); stats->rx_packets++; stats->rx_bytes += skb->len + 13; - netif_rx(skb); /* Send the SKB up to a higher place. */ - return 0; + return netif_rx(skb); /* Send the SKB up to a higher place. */ } #else /* make it easy for gcc to optimize this test out, i.e. kill the code */ @@ -1290,9 +1291,8 @@ static int handle_ip_over_ddp(struct sk_buff *skb) #define handle_ip_over_ddp(skb) 0 #endif -static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev, - struct ddpehdr *ddp, __u16 len_hops, - int origlen) +static int atalk_route_packet(struct sk_buff *skb, struct net_device *dev, + struct ddpehdr *ddp, __u16 len_hops, int origlen) { struct atalk_route *rt; struct atalk_addr ta; @@ -1359,8 +1359,6 @@ static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev, /* 22 bytes - 12 ether, 2 len, 3 802.2 5 snap */ struct sk_buff *nskb = skb_realloc_headroom(skb, 32); kfree_skb(skb); - if (!nskb) - goto out; skb = nskb; } else skb = skb_unshare(skb, GFP_ATOMIC); @@ -1369,12 +1367,16 @@ static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev, * If the buffer didn't vanish into the lack of space bitbucket we can * send it. */ - if (skb && aarp_send_ddp(rt->dev, skb, &ta, NULL) == -1) - goto free_it; -out: - return; + if (skb == NULL) + goto drop; + + if (aarp_send_ddp(rt->dev, skb, &ta, NULL) == NET_XMIT_DROP) + return NET_RX_DROP; + return NET_RX_SUCCESS; free_it: kfree_skb(skb); +drop: + return NET_RX_DROP; } /** @@ -1400,7 +1402,7 @@ 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))) @@ -1408,7 +1410,7 @@ 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); @@ -1426,7 +1428,7 @@ 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; } /* @@ -1436,7 +1438,7 @@ 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' */ @@ -1448,8 +1450,7 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, /* Not ours, so we route the packet via the correct * AppleTalk iface */ - atalk_route_packet(skb, dev, ddp, len_hops, origlen); - goto out; + return atalk_route_packet(skb, dev, ddp, len_hops, origlen); } /* if IP over DDP is not selected this code will be optimized out */ @@ -1465,18 +1466,21 @@ 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; + } /* @@ -1652,10 +1656,10 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr if (skb2) { loopback = 1; SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk); - if (aarp_send_ddp(dev, skb2, - &usat->sat_addr, NULL) == -1) - kfree_skb(skb2); - /* else queued/sent above in the aarp queue */ + /* + * If it fails it is queued/sent above in the aarp queue + */ + aarp_send_ddp(dev, skb2, &usat->sat_addr, NULL); } } @@ -1685,9 +1689,10 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr usat = &gsat; } - if (aarp_send_ddp(dev, skb, &usat->sat_addr, NULL) == -1) - kfree_skb(skb); - /* else queued/sent above in the aarp queue */ + /* + * If it fails it is queued/sent above in the aarp queue + */ + aarp_send_ddp(dev, skb, &usat->sat_addr, NULL); } SOCK_DEBUG(sk, "SK %p: Done write (%Zd).\n", sk, len); @@ -1865,7 +1870,6 @@ static struct packet_type ppptalk_packet_type __read_mostly = { static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B }; /* Export symbols for use by drivers when AppleTalk is a module */ -EXPORT_SYMBOL(aarp_send_ddp); EXPORT_SYMBOL(atrtr_get_dev); EXPORT_SYMBOL(atalk_find_dev_addr); diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 2912665fc58..26a646d4eb3 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; @@ -238,7 +254,7 @@ static int br2684_start_xmit(struct sk_buff *skb, struct net_device *dev) /* netif_stop_queue(dev); */ dev_kfree_skb(skb); read_unlock(&devs_lock); - return 0; + return NETDEV_TX_OK; } if (!br2684_xmit_vcc(skb, dev, brvcc)) { /* @@ -252,7 +268,7 @@ static int br2684_start_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_fifo_errors++; } read_unlock(&devs_lock); - return 0; + return NETDEV_TX_OK; } /* @@ -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 e65a3b1477f..64629c35434 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; @@ -373,7 +374,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) printk(KERN_ERR "clip_start_xmit: skb_dst(skb) == NULL\n"); dev_kfree_skb(skb); dev->stats.tx_dropped++; - return 0; + return NETDEV_TX_OK; } if (!skb_dst(skb)->neighbour) { #if 0 @@ -387,7 +388,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) printk(KERN_ERR "clip_start_xmit: NO NEIGHBOUR !\n"); dev_kfree_skb(skb); dev->stats.tx_dropped++; - return 0; + return NETDEV_TX_OK; } entry = NEIGH2ENTRY(skb_dst(skb)->neighbour); if (!entry->vccs) { @@ -402,7 +403,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) dev_kfree_skb(skb); dev->stats.tx_dropped++; } - return 0; + return NETDEV_TX_OK; } pr_debug("neigh %p, vccs %p\n", entry, entry->vccs); ATM_SKB(skb)->vcc = vcc = entry->vccs->vcc; @@ -421,14 +422,14 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) old = xchg(&entry->vccs->xoff, 1); /* assume XOFF ... */ if (old) { printk(KERN_WARNING "clip_start_xmit: XOFF->XOFF transition\n"); - return 0; + return NETDEV_TX_OK; } dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; vcc->send(vcc, skb); if (atm_may_send(vcc, 0)) { entry->vccs->xoff = 0; - return 0; + return NETDEV_TX_OK; } spin_lock_irqsave(&clip_priv->xoff_lock, flags); netif_stop_queue(dev); /* XOFF -> throttle immediately */ @@ -440,7 +441,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) of the brief netif_stop_queue. If this isn't true or if it changes, use netif_wake_queue instead. */ spin_unlock_irqrestore(&clip_priv->xoff_lock, flags); - return 0; + return NETDEV_TX_OK; } static int clip_mkip(struct atm_vcc *vcc, int timeout) diff --git a/net/atm/common.c b/net/atm/common.c index 8c4d843eb17..950bd16d238 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -679,7 +679,7 @@ static int check_qos(const struct atm_qos *qos) } int vcc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct atm_vcc *vcc; unsigned long value; diff --git a/net/atm/common.h b/net/atm/common.h index 92e2981f479..f48a76b6cdf 100644 --- a/net/atm/common.h +++ b/net/atm/common.h @@ -21,7 +21,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait); int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int vcc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); int vcc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); diff --git a/net/atm/lec.c b/net/atm/lec.c index ff2e594dca9..b2d64456032 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); @@ -289,7 +291,7 @@ static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev) skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); kfree_skb(skb); if (skb2 == NULL) - return 0; + return NETDEV_TX_OK; skb = skb2; } skb_push(skb, 2); @@ -307,7 +309,7 @@ static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev) skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); kfree_skb(skb); if (skb2 == NULL) - return 0; + return NETDEV_TX_OK; skb = skb2; } #endif @@ -345,7 +347,7 @@ static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev) dev_kfree_skb(skb); if (skb2 == NULL) { dev->stats.tx_dropped++; - return 0; + return NETDEV_TX_OK; } skb = skb2; } @@ -416,7 +418,7 @@ out: if (entry) lec_arp_put(entry); dev->trans_start = jiffies; - return 0; + return NETDEV_TX_OK; } /* The inverse routine to net_open(). */ @@ -935,9 +937,9 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) } #ifdef CONFIG_PROC_FS -static char *lec_arp_get_status_string(unsigned char status) +static const char *lec_arp_get_status_string(unsigned char status) { - static char *lec_arp_status_string[] = { + static const char *const lec_arp_status_string[] = { "ESI_UNKNOWN ", "ESI_ARP_PENDING ", "ESI_VC_PENDING ", @@ -1121,7 +1123,8 @@ static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos) static int lec_seq_show(struct seq_file *seq, void *v) { - static char lec_banner[] = "Itf MAC ATM destination" + static const char lec_banner[] = + "Itf MAC ATM destination" " Status Flags " "VPI/VCI Recv VPI/VCI\n"; @@ -1505,7 +1508,7 @@ lec_arp_remove(struct lec_priv *priv, struct lec_arp_table *to_remove) } #if DEBUG_ARP_TABLE -static char *get_status_string(unsigned char st) +static const char *get_status_string(unsigned char st) { switch (st) { case ESI_UNKNOWN: diff --git a/net/atm/mpc.c b/net/atm/mpc.c index e5bf11453a1..38a6cb0863f 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; @@ -554,7 +556,7 @@ static int mpc_send_packet(struct sk_buff *skb, struct net_device *dev) while (i < mpc->number_of_mps_macs) { if (!compare_ether_addr(eth->h_dest, (mpc->mps_macs + i*ETH_ALEN))) if ( send_via_shortcut(skb, mpc) == 0 ) /* try shortcut */ - return 0; /* success! */ + return NETDEV_TX_OK; /* success! */ i++; } diff --git a/net/atm/proc.c b/net/atm/proc.c index 38de5ff61ec..ab8419a324b 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -151,8 +151,9 @@ static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void pvc_info(struct seq_file *seq, struct atm_vcc *vcc) { - static const char *class_name[] = { "off","UBR","CBR","VBR","ABR" }; - static const char *aal_name[] = { + static const char *const class_name[] = + {"off","UBR","CBR","VBR","ABR"}; + static const char *const aal_name[] = { "---", "1", "2", "3/4", /* 0- 3 */ "???", "5", "???", "???", /* 4- 7 */ "???", "???", "???", "???", /* 8-11 */ @@ -178,7 +179,7 @@ static void pvc_info(struct seq_file *seq, struct atm_vcc *vcc) static const char *vcc_state(struct atm_vcc *vcc) { - static const char *map[] = { ATM_VS2TXT_MAP }; + static const char *const map[] = { ATM_VS2TXT_MAP }; return map[ATM_VF2VS(vcc->flags)]; } @@ -335,7 +336,7 @@ static const struct file_operations vcc_seq_fops = { static int svc_seq_show(struct seq_file *seq, void *v) { - static char atm_svc_banner[] = + static const char atm_svc_banner[] = "Itf VPI VCI State Remote\n"; if (v == SEQ_START_TOKEN) diff --git a/net/atm/pvc.c b/net/atm/pvc.c index e1d22d9430d..d4c024504f9 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -59,7 +59,7 @@ static int pvc_connect(struct socket *sock,struct sockaddr *sockaddr, } static int pvc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int error; diff --git a/net/atm/svc.c b/net/atm/svc.c index 7b831b526d0..f90d143c4b2 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -446,7 +446,7 @@ int svc_change_qos(struct atm_vcc *vcc,struct atm_qos *qos) static int svc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index da0f64f82b5..f4546073037 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -358,6 +358,7 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) ax25_dev *ax25_dev; ax25_cb *ax25; unsigned int k; + int ret = 0; if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl))) return -EFAULT; @@ -388,57 +389,63 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) case AX25_WINDOW: if (ax25->modulus == AX25_MODULUS) { if (ax25_ctl.arg < 1 || ax25_ctl.arg > 7) - return -EINVAL; + goto einval_put; } else { if (ax25_ctl.arg < 1 || ax25_ctl.arg > 63) - return -EINVAL; + goto einval_put; } ax25->window = ax25_ctl.arg; break; case AX25_T1: if (ax25_ctl.arg < 1) - return -EINVAL; + goto einval_put; ax25->rtt = (ax25_ctl.arg * HZ) / 2; ax25->t1 = ax25_ctl.arg * HZ; break; case AX25_T2: if (ax25_ctl.arg < 1) - return -EINVAL; + goto einval_put; ax25->t2 = ax25_ctl.arg * HZ; break; case AX25_N2: if (ax25_ctl.arg < 1 || ax25_ctl.arg > 31) - return -EINVAL; + goto einval_put; ax25->n2count = 0; ax25->n2 = ax25_ctl.arg; break; case AX25_T3: if (ax25_ctl.arg < 0) - return -EINVAL; + goto einval_put; ax25->t3 = ax25_ctl.arg * HZ; break; case AX25_IDLE: if (ax25_ctl.arg < 0) - return -EINVAL; + goto einval_put; ax25->idle = ax25_ctl.arg * 60 * HZ; break; case AX25_PACLEN: if (ax25_ctl.arg < 16 || ax25_ctl.arg > 65535) - return -EINVAL; + goto einval_put; ax25->paclen = ax25_ctl.arg; break; default: - return -EINVAL; + goto einval_put; } - return 0; +out_put: + ax25_cb_put(ax25); + return ret; + +einval_put: + ret = -EINVAL; + goto out_put; } static void ax25_fillin_cb_from_dev(ax25_cb *ax25, ax25_dev *ax25_dev) @@ -527,7 +534,7 @@ ax25_cb *ax25_create_cb(void) */ static int ax25_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; ax25_cb *ax25; @@ -634,15 +641,10 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, case SO_BINDTODEVICE: if (optlen > IFNAMSIZ) - optlen=IFNAMSIZ; - if (copy_from_user(devname, optval, optlen)) { - res = -EFAULT; - break; - } + optlen = IFNAMSIZ; - dev = dev_get_by_name(&init_net, devname); - if (dev == NULL) { - res = -ENODEV; + if (copy_from_user(devname, optval, optlen)) { + res = -EFAULT; break; } @@ -650,12 +652,18 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, (sock->state != SS_UNCONNECTED || sk->sk_state == TCP_LISTEN)) { res = -EADDRNOTAVAIL; - dev_put(dev); + break; + } + + dev = dev_get_by_name(&init_net, devname); + if (!dev) { + res = -ENODEV; break; } ax25->ax25_dev = ax25_dev_ax25dev(dev); ax25_fillin_cb(ax25, ax25->ax25_dev); + dev_put(dev); break; default: @@ -893,7 +901,6 @@ struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev) sock_init_data(NULL, sk); - sk->sk_destruct = ax25_free_sock; sk->sk_type = osk->sk_type; sk->sk_priority = osk->sk_priority; sk->sk_protocol = osk->sk_protocol; @@ -931,6 +938,7 @@ struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev) } sk->sk_protinfo = ax25; + sk->sk_destruct = ax25_free_sock; ax25->sk = sk; return sk; @@ -1781,8 +1789,8 @@ static int ax25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) ax25_info.idletimer = ax25_display_timer(&ax25->idletimer) / (60 * HZ); ax25_info.n2count = ax25->n2count; ax25_info.state = ax25->state; - ax25_info.rcv_q = sk_wmem_alloc_get(sk); - ax25_info.snd_q = sk_rmem_alloc_get(sk); + ax25_info.rcv_q = sk_rmem_alloc_get(sk); + ax25_info.snd_q = sk_wmem_alloc_get(sk); ax25_info.vs = ax25->vs; ax25_info.vr = ax25->vr; ax25_info.va = ax25->va; diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 59fdb1d2e8e..ed371684c13 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/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 0250e060015..8cfb5a84984 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -49,7 +49,7 @@ static struct net_proto_family *bt_proto[BT_MAX_PROTO]; static DEFINE_RWLOCK(bt_proto_lock); static struct lock_class_key bt_lock_key[BT_MAX_PROTO]; -static const char *bt_key_strings[BT_MAX_PROTO] = { +static const char *const bt_key_strings[BT_MAX_PROTO] = { "sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP", "sk_lock-AF_BLUETOOTH-BTPROTO_HCI", "sk_lock-AF_BLUETOOTH-BTPROTO_SCO", @@ -61,7 +61,7 @@ static const char *bt_key_strings[BT_MAX_PROTO] = { }; static struct lock_class_key bt_slock_key[BT_MAX_PROTO]; -static const char *bt_slock_key_strings[BT_MAX_PROTO] = { +static const char *const bt_slock_key_strings[BT_MAX_PROTO] = { "slock-AF_BLUETOOTH-BTPROTO_L2CAP", "slock-AF_BLUETOOTH-BTPROTO_HCI", "slock-AF_BLUETOOTH-BTPROTO_SCO", diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 52a6ce0d772..cafe9f54d84 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -533,6 +533,10 @@ static struct device *bnep_get_device(struct bnep_session *session) return conn ? &conn->dev : NULL; } +static struct device_type bnep_type = { + .name = "bluetooth", +}; + int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) { struct net_device *dev; @@ -586,6 +590,7 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) #endif SET_NETDEV_DEV(dev, bnep_get_device(s)); + SET_NETDEV_DEVTYPE(dev, &bnep_type); err = register_netdev(dev); if (err) { diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index d7a0e9722de..26fb831ef7e 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; @@ -175,14 +176,14 @@ static int bnep_net_xmit(struct sk_buff *skb, struct net_device *dev) #ifdef CONFIG_BT_BNEP_MC_FILTER if (bnep_net_mc_filter(skb, s)) { kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } #endif #ifdef CONFIG_BT_BNEP_PROTO_FILTER if (bnep_net_proto_filter(skb, s)) { kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } #endif @@ -203,7 +204,7 @@ static int bnep_net_xmit(struct sk_buff *skb, struct net_device *dev) netif_stop_queue(dev); } - return 0; + return NETDEV_TX_OK; } static const struct net_device_ops bnep_netdev_ops = { diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index fa47d5d84f5..b7c4224f4e7 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -211,6 +211,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) conn->type = type; conn->mode = HCI_CM_ACTIVE; conn->state = BT_OPEN; + conn->auth_type = HCI_AT_GENERAL_BONDING; conn->power_save = 1; conn->disc_timeout = HCI_DISCONN_TIMEOUT; @@ -246,6 +247,8 @@ 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 +291,7 @@ 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 +586,19 @@ 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 406ad07cdea..e1da8f68759 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 184ba0a88ec..e99fe385fba 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/hci_sock.c b/net/bluetooth/hci_sock.c index 4f9621f759a..75302a98606 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -466,7 +466,7 @@ drop: goto done; } -static int hci_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int len) +static int hci_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int len) { struct hci_ufilter uf = { .opcode = 0 }; struct sock *sk = sock->sk; diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 95f7a7a544b..2bc6f6a8de6 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -68,7 +68,7 @@ static struct attribute_group bt_link_group = { .attrs = bt_link_attrs, }; -static struct attribute_group *bt_link_groups[] = { +static const struct attribute_group *bt_link_groups[] = { &bt_link_group, NULL }; @@ -92,6 +92,8 @@ static void add_conn(struct work_struct *work) dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); + dev_set_drvdata(&conn->dev, conn); + if (device_add(&conn->dev) < 0) { BT_ERR("Failed to register connection device"); return; @@ -144,8 +146,6 @@ void hci_conn_init_sysfs(struct hci_conn *conn) conn->dev.class = bt_class; conn->dev.parent = &hdev->dev; - dev_set_drvdata(&conn->dev, conn); - device_initialize(&conn->dev); INIT_WORK(&conn->work_add, add_conn); @@ -392,7 +392,7 @@ static struct attribute_group bt_host_group = { .attrs = bt_host_attrs, }; -static struct attribute_group *bt_host_groups[] = { +static const struct attribute_group *bt_host_groups[] = { &bt_host_group, NULL }; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index b18676870d5..49d8495d69b 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); } } @@ -571,9 +577,8 @@ static int hidp_session(void *arg) } if (session->hid) { - if (session->hid->claimed & HID_CLAIMED_INPUT) - hidinput_disconnect(session->hid); hid_destroy_device(session->hid); + session->hid = NULL; } /* Wakeup user-space polling for socket errors */ @@ -601,25 +606,27 @@ 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 +673,13 @@ 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) @@ -729,8 +742,6 @@ static void hidp_stop(struct hid_device *hid) skb_queue_purge(&session->ctrl_transmit); skb_queue_purge(&session->intr_transmit); - if (hid->claimed & HID_CLAIMED_INPUT) - hidinput_disconnect(hid); hid->claimed = 0; } @@ -748,13 +759,11 @@ 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 +785,17 @@ 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 +845,13 @@ 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 +879,20 @@ 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 e503c89057a..faf3d74c358 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 bd0a4c1bced..947f8bbb4bb 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) { @@ -500,12 +555,12 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status) conn->feat_mask = 0; - setup_timer(&conn->info_timer, l2cap_info_timeout, - (unsigned long) conn); - spin_lock_init(&conn->lock); rwlock_init(&conn->chan_list.lock); + setup_timer(&conn->info_timer, l2cap_info_timeout, + (unsigned long) conn); + conn->disc_reason = 0x13; return 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; @@ -729,6 +783,9 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) /* Default config options */ pi->conf_len = 0; pi->flush_to = L2CAP_DEFAULT_FLUSH_TO; + skb_queue_head_init(TX_QUEUE(sk)); + skb_queue_head_init(SREJ_QUEUE(sk)); + INIT_LIST_HEAD(SREJ_LIST(sk)); } static struct proto l2cap_proto = { @@ -956,6 +1013,19 @@ 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 +1077,19 @@ 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 +1200,219 @@ 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; - if (sk->sk_type == SOCK_DGRAM) - put_unaligned(l2cap_pi(sk)->psm, (__le16 *) skb_put(skb, 2)); + 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); + + 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 +1425,173 @@ 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 +1603,73 @@ 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; } @@ -1241,7 +1701,7 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct ms return bt_sock_recvmsg(iocb, sock, msg, len, flags); } -static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, int optlen) +static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct l2cap_options opts; @@ -1257,7 +1717,8 @@ 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 +1726,10 @@ 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: @@ -1295,7 +1758,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us return err; } -static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct bt_security sec; @@ -1379,7 +1842,8 @@ 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 +2172,108 @@ 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_BASIC }; 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 +2323,12 @@ 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 +2339,88 @@ 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; - } - - l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->omtu); - } else { + 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); - memset(&rfc, 0, sizeof(rfc)); - rfc.mode = L2CAP_MODE_BASIC; + 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; l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, - sizeof(rfc), (unsigned long) &rfc); + sizeof(rfc), (unsigned long) &rfc); + + 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; + + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, + sizeof(rfc), (unsigned long) &rfc); + + break; + + default: + result = L2CAP_CONF_UNACCEPT; + + memset(&rfc, 0, sizeof(rfc)); + rfc.mode = pi->mode; } - } + 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 +2428,73 @@ 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 +2681,7 @@ 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 +2740,13 @@ 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 +2755,22 @@ 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 +2779,7 @@ 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 +2809,32 @@ 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 +2844,16 @@ 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 +2884,11 @@ 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 +2911,11 @@ 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 +2934,14 @@ 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 +3092,374 @@ 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 +3467,91 @@ 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 +3600,11 @@ 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 +3613,7 @@ 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 +4000,9 @@ 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 94b3388c188..25692bc0a34 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; @@ -2080,7 +2121,7 @@ static CLASS_ATTR(rfcomm_dlc, S_IRUGO, rfcomm_dlc_sysfs_show, NULL); /* ---- Initialization ---- */ static int __init rfcomm_init(void) { - int ret; + int err; l2cap_load(); @@ -2088,33 +2129,35 @@ static int __init rfcomm_init(void) rfcomm_thread = kthread_run(rfcomm_run, NULL, "krfcommd"); if (IS_ERR(rfcomm_thread)) { - ret = PTR_ERR(rfcomm_thread); - goto out_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"); - ret = rfcomm_init_ttys(); - if (ret) - goto out_tty; + err = rfcomm_init_ttys(); + if (err < 0) + goto stop; - ret = rfcomm_init_sockets(); - if (ret) - goto out_sock; + err = rfcomm_init_sockets(); + if (err < 0) + goto cleanup; BT_INFO("RFCOMM ver %s", VERSION); return 0; -out_sock: +cleanup: rfcomm_cleanup_ttys(); -out_tty: + +stop: kthread_stop(rfcomm_thread); -out_thread: + +unregister: hci_unregister_cb(&rfcomm_cb); - return ret; + return err; } static void __exit rfcomm_exit(void) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 0b85e811685..8a20aaf1f23 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -730,7 +730,7 @@ out: return copied ? : err; } -static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, int optlen) +static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; @@ -766,7 +766,7 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __u return err; } -static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct bt_security sec; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 51ae0c3e470..77f4153bdb5 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); } @@ -649,7 +644,7 @@ static int sco_sock_sendmsg(struct kiocb *iocb, struct socket *sock, return err; } -static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; @@ -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 18538d7460d..07a07770c8b 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; @@ -39,7 +39,7 @@ int br_dev_xmit(struct sk_buff *skb, struct net_device *dev) else br_flood_deliver(br, skb); - return 0; + return NETDEV_TX_OK; } static int br_dev_open(struct net_device *dev) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index d2c27c808d3..bc1704ac6cd 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 eb404dc3ed6..4a9f5273265 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); @@ -263,6 +264,10 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, return p; } +static struct device_type br_type = { + .name = "bridge", +}; + int br_add_bridge(struct net *net, const char *name) { struct net_device *dev; @@ -279,6 +284,8 @@ int br_add_bridge(struct net *net, const char *name) goto out_free; } + SET_NETDEV_DEVTYPE(dev, &br_type); + ret = register_netdevice(dev); if (ret) goto out_free; @@ -370,12 +377,16 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) struct net_bridge_port *p; int err = 0; - if (dev->flags & IFF_LOOPBACK || dev->type != ARPHRD_ETHER) + /* Don't allow bridging non-ethernet like devices */ + if ((dev->flags & IFF_LOOPBACK) || + dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) return -EINVAL; + /* No bridging of bridges */ if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) return -ELOOP; + /* Device is already being bridged */ if (dev->br_port != NULL) return -EBUSY; @@ -425,6 +436,7 @@ err2: br_fdb_delete_by_port(br, p, 1); err1: kobject_put(&p->kobj); + p = NULL; /* kobject_put frees */ err0: dev_set_promiscuity(dev, -1); put_back: diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index d22f611e400..a16a2342f6b 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -359,7 +359,7 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) }, .proto = 0, }; - struct in_device *in_dev = in_dev_get(dev); + struct in_device *in_dev = __in_dev_get_rcu(dev); /* If err equals -EHOSTUNREACH the error is due to a * martian destination or due to the fact that @@ -905,56 +905,72 @@ static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb, * For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because * ip_refrag() can return NF_STOLEN. */ static struct nf_hook_ops br_nf_ops[] __read_mostly = { - { .hook = br_nf_pre_routing, - .owner = THIS_MODULE, - .pf = PF_BRIDGE, - .hooknum = NF_BR_PRE_ROUTING, - .priority = NF_BR_PRI_BRNF, }, - { .hook = br_nf_local_in, - .owner = THIS_MODULE, - .pf = PF_BRIDGE, - .hooknum = NF_BR_LOCAL_IN, - .priority = NF_BR_PRI_BRNF, }, - { .hook = br_nf_forward_ip, - .owner = THIS_MODULE, - .pf = PF_BRIDGE, - .hooknum = NF_BR_FORWARD, - .priority = NF_BR_PRI_BRNF - 1, }, - { .hook = br_nf_forward_arp, - .owner = THIS_MODULE, - .pf = PF_BRIDGE, - .hooknum = NF_BR_FORWARD, - .priority = NF_BR_PRI_BRNF, }, - { .hook = br_nf_local_out, - .owner = THIS_MODULE, - .pf = PF_BRIDGE, - .hooknum = NF_BR_LOCAL_OUT, - .priority = NF_BR_PRI_FIRST, }, - { .hook = br_nf_post_routing, - .owner = THIS_MODULE, - .pf = PF_BRIDGE, - .hooknum = NF_BR_POST_ROUTING, - .priority = NF_BR_PRI_LAST, }, - { .hook = ip_sabotage_in, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP_PRI_FIRST, }, - { .hook = ip_sabotage_in, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_FIRST, }, + { + .hook = br_nf_pre_routing, + .owner = THIS_MODULE, + .pf = PF_BRIDGE, + .hooknum = NF_BR_PRE_ROUTING, + .priority = NF_BR_PRI_BRNF, + }, + { + .hook = br_nf_local_in, + .owner = THIS_MODULE, + .pf = PF_BRIDGE, + .hooknum = NF_BR_LOCAL_IN, + .priority = NF_BR_PRI_BRNF, + }, + { + .hook = br_nf_forward_ip, + .owner = THIS_MODULE, + .pf = PF_BRIDGE, + .hooknum = NF_BR_FORWARD, + .priority = NF_BR_PRI_BRNF - 1, + }, + { + .hook = br_nf_forward_arp, + .owner = THIS_MODULE, + .pf = PF_BRIDGE, + .hooknum = NF_BR_FORWARD, + .priority = NF_BR_PRI_BRNF, + }, + { + .hook = br_nf_local_out, + .owner = THIS_MODULE, + .pf = PF_BRIDGE, + .hooknum = NF_BR_LOCAL_OUT, + .priority = NF_BR_PRI_FIRST, + }, + { + .hook = br_nf_post_routing, + .owner = THIS_MODULE, + .pf = PF_BRIDGE, + .hooknum = NF_BR_POST_ROUTING, + .priority = NF_BR_PRI_LAST, + }, + { + .hook = ip_sabotage_in, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP_PRI_FIRST, + }, + { + .hook = ip_sabotage_in, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_FIRST, + }, }; #ifdef CONFIG_SYSCTL static -int brnf_sysctl_call_tables(ctl_table * ctl, int write, struct file *filp, +int brnf_sysctl_call_tables(ctl_table * ctl, int write, void __user * buffer, size_t * lenp, loff_t * ppos) { int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *(int *)(ctl->data)) *(int *)(ctl->data) = 1; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d5b5537272b..2114e45682e 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_stp.c b/net/bridge/br_stp.c index 0660515f399..fd3f8d6c099 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -21,7 +21,7 @@ */ #define MESSAGE_AGE_INCR ((HZ < 256) ? 1 : (HZ/256)) -static const char *br_port_state_names[] = { +static const char *const br_port_state_names[] = { [BR_STATE_DISABLED] = "disabled", [BR_STATE_LISTENING] = "listening", [BR_STATE_LEARNING] = "learning", diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 4a3cdf8f381..820643a3ba9 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/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index a94f3cc377c..e4ea3fdd1d4 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -50,14 +50,6 @@ struct arppayload unsigned char ip_dst[4]; }; -static void print_MAC(const unsigned char *p) -{ - int i; - - for (i = 0; i < ETH_ALEN; i++, p++) - printk("%02x%c", *p, i == ETH_ALEN - 1 ? ' ':':'); -} - static void print_ports(const struct sk_buff *skb, uint8_t protocol, int offset) { @@ -88,14 +80,11 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum, unsigned int bitmask; spin_lock_bh(&ebt_log_lock); - printk("<%c>%s IN=%s OUT=%s MAC source = ", '0' + loginfo->u.log.level, - prefix, in ? in->name : "", out ? out->name : ""); - - print_MAC(eth_hdr(skb)->h_source); - printk("MAC dest = "); - print_MAC(eth_hdr(skb)->h_dest); - - printk("proto = 0x%04x", ntohs(eth_hdr(skb)->h_proto)); + printk("<%c>%s IN=%s OUT=%s MAC source = %pM MAC dest = %pM proto = 0x%04x", + '0' + loginfo->u.log.level, prefix, + in ? in->name : "", out ? out->name : "", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); if (loginfo->type == NF_LOG_TYPE_LOG) bitmask = loginfo->u.log.logflags; @@ -171,12 +160,8 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum, printk(" INCOMPLETE ARP payload"); goto out; } - printk(" ARP MAC SRC="); - print_MAC(ap->mac_src); - printk(" ARP IP SRC=%pI4", ap->ip_src); - printk(" ARP MAC DST="); - print_MAC(ap->mac_dst); - printk(" ARP IP DST=%pI4", ap->ip_dst); + printk(" ARP MAC SRC=%pM ARP IP SRC=%pI4 ARP MAC DST=%pM ARP IP DST=%pI4", + ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst); } } out: diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 133eeae45a4..ce50688a643 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -266,7 +266,7 @@ static bool ebt_ulog_tg_check(const struct xt_tgchk_param *par) if (uloginfo->qthreshold > EBT_ULOG_MAX_QLEN) uloginfo->qthreshold = EBT_ULOG_MAX_QLEN; - return 0; + return true; } static struct xt_target ebt_ulog_tg_reg __read_mostly = { diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index c751111440f..d32ab13e728 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -41,7 +41,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks) return 0; } -static struct ebt_table broute_table = +static const struct ebt_table broute_table = { .name = "broute", .table = &initial_table, diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index a5eea72938a..60b1a6ca718 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -50,7 +50,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks) return 0; } -static struct ebt_table frame_filter = +static const struct ebt_table frame_filter = { .name = "filter", .table = &initial_table, @@ -77,21 +77,21 @@ static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { { .hook = ebt_in_hook, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { .hook = ebt_in_hook, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { .hook = ebt_out_hook, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_FILTER_OTHER, }, diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 6024c551f9a..4a98804203b 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -77,21 +77,21 @@ static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { { .hook = ebt_nat_out, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_NAT_DST_OTHER, }, { .hook = ebt_nat_out, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_NAT_SRC, }, { .hook = ebt_nat_in, .owner = THIS_MODULE, - .pf = PF_BRIDGE, + .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_NAT_DST_BRIDGED, }, diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 37928d5f284..bd1c65425d4 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1103,23 +1103,24 @@ free_newinfo: return ret; } -struct ebt_table *ebt_register_table(struct net *net, struct ebt_table *table) +struct ebt_table * +ebt_register_table(struct net *net, const struct ebt_table *input_table) { struct ebt_table_info *newinfo; - struct ebt_table *t; + struct ebt_table *t, *table; struct ebt_replace_kernel *repl; int ret, i, countersize; void *p; - if (!table || !(repl = table->table) || !repl->entries || - repl->entries_size == 0 || - repl->counters || table->private) { + if (input_table == NULL || (repl = input_table->table) == NULL || + repl->entries == 0 || repl->entries_size == 0 || + repl->counters != NULL || input_table->private != NULL) { BUGPRINT("Bad table data for ebt_register_table!!!\n"); return ERR_PTR(-EINVAL); } /* Don't add one table to multiple lists. */ - table = kmemdup(table, sizeof(struct ebt_table), GFP_KERNEL); + table = kmemdup(input_table, sizeof(struct ebt_table), GFP_KERNEL); if (!table) { ret = -ENOMEM; goto out; diff --git a/net/can/af_can.c b/net/can/af_can.c index e733725b11d..60683211567 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -199,6 +199,8 @@ static int can_create(struct net *net, struct socket *sock, int protocol) * @skb: pointer to socket buffer with CAN frame in data section * @loop: loopback for listeners on local CAN sockets (recommended default!) * + * Due to the loopback this routine must not be called from hardirq context. + * * Return: * 0 on success * -ENETDOWN when the selected interface is down @@ -278,7 +280,7 @@ int can_send(struct sk_buff *skb, int loop) } if (newskb) - netif_rx(newskb); + netif_rx_ni(newskb); /* update statistics */ can_stats.tx_frames++; @@ -651,12 +653,16 @@ 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 +688,11 @@ 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 72720c71035..e8d58f33fe0 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> @@ -131,38 +132,37 @@ static inline struct bcm_sock *bcm_sk(const struct sock *sk) /* * procfs functions */ -static char *bcm_proc_getifname(int ifindex) +static char *bcm_proc_getifname(char *result, int ifindex) { struct net_device *dev; if (!ifindex) return "any"; - /* no usage counting */ + read_lock(&dev_base_lock); dev = __dev_get_by_index(&init_net, ifindex); if (dev) - return dev->name; + strcpy(result, dev->name); + else + strcpy(result, "???"); + read_unlock(&dev_base_lock); - return "???"; + return result; } -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; + char ifname[IFNAMSIZ]; + 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(ifname, bo->ifindex)); + seq_printf(m, " <<<\n"); list_for_each_entry(op, &bo->rx_ops, list) { @@ -172,71 +172,63 @@ 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 ", - op->can_id, bcm_proc_getifname(op->ifindex)); - len += snprintf(page + len, PAGE_SIZE - len, "[%d]%c ", - op->nframes, + seq_printf(m, "rx_op: %03X %-5s ", + op->can_id, bcm_proc_getifname(ifname, op->ifindex)); + 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] ", - op->can_id, bcm_proc_getifname(op->ifindex), + seq_printf(m, "tx_op: %03X %s [%d] ", + op->can_id, + bcm_proc_getifname(ifname, 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 +1507,9 @@ 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 1463653dbe3..9b9ad29be56 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 db3152df7d2..b5e897922d3 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -411,7 +411,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, } static int raw_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); diff --git a/net/compat.c b/net/compat.c index 8d739053afe..a407c3addba 100644 --- a/net/compat.c +++ b/net/compat.c @@ -331,7 +331,7 @@ struct compat_sock_fprog { }; static int do_set_attach_filter(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval; struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog)); @@ -351,7 +351,7 @@ static int do_set_attach_filter(struct socket *sock, int level, int optname, } static int do_set_sock_timeout(struct socket *sock, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct compat_timeval __user *up = (struct compat_timeval __user *) optval; struct timeval ktime; @@ -373,7 +373,7 @@ static int do_set_sock_timeout(struct socket *sock, int level, } static int compat_sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (optname == SO_ATTACH_FILTER) return do_set_attach_filter(sock, level, optname, @@ -385,7 +385,7 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname, } asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; struct socket *sock; @@ -558,8 +558,8 @@ struct compat_group_filter { int compat_mc_setsockopt(struct sock *sock, int level, int optname, - char __user *optval, int optlen, - int (*setsockopt)(struct sock *,int,int,char __user *,int)) + char __user *optval, unsigned int optlen, + int (*setsockopt)(struct sock *,int,int,char __user *,unsigned int)) { char __user *koptval = optval; int koptlen = optlen; @@ -743,6 +743,18 @@ asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, uns return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } +asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, unsigned flags) +{ + return sys_recv(fd, buf, len, flags | MSG_CMSG_COMPAT); +} + +asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, size_t len, + unsigned flags, struct sockaddr __user *addr, + int __user *addrlen) +{ + return sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr, addrlen); +} + asmlinkage long compat_sys_socketcall(int call, u32 __user *args) { int ret; @@ -788,10 +800,11 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) ret = sys_sendto(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), a[5]); break; case SYS_RECV: - ret = sys_recv(a0, compat_ptr(a1), a[2], a[3]); + ret = compat_sys_recv(a0, compat_ptr(a1), a[2], a[3]); break; case SYS_RECVFROM: - ret = sys_recvfrom(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), compat_ptr(a[5])); + ret = compat_sys_recvfrom(a0, compat_ptr(a1), a[2], a[3], + compat_ptr(a[4]), compat_ptr(a[5])); break; case SYS_SHUTDOWN: ret = sys_shutdown(a0,a1); diff --git a/net/core/datagram.c b/net/core/datagram.c index b0fe69211ee..4ade3011bb3 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' ? @@ -223,6 +224,15 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) consume_skb(skb); sk_mem_reclaim_partial(sk); } +EXPORT_SYMBOL(skb_free_datagram); + +void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) +{ + lock_sock(sk); + skb_free_datagram(sk, skb); + release_sock(sk); +} +EXPORT_SYMBOL(skb_free_datagram_locked); /** * skb_kill_datagram - Free a datagram skbuff forcibly @@ -284,6 +294,8 @@ 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) @@ -749,5 +761,4 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, EXPORT_SYMBOL(datagram_poll); EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec); EXPORT_SYMBOL(skb_copy_datagram_iovec); -EXPORT_SYMBOL(skb_free_datagram); EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index 6a94475aee8..fe10551d367 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 /* @@ -269,10 +269,10 @@ 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 *netdev_lock_name[] = +static const char *const netdev_lock_name[] = {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", @@ -287,7 +287,7 @@ static const char *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); @@ -933,14 +942,15 @@ rollback: ret = notifier_to_errno(ret); if (ret) { - if (err) { - printk(KERN_ERR - "%s: name change rollback failed: %d.\n", - dev->name, ret); - } else { + /* err >= 0 after dev_alloc_name() or stores the first errno */ + if (err >= 0) { err = ret; memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; + } else { + printk(KERN_ERR + "%s: name change rollback failed: %d.\n", + dev->name, ret); } } @@ -970,7 +980,7 @@ 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; @@ -1006,10 +1016,11 @@ 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) +void netdev_bonding_change(struct net_device *dev, unsigned long event) { - call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, dev); + call_netdevice_notifiers(event, dev); } EXPORT_SYMBOL(netdev_bonding_change); @@ -1031,9 +1042,10 @@ void dev_load(struct net *net, const char *name) dev = __dev_get_by_name(net, name); read_unlock(&dev_base_lock); - if (!dev && capable(CAP_SYS_MODULE)) + if (!dev && capable(CAP_NET_ADMIN)) request_module("%s", name); } +EXPORT_SYMBOL(dev_load); /** * dev_open - prepare an interface for use. @@ -1118,6 +1130,7 @@ int dev_open(struct net_device *dev) return ret; } +EXPORT_SYMBOL(dev_open); /** * dev_close - shutdown an interface. @@ -1184,6 +1197,7 @@ int dev_close(struct net_device *dev) return 0; } +EXPORT_SYMBOL(dev_close); /** @@ -1279,6 +1293,7 @@ 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 +1314,7 @@ 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 +1337,13 @@ 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 +1377,7 @@ 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 +1545,7 @@ out_set_summed: out: return ret; } +EXPORT_SYMBOL(skb_checksum_help); /** * skb_gso_segment - Perform segmentation on skb. @@ -1589,7 +1608,6 @@ 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. */ @@ -1704,7 +1722,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb_dst_drop(skb); rc = ops->ndo_start_xmit(skb, dev); - if (rc == 0) + if (rc == NETDEV_TX_OK) txq_trans_update(txq); /* * TODO: if skb_orphan() was called by @@ -1730,7 +1748,7 @@ gso: skb->next = nskb->next; nskb->next = NULL; rc = ops->ndo_start_xmit(nskb, dev); - if (unlikely(rc)) { + if (unlikely(rc != NETDEV_TX_OK)) { nskb->next = skb->next; skb->next = nskb; return rc; @@ -1744,7 +1762,7 @@ gso: out_kfree_skb: kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } static u32 skb_tx_hashrnd; @@ -1755,7 +1773,7 @@ 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; } @@ -1786,6 +1804,40 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, return netdev_get_tx_queue(dev, queue_index); } +static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, + struct netdev_queue *txq) +{ + spinlock_t *root_lock = qdisc_lock(q); + int rc; + + spin_lock(root_lock); + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { + kfree_skb(skb); + rc = NET_XMIT_DROP; + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { + /* + * This is a work-conserving queue; there are no old skbs + * waiting to be sent out; and the qdisc is not running - + * xmit the skb directly. + */ + __qdisc_update_bstats(q, skb->len); + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) + __qdisc_run(q); + else + clear_bit(__QDISC_STATE_RUNNING, &q->state); + + rc = NET_XMIT_SUCCESS; + } else { + rc = qdisc_enqueue_root(skb, q); + qdisc_run(q); + } + spin_unlock(root_lock); + + return rc; +} + /** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit @@ -1856,22 +1908,10 @@ 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) { - spinlock_t *root_lock = qdisc_lock(q); - - spin_lock(root_lock); - - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { - kfree_skb(skb); - rc = NET_XMIT_DROP; - } else { - rc = qdisc_enqueue_root(skb, q); - qdisc_run(q); - } - spin_unlock(root_lock); - + rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } @@ -1895,7 +1935,7 @@ 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; @@ -1924,6 +1964,7 @@ out: rcu_read_unlock_bh(); return rc; } +EXPORT_SYMBOL(dev_queue_xmit); /*======================================================================= @@ -1990,6 +2031,7 @@ enqueue: kfree_skb(skb); return NET_RX_DROP; } +EXPORT_SYMBOL(netif_rx); int netif_rx_ni(struct sk_buff *skb) { @@ -2003,7 +2045,6 @@ int netif_rx_ni(struct sk_buff *skb) return err; } - EXPORT_SYMBOL(netif_rx_ni); static void net_tx_action(struct softirq_action *h) @@ -2076,7 +2117,7 @@ static inline int deliver_skb(struct sk_buff *skb, /* This hook is defined here for ATM LANE */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; -EXPORT_SYMBOL(br_fdb_test_addr_hook); +EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif /* @@ -2085,7 +2126,7 @@ EXPORT_SYMBOL(br_fdb_test_addr_hook); */ struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff *skb) __read_mostly; -EXPORT_SYMBOL(br_handle_frame_hook); +EXPORT_SYMBOL_GPL(br_handle_frame_hook); static inline struct sk_buff *handle_bridge(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, @@ -2248,6 +2289,9 @@ int netif_receive_skb(struct sk_buff *skb) int ret = NET_RX_DROP; __be16 type; + if (!skb->tstamp.tv64) + net_timestamp(skb); + if (skb->vlan_tci && vlan_hwaccel_do_receive(skb)) return NET_RX_SUCCESS; @@ -2255,9 +2299,6 @@ int netif_receive_skb(struct sk_buff *skb) if (netpoll_receive_skb(skb)) return NET_RX_DROP; - if (!skb->tstamp.tv64) - net_timestamp(skb); - if (!skb->iif) skb->iif = skb->dev->ifindex; @@ -2336,6 +2377,7 @@ 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) @@ -2852,7 +2894,7 @@ softnet_break: goto out; } -static gifconf_func_t * gifconf_list [NPROTO]; +static gifconf_func_t *gifconf_list[NPROTO]; /** * register_gifconf - register a SIOCGIF handler @@ -2863,13 +2905,14 @@ 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); /* @@ -3080,7 +3123,7 @@ 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; } @@ -3316,6 +3359,7 @@ 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) { @@ -3394,6 +3438,7 @@ 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 @@ -3437,6 +3482,7 @@ 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 @@ -3927,6 +3973,7 @@ int __dev_addr_sync(struct dev_addr_list **to, int *to_count, } return err; } +EXPORT_SYMBOL_GPL(__dev_addr_sync); void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count) @@ -3946,6 +3993,7 @@ void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, da = next; } } +EXPORT_SYMBOL_GPL(__dev_addr_unsync); /** * dev_unicast_sync - Synchronize device's unicast list to another device @@ -4064,6 +4112,7 @@ unsigned dev_get_flags(const struct net_device *dev) return flags; } +EXPORT_SYMBOL(dev_get_flags); /** * dev_change_flags - change device settings @@ -4114,12 +4163,13 @@ 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); } @@ -4129,7 +4179,8 @@ 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); } @@ -4141,6 +4192,7 @@ int dev_change_flags(struct net_device *dev, unsigned flags) return ret; } +EXPORT_SYMBOL(dev_change_flags); /** * dev_set_mtu - Change maximum transfer unit @@ -4174,6 +4226,7 @@ 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 @@ -4198,6 +4251,7 @@ 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) @@ -4211,56 +4265,56 @@ 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; @@ -4281,92 +4335,91 @@ 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 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 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 SIOCSIFHWADDR: + return dev_set_mac_address(dev, &ifr->ifr_hwaddr); - 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 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; @@ -4423,135 +4476,135 @@ 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; } } @@ -4816,6 +4869,7 @@ err_uninit: dev->netdev_ops->ndo_uninit(dev); goto out; } +EXPORT_SYMBOL(register_netdevice); /** * init_dummy_netdev - init a dummy network device for NAPI @@ -5168,6 +5222,7 @@ 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 @@ -5180,6 +5235,7 @@ void synchronize_net(void) might_sleep(); synchronize_rcu(); } +EXPORT_SYMBOL(synchronize_net); /** * unregister_netdevice - remove device from the kernel @@ -5200,6 +5256,7 @@ 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 @@ -5218,7 +5275,6 @@ void unregister_netdev(struct net_device *dev) unregister_netdevice(dev); rtnl_unlock(); } - EXPORT_SYMBOL(unregister_netdev); /** @@ -5347,6 +5403,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char out: return err; } +EXPORT_SYMBOL_GPL(dev_change_net_namespace); static int dev_cpu_callback(struct notifier_block *nfb, unsigned long action, @@ -5407,7 +5464,7 @@ 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. */ @@ -5633,41 +5690,3 @@ 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 9d66fa953ab..0a113f26bc9 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 d9d5160610d..4c12ddb5f5e 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -30,10 +30,17 @@ u32 ethtool_op_get_link(struct net_device *dev) return netif_carrier_ok(dev) ? 1 : 0; } +u32 ethtool_op_get_rx_csum(struct net_device *dev) +{ + return (dev->features & NETIF_F_ALL_CSUM) != 0; +} +EXPORT_SYMBOL(ethtool_op_get_rx_csum); + u32 ethtool_op_get_tx_csum(struct net_device *dev) { return (dev->features & NETIF_F_ALL_CSUM) != 0; } +EXPORT_SYMBOL(ethtool_op_get_tx_csum); int ethtool_op_set_tx_csum(struct net_device *dev, u32 data) { @@ -891,6 +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) @@ -1004,7 +1024,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) break; case ETHTOOL_GRXCSUM: rc = ethtool_get_value(dev, useraddr, ethcmd, - dev->ethtool_ops->get_rx_csum); + (dev->ethtool_ops->get_rx_csum ? + dev->ethtool_ops->get_rx_csum : + ethtool_op_get_rx_csum)); break; case ETHTOOL_SRXCSUM: rc = ethtool_set_rx_csum(dev, useraddr); @@ -1068,7 +1090,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) break; case ETHTOOL_GFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, - dev->ethtool_ops->get_flags); + (dev->ethtool_ops->get_flags ? + dev->ethtool_ops->get_flags : + ethtool_op_get_flags)); break; case ETHTOOL_SFLAGS: rc = ethtool_set_value(dev, useraddr, @@ -1100,6 +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; } @@ -1116,7 +1143,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) EXPORT_SYMBOL(ethtool_op_get_link); EXPORT_SYMBOL(ethtool_op_get_sg); EXPORT_SYMBOL(ethtool_op_get_tso); -EXPORT_SYMBOL(ethtool_op_get_tx_csum); EXPORT_SYMBOL(ethtool_op_set_sg); EXPORT_SYMBOL(ethtool_op_set_tso); EXPORT_SYMBOL(ethtool_op_set_tx_csum); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 163b4f5b036..e587e681969 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -692,75 +692,74 @@ static void neigh_connect(struct neighbour *neigh) hh->hh_output = neigh->ops->hh_output; } -static void neigh_periodic_timer(unsigned long arg) +static void neigh_periodic_work(struct work_struct *work) { - struct neigh_table *tbl = (struct neigh_table *)arg; + struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work); struct neighbour *n, **np; - unsigned long expire, now = jiffies; + unsigned int i; NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); - write_lock(&tbl->lock); + write_lock_bh(&tbl->lock); /* * periodically recompute ReachableTime from random function */ - if (time_after(now, tbl->last_rand + 300 * HZ)) { + if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; - tbl->last_rand = now; + tbl->last_rand = jiffies; for (p = &tbl->parms; p; p = p->next) p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); } - np = &tbl->hash_buckets[tbl->hash_chain_gc]; - tbl->hash_chain_gc = ((tbl->hash_chain_gc + 1) & tbl->hash_mask); + for (i = 0 ; i <= tbl->hash_mask; i++) { + np = &tbl->hash_buckets[i]; - while ((n = *np) != NULL) { - unsigned int state; + while ((n = *np) != NULL) { + unsigned int state; - write_lock(&n->lock); + write_lock(&n->lock); - state = n->nud_state; - if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { - write_unlock(&n->lock); - goto next_elt; - } + state = n->nud_state; + if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { + write_unlock(&n->lock); + goto next_elt; + } - if (time_before(n->used, n->confirmed)) - n->used = n->confirmed; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; - if (atomic_read(&n->refcnt) == 1 && - (state == NUD_FAILED || - time_after(now, n->used + n->parms->gc_staletime))) { - *np = n->next; - n->dead = 1; + if (atomic_read(&n->refcnt) == 1 && + (state == NUD_FAILED || + time_after(jiffies, n->used + n->parms->gc_staletime))) { + *np = n->next; + n->dead = 1; + write_unlock(&n->lock); + neigh_cleanup_and_release(n); + continue; + } write_unlock(&n->lock); - neigh_cleanup_and_release(n); - continue; - } - write_unlock(&n->lock); next_elt: - np = &n->next; + np = &n->next; + } + /* + * It's fine to release lock here, even if hash table + * grows while we are preempted. + */ + write_unlock_bh(&tbl->lock); + cond_resched(); + write_lock_bh(&tbl->lock); } - /* Cycle through all hash buckets every base_reachable_time/2 ticks. * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 * base_reachable_time. */ - expire = tbl->parms.base_reachable_time >> 1; - expire /= (tbl->hash_mask + 1); - if (!expire) - expire = 1; - - if (expire>HZ) - mod_timer(&tbl->gc_timer, round_jiffies(now + expire)); - else - mod_timer(&tbl->gc_timer, now + expire); - - write_unlock(&tbl->lock); + schedule_delayed_work(&tbl->gc_work, + tbl->parms.base_reachable_time >> 1); + write_unlock_bh(&tbl->lock); } static __inline__ int neigh_max_probes(struct neighbour *n) @@ -1316,7 +1315,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, } EXPORT_SYMBOL(pneigh_enqueue); -static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, +static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl, struct net *net, int ifindex) { struct neigh_parms *p; @@ -1337,7 +1336,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct net *net = dev_net(dev); const struct net_device_ops *ops = dev->netdev_ops; - ref = lookup_neigh_params(tbl, net, 0); + ref = lookup_neigh_parms(tbl, net, 0); if (!ref) return NULL; @@ -1442,10 +1441,8 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); rwlock_init(&tbl->lock); - setup_timer(&tbl->gc_timer, neigh_periodic_timer, (unsigned long)tbl); - tbl->gc_timer.expires = now + 1; - add_timer(&tbl->gc_timer); - + INIT_DELAYED_WORK_DEFERRABLE(&tbl->gc_work, neigh_periodic_work); + schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1482,7 +1479,8 @@ int neigh_table_clear(struct neigh_table *tbl) struct neigh_table **tp; /* It is not clean... Fix it to unload IPv6 module safely */ - del_timer_sync(&tbl->gc_timer); + cancel_delayed_work(&tbl->gc_work); + flush_scheduled_work(); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); neigh_ifdown(tbl, NULL); @@ -1752,7 +1750,6 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, .ndtc_last_rand = jiffies_to_msecs(rand_delta), .ndtc_hash_rnd = tbl->hash_rnd, .ndtc_hash_mask = tbl->hash_mask, - .ndtc_hash_chain_gc = tbl->hash_chain_gc, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; @@ -1906,7 +1903,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (tbp[NDTPA_IFINDEX]) ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); - p = lookup_neigh_params(tbl, net, ifindex); + p = lookup_neigh_parms(tbl, net, ifindex); if (p == NULL) { err = -ENOENT; goto errout_tbl_lock; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 3994680c08b..427ded84122 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -16,7 +16,7 @@ #include <net/sock.h> #include <linux/rtnetlink.h> #include <linux/wireless.h> -#include <net/iw_handler.h> +#include <net/wext.h> #include "net-sysfs.h" @@ -141,7 +141,7 @@ static ssize_t show_dormant(struct device *dev, return -EINVAL; } -static const char *operstates[] = { +static const char *const operstates[] = { "unknown", "notpresent", /* currently unused */ "down", @@ -363,18 +363,16 @@ static ssize_t wireless_show(struct device *d, char *buf, char *)) { struct net_device *dev = to_net_dev(d); - const struct iw_statistics *iw = NULL; + const struct iw_statistics *iw; ssize_t ret = -EINVAL; - read_lock(&dev_base_lock); + rtnl_lock(); if (dev_isalive(dev)) { - if (dev->wireless_handlers && - dev->wireless_handlers->get_wireless_stats) - iw = dev->wireless_handlers->get_wireless_stats(dev); - if (iw != NULL) + iw = get_wireless_stats(dev); + if (iw) ret = (*format)(iw, buf); } - read_unlock(&dev_base_lock); + rtnl_unlock(); return ret; } @@ -493,7 +491,7 @@ void netdev_unregister_kobject(struct net_device * net) int netdev_register_kobject(struct net_device *net) { struct device *dev = &(net->dev); - struct attribute_group **groups = net->sysfs_groups; + const struct attribute_group **groups = net->sysfs_groups; dev->class = &net_class; dev->platform_data = net; @@ -505,7 +503,7 @@ int netdev_register_kobject(struct net_device *net) *groups++ = &netstat_group; #ifdef CONFIG_WIRELESS_EXT_SYSFS - if (net->wireless_handlers && net->wireless_handlers->get_wireless_stats) + if (net->wireless_handlers || net->ieee80211_ptr) *groups++ = &wireless_group; #endif #endif /* CONFIG_SYSFS */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 197283072cc..1c1af2756f3 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -6,6 +6,8 @@ #include <linux/delay.h> #include <linux/sched.h> #include <linux/idr.h> +#include <linux/rculist.h> +#include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -127,7 +129,7 @@ static struct net *net_create(void) rv = setup_net(net); if (rv == 0) { rtnl_lock(); - list_add_tail(&net->list, &net_namespace_list); + list_add_tail_rcu(&net->list, &net_namespace_list); rtnl_unlock(); } mutex_unlock(&net_mutex); @@ -156,9 +158,16 @@ static void cleanup_net(struct work_struct *work) /* Don't let anyone else find us. */ rtnl_lock(); - list_del(&net->list); + list_del_rcu(&net->list); rtnl_unlock(); + /* + * Another CPU might be rcu-iterating the list, wait for it. + * This needs to be before calling the exit() notifiers, so + * the rcu_barrier() below isn't sufficient alone. + */ + synchronize_rcu(); + /* Run all of the network namespace exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) { if (ops->exit) @@ -193,6 +202,26 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) } #endif +struct net *get_net_ns_by_pid(pid_t pid) +{ + struct task_struct *tsk; + struct net *net; + + /* Lookup the network namespace */ + net = ERR_PTR(-ESRCH); + rcu_read_lock(); + tsk = find_task_by_vpid(pid); + if (tsk) { + struct nsproxy *nsproxy; + nsproxy = task_nsproxy(tsk); + if (nsproxy) + net = get_net(nsproxy->net_ns); + } + rcu_read_unlock(); + return net; +} +EXPORT_SYMBOL_GPL(get_net_ns_by_pid); + static int __init net_ns_init(void) { struct net_generic *ng; @@ -219,7 +248,7 @@ static int __init net_ns_init(void) panic("Could not setup the initial network namespace"); rtnl_lock(); - list_add_tail(&init_net.list, &net_namespace_list); + list_add_tail_rcu(&init_net.list, &net_namespace_list); rtnl_unlock(); mutex_unlock(&net_mutex); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 1b76eb11deb..0b4d0d35ef4 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -9,6 +9,7 @@ * Copyright (C) 2002 Red Hat, Inc. */ +#include <linux/moduleparam.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> @@ -50,6 +51,9 @@ static atomic_t trapped; static void zap_completion_queue(void); static void arp_reply(struct sk_buff *skb); +static unsigned int carrier_timeout = 4; +module_param(carrier_timeout, uint, 0644); + static void queue_process(struct work_struct *work) { struct netpoll_info *npinfo = @@ -737,7 +741,7 @@ int netpoll_setup(struct netpoll *np) } atleast = jiffies + HZ/10; - atmost = jiffies + 4*HZ; + atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { if (time_after(jiffies, atmost)) { printk(KERN_NOTICE diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 19b8c20e98a..6e79e96cb4f 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) @@ -192,11 +192,10 @@ #define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ /* Thread control flag bits */ -#define T_TERMINATE (1<<0) -#define T_STOP (1<<1) /* Stop run */ -#define T_RUN (1<<2) /* Start run */ -#define T_REMDEVALL (1<<3) /* Remove all devs */ -#define T_REMDEV (1<<4) /* Remove one dev */ +#define T_STOP (1<<0) /* Stop run */ +#define T_RUN (1<<1) /* Start run */ +#define T_REMDEVALL (1<<2) /* Remove all devs */ +#define T_REMDEV (1<<3) /* Remove one dev */ /* If lock -- can be removed after some work */ #define if_lock(t) spin_lock(&(t->if_lock)); @@ -206,7 +205,7 @@ #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 +230,9 @@ 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 +245,37 @@ 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 +307,10 @@ 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 */ @@ -330,6 +335,7 @@ struct pktgen_dev { __u32 cur_src_mac_offset; __be32 cur_saddr; __be32 cur_daddr; + __u16 ip_id; __u16 cur_udp_dst; __u16 cur_udp_src; __u16 cur_queue_map; @@ -346,15 +352,18 @@ 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.) + */ + char odevname[32]; struct flow_state *flows; unsigned cflows; /* Concurrent flows (config) */ unsigned lflow; /* Flow length (config) */ @@ -379,13 +388,14 @@ 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; @@ -397,34 +407,32 @@ 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); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname); + const char *ifname, bool exact); 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 +440,10 @@ 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 +459,12 @@ 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 +517,9 @@ 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", @@ -520,10 +527,9 @@ 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, - pkt_dev->clone_skb, pkt_dev->odev->name); + " 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->odevname); seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); @@ -549,11 +555,14 @@ 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 src_min: %s src_max: %s\n", - pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min, - pkt_dev->src_max); + " dst_min: %s dst_max: %s\n", + pkt_dev->dst_min, pkt_dev->dst_max); + seq_printf(seq, + " src_min: %s src_max: %s\n", + pkt_dev->src_min, pkt_dev->src_max); + } seq_puts(seq, " src_mac: "); @@ -565,7 +574,8 @@ 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 +591,21 @@ 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 +662,21 @@ 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 +708,8 @@ 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 +859,9 @@ 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 +885,9 @@ 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 +902,9 @@ 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 +921,9 @@ 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 +938,9 @@ 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 +949,9 @@ 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 +959,24 @@ 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; + + 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 +987,9 @@ 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 +1000,9 @@ 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 +1013,9 @@ 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 +1026,9 @@ 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 +1037,9 @@ 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 +1048,9 @@ 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 +1062,9 @@ 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 +1078,9 @@ 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 +1179,8 @@ 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 +1200,9 @@ 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 +1313,9 @@ 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 +1334,9 @@ 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 +1360,9 @@ 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 +1402,9 @@ 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 +1445,9 @@ 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 +1459,9 @@ 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 +1470,9 @@ 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 +1481,9 @@ 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 +1515,9 @@ 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 +1542,9 @@ 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 +1557,9 @@ 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 +1572,9 @@ 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 +1599,9 @@ 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 +1614,9 @@ 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 +1630,9 @@ 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 +1646,9 @@ 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 +1680,7 @@ 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); @@ -1679,13 +1689,13 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); seq_printf(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); @@ -1808,9 +1818,10 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; + bool exact = (remove == FIND); list_for_each_entry(t, &pktgen_threads, th_list) { - pkt_dev = pktgen_find_dev(t, ifname); + pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { if_lock(t); @@ -1873,8 +1884,10 @@ 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 +1921,14 @@ 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]; @@ -1981,16 +1995,16 @@ 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->odev->name); + pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, + pkt_dev->odevname); pkt_dev->queue_map_min = ntxq - 1; } if (pkt_dev->queue_map_max >= ntxq) { 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->odev->name); + pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, + pkt_dev->odevname); pkt_dev->queue_map_max = ntxq - 1; } @@ -2030,7 +2044,8 @@ 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 +2104,45 @@ 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_time, end_time; + s64 remaining; + struct hrtimer_sleeper t; - 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()) + 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) { + pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); + return; + } + + start_time = 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); } + end_time = ktime_now(); - pkt_dev->idle_acc += now - start; + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time)); + pkt_dev->next_tx = ktime_add_ns(end_time, pkt_dev->delay); } static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) @@ -2120,13 +2153,9 @@ 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 +2203,7 @@ 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; } } @@ -2186,7 +2215,7 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev) if (pkt_dev->flags & F_QUEUE_MAP_CPU) pkt_dev->cur_queue_map = smp_processor_id(); - else if (pkt_dev->queue_map_min < pkt_dev->queue_map_max) { + else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) { __u16 t; if (pkt_dev->flags & F_QUEUE_MAP_RND) { t = random32() % @@ -2313,18 +2342,18 @@ 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 +2464,14 @@ 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 +2486,7 @@ 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 +2496,11 @@ 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 +2510,13 @@ 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 +2529,9 @@ 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 +2572,9 @@ 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; @@ -2603,6 +2633,8 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->protocol = IPPROTO_UDP; /* UDP */ iph->saddr = pkt_dev->cur_saddr; iph->daddr = pkt_dev->cur_daddr; + iph->id = htons(pkt_dev->ip_id); + pkt_dev->ip_id++; iph->frag_off = 0; iplen = 20 + 8 + datalen; iph->tot_len = htons(iplen); @@ -2614,24 +2646,26 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; - if (pkt_dev->nfrags <= 0) + if (pkt_dev->nfrags <= 0) { pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - else { + memset(pgh + 1, 0, datalen - sizeof(struct pktgen_hdr)); + } else { int frags = pkt_dev->nfrags; - int i; + int i, len; pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); if (frags > MAX_SKB_FRAGS) frags = MAX_SKB_FRAGS; if (datalen > frags * PAGE_SIZE) { - skb_put(skb, datalen - frags * PAGE_SIZE); + len = datalen - frags * PAGE_SIZE; + memset(skb_put(skb, len), 0, len); datalen = frags * PAGE_SIZE; } i = 0; while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL, 0); + struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); skb_shinfo(skb)->frags[i].page = page; skb_shinfo(skb)->frags[i].page_offset = 0; skb_shinfo(skb)->frags[i].size = @@ -2668,8 +2702,9 @@ 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 +2917,9 @@ 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 +2958,7 @@ 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 +3052,10 @@ 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 +3071,8 @@ 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 +3110,9 @@ 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 +3139,14 @@ 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 +3203,8 @@ 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 +3222,29 @@ 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; @@ -3228,18 +3258,19 @@ 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; if (!pkt_dev->running) { printk(KERN_WARNING "pktgen: interface: %s is already " - "stopped\n", pkt_dev->odev->name); + "stopped\n", pkt_dev->odevname); 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 +3289,7 @@ 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 +3306,6 @@ 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); @@ -3348,156 +3376,114 @@ 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 pktgen_resched(struct pktgen_dev *pkt_dev) +{ + ktime_t idle_start = ktime_now(); + schedule(); + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start)); +} + +static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) +{ + ktime_t idle_start = ktime_now(); + + while (atomic_read(&(pkt_dev->skb->users)) != 1) { + if (signal_pending(current)) + break; + + if (need_resched()) + pktgen_resched(pkt_dev); + 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); - - /* 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 device is offline, then don't send */ + if (unlikely(!netif_running(odev) || !netif_carrier_ok(odev))) { + pktgen_stop_device(pkt_dev); + return; } - if (!pkt_dev->skb) { - set_cur_queue_map(pkt_dev); - queue_map = pkt_dev->cur_queue_map; - } else { - queue_map = skb_get_queue_mapping(pkt_dev->skb); + /* This is max DELAY, this has special meaning of + * "never transmit" + */ + if (unlikely(pkt_dev->delay == ULLONG_MAX)) { + pkt_dev->next_tx = ktime_add_ns(ktime_now(), ULONG_MAX); + return; } - 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)) { - 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 no skb or clone count exhausted then get new one */ + 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); - 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 */ + 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; } - } - - 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); - 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->allocated_skbs++; + pkt_dev->clone_count = 0; /* reset counter */ } - /* fill_packet() might have changed the queue */ + if (pkt_dev->delay && pkt_dev->last_ok) + spin(pkt_dev, pkt_dev->next_tx); + queue_map = skb_get_queue_mapping(pkt_dev->skb); txq = netdev_get_tx_queue(odev, queue_map); __netif_tx_lock_bh(txq); - if (!netif_tx_queue_stopped(txq) && - !netif_tx_queue_frozen(txq)) { + atomic_inc(&(pkt_dev->skb->users)); - atomic_inc(&(pkt_dev->skb->users)); - retry_now: + if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) + ret = NETDEV_TX_BUSY; + else ret = (*xmit)(pkt_dev->skb, odev); - if (likely(ret == 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)) { - 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"); - - pkt_dev->errors++; - 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; - } - } - - else { /* Retry it next time */ + 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; + break; + default: /* Drivers are not supposed to return other values! */ + if (net_ratelimit()) + pr_info("pktgen: %s xmit error: %d\n", + pkt_dev->odevname, ret); + pkt_dev->errors++; + /* fallthru */ + case NETDEV_TX_LOCKED: + 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(); /* 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; - } + pktgen_wait_for_skb(pkt_dev); /* Done with this */ pktgen_stop_device(pkt_dev); - kfree_skb(pkt_dev->skb); - pkt_dev->skb = NULL; } -out:; } /* @@ -3516,7 +3502,8 @@ 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); @@ -3525,20 +3512,24 @@ static int pktgen_thread_worker(void *arg) while (!kthread_should_stop()) { pkt_dev = next_to_run(t); - if (!pkt_dev && - (t->control & (T_STOP | T_RUN | T_REMDEVALL | T_REMDEV)) - == 0) { - prepare_to_wait(&(t->queue), &wait, - TASK_INTERRUPTIBLE); - schedule_timeout(HZ / 10); - finish_wait(&(t->queue), &wait); + if (unlikely(!pkt_dev && t->control == 0)) { + wait_event_interruptible_timeout(t->queue, + t->control != 0, + HZ/10); + continue; } __set_current_state(TASK_RUNNING); - if (pkt_dev) + if (likely(pkt_dev)) { pktgen_xmit(pkt_dev); + if (need_resched()) + pktgen_resched(pkt_dev); + else + cpu_relax(); + } + if (t->control & T_STOP) { pktgen_stop(t); t->control &= ~(T_STOP); @@ -3577,13 +3568,18 @@ static int pktgen_thread_worker(void *arg) } static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname) + const char *ifname, bool exact) { struct pktgen_dev *p, *pkt_dev = NULL; - if_lock(t); + size_t len = strlen(ifname); + if_lock(t); list_for_each_entry(p, &t->if_list, list) - if (strncmp(p->odev->name, ifname, IFNAMSIZ) == 0) { + if (strncmp(p->odevname, ifname, len) == 0) { + if (p->odevname[len]) { + if (exact || p->odevname[len] != '@') + continue; + } pkt_dev = p; break; } @@ -3639,6 +3635,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) if (!pkt_dev) return -ENOMEM; + strcpy(pkt_dev->odevname, ifname); pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state)); if (pkt_dev->flows == NULL) { kfree(pkt_dev); @@ -3651,8 +3648,7 @@ 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 +3860,15 @@ 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 d78030f88bd..eb42873f2a3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,7 +35,6 @@ #include <linux/security.h> #include <linux/mutex.h> #include <linux/if_addr.h> -#include <linux/nsproxy.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -52,6 +51,7 @@ #include <net/pkt_sched.h> #include <net/fib_rules.h> #include <net/rtnetlink.h> +#include <net/net_namespace.h> struct rtnl_link { @@ -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); @@ -725,25 +723,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_DATA] = { .type = NLA_NESTED }, }; -static struct net *get_net_ns_by_pid(pid_t pid) -{ - struct task_struct *tsk; - struct net *net; - - /* Lookup the network namespace */ - net = ERR_PTR(-ESRCH); - rcu_read_lock(); - tsk = find_task_by_vpid(pid); - if (tsk) { - struct nsproxy *nsproxy; - nsproxy = task_nsproxy(tsk); - if (nsproxy) - net = get_net(nsproxy->net_ns); - } - rcu_read_unlock(); - return net; -} - static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) { if (dev) { @@ -993,12 +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/skbuff.c b/net/core/skbuff.c index 9e0597d189b..ec85681a7dd 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -559,9 +559,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif #endif new->vlan_tci = old->vlan_tci; -#if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE) - new->do_not_encrypt = old->do_not_encrypt; -#endif skb_copy_secmark(new, old); } @@ -2704,7 +2701,8 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) NAPI_GRO_CB(skb)->free = 1; goto done; - } + } else if (skb_gro_len(p) != pinfo->gso_size) + return -E2BIG; headroom = skb_headroom(p); nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p)); diff --git a/net/core/sock.c b/net/core/sock.c index 76334228ed1..7626b6aacd6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -142,7 +142,7 @@ static struct lock_class_key af_family_slock_keys[AF_MAX]; * strings build-time, so that runtime initialization of socket * locks is fast): */ -static const char *af_family_key_strings[AF_MAX+1] = { +static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" , "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK", "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" , @@ -158,7 +158,7 @@ static const char *af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_IEEE802154", "sk_lock-AF_MAX" }; -static const char *af_family_slock_key_strings[AF_MAX+1] = { +static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK", "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" , @@ -174,7 +174,7 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_IEEE802154", "slock-AF_MAX" }; -static const char *af_family_clock_key_strings[AF_MAX+1] = { +static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK", "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" , @@ -446,7 +446,7 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) */ int sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int val; @@ -482,6 +482,8 @@ int sock_setsockopt(struct socket *sock, int level, int optname, sk->sk_reuse = valbool; break; case SO_TYPE: + case SO_PROTOCOL: + case SO_DOMAIN: case SO_ERROR: ret = -ENOPROTOOPT; break; @@ -764,6 +766,14 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_type; break; + case SO_PROTOCOL: + v.val = sk->sk_protocol; + break; + + case SO_DOMAIN: + v.val = sk->sk_family; + break; + case SO_ERROR: v.val = -sock_error(sk); if (v.val == 0) @@ -1196,12 +1206,12 @@ EXPORT_SYMBOL_GPL(sk_setup_caps); void __init sk_init(void) { - if (num_physpages <= 4096) { + if (totalram_pages <= 4096) { sysctl_wmem_max = 32767; sysctl_rmem_max = 32767; sysctl_wmem_default = 32767; sysctl_rmem_default = 32767; - } else if (num_physpages >= 131072) { + } else if (totalram_pages >= 131072) { sysctl_wmem_max = 131071; sysctl_rmem_max = 131071; } @@ -1218,17 +1228,22 @@ void __init sk_init(void) void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; - int res; + unsigned int len = skb->truesize; - /* In case it might be waiting for more memory. */ - res = atomic_sub_return(skb->truesize, &sk->sk_wmem_alloc); - if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) + if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { + /* + * Keep a reference on sk_wmem_alloc, this will be released + * after sk_write_space() call + */ + atomic_sub(len - 1, &sk->sk_wmem_alloc); sk->sk_write_space(sk); + len = 1; + } /* - * if sk_wmem_alloc reached 0, we are last user and should - * free this sock, as sk_free() call could not do it. + * if sk_wmem_alloc reaches 0, we must finish what sk_free() + * could not do because of in-flight packets */ - if (res == 0) + if (atomic_sub_and_test(len, &sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sock_wfree); @@ -1687,7 +1702,7 @@ int sock_no_shutdown(struct socket *sock, int how) EXPORT_SYMBOL(sock_no_shutdown); int sock_no_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } @@ -2008,7 +2023,7 @@ EXPORT_SYMBOL(sock_common_recvmsg); * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; @@ -2018,7 +2033,7 @@ EXPORT_SYMBOL(sock_common_setsockopt); #ifdef CONFIG_COMPAT int compat_sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 8379496de82..ac1205df6c8 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) @@ -186,7 +194,7 @@ static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid, nlmsg_end(dcbnl_skb, nlh); ret = rtnl_unicast(dcbnl_skb, &init_net, pid); if (ret) - goto err; + return -EINVAL; return 0; nlmsg_failure: @@ -267,7 +275,7 @@ static int dcbnl_getpfccfg(struct net_device *netdev, struct nlattr **tb, ret = rtnl_unicast(dcbnl_skb, &init_net, pid); if (ret) - goto err; + goto err_out; return 0; nlmsg_failure: @@ -308,12 +316,11 @@ static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlattr **tb, ret = rtnl_unicast(dcbnl_skb, &init_net, pid); if (ret) - goto err; + goto err_out; return 0; nlmsg_failure: -err: kfree_skb(dcbnl_skb); err_out: return -EINVAL; @@ -375,7 +382,7 @@ static int dcbnl_getcap(struct net_device *netdev, struct nlattr **tb, ret = rtnl_unicast(dcbnl_skb, &init_net, pid); if (ret) - goto err; + goto err_out; return 0; nlmsg_failure: @@ -452,7 +459,7 @@ static int dcbnl_getnumtcs(struct net_device *netdev, struct nlattr **tb, ret = rtnl_unicast(dcbnl_skb, &init_net, pid); if (ret) { ret = -EINVAL; - goto err; + goto err_out; } return 0; @@ -536,6 +543,120 @@ 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) { @@ -677,7 +798,7 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb, ret = rtnl_unicast(dcbnl_skb, &init_net, pid); if (ret) - goto err; + goto err_out; return 0; @@ -941,7 +1062,7 @@ static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlattr **tb, ret = rtnl_unicast(dcbnl_skb, &init_net, pid); if (ret) - goto err; + goto err_out; return 0; @@ -1093,6 +1214,14 @@ 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/ccids/Kconfig b/net/dccp/ccids/Kconfig index 4b5db44970a..8408398cd44 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -66,9 +66,9 @@ config IP_DCCP_CCID3_RTO A value of 0 disables this feature by enforcing the value specified in RFC 3448. The following values have been suggested as bounds for experimental use: - * 16-20ms to match the typical multimedia inter-frame interval - * 100ms as a reasonable compromise [default] - * 1000ms corresponds to the lower TCP RTO bound (RFC 2988, 2.4) + * 16-20ms to match the typical multimedia inter-frame interval + * 100ms as a reasonable compromise [default] + * 1000ms corresponds to the lower TCP RTO bound (RFC 2988, 2.4) The default of 100ms is a compromise between a large value for efficient DCCP implementations, and a small value to avoid disrupting diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index d235294ace2..e8cf99e880b 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/ccid2.c - * * Copyright (c) 2005, 2006 Andrea Bittau <a.bittau@cs.ucl.ac.uk> * * Changes to meet Linux coding standards, and DCCP infrastructure fixes. diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 2c94ca02901..326ac90fb90 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/ccid2.h - * * Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk> * * This program is free software; you can redistribute it and/or modify @@ -40,14 +38,14 @@ struct ccid2_seq { #define CCID2_SEQBUF_LEN 1024 #define CCID2_SEQBUF_MAX 128 -/** struct ccid2_hc_tx_sock - CCID2 TX half connection - * +/** + * struct ccid2_hc_tx_sock - CCID2 TX half connection * @ccid2hctx_{cwnd,ssthresh,pipe}: as per RFC 4341, section 5 * @ccid2hctx_packets_acked - Ack counter for deriving cwnd growth (RFC 3465) * @ccid2hctx_lastrtt -time RTT was last measured * @ccid2hctx_rpseq - last consecutive seqno * @ccid2hctx_rpdupack - dupacks since rpseq -*/ + */ struct ccid2_hc_tx_sock { u32 ccid2hctx_cwnd; u32 ccid2hctx_ssthresh; diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index a27b7f4c19c..34dcc798c45 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/ccid3.c - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz> @@ -52,7 +50,7 @@ static int ccid3_debug; #ifdef CONFIG_IP_DCCP_CCID3_DEBUG static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) { - static char *ccid3_state_names[] = { + static const char *const ccid3_state_names[] = { [TFRC_SSTATE_NO_SENT] = "NO_SENT", [TFRC_SSTATE_NO_FBACK] = "NO_FBACK", [TFRC_SSTATE_FBACK] = "FBACK", @@ -646,7 +644,7 @@ enum ccid3_fback_type { #ifdef CONFIG_IP_DCCP_CCID3_DEBUG static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) { - static char *ccid3_rx_state_names[] = { + static const char *const ccid3_rx_state_names[] = { [TFRC_RSTATE_NO_DATA] = "NO_DATA", [TFRC_RSTATE_DATA] = "DATA", [TFRC_RSTATE_TERM] = "TERM", @@ -750,7 +748,8 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) return 0; } -/** ccid3_first_li - Implements [RFC 3448, 6.3.1] +/** + * ccid3_first_li - Implements [RFC 5348, 6.3.1] * * Determine the length of the first loss interval via inverse lookup. * Assume that X_recv can be computed by the throughput equation diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 49ca32bd7e7..e5a24414384 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/ccid3.h - * * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * @@ -75,8 +73,8 @@ enum ccid3_hc_tx_states { TFRC_SSTATE_TERM, }; -/** struct ccid3_hc_tx_sock - CCID3 sender half-connection socket - * +/** + * struct ccid3_hc_tx_sock - CCID3 sender half-connection socket * @ccid3hctx_x - Current sending rate in 64 * bytes per second * @ccid3hctx_x_recv - Receive rate in 64 * bytes per second * @ccid3hctx_x_calc - Calculated rate in bytes per second @@ -119,9 +117,9 @@ struct ccid3_hc_tx_sock { static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) { - struct ccid3_hc_tx_sock *hctx = ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid); - BUG_ON(hctx == NULL); - return hctx; + struct ccid3_hc_tx_sock *hctx = ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid); + BUG_ON(hctx == NULL); + return hctx; } /* TFRC receiver states */ @@ -131,22 +129,22 @@ enum ccid3_hc_rx_states { TFRC_RSTATE_TERM = 127, }; -/** struct ccid3_hc_rx_sock - CCID3 receiver half-connection socket - * - * @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448 4.3) - * @ccid3hcrx_rtt - Receiver estimate of rtt (non-standard) - * @ccid3hcrx_p - Current loss event rate (RFC 3448 5.4) - * @ccid3hcrx_last_counter - Tracks window counter (RFC 4342, 8.1) - * @ccid3hcrx_state - Receiver state, one of %ccid3_hc_rx_states - * @ccid3hcrx_bytes_recv - Total sum of DCCP payload bytes - * @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448, sec. 4.3) - * @ccid3hcrx_rtt - Receiver estimate of RTT - * @ccid3hcrx_tstamp_last_feedback - Time at which last feedback was sent - * @ccid3hcrx_tstamp_last_ack - Time at which last feedback was sent - * @ccid3hcrx_hist - Packet history (loss detection + RTT sampling) - * @ccid3hcrx_li_hist - Loss Interval database - * @ccid3hcrx_s - Received packet size in bytes - * @ccid3hcrx_pinv - Inverse of Loss Event Rate (RFC 4342, sec. 8.5) +/** + * struct ccid3_hc_rx_sock - CCID3 receiver half-connection socket + * @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448 4.3) + * @ccid3hcrx_rtt - Receiver estimate of rtt (non-standard) + * @ccid3hcrx_p - Current loss event rate (RFC 3448 5.4) + * @ccid3hcrx_last_counter - Tracks window counter (RFC 4342, 8.1) + * @ccid3hcrx_state - Receiver state, one of %ccid3_hc_rx_states + * @ccid3hcrx_bytes_recv - Total sum of DCCP payload bytes + * @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448, sec. 4.3) + * @ccid3hcrx_rtt - Receiver estimate of RTT + * @ccid3hcrx_tstamp_last_feedback - Time at which last feedback was sent + * @ccid3hcrx_tstamp_last_ack - Time at which last feedback was sent + * @ccid3hcrx_hist - Packet history (loss detection + RTT sampling) + * @ccid3hcrx_li_hist - Loss Interval database + * @ccid3hcrx_s - Received packet size in bytes + * @ccid3hcrx_pinv - Inverse of Loss Event Rate (RFC 4342, sec. 8.5) */ struct ccid3_hc_rx_sock { u8 ccid3hcrx_last_counter:4; @@ -163,9 +161,9 @@ struct ccid3_hc_rx_sock { static inline struct ccid3_hc_rx_sock *ccid3_hc_rx_sk(const struct sock *sk) { - struct ccid3_hc_rx_sock *hcrx = ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid); - BUG_ON(hcrx == NULL); - return hcrx; + struct ccid3_hc_rx_sock *hcrx = ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid); + BUG_ON(hcrx == NULL); + return hcrx; } #endif /* _DCCP_CCID3_H_ */ diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c index 4d1e4012726..8fc3cbf7907 100644 --- a/net/dccp/ccids/lib/loss_interval.c +++ b/net/dccp/ccids/lib/loss_interval.c @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/lib/loss_interval.c - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz> @@ -21,7 +19,7 @@ static const int tfrc_lh_weights[NINTERVAL] = { 10, 10, 10, 10, 8, 6, 4, 2 }; /* implements LIFO semantics on the array */ static inline u8 LIH_INDEX(const u8 ctr) { - return (LIH_SIZE - 1 - (ctr % LIH_SIZE)); + return LIH_SIZE - 1 - (ctr % LIH_SIZE); } /* the `counter' index always points at the next entry to be populated */ @@ -129,7 +127,8 @@ static inline u8 tfrc_lh_is_new_loss(struct tfrc_loss_interval *cur, (cur->li_is_closed || SUB16(new_loss->tfrchrx_ccval, cur->li_ccval) > 4); } -/** tfrc_lh_interval_add - Insert new record into the Loss Interval database +/** + * tfrc_lh_interval_add - Insert new record into the Loss Interval database * @lh: Loss Interval database * @rh: Receive history containing a fresh loss event * @calc_first_li: Caller-dependent routine to compute length of first interval diff --git a/net/dccp/ccids/lib/loss_interval.h b/net/dccp/ccids/lib/loss_interval.h index 246018a3b26..d1d2f5383b7 100644 --- a/net/dccp/ccids/lib/loss_interval.h +++ b/net/dccp/ccids/lib/loss_interval.h @@ -1,8 +1,6 @@ #ifndef _DCCP_LI_HIST_ #define _DCCP_LI_HIST_ /* - * net/dccp/ccids/lib/loss_interval.h - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz> diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c index b7785b3581e..3a4f414e94a 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -1,6 +1,4 @@ /* - * net/dccp/packet_history.c - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * @@ -128,7 +126,7 @@ u32 tfrc_tx_hist_rtt(struct tfrc_tx_hist_entry *head, const u64 seqno, /* - * Receiver History Routines + * Receiver History Routines */ static struct kmem_cache *tfrc_rx_hist_slab; diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h index 461cc91cce8..7df6c529999 100644 --- a/net/dccp/ccids/lib/packet_history.h +++ b/net/dccp/ccids/lib/packet_history.h @@ -70,7 +70,6 @@ struct tfrc_rx_hist_entry { /** * tfrc_rx_hist - RX history structure for TFRC-based protocols - * * @ring: Packet history for RTT sampling and loss detection * @loss_count: Number of entries in circular history * @loss_start: Movable index (for loss detection) diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index e9720b14327..01bb48e96c2 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -1,8 +1,6 @@ #ifndef _TFRC_H_ #define _TFRC_H_ /* - * net/dccp/ccids/lib/tfrc.h - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-6 Ian McDonald <ian.mcdonald@jandi.co.nz> @@ -32,7 +30,7 @@ extern int tfrc_debug; /* integer-arithmetic divisions of type (a * 1000000)/b */ static inline u64 scaled_div(u64 a, u64 b) { - BUG_ON(b==0); + BUG_ON(b == 0); return div64_u64(a * 1000000, b); } diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index c5d3a9e5a5a..22ca1cf0eb5 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/lib/tfrc_equation.c - * * Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz> * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br> @@ -79,10 +77,10 @@ } With the given configuration, we have, with M = TFRC_CALC_X_ARRSIZE-1, - lookup[0][0] = g(1000000/(M+1)) = 1000000 * f(0.2%) - lookup[M][0] = g(1000000) = 1000000 * f(100%) - lookup[0][1] = g(TFRC_SMALLEST_P) = 1000000 * f(0.01%) - lookup[M][1] = g(TFRC_CALC_X_SPLIT) = 1000000 * f(5%) + lookup[0][0] = g(1000000/(M+1)) = 1000000 * f(0.2%) + lookup[M][0] = g(1000000) = 1000000 * f(100%) + lookup[0][1] = g(TFRC_SMALLEST_P) = 1000000 * f(0.01%) + lookup[M][1] = g(TFRC_CALC_X_SPLIT) = 1000000 * f(5%) In summary, the two columns represent f(p) for the following ranges: * The first column is for 0.002 <= p <= 1.0 @@ -610,11 +608,10 @@ static inline u32 tfrc_binsearch(u32 fval, u8 small) /** * tfrc_calc_x - Calculate the send rate as per section 3.1 of RFC3448 - * - * @s: packet size in bytes - * @R: RTT scaled by 1000000 (i.e., microseconds) - * @p: loss ratio estimate scaled by 1000000 - * Returns X_calc in bytes per second (not scaled). + * @s: packet size in bytes + * @R: RTT scaled by 1000000 (i.e., microseconds) + * @p: loss ratio estimate scaled by 1000000 + * Returns X_calc in bytes per second (not scaled). */ u32 tfrc_calc_x(u16 s, u32 R, u32 p) { @@ -630,17 +627,17 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) return ~0U; } - if (p <= TFRC_CALC_X_SPLIT) { /* 0.0000 < p <= 0.05 */ + if (p <= TFRC_CALC_X_SPLIT) { /* 0.0000 < p <= 0.05 */ if (p < TFRC_SMALLEST_P) { /* 0.0000 < p < 0.0001 */ DCCP_WARN("Value of p (%d) below resolution. " "Substituting %d\n", p, TFRC_SMALLEST_P); index = 0; - } else /* 0.0001 <= p <= 0.05 */ + } else /* 0.0001 <= p <= 0.05 */ index = p/TFRC_SMALLEST_P - 1; f = tfrc_calc_x_lookup[index][1]; - } else { /* 0.05 < p <= 1.00 */ + } else { /* 0.05 < p <= 1.00 */ index = p/(1000000/TFRC_CALC_X_ARRSIZE) - 1; f = tfrc_calc_x_lookup[index][0]; @@ -661,7 +658,6 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) /** * tfrc_calc_x_reverse_lookup - try to find p given f(p) - * * @fvalue: function value to match, scaled by 1000000 * Returns closest match for p, also scaled by 1000000 */ diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index d6bc47363b1..5ef32c2f0d6 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -290,14 +290,14 @@ extern int dccp_disconnect(struct sock *sk, int flags); extern int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT extern int compat_dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #endif extern int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, diff --git a/net/dccp/feat.c b/net/dccp/feat.c index b04160a2eea..972b8dc918d 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -213,7 +213,7 @@ static int dccp_feat_default_value(u8 feat_num) */ static const char *dccp_feat_fname(const u8 feat) { - static const char *feature_names[] = { + static const char *const feature_names[] = { [DCCPF_RESERVED] = "Reserved", [DCCPF_CCID] = "CCID", [DCCPF_SHORT_SEQNOS] = "Allow Short Seqnos", @@ -236,8 +236,9 @@ static const char *dccp_feat_fname(const u8 feat) return feature_names[feat]; } -static const char *dccp_feat_sname[] = { "DEFAULT", "INITIALISING", "CHANGING", - "UNSTABLE", "STABLE" }; +static const char *const dccp_feat_sname[] = { + "DEFAULT", "INITIALISING", "CHANGING", "UNSTABLE", "STABLE", +}; #ifdef CONFIG_IP_DCCP_DEBUG static const char *dccp_feat_oname(const u8 opt) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index a0a36c9e6cc..7302e1498d4 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, @@ -948,7 +948,7 @@ static struct proto dccp_v4_prot = { #endif }; -static struct net_protocol dccp_v4_protocol = { +static const struct net_protocol dccp_v4_protocol = { .handler = dccp_v4_rcv, .err_handler = dccp_v4_err, .no_policy = 1, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 3e70faab298..e48ca5d4565 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, @@ -1152,13 +1152,13 @@ static struct proto dccp_v6_prot = { #endif }; -static struct inet6_protocol dccp_v6_protocol = { +static const struct inet6_protocol dccp_v6_protocol = { .handler = dccp_v6_rcv, .err_handler = dccp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; -static struct proto_ops inet6_dccp_ops = { +static const struct proto_ops inet6_dccp_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 1bca9205104..a156319fd0a 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -124,7 +124,7 @@ EXPORT_SYMBOL_GPL(dccp_done); const char *dccp_packet_name(const int type) { - static const char *dccp_packet_names[] = { + static const char *const dccp_packet_names[] = { [DCCP_PKT_REQUEST] = "REQUEST", [DCCP_PKT_RESPONSE] = "RESPONSE", [DCCP_PKT_DATA] = "DATA", @@ -147,7 +147,7 @@ EXPORT_SYMBOL_GPL(dccp_packet_name); const char *dccp_state_name(const int state) { - static char *dccp_state_names[] = { + static const char *const dccp_state_names[] = { [DCCP_OPEN] = "OPEN", [DCCP_REQUESTING] = "REQUESTING", [DCCP_PARTOPEN] = "PARTOPEN", @@ -393,7 +393,7 @@ out: EXPORT_SYMBOL_GPL(dccp_ioctl); static int dccp_setsockopt_service(struct sock *sk, const __be32 service, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_service_list *sl = NULL; @@ -464,7 +464,7 @@ static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) } static int dccp_setsockopt_ccid(struct sock *sk, int type, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { u8 *val; int rc = 0; @@ -494,7 +494,7 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type, } static int do_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); int val, err = 0; @@ -546,7 +546,7 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, } int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, @@ -559,7 +559,7 @@ EXPORT_SYMBOL_GPL(dccp_setsockopt); #ifdef CONFIG_COMPAT int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk_compat_setsockopt(sk, level, optname, @@ -1049,10 +1049,10 @@ static int __init dccp_init(void) * * The methodology is similar to that of the buffer cache. */ - if (num_physpages >= (128 * 1024)) - goal = num_physpages >> (21 - PAGE_SHIFT); + if (totalram_pages >= (128 * 1024)) + goal = totalram_pages >> (21 - PAGE_SHIFT); else - goal = num_physpages >> (23 - PAGE_SHIFT); + goal = totalram_pages >> (23 - PAGE_SHIFT); if (thash_entries) goal = (thash_entries * diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 77d40289653..7a58c87baf1 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -157,7 +157,7 @@ static struct hlist_head dn_sk_hash[DN_SK_HASH_SIZE]; static struct hlist_head dn_wild_sk; static atomic_t decnet_memory_allocated; -static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen, int flags); +static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen, int flags); static int __dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen, int flags); static struct hlist_head *dn_find_list(struct sock *sk) @@ -1325,7 +1325,7 @@ out: return err; } -static int dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err; @@ -1337,7 +1337,7 @@ static int dn_setsockopt(struct socket *sock, int level, int optname, char __use return err; } -static int __dn_setsockopt(struct socket *sock, int level,int optname, char __user *optval, int optlen, int flags) +static int __dn_setsockopt(struct socket *sock, int level,int optname, char __user *optval, unsigned int optlen, int flags) { struct sock *sk = sock->sk; struct dn_scp *scp = DN_SK(sk); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 1c6a5bb6f0c..6e1f085db06 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -164,7 +164,7 @@ static int max_t3[] = { 8191 }; /* Must fit in 16 bits when multiplied by BCT3MU static int min_priority[1]; static int max_priority[] = { 127 }; /* From DECnet spec */ -static int dn_forwarding_proc(ctl_table *, int, struct file *, +static int dn_forwarding_proc(ctl_table *, int, void __user *, size_t *, loff_t *); static int dn_forwarding_sysctl(ctl_table *table, void __user *oldval, size_t __user *oldlenp, @@ -274,7 +274,6 @@ static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) } static int dn_forwarding_proc(ctl_table *table, int write, - struct file *filep, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -290,7 +289,7 @@ static int dn_forwarding_proc(ctl_table *table, int write, dn_db = dev->dn_ptr; old = dn_db->parms.forwarding; - err = proc_dointvec(table, write, filep, buffer, lenp, ppos); + err = proc_dointvec(table, write, buffer, lenp, ppos); if ((err >= 0) && write) { if (dn_db->parms.forwarding < 0) diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 923786bd6d0..794b5bf95af 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/decnet/dn_route.c b/net/decnet/dn_route.c index 1d6ca8a98dc..57662cabaf9 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -774,7 +774,7 @@ static int dn_rt_bug(struct sk_buff *skb) kfree_skb(skb); - return NET_RX_BAD; + return NET_RX_DROP; } static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) @@ -1750,7 +1750,7 @@ void __init dn_route_init(void) dn_route_timer.expires = jiffies + decnet_dst_gc_interval * HZ; add_timer(&dn_route_timer); - goal = num_physpages >> (26 - PAGE_SHIFT); + goal = totalram_pages >> (26 - PAGE_SHIFT); for(order = 0; (1UL << order) < goal; order++) /* NOTHING */; diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index 5bcd592ae6d..2036568beea 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -165,7 +165,6 @@ static int dn_node_address_strategy(ctl_table *table, } static int dn_node_address_handler(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -264,11 +263,10 @@ static int dn_def_dev_strategy(ctl_table *table, return -ENODEV; rv = -ENODEV; - if (dev->dn_ptr != NULL) { + if (dev->dn_ptr != NULL) rv = dn_dev_set_default(dev, 1); - if (rv) - dev_put(dev); - } + if (rv) + dev_put(dev); } return rv; @@ -276,7 +274,6 @@ static int dn_def_dev_strategy(ctl_table *table, static int dn_def_dev_handler(ctl_table *table, int write, - struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 41055f33d28..4b0ea054044 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 8fa25bafe6c..cdf2d28a029 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 815607bd286..8f53948cff4 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 1c3e30c38b8..a85c829853c 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 f0bbc57926c..0e0254fd767 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -1073,7 +1073,7 @@ static int econet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet skb->protocol = htons(ETH_P_IP); skb_pull(skb, sizeof(struct ec_framehdr)); netif_rx(skb); - return 0; + return NET_RX_SUCCESS; } sk = ec_listening_socket(hdr->port, hdr->src_stn, hdr->src_net); @@ -1084,7 +1084,7 @@ static int econet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet hdr->port)) goto drop; - return 0; + return NET_RX_SUCCESS; drop: kfree_skb(skb); diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index f99338a2610..4068a9f5113 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 af661805b9f..cd949d5e451 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -34,8 +34,8 @@ #include <net/tcp_states.h> #include <net/route.h> -#include <net/ieee802154/af_ieee802154.h> -#include <net/ieee802154/netdevice.h> +#include <net/af_ieee802154.h> +#include <net/ieee802154_netdev.h> #include "af802154.h" @@ -147,9 +147,7 @@ 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) && - dev->netdev_ops->ndo_do_ioctl) + 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 ba8b214dda8..a413b1bf446 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -26,9 +26,9 @@ #include <linux/if_arp.h> #include <linux/list.h> #include <net/sock.h> -#include <net/ieee802154/af_ieee802154.h> -#include <net/ieee802154/mac_def.h> -#include <net/ieee802154/netdevice.h> +#include <net/af_ieee802154.h> +#include <net/ieee802154.h> +#include <net/ieee802154_netdev.h> #include <asm/ioctls.h> @@ -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); @@ -380,13 +386,59 @@ int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) static int dgram_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { - return -EOPNOTSUPP; + 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) + char __user *optval, unsigned int optlen) { - return -EOPNOTSUPP; + 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 = { diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 27eda9fdf3c..ca767bde17a 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> @@ -26,12 +27,15 @@ #include <linux/netdevice.h> #include <net/netlink.h> #include <net/genetlink.h> +#include <net/sock.h> #include <linux/nl802154.h> -#include <net/ieee802154/af_ieee802154.h> -#include <net/ieee802154/nl802154.h> -#include <net/ieee802154/netdevice.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; +static DEFINE_SPINLOCK(ieee802154_seq_lock); static struct genl_family ieee802154_coordinator_family = { .id = GENL_ID_GENERATE, @@ -54,12 +58,15 @@ static struct sk_buff *ieee802154_nl_create(int flags, u8 req) { void *hdr; struct sk_buff *msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + unsigned long f; if (!msg) return NULL; + spin_lock_irqsave(&ieee802154_seq_lock, f); hdr = genlmsg_put(msg, 0, ieee802154_seq_num++, &ieee802154_coordinator_family, flags, req); + spin_unlock_irqrestore(&ieee802154_seq_lock, f); if (!hdr) { nlmsg_free(msg); return NULL; @@ -73,7 +80,7 @@ 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 +236,7 @@ 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 +255,7 @@ 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 +268,60 @@ 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 +334,7 @@ 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 +354,7 @@ 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 +380,14 @@ 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 +470,7 @@ 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 +501,19 @@ 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 +527,7 @@ 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 +542,80 @@ 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 +625,22 @@ 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 c7d71d1adca..2363ebee02e 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 9315977c4c6..30e74eee07d 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -26,7 +26,7 @@ #include <linux/if_arp.h> #include <linux/list.h> #include <net/sock.h> -#include <net/ieee802154/af_ieee802154.h> +#include <net/af_ieee802154.h> #include "af802154.h" @@ -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; } @@ -245,7 +244,7 @@ static int raw_getsockopt(struct sock *sk, int level, int optname, } static int raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c new file mode 100644 index 00000000000..f306604da67 --- /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 566ea6c4321..57737b8d171 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); @@ -243,7 +244,7 @@ EXPORT_SYMBOL(build_ehash_secret); static inline int inet_netns_ok(struct net *net, int protocol) { int hash; - struct net_protocol *ipprot; + const struct net_protocol *ipprot; if (net_eq(net, &init_net)) return 1; @@ -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? @@ -1103,6 +1119,7 @@ int inet_sk_rebuild_header(struct sock *sk) { struct flowi fl = { .oif = sk->sk_bound_dev_if, + .mark = sk->sk_mark, .nl_u = { .ip4_u = { .daddr = daddr, @@ -1141,13 +1158,12 @@ 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) { struct iphdr *iph; - struct net_protocol *ops; + const struct net_protocol *ops; int proto; int ihl; int err = -EINVAL; @@ -1183,10 +1199,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct iphdr *iph; - struct net_protocol *ops; + const struct net_protocol *ops; int proto; int ihl; int id; + unsigned int offset = 0; if (!(features & NETIF_F_V4_CSUM)) features &= ~NETIF_F_SG; @@ -1229,7 +1246,14 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features) skb = segs; do { iph = ip_hdr(skb); - iph->id = htons(id++); + if (proto == IPPROTO_UDP) { + iph->id = htons(id); + iph->frag_off = htons(offset >> 3); + if (skb->next != NULL) + iph->frag_off |= htons(IP_MF); + offset += (skb->len - skb->mac_len - iph->ihl * 4); + } else + iph->id = htons(id++); iph->tot_len = htons(skb->len - skb->mac_len); iph->check = 0; iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl); @@ -1242,7 +1266,7 @@ out: static struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - struct net_protocol *ops; + const struct net_protocol *ops; struct sk_buff **pp = NULL; struct sk_buff *p; struct iphdr *iph; @@ -1319,7 +1343,7 @@ out: static int inet_gro_complete(struct sk_buff *skb) { - struct net_protocol *ops; + const struct net_protocol *ops; struct iphdr *iph = ip_hdr(skb); int proto = iph->protocol & (MAX_INET_PROTOS - 1); int err = -ENOSYS; @@ -1361,7 +1385,6 @@ 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) @@ -1405,13 +1428,13 @@ void snmp_mib_free(void *ptr[2]) EXPORT_SYMBOL_GPL(snmp_mib_free); #ifdef CONFIG_IP_MULTICAST -static struct net_protocol igmp_protocol = { +static const struct net_protocol igmp_protocol = { .handler = igmp_rcv, .netns_ok = 1, }; #endif -static struct net_protocol tcp_protocol = { +static const struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .gso_send_check = tcp_v4_gso_send_check, @@ -1422,14 +1445,16 @@ static struct net_protocol tcp_protocol = { .netns_ok = 1, }; -static struct net_protocol udp_protocol = { +static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, + .gso_send_check = udp4_ufo_send_check, + .gso_segment = udp4_ufo_fragment, .no_policy = 1, .netns_ok = 1, }; -static struct net_protocol icmp_protocol = { +static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .no_policy = 1, .netns_ok = 1, @@ -1666,19 +1691,3 @@ 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/ah4.c b/net/ipv4/ah4.c index e878e494296..5c662703eb1 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -311,7 +311,7 @@ static const struct xfrm_type ah_type = .output = ah_output }; -static struct net_protocol ah4_protocol = { +static const struct net_protocol ah4_protocol = { .handler = xfrm4_rcv, .err_handler = ah4_err, .no_policy = 1, diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 090e9991ac2..4e80f336c0c 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/devinet.c b/net/ipv4/devinet.c index 3863c3a4223..5df2f6a0b0f 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1077,16 +1077,26 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, ip_mc_up(in_dev); /* fall through */ case NETDEV_CHANGEADDR: - if (IN_DEV_ARP_NOTIFY(in_dev)) - arp_send(ARPOP_REQUEST, ETH_P_ARP, - in_dev->ifa_list->ifa_address, - dev, - in_dev->ifa_list->ifa_address, - NULL, dev->dev_addr, NULL); + /* Send gratuitous ARP to notify of link change */ + if (IN_DEV_ARP_NOTIFY(in_dev)) { + struct in_ifaddr *ifa = in_dev->ifa_list; + + if (ifa) + arp_send(ARPOP_REQUEST, ETH_P_ARP, + ifa->ifa_address, dev, + ifa->ifa_address, NULL, + dev->dev_addr, NULL); + } break; case NETDEV_DOWN: ip_mc_down(in_dev); break; + case NETDEV_BONDING_OLDTYPE: + ip_mc_unmap(in_dev); + break; + case NETDEV_BONDING_NEWTYPE: + ip_mc_remap(in_dev); + break; case NETDEV_CHANGEMTU: if (inetdev_valid_mtu(dev->mtu)) break; @@ -1264,10 +1274,10 @@ static void inet_forward_change(struct net *net) } static int devinet_conf_proc(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { struct ipv4_devconf *cnf = ctl->extra1; @@ -1336,12 +1346,12 @@ static int devinet_conf_sysctl(ctl_table *table, } static int devinet_sysctl_forward(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *valp != val) { struct net *net = ctl->extra2; @@ -1366,12 +1376,12 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, } int ipv4_doint_and_flush(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); struct net *net = ctl->extra2; if (write && *valp != val) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 18bb383ea39..12f7287e902 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -615,7 +615,7 @@ static const struct xfrm_type esp_type = .output = esp_output }; -static struct net_protocol esp4_protocol = { +static const struct net_protocol esp4_protocol = { .handler = xfrm4_rcv, .err_handler = esp4_err, .no_policy = 1, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e2f95059256..aa00398be80 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -229,14 +229,17 @@ unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, */ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, - struct net_device *dev, __be32 *spec_dst, u32 *itag) + struct net_device *dev, __be32 *spec_dst, + u32 *itag, u32 mark) { struct in_device *in_dev; struct flowi fl = { .nl_u = { .ip4_u = { .daddr = src, .saddr = dst, .tos = tos } }, + .mark = mark, .iif = oif }; + struct fib_result res; int no_addr, rpf; int ret; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 63c2fa7b68c..291bdf50a21 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> @@ -164,6 +164,14 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn); static struct tnode *halve(struct trie *t, struct tnode *tn); /* tnodes to free after resize(); protected by RTNL */ static struct tnode *tnode_free_head; +static size_t tnode_free_size; + +/* + * synchronize_rcu after call_rcu for that many pages; it should be especially + * useful before resizing the root node with PREEMPT_NONE configs; the value was + * obtained experimentally, aiming to avoid visible slowdown. + */ +static const int sync_pages = 128; static struct kmem_cache *fn_alias_kmem __read_mostly; static struct kmem_cache *trie_leaf_kmem __read_mostly; @@ -317,8 +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 const int inflate_threshold_root = 30; static void __alias_free_mem(struct rcu_head *head) { @@ -393,6 +400,8 @@ static void tnode_free_safe(struct tnode *tn) BUG_ON(IS_LEAF(tn)); tn->tnode_free = tnode_free_head; tnode_free_head = tn; + tnode_free_size += sizeof(struct tnode) + + (sizeof(struct node *) << tn->bits); } static void tnode_free_flush(void) @@ -404,6 +413,11 @@ static void tnode_free_flush(void) tn->tnode_free = NULL; tnode_free(tn); } + + if (tnode_free_size >= PAGE_SIZE * sync_pages) { + tnode_free_size = 0; + synchronize_rcu(); + } } static struct leaf *leaf_new(void) @@ -499,14 +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; @@ -521,18 +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. @@ -601,14 +604,17 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* Keep root node larger */ - if (!tn->parent) + if (!node_parent((struct node*) tn)) { inflate_threshold_use = inflate_threshold_root; - else + 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))) { @@ -625,35 +631,19 @@ static struct node *resize(struct trie *t, struct tnode *tn) } } - if (max_resize < 0) { - if (!tn->parent) - pr_warning("Fix inflate_threshold_root." - " Now=%d size=%d bits\n", - inflate_threshold_root, tn->bits); - else - pr_warning("Fix inflate_threshold." - " Now=%d size=%d bits\n", - inflate_threshold, tn->bits); - } - 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)) { @@ -668,19 +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; @@ -694,7 +675,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) tnode_free_safe(tn); return n; } - + } return (struct node *) tn; } @@ -1435,7 +1416,7 @@ static int fn_trie_lookup(struct fib_table *tb, const struct flowi *flp, cindex = tkey_extract_bits(mask_pfx(key, current_prefix_length), pos, bits); - n = tnode_get_child(pn, cindex); + n = tnode_get_child_rcu(pn, cindex); if (n == NULL) { #ifdef CONFIG_IP_FIB_TRIE_STATS @@ -1570,7 +1551,7 @@ backtrace: if (chopped_off <= pn->bits) { cindex &= ~(1 << (chopped_off-1)); } else { - struct tnode *parent = node_parent((struct node *) pn); + struct tnode *parent = node_parent_rcu((struct node *) pn); if (!parent) goto failed; @@ -1783,7 +1764,7 @@ static struct leaf *trie_firstleaf(struct trie *t) static struct leaf *trie_nextleaf(struct leaf *l) { struct node *c = (struct node *) l; - struct tnode *p = node_parent(c); + struct tnode *p = node_parent_rcu(c); if (!p) return NULL; /* trie with just one leaf */ @@ -2391,7 +2372,7 @@ static inline const char *rtn_scope(char *buf, size_t len, enum rt_scope_t s) } } -static const char *rtn_type_names[__RTN_MAX] = { +static const char *const rtn_type_names[__RTN_MAX] = { [RTN_UNSPEC] = "UNSPEC", [RTN_UNICAST] = "UNICAST", [RTN_LOCAL] = "LOCAL", diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 97c410e8438..5bc13fe816d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -655,7 +655,7 @@ static void icmp_unreach(struct sk_buff *skb) struct iphdr *iph; struct icmphdr *icmph; int hash, protocol; - struct net_protocol *ipprot; + const struct net_protocol *ipprot; u32 info = 0; struct net *net; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 01b4284ed69..d41e5de79a8 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1298,6 +1298,28 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) } } +/* Device changing type */ + +void ip_mc_unmap(struct in_device *in_dev) +{ + struct ip_mc_list *i; + + ASSERT_RTNL(); + + for (i = in_dev->mc_list; i; i = i->next) + igmp_group_dropped(i); +} + +void ip_mc_remap(struct in_device *in_dev) +{ + struct ip_mc_list *i; + + ASSERT_RTNL(); + + for (i = in_dev->mc_list; i; i = i->next) + igmp_group_added(i); +} + /* Device going down */ void ip_mc_down(struct in_device *in_dev) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 22cd19ee44e..537731b3bcb 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -446,6 +446,28 @@ extern int sysctl_tcp_synack_retries; EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); +/* Decide when to expire the request and when to resend SYN-ACK */ +static inline void syn_ack_recalc(struct request_sock *req, const int thresh, + const int max_retries, + const u8 rskq_defer_accept, + int *expire, int *resend) +{ + if (!rskq_defer_accept) { + *expire = req->retrans >= thresh; + *resend = 1; + return; + } + *expire = req->retrans >= thresh && + (!inet_rsk(req)->acked || req->retrans >= max_retries); + /* + * Do not resend while waiting for data after ACK, + * start to resend on end of deferring period to give + * last chance for data or ACK to create established socket. + */ + *resend = !inet_rsk(req)->acked || + req->retrans >= rskq_defer_accept - 1; +} + void inet_csk_reqsk_queue_prune(struct sock *parent, const unsigned long interval, const unsigned long timeout, @@ -501,9 +523,15 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, reqp=&lopt->syn_table[i]; while ((req = *reqp) != NULL) { if (time_after_eq(now, req->expires)) { - if ((req->retrans < thresh || - (inet_rsk(req)->acked && req->retrans < max_retries)) - && !req->rsk_ops->rtx_syn_ack(parent, req)) { + int expire = 0, resend = 0; + + syn_ack_recalc(req, thresh, max_retries, + queue->rskq_defer_accept, + &expire, &resend); + if (!expire && + (!resend || + !req->rsk_ops->rtx_syn_ack(parent, req) || + inet_rsk(req)->acked)) { unsigned long timeo; if (req->retrans++ == 0) @@ -714,7 +742,7 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt); int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { const struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 61283f92882..13f0781f35c 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_fragment.c b/net/ipv4/ip_fragment.c index 575f9bd51cc..d3fe10be721 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -563,7 +563,7 @@ out_oversize: printk(KERN_INFO "Oversized IP packet from %pI4.\n", &qp->saddr); out_fail: - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMFAILS); + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); return err; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 82c11dd10a6..14333385262 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -66,10 +66,7 @@ solution, but it supposes maintaing new variable in ALL skb, even if no tunneling is used. - Current solution: t->recursion lock breaks dead loops. It looks - like dev->tbusy flag, but I preferred new variable, because - the semantics is different. One day, when hard_start_xmit - will be multithreaded we will have to use skb->encapsulation. + Current solution: HARD_TX_LOCK lock breaks dead loops. @@ -662,7 +659,7 @@ 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; @@ -678,11 +675,6 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) __be32 dst; int mtu; - if (tunnel->recursion++) { - stats->collisions++; - goto tx_error; - } - if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -820,8 +812,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) ip_rt_put(rt); stats->tx_dropped++; dev_kfree_skb(skb); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); @@ -888,8 +879,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset(skb); IPTUNNEL_XMIT(); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); @@ -897,8 +887,7 @@ tx_error_icmp: tx_error: stats->tx_errors++; dev_kfree_skb(skb); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; } static int ipgre_tunnel_bind_dev(struct net_device *dev) @@ -1288,7 +1277,7 @@ static void ipgre_fb_tunnel_init(struct net_device *dev) } -static struct net_protocol ipgre_protocol = { +static const struct net_protocol ipgre_protocol = { .handler = ipgre_rcv, .err_handler = ipgre_err, .netns_ok = 1, @@ -1475,7 +1464,7 @@ static void ipgre_tap_setup(struct net_device *dev) ether_setup(dev); - dev->netdev_ops = &ipgre_netdev_ops; + dev->netdev_ops = &ipgre_tap_netdev_ops; dev->destructor = free_netdev; dev->iflink = 0; @@ -1536,25 +1525,29 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], if (t->dev != dev) return -EEXIST; } else { - unsigned nflags = 0; - t = nt; - if (ipv4_is_multicast(p.iph.daddr)) - nflags = IFF_BROADCAST; - else if (p.iph.daddr) - nflags = IFF_POINTOPOINT; + if (dev->type != ARPHRD_ETHER) { + unsigned nflags = 0; - if ((dev->flags ^ nflags) & - (IFF_POINTOPOINT | IFF_BROADCAST)) - return -EINVAL; + if (ipv4_is_multicast(p.iph.daddr)) + nflags = IFF_BROADCAST; + else if (p.iph.daddr) + nflags = IFF_POINTOPOINT; + + if ((dev->flags ^ nflags) & + (IFF_POINTOPOINT | IFF_BROADCAST)) + return -EINVAL; + } ipgre_tunnel_unlink(ign, t); t->parms.iph.saddr = p.iph.saddr; t->parms.iph.daddr = p.iph.daddr; t->parms.i_key = p.i_key; - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); + if (dev->type != ARPHRD_ETHER) { + memcpy(dev->dev_addr, &p.iph.saddr, 4); + memcpy(dev->broadcast, &p.iph.daddr, 4); + } ipgre_tunnel_link(ign, t); netdev_state_change(dev); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index db46b4b5b2b..6c98b43badf 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -202,7 +202,7 @@ static int ip_local_deliver_finish(struct sk_buff *skb) { int protocol = ip_hdr(skb)->protocol; int hash, raw; - struct net_protocol *ipprot; + const struct net_protocol *ipprot; resubmit: raw = raw_local_deliver(skb, protocol); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7ffcd96fe59..f9895180f48 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -335,6 +335,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) { struct flowi fl = { .oif = sk->sk_bound_dev_if, + .mark = sk->sk_mark, .nl_u = { .ip4_u = { .daddr = daddr, .saddr = inet->saddr, @@ -1304,7 +1305,7 @@ 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/ip_sockglue.c b/net/ipv4/ip_sockglue.c index fc7993e9061..e982b5c1ee1 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -440,7 +440,7 @@ out: */ static int do_ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); int val = 0, err; @@ -611,6 +611,9 @@ static int do_ip_setsockopt(struct sock *sk, int level, * Check the arguments are allowable */ + if (optlen < sizeof(struct in_addr)) + goto e_inval; + err = -EFAULT; if (optlen >= sizeof(struct ip_mreqn)) { if (copy_from_user(&mreq, optval, sizeof(mreq))) @@ -631,17 +634,16 @@ static int do_ip_setsockopt(struct sock *sk, int level, break; } dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr); - if (dev) { + if (dev) mreq.imr_ifindex = dev->ifindex; - dev_put(dev); - } } else - dev = __dev_get_by_index(sock_net(sk), mreq.imr_ifindex); + dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex); err = -EADDRNOTAVAIL; if (!dev) break; + dev_put(dev); err = -EINVAL; if (sk->sk_bound_dev_if && @@ -947,7 +949,7 @@ e_inval: } int ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { int err; @@ -972,7 +974,7 @@ EXPORT_SYMBOL(ip_setsockopt); #ifdef CONFIG_COMPAT int compat_ip_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 3262ce06294..38fbf04150a 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -146,7 +146,7 @@ static const struct xfrm_type ipcomp_type = { .output = ipcomp_output }; -static struct net_protocol ipcomp4_protocol = { +static const struct net_protocol ipcomp4_protocol = { .handler = xfrm4_rcv, .err_handler = ipcomp4_err, .no_policy = 1, diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 93e2b787da2..ae40ed1ba56 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; @@ -402,11 +402,6 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) __be32 dst = tiph->daddr; int mtu; - if (tunnel->recursion++) { - stats->collisions++; - goto tx_error; - } - if (skb->protocol != htons(ETH_P_IP)) goto tx_error; @@ -443,25 +438,27 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_error; } - if (tiph->frag_off) + df |= old_iph->frag_off & htons(IP_DF); + + if (df) { mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); - else - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; - if (mtu < 68) { - stats->collisions++; - ip_rt_put(rt); - goto tx_error; - } - if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + if (mtu < 68) { + stats->collisions++; + ip_rt_put(rt); + goto tx_error; + } - df |= (old_iph->frag_off&htons(IP_DF)); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); - if ((old_iph->frag_off&htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); - ip_rt_put(rt); - goto tx_error; + if ((old_iph->frag_off & htons(IP_DF)) && + mtu < ntohs(old_iph->tot_len)) { + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + ip_rt_put(rt); + goto tx_error; + } } if (tunnel->err_count > 0) { @@ -485,8 +482,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) ip_rt_put(rt); stats->tx_dropped++; dev_kfree_skb(skb); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); @@ -523,16 +519,14 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset(skb); IPTUNNEL_XMIT(); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: stats->tx_errors++; dev_kfree_skb(skb); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; } static void ipip_tunnel_bind_dev(struct net_device *dev) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9a8da5ed92b..99508d66a64 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -99,10 +99,6 @@ static int ipmr_cache_report(struct net *net, struct sk_buff *pkt, vifi_t vifi, int assert); static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); -#ifdef CONFIG_IP_PIMSM_V2 -static struct net_protocol pim_protocol; -#endif - static struct timer_list ipmr_expire_timer; /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ @@ -201,7 +197,7 @@ 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); @@ -212,7 +208,7 @@ static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) IGMPMSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } static const struct net_device_ops reg_vif_netdev_ops = { @@ -487,8 +483,10 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) return -EINVAL; } - if ((in_dev = __in_dev_get_rtnl(dev)) == NULL) + if ((in_dev = __in_dev_get_rtnl(dev)) == NULL) { + dev_put(dev); return -EADDRNOTAVAIL; + } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; ip_rt_multicast_event(in_dev); @@ -935,7 +933,7 @@ static void mrtsock_destruct(struct sock *sk) * MOSPF/PIM router set up we can clean this up. */ -int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) +int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { int ret; struct vifctl vif; @@ -1945,7 +1943,7 @@ static const struct file_operations ipmr_mfc_fops = { #endif #ifdef CONFIG_IP_PIMSM_V2 -static struct net_protocol pim_protocol = { +static const struct net_protocol pim_protocol = { .handler = pim_rcv, .netns_ok = 1, }; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 7505dff4ffd..27774c99d88 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -8,7 +8,7 @@ * Copyright (C) 2002 David S. Miller (davem@redhat.com) * */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netdevice.h> @@ -341,15 +341,11 @@ unsigned int arpt_do_table(struct sk_buff *skb, } /* All zeroes == unconditional rule. */ -static inline int unconditional(const struct arpt_arp *arp) +static inline bool unconditional(const struct arpt_arp *arp) { - unsigned int i; + static const struct arpt_arp uncond; - for (i = 0; i < sizeof(*arp)/sizeof(__u32); i++) - if (((__u32 *)arp)[i]) - return 0; - - return 1; + return memcmp(arp, &uncond, sizeof(uncond)) == 0; } /* Figures out from what hook each rule can be called: returns 0 if @@ -537,12 +533,28 @@ out: return ret; } +static bool check_underflow(struct arpt_entry *e) +{ + const struct arpt_entry_target *t; + unsigned int verdict; + + if (!unconditional(&e->arp)) + return false; + t = arpt_get_target(e); + if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) + return false; + verdict = ((struct arpt_standard_target *)t)->verdict; + verdict = -verdict - 1; + return verdict == NF_DROP || verdict == NF_ACCEPT; +} + static inline int check_entry_size_and_hooks(struct arpt_entry *e, struct xt_table_info *newinfo, unsigned char *base, unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, + unsigned int valid_hooks, unsigned int *i) { unsigned int h; @@ -562,15 +574,21 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, /* Check hooks & underflows */ for (h = 0; h < NF_ARP_NUMHOOKS; h++) { + if (!(valid_hooks & (1 << h))) + continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) + if ((unsigned char *)e - base == underflows[h]) { + if (!check_underflow(e)) { + pr_err("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); + return -EINVAL; + } newinfo->underflow[h] = underflows[h]; + } } - /* FIXME: underflows must be unconditional, standard verdicts - < 0 (not ARPT_RETURN). --RR */ - /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; @@ -630,7 +648,7 @@ static int translate_table(const char *name, newinfo, entry0, entry0 + size, - hook_entries, underflows, &i); + hook_entries, underflows, valid_hooks, &i); duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret); if (ret != 0) return ret; @@ -1760,7 +1778,8 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } -struct xt_table *arpt_register_table(struct net *net, struct xt_table *table, +struct xt_table *arpt_register_table(struct net *net, + const struct xt_table *table, const struct arpt_replace *repl) { int ret; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 6ecfdae7c58..97337601827 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -15,7 +15,7 @@ MODULE_DESCRIPTION("arptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \ (1 << NF_ARP_FORWARD)) -static struct +static const struct { struct arpt_replace repl; struct arpt_standard entries[3]; @@ -45,7 +45,7 @@ static struct .term = ARPT_ERROR_INIT, }; -static struct xt_table packet_filter = { +static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index fdefae6b5df..cde755d5eea 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -8,6 +8,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cache.h> #include <linux/capability.h> #include <linux/skbuff.h> @@ -190,16 +191,11 @@ get_entry(void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline int -unconditional(const struct ipt_ip *ip) +static inline bool unconditional(const struct ipt_ip *ip) { - unsigned int i; - - for (i = 0; i < sizeof(*ip)/sizeof(__u32); i++) - if (((__u32 *)ip)[i]) - return 0; + static const struct ipt_ip uncond; - return 1; + return memcmp(ip, &uncond, sizeof(uncond)) == 0; #undef FWINV } @@ -315,7 +311,6 @@ ipt_do_table(struct sk_buff *skb, static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; - u_int16_t datalen; bool hotdrop = false; /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; @@ -328,7 +323,6 @@ ipt_do_table(struct sk_buff *skb, /* Initialization */ ip = ip_hdr(skb); - datalen = skb->len - ip->ihl * 4; indev = in ? in->name : nulldevname; outdev = out ? out->name : nulldevname; /* We handle fragments by dealing with the first fragment as @@ -427,8 +421,6 @@ ipt_do_table(struct sk_buff *skb, #endif /* Target might have changed stuff. */ ip = ip_hdr(skb); - datalen = skb->len - ip->ihl * 4; - if (verdict == IPT_CONTINUE) e = ipt_next_entry(e); else @@ -716,6 +708,21 @@ find_check_entry(struct ipt_entry *e, const char *name, unsigned int size, return ret; } +static bool check_underflow(struct ipt_entry *e) +{ + const struct ipt_entry_target *t; + unsigned int verdict; + + if (!unconditional(&e->ip)) + return false; + t = ipt_get_target(e); + if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) + return false; + verdict = ((struct ipt_standard_target *)t)->verdict; + verdict = -verdict - 1; + return verdict == NF_DROP || verdict == NF_ACCEPT; +} + static int check_entry_size_and_hooks(struct ipt_entry *e, struct xt_table_info *newinfo, @@ -723,6 +730,7 @@ check_entry_size_and_hooks(struct ipt_entry *e, unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, + unsigned int valid_hooks, unsigned int *i) { unsigned int h; @@ -742,15 +750,21 @@ check_entry_size_and_hooks(struct ipt_entry *e, /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { + if (!(valid_hooks & (1 << h))) + continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) + if ((unsigned char *)e - base == underflows[h]) { + if (!check_underflow(e)) { + pr_err("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); + return -EINVAL; + } newinfo->underflow[h] = underflows[h]; + } } - /* FIXME: underflows must be unconditional, standard verdicts - < 0 (not IPT_RETURN). --RR */ - /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; @@ -813,7 +827,7 @@ translate_table(const char *name, newinfo, entry0, entry0 + size, - hook_entries, underflows, &i); + hook_entries, underflows, valid_hooks, &i); if (ret != 0) return ret; @@ -2051,7 +2065,8 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -struct xt_table *ipt_register_table(struct net *net, struct xt_table *table, +struct xt_table *ipt_register_table(struct net *net, + const struct xt_table *table, const struct ipt_replace *repl) { int ret; diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index c30a969724f..df566cbd68e 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -53,11 +53,11 @@ static struct .term = IPT_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_filter = { +static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET, + .af = NFPROTO_IPV4, }; /* The work comes in here from netfilter.c. */ @@ -102,21 +102,21 @@ static struct nf_hook_ops ipt_ops[] __read_mostly = { { .hook = ipt_local_in_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_FILTER, }, { .hook = ipt_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_FILTER, }, { .hook = ipt_local_out_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_FILTER, }, diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 4087614d951..036047f9b0f 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -28,7 +28,7 @@ MODULE_DESCRIPTION("iptables mangle table"); (1 << NF_INET_POST_ROUTING)) /* Ouch - five different hooks? Maybe this should be a config option..... -- BC */ -static struct +static const struct { struct ipt_replace repl; struct ipt_standard entries[5]; @@ -64,11 +64,11 @@ static struct .term = IPT_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_mangler = { +static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET, + .af = NFPROTO_IPV4, }; /* The work comes in here from netfilter.c. */ @@ -162,35 +162,35 @@ static struct nf_hook_ops ipt_ops[] __read_mostly = { { .hook = ipt_pre_routing_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_MANGLE, }, { .hook = ipt_local_in_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_MANGLE, }, { .hook = ipt_forward_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_MANGLE, }, { .hook = ipt_local_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_MANGLE, }, { .hook = ipt_post_routing_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_MANGLE, }, diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index e5356da1fb5..993edc23be0 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -9,7 +9,7 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static struct +static const struct { struct ipt_replace repl; struct ipt_standard entries[2]; @@ -36,11 +36,11 @@ static struct .term = IPT_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_raw = { +static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET, + .af = NFPROTO_IPV4, }; /* The work comes in here from netfilter.c. */ @@ -74,14 +74,14 @@ ipt_local_hook(unsigned int hook, static struct nf_hook_ops ipt_ops[] __read_mostly = { { .hook = ipt_hook, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_RAW, .owner = THIS_MODULE, }, { .hook = ipt_local_hook, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_RAW, .owner = THIS_MODULE, diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 29ab630f240..99eb76c65d2 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -27,7 +27,7 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static struct +static const struct { struct ipt_replace repl; struct ipt_standard entries[3]; @@ -57,11 +57,11 @@ static struct .term = IPT_ERROR_INIT, /* ERROR */ }; -static struct xt_table security_table = { +static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET, + .af = NFPROTO_IPV4, }; static unsigned int @@ -105,21 +105,21 @@ static struct nf_hook_ops ipt_ops[] __read_mostly = { { .hook = ipt_local_in_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_SECURITY, }, { .hook = ipt_forward_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SECURITY, }, { .hook = ipt_local_out_hook, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SECURITY, }, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 7d2ead7228a..aa95bb82ee6 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -26,6 +26,7 @@ #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/nf_nat_helper.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> +#include <net/netfilter/nf_log.h> int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, struct nf_conn *ct, @@ -113,8 +114,11 @@ static unsigned int ipv4_confirm(unsigned int hooknum, ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), ct, ctinfo); - if (ret != NF_ACCEPT) + if (ret != NF_ACCEPT) { + nf_log_packet(NFPROTO_IPV4, hooknum, skb, in, out, NULL, + "nf_ct_%s: dropping packet", helper->name); return ret; + } if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) { typeof(nf_nat_seq_adjust_hook) seq_adjust; @@ -158,28 +162,28 @@ static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = { { .hook = ipv4_conntrack_in, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_CONNTRACK, }, { .hook = ipv4_conntrack_local, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_CONNTRACK, }, { .hook = ipv4_confirm, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, { .hook = ipv4_confirm, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, @@ -256,11 +260,11 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) tuple.dst.u3.ip = inet->daddr; tuple.dst.u.tcp.port = inet->dport; tuple.src.l3num = PF_INET; - tuple.dst.protonum = IPPROTO_TCP; + tuple.dst.protonum = sk->sk_protocol; - /* We only do TCP at the moment: is there a better way? */ - if (strcmp(sk->sk_prot->name, "TCP")) { - pr_debug("SO_ORIGINAL_DST: Not a TCP socket\n"); + /* We only do TCP and SCTP at the moment: is there a better way? */ + if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP) { + pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n"); return -ENOPROTOOPT; } diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 3229e0a81ba..fe1a64479dd 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -212,7 +212,7 @@ find_best_ips_proto(struct nf_conntrack_tuple *tuple, maxip = ntohl(range->max_ip); j = jhash_2words((__force u32)tuple->src.u3.ip, range->flags & IP_NAT_RANGE_PERSISTENT ? - (__force u32)tuple->dst.u3.ip : 0, 0); + 0 : (__force u32)tuple->dst.u3.ip, 0); j = ((u64)j * (maxip - minip + 1)) >> 32; *var_ipp = htonl(minip + j); } @@ -620,7 +620,7 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { }; static int -nfnetlink_parse_nat(struct nlattr *nat, +nfnetlink_parse_nat(const struct nlattr *nat, const struct nf_conn *ct, struct nf_nat_range *range) { struct nlattr *tb[CTA_NAT_MAX+1]; @@ -656,7 +656,7 @@ nfnetlink_parse_nat(struct nlattr *nat, static int nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, - struct nlattr *attr) + const struct nlattr *attr) { struct nf_nat_range range; @@ -671,7 +671,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, static int nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, - struct nlattr *attr) + const struct nlattr *attr) { return -EOPNOTSUPP; } @@ -750,6 +750,8 @@ static int __init nf_nat_init(void) BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); rcu_assign_pointer(nfnetlink_parse_nat_setup_hook, nfnetlink_parse_nat_setup); + BUG_ON(nf_ct_nat_offset != NULL); + rcu_assign_pointer(nf_ct_nat_offset, nf_nat_get_offset); return 0; cleanup_extend: @@ -764,6 +766,7 @@ static void __exit nf_nat_cleanup(void) nf_ct_extend_unregister(&nat_extend); rcu_assign_pointer(nf_nat_seq_adjust_hook, NULL); rcu_assign_pointer(nfnetlink_parse_nat_setup_hook, NULL); + rcu_assign_pointer(nf_ct_nat_offset, NULL); synchronize_net(); } diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 09172a65d9b..f9520fa3aba 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -73,6 +73,28 @@ adjust_tcp_sequence(u32 seq, DUMP_OFFSET(this_way); } +/* Get the offset value, for conntrack */ +s16 nf_nat_get_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq) +{ + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way; + s16 offset; + + if (!nat) + return 0; + + this_way = &nat->seq[dir]; + spin_lock_bh(&nf_nat_seqofs_lock); + offset = after(seq, this_way->correction_pos) + ? this_way->offset_after : this_way->offset_before; + spin_unlock_bh(&nf_nat_seqofs_lock); + + return offset; +} +EXPORT_SYMBOL_GPL(nf_nat_get_offset); + /* Frobs data inside this packet, which is linear. */ static void mangle_contents(struct sk_buff *skb, unsigned int dataoff, @@ -189,11 +211,6 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb, adjust_tcp_sequence(ntohl(tcph->seq), (int)rep_len - (int)match_len, ct, ctinfo); - /* Tell TCP window tracking about seq change */ - nf_conntrack_tcp_update(skb, ip_hdrlen(skb), - ct, CTINFO2DIR(ctinfo), - (int)rep_len - (int)match_len); - nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); } return 1; @@ -415,12 +432,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, tcph->seq = newseq; tcph->ack_seq = newack; - if (!nf_nat_sack_adjust(skb, tcph, ct, ctinfo)) - return 0; - - nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir, seqoff); - - return 1; + return nf_nat_sack_adjust(skb, tcph, ct, ctinfo); } /* Setup NAT on this expected conntrack so it follows master. */ diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index 6348a793936..9e81e0dfb4e 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -28,7 +28,7 @@ (1 << NF_INET_POST_ROUTING) | \ (1 << NF_INET_LOCAL_OUT)) -static struct +static const struct { struct ipt_replace repl; struct ipt_standard entries[3]; @@ -58,11 +58,11 @@ static struct .term = IPT_ERROR_INIT, /* ERROR */ }; -static struct xt_table nat_table = { +static const struct xt_table nat_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET, + .af = NFPROTO_IPV4, }; /* Source NAT */ diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 5567bd0d075..5f41d017ddd 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -251,7 +251,7 @@ static struct nf_hook_ops nf_nat_ops[] __read_mostly = { { .hook = nf_nat_in, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, @@ -259,7 +259,7 @@ static struct nf_hook_ops nf_nat_ops[] __read_mostly = { { .hook = nf_nat_out, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, @@ -267,7 +267,7 @@ static struct nf_hook_ops nf_nat_ops[] __read_mostly = { { .hook = nf_nat_local_fn, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, @@ -275,7 +275,7 @@ static struct nf_hook_ops nf_nat_ops[] __read_mostly = { { .hook = nf_nat_fn, .owner = THIS_MODULE, - .pf = PF_INET, + .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, }, diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index ea50da0649f..542f22fc98b 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -22,35 +22,20 @@ * 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; +const struct net_protocol *inet_protos[MAX_INET_PROTOS] ____cacheline_aligned_in_smp; static DEFINE_SPINLOCK(inet_proto_lock); /* * Add a protocol handler to the hash tables */ -int inet_add_protocol(struct net_protocol *prot, unsigned char protocol) +int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { int hash, ret; @@ -72,7 +57,7 @@ int inet_add_protocol(struct net_protocol *prot, unsigned char protocol) * Remove a protocol from the hash tables. */ -int inet_del_protocol(struct net_protocol *prot, unsigned char protocol) +int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol) { int hash, ret; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 2979f14bb18..ab996f9c0fe 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -352,13 +352,24 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, skb->ip_summed = CHECKSUM_NONE; skb->transport_header = skb->network_header; - err = memcpy_fromiovecend((void *)iph, from, 0, length); - if (err) - goto error_fault; + err = -EFAULT; + if (memcpy_fromiovecend((void *)iph, from, 0, length)) + goto error_free; - /* We don't modify invalid header */ iphlen = iph->ihl * 4; - if (iphlen >= sizeof(*iph) && iphlen <= length) { + + /* + * We don't want to modify the ip header, but we do need to + * be sure that it won't cause problems later along the network + * stack. Specifically we want to make sure that iph->ihl is a + * sane value. If ihl points beyond the length of the buffer passed + * in, reject the frame as invalid + */ + err = -EINVAL; + if (iphlen > length) + goto error_free; + + if (iphlen >= sizeof(*iph)) { if (!iph->saddr) iph->saddr = rt->rt_src; iph->check = 0; @@ -375,17 +386,18 @@ 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: return 0; -error_fault: - err = -EFAULT; +error_free: kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); + if (err == -ENOBUFS && !inet->recverr) + err = 0; return err; } @@ -576,8 +588,11 @@ 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: @@ -736,7 +751,7 @@ out: return ret; } static int do_raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (optname == ICMP_FILTER) { if (inet_sk(sk)->num != IPPROTO_ICMP) @@ -748,7 +763,7 @@ static int do_raw_setsockopt(struct sock *sk, int level, int optname, } static int raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_RAW) return ip_setsockopt(sk, level, optname, optval, optlen); @@ -757,7 +772,7 @@ static int raw_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT static int compat_raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_RAW) return compat_ip_setsockopt(sk, level, optname, optval, optlen); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 278f46f5011..5b1050a5d87 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) @@ -1852,7 +1854,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto e_inval; spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); } else if (fib_validate_source(saddr, 0, tos, 0, - dev, &spec_dst, &itag) < 0) + dev, &spec_dst, &itag, 0) < 0) goto e_inval; rth = dst_alloc(&ipv4_dst_ops); @@ -1965,7 +1967,7 @@ static int __mkroute_input(struct sk_buff *skb, err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(*res), - in_dev->dev, &spec_dst, &itag); + in_dev->dev, &spec_dst, &itag, skb->mark); if (err < 0) { ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); @@ -2139,7 +2141,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, int result; result = fib_validate_source(saddr, daddr, tos, net->loopback_dev->ifindex, - dev, &spec_dst, &itag); + dev, &spec_dst, &itag, skb->mark); if (result < 0) goto martian_source; if (result) @@ -2168,7 +2170,7 @@ brd_input: spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); else { err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst, - &itag); + &itag, skb->mark); if (err < 0) goto martian_source; if (err) @@ -3034,7 +3036,7 @@ void ip_rt_multicast_event(struct in_device *in_dev) #ifdef CONFIG_SYSCTL static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { if (write) { @@ -3044,7 +3046,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, memcpy(&ctl, __ctl, sizeof(ctl)); ctl.data = &flush_delay; - proc_dointvec(&ctl, write, filp, buffer, lenp, ppos); + proc_dointvec(&ctl, write, buffer, lenp, ppos); net = (struct net *)__ctl->extra1; rt_cache_flush(net, flush_delay); @@ -3104,12 +3106,11 @@ static void rt_secret_reschedule(int old) } static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int old = ip_rt_secret_interval; - int ret = proc_dointvec_jiffies(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); rt_secret_reschedule(old); @@ -3412,7 +3413,7 @@ int __init ip_rt_init(void) alloc_large_system_hash("IP route cache", sizeof(struct rt_hash_bucket), rhash_entries, - (num_physpages >= 128 * 1024) ? + (totalram_pages >= 128 * 1024) ? 15 : 17, 0, &rt_hash_log, @@ -3442,7 +3443,7 @@ int __init ip_rt_init(void) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); - xfrm4_init(); + xfrm4_init(ip_rt_max_size); #endif rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index cd2b97f1b6e..a6e0e077ac3 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -37,12 +37,13 @@ __initcall(init_syncookies); #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) -static DEFINE_PER_CPU(__u32, cookie_scratch)[16 + 5 + SHA_WORKSPACE_WORDS]; +static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], + ipv4_cookie_scratch); static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, u32 count, int c) { - __u32 *tmp = __get_cpu_var(cookie_scratch); + __u32 *tmp = __get_cpu_var(ipv4_cookie_scratch); memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c])); tmp[0] = (__force u32)saddr; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4710d219f06..2dcf04d9b00 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -36,7 +36,7 @@ static void set_local_port_range(int range[2]) } /* Validate changes from /proc interface. */ -static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp, +static int ipv4_local_port_range(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -51,7 +51,7 @@ static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp, }; inet_get_local_port_range(range, range + 1); - ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { if (range[1] < range[0]) @@ -91,7 +91,7 @@ static int ipv4_sysctl_local_port_range(ctl_table *table, } -static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * filp, +static int proc_tcp_congestion_control(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char val[TCP_CA_NAME_MAX]; @@ -103,7 +103,7 @@ static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * tcp_get_default_congestion_control(val); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_default_congestion_control(val); return ret; @@ -129,7 +129,7 @@ static int sysctl_tcp_congestion_control(ctl_table *table, } static int proc_tcp_available_congestion_control(ctl_table *ctl, - int write, struct file * filp, + int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -140,13 +140,13 @@ static int proc_tcp_available_congestion_control(ctl_table *ctl, if (!tbl.data) return -ENOMEM; tcp_get_available_congestion_control(tbl.data, TCP_CA_BUF_MAX); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_allowed_congestion_control(ctl_table *ctl, - int write, struct file * filp, + int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -158,7 +158,7 @@ static int proc_allowed_congestion_control(ctl_table *ctl, return -ENOMEM; tcp_get_allowed_congestion_control(tbl.data, tbl.maxlen); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_allowed_congestion_control(tbl.data); kfree(tbl.data); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 91145244ea6..f1813bc7108 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -326,6 +326,43 @@ void tcp_enter_memory_pressure(struct sock *sk) EXPORT_SYMBOL(tcp_enter_memory_pressure); +/* Convert seconds to retransmits based on initial and max timeout */ +static u8 secs_to_retrans(int seconds, int timeout, int rto_max) +{ + u8 res = 0; + + if (seconds > 0) { + int period = timeout; + + res = 1; + while (seconds > period && res < 255) { + res++; + timeout <<= 1; + if (timeout > rto_max) + timeout = rto_max; + period += timeout; + } + } + return res; +} + +/* Convert retransmits to seconds based on initial and max timeout */ +static int retrans_to_secs(u8 retrans, int timeout, int rto_max) +{ + int period = 0; + + if (retrans > 0) { + period = timeout; + while (--retrans) { + timeout <<= 1; + if (timeout > rto_max) + timeout = rto_max; + period += timeout; + } + } + return period; +} + /* * Wait for a TCP event. * @@ -580,7 +617,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, lock_sock(sk); - timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); + timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK); while (tss.len) { ret = __tcp_splice_read(sk, &tss); if (ret < 0) @@ -1146,7 +1183,9 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) #if TCP_DEBUG struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); - WARN_ON(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)); + WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), + KERN_INFO "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", + tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); #endif if (inet_csk_ack_scheduled(sk)) { @@ -1393,11 +1432,13 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* Now that we have two receive queues this * shouldn't happen. */ - if (before(*seq, TCP_SKB_CB(skb)->seq)) { - printk(KERN_INFO "recvmsg bug: copied %X " - "seq %X\n", *seq, TCP_SKB_CB(skb)->seq); + if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), + KERN_INFO "recvmsg bug: copied %X " + "seq %X rcvnxt %X fl %X\n", *seq, + TCP_SKB_CB(skb)->seq, tp->rcv_nxt, + flags)) break; - } + offset = *seq - TCP_SKB_CB(skb)->seq; if (tcp_hdr(skb)->syn) offset--; @@ -1405,7 +1446,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto found_ok_skb; if (tcp_hdr(skb)->fin) goto found_fin_ok; - WARN_ON(!(flags & MSG_PEEK)); + WARN(!(flags & MSG_PEEK), KERN_INFO "recvmsg bug 2: " + "copied %X seq %X rcvnxt %X fl %X\n", + *seq, TCP_SKB_CB(skb)->seq, + tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ @@ -1839,7 +1883,7 @@ 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); @@ -2012,7 +2056,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; tp->packets_out = 0; - tp->snd_ssthresh = 0x7fffffff; + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->bytes_acked = 0; tcp_set_ca_state(sk, TCP_CA_Open); @@ -2032,7 +2076,7 @@ int tcp_disconnect(struct sock *sk, int flags) * Socket option code for TCP. */ static int do_tcp_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -2047,7 +2091,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, return -EINVAL; val = strncpy_from_user(name, optval, - min(TCP_CA_NAME_MAX-1, optlen)); + min_t(long, TCP_CA_NAME_MAX-1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; @@ -2163,16 +2207,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_DEFER_ACCEPT: - icsk->icsk_accept_queue.rskq_defer_accept = 0; - if (val > 0) { - /* Translate value in seconds to number of - * retransmits */ - while (icsk->icsk_accept_queue.rskq_defer_accept < 32 && - val > ((TCP_TIMEOUT_INIT / HZ) << - icsk->icsk_accept_queue.rskq_defer_accept)) - icsk->icsk_accept_queue.rskq_defer_accept++; - icsk->icsk_accept_queue.rskq_defer_accept++; - } + /* Translate value in seconds to number of retransmits */ + icsk->icsk_accept_queue.rskq_defer_accept = + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: @@ -2220,7 +2258,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, } int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen) + unsigned int optlen) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -2232,7 +2270,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, #ifdef CONFIG_COMPAT int compat_tcp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_TCP) return inet_csk_compat_setsockopt(sk, level, optname, @@ -2336,13 +2374,13 @@ 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; @@ -2353,8 +2391,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : sysctl_tcp_fin_timeout) / HZ; break; case TCP_DEFER_ACCEPT: - val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 : - ((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1)); + val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, + TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; @@ -2658,7 +2696,7 @@ 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 +2709,7 @@ 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 +2726,7 @@ 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 +2747,7 @@ 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--; @@ -2862,7 +2900,7 @@ void __init tcp_init(void) alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, - (num_physpages >= 128 * 1024) ? + (totalram_pages >= 128 * 1024) ? 13 : 15, 0, &tcp_hashinfo.ehash_size, @@ -2879,7 +2917,7 @@ void __init tcp_init(void) alloc_large_system_hash("TCP bind", sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_size, - (num_physpages >= 128 * 1024) ? + (totalram_pages >= 128 * 1024) ? 13 : 15, 0, &tcp_hashinfo.bhash_size, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index e92beb9e55e..6428b342b16 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -116,7 +116,7 @@ int tcp_set_default_congestion_control(const char *name) spin_lock(&tcp_cong_list_lock); ca = tcp_ca_find(name); #ifdef CONFIG_MODULES - if (!ca && capable(CAP_SYS_MODULE)) { + if (!ca && capable(CAP_NET_ADMIN)) { spin_unlock(&tcp_cong_list_lock); request_module("tcp_%s", name); @@ -246,7 +246,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) #ifdef CONFIG_MODULES /* not found attempt to autoload module */ - if (!ca && capable(CAP_SYS_MODULE)) { + if (!ca && capable(CAP_NET_ADMIN)) { rcu_read_unlock(); request_module("tcp_%s", name); rcu_read_lock(); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2bdb0da237e..d86784be7ab 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. @@ -762,7 +761,7 @@ void tcp_update_metrics(struct sock *sk) set_dst_metric_rtt(dst, RTAX_RTTVAR, var); } - if (tp->snd_ssthresh >= 0xFFFF) { + if (tcp_in_initial_slowstart(tp)) { /* Slow start still did not finish. */ if (dst_metric(dst, RTAX_SSTHRESH) && !dst_metric_locked(dst, RTAX_SSTHRESH) && diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6d88219c5e2..7cda24b53f6 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, @@ -1770,7 +1808,7 @@ static int tcp_v4_init_sock(struct sock *sk) /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ - tp->snd_ssthresh = 0x7fffffff; /* Infinity */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = 536; @@ -2246,7 +2284,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - tp->snd_ssthresh >= 0xFFFF ? -1 : tp->snd_ssthresh, + tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh, len); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f8d67ccc64f..4c03598ed92 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); @@ -363,7 +363,7 @@ void tcp_twsk_destructor(struct sock *sk) #ifdef CONFIG_TCP_MD5SIG struct tcp_timewait_sock *twsk = tcp_twsk(sk); if (twsk->tw_md5_keylen) - tcp_put_md5sig_pool(); + tcp_free_md5sig_pool(); #endif } @@ -410,7 +410,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->retrans_out = 0; newtp->sacked_out = 0; newtp->fackets_out = 0; - newtp->snd_ssthresh = 0x7fffffff; + newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -641,8 +641,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; - /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ - if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && + /* While TCP_DEFER_ACCEPT is active, drop bare ACK. */ + if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { inet_rsk(req)->acked = 1; return NULL; @@ -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 bd62712848f..fcd278a7080 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -59,6 +59,7 @@ int sysctl_tcp_base_mss __read_mostly = 512; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; +/* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -142,6 +143,7 @@ static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst) tp->snd_cwnd_used = 0; } +/* Congestion state accounting after a packet has been sent. */ static void tcp_event_data_sent(struct tcp_sock *tp, struct sk_buff *skb, struct sock *sk) { @@ -161,6 +163,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, icsk->icsk_ack.pingpong = 1; } +/* Account for an ACK we sent. */ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) { tcp_dec_quickack_mode(sk, pkts); @@ -276,6 +279,7 @@ static u16 tcp_select_window(struct sock *sk) return new_win; } +/* Packet ECN state for a SYN-ACK */ static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_CWR; @@ -283,6 +287,7 @@ static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb) TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_ECE; } +/* Packet ECN state for a SYN. */ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -301,6 +306,9 @@ TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th) th->ece = 1; } +/* Set up ECN state for a packet on a ESTABLISHED socket that is about to + * be sent. + */ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb, int tcp_header_len) { @@ -353,6 +361,7 @@ static inline int tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_SACK_ADVERTISE (1 << 0) #define OPTION_TS (1 << 1) #define OPTION_MD5 (1 << 2) +#define OPTION_WSCALE (1 << 3) struct tcp_out_options { u8 options; /* bit field of OPTION_* */ @@ -362,7 +371,9 @@ struct tcp_out_options { __u32 tsval, tsecr; /* need to include OPTION_TS */ }; -/* Beware: Something in the Internet is very sensitive to the ordering of +/* Write previously computed TCP options to the packet. + * + * Beware: Something in the Internet is very sensitive to the ordering of * TCP options, we learned this through the hard way, so be careful here. * Luckily we can at least blame others for their non-compliance but from * inter-operatibility perspective it seems that we're somewhat stuck with @@ -417,7 +428,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, TCPOLEN_SACK_PERM); } - if (unlikely(opts->ws)) { + if (unlikely(OPTION_WSCALE & opts->options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | @@ -445,6 +456,9 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, } } +/* Compute TCP options for SYN packets. This is not the final + * network wire format yet. + */ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { @@ -481,8 +495,8 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, } if (likely(sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; - if (likely(opts->ws)) - size += TCPOLEN_WSCALE_ALIGNED; + opts->options |= OPTION_WSCALE; + size += TCPOLEN_WSCALE_ALIGNED; } if (likely(sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; @@ -493,6 +507,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, return size; } +/* Set up TCP options for SYN-ACKs. */ static unsigned tcp_synack_options(struct sock *sk, struct request_sock *req, unsigned mss, struct sk_buff *skb, @@ -523,8 +538,8 @@ static unsigned tcp_synack_options(struct sock *sk, if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; - if (likely(opts->ws)) - size += TCPOLEN_WSCALE_ALIGNED; + opts->options |= OPTION_WSCALE; + size += TCPOLEN_WSCALE_ALIGNED; } if (likely(doing_ts)) { opts->options |= OPTION_TS; @@ -541,6 +556,9 @@ static unsigned tcp_synack_options(struct sock *sk, return size; } +/* Compute TCP options for ESTABLISHED sockets. This is not the + * final wire format yet. + */ static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { @@ -705,7 +723,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, return net_xmit_eval(err); } -/* This routine just queue's the buffer +/* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, * otherwise socket can stall. @@ -722,6 +740,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) sk_mem_charge(sk, skb->truesize); } +/* Initialize TSO segments for a packet. */ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { @@ -909,6 +928,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) skb->len = skb->data_len; } +/* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) @@ -937,7 +957,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) return 0; } -/* Not accounting for SACKs here. */ +/* Calculate MSS. Not accounting for SACKs here. */ int tcp_mtu_to_mss(struct sock *sk, int pmtu) { struct tcp_sock *tp = tcp_sk(sk); @@ -981,6 +1001,7 @@ int tcp_mss_to_mtu(struct sock *sk, int mss) return mtu; } +/* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -1143,7 +1164,8 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, return 0; } -/* This must be invoked the first time we consider transmitting +/* Intialize TSO state of a skb. + * This must be invoked the first time we consider transmitting * SKB onto the wire. */ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, @@ -1158,6 +1180,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, return tso_segs; } +/* Minshall's variant of the Nagle send check. */ static inline int tcp_minshall_check(const struct tcp_sock *tp) { return after(tp->snd_sml, tp->snd_una) && @@ -1242,6 +1265,7 @@ static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb, return cwnd_quota; } +/* Test if sending is allowed right now. */ int tcp_may_send_now(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -1378,6 +1402,10 @@ send_now: } /* Create a new MTU probe if we are ready. + * MTU probe is regularly attempting to increase the path MTU by + * deliberately sending larger packets. This discovers routing + * changes resulting in larger path MTUs. + * * Returns 0 if we should wait to probe (no cwnd available), * 1 if a probe was sent, * -1 otherwise @@ -1790,6 +1818,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) sk_wmem_free_skb(sk, next_skb); } +/* Check if coalescing SKBs is legal. */ static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) @@ -1808,6 +1837,9 @@ static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb) return 1; } +/* Collapse packets in the retransmit queue to make to create + * less packets on the wire. This is only done on retransmission. + */ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, int space) { @@ -1957,6 +1989,9 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) return err; } +/* Check if we forward retransmits are possible in the current + * window/congestion state. + */ static int tcp_can_forward_retransmit(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -2101,7 +2136,8 @@ 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(); @@ -2145,7 +2181,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); } -/* WARNING: This routine must only be called when we have already sent +/* Send a crossed SYN-ACK during socket establishment. + * WARNING: This routine must only be called when we have already sent * a SYN packet that crossed the incoming SYN that caused this routine * to get called. If this assumption fails then the initial rcv_wnd * and rcv_wscale values will not be correct. @@ -2180,9 +2217,7 @@ int tcp_send_synack(struct sock *sk) return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } -/* - * Prepare a SYN-ACK. - */ +/* Prepare a SYN-ACK. */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req) { @@ -2269,9 +2304,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, return skb; } -/* - * Do all connect socket setups that can be done AF independent. - */ +/* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { struct dst_entry *dst = __sk_dst_get(sk); @@ -2330,9 +2363,7 @@ static void tcp_connect_init(struct sock *sk) tcp_clear_retrans(tp); } -/* - * Build a SYN and send it off. - */ +/* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2359,7 +2390,7 @@ 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. @@ -2493,6 +2524,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } +/* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b144a26359b..cdb2ca7684d 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/tunnel4.c b/net/ipv4/tunnel4.c index cb1f0e83830..3959e0ca456 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -132,7 +132,7 @@ static void tunnel64_err(struct sk_buff *skb, u32 info) } #endif -static struct net_protocol tunnel4_protocol = { +static const struct net_protocol tunnel4_protocol = { .handler = tunnel4_rcv, .err_handler = tunnel4_err, .no_policy = 1, @@ -140,7 +140,7 @@ static struct net_protocol tunnel4_protocol = { }; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static struct net_protocol tunnel64_protocol = { +static const struct net_protocol tunnel64_protocol = { .handler = tunnel64_rcv, .err_handler = tunnel64_err, .no_policy = 1, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 80e3812837a..0fa9f70e4b1 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -110,11 +110,12 @@ struct udp_table udp_table; EXPORT_SYMBOL(udp_table); int sysctl_udp_mem[3] __read_mostly; -int sysctl_udp_rmem_min __read_mostly; -int sysctl_udp_wmem_min __read_mostly; - EXPORT_SYMBOL(sysctl_udp_mem); + +int sysctl_udp_rmem_min __read_mostly; EXPORT_SYMBOL(sysctl_udp_rmem_min); + +int sysctl_udp_wmem_min __read_mostly; EXPORT_SYMBOL(sysctl_udp_wmem_min); atomic_t udp_memory_allocated; @@ -158,7 +159,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, */ int udp_lib_get_port(struct sock *sk, unsigned short snum, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2 ) ) + const struct sock *sk2)) { struct udp_hslot *hslot; struct udp_table *udptable = sk->sk_prot->h.udp_table; @@ -221,14 +222,15 @@ fail_unlock: fail: return error; } +EXPORT_SYMBOL(udp_lib_get_port); static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) { struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); - return ( !ipv6_only_sock(sk2) && - (!inet1->rcv_saddr || !inet2->rcv_saddr || - inet1->rcv_saddr == inet2->rcv_saddr )); + return (!ipv6_only_sock(sk2) && + (!inet1->rcv_saddr || !inet2->rcv_saddr || + inet1->rcv_saddr == inet2->rcv_saddr)); } int udp_v4_get_port(struct sock *sk, unsigned short snum) @@ -383,8 +385,8 @@ found: void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) { struct inet_sock *inet; - struct iphdr *iph = (struct iphdr*)skb->data; - struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2)); + struct iphdr *iph = (struct iphdr *)skb->data; + struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2)); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; @@ -439,7 +441,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else { - ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1)); + ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1)); } sk->sk_err = err; sk->sk_error_report(sk); @@ -474,7 +476,7 @@ EXPORT_SYMBOL(udp_flush_pending_frames); * (checksum field must be zeroed out) */ static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, int len ) + __be32 src, __be32 dst, int len) { unsigned int offset; struct udphdr *uh = udp_hdr(skb); @@ -545,7 +547,7 @@ static int udp_push_pending_frames(struct sock *sk) } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ - udp4_hwcsum_outgoing(sk, skb, fl->fl4_src,fl->fl4_dst, up->len); + udp4_hwcsum_outgoing(sk, skb, fl->fl4_src, fl->fl4_dst, up->len); goto send; } else /* `normal' UDP */ @@ -553,18 +555,24 @@ static int udp_push_pending_frames(struct sock *sk) /* add protocol-dependent pseudo-header */ uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len, - sk->sk_protocol, csum ); + sk->sk_protocol, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; 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; } @@ -592,7 +600,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * Check the flags. */ - if (msg->msg_flags&MSG_OOB) /* Mirror BSD error message compatibility */ + if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */ return -EOPNOTSUPP; ipc.opt = NULL; @@ -619,7 +627,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * Get and verify the address. */ if (msg->msg_name) { - struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name; + struct sockaddr_in * usin = (struct sockaddr_in *)msg->msg_name; if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -684,10 +692,11 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } if (connected) - rt = (struct rtable*)sk_dst_check(sk, 0); + rt = (struct rtable *)sk_dst_check(sk, 0); if (rt == NULL) { struct flowi fl = { .oif = ipc.oif, + .mark = sk->sk_mark, .nl_u = { .ip4_u = { .daddr = faddr, .saddr = saddr, @@ -782,6 +791,7 @@ do_confirm: err = 0; goto out; } +EXPORT_SYMBOL(udp_sendmsg); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) @@ -831,6 +841,42 @@ out: return ret; } + +/** + * first_packet_length - return length of first packet in receive queue + * @sk: socket + * + * Drops all bad checksum frames, until a valid one is found. + * Returns the length of found skb, or 0 if none is found. + */ +static unsigned int first_packet_length(struct sock *sk) +{ + struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue; + struct sk_buff *skb; + unsigned int res; + + __skb_queue_head_init(&list_kill); + + spin_lock_bh(&rcvq->lock); + while ((skb = skb_peek(rcvq)) != NULL && + udp_lib_checksum_complete(skb)) { + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + __skb_unlink(skb, rcvq); + __skb_queue_tail(&list_kill, skb); + } + res = skb ? skb->len : 0; + spin_unlock_bh(&rcvq->lock); + + if (!skb_queue_empty(&list_kill)) { + lock_sock(sk); + __skb_queue_purge(&list_kill); + sk_mem_reclaim_partial(sk); + release_sock(sk); + } + return res; +} + /* * IOCTL requests applicable to the UDP protocol */ @@ -847,21 +893,16 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) case SIOCINQ: { - struct sk_buff *skb; - unsigned long amount; + unsigned int amount = first_packet_length(sk); - amount = 0; - spin_lock_bh(&sk->sk_receive_queue.lock); - skb = skb_peek(&sk->sk_receive_queue); - if (skb != NULL) { + if (amount) /* * We will only return the amount * of this packet since that is all * that will be read. */ - amount = skb->len - sizeof(struct udphdr); - } - spin_unlock_bh(&sk->sk_receive_queue.lock); + amount -= sizeof(struct udphdr); + return put_user(amount, (int __user *)arg); } @@ -871,6 +912,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) return 0; } +EXPORT_SYMBOL(udp_ioctl); /* * This should be easy, if there is something there we @@ -892,7 +934,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * Check any passed addresses */ if (addr_len) - *addr_len=sizeof(*sin); + *addr_len = sizeof(*sin); if (flags & MSG_ERRQUEUE) return ip_recv_error(sk, msg, len); @@ -923,9 +965,11 @@ try_again: if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied ); + msg->msg_iov, copied); else { - err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); + err = skb_copy_and_csum_datagram_iovec(skb, + sizeof(struct udphdr), + msg->msg_iov); if (err == -EINVAL) goto csum_copy_err; @@ -941,8 +985,7 @@ try_again: sock_recv_timestamp(msg, sk, skb); /* Copy the address. */ - if (sin) - { + if (sin) { sin->sin_family = AF_INET; sin->sin_port = udp_hdr(skb)->source; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; @@ -956,9 +999,7 @@ try_again: err = ulen; out_free: - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); + skb_free_datagram_locked(sk, skb); out: return err; @@ -995,6 +1036,7 @@ int udp_disconnect(struct sock *sk, int flags) sk_dst_reset(sk); return 0; } +EXPORT_SYMBOL(udp_disconnect); void udp_lib_unhash(struct sock *sk) { @@ -1044,7 +1086,7 @@ drop: * Note that in the success and error cases, the skb is assumed to * have either been requeued or freed. */ -int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int rc; @@ -1214,7 +1256,7 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, if (uh->check == 0) { skb->ip_summed = CHECKSUM_UNNECESSARY; } else if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len, + if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len, proto, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -1347,7 +1389,7 @@ void udp_destroy_sock(struct sock *sk) * Socket option code for UDP */ int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen, + char __user *optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); @@ -1355,7 +1397,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, int err = 0; int is_udplite = IS_UDPLITE(sk); - if (optlen<sizeof(int)) + if (optlen < sizeof(int)) return -EINVAL; if (get_user(val, (int __user *)optval)) @@ -1426,9 +1468,10 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return err; } +EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1438,7 +1481,7 @@ int udp_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1453,7 +1496,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, struct udp_sock *up = udp_sk(sk); int val, len; - if (get_user(len,optlen)) + if (get_user(len, optlen)) return -EFAULT; len = min_t(unsigned int, len, sizeof(int)); @@ -1486,10 +1529,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (put_user(len, optlen)) return -EFAULT; - if (copy_to_user(optval, &val,len)) + if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } +EXPORT_SYMBOL(udp_lib_getsockopt); int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) @@ -1525,33 +1569,16 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) { unsigned int mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; - int is_lite = IS_UDPLITE(sk); /* Check for false positives due to checksum errors */ - if ( (mask & POLLRDNORM) && - !(file->f_flags & O_NONBLOCK) && - !(sk->sk_shutdown & RCV_SHUTDOWN)){ - struct sk_buff_head *rcvq = &sk->sk_receive_queue; - struct sk_buff *skb; - - spin_lock_bh(&rcvq->lock); - while ((skb = skb_peek(rcvq)) != NULL && - udp_lib_checksum_complete(skb)) { - UDP_INC_STATS_BH(sock_net(sk), - UDP_MIB_INERRORS, is_lite); - __skb_unlink(skb, rcvq); - kfree_skb(skb); - } - spin_unlock_bh(&rcvq->lock); - - /* nothing to see, move along */ - if (skb == NULL) - mask &= ~(POLLIN | POLLRDNORM); - } + if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && + !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk)) + mask &= ~(POLLIN | POLLRDNORM); return mask; } +EXPORT_SYMBOL(udp_poll); struct proto udp_prot = { .name = "UDP", @@ -1582,6 +1609,7 @@ struct proto udp_prot = { .compat_getsockopt = compat_udp_getsockopt, #endif }; +EXPORT_SYMBOL(udp_prot); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS @@ -1703,11 +1731,13 @@ int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo) rc = -ENOMEM; return rc; } +EXPORT_SYMBOL(udp_proc_register); void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo) { proc_net_remove(net, afinfo->name); } +EXPORT_SYMBOL(udp_proc_unregister); /* ------------------------------------------------------------------------ */ static void udp4_format_sock(struct sock *sp, struct seq_file *f, @@ -1741,7 +1771,7 @@ int udp4_seq_show(struct seq_file *seq, void *v) int len; udp4_format_sock(v, seq, state->bucket, &len); - seq_printf(seq, "%*s\n", 127 - len ,""); + seq_printf(seq, "%*s\n", 127 - len, ""); } return 0; } @@ -1816,16 +1846,64 @@ void __init udp_init(void) sysctl_udp_wmem_min = SK_MEM_QUANTUM; } -EXPORT_SYMBOL(udp_disconnect); -EXPORT_SYMBOL(udp_ioctl); -EXPORT_SYMBOL(udp_prot); -EXPORT_SYMBOL(udp_sendmsg); -EXPORT_SYMBOL(udp_lib_getsockopt); -EXPORT_SYMBOL(udp_lib_setsockopt); -EXPORT_SYMBOL(udp_poll); -EXPORT_SYMBOL(udp_lib_get_port); +int udp4_ufo_send_check(struct sk_buff *skb) +{ + const struct iphdr *iph; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(*uh))) + return -EINVAL; + + iph = ip_hdr(skb); + uh = udp_hdr(skb); + + uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len, + IPPROTO_UDP, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + return 0; +} + +struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + int offset; + __wsum csum; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + int type = skb_shinfo(skb)->gso_type; + + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + !(type & (SKB_GSO_UDP)))) + goto out; + + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + + segs = NULL; + goto out; + } + + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + offset = skb->csum_start - skb_headroom(skb); + csum = skb_checksum(skb, offset, skb->len - offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + + /* Fragment the skb. IP headers of the fragments are updated in + * inet_gso_segment() + */ + segs = skb_segment(skb, features); +out: + return segs; +} -#ifdef CONFIG_PROC_FS -EXPORT_SYMBOL(udp_proc_register); -EXPORT_SYMBOL(udp_proc_unregister); -#endif diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index 9f4a6165f72..aaad650d47d 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -11,13 +11,13 @@ extern void __udp4_lib_err(struct sk_buff *, u32, struct udp_table *); extern int udp_v4_get_port(struct sock *sk, unsigned short snum); extern int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #ifdef CONFIG_COMPAT extern int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index c784891cb7e..95248d7f75e 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -25,7 +25,7 @@ static void udplite_err(struct sk_buff *skb, u32 info) __udp4_lib_err(skb, info, &udplite_table); } -static struct net_protocol udplite_protocol = { +static const struct net_protocol udplite_protocol = { .handler = udplite_rcv, .err_handler = udplite_err, .no_policy = 1, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 0071ee6f441..74fb2eb833e 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -264,6 +264,22 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .fill_dst = xfrm4_fill_dst, }; +#ifdef CONFIG_SYSCTL +static struct ctl_table xfrm4_policy_table[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "xfrm4_gc_thresh", + .data = &xfrm4_dst_ops.gc_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static struct ctl_table_header *sysctl_hdr; +#endif + static void __init xfrm4_policy_init(void) { xfrm_policy_register_afinfo(&xfrm4_policy_afinfo); @@ -271,12 +287,31 @@ static void __init xfrm4_policy_init(void) static void __exit xfrm4_policy_fini(void) { +#ifdef CONFIG_SYSCTL + if (sysctl_hdr) + unregister_net_sysctl_table(sysctl_hdr); +#endif xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo); } -void __init xfrm4_init(void) +void __init xfrm4_init(int rt_max_size) { xfrm4_state_init(); xfrm4_policy_init(); + /* + * Select a default value for the gc_thresh based on the main route + * table hash size. It seems to me the worst case scenario is when + * we have ipsec operating in transport mode, in which we create a + * dst_entry per socket. The xfrm gc algorithm starts trying to remove + * entries at gc_thresh, and prevents new allocations as 2*gc_thresh + * so lets set an initial xfrm gc_thresh value at the rt_max_size/2. + * That will let us store an ipsec connection per route table entry, + * and start cleaning when were 1/2 full + */ + xfrm4_dst_ops.gc_thresh = rt_max_size/2; +#ifdef CONFIG_SYSCTL + sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv4_ctl_path, + xfrm4_policy_table); +#endif } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 43b3c9f89c1..1fd0a3d775d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -137,6 +137,8 @@ static DEFINE_SPINLOCK(addrconf_verify_lock); static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); +static void addrconf_bonding_change(struct net_device *dev, + unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags); @@ -1371,12 +1373,14 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add /* Gets referenced address, destroys ifaddr */ -static void addrconf_dad_stop(struct inet6_ifaddr *ifp) +static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { if (ifp->flags&IFA_F_PERMANENT) { spin_lock_bh(&ifp->lock); addrconf_del_timer(ifp); ifp->flags |= IFA_F_TENTATIVE; + if (dad_failed) + ifp->flags |= IFA_F_DADFAILED; spin_unlock_bh(&ifp->lock); in6_ifa_put(ifp); #ifdef CONFIG_IPV6_PRIVACY @@ -1403,8 +1407,8 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) struct inet6_dev *idev = ifp->idev; if (net_ratelimit()) - printk(KERN_INFO "%s: IPv6 duplicate address detected!\n", - ifp->idev->dev->name); + printk(KERN_INFO "%s: IPv6 duplicate address %pI6c detected!\n", + ifp->idev->dev->name, &ifp->addr); if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { struct in6_addr addr; @@ -1422,7 +1426,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) } } - addrconf_dad_stop(ifp); + addrconf_dad_stop(ifp, 1); } /* Join to solicited addr multicast group. */ @@ -2580,6 +2584,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, return notifier_from_errno(err); } break; + case NETDEV_BONDING_OLDTYPE: + case NETDEV_BONDING_NEWTYPE: + addrconf_bonding_change(dev, event); + break; } return NOTIFY_OK; @@ -2593,6 +2601,19 @@ static struct notifier_block ipv6_dev_notf = { .priority = 0 }; +static void addrconf_bonding_change(struct net_device *dev, unsigned long event) +{ + struct inet6_dev *idev; + ASSERT_RTNL(); + + idev = __in6_dev_get(dev); + + if (event == NETDEV_BONDING_NEWTYPE) + ipv6_mc_remap(idev); + else if (event == NETDEV_BONDING_OLDTYPE) + ipv6_mc_unmap(idev); +} + static int addrconf_ifdown(struct net_device *dev, int how) { struct inet6_dev *idev; @@ -2778,7 +2799,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) idev->cnf.accept_dad < 1 || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { - ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC); + ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock_bh(&ifp->lock); read_unlock_bh(&idev->lock); @@ -2795,7 +2816,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) * - otherwise, kill it. */ in6_ifa_hold(ifp); - addrconf_dad_stop(ifp); + addrconf_dad_stop(ifp, 0); return; } @@ -2829,7 +2850,7 @@ static void addrconf_dad_timer(unsigned long data) * DAD was successful */ - ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC); + ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock_bh(&ifp->lock); read_unlock_bh(&idev->lock); @@ -3965,14 +3986,14 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) #ifdef CONFIG_SYSCTL static -int addrconf_sysctl_forward(ctl_table *ctl, int write, struct file * filp, +int addrconf_sysctl_forward(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_forwarding(ctl, valp, val); @@ -4069,14 +4090,14 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old) } static -int addrconf_sysctl_disable(ctl_table *ctl, int write, struct file * filp, +int addrconf_sysctl_disable(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) ret = addrconf_disable_ipv6(ctl, valp, val); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 45f9a2a42d5..e127a32f954 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -710,7 +710,7 @@ EXPORT_SYMBOL_GPL(ipv6_opt_accepted); static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) { - struct inet6_protocol *ops = NULL; + const struct inet6_protocol *ops = NULL; for (;;) { struct ipv6_opt_hdr *opth; @@ -745,7 +745,7 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) static int ipv6_gso_send_check(struct sk_buff *skb) { struct ipv6hdr *ipv6h; - struct inet6_protocol *ops; + const struct inet6_protocol *ops; int err = -EINVAL; if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) @@ -773,7 +773,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; - struct inet6_protocol *ops; + const struct inet6_protocol *ops; + int proto; + struct frag_hdr *fptr; + unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; if (!(features & NETIF_F_V6_CSUM)) features &= ~NETIF_F_SG; @@ -793,10 +798,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) __skb_pull(skb, sizeof(*ipv6h)); segs = ERR_PTR(-EPROTONOSUPPORT); + proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); rcu_read_lock(); - ops = rcu_dereference(inet6_protos[ - ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); - + ops = rcu_dereference(inet6_protos[proto]); if (likely(ops && ops->gso_segment)) { skb_reset_transport_header(skb); segs = ops->gso_segment(skb, features); @@ -810,6 +814,16 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) ipv6h = ipv6_hdr(skb); ipv6h->payload_len = htons(skb->len - skb->mac_len - sizeof(*ipv6h)); + if (proto == IPPROTO_UDP) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + fptr = (struct frag_hdr *)(skb_network_header(skb) + + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next != NULL) + fptr->frag_off |= htons(IP6_MF); + offset += (ntohs(ipv6h->payload_len) - + sizeof(struct frag_hdr)); + } } out: @@ -826,7 +840,7 @@ struct ipv6_gro_cb { static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - struct inet6_protocol *ops; + const struct inet6_protocol *ops; struct sk_buff **pp = NULL; struct sk_buff *p; struct ipv6hdr *iph; @@ -912,7 +926,7 @@ out: static int ipv6_gro_complete(struct sk_buff *skb) { - struct inet6_protocol *ops; + const struct inet6_protocol *ops; struct ipv6hdr *iph = ipv6_hdr(skb); int err = -ENOSYS; diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 86f42a288c4..c1589e2f1dc 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -527,7 +527,7 @@ static const struct xfrm_type ah6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static struct inet6_protocol ah6_protocol = { +static const struct inet6_protocol ah6_protocol = { .handler = xfrm6_rcv, .err_handler = ah6_err, .flags = INET6_PROTO_NOPOLICY, diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 678bb95b152..af597c73ebe 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -558,7 +558,7 @@ static const struct xfrm_type esp6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static struct inet6_protocol esp6_protocol = { +static const struct inet6_protocol esp6_protocol = { .handler = xfrm6_rcv, .err_handler = esp6_err, .flags = INET6_PROTO_NOPOLICY, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 4aae658e550..df159fffe4b 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -500,17 +500,17 @@ unknown_rh: return -1; } -static struct inet6_protocol rthdr_protocol = { +static const struct inet6_protocol rthdr_protocol = { .handler = ipv6_rthdr_rcv, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR, }; -static struct inet6_protocol destopt_protocol = { +static const struct inet6_protocol destopt_protocol = { .handler = ipv6_destopt_rcv, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR, }; -static struct inet6_protocol nodata_protocol = { +static const struct inet6_protocol nodata_protocol = { .handler = dst_discard, .flags = INET6_PROTO_NOPOLICY, }; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index eab62a7a8f0..f23ebbec063 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -86,7 +86,7 @@ static inline struct sock *icmpv6_sk(struct net *net) static int icmpv6_rcv(struct sk_buff *skb); -static struct inet6_protocol icmpv6_protocol = { +static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; @@ -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) { @@ -592,7 +583,7 @@ out: static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { - struct inet6_protocol *ipprot; + const struct inet6_protocol *ipprot; int inner_offset; int hash; u8 nexthdr; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 52ee1dced2f..0e93ca56eb6 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -164,12 +164,6 @@ static __inline__ void rt6_release(struct rt6_info *rt) dst_free(&rt->u.dst); } -#ifdef CONFIG_IPV6_MULTIPLE_TABLES -#define FIB_TABLE_HASHSZ 256 -#else -#define FIB_TABLE_HASHSZ 1 -#endif - static void fib6_link_table(struct net *net, struct fib6_table *tb) { unsigned int h; @@ -180,7 +174,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb) */ rwlock_init(&tb->tb6_lock); - h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1); + h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* * No protection necessary, this is the only list mutatation @@ -231,7 +225,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) if (id == 0) id = RT6_TABLE_MAIN; - h = id & (FIB_TABLE_HASHSZ - 1); + h = id & (FIB6_TABLE_HASHSZ - 1); rcu_read_lock(); head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) { @@ -382,7 +376,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) arg.net = net; w->args = &arg; - for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { + for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry(tb, node, head, tb6_hlist) { @@ -1368,7 +1362,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), unsigned int h; rcu_read_lock(); - for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, node, head, tb6_hlist) { write_lock_bh(&table->tb6_lock); @@ -1483,7 +1477,7 @@ static int fib6_net_init(struct net *net) if (!net->ipv6.rt6_stats) goto out_timer; - net->ipv6.fib_table_hash = kcalloc(FIB_TABLE_HASHSZ, + net->ipv6.fib_table_hash = kcalloc(FIB6_TABLE_HASHSZ, sizeof(*net->ipv6.fib_table_hash), GFP_KERNEL); if (!net->ipv6.fib_table_hash) diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 6d6a4277c67..237e2dba6e9 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -63,7 +63,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (skb->pkt_type == PACKET_OTHERHOST) { kfree_skb(skb); - return 0; + return NET_RX_DROP; } rcu_read_lock(); @@ -133,7 +133,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (ipv6_parse_hopopts(skb) < 0) { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); rcu_read_unlock(); - return 0; + return NET_RX_DROP; } } @@ -149,7 +149,7 @@ err: drop: rcu_read_unlock(); kfree_skb(skb); - return 0; + return NET_RX_DROP; } /* @@ -159,7 +159,7 @@ drop: static int ip6_input_finish(struct sk_buff *skb) { - struct inet6_protocol *ipprot; + const struct inet6_protocol *ipprot; unsigned int nhoff; int nexthdr, raw; u8 hash; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 87f8419a68f..cd48801a8d6 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -57,18 +57,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); -static __inline__ void ipv6_select_ident(struct sk_buff *skb, struct frag_hdr *fhdr) -{ - static u32 ipv6_fragmentation_id = 1; - static DEFINE_SPINLOCK(ip6_id_lock); - - spin_lock_bh(&ip6_id_lock); - fhdr->identification = htonl(ipv6_fragmentation_id); - if (++ipv6_fragmentation_id == 0) - ipv6_fragmentation_id = 1; - spin_unlock_bh(&ip6_id_lock); -} - int __ip6_local_out(struct sk_buff *skb) { int len; @@ -206,7 +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) { @@ -249,19 +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); @@ -706,7 +689,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); - ipv6_select_ident(skb, fh); + ipv6_select_ident(fh); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); @@ -844,7 +827,7 @@ slow_path: fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { - ipv6_select_ident(skb, fh); + ipv6_select_ident(fh); frag_id = fh->identification; } else fh->identification = frag_id; @@ -1087,11 +1070,13 @@ static inline int ip6_ufo_append_data(struct sock *sk, if (!err) { struct frag_hdr fhdr; - /* specify the length of each IP datagram fragment*/ - skb_shinfo(skb)->gso_size = mtu - fragheaderlen - - sizeof(struct frag_hdr); + /* Specify the length of each IPv6 datagram fragment. + * It has to be a multiple of 8. + */ + skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - + sizeof(struct frag_hdr)) & ~7; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(skb, &fhdr); + ipv6_select_ident(&fhdr); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); @@ -1526,7 +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; } @@ -1535,6 +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 51f410e7775..c595bbe1ed9 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1036,18 +1036,13 @@ 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); struct net_device_stats *stats = &t->dev->stats; int ret; - if (t->recursion++) { - stats->collisions++; - goto tx_err; - } - switch (skb->protocol) { case htons(ETH_P_IP): ret = ip4ip6_tnl_xmit(skb, dev); @@ -1062,15 +1057,13 @@ ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) if (ret < 0) goto tx_err; - t->recursion--; - return 0; + return NETDEV_TX_OK; tx_err: stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); - t->recursion--; - return 0; + return NETDEV_TX_OK; } static void ip6_tnl_set_cap(struct ip6_tnl *t) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index c769f155c69..716153941fc 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -83,10 +83,6 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, static int ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); static void mroute_clean_tables(struct net *net); -#ifdef CONFIG_IPV6_PIMSM_V2 -static struct inet6_protocol pim6_protocol; -#endif - static struct timer_list ipmr_expire_timer; @@ -204,7 +200,7 @@ 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 +213,7 @@ 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, @@ -328,7 +324,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations ipmr_mfc_seq_ops = { +static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, .next = ipmr_mfc_seq_next, .stop = ipmr_mfc_seq_stop, @@ -341,7 +337,7 @@ 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, @@ -410,13 +406,14 @@ static int pim6_rcv(struct sk_buff *skb) return 0; } -static struct inet6_protocol pim6_protocol = { +static const struct inet6_protocol pim6_protocol = { .handler = pim6_rcv, }; /* 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); @@ -427,7 +424,7 @@ static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) MRT6MSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } static const struct net_device_ops reg_vif_netdev_ops = { @@ -1284,7 +1281,7 @@ int ip6mr_sk_done(struct sock *sk) * MOSPF/PIM router set up we can clean this up. */ -int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) +int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { int ret; struct mif6ctl vif; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 79c172f1ff0..2f2a5ca2c87 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -178,7 +178,7 @@ static const struct xfrm_type ipcomp6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static struct inet6_protocol ipcomp6_protocol = +static const struct inet6_protocol ipcomp6_protocol = { .handler = xfrm6_rcv, .err_handler = ipcomp6_err, diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a7fdf9a27f1..4f7aaf6996a 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -123,7 +123,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, } static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); @@ -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; @@ -493,13 +496,17 @@ done: goto e_inval; if (val) { + struct net_device *dev; + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val) goto e_inval; - if (__dev_get_by_index(net, val) == NULL) { + dev = dev_get_by_index(net, val); + if (!dev) { retv = -ENODEV; break; } + dev_put(dev); } np->mcast_oif = val; retv = 0; @@ -770,7 +777,7 @@ e_inval: } int ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; @@ -798,7 +805,7 @@ EXPORT_SYMBOL(ipv6_setsockopt); #ifdef CONFIG_COMPAT int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; @@ -1037,8 +1044,6 @@ 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/mcast.c b/net/ipv6/mcast.c index 4b264ed40a8..f9fcf690bd5 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2107,7 +2107,6 @@ static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca, for (j=0; j<i; j++) (void) ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { - struct inet6_dev *idev = pmc->idev; struct ip6_sf_list *psf; /* filter mode change */ @@ -2250,6 +2249,25 @@ static void igmp6_timer_handler(unsigned long data) ma_put(ma); } +/* Device changing type */ + +void ipv6_mc_unmap(struct inet6_dev *idev) +{ + struct ifmcaddr6 *i; + + /* Install multicast list, except for all-nodes (already installed) */ + + read_lock_bh(&idev->lock); + for (i = idev->mc_list; i; i = i->next) + igmp6_group_dropped(i); + read_unlock_bh(&idev->lock); +} + +void ipv6_mc_remap(struct inet6_dev *idev) +{ + ipv6_mc_up(idev); +} + /* Device going down */ void ipv6_mc_down(struct inet6_dev *idev) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9eb68e92cc1..f74e4e2cdd0 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, @@ -658,7 +658,6 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, &icmp6h, NULL, send_sllao ? ND_OPT_SOURCE_LL_ADDR : 0); } -EXPORT_SYMBOL(ndisc_send_rs); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) @@ -955,8 +954,8 @@ 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 +1150,6 @@ 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 +1158,10 @@ 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 +1282,7 @@ skip_defrtr: } } -#ifdef CONFIG_IPV6_NDISC_NODETYPE skip_linkparms: -#endif /* * Process options. @@ -1312,6 +1309,10 @@ 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; @@ -1733,7 +1734,7 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, } } -int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos) +int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; @@ -1744,16 +1745,16 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * f ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = proc_dointvec_jiffies(ctl, write, - filp, buffer, lenp, ppos); + buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) ret = proc_dointvec_ms_jiffies(ctl, write, - filp, buffer, lenp, ppos); + buffer, lenp, ppos); else ret = -1; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index ced1f2c0cb6..cc9f8ef303f 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -8,7 +8,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> @@ -222,16 +222,11 @@ get_entry(void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline int -unconditional(const struct ip6t_ip6 *ipv6) +static inline bool unconditional(const struct ip6t_ip6 *ipv6) { - unsigned int i; - - for (i = 0; i < sizeof(*ipv6); i++) - if (((char *)ipv6)[i]) - break; + static const struct ip6t_ip6 uncond; - return (i == sizeof(*ipv6)); + return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; } #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ @@ -745,6 +740,21 @@ find_check_entry(struct ip6t_entry *e, const char *name, unsigned int size, return ret; } +static bool check_underflow(struct ip6t_entry *e) +{ + const struct ip6t_entry_target *t; + unsigned int verdict; + + if (!unconditional(&e->ipv6)) + return false; + t = ip6t_get_target(e); + if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) + return false; + verdict = ((struct ip6t_standard_target *)t)->verdict; + verdict = -verdict - 1; + return verdict == NF_DROP || verdict == NF_ACCEPT; +} + static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, @@ -752,6 +762,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, + unsigned int valid_hooks, unsigned int *i) { unsigned int h; @@ -771,15 +782,21 @@ check_entry_size_and_hooks(struct ip6t_entry *e, /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { + if (!(valid_hooks & (1 << h))) + continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) + if ((unsigned char *)e - base == underflows[h]) { + if (!check_underflow(e)) { + pr_err("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); + return -EINVAL; + } newinfo->underflow[h] = underflows[h]; + } } - /* FIXME: underflows must be unconditional, standard verdicts - < 0 (not IP6T_RETURN). --RR */ - /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; @@ -842,7 +859,7 @@ translate_table(const char *name, newinfo, entry0, entry0 + size, - hook_entries, underflows, &i); + hook_entries, underflows, valid_hooks, &i); if (ret != 0) return ret; @@ -2083,7 +2100,8 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -struct xt_table *ip6t_register_table(struct net *net, struct xt_table *table, +struct xt_table *ip6t_register_table(struct net *net, + const struct xt_table *table, const struct ip6t_replace *repl) { int ret; diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c index db610bacbcc..ca287f6d2bc 100644 --- a/net/ipv6/netfilter/ip6t_eui64.c +++ b/net/ipv6/netfilter/ip6t_eui64.c @@ -23,7 +23,6 @@ static bool eui64_mt6(const struct sk_buff *skb, const struct xt_match_param *par) { unsigned char eui64[8]; - int i = 0; if (!(skb_mac_header(skb) >= skb->head && skb_mac_header(skb) + ETH_HLEN <= skb->data) && @@ -42,12 +41,8 @@ eui64_mt6(const struct sk_buff *skb, const struct xt_match_param *par) eui64[4] = 0xfe; eui64[0] ^= 0x02; - i = 0; - while (ipv6_hdr(skb)->saddr.s6_addr[8 + i] == eui64[i] - && i < 8) - i++; - - if (i == 8) + if (!memcmp(ipv6_hdr(skb)->saddr.s6_addr + 8, eui64, + sizeof(eui64))) return true; } } diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index ef5a0a32bf8..6f4383ad86f 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -51,11 +51,11 @@ static struct .term = IP6T_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_filter = { +static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET6, + .af = NFPROTO_IPV6, }; /* The work comes in here from netfilter.c. */ @@ -95,21 +95,21 @@ static struct nf_hook_ops ip6t_ops[] __read_mostly = { { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_FILTER, }, { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_FILTER, }, { .hook = ip6t_local_out_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_FILTER, }, diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index ab0d398a2ba..0ad91433ed6 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -21,7 +21,7 @@ MODULE_DESCRIPTION("ip6tables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -static struct +static const struct { struct ip6t_replace repl; struct ip6t_standard entries[5]; @@ -57,11 +57,11 @@ static struct .term = IP6T_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_mangler = { +static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET6, + .af = NFPROTO_IPV6, }; /* The work comes in here from netfilter.c. */ @@ -136,35 +136,35 @@ static struct nf_hook_ops ip6t_ops[] __read_mostly = { { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_MANGLE, }, { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_MANGLE, }, { .hook = ip6t_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_MANGLE, }, { .hook = ip6t_local_out_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_MANGLE, }, { .hook = ip6t_post_routing_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_MANGLE, }, diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 4b792b6ca32..ed1a1180f3b 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -8,7 +8,7 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static struct +static const struct { struct ip6t_replace repl; struct ip6t_standard entries[2]; @@ -35,11 +35,11 @@ static struct .term = IP6T_ERROR_INIT, /* ERROR */ }; -static struct xt_table packet_raw = { +static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET6, + .af = NFPROTO_IPV6, }; /* The work comes in here from netfilter.c. */ @@ -68,14 +68,14 @@ ip6t_local_out_hook(unsigned int hook, static struct nf_hook_ops ip6t_ops[] __read_mostly = { { .hook = ip6t_pre_routing_hook, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_FIRST, .owner = THIS_MODULE, }, { .hook = ip6t_local_out_hook, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_FIRST, .owner = THIS_MODULE, diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 0ea37ff15d5..41b444c6093 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -26,7 +26,7 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static struct +static const struct { struct ip6t_replace repl; struct ip6t_standard entries[3]; @@ -56,11 +56,11 @@ static struct .term = IP6T_ERROR_INIT, /* ERROR */ }; -static struct xt_table security_table = { +static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, - .af = AF_INET6, + .af = NFPROTO_IPV6, }; static unsigned int @@ -101,21 +101,21 @@ static struct nf_hook_ops ip6t_ops[] __read_mostly = { { .hook = ip6t_local_in_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_SECURITY, }, { .hook = ip6t_forward_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SECURITY, }, { .hook = ip6t_local_out_hook, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SECURITY, }, diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 2a15c2d66c6..5f2ec208a8c 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -27,6 +27,7 @@ #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <net/netfilter/nf_log.h> static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_tuple *tuple) @@ -176,8 +177,11 @@ static unsigned int ipv6_confirm(unsigned int hooknum, } ret = helper->help(skb, protoff, ct, ctinfo); - if (ret != NF_ACCEPT) + if (ret != NF_ACCEPT) { + nf_log_packet(NFPROTO_IPV6, hooknum, skb, in, out, NULL, + "nf_ct_%s: dropping packet", helper->name); return ret; + } out: /* We've seen it coming out the other side: confirm it */ return nf_conntrack_confirm(skb); @@ -265,42 +269,42 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { { .hook = ipv6_defrag, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv6_conntrack_in, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK, }, { .hook = ipv6_conntrack_local, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK, }, { .hook = ipv6_defrag, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv6_confirm, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_LAST, }, { .hook = ipv6_confirm, .owner = THIS_MODULE, - .pf = PF_INET6, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_LAST-1, }, diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 590ddefb7ff..c9605c3ad91 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -101,7 +101,7 @@ static struct snmp_mib snmp6_icmp6_list[] = { }; /* RFC 4293 v6 ICMPMsgStatsTable; named items for RFC 2466 compatibility */ -static char *icmp6type2name[256] = { +static const char *const icmp6type2name[256] = { [ICMPV6_DEST_UNREACH] = "DestUnreachs", [ICMPV6_PKT_TOOBIG] = "PktTooBigs", [ICMPV6_TIME_EXCEED] = "TimeExcds", @@ -144,7 +144,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void **mib) /* print by name -- deprecated items */ for (i = 0; i < ICMP6MSG_MIB_MAX; i++) { int icmptype; - char *p; + const char *p; icmptype = i & 0xff; p = icmp6type2name[icmptype]; diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 9ab78915991..1fa3468f0f3 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -20,27 +20,16 @@ * - 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]; +const struct inet6_protocol *inet6_protos[MAX_INET_PROTOS]; static DEFINE_SPINLOCK(inet6_proto_lock); -int inet6_add_protocol(struct inet6_protocol *prot, unsigned char protocol) +int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) { int ret, hash = protocol & (MAX_INET_PROTOS - 1); @@ -64,7 +53,7 @@ EXPORT_SYMBOL(inet6_add_protocol); * Remove a protocol from the hash tables. */ -int inet6_del_protocol(struct inet6_protocol *prot, unsigned char protocol) +int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol) { int ret, hash = protocol & (MAX_INET_PROTOS - 1); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d6c3c1c34b2..4f24570b086 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; @@ -958,7 +957,7 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; @@ -1001,7 +1000,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, } static int rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { switch(level) { case SOL_RAW: @@ -1025,7 +1024,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { switch (level) { case SOL_RAW: diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 2642a41a853..da5bd0ed83d 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -627,7 +627,7 @@ fail_hdr: return -1; } -static struct inet6_protocol frag_protocol = +static const struct inet6_protocol frag_protocol = { .handler = ipv6_frag_rcv, .flags = INET6_PROTO_NOPOLICY, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1473ee0a1f5..d6fe7646a8f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -481,7 +481,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, pref = rinfo->route_pref; if (pref == ICMPV6_ROUTER_PREF_INVALID) - pref = ICMPV6_ROUTER_PREF_MEDIUM; + return -EINVAL; lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); @@ -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; @@ -2524,13 +2524,13 @@ static const struct file_operations rt6_stats_seq_fops = { #ifdef CONFIG_SYSCTL static -int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp, +int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; int delay = net->ipv6.sysctl.flush_delay; if (write) { - proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + proc_dointvec(ctl, write, buffer, lenp, ppos); fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); return 0; } else @@ -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 98b7327d094..dbd19a78ca7 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -15,7 +15,6 @@ * Roger Venning <r.venning@telstra.com>: 6to4 support * Nate Thompson <nate@thebog.net>: 6to4 support * Fred Templin <fred.l.templin@boeing.com>: isatap support - * Sascha Hlusiak <mail@saschahlusiak.de>: stateless autoconf for isatap */ #include <linux/module.h> @@ -223,44 +222,6 @@ failed: return NULL; } -static void ipip6_tunnel_rs_timer(unsigned long data) -{ - struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *) data; - struct inet6_dev *ifp; - struct inet6_ifaddr *addr; - - spin_lock(&p->lock); - ifp = __in6_dev_get(p->tunnel->dev); - - read_lock_bh(&ifp->lock); - for (addr = ifp->addr_list; addr; addr = addr->if_next) { - struct in6_addr rtr; - - if (!(ipv6_addr_type(&addr->addr) & IPV6_ADDR_LINKLOCAL)) - continue; - - /* Send RS to guessed linklocal address of router - * - * Better: send to ff02::2 encapsuled in unicast directly - * to router-v4 instead of guessing the v6 address. - * - * Cisco/Windows seem to not set the u/l bit correctly, - * so we won't guess right. - */ - ipv6_addr_set(&rtr, htonl(0xFE800000), 0, 0, 0); - if (!__ipv6_isatap_ifid(rtr.s6_addr + 8, - p->addr)) { - ndisc_send_rs(p->tunnel->dev, &addr->addr, &rtr); - } - } - read_unlock_bh(&ifp->lock); - - mod_timer(&p->rs_timer, jiffies + HZ * p->rs_delay); - spin_unlock(&p->lock); - - return; -} - static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { @@ -313,13 +274,12 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, c = 0; for (prl = t->prl; prl; prl = prl->next) { - if (c > cmax) + if (c >= cmax) break; if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; - kp[c].rs_delay = prl->rs_delay; c++; if (kprl.addr != htonl(INADDR_ANY)) break; @@ -369,23 +329,11 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) } p->next = t->prl; - p->tunnel = t; t->prl = p; t->prl_count++; - - spin_lock_init(&p->lock); - setup_timer(&p->rs_timer, ipip6_tunnel_rs_timer, (unsigned long) p); update: p->addr = a->addr; p->flags = a->flags; - p->rs_delay = a->rs_delay; - if (p->rs_delay == 0) - p->rs_delay = IPTUNNEL_RS_DEFAULT_DELAY; - spin_lock(&p->lock); - del_timer(&p->rs_timer); - if (p->flags & PRL_DEFAULT) - mod_timer(&p->rs_timer, jiffies + 1); - spin_unlock(&p->lock); out: write_unlock(&ipip6_lock); return err; @@ -404,9 +352,6 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) if ((*p)->addr == a->addr) { x = *p; *p = x->next; - spin_lock(&x->lock); - del_timer(&x->rs_timer); - spin_unlock(&x->lock); kfree(x); t->prl_count--; goto out; @@ -417,9 +362,6 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) while (t->prl) { x = t->prl; t->prl = t->prl->next; - spin_lock(&x->lock); - del_timer(&x->rs_timer); - spin_unlock(&x->lock); kfree(x); t->prl_count--; } @@ -609,7 +551,8 @@ 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; @@ -625,11 +568,6 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct in6_addr *addr6; int addr_type; - if (tunnel->recursion++) { - stats->collisions++; - goto tx_error; - } - if (skb->protocol != htons(ETH_P_IPV6)) goto tx_error; @@ -752,8 +690,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) ip_rt_put(rt); stats->tx_dropped++; dev_kfree_skb(skb); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); @@ -778,7 +715,7 @@ 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; @@ -793,16 +730,14 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset(skb); IPTUNNEL_XMIT(); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: stats->tx_errors++; dev_kfree_skb(skb); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; } static void ipip6_tunnel_bind_dev(struct net_device *dev) diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8c2513982b6..6b6ae913b5d 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -74,12 +74,13 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, return child; } -static DEFINE_PER_CPU(__u32, cookie_scratch)[16 + 5 + SHA_WORKSPACE_WORDS]; +static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], + ipv6_cookie_scratch); static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr, __be16 sport, __be16 dport, u32 count, int c) { - __u32 *tmp = __get_cpu_var(cookie_scratch); + __u32 *tmp = __get_cpu_var(ipv6_cookie_scratch); /* * we have 320 bits of information to hash, copy in the remaining diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index a031034720b..0dc6a4e5ed4 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -40,7 +40,7 @@ static ctl_table ipv6_table_template[] = { { .ctl_name = 0 } }; -static ctl_table ipv6_table[] = { +static ctl_table ipv6_rotable[] = { { .ctl_name = NET_IPV6_MLD_MAX_MSF, .procname = "mld_max_msf", @@ -130,7 +130,7 @@ int ipv6_sysctl_register(void) { int err = -ENOMEM; - ip6_header = register_net_sysctl_rotable(net_ipv6_ctl_path, ipv6_table); + ip6_header = register_net_sysctl_rotable(net_ipv6_ctl_path, ipv6_rotable); if (ip6_header == NULL) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d849dd53b78..21d100b68b1 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, @@ -1845,7 +1846,7 @@ static int tcp_v6_init_sock(struct sock *sk) /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ - tp->snd_ssthresh = 0x7fffffff; + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = 536; @@ -1968,7 +1969,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1 ) | icsk->icsk_ack.pingpong, - tp->snd_cwnd, tp->snd_ssthresh>=0xFFFF?-1:tp->snd_ssthresh + tp->snd_cwnd, + tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh ); } @@ -2092,7 +2094,7 @@ struct proto tcpv6_prot = { #endif }; -static struct inet6_protocol tcpv6_protocol = { +static const struct inet6_protocol tcpv6_protocol = { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .gso_send_check = tcp_v6_gso_send_check, diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 633ad789eff..51e2832d13a 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -133,13 +133,13 @@ static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, break; } -static struct inet6_protocol tunnel6_protocol = { +static const struct inet6_protocol tunnel6_protocol = { .handler = tunnel6_rcv, .err_handler = tunnel6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; -static struct inet6_protocol tunnel46_protocol = { +static const struct inet6_protocol tunnel46_protocol = { .handler = tunnel46_rcv, .err_handler = tunnel6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 33b59bd92c4..cf538ed5ef6 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -288,9 +288,7 @@ try_again: err = ulen; out_free: - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); + skb_free_datagram_locked(sk, skb); out: return err; @@ -638,6 +636,47 @@ static void udp_v6_flush_pending_frames(struct sock *sk) } } +/** + * udp6_hwcsum_outgoing - handle outgoing HW checksumming + * @sk: socket we are sending on + * @skb: sk_buff containing the filled-in UDP header + * (checksum field must be zeroed out) + */ +static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, int len) +{ + unsigned int offset; + struct udphdr *uh = udp_hdr(skb); + __wsum csum = 0; + + if (skb_queue_len(&sk->sk_write_queue) == 1) { + /* Only one fragment on the socket. */ + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0); + } else { + /* + * HW-checksum won't work as there are two or more + * fragments on the socket so that all csums of sk_buffs + * should be together + */ + offset = skb_transport_offset(skb); + skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + + skb->ip_summed = CHECKSUM_NONE; + + skb_queue_walk(&sk->sk_write_queue, skb) { + csum = csum_add(csum, skb->csum); + } + + uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, + csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } +} + /* * Sending */ @@ -668,7 +707,11 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (is_udplite) csum = udplite_csum_outgoing(sk, skb); - else + else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ + udp6_hwcsum_outgoing(sk, skb, &fl->fl6_src, &fl->fl6_dst, + up->len); + goto send; + } else csum = udp_csum_outgoing(sk, skb); /* add protocol-dependent pseudo-header */ @@ -677,13 +720,20 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (uh->check == 0) uh->check = CSUM_MANGLED_0; +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; } @@ -900,11 +950,8 @@ 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; @@ -995,7 +1042,7 @@ void udpv6_destroy_sock(struct sock *sk) * Socket option code for UDP */ int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1005,7 +1052,7 @@ int udpv6_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1032,9 +1079,102 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, } #endif -static struct inet6_protocol udpv6_protocol = { +static int udp6_ufo_send_check(struct sk_buff *skb) +{ + struct ipv6hdr *ipv6h; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(*uh))) + return -EINVAL; + + ipv6h = ipv6_hdr(skb); + uh = udp_hdr(skb); + + uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, + IPPROTO_UDP, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + return 0; +} + +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + unsigned int unfrag_ip6hlen, unfrag_len; + struct frag_hdr *fptr; + u8 *mac_start, *prevhdr; + u8 nexthdr; + u8 frag_hdr_sz = sizeof(struct frag_hdr); + int offset; + __wsum csum; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + int type = skb_shinfo(skb)->gso_type; + + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + !(type & (SKB_GSO_UDP)))) + goto out; + + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + + segs = NULL; + goto out; + } + + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + offset = skb->csum_start - skb_headroom(skb); + csum = skb_checksum(skb, offset, skb->len- offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + + /* Check if there is enough headroom to insert fragment header. */ + if ((skb_headroom(skb) < frag_hdr_sz) && + pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) + goto out; + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + + unfrag_ip6hlen; + mac_start = skb_mac_header(skb); + memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); + + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + ipv6_select_ident(fptr); + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); + +out: + return segs; +} + +static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, + .gso_send_check = udp6_ufo_send_check, + .gso_segment = udp6_ufo_fragment, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 6bb303471e2..d7571046bfc 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -16,10 +16,10 @@ extern int udp_v6_get_port(struct sock *sk, unsigned short snum); extern int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT extern int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 4818c48688f..d737a27ee01 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -25,7 +25,7 @@ static void udplitev6_err(struct sk_buff *skb, __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table); } -static struct inet6_protocol udplitev6_protocol = { +static const struct inet6_protocol udplitev6_protocol = { .handler = udplitev6_rcv, .err_handler = udplitev6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 3a3c677bc0f..8ec3d45cd1d 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -306,9 +306,26 @@ static void xfrm6_policy_fini(void) xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo); } +#ifdef CONFIG_SYSCTL +static struct ctl_table xfrm6_policy_table[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "xfrm6_gc_thresh", + .data = &xfrm6_dst_ops.gc_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static struct ctl_table_header *sysctl_hdr; +#endif + int __init xfrm6_init(void) { int ret; + unsigned int gc_thresh; ret = xfrm6_policy_init(); if (ret) @@ -317,6 +334,23 @@ int __init xfrm6_init(void) ret = xfrm6_state_init(); if (ret) goto out_policy; + /* + * We need a good default value for the xfrm6 gc threshold. + * In ipv4 we set it to the route hash table size * 8, which + * is half the size of the maximaum route cache for ipv4. It + * would be good to do the same thing for v6, except the table is + * constructed differently here. Here each table for a net namespace + * can have FIB_TABLE_HASHSZ entries, so lets go with the same + * computation that we used for ipv4 here. Also, lets keep the initial + * gc_thresh to a minimum of 1024, since, the ipv6 route cache defaults + * to that as a minimum as well + */ + gc_thresh = FIB6_TABLE_HASHSZ * 8; + xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; +#ifdef CONFIG_SYSCTL + sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path, + xfrm6_policy_table); +#endif out: return ret; out_policy: @@ -326,6 +360,10 @@ out_policy: void xfrm6_fini(void) { +#ifdef CONFIG_SYSCTL + if (sysctl_hdr) + unregister_net_sysctl_table(sysctl_hdr); +#endif //xfrm6_input_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index f1118d92a19..66c7a20011f 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1292,7 +1292,7 @@ const char *ipx_device_name(struct ipx_interface *intrfc) * socket object. */ static int ipx_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int opt; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 50b43c57d5d..dd35641835f 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1826,7 +1826,7 @@ static int irda_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon * */ static int irda_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); diff --git a/net/irda/ircomm/ircomm_event.c b/net/irda/ircomm/ircomm_event.c index c35b3ef5c2f..d78554fedba 100644 --- a/net/irda/ircomm/ircomm_event.c +++ b/net/irda/ircomm/ircomm_event.c @@ -49,7 +49,7 @@ static int ircomm_state_waitr(struct ircomm_cb *self, IRCOMM_EVENT event, static int ircomm_state_conn(struct ircomm_cb *self, IRCOMM_EVENT event, struct sk_buff *skb, struct ircomm_info *info); -char *ircomm_state[] = { +const char *const ircomm_state[] = { "IRCOMM_IDLE", "IRCOMM_WAITI", "IRCOMM_WAITR", @@ -57,7 +57,7 @@ char *ircomm_state[] = { }; #ifdef CONFIG_IRDA_DEBUG -static char *ircomm_event[] = { +static const char *const ircomm_event[] = { "IRCOMM_CONNECT_REQUEST", "IRCOMM_CONNECT_RESPONSE", "IRCOMM_TTP_CONNECT_INDICATION", diff --git a/net/irda/ircomm/ircomm_tty_attach.c b/net/irda/ircomm/ircomm_tty_attach.c index 9032a1d1190..3c175402302 100644 --- a/net/irda/ircomm/ircomm_tty_attach.c +++ b/net/irda/ircomm/ircomm_tty_attach.c @@ -30,6 +30,7 @@ ********************************************************************/ #include <linux/init.h> +#include <linux/sched.h> #include <net/irda/irda.h> #include <net/irda/irlmp.h> @@ -80,7 +81,7 @@ static int ircomm_tty_state_ready(struct ircomm_tty_cb *self, struct sk_buff *skb, struct ircomm_tty_info *info); -char *ircomm_tty_state[] = { +const char *const ircomm_tty_state[] = { "IRCOMM_TTY_IDLE", "IRCOMM_TTY_SEARCH", "IRCOMM_TTY_QUERY_PARAMETERS", @@ -91,7 +92,7 @@ char *ircomm_tty_state[] = { }; #ifdef CONFIG_IRDA_DEBUG -static char *ircomm_tty_event[] = { +static const char *const ircomm_tty_event[] = { "IRCOMM_TTY_ATTACH_CABLE", "IRCOMM_TTY_DETACH_CABLE", "IRCOMM_TTY_DATA_REQUEST", diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 4a105dc32dc..294e34d3517 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -44,7 +44,7 @@ #ifdef CONFIG_IRDA_DEBUG /* FIXME: This one should go in irlmp.c */ -static const char *ias_charset_types[] = { +static const char *const ias_charset_types[] = { "CS_ASCII", "CS_ISO_8859_1", "CS_ISO_8859_2", @@ -966,7 +966,7 @@ static void iriap_watchdog_timer_expired(void *data) #ifdef CONFIG_PROC_FS -static const char *ias_value_types[] = { +static const char *const ias_value_types[] = { "IAS_MISSING", "IAS_INTEGER", "IAS_OCT_SEQ", diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index 774d73a7685..315ead3cb92 100644 --- a/net/irda/irlan/irlan_common.c +++ b/net/irda/irlan/irlan_common.c @@ -30,6 +30,7 @@ #include <linux/init.h> #include <linux/errno.h> #include <linux/proc_fs.h> +#include <linux/sched.h> #include <linux/seq_file.h> #include <linux/random.h> #include <linux/netdevice.h> @@ -69,14 +70,14 @@ static int eth; /* Use "eth" or "irlan" name for devices */ static int access = ACCESS_PEER; /* PEER, DIRECT or HOSTED */ #ifdef CONFIG_PROC_FS -static const char *irlan_access[] = { +static const char *const irlan_access[] = { "UNKNOWN", "DIRECT", "PEER", "HOSTED" }; -static const char *irlan_media[] = { +static const char *const irlan_media[] = { "UNKNOWN", "802.3", "802.5" diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index 724bcf951b8..d340110f5c0 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -30,6 +30,7 @@ #include <linux/inetdevice.h> #include <linux/if_arp.h> #include <linux/module.h> +#include <linux/sched.h> #include <net/arp.h> #include <net/irda/irda.h> @@ -41,7 +42,8 @@ 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 +164,8 @@ 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; @@ -177,7 +180,7 @@ static int irlan_eth_xmit(struct sk_buff *skb, struct net_device *dev) /* Did the realloc succeed? */ if (new_skb == NULL) - return 0; + return NETDEV_TX_OK; /* Use the new skb instead */ skb = new_skb; @@ -209,7 +212,7 @@ static int irlan_eth_xmit(struct sk_buff *skb, struct net_device *dev) self->stats.tx_bytes += skb->len; } - return 0; + return NETDEV_TX_OK; } /* diff --git a/net/irda/irlap.c b/net/irda/irlap.c index e4965b764b9..356e65b1dc4 100644 --- a/net/irda/irlap.c +++ b/net/irda/irlap.c @@ -63,7 +63,7 @@ static void irlap_init_qos_capabilities(struct irlap_cb *self, struct qos_info *qos_user); #ifdef CONFIG_IRDA_DEBUG -static char *lap_reasons[] = { +static const char *const lap_reasons[] = { "ERROR, NOT USED", "LAP_DISC_INDICATION", "LAP_NO_RESPONSE", diff --git a/net/irda/irlap_event.c b/net/irda/irlap_event.c index 16c4ef0f5c1..c5c51959e3c 100644 --- a/net/irda/irlap_event.c +++ b/net/irda/irlap_event.c @@ -78,7 +78,7 @@ static int irlap_state_reset_check(struct irlap_cb *, IRLAP_EVENT event, struct sk_buff *, struct irlap_info *); #ifdef CONFIG_IRDA_DEBUG -static const char *irlap_event[] = { +static const char *const irlap_event[] = { "DISCOVERY_REQUEST", "CONNECT_REQUEST", "CONNECT_RESPONSE", @@ -120,7 +120,7 @@ static const char *irlap_event[] = { }; #endif /* CONFIG_IRDA_DEBUG */ -const char *irlap_state[] = { +const char *const irlap_state[] = { "LAP_NDM", "LAP_QUERY", "LAP_REPLY", diff --git a/net/irda/irlmp_event.c b/net/irda/irlmp_event.c index 78cce0cb073..c1fb5db8104 100644 --- a/net/irda/irlmp_event.c +++ b/net/irda/irlmp_event.c @@ -33,13 +33,13 @@ #include <net/irda/irlmp_frame.h> #include <net/irda/irlmp_event.h> -const char *irlmp_state[] = { +const char *const irlmp_state[] = { "LAP_STANDBY", "LAP_U_CONNECT", "LAP_ACTIVE", }; -const char *irlsap_state[] = { +const char *const irlsap_state[] = { "LSAP_DISCONNECTED", "LSAP_CONNECT", "LSAP_CONNECT_PEND", @@ -49,7 +49,7 @@ const char *irlsap_state[] = { }; #ifdef CONFIG_IRDA_DEBUG -static const char *irlmp_event[] = { +static const char *const irlmp_event[] = { "LM_CONNECT_REQUEST", "LM_CONNECT_CONFIRM", "LM_CONNECT_RESPONSE", diff --git a/net/irda/irnet/irnet_irda.c b/net/irda/irnet/irnet_irda.c index cf9a4b531a9..cccc2e93234 100644 --- a/net/irda/irnet/irnet_irda.c +++ b/net/irda/irnet/irnet_irda.c @@ -9,6 +9,7 @@ */ #include "irnet_irda.h" /* Private header */ +#include <linux/sched.h> #include <linux/seq_file.h> #include <asm/unaligned.h> diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 68cbcb19cbd..7dea882dbb7 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/sched.h> #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 d9f8bd4ebd0..b5df2418f90 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/irnetlink.c b/net/irda/irnetlink.c index 8dd7ed7e7c1..476b307bd80 100644 --- a/net/irda/irnetlink.c +++ b/net/irda/irnetlink.c @@ -115,7 +115,7 @@ static int irda_nl_get_mode(struct sk_buff *skb, struct genl_info *info) genlmsg_end(msg, hdr); - return genlmsg_unicast(msg, info->snd_pid); + return genlmsg_reply(msg, info); err_out: nlmsg_free(msg); diff --git a/net/irda/irproc.c b/net/irda/irproc.c index 8ff1861649e..318766e5dbd 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/irda/irsysctl.c b/net/irda/irsysctl.c index 57f8817c397..5c86567e5a7 100644 --- a/net/irda/irsysctl.c +++ b/net/irda/irsysctl.c @@ -73,12 +73,12 @@ static int min_lap_keepalive_time = 100; /* 100us */ /* For other sysctl, I've no idea of the range. Maybe Dag could help * us on that - Jean II */ -static int do_devname(ctl_table *table, int write, struct file *filp, +static int do_devname(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dostring(table, write, filp, buffer, lenp, ppos); + ret = proc_dostring(table, write, buffer, lenp, ppos); if (ret == 0 && write) { struct ias_value *val; @@ -90,12 +90,12 @@ static int do_devname(ctl_table *table, int write, struct file *filp, } -static int do_discovery(ctl_table *table, int write, struct file *filp, +static int do_discovery(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret) return ret; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 49c15b48408..bada1b9c670 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -34,7 +34,7 @@ static char iucv_userid[80]; -static struct proto_ops iucv_sock_ops; +static const struct proto_ops iucv_sock_ops; static struct proto iucv_proto = { .name = "AF_IUCV", @@ -59,8 +59,8 @@ do { \ DEFINE_WAIT(__wait); \ long __timeo = timeo; \ ret = 0; \ + prepare_to_wait(sk->sk_sleep, &__wait, TASK_INTERRUPTIBLE); \ while (!(condition)) { \ - prepare_to_wait(sk->sk_sleep, &__wait, TASK_INTERRUPTIBLE); \ if (!__timeo) { \ ret = -EAGAIN; \ break; \ @@ -361,10 +361,9 @@ static void iucv_sock_cleanup_listen(struct sock *parent) } parent->sk_state = IUCV_CLOSED; - sock_set_flag(parent, SOCK_ZAPPED); } -/* Kill socket */ +/* Kill socket (only if zapped and orphaned) */ static void iucv_sock_kill(struct sock *sk) { if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) @@ -426,17 +425,18 @@ static void iucv_sock_close(struct sock *sk) skb_queue_purge(&iucv->send_skb_q); skb_queue_purge(&iucv->backlog_skb_q); - - sock_set_flag(sk, SOCK_ZAPPED); break; default: sock_set_flag(sk, SOCK_ZAPPED); + /* nothing to do here */ break; } + /* mark socket for deletion by iucv_sock_kill() */ + sock_set_flag(sk, SOCK_ZAPPED); + release_sock(sk); - iucv_sock_kill(sk); } static void iucv_sock_init(struct sock *sk, struct sock *parent) @@ -569,6 +569,7 @@ struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock) if (sk->sk_state == IUCV_CONNECTED || sk->sk_state == IUCV_SEVERED || + sk->sk_state == IUCV_DISCONN || /* due to PM restore */ !newsock) { iucv_accept_unlink(sk); if (newsock) @@ -1035,6 +1036,10 @@ out: return err; } +/* iucv_fragment_skb() - Fragment a single IUCV message into multiple skb's + * + * Locking: must be called with message_q.lock held + */ static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len) { int dataleft, size, copied = 0; @@ -1069,6 +1074,10 @@ static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len) return 0; } +/* iucv_process_message() - Receive a single outstanding IUCV message + * + * Locking: must be called with message_q.lock held + */ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, struct iucv_path *path, struct iucv_message *msg) @@ -1119,6 +1128,10 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, skb_queue_head(&iucv_sk(sk)->backlog_skb_q, skb); } +/* iucv_process_message_q() - Process outstanding IUCV messages + * + * Locking: must be called with message_q.lock held + */ static void iucv_process_message_q(struct sock *sk) { struct iucv_sock *iucv = iucv_sk(sk); @@ -1209,6 +1222,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, kfree_skb(skb); /* Queue backlog skbs */ + spin_lock_bh(&iucv->message_q.lock); rskb = skb_dequeue(&iucv->backlog_skb_q); while (rskb) { if (sock_queue_rcv_skb(sk, rskb)) { @@ -1220,11 +1234,10 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, } } if (skb_queue_empty(&iucv->backlog_skb_q)) { - spin_lock_bh(&iucv->message_q.lock); if (!list_empty(&iucv->message_q.list)) iucv_process_message_q(sk); - spin_unlock_bh(&iucv->message_q.lock); } + spin_unlock_bh(&iucv->message_q.lock); } done: @@ -1374,7 +1387,7 @@ static int iucv_sock_release(struct socket *sock) /* getsockopt and setsockopt */ static int iucv_sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); @@ -1682,7 +1695,7 @@ static void iucv_callback_shutdown(struct iucv_path *path, u8 ipuser[16]) bh_unlock_sock(sk); } -static struct proto_ops iucv_sock_ops = { +static const struct proto_ops iucv_sock_ops = { .family = PF_IUCV, .owner = THIS_MODULE, .release = iucv_sock_release, diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index c833481d32e..3973d0e61e5 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -79,6 +79,14 @@ static int iucv_bus_match(struct device *dev, struct device_driver *drv) return 0; } +enum iucv_pm_states { + IUCV_PM_INITIAL = 0, + IUCV_PM_FREEZING = 1, + IUCV_PM_THAWING = 2, + IUCV_PM_RESTORING = 3, +}; +static enum iucv_pm_states iucv_pm_state; + static int iucv_pm_prepare(struct device *); static void iucv_pm_complete(struct device *); static int iucv_pm_freeze(struct device *); @@ -354,7 +362,7 @@ static int iucv_query_maxconn(void) " srl %0,28\n" : "=d" (ccode), "+d" (reg0), "+d" (reg1) : : "cc"); if (ccode == 0) - iucv_max_pathid = reg0; + iucv_max_pathid = reg1; kfree(param); return ccode ? -EPERM : 0; } @@ -856,7 +864,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, int rc; local_bh_disable(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -905,7 +913,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, spin_lock_bh(&iucv_table_lock); iucv_cleanup_queue(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -965,7 +973,7 @@ int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]) int rc; local_bh_disable(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -997,7 +1005,7 @@ int iucv_path_resume(struct iucv_path *path, u8 userdata[16]) int rc; local_bh_disable(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1026,7 +1034,7 @@ int iucv_path_sever(struct iucv_path *path, u8 userdata[16]) int rc; preempt_disable(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1060,7 +1068,7 @@ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg, int rc; local_bh_disable(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1152,7 +1160,7 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, if (msg->flags & IUCV_IPRMDATA) return iucv_message_receive_iprmdata(path, msg, flags, buffer, size, residual); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1225,7 +1233,7 @@ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg) int rc; local_bh_disable(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1264,7 +1272,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, int rc; local_bh_disable(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1314,7 +1322,7 @@ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, union iucv_param *parm; int rc; - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1401,7 +1409,7 @@ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, int rc; local_bh_disable(); - if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + if (cpus_empty(iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1875,6 +1883,7 @@ static int iucv_pm_freeze(struct device *dev) #ifdef CONFIG_PM_DEBUG printk(KERN_WARNING "iucv_pm_freeze\n"); #endif + iucv_pm_state = IUCV_PM_FREEZING; for_each_cpu_mask_nr(cpu, iucv_irq_cpumask) smp_call_function_single(cpu, iucv_block_cpu_almost, NULL, 1); if (dev->driver && dev->driver->pm && dev->driver->pm->freeze) @@ -1899,6 +1908,7 @@ static int iucv_pm_thaw(struct device *dev) #ifdef CONFIG_PM_DEBUG printk(KERN_WARNING "iucv_pm_thaw\n"); #endif + iucv_pm_state = IUCV_PM_THAWING; if (!iucv_path_table) { rc = iucv_enable(); if (rc) @@ -1933,6 +1943,10 @@ static int iucv_pm_restore(struct device *dev) #ifdef CONFIG_PM_DEBUG printk(KERN_WARNING "iucv_pm_restore %p\n", iucv_path_table); #endif + if ((iucv_pm_state != IUCV_PM_RESTORING) && iucv_path_table) + pr_warning("Suspending Linux did not completely close all IUCV " + "connections\n"); + iucv_pm_state = IUCV_PM_RESTORING; if (cpus_empty(iucv_irq_cpumask)) { rc = iucv_query_maxconn(); rc = iucv_enable(); diff --git a/net/key/af_key.c b/net/key/af_key.c index dba9abd27f9..4e98193dfa0 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/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index 2ba1bc4f3c3..bda96d18fd9 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -407,7 +407,7 @@ int lapb_data_indication(struct lapb_cb *lapb, struct sk_buff *skb) return lapb->callbacks.data_indication(lapb->dev, skb); kfree_skb(skb); - return NET_RX_CN_HIGH; /* For now; must be != NET_RX_DROP */ + return NET_RX_SUCCESS; /* For now; must be != NET_RX_DROP */ } int lapb_data_transmit(struct lapb_cb *lapb, struct sk_buff *skb) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c45eee1c0e8..7aa4fd17010 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -973,7 +973,7 @@ static int llc_ui_ioctl(struct socket *sock, unsigned int cmd, * Set various connection specific parameters. */ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index f97be471fe2..be47ac427f6 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -143,7 +143,7 @@ out: return 0; } -static char *llc_conn_state_names[] = { +static const char *const llc_conn_state_names[] = { [LLC_CONN_STATE_ADM] = "adm", [LLC_CONN_STATE_SETUP] = "setup", [LLC_CONN_STATE_NORMAL] = "normal", diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 7836ee92898..4d5543af312 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -6,7 +6,6 @@ config MAC80211 select CRYPTO_ARC4 select CRYPTO_AES select CRC32 - select WIRELESS_EXT ---help--- This option enables the hardware independent IEEE 802.11 networking stack. @@ -14,24 +13,7 @@ config MAC80211 comment "CFG80211 needs to be enabled for MAC80211" depends on CFG80211=n -config MAC80211_DEFAULT_PS - bool "enable powersave by default" - depends on MAC80211 - default y - help - This option enables powersave mode by default. - - If this causes your applications to misbehave you should fix your - applications instead -- they need to register their network - latency requirement, see Documentation/power/pm_qos_interface.txt. - -config MAC80211_DEFAULT_PS_VALUE - int - default 1 if MAC80211_DEFAULT_PS - default 0 - -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 @@ -78,17 +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" @@ -222,3 +204,15 @@ config MAC80211_DEBUG_COUNTERS and show them in debugfs. If unsure, say N. + +config MAC80211_DRIVER_API_TRACER + bool "Driver API tracer" + depends on MAC80211_DEBUG_MENU + depends on EVENT_TRACING + help + Say Y here to make mac80211 register with the ftrace + framework for the driver API -- you can see which + driver methods it is calling then by looking at the + trace. + + If unsure, say N. diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 0e3ab88bb70..9f3cf712932 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -3,7 +3,6 @@ obj-$(CONFIG_MAC80211) += mac80211.o # mac80211 objects mac80211-y := \ main.o \ - wext.o \ sta_info.o \ wep.o \ wpa.o \ @@ -41,6 +40,9 @@ mac80211-$(CONFIG_MAC80211_MESH) += \ mac80211-$(CONFIG_PM) += pm.o +mac80211-$(CONFIG_MAC80211_DRIVER_API_TRACER) += driver-trace.o +CFLAGS_driver-trace.o := -I$(src) + # objects for PID algorithm rc80211_pid-y := rc80211_pid_algo.o rc80211_pid-$(CONFIG_MAC80211_DEBUGFS) += rc80211_pid_debugfs.o diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index bc064d7933f..ce8e0e772ba 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -85,10 +85,6 @@ void ieee80211_sta_stop_rx_ba_session(struct ieee80211_sub_if_data *sdata, u8 *r struct ieee80211_local *local = sdata->local; struct sta_info *sta; - /* stop HW Rx aggregation. ampdu_action existence - * already verified in session init so we add the BUG_ON */ - BUG_ON(!local->ops->ampdu_action); - rcu_read_lock(); sta = sta_info_get(local, ra); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index a24e59816b9..89e238b001d 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -123,13 +123,18 @@ void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u1 ieee80211_tx_skb(sdata, skb, 0); } -static int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator) +int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, + enum ieee80211_back_parties initiator) { struct ieee80211_local *local = sta->local; int ret; u8 *state; +#ifdef CONFIG_MAC80211_HT_DEBUG + printk(KERN_DEBUG "Tx BA session stop requested for %pM tid %u\n", + sta->sta.addr, tid); +#endif /* CONFIG_MAC80211_HT_DEBUG */ + state = &sta->ampdu_mlme.tid_state_tx[tid]; if (*state == HT_AGG_STATE_OPERATIONAL) @@ -143,7 +148,6 @@ static int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { - *state = HT_AGG_STATE_OPERATIONAL; /* * We may have pending packets get stuck in this case... * Not bothering with a workaround for now. @@ -173,12 +177,14 @@ static void sta_addba_resp_timer_expired(unsigned long data) /* check if the TID waits for addBA response */ spin_lock_bh(&sta->lock); - if (!(*state & HT_ADDBA_REQUESTED_MSK)) { + if ((*state & (HT_ADDBA_REQUESTED_MSK | HT_ADDBA_RECEIVED_MSK)) != + HT_ADDBA_REQUESTED_MSK) { spin_unlock_bh(&sta->lock); *state = HT_AGG_STATE_IDLE; #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "timer expired on tid %d but we are not " - "expecting addBA response there", tid); + "(or no longer) expecting addBA response there", + tid); #endif return; } @@ -391,9 +397,6 @@ static void ieee80211_agg_splice_packets(struct ieee80211_local *local, if (!skb_queue_empty(&sta->ampdu_mlme.tid_tx[tid]->pending)) { spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - /* mark queue as pending, it is stopped already */ - __set_bit(IEEE80211_QUEUE_STOP_REASON_PENDING, - &local->queue_stop_reasons[queue]); /* copy over remaining packets */ skb_queue_splice_tail_init( &sta->ampdu_mlme.tid_tx[tid]->pending, @@ -526,11 +529,6 @@ int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, goto unlock; } -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Tx BA session stop requested for %pM tid %u\n", - sta->sta.addr, tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ - ret = ___ieee80211_stop_tx_ba_session(sta, tid, initiator); unlock: @@ -546,7 +544,7 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_hw *hw, struct sta_info *sta; int ret = 0; - if (WARN_ON(!local->ops->ampdu_action)) + if (!local->ops->ampdu_action) return -EINVAL; if (tid >= STA_TID_NUM) @@ -671,24 +669,23 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, spin_lock_bh(&sta->lock); - if (!(*state & HT_ADDBA_REQUESTED_MSK)) { - spin_unlock_bh(&sta->lock); - return; - } + if (!(*state & HT_ADDBA_REQUESTED_MSK)) + goto out; if (mgmt->u.action.u.addba_resp.dialog_token != sta->ampdu_mlme.tid_tx[tid]->dialog_token) { - spin_unlock_bh(&sta->lock); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "wrong addBA response token, tid %d\n", tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ - return; + goto out; } - del_timer_sync(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer); + del_timer(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer); + #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "switched off addBA timer for tid %d \n", tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ + if (le16_to_cpu(mgmt->u.action.u.addba_resp.status) == WLAN_STATUS_SUCCESS) { u8 curstate = *state; @@ -702,5 +699,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, } else { ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR); } + + out: spin_unlock_bh(&sta->lock); } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 3f47276caeb..7b5131bd6fa 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -57,35 +57,23 @@ static int ieee80211_add_iface(struct wiphy *wiphy, char *name, return 0; } -static int ieee80211_del_iface(struct wiphy *wiphy, int ifindex) +static int ieee80211_del_iface(struct wiphy *wiphy, struct net_device *dev) { - struct net_device *dev; - struct ieee80211_sub_if_data *sdata; - - /* we're under RTNL */ - dev = __dev_get_by_index(&init_net, ifindex); - if (!dev) - return -ENODEV; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - ieee80211_if_remove(sdata); + ieee80211_if_remove(IEEE80211_DEV_TO_SUB_IF(dev)); return 0; } -static int ieee80211_change_iface(struct wiphy *wiphy, int ifindex, +static int ieee80211_change_iface(struct wiphy *wiphy, + struct net_device *dev, enum nl80211_iftype type, u32 *flags, struct vif_params *params) { - struct net_device *dev; struct ieee80211_sub_if_data *sdata; int ret; - /* we're under RTNL */ - dev = __dev_get_by_index(&init_net, ifindex); - if (!dev) - return -ENODEV; + if (netif_running(dev)) + return -EBUSY; if (!nl80211_type_check(type)) return -EINVAL; @@ -96,9 +84,6 @@ static int ieee80211_change_iface(struct wiphy *wiphy, int ifindex, if (ret) return ret; - if (netif_running(sdata->dev)) - return -EBUSY; - if (ieee80211_vif_is_mesh(&sdata->vif) && params->mesh_id_len) ieee80211_sdata_set_mesh_id(sdata, params->mesh_id_len, @@ -338,6 +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 | @@ -924,6 +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 | @@ -1177,123 +1166,29 @@ static int ieee80211_scan(struct wiphy *wiphy, static int ieee80211_auth(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_auth_request *req) { - struct ieee80211_sub_if_data *sdata; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - switch (req->auth_type) { - case NL80211_AUTHTYPE_OPEN_SYSTEM: - sdata->u.mgd.auth_algs = IEEE80211_AUTH_ALG_OPEN; - break; - case NL80211_AUTHTYPE_SHARED_KEY: - sdata->u.mgd.auth_algs = IEEE80211_AUTH_ALG_SHARED_KEY; - break; - case NL80211_AUTHTYPE_FT: - sdata->u.mgd.auth_algs = IEEE80211_AUTH_ALG_FT; - break; - case NL80211_AUTHTYPE_NETWORK_EAP: - sdata->u.mgd.auth_algs = IEEE80211_AUTH_ALG_LEAP; - break; - default: - return -EOPNOTSUPP; - } - - memcpy(sdata->u.mgd.bssid, req->peer_addr, ETH_ALEN); - sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_BSSID_SEL; - sdata->u.mgd.flags |= IEEE80211_STA_BSSID_SET; - - /* TODO: req->chan */ - sdata->u.mgd.flags |= IEEE80211_STA_AUTO_CHANNEL_SEL; - - if (req->ssid) { - sdata->u.mgd.flags |= IEEE80211_STA_SSID_SET; - memcpy(sdata->u.mgd.ssid, req->ssid, req->ssid_len); - sdata->u.mgd.ssid_len = req->ssid_len; - sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_SSID_SEL; - } - - kfree(sdata->u.mgd.sme_auth_ie); - sdata->u.mgd.sme_auth_ie = NULL; - sdata->u.mgd.sme_auth_ie_len = 0; - if (req->ie) { - sdata->u.mgd.sme_auth_ie = kmalloc(req->ie_len, GFP_KERNEL); - if (sdata->u.mgd.sme_auth_ie == NULL) - return -ENOMEM; - memcpy(sdata->u.mgd.sme_auth_ie, req->ie, req->ie_len); - sdata->u.mgd.sme_auth_ie_len = req->ie_len; - } - - sdata->u.mgd.flags |= IEEE80211_STA_EXT_SME; - sdata->u.mgd.state = IEEE80211_STA_MLME_DIRECT_PROBE; - ieee80211_sta_req_auth(sdata); - return 0; + return ieee80211_mgd_auth(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_assoc_request *req) { - struct ieee80211_sub_if_data *sdata; - int ret; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - if (memcmp(sdata->u.mgd.bssid, req->peer_addr, ETH_ALEN) != 0 || - !(sdata->u.mgd.flags & IEEE80211_STA_AUTHENTICATED)) - return -ENOLINK; /* not authenticated */ - - sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_BSSID_SEL; - sdata->u.mgd.flags |= IEEE80211_STA_BSSID_SET; - - /* TODO: req->chan */ - sdata->u.mgd.flags |= IEEE80211_STA_AUTO_CHANNEL_SEL; - - if (req->ssid) { - sdata->u.mgd.flags |= IEEE80211_STA_SSID_SET; - memcpy(sdata->u.mgd.ssid, req->ssid, req->ssid_len); - sdata->u.mgd.ssid_len = req->ssid_len; - sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_SSID_SEL; - } else - sdata->u.mgd.flags |= IEEE80211_STA_AUTO_SSID_SEL; - - ret = ieee80211_sta_set_extra_ie(sdata, req->ie, req->ie_len); - if (ret && ret != -EALREADY) - return ret; - - if (req->use_mfp) { - sdata->u.mgd.mfp = IEEE80211_MFP_REQUIRED; - sdata->u.mgd.flags |= IEEE80211_STA_MFP_ENABLED; - } else { - sdata->u.mgd.mfp = IEEE80211_MFP_DISABLED; - sdata->u.mgd.flags &= ~IEEE80211_STA_MFP_ENABLED; - } - - if (req->control_port) - sdata->u.mgd.flags |= IEEE80211_STA_CONTROL_PORT; - else - sdata->u.mgd.flags &= ~IEEE80211_STA_CONTROL_PORT; - - sdata->u.mgd.flags |= IEEE80211_STA_EXT_SME; - sdata->u.mgd.state = IEEE80211_STA_MLME_ASSOCIATE; - ieee80211_sta_req_auth(sdata); - return 0; + return ieee80211_mgd_assoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_deauth(struct wiphy *wiphy, struct net_device *dev, - struct cfg80211_deauth_request *req) + struct cfg80211_deauth_request *req, + void *cookie) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - /* TODO: req->ie, req->peer_addr */ - return ieee80211_sta_deauthenticate(sdata, req->reason_code); + return ieee80211_mgd_deauth(IEEE80211_DEV_TO_SUB_IF(dev), + req, cookie); } static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev, - struct cfg80211_disassoc_request *req) + struct cfg80211_disassoc_request *req, + void *cookie) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - /* TODO: req->ie, req->peer_addr */ - return ieee80211_sta_disassociate(sdata, req->reason_code); + return ieee80211_mgd_disassoc(IEEE80211_DEV_TO_SUB_IF(dev), + req, cookie); } static int ieee80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, @@ -1374,6 +1269,16 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy, int *dbm) return 0; } +static int ieee80211_set_wds_peer(struct wiphy *wiphy, struct net_device *dev, + u8 *addr) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + memcpy(&sdata->u.wds.remote_addr, addr, ETH_ALEN); + + return 0; +} + static void ieee80211_rfkill_poll(struct wiphy *wiphy) { struct ieee80211_local *local = wiphy_priv(wiphy); @@ -1381,6 +1286,85 @@ static void ieee80211_rfkill_poll(struct wiphy *wiphy) drv_rfkill_poll(local); } +#ifdef CONFIG_NL80211_TESTMODE +static int ieee80211_testmode_cmd(struct wiphy *wiphy, void *data, int len) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + + if (!local->ops->testmode_cmd) + return -EOPNOTSUPP; + + return local->ops->testmode_cmd(&local->hw, data, len); +} +#endif + +static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, + bool enabled, int timeout) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_conf *conf = &local->hw.conf; + + if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) + return -EOPNOTSUPP; + + if (enabled == sdata->u.mgd.powersave && + timeout == conf->dynamic_ps_timeout) + return 0; + + sdata->u.mgd.powersave = enabled; + conf->dynamic_ps_timeout = timeout; + + if (local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS) + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); + + ieee80211_recalc_ps(local, -1); + + return 0; +} + +static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, + struct net_device *dev, + const u8 *addr, + const struct cfg80211_bitrate_mask *mask) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + int i, err = -EINVAL; + u32 target_rate; + struct ieee80211_supported_band *sband; + + sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + + /* target_rate = -1, rate->fixed = 0 means auto only, so use all rates + * target_rate = X, rate->fixed = 1 means only rate X + * target_rate = X, rate->fixed = 0 means all rates <= X */ + sdata->max_ratectrl_rateidx = -1; + sdata->force_unicast_rateidx = -1; + + if (mask->fixed) + target_rate = mask->fixed / 100; + else if (mask->maxrate) + target_rate = mask->maxrate / 100; + else + return 0; + + for (i=0; i< sband->n_bitrates; i++) { + struct ieee80211_rate *brate = &sband->bitrates[i]; + int this_rate = brate->bitrate; + + if (target_rate == this_rate) { + sdata->max_ratectrl_rateidx = i; + if (mask->fixed) + sdata->force_unicast_rateidx = i; + err = 0; + break; + } + } + + return err; +} + struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -1422,5 +1406,9 @@ struct cfg80211_ops mac80211_config_ops = { .set_wiphy_params = ieee80211_set_wiphy_params, .set_tx_power = ieee80211_set_tx_power, .get_tx_power = ieee80211_get_tx_power, + .set_wds_peer = ieee80211_set_wds_peer, .rfkill_poll = ieee80211_rfkill_poll, + CFG80211_TESTMODE_CMD(ieee80211_testmode_cmd) + .set_power_mgmt = ieee80211_set_power_mgmt, + .set_bitrate_mask = ieee80211_set_bitrate_mask, }; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 6c439cd5cce..96991b68f04 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -175,7 +175,7 @@ static ssize_t queues_read(struct file *file, char __user *user_buf, for (q = 0; q < local->hw.queues; q++) res += sprintf(buf + res, "%02d: %#.8lx/%d\n", q, local->queue_stop_reasons[q], - __netif_subqueue_stopped(local->mdev, q)); + skb_queue_len(&local->pending[q])); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); return simple_read_from_buffer(user_buf, count, ppos, buf, res); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index e3420329f4e..61234e79022 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -95,33 +95,9 @@ IEEE80211_IF_FILE(force_unicast_rateidx, force_unicast_rateidx, DEC); IEEE80211_IF_FILE(max_ratectrl_rateidx, max_ratectrl_rateidx, DEC); /* STA attributes */ -IEEE80211_IF_FILE(state, u.mgd.state, DEC); IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC); -IEEE80211_IF_FILE(prev_bssid, u.mgd.prev_bssid, MAC); -IEEE80211_IF_FILE(ssid_len, u.mgd.ssid_len, SIZE); IEEE80211_IF_FILE(aid, u.mgd.aid, DEC); -IEEE80211_IF_FILE(ap_capab, u.mgd.ap_capab, HEX); IEEE80211_IF_FILE(capab, u.mgd.capab, HEX); -IEEE80211_IF_FILE(extra_ie_len, u.mgd.extra_ie_len, SIZE); -IEEE80211_IF_FILE(auth_tries, u.mgd.auth_tries, DEC); -IEEE80211_IF_FILE(assoc_tries, u.mgd.assoc_tries, DEC); -IEEE80211_IF_FILE(auth_algs, u.mgd.auth_algs, HEX); -IEEE80211_IF_FILE(auth_alg, u.mgd.auth_alg, DEC); -IEEE80211_IF_FILE(auth_transaction, u.mgd.auth_transaction, DEC); - -static ssize_t ieee80211_if_fmt_flags( - const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) -{ - return scnprintf(buf, buflen, "%s%s%s%s%s%s%s\n", - sdata->u.mgd.flags & IEEE80211_STA_SSID_SET ? "SSID\n" : "", - sdata->u.mgd.flags & IEEE80211_STA_BSSID_SET ? "BSSID\n" : "", - sdata->u.mgd.flags & IEEE80211_STA_PREV_BSSID_SET ? "prev BSSID\n" : "", - sdata->u.mgd.flags & IEEE80211_STA_AUTHENTICATED ? "AUTH\n" : "", - sdata->u.mgd.flags & IEEE80211_STA_ASSOCIATED ? "ASSOC\n" : "", - sdata->u.mgd.flags & IEEE80211_STA_PROBEREQ_POLL ? "PROBEREQ POLL\n" : "", - sdata->vif.bss_conf.use_cts_prot ? "CTS prot\n" : ""); -} -__IEEE80211_IF_FILE(flags); /* AP attributes */ IEEE80211_IF_FILE(num_sta_ps, u.ap.num_sta_ps, ATOMIC); @@ -140,6 +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, @@ -184,20 +162,9 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(force_unicast_rateidx, sta); DEBUGFS_ADD(max_ratectrl_rateidx, sta); - DEBUGFS_ADD(state, sta); DEBUGFS_ADD(bssid, sta); - DEBUGFS_ADD(prev_bssid, sta); - DEBUGFS_ADD(ssid_len, sta); DEBUGFS_ADD(aid, sta); - DEBUGFS_ADD(ap_capab, sta); DEBUGFS_ADD(capab, sta); - DEBUGFS_ADD(extra_ie_len, sta); - DEBUGFS_ADD(auth_tries, sta); - DEBUGFS_ADD(assoc_tries, sta); - DEBUGFS_ADD(auth_algs, sta); - DEBUGFS_ADD(auth_alg, sta); - DEBUGFS_ADD(auth_transaction, sta); - DEBUGFS_ADD(flags, sta); } static void add_ap_files(struct ieee80211_sub_if_data *sdata) @@ -240,6 +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); @@ -317,20 +286,9 @@ static void del_sta_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_DEL(force_unicast_rateidx, sta); DEBUGFS_DEL(max_ratectrl_rateidx, sta); - DEBUGFS_DEL(state, sta); DEBUGFS_DEL(bssid, sta); - DEBUGFS_DEL(prev_bssid, sta); - DEBUGFS_DEL(ssid_len, sta); DEBUGFS_DEL(aid, sta); - DEBUGFS_DEL(ap_capab, sta); DEBUGFS_DEL(capab, sta); - DEBUGFS_DEL(extra_ie_len, sta); - DEBUGFS_DEL(auth_tries, sta); - DEBUGFS_DEL(assoc_tries, sta); - DEBUGFS_DEL(auth_algs, sta); - DEBUGFS_DEL(auth_alg, sta); - DEBUGFS_DEL(auth_transaction, sta); - DEBUGFS_DEL(flags, sta); } static void del_ap_files(struct ieee80211_sub_if_data *sdata) @@ -373,6 +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/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 90230c718b5..33a2e892115 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -120,45 +120,38 @@ STA_OPS(last_seq_ctrl); static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - char buf[768], *p = buf; + char buf[30 + STA_TID_NUM * 70], *p = buf; int i; struct sta_info *sta = file->private_data; - p += scnprintf(p, sizeof(buf)+buf-p, "Agg state for STA is:\n"); - p += scnprintf(p, sizeof(buf)+buf-p, " STA next dialog_token is %d \n " - "TIDs info is: \n TID :", - (sta->ampdu_mlme.dialog_token_allocator + 1)); - for (i = 0; i < STA_TID_NUM; i++) - p += scnprintf(p, sizeof(buf)+buf-p, "%5d", i); - - p += scnprintf(p, sizeof(buf)+buf-p, "\n RX :"); - for (i = 0; i < STA_TID_NUM; i++) - p += scnprintf(p, sizeof(buf)+buf-p, "%5d", - sta->ampdu_mlme.tid_state_rx[i]); - - p += scnprintf(p, sizeof(buf)+buf-p, "\n DTKN:"); - for (i = 0; i < STA_TID_NUM; i++) - p += scnprintf(p, sizeof(buf)+buf-p, "%5d", - sta->ampdu_mlme.tid_state_rx[i] ? - sta->ampdu_mlme.tid_rx[i]->dialog_token : 0); - - p += scnprintf(p, sizeof(buf)+buf-p, "\n TX :"); - for (i = 0; i < STA_TID_NUM; i++) - p += scnprintf(p, sizeof(buf)+buf-p, "%5d", - sta->ampdu_mlme.tid_state_tx[i]); - - p += scnprintf(p, sizeof(buf)+buf-p, "\n DTKN:"); - for (i = 0; i < STA_TID_NUM; i++) - p += scnprintf(p, sizeof(buf)+buf-p, "%5d", - sta->ampdu_mlme.tid_state_tx[i] ? - sta->ampdu_mlme.tid_tx[i]->dialog_token : 0); - - p += scnprintf(p, sizeof(buf)+buf-p, "\n SSN :"); - for (i = 0; i < STA_TID_NUM; i++) - p += scnprintf(p, sizeof(buf)+buf-p, "%5d", - sta->ampdu_mlme.tid_state_tx[i] ? - sta->ampdu_mlme.tid_tx[i]->ssn : 0); - p += scnprintf(p, sizeof(buf)+buf-p, "\n"); + spin_lock_bh(&sta->lock); + p += scnprintf(p, sizeof(buf)+buf-p, "next dialog_token is %#02x\n", + sta->ampdu_mlme.dialog_token_allocator + 1); + for (i = 0; i < STA_TID_NUM; i++) { + p += scnprintf(p, sizeof(buf)+buf-p, "TID %02d:", i); + p += scnprintf(p, sizeof(buf)+buf-p, " RX=%x", + sta->ampdu_mlme.tid_state_rx[i]); + p += scnprintf(p, sizeof(buf)+buf-p, "/DTKN=%#.2x", + sta->ampdu_mlme.tid_state_rx[i] ? + sta->ampdu_mlme.tid_rx[i]->dialog_token : 0); + p += scnprintf(p, sizeof(buf)+buf-p, "/SSN=%#.3x", + sta->ampdu_mlme.tid_state_rx[i] ? + sta->ampdu_mlme.tid_rx[i]->ssn : 0); + + p += scnprintf(p, sizeof(buf)+buf-p, " TX=%x", + sta->ampdu_mlme.tid_state_tx[i]); + p += scnprintf(p, sizeof(buf)+buf-p, "/DTKN=%#.2x", + sta->ampdu_mlme.tid_state_tx[i] ? + sta->ampdu_mlme.tid_tx[i]->dialog_token : 0); + p += scnprintf(p, sizeof(buf)+buf-p, "/SSN=%#.3x", + sta->ampdu_mlme.tid_state_tx[i] ? + sta->ampdu_mlme.tid_tx[i]->ssn : 0); + p += scnprintf(p, sizeof(buf)+buf-p, "/pending=%03d", + sta->ampdu_mlme.tid_state_tx[i] ? + skb_queue_len(&sta->ampdu_mlme.tid_tx[i]->pending) : 0); + p += scnprintf(p, sizeof(buf)+buf-p, "\n"); + } + spin_unlock_bh(&sta->lock); return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } @@ -203,6 +196,22 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(inactive_ms); DEBUGFS_ADD(last_seq_ctrl); DEBUGFS_ADD(agg_status); + DEBUGFS_ADD(dev); + DEBUGFS_ADD(rx_packets); + DEBUGFS_ADD(tx_packets); + DEBUGFS_ADD(rx_bytes); + DEBUGFS_ADD(tx_bytes); + DEBUGFS_ADD(rx_duplicates); + DEBUGFS_ADD(rx_fragments); + DEBUGFS_ADD(rx_dropped); + DEBUGFS_ADD(tx_fragments); + DEBUGFS_ADD(tx_filtered); + DEBUGFS_ADD(tx_retry_failed); + DEBUGFS_ADD(tx_retry_count); + DEBUGFS_ADD(last_signal); + DEBUGFS_ADD(last_qual); + DEBUGFS_ADD(last_noise); + DEBUGFS_ADD(wep_weak_iv_count); } void ieee80211_sta_debugfs_remove(struct sta_info *sta) @@ -212,6 +221,23 @@ void ieee80211_sta_debugfs_remove(struct sta_info *sta) DEBUGFS_DEL(inactive_ms); DEBUGFS_DEL(last_seq_ctrl); DEBUGFS_DEL(agg_status); + DEBUGFS_DEL(aid); + DEBUGFS_DEL(dev); + DEBUGFS_DEL(rx_packets); + DEBUGFS_DEL(tx_packets); + DEBUGFS_DEL(rx_bytes); + DEBUGFS_DEL(tx_bytes); + DEBUGFS_DEL(rx_duplicates); + DEBUGFS_DEL(rx_fragments); + DEBUGFS_DEL(rx_dropped); + DEBUGFS_DEL(tx_fragments); + DEBUGFS_DEL(tx_filtered); + DEBUGFS_DEL(tx_retry_failed); + DEBUGFS_DEL(tx_retry_count); + DEBUGFS_DEL(last_signal); + DEBUGFS_DEL(last_qual); + DEBUGFS_DEL(last_noise); + DEBUGFS_DEL(wep_weak_iv_count); debugfs_remove(sta->debugfs.dir); sta->debugfs.dir = NULL; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index b13446afd48..020a94a3110 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -3,6 +3,7 @@ #include <net/mac80211.h> #include "ieee80211_i.h" +#include "driver-trace.h" static inline int drv_tx(struct ieee80211_local *local, struct sk_buff *skb) { @@ -11,29 +12,49 @@ static inline int drv_tx(struct ieee80211_local *local, struct sk_buff *skb) static inline int drv_start(struct ieee80211_local *local) { - return 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; } 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, struct ieee80211_if_init_conf *conf) { - return local->ops->add_interface(&local->hw, conf); + int ret = local->ops->add_interface(&local->hw, conf); + trace_drv_add_interface(local, conf->mac_addr, conf->vif, ret); + return ret; } static inline void drv_remove_interface(struct ieee80211_local *local, struct ieee80211_if_init_conf *conf) { local->ops->remove_interface(&local->hw, conf); + trace_drv_remove_interface(local, conf->mac_addr, conf->vif); } static inline int drv_config(struct ieee80211_local *local, u32 changed) { - return local->ops->config(&local->hw, changed); + int ret = local->ops->config(&local->hw, changed); + trace_drv_config(local, changed, ret); + return ret; } static inline void drv_bss_info_changed(struct ieee80211_local *local, @@ -43,24 +64,45 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local, { if (local->ops->bss_info_changed) local->ops->bss_info_changed(&local->hw, vif, info, changed); + 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, + multicast); } static inline int drv_set_tim(struct ieee80211_local *local, struct ieee80211_sta *sta, bool set) { + int ret = 0; if (local->ops->set_tim) - return local->ops->set_tim(&local->hw, sta, set); - return 0; + ret = local->ops->set_tim(&local->hw, sta, set); + trace_drv_set_tim(local, sta, set, ret); + return ret; } static inline int drv_set_key(struct ieee80211_local *local, @@ -68,7 +110,9 @@ static inline int drv_set_key(struct ieee80211_local *local, struct ieee80211_sta *sta, struct ieee80211_key_conf *key) { - return local->ops->set_key(&local->hw, cmd, vif, sta, key); + int ret = local->ops->set_key(&local->hw, cmd, vif, sta, key); + trace_drv_set_key(local, cmd, vif, sta, key, ret); + return ret; } static inline void drv_update_tkip_key(struct ieee80211_local *local, @@ -79,32 +123,41 @@ static inline void drv_update_tkip_key(struct ieee80211_local *local, if (local->ops->update_tkip_key) local->ops->update_tkip_key(&local->hw, conf, address, iv32, phase1key); + trace_drv_update_tkip_key(local, conf, address, iv32); } static inline int drv_hw_scan(struct ieee80211_local *local, struct cfg80211_scan_request *req) { - return local->ops->hw_scan(&local->hw, req); + int ret = local->ops->hw_scan(&local->hw, req); + trace_drv_hw_scan(local, req, ret); + return ret; } static inline void drv_sw_scan_start(struct ieee80211_local *local) { if (local->ops->sw_scan_start) local->ops->sw_scan_start(&local->hw); + trace_drv_sw_scan_start(local); } static inline void drv_sw_scan_complete(struct ieee80211_local *local) { if (local->ops->sw_scan_complete) local->ops->sw_scan_complete(&local->hw); + trace_drv_sw_scan_complete(local); } static inline int drv_get_stats(struct ieee80211_local *local, struct ieee80211_low_level_stats *stats) { - if (!local->ops->get_stats) - return -EOPNOTSUPP; - return local->ops->get_stats(&local->hw, stats); + int ret = -EOPNOTSUPP; + + if (local->ops->get_stats) + ret = local->ops->get_stats(&local->hw, stats); + trace_drv_get_stats(local, stats, ret); + + return ret; } static inline void drv_get_tkip_seq(struct ieee80211_local *local, @@ -112,14 +165,17 @@ static inline void drv_get_tkip_seq(struct ieee80211_local *local, { if (local->ops->get_tkip_seq) local->ops->get_tkip_seq(&local->hw, hw_key_idx, iv32, iv16); + trace_drv_get_tkip_seq(local, hw_key_idx, iv32, iv16); } static inline int drv_set_rts_threshold(struct ieee80211_local *local, u32 value) { + int ret = 0; if (local->ops->set_rts_threshold) - return local->ops->set_rts_threshold(&local->hw, value); - return 0; + ret = local->ops->set_rts_threshold(&local->hw, value); + trace_drv_set_rts_threshold(local, value, ret); + return ret; } static inline void drv_sta_notify(struct ieee80211_local *local, @@ -129,46 +185,57 @@ static inline void drv_sta_notify(struct ieee80211_local *local, { if (local->ops->sta_notify) local->ops->sta_notify(&local->hw, vif, cmd, sta); + trace_drv_sta_notify(local, vif, cmd, sta); } static inline int drv_conf_tx(struct ieee80211_local *local, u16 queue, const struct ieee80211_tx_queue_params *params) { + int ret = -EOPNOTSUPP; if (local->ops->conf_tx) - return local->ops->conf_tx(&local->hw, queue, params); - return -EOPNOTSUPP; + ret = local->ops->conf_tx(&local->hw, queue, params); + trace_drv_conf_tx(local, queue, params, ret); + return ret; } static inline int drv_get_tx_stats(struct ieee80211_local *local, struct ieee80211_tx_queue_stats *stats) { - return local->ops->get_tx_stats(&local->hw, stats); + int ret = local->ops->get_tx_stats(&local->hw, stats); + trace_drv_get_tx_stats(local, stats, ret); + return ret; } static inline u64 drv_get_tsf(struct ieee80211_local *local) { + u64 ret = -1ULL; if (local->ops->get_tsf) - return local->ops->get_tsf(&local->hw); - return -1ULL; + ret = local->ops->get_tsf(&local->hw); + trace_drv_get_tsf(local, ret); + return ret; } static inline void drv_set_tsf(struct ieee80211_local *local, u64 tsf) { if (local->ops->set_tsf) local->ops->set_tsf(&local->hw, tsf); + trace_drv_set_tsf(local, tsf); } static inline void drv_reset_tsf(struct ieee80211_local *local) { if (local->ops->reset_tsf) local->ops->reset_tsf(&local->hw); + trace_drv_reset_tsf(local); } static inline int drv_tx_last_beacon(struct ieee80211_local *local) { + int ret = 1; if (local->ops->tx_last_beacon) - return local->ops->tx_last_beacon(&local->hw); - return 1; + ret = local->ops->tx_last_beacon(&local->hw); + trace_drv_tx_last_beacon(local, ret); + return ret; } static inline int drv_ampdu_action(struct ieee80211_local *local, @@ -176,10 +243,12 @@ static inline int drv_ampdu_action(struct ieee80211_local *local, struct ieee80211_sta *sta, u16 tid, u16 *ssn) { + int ret = -EOPNOTSUPP; if (local->ops->ampdu_action) - return local->ops->ampdu_action(&local->hw, action, - sta, tid, ssn); - return -EOPNOTSUPP; + ret = local->ops->ampdu_action(&local->hw, action, + sta, tid, ssn); + trace_drv_ampdu_action(local, action, sta, tid, ssn, ret); + return ret; } diff --git a/net/mac80211/driver-trace.c b/net/mac80211/driver-trace.c new file mode 100644 index 00000000000..8ed8711b1a6 --- /dev/null +++ b/net/mac80211/driver-trace.c @@ -0,0 +1,9 @@ +/* bug in tracepoint.h, it should include this */ +#include <linux/module.h> + +/* sparse isn't too happy with all macros... */ +#ifndef __CHECKER__ +#include "driver-ops.h" +#define CREATE_TRACE_POINTS +#include "driver-trace.h" +#endif diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h new file mode 100644 index 00000000000..37b9051afcf --- /dev/null +++ b/net/mac80211/driver-trace.h @@ -0,0 +1,672 @@ +#if !defined(__MAC80211_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) +#define __MAC80211_DRIVER_TRACE + +#include <linux/tracepoint.h> +#include <net/mac80211.h> +#include "ieee80211_i.h" + +#if !defined(CONFIG_MAC80211_DRIVER_API_TRACER) || defined(__CHECKER__) +#undef TRACE_EVENT +#define TRACE_EVENT(name, proto, ...) \ +static inline void trace_ ## name(proto) {} +#endif + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mac80211 + +#define MAXNAME 32 +#define LOCAL_ENTRY __array(char, wiphy_name, 32) +#define LOCAL_ASSIGN strlcpy(__entry->wiphy_name, wiphy_name(local->hw.wiphy), MAXNAME) +#define LOCAL_PR_FMT "%s" +#define LOCAL_PR_ARG __entry->wiphy_name + +#define STA_ENTRY __array(char, sta_addr, ETH_ALEN) +#define STA_ASSIGN (sta ? memcpy(__entry->sta_addr, sta->addr, ETH_ALEN) : memset(__entry->sta_addr, 0, ETH_ALEN)) +#define STA_PR_FMT " sta:%pM" +#define STA_PR_ARG __entry->sta_addr + +#define VIF_ENTRY __field(enum nl80211_iftype, vif_type) __field(void *, vif) +#define VIF_ASSIGN __entry->vif_type = vif ? vif->type : 0; __entry->vif = vif +#define VIF_PR_FMT " vif:%p(%d)" +#define VIF_PR_ARG __entry->vif, __entry->vif_type + +TRACE_EVENT(drv_start, + TP_PROTO(struct ieee80211_local *local, int ret), + + TP_ARGS(local, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT, LOCAL_PR_ARG + ) +); + +TRACE_EVENT(drv_stop, + TP_PROTO(struct ieee80211_local *local), + + TP_ARGS(local), + + TP_STRUCT__entry( + LOCAL_ENTRY + ), + + TP_fast_assign( + LOCAL_ASSIGN; + ), + + TP_printk( + LOCAL_PR_FMT, LOCAL_PR_ARG + ) +); + +TRACE_EVENT(drv_add_interface, + TP_PROTO(struct ieee80211_local *local, + const u8 *addr, + struct ieee80211_vif *vif, + int ret), + + TP_ARGS(local, addr, vif, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __array(char, addr, 6) + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + memcpy(__entry->addr, addr, 6); + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT " addr:%pM ret:%d", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->addr, __entry->ret + ) +); + +TRACE_EVENT(drv_remove_interface, + TP_PROTO(struct ieee80211_local *local, + const u8 *addr, struct ieee80211_vif *vif), + + TP_ARGS(local, addr, vif), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __array(char, addr, 6) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + memcpy(__entry->addr, addr, 6); + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT " addr:%pM", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->addr + ) +); + +TRACE_EVENT(drv_config, + TP_PROTO(struct ieee80211_local *local, + u32 changed, + int ret), + + TP_ARGS(local, changed, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u32, changed) + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->changed = changed; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT " ch:%#x ret:%d", + LOCAL_PR_ARG, __entry->changed, __entry->ret + ) +); + +TRACE_EVENT(drv_bss_info_changed, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *info, + u32 changed), + + TP_ARGS(local, vif, info, changed), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __field(bool, assoc) + __field(u16, aid) + __field(bool, cts) + __field(bool, shortpre) + __field(bool, shortslot) + __field(u8, dtimper) + __field(u16, bcnint) + __field(u16, assoc_cap) + __field(u64, timestamp) + __field(u32, basic_rates) + __field(u32, changed) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + __entry->changed = changed; + __entry->aid = info->aid; + __entry->assoc = info->assoc; + __entry->shortpre = info->use_short_preamble; + __entry->cts = info->use_cts_prot; + __entry->shortslot = info->use_short_slot; + __entry->dtimper = info->dtim_period; + __entry->bcnint = info->beacon_int; + __entry->assoc_cap = info->assoc_capability; + __entry->timestamp = info->timestamp; + __entry->basic_rates = info->basic_rates; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT " changed:%#x", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->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, + u64 multicast), + + TP_ARGS(local, changed_flags, total_flags, multicast), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(unsigned int, changed) + __field(unsigned int, total) + __field(u64, multicast) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->changed = changed_flags; + __entry->total = *total_flags; + __entry->multicast = multicast; + ), + + TP_printk( + LOCAL_PR_FMT " changed:%#x total:%#x", + LOCAL_PR_ARG, __entry->changed, __entry->total + ) +); + +TRACE_EVENT(drv_set_tim, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sta *sta, bool set, int ret), + + TP_ARGS(local, sta, set, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + STA_ENTRY + __field(bool, set) + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + STA_ASSIGN; + __entry->set = set; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT STA_PR_FMT " set:%d ret:%d", + LOCAL_PR_ARG, STA_PR_FMT, __entry->set, __entry->ret + ) +); + +TRACE_EVENT(drv_set_key, + TP_PROTO(struct ieee80211_local *local, + enum set_key_cmd cmd, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key, int ret), + + TP_ARGS(local, cmd, vif, sta, key, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + STA_ENTRY + __field(enum ieee80211_key_alg, alg) + __field(u8, hw_key_idx) + __field(u8, flags) + __field(s8, keyidx) + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + STA_ASSIGN; + __entry->alg = key->alg; + __entry->flags = key->flags; + __entry->keyidx = key->keyidx; + __entry->hw_key_idx = key->hw_key_idx; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " ret:%d", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->ret + ) +); + +TRACE_EVENT(drv_update_tkip_key, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_key_conf *conf, + const u8 *address, u32 iv32), + + TP_ARGS(local, conf, address, iv32), + + TP_STRUCT__entry( + LOCAL_ENTRY + __array(u8, addr, 6) + __field(u32, iv32) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + memcpy(__entry->addr, address, 6); + __entry->iv32 = iv32; + ), + + TP_printk( + LOCAL_PR_FMT " addr:%pM iv32:%#x", + LOCAL_PR_ARG, __entry->addr, __entry->iv32 + ) +); + +TRACE_EVENT(drv_hw_scan, + TP_PROTO(struct ieee80211_local *local, + struct cfg80211_scan_request *req, int ret), + + TP_ARGS(local, req, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT " ret:%d", + LOCAL_PR_ARG, __entry->ret + ) +); + +TRACE_EVENT(drv_sw_scan_start, + TP_PROTO(struct ieee80211_local *local), + + TP_ARGS(local), + + TP_STRUCT__entry( + LOCAL_ENTRY + ), + + TP_fast_assign( + LOCAL_ASSIGN; + ), + + TP_printk( + LOCAL_PR_FMT, LOCAL_PR_ARG + ) +); + +TRACE_EVENT(drv_sw_scan_complete, + TP_PROTO(struct ieee80211_local *local), + + TP_ARGS(local), + + TP_STRUCT__entry( + LOCAL_ENTRY + ), + + TP_fast_assign( + LOCAL_ASSIGN; + ), + + TP_printk( + LOCAL_PR_FMT, LOCAL_PR_ARG + ) +); + +TRACE_EVENT(drv_get_stats, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_low_level_stats *stats, + int ret), + + TP_ARGS(local, stats, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(int, ret) + __field(unsigned int, ackfail) + __field(unsigned int, rtsfail) + __field(unsigned int, fcserr) + __field(unsigned int, rtssucc) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->ret = ret; + __entry->ackfail = stats->dot11ACKFailureCount; + __entry->rtsfail = stats->dot11RTSFailureCount; + __entry->fcserr = stats->dot11FCSErrorCount; + __entry->rtssucc = stats->dot11RTSSuccessCount; + ), + + TP_printk( + LOCAL_PR_FMT " ret:%d", + LOCAL_PR_ARG, __entry->ret + ) +); + +TRACE_EVENT(drv_get_tkip_seq, + TP_PROTO(struct ieee80211_local *local, + u8 hw_key_idx, u32 *iv32, u16 *iv16), + + TP_ARGS(local, hw_key_idx, iv32, iv16), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u8, hw_key_idx) + __field(u32, iv32) + __field(u16, iv16) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->hw_key_idx = hw_key_idx; + __entry->iv32 = *iv32; + __entry->iv16 = *iv16; + ), + + TP_printk( + LOCAL_PR_FMT, LOCAL_PR_ARG + ) +); + +TRACE_EVENT(drv_set_rts_threshold, + TP_PROTO(struct ieee80211_local *local, u32 value, int ret), + + TP_ARGS(local, value, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u32, value) + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->ret = ret; + __entry->value = value; + ), + + TP_printk( + LOCAL_PR_FMT " value:%d ret:%d", + LOCAL_PR_ARG, __entry->value, __entry->ret + ) +); + +TRACE_EVENT(drv_sta_notify, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_vif *vif, + enum sta_notify_cmd cmd, + struct ieee80211_sta *sta), + + TP_ARGS(local, vif, cmd, sta), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + STA_ENTRY + __field(u32, cmd) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + STA_ASSIGN; + __entry->cmd = cmd; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " cmd:%d", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->cmd + ) +); + +TRACE_EVENT(drv_conf_tx, + TP_PROTO(struct ieee80211_local *local, u16 queue, + const struct ieee80211_tx_queue_params *params, + int ret), + + TP_ARGS(local, queue, params, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u16, queue) + __field(u16, txop) + __field(u16, cw_min) + __field(u16, cw_max) + __field(u8, aifs) + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->queue = queue; + __entry->ret = ret; + __entry->txop = params->txop; + __entry->cw_max = params->cw_max; + __entry->cw_min = params->cw_min; + __entry->aifs = params->aifs; + ), + + TP_printk( + LOCAL_PR_FMT " queue:%d ret:%d", + LOCAL_PR_ARG, __entry->queue, __entry->ret + ) +); + +TRACE_EVENT(drv_get_tx_stats, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_tx_queue_stats *stats, + int ret), + + TP_ARGS(local, stats, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT " ret:%d", + LOCAL_PR_ARG, __entry->ret + ) +); + +TRACE_EVENT(drv_get_tsf, + TP_PROTO(struct ieee80211_local *local, u64 ret), + + TP_ARGS(local, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u64, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT " ret:%llu", + LOCAL_PR_ARG, (unsigned long long)__entry->ret + ) +); + +TRACE_EVENT(drv_set_tsf, + TP_PROTO(struct ieee80211_local *local, u64 tsf), + + TP_ARGS(local, tsf), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u64, tsf) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->tsf = tsf; + ), + + TP_printk( + LOCAL_PR_FMT " tsf:%llu", + LOCAL_PR_ARG, (unsigned long long)__entry->tsf + ) +); + +TRACE_EVENT(drv_reset_tsf, + TP_PROTO(struct ieee80211_local *local), + + TP_ARGS(local), + + TP_STRUCT__entry( + LOCAL_ENTRY + ), + + TP_fast_assign( + LOCAL_ASSIGN; + ), + + TP_printk( + LOCAL_PR_FMT, LOCAL_PR_ARG + ) +); + +TRACE_EVENT(drv_tx_last_beacon, + TP_PROTO(struct ieee80211_local *local, int ret), + + TP_ARGS(local, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->ret = ret; + ), + + TP_printk( + LOCAL_PR_FMT " ret:%d", + LOCAL_PR_ARG, __entry->ret + ) +); + +TRACE_EVENT(drv_ampdu_action, + TP_PROTO(struct ieee80211_local *local, + enum ieee80211_ampdu_mlme_action action, + struct ieee80211_sta *sta, u16 tid, + u16 *ssn, int ret), + + TP_ARGS(local, action, sta, tid, ssn, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + STA_ENTRY + __field(u32, action) + __field(u16, tid) + __field(u16, ssn) + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + STA_ASSIGN; + __entry->ret = ret; + __entry->action = action; + __entry->tid = tid; + __entry->ssn = *ssn; + ), + + TP_printk( + LOCAL_PR_FMT STA_PR_FMT " action:%d tid:%d ret:%d", + LOCAL_PR_ARG, STA_PR_ARG, __entry->action, __entry->tid, __entry->ret + ) +); +#endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE driver-trace +#include <trace/define_trace.h> diff --git a/net/mac80211/event.c b/net/mac80211/event.c index f288d01a634..01ae759518f 100644 --- a/net/mac80211/event.c +++ b/net/mac80211/event.c @@ -7,8 +7,7 @@ * * mac80211 - events */ - -#include <net/iw_handler.h> +#include <net/cfg80211.h> #include "ieee80211_i.h" /* @@ -17,26 +16,12 @@ * driver or is still in the frame), it should provide that information. */ void mac80211_ev_michael_mic_failure(struct ieee80211_sub_if_data *sdata, int keyidx, - struct ieee80211_hdr *hdr, const u8 *tsc) + struct ieee80211_hdr *hdr, const u8 *tsc, + gfp_t gfp) { - union iwreq_data wrqu; - char *buf = kmalloc(128, GFP_ATOMIC); - - if (buf) { - /* TODO: needed parameters: count, key type, TSC */ - sprintf(buf, "MLME-MICHAELMICFAILURE.indication(" - "keyid=%d %scast addr=%pM)", - keyidx, hdr->addr1[0] & 0x01 ? "broad" : "uni", - hdr->addr2); - memset(&wrqu, 0, sizeof(wrqu)); - wrqu.data.length = strlen(buf); - wireless_send_event(sdata->dev, IWEVCUSTOM, &wrqu, buf); - kfree(buf); - } - cfg80211_michael_mic_failure(sdata->dev, hdr->addr2, (hdr->addr1[0] & 0x01) ? NL80211_KEYTYPE_GROUP : NL80211_KEYTYPE_PAIRWISE, - keyidx, tsc); + keyidx, tsc, gfp); } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 0891bfb0699..cdc58e61d92 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -141,7 +141,6 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_mgmt *mgmt, size_t len) { - struct ieee80211_local *local = sdata->local; u16 tid, params; u16 initiator; @@ -153,7 +152,7 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, if (net_ratelimit()) printk(KERN_DEBUG "delba from %pM (%s) tid %d reason code %d\n", mgmt->sa, initiator ? "initiator" : "recipient", tid, - mgmt->u.action.u.delba.reason_code); + le16_to_cpu(mgmt->u.action.u.delba.reason_code)); #endif /* CONFIG_MAC80211_HT_DEBUG */ if (initiator == WLAN_BACK_INITIATOR) @@ -161,10 +160,9 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, WLAN_BACK_INITIATOR, 0); else { /* WLAN_BACK_RECIPIENT */ spin_lock_bh(&sta->lock); - sta->ampdu_mlme.tid_state_tx[tid] = - HT_AGG_STATE_OPERATIONAL; + if (sta->ampdu_mlme.tid_state_tx[tid] & HT_ADDBA_REQUESTED_MSK) + ___ieee80211_stop_tx_ba_session(sta, tid, + WLAN_BACK_RECIPIENT); spin_unlock_bh(&sta->lock); - ieee80211_stop_tx_ba_session(&local->hw, sta->sta.addr, tid, - WLAN_BACK_RECIPIENT); } } diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 0b30277eb36..f1362f32c17 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -57,7 +57,7 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, */ if (auth_alg == WLAN_AUTH_OPEN && auth_transaction == 1) ieee80211_send_auth(sdata, 2, WLAN_AUTH_OPEN, NULL, 0, - sdata->u.ibss.bssid, 0); + sdata->u.ibss.bssid, NULL, 0, 0); } static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, @@ -73,6 +73,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt; u8 *pos; struct ieee80211_supported_band *sband; + struct cfg80211_bss *bss; u32 bss_change; u8 supp_rates[IEEE80211_MAX_SUPP_RATES]; @@ -177,8 +178,9 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, mod_timer(&ifibss->timer, round_jiffies(jiffies + IEEE80211_IBSS_MERGE_INTERVAL)); - cfg80211_inform_bss_frame(local->hw.wiphy, local->hw.conf.channel, - mgmt, skb->len, 0, GFP_KERNEL); + bss = cfg80211_inform_bss_frame(local->hw.wiphy, local->hw.conf.channel, + mgmt, skb->len, 0, GFP_KERNEL); + cfg80211_put_bss(bss); cfg80211_ibss_joined(sdata->dev, ifibss->bssid, GFP_KERNEL); } @@ -494,7 +496,7 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) capability = WLAN_CAPABILITY_IBSS; - if (sdata->default_key) + if (ifibss->privacy) capability |= WLAN_CAPABILITY_PRIVACY; else sdata->drop_unencrypted = 0; @@ -524,9 +526,8 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) return; capability = WLAN_CAPABILITY_IBSS; - if (sdata->default_key) + if (ifibss->privacy) capability |= WLAN_CAPABILITY_PRIVACY; - if (ifibss->fixed_bssid) bssid = ifibss->bssid; if (ifibss->fixed_channel) @@ -539,13 +540,12 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) WLAN_CAPABILITY_PRIVACY, capability); + if (bss) { #ifdef CONFIG_MAC80211_IBSS_DEBUG - if (bss) printk(KERN_DEBUG " sta_find_ibss: selected %pM current " "%pM\n", bss->cbss.bssid, ifibss->bssid); #endif /* CONFIG_MAC80211_IBSS_DEBUG */ - if (bss && memcmp(ifibss->bssid, bss->cbss.bssid, ETH_ALEN)) { printk(KERN_DEBUG "%s: Selected IBSS BSSID %pM" " based on configured SSID\n", sdata->dev->name, bss->cbss.bssid); @@ -553,8 +553,7 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) ieee80211_sta_join_ibss(sdata, bss); ieee80211_rx_bss_put(local, bss); return; - } else if (bss) - ieee80211_rx_bss_put(local, bss); + } #ifdef CONFIG_MAC80211_IBSS_DEBUG printk(KERN_DEBUG " did not try to join ibss\n"); @@ -705,7 +704,7 @@ static void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt; u16 fc; - rx_status = (struct ieee80211_rx_status *) skb->cb; + rx_status = IEEE80211_SKB_RXCB(skb); mgmt = (struct ieee80211_mgmt *) skb->data; fc = le16_to_cpu(mgmt->frame_control); @@ -743,7 +742,7 @@ static void ieee80211_ibss_work(struct work_struct *work) if (!netif_running(sdata->dev)) return; - if (local->sw_scanning || local->hw_scanning) + if (local->scanning) return; if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_ADHOC)) @@ -782,7 +781,7 @@ static void ieee80211_ibss_timer(unsigned long data) } set_bit(IEEE80211_IBSS_REQ_RUN, &ifibss->request); - queue_work(local->hw.workqueue, &ifibss->work); + ieee80211_queue_work(&local->hw, &ifibss->work); } #ifdef CONFIG_PM @@ -830,14 +829,13 @@ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local) if (!sdata->u.ibss.ssid_len) continue; sdata->u.ibss.last_scan_completed = jiffies; - ieee80211_sta_find_ibss(sdata); + mod_timer(&sdata->u.ibss.timer, 0); } mutex_unlock(&local->iflist_mtx); } ieee80211_rx_result -ieee80211_ibss_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - struct ieee80211_rx_status *rx_status) +ieee80211_ibss_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee80211_mgmt *mgmt; @@ -852,11 +850,10 @@ ieee80211_ibss_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, switch (fc & IEEE80211_FCTL_STYPE) { case IEEE80211_STYPE_PROBE_RESP: case IEEE80211_STYPE_BEACON: - memcpy(skb->cb, rx_status, sizeof(*rx_status)); case IEEE80211_STYPE_PROBE_REQ: case IEEE80211_STYPE_AUTH: skb_queue_tail(&sdata->u.ibss.skb_queue, skb); - queue_work(local->hw.workqueue, &sdata->u.ibss.work); + ieee80211_queue_work(&local->hw, &sdata->u.ibss.work); return RX_QUEUED; } @@ -874,6 +871,8 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, } else sdata->u.ibss.fixed_bssid = false; + sdata->u.ibss.privacy = params->privacy; + sdata->vif.bss_conf.beacon_int = params->beacon_interval; sdata->u.ibss.channel = params->channel; @@ -913,7 +912,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_idle(sdata->local); set_bit(IEEE80211_IBSS_REQ_RUN, &sdata->u.ibss.request); - queue_work(sdata->local->hw.workqueue, &sdata->u.ibss.work); + ieee80211_queue_work(&sdata->local->hw, &sdata->u.ibss.work); return 0; } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 68eb5052179..10d316e455d 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -24,7 +24,6 @@ #include <linux/spinlock.h> #include <linux/etherdevice.h> #include <net/cfg80211.h> -#include <net/iw_handler.h> #include <net/mac80211.h> #include "key.h" #include "sta_info.h" @@ -213,7 +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; @@ -227,86 +228,81 @@ struct mesh_preq_queue { u8 flags; }; +enum ieee80211_mgd_state { + IEEE80211_MGD_STATE_IDLE, + IEEE80211_MGD_STATE_PROBE, + IEEE80211_MGD_STATE_AUTH, + IEEE80211_MGD_STATE_ASSOC, +}; + +struct ieee80211_mgd_work { + struct list_head list; + struct ieee80211_bss *bss; + int ie_len; + u8 prev_bssid[ETH_ALEN]; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + unsigned long timeout; + enum ieee80211_mgd_state state; + u16 auth_alg, auth_transaction; + + int tries; + + u8 key[WLAN_KEY_LEN_WEP104]; + u8 key_len, key_idx; + + /* must be last */ + u8 ie[0]; /* for auth or assoc frame, not probe */ +}; + /* flags used in struct ieee80211_if_managed.flags */ -#define IEEE80211_STA_SSID_SET BIT(0) -#define IEEE80211_STA_BSSID_SET BIT(1) -#define IEEE80211_STA_PREV_BSSID_SET BIT(2) -#define IEEE80211_STA_AUTHENTICATED BIT(3) -#define IEEE80211_STA_ASSOCIATED BIT(4) -#define IEEE80211_STA_PROBEREQ_POLL BIT(5) -#define IEEE80211_STA_CREATE_IBSS BIT(6) -#define IEEE80211_STA_CONTROL_PORT BIT(7) -#define IEEE80211_STA_WMM_ENABLED BIT(8) -/* hole at 9, please re-use */ -#define IEEE80211_STA_AUTO_SSID_SEL BIT(10) -#define IEEE80211_STA_AUTO_BSSID_SEL BIT(11) -#define IEEE80211_STA_AUTO_CHANNEL_SEL BIT(12) -#define IEEE80211_STA_PRIVACY_INVOKED BIT(13) -#define IEEE80211_STA_TKIP_WEP_USED BIT(14) -#define IEEE80211_STA_CSA_RECEIVED BIT(15) -#define IEEE80211_STA_MFP_ENABLED BIT(16) -#define IEEE80211_STA_EXT_SME BIT(17) -/* flags for MLME request */ -#define IEEE80211_STA_REQ_SCAN 0 -#define IEEE80211_STA_REQ_AUTH 1 -#define IEEE80211_STA_REQ_RUN 2 +enum ieee80211_sta_flags { + IEEE80211_STA_BEACON_POLL = BIT(0), + IEEE80211_STA_CONNECTION_POLL = BIT(1), + IEEE80211_STA_CONTROL_PORT = BIT(2), + IEEE80211_STA_WMM_ENABLED = BIT(3), + IEEE80211_STA_DISABLE_11N = BIT(4), + IEEE80211_STA_CSA_RECEIVED = BIT(5), + IEEE80211_STA_MFP_ENABLED = BIT(6), +}; -/* bitfield of allowed auth algs */ -#define IEEE80211_AUTH_ALG_OPEN BIT(0) -#define IEEE80211_AUTH_ALG_SHARED_KEY BIT(1) -#define IEEE80211_AUTH_ALG_LEAP BIT(2) -#define IEEE80211_AUTH_ALG_FT BIT(3) +/* flags for MLME request */ +enum ieee80211_sta_request { + IEEE80211_STA_REQ_SCAN, +}; struct ieee80211_if_managed { struct timer_list timer; + struct timer_list conn_mon_timer; + struct timer_list bcn_mon_timer; struct timer_list chswitch_timer; struct work_struct work; + struct work_struct monitor_work; struct work_struct chswitch_work; struct work_struct beacon_loss_work; - u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; + unsigned long probe_timeout; + int probe_send_count; - u8 ssid[IEEE80211_MAX_SSID_LEN]; - size_t ssid_len; + struct mutex mtx; + struct ieee80211_bss *associated; + struct ieee80211_mgd_work *old_associate_work; + struct list_head work_list; - enum { - IEEE80211_STA_MLME_DISABLED, - IEEE80211_STA_MLME_DIRECT_PROBE, - IEEE80211_STA_MLME_AUTHENTICATE, - IEEE80211_STA_MLME_ASSOCIATE, - IEEE80211_STA_MLME_ASSOCIATED, - } state; + u8 bssid[ETH_ALEN]; u16 aid; - u16 ap_capab, capab; - u8 *extra_ie; /* to be added to the end of AssocReq */ - size_t extra_ie_len; - - /* The last AssocReq/Resp IEs */ - u8 *assocreq_ies, *assocresp_ies; - size_t assocreq_ies_len, assocresp_ies_len; + u16 capab; struct sk_buff_head skb_queue; - int assoc_scan_tries; /* number of scans done pre-association */ - int direct_probe_tries; /* retries for direct probes */ - int auth_tries; /* retries for auth req */ - int assoc_tries; /* retries for assoc req */ - unsigned long timers_running; /* used for quiesce/restart */ bool powersave; /* powersave requested for this iface */ unsigned long request; - unsigned long last_probe; - unsigned long last_beacon; - unsigned int flags; - unsigned int auth_algs; /* bitfield of allowed auth algs */ - int auth_alg; /* currently used IEEE 802.11 authentication algorithm */ - int auth_transaction; - u32 beacon_crc; enum { @@ -316,10 +312,6 @@ struct ieee80211_if_managed { } mfp; /* management frame protection */ int wmm_last_param_set; - - /* Extra IE data for management frames */ - u8 *sme_auth_ie; - size_t sme_auth_ie_len; }; enum ieee80211_ibss_request { @@ -339,6 +331,7 @@ struct ieee80211_if_ibss { bool fixed_bssid; bool fixed_channel; + bool privacy; u8 bssid[ETH_ALEN]; u8 ssid[IEEE80211_MAX_SSID_LEN]; @@ -364,7 +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; @@ -374,6 +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 */ @@ -478,20 +475,9 @@ struct ieee80211_sub_if_data { union { struct { struct dentry *drop_unencrypted; - struct dentry *state; struct dentry *bssid; - struct dentry *prev_bssid; - struct dentry *ssid_len; struct dentry *aid; - struct dentry *ap_capab; struct dentry *capab; - struct dentry *extra_ie_len; - struct dentry *auth_tries; - struct dentry *assoc_tries; - struct dentry *auth_algs; - struct dentry *auth_alg; - struct dentry *auth_transaction; - struct dentry *flags; struct dentry *force_unicast_rateidx; struct dentry *max_ratectrl_rateidx; } sta; @@ -526,6 +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; @@ -588,12 +576,44 @@ enum queue_stop_reason { IEEE80211_QUEUE_STOP_REASON_CSA, IEEE80211_QUEUE_STOP_REASON_AGGREGATION, IEEE80211_QUEUE_STOP_REASON_SUSPEND, - IEEE80211_QUEUE_STOP_REASON_PENDING, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, }; -struct ieee80211_master_priv { - struct ieee80211_local *local; +/** + * mac80211 scan flags - currently active scan mode + * + * @SCAN_SW_SCANNING: We're currently in the process of scanning but may as + * well be on the operating channel + * @SCAN_HW_SCANNING: The hardware is scanning for us, we have no way to + * determine if we are on the operating channel or not + * @SCAN_OFF_CHANNEL: We're off our operating channel for scanning, + * gets only set in conjunction with SCAN_SW_SCANNING + */ +enum { + SCAN_SW_SCANNING, + SCAN_HW_SCANNING, + SCAN_OFF_CHANNEL, +}; + +/** + * enum mac80211_scan_state - scan state machine states + * + * @SCAN_DECISION: Main entry point to the scan state machine, this state + * determines if we should keep on scanning or switch back to the + * operating channel + * @SCAN_SET_CHANNEL: Set the next channel to be scanned + * @SCAN_SEND_PROBE: Send probe requests and wait for probe responses + * @SCAN_LEAVE_OPER_CHANNEL: Leave the operating channel, notify the AP + * about us leaving the channel and stop all associated STA interfaces + * @SCAN_ENTER_OPER_CHANNEL: Enter the operating channel again, notify the + * AP about us being back and restart all associated STA interfaces + */ +enum mac80211_scan_state { + SCAN_DECISION, + SCAN_SET_CHANNEL, + SCAN_SEND_PROBE, + SCAN_LEAVE_OPER_CHANNEL, + SCAN_ENTER_OPER_CHANNEL, }; struct ieee80211_local { @@ -604,17 +624,33 @@ struct ieee80211_local { const struct ieee80211_ops *ops; + /* + * private workqueue to mac80211. mac80211 makes this accessible + * via ieee80211_queue_work() + */ + struct workqueue_struct *workqueue; + unsigned long queue_stop_reasons[IEEE80211_MAX_QUEUES]; /* also used to protect ampdu_ac_queue and amdpu_ac_stop_refcnt */ spinlock_t queue_stop_reason_lock; - struct net_device *mdev; /* wmaster# - "master" 802.11 device */ int open_count; int monitors, cooked_mntrs; /* number of interfaces with corresponding FIF_ flags */ - int fif_fcsfail, fif_plcpfail, fif_control, fif_other_bss; + int fif_fcsfail, fif_plcpfail, fif_control, fif_other_bss, fif_pspoll; unsigned int filter_flags; /* FIF_* */ struct iw_statistics wstats; + + /* 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; + bool tim_in_locked_section; /* see ieee80211_beacon_get() */ /* @@ -626,11 +662,22 @@ struct ieee80211_local { bool suspended; /* + * Resuming is true while suspended, but when we're reprogramming the + * hardware -- at that time it's allowed to use ieee80211_queue_work() + * again even though some other parts of the stack are still suspended + * and we still drop received frames to avoid waking the stack. + */ + bool resuming; + + /* * quiescing is true during the suspend process _only_ to * ease timer cancelling etc. */ 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 @@ -653,6 +700,7 @@ 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; @@ -687,9 +735,9 @@ struct ieee80211_local { /* Scanning and BSS list */ struct mutex scan_mtx; - bool sw_scanning, hw_scanning; + 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; @@ -697,7 +745,7 @@ struct ieee80211_local { int scan_channel_idx; int scan_ies_len; - enum { SCAN_SET_CHANNEL, SCAN_SEND_PROBE } scan_state; + enum mac80211_scan_state next_scan_state; struct delayed_work scan_work; struct ieee80211_sub_if_data *scan_sdata; enum nl80211_channel_type oper_channel_type; @@ -834,10 +882,6 @@ struct ieee80211_local { static inline struct ieee80211_sub_if_data * IEEE80211_DEV_TO_SUB_IF(struct net_device *dev) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - - BUG_ON(!local || local->mdev == dev); - return netdev_priv(dev); } @@ -937,21 +981,20 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, void ieee80211_configure_filter(struct ieee80211_local *local); u32 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata); -/* wireless extensions */ -extern const struct iw_handler_def ieee80211_iw_handler_def; - /* STA code */ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata); +int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, + struct cfg80211_auth_request *req); +int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, + struct cfg80211_assoc_request *req); +int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, + struct cfg80211_deauth_request *req, + void *cookie); +int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, + struct cfg80211_disassoc_request *req, + void *cookie); ieee80211_rx_result ieee80211_sta_rx_mgmt(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, - struct ieee80211_rx_status *rx_status); -int ieee80211_sta_commit(struct ieee80211_sub_if_data *sdata); -int ieee80211_sta_set_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size_t len); -int ieee80211_sta_get_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size_t *len); -int ieee80211_sta_set_bssid(struct ieee80211_sub_if_data *sdata, u8 *bssid); -void ieee80211_sta_req_auth(struct ieee80211_sub_if_data *sdata); -int ieee80211_sta_deauthenticate(struct ieee80211_sub_if_data *sdata, u16 reason); -int ieee80211_sta_disassociate(struct ieee80211_sub_if_data *sdata, u16 reason); + struct sk_buff *skb); void ieee80211_send_pspoll(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency); @@ -967,8 +1010,7 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata); void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local); void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata); ieee80211_rx_result -ieee80211_ibss_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - struct ieee80211_rx_status *rx_status); +ieee80211_ibss_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); struct sta_info *ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, u8 *bssid, u8 *addr, u32 supp_rates); int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, @@ -983,16 +1025,9 @@ int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, const u8 *ssid, u8 ssid_len); int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req); -int ieee80211_scan_results(struct ieee80211_local *local, - struct iw_request_info *info, - char *buf, size_t len); void ieee80211_scan_cancel(struct ieee80211_local *local); ieee80211_rx_result -ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, - struct ieee80211_rx_status *rx_status); -int ieee80211_sta_set_extra_ie(struct ieee80211_sub_if_data *sdata, - const char *ie, size_t len); +ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local); struct ieee80211_bss * @@ -1008,8 +1043,6 @@ ieee80211_rx_bss_get(struct ieee80211_local *local, u8 *bssid, int freq, u8 *ssid, u8 ssid_len); void ieee80211_rx_bss_put(struct ieee80211_local *local, struct ieee80211_bss *bss); -void ieee80211_rx_bss_remove(struct ieee80211_sub_if_data *sdata, u8 *bssid, - int freq, u8 *ssid, u8 ssid_len); /* interface handling */ int ieee80211_if_add(struct ieee80211_local *local, const char *name, @@ -1025,9 +1058,10 @@ 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_master_start_xmit(struct sk_buff *skb, struct net_device *dev); -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, @@ -1057,6 +1091,8 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_back_parties initiator); +int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, + enum ieee80211_back_parties initiator); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, @@ -1065,6 +1101,7 @@ 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); @@ -1092,7 +1129,8 @@ u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, int ieee80211_frame_duration(struct ieee80211_local *local, size_t len, int rate, int erp, int short_preamble); void mac80211_ev_michael_mic_failure(struct ieee80211_sub_if_data *sdata, int keyidx, - struct ieee80211_hdr *hdr, const u8 *tsc); + struct ieee80211_hdr *hdr, const u8 *tsc, + gfp_t gfp); void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata); void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int encrypt); @@ -1129,8 +1167,8 @@ int ieee80211_add_pending_skbs(struct ieee80211_local *local, void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, - u8 *extra, size_t extra_len, - const u8 *bssid, int encrypt); + u8 *extra, size_t extra_len, const u8 *bssid, + const u8 *key, u8 key_len, u8 key_idx); int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, const u8 *ie, size_t ie_len); void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b7c8a448429..b8295cbd7e8 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -190,10 +190,6 @@ static int ieee80211_open(struct net_device *dev) ETH_ALEN); } - if (compare_ether_addr(null_addr, local->mdev->dev_addr) == 0) - memcpy(local->mdev->dev_addr, local->hw.wiphy->perm_addr, - ETH_ALEN); - /* * Validate the MAC address for this device. */ @@ -224,18 +220,15 @@ static int ieee80211_open(struct net_device *dev) local->fif_fcsfail++; if (sdata->u.mntr_flags & MONITOR_FLAG_PLCPFAIL) local->fif_plcpfail++; - if (sdata->u.mntr_flags & MONITOR_FLAG_CONTROL) + if (sdata->u.mntr_flags & MONITOR_FLAG_CONTROL) { local->fif_control++; + local->fif_pspoll++; + } if (sdata->u.mntr_flags & MONITOR_FLAG_OTHER_BSS) local->fif_other_bss++; - netif_addr_lock_bh(local->mdev); ieee80211_configure_filter(local); - netif_addr_unlock_bh(local->mdev); break; - case NL80211_IFTYPE_STATION: - sdata->u.mgd.flags &= ~IEEE80211_STA_PREV_BSSID_SET; - /* fall through */ default: conf.vif = &sdata->vif; conf.type = sdata->vif.type; @@ -246,12 +239,15 @@ static int ieee80211_open(struct net_device *dev) if (ieee80211_vif_is_mesh(&sdata->vif)) { local->fif_other_bss++; - netif_addr_lock_bh(local->mdev); ieee80211_configure_filter(local); - netif_addr_unlock_bh(local->mdev); ieee80211_start_mesh(sdata); + } else if (sdata->vif.type == NL80211_IFTYPE_AP) { + local->fif_pspoll++; + + ieee80211_configure_filter(local); } + changed |= ieee80211_reset_erp_info(sdata); ieee80211_bss_info_change_notify(sdata, changed); ieee80211_enable_keys(sdata); @@ -281,15 +277,6 @@ static int ieee80211_open(struct net_device *dev) } } - if (local->open_count == 0) { - res = dev_open(local->mdev); - WARN_ON(res); - if (res) - goto err_del_interface; - 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 @@ -323,7 +310,7 @@ static int ieee80211_open(struct net_device *dev) * to fix this. */ if (sdata->vif.type == NL80211_IFTYPE_STATION) - queue_work(local->hw.workqueue, &sdata->u.mgd.work); + ieee80211_queue_work(&local->hw, &sdata->u.mgd.work); netif_tx_start_all_queues(dev); @@ -346,7 +333,10 @@ static int ieee80211_stop(struct net_device *dev) struct ieee80211_local *local = sdata->local; struct ieee80211_if_init_conf conf; struct sta_info *sta; + unsigned long flags; + struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; + int i; /* * Stop TX on this interface first. @@ -366,18 +356,6 @@ static int ieee80211_stop(struct net_device *dev) rcu_read_unlock(); /* - * Announce that we are leaving the network, in case we are a - * station interface type. This must be done before removing - * all stations associated with sta_info_flush, otherwise STA - * information will be gone and no announce being done. - */ - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - if (sdata->u.mgd.state != IEEE80211_STA_MLME_DISABLED) - ieee80211_sta_deauthenticate(sdata, - WLAN_REASON_DEAUTH_LEAVING); - } - - /* * Remove all stations associated with this interface. * * This must be done before calling ops->remove_interface() @@ -408,13 +386,24 @@ static int ieee80211_stop(struct net_device *dev) if (sdata->flags & IEEE80211_SDATA_PROMISC) atomic_dec(&local->iff_promiscs); - dev_mc_unsync(local->mdev, dev); + if (sdata->vif.type == NL80211_IFTYPE_AP) + local->fif_pspoll--; + + netif_addr_lock_bh(dev); + spin_lock_bh(&local->filter_lock); + __dev_addr_unsync(&local->mc_list, &local->mc_count, + &dev->mc_list, &dev->mc_count); + 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); /* APs need special treatment */ if (sdata->vif.type == NL80211_IFTYPE_AP) { - struct ieee80211_sub_if_data *vlan, *tmp; + struct ieee80211_sub_if_data *vlan, *tmpsdata; struct beacon_data *old_beacon = sdata->u.ap.beacon; /* remove beacon */ @@ -423,7 +412,7 @@ static int ieee80211_stop(struct net_device *dev) kfree(old_beacon); /* down all dependent devices, that is VLANs */ - list_for_each_entry_safe(vlan, tmp, &sdata->u.ap.vlans, + list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, u.vlan.list) dev_close(vlan->dev); WARN_ON(!list_empty(&sdata->u.ap.vlans)); @@ -452,29 +441,30 @@ static int ieee80211_stop(struct net_device *dev) local->fif_fcsfail--; if (sdata->u.mntr_flags & MONITOR_FLAG_PLCPFAIL) local->fif_plcpfail--; - if (sdata->u.mntr_flags & MONITOR_FLAG_CONTROL) + if (sdata->u.mntr_flags & MONITOR_FLAG_CONTROL) { + local->fif_pspoll--; local->fif_control--; + } if (sdata->u.mntr_flags & MONITOR_FLAG_OTHER_BSS) local->fif_other_bss--; - netif_addr_lock_bh(local->mdev); ieee80211_configure_filter(local); - netif_addr_unlock_bh(local->mdev); break; case NL80211_IFTYPE_STATION: - memset(sdata->u.mgd.bssid, 0, ETH_ALEN); del_timer_sync(&sdata->u.mgd.chswitch_timer); del_timer_sync(&sdata->u.mgd.timer); + del_timer_sync(&sdata->u.mgd.conn_mon_timer); + del_timer_sync(&sdata->u.mgd.bcn_mon_timer); /* - * If the timer fired while we waited for it, it will have - * requeued the work. Now the work will be running again + * If any of the timers fired while we waited for it, it will + * have queued its work. Now the work will be running again * but will not rearm the timer again because it checks * whether the interface is running, which, at this point, * it no longer is. */ cancel_work_sync(&sdata->u.mgd.work); cancel_work_sync(&sdata->u.mgd.chswitch_work); - + cancel_work_sync(&sdata->u.mgd.monitor_work); cancel_work_sync(&sdata->u.mgd.beacon_loss_work); /* @@ -485,12 +475,6 @@ static int ieee80211_stop(struct net_device *dev) */ synchronize_rcu(); skb_queue_purge(&sdata->u.mgd.skb_queue); - - sdata->u.mgd.flags &= ~(IEEE80211_STA_PRIVACY_INVOKED | - IEEE80211_STA_TKIP_WEP_USED); - kfree(sdata->u.mgd.extra_ie); - sdata->u.mgd.extra_ie = NULL; - sdata->u.mgd.extra_ie_len = 0; /* fall through */ case NL80211_IFTYPE_ADHOC: if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { @@ -507,37 +491,23 @@ static int ieee80211_stop(struct net_device *dev) local->fif_other_bss--; atomic_dec(&local->iff_allmultis); - netif_addr_lock_bh(local->mdev); ieee80211_configure_filter(local); - netif_addr_unlock_bh(local->mdev); 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 (local->sw_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 + * still be joined to a network at this point. + */ + if (sdata->vif.type == NL80211_IFTYPE_AP || + sdata->vif.type == NL80211_IFTYPE_MESH_POINT) { + ieee80211_bss_info_change_notify(sdata, + BSS_CHANGED_BEACON_ENABLED); } conf.vif = &sdata->vif; @@ -555,17 +525,8 @@ static int ieee80211_stop(struct net_device *dev) ieee80211_recalc_ps(local, -1); if (local->open_count == 0) { - if (netif_running(local->mdev)) - dev_close(local->mdev); - - drv_stop(local); - - ieee80211_led_radio(local, false); - - flush_workqueue(local->hw.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; @@ -575,6 +536,18 @@ static int ieee80211_stop(struct net_device *dev) if (hw_reconf_flags) ieee80211_hw_config(local, hw_reconf_flags); + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + for (i = 0; i < IEEE80211_MAX_QUEUES; i++) { + skb_queue_walk_safe(&local->pending[i], skb, tmp) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + if (info->control.vif == &sdata->vif) { + __skb_unlink(skb, &local->pending[i]); + dev_kfree_skb_irq(skb); + } + } + } + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + return 0; } @@ -604,8 +577,11 @@ static void ieee80211_set_multicast_list(struct net_device *dev) atomic_dec(&local->iff_promiscs); sdata->flags ^= IEEE80211_SDATA_PROMISC; } - - dev_mc_sync(local->mdev, dev); + spin_lock_bh(&local->filter_lock); + __dev_addr_sync(&local->mc_list, &local->mc_count, + &dev->mc_list, &dev->mc_count); + spin_unlock_bh(&local->filter_lock); + ieee80211_queue_work(&local->hw, &local->reconfig_filter); } /* @@ -652,11 +628,6 @@ static void ieee80211_teardown_sdata(struct net_device *dev) kfree_skb(sdata->u.ibss.presp); break; case NL80211_IFTYPE_STATION: - kfree(sdata->u.mgd.extra_ie); - kfree(sdata->u.mgd.assocreq_ies); - kfree(sdata->u.mgd.assocresp_ies); - kfree(sdata->u.mgd.sme_auth_ie); - break; case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: @@ -695,7 +666,6 @@ static void ieee80211_if_setup(struct net_device *dev) { ether_setup(dev); dev->netdev_ops = &ieee80211_dataif_ops; - dev->wireless_handlers = &ieee80211_iw_handler_def; dev->destructor = free_netdev; } @@ -784,6 +754,10 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, return 0; } +static struct device_type wiphy_type = { + .name = "wlan", +}; + int ieee80211_if_add(struct ieee80211_local *local, const char *name, struct net_device **new_dev, enum nl80211_iftype type, struct vif_params *params) @@ -798,6 +772,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, name, ieee80211_if_setup); if (!ndev) return -ENOMEM; + dev_net_set(ndev, wiphy_net(local->hw.wiphy)); ndev->needed_headroom = local->tx_headroom + 4*6 /* four MAC addresses */ @@ -814,7 +789,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, memcpy(ndev->dev_addr, local->hw.wiphy->perm_addr, ETH_ALEN); SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy)); - ndev->features |= NETIF_F_NETNS_LOCAL; + SET_NETDEV_DEVTYPE(ndev, &wiphy_type); /* don't use IEEE80211_DEV_TO_SUB_IF because it checks too much */ sdata = netdev_priv(ndev); @@ -931,7 +906,7 @@ u32 __ieee80211_recalc_idle(struct ieee80211_local *local) struct ieee80211_sub_if_data *sdata; int count = 0; - if (local->hw_scanning || local->sw_scanning) + if (local->scanning) return ieee80211_idle_off(local, "scanning"); list_for_each_entry(sdata, &local->interfaces, list) { @@ -939,7 +914,8 @@ u32 __ieee80211_recalc_idle(struct ieee80211_local *local) continue; /* do not count disabled managed interfaces */ if (sdata->vif.type == NL80211_IFTYPE_STATION && - sdata->u.mgd.state == IEEE80211_STA_MLME_DISABLED) + !sdata->u.mgd.associated && + list_empty(&sdata->u.mgd.work_list)) continue; /* do not count unused IBSS interfaces */ if (sdata->vif.type == NL80211_IFTYPE_ADHOC && diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 092a017b237..797f53942e5 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) @@ -77,77 +77,29 @@ void ieee80211_configure_filter(struct ieee80211_local *local) if (local->fif_other_bss) new_flags |= FIF_OTHER_BSS; + 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->mdev->mc_count, - local->mdev->mc_list); + drv_configure_filter(local, changed_flags, &new_flags, mc); WARN_ON(new_flags & (1<<31)); local->filter_flags = new_flags & ~(1<<31); } -/* master interface */ - -static int header_parse_80211(const struct sk_buff *skb, unsigned char *haddr) -{ - memcpy(haddr, skb_mac_header(skb) + 10, ETH_ALEN); /* addr2 */ - return ETH_ALEN; -} - -static const struct header_ops ieee80211_header_ops = { - .create = eth_header, - .parse = header_parse_80211, - .rebuild = eth_rebuild_header, - .cache = eth_header_cache, - .cache_update = eth_header_cache_update, -}; - -static int ieee80211_master_open(struct net_device *dev) +static void ieee80211_reconfig_filter(struct work_struct *work) { - struct ieee80211_master_priv *mpriv = netdev_priv(dev); - struct ieee80211_local *local = mpriv->local; - struct ieee80211_sub_if_data *sdata; - int res = -EOPNOTSUPP; - - /* we hold the RTNL here so can safely walk the list */ - list_for_each_entry(sdata, &local->interfaces, list) { - if (netif_running(sdata->dev)) { - res = 0; - break; - } - } - - if (res) - return res; - - netif_tx_start_all_queues(local->mdev); - - return 0; -} - -static int ieee80211_master_stop(struct net_device *dev) -{ - struct ieee80211_master_priv *mpriv = netdev_priv(dev); - struct ieee80211_local *local = mpriv->local; - struct ieee80211_sub_if_data *sdata; - - /* we hold the RTNL here so can safely walk the list */ - list_for_each_entry(sdata, &local->interfaces, list) - if (netif_running(sdata->dev)) - dev_close(sdata->dev); - - return 0; -} - -static void ieee80211_master_set_multicast_list(struct net_device *dev) -{ - struct ieee80211_master_priv *mpriv = netdev_priv(dev); - struct ieee80211_local *local = mpriv->local; + struct ieee80211_local *local = + container_of(work, struct ieee80211_local, reconfig_filter); ieee80211_configure_filter(local); } @@ -259,7 +211,8 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, } if (changed & BSS_CHANGED_BEACON_ENABLED) { - if (local->sw_scanning) { + if (local->quiescing || !netif_running(sdata->dev) || + test_bit(SCAN_SW_SCANNING, &local->scanning)) { sdata->vif.bss_conf.enable_beacon = false; } else { /* @@ -288,9 +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) @@ -310,7 +260,6 @@ void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int tmp; - skb->dev = local->mdev; skb->pkt_type = IEEE80211_TX_STATUS_MSG; skb_queue_tail(info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS ? &local->skb_queue : &local->skb_queue_unreliable, skb); @@ -330,19 +279,16 @@ static void ieee80211_tasklet_handler(unsigned long data) { struct ieee80211_local *local = (struct ieee80211_local *) data; struct sk_buff *skb; - struct ieee80211_rx_status rx_status; struct ieee80211_ra_tid *ra_tid; while ((skb = skb_dequeue(&local->skb_queue)) || (skb = skb_dequeue(&local->skb_queue_unreliable))) { switch (skb->pkt_type) { case IEEE80211_RX_MSG: - /* status is in skb->cb */ - memcpy(&rx_status, skb->cb, sizeof(rx_status)); /* Clear skb->pkt_type in order to not confuse kernel * netstack. */ skb->pkt_type = 0; - __ieee80211_rx(local_to_hw(local), skb, &rx_status); + ieee80211_rx(local_to_hw(local), skb); break; case IEEE80211_TX_STATUS_MSG: skb->pkt_type = 0; @@ -375,6 +321,31 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + /* + * XXX: This is temporary! + * + * The problem here is that when we get here, the driver will + * quite likely have pretty much overwritten info->control by + * using info->driver_data or info->rate_driver_data. Thus, + * when passing out the frame to the driver again, we would be + * passing completely bogus data since the driver would then + * expect a properly filled info->control. In mac80211 itself + * the same problem occurs, since we need info->control.vif + * internally. + * + * To fix this, we should send the frame through TX processing + * again. However, it's not that simple, since the frame will + * have been software-encrypted (if applicable) already, and + * encrypting it again doesn't do much good. So to properly do + * that, we not only have to skip the actual 'raw' encryption + * (key selection etc. still has to be done!) but also the + * sequence number assignment since that impacts the crypto + * encapsulation, of course. + * + * Hence, for now, fix the bug by just dropping the frame. + */ + goto drop; + sta->tx_filtered_count++; /* @@ -428,6 +399,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, return; } + drop: #ifdef CONFIG_MAC80211_VERBOSE_DEBUG if (net_ratelimit()) printk(KERN_DEBUG "%s: dropped TX filtered frame, " @@ -510,6 +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(); @@ -685,6 +659,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, if (!wiphy) return NULL; + wiphy->netnsok = true; wiphy->privid = mac80211_wiphy_privid; /* Yes, putting cfg80211_bss into ieee80211_bss is a hack */ @@ -711,7 +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); @@ -719,13 +693,15 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, mutex_init(&local->scan_mtx); spin_lock_init(&local->key_lock); - + spin_lock_init(&local->filter_lock); spin_lock_init(&local->queue_stop_reason_lock); INIT_DELAYED_WORK(&local->scan_work, ieee80211_scan_work); 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, @@ -739,12 +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); @@ -755,30 +729,11 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, } EXPORT_SYMBOL(ieee80211_alloc_hw); -static const struct net_device_ops ieee80211_master_ops = { - .ndo_start_xmit = ieee80211_master_start_xmit, - .ndo_open = ieee80211_master_open, - .ndo_stop = ieee80211_master_stop, - .ndo_set_multicast_list = ieee80211_master_set_multicast_list, - .ndo_select_queue = ieee80211_select_queue, -}; - -static void ieee80211_master_setup(struct net_device *mdev) -{ - mdev->type = ARPHRD_IEEE80211; - mdev->netdev_ops = &ieee80211_master_ops; - mdev->header_ops = &ieee80211_header_ops; - mdev->tx_queue_len = 1000; - mdev->addr_len = ETH_ALEN; -} - int ieee80211_register_hw(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); int result; enum ieee80211_band band; - struct net_device *mdev; - struct ieee80211_master_priv *mpriv; int channels, i, j, max_bitrates; bool supp_ht; static const u32 cipher_suites[] = { @@ -818,9 +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 */ @@ -877,19 +832,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (hw->queues > IEEE80211_MAX_QUEUES) hw->queues = IEEE80211_MAX_QUEUES; - mdev = alloc_netdev_mq(sizeof(struct ieee80211_master_priv), - "wmaster%d", ieee80211_master_setup, - hw->queues); - if (!mdev) - goto fail_mdev_alloc; - - mpriv = netdev_priv(mdev); - mpriv->local = local; - local->mdev = mdev; - - local->hw.workqueue = + local->workqueue = create_singlethread_workqueue(wiphy_name(local->hw.wiphy)); - if (!local->hw.workqueue) { + if (!local->workqueue) { result = -ENOMEM; goto fail_workqueue; } @@ -921,17 +866,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } rtnl_lock(); - result = dev_alloc_name(local->mdev, local->mdev->name); - if (result < 0) - goto fail_dev; - - memcpy(local->mdev->dev_addr, local->hw.wiphy->perm_addr, ETH_ALEN); - SET_NETDEV_DEV(local->mdev, wiphy_dev(local->hw.wiphy)); - local->mdev->features |= NETIF_F_NETNS_LOCAL; - - result = register_netdevice(local->mdev); - if (result < 0) - goto fail_dev; result = ieee80211_init_rate_ctrl_alg(local, hw->rate_control_algorithm); @@ -956,13 +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++; } @@ -984,23 +918,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_led_exit(local); ieee80211_remove_interfaces(local); fail_rate: - unregister_netdevice(local->mdev); - local->mdev = NULL; - fail_dev: rtnl_unlock(); ieee80211_wep_free(local); fail_wep: sta_info_stop(local); fail_sta_info: debugfs_hw_del(local); - destroy_workqueue(local->hw.workqueue); + destroy_workqueue(local->workqueue); fail_workqueue: - if (local->mdev) - free_netdev(local->mdev); - fail_mdev_alloc: 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); @@ -1022,15 +950,12 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) * because the driver cannot be handing us frames any * more and the tasklet is killed. */ - - /* First, we remove all virtual interfaces. */ ieee80211_remove_interfaces(local); - /* then, finally, remove the master interface */ - unregister_netdevice(local->mdev); - rtnl_unlock(); + cancel_work_sync(&local->reconfig_filter); + ieee80211_clear_tx_pending(local); sta_info_stop(local); rate_control_deinitialize(local); @@ -1043,12 +968,11 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) skb_queue_purge(&local->skb_queue); skb_queue_purge(&local->skb_queue_unreliable); - destroy_workqueue(local->hw.workqueue); + destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); ieee80211_wep_free(local); ieee80211_led_exit(local); - free_netdev(local->mdev); - 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 11cf45bce38..f7364e56f1e 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; } - 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; } - 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; - 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) @@ -568,7 +580,7 @@ static void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, ifmsh = &sdata->u.mesh; - rx_status = (struct ieee80211_rx_status *) skb->cb; + rx_status = IEEE80211_SKB_RXCB(skb); mgmt = (struct ieee80211_mgmt *) skb->data; stype = le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_STYPE; @@ -597,7 +609,7 @@ static void ieee80211_mesh_work(struct work_struct *work) if (!netif_running(sdata->dev)) return; - if (local->sw_scanning || local->hw_scanning) + if (local->scanning) return; while ((skb = skb_dequeue(&ifmsh->skb_queue))) @@ -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)) - queue_work(local->hw.workqueue, &sdata->u.mesh.work); + ieee80211_queue_work(&local->hw, &sdata->u.mesh.work); rcu_read_unlock(); } @@ -671,8 +689,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) } ieee80211_rx_result -ieee80211_mesh_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - struct ieee80211_rx_status *rx_status) +ieee80211_mesh_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; @@ -686,12 +703,14 @@ ieee80211_mesh_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, fc = le16_to_cpu(mgmt->frame_control); switch (fc & IEEE80211_FCTL_STYPE) { + case IEEE80211_STYPE_ACTION: + if (skb->len < IEEE80211_MIN_ACTION_SIZE) + return RX_DROP_MONITOR; + /* fall through */ case IEEE80211_STYPE_PROBE_RESP: case IEEE80211_STYPE_BEACON: - case IEEE80211_STYPE_ACTION: - memcpy(skb->cb, rx_status, sizeof(*rx_status)); skb_queue_tail(&ifmsh->skb_queue, skb); - 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 c7d72819cdd..dd1c19319f0 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, @@ -205,11 +226,12 @@ 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 -ieee80211_mesh_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - struct ieee80211_rx_status *rx_status); +ieee80211_mesh_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata); @@ -247,7 +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 */ @@ -266,6 +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 f49ef288e2e..29b82e98eff 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) { @@ -241,7 +259,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, * @hwmp_ie: hwmp information element (PREP or PREQ) * * This function updates the path routing information to the originator and the - * transmitter of a HWMP PREQ or PREP fram. + * transmitter of a HWMP PREQ or PREP frame. * * Returns: metric to frame originator or 0 if the frame should not be further * processed @@ -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))) - 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; - 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)); @@ -686,11 +708,11 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) u8 ttl, dst_flags; u32 lifetime; - spin_lock(&ifmsh->mesh_preq_queue_lock); + spin_lock_bh(&ifmsh->mesh_preq_queue_lock); if (!ifmsh->preq_queue_len || time_before(jiffies, ifmsh->last_preq + min_preq_int_jiff(sdata))) { - spin_unlock(&ifmsh->mesh_preq_queue_lock); + spin_unlock_bh(&ifmsh->mesh_preq_queue_lock); return; } @@ -698,7 +720,7 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) struct mesh_preq_queue, list); list_del(&preq_node->list); --ifmsh->preq_queue_len; - spin_unlock(&ifmsh->mesh_preq_queue_lock); + spin_unlock_bh(&ifmsh->mesh_preq_queue_lock); rcu_read_lock(); mpath = mesh_path_lookup(preq_node->dst, sdata); @@ -784,7 +806,6 @@ int mesh_nexthop_lookup(struct sk_buff *skb, mesh_path_add(dst_addr, sdata); mpath = mesh_path_lookup(dst_addr, sdata); if (!mpath) { - dev_kfree_skb(skb); sdata->u.mesh.mshstats.dropped_frames_no_route++; err = -ENOSPC; goto endlookup; @@ -792,7 +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) @@ -804,17 +825,17 @@ int mesh_nexthop_lookup(struct sk_buff *skb, memcpy(hdr->addr1, mpath->next_hop->sta.addr, ETH_ALEN); } else { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (!(mpath->flags & MESH_PATH_RESOLVING)) { /* Start discovery only if it is not running yet */ mesh_queue_preq(mpath, PREQ_Q_F_START); } 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); if (skb_to_free) mesh_path_discard_frame(skb_to_free, sdata); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 479597e8858..751c4d0e2b3 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 @@ -55,7 +120,25 @@ static DEFINE_RWLOCK(pathtbl_resize_lock); */ void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta) { + struct sk_buff *skb; + struct ieee80211_hdr *hdr; + struct sk_buff_head tmpq; + unsigned long flags; + rcu_assign_pointer(mpath->next_hop, sta); + + __skb_queue_head_init(&tmpq); + + spin_lock_irqsave(&mpath->frame_queue.lock, flags); + + while ((skb = __skb_dequeue(&mpath->frame_queue)) != NULL) { + hdr = (struct ieee80211_hdr *) skb->data; + memcpy(hdr->addr1, sta->sta.addr, ETH_ALEN); + __skb_queue_tail(&tmpq, skb); + } + + skb_queue_splice(&tmpq, &mpath->frame_queue); + spin_unlock_irqrestore(&mpath->frame_queue.lock, flags); } @@ -167,6 +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; @@ -175,8 +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; @@ -188,11 +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; @@ -225,23 +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; @@ -256,9 +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; @@ -267,8 +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; @@ -277,11 +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; @@ -315,20 +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; @@ -466,6 +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; @@ -481,11 +578,9 @@ enddel: */ void mesh_path_tx_pending(struct mesh_path *mpath) { - struct sk_buff *skb; - - while ((skb = skb_dequeue(&mpath->frame_queue)) && - (mpath->flags & MESH_PATH_ACTIVE)) - dev_queue_xmit(skb); + if (mpath->flags & MESH_PATH_ACTIVE) + ieee80211_add_pending_skbs(mpath->sdata->local, + &mpath->frame_queue); } /** diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index cb14253587f..ffcbad75e09 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 07e7e41816b..dc5049d58c5 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -27,43 +27,99 @@ #include "rate.h" #include "led.h" -#define IEEE80211_ASSOC_SCANS_MAX_TRIES 2 #define IEEE80211_AUTH_TIMEOUT (HZ / 5) #define IEEE80211_AUTH_MAX_TRIES 3 #define IEEE80211_ASSOC_TIMEOUT (HZ / 5) #define IEEE80211_ASSOC_MAX_TRIES 3 -#define IEEE80211_MONITORING_INTERVAL (2 * HZ) -#define IEEE80211_PROBE_WAIT (HZ / 5) -#define IEEE80211_PROBE_IDLE_TIME (60 * HZ) -#define IEEE80211_RETRY_AUTH_INTERVAL (1 * HZ) +#define IEEE80211_MAX_PROBE_TRIES 5 + +/* + * beacon loss detection timeout + * XXX: should depend on beacon interval + */ +#define IEEE80211_BEACON_LOSS_TIME (2 * HZ) +/* + * Time the connection can be idle before we probe + * it to see if we can still talk to the AP. + */ +#define IEEE80211_CONNECTION_IDLE_TIME (30 * HZ) +/* + * Time we wait for a probe response after sending + * a probe request because of beacon loss or for + * checking the connection still works. + */ +#define IEEE80211_PROBE_WAIT (HZ / 2) #define TMR_RUNNING_TIMER 0 #define TMR_RUNNING_CHANSW 1 +/* + * All cfg80211 functions have to be called outside a locked + * section so that they can acquire a lock themselves... This + * is much simpler than queuing up things in cfg80211, but we + * do need some indirection for that here. + */ +enum rx_mgmt_action { + /* no action required */ + RX_MGMT_NONE, + + /* caller must call cfg80211_send_rx_auth() */ + RX_MGMT_CFG80211_AUTH, + + /* caller must call cfg80211_send_rx_assoc() */ + RX_MGMT_CFG80211_ASSOC, + + /* caller must call cfg80211_send_deauth() */ + RX_MGMT_CFG80211_DEAUTH, + + /* caller must call cfg80211_send_disassoc() */ + RX_MGMT_CFG80211_DISASSOC, + + /* caller must call cfg80211_auth_timeout() & free work */ + RX_MGMT_CFG80211_AUTH_TO, + + /* caller must call cfg80211_assoc_timeout() & free work */ + RX_MGMT_CFG80211_ASSOC_TO, +}; + /* utils */ -static int ecw2cw(int ecw) +static inline void ASSERT_MGD_MTX(struct ieee80211_if_managed *ifmgd) { - return (1 << ecw) - 1; + WARN_ON(!mutex_is_locked(&ifmgd->mtx)); } -static u8 *ieee80211_bss_get_ie(struct ieee80211_bss *bss, u8 ie) +/* + * We can have multiple work items (and connection probing) + * scheduling this timer, but we need to take care to only + * reschedule it when it should fire _earlier_ than it was + * asked for before, or if it's not pending right now. This + * function ensures that. Note that it then is required to + * run this function for all timeouts after the first one + * has happened -- the work that runs from this timer will + * do that. + */ +static void run_again(struct ieee80211_if_managed *ifmgd, + unsigned long timeout) { - u8 *end, *pos; + ASSERT_MGD_MTX(ifmgd); - pos = bss->cbss.information_elements; - if (pos == NULL) - return NULL; - end = pos + bss->cbss.len_information_elements; + if (!timer_pending(&ifmgd->timer) || + time_before(timeout, ifmgd->timer.expires)) + mod_timer(&ifmgd->timer, timeout); +} - while (pos + 1 < end) { - if (pos + 2 + pos[1] > end) - break; - if (pos[0] == ie) - return pos; - pos += 2 + pos[1]; - } +static void mod_beacon_timer(struct ieee80211_sub_if_data *sdata) +{ + if (sdata->local->hw.flags & IEEE80211_HW_BEACON_FILTER) + return; + + mod_timer(&sdata->u.mgd.bcn_mon_timer, + round_jiffies_up(jiffies + IEEE80211_BEACON_LOSS_TIME)); +} - return NULL; +static int ecw2cw(int ecw) +{ + return (1 << ecw) - 1; } static int ieee80211_compatible_rates(struct ieee80211_bss *bss, @@ -94,11 +150,10 @@ static int ieee80211_compatible_rates(struct ieee80211_bss *bss, */ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, struct ieee80211_ht_info *hti, - u16 ap_ht_cap_flags) + const u8 *bssid, u16 ap_ht_cap_flags) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct sta_info *sta; u32 changed = 0; u16 ht_opmode; @@ -147,12 +202,10 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, ieee80211_hw_config(local, 0); rcu_read_lock(); - - sta = sta_info_get(local, ifmgd->bssid); + sta = sta_info_get(local, bssid); if (sta) rate_control_rate_update(local, sband, sta, IEEE80211_RC_HT_CHANGED); - rcu_read_unlock(); } @@ -175,23 +228,24 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, /* frame sending functions */ -static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) +static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; - u8 *pos, *ies, *ht_ie; + u8 *pos; + const u8 *ies, *ht_ie; int i, len, count, rates_len, supp_rates_len; u16 capab; - struct ieee80211_bss *bss; int wmm = 0; struct ieee80211_supported_band *sband; u32 rates = 0; skb = dev_alloc_skb(local->hw.extra_tx_headroom + - sizeof(*mgmt) + 200 + ifmgd->extra_ie_len + - ifmgd->ssid_len); + sizeof(*mgmt) + 200 + wk->ie_len + + wk->ssid_len); if (!skb) { printk(KERN_DEBUG "%s: failed to allocate buffer for assoc " "frame\n", sdata->dev->name); @@ -210,45 +264,35 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) capab |= WLAN_CAPABILITY_SHORT_PREAMBLE; } - bss = ieee80211_rx_bss_get(local, ifmgd->bssid, - local->hw.conf.channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); - if (bss) { - if (bss->cbss.capability & WLAN_CAPABILITY_PRIVACY) - capab |= WLAN_CAPABILITY_PRIVACY; - if (bss->wmm_used) - wmm = 1; + if (wk->bss->cbss.capability & WLAN_CAPABILITY_PRIVACY) + capab |= WLAN_CAPABILITY_PRIVACY; + if (wk->bss->wmm_used) + wmm = 1; - /* get all rates supported by the device and the AP as - * some APs don't like getting a superset of their rates - * in the association request (e.g. D-Link DAP 1353 in - * b-only mode) */ - rates_len = ieee80211_compatible_rates(bss, sband, &rates); + /* get all rates supported by the device and the AP as + * some APs don't like getting a superset of their rates + * in the association request (e.g. D-Link DAP 1353 in + * b-only mode) */ + rates_len = ieee80211_compatible_rates(wk->bss, sband, &rates); - if ((bss->cbss.capability & WLAN_CAPABILITY_SPECTRUM_MGMT) && - (local->hw.flags & IEEE80211_HW_SPECTRUM_MGMT)) - capab |= WLAN_CAPABILITY_SPECTRUM_MGMT; - - ieee80211_rx_bss_put(local, bss); - } else { - rates = ~0; - rates_len = sband->n_bitrates; - } + if ((wk->bss->cbss.capability & WLAN_CAPABILITY_SPECTRUM_MGMT) && + (local->hw.flags & IEEE80211_HW_SPECTRUM_MGMT)) + capab |= WLAN_CAPABILITY_SPECTRUM_MGMT; mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); memset(mgmt, 0, 24); - memcpy(mgmt->da, ifmgd->bssid, ETH_ALEN); + memcpy(mgmt->da, wk->bss->cbss.bssid, ETH_ALEN); memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN); - memcpy(mgmt->bssid, ifmgd->bssid, ETH_ALEN); + memcpy(mgmt->bssid, wk->bss->cbss.bssid, ETH_ALEN); - if (ifmgd->flags & IEEE80211_STA_PREV_BSSID_SET) { + if (!is_zero_ether_addr(wk->prev_bssid)) { skb_put(skb, 10); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_REQ); mgmt->u.reassoc_req.capab_info = cpu_to_le16(capab); mgmt->u.reassoc_req.listen_interval = cpu_to_le16(local->hw.conf.listen_interval); - memcpy(mgmt->u.reassoc_req.current_ap, ifmgd->prev_bssid, + memcpy(mgmt->u.reassoc_req.current_ap, wk->prev_bssid, ETH_ALEN); } else { skb_put(skb, 4); @@ -260,10 +304,10 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } /* SSID */ - ies = pos = skb_put(skb, 2 + ifmgd->ssid_len); + ies = pos = skb_put(skb, 2 + wk->ssid_len); *pos++ = WLAN_EID_SSID; - *pos++ = ifmgd->ssid_len; - memcpy(pos, ifmgd->ssid, ifmgd->ssid_len); + *pos++ = wk->ssid_len; + memcpy(pos, wk->ssid, wk->ssid_len); /* add all rates which were marked to be used above */ supp_rates_len = rates_len; @@ -318,9 +362,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } } - if (ifmgd->extra_ie) { - pos = skb_put(skb, ifmgd->extra_ie_len); - memcpy(pos, ifmgd->extra_ie, ifmgd->extra_ie_len); + if (wk->ie_len && wk->ie) { + pos = skb_put(skb, wk->ie_len); + memcpy(pos, wk->ie, wk->ie_len); } if (wmm && (ifmgd->flags & IEEE80211_STA_WMM_ENABLED)) { @@ -345,9 +389,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) */ if (wmm && (ifmgd->flags & IEEE80211_STA_WMM_ENABLED) && sband->ht_cap.ht_supported && - (ht_ie = ieee80211_bss_get_ie(bss, WLAN_EID_HT_INFORMATION)) && + (ht_ie = ieee80211_bss_get_ie(&wk->bss->cbss, WLAN_EID_HT_INFORMATION)) && ht_ie[1] >= sizeof(struct ieee80211_ht_info) && - (!(ifmgd->flags & IEEE80211_STA_TKIP_WEP_USED))) { + (!(ifmgd->flags & IEEE80211_STA_DISABLE_11N))) { struct ieee80211_ht_info *ht_info = (struct ieee80211_ht_info *)(ht_ie + 2); u16 cap = sband->ht_cap.cap; @@ -382,18 +426,13 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) memcpy(pos, &sband->ht_cap.mcs, sizeof(sband->ht_cap.mcs)); } - kfree(ifmgd->assocreq_ies); - ifmgd->assocreq_ies_len = (skb->data + skb->len) - ies; - ifmgd->assocreq_ies = kmalloc(ifmgd->assocreq_ies_len, GFP_KERNEL); - if (ifmgd->assocreq_ies) - memcpy(ifmgd->assocreq_ies, ies, ifmgd->assocreq_ies_len); - ieee80211_tx_skb(sdata, skb, 0); } static void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, - u16 stype, u16 reason) + const u8 *bssid, u16 stype, u16 reason, + void *cookie) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -410,18 +449,18 @@ static void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24); memset(mgmt, 0, 24); - memcpy(mgmt->da, ifmgd->bssid, ETH_ALEN); + memcpy(mgmt->da, bssid, ETH_ALEN); memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN); - memcpy(mgmt->bssid, ifmgd->bssid, ETH_ALEN); + memcpy(mgmt->bssid, bssid, ETH_ALEN); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | stype); skb_put(skb, 2); /* u.deauth.reason_code == u.disassoc.reason_code */ mgmt->u.deauth.reason_code = cpu_to_le16(reason); if (stype == IEEE80211_STYPE_DEAUTH) - cfg80211_send_deauth(sdata->dev, (u8 *) mgmt, skb->len); + cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len, cookie); else - cfg80211_send_disassoc(sdata->dev, (u8 *) mgmt, skb->len); + cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len, cookie); ieee80211_tx_skb(sdata, skb, ifmgd->flags & IEEE80211_STA_MFP_ENABLED); } @@ -494,28 +533,26 @@ static void ieee80211_chswitch_work(struct work_struct *work) { struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, u.mgd.chswitch_work); - struct ieee80211_bss *bss; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; if (!netif_running(sdata->dev)) return; - bss = ieee80211_rx_bss_get(sdata->local, ifmgd->bssid, - sdata->local->hw.conf.channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); - if (!bss) - goto exit; + mutex_lock(&ifmgd->mtx); + if (!ifmgd->associated) + goto out; sdata->local->oper_channel = sdata->local->csa_channel; + ieee80211_hw_config(sdata->local, IEEE80211_CONF_CHANGE_CHANNEL); + /* XXX: shouldn't really modify cfg80211-owned data! */ - if (!ieee80211_hw_config(sdata->local, IEEE80211_CONF_CHANGE_CHANNEL)) - bss->cbss.channel = sdata->local->oper_channel; + ifmgd->associated->cbss.channel = sdata->local->oper_channel; - ieee80211_rx_bss_put(sdata->local, bss); -exit: - ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; ieee80211_wake_queues_by_reason(&sdata->local->hw, IEEE80211_QUEUE_STOP_REASON_CSA); + out: + ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; + mutex_unlock(&ifmgd->mtx); } static void ieee80211_chswitch_timer(unsigned long data) @@ -529,7 +566,7 @@ static void ieee80211_chswitch_timer(unsigned long data) return; } - queue_work(sdata->local->hw.workqueue, &ifmgd->chswitch_work); + ieee80211_queue_work(&sdata->local->hw, &ifmgd->chswitch_work); } void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, @@ -540,10 +577,12 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num); - if (ifmgd->state != IEEE80211_STA_MLME_ASSOCIATED) + ASSERT_MGD_MTX(ifmgd); + + if (!ifmgd->associated) return; - if (sdata->local->sw_scanning || sdata->local->hw_scanning) + if (sdata->local->scanning) return; /* Disregard subsequent beacons if we are already running a timer @@ -559,7 +598,7 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, sdata->local->csa_channel = new_ch; if (sw_elem->count <= 1) { - queue_work(sdata->local->hw.workqueue, &ifmgd->chswitch_work); + ieee80211_queue_work(&sdata->local->hw, &ifmgd->chswitch_work); } else { ieee80211_stop_queues_by_reason(&sdata->local->hw, IEEE80211_QUEUE_STOP_REASON_CSA); @@ -601,7 +640,7 @@ static void ieee80211_enable_ps(struct ieee80211_local *local, * If we are scanning right now then the parameters will * take effect when scan finishes. */ - if (local->hw_scanning || local->sw_scanning) + if (local->scanning) return; if (conf->dynamic_ps_timeout > 0 && @@ -651,8 +690,9 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) } if (count == 1 && found->u.mgd.powersave && - (found->u.mgd.flags & IEEE80211_STA_ASSOCIATED) && - !(found->u.mgd.flags & IEEE80211_STA_PROBEREQ_POLL)) { + found->u.mgd.associated && list_empty(&found->u.mgd.work_list) && + !(found->u.mgd.flags & (IEEE80211_STA_BEACON_POLL | + IEEE80211_STA_CONNECTION_POLL))) { s32 beaconint_us; if (latency < 0) @@ -724,7 +764,7 @@ void ieee80211_dynamic_ps_timer(unsigned long data) if (local->quiescing || local->suspended) return; - queue_work(local->hw.workqueue, &local->dynamic_ps_enable_work); + ieee80211_queue_work(&local->hw, &local->dynamic_ps_enable_work); } /* MLME */ @@ -806,9 +846,6 @@ static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, u16 capab, bool erp_valid, u8 erp) { struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; -#endif u32 changed = 0; bool use_protection; bool use_short_preamble; @@ -825,42 +862,16 @@ static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, use_short_slot = !!(capab & WLAN_CAPABILITY_SHORT_SLOT_TIME); if (use_protection != bss_conf->use_cts_prot) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: CTS protection %s (BSSID=%pM)\n", - sdata->dev->name, - use_protection ? "enabled" : "disabled", - ifmgd->bssid); - } -#endif bss_conf->use_cts_prot = use_protection; changed |= BSS_CHANGED_ERP_CTS_PROT; } if (use_short_preamble != bss_conf->use_short_preamble) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: switched to %s barker preamble" - " (BSSID=%pM)\n", - sdata->dev->name, - use_short_preamble ? "short" : "long", - ifmgd->bssid); - } -#endif bss_conf->use_short_preamble = use_short_preamble; changed |= BSS_CHANGED_ERP_PREAMBLE; } if (use_short_slot != bss_conf->use_short_slot) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: switched to %s slot time" - " (BSSID=%pM)\n", - sdata->dev->name, - use_short_slot ? "short" : "long", - ifmgd->bssid); - } -#endif bss_conf->use_short_slot = use_short_slot; changed |= BSS_CHANGED_ERP_SLOT; } @@ -868,105 +879,31 @@ static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, return changed; } -static void ieee80211_sta_send_apinfo(struct ieee80211_sub_if_data *sdata) -{ - union iwreq_data wrqu; - - memset(&wrqu, 0, sizeof(wrqu)); - if (sdata->u.mgd.flags & IEEE80211_STA_ASSOCIATED) - memcpy(wrqu.ap_addr.sa_data, sdata->u.mgd.bssid, ETH_ALEN); - wrqu.ap_addr.sa_family = ARPHRD_ETHER; - wireless_send_event(sdata->dev, SIOCGIWAP, &wrqu, NULL); -} - -static void ieee80211_sta_send_associnfo(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - char *buf; - size_t len; - int i; - union iwreq_data wrqu; - - if (!ifmgd->assocreq_ies && !ifmgd->assocresp_ies) - return; - - buf = kmalloc(50 + 2 * (ifmgd->assocreq_ies_len + - ifmgd->assocresp_ies_len), GFP_KERNEL); - if (!buf) - return; - - len = sprintf(buf, "ASSOCINFO("); - if (ifmgd->assocreq_ies) { - len += sprintf(buf + len, "ReqIEs="); - for (i = 0; i < ifmgd->assocreq_ies_len; i++) { - len += sprintf(buf + len, "%02x", - ifmgd->assocreq_ies[i]); - } - } - if (ifmgd->assocresp_ies) { - if (ifmgd->assocreq_ies) - len += sprintf(buf + len, " "); - len += sprintf(buf + len, "RespIEs="); - for (i = 0; i < ifmgd->assocresp_ies_len; i++) { - len += sprintf(buf + len, "%02x", - ifmgd->assocresp_ies[i]); - } - } - len += sprintf(buf + len, ")"); - - if (len > IW_CUSTOM_MAX) { - len = sprintf(buf, "ASSOCRESPIE="); - for (i = 0; i < ifmgd->assocresp_ies_len; i++) { - len += sprintf(buf + len, "%02x", - ifmgd->assocresp_ies[i]); - } - } - - if (len <= IW_CUSTOM_MAX) { - memset(&wrqu, 0, sizeof(wrqu)); - wrqu.data.length = len; - wireless_send_event(sdata->dev, IWEVCUSTOM, &wrqu, buf); - } - - kfree(buf); -} - - static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk, u32 bss_info_changed) { - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - struct ieee80211_conf *conf = &local_to_hw(local)->conf; - - struct ieee80211_bss *bss; + struct ieee80211_bss *bss = wk->bss; bss_info_changed |= BSS_CHANGED_ASSOC; - ifmgd->flags |= IEEE80211_STA_ASSOCIATED; + /* set timing information */ + sdata->vif.bss_conf.beacon_int = bss->cbss.beacon_interval; + sdata->vif.bss_conf.timestamp = bss->cbss.tsf; + sdata->vif.bss_conf.dtim_period = bss->dtim_period; - bss = ieee80211_rx_bss_get(local, ifmgd->bssid, - conf->channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); - if (bss) { - /* set timing information */ - sdata->vif.bss_conf.beacon_int = bss->cbss.beacon_interval; - sdata->vif.bss_conf.timestamp = bss->cbss.tsf; - sdata->vif.bss_conf.dtim_period = bss->dtim_period; + bss_info_changed |= BSS_CHANGED_BEACON_INT; + bss_info_changed |= ieee80211_handle_bss_capability(sdata, + bss->cbss.capability, bss->has_erp_value, bss->erp_value); - bss_info_changed |= BSS_CHANGED_BEACON_INT; - bss_info_changed |= ieee80211_handle_bss_capability(sdata, - bss->cbss.capability, bss->has_erp_value, bss->erp_value); - - cfg80211_hold_bss(&bss->cbss); - - ieee80211_rx_bss_put(local, bss); - } + sdata->u.mgd.associated = bss; + sdata->u.mgd.old_associate_work = wk; + memcpy(sdata->u.mgd.bssid, bss->cbss.bssid, ETH_ALEN); - ifmgd->flags |= IEEE80211_STA_PREV_BSSID_SET; - memcpy(ifmgd->prev_bssid, sdata->u.mgd.bssid, ETH_ALEN); - ieee80211_sta_send_associnfo(sdata); + /* just to be sure */ + sdata->u.mgd.flags &= ~(IEEE80211_STA_CONNECTION_POLL | + IEEE80211_STA_BEACON_POLL); - ifmgd->last_probe = jiffies; ieee80211_led_assoc(local, 1); sdata->vif.bss_conf.assoc = 1; @@ -982,176 +919,157 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, ieee80211_bss_info_change_notify(sdata, bss_info_changed); - /* will be same as sdata */ - if (local->ps_sdata) { - mutex_lock(&local->iflist_mtx); - ieee80211_recalc_ps(local, -1); - mutex_unlock(&local->iflist_mtx); - } + mutex_lock(&local->iflist_mtx); + ieee80211_recalc_ps(local, -1); + mutex_unlock(&local->iflist_mtx); netif_tx_start_all_queues(sdata->dev); netif_carrier_on(sdata->dev); - - ieee80211_sta_send_apinfo(sdata); } -static void ieee80211_direct_probe(struct ieee80211_sub_if_data *sdata) +static enum rx_mgmt_action __must_check +ieee80211_direct_probe(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - ifmgd->direct_probe_tries++; - if (ifmgd->direct_probe_tries > IEEE80211_AUTH_MAX_TRIES) { + wk->tries++; + if (wk->tries > IEEE80211_AUTH_MAX_TRIES) { printk(KERN_DEBUG "%s: direct probe to AP %pM timed out\n", - sdata->dev->name, ifmgd->bssid); - ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_recalc_idle(local); - cfg80211_send_auth_timeout(sdata->dev, ifmgd->bssid); + sdata->dev->name, wk->bss->cbss.bssid); /* * Most likely AP is not in the range so remove the - * bss information associated to the AP + * bss struct for that AP. */ - ieee80211_rx_bss_remove(sdata, ifmgd->bssid, - sdata->local->hw.conf.channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); + cfg80211_unlink_bss(local->hw.wiphy, &wk->bss->cbss); /* * We might have a pending scan which had no chance to run yet - * due to state == IEEE80211_STA_MLME_DIRECT_PROBE. - * Hence, queue the STAs work again + * due to work needing to be done. Hence, queue the STAs work + * again for that. */ - queue_work(local->hw.workqueue, &ifmgd->work); - return; + ieee80211_queue_work(&local->hw, &ifmgd->work); + return RX_MGMT_CFG80211_AUTH_TO; } - printk(KERN_DEBUG "%s: direct probe to AP %pM try %d\n", - sdata->dev->name, ifmgd->bssid, - ifmgd->direct_probe_tries); + printk(KERN_DEBUG "%s: direct probe to AP %pM (try %d)\n", + sdata->dev->name, wk->bss->cbss.bssid, + wk->tries); - ifmgd->state = IEEE80211_STA_MLME_DIRECT_PROBE; - - /* Direct probe is sent to broadcast address as some APs + /* + * Direct probe is sent to broadcast address as some APs * will not answer to direct packet in unassociated state. */ - ieee80211_send_probe_req(sdata, NULL, - ifmgd->ssid, ifmgd->ssid_len, NULL, 0); + ieee80211_send_probe_req(sdata, NULL, wk->ssid, wk->ssid_len, NULL, 0); + + wk->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; + run_again(ifmgd, wk->timeout); - mod_timer(&ifmgd->timer, jiffies + IEEE80211_AUTH_TIMEOUT); + return RX_MGMT_NONE; } -static void ieee80211_authenticate(struct ieee80211_sub_if_data *sdata) +static enum rx_mgmt_action __must_check +ieee80211_authenticate(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - u8 *ies; - size_t ies_len; - ifmgd->auth_tries++; - if (ifmgd->auth_tries > IEEE80211_AUTH_MAX_TRIES) { + wk->tries++; + if (wk->tries > IEEE80211_AUTH_MAX_TRIES) { printk(KERN_DEBUG "%s: authentication with AP %pM" " timed out\n", - sdata->dev->name, ifmgd->bssid); - ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_recalc_idle(local); - cfg80211_send_auth_timeout(sdata->dev, ifmgd->bssid); - ieee80211_rx_bss_remove(sdata, ifmgd->bssid, - sdata->local->hw.conf.channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); + sdata->dev->name, wk->bss->cbss.bssid); + + /* + * Most likely AP is not in the range so remove the + * bss struct for that AP. + */ + cfg80211_unlink_bss(local->hw.wiphy, &wk->bss->cbss); /* * We might have a pending scan which had no chance to run yet - * due to state == IEEE80211_STA_MLME_AUTHENTICATE. - * Hence, queue the STAs work again + * due to work needing to be done. Hence, queue the STAs work + * again for that. */ - queue_work(local->hw.workqueue, &ifmgd->work); - return; + ieee80211_queue_work(&local->hw, &ifmgd->work); + return RX_MGMT_CFG80211_AUTH_TO; } - ifmgd->state = IEEE80211_STA_MLME_AUTHENTICATE; - printk(KERN_DEBUG "%s: authenticate with AP %pM\n", - sdata->dev->name, ifmgd->bssid); + printk(KERN_DEBUG "%s: authenticate with AP %pM (try %d)\n", + sdata->dev->name, wk->bss->cbss.bssid, wk->tries); - if (ifmgd->flags & IEEE80211_STA_EXT_SME) { - ies = ifmgd->sme_auth_ie; - ies_len = ifmgd->sme_auth_ie_len; - } else { - ies = NULL; - ies_len = 0; - } - ieee80211_send_auth(sdata, 1, ifmgd->auth_alg, ies, ies_len, - ifmgd->bssid, 0); - ifmgd->auth_transaction = 2; + ieee80211_send_auth(sdata, 1, wk->auth_alg, wk->ie, wk->ie_len, + wk->bss->cbss.bssid, NULL, 0, 0); + wk->auth_transaction = 2; + + wk->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; + run_again(ifmgd, wk->timeout); - mod_timer(&ifmgd->timer, jiffies + IEEE80211_AUTH_TIMEOUT); + return RX_MGMT_NONE; } -/* - * The disassoc 'reason' argument can be either our own reason - * if self disconnected or a reason code from the AP. - */ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, - bool deauth, bool self_disconnected, - u16 reason) + bool deauth) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - struct ieee80211_conf *conf = &local_to_hw(local)->conf; - struct ieee80211_bss *bss; struct sta_info *sta; u32 changed = 0, config_changed = 0; + u8 bssid[ETH_ALEN]; + + ASSERT_MGD_MTX(ifmgd); + + if (WARN_ON(!ifmgd->associated)) + return; + + memcpy(bssid, ifmgd->associated->cbss.bssid, ETH_ALEN); + + ifmgd->associated = NULL; + memset(ifmgd->bssid, 0, ETH_ALEN); if (deauth) { - ifmgd->direct_probe_tries = 0; - ifmgd->auth_tries = 0; + 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); } - ifmgd->assoc_scan_tries = 0; - ifmgd->assoc_tries = 0; + + /* + * we need to commit the associated = NULL change because the + * scan code uses that to determine whether this iface should + * go to/wake up from powersave or not -- and could otherwise + * wake the queues erroneously. + */ + smp_mb(); + + /* + * Thus, we can only afterwards stop the queues -- to account + * for the case where another CPU is finishing a scan at this + * time -- we don't want the scan code to enable queues. + */ netif_tx_stop_all_queues(sdata->dev); netif_carrier_off(sdata->dev); rcu_read_lock(); - sta = sta_info_get(local, ifmgd->bssid); + sta = sta_info_get(local, bssid); if (sta) ieee80211_sta_tear_down_BA_sessions(sta); rcu_read_unlock(); - bss = ieee80211_rx_bss_get(local, ifmgd->bssid, - conf->channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); - - if (bss) { - cfg80211_unhold_bss(&bss->cbss); - ieee80211_rx_bss_put(local, bss); - } - - if (self_disconnected) { - if (deauth) - ieee80211_send_deauth_disassoc(sdata, - IEEE80211_STYPE_DEAUTH, reason); - else - ieee80211_send_deauth_disassoc(sdata, - IEEE80211_STYPE_DISASSOC, reason); - } - - ifmgd->flags &= ~IEEE80211_STA_ASSOCIATED; changed |= ieee80211_reset_erp_info(sdata); ieee80211_led_assoc(local, 0); changed |= BSS_CHANGED_ASSOC; sdata->vif.bss_conf.assoc = false; - ieee80211_sta_send_apinfo(sdata); - - if (self_disconnected || reason == WLAN_REASON_DISASSOC_STA_HAS_LEFT) { - ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_rx_bss_remove(sdata, ifmgd->bssid, - sdata->local->hw.conf.channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); - } - ieee80211_set_wmm_default(sdata); ieee80211_recalc_idle(local); @@ -1180,7 +1098,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); - sta = sta_info_get(local, ifmgd->bssid); + sta = sta_info_get(local, bssid); if (!sta) { rcu_read_unlock(); return; @@ -1193,83 +1111,42 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sta_info_destroy(sta); } -static int ieee80211_sta_wep_configured(struct ieee80211_sub_if_data *sdata) -{ - if (!sdata || !sdata->default_key || - sdata->default_key->conf.alg != ALG_WEP) - return 0; - return 1; -} - -static int ieee80211_privacy_mismatch(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_local *local = sdata->local; - struct ieee80211_bss *bss; - int bss_privacy; - int wep_privacy; - int privacy_invoked; - - if (!ifmgd || (ifmgd->flags & IEEE80211_STA_EXT_SME)) - return 0; - - bss = ieee80211_rx_bss_get(local, ifmgd->bssid, - local->hw.conf.channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); - if (!bss) - return 0; - - bss_privacy = !!(bss->cbss.capability & WLAN_CAPABILITY_PRIVACY); - wep_privacy = !!ieee80211_sta_wep_configured(sdata); - privacy_invoked = !!(ifmgd->flags & IEEE80211_STA_PRIVACY_INVOKED); - - ieee80211_rx_bss_put(local, bss); - - if ((bss_privacy == wep_privacy) || (bss_privacy == privacy_invoked)) - return 0; - - return 1; -} - -static void ieee80211_associate(struct ieee80211_sub_if_data *sdata) +static enum rx_mgmt_action __must_check +ieee80211_associate(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - ifmgd->assoc_tries++; - if (ifmgd->assoc_tries > IEEE80211_ASSOC_MAX_TRIES) { + wk->tries++; + if (wk->tries > IEEE80211_ASSOC_MAX_TRIES) { printk(KERN_DEBUG "%s: association with AP %pM" " timed out\n", - sdata->dev->name, ifmgd->bssid); - ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_recalc_idle(local); - cfg80211_send_assoc_timeout(sdata->dev, ifmgd->bssid); - ieee80211_rx_bss_remove(sdata, ifmgd->bssid, - sdata->local->hw.conf.channel->center_freq, - ifmgd->ssid, ifmgd->ssid_len); + sdata->dev->name, wk->bss->cbss.bssid); + + /* + * Most likely AP is not in the range so remove the + * bss struct for that AP. + */ + cfg80211_unlink_bss(local->hw.wiphy, &wk->bss->cbss); + /* * We might have a pending scan which had no chance to run yet - * due to state == IEEE80211_STA_MLME_ASSOCIATE. - * Hence, queue the STAs work again + * due to work needing to be done. Hence, queue the STAs work + * again for that. */ - queue_work(local->hw.workqueue, &ifmgd->work); - return; + ieee80211_queue_work(&local->hw, &ifmgd->work); + return RX_MGMT_CFG80211_ASSOC_TO; } - ifmgd->state = IEEE80211_STA_MLME_ASSOCIATE; - printk(KERN_DEBUG "%s: associate with AP %pM\n", - sdata->dev->name, ifmgd->bssid); - if (ieee80211_privacy_mismatch(sdata)) { - printk(KERN_DEBUG "%s: mismatch in privacy configuration and " - "mixed-cell disabled - abort association\n", sdata->dev->name); - ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_recalc_idle(local); - return; - } + printk(KERN_DEBUG "%s: associate with AP %pM (try %d)\n", + sdata->dev->name, wk->bss->cbss.bssid, wk->tries); + ieee80211_send_assoc(sdata, wk); - ieee80211_send_assoc(sdata); + wk->timeout = jiffies + IEEE80211_ASSOC_TIMEOUT; + run_again(ifmgd, wk->timeout); - mod_timer(&ifmgd->timer, jiffies + IEEE80211_ASSOC_TIMEOUT); + return RX_MGMT_NONE; } void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, @@ -1280,160 +1157,113 @@ void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, * from AP because we know that the connection is working both ways * at that time. But multicast frames (and hence also beacons) must * be ignored here, because we need to trigger the timer during - * data idle periods for sending the periodical probe request to - * the AP. + * data idle periods for sending the periodic probe request to the + * AP we're connected to. */ - if (!is_multicast_ether_addr(hdr->addr1)) - mod_timer(&sdata->u.mgd.timer, - jiffies + IEEE80211_MONITORING_INTERVAL); -} - -void ieee80211_beacon_loss_work(struct work_struct *work) -{ - struct ieee80211_sub_if_data *sdata = - container_of(work, struct ieee80211_sub_if_data, - u.mgd.beacon_loss_work); - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - - /* - * The driver has already reported this event and we have - * already sent a probe request. Maybe the AP died and the - * driver keeps reporting until we disassociate... We have - * to ignore that because otherwise we would continually - * reset the timer and never check whether we received a - * probe response! - */ - if (ifmgd->flags & IEEE80211_STA_PROBEREQ_POLL) + if (is_multicast_ether_addr(hdr->addr1)) return; -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: driver reports beacon loss from AP %pM " - "- sending probe request\n", sdata->dev->name, - sdata->u.mgd.bssid); - } -#endif - - ifmgd->flags |= IEEE80211_STA_PROBEREQ_POLL; - - mutex_lock(&sdata->local->iflist_mtx); - ieee80211_recalc_ps(sdata->local, -1); - mutex_unlock(&sdata->local->iflist_mtx); - - ieee80211_send_probe_req(sdata, ifmgd->bssid, ifmgd->ssid, - ifmgd->ssid_len, NULL, 0); - - mod_timer(&ifmgd->timer, jiffies + IEEE80211_PROBE_WAIT); + mod_timer(&sdata->u.mgd.conn_mon_timer, + round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); } -void ieee80211_beacon_loss(struct ieee80211_vif *vif) +static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + const u8 *ssid; - queue_work(sdata->local->hw.workqueue, - &sdata->u.mgd.beacon_loss_work); + ssid = ieee80211_bss_get_ie(&ifmgd->associated->cbss, WLAN_EID_SSID); + ieee80211_send_probe_req(sdata, ifmgd->associated->cbss.bssid, + ssid + 2, ssid[1], NULL, 0); + + ifmgd->probe_send_count++; + ifmgd->probe_timeout = jiffies + IEEE80211_PROBE_WAIT; + run_again(ifmgd, ifmgd->probe_timeout); } -EXPORT_SYMBOL(ieee80211_beacon_loss); -static void ieee80211_associated(struct ieee80211_sub_if_data *sdata) +static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, + bool beacon) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_local *local = sdata->local; - struct sta_info *sta; - unsigned long last_rx; - bool disassoc = false; + bool already = false; - /* TODO: start monitoring current AP signal quality and number of - * missed beacons. Scan other channels every now and then and search - * for better APs. */ - /* TODO: remove expired BSSes */ + if (!netif_running(sdata->dev)) + return; - ifmgd->state = IEEE80211_STA_MLME_ASSOCIATED; + if (sdata->local->scanning) + return; - rcu_read_lock(); + mutex_lock(&ifmgd->mtx); - sta = sta_info_get(local, ifmgd->bssid); - if (!sta) { - printk(KERN_DEBUG "%s: No STA entry for own AP %pM\n", - sdata->dev->name, ifmgd->bssid); - disassoc = true; - rcu_read_unlock(); + if (!ifmgd->associated) goto out; - } - - last_rx = sta->last_rx; - rcu_read_unlock(); - if ((ifmgd->flags & IEEE80211_STA_PROBEREQ_POLL) && - time_after(jiffies, last_rx + IEEE80211_PROBE_WAIT)) { - printk(KERN_DEBUG "%s: no probe response from AP %pM " - "- disassociating\n", - sdata->dev->name, ifmgd->bssid); - disassoc = true; - ifmgd->flags &= ~IEEE80211_STA_PROBEREQ_POLL; - goto out; - } +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG + if (beacon && net_ratelimit()) + printk(KERN_DEBUG "%s: detected beacon loss from AP " + "- sending probe request\n", sdata->dev->name); +#endif /* - * Beacon filtering is only enabled with power save and then the - * stack should not check for beacon loss. + * The driver/our work has already reported this event or the + * connection monitoring has kicked in and we have already sent + * a probe request. Or maybe the AP died and the driver keeps + * reporting until we disassociate... + * + * In either case we have to ignore the current call to this + * function (except for setting the correct probe reason bit) + * because otherwise we would reset the timer every time and + * never check whether we received a probe response! */ - if (!((local->hw.flags & IEEE80211_HW_BEACON_FILTER) && - (local->hw.conf.flags & IEEE80211_CONF_PS)) && - time_after(jiffies, - ifmgd->last_beacon + IEEE80211_MONITORING_INTERVAL)) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: beacon loss from AP %pM " - "- sending probe request\n", - sdata->dev->name, ifmgd->bssid); - } -#endif - ifmgd->flags |= IEEE80211_STA_PROBEREQ_POLL; - mutex_lock(&local->iflist_mtx); - ieee80211_recalc_ps(local, -1); - mutex_unlock(&local->iflist_mtx); - ieee80211_send_probe_req(sdata, ifmgd->bssid, ifmgd->ssid, - ifmgd->ssid_len, NULL, 0); - mod_timer(&ifmgd->timer, jiffies + IEEE80211_PROBE_WAIT); + if (ifmgd->flags & (IEEE80211_STA_BEACON_POLL | + IEEE80211_STA_CONNECTION_POLL)) + already = true; + + if (beacon) + ifmgd->flags |= IEEE80211_STA_BEACON_POLL; + else + ifmgd->flags |= IEEE80211_STA_CONNECTION_POLL; + + if (already) goto out; - } - if (time_after(jiffies, last_rx + IEEE80211_PROBE_IDLE_TIME)) { - ifmgd->flags |= IEEE80211_STA_PROBEREQ_POLL; - mutex_lock(&local->iflist_mtx); - ieee80211_recalc_ps(local, -1); - mutex_unlock(&local->iflist_mtx); - ieee80211_send_probe_req(sdata, ifmgd->bssid, ifmgd->ssid, - ifmgd->ssid_len, NULL, 0); - } + mutex_lock(&sdata->local->iflist_mtx); + ieee80211_recalc_ps(sdata->local, -1); + mutex_unlock(&sdata->local->iflist_mtx); + ifmgd->probe_send_count = 0; + ieee80211_mgd_probe_ap_send(sdata); out: - if (!disassoc) - mod_timer(&ifmgd->timer, - jiffies + IEEE80211_MONITORING_INTERVAL); - else - ieee80211_set_disassoc(sdata, true, true, - WLAN_REASON_PREV_AUTH_NOT_VALID); + mutex_unlock(&ifmgd->mtx); } +void ieee80211_beacon_loss_work(struct work_struct *work) +{ + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, + u.mgd.beacon_loss_work); -static void ieee80211_auth_completed(struct ieee80211_sub_if_data *sdata) + ieee80211_mgd_probe_ap(sdata, true); +} + +void ieee80211_beacon_loss(struct ieee80211_vif *vif) { - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.beacon_loss_work); +} +EXPORT_SYMBOL(ieee80211_beacon_loss); + +static void ieee80211_auth_completed(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk) +{ + wk->state = IEEE80211_MGD_STATE_IDLE; printk(KERN_DEBUG "%s: authenticated\n", sdata->dev->name); - ifmgd->flags |= IEEE80211_STA_AUTHENTICATED; - if (ifmgd->flags & IEEE80211_STA_EXT_SME) { - /* Wait for SME to request association */ - ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_recalc_idle(sdata->local); - } else - ieee80211_associate(sdata); } static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk, struct ieee80211_mgmt *mgmt, size_t len) { @@ -1444,161 +1274,133 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(pos, len - (pos - (u8 *) mgmt), &elems); if (!elems.challenge) return; - ieee80211_send_auth(sdata, 3, sdata->u.mgd.auth_alg, + ieee80211_send_auth(sdata, 3, wk->auth_alg, elems.challenge - 2, elems.challenge_len + 2, - sdata->u.mgd.bssid, 1); - sdata->u.mgd.auth_transaction = 4; + wk->bss->cbss.bssid, + wk->key, wk->key_len, wk->key_idx); + wk->auth_transaction = 4; } -static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len) +static enum rx_mgmt_action __must_check +ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk, + struct ieee80211_mgmt *mgmt, size_t len) { - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u16 auth_alg, auth_transaction, status_code; - if (ifmgd->state != IEEE80211_STA_MLME_AUTHENTICATE) - return; + if (wk->state != IEEE80211_MGD_STATE_AUTH) + return RX_MGMT_NONE; if (len < 24 + 6) - return; + return RX_MGMT_NONE; - if (memcmp(ifmgd->bssid, mgmt->sa, ETH_ALEN) != 0) - return; + if (memcmp(wk->bss->cbss.bssid, mgmt->sa, ETH_ALEN) != 0) + return RX_MGMT_NONE; - if (memcmp(ifmgd->bssid, mgmt->bssid, ETH_ALEN) != 0) - return; + if (memcmp(wk->bss->cbss.bssid, mgmt->bssid, ETH_ALEN) != 0) + return RX_MGMT_NONE; auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg); auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction); status_code = le16_to_cpu(mgmt->u.auth.status_code); - if (auth_alg != ifmgd->auth_alg || - auth_transaction != ifmgd->auth_transaction) - return; + if (auth_alg != wk->auth_alg || + auth_transaction != wk->auth_transaction) + return RX_MGMT_NONE; if (status_code != WLAN_STATUS_SUCCESS) { - if (status_code == WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG) { - u8 algs[3]; - const int num_algs = ARRAY_SIZE(algs); - int i, pos; - algs[0] = algs[1] = algs[2] = 0xff; - if (ifmgd->auth_algs & IEEE80211_AUTH_ALG_OPEN) - algs[0] = WLAN_AUTH_OPEN; - if (ifmgd->auth_algs & IEEE80211_AUTH_ALG_SHARED_KEY) - algs[1] = WLAN_AUTH_SHARED_KEY; - if (ifmgd->auth_algs & IEEE80211_AUTH_ALG_LEAP) - algs[2] = WLAN_AUTH_LEAP; - if (ifmgd->auth_alg == WLAN_AUTH_OPEN) - pos = 0; - else if (ifmgd->auth_alg == WLAN_AUTH_SHARED_KEY) - pos = 1; - else - pos = 2; - for (i = 0; i < num_algs; i++) { - pos++; - if (pos >= num_algs) - pos = 0; - if (algs[pos] == ifmgd->auth_alg || - algs[pos] == 0xff) - continue; - if (algs[pos] == WLAN_AUTH_SHARED_KEY && - !ieee80211_sta_wep_configured(sdata)) - continue; - ifmgd->auth_alg = algs[pos]; - break; - } - } - return; + list_del(&wk->list); + kfree(wk); + return RX_MGMT_CFG80211_AUTH; } - switch (ifmgd->auth_alg) { + switch (wk->auth_alg) { case WLAN_AUTH_OPEN: case WLAN_AUTH_LEAP: case WLAN_AUTH_FT: - ieee80211_auth_completed(sdata); - cfg80211_send_rx_auth(sdata->dev, (u8 *) mgmt, len); - break; + ieee80211_auth_completed(sdata, wk); + return RX_MGMT_CFG80211_AUTH; case WLAN_AUTH_SHARED_KEY: - if (ifmgd->auth_transaction == 4) { - ieee80211_auth_completed(sdata); - cfg80211_send_rx_auth(sdata->dev, (u8 *) mgmt, len); + if (wk->auth_transaction == 4) { + ieee80211_auth_completed(sdata, wk); + return RX_MGMT_CFG80211_AUTH; } else - ieee80211_auth_challenge(sdata, mgmt, len); + ieee80211_auth_challenge(sdata, wk, mgmt, len); break; } + + return RX_MGMT_NONE; } -static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len) +static enum rx_mgmt_action __must_check +ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk, + struct ieee80211_mgmt *mgmt, size_t len) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + const u8 *bssid = NULL; u16 reason_code; if (len < 24 + 2) - return; + return RX_MGMT_NONE; - if (memcmp(ifmgd->bssid, mgmt->sa, ETH_ALEN)) - return; + ASSERT_MGD_MTX(ifmgd); + + if (wk) + bssid = wk->bss->cbss.bssid; + else + bssid = ifmgd->associated->cbss.bssid; reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); - if (ifmgd->flags & IEEE80211_STA_AUTHENTICATED) - printk(KERN_DEBUG "%s: deauthenticated (Reason: %u)\n", - sdata->dev->name, reason_code); + printk(KERN_DEBUG "%s: deauthenticated from %pM (Reason: %u)\n", + sdata->dev->name, bssid, reason_code); - if (!(ifmgd->flags & IEEE80211_STA_EXT_SME) && - (ifmgd->state == IEEE80211_STA_MLME_AUTHENTICATE || - ifmgd->state == IEEE80211_STA_MLME_ASSOCIATE || - ifmgd->state == IEEE80211_STA_MLME_ASSOCIATED)) { - ifmgd->state = IEEE80211_STA_MLME_DIRECT_PROBE; - mod_timer(&ifmgd->timer, jiffies + - IEEE80211_RETRY_AUTH_INTERVAL); + if (!wk) { + ieee80211_set_disassoc(sdata, true); + } else { + list_del(&wk->list); + kfree(wk); } - ieee80211_set_disassoc(sdata, true, false, 0); - ifmgd->flags &= ~IEEE80211_STA_AUTHENTICATED; - cfg80211_send_deauth(sdata->dev, (u8 *) mgmt, len); + return RX_MGMT_CFG80211_DEAUTH; } -static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len) +static enum rx_mgmt_action __must_check +ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u16 reason_code; if (len < 24 + 2) - return; + return RX_MGMT_NONE; - if (memcmp(ifmgd->bssid, mgmt->sa, ETH_ALEN)) - return; + ASSERT_MGD_MTX(ifmgd); - reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); + if (WARN_ON(!ifmgd->associated)) + return RX_MGMT_NONE; - if (ifmgd->flags & IEEE80211_STA_ASSOCIATED) - printk(KERN_DEBUG "%s: disassociated (Reason: %u)\n", - sdata->dev->name, reason_code); + if (WARN_ON(memcmp(ifmgd->associated->cbss.bssid, mgmt->sa, ETH_ALEN))) + return RX_MGMT_NONE; - if (!(ifmgd->flags & IEEE80211_STA_EXT_SME) && - ifmgd->state == IEEE80211_STA_MLME_ASSOCIATED) { - ifmgd->state = IEEE80211_STA_MLME_ASSOCIATE; - mod_timer(&ifmgd->timer, jiffies + - IEEE80211_RETRY_AUTH_INTERVAL); - } + reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); + + printk(KERN_DEBUG "%s: disassociated from %pM (Reason: %u)\n", + sdata->dev->name, mgmt->sa, reason_code); - ieee80211_set_disassoc(sdata, false, false, reason_code); - cfg80211_send_disassoc(sdata->dev, (u8 *) mgmt, len); + ieee80211_set_disassoc(sdata, false); + return RX_MGMT_CFG80211_DISASSOC; } -static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len, - int reassoc) +static enum rx_mgmt_action __must_check +ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_work *wk, + struct ieee80211_mgmt *mgmt, size_t len, + bool reassoc) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; @@ -1614,17 +1416,16 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, bool have_higher_than_11mbit = false, newsta = false; u16 ap_ht_cap_flags; - /* AssocResp and ReassocResp have identical structure, so process both - * of them in this function. */ - - if (ifmgd->state != IEEE80211_STA_MLME_ASSOCIATE) - return; + /* + * AssocResp and ReassocResp have identical structure, so process both + * of them in this function. + */ if (len < 24 + 6) - return; + return RX_MGMT_NONE; - if (memcmp(ifmgd->bssid, mgmt->sa, ETH_ALEN) != 0) - return; + if (memcmp(wk->bss->cbss.bssid, mgmt->sa, ETH_ALEN) != 0) + return RX_MGMT_NONE; capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code); @@ -1647,26 +1448,17 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, printk(KERN_DEBUG "%s: AP rejected association temporarily; " "comeback duration %u TU (%u ms)\n", sdata->dev->name, tu, ms); + wk->timeout = jiffies + msecs_to_jiffies(ms); if (ms > IEEE80211_ASSOC_TIMEOUT) - mod_timer(&ifmgd->timer, - jiffies + msecs_to_jiffies(ms)); - return; + run_again(ifmgd, jiffies + msecs_to_jiffies(ms)); + return RX_MGMT_NONE; } if (status_code != WLAN_STATUS_SUCCESS) { printk(KERN_DEBUG "%s: AP denied association (code=%d)\n", sdata->dev->name, status_code); - /* if this was a reassociation, ensure we try a "full" - * association next time. This works around some broken APs - * which do not correctly reject reassociation requests. */ - ifmgd->flags &= ~IEEE80211_STA_PREV_BSSID_SET; - cfg80211_send_rx_assoc(sdata->dev, (u8 *) mgmt, len); - if (ifmgd->flags & IEEE80211_STA_EXT_SME) { - /* Wait for SME to decide what to do next */ - ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_recalc_idle(local); - } - return; + wk->state = IEEE80211_MGD_STATE_IDLE; + return RX_MGMT_CFG80211_ASSOC; } if ((aid & (BIT(15) | BIT(14))) != (BIT(15) | BIT(14))) @@ -1677,51 +1469,35 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, if (!elems.supp_rates) { printk(KERN_DEBUG "%s: no SuppRates element in AssocResp\n", sdata->dev->name); - return; + return RX_MGMT_NONE; } printk(KERN_DEBUG "%s: associated\n", sdata->dev->name); ifmgd->aid = aid; - ifmgd->ap_capab = capab_info; - - kfree(ifmgd->assocresp_ies); - ifmgd->assocresp_ies_len = len - (pos - (u8 *) mgmt); - ifmgd->assocresp_ies = kmalloc(ifmgd->assocresp_ies_len, GFP_KERNEL); - if (ifmgd->assocresp_ies) - memcpy(ifmgd->assocresp_ies, pos, ifmgd->assocresp_ies_len); rcu_read_lock(); /* Add STA entry for the AP */ - sta = sta_info_get(local, ifmgd->bssid); + sta = sta_info_get(local, wk->bss->cbss.bssid); if (!sta) { newsta = true; - sta = sta_info_alloc(sdata, ifmgd->bssid, GFP_ATOMIC); + rcu_read_unlock(); + + sta = sta_info_alloc(sdata, wk->bss->cbss.bssid, GFP_KERNEL); if (!sta) { printk(KERN_DEBUG "%s: failed to alloc STA entry for" " the AP\n", sdata->dev->name); - rcu_read_unlock(); - return; + return RX_MGMT_NONE; } - /* update new sta with its last rx activity */ - sta->last_rx = jiffies; - } + set_sta_flags(sta, WLAN_STA_AUTH | WLAN_STA_ASSOC | + WLAN_STA_ASSOC_AP); + if (!(ifmgd->flags & IEEE80211_STA_CONTROL_PORT)) + set_sta_flags(sta, WLAN_STA_AUTHORIZED); - /* - * FIXME: Do we really need to update the sta_info's information here? - * We already know about the AP (we found it in our list) so it - * should already be filled with the right info, no? - * As is stands, all this is racy because typically we assume - * the information that is filled in here (except flags) doesn't - * change while a STA structure is alive. As such, it should move - * to between the sta_info_alloc() and sta_info_insert() above. - */ - - set_sta_flags(sta, WLAN_STA_AUTH | WLAN_STA_ASSOC | WLAN_STA_ASSOC_AP); - if (!(ifmgd->flags & IEEE80211_STA_CONTROL_PORT)) - set_sta_flags(sta, WLAN_STA_AUTHORIZED); + rcu_read_lock(); + } rates = 0; basic_rates = 0; @@ -1771,8 +1547,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, else sdata->flags &= ~IEEE80211_SDATA_OPERATING_GMODE; - /* If TKIP/WEP is used, no need to parse AP's HT capabilities */ - if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_TKIP_WEP_USED)) + if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) ieee80211_ht_cap_ie_to_sta_ht_cap(sband, elems.ht_cap_elem, &sta->sta.ht_cap); @@ -1792,7 +1567,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, printk(KERN_DEBUG "%s: failed to insert STA entry for" " the AP (error %d)\n", sdata->dev->name, err); rcu_read_unlock(); - return; + return RX_MGMT_NONE; } } @@ -1806,24 +1581,29 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, if (elems.ht_info_elem && elems.wmm_param && (ifmgd->flags & IEEE80211_STA_WMM_ENABLED) && - !(ifmgd->flags & IEEE80211_STA_TKIP_WEP_USED)) + !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) changed |= ieee80211_enable_ht(sdata, elems.ht_info_elem, + wk->bss->cbss.bssid, ap_ht_cap_flags); + /* delete work item -- must be before set_associated for PS */ + list_del(&wk->list); + /* set AID and assoc capability, * ieee80211_set_associated() will tell the driver */ bss_conf->aid = aid; bss_conf->assoc_capability = capab_info; - ieee80211_set_associated(sdata, changed); + /* this will take ownership of wk */ + ieee80211_set_associated(sdata, wk, changed); /* - * initialise the time of last beacon to be the association time, - * otherwise beacon loss check will trigger immediately + * Start timer to probe the connection to the AP now. + * Also start the timer that will detect beacon loss. */ - ifmgd->last_beacon = jiffies; + ieee80211_sta_rx_notify(sdata, (struct ieee80211_hdr *)mgmt); + mod_beacon_timer(sdata); - ieee80211_associated(sdata); - cfg80211_send_rx_assoc(sdata->dev, (u8 *) mgmt, len); + return RX_MGMT_CFG80211_ASSOC; } @@ -1851,23 +1631,25 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems, channel, beacon); - if (!bss) + if (bss) + ieee80211_rx_bss_put(local, bss); + + if (!sdata->u.mgd.associated) return; if (elems->ch_switch_elem && (elems->ch_switch_elem_len == 3) && - (memcmp(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN) == 0)) { + (memcmp(mgmt->bssid, sdata->u.mgd.associated->cbss.bssid, + ETH_ALEN) == 0)) { struct ieee80211_channel_sw_ie *sw_elem = (struct ieee80211_channel_sw_ie *)elems->ch_switch_elem; ieee80211_sta_process_chanswitch(sdata, sw_elem, bss); } - - ieee80211_rx_bss_put(local, bss); } static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len, + struct ieee80211_mgd_work *wk, + struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status) { struct ieee80211_if_managed *ifmgd; @@ -1876,6 +1658,8 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, ifmgd = &sdata->u.mgd; + ASSERT_MGD_MTX(ifmgd); + if (memcmp(mgmt->da, sdata->dev->dev_addr, ETH_ALEN)) return; /* ignore ProbeResp to foreign address */ @@ -1889,17 +1673,32 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, false); /* direct probe may be part of the association flow */ - if (ifmgd->state == IEEE80211_STA_MLME_DIRECT_PROBE) { - printk(KERN_DEBUG "%s direct probe responded\n", + if (wk && wk->state == IEEE80211_MGD_STATE_PROBE) { + printk(KERN_DEBUG "%s: direct probe responded\n", sdata->dev->name); - ieee80211_authenticate(sdata); + wk->tries = 0; + wk->state = IEEE80211_MGD_STATE_AUTH; + WARN_ON(ieee80211_authenticate(sdata, wk) != RX_MGMT_NONE); } - if (ifmgd->flags & IEEE80211_STA_PROBEREQ_POLL) { - ifmgd->flags &= ~IEEE80211_STA_PROBEREQ_POLL; + if (ifmgd->associated && + memcmp(mgmt->bssid, ifmgd->associated->cbss.bssid, ETH_ALEN) == 0 && + ifmgd->flags & (IEEE80211_STA_BEACON_POLL | + IEEE80211_STA_CONNECTION_POLL)) { + ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | + IEEE80211_STA_BEACON_POLL); mutex_lock(&sdata->local->iflist_mtx); ieee80211_recalc_ps(sdata->local, -1); mutex_unlock(&sdata->local->iflist_mtx); + /* + * We've received a probe response, but are not sure whether + * we have or will be receiving any beacons or data, so let's + * schedule the timers again, just in case. + */ + mod_beacon_timer(sdata); + mod_timer(&ifmgd->conn_mon_timer, + round_jiffies_up(jiffies + + IEEE80211_CONNECTION_IDLE_TIME)); } } @@ -1937,6 +1736,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, bool erp_valid, directed_tim = false; u8 erp_value = 0; u32 ncrc; + u8 *bssid; + + ASSERT_MGD_MTX(ifmgd); /* Process beacon from the current BSS */ baselen = (u8 *) mgmt->u.beacon.variable - (u8 *) mgmt; @@ -1946,23 +1748,41 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (rx_status->freq != local->hw.conf.channel->center_freq) return; - if (!(ifmgd->flags & IEEE80211_STA_ASSOCIATED) || - memcmp(ifmgd->bssid, mgmt->bssid, ETH_ALEN) != 0) + /* + * We might have received a number of frames, among them a + * disassoc frame and a beacon... + */ + if (!ifmgd->associated) + return; + + bssid = ifmgd->associated->cbss.bssid; + + /* + * And in theory even frames from a different AP we were just + * associated to a split-second ago! + */ + if (memcmp(bssid, mgmt->bssid, ETH_ALEN) != 0) return; - if (ifmgd->flags & IEEE80211_STA_PROBEREQ_POLL) { + if (ifmgd->flags & IEEE80211_STA_BEACON_POLL) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG if (net_ratelimit()) { printk(KERN_DEBUG "%s: cancelling probereq poll due " "to a received beacon\n", sdata->dev->name); } #endif - ifmgd->flags &= ~IEEE80211_STA_PROBEREQ_POLL; + ifmgd->flags &= ~IEEE80211_STA_BEACON_POLL; mutex_lock(&local->iflist_mtx); ieee80211_recalc_ps(local, -1); mutex_unlock(&local->iflist_mtx); } + /* + * Push the beacon loss detection into the future since + * we are processing a beacon from the AP just now. + */ + mod_beacon_timer(sdata); + ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4); ncrc = ieee802_11_parse_elems_crc(mgmt->u.beacon.variable, len - baselen, &elems, @@ -2019,15 +1839,15 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (elems.ht_cap_elem && elems.ht_info_elem && elems.wmm_param && - !(ifmgd->flags & IEEE80211_STA_TKIP_WEP_USED)) { + !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) { struct sta_info *sta; struct ieee80211_supported_band *sband; u16 ap_ht_cap_flags; rcu_read_lock(); - sta = sta_info_get(local, ifmgd->bssid); - if (!sta) { + sta = sta_info_get(local, bssid); + if (WARN_ON(!sta)) { rcu_read_unlock(); return; } @@ -2042,15 +1862,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); changed |= ieee80211_enable_ht(sdata, elems.ht_info_elem, - ap_ht_cap_flags); + bssid, ap_ht_cap_flags); } + /* Note: country IE parsing is done for us by cfg80211 */ if (elems.country_elem) { - /* Note we are only reviewing this on beacons - * for the BSSID we are associated to */ - regulatory_hint_11d(local->hw.wiphy, - elems.country_elem, elems.country_elem_len); - /* TODO: IBSS also needs this */ if (elems.pwr_constr_elem) ieee80211_handle_pwr_constr(sdata, @@ -2063,8 +1879,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } ieee80211_rx_result ieee80211_sta_rx_mgmt(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, - struct ieee80211_rx_status *rx_status) + struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee80211_mgmt *mgmt; @@ -2080,14 +1895,14 @@ ieee80211_rx_result ieee80211_sta_rx_mgmt(struct ieee80211_sub_if_data *sdata, case IEEE80211_STYPE_PROBE_REQ: case IEEE80211_STYPE_PROBE_RESP: case IEEE80211_STYPE_BEACON: - memcpy(skb->cb, rx_status, sizeof(*rx_status)); case IEEE80211_STYPE_AUTH: case IEEE80211_STYPE_ASSOC_RESP: case IEEE80211_STYPE_REASSOC_RESP: case IEEE80211_STYPE_DEAUTH: case IEEE80211_STYPE_DISASSOC: + case IEEE80211_STYPE_ACTION: skb_queue_tail(&sdata->u.mgd.skb_queue, skb); - queue_work(local->hw.workqueue, &sdata->u.mgd.work); + ieee80211_queue_work(&local->hw, &sdata->u.mgd.work); return RX_QUEUED; } @@ -2097,40 +1912,119 @@ ieee80211_rx_result ieee80211_sta_rx_mgmt(struct ieee80211_sub_if_data *sdata, static void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_rx_status *rx_status; struct ieee80211_mgmt *mgmt; + struct ieee80211_mgd_work *wk; + enum rx_mgmt_action rma = RX_MGMT_NONE; u16 fc; rx_status = (struct ieee80211_rx_status *) skb->cb; mgmt = (struct ieee80211_mgmt *) skb->data; fc = le16_to_cpu(mgmt->frame_control); - switch (fc & IEEE80211_FCTL_STYPE) { - case IEEE80211_STYPE_PROBE_RESP: - ieee80211_rx_mgmt_probe_resp(sdata, mgmt, skb->len, - rx_status); - break; - case IEEE80211_STYPE_BEACON: - ieee80211_rx_mgmt_beacon(sdata, mgmt, skb->len, - rx_status); - break; - case IEEE80211_STYPE_AUTH: - ieee80211_rx_mgmt_auth(sdata, mgmt, skb->len); + mutex_lock(&ifmgd->mtx); + + if (ifmgd->associated && + memcmp(ifmgd->associated->cbss.bssid, mgmt->bssid, + ETH_ALEN) == 0) { + switch (fc & IEEE80211_FCTL_STYPE) { + case IEEE80211_STYPE_BEACON: + ieee80211_rx_mgmt_beacon(sdata, mgmt, skb->len, + rx_status); + break; + case IEEE80211_STYPE_PROBE_RESP: + ieee80211_rx_mgmt_probe_resp(sdata, NULL, mgmt, + skb->len, rx_status); + break; + case IEEE80211_STYPE_DEAUTH: + rma = ieee80211_rx_mgmt_deauth(sdata, NULL, + mgmt, skb->len); + break; + case IEEE80211_STYPE_DISASSOC: + rma = ieee80211_rx_mgmt_disassoc(sdata, mgmt, skb->len); + break; + case IEEE80211_STYPE_ACTION: + /* XXX: differentiate, can only happen for CSA now! */ + ieee80211_sta_process_chanswitch(sdata, + &mgmt->u.action.u.chan_switch.sw_elem, + ifmgd->associated); + break; + } + mutex_unlock(&ifmgd->mtx); + + switch (rma) { + case RX_MGMT_NONE: + /* no action */ + break; + case RX_MGMT_CFG80211_DEAUTH: + cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len, + NULL); + break; + case RX_MGMT_CFG80211_DISASSOC: + cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len, + NULL); + break; + default: + WARN(1, "unexpected: %d", rma); + } + goto out; + } + + list_for_each_entry(wk, &ifmgd->work_list, list) { + if (memcmp(wk->bss->cbss.bssid, mgmt->bssid, ETH_ALEN) != 0) + continue; + + switch (fc & IEEE80211_FCTL_STYPE) { + case IEEE80211_STYPE_PROBE_RESP: + ieee80211_rx_mgmt_probe_resp(sdata, wk, mgmt, skb->len, + rx_status); + break; + case IEEE80211_STYPE_AUTH: + rma = ieee80211_rx_mgmt_auth(sdata, wk, mgmt, skb->len); + break; + case IEEE80211_STYPE_ASSOC_RESP: + rma = ieee80211_rx_mgmt_assoc_resp(sdata, wk, mgmt, + skb->len, false); + break; + case IEEE80211_STYPE_REASSOC_RESP: + rma = ieee80211_rx_mgmt_assoc_resp(sdata, wk, mgmt, + skb->len, true); + break; + case IEEE80211_STYPE_DEAUTH: + rma = ieee80211_rx_mgmt_deauth(sdata, wk, mgmt, + skb->len); + break; + } + /* + * We've processed this frame for that work, so it can't + * belong to another work struct. + * NB: this is also required for correctness because the + * called functions can free 'wk', and for 'rma'! + */ break; - case IEEE80211_STYPE_ASSOC_RESP: - ieee80211_rx_mgmt_assoc_resp(sdata, mgmt, skb->len, 0); + } + + mutex_unlock(&ifmgd->mtx); + + switch (rma) { + case RX_MGMT_NONE: + /* no action */ break; - case IEEE80211_STYPE_REASSOC_RESP: - ieee80211_rx_mgmt_assoc_resp(sdata, mgmt, skb->len, 1); + case RX_MGMT_CFG80211_AUTH: + cfg80211_send_rx_auth(sdata->dev, (u8 *) mgmt, skb->len); break; - case IEEE80211_STYPE_DEAUTH: - ieee80211_rx_mgmt_deauth(sdata, mgmt, skb->len); + case RX_MGMT_CFG80211_ASSOC: + cfg80211_send_rx_assoc(sdata->dev, (u8 *) mgmt, skb->len); break; - case IEEE80211_STYPE_DISASSOC: - ieee80211_rx_mgmt_disassoc(sdata, mgmt, skb->len); + case RX_MGMT_CFG80211_DEAUTH: + cfg80211_send_deauth(sdata->dev, (u8 *)mgmt, skb->len, NULL); break; + default: + WARN(1, "unexpected: %d", rma); } + out: kfree_skb(skb); } @@ -2146,215 +2040,216 @@ static void ieee80211_sta_timer(unsigned long data) return; } - set_bit(IEEE80211_STA_REQ_RUN, &ifmgd->request); - queue_work(local->hw.workqueue, &ifmgd->work); + ieee80211_queue_work(&local->hw, &ifmgd->work); } -static void ieee80211_sta_reset_auth(struct ieee80211_sub_if_data *sdata) +static void ieee80211_sta_work(struct work_struct *work) { - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, u.mgd.work); struct ieee80211_local *local = sdata->local; + struct ieee80211_if_managed *ifmgd; + struct sk_buff *skb; + struct ieee80211_mgd_work *wk, *tmp; + LIST_HEAD(free_work); + enum rx_mgmt_action rma; + bool anybusy = false; - /* Reset own TSF to allow time synchronization work. */ - drv_reset_tsf(local); + if (!netif_running(sdata->dev)) + return; - ifmgd->wmm_last_param_set = -1; /* allow any WMM update */ + if (local->scanning) + return; + if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) + return; - if (ifmgd->auth_algs & IEEE80211_AUTH_ALG_OPEN) - ifmgd->auth_alg = WLAN_AUTH_OPEN; - else if (ifmgd->auth_algs & IEEE80211_AUTH_ALG_SHARED_KEY) - ifmgd->auth_alg = WLAN_AUTH_SHARED_KEY; - else if (ifmgd->auth_algs & IEEE80211_AUTH_ALG_LEAP) - ifmgd->auth_alg = WLAN_AUTH_LEAP; - else if (ifmgd->auth_algs & IEEE80211_AUTH_ALG_FT) - ifmgd->auth_alg = WLAN_AUTH_FT; - else - ifmgd->auth_alg = WLAN_AUTH_OPEN; - ifmgd->auth_transaction = -1; - ifmgd->flags &= ~IEEE80211_STA_ASSOCIATED; - ifmgd->assoc_scan_tries = 0; - ifmgd->direct_probe_tries = 0; - ifmgd->auth_tries = 0; - ifmgd->assoc_tries = 0; - netif_tx_stop_all_queues(sdata->dev); - netif_carrier_off(sdata->dev); -} + /* + * ieee80211_queue_work() should have picked up most cases, + * here we'll pick the the rest. + */ + if (WARN(local->suspended, "STA MLME work scheduled while " + "going to suspend\n")) + return; -static int ieee80211_sta_config_auth(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_local *local = sdata->local; - struct ieee80211_bss *bss; - u8 *bssid = ifmgd->bssid, *ssid = ifmgd->ssid; - u8 ssid_len = ifmgd->ssid_len; - u16 capa_mask = WLAN_CAPABILITY_ESS; - u16 capa_val = WLAN_CAPABILITY_ESS; - struct ieee80211_channel *chan = local->oper_channel; + ifmgd = &sdata->u.mgd; - if (!(ifmgd->flags & IEEE80211_STA_EXT_SME) && - ifmgd->flags & (IEEE80211_STA_AUTO_SSID_SEL | - IEEE80211_STA_AUTO_BSSID_SEL | - IEEE80211_STA_AUTO_CHANNEL_SEL)) { - capa_mask |= WLAN_CAPABILITY_PRIVACY; - if (sdata->default_key) - capa_val |= WLAN_CAPABILITY_PRIVACY; - } + /* first process frames to avoid timing out while a frame is pending */ + while ((skb = skb_dequeue(&ifmgd->skb_queue))) + ieee80211_sta_rx_queued_mgmt(sdata, skb); - if (ifmgd->flags & IEEE80211_STA_AUTO_CHANNEL_SEL) - chan = NULL; + /* then process the rest of the work */ + mutex_lock(&ifmgd->mtx); - if (ifmgd->flags & IEEE80211_STA_AUTO_BSSID_SEL) - bssid = NULL; + if (ifmgd->flags & (IEEE80211_STA_BEACON_POLL | + IEEE80211_STA_CONNECTION_POLL) && + ifmgd->associated) { + u8 bssid[ETH_ALEN]; - if (ifmgd->flags & IEEE80211_STA_AUTO_SSID_SEL) { - ssid = NULL; - ssid_len = 0; + memcpy(bssid, ifmgd->associated->cbss.bssid, ETH_ALEN); + if (time_is_after_jiffies(ifmgd->probe_timeout)) + run_again(ifmgd, ifmgd->probe_timeout); + + else if (ifmgd->probe_send_count < IEEE80211_MAX_PROBE_TRIES) { +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG + printk(KERN_DEBUG "No probe response from AP %pM" + " after %dms, try %d\n", bssid, + (1000 * IEEE80211_PROBE_WAIT)/HZ, + ifmgd->probe_send_count); +#endif + ieee80211_mgd_probe_ap_send(sdata); + } else { + /* + * We actually lost the connection ... or did we? + * Let's make sure! + */ + ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | + IEEE80211_STA_BEACON_POLL); + printk(KERN_DEBUG "No probe response from AP %pM" + " after %dms, disconnecting.\n", + bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ); + ieee80211_set_disassoc(sdata, true); + mutex_unlock(&ifmgd->mtx); + /* + * must be outside lock due to cfg80211, + * but that's not a problem. + */ + ieee80211_send_deauth_disassoc(sdata, bssid, + IEEE80211_STYPE_DEAUTH, + WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, + NULL); + mutex_lock(&ifmgd->mtx); + } } - bss = (void *)cfg80211_get_bss(local->hw.wiphy, chan, - bssid, ssid, ssid_len, - capa_mask, capa_val); - if (bss) { - local->oper_channel = bss->cbss.channel; - local->oper_channel_type = NL80211_CHAN_NO_HT; - ieee80211_hw_config(local, 0); + ieee80211_recalc_idle(local); - if (!(ifmgd->flags & IEEE80211_STA_SSID_SET)) - ieee80211_sta_set_ssid(sdata, bss->ssid, - bss->ssid_len); - ieee80211_sta_set_bssid(sdata, bss->cbss.bssid); - ieee80211_sta_def_wmm_params(sdata, bss->supp_rates_len, - bss->supp_rates); - if (sdata->u.mgd.mfp == IEEE80211_MFP_REQUIRED) - sdata->u.mgd.flags |= IEEE80211_STA_MFP_ENABLED; - else - sdata->u.mgd.flags &= ~IEEE80211_STA_MFP_ENABLED; - - /* Send out direct probe if no probe resp was received or - * the one we have is outdated - */ - if (!bss->last_probe_resp || - time_after(jiffies, bss->last_probe_resp - + IEEE80211_SCAN_RESULT_EXPIRE)) - ifmgd->state = IEEE80211_STA_MLME_DIRECT_PROBE; - else - ifmgd->state = IEEE80211_STA_MLME_AUTHENTICATE; + list_for_each_entry_safe(wk, tmp, &ifmgd->work_list, list) { + if (time_is_after_jiffies(wk->timeout)) { + /* + * This work item isn't supposed to be worked on + * right now, but take care to adjust the timer + * properly. + */ + run_again(ifmgd, wk->timeout); + continue; + } - ieee80211_rx_bss_put(local, bss); - ieee80211_sta_reset_auth(sdata); - return 0; - } else { - if (ifmgd->assoc_scan_tries < IEEE80211_ASSOC_SCANS_MAX_TRIES) { + switch (wk->state) { + default: + WARN_ON(1); + /* fall through */ + case IEEE80211_MGD_STATE_IDLE: + /* nothing */ + rma = RX_MGMT_NONE; + break; + case IEEE80211_MGD_STATE_PROBE: + rma = ieee80211_direct_probe(sdata, wk); + break; + case IEEE80211_MGD_STATE_AUTH: + rma = ieee80211_authenticate(sdata, wk); + break; + case IEEE80211_MGD_STATE_ASSOC: + rma = ieee80211_associate(sdata, wk); + break; + } - ifmgd->assoc_scan_tries++; + switch (rma) { + case RX_MGMT_NONE: + /* no action required */ + break; + case RX_MGMT_CFG80211_AUTH_TO: + case RX_MGMT_CFG80211_ASSOC_TO: + list_del(&wk->list); + list_add(&wk->list, &free_work); + wk->tries = rma; /* small abuse but only local */ + break; + default: + WARN(1, "unexpected: %d", rma); + } + } - ieee80211_request_internal_scan(sdata, ifmgd->ssid, - ssid_len); + 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)); - ifmgd->state = IEEE80211_STA_MLME_AUTHENTICATE; - set_bit(IEEE80211_STA_REQ_AUTH, &ifmgd->request); - } else { - ifmgd->assoc_scan_tries = 0; - ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_recalc_idle(local); + mutex_unlock(&ifmgd->mtx); + + list_for_each_entry_safe(wk, tmp, &free_work, list) { + switch (wk->tries) { + case RX_MGMT_CFG80211_AUTH_TO: + cfg80211_send_auth_timeout(sdata->dev, + wk->bss->cbss.bssid); + break; + case RX_MGMT_CFG80211_ASSOC_TO: + cfg80211_send_assoc_timeout(sdata->dev, + wk->bss->cbss.bssid); + break; + default: + WARN(1, "unexpected: %d", wk->tries); } + + list_del(&wk->list); + kfree(wk); } - return -1; -} + ieee80211_recalc_idle(local); +} -static void ieee80211_sta_work(struct work_struct *work) +static void ieee80211_sta_bcn_mon_timer(unsigned long data) { struct ieee80211_sub_if_data *sdata = - container_of(work, struct ieee80211_sub_if_data, u.mgd.work); + (struct ieee80211_sub_if_data *) data; struct ieee80211_local *local = sdata->local; - struct ieee80211_if_managed *ifmgd; - struct sk_buff *skb; - if (!netif_running(sdata->dev)) - return; - - if (local->sw_scanning || local->hw_scanning) - return; - - if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) - return; - - /* - * Nothing should have been stuffed into the workqueue during - * the suspend->resume cycle. If this WARN is seen then there - * is a bug with either the driver suspend or something in - * mac80211 stuffing into the workqueue which we haven't yet - * cleared during mac80211's suspend cycle. - */ - if (WARN_ON(local->suspended)) + if (local->quiescing) return; - ifmgd = &sdata->u.mgd; - - while ((skb = skb_dequeue(&ifmgd->skb_queue))) - ieee80211_sta_rx_queued_mgmt(sdata, skb); + ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.beacon_loss_work); +} - if (ifmgd->state != IEEE80211_STA_MLME_DIRECT_PROBE && - ifmgd->state != IEEE80211_STA_MLME_AUTHENTICATE && - ifmgd->state != IEEE80211_STA_MLME_ASSOCIATE && - test_and_clear_bit(IEEE80211_STA_REQ_SCAN, &ifmgd->request)) { - queue_delayed_work(local->hw.workqueue, &local->scan_work, - round_jiffies_relative(0)); - return; - } +static void ieee80211_sta_conn_mon_timer(unsigned long data) +{ + struct ieee80211_sub_if_data *sdata = + (struct ieee80211_sub_if_data *) data; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_local *local = sdata->local; - if (test_and_clear_bit(IEEE80211_STA_REQ_AUTH, &ifmgd->request)) { - if (ieee80211_sta_config_auth(sdata)) - return; - clear_bit(IEEE80211_STA_REQ_RUN, &ifmgd->request); - } else if (!test_and_clear_bit(IEEE80211_STA_REQ_RUN, &ifmgd->request)) + if (local->quiescing) return; - ieee80211_recalc_idle(local); - - switch (ifmgd->state) { - case IEEE80211_STA_MLME_DISABLED: - break; - case IEEE80211_STA_MLME_DIRECT_PROBE: - ieee80211_direct_probe(sdata); - break; - case IEEE80211_STA_MLME_AUTHENTICATE: - ieee80211_authenticate(sdata); - break; - case IEEE80211_STA_MLME_ASSOCIATE: - ieee80211_associate(sdata); - break; - case IEEE80211_STA_MLME_ASSOCIATED: - ieee80211_associated(sdata); - break; - default: - WARN_ON(1); - break; - } + ieee80211_queue_work(&local->hw, &ifmgd->monitor_work); +} - if (ieee80211_privacy_mismatch(sdata)) { - printk(KERN_DEBUG "%s: privacy configuration mismatch and " - "mixed-cell disabled - disassociate\n", sdata->dev->name); +static void ieee80211_sta_monitor_work(struct work_struct *work) +{ + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, + u.mgd.monitor_work); - ieee80211_set_disassoc(sdata, false, true, - WLAN_REASON_UNSPECIFIED); - } + ieee80211_mgd_probe_ap(sdata, false); } static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) { if (sdata->vif.type == NL80211_IFTYPE_STATION) { - /* - * Need to update last_beacon to avoid beacon loss - * test to trigger. - */ - sdata->u.mgd.last_beacon = jiffies; - - - queue_work(sdata->local->hw.workqueue, + sdata->u.mgd.flags &= ~(IEEE80211_STA_BEACON_POLL | + IEEE80211_STA_CONNECTION_POLL); + + /* let's probe the connection once */ + ieee80211_queue_work(&sdata->local->hw, + &sdata->u.mgd.monitor_work); + /* and do all the other regular work too */ + ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.work); } } @@ -2378,6 +2273,11 @@ void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) cancel_work_sync(&ifmgd->chswitch_work); if (del_timer_sync(&ifmgd->chswitch_timer)) set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running); + + cancel_work_sync(&ifmgd->monitor_work); + /* these will just be re-established on connection */ + del_timer_sync(&ifmgd->conn_mon_timer); + del_timer_sync(&ifmgd->bcn_mon_timer); } void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) @@ -2395,210 +2295,277 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd; - u32 hw_flags; ifmgd = &sdata->u.mgd; INIT_WORK(&ifmgd->work, ieee80211_sta_work); + INIT_WORK(&ifmgd->monitor_work, ieee80211_sta_monitor_work); INIT_WORK(&ifmgd->chswitch_work, ieee80211_chswitch_work); INIT_WORK(&ifmgd->beacon_loss_work, ieee80211_beacon_loss_work); setup_timer(&ifmgd->timer, ieee80211_sta_timer, (unsigned long) sdata); + setup_timer(&ifmgd->bcn_mon_timer, ieee80211_sta_bcn_mon_timer, + (unsigned long) sdata); + setup_timer(&ifmgd->conn_mon_timer, ieee80211_sta_conn_mon_timer, + (unsigned long) sdata); setup_timer(&ifmgd->chswitch_timer, ieee80211_chswitch_timer, (unsigned long) sdata); skb_queue_head_init(&ifmgd->skb_queue); + INIT_LIST_HEAD(&ifmgd->work_list); + ifmgd->capab = WLAN_CAPABILITY_ESS; - ifmgd->auth_algs = IEEE80211_AUTH_ALG_OPEN | - IEEE80211_AUTH_ALG_SHARED_KEY; - ifmgd->flags |= IEEE80211_STA_CREATE_IBSS | - IEEE80211_STA_AUTO_BSSID_SEL | - IEEE80211_STA_AUTO_CHANNEL_SEL; + ifmgd->flags = 0; if (sdata->local->hw.queues >= 4) ifmgd->flags |= IEEE80211_STA_WMM_ENABLED; - hw_flags = sdata->local->hw.flags; + mutex_init(&ifmgd->mtx); +} - if (hw_flags & IEEE80211_HW_SUPPORTS_PS) { - ifmgd->powersave = CONFIG_MAC80211_DEFAULT_PS_VALUE; - sdata->local->hw.conf.dynamic_ps_timeout = 500; - } +/* scan finished notification */ +void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata = local->scan_sdata; + + /* Restart STA timers */ + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &local->interfaces, list) + ieee80211_restart_sta_timer(sdata); + rcu_read_unlock(); } -/* configuration hooks */ -void ieee80211_sta_req_auth(struct ieee80211_sub_if_data *sdata) +int ieee80211_max_network_latency(struct notifier_block *nb, + unsigned long data, void *dummy) +{ + s32 latency_usec = (s32) data; + struct ieee80211_local *local = + container_of(nb, struct ieee80211_local, + network_latency_notifier); + + mutex_lock(&local->iflist_mtx); + ieee80211_recalc_ps(local, latency_usec); + mutex_unlock(&local->iflist_mtx); + + return 0; +} + +/* config hooks */ +int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, + struct cfg80211_auth_request *req) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_local *local = sdata->local; + const u8 *ssid; + struct ieee80211_mgd_work *wk; + u16 auth_alg; - if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) - return; + switch (req->auth_type) { + case NL80211_AUTHTYPE_OPEN_SYSTEM: + auth_alg = WLAN_AUTH_OPEN; + break; + case NL80211_AUTHTYPE_SHARED_KEY: + auth_alg = WLAN_AUTH_SHARED_KEY; + break; + case NL80211_AUTHTYPE_FT: + auth_alg = WLAN_AUTH_FT; + break; + case NL80211_AUTHTYPE_NETWORK_EAP: + auth_alg = WLAN_AUTH_LEAP; + break; + default: + return -EOPNOTSUPP; + } - if ((ifmgd->flags & (IEEE80211_STA_BSSID_SET | - IEEE80211_STA_AUTO_BSSID_SEL)) && - (ifmgd->flags & (IEEE80211_STA_SSID_SET | - IEEE80211_STA_AUTO_SSID_SEL))) { + wk = kzalloc(sizeof(*wk) + req->ie_len, GFP_KERNEL); + if (!wk) + return -ENOMEM; - if (ifmgd->state == IEEE80211_STA_MLME_ASSOCIATED) - ieee80211_set_disassoc(sdata, true, true, - WLAN_REASON_DEAUTH_LEAVING); + wk->bss = (void *)req->bss; - if (ifmgd->ssid_len == 0) { - /* - * Only allow association to be started if a valid SSID - * is configured. - */ - return; - } + if (req->ie && req->ie_len) { + memcpy(wk->ie, req->ie, req->ie_len); + wk->ie_len = req->ie_len; + } - if (!(ifmgd->flags & IEEE80211_STA_EXT_SME) || - ifmgd->state != IEEE80211_STA_MLME_ASSOCIATE) - set_bit(IEEE80211_STA_REQ_AUTH, &ifmgd->request); - else if (ifmgd->flags & IEEE80211_STA_EXT_SME) - set_bit(IEEE80211_STA_REQ_RUN, &ifmgd->request); - queue_work(local->hw.workqueue, &ifmgd->work); + if (req->key && req->key_len) { + wk->key_len = req->key_len; + wk->key_idx = req->key_idx; + memcpy(wk->key, req->key, req->key_len); } -} -int ieee80211_sta_commit(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + ssid = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID); + memcpy(wk->ssid, ssid + 2, ssid[1]); + wk->ssid_len = ssid[1]; - if (ifmgd->ssid_len) - ifmgd->flags |= IEEE80211_STA_SSID_SET; - else - ifmgd->flags &= ~IEEE80211_STA_SSID_SET; + wk->state = IEEE80211_MGD_STATE_PROBE; + wk->auth_alg = auth_alg; + wk->timeout = jiffies; /* run right away */ + /* + * XXX: if still associated need to tell AP that we're going + * to sleep and then change channel etc. + */ + sdata->local->oper_channel = req->bss->channel; + ieee80211_hw_config(sdata->local, 0); + + mutex_lock(&ifmgd->mtx); + list_add(&wk->list, &sdata->u.mgd.work_list); + mutex_unlock(&ifmgd->mtx); + + ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.work); return 0; } -int ieee80211_sta_set_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size_t len) +int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, + struct cfg80211_assoc_request *req) { - struct ieee80211_if_managed *ifmgd; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_mgd_work *wk, *found = NULL; + int i, err; - if (len > IEEE80211_MAX_SSID_LEN) - return -EINVAL; + mutex_lock(&ifmgd->mtx); - ifmgd = &sdata->u.mgd; + list_for_each_entry(wk, &ifmgd->work_list, list) { + if (&wk->bss->cbss == req->bss && + wk->state == IEEE80211_MGD_STATE_IDLE) { + found = wk; + break; + } + } - if (ifmgd->ssid_len != len || memcmp(ifmgd->ssid, ssid, len) != 0) { - if (ifmgd->state == IEEE80211_STA_MLME_ASSOCIATED) - ieee80211_set_disassoc(sdata, true, true, - WLAN_REASON_DEAUTH_LEAVING); + if (!found) { + err = -ENOLINK; + goto out; + } - /* - * Do not use reassociation if SSID is changed (different ESS). - */ - ifmgd->flags &= ~IEEE80211_STA_PREV_BSSID_SET; - memset(ifmgd->ssid, 0, sizeof(ifmgd->ssid)); - memcpy(ifmgd->ssid, ssid, len); - ifmgd->ssid_len = len; + list_del(&found->list); + + wk = krealloc(found, sizeof(*wk) + req->ie_len, GFP_KERNEL); + if (!wk) { + list_add(&found->list, &ifmgd->work_list); + err = -ENOMEM; + goto out; } - return ieee80211_sta_commit(sdata); -} + list_add(&wk->list, &ifmgd->work_list); -int ieee80211_sta_get_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size_t *len) -{ - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - memcpy(ssid, ifmgd->ssid, ifmgd->ssid_len); - *len = ifmgd->ssid_len; - return 0; -} + ifmgd->flags &= ~IEEE80211_STA_DISABLE_11N; -int ieee80211_sta_set_bssid(struct ieee80211_sub_if_data *sdata, u8 *bssid) -{ - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + for (i = 0; i < req->crypto.n_ciphers_pairwise; i++) + if (req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP40 || + req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_TKIP || + req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) + ifmgd->flags |= IEEE80211_STA_DISABLE_11N; - if (compare_ether_addr(bssid, ifmgd->bssid) != 0 && - ifmgd->state == IEEE80211_STA_MLME_ASSOCIATED) - ieee80211_set_disassoc(sdata, true, true, - WLAN_REASON_DEAUTH_LEAVING); + sdata->local->oper_channel = req->bss->channel; + ieee80211_hw_config(sdata->local, 0); - if (is_valid_ether_addr(bssid)) { - memcpy(ifmgd->bssid, bssid, ETH_ALEN); - ifmgd->flags |= IEEE80211_STA_BSSID_SET; + if (req->ie && req->ie_len) { + memcpy(wk->ie, req->ie, req->ie_len); + wk->ie_len = req->ie_len; + } else + wk->ie_len = 0; + + if (req->prev_bssid) + memcpy(wk->prev_bssid, req->prev_bssid, ETH_ALEN); + + wk->state = IEEE80211_MGD_STATE_ASSOC; + wk->tries = 0; + wk->timeout = jiffies; /* run right away */ + + if (req->use_mfp) { + ifmgd->mfp = IEEE80211_MFP_REQUIRED; + ifmgd->flags |= IEEE80211_STA_MFP_ENABLED; } else { - memset(ifmgd->bssid, 0, ETH_ALEN); - ifmgd->flags &= ~IEEE80211_STA_BSSID_SET; + ifmgd->mfp = IEEE80211_MFP_DISABLED; + ifmgd->flags &= ~IEEE80211_STA_MFP_ENABLED; } - return ieee80211_sta_commit(sdata); + if (req->crypto.control_port) + ifmgd->flags |= IEEE80211_STA_CONTROL_PORT; + else + ifmgd->flags &= ~IEEE80211_STA_CONTROL_PORT; + + ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.work); + + err = 0; + + out: + mutex_unlock(&ifmgd->mtx); + return err; } -int ieee80211_sta_set_extra_ie(struct ieee80211_sub_if_data *sdata, - const char *ie, size_t len) +int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, + struct cfg80211_deauth_request *req, + void *cookie) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_mgd_work *wk; + const u8 *bssid = NULL; + + mutex_lock(&ifmgd->mtx); + + if (ifmgd->associated && &ifmgd->associated->cbss == req->bss) { + bssid = req->bss->bssid; + 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; + list_del(&wk->list); + kfree(wk); + break; + } + } - if (len == 0 && ifmgd->extra_ie_len == 0) - return -EALREADY; + /* + * cfg80211 should catch this ... but it's racy since + * we can receive a deauth frame, process it, hand it + * to cfg80211 while that's in a locked section already + * trying to tell us that the user wants to disconnect. + */ + if (!bssid) { + mutex_unlock(&ifmgd->mtx); + return -ENOLINK; + } - if (len == ifmgd->extra_ie_len && ifmgd->extra_ie && - memcmp(ifmgd->extra_ie, ie, len) == 0) - return -EALREADY; + mutex_unlock(&ifmgd->mtx); - kfree(ifmgd->extra_ie); - if (len == 0) { - ifmgd->extra_ie = NULL; - ifmgd->extra_ie_len = 0; - return 0; - } - ifmgd->extra_ie = kmalloc(len, GFP_KERNEL); - if (!ifmgd->extra_ie) { - ifmgd->extra_ie_len = 0; - return -ENOMEM; - } - memcpy(ifmgd->extra_ie, ie, len); - ifmgd->extra_ie_len = len; - return 0; -} + printk(KERN_DEBUG "%s: deauthenticating from %pM by local choice (reason=%d)\n", + sdata->dev->name, bssid, req->reason_code); -int ieee80211_sta_deauthenticate(struct ieee80211_sub_if_data *sdata, u16 reason) -{ - printk(KERN_DEBUG "%s: deauthenticating by local choice (reason=%d)\n", - sdata->dev->name, reason); + ieee80211_send_deauth_disassoc(sdata, bssid, + IEEE80211_STYPE_DEAUTH, req->reason_code, + cookie); - ieee80211_set_disassoc(sdata, true, true, reason); return 0; } -int ieee80211_sta_disassociate(struct ieee80211_sub_if_data *sdata, u16 reason) +int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, + struct cfg80211_disassoc_request *req, + void *cookie) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - printk(KERN_DEBUG "%s: disassociating by local choice (reason=%d)\n", - sdata->dev->name, reason); + mutex_lock(&ifmgd->mtx); - if (!(ifmgd->flags & IEEE80211_STA_ASSOCIATED)) + /* + * cfg80211 should catch this ... but it's racy since + * we can receive a disassoc frame, process it, hand it + * to cfg80211 while that's in a locked section already + * trying to tell us that the user wants to disconnect. + */ + if (&ifmgd->associated->cbss != req->bss) { + mutex_unlock(&ifmgd->mtx); return -ENOLINK; + } - ieee80211_set_disassoc(sdata, false, true, reason); - return 0; -} - -/* scan finished notification */ -void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata = local->scan_sdata; - - /* Restart STA timers */ - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - ieee80211_restart_sta_timer(sdata); - rcu_read_unlock(); -} + printk(KERN_DEBUG "%s: disassociating from %pM by local choice (reason=%d)\n", + sdata->dev->name, req->bss->bssid, req->reason_code); -int ieee80211_max_network_latency(struct notifier_block *nb, - unsigned long data, void *dummy) -{ - s32 latency_usec = (s32) data; - struct ieee80211_local *local = - container_of(nb, struct ieee80211_local, - network_latency_notifier); + ieee80211_set_disassoc(sdata, false); - mutex_lock(&local->iflist_mtx); - ieee80211_recalc_ps(local, latency_usec); - mutex_unlock(&local->iflist_mtx); + mutex_unlock(&ifmgd->mtx); + ieee80211_send_deauth_disassoc(sdata, req->bss->bssid, + IEEE80211_STYPE_DISASSOC, req->reason_code, + cookie); return 0; } diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 5e3d476972f..e535f1c988f 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -26,7 +26,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) /* make quiescing visible to timers everywhere */ mb(); - flush_workqueue(local->hw.workqueue); + flush_workqueue(local->workqueue); /* Don't try to run timers while suspended. */ del_timer_sync(&local->sta_cleanup); @@ -96,6 +96,10 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) if (!netif_running(sdata->dev)) continue; + /* disable beaconing */ + ieee80211_bss_info_change_notify(sdata, + BSS_CHANGED_BEACON_ENABLED); + conf.vif = &sdata->vif; conf.type = sdata->vif.type; conf.mac_addr = sdata->dev->dev_addr; @@ -103,17 +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->hw.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/rate.c b/net/mac80211/rate.c index 4641f00a1e5..b33efc4fc26 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -198,6 +198,35 @@ static void rate_control_release(struct kref *kref) kfree(ctrl_ref); } +static bool rc_no_data_or_no_ack(struct ieee80211_tx_rate_control *txrc) +{ + struct sk_buff *skb = txrc->skb; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + __le16 fc; + + fc = hdr->frame_control; + + return ((info->flags & IEEE80211_TX_CTL_NO_ACK) || !ieee80211_is_data(fc)); +} + +bool rate_control_send_low(struct ieee80211_sta *sta, + void *priv_sta, + struct ieee80211_tx_rate_control *txrc) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(txrc->skb); + + if (!sta || !priv_sta || rc_no_data_or_no_ack(txrc)) { + info->control.rates[0].idx = rate_lowest_index(txrc->sband, sta); + info->control.rates[0].count = + (info->flags & IEEE80211_TX_CTL_NO_ACK) ? + 1 : txrc->hw->max_rate_tries; + return true; + } + return false; +} +EXPORT_SYMBOL(rate_control_send_low); + void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_tx_rate_control *txrc) @@ -258,7 +287,7 @@ int ieee80211_init_rate_ctrl_alg(struct ieee80211_local *local, struct rate_control_ref *ref, *old; ASSERT_RTNL(); - if (local->open_count || netif_running(local->mdev)) + if (local->open_count) return -EBUSY; ref = rate_control_alloc(name, local); diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 37771abd8f5..6e5d68b4e42 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -70,20 +70,6 @@ rix_to_ndx(struct minstrel_sta_info *mi, int rix) return i; } -static inline bool -use_low_rate(struct sk_buff *skb) -{ - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - u16 fc; - - fc = le16_to_cpu(hdr->frame_control); - - return ((info->flags & IEEE80211_TX_CTL_NO_ACK) || - (fc & IEEE80211_FCTL_FTYPE) != IEEE80211_FTYPE_DATA); -} - - static void minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) { @@ -232,7 +218,6 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, struct ieee80211_tx_rate_control *txrc) { struct sk_buff *skb = txrc->skb; - struct ieee80211_supported_band *sband = txrc->sband; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct minstrel_sta_info *mi = priv_sta; struct minstrel_priv *mp = priv; @@ -245,14 +230,8 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, int mrr_ndx[3]; int sample_rate; - if (!sta || !mi || use_low_rate(skb)) { - ar[0].idx = rate_lowest_index(sband, sta); - if (info->flags & IEEE80211_TX_CTL_NO_ACK) - ar[0].count = 1; - else - ar[0].count = mp->max_retry; + if (rate_control_send_low(sta, priv_sta, txrc)) return; - } mrr = mp->has_mrr && !txrc->rts && !txrc->bss_conf->use_cts_prot; @@ -439,7 +418,7 @@ minstrel_rate_init(void *priv, struct ieee80211_supported_band *sband, /* contention window */ tx_time_single += t_slot + min(cw, mp->cw_max); - cw = (cw + 1) << 1; + cw = (cw << 1) | 1; tx_time += tx_time_single; tx_time_cts += tx_time_single + mi->sp_ack_dur; diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index 869fe0ef951..38bf4168fc3 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 98f48070805..a715d9454f6 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 a0bef767ceb..699d3ed869c 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; @@ -276,11 +266,9 @@ rate_control_pid_get_rate(void *priv, struct ieee80211_sta *sta, { struct sk_buff *skb = txrc->skb; struct ieee80211_supported_band *sband = txrc->sband; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct rc_pid_sta_info *spinfo = priv_sta; int rateidx; - u16 fc; if (txrc->rts) info->control.rates[0].count = @@ -290,16 +278,8 @@ rate_control_pid_get_rate(void *priv, struct ieee80211_sta *sta, txrc->hw->conf.short_frame_max_tx_count; /* Send management frames and NO_ACK data using lowest rate. */ - fc = le16_to_cpu(hdr->frame_control); - if (!sta || !spinfo || - (fc & IEEE80211_FCTL_FTYPE) != IEEE80211_FTYPE_DATA || - info->flags & IEEE80211_TX_CTL_NO_ACK) { - info->control.rates[0].idx = rate_lowest_index(sband, sta); - if (info->flags & IEEE80211_TX_CTL_NO_ACK) - info->control.rates[0].count = 1; - + if (rate_control_send_low(sta, priv_sta, txrc)) return; - } rateidx = spinfo->txrate_idx; @@ -321,7 +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; @@ -358,9 +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 a08a9b53034..45667054a5f 100644 --- a/net/mac80211/rc80211_pid_debugfs.c +++ b/net/mac80211/rc80211_pid_debugfs.c @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/poll.h> #include <linux/netdevice.h> @@ -198,7 +199,7 @@ 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 0936fc24942..7170bf4565a 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -30,7 +30,6 @@ static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *skb, - struct ieee80211_rx_status *status, u16 mpdu_seq_num, int bar_req); /* @@ -59,11 +58,11 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local, return skb; } -static inline int should_drop_frame(struct ieee80211_rx_status *status, - struct sk_buff *skb, +static inline int should_drop_frame(struct sk_buff *skb, int present_fcs_len, int radiotap_len) { + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; if (status->flag & (RX_FLAG_FAILED_FCS_CRC | RX_FLAG_FAILED_PLCP_CRC)) @@ -111,10 +110,10 @@ ieee80211_rx_radiotap_len(struct ieee80211_local *local, static void ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, struct sk_buff *skb, - struct ieee80211_rx_status *status, struct ieee80211_rate *rate, int rtap_len) { + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_radiotap_header *rthdr; unsigned char *pos; @@ -220,9 +219,9 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, */ static struct sk_buff * ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, - struct ieee80211_rx_status *status, struct ieee80211_rate *rate) { + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(origskb); struct ieee80211_sub_if_data *sdata; int needed_headroom = 0; struct sk_buff *skb, *skb2; @@ -248,8 +247,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, present_fcs_len = FCS_LEN; if (!local->monitors) { - if (should_drop_frame(status, origskb, present_fcs_len, - rtap_len)) { + if (should_drop_frame(origskb, present_fcs_len, rtap_len)) { dev_kfree_skb(origskb); return NULL; } @@ -257,7 +255,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, return remove_monitor_info(local, origskb, rtap_len); } - if (should_drop_frame(status, origskb, present_fcs_len, rtap_len)) { + if (should_drop_frame(origskb, present_fcs_len, rtap_len)) { /* only need to expand headroom if necessary */ skb = origskb; origskb = NULL; @@ -289,7 +287,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, /* if necessary, prepend radiotap information */ if (!(status->flag & RX_FLAG_RADIOTAP)) - ieee80211_add_rx_radiotap_header(local, skb, status, rate, + ieee80211_add_rx_radiotap_header(local, skb, rate, needed_headroom); skb_reset_mac_header(skb); @@ -420,13 +418,13 @@ ieee80211_rx_h_passive_scan(struct ieee80211_rx_data *rx) struct ieee80211_local *local = rx->local; struct sk_buff *skb = rx->skb; - if (unlikely(local->hw_scanning)) - return ieee80211_scan_rx(rx->sdata, skb, rx->status); + if (unlikely(test_bit(SCAN_HW_SCANNING, &local->scanning))) + return ieee80211_scan_rx(rx->sdata, skb); - if (unlikely(local->sw_scanning)) { + if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning) && + (rx->flags & IEEE80211_RX_IN_SCAN))) { /* drop all the other packets during a software scan anyway */ - if (ieee80211_scan_rx(rx->sdata, skb, rx->status) - != RX_QUEUED) + if (ieee80211_scan_rx(rx->sdata, skb) != RX_QUEUED) dev_kfree_skb(skb); return RX_QUEUED; } @@ -491,12 +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 @@ -529,7 +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 @@ -785,7 +792,7 @@ static void ap_sta_ps_start(struct sta_info *sta) struct ieee80211_local *local = sdata->local; atomic_inc(&sdata->bss->num_sta_ps); - set_and_clear_sta_flags(sta, WLAN_STA_PS, WLAN_STA_PSPOLL); + set_sta_flags(sta, WLAN_STA_PS); drv_sta_notify(local, &sdata->vif, STA_NOTIFY_SLEEP, &sta->sta); #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG printk(KERN_DEBUG "%s: STA %pM aid %d enters power save mode\n", @@ -801,7 +808,7 @@ static int ap_sta_ps_end(struct sta_info *sta) atomic_dec(&sdata->bss->num_sta_ps); - clear_sta_flags(sta, WLAN_STA_PS | WLAN_STA_PSPOLL); + clear_sta_flags(sta, WLAN_STA_PS); drv_sta_notify(local, &sdata->vif, STA_NOTIFY_AWAKE, &sta->sta); if (!skb_queue_empty(&sta->ps_tx_buf)) @@ -836,28 +843,22 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) if (!sta) return RX_CONTINUE; - /* Update last_rx only for IBSS packets which are for the current - * BSSID to avoid keeping the current IBSS network alive in cases where - * other STAs are using different BSSID. */ + /* + * Update last_rx only for IBSS packets which are for the current + * BSSID to avoid keeping the current IBSS network alive in cases + * where other STAs start using different BSSID. + */ if (rx->sdata->vif.type == NL80211_IFTYPE_ADHOC) { u8 *bssid = ieee80211_get_bssid(hdr, rx->skb->len, NL80211_IFTYPE_ADHOC); if (compare_ether_addr(bssid, rx->sdata->u.ibss.bssid) == 0) sta->last_rx = jiffies; - } else - if (!is_multicast_ether_addr(hdr->addr1) || - rx->sdata->vif.type == NL80211_IFTYPE_STATION) { - /* Update last_rx only for unicast frames in order to prevent - * the Probe Request frames (the only broadcast frames from a - * STA in infrastructure mode) from keeping a connection alive. + } else if (!is_multicast_ether_addr(hdr->addr1)) { + /* * Mesh beacons will update last_rx when if they are found to * match the current local configuration when processed. */ - if (rx->sdata->vif.type == NL80211_IFTYPE_STATION && - ieee80211_is_beacon(hdr->frame_control)) { - rx->sdata->u.mgd.last_beacon = jiffies; - } else - sta->last_rx = jiffies; + sta->last_rx = jiffies; } if (!(rx->flags & IEEE80211_RX_RA_MATCH)) @@ -1125,14 +1126,15 @@ ieee80211_rx_h_ps_poll(struct ieee80211_rx_data *rx) skb_queue_empty(&rx->sta->ps_tx_buf); if (skb) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; /* - * Tell TX path to send one frame even though the STA may + * Tell TX path to send this frame even though the STA may * still remain is PS mode after this frame exchange. */ - set_sta_flags(rx->sta, WLAN_STA_PSPOLL); + info->flags |= IEEE80211_TX_CTL_PSPOLL_RESPONSE; #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG printk(KERN_DEBUG "STA %pM aid %d: PS Poll (entries after %d)\n", @@ -1147,7 +1149,7 @@ ieee80211_rx_h_ps_poll(struct ieee80211_rx_data *rx) else hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA); - dev_queue_xmit(skb); + ieee80211_add_pending_skb(rx->local, skb); if (no_pending_pkts) sta_info_clear_tim_bit(rx->sta); @@ -1487,10 +1489,13 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211s_hdr *mesh_hdr; unsigned int hdrlen; struct sk_buff *skb = rx->skb, *fwd_skb; + struct ieee80211_local *local = rx->local; + struct ieee80211_sub_if_data *sdata; hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + sdata = IEEE80211_DEV_TO_SUB_IF(rx->dev); if (!ieee80211_is_data(hdr->frame_control)) return RX_CONTINUE; @@ -1499,11 +1504,10 @@ 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){ - struct ieee80211_sub_if_data *sdata; + if (!is_multicast_ether_addr(hdr->addr1) && + (mesh_hdr->flags & MESH_FLAGS_AE_A5_A6)) { struct mesh_path *mppath; - sdata = IEEE80211_DEV_TO_SUB_IF(rx->dev); rcu_read_lock(); mppath = mpp_path_lookup(mesh_hdr->eaddr2, sdata); if (!mppath) { @@ -1518,7 +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--; @@ -1529,6 +1535,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) dropped_frames_ttl); else { struct ieee80211_hdr *fwd_hdr; + struct ieee80211_tx_info *info; + fwd_skb = skb_copy(skb, GFP_ATOMIC); if (!fwd_skb && net_ratelimit()) @@ -1536,19 +1544,40 @@ 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); - fwd_skb->dev = rx->local->mdev; - fwd_skb->iif = rx->dev->ifindex; - dev_queue_xmit(fwd_skb); + 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->addr1)) + IEEE80211_IFSTA_MESH_CTR_INC(&sdata->u.mesh, + fwded_mcast); + else { + 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); + ieee80211_add_pending_skb(local, fwd_skb); } } - if (is_multicast_ether_addr(hdr->addr3) || + if (is_multicast_ether_addr(hdr->addr1) || rx->dev->flags & IFF_PROMISC) return RX_CONTINUE; else @@ -1620,7 +1649,7 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx) /* manage reordering buffer according to requested */ /* sequence number */ rcu_read_lock(); - ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, NULL, NULL, + ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, NULL, start_seq_num, 1); rcu_read_unlock(); return RX_DROP_UNUSABLE; @@ -1644,12 +1673,7 @@ static void ieee80211_process_sa_query_req(struct ieee80211_sub_if_data *sdata, if (compare_ether_addr(mgmt->sa, sdata->u.mgd.bssid) != 0 || compare_ether_addr(mgmt->bssid, sdata->u.mgd.bssid) != 0) { - /* Not from the current AP. */ - return; - } - - if (sdata->u.mgd.state == IEEE80211_STA_MLME_ASSOCIATE) { - /* Association in progress; ignore SA Query */ + /* Not from the current AP or not associated yet. */ return; } @@ -1686,7 +1710,6 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) struct ieee80211_local *local = rx->local; struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(rx->dev); struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *) rx->skb->data; - struct ieee80211_bss *bss; int len = rx->skb->len; if (!ieee80211_is_action(mgmt->frame_control)) @@ -1764,17 +1787,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) if (memcmp(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN)) return RX_DROP_MONITOR; - bss = ieee80211_rx_bss_get(local, sdata->u.mgd.bssid, - local->hw.conf.channel->center_freq, - sdata->u.mgd.ssid, - sdata->u.mgd.ssid_len); - if (!bss) - return RX_DROP_MONITOR; - - ieee80211_sta_process_chanswitch(sdata, - &mgmt->u.action.u.chan_switch.sw_elem, bss); - ieee80211_rx_bss_put(local, bss); - break; + return ieee80211_sta_rx_mgmt(sdata, rx->skb); } break; case WLAN_CATEGORY_SA_QUERY: @@ -1817,19 +1830,18 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; if (ieee80211_vif_is_mesh(&sdata->vif)) - return ieee80211_mesh_rx_mgmt(sdata, rx->skb, rx->status); + return ieee80211_mesh_rx_mgmt(sdata, rx->skb); if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - return ieee80211_ibss_rx_mgmt(sdata, rx->skb, rx->status); + return ieee80211_ibss_rx_mgmt(sdata, rx->skb); if (sdata->vif.type == NL80211_IFTYPE_STATION) - return ieee80211_sta_rx_mgmt(sdata, rx->skb, rx->status); + return ieee80211_sta_rx_mgmt(sdata, rx->skb); return RX_DROP_MONITOR; } -static void ieee80211_rx_michael_mic_report(struct net_device *dev, - struct ieee80211_hdr *hdr, +static void ieee80211_rx_michael_mic_report(struct ieee80211_hdr *hdr, struct ieee80211_rx_data *rx) { int keyidx; @@ -1866,7 +1878,8 @@ static void ieee80211_rx_michael_mic_report(struct net_device *dev, !ieee80211_is_auth(hdr->frame_control)) goto ignore; - mac80211_ev_michael_mic_failure(rx->sdata, keyidx, hdr, NULL); + mac80211_ev_michael_mic_failure(rx->sdata, keyidx, hdr, NULL, + GFP_ATOMIC); ignore: dev_kfree_skb(rx->skb); rx->skb = NULL; @@ -2028,13 +2041,8 @@ static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_STATION: if (!bssid) return 0; - if (!ieee80211_bssid_match(bssid, sdata->u.mgd.bssid)) { - if (!(rx->flags & IEEE80211_RX_IN_SCAN)) - return 0; - rx->flags &= ~IEEE80211_RX_RA_MATCH; - } else if (!multicast && - compare_ether_addr(sdata->dev->dev_addr, - hdr->addr1) != 0) { + if (!multicast && + compare_ether_addr(sdata->dev->dev_addr, hdr->addr1) != 0) { if (!(sdata->dev->flags & IFF_PROMISC)) return 0; rx->flags &= ~IEEE80211_RX_RA_MATCH; @@ -2114,9 +2122,9 @@ static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, */ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, struct sk_buff *skb, - struct ieee80211_rx_status *status, struct ieee80211_rate *rate) { + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr; @@ -2143,11 +2151,12 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, } if ((status->flag & RX_FLAG_MMIC_ERROR)) { - ieee80211_rx_michael_mic_report(local->mdev, hdr, &rx); + ieee80211_rx_michael_mic_report(hdr, &rx); return; } - if (unlikely(local->sw_scanning || local->hw_scanning)) + if (unlikely(test_bit(SCAN_HW_SCANNING, &local->scanning) || + test_bit(SCAN_OFF_CHANNEL, &local->scanning))) rx.flags |= IEEE80211_RX_IN_SCAN; ieee80211_parse_qos(&rx); @@ -2155,11 +2164,17 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, skb = rx.skb; - list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (rx.sdata && ieee80211_is_data(hdr->frame_control)) { + rx.flags |= IEEE80211_RX_RA_MATCH; + prepares = prepare_for_handlers(rx.sdata, &rx, hdr); + if (prepares) + prev = rx.sdata; + } else list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (!netif_running(sdata->dev)) continue; - if (sdata->vif.type == NL80211_IFTYPE_MONITOR) + if (sdata->vif.type == NL80211_IFTYPE_MONITOR || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN) continue; rx.flags |= IEEE80211_RX_RA_MATCH; @@ -2227,20 +2242,21 @@ static void ieee80211_release_reorder_frame(struct ieee80211_hw *hw, { struct ieee80211_supported_band *sband; struct ieee80211_rate *rate; - struct ieee80211_rx_status status; + struct sk_buff *skb = tid_agg_rx->reorder_buf[index]; + struct ieee80211_rx_status *status; - if (!tid_agg_rx->reorder_buf[index]) + if (!skb) goto no_frame; + status = IEEE80211_SKB_RXCB(skb); + /* release the reordered frames to stack */ - memcpy(&status, tid_agg_rx->reorder_buf[index]->cb, sizeof(status)); - sband = hw->wiphy->bands[status.band]; - if (status.flag & RX_FLAG_HT) + sband = hw->wiphy->bands[status->band]; + if (status->flag & RX_FLAG_HT) rate = sband->bitrates; /* TODO: HT rates */ else - rate = &sband->bitrates[status.rate_idx]; - __ieee80211_rx_handle_packet(hw, tid_agg_rx->reorder_buf[index], - &status, rate); + rate = &sband->bitrates[status->rate_idx]; + __ieee80211_rx_handle_packet(hw, skb, rate); tid_agg_rx->stored_mpdu_num--; tid_agg_rx->reorder_buf[index] = NULL; @@ -2265,7 +2281,6 @@ no_frame: static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, struct tid_ampdu_rx *tid_agg_rx, struct sk_buff *skb, - struct ieee80211_rx_status *rxstatus, u16 mpdu_seq_num, int bar_req) { @@ -2324,8 +2339,6 @@ static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, /* put the frame in the reordering buffer */ tid_agg_rx->reorder_buf[index] = skb; tid_agg_rx->reorder_time[index] = jiffies; - memcpy(tid_agg_rx->reorder_buf[index]->cb, rxstatus, - sizeof(*rxstatus)); tid_agg_rx->stored_mpdu_num++; /* release the buffer until next missing frame */ index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) @@ -2374,8 +2387,7 @@ static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, } static u8 ieee80211_rx_reorder_ampdu(struct ieee80211_local *local, - struct sk_buff *skb, - struct ieee80211_rx_status *status) + struct sk_buff *skb) { struct ieee80211_hw *hw = &local->hw; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -2424,7 +2436,7 @@ static u8 ieee80211_rx_reorder_ampdu(struct ieee80211_local *local, /* according to mpdu sequence number deal with reordering buffer */ mpdu_seq_num = (sc & IEEE80211_SCTL_SEQ) >> 4; - ret = ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, skb, status, + ret = ieee80211_sta_manage_reorder_buf(hw, tid_agg_rx, skb, mpdu_seq_num, 0); end_reorder: return ret; @@ -2434,24 +2446,22 @@ 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, - struct ieee80211_rx_status *status) +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; - } + WARN_ON_ONCE(softirq_count() == 0); + + 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 @@ -2460,16 +2470,21 @@ 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. */ @@ -2477,7 +2492,7 @@ 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]; } @@ -2494,7 +2509,7 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb, * if it was previously present. * Also, frames with less than 16 bytes are dropped. */ - skb = ieee80211_rx_monitor(local, skb, status, rate); + skb = ieee80211_rx_monitor(local, skb, rate); if (!skb) { rcu_read_unlock(); return; @@ -2512,25 +2527,25 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb, * frames from other than operational channel), but that should not * happen in normal networks. */ - if (!ieee80211_rx_reorder_ampdu(local, skb, status)) - __ieee80211_rx_handle_packet(hw, skb, status, rate); + if (!ieee80211_rx_reorder_ampdu(local, 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 */ -void ieee80211_rx_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb, - struct ieee80211_rx_status *status) +void ieee80211_rx_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb) { struct ieee80211_local *local = hw_to_local(hw); BUILD_BUG_ON(sizeof(struct ieee80211_rx_status) > sizeof(skb->cb)); - skb->dev = local->mdev; - /* copy status into skb->cb for use by tasklet */ - memcpy(skb->cb, status, sizeof(*status)); skb->pkt_type = IEEE80211_RX_MSG; skb_queue_tail(&local->skb_queue, skb); tasklet_schedule(&local->tasklet); diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 2a8d09ad17f..71e10cabf81 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -18,7 +18,6 @@ #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <net/mac80211.h> -#include <net/iw_handler.h> #include "ieee80211_i.h" #include "driver-ops.h" @@ -26,7 +25,7 @@ #define IEEE80211_PROBE_DELAY (HZ / 33) #define IEEE80211_CHANNEL_TIME (HZ / 33) -#define IEEE80211_PASSIVE_CHANNEL_TIME (HZ / 5) +#define IEEE80211_PASSIVE_CHANNEL_TIME (HZ / 8) struct ieee80211_bss * ieee80211_rx_bss_get(struct ieee80211_local *local, u8 *bssid, int freq, @@ -91,8 +90,8 @@ ieee80211_bss_info_update(struct ieee80211_local *local, bss->dtim_period = tim_ie->dtim_period; } - /* set default value for buggy APs */ - if (!elems->tim || bss->dtim_period == 0) + /* set default value for buggy AP/no TIM element */ + if (bss->dtim_period == 0) bss->dtim_period = 1; bss->supp_rates_len = 0; @@ -121,23 +120,10 @@ ieee80211_bss_info_update(struct ieee80211_local *local, return bss; } -void ieee80211_rx_bss_remove(struct ieee80211_sub_if_data *sdata, u8 *bssid, - int freq, u8 *ssid, u8 ssid_len) -{ - struct ieee80211_bss *bss; - struct ieee80211_local *local = sdata->local; - - bss = ieee80211_rx_bss_get(local, bssid, freq, ssid, ssid_len); - if (bss) { - cfg80211_unlink_bss(local->hw.wiphy, (void *)bss); - ieee80211_rx_bss_put(local, bss); - } -} - ieee80211_rx_result -ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - struct ieee80211_rx_status *rx_status) +ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { + struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); struct ieee80211_mgmt *mgmt; struct ieee80211_bss *bss; u8 *elements; @@ -278,7 +264,7 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) mutex_lock(&local->scan_mtx); - if (WARN_ON(!local->hw_scanning && !local->sw_scanning)) { + if (WARN_ON(!local->scanning)) { mutex_unlock(&local->scan_mtx); return; } @@ -288,16 +274,16 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) return; } - if (local->hw_scanning) + 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 = local->hw_scanning; - local->hw_scanning = false; - local->sw_scanning = false; + was_hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning); + local->scanning = 0; local->scan_channel = NULL; /* we only have to protect scan_req and hw/sw scan */ @@ -307,16 +293,7 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) if (was_hw_scan) goto done; - netif_tx_lock_bh(local->mdev); - netif_addr_lock(local->mdev); - local->filter_flags &= ~FIF_BCN_PRBRESP_PROMISC; - drv_configure_filter(local, FIF_BCN_PRBRESP_PROMISC, - &local->filter_flags, - local->mdev->mc_count, - local->mdev->mc_list); - - netif_addr_unlock(local->mdev); - netif_tx_unlock_bh(local->mdev); + ieee80211_configure_filter(local); drv_sw_scan_complete(local); @@ -327,7 +304,7 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) /* Tell AP we're back */ if (sdata->vif.type == NL80211_IFTYPE_STATION) { - if (sdata->u.mgd.flags & IEEE80211_STA_ASSOCIATED) { + if (sdata->u.mgd.associated) { ieee80211_scan_ps_disable(sdata); netif_tx_wake_all_queues(sdata->dev); } @@ -382,30 +359,24 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) ieee80211_bss_info_change_notify( sdata, BSS_CHANGED_BEACON_ENABLED); - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - if (sdata->u.mgd.flags & IEEE80211_STA_ASSOCIATED) { - netif_tx_stop_all_queues(sdata->dev); - ieee80211_scan_ps_enable(sdata); - } - } else + /* + * only handle non-STA interfaces here, STA interfaces + * are handled in the scan state machine + */ + if (sdata->vif.type != NL80211_IFTYPE_STATION) netif_tx_stop_all_queues(sdata->dev); } mutex_unlock(&local->iflist_mtx); - local->scan_state = SCAN_SET_CHANNEL; + local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; - netif_addr_lock_bh(local->mdev); - local->filter_flags |= FIF_BCN_PRBRESP_PROMISC; - drv_configure_filter(local, FIF_BCN_PRBRESP_PROMISC, - &local->filter_flags, - local->mdev->mc_count, - local->mdev->mc_list); - netif_addr_unlock_bh(local->mdev); + ieee80211_configure_filter(local); /* TODO: start scan as soon as all nullfunc frames are ACKed */ - queue_delayed_work(local->hw.workqueue, &local->scan_work, - IEEE80211_CHANNEL_TIME); + ieee80211_queue_delayed_work(&local->hw, + &local->scan_work, + IEEE80211_CHANNEL_TIME); return 0; } @@ -441,20 +412,18 @@ 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 && - (ifmgd->state == IEEE80211_STA_MLME_DIRECT_PROBE || - ifmgd->state == IEEE80211_STA_MLME_AUTHENTICATE || - ifmgd->state == IEEE80211_STA_MLME_ASSOCIATE)) { - /* actually wait for the assoc to finish/time out */ + !list_empty(&ifmgd->work_list)) { + /* actually wait for the work it's doing to finish/time out */ set_bit(IEEE80211_STA_REQ_SCAN, &ifmgd->request); return 0; } if (local->ops->hw_scan) - local->hw_scanning = true; + __set_bit(SCAN_HW_SCANNING, &local->scanning); else - local->sw_scanning = true; + __set_bit(SCAN_SW_SCANNING, &local->scanning); /* * Kicking off the scan need not be protected, * only the scan variable stuff, since now @@ -477,11 +446,9 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, mutex_lock(&local->scan_mtx); if (rc) { - if (local->ops->hw_scan) { - local->hw_scanning = false; + if (local->ops->hw_scan) ieee80211_restore_scan_ies(local); - } else - local->sw_scanning = false; + local->scanning = 0; ieee80211_recalc_idle(local); @@ -492,13 +459,195 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, return rc; } +static int ieee80211_scan_state_decision(struct ieee80211_local *local, + unsigned long *next_delay) +{ + bool associated = false; + struct ieee80211_sub_if_data *sdata; + + /* if no more bands/channels left, complete scan and advance to the idle state */ + if (local->scan_channel_idx >= local->scan_req->n_channels) { + ieee80211_scan_completed(&local->hw, false); + return 1; + } + + /* check if at least one STA interface is associated */ + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata, &local->interfaces, list) { + if (!netif_running(sdata->dev)) + continue; + + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + if (sdata->u.mgd.associated) { + associated = true; + break; + } + } + } + mutex_unlock(&local->iflist_mtx); + + if (local->scan_channel) { + /* + * we're currently scanning a different channel, let's + * switch back to the operating channel now if at least + * one interface is associated. Otherwise just scan the + * next channel + */ + if (associated) + local->next_scan_state = SCAN_ENTER_OPER_CHANNEL; + else + local->next_scan_state = SCAN_SET_CHANNEL; + } else { + /* + * we're on the operating channel currently, let's + * leave that channel now to scan another one + */ + local->next_scan_state = SCAN_LEAVE_OPER_CHANNEL; + } + + *next_delay = 0; + return 0; +} + +static void ieee80211_scan_state_leave_oper_channel(struct ieee80211_local *local, + unsigned long *next_delay) +{ + struct ieee80211_sub_if_data *sdata; + + /* + * notify the AP about us leaving the channel and stop all STA interfaces + */ + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata, &local->interfaces, list) { + if (!netif_running(sdata->dev)) + continue; + + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + netif_tx_stop_all_queues(sdata->dev); + if (sdata->u.mgd.associated) + ieee80211_scan_ps_enable(sdata); + } + } + mutex_unlock(&local->iflist_mtx); + + __set_bit(SCAN_OFF_CHANNEL, &local->scanning); + + /* advance to the next channel to be scanned */ + *next_delay = HZ / 10; + local->next_scan_state = SCAN_SET_CHANNEL; +} + +static void ieee80211_scan_state_enter_oper_channel(struct ieee80211_local *local, + unsigned long *next_delay) +{ + struct ieee80211_sub_if_data *sdata = local->scan_sdata; + + /* switch back to the operating channel */ + local->scan_channel = NULL; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + + /* + * notify the AP about us being back and restart all STA interfaces + */ + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata, &local->interfaces, list) { + if (!netif_running(sdata->dev)) + continue; + + /* Tell AP we're back */ + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + if (sdata->u.mgd.associated) + ieee80211_scan_ps_disable(sdata); + netif_tx_wake_all_queues(sdata->dev); + } + } + mutex_unlock(&local->iflist_mtx); + + __clear_bit(SCAN_OFF_CHANNEL, &local->scanning); + + *next_delay = HZ / 5; + local->next_scan_state = SCAN_DECISION; +} + +static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, + unsigned long *next_delay) +{ + int skip; + struct ieee80211_channel *chan; + struct ieee80211_sub_if_data *sdata = local->scan_sdata; + + skip = 0; + chan = local->scan_req->channels[local->scan_channel_idx]; + + if (chan->flags & IEEE80211_CHAN_DISABLED || + (sdata->vif.type == NL80211_IFTYPE_ADHOC && + chan->flags & IEEE80211_CHAN_NO_IBSS)) + skip = 1; + + if (!skip) { + local->scan_channel = chan; + if (ieee80211_hw_config(local, + IEEE80211_CONF_CHANGE_CHANNEL)) + skip = 1; + } + + /* advance state machine to next channel/band */ + local->scan_channel_idx++; + + if (skip) { + /* if we skip this channel return to the decision state */ + local->next_scan_state = SCAN_DECISION; + return; + } + + /* + * Probe delay is used to update the NAV, cf. 11.1.3.2.2 + * (which unfortunately doesn't say _why_ step a) is done, + * but it waits for the probe delay or until a frame is + * received - and the received frame would update the NAV). + * For now, we do not support waiting until a frame is + * received. + * + * In any case, it is not necessary for a passive scan. + */ + if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN || + !local->scan_req->n_ssids) { + *next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; + local->next_scan_state = SCAN_DECISION; + return; + } + + /* active scan, send probes */ + *next_delay = IEEE80211_PROBE_DELAY; + local->next_scan_state = SCAN_SEND_PROBE; +} + +static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, + unsigned long *next_delay) +{ + int i; + struct ieee80211_sub_if_data *sdata = local->scan_sdata; + + for (i = 0; i < local->scan_req->n_ssids; i++) + ieee80211_send_probe_req( + sdata, NULL, + local->scan_req->ssids[i].ssid, + local->scan_req->ssids[i].ssid_len, + local->scan_req->ie, local->scan_req->ie_len); + + /* + * After sending probe requests, wait for probe responses + * on the channel. + */ + *next_delay = IEEE80211_CHANNEL_TIME; + local->next_scan_state = SCAN_DECISION; +} + void ieee80211_scan_work(struct work_struct *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, scan_work.work); struct ieee80211_sub_if_data *sdata = local->scan_sdata; - struct ieee80211_channel *chan; - int skip, i; unsigned long next_delay = 0; mutex_lock(&local->scan_mtx); @@ -507,11 +656,12 @@ void ieee80211_scan_work(struct work_struct *work) return; } - if (local->scan_req && !(local->sw_scanning || local->hw_scanning)) { + if (local->scan_req && !local->scanning) { struct cfg80211_scan_request *req = local->scan_req; int rc; local->scan_req = NULL; + local->scan_sdata = NULL; rc = __ieee80211_start_scan(sdata, req); mutex_unlock(&local->scan_mtx); @@ -531,72 +681,32 @@ void ieee80211_scan_work(struct work_struct *work) return; } - switch (local->scan_state) { - case SCAN_SET_CHANNEL: - /* if no more bands/channels left, complete scan */ - if (local->scan_channel_idx >= local->scan_req->n_channels) { - ieee80211_scan_completed(&local->hw, false); - return; - } - skip = 0; - chan = local->scan_req->channels[local->scan_channel_idx]; - - if (chan->flags & IEEE80211_CHAN_DISABLED || - (sdata->vif.type == NL80211_IFTYPE_ADHOC && - chan->flags & IEEE80211_CHAN_NO_IBSS)) - skip = 1; - - if (!skip) { - local->scan_channel = chan; - if (ieee80211_hw_config(local, - IEEE80211_CONF_CHANGE_CHANNEL)) - skip = 1; - } - - /* advance state machine to next channel/band */ - local->scan_channel_idx++; - - if (skip) + /* + * as long as no delay is required advance immediately + * without scheduling a new work + */ + do { + switch (local->next_scan_state) { + case SCAN_DECISION: + if (ieee80211_scan_state_decision(local, &next_delay)) + return; break; - - /* - * Probe delay is used to update the NAV, cf. 11.1.3.2.2 - * (which unfortunately doesn't say _why_ step a) is done, - * but it waits for the probe delay or until a frame is - * received - and the received frame would update the NAV). - * For now, we do not support waiting until a frame is - * received. - * - * In any case, it is not necessary for a passive scan. - */ - if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN || - !local->scan_req->n_ssids) { - next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; + case SCAN_SET_CHANNEL: + ieee80211_scan_state_set_channel(local, &next_delay); + break; + case SCAN_SEND_PROBE: + ieee80211_scan_state_send_probe(local, &next_delay); + break; + case SCAN_LEAVE_OPER_CHANNEL: + ieee80211_scan_state_leave_oper_channel(local, &next_delay); + break; + case SCAN_ENTER_OPER_CHANNEL: + ieee80211_scan_state_enter_oper_channel(local, &next_delay); break; } + } while (next_delay == 0); - next_delay = IEEE80211_PROBE_DELAY; - local->scan_state = SCAN_SEND_PROBE; - break; - case SCAN_SEND_PROBE: - for (i = 0; i < local->scan_req->n_ssids; i++) - ieee80211_send_probe_req( - sdata, NULL, - local->scan_req->ssids[i].ssid, - local->scan_req->ssids[i].ssid_len, - local->scan_req->ie, local->scan_req->ie_len); - - /* - * After sending probe requests, wait for probe responses - * on the channel. - */ - next_delay = IEEE80211_CHANNEL_TIME; - local->scan_state = SCAN_SET_CHANNEL; - break; - } - - queue_delayed_work(local->hw.workqueue, &local->scan_work, - next_delay); + ieee80211_queue_delayed_work(&local->hw, &local->scan_work, next_delay); } int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, @@ -623,10 +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; @@ -634,7 +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); @@ -643,9 +753,10 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) * queued -- mostly at suspend under RTNL. */ mutex_lock(&local->scan_mtx); - swscan = local->sw_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 a360bceeba5..594f2318c3d 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); @@ -360,6 +361,7 @@ int sta_info_insert(struct sta_info *sta) u.ap); drv_sta_notify(local, &sdata->vif, STA_NOTIFY_ADD, &sta->sta); + sdata = sta->sdata; } #ifdef CONFIG_MAC80211_VERBOSE_DEBUG @@ -485,6 +487,7 @@ 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) @@ -494,6 +497,7 @@ static void __sta_info_unlink(struct sta_info **sta) drv_sta_notify(local, &sdata->vif, STA_NOTIFY_REMOVE, &(*sta)->sta); + sdata = (*sta)->sdata; } if (ieee80211_vif_is_mesh(&sdata->vif)) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 49a1a1f7651..ccc3adf962c 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -30,7 +30,6 @@ * @WLAN_STA_ASSOC_AP: We're associated to that station, it is an AP. * @WLAN_STA_WME: Station is a QoS-STA. * @WLAN_STA_WDS: Station is one of our WDS peers. - * @WLAN_STA_PSPOLL: Station has just PS-polled us. * @WLAN_STA_CLEAR_PS_FILT: Clear PS filter in hardware (using the * IEEE80211_TX_CTL_CLEAR_PS_FILT control flag) when the next * frame to this station is transmitted. @@ -47,7 +46,6 @@ enum ieee80211_sta_info_flags { WLAN_STA_ASSOC_AP = 1<<5, WLAN_STA_WME = 1<<6, WLAN_STA_WDS = 1<<7, - WLAN_STA_PSPOLL = 1<<8, WLAN_STA_CLEAR_PS_FILT = 1<<9, WLAN_STA_MFP = 1<<10, WLAN_STA_SUSPEND = 1<<11 @@ -308,6 +306,23 @@ struct sta_info { struct dentry *inactive_ms; struct dentry *last_seq_ctrl; struct dentry *agg_status; + struct dentry *aid; + struct dentry *dev; + struct dentry *rx_packets; + struct dentry *tx_packets; + struct dentry *rx_bytes; + struct dentry *tx_bytes; + struct dentry *rx_duplicates; + struct dentry *rx_fragments; + struct dentry *rx_dropped; + struct dentry *tx_fragments; + struct dentry *tx_filtered; + struct dentry *tx_retry_failed; + struct dentry *tx_retry_count; + struct dentry *last_signal; + struct dentry *last_qual; + struct dentry *last_noise; + struct dentry *wep_weak_iv_count; bool add_has_run; } debugfs; #endif @@ -342,17 +357,6 @@ static inline void clear_sta_flags(struct sta_info *sta, const u32 flags) spin_unlock_irqrestore(&sta->flaglock, irqfl); } -static inline void set_and_clear_sta_flags(struct sta_info *sta, - const u32 set, const u32 clear) -{ - unsigned long irqfl; - - spin_lock_irqsave(&sta->flaglock, irqfl); - sta->flags |= set; - sta->flags &= ~clear; - spin_unlock_irqrestore(&sta->flaglock, irqfl); -} - static inline u32 test_sta_flags(struct sta_info *sta, const u32 flags) { u32 ret; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 3a8922cd103..eaa4118de98 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -192,7 +192,7 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) if (unlikely(info->flags & IEEE80211_TX_CTL_INJECTED)) return TX_CONTINUE; - if (unlikely(tx->local->sw_scanning) && + if (unlikely(test_bit(SCAN_OFF_CHANNEL, &tx->local->scanning)) && !ieee80211_is_probe_req(hdr->frame_control) && !ieee80211_is_nullfunc(hdr->frame_control)) /* @@ -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, @@ -367,13 +367,16 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; u32 staflags; - if (unlikely(!sta || ieee80211_is_probe_resp(hdr->frame_control))) + if (unlikely(!sta || ieee80211_is_probe_resp(hdr->frame_control) + || ieee80211_is_auth(hdr->frame_control) + || ieee80211_is_assoc_resp(hdr->frame_control) + || ieee80211_is_reassoc_resp(hdr->frame_control))) return TX_CONTINUE; staflags = get_sta_flags(sta); if (unlikely((staflags & WLAN_STA_PS) && - !(staflags & WLAN_STA_PSPOLL))) { + !(info->flags & IEEE80211_TX_CTL_PSPOLL_RESPONSE))) { #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG printk(KERN_DEBUG "STA %pM aid %d: PS buffer (entries " "before %d)\n", @@ -400,6 +403,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta_info_set_tim_bit(sta); info->control.jiffies = jiffies; + info->control.vif = &tx->sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; skb_queue_tail(&sta->ps_tx_buf, tx->skb); return TX_QUEUED; @@ -411,24 +415,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta->sta.addr); } #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ - if (test_and_clear_sta_flags(sta, WLAN_STA_PSPOLL)) { - /* - * The sleeping station with pending data is now snoozing. - * It queried us for its buffered frames and will go back - * to deep sleep once it got everything. - * - * inform the driver, in case the hardware does powersave - * frame filtering and keeps a station blacklist on its own - * (e.g: p54), so that frames can be delivered unimpeded. - * - * Note: It should be safe to disable the filter now. - * As, it is really unlikely that we still have any pending - * frame for this station in the hw's buffers/fifos left, - * that is not rejected with a unsuccessful tx_status yet. - */ - info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; - } return TX_CONTINUE; } @@ -451,7 +438,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; - if (unlikely(tx->skb->do_not_encrypt)) + if (unlikely(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)) tx->key = NULL; else if (tx->sta && (key = rcu_dereference(tx->sta->key))) tx->key = key; @@ -497,7 +484,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) } if (!tx->key || !(tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) - tx->skb->do_not_encrypt = 1; + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; return TX_CONTINUE; } @@ -512,6 +499,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) int i, len; bool inval = false, rts = false, short_preamble = false; struct ieee80211_tx_rate_control txrc; + u32 sta_flags; memset(&txrc, 0, sizeof(txrc)); @@ -544,7 +532,26 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) (tx->sta && test_sta_flags(tx->sta, WLAN_STA_SHORT_PREAMBLE)))) txrc.short_preamble = short_preamble = true; + sta_flags = tx->sta ? get_sta_flags(tx->sta) : 0; + + /* + * Lets not bother rate control if we're associated and cannot + * talk to the sta. This should not happen. + */ + if (WARN(test_bit(SCAN_SW_SCANNING, &tx->local->scanning) && + (sta_flags & WLAN_STA_ASSOC) && + !rate_usable_index_exists(sband, &tx->sta->sta), + "%s: Dropped data frame as no usable bitrate found while " + "scanning and associated. Target station: " + "%pM on %d GHz band\n", + tx->dev->name, hdr->addr1, + tx->channel->band ? 5 : 2)) + return TX_DROP; + /* + * If we're associated with the sta at this point we know we can at + * least send the frame at the lowest bit rate. + */ rate_control_get_rate(tx->sdata, tx->sta, &txrc); if (unlikely(info->control.rates[0].idx < 0)) @@ -676,7 +683,7 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) * number, if we have no matching interface then we * neither assign one ourselves nor ask the driver to. */ - if (unlikely(!info->control.vif)) + if (unlikely(info->control.vif->type == NL80211_IFTYPE_MONITOR)) return TX_CONTINUE; if (unlikely(ieee80211_is_ctl(hdr->frame_control))) @@ -696,7 +703,6 @@ 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; } @@ -754,9 +760,7 @@ static int ieee80211_fragment(struct ieee80211_local *local, memcpy(tmp->cb, skb->cb, sizeof(tmp->cb)); skb_copy_queue_mapping(tmp, skb); tmp->priority = skb->priority; - tmp->do_not_encrypt = skb->do_not_encrypt; tmp->dev = skb->dev; - tmp->iif = skb->iif; /* copy header and data */ memcpy(skb_put(tmp, hdrlen), skb->data, hdrlen); @@ -784,7 +788,7 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) /* * Warn when submitting a fragmented A-MPDU frame and drop it. - * This scenario is handled in __ieee80211_tx_prepare but extra + * This scenario is handled in ieee80211_tx_prepare but extra * caution taken here as fragmented ampdu may cause Tx stop. */ if (WARN_ON(info->flags & IEEE80211_TX_CTL_AMPDU)) @@ -842,6 +846,23 @@ 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) @@ -885,23 +906,6 @@ 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 */ /* @@ -923,11 +927,12 @@ static bool __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, struct ieee80211_radiotap_header *rthdr = (struct ieee80211_radiotap_header *) skb->data; struct ieee80211_supported_band *sband; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len); sband = tx->local->hw.wiphy->bands[tx->channel->band]; - skb->do_not_encrypt = 1; + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; tx->flags &= ~IEEE80211_TX_FRAGMENTED; /* @@ -965,7 +970,7 @@ static bool __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, skb_trim(skb, skb->len - FCS_LEN); } if (*iterator.this_arg & IEEE80211_RADIOTAP_F_WEP) - tx->skb->do_not_encrypt = 0; + info->flags &= ~IEEE80211_TX_INTFL_DONT_ENCRYPT; if (*iterator.this_arg & IEEE80211_RADIOTAP_F_FRAG) tx->flags |= IEEE80211_TX_FRAGMENTED; break; @@ -998,13 +1003,12 @@ static bool __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, * initialises @tx */ static ieee80211_tx_result -__ieee80211_tx_prepare(struct ieee80211_tx_data *tx, - struct sk_buff *skb, - struct net_device *dev) +ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, + struct ieee80211_tx_data *tx, + struct sk_buff *skb) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_local *local = sdata->local; struct ieee80211_hdr *hdr; - struct ieee80211_sub_if_data *sdata; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int hdrlen, tid; u8 *qc, *state; @@ -1012,9 +1016,9 @@ __ieee80211_tx_prepare(struct ieee80211_tx_data *tx, memset(tx, 0, sizeof(*tx)); tx->skb = skb; - tx->dev = dev; /* use original interface */ + tx->dev = sdata->dev; /* use original interface */ tx->local = local; - tx->sdata = IEEE80211_DEV_TO_SUB_IF(dev); + tx->sdata = sdata; tx->channel = local->hw.conf.channel; /* * Set this flag (used below to indicate "automatic fragmentation"), @@ -1023,7 +1027,6 @@ __ieee80211_tx_prepare(struct ieee80211_tx_data *tx, tx->flags |= IEEE80211_TX_FRAGMENTED; /* process and remove the injection radiotap header */ - sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (unlikely(info->flags & IEEE80211_TX_CTL_INJECTED)) { if (!__ieee80211_parse_tx_radiotap(tx, skb)) return TX_DROP; @@ -1075,6 +1078,7 @@ __ieee80211_tx_prepare(struct ieee80211_tx_data *tx, } else if (*state != HT_AGG_STATE_IDLE) { /* in progress */ queued = true; + info->control.vif = &sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; __skb_queue_tail(&tid_tx->pending, skb); } @@ -1119,50 +1123,29 @@ __ieee80211_tx_prepare(struct ieee80211_tx_data *tx, return TX_CONTINUE; } -/* - * NB: @tx is uninitialised when passed in here - */ -static int ieee80211_tx_prepare(struct ieee80211_local *local, - struct ieee80211_tx_data *tx, - struct sk_buff *skb) -{ - struct net_device *dev; - - dev = dev_get_by_index(&init_net, skb->iif); - if (unlikely(dev && !is_ieee80211_device(local, dev))) { - dev_put(dev); - dev = NULL; - } - if (unlikely(!dev)) - return -ENODEV; - /* - * initialises tx with control - * - * return value is safe to ignore here because this function - * can only be invoked for multicast frames - * - * XXX: clean up - */ - __ieee80211_tx_prepare(tx, skb, dev); - dev_put(dev); - return 0; -} - static int __ieee80211_tx(struct ieee80211_local *local, struct sk_buff **skbp, - struct sta_info *sta) + struct sta_info *sta, + bool txpending) { struct sk_buff *skb = *skbp, *next; struct ieee80211_tx_info *info; + struct ieee80211_sub_if_data *sdata; + unsigned long flags; int ret, len; bool fragm = false; - local->mdev->trans_start = jiffies; - while (skb) { - if (ieee80211_queue_stopped(&local->hw, - skb_get_queue_mapping(skb))) - return IEEE80211_TX_PENDING; + int q = skb_get_queue_mapping(skb); + + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + ret = IEEE80211_TX_OK; + if (local->queue_stop_reasons[q] || + (!txpending && !skb_queue_empty(&local->pending[q]))) + ret = IEEE80211_TX_PENDING; + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + if (ret != IEEE80211_TX_OK) + return ret; info = IEEE80211_SKB_CB(skb); @@ -1172,13 +1155,35 @@ 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) { + case NL80211_IFTYPE_MONITOR: + info->control.vif = NULL; + break; + case NL80211_IFTYPE_AP_VLAN: + info->control.vif = &container_of(sdata->bss, + struct ieee80211_sub_if_data, u.ap)->vif; + break; + default: + /* keep */ + break; + } + ret = drv_tx(local, skb); if (WARN_ON(ret != NETDEV_TX_OK && skb->len != len)) { dev_kfree_skb(skb); ret = NETDEV_TX_OK; } - if (ret != NETDEV_TX_OK) + if (ret != NETDEV_TX_OK) { + info->control.vif = &sdata->vif; return IEEE80211_TX_AGAIN; + } + *skbp = skb = next; ieee80211_led_tx(local, 1); fragm = true; @@ -1210,9 +1215,9 @@ 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: @@ -1234,10 +1239,10 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx) return 0; } -static void ieee80211_tx(struct net_device *dev, struct sk_buff *skb, - bool txpending) +static void ieee80211_tx(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, bool txpending) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_local *local = sdata->local; struct ieee80211_tx_data tx; ieee80211_tx_result res_prepare; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -1248,8 +1253,6 @@ static void ieee80211_tx(struct net_device *dev, struct sk_buff *skb, queue = skb_get_queue_mapping(skb); - WARN_ON(!txpending && !skb_queue_empty(&local->pending[queue])); - if (unlikely(skb->len < 10)) { dev_kfree_skb(skb); return; @@ -1258,7 +1261,7 @@ static void ieee80211_tx(struct net_device *dev, struct sk_buff *skb, rcu_read_lock(); /* initialises tx */ - res_prepare = __ieee80211_tx_prepare(&tx, skb, dev); + res_prepare = ieee80211_tx_prepare(sdata, &tx, skb); if (unlikely(res_prepare == TX_DROP)) { dev_kfree_skb(skb); @@ -1277,7 +1280,7 @@ static void ieee80211_tx(struct net_device *dev, struct sk_buff *skb, retries = 0; retry: - ret = __ieee80211_tx(local, &tx.skb, tx.sta); + ret = __ieee80211_tx(local, &tx.skb, tx.sta, txpending); switch (ret) { case IEEE80211_TX_OK: break; @@ -1295,34 +1298,35 @@ static void ieee80211_tx(struct net_device *dev, struct sk_buff *skb, spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - if (__netif_subqueue_stopped(local->mdev, queue)) { + if (local->queue_stop_reasons[queue] || + !skb_queue_empty(&local->pending[queue])) { + /* + * if queue is stopped, queue up frames for later + * transmission from the tasklet + */ do { next = skb->next; skb->next = NULL; if (unlikely(txpending)) - skb_queue_head(&local->pending[queue], - skb); + __skb_queue_head(&local->pending[queue], + skb); else - skb_queue_tail(&local->pending[queue], - skb); + __skb_queue_tail(&local->pending[queue], + skb); } while ((skb = next)); - /* - * Make sure nobody will enable the queue on us - * (without going through the tasklet) nor disable the - * netdev queue underneath the pending handling code. - */ - __set_bit(IEEE80211_QUEUE_STOP_REASON_PENDING, - &local->queue_stop_reasons[queue]); - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } else { + /* + * otherwise retry, but this is a race condition or + * a driver bug (which we warn about if it persists) + */ spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); retries++; - if (WARN(retries > 10, "tx refused but queue active")) + if (WARN(retries > 10, "tx refused but queue active\n")) goto drop; goto retry; } @@ -1383,44 +1387,25 @@ static int ieee80211_skb_resize(struct ieee80211_local *local, return 0; } -int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) +static void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) { - struct ieee80211_master_priv *mpriv = netdev_priv(dev); - struct ieee80211_local *local = mpriv->local; + struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - struct net_device *odev = NULL; - struct ieee80211_sub_if_data *osdata; + struct ieee80211_sub_if_data *tmp_sdata; int headroom; bool may_encrypt; - enum { - NOT_MONITOR, - FOUND_SDATA, - UNKNOWN_ADDRESS, - } monitor_iface = NOT_MONITOR; - - if (skb->iif) - odev = dev_get_by_index(&init_net, skb->iif); - if (unlikely(odev && !is_ieee80211_device(local, odev))) { - dev_put(odev); - odev = NULL; - } - if (unlikely(!odev)) { -#ifdef CONFIG_MAC80211_VERBOSE_DEBUG - printk(KERN_DEBUG "%s: Discarded packet with nonexistent " - "originating device\n", dev->name); -#endif - dev_kfree_skb(skb); - return NETDEV_TX_OK; - } + + dev_hold(sdata->dev); if ((local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) && local->hw.conf.dynamic_ps_timeout > 0 && - !local->sw_scanning && !local->hw_scanning && local->ps_sdata) { + !(local->scanning) && local->ps_sdata) { if (local->hw.conf.flags & IEEE80211_CONF_PS) { ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_QUEUE_STOP_REASON_PS); - queue_work(local->hw.workqueue, + ieee80211_queue_work(&local->hw, &local->dynamic_ps_disable_work); } @@ -1428,31 +1413,13 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout)); } - memset(info, 0, sizeof(*info)); - info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; - osdata = IEEE80211_DEV_TO_SUB_IF(odev); - - if (ieee80211_vif_is_mesh(&osdata->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, osdata)) { - dev_put(odev); - return NETDEV_TX_OK; - } - if (memcmp(odev->dev_addr, hdr->addr4, ETH_ALEN) != 0) - IEEE80211_IFSTA_MESH_CTR_INC(&osdata->u.mesh, - fwded_frames); - } else if (unlikely(osdata->vif.type == NL80211_IFTYPE_MONITOR)) { - struct ieee80211_sub_if_data *sdata; + if (unlikely(sdata->vif.type == NL80211_IFTYPE_MONITOR)) { int hdrlen; u16 len_rthdr; info->flags |= IEEE80211_TX_CTL_INJECTED; - monitor_iface = UNKNOWN_ADDRESS; len_rthdr = ieee80211_get_radiotap_len(skb->data); hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr); @@ -1471,20 +1438,17 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) */ rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, + list_for_each_entry_rcu(tmp_sdata, &local->interfaces, list) { - if (!netif_running(sdata->dev)) + if (!netif_running(tmp_sdata->dev)) continue; - if (sdata->vif.type != NL80211_IFTYPE_AP) + if (tmp_sdata->vif.type != NL80211_IFTYPE_AP) continue; - if (compare_ether_addr(sdata->dev->dev_addr, - hdr->addr2)) { - dev_hold(sdata->dev); - dev_put(odev); - osdata = sdata; - odev = osdata->dev; - skb->iif = sdata->dev->ifindex; - monitor_iface = FOUND_SDATA; + if (compare_ether_addr(tmp_sdata->dev->dev_addr, + hdr->addr2) == 0) { + dev_hold(tmp_sdata->dev); + dev_put(sdata->dev); + sdata = tmp_sdata; break; } } @@ -1492,40 +1456,44 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) } } - may_encrypt = !skb->do_not_encrypt; + may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT); - headroom = osdata->local->tx_headroom; + headroom = local->tx_headroom; if (may_encrypt) headroom += IEEE80211_ENCRYPT_HEADROOM; headroom -= skb_headroom(skb); headroom = max_t(int, 0, headroom); - if (ieee80211_skb_resize(osdata->local, skb, headroom, may_encrypt)) { + if (ieee80211_skb_resize(local, skb, headroom, may_encrypt)) { dev_kfree_skb(skb); - dev_put(odev); - return NETDEV_TX_OK; + dev_put(sdata->dev); + return; } - if (osdata->vif.type == NL80211_IFTYPE_AP_VLAN) - osdata = container_of(osdata->bss, - struct ieee80211_sub_if_data, - u.ap); - if (likely(monitor_iface != UNKNOWN_ADDRESS)) - info->control.vif = &osdata->vif; + info->control.vif = &sdata->vif; - ieee80211_tx(odev, skb, false); - dev_put(odev); + 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; + } - return NETDEV_TX_OK; + 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; struct ieee80211_radiotap_header *prthdr = (struct ieee80211_radiotap_header *)skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); u16 len_rthdr; /* @@ -1563,15 +1531,6 @@ int ieee80211_monitor_start_xmit(struct sk_buff *skb, if (unlikely(skb->len < len_rthdr)) goto fail; /* skb too short for claimed rt header extent */ - skb->dev = local->mdev; - - /* needed because we set skb device to master */ - skb->iif = dev->ifindex; - - /* sometimes we do encrypt injected frames, will be fixed - * up in radiotap parser if not wanted */ - skb->do_not_encrypt = 0; - /* * fix up the pointers accounting for the radiotap * header still being in there. We are being given @@ -1586,8 +1545,10 @@ int ieee80211_monitor_start_xmit(struct sk_buff *skb, skb_set_network_header(skb, len_rthdr); skb_set_transport_header(skb, len_rthdr); - /* pass the radiotap header up to the next stage intact */ - dev_queue_xmit(skb); + memset(info, 0, sizeof(*info)); + + /* pass the radiotap header up to xmit */ + ieee80211_xmit(IEEE80211_DEV_TO_SUB_IF(dev), skb); return NETDEV_TX_OK; fail: @@ -1610,11 +1571,12 @@ 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; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int ret = NETDEV_TX_BUSY, head_need; u16 ethertype, hdrlen, meshhdrlen = 0; __le16 fc; @@ -1627,7 +1589,7 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, u32 sta_flags = 0; if (unlikely(skb->len < ETH_HLEN)) { - ret = 0; + ret = NETDEV_TX_OK; goto fail; } @@ -1660,52 +1622,58 @@ 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 = 0; + 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: @@ -1724,7 +1692,7 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, hdrlen = 24; break; default: - ret = 0; + ret = NETDEV_TX_OK; goto fail; } @@ -1736,7 +1704,8 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, if (!is_multicast_ether_addr(hdr.addr1)) { rcu_read_lock(); sta = sta_info_get(local, hdr.addr1); - if (sta) + /* XXX: in the future, use sdata to look up the sta */ + if (sta && sta->sdata == sdata) sta_flags = get_sta_flags(sta); rcu_read_unlock(); } @@ -1766,7 +1735,7 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, I802_DEBUG_INC(local->tx_handlers_drop_unauth_port); - ret = 0; + ret = NETDEV_TX_OK; goto fail; } @@ -1842,9 +1811,6 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, nh_pos += hdrlen; h_pos += hdrlen; - skb->iif = dev->ifindex; - - skb->dev = local->mdev; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; @@ -1855,13 +1821,15 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, skb_set_network_header(skb, nh_pos); skb_set_transport_header(skb, h_pos); + memset(info, 0, sizeof(*info)); + dev->trans_start = jiffies; - dev_queue_xmit(skb); + ieee80211_xmit(sdata, skb); - return 0; + return NETDEV_TX_OK; fail: - if (!ret) + if (ret == NETDEV_TX_OK) dev_kfree_skb(skb); return ret; @@ -1887,101 +1855,74 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata; struct sta_info *sta; struct ieee80211_hdr *hdr; - struct net_device *dev; int ret; bool result = true; - /* does interface still exist? */ - dev = dev_get_by_index(&init_net, skb->iif); - if (!dev) { - dev_kfree_skb(skb); - return true; - } - - /* validate info->control.vif against skb->iif */ - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - sdata = container_of(sdata->bss, - struct ieee80211_sub_if_data, - u.ap); - - if (unlikely(info->control.vif && info->control.vif != &sdata->vif)) { - dev_kfree_skb(skb); - result = true; - goto out; - } + sdata = vif_to_sdata(info->control.vif); if (info->flags & IEEE80211_TX_INTFL_NEED_TXPROCESSING) { - ieee80211_tx(dev, skb, true); + ieee80211_tx(sdata, skb, true); } else { hdr = (struct ieee80211_hdr *)skb->data; sta = sta_info_get(local, hdr->addr1); - ret = __ieee80211_tx(local, &skb, sta); + ret = __ieee80211_tx(local, &skb, sta, true); if (ret != IEEE80211_TX_OK) result = false; } - out: - dev_put(dev); - return result; } /* - * Transmit all pending packets. Called from tasklet, locks master device - * TX lock so that no new packets can come in. + * Transmit all pending packets. Called from tasklet. */ void ieee80211_tx_pending(unsigned long data) { struct ieee80211_local *local = (struct ieee80211_local *)data; - struct net_device *dev = local->mdev; unsigned long flags; int i; - bool next; + bool txok; rcu_read_lock(); - netif_tx_lock_bh(dev); + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for (i = 0; i < local->hw.queues; i++) { /* * If queue is stopped by something other than due to pending * frames, or we have no pending frames, proceed to next queue. */ - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - next = false; - if (local->queue_stop_reasons[i] != - BIT(IEEE80211_QUEUE_STOP_REASON_PENDING) || + if (local->queue_stop_reasons[i] || skb_queue_empty(&local->pending[i])) - next = true; - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - - if (next) continue; - /* - * start the queue now to allow processing our packets, - * we're under the tx lock here anyway so nothing will - * happen as a result of this - */ - netif_start_subqueue(local->mdev, i); - while (!skb_queue_empty(&local->pending[i])) { - struct sk_buff *skb = skb_dequeue(&local->pending[i]); + struct sk_buff *skb = __skb_dequeue(&local->pending[i]); + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_sub_if_data *sdata; - if (!ieee80211_tx_pending_skb(local, skb)) { - skb_queue_head(&local->pending[i], skb); - break; + if (WARN_ON(!info->control.vif)) { + kfree_skb(skb); + continue; } - } - /* Start regular packet processing again. */ - if (skb_queue_empty(&local->pending[i])) - ieee80211_wake_queue_by_reason(&local->hw, i, - IEEE80211_QUEUE_STOP_REASON_PENDING); + sdata = vif_to_sdata(info->control.vif); + dev_hold(sdata->dev); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, + flags); + + txok = ieee80211_tx_pending_skb(local, skb); + dev_put(sdata->dev); + if (!txok) + __skb_queue_head(&local->pending[i], skb); + spin_lock_irqsave(&local->queue_stop_reason_lock, + flags); + if (!txok) + break; + } } + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - netif_tx_unlock_bh(dev); rcu_read_unlock(); } @@ -2156,8 +2097,7 @@ struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, info = IEEE80211_SKB_CB(skb); - skb->do_not_encrypt = 1; - + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; info->band = band; /* * XXX: For now, always use the lowest rate @@ -2228,9 +2168,6 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, sdata = vif_to_sdata(vif); bss = &sdata->u.ap; - if (!bss) - return NULL; - rcu_read_lock(); beacon = rcu_dereference(bss->beacon); @@ -2256,7 +2193,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, cpu_to_le16(IEEE80211_FCTL_MOREDATA); } - if (!ieee80211_tx_prepare(local, &tx, skb)) + if (!ieee80211_tx_prepare(sdata, &tx, skb)) break; dev_kfree_skb_any(skb); } @@ -2276,3 +2213,24 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, return skb; } EXPORT_SYMBOL(ieee80211_get_buffered_bc); + +void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, + int encrypt) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, 0); + skb_set_transport_header(skb, 0); + + if (!encrypt) + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + + /* + * The other path calling ieee80211_xmit is from the tasklet, + * and while we can handle concurrent transmissions locking + * requirements are that we do not come into tx with bhs on. + */ + local_bh_disable(); + ieee80211_xmit(sdata, skb); + local_bh_enable(); +} diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 915e7776931..e6c08da8da2 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -31,6 +31,7 @@ #include "mesh.h" #include "wme.h" #include "led.h" +#include "wep.h" /* privid for wiphys to determine whether they belong to us or not */ void *mac80211_wiphy_privid = &mac80211_wiphy_privid; @@ -274,16 +275,12 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, __clear_bit(reason, &local->queue_stop_reasons[queue]); - if (!skb_queue_empty(&local->pending[queue]) && - local->queue_stop_reasons[queue] == - BIT(IEEE80211_QUEUE_STOP_REASON_PENDING)) - tasklet_schedule(&local->tx_pending_tasklet); - if (local->queue_stop_reasons[queue] != 0) /* someone still has this queue stopped */ return; - netif_wake_subqueue(local->mdev, queue); + if (!skb_queue_empty(&local->pending[queue])) + tasklet_schedule(&local->tx_pending_tasklet); } void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, @@ -312,14 +309,6 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, if (WARN_ON(queue >= hw->queues)) return; - /* - * Only stop if it was previously running, this is necessary - * for correct pending packets handling because there we may - * start (but not wake) the queue and rely on that. - */ - if (!local->queue_stop_reasons[queue]) - netif_stop_subqueue(local->mdev, queue); - __set_bit(reason, &local->queue_stop_reasons[queue]); } @@ -347,11 +336,16 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local, struct ieee80211_hw *hw = &local->hw; unsigned long flags; int queue = skb_get_queue_mapping(skb); + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + if (WARN_ON(!info->control.vif)) { + kfree_skb(skb); + return; + } spin_lock_irqsave(&local->queue_stop_reason_lock, flags); __ieee80211_stop_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); - __ieee80211_stop_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_PENDING); - skb_queue_tail(&local->pending[queue], skb); + __skb_queue_tail(&local->pending[queue], skb); __ieee80211_wake_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } @@ -370,18 +364,21 @@ int ieee80211_add_pending_skbs(struct ieee80211_local *local, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); while ((skb = skb_dequeue(skbs))) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + if (WARN_ON(!info->control.vif)) { + kfree_skb(skb); + continue; + } + ret++; queue = skb_get_queue_mapping(skb); - skb_queue_tail(&local->pending[queue], skb); + __skb_queue_tail(&local->pending[queue], skb); } - for (i = 0; i < hw->queues; i++) { - if (ret) - __ieee80211_stop_queue(hw, i, - IEEE80211_QUEUE_STOP_REASON_PENDING); + for (i = 0; i < hw->queues; i++) __ieee80211_wake_queue(hw, i, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); - } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); return ret; @@ -412,11 +409,16 @@ EXPORT_SYMBOL(ieee80211_stop_queues); int ieee80211_queue_stopped(struct ieee80211_hw *hw, int queue) { struct ieee80211_local *local = hw_to_local(hw); + unsigned long flags; + int ret; if (WARN_ON(queue >= hw->queues)) return true; - return __netif_subqueue_stopped(local->mdev, queue); + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + ret = !!local->queue_stop_reasons[queue]; + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + return ret; } EXPORT_SYMBOL(ieee80211_queue_stopped); @@ -509,6 +511,46 @@ void ieee80211_iterate_active_interfaces_atomic( } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); +/* + * Nothing should have been stuffed into the workqueue during + * the suspend->resume cycle. If this WARN is seen then there + * is a bug with either the driver suspend or something in + * mac80211 stuffing into the workqueue which we haven't yet + * cleared during mac80211's suspend cycle. + */ +static bool ieee80211_can_queue_work(struct ieee80211_local *local) +{ + if (WARN(local->suspended && !local->resuming, + "queueing ieee80211 work while going to suspend\n")) + return false; + + return true; +} + +void ieee80211_queue_work(struct ieee80211_hw *hw, struct work_struct *work) +{ + struct ieee80211_local *local = hw_to_local(hw); + + if (!ieee80211_can_queue_work(local)) + return; + + queue_work(local->workqueue, work); +} +EXPORT_SYMBOL(ieee80211_queue_work); + +void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, + struct delayed_work *dwork, + unsigned long delay) +{ + struct ieee80211_local *local = hw_to_local(hw); + + if (!ieee80211_can_queue_work(local)) + return; + + queue_delayed_work(local->workqueue, dwork, delay); +} +EXPORT_SYMBOL(ieee80211_queue_delayed_work); + void ieee802_11_parse_elems(u8 *start, size_t len, struct ieee802_11_elems *elems) { @@ -760,20 +802,6 @@ void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, ieee80211_set_wmm_default(sdata); } -void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - int encrypt) -{ - skb->dev = sdata->local->mdev; - skb_set_mac_header(skb, 0); - skb_set_network_header(skb, 0); - skb_set_transport_header(skb, 0); - - skb->iif = sdata->dev->ifindex; - skb->do_not_encrypt = !encrypt; - - dev_queue_xmit(skb); -} - u32 ieee80211_mandatory_rates(struct ieee80211_local *local, enum ieee80211_band band) { @@ -804,12 +832,13 @@ u32 ieee80211_mandatory_rates(struct ieee80211_local *local, void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, - u8 *extra, size_t extra_len, - const u8 *bssid, int encrypt) + u8 *extra, size_t extra_len, const u8 *bssid, + const u8 *key, u8 key_len, u8 key_idx) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; + int err; skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*mgmt) + 6 + extra_len); @@ -824,8 +853,6 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, memset(mgmt, 0, 24 + 6); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH); - if (encrypt) - mgmt->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); memcpy(mgmt->da, bssid, ETH_ALEN); memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN); memcpy(mgmt->bssid, bssid, ETH_ALEN); @@ -835,7 +862,13 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, if (extra) memcpy(skb_put(skb, extra_len), extra, extra_len); - ieee80211_tx_skb(sdata, skb, encrypt); + if (auth_alg == WLAN_AUTH_SHARED_KEY && transaction == 3) { + mgmt->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); + err = ieee80211_wep_encrypt(local, skb, key, key_len, key_idx); + WARN_ON(err); + } + + ieee80211_tx_skb(sdata, skb, 0); } int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, @@ -974,6 +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; @@ -982,13 +1025,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct sta_info *sta; unsigned long flags; int res; - bool from_suspend = local->suspended; - /* - * We're going to start the hardware, at that point - * we are no longer suspended and can RX frames. - */ - local->suspended = false; + if (local->suspended) + local->resuming = true; /* restart hardware */ if (local->open_count) { @@ -1043,9 +1082,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* reconfigure hardware */ ieee80211_hw_config(local, ~0); - netif_addr_lock_bh(local->mdev); ieee80211_configure_filter(local); - netif_addr_unlock_bh(local->mdev); /* Finally also reconfigure all the BSS information */ list_for_each_entry(sdata, &local->interfaces, list) { @@ -1088,11 +1125,14 @@ int ieee80211_reconfig(struct ieee80211_local *local) * If this is for hw restart things are still running. * We may want to change that later, however. */ - if (!from_suspend) + if (!local->suspended) return 0; #ifdef CONFIG_PM + /* first set suspended false, then resuming */ local->suspended = false; + mb(); + local->resuming = false; list_for_each_entry(sdata, &local->interfaces, list) { switch(sdata->vif.type) { @@ -1121,3 +1161,4 @@ int ieee80211_reconfig(struct ieee80211_local *local) #endif return 0; } + diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index ef73105b306..8a980f13694 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -67,10 +67,10 @@ static inline bool ieee80211_wep_weak_iv(u32 iv, int keylen) static void ieee80211_wep_get_iv(struct ieee80211_local *local, - struct ieee80211_key *key, u8 *iv) + int keylen, int keyidx, u8 *iv) { local->wep_iv++; - if (ieee80211_wep_weak_iv(local->wep_iv, key->conf.keylen)) + if (ieee80211_wep_weak_iv(local->wep_iv, keylen)) local->wep_iv += 0x0100; if (!iv) @@ -79,13 +79,13 @@ static void ieee80211_wep_get_iv(struct ieee80211_local *local, *iv++ = (local->wep_iv >> 16) & 0xff; *iv++ = (local->wep_iv >> 8) & 0xff; *iv++ = local->wep_iv & 0xff; - *iv++ = key->conf.keyidx << 6; + *iv++ = keyidx << 6; } static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local, struct sk_buff *skb, - struct ieee80211_key *key) + int keylen, int keyidx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; unsigned int hdrlen; @@ -100,7 +100,7 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local, hdrlen = ieee80211_hdrlen(hdr->frame_control); newhdr = skb_push(skb, WEP_IV_LEN); memmove(newhdr, newhdr + WEP_IV_LEN, hdrlen); - ieee80211_wep_get_iv(local, key, newhdr + hdrlen); + ieee80211_wep_get_iv(local, keylen, keyidx, newhdr + hdrlen); return newhdr + hdrlen; } @@ -144,26 +144,17 @@ void ieee80211_wep_encrypt_data(struct crypto_blkcipher *tfm, u8 *rc4key, * * WEP frame payload: IV + TX key idx, RC4(data), ICV = RC4(CRC32(data)) */ -int ieee80211_wep_encrypt(struct ieee80211_local *local, struct sk_buff *skb, - struct ieee80211_key *key) +int ieee80211_wep_encrypt(struct ieee80211_local *local, + struct sk_buff *skb, + const u8 *key, int keylen, int keyidx) { - u32 klen; - u8 *rc4key, *iv; + u8 *iv; size_t len; + u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; - if (!key || key->conf.alg != ALG_WEP) - return -1; - - klen = 3 + key->conf.keylen; - rc4key = kmalloc(klen, GFP_ATOMIC); - if (!rc4key) - return -1; - - iv = ieee80211_wep_add_iv(local, skb, key); - if (!iv) { - kfree(rc4key); + iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx); + if (!iv) return -1; - } len = skb->len - (iv + WEP_IV_LEN - skb->data); @@ -171,16 +162,14 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local, struct sk_buff *skb, memcpy(rc4key, iv, 3); /* Copy rest of the WEP key (the secret part) */ - memcpy(rc4key + 3, key->conf.key, key->conf.keylen); + memcpy(rc4key + 3, key, keylen); /* Add room for ICV */ skb_put(skb, WEP_ICV_LEN); - ieee80211_wep_encrypt_data(local->wep_tx_tfm, rc4key, klen, + ieee80211_wep_encrypt_data(local->wep_tx_tfm, rc4key, keylen + 3, iv + WEP_IV_LEN, len); - kfree(rc4key); - return 0; } @@ -216,8 +205,9 @@ int ieee80211_wep_decrypt_data(struct crypto_blkcipher *tfm, u8 *rc4key, * failure. If frame is OK, IV and ICV will be removed, i.e., decrypted payload * is moved to the beginning of the skb and skb length will be reduced. */ -int ieee80211_wep_decrypt(struct ieee80211_local *local, struct sk_buff *skb, - struct ieee80211_key *key) +static int ieee80211_wep_decrypt(struct ieee80211_local *local, + struct sk_buff *skb, + struct ieee80211_key *key) { u32 klen; u8 *rc4key; @@ -314,12 +304,16 @@ static int wep_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (!(tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) { - if (ieee80211_wep_encrypt(tx->local, skb, tx->key)) + if (ieee80211_wep_encrypt(tx->local, skb, tx->key->conf.key, + tx->key->conf.keylen, + tx->key->conf.keyidx)) return -1; } else { info->control.hw_key = &tx->key->conf; if (tx->key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) { - if (!ieee80211_wep_add_iv(tx->local, skb, tx->key)) + if (!ieee80211_wep_add_iv(tx->local, skb, + tx->key->conf.keylen, + tx->key->conf.keyidx)) return -1; } } diff --git a/net/mac80211/wep.h b/net/mac80211/wep.h index d3f0db48314..fe29d7e5759 100644 --- a/net/mac80211/wep.h +++ b/net/mac80211/wep.h @@ -20,12 +20,11 @@ int ieee80211_wep_init(struct ieee80211_local *local); void ieee80211_wep_free(struct ieee80211_local *local); void ieee80211_wep_encrypt_data(struct crypto_blkcipher *tfm, u8 *rc4key, size_t klen, u8 *data, size_t data_len); +int ieee80211_wep_encrypt(struct ieee80211_local *local, + struct sk_buff *skb, + const u8 *key, int keylen, int keyidx); int ieee80211_wep_decrypt_data(struct crypto_blkcipher *tfm, u8 *rc4key, size_t klen, u8 *data, size_t data_len); -int ieee80211_wep_encrypt(struct ieee80211_local *local, struct sk_buff *skb, - struct ieee80211_key *key); -int ieee80211_wep_decrypt(struct ieee80211_local *local, struct sk_buff *skb, - struct ieee80211_key *key); bool ieee80211_wep_is_weak_iv(struct sk_buff *skb, struct ieee80211_key *key); ieee80211_rx_result diff --git a/net/mac80211/wext.c b/net/mac80211/wext.c deleted file mode 100644 index 1da81f45674..00000000000 --- a/net/mac80211/wext.c +++ /dev/null @@ -1,633 +0,0 @@ -/* - * Copyright 2002-2005, Instant802 Networks, Inc. - * Copyright 2005-2006, Devicescape Software, Inc. - * - * 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/module.h> -#include <linux/init.h> -#include <linux/netdevice.h> -#include <linux/types.h> -#include <linux/slab.h> -#include <linux/skbuff.h> -#include <linux/etherdevice.h> -#include <linux/if_arp.h> -#include <linux/wireless.h> -#include <net/iw_handler.h> -#include <asm/uaccess.h> - -#include <net/mac80211.h> -#include "ieee80211_i.h" -#include "led.h" -#include "rate.h" -#include "wpa.h" -#include "aes_ccm.h" - - -static int ieee80211_ioctl_siwgenie(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *data, char *extra) -{ - struct ieee80211_sub_if_data *sdata; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - int ret = ieee80211_sta_set_extra_ie(sdata, extra, data->length); - if (ret && ret != -EALREADY) - return ret; - sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_BSSID_SEL; - sdata->u.mgd.flags &= ~IEEE80211_STA_EXT_SME; - sdata->u.mgd.flags &= ~IEEE80211_STA_CONTROL_PORT; - if (ret != -EALREADY) - ieee80211_sta_req_auth(sdata); - return 0; - } - - return -EOPNOTSUPP; -} - -static int ieee80211_ioctl_siwfreq(struct net_device *dev, - struct iw_request_info *info, - struct iw_freq *freq, char *extra) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; - struct ieee80211_channel *chan; - - if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - return cfg80211_ibss_wext_siwfreq(dev, info, freq, extra); - else if (sdata->vif.type == NL80211_IFTYPE_STATION) - sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_CHANNEL_SEL; - - /* freq->e == 0: freq->m = channel; otherwise freq = m * 10^e */ - if (freq->e == 0) { - if (freq->m < 0) { - if (sdata->vif.type == NL80211_IFTYPE_STATION) - sdata->u.mgd.flags |= - IEEE80211_STA_AUTO_CHANNEL_SEL; - return 0; - } else - chan = ieee80211_get_channel(local->hw.wiphy, - ieee80211_channel_to_frequency(freq->m)); - } else { - int i, div = 1000000; - for (i = 0; i < freq->e; i++) - div /= 10; - if (div <= 0) - return -EINVAL; - chan = ieee80211_get_channel(local->hw.wiphy, freq->m / div); - } - - if (!chan) - return -EINVAL; - - if (chan->flags & IEEE80211_CHAN_DISABLED) - return -EINVAL; - - /* - * no change except maybe auto -> fixed, ignore the HT - * setting so you can fix a channel you're on already - */ - if (local->oper_channel == chan) - return 0; - - if (sdata->vif.type == NL80211_IFTYPE_STATION) - ieee80211_sta_req_auth(sdata); - - local->oper_channel = chan; - local->oper_channel_type = NL80211_CHAN_NO_HT; - ieee80211_hw_config(local, 0); - - return 0; -} - - -static int ieee80211_ioctl_giwfreq(struct net_device *dev, - struct iw_request_info *info, - struct iw_freq *freq, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - return cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); - - freq->m = local->oper_channel->center_freq; - freq->e = 6; - - return 0; -} - - -static int ieee80211_ioctl_siwessid(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *data, char *ssid) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - size_t len = data->length; - int ret; - - if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - return cfg80211_ibss_wext_siwessid(dev, info, data, ssid); - - /* iwconfig uses nul termination in SSID.. */ - if (len > 0 && ssid[len - 1] == '\0') - len--; - - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - if (data->flags) - sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_SSID_SEL; - else - sdata->u.mgd.flags |= IEEE80211_STA_AUTO_SSID_SEL; - - ret = ieee80211_sta_set_ssid(sdata, ssid, len); - if (ret) - return ret; - - sdata->u.mgd.flags &= ~IEEE80211_STA_EXT_SME; - sdata->u.mgd.flags &= ~IEEE80211_STA_CONTROL_PORT; - ieee80211_sta_req_auth(sdata); - return 0; - } - - return -EOPNOTSUPP; -} - - -static int ieee80211_ioctl_giwessid(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *data, char *ssid) -{ - size_t len; - struct ieee80211_sub_if_data *sdata; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - return cfg80211_ibss_wext_giwessid(dev, info, data, ssid); - - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - int res = ieee80211_sta_get_ssid(sdata, ssid, &len); - if (res == 0) { - data->length = len; - data->flags = 1; - } else - data->flags = 0; - return res; - } - - return -EOPNOTSUPP; -} - - -static int ieee80211_ioctl_siwap(struct net_device *dev, - struct iw_request_info *info, - struct sockaddr *ap_addr, char *extra) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); - - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - int ret; - - if (is_zero_ether_addr((u8 *) &ap_addr->sa_data)) - sdata->u.mgd.flags |= IEEE80211_STA_AUTO_BSSID_SEL | - IEEE80211_STA_AUTO_CHANNEL_SEL; - else if (is_broadcast_ether_addr((u8 *) &ap_addr->sa_data)) - sdata->u.mgd.flags |= IEEE80211_STA_AUTO_BSSID_SEL; - else - sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_BSSID_SEL; - ret = ieee80211_sta_set_bssid(sdata, (u8 *) &ap_addr->sa_data); - if (ret) - return ret; - sdata->u.mgd.flags &= ~IEEE80211_STA_EXT_SME; - sdata->u.mgd.flags &= ~IEEE80211_STA_CONTROL_PORT; - ieee80211_sta_req_auth(sdata); - return 0; - } else if (sdata->vif.type == NL80211_IFTYPE_WDS) { - /* - * If it is necessary to update the WDS peer address - * while the interface is running, then we need to do - * more work here, namely if it is running we need to - * add a new and remove the old STA entry, this is - * normally handled by _open() and _stop(). - */ - if (netif_running(dev)) - return -EBUSY; - - memcpy(&sdata->u.wds.remote_addr, (u8 *) &ap_addr->sa_data, - ETH_ALEN); - - return 0; - } - - return -EOPNOTSUPP; -} - - -static int ieee80211_ioctl_giwap(struct net_device *dev, - struct iw_request_info *info, - struct sockaddr *ap_addr, char *extra) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); - - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - if (sdata->u.mgd.state == IEEE80211_STA_MLME_ASSOCIATED) { - ap_addr->sa_family = ARPHRD_ETHER; - memcpy(&ap_addr->sa_data, sdata->u.mgd.bssid, ETH_ALEN); - } else - memset(&ap_addr->sa_data, 0, ETH_ALEN); - return 0; - } else if (sdata->vif.type == NL80211_IFTYPE_WDS) { - ap_addr->sa_family = ARPHRD_ETHER; - memcpy(&ap_addr->sa_data, sdata->u.wds.remote_addr, ETH_ALEN); - return 0; - } - - return -EOPNOTSUPP; -} - - -static int ieee80211_ioctl_siwrate(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *rate, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - int i, err = -EINVAL; - u32 target_rate = rate->value / 100000; - struct ieee80211_sub_if_data *sdata; - struct ieee80211_supported_band *sband; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - - /* target_rate = -1, rate->fixed = 0 means auto only, so use all rates - * target_rate = X, rate->fixed = 1 means only rate X - * target_rate = X, rate->fixed = 0 means all rates <= X */ - sdata->max_ratectrl_rateidx = -1; - sdata->force_unicast_rateidx = -1; - if (rate->value < 0) - return 0; - - for (i=0; i< sband->n_bitrates; i++) { - struct ieee80211_rate *brate = &sband->bitrates[i]; - int this_rate = brate->bitrate; - - if (target_rate == this_rate) { - sdata->max_ratectrl_rateidx = i; - if (rate->fixed) - sdata->force_unicast_rateidx = i; - err = 0; - break; - } - } - return err; -} - -static int ieee80211_ioctl_giwrate(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *rate, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct sta_info *sta; - struct ieee80211_sub_if_data *sdata; - struct ieee80211_supported_band *sband; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - if (sdata->vif.type != NL80211_IFTYPE_STATION) - return -EOPNOTSUPP; - - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - - rcu_read_lock(); - - sta = sta_info_get(local, sdata->u.mgd.bssid); - - if (sta && !(sta->last_tx_rate.flags & IEEE80211_TX_RC_MCS)) - rate->value = sband->bitrates[sta->last_tx_rate.idx].bitrate; - else - rate->value = 0; - - rcu_read_unlock(); - - if (!sta) - return -ENODEV; - - rate->value *= 100000; - - return 0; -} - -static int ieee80211_ioctl_siwpower(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *wrq, - char *extra) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_conf *conf = &local->hw.conf; - int timeout = 0; - bool ps; - - if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) - return -EOPNOTSUPP; - - if (sdata->vif.type != NL80211_IFTYPE_STATION) - return -EINVAL; - - if (wrq->disabled) { - ps = false; - timeout = 0; - goto set; - } - - switch (wrq->flags & IW_POWER_MODE) { - case IW_POWER_ON: /* If not specified */ - case IW_POWER_MODE: /* If set all mask */ - case IW_POWER_ALL_R: /* If explicitely state all */ - ps = true; - break; - default: /* Otherwise we ignore */ - return -EINVAL; - } - - if (wrq->flags & ~(IW_POWER_MODE | IW_POWER_TIMEOUT)) - return -EINVAL; - - if (wrq->flags & IW_POWER_TIMEOUT) - timeout = wrq->value / 1000; - - set: - if (ps == sdata->u.mgd.powersave && timeout == conf->dynamic_ps_timeout) - return 0; - - sdata->u.mgd.powersave = ps; - conf->dynamic_ps_timeout = timeout; - - if (local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS) - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); - - ieee80211_recalc_ps(local, -1); - - return 0; -} - -static int ieee80211_ioctl_giwpower(struct net_device *dev, - struct iw_request_info *info, - union iwreq_data *wrqu, - char *extra) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - wrqu->power.disabled = !sdata->u.mgd.powersave; - - return 0; -} - -static int ieee80211_ioctl_siwauth(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *data, char *extra) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - int ret = 0; - - switch (data->flags & IW_AUTH_INDEX) { - case IW_AUTH_WPA_VERSION: - case IW_AUTH_CIPHER_GROUP: - case IW_AUTH_WPA_ENABLED: - case IW_AUTH_RX_UNENCRYPTED_EAPOL: - case IW_AUTH_KEY_MGMT: - case IW_AUTH_CIPHER_GROUP_MGMT: - break; - case IW_AUTH_CIPHER_PAIRWISE: - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - if (data->value & (IW_AUTH_CIPHER_WEP40 | - IW_AUTH_CIPHER_WEP104 | IW_AUTH_CIPHER_TKIP)) - sdata->u.mgd.flags |= - IEEE80211_STA_TKIP_WEP_USED; - else - sdata->u.mgd.flags &= - ~IEEE80211_STA_TKIP_WEP_USED; - } - break; - case IW_AUTH_DROP_UNENCRYPTED: - sdata->drop_unencrypted = !!data->value; - break; - case IW_AUTH_PRIVACY_INVOKED: - if (sdata->vif.type != NL80211_IFTYPE_STATION) - ret = -EINVAL; - else { - sdata->u.mgd.flags &= ~IEEE80211_STA_PRIVACY_INVOKED; - /* - * Privacy invoked by wpa_supplicant, store the - * value and allow associating to a protected - * network without having a key up front. - */ - if (data->value) - sdata->u.mgd.flags |= - IEEE80211_STA_PRIVACY_INVOKED; - } - break; - case IW_AUTH_80211_AUTH_ALG: - if (sdata->vif.type == NL80211_IFTYPE_STATION) - sdata->u.mgd.auth_algs = data->value; - else - ret = -EOPNOTSUPP; - break; - case IW_AUTH_MFP: - if (!(sdata->local->hw.flags & IEEE80211_HW_MFP_CAPABLE)) { - ret = -EOPNOTSUPP; - break; - } - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - switch (data->value) { - case IW_AUTH_MFP_DISABLED: - sdata->u.mgd.mfp = IEEE80211_MFP_DISABLED; - break; - case IW_AUTH_MFP_OPTIONAL: - sdata->u.mgd.mfp = IEEE80211_MFP_OPTIONAL; - break; - case IW_AUTH_MFP_REQUIRED: - sdata->u.mgd.mfp = IEEE80211_MFP_REQUIRED; - break; - default: - ret = -EINVAL; - } - } else - ret = -EOPNOTSUPP; - break; - default: - ret = -EOPNOTSUPP; - break; - } - return ret; -} - -/* Get wireless statistics. Called by /proc/net/wireless and by SIOCGIWSTATS */ -static struct iw_statistics *ieee80211_get_wireless_stats(struct net_device *dev) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct iw_statistics *wstats = &local->wstats; - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct sta_info *sta = NULL; - - rcu_read_lock(); - - if (sdata->vif.type == NL80211_IFTYPE_STATION) - sta = sta_info_get(local, sdata->u.mgd.bssid); - - if (!sta) { - wstats->discard.fragment = 0; - wstats->discard.misc = 0; - wstats->qual.qual = 0; - wstats->qual.level = 0; - wstats->qual.noise = 0; - wstats->qual.updated = IW_QUAL_ALL_INVALID; - } else { - wstats->qual.updated = 0; - /* - * mirror what cfg80211 does for iwrange/scan results, - * otherwise userspace gets confused. - */ - if (local->hw.flags & (IEEE80211_HW_SIGNAL_UNSPEC | - IEEE80211_HW_SIGNAL_DBM)) { - wstats->qual.updated |= IW_QUAL_LEVEL_UPDATED; - wstats->qual.updated |= IW_QUAL_QUAL_UPDATED; - } else { - wstats->qual.updated |= IW_QUAL_LEVEL_INVALID; - wstats->qual.updated |= IW_QUAL_QUAL_INVALID; - } - - if (local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC) { - wstats->qual.level = sta->last_signal; - wstats->qual.qual = sta->last_signal; - } else if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM) { - int sig = sta->last_signal; - - wstats->qual.updated |= IW_QUAL_DBM; - wstats->qual.level = sig; - if (sig < -110) - sig = -110; - else if (sig > -40) - sig = -40; - wstats->qual.qual = sig + 110; - } - - if (local->hw.flags & IEEE80211_HW_NOISE_DBM) { - /* - * This assumes that if driver reports noise, it also - * reports signal in dBm. - */ - wstats->qual.noise = sta->last_noise; - wstats->qual.updated |= IW_QUAL_NOISE_UPDATED; - } else { - wstats->qual.updated |= IW_QUAL_NOISE_INVALID; - } - } - - rcu_read_unlock(); - - return wstats; -} - -static int ieee80211_ioctl_giwauth(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *data, char *extra) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - int ret = 0; - - switch (data->flags & IW_AUTH_INDEX) { - case IW_AUTH_80211_AUTH_ALG: - if (sdata->vif.type == NL80211_IFTYPE_STATION) - data->value = sdata->u.mgd.auth_algs; - else - ret = -EOPNOTSUPP; - break; - default: - ret = -EOPNOTSUPP; - break; - } - return ret; -} - - -/* Structures to export the Wireless Handlers */ - -static const iw_handler ieee80211_handler[] = -{ - (iw_handler) NULL, /* SIOCSIWCOMMIT */ - (iw_handler) cfg80211_wext_giwname, /* SIOCGIWNAME */ - (iw_handler) NULL, /* SIOCSIWNWID */ - (iw_handler) NULL, /* SIOCGIWNWID */ - (iw_handler) ieee80211_ioctl_siwfreq, /* SIOCSIWFREQ */ - (iw_handler) ieee80211_ioctl_giwfreq, /* SIOCGIWFREQ */ - (iw_handler) cfg80211_wext_siwmode, /* SIOCSIWMODE */ - (iw_handler) cfg80211_wext_giwmode, /* SIOCGIWMODE */ - (iw_handler) NULL, /* SIOCSIWSENS */ - (iw_handler) NULL, /* SIOCGIWSENS */ - (iw_handler) NULL /* not used */, /* SIOCSIWRANGE */ - (iw_handler) cfg80211_wext_giwrange, /* SIOCGIWRANGE */ - (iw_handler) NULL /* not used */, /* SIOCSIWPRIV */ - (iw_handler) NULL /* kernel code */, /* SIOCGIWPRIV */ - (iw_handler) NULL /* not used */, /* SIOCSIWSTATS */ - (iw_handler) NULL /* kernel code */, /* SIOCGIWSTATS */ - (iw_handler) NULL, /* SIOCSIWSPY */ - (iw_handler) NULL, /* SIOCGIWSPY */ - (iw_handler) NULL, /* SIOCSIWTHRSPY */ - (iw_handler) NULL, /* SIOCGIWTHRSPY */ - (iw_handler) ieee80211_ioctl_siwap, /* SIOCSIWAP */ - (iw_handler) ieee80211_ioctl_giwap, /* SIOCGIWAP */ - (iw_handler) cfg80211_wext_siwmlme, /* SIOCSIWMLME */ - (iw_handler) NULL, /* SIOCGIWAPLIST */ - (iw_handler) cfg80211_wext_siwscan, /* SIOCSIWSCAN */ - (iw_handler) cfg80211_wext_giwscan, /* SIOCGIWSCAN */ - (iw_handler) ieee80211_ioctl_siwessid, /* SIOCSIWESSID */ - (iw_handler) ieee80211_ioctl_giwessid, /* SIOCGIWESSID */ - (iw_handler) NULL, /* SIOCSIWNICKN */ - (iw_handler) NULL, /* SIOCGIWNICKN */ - (iw_handler) NULL, /* -- hole -- */ - (iw_handler) NULL, /* -- hole -- */ - (iw_handler) ieee80211_ioctl_siwrate, /* SIOCSIWRATE */ - (iw_handler) ieee80211_ioctl_giwrate, /* SIOCGIWRATE */ - (iw_handler) cfg80211_wext_siwrts, /* SIOCSIWRTS */ - (iw_handler) cfg80211_wext_giwrts, /* SIOCGIWRTS */ - (iw_handler) cfg80211_wext_siwfrag, /* SIOCSIWFRAG */ - (iw_handler) cfg80211_wext_giwfrag, /* SIOCGIWFRAG */ - (iw_handler) cfg80211_wext_siwtxpower, /* SIOCSIWTXPOW */ - (iw_handler) cfg80211_wext_giwtxpower, /* SIOCGIWTXPOW */ - (iw_handler) cfg80211_wext_siwretry, /* SIOCSIWRETRY */ - (iw_handler) cfg80211_wext_giwretry, /* SIOCGIWRETRY */ - (iw_handler) cfg80211_wext_siwencode, /* SIOCSIWENCODE */ - (iw_handler) cfg80211_wext_giwencode, /* SIOCGIWENCODE */ - (iw_handler) ieee80211_ioctl_siwpower, /* SIOCSIWPOWER */ - (iw_handler) ieee80211_ioctl_giwpower, /* SIOCGIWPOWER */ - (iw_handler) NULL, /* -- hole -- */ - (iw_handler) NULL, /* -- hole -- */ - (iw_handler) ieee80211_ioctl_siwgenie, /* SIOCSIWGENIE */ - (iw_handler) NULL, /* SIOCGIWGENIE */ - (iw_handler) ieee80211_ioctl_siwauth, /* SIOCSIWAUTH */ - (iw_handler) ieee80211_ioctl_giwauth, /* SIOCGIWAUTH */ - (iw_handler) cfg80211_wext_siwencodeext, /* SIOCSIWENCODEEXT */ - (iw_handler) NULL, /* SIOCGIWENCODEEXT */ - (iw_handler) NULL, /* SIOCSIWPMKSA */ - (iw_handler) NULL, /* -- hole -- */ -}; - -const struct iw_handler_def ieee80211_iw_handler_def = -{ - .num_standard = ARRAY_SIZE(ieee80211_handler), - .standard = (iw_handler *) ieee80211_handler, - .get_wireless_stats = ieee80211_get_wireless_stats, -}; diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 116a923b14d..b19b7696f3a 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -85,10 +85,8 @@ static u16 classify80211(struct ieee80211_local *local, struct sk_buff *skb) return ieee802_1d_to_ac[skb->priority]; } -u16 ieee80211_select_queue(struct net_device *dev, struct sk_buff *skb) +void ieee80211_select_queue(struct ieee80211_local *local, struct sk_buff *skb) { - struct ieee80211_master_priv *mpriv = netdev_priv(dev); - struct ieee80211_local *local = mpriv->local; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; u16 queue; u8 tid; @@ -113,5 +111,5 @@ u16 ieee80211_select_queue(struct net_device *dev, struct sk_buff *skb) *p = 0; } - return queue; + skb_set_queue_mapping(skb, queue); } diff --git a/net/mac80211/wme.h b/net/mac80211/wme.h index 7520d2e014d..d4fd87ca511 100644 --- a/net/mac80211/wme.h +++ b/net/mac80211/wme.h @@ -20,6 +20,7 @@ extern const int ieee802_1d_to_ac[8]; -u16 ieee80211_select_queue(struct net_device *dev, struct sk_buff *skb); +void ieee80211_select_queue(struct ieee80211_local *local, + struct sk_buff *skb); #endif /* _WME_H */ diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index dcfae8884b8..70778694877 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -122,7 +122,8 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; mac80211_ev_michael_mic_failure(rx->sdata, rx->key->conf.keyidx, - (void *) skb->data, NULL); + (void *) skb->data, NULL, + GFP_ATOMIC); return RX_DROP_UNUSABLE; } diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 201b8ea3020..3c7e42735b6 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -18,6 +18,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> @@ -262,12 +265,12 @@ static inline void vs_fix_seq(const struct ip_vs_seq *vseq, struct tcphdr *th) if (vseq->delta || vseq->previous_delta) { if(after(seq, vseq->init_seq)) { th->seq = htonl(seq + vseq->delta); - IP_VS_DBG(9, "vs_fix_seq(): added delta (%d) to seq\n", - vseq->delta); + IP_VS_DBG(9, "%s(): added delta (%d) to seq\n", + __func__, vseq->delta); } else { th->seq = htonl(seq + vseq->previous_delta); - IP_VS_DBG(9, "vs_fix_seq(): added previous_delta " - "(%d) to seq\n", vseq->previous_delta); + IP_VS_DBG(9, "%s(): added previous_delta (%d) to seq\n", + __func__, vseq->previous_delta); } } } @@ -291,14 +294,14 @@ vs_fix_ack_seq(const struct ip_vs_seq *vseq, struct tcphdr *th) to receive next, so compare it with init_seq+delta */ if(after(ack_seq, vseq->init_seq+vseq->delta)) { th->ack_seq = htonl(ack_seq - vseq->delta); - IP_VS_DBG(9, "vs_fix_ack_seq(): subtracted delta " - "(%d) from ack_seq\n", vseq->delta); + IP_VS_DBG(9, "%s(): subtracted delta " + "(%d) from ack_seq\n", __func__, vseq->delta); } else { th->ack_seq = htonl(ack_seq - vseq->previous_delta); - IP_VS_DBG(9, "vs_fix_ack_seq(): subtracted " + IP_VS_DBG(9, "%s(): subtracted " "previous_delta (%d) from ack_seq\n", - vseq->previous_delta); + __func__, vseq->previous_delta); } } } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 77bfdfeb966..27c30cf933d 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -22,6 +22,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/interrupt.h> #include <linux/in.h> #include <linux/net.h> @@ -150,8 +153,8 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) atomic_inc(&cp->refcnt); ret = 1; } else { - IP_VS_ERR("ip_vs_conn_hash(): request for already hashed, " - "called from %p\n", __builtin_return_address(0)); + pr_err("%s(): request for already hashed, called from %pF\n", + __func__, __builtin_return_address(0)); ret = 0; } @@ -689,7 +692,7 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport, cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC); if (cp == NULL) { - IP_VS_ERR_RL("ip_vs_conn_new: no memory available.\n"); + IP_VS_ERR_RL("%s(): no memory\n", __func__); return NULL; } @@ -1073,10 +1076,10 @@ int __init ip_vs_conn_init(void) return -ENOMEM; } - IP_VS_INFO("Connection hash table configured " - "(size=%d, memory=%ldKbytes)\n", - IP_VS_CONN_TAB_SIZE, - (long)(IP_VS_CONN_TAB_SIZE*sizeof(struct list_head))/1024); + pr_info("Connection hash table configured " + "(size=%d, memory=%ldKbytes)\n", + IP_VS_CONN_TAB_SIZE, + (long)(IP_VS_CONN_TAB_SIZE*sizeof(struct list_head))/1024); IP_VS_DBG(0, "Each connection entry needs %Zd bytes at least\n", sizeof(struct ip_vs_conn)); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 8dddb17a947..b95699f0054 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -24,6 +24,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/ip.h> @@ -388,9 +391,9 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) */ if (!svc->fwmark && pptr[1] != svc->port) { if (!svc->port) - IP_VS_ERR("Schedule: port zero only supported " - "in persistent services, " - "check your ipvs configuration\n"); + pr_err("Schedule: port zero only supported " + "in persistent services, " + "check your ipvs configuration\n"); return NULL; } @@ -462,7 +465,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_service_put(svc); /* create a new connection entry */ - IP_VS_DBG(6, "ip_vs_leave: create a cache_bypass entry\n"); + IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); cp = ip_vs_conn_new(svc->af, iph.protocol, &iph.saddr, pptr[0], &iph.daddr, pptr[1], @@ -664,8 +667,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != 0) { - IP_VS_ERR("shouldn't reach here, because the box is on the " - "half connection in the tun/dr module.\n"); + pr_err("shouldn't reach here, because the box is on the " + "half connection in the tun/dr module.\n"); } /* Ensure the checksum is correct */ @@ -1256,7 +1259,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_conn *cp; - int ret, restart, af; + int ret, restart, af, pkts; af = (skb->protocol == htons(ETH_P_IP)) ? AF_INET : AF_INET6; @@ -1274,13 +1277,24 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, return NF_ACCEPT; } - if (unlikely(iph.protocol == IPPROTO_ICMP)) { - int related, verdict = ip_vs_in_icmp(skb, &related, hooknum); +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) { + if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { + int related, verdict = ip_vs_in_icmp_v6(skb, &related, hooknum); - if (related) - return verdict; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); - } + if (related) + return verdict; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + } + } else +#endif + if (unlikely(iph.protocol == IPPROTO_ICMP)) { + int related, verdict = ip_vs_in_icmp(skb, &related, hooknum); + + if (related) + return verdict; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + } /* Protocol supported? */ pp = ip_vs_proto_get(iph.protocol); @@ -1343,12 +1357,12 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, * Sync connection if it is about to close to * encorage the standby servers to update the connections timeout */ - atomic_inc(&cp->in_pkts); + pkts = atomic_add_return(1, &cp->in_pkts); if (af == AF_INET && (ip_vs_sync_state & IP_VS_STATE_MASTER) && (((cp->protocol != IPPROTO_TCP || cp->state == IP_VS_TCP_S_ESTABLISHED) && - (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1] + (pkts % sysctl_ip_vs_sync_threshold[1] == sysctl_ip_vs_sync_threshold[0])) || ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) && ((cp->state == IP_VS_TCP_S_FIN_WAIT) || @@ -1487,7 +1501,7 @@ static int __init ip_vs_init(void) ret = ip_vs_control_init(); if (ret < 0) { - IP_VS_ERR("can't setup control.\n"); + pr_err("can't setup control.\n"); goto cleanup_estimator; } @@ -1495,23 +1509,23 @@ static int __init ip_vs_init(void) ret = ip_vs_app_init(); if (ret < 0) { - IP_VS_ERR("can't setup application helper.\n"); + pr_err("can't setup application helper.\n"); goto cleanup_protocol; } ret = ip_vs_conn_init(); if (ret < 0) { - IP_VS_ERR("can't setup connection table.\n"); + pr_err("can't setup connection table.\n"); goto cleanup_app; } ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { - IP_VS_ERR("can't register hooks.\n"); + pr_err("can't register hooks.\n"); goto cleanup_conn; } - IP_VS_INFO("ipvs loaded.\n"); + pr_info("ipvs loaded.\n"); return ret; cleanup_conn: @@ -1534,7 +1548,7 @@ static void __exit ip_vs_cleanup(void) ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); - IP_VS_INFO("ipvs unloaded.\n"); + pr_info("ipvs unloaded.\n"); } module_init(ip_vs_init); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 7c1333c67ff..446e9bd4b4b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -18,6 +18,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> @@ -340,8 +343,8 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) unsigned hash; if (svc->flags & IP_VS_SVC_F_HASHED) { - IP_VS_ERR("ip_vs_svc_hash(): request for already hashed, " - "called from %p\n", __builtin_return_address(0)); + pr_err("%s(): request for already hashed, called from %pF\n", + __func__, __builtin_return_address(0)); return 0; } @@ -374,8 +377,8 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) static int ip_vs_svc_unhash(struct ip_vs_service *svc) { if (!(svc->flags & IP_VS_SVC_F_HASHED)) { - IP_VS_ERR("ip_vs_svc_unhash(): request for unhash flagged, " - "called from %p\n", __builtin_return_address(0)); + pr_err("%s(): request for unhash flagged, called from %pF\n", + __func__, __builtin_return_address(0)); return 0; } @@ -841,7 +844,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, dest = kzalloc(sizeof(struct ip_vs_dest), GFP_ATOMIC); if (dest == NULL) { - IP_VS_ERR("ip_vs_new_dest: kmalloc failed.\n"); + pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } @@ -885,13 +888,13 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) EnterFunction(2); if (udest->weight < 0) { - IP_VS_ERR("ip_vs_add_dest(): server weight less than zero\n"); + pr_err("%s(): server weight less than zero\n", __func__); return -ERANGE; } if (udest->l_threshold > udest->u_threshold) { - IP_VS_ERR("ip_vs_add_dest(): lower threshold is higher than " - "upper threshold\n"); + pr_err("%s(): lower threshold is higher than upper threshold\n", + __func__); return -ERANGE; } @@ -903,7 +906,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) dest = ip_vs_lookup_dest(svc, &daddr, dport); if (dest != NULL) { - IP_VS_DBG(1, "ip_vs_add_dest(): dest already exists\n"); + IP_VS_DBG(1, "%s(): dest already exists\n", __func__); return -EEXIST; } @@ -997,13 +1000,13 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) EnterFunction(2); if (udest->weight < 0) { - IP_VS_ERR("ip_vs_edit_dest(): server weight less than zero\n"); + pr_err("%s(): server weight less than zero\n", __func__); return -ERANGE; } if (udest->l_threshold > udest->u_threshold) { - IP_VS_ERR("ip_vs_edit_dest(): lower threshold is higher than " - "upper threshold\n"); + pr_err("%s(): lower threshold is higher than upper threshold\n", + __func__); return -ERANGE; } @@ -1015,7 +1018,7 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) dest = ip_vs_lookup_dest(svc, &daddr, dport); if (dest == NULL) { - IP_VS_DBG(1, "ip_vs_edit_dest(): dest doesn't exist\n"); + IP_VS_DBG(1, "%s(): dest doesn't exist\n", __func__); return -ENOENT; } @@ -1115,7 +1118,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) dest = ip_vs_lookup_dest(svc, &udest->addr, dport); if (dest == NULL) { - IP_VS_DBG(1, "ip_vs_del_dest(): destination not found!\n"); + IP_VS_DBG(1, "%s(): destination not found!\n", __func__); return -ENOENT; } @@ -1161,8 +1164,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, /* Lookup the scheduler by 'u->sched_name' */ sched = ip_vs_scheduler_get(u->sched_name); if (sched == NULL) { - IP_VS_INFO("Scheduler module ip_vs_%s not found\n", - u->sched_name); + pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); ret = -ENOENT; goto out_mod_dec; } @@ -1176,7 +1178,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, svc = kzalloc(sizeof(struct ip_vs_service), GFP_ATOMIC); if (svc == NULL) { - IP_VS_DBG(1, "ip_vs_add_service: kmalloc failed.\n"); + IP_VS_DBG(1, "%s(): no memory\n", __func__); ret = -ENOMEM; goto out_err; } @@ -1259,8 +1261,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) */ sched = ip_vs_scheduler_get(u->sched_name); if (sched == NULL) { - IP_VS_INFO("Scheduler module ip_vs_%s not found\n", - u->sched_name); + pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name); return -ENOENT; } old_sched = sched; @@ -1495,14 +1496,14 @@ static int ip_vs_zero_all(void) static int -proc_do_defense_mode(ctl_table *table, int write, struct file * filp, +proc_do_defense_mode(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; int val = *valp; int rc; - rc = proc_dointvec(table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec(table, write, buffer, lenp, ppos); if (write && (*valp != val)) { if ((*valp < 0) || (*valp > 3)) { /* Restore the correct value */ @@ -1516,7 +1517,7 @@ proc_do_defense_mode(ctl_table *table, int write, struct file * filp, static int -proc_do_sync_threshold(ctl_table *table, int write, struct file *filp, +proc_do_sync_threshold(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; @@ -1526,7 +1527,7 @@ proc_do_sync_threshold(ctl_table *table, int write, struct file *filp, /* backup the value first */ memcpy(val, valp, sizeof(val)); - rc = proc_dointvec(table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec(table, write, buffer, lenp, ppos); if (write && (valp[0] < 0 || valp[1] < 0 || valp[0] >= valp[1])) { /* Restore the correct value */ memcpy(valp, val, sizeof(val)); @@ -2077,8 +2078,8 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) return -EPERM; if (len != set_arglen[SET_CMDID(cmd)]) { - IP_VS_ERR("set_ctl: len %u != %u\n", - len, set_arglen[SET_CMDID(cmd)]); + pr_err("set_ctl: len %u != %u\n", + len, set_arglen[SET_CMDID(cmd)]); return -EINVAL; } @@ -2129,9 +2130,9 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Check for valid protocol: TCP or UDP, even for fwmark!=0 */ if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP) { - IP_VS_ERR("set_ctl: invalid protocol: %d %pI4:%d %s\n", - usvc.protocol, &usvc.addr.ip, - ntohs(usvc.port), usvc.sched_name); + pr_err("set_ctl: invalid protocol: %d %pI4:%d %s\n", + usvc.protocol, &usvc.addr.ip, + ntohs(usvc.port), usvc.sched_name); ret = -EFAULT; goto out_unlock; } @@ -2356,8 +2357,8 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return -EPERM; if (*len < get_arglen[GET_CMDID(cmd)]) { - IP_VS_ERR("get_ctl: len %u < %u\n", - *len, get_arglen[GET_CMDID(cmd)]); + pr_err("get_ctl: len %u < %u\n", + *len, get_arglen[GET_CMDID(cmd)]); return -EINVAL; } @@ -2402,7 +2403,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) size = sizeof(*get) + sizeof(struct ip_vs_service_entry) * get->num_services; if (*len != size) { - IP_VS_ERR("length: %u != %u\n", *len, size); + pr_err("length: %u != %u\n", *len, size); ret = -EINVAL; goto out; } @@ -2442,7 +2443,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) size = sizeof(*get) + sizeof(struct ip_vs_dest_entry) * get->num_dests; if (*len != size) { - IP_VS_ERR("length: %u != %u\n", *len, size); + pr_err("length: %u != %u\n", *len, size); ret = -EINVAL; goto out; } @@ -3170,7 +3171,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) else if (cmd == IPVS_CMD_GET_CONFIG) reply_cmd = IPVS_CMD_SET_CONFIG; else { - IP_VS_ERR("unknown Generic Netlink command\n"); + pr_err("unknown Generic Netlink command\n"); return -EINVAL; } @@ -3231,11 +3232,11 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) } genlmsg_end(msg, reply); - ret = genlmsg_unicast(msg, info->snd_pid); + ret = genlmsg_reply(msg, info); goto out; nla_put_failure: - IP_VS_ERR("not enough space in Netlink message\n"); + pr_err("not enough space in Netlink message\n"); ret = -EMSGSIZE; out_err: @@ -3366,13 +3367,13 @@ int __init ip_vs_control_init(void) ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { - IP_VS_ERR("cannot register sockopt.\n"); + pr_err("cannot register sockopt.\n"); return ret; } ret = ip_vs_genl_register(); if (ret) { - IP_VS_ERR("cannot register Generic Netlink interface.\n"); + pr_err("cannot register Generic Netlink interface.\n"); nf_unregister_sockopt(&ip_vs_sockopts); return ret; } diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index a9dac74bb13..fe3e18834b9 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -35,6 +35,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/ip.h> #include <linux/module.h> #include <linux/kernel.h> @@ -147,7 +150,7 @@ static int ip_vs_dh_init_svc(struct ip_vs_service *svc) tbl = kmalloc(sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE, GFP_ATOMIC); if (tbl == NULL) { - IP_VS_ERR("ip_vs_dh_init_svc(): no memory\n"); + pr_err("%s(): no memory\n", __func__); return -ENOMEM; } svc->sched_data = tbl; @@ -214,7 +217,7 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); - IP_VS_DBG(6, "ip_vs_dh_schedule(): Scheduling...\n"); + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); tbl = (struct ip_vs_dh_bucket *)svc->sched_data; dest = ip_vs_dh_get(svc->af, tbl, &iph.daddr); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 2eb2860dabb..702b53ca937 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -11,6 +11,10 @@ * Changes: * */ + +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/slab.h> diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 428edbf481c..33e2c799cba 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -22,6 +22,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kernel.h> @@ -382,8 +385,8 @@ static int __init ip_vs_ftp_init(void) ret = register_ip_vs_app_inc(app, app->protocol, ports[i]); if (ret) break; - IP_VS_INFO("%s: loaded support on port[%d] = %d\n", - app->name, i, ports[i]); + pr_info("%s: loaded support on port[%d] = %d\n", + app->name, i, ports[i]); } if (ret) diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 3eb5e2660c4..c1757f3620c 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -39,6 +39,9 @@ * me to write this module. */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/ip.h> #include <linux/module.h> #include <linux/kernel.h> @@ -199,7 +202,7 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr, if (!en) { en = kmalloc(sizeof(*en), GFP_ATOMIC); if (!en) { - IP_VS_ERR("ip_vs_lblc_new(): no memory\n"); + pr_err("%s(): no memory\n", __func__); return NULL; } @@ -332,7 +335,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) */ tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC); if (tbl == NULL) { - IP_VS_ERR("ip_vs_lblc_init_svc(): no memory\n"); + pr_err("%s(): no memory\n", __func__); return -ENOMEM; } svc->sched_data = tbl; @@ -477,7 +480,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); - IP_VS_DBG(6, "ip_vs_lblc_schedule(): Scheduling...\n"); + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* First look in our cache */ read_lock(&svc->sched_lock); diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index c04ce56c7f0..715b57f9540 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -37,6 +37,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/ip.h> #include <linux/module.h> #include <linux/kernel.h> @@ -108,7 +111,7 @@ ip_vs_dest_set_insert(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) e = kmalloc(sizeof(*e), GFP_ATOMIC); if (e == NULL) { - IP_VS_ERR("ip_vs_dest_set_insert(): no memory\n"); + pr_err("%s(): no memory\n", __func__); return NULL; } @@ -202,8 +205,9 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) } } - IP_VS_DBG_BUF(6, "ip_vs_dest_set_min: server %s:%d " + IP_VS_DBG_BUF(6, "%s(): server %s:%d " "activeconns %d refcnt %d weight %d overhead %d\n", + __func__, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), @@ -249,8 +253,9 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) } } - IP_VS_DBG_BUF(6, "ip_vs_dest_set_max: server %s:%d " + IP_VS_DBG_BUF(6, "%s(): server %s:%d " "activeconns %d refcnt %d weight %d overhead %d\n", + __func__, IP_VS_DBG_ADDR(most->af, &most->addr), ntohs(most->port), atomic_read(&most->activeconns), atomic_read(&most->refcnt), @@ -374,7 +379,7 @@ ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr, if (!en) { en = kmalloc(sizeof(*en), GFP_ATOMIC); if (!en) { - IP_VS_ERR("ip_vs_lblcr_new(): no memory\n"); + pr_err("%s(): no memory\n", __func__); return NULL; } @@ -508,7 +513,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) */ tbl = kmalloc(sizeof(*tbl), GFP_ATOMIC); if (tbl == NULL) { - IP_VS_ERR("ip_vs_lblcr_init_svc(): no memory\n"); + pr_err("%s(): no memory\n", __func__); return -ENOMEM; } svc->sched_data = tbl; @@ -654,7 +659,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); - IP_VS_DBG(6, "ip_vs_lblcr_schedule(): Scheduling...\n"); + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* First look in our cache */ read_lock(&svc->sched_lock); diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c index d0dadc8a65f..4f69db1fac5 100644 --- a/net/netfilter/ipvs/ip_vs_lc.c +++ b/net/netfilter/ipvs/ip_vs_lc.c @@ -14,6 +14,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> @@ -44,7 +47,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_dest *dest, *least = NULL; unsigned int loh = 0, doh; - IP_VS_DBG(6, "ip_vs_lc_schedule(): Scheduling...\n"); + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* * Simply select the server with the least number of diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index 694952db502..c413e183082 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -31,6 +31,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> @@ -57,7 +60,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_dest *dest, *least = NULL; unsigned int loh = 0, doh; - IP_VS_DBG(6, "ip_vs_nq_schedule(): Scheduling...\n"); + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* * We calculate the load of each dest server as follows: diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index a01520e3d6b..3e767167454 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -13,6 +13,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> @@ -124,7 +127,8 @@ ip_vs_create_timeout_table(int *table, int size) * Set timeout value for state specified by name */ int -ip_vs_set_state_timeout(int *table, int num, char **names, char *name, int to) +ip_vs_set_state_timeout(int *table, int num, const char *const *names, + const char *name, int to) { int i; @@ -181,7 +185,7 @@ ip_vs_tcpudp_debug_packet_v4(struct ip_vs_protocol *pp, &ih->daddr, ntohs(pptr[1])); } - printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); + pr_debug("%s: %s\n", msg, buf); } #ifdef CONFIG_IP_VS_IPV6 @@ -215,7 +219,7 @@ ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp, &ih->daddr, ntohs(pptr[1])); } - printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); + pr_debug("%s: %s\n", msg, buf); } #endif @@ -259,7 +263,7 @@ int __init ip_vs_protocol_init(void) #ifdef CONFIG_IP_VS_PROTO_ESP REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif - IP_VS_INFO("Registered protocols (%s)\n", &protocols[2]); + pr_info("Registered protocols (%s)\n", &protocols[2]); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 79f56c1e7c1..c30b43c36cd 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -10,6 +10,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/in.h> #include <linux/ip.h> #include <linux/module.h> @@ -138,7 +141,7 @@ ah_esp_debug_packet_v4(struct ip_vs_protocol *pp, const struct sk_buff *skb, sprintf(buf, "%s %pI4->%pI4", pp->name, &ih->saddr, &ih->daddr); - printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); + pr_debug("%s: %s\n", msg, buf); } #ifdef CONFIG_IP_VS_IPV6 @@ -156,7 +159,7 @@ ah_esp_debug_packet_v6(struct ip_vs_protocol *pp, const struct sk_buff *skb, sprintf(buf, "%s %pI6->%pI6", pp->name, &ih->saddr, &ih->daddr); - printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf); + pr_debug("%s: %s\n", msg, buf); } #endif diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 8cba4180285..91d28e07374 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -13,6 +13,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> /* for tcphdr */ @@ -374,7 +377,7 @@ static int tcp_timeouts[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_LAST] = 2*HZ, }; -static char * tcp_state_name_table[IP_VS_TCP_S_LAST+1] = { +static const char *const tcp_state_name_table[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = "NONE", [IP_VS_TCP_S_ESTABLISHED] = "ESTABLISHED", [IP_VS_TCP_S_SYN_SENT] = "SYN_SENT", @@ -661,7 +664,7 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) break; spin_unlock(&tcp_app_lock); - IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->" + IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", __func__, IP_VS_DBG_ADDR(cp->af, &cp->caddr), diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index d2930a71084..e7a6885e016 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -13,6 +13,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/in.h> #include <linux/ip.h> #include <linux/kernel.h> @@ -442,7 +445,7 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp) break; spin_unlock(&udp_app_lock); - IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->" + IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", __func__, IP_VS_DBG_ADDR(cp->af, &cp->caddr), @@ -469,7 +472,7 @@ static int udp_timeouts[IP_VS_UDP_S_LAST+1] = { [IP_VS_UDP_S_LAST] = 2*HZ, }; -static char * udp_state_name_table[IP_VS_UDP_S_LAST+1] = { +static const char *const udp_state_name_table[IP_VS_UDP_S_LAST+1] = { [IP_VS_UDP_S_NORMAL] = "UDP", [IP_VS_UDP_S_LAST] = "BUG!", }; diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c index 2d16ab7f8c1..e210f37d8ea 100644 --- a/net/netfilter/ipvs/ip_vs_rr.c +++ b/net/netfilter/ipvs/ip_vs_rr.c @@ -19,6 +19,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> @@ -48,7 +51,7 @@ ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct list_head *p, *q; struct ip_vs_dest *dest; - IP_VS_DBG(6, "ip_vs_rr_schedule(): Scheduling...\n"); + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); write_lock(&svc->sched_lock); p = (struct list_head *)svc->sched_data; diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index a46ad9e3501..bbc1ac79595 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -17,6 +17,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/spinlock.h> #include <linux/interrupt.h> @@ -44,11 +47,11 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc, int ret; if (svc == NULL) { - IP_VS_ERR("ip_vs_bind_scheduler(): svc arg NULL\n"); + pr_err("%s(): svc arg NULL\n", __func__); return -EINVAL; } if (scheduler == NULL) { - IP_VS_ERR("ip_vs_bind_scheduler(): scheduler arg NULL\n"); + pr_err("%s(): scheduler arg NULL\n", __func__); return -EINVAL; } @@ -57,7 +60,7 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc, if (scheduler->init_service) { ret = scheduler->init_service(svc); if (ret) { - IP_VS_ERR("ip_vs_bind_scheduler(): init error\n"); + pr_err("%s(): init error\n", __func__); return ret; } } @@ -74,19 +77,19 @@ int ip_vs_unbind_scheduler(struct ip_vs_service *svc) struct ip_vs_scheduler *sched; if (svc == NULL) { - IP_VS_ERR("ip_vs_unbind_scheduler(): svc arg NULL\n"); + pr_err("%s(): svc arg NULL\n", __func__); return -EINVAL; } sched = svc->scheduler; if (sched == NULL) { - IP_VS_ERR("ip_vs_unbind_scheduler(): svc isn't bound\n"); + pr_err("%s(): svc isn't bound\n", __func__); return -EINVAL; } if (sched->done_service) { if (sched->done_service(svc) != 0) { - IP_VS_ERR("ip_vs_unbind_scheduler(): done error\n"); + pr_err("%s(): done error\n", __func__); return -EINVAL; } } @@ -103,8 +106,7 @@ static struct ip_vs_scheduler *ip_vs_sched_getbyname(const char *sched_name) { struct ip_vs_scheduler *sched; - IP_VS_DBG(2, "ip_vs_sched_getbyname(): sched_name \"%s\"\n", - sched_name); + IP_VS_DBG(2, "%s(): sched_name \"%s\"\n", __func__, sched_name); read_lock_bh(&__ip_vs_sched_lock); @@ -170,12 +172,12 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) struct ip_vs_scheduler *sched; if (!scheduler) { - IP_VS_ERR("register_ip_vs_scheduler(): NULL arg\n"); + pr_err("%s(): NULL arg\n", __func__); return -EINVAL; } if (!scheduler->name) { - IP_VS_ERR("register_ip_vs_scheduler(): NULL scheduler_name\n"); + pr_err("%s(): NULL scheduler_name\n", __func__); return -EINVAL; } @@ -187,8 +189,8 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) if (!list_empty(&scheduler->n_list)) { write_unlock_bh(&__ip_vs_sched_lock); ip_vs_use_count_dec(); - IP_VS_ERR("register_ip_vs_scheduler(): [%s] scheduler " - "already linked\n", scheduler->name); + pr_err("%s(): [%s] scheduler already linked\n", + __func__, scheduler->name); return -EINVAL; } @@ -200,9 +202,8 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) if (strcmp(scheduler->name, sched->name) == 0) { write_unlock_bh(&__ip_vs_sched_lock); ip_vs_use_count_dec(); - IP_VS_ERR("register_ip_vs_scheduler(): [%s] scheduler " - "already existed in the system\n", - scheduler->name); + pr_err("%s(): [%s] scheduler already existed " + "in the system\n", __func__, scheduler->name); return -EINVAL; } } @@ -212,7 +213,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) list_add(&scheduler->n_list, &ip_vs_schedulers); write_unlock_bh(&__ip_vs_sched_lock); - IP_VS_INFO("[%s] scheduler registered.\n", scheduler->name); + pr_info("[%s] scheduler registered.\n", scheduler->name); return 0; } @@ -224,15 +225,15 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) { if (!scheduler) { - IP_VS_ERR( "unregister_ip_vs_scheduler(): NULL arg\n"); + pr_err("%s(): NULL arg\n", __func__); return -EINVAL; } write_lock_bh(&__ip_vs_sched_lock); if (list_empty(&scheduler->n_list)) { write_unlock_bh(&__ip_vs_sched_lock); - IP_VS_ERR("unregister_ip_vs_scheduler(): [%s] scheduler " - "is not in the list. failed\n", scheduler->name); + pr_err("%s(): [%s] scheduler is not in the list. failed\n", + __func__, scheduler->name); return -EINVAL; } @@ -245,7 +246,7 @@ int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) /* decrease the module use count */ ip_vs_use_count_dec(); - IP_VS_INFO("[%s] scheduler unregistered.\n", scheduler->name); + pr_info("[%s] scheduler unregistered.\n", scheduler->name); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index 20e4657d2f3..1ab75a9dc40 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -35,6 +35,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> @@ -61,7 +64,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_dest *dest, *least; unsigned int loh, doh; - IP_VS_DBG(6, "ip_vs_sed_schedule(): Scheduling...\n"); + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* * We calculate the load of each dest server as follows: diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index 75709ebeb63..8e6cfd36e6f 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -32,6 +32,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/ip.h> #include <linux/module.h> #include <linux/kernel.h> @@ -144,7 +147,7 @@ static int ip_vs_sh_init_svc(struct ip_vs_service *svc) tbl = kmalloc(sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE, GFP_ATOMIC); if (tbl == NULL) { - IP_VS_ERR("ip_vs_sh_init_svc(): no memory\n"); + pr_err("%s(): no memory\n", __func__); return -ENOMEM; } svc->sched_data = tbl; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 5c48378a852..e177f0dc208 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -17,6 +17,9 @@ * Justin Ossevoort : Fix endian problem on sync message size. */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/slab.h> #include <linux/inetdevice.h> @@ -243,7 +246,7 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp) if (!curr_sb) { if (!(curr_sb=ip_vs_sync_buff_create())) { spin_unlock(&curr_sb_lock); - IP_VS_ERR("ip_vs_sync_buff_create failed.\n"); + pr_err("ip_vs_sync_buff_create failed.\n"); return; } } @@ -409,7 +412,7 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) if (dest) atomic_dec(&dest->refcnt); if (!cp) { - IP_VS_ERR("ip_vs_conn_new failed\n"); + pr_err("ip_vs_conn_new failed\n"); return; } } else if (!cp->dest) { @@ -577,8 +580,8 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname) addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); if (!addr) - IP_VS_ERR("You probably need to specify IP address on " - "multicast interface.\n"); + pr_err("You probably need to specify IP address on " + "multicast interface.\n"); IP_VS_DBG(7, "binding socket with (%s) %pI4\n", ifname, &addr); @@ -602,13 +605,13 @@ static struct socket * make_send_sock(void) /* First create a socket */ result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { - IP_VS_ERR("Error during creation of socket; terminating\n"); + pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } result = set_mcast_if(sock->sk, ip_vs_master_mcast_ifn); if (result < 0) { - IP_VS_ERR("Error setting outbound mcast interface\n"); + pr_err("Error setting outbound mcast interface\n"); goto error; } @@ -617,14 +620,14 @@ static struct socket * make_send_sock(void) result = bind_mcastif_addr(sock, ip_vs_master_mcast_ifn); if (result < 0) { - IP_VS_ERR("Error binding address of the mcast interface\n"); + pr_err("Error binding address of the mcast interface\n"); goto error; } result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr, sizeof(struct sockaddr), 0); if (result < 0) { - IP_VS_ERR("Error connecting to the multicast addr\n"); + pr_err("Error connecting to the multicast addr\n"); goto error; } @@ -647,7 +650,7 @@ static struct socket * make_receive_sock(void) /* First create a socket */ result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { - IP_VS_ERR("Error during creation of socket; terminating\n"); + pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } @@ -657,7 +660,7 @@ static struct socket * make_receive_sock(void) result = sock->ops->bind(sock, (struct sockaddr *) &mcast_addr, sizeof(struct sockaddr)); if (result < 0) { - IP_VS_ERR("Error binding to the multicast addr\n"); + pr_err("Error binding to the multicast addr\n"); goto error; } @@ -666,7 +669,7 @@ static struct socket * make_receive_sock(void) (struct in_addr *) &mcast_addr.sin_addr, ip_vs_backup_mcast_ifn); if (result < 0) { - IP_VS_ERR("Error joining to the multicast group\n"); + pr_err("Error joining to the multicast group\n"); goto error; } @@ -706,7 +709,7 @@ ip_vs_send_sync_msg(struct socket *sock, struct ip_vs_sync_mesg *msg) msg->size = htons(msg->size); if (ip_vs_send_async(sock, (char *)msg, msize) != msize) - IP_VS_ERR("ip_vs_send_async error\n"); + pr_err("ip_vs_send_async error\n"); } static int @@ -737,9 +740,9 @@ static int sync_thread_master(void *data) struct ip_vs_sync_thread_data *tinfo = data; struct ip_vs_sync_buff *sb; - IP_VS_INFO("sync thread started: state = MASTER, mcast_ifn = %s, " - "syncid = %d\n", - ip_vs_master_mcast_ifn, ip_vs_master_syncid); + pr_info("sync thread started: state = MASTER, mcast_ifn = %s, " + "syncid = %d\n", + ip_vs_master_mcast_ifn, ip_vs_master_syncid); while (!kthread_should_stop()) { while ((sb = sb_dequeue())) { @@ -780,9 +783,9 @@ static int sync_thread_backup(void *data) struct ip_vs_sync_thread_data *tinfo = data; int len; - IP_VS_INFO("sync thread started: state = BACKUP, mcast_ifn = %s, " - "syncid = %d\n", - ip_vs_backup_mcast_ifn, ip_vs_backup_syncid); + pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " + "syncid = %d\n", + ip_vs_backup_mcast_ifn, ip_vs_backup_syncid); while (!kthread_should_stop()) { wait_event_interruptible(*tinfo->sock->sk->sk_sleep, @@ -794,7 +797,7 @@ static int sync_thread_backup(void *data) len = ip_vs_receive(tinfo->sock, tinfo->buf, sync_recv_mesg_maxlen); if (len <= 0) { - IP_VS_ERR("receiving message error\n"); + pr_err("receiving message error\n"); break; } @@ -824,7 +827,7 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) int (*threadfn)(void *data); int result = -ENOMEM; - IP_VS_DBG(7, "%s: pid %d\n", __func__, task_pid_nr(current)); + IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n", sizeof(struct ip_vs_sync_conn)); @@ -901,14 +904,14 @@ out: int stop_sync_thread(int state) { - IP_VS_DBG(7, "%s: pid %d\n", __func__, task_pid_nr(current)); + IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); if (state == IP_VS_STATE_MASTER) { if (!sync_master_thread) return -ESRCH; - IP_VS_INFO("stopping master sync thread %d ...\n", - task_pid_nr(sync_master_thread)); + pr_info("stopping master sync thread %d ...\n", + task_pid_nr(sync_master_thread)); /* * The lock synchronizes with sb_queue_tail(), so that we don't @@ -925,8 +928,8 @@ int stop_sync_thread(int state) if (!sync_backup_thread) return -ESRCH; - IP_VS_INFO("stopping backup sync thread %d ...\n", - task_pid_nr(sync_backup_thread)); + pr_info("stopping backup sync thread %d ...\n", + task_pid_nr(sync_backup_thread)); ip_vs_sync_state &= ~IP_VS_STATE_BACKUP; kthread_stop(sync_backup_thread); diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index 8e942565b47..bbddfdb10db 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -19,6 +19,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index f7d74ef1ecf..6182e8ea0be 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -18,6 +18,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/net.h> @@ -74,11 +77,12 @@ static int ip_vs_wrr_gcd_weight(struct ip_vs_service *svc) static int ip_vs_wrr_max_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; - int weight = 0; + int new_weight, weight = 0; list_for_each_entry(dest, &svc->destinations, n_list) { - if (atomic_read(&dest->weight) > weight) - weight = atomic_read(&dest->weight); + new_weight = atomic_read(&dest->weight); + if (new_weight > weight) + weight = new_weight; } return weight; @@ -94,7 +98,7 @@ static int ip_vs_wrr_init_svc(struct ip_vs_service *svc) */ mark = kmalloc(sizeof(struct ip_vs_wrr_mark), GFP_ATOMIC); if (mark == NULL) { - IP_VS_ERR("ip_vs_wrr_init_svc(): no memory\n"); + pr_err("%s(): no memory\n", __func__); return -ENOMEM; } mark->cl = &svc->destinations; @@ -141,7 +145,7 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_wrr_mark *mark = svc->sched_data; struct list_head *p; - IP_VS_DBG(6, "ip_vs_wrr_schedule(): Scheduling...\n"); + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* * This loop will always terminate, because mark->cw in (0, max_weight] diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 5874657af7f..30b3189bd29 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -13,6 +13,9 @@ * */ +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/kernel.h> #include <linux/tcp.h> /* for tcphdr */ #include <net/ip.h> @@ -235,8 +238,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (ip_route_output_key(&init_net, &rt, &fl)) { - IP_VS_DBG_RL("ip_vs_bypass_xmit(): ip_route_output error, dest: %pI4\n", - &iph->daddr); + IP_VS_DBG_RL("%s(): ip_route_output error, dest: %pI4\n", + __func__, &iph->daddr); goto tx_error_icmp; } @@ -245,7 +248,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); - IP_VS_DBG_RL("ip_vs_bypass_xmit(): frag needed\n"); + IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -299,8 +302,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl); if (!rt) { - IP_VS_DBG_RL("ip_vs_bypass_xmit_v6(): ip6_route_output error, dest: %pI6\n", - &iph->daddr); + IP_VS_DBG_RL("%s(): ip6_route_output error, dest: %pI6\n", + __func__, &iph->daddr); goto tx_error_icmp; } @@ -309,7 +312,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb->len > mtu) { dst_release(&rt->u.dst); icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); - IP_VS_DBG_RL("ip_vs_bypass_xmit_v6(): frag needed\n"); + IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -536,9 +539,9 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (skb->protocol != htons(ETH_P_IP)) { - IP_VS_DBG_RL("ip_vs_tunnel_xmit(): protocol error, " + IP_VS_DBG_RL("%s(): protocol error, " "ETH_P_IP: %d, skb protocol: %d\n", - htons(ETH_P_IP), skb->protocol); + __func__, htons(ETH_P_IP), skb->protocol); goto tx_error; } @@ -550,7 +553,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); if (mtu < 68) { ip_rt_put(rt); - IP_VS_DBG_RL("ip_vs_tunnel_xmit(): mtu less than 68\n"); + IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__); goto tx_error; } if (skb_dst(skb)) @@ -562,7 +565,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, && mtu < ntohs(old_iph->tot_len)) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); - IP_VS_DBG_RL("ip_vs_tunnel_xmit(): frag needed\n"); + IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -578,7 +581,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!new_skb) { ip_rt_put(rt); kfree_skb(skb); - IP_VS_ERR_RL("ip_vs_tunnel_xmit(): no memory\n"); + IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } kfree_skb(skb); @@ -646,9 +649,9 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (skb->protocol != htons(ETH_P_IPV6)) { - IP_VS_DBG_RL("ip_vs_tunnel_xmit_v6(): protocol error, " + IP_VS_DBG_RL("%s(): protocol error, " "ETH_P_IPV6: %d, skb protocol: %d\n", - htons(ETH_P_IPV6), skb->protocol); + __func__, htons(ETH_P_IPV6), skb->protocol); goto tx_error; } @@ -662,7 +665,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* TODO IPv6: do we need this check in IPv6? */ if (mtu < 1280) { dst_release(&rt->u.dst); - IP_VS_DBG_RL("ip_vs_tunnel_xmit_v6(): mtu less than 1280\n"); + IP_VS_DBG_RL("%s(): mtu less than 1280\n", __func__); goto tx_error; } if (skb_dst(skb)) @@ -671,7 +674,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); dst_release(&rt->u.dst); - IP_VS_DBG_RL("ip_vs_tunnel_xmit_v6(): frag needed\n"); + IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -687,7 +690,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (!new_skb) { dst_release(&rt->u.dst); kfree_skb(skb); - IP_VS_ERR_RL("ip_vs_tunnel_xmit_v6(): no memory\n"); + IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } kfree_skb(skb); @@ -760,7 +763,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); - IP_VS_DBG_RL("ip_vs_dr_xmit(): frag needed\n"); + IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -813,7 +816,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); dst_release(&rt->u.dst); - IP_VS_DBG_RL("ip_vs_dr_xmit_v6(): frag needed\n"); + IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -888,7 +891,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) { ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); - IP_VS_DBG_RL("ip_vs_in_icmp(): frag needed\n"); + IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -963,7 +966,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb->len > mtu) { dst_release(&rt->u.dst); icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); - IP_VS_DBG_RL("ip_vs_in_icmp(): frag needed\n"); + IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index b5869b9574b..b9168c1864c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/netfilter.h> #include <linux/module.h> +#include <linux/sched.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/vmalloc.h> @@ -47,7 +48,7 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, enum nf_nat_manip_type manip, - struct nlattr *attr) __read_mostly; + const struct nlattr *attr) __read_mostly; EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); DEFINE_SPINLOCK(nf_conntrack_lock); @@ -1089,14 +1090,14 @@ void nf_conntrack_flush_report(struct net *net, u32 pid, int report) } EXPORT_SYMBOL_GPL(nf_conntrack_flush_report); -static void nf_ct_release_dying_list(void) +static void nf_ct_release_dying_list(struct net *net) { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; spin_lock_bh(&nf_conntrack_lock); - hlist_nulls_for_each_entry(h, n, &init_net.ct.dying, hnnode) { + hlist_nulls_for_each_entry(h, n, &net->ct.dying, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); /* never fails to remove them, no listeners at this point */ nf_ct_kill(ct); @@ -1115,7 +1116,7 @@ static void nf_conntrack_cleanup_net(struct net *net) { i_see_dead_people: nf_ct_iterate_cleanup(net, kill_all, NULL); - nf_ct_release_dying_list(); + nf_ct_release_dying_list(net); if (atomic_read(&net->ct.count) != 0) { schedule(); goto i_see_dead_people; @@ -1245,9 +1246,9 @@ static int nf_conntrack_init_init_net(void) * machine has 512 buckets. >= 1GB machines have 16384 buckets. */ if (!nf_conntrack_htable_size) { nf_conntrack_htable_size - = (((num_physpages << PAGE_SHIFT) / 16384) + = (((totalram_pages << PAGE_SHIFT) / 16384) / sizeof(struct hlist_head)); - if (num_physpages > (1024 * 1024 * 1024 / PAGE_SIZE)) + if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE)) nf_conntrack_htable_size = 16384; if (nf_conntrack_htable_size < 32) nf_conntrack_htable_size = 32; @@ -1350,6 +1351,11 @@ err_stat: return ret; } +s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq); +EXPORT_SYMBOL_GPL(nf_ct_nat_offset); + int nf_conntrack_init(struct net *net) { int ret; @@ -1367,6 +1373,9 @@ int nf_conntrack_init(struct net *net) /* For use by REJECT target */ rcu_assign_pointer(ip_ct_attach, nf_conntrack_attach); rcu_assign_pointer(nf_ct_destroy, destroy_conntrack); + + /* Howto get NAT offsets */ + rcu_assign_pointer(nf_ct_nat_offset, NULL); } return 0; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 49479d19457..59d8064eb52 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -704,7 +704,8 @@ ctnetlink_parse_tuple_proto(struct nlattr *attr, } static int -ctnetlink_parse_tuple(struct nlattr *cda[], struct nf_conntrack_tuple *tuple, +ctnetlink_parse_tuple(const struct nlattr * const cda[], + struct nf_conntrack_tuple *tuple, enum ctattr_tuple type, u_int8_t l3num) { struct nlattr *tb[CTA_TUPLE_MAX+1]; @@ -740,7 +741,7 @@ ctnetlink_parse_tuple(struct nlattr *cda[], struct nf_conntrack_tuple *tuple, } static inline int -ctnetlink_parse_help(struct nlattr *attr, char **helper_name) +ctnetlink_parse_help(const struct nlattr *attr, char **helper_name) { struct nlattr *tb[CTA_HELP_MAX+1]; @@ -764,7 +765,8 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { static int ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *cda[]) + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; @@ -823,7 +825,8 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, static int ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *cda[]) + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; @@ -884,7 +887,7 @@ out: static int ctnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, - struct nlattr *attr) + const struct nlattr *attr) { typeof(nfnetlink_parse_nat_setup_hook) parse_nat_setup; @@ -914,7 +917,7 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, #endif static int -ctnetlink_change_status(struct nf_conn *ct, struct nlattr *cda[]) +ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) { unsigned long d; unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS])); @@ -940,7 +943,7 @@ ctnetlink_change_status(struct nf_conn *ct, struct nlattr *cda[]) } static int -ctnetlink_change_nat(struct nf_conn *ct, struct nlattr *cda[]) +ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_NAT_NEEDED int ret; @@ -966,7 +969,7 @@ ctnetlink_change_nat(struct nf_conn *ct, struct nlattr *cda[]) } static inline int -ctnetlink_change_helper(struct nf_conn *ct, struct nlattr *cda[]) +ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conntrack_helper *helper; struct nf_conn_help *help = nfct_help(ct); @@ -1028,7 +1031,7 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nlattr *cda[]) } static inline int -ctnetlink_change_timeout(struct nf_conn *ct, struct nlattr *cda[]) +ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[]) { u_int32_t timeout = ntohl(nla_get_be32(cda[CTA_TIMEOUT])); @@ -1042,9 +1045,10 @@ ctnetlink_change_timeout(struct nf_conn *ct, struct nlattr *cda[]) } static inline int -ctnetlink_change_protoinfo(struct nf_conn *ct, struct nlattr *cda[]) +ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[]) { - struct nlattr *tb[CTA_PROTOINFO_MAX+1], *attr = cda[CTA_PROTOINFO]; + const struct nlattr *attr = cda[CTA_PROTOINFO]; + struct nlattr *tb[CTA_PROTOINFO_MAX+1]; struct nf_conntrack_l4proto *l4proto; int err = 0; @@ -1061,7 +1065,7 @@ ctnetlink_change_protoinfo(struct nf_conn *ct, struct nlattr *cda[]) #ifdef CONFIG_NF_NAT_NEEDED static inline int -change_nat_seq_adj(struct nf_nat_seq *natseq, struct nlattr *attr) +change_nat_seq_adj(struct nf_nat_seq *natseq, const struct nlattr * const attr) { struct nlattr *cda[CTA_NAT_SEQ_MAX+1]; @@ -1089,7 +1093,8 @@ change_nat_seq_adj(struct nf_nat_seq *natseq, struct nlattr *attr) } static int -ctnetlink_change_nat_seq_adj(struct nf_conn *ct, struct nlattr *cda[]) +ctnetlink_change_nat_seq_adj(struct nf_conn *ct, + const struct nlattr * const cda[]) { int ret = 0; struct nf_conn_nat *nat = nfct_nat(ct); @@ -1120,7 +1125,8 @@ ctnetlink_change_nat_seq_adj(struct nf_conn *ct, struct nlattr *cda[]) #endif static int -ctnetlink_change_conntrack(struct nf_conn *ct, struct nlattr *cda[]) +ctnetlink_change_conntrack(struct nf_conn *ct, + const struct nlattr * const cda[]) { int err; @@ -1169,7 +1175,7 @@ ctnetlink_change_conntrack(struct nf_conn *ct, struct nlattr *cda[]) } static struct nf_conn * -ctnetlink_create_conntrack(struct nlattr *cda[], +ctnetlink_create_conntrack(const struct nlattr * const cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple, u8 u3) @@ -1304,7 +1310,8 @@ err1: static int ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *cda[]) + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) { struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; @@ -1629,7 +1636,8 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { static int ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *cda[]) + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; @@ -1689,7 +1697,8 @@ out: static int ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *cda[]) + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) { struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; @@ -1767,13 +1776,15 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, return 0; } static int -ctnetlink_change_expect(struct nf_conntrack_expect *x, struct nlattr *cda[]) +ctnetlink_change_expect(struct nf_conntrack_expect *x, + const struct nlattr * const cda[]) { return -EOPNOTSUPP; } static int -ctnetlink_create_expect(struct nlattr *cda[], u_int8_t u3, u32 pid, int report) +ctnetlink_create_expect(const struct nlattr * const cda[], u_int8_t u3, + u32 pid, int report) { struct nf_conntrack_tuple tuple, mask, master_tuple; struct nf_conntrack_tuple_hash *h = NULL; @@ -1831,7 +1842,8 @@ out: static int ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *cda[]) + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 97a82ba7537..ba2b7693728 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -492,6 +492,21 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } } +#ifdef CONFIG_NF_NAT_NEEDED +static inline s16 nat_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq) +{ + typeof(nf_ct_nat_offset) get_offset = rcu_dereference(nf_ct_nat_offset); + + return get_offset != NULL ? get_offset(ct, dir, seq) : 0; +} +#define NAT_OFFSET(pf, ct, dir, seq) \ + (pf == NFPROTO_IPV4 ? nat_offset(ct, dir, seq) : 0) +#else +#define NAT_OFFSET(pf, ct, dir, seq) 0 +#endif + static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp *state, enum ip_conntrack_dir dir, @@ -506,6 +521,7 @@ static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; + s16 receiver_offset; bool res; /* @@ -519,11 +535,16 @@ static bool tcp_in_window(const struct nf_conn *ct, if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM) tcp_sack(skb, dataoff, tcph, &sack); + /* Take into account NAT sequence number mangling */ + receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1); + ack -= receiver_offset; + sack -= receiver_offset; + pr_debug("tcp_in_window: START\n"); pr_debug("tcp_in_window: "); nf_ct_dump_tuple(tuple); - pr_debug("seq=%u ack=%u sack=%u win=%u end=%u\n", - seq, ack, sack, win, end); + pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n", + seq, ack, receiver_offset, sack, receiver_offset, win, end); pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, @@ -613,8 +634,8 @@ static bool tcp_in_window(const struct nf_conn *ct, pr_debug("tcp_in_window: "); nf_ct_dump_tuple(tuple); - pr_debug("seq=%u ack=%u sack =%u win=%u end=%u\n", - seq, ack, sack, win, end); + pr_debug("seq=%u ack=%u+(%d) sack=%u+(%d) win=%u end=%u\n", + seq, ack, receiver_offset, sack, receiver_offset, win, end); pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i " "receiver end=%u maxend=%u maxwin=%u scale=%i\n", sender->td_end, sender->td_maxend, sender->td_maxwin, @@ -700,7 +721,7 @@ static bool tcp_in_window(const struct nf_conn *ct, before(seq, sender->td_maxend + 1) ? after(end, sender->td_end - receiver->td_maxwin - 1) ? before(sack, receiver->td_end + 1) ? - after(ack, receiver->td_end - MAXACKWINDOW(sender)) ? "BUG" + after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG" : "ACK is under the lower bound (possible overly delayed ACK)" : "ACK is over the upper bound (ACKed data not seen yet)" : "SEQ is under the lower bound (already ACKed data retransmitted)" @@ -715,39 +736,6 @@ static bool tcp_in_window(const struct nf_conn *ct, return res; } -#ifdef CONFIG_NF_NAT_NEEDED -/* Update sender->td_end after NAT successfully mangled the packet */ -/* Caller must linearize skb at tcp header. */ -void nf_conntrack_tcp_update(const struct sk_buff *skb, - unsigned int dataoff, - struct nf_conn *ct, int dir, - s16 offset) -{ - const struct tcphdr *tcph = (const void *)skb->data + dataoff; - const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[dir]; - const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[!dir]; - __u32 end; - - end = segment_seq_plus_len(ntohl(tcph->seq), skb->len, dataoff, tcph); - - spin_lock_bh(&ct->lock); - /* - * We have to worry for the ack in the reply packet only... - */ - if (ct->proto.tcp.seen[dir].td_end + offset == end) - ct->proto.tcp.seen[dir].td_end = end; - ct->proto.tcp.last_end = end; - spin_unlock_bh(&ct->lock); - pr_debug("tcp_update: sender end=%u maxend=%u maxwin=%u scale=%i " - "receiver end=%u maxend=%u maxwin=%u scale=%i\n", - sender->td_end, sender->td_maxend, sender->td_maxwin, - sender->td_scale, - receiver->td_end, receiver->td_maxend, receiver->td_maxwin, - receiver->td_scale); -} -EXPORT_SYMBOL_GPL(nf_conntrack_tcp_update); -#endif - #define TH_FIN 0x01 #define TH_SYN 0x02 #define TH_RST 0x04 diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 4e620305f28..d65d3481919 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -128,9 +128,8 @@ EXPORT_SYMBOL(nf_log_packet); #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) { - rcu_read_lock(); + mutex_lock(&nf_log_mutex); if (*pos >= ARRAY_SIZE(nf_loggers)) return NULL; @@ -149,9 +148,8 @@ static void *seq_next(struct seq_file *s, void *v, loff_t *pos) } static void seq_stop(struct seq_file *s, void *v) - __releases(RCU) { - rcu_read_unlock(); + mutex_unlock(&nf_log_mutex); } static int seq_show(struct seq_file *s, void *v) @@ -161,7 +159,7 @@ static int seq_show(struct seq_file *s, void *v) struct nf_logger *t; int ret; - logger = rcu_dereference(nf_loggers[*pos]); + logger = nf_loggers[*pos]; if (!logger) ret = seq_printf(s, "%2lld NONE (", *pos); @@ -171,22 +169,16 @@ static int seq_show(struct seq_file *s, void *v) if (ret < 0) return ret; - mutex_lock(&nf_log_mutex); list_for_each_entry(t, &nf_loggers_l[*pos], list[*pos]) { ret = seq_printf(s, "%s", t->name); - if (ret < 0) { - mutex_unlock(&nf_log_mutex); + if (ret < 0) return ret; - } if (&t->list[*pos] != nf_loggers_l[*pos].prev) { ret = seq_printf(s, ","); - if (ret < 0) { - mutex_unlock(&nf_log_mutex); + if (ret < 0) return ret; - } } } - mutex_unlock(&nf_log_mutex); return seq_printf(s, ")\n"); } @@ -226,7 +218,7 @@ static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; static struct ctl_table_header *nf_log_dir_header; -static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp, +static int nf_log_proc_dostring(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; @@ -260,7 +252,7 @@ static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp, table->data = "NONE"; else table->data = logger->name; - r = proc_dostring(table, write, filp, buffer, lenp, ppos); + r = proc_dostring(table, write, buffer, lenp, ppos); mutex_unlock(&nf_log_mutex); } diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index 8ab829f8657..f042ae52155 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -113,7 +113,7 @@ static int nf_sockopt(struct sock *sk, u_int8_t pf, int val, } int nf_setsockopt(struct sock *sk, u_int8_t pf, int val, char __user *opt, - int len) + unsigned int len) { return nf_sockopt(sk, pf, val, opt, &len, 0); } @@ -154,7 +154,7 @@ static int compat_nf_sockopt(struct sock *sk, u_int8_t pf, int val, } int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, - int val, char __user *opt, int len) + int val, char __user *opt, unsigned int len) { return compat_nf_sockopt(sk, pf, val, opt, &len, 0); } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 92761a98837..eedc0c1ac7a 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -170,7 +170,7 @@ replay: if (err < 0) return err; - err = nc->call(nfnl, skb, nlh, cda); + err = nc->call(nfnl, skb, nlh, (const struct nlattr **)cda); if (err == -EAGAIN) goto replay; return err; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 66a6dd5c519..f900dc3194a 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -694,7 +694,8 @@ static struct notifier_block nfulnl_rtnl_notifier = { static int nfulnl_recv_unsupp(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *nfqa[]) + const struct nlmsghdr *nlh, + const struct nlattr * const nfqa[]) { return -ENOTSUPP; } @@ -716,7 +717,8 @@ static const struct nla_policy nfula_cfg_policy[NFULA_CFG_MAX+1] = { static int nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *nfula[]) + const struct nlmsghdr *nlh, + const struct nlattr * const nfula[]) { struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); u_int16_t group_num = ntohs(nfmsg->res_id); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 71daa0934b6..7a9dec9fb82 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -608,7 +608,8 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { static int nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *nfqa[]) + const struct nlmsghdr *nlh, + const struct nlattr * const nfqa[]) { struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); @@ -670,7 +671,8 @@ err_out_unlock: static int nfqnl_recv_unsupp(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *nfqa[]) + const struct nlmsghdr *nlh, + const struct nlattr * const nfqa[]) { return -ENOTSUPP; } @@ -687,7 +689,8 @@ static const struct nf_queue_handler nfqh = { static int nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *nfqa[]) + const struct nlmsghdr *nlh, + const struct nlattr * const nfqa[]) { struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 025d1a0af78..f01955cce31 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -617,7 +617,7 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) int cpu; /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > num_physpages) + if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages) return NULL; newinfo = kzalloc(XT_TABLE_INFO_SZ, GFP_KERNEL); @@ -736,16 +736,17 @@ xt_replace_table(struct xt_table *table, } EXPORT_SYMBOL_GPL(xt_replace_table); -struct xt_table *xt_register_table(struct net *net, struct xt_table *table, +struct xt_table *xt_register_table(struct net *net, + const struct xt_table *input_table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { int ret; struct xt_table_info *private; - struct xt_table *t; + struct xt_table *t, *table; /* Don't add one object to multiple lists. */ - table = kmemdup(table, sizeof(struct xt_table), GFP_KERNEL); + table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); if (!table) { ret = -ENOMEM; goto out; diff --git a/net/netfilter/xt_CONNMARK.c b/net/netfilter/xt_CONNMARK.c index d6e5ab46327..593457068ae 100644 --- a/net/netfilter/xt_CONNMARK.c +++ b/net/netfilter/xt_CONNMARK.c @@ -36,45 +36,6 @@ MODULE_ALIAS("ip6t_CONNMARK"); #include <net/netfilter/nf_conntrack_ecache.h> static unsigned int -connmark_tg_v0(struct sk_buff *skb, const struct xt_target_param *par) -{ - const struct xt_connmark_target_info *markinfo = par->targinfo; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - u_int32_t diff; - u_int32_t mark; - u_int32_t newmark; - - ct = nf_ct_get(skb, &ctinfo); - if (ct) { - switch(markinfo->mode) { - case XT_CONNMARK_SET: - newmark = (ct->mark & ~markinfo->mask) | markinfo->mark; - if (newmark != ct->mark) { - ct->mark = newmark; - nf_conntrack_event_cache(IPCT_MARK, ct); - } - break; - case XT_CONNMARK_SAVE: - newmark = (ct->mark & ~markinfo->mask) | - (skb->mark & markinfo->mask); - if (ct->mark != newmark) { - ct->mark = newmark; - nf_conntrack_event_cache(IPCT_MARK, ct); - } - break; - case XT_CONNMARK_RESTORE: - mark = skb->mark; - diff = (ct->mark ^ mark) & markinfo->mask; - skb->mark = mark ^ diff; - break; - } - } - - return XT_CONTINUE; -} - -static unsigned int connmark_tg(struct sk_buff *skb, const struct xt_target_param *par) { const struct xt_connmark_tginfo1 *info = par->targinfo; @@ -112,30 +73,6 @@ connmark_tg(struct sk_buff *skb, const struct xt_target_param *par) return XT_CONTINUE; } -static bool connmark_tg_check_v0(const struct xt_tgchk_param *par) -{ - const struct xt_connmark_target_info *matchinfo = par->targinfo; - - if (matchinfo->mode == XT_CONNMARK_RESTORE) { - if (strcmp(par->table, "mangle") != 0) { - printk(KERN_WARNING "CONNMARK: restore can only be " - "called from \"mangle\" table, not \"%s\"\n", - par->table); - return false; - } - } - if (matchinfo->mark > 0xffffffff || matchinfo->mask > 0xffffffff) { - printk(KERN_WARNING "CONNMARK: Only supports 32bit mark\n"); - return false; - } - if (nf_ct_l3proto_try_module_get(par->family) < 0) { - printk(KERN_WARNING "can't load conntrack support for " - "proto=%u\n", par->family); - return false; - } - return true; -} - static bool connmark_tg_check(const struct xt_tgchk_param *par) { if (nf_ct_l3proto_try_module_get(par->family) < 0) { @@ -151,74 +88,25 @@ static void connmark_tg_destroy(const struct xt_tgdtor_param *par) nf_ct_l3proto_module_put(par->family); } -#ifdef CONFIG_COMPAT -struct compat_xt_connmark_target_info { - compat_ulong_t mark, mask; - u_int8_t mode; - u_int8_t __pad1; - u_int16_t __pad2; -}; - -static void connmark_tg_compat_from_user_v0(void *dst, void *src) -{ - const struct compat_xt_connmark_target_info *cm = src; - struct xt_connmark_target_info m = { - .mark = cm->mark, - .mask = cm->mask, - .mode = cm->mode, - }; - memcpy(dst, &m, sizeof(m)); -} - -static int connmark_tg_compat_to_user_v0(void __user *dst, void *src) -{ - const struct xt_connmark_target_info *m = src; - struct compat_xt_connmark_target_info cm = { - .mark = m->mark, - .mask = m->mask, - .mode = m->mode, - }; - return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; -} -#endif /* CONFIG_COMPAT */ - -static struct xt_target connmark_tg_reg[] __read_mostly = { - { - .name = "CONNMARK", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = connmark_tg_check_v0, - .destroy = connmark_tg_destroy, - .target = connmark_tg_v0, - .targetsize = sizeof(struct xt_connmark_target_info), -#ifdef CONFIG_COMPAT - .compatsize = sizeof(struct compat_xt_connmark_target_info), - .compat_from_user = connmark_tg_compat_from_user_v0, - .compat_to_user = connmark_tg_compat_to_user_v0, -#endif - .me = THIS_MODULE - }, - { - .name = "CONNMARK", - .revision = 1, - .family = NFPROTO_UNSPEC, - .checkentry = connmark_tg_check, - .target = connmark_tg, - .targetsize = sizeof(struct xt_connmark_tginfo1), - .destroy = connmark_tg_destroy, - .me = THIS_MODULE, - }, +static struct xt_target connmark_tg_reg __read_mostly = { + .name = "CONNMARK", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = connmark_tg_check, + .target = connmark_tg, + .targetsize = sizeof(struct xt_connmark_tginfo1), + .destroy = connmark_tg_destroy, + .me = THIS_MODULE, }; static int __init connmark_tg_init(void) { - return xt_register_targets(connmark_tg_reg, - ARRAY_SIZE(connmark_tg_reg)); + return xt_register_target(&connmark_tg_reg); } static void __exit connmark_tg_exit(void) { - xt_unregister_targets(connmark_tg_reg, ARRAY_SIZE(connmark_tg_reg)); + xt_unregister_target(&connmark_tg_reg); } module_init(connmark_tg_init); diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c index 6a347e768f8..74ce8926005 100644 --- a/net/netfilter/xt_DSCP.c +++ b/net/netfilter/xt_DSCP.c @@ -18,7 +18,6 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_DSCP.h> -#include <linux/netfilter_ipv4/ipt_TOS.h> MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: DSCP/TOS field modification"); @@ -73,41 +72,6 @@ static bool dscp_tg_check(const struct xt_tgchk_param *par) } static unsigned int -tos_tg_v0(struct sk_buff *skb, const struct xt_target_param *par) -{ - const struct ipt_tos_target_info *info = par->targinfo; - struct iphdr *iph = ip_hdr(skb); - u_int8_t oldtos; - - if ((iph->tos & IPTOS_TOS_MASK) != info->tos) { - if (!skb_make_writable(skb, sizeof(struct iphdr))) - return NF_DROP; - - iph = ip_hdr(skb); - oldtos = iph->tos; - iph->tos = (iph->tos & IPTOS_PREC_MASK) | info->tos; - csum_replace2(&iph->check, htons(oldtos), htons(iph->tos)); - } - - return XT_CONTINUE; -} - -static bool tos_tg_check_v0(const struct xt_tgchk_param *par) -{ - const struct ipt_tos_target_info *info = par->targinfo; - const uint8_t tos = info->tos; - - if (tos != IPTOS_LOWDELAY && tos != IPTOS_THROUGHPUT && - tos != IPTOS_RELIABILITY && tos != IPTOS_MINCOST && - tos != IPTOS_NORMALSVC) { - printk(KERN_WARNING "TOS: bad tos value %#x\n", tos); - return false; - } - - return true; -} - -static unsigned int tos_tg(struct sk_buff *skb, const struct xt_target_param *par) { const struct xt_tos_target_info *info = par->targinfo; @@ -168,16 +132,6 @@ static struct xt_target dscp_tg_reg[] __read_mostly = { }, { .name = "TOS", - .revision = 0, - .family = NFPROTO_IPV4, - .table = "mangle", - .target = tos_tg_v0, - .targetsize = sizeof(struct ipt_tos_target_info), - .checkentry = tos_tg_check_v0, - .me = THIS_MODULE, - }, - { - .name = "TOS", .revision = 1, .family = NFPROTO_IPV4, .table = "mangle", diff --git a/net/netfilter/xt_MARK.c b/net/netfilter/xt_MARK.c index 67574bcfb8a..225f8d11e17 100644 --- a/net/netfilter/xt_MARK.c +++ b/net/netfilter/xt_MARK.c @@ -25,39 +25,6 @@ MODULE_ALIAS("ipt_MARK"); MODULE_ALIAS("ip6t_MARK"); static unsigned int -mark_tg_v0(struct sk_buff *skb, const struct xt_target_param *par) -{ - const struct xt_mark_target_info *markinfo = par->targinfo; - - skb->mark = markinfo->mark; - return XT_CONTINUE; -} - -static unsigned int -mark_tg_v1(struct sk_buff *skb, const struct xt_target_param *par) -{ - const struct xt_mark_target_info_v1 *markinfo = par->targinfo; - int mark = 0; - - switch (markinfo->mode) { - case XT_MARK_SET: - mark = markinfo->mark; - break; - - case XT_MARK_AND: - mark = skb->mark & markinfo->mark; - break; - - case XT_MARK_OR: - mark = skb->mark | markinfo->mark; - break; - } - - skb->mark = mark; - return XT_CONTINUE; -} - -static unsigned int mark_tg(struct sk_buff *skb, const struct xt_target_param *par) { const struct xt_mark_tginfo2 *info = par->targinfo; @@ -66,135 +33,23 @@ mark_tg(struct sk_buff *skb, const struct xt_target_param *par) return XT_CONTINUE; } -static bool mark_tg_check_v0(const struct xt_tgchk_param *par) -{ - const struct xt_mark_target_info *markinfo = par->targinfo; - - if (markinfo->mark > 0xffffffff) { - printk(KERN_WARNING "MARK: Only supports 32bit wide mark\n"); - return false; - } - return true; -} - -static bool mark_tg_check_v1(const struct xt_tgchk_param *par) -{ - const struct xt_mark_target_info_v1 *markinfo = par->targinfo; - - if (markinfo->mode != XT_MARK_SET - && markinfo->mode != XT_MARK_AND - && markinfo->mode != XT_MARK_OR) { - printk(KERN_WARNING "MARK: unknown mode %u\n", - markinfo->mode); - return false; - } - if (markinfo->mark > 0xffffffff) { - printk(KERN_WARNING "MARK: Only supports 32bit wide mark\n"); - return false; - } - return true; -} - -#ifdef CONFIG_COMPAT -struct compat_xt_mark_target_info { - compat_ulong_t mark; -}; - -static void mark_tg_compat_from_user_v0(void *dst, void *src) -{ - const struct compat_xt_mark_target_info *cm = src; - struct xt_mark_target_info m = { - .mark = cm->mark, - }; - memcpy(dst, &m, sizeof(m)); -} - -static int mark_tg_compat_to_user_v0(void __user *dst, void *src) -{ - const struct xt_mark_target_info *m = src; - struct compat_xt_mark_target_info cm = { - .mark = m->mark, - }; - return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; -} - -struct compat_xt_mark_target_info_v1 { - compat_ulong_t mark; - u_int8_t mode; - u_int8_t __pad1; - u_int16_t __pad2; -}; - -static void mark_tg_compat_from_user_v1(void *dst, void *src) -{ - const struct compat_xt_mark_target_info_v1 *cm = src; - struct xt_mark_target_info_v1 m = { - .mark = cm->mark, - .mode = cm->mode, - }; - memcpy(dst, &m, sizeof(m)); -} - -static int mark_tg_compat_to_user_v1(void __user *dst, void *src) -{ - const struct xt_mark_target_info_v1 *m = src; - struct compat_xt_mark_target_info_v1 cm = { - .mark = m->mark, - .mode = m->mode, - }; - return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; -} -#endif /* CONFIG_COMPAT */ - -static struct xt_target mark_tg_reg[] __read_mostly = { - { - .name = "MARK", - .family = NFPROTO_UNSPEC, - .revision = 0, - .checkentry = mark_tg_check_v0, - .target = mark_tg_v0, - .targetsize = sizeof(struct xt_mark_target_info), -#ifdef CONFIG_COMPAT - .compatsize = sizeof(struct compat_xt_mark_target_info), - .compat_from_user = mark_tg_compat_from_user_v0, - .compat_to_user = mark_tg_compat_to_user_v0, -#endif - .table = "mangle", - .me = THIS_MODULE, - }, - { - .name = "MARK", - .family = NFPROTO_UNSPEC, - .revision = 1, - .checkentry = mark_tg_check_v1, - .target = mark_tg_v1, - .targetsize = sizeof(struct xt_mark_target_info_v1), -#ifdef CONFIG_COMPAT - .compatsize = sizeof(struct compat_xt_mark_target_info_v1), - .compat_from_user = mark_tg_compat_from_user_v1, - .compat_to_user = mark_tg_compat_to_user_v1, -#endif - .table = "mangle", - .me = THIS_MODULE, - }, - { - .name = "MARK", - .revision = 2, - .family = NFPROTO_UNSPEC, - .target = mark_tg, - .targetsize = sizeof(struct xt_mark_tginfo2), - .me = THIS_MODULE, - }, +static struct xt_target mark_tg_reg __read_mostly = { + .name = "MARK", + .revision = 2, + .family = NFPROTO_UNSPEC, + .target = mark_tg, + .targetsize = sizeof(struct xt_mark_tginfo2), + .me = THIS_MODULE, }; static int __init mark_tg_init(void) { - return xt_register_targets(mark_tg_reg, ARRAY_SIZE(mark_tg_reg)); + return xt_register_target(&mark_tg_reg); } static void __exit mark_tg_exit(void) { - xt_unregister_targets(mark_tg_reg, ARRAY_SIZE(mark_tg_reg)); + xt_unregister_target(&mark_tg_reg); } module_init(mark_tg_init); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 68098095439..38f03f75a63 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -103,7 +103,7 @@ static int count_them(struct xt_connlimit_data *data, const struct nf_conntrack_tuple *tuple, const union nf_inet_addr *addr, const union nf_inet_addr *mask, - const struct xt_match *match) + u_int8_t family) { const struct nf_conntrack_tuple_hash *found; struct xt_connlimit_conn *conn; @@ -113,8 +113,7 @@ static int count_them(struct xt_connlimit_data *data, bool addit = true; int matches = 0; - - if (match->family == NFPROTO_IPV6) + if (family == NFPROTO_IPV6) hash = &data->iphash[connlimit_iphash6(addr, mask)]; else hash = &data->iphash[connlimit_iphash(addr->ip & mask->ip)]; @@ -157,8 +156,7 @@ static int count_them(struct xt_connlimit_data *data, continue; } - if (same_source_net(addr, mask, &conn->tuple.src.u3, - match->family)) + if (same_source_net(addr, mask, &conn->tuple.src.u3, family)) /* same source network -> be counted! */ ++matches; nf_ct_put(found_ct); @@ -207,7 +205,7 @@ connlimit_mt(const struct sk_buff *skb, const struct xt_match_param *par) spin_lock_bh(&info->data->lock); connections = count_them(info->data, tuple_ptr, &addr, - &info->mask, par->match); + &info->mask, par->family); spin_unlock_bh(&info->data->lock); if (connections < 0) { diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 86cacab7a4a..122aa8b0147 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -47,36 +47,6 @@ connmark_mt(const struct sk_buff *skb, const struct xt_match_param *par) return ((ct->mark & info->mask) == info->mark) ^ info->invert; } -static bool -connmark_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) -{ - const struct xt_connmark_info *info = par->matchinfo; - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct) - return false; - - return ((ct->mark & info->mask) == info->mark) ^ info->invert; -} - -static bool connmark_mt_check_v0(const struct xt_mtchk_param *par) -{ - const struct xt_connmark_info *cm = par->matchinfo; - - if (cm->mark > 0xffffffff || cm->mask > 0xffffffff) { - printk(KERN_WARNING "connmark: only support 32bit mark\n"); - return false; - } - if (nf_ct_l3proto_try_module_get(par->family) < 0) { - printk(KERN_WARNING "can't load conntrack support for " - "proto=%u\n", par->family); - return false; - } - return true; -} - static bool connmark_mt_check(const struct xt_mtchk_param *par) { if (nf_ct_l3proto_try_module_get(par->family) < 0) { @@ -92,74 +62,25 @@ static void connmark_mt_destroy(const struct xt_mtdtor_param *par) nf_ct_l3proto_module_put(par->family); } -#ifdef CONFIG_COMPAT -struct compat_xt_connmark_info { - compat_ulong_t mark, mask; - u_int8_t invert; - u_int8_t __pad1; - u_int16_t __pad2; -}; - -static void connmark_mt_compat_from_user_v0(void *dst, void *src) -{ - const struct compat_xt_connmark_info *cm = src; - struct xt_connmark_info m = { - .mark = cm->mark, - .mask = cm->mask, - .invert = cm->invert, - }; - memcpy(dst, &m, sizeof(m)); -} - -static int connmark_mt_compat_to_user_v0(void __user *dst, void *src) -{ - const struct xt_connmark_info *m = src; - struct compat_xt_connmark_info cm = { - .mark = m->mark, - .mask = m->mask, - .invert = m->invert, - }; - return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; -} -#endif /* CONFIG_COMPAT */ - -static struct xt_match connmark_mt_reg[] __read_mostly = { - { - .name = "connmark", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = connmark_mt_check_v0, - .match = connmark_mt_v0, - .destroy = connmark_mt_destroy, - .matchsize = sizeof(struct xt_connmark_info), -#ifdef CONFIG_COMPAT - .compatsize = sizeof(struct compat_xt_connmark_info), - .compat_from_user = connmark_mt_compat_from_user_v0, - .compat_to_user = connmark_mt_compat_to_user_v0, -#endif - .me = THIS_MODULE - }, - { - .name = "connmark", - .revision = 1, - .family = NFPROTO_UNSPEC, - .checkentry = connmark_mt_check, - .match = connmark_mt, - .matchsize = sizeof(struct xt_connmark_mtinfo1), - .destroy = connmark_mt_destroy, - .me = THIS_MODULE, - }, +static struct xt_match connmark_mt_reg __read_mostly = { + .name = "connmark", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = connmark_mt_check, + .match = connmark_mt, + .matchsize = sizeof(struct xt_connmark_mtinfo1), + .destroy = connmark_mt_destroy, + .me = THIS_MODULE, }; static int __init connmark_mt_init(void) { - return xt_register_matches(connmark_mt_reg, - ARRAY_SIZE(connmark_mt_reg)); + return xt_register_match(&connmark_mt_reg); } static void __exit connmark_mt_exit(void) { - xt_unregister_matches(connmark_mt_reg, ARRAY_SIZE(connmark_mt_reg)); + xt_unregister_match(&connmark_mt_reg); } module_init(connmark_mt_init); diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index fc581800698..6dc4652f2fe 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -19,101 +19,12 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); -MODULE_AUTHOR("Jan Engelhardt <jengelh@computergmbh.de>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: connection tracking state match"); MODULE_ALIAS("ipt_conntrack"); MODULE_ALIAS("ip6t_conntrack"); static bool -conntrack_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) -{ - const struct xt_conntrack_info *sinfo = par->matchinfo; - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - unsigned int statebit; - - ct = nf_ct_get(skb, &ctinfo); - -#define FWINV(bool, invflg) ((bool) ^ !!(sinfo->invflags & (invflg))) - - if (ct == &nf_conntrack_untracked) - statebit = XT_CONNTRACK_STATE_UNTRACKED; - else if (ct) - statebit = XT_CONNTRACK_STATE_BIT(ctinfo); - else - statebit = XT_CONNTRACK_STATE_INVALID; - - if (sinfo->flags & XT_CONNTRACK_STATE) { - if (ct) { - if (test_bit(IPS_SRC_NAT_BIT, &ct->status)) - statebit |= XT_CONNTRACK_STATE_SNAT; - if (test_bit(IPS_DST_NAT_BIT, &ct->status)) - statebit |= XT_CONNTRACK_STATE_DNAT; - } - if (FWINV((statebit & sinfo->statemask) == 0, - XT_CONNTRACK_STATE)) - return false; - } - - if (ct == NULL) { - if (sinfo->flags & ~XT_CONNTRACK_STATE) - return false; - return true; - } - - if (sinfo->flags & XT_CONNTRACK_PROTO && - FWINV(nf_ct_protonum(ct) != - sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, - XT_CONNTRACK_PROTO)) - return false; - - if (sinfo->flags & XT_CONNTRACK_ORIGSRC && - FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip & - sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != - sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, - XT_CONNTRACK_ORIGSRC)) - return false; - - if (sinfo->flags & XT_CONNTRACK_ORIGDST && - FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip & - sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != - sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, - XT_CONNTRACK_ORIGDST)) - return false; - - if (sinfo->flags & XT_CONNTRACK_REPLSRC && - FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip & - sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != - sinfo->tuple[IP_CT_DIR_REPLY].src.ip, - XT_CONNTRACK_REPLSRC)) - return false; - - if (sinfo->flags & XT_CONNTRACK_REPLDST && - FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip & - sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != - sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, - XT_CONNTRACK_REPLDST)) - return false; - - if (sinfo->flags & XT_CONNTRACK_STATUS && - FWINV((ct->status & sinfo->statusmask) == 0, - XT_CONNTRACK_STATUS)) - return false; - - if(sinfo->flags & XT_CONNTRACK_EXPIRES) { - unsigned long expires = timer_pending(&ct->timeout) ? - (ct->timeout.expires - jiffies)/HZ : 0; - - if (FWINV(!(expires >= sinfo->expires_min && - expires <= sinfo->expires_max), - XT_CONNTRACK_EXPIRES)) - return false; - } - return true; -#undef FWINV -} - -static bool conntrack_addrcmp(const union nf_inet_addr *kaddr, const union nf_inet_addr *uaddr, const union nf_inet_addr *umask, unsigned int l3proto) @@ -337,73 +248,9 @@ static void conntrack_mt_destroy_v1(const struct xt_mtdtor_param *par) conntrack_mt_destroy(par); } -#ifdef CONFIG_COMPAT -struct compat_xt_conntrack_info -{ - compat_uint_t statemask; - compat_uint_t statusmask; - struct ip_conntrack_old_tuple tuple[IP_CT_DIR_MAX]; - struct in_addr sipmsk[IP_CT_DIR_MAX]; - struct in_addr dipmsk[IP_CT_DIR_MAX]; - compat_ulong_t expires_min; - compat_ulong_t expires_max; - u_int8_t flags; - u_int8_t invflags; -}; - -static void conntrack_mt_compat_from_user_v0(void *dst, void *src) -{ - const struct compat_xt_conntrack_info *cm = src; - struct xt_conntrack_info m = { - .statemask = cm->statemask, - .statusmask = cm->statusmask, - .expires_min = cm->expires_min, - .expires_max = cm->expires_max, - .flags = cm->flags, - .invflags = cm->invflags, - }; - memcpy(m.tuple, cm->tuple, sizeof(m.tuple)); - memcpy(m.sipmsk, cm->sipmsk, sizeof(m.sipmsk)); - memcpy(m.dipmsk, cm->dipmsk, sizeof(m.dipmsk)); - memcpy(dst, &m, sizeof(m)); -} - -static int conntrack_mt_compat_to_user_v0(void __user *dst, void *src) -{ - const struct xt_conntrack_info *m = src; - struct compat_xt_conntrack_info cm = { - .statemask = m->statemask, - .statusmask = m->statusmask, - .expires_min = m->expires_min, - .expires_max = m->expires_max, - .flags = m->flags, - .invflags = m->invflags, - }; - memcpy(cm.tuple, m->tuple, sizeof(cm.tuple)); - memcpy(cm.sipmsk, m->sipmsk, sizeof(cm.sipmsk)); - memcpy(cm.dipmsk, m->dipmsk, sizeof(cm.dipmsk)); - return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; -} -#endif - static struct xt_match conntrack_mt_reg[] __read_mostly = { { .name = "conntrack", - .revision = 0, - .family = NFPROTO_IPV4, - .match = conntrack_mt_v0, - .checkentry = conntrack_mt_check, - .destroy = conntrack_mt_destroy, - .matchsize = sizeof(struct xt_conntrack_info), - .me = THIS_MODULE, -#ifdef CONFIG_COMPAT - .compatsize = sizeof(struct compat_xt_conntrack_info), - .compat_from_user = conntrack_mt_compat_from_user_v0, - .compat_to_user = conntrack_mt_compat_to_user_v0, -#endif - }, - { - .name = "conntrack", .revision = 1, .family = NFPROTO_UNSPEC, .matchsize = sizeof(struct xt_conntrack_mtinfo1), diff --git a/net/netfilter/xt_dscp.c b/net/netfilter/xt_dscp.c index c3f8085460d..0280d3a8c16 100644 --- a/net/netfilter/xt_dscp.c +++ b/net/netfilter/xt_dscp.c @@ -15,7 +15,6 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_dscp.h> -#include <linux/netfilter_ipv4/ipt_tos.h> MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: DSCP/TOS field match"); @@ -55,14 +54,6 @@ static bool dscp_mt_check(const struct xt_mtchk_param *par) return true; } -static bool -tos_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) -{ - const struct ipt_tos_info *info = par->matchinfo; - - return (ip_hdr(skb)->tos == info->tos) ^ info->invert; -} - static bool tos_mt(const struct sk_buff *skb, const struct xt_match_param *par) { const struct xt_tos_match_info *info = par->matchinfo; @@ -94,14 +85,6 @@ static struct xt_match dscp_mt_reg[] __read_mostly = { }, { .name = "tos", - .revision = 0, - .family = NFPROTO_IPV4, - .match = tos_mt_v0, - .matchsize = sizeof(struct ipt_tos_info), - .me = THIS_MODULE, - }, - { - .name = "tos", .revision = 1, .family = NFPROTO_IPV4, .match = tos_mt, diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 219dcdbe388..dd16e404424 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -194,9 +194,9 @@ static int htable_create_v0(struct xt_hashlimit_info *minfo, u_int8_t family) if (minfo->cfg.size) size = minfo->cfg.size; else { - size = ((num_physpages << PAGE_SHIFT) / 16384) / + size = ((totalram_pages << PAGE_SHIFT) / 16384) / sizeof(struct list_head); - if (num_physpages > (1024 * 1024 * 1024 / PAGE_SIZE)) + if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE)) size = 8192; if (size < 16) size = 16; @@ -266,9 +266,9 @@ static int htable_create(struct xt_hashlimit_mtinfo1 *minfo, u_int8_t family) if (minfo->cfg.size) { size = minfo->cfg.size; } else { - size = (num_physpages << PAGE_SHIFT) / 16384 / + size = (totalram_pages << PAGE_SHIFT) / 16384 / sizeof(struct list_head); - if (num_physpages > 1024 * 1024 * 1024 / PAGE_SIZE) + if (totalram_pages > 1024 * 1024 * 1024 / PAGE_SIZE) size = 8192; if (size < 16) size = 16; diff --git a/net/netfilter/xt_iprange.c b/net/netfilter/xt_iprange.c index 501f9b62318..ffc96387d55 100644 --- a/net/netfilter/xt_iprange.c +++ b/net/netfilter/xt_iprange.c @@ -14,40 +14,6 @@ #include <linux/ipv6.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_iprange.h> -#include <linux/netfilter_ipv4/ipt_iprange.h> - -static bool -iprange_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) -{ - const struct ipt_iprange_info *info = par->matchinfo; - const struct iphdr *iph = ip_hdr(skb); - - if (info->flags & IPRANGE_SRC) { - if ((ntohl(iph->saddr) < ntohl(info->src.min_ip) - || ntohl(iph->saddr) > ntohl(info->src.max_ip)) - ^ !!(info->flags & IPRANGE_SRC_INV)) { - pr_debug("src IP %pI4 NOT in range %s%pI4-%pI4\n", - &iph->saddr, - info->flags & IPRANGE_SRC_INV ? "(INV) " : "", - &info->src.min_ip, - &info->src.max_ip); - return false; - } - } - if (info->flags & IPRANGE_DST) { - if ((ntohl(iph->daddr) < ntohl(info->dst.min_ip) - || ntohl(iph->daddr) > ntohl(info->dst.max_ip)) - ^ !!(info->flags & IPRANGE_DST_INV)) { - pr_debug("dst IP %pI4 NOT in range %s%pI4-%pI4\n", - &iph->daddr, - info->flags & IPRANGE_DST_INV ? "(INV) " : "", - &info->dst.min_ip, - &info->dst.max_ip); - return false; - } - } - return true; -} static bool iprange_mt4(const struct sk_buff *skb, const struct xt_match_param *par) @@ -127,14 +93,6 @@ iprange_mt6(const struct sk_buff *skb, const struct xt_match_param *par) static struct xt_match iprange_mt_reg[] __read_mostly = { { .name = "iprange", - .revision = 0, - .family = NFPROTO_IPV4, - .match = iprange_mt_v0, - .matchsize = sizeof(struct ipt_iprange_info), - .me = THIS_MODULE, - }, - { - .name = "iprange", .revision = 1, .family = NFPROTO_IPV4, .match = iprange_mt4, @@ -164,7 +122,8 @@ static void __exit iprange_mt_exit(void) module_init(iprange_mt_init); module_exit(iprange_mt_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>, Jan Engelhardt <jengelh@computergmbh.de>"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: arbitrary IPv4 range matching"); MODULE_ALIAS("ipt_iprange"); MODULE_ALIAS("ip6t_iprange"); diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 2e8089ecd0a..2773be6a71d 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -112,7 +112,7 @@ static bool limit_mt_check(const struct xt_mtchk_param *par) priv = kmalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) - return -ENOMEM; + return false; /* For SMP, we only want to use one set of state. */ r->master = priv; diff --git a/net/netfilter/xt_mark.c b/net/netfilter/xt_mark.c index 10b9e34bbc5..1db07d8125f 100644 --- a/net/netfilter/xt_mark.c +++ b/net/netfilter/xt_mark.c @@ -3,7 +3,7 @@ * * (C) 1999-2001 Marc Boucher <marc@mbsi.ca> * Copyright © CC Computer Consultants GmbH, 2007 - 2008 - * Jan Engelhardt <jengelh@computergmbh.de> + * Jan Engelhardt <jengelh@medozas.de> * * 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 @@ -23,14 +23,6 @@ MODULE_ALIAS("ipt_mark"); MODULE_ALIAS("ip6t_mark"); static bool -mark_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) -{ - const struct xt_mark_info *info = par->matchinfo; - - return ((skb->mark & info->mask) == info->mark) ^ info->invert; -} - -static bool mark_mt(const struct sk_buff *skb, const struct xt_match_param *par) { const struct xt_mark_mtinfo1 *info = par->matchinfo; @@ -38,81 +30,23 @@ mark_mt(const struct sk_buff *skb, const struct xt_match_param *par) return ((skb->mark & info->mask) == info->mark) ^ info->invert; } -static bool mark_mt_check_v0(const struct xt_mtchk_param *par) -{ - const struct xt_mark_info *minfo = par->matchinfo; - - if (minfo->mark > 0xffffffff || minfo->mask > 0xffffffff) { - printk(KERN_WARNING "mark: only supports 32bit mark\n"); - return false; - } - return true; -} - -#ifdef CONFIG_COMPAT -struct compat_xt_mark_info { - compat_ulong_t mark, mask; - u_int8_t invert; - u_int8_t __pad1; - u_int16_t __pad2; -}; - -static void mark_mt_compat_from_user_v0(void *dst, void *src) -{ - const struct compat_xt_mark_info *cm = src; - struct xt_mark_info m = { - .mark = cm->mark, - .mask = cm->mask, - .invert = cm->invert, - }; - memcpy(dst, &m, sizeof(m)); -} - -static int mark_mt_compat_to_user_v0(void __user *dst, void *src) -{ - const struct xt_mark_info *m = src; - struct compat_xt_mark_info cm = { - .mark = m->mark, - .mask = m->mask, - .invert = m->invert, - }; - return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; -} -#endif /* CONFIG_COMPAT */ - -static struct xt_match mark_mt_reg[] __read_mostly = { - { - .name = "mark", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = mark_mt_check_v0, - .match = mark_mt_v0, - .matchsize = sizeof(struct xt_mark_info), -#ifdef CONFIG_COMPAT - .compatsize = sizeof(struct compat_xt_mark_info), - .compat_from_user = mark_mt_compat_from_user_v0, - .compat_to_user = mark_mt_compat_to_user_v0, -#endif - .me = THIS_MODULE, - }, - { - .name = "mark", - .revision = 1, - .family = NFPROTO_UNSPEC, - .match = mark_mt, - .matchsize = sizeof(struct xt_mark_mtinfo1), - .me = THIS_MODULE, - }, +static struct xt_match mark_mt_reg __read_mostly = { + .name = "mark", + .revision = 1, + .family = NFPROTO_UNSPEC, + .match = mark_mt, + .matchsize = sizeof(struct xt_mark_mtinfo1), + .me = THIS_MODULE, }; static int __init mark_mt_init(void) { - return xt_register_matches(mark_mt_reg, ARRAY_SIZE(mark_mt_reg)); + return xt_register_match(&mark_mt_reg); } static void __exit mark_mt_exit(void) { - xt_unregister_matches(mark_mt_reg, ARRAY_SIZE(mark_mt_reg)); + xt_unregister_match(&mark_mt_reg); } module_init(mark_mt_init); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 0f482e2440b..4d1a41bbd5d 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -70,7 +70,8 @@ static void xt_osf_finger_free_rcu(struct rcu_head *rcu_head) } static int xt_osf_add_callback(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *osf_attrs[]) + const struct nlmsghdr *nlh, + const struct nlattr * const osf_attrs[]) { struct xt_osf_user_finger *f; struct xt_osf_finger *kf = NULL, *sf; @@ -112,11 +113,12 @@ static int xt_osf_add_callback(struct sock *ctnl, struct sk_buff *skb, } static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nlattr *osf_attrs[]) + const struct nlmsghdr *nlh, + const struct nlattr * const osf_attrs[]) { struct xt_osf_user_finger *f; struct xt_osf_finger *sf; - int err = ENOENT; + int err = -ENOENT; if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 22b2a5e881e..d24c76dffee 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -5,7 +5,6 @@ * (C) 2000 Marc Boucher <marc@mbsi.ca> * * Copyright © CC Computer Consultants GmbH, 2007 - 2008 - * <jengelh@computergmbh.de> * * 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 @@ -17,60 +16,6 @@ #include <net/sock.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_owner.h> -#include <linux/netfilter_ipv4/ipt_owner.h> -#include <linux/netfilter_ipv6/ip6t_owner.h> - -static bool -owner_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) -{ - const struct ipt_owner_info *info = par->matchinfo; - const struct file *filp; - - if (skb->sk == NULL || skb->sk->sk_socket == NULL) - return false; - - filp = skb->sk->sk_socket->file; - if (filp == NULL) - return false; - - if (info->match & IPT_OWNER_UID) - if ((filp->f_cred->fsuid != info->uid) ^ - !!(info->invert & IPT_OWNER_UID)) - return false; - - if (info->match & IPT_OWNER_GID) - if ((filp->f_cred->fsgid != info->gid) ^ - !!(info->invert & IPT_OWNER_GID)) - return false; - - return true; -} - -static bool -owner_mt6_v0(const struct sk_buff *skb, const struct xt_match_param *par) -{ - const struct ip6t_owner_info *info = par->matchinfo; - const struct file *filp; - - if (skb->sk == NULL || skb->sk->sk_socket == NULL) - return false; - - filp = skb->sk->sk_socket->file; - if (filp == NULL) - return false; - - if (info->match & IP6T_OWNER_UID) - if ((filp->f_cred->fsuid != info->uid) ^ - !!(info->invert & IP6T_OWNER_UID)) - return false; - - if (info->match & IP6T_OWNER_GID) - if ((filp->f_cred->fsgid != info->gid) ^ - !!(info->invert & IP6T_OWNER_GID)) - return false; - - return true; -} static bool owner_mt(const struct sk_buff *skb, const struct xt_match_param *par) @@ -107,81 +52,30 @@ owner_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } -static bool owner_mt_check_v0(const struct xt_mtchk_param *par) -{ - const struct ipt_owner_info *info = par->matchinfo; - - if (info->match & (IPT_OWNER_PID | IPT_OWNER_SID | IPT_OWNER_COMM)) { - printk(KERN_WARNING KBUILD_MODNAME - ": PID, SID and command matching is not " - "supported anymore\n"); - return false; - } - - return true; -} - -static bool owner_mt6_check_v0(const struct xt_mtchk_param *par) -{ - const struct ip6t_owner_info *info = par->matchinfo; - - if (info->match & (IP6T_OWNER_PID | IP6T_OWNER_SID)) { - printk(KERN_WARNING KBUILD_MODNAME - ": PID and SID matching is not supported anymore\n"); - return false; - } - - return true; -} - -static struct xt_match owner_mt_reg[] __read_mostly = { - { - .name = "owner", - .revision = 0, - .family = NFPROTO_IPV4, - .match = owner_mt_v0, - .matchsize = sizeof(struct ipt_owner_info), - .checkentry = owner_mt_check_v0, - .hooks = (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING), - .me = THIS_MODULE, - }, - { - .name = "owner", - .revision = 0, - .family = NFPROTO_IPV6, - .match = owner_mt6_v0, - .matchsize = sizeof(struct ip6t_owner_info), - .checkentry = owner_mt6_check_v0, - .hooks = (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING), - .me = THIS_MODULE, - }, - { - .name = "owner", - .revision = 1, - .family = NFPROTO_UNSPEC, - .match = owner_mt, - .matchsize = sizeof(struct xt_owner_match_info), - .hooks = (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_POST_ROUTING), - .me = THIS_MODULE, - }, +static struct xt_match owner_mt_reg __read_mostly = { + .name = "owner", + .revision = 1, + .family = NFPROTO_UNSPEC, + .match = owner_mt, + .matchsize = sizeof(struct xt_owner_match_info), + .hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING), + .me = THIS_MODULE, }; static int __init owner_mt_init(void) { - return xt_register_matches(owner_mt_reg, ARRAY_SIZE(owner_mt_reg)); + return xt_register_match(&owner_mt_reg); } static void __exit owner_mt_exit(void) { - xt_unregister_matches(owner_mt_reg, ARRAY_SIZE(owner_mt_reg)); + xt_unregister_match(&owner_mt_reg); } module_init(owner_mt_init); module_exit(owner_mt_exit); -MODULE_AUTHOR("Jan Engelhardt <jengelh@computergmbh.de>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: socket owner matching"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_owner"); diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 16e6c4378ff..6ce00205f34 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -185,8 +185,7 @@ int netlbl_cfg_unlbl_map_add(const char *domain, return 0; cfg_unlbl_map_add_failure: - if (entry != NULL) - kfree(entry->domain); + kfree(entry->domain); kfree(entry); kfree(addrmap); kfree(map4); @@ -385,8 +384,7 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, cfg_cipsov4_map_add_failure: cipso_v4_doi_putdef(doi_def); - if (entry != NULL) - kfree(entry->domain); + kfree(entry->domain); kfree(entry); kfree(addrmap); kfree(addrinfo); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 2936fa3b6dc..19e98007691 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -83,6 +83,11 @@ struct netlink_sock { struct module *module; }; +struct listeners_rcu_head { + struct rcu_head rcu_head; + void *ptr; +}; + #define NETLINK_KERNEL_SOCKET 0x1 #define NETLINK_RECV_PKTINFO 0x2 #define NETLINK_BROADCAST_SEND_ERROR 0x4 @@ -172,9 +177,11 @@ static void netlink_sock_destruct(struct sock *sk) * this, _but_ remember, it adds useless work on UP machines. */ -static void netlink_table_grab(void) +void netlink_table_grab(void) __acquires(nl_table_lock) { + might_sleep(); + write_lock_irq(&nl_table_lock); if (atomic_read(&nl_table_users)) { @@ -195,7 +202,7 @@ static void netlink_table_grab(void) } } -static void netlink_table_ungrab(void) +void netlink_table_ungrab(void) __releases(nl_table_lock) { write_unlock_irq(&nl_table_lock); @@ -1143,7 +1150,7 @@ static void netlink_update_socket_mc(struct netlink_sock *nlk, } static int netlink_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); @@ -1356,7 +1363,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, struct netlink_sock *nlk = nlk_sk(sk); int noblock = flags&MSG_DONTWAIT; size_t copied; - struct sk_buff *skb; + struct sk_buff *skb, *frag __maybe_unused = NULL; int err; if (flags&MSG_OOB) @@ -1368,6 +1375,35 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, if (skb == NULL) goto out; +#ifdef CONFIG_COMPAT_NETLINK_MESSAGES + if (unlikely(skb_shinfo(skb)->frag_list)) { + bool need_compat = !!(flags & MSG_CMSG_COMPAT); + + /* + * If this skb has a frag_list, then here that means that + * we will have to use the frag_list skb for compat tasks + * and the regular skb for non-compat tasks. + * + * The skb might (and likely will) be cloned, so we can't + * just reset frag_list and go on with things -- we need to + * keep that. For the compat case that's easy -- simply get + * a reference to the compat skb and free the regular one + * including the frag. For the non-compat case, we need to + * avoid sending the frag to the user -- so assign NULL but + * restore it below before freeing the skb. + */ + if (need_compat) { + struct sk_buff *compskb = skb_shinfo(skb)->frag_list; + skb_get(compskb); + kfree_skb(skb); + skb = compskb; + } else { + frag = skb_shinfo(skb)->frag_list; + skb_shinfo(skb)->frag_list = NULL; + } + } +#endif + msg->msg_namelen = 0; copied = skb->len; @@ -1398,6 +1434,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, siocb->scm->creds = *NETLINK_CREDS(skb); if (flags & MSG_TRUNC) copied = skb->len; + +#ifdef CONFIG_COMPAT_NETLINK_MESSAGES + skb_shinfo(skb)->frag_list = frag; +#endif + skb_free_datagram(sk, skb); if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) @@ -1453,7 +1494,8 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups, if (groups < 32) groups = 32; - listeners = kzalloc(NLGRPSZ(groups), GFP_KERNEL); + listeners = kzalloc(NLGRPSZ(groups) + sizeof(struct listeners_rcu_head), + GFP_KERNEL); if (!listeners) goto out_sock_release; @@ -1501,6 +1543,49 @@ netlink_kernel_release(struct sock *sk) EXPORT_SYMBOL(netlink_kernel_release); +static void netlink_free_old_listeners(struct rcu_head *rcu_head) +{ + struct listeners_rcu_head *lrh; + + lrh = container_of(rcu_head, struct listeners_rcu_head, rcu_head); + kfree(lrh->ptr); +} + +int __netlink_change_ngroups(struct sock *sk, unsigned int groups) +{ + unsigned long *listeners, *old = NULL; + struct listeners_rcu_head *old_rcu_head; + struct netlink_table *tbl = &nl_table[sk->sk_protocol]; + + if (groups < 32) + groups = 32; + + if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { + listeners = kzalloc(NLGRPSZ(groups) + + sizeof(struct listeners_rcu_head), + GFP_ATOMIC); + if (!listeners) + return -ENOMEM; + old = tbl->listeners; + memcpy(listeners, old, NLGRPSZ(tbl->groups)); + rcu_assign_pointer(tbl->listeners, listeners); + /* + * Free the old memory after an RCU grace period so we + * don't leak it. We use call_rcu() here in order to be + * able to call this function from atomic contexts. The + * allocation of this memory will have reserved enough + * space for struct listeners_rcu_head at the end. + */ + old_rcu_head = (void *)(tbl->listeners + + NLGRPLONGS(tbl->groups)); + old_rcu_head->ptr = old; + call_rcu(&old_rcu_head->rcu_head, netlink_free_old_listeners); + } + tbl->groups = groups; + + return 0; +} + /** * netlink_change_ngroups - change number of multicast groups * @@ -1515,33 +1600,24 @@ EXPORT_SYMBOL(netlink_kernel_release); */ int netlink_change_ngroups(struct sock *sk, unsigned int groups) { - unsigned long *listeners, *old = NULL; - struct netlink_table *tbl = &nl_table[sk->sk_protocol]; - int err = 0; - - if (groups < 32) - groups = 32; + int err; netlink_table_grab(); - if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { - listeners = kzalloc(NLGRPSZ(groups), GFP_ATOMIC); - if (!listeners) { - err = -ENOMEM; - goto out_ungrab; - } - old = tbl->listeners; - memcpy(listeners, old, NLGRPSZ(tbl->groups)); - rcu_assign_pointer(tbl->listeners, listeners); - } - tbl->groups = groups; - - out_ungrab: + err = __netlink_change_ngroups(sk, groups); netlink_table_ungrab(); - synchronize_rcu(); - kfree(old); + return err; } -EXPORT_SYMBOL(netlink_change_ngroups); + +void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) +{ + struct sock *sk; + struct hlist_node *node; + struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; + + sk_for_each_bound(sk, node, &tbl->mc_list) + netlink_update_socket_mc(nlk_sk(sk), group, 0); +} /** * netlink_clear_multicast_users - kick off multicast listeners @@ -1553,18 +1629,10 @@ EXPORT_SYMBOL(netlink_change_ngroups); */ void netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { - struct sock *sk; - struct hlist_node *node; - struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; - netlink_table_grab(); - - sk_for_each_bound(sk, node, &tbl->mc_list) - netlink_update_socket_mc(nlk_sk(sk), group, 0); - + __netlink_clear_multicast_users(ksk, group); netlink_table_ungrab(); } -EXPORT_SYMBOL(netlink_clear_multicast_users); void netlink_set_nonroot(int protocol, unsigned int flags) { @@ -1647,7 +1715,7 @@ errout: } int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, - struct nlmsghdr *nlh, + const struct nlmsghdr *nlh, int (*dump)(struct sk_buff *skb, struct netlink_callback *), int (*done)(struct netlink_callback *)) @@ -1720,7 +1788,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) } rep = __nlmsg_put(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, - NLMSG_ERROR, sizeof(struct nlmsgerr), 0); + NLMSG_ERROR, payload, 0); errmsg = nlmsg_data(rep); errmsg->error = err; memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(*nlh)); @@ -2026,10 +2094,10 @@ static int __init netlink_proto_init(void) if (!nl_table) goto panic; - if (num_physpages >= (128 * 1024)) - limit = num_physpages >> (21 - PAGE_SHIFT); + if (totalram_pages >= (128 * 1024)) + limit = totalram_pages >> (21 - PAGE_SHIFT); else - limit = num_physpages >> (23 - PAGE_SHIFT); + limit = totalram_pages >> (23 - PAGE_SHIFT); order = get_bitmask_order(limit) - 1 + PAGE_SHIFT; limit = (1UL << order) / sizeof(struct hlist_head); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index eed4c6a8afc..44ff3f3810f 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -18,8 +18,6 @@ #include <net/sock.h> #include <net/genetlink.h> -struct sock *genl_sock = NULL; - static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static inline void genl_lock(void) @@ -138,7 +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'); @@ -175,10 +173,34 @@ int genl_register_mc_group(struct genl_family *family, mc_groups_longs++; } - err = netlink_change_ngroups(genl_sock, - mc_groups_longs * BITS_PER_LONG); - if (err) - goto out; + if (family->netnsok) { + struct net *net; + + netlink_table_grab(); + rcu_read_lock(); + for_each_net_rcu(net) { + err = __netlink_change_ngroups(net->genl_sock, + mc_groups_longs * BITS_PER_LONG); + if (err) { + /* + * No need to roll back, can only fail if + * memory allocation fails and then the + * number of _possible_ groups has been + * increased on some sockets which is ok. + */ + rcu_read_unlock(); + netlink_table_ungrab(); + goto out; + } + } + rcu_read_unlock(); + netlink_table_ungrab(); + } else { + err = netlink_change_ngroups(init_net.genl_sock, + mc_groups_longs * BITS_PER_LONG); + if (err) + goto out; + } grp->id = id; set_bit(id, mc_groups); @@ -195,8 +217,16 @@ EXPORT_SYMBOL(genl_register_mc_group); static void __genl_unregister_mc_group(struct genl_family *family, struct genl_multicast_group *grp) { + struct net *net; BUG_ON(grp->family != family); - netlink_clear_multicast_users(genl_sock, grp->id); + + netlink_table_grab(); + rcu_read_lock(); + for_each_net_rcu(net) + __netlink_clear_multicast_users(net->genl_sock, grp->id); + rcu_read_unlock(); + netlink_table_ungrab(); + clear_bit(grp->id, mc_groups); list_del(&grp->list); genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, grp); @@ -467,6 +497,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { struct genl_ops *ops; struct genl_family *family; + struct net *net = sock_net(skb->sk); struct genl_info info; struct genlmsghdr *hdr = nlmsg_data(nlh); int hdrlen, err; @@ -475,6 +506,10 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (family == NULL) return -ENOENT; + /* this family doesn't exist in this netns */ + if (!family->netnsok && !net_eq(net, &init_net)) + return -ENOENT; + hdrlen = GENL_HDRLEN + family->hdrsize; if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; @@ -492,7 +527,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EOPNOTSUPP; genl_unlock(); - err = netlink_dump_start(genl_sock, skb, nlh, + err = netlink_dump_start(net->genl_sock, skb, nlh, ops->dumpit, ops->done); genl_lock(); return err; @@ -514,6 +549,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) info.genlhdr = nlmsg_data(nlh); info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; info.attrs = family->attrbuf; + genl_info_net_set(&info, net); return ops->doit(skb, &info); } @@ -534,6 +570,7 @@ static struct genl_family genl_ctrl = { .name = "nlctrl", .version = 0x2, .maxattr = CTRL_ATTR_MAX, + .netnsok = true, }; static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, @@ -650,6 +687,7 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) int i, n = 0; struct genl_family *rt; + struct net *net = sock_net(skb->sk); int chains_to_skip = cb->args[0]; int fams_to_skip = cb->args[1]; @@ -658,6 +696,8 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) continue; n = 0; list_for_each_entry(rt, genl_family_chain(i), family_list) { + if (!rt->netnsok && !net_eq(net, &init_net)) + continue; if (++n < fams_to_skip) continue; if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).pid, @@ -729,6 +769,7 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) if (info->attrs[CTRL_ATTR_FAMILY_ID]) { u16 id = nla_get_u16(info->attrs[CTRL_ATTR_FAMILY_ID]); res = genl_family_find_byid(id); + err = -ENOENT; } if (info->attrs[CTRL_ATTR_FAMILY_NAME]) { @@ -736,49 +777,61 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]); res = genl_family_find_byname(name); + err = -ENOENT; } - if (res == NULL) { - err = -ENOENT; - goto errout; + if (res == NULL) + return err; + + if (!res->netnsok && !net_eq(genl_info_net(info), &init_net)) { + /* family doesn't exist here */ + return -ENOENT; } msg = ctrl_build_family_msg(res, info->snd_pid, info->snd_seq, CTRL_CMD_NEWFAMILY); - if (IS_ERR(msg)) { - err = PTR_ERR(msg); - goto errout; - } + if (IS_ERR(msg)) + return PTR_ERR(msg); - err = genlmsg_reply(msg, info); -errout: - return err; + return genlmsg_reply(msg, info); } static int genl_ctrl_event(int event, void *data) { struct sk_buff *msg; + struct genl_family *family; + struct genl_multicast_group *grp; - if (genl_sock == NULL) + /* genl is still initialising */ + if (!init_net.genl_sock) return 0; switch (event) { case CTRL_CMD_NEWFAMILY: case CTRL_CMD_DELFAMILY: - msg = ctrl_build_family_msg(data, 0, 0, event); - if (IS_ERR(msg)) - return PTR_ERR(msg); - - genlmsg_multicast(msg, 0, GENL_ID_CTRL, GFP_KERNEL); + family = data; + msg = ctrl_build_family_msg(family, 0, 0, event); break; case CTRL_CMD_NEWMCAST_GRP: case CTRL_CMD_DELMCAST_GRP: + grp = data; + family = grp->family; msg = ctrl_build_mcgrp_msg(data, 0, 0, event); - if (IS_ERR(msg)) - return PTR_ERR(msg); - - genlmsg_multicast(msg, 0, GENL_ID_CTRL, GFP_KERNEL); break; + default: + return -EINVAL; + } + + if (IS_ERR(msg)) + return PTR_ERR(msg); + + if (!family->netnsok) { + genlmsg_multicast_netns(&init_net, msg, 0, + GENL_ID_CTRL, GFP_KERNEL); + } else { + rcu_read_lock(); + genlmsg_multicast_allns(msg, 0, GENL_ID_CTRL, GFP_ATOMIC); + rcu_read_unlock(); } return 0; @@ -795,6 +848,33 @@ static struct genl_multicast_group notify_grp = { .name = "notify", }; +static int __net_init genl_pernet_init(struct net *net) +{ + /* we'll bump the group number right afterwards */ + net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, 0, + genl_rcv, &genl_mutex, + THIS_MODULE); + + if (!net->genl_sock && net_eq(net, &init_net)) + panic("GENL: Cannot initialize generic netlink\n"); + + if (!net->genl_sock) + return -ENOMEM; + + return 0; +} + +static void __net_exit genl_pernet_exit(struct net *net) +{ + netlink_kernel_release(net->genl_sock); + net->genl_sock = NULL; +} + +static struct pernet_operations genl_pernet_ops = { + .init = genl_pernet_init, + .exit = genl_pernet_exit, +}; + static int __init genl_init(void) { int i, err; @@ -804,36 +884,67 @@ static int __init genl_init(void) err = genl_register_family(&genl_ctrl); if (err < 0) - goto errout; + goto problem; err = genl_register_ops(&genl_ctrl, &genl_ctrl_ops); if (err < 0) - goto errout_register; + goto problem; netlink_set_nonroot(NETLINK_GENERIC, NL_NONROOT_RECV); - /* we'll bump the group number right afterwards */ - genl_sock = netlink_kernel_create(&init_net, NETLINK_GENERIC, 0, - genl_rcv, &genl_mutex, THIS_MODULE); - if (genl_sock == NULL) - panic("GENL: Cannot initialize generic netlink\n"); + err = register_pernet_subsys(&genl_pernet_ops); + if (err) + goto problem; err = genl_register_mc_group(&genl_ctrl, ¬ify_grp); if (err < 0) - goto errout_register; + goto problem; return 0; -errout_register: - genl_unregister_family(&genl_ctrl); -errout: +problem: panic("GENL: Cannot register controller: %d\n", err); } subsys_initcall(genl_init); -EXPORT_SYMBOL(genl_sock); EXPORT_SYMBOL(genl_register_ops); EXPORT_SYMBOL(genl_unregister_ops); EXPORT_SYMBOL(genl_register_family); EXPORT_SYMBOL(genl_unregister_family); + +static int genlmsg_mcast(struct sk_buff *skb, u32 pid, unsigned long group, + gfp_t flags) +{ + struct sk_buff *tmp; + struct net *net, *prev = NULL; + int err; + + for_each_net_rcu(net) { + if (prev) { + tmp = skb_clone(skb, flags); + if (!tmp) { + err = -ENOMEM; + goto error; + } + err = nlmsg_multicast(prev->genl_sock, tmp, + pid, group, flags); + if (err) + goto error; + } + + prev = net; + } + + return nlmsg_multicast(prev->genl_sock, skb, pid, group, flags); + error: + kfree_skb(skb); + return err; +} + +int genlmsg_multicast_allns(struct sk_buff *skb, u32 pid, unsigned int group, + gfp_t flags) +{ + return genlmsg_mcast(skb, pid, group, flags); +} +EXPORT_SYMBOL(genlmsg_multicast_allns); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ce1a34b99c2..7a834952f67 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -301,7 +301,7 @@ void nr_destroy_socket(struct sock *sk) */ static int nr_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 351372463fe..7aa11b01b2e 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; @@ -177,13 +177,13 @@ static int nr_xmit(struct sk_buff *skb, struct net_device *dev) if (!nr_route_frame(skb, NULL)) { kfree_skb(skb); stats->tx_errors++; - return 0; + return NETDEV_TX_OK; } stats->tx_packets++; stats->tx_bytes += len; - return 0; + return NETDEV_TX_OK; } static const struct header_ops nr_header_ops = { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ebe5718baa3..f2d116a5cb3 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -137,8 +137,7 @@ dev->hard_header == NULL (ll header is added by device, we cannot control it) /* Private packet socket structures. */ -struct packet_mclist -{ +struct packet_mclist { struct packet_mclist *next; int ifindex; int count; @@ -149,8 +148,7 @@ struct packet_mclist /* identical to struct packet_mreq except it has * a longer address field. */ -struct packet_mreq_max -{ +struct packet_mreq_max { int mr_ifindex; unsigned short mr_type; unsigned short mr_alen; @@ -162,7 +160,7 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing, int tx_ring); struct packet_ring_buffer { - char * *pg_vec; + char **pg_vec; unsigned int head; unsigned int frames_per_block; unsigned int frame_size; @@ -239,7 +237,7 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) flush_dcache_page(virt_to_page(&h.h2->tp_status)); break; default: - printk(KERN_ERR "TPACKET version not supported\n"); + pr_err("TPACKET version not supported\n"); BUG(); } @@ -265,7 +263,7 @@ static int __packet_get_status(struct packet_sock *po, void *frame) flush_dcache_page(virt_to_page(&h.h2->tp_status)); return h.h2->tp_status; default: - printk(KERN_ERR "TPACKET version not supported\n"); + pr_err("TPACKET version not supported\n"); BUG(); return 0; } @@ -327,7 +325,7 @@ static void packet_sock_destruct(struct sock *sk) WARN_ON(atomic_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { - printk("Attempt to release alive packet socket: %p\n", sk); + pr_err("Attempt to release alive packet socket: %p\n", sk); return; } @@ -339,7 +337,8 @@ static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; -static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_pkt *spkt; @@ -368,7 +367,8 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct if (dev_net(dev) != sock_net(sk)) goto out; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (skb == NULL) goto oom; /* drop any routing info */ @@ -394,7 +394,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct * to prevent sockets using all the memory up. */ - if (sock_queue_rcv_skb(sk,skb) == 0) + if (sock_queue_rcv_skb(sk, skb) == 0) return 0; out: @@ -413,25 +413,23 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct sockaddr_pkt *saddr=(struct sockaddr_pkt *)msg->msg_name; + struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name; struct sk_buff *skb; struct net_device *dev; - __be16 proto=0; + __be16 proto = 0; int err; /* * Get and verify the address. */ - if (saddr) - { + if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) - return(-EINVAL); - if (msg->msg_namelen==sizeof(struct sockaddr_pkt)) - proto=saddr->spkt_protocol; - } - else - return(-ENOTCONN); /* SOCK_PACKET must be sent giving an address */ + return -EINVAL; + if (msg->msg_namelen == sizeof(struct sockaddr_pkt)) + proto = saddr->spkt_protocol; + } else + return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it @@ -448,8 +446,8 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, goto out_unlock; /* - * You may not queue a frame bigger than the mtu. This is the lowest level - * raw protocol and you must do your own fragmentation at this level. + * You may not queue a frame bigger than the mtu. This is the lowest level + * raw protocol and you must do your own fragmentation at this level. */ err = -EMSGSIZE; @@ -460,9 +458,9 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, skb = sock_wmalloc(sk, len + LL_RESERVED_SPACE(dev), 0, GFP_KERNEL); /* - * If the write buffer is full, then tough. At this level the user gets to - * deal with the problem - do your own algorithmic backoffs. That's far - * more flexible. + * If the write buffer is full, then tough. At this level the user + * gets to deal with the problem - do your own algorithmic backoffs. + * That's far more flexible. */ if (skb == NULL) @@ -488,7 +486,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, } /* Returns -EFAULT on error */ - err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len); + err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; @@ -501,7 +499,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, dev_queue_xmit(skb); dev_put(dev); - return(len); + return len; out_free: kfree_skb(skb); @@ -537,12 +535,13 @@ static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk, we will not harm anyone. */ -static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +static int packet_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_ll *sll; struct packet_sock *po; - u8 * skb_head = skb->data; + u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; @@ -648,7 +647,8 @@ drop: } #ifdef CONFIG_PACKET_MMAP -static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct packet_sock *po; @@ -658,7 +658,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe struct tpacket2_hdr *h2; void *raw; } h; - u8 * skb_head = skb->data; + u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_LOSING|TP_STATUS_USER; @@ -821,7 +821,7 @@ ring_is_full: static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); - void * ph; + void *ph; BUG_ON(skb == NULL); @@ -836,9 +836,9 @@ static void tpacket_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } -static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff * skb, - void * frame, struct net_device *dev, int size_max, - __be16 proto, unsigned char * addr) +static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, + void *frame, struct net_device *dev, int size_max, + __be16 proto, unsigned char *addr) { union { struct tpacket_hdr *h1; @@ -867,8 +867,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff * skb, break; } if (unlikely(tp_len > size_max)) { - printk(KERN_ERR "packet size is too long (%d > %d)\n", - tp_len, size_max); + pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); return -EMSGSIZE; } @@ -883,12 +882,11 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff * skb, NULL, tp_len); if (unlikely(err < 0)) return -EINVAL; - } else if (dev->hard_header_len ) { + } else if (dev->hard_header_len) { /* net device doesn't like empty head */ if (unlikely(tp_len <= dev->hard_header_len)) { - printk(KERN_ERR "packet size is too short " - "(%d < %d)\n", tp_len, - dev->hard_header_len); + pr_err("packet size is too short (%d < %d)\n", + tp_len, dev->hard_header_len); return -EINVAL; } @@ -917,9 +915,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff * skb, nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { - printk(KERN_ERR "Packet exceed the number " - "of skb frags(%lu)\n", - MAX_SKB_FRAGS); + pr_err("Packet exceed the number of skb frags(%lu)\n", + MAX_SKB_FRAGS); return -EFAULT; } @@ -944,8 +941,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) struct net_device *dev; __be16 proto; int ifindex, err, reserve = 0; - void * ph; - struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name; + void *ph; + struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; int tp_len, size_max; unsigned char *addr; int len_sum = 0; @@ -985,10 +982,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_put; size_max = po->tx_ring.frame_size - - sizeof(struct skb_shared_info) - - po->tp_hdrlen - - LL_ALLOCATED_SPACE(dev) - - sizeof(struct sockaddr_ll); + - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); if (size_max > dev->mtu + reserve) size_max = dev->mtu + reserve; @@ -1038,8 +1032,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_xmit; packet_increment_head(&po->tx_ring); len_sum += tp_len; - } - while (likely((ph != NULL) || ((!(msg->msg_flags & MSG_DONTWAIT)) + } while (likely((ph != NULL) || ((!(msg->msg_flags & MSG_DONTWAIT)) && (atomic_read(&po->tx_ring.pending)))) ); @@ -1064,7 +1057,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name; + struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; struct sk_buff *skb; struct net_device *dev; __be16 proto; @@ -1110,7 +1103,7 @@ static int packet_snd(struct socket *sock, skb = sock_alloc_send_skb(sk, len + LL_ALLOCATED_SPACE(dev), msg->msg_flags & MSG_DONTWAIT, &err); - if (skb==NULL) + if (skb == NULL) goto out_unlock; skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -1122,7 +1115,7 @@ static int packet_snd(struct socket *sock, goto out_free; /* Returns -EFAULT on error */ - err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len); + err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); if (err) goto out_free; @@ -1140,7 +1133,7 @@ static int packet_snd(struct socket *sock, dev_put(dev); - return(len); + return len; out_free: kfree_skb(skb); @@ -1283,9 +1276,10 @@ out_unlock: * Bind a packet socket to a device */ -static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, + int addr_len) { - struct sock *sk=sock->sk; + struct sock *sk = sock->sk; char name[15]; struct net_device *dev; int err = -ENODEV; @@ -1296,7 +1290,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int add if (addr_len != sizeof(struct sockaddr)) return -EINVAL; - strlcpy(name,uaddr->sa_data,sizeof(name)); + strlcpy(name, uaddr->sa_data, sizeof(name)); dev = dev_get_by_name(sock_net(sk), name); if (dev) { @@ -1308,8 +1302,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int add static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { - struct sockaddr_ll *sll = (struct sockaddr_ll*)uaddr; - struct sock *sk=sock->sk; + struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; + struct sock *sk = sock->sk; struct net_device *dev = NULL; int err; @@ -1404,7 +1398,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol) sk_add_node(sk, &net->packet.sklist); sock_prot_inuse_add(net, &packet_proto, 1); write_unlock_bh(&net->packet.sklist_lock); - return(0); + return 0; out: return err; } @@ -1441,7 +1435,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, * but then it will block. */ - skb=skb_recv_datagram(sk,flags,flags&MSG_DONTWAIT,&err); + skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err); /* * An error occurred so return it. Because skb_recv_datagram() @@ -1469,10 +1463,9 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, */ copied = skb->len; - if (copied > len) - { - copied=len; - msg->msg_flags|=MSG_TRUNC; + if (copied > len) { + copied = len; + msg->msg_flags |= MSG_TRUNC; } err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); @@ -1539,7 +1532,7 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct net_device *dev; struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - struct sockaddr_ll *sll = (struct sockaddr_ll*)uaddr; + struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; if (peer) return -EOPNOTSUPP; @@ -1584,14 +1577,15 @@ static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, else return dev_unicast_delete(dev, i->addr); break; - default:; + default: + break; } return 0; } static void packet_dev_mclist(struct net_device *dev, struct packet_mclist *i, int what) { - for ( ; i; i=i->next) { + for ( ; i; i = i->next) { if (i->ifindex == dev->ifindex) packet_dev_mc(dev, i, what); } @@ -1693,7 +1687,8 @@ static void packet_flush_mclist(struct sock *sk) struct net_device *dev; po->mclist = ml->next; - if ((dev = dev_get_by_index(sock_net(sk), ml->ifindex)) != NULL) { + dev = dev_get_by_index(sock_net(sk), ml->ifindex); + if (dev != NULL) { packet_dev_mc(dev, ml, -1); dev_put(dev); } @@ -1703,7 +1698,7 @@ static void packet_flush_mclist(struct sock *sk) } static int -packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); @@ -1723,7 +1718,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); - if (copy_from_user(&mreq,optval,len)) + if (copy_from_user(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; @@ -1740,9 +1735,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv { struct tpacket_req req; - if (optlen<sizeof(req)) + if (optlen < sizeof(req)) return -EINVAL; - if (copy_from_user(&req,optval,sizeof(req))) + if (copy_from_user(&req, optval, sizeof(req))) return -EFAULT; return packet_set_ring(sk, &req, 0, optname == PACKET_TX_RING); } @@ -1750,9 +1745,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv { int val; - if (optlen!=sizeof(val)) + if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val,optval,sizeof(val))) + if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; pkt_sk(sk)->copy_thresh = val; @@ -1985,51 +1980,51 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd, struct sock *sk = sock->sk; switch (cmd) { - case SIOCOUTQ: - { - int amount = sk_wmem_alloc_get(sk); + case SIOCOUTQ: + { + int amount = sk_wmem_alloc_get(sk); - return put_user(amount, (int __user *)arg); - } - case SIOCINQ: - { - struct sk_buff *skb; - int amount = 0; - - spin_lock_bh(&sk->sk_receive_queue.lock); - skb = skb_peek(&sk->sk_receive_queue); - if (skb) - amount = skb->len; - spin_unlock_bh(&sk->sk_receive_queue.lock); - return put_user(amount, (int __user *)arg); - } - case SIOCGSTAMP: - return sock_get_timestamp(sk, (struct timeval __user *)arg); - case SIOCGSTAMPNS: - return sock_get_timestampns(sk, (struct timespec __user *)arg); + return put_user(amount, (int __user *)arg); + } + case SIOCINQ: + { + struct sk_buff *skb; + int amount = 0; + + spin_lock_bh(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + if (skb) + amount = skb->len; + spin_unlock_bh(&sk->sk_receive_queue.lock); + return put_user(amount, (int __user *)arg); + } + case SIOCGSTAMP: + return sock_get_timestamp(sk, (struct timeval __user *)arg); + case SIOCGSTAMPNS: + return sock_get_timestampns(sk, (struct timespec __user *)arg); #ifdef CONFIG_INET - case SIOCADDRT: - case SIOCDELRT: - case SIOCDARP: - case SIOCGARP: - case SIOCSARP: - case SIOCGIFADDR: - case SIOCSIFADDR: - case SIOCGIFBRDADDR: - case SIOCSIFBRDADDR: - case SIOCGIFNETMASK: - case SIOCSIFNETMASK: - case SIOCGIFDSTADDR: - case SIOCSIFDSTADDR: - case SIOCSIFFLAGS: - if (!net_eq(sock_net(sk), &init_net)) - return -ENOIOCTLCMD; - return inet_dgram_ops.ioctl(sock, cmd, arg); + case SIOCADDRT: + case SIOCDELRT: + case SIOCDARP: + case SIOCGARP: + case SIOCSARP: + case SIOCGIFADDR: + case SIOCSIFADDR: + case SIOCGIFBRDADDR: + case SIOCSIFBRDADDR: + case SIOCGIFNETMASK: + case SIOCSIFNETMASK: + case SIOCGIFDSTADDR: + case SIOCSIFDSTADDR: + case SIOCSIFFLAGS: + if (!net_eq(sock_net(sk), &init_net)) + return -ENOIOCTLCMD; + return inet_dgram_ops.ioctl(sock, cmd, arg); #endif - default: - return -ENOIOCTLCMD; + default: + return -ENOIOCTLCMD; } return 0; } @@ -2039,7 +2034,7 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd, #define packet_poll datagram_poll #else -static unsigned int packet_poll(struct file * file, struct socket *sock, +static unsigned int packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; @@ -2069,7 +2064,7 @@ static unsigned int packet_poll(struct file * file, struct socket *sock, static void packet_mm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; - struct socket * sock = file->private_data; + struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) @@ -2079,16 +2074,16 @@ static void packet_mm_open(struct vm_area_struct *vma) static void packet_mm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; - struct socket * sock = file->private_data; + struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_dec(&pkt_sk(sk)->mapped); } -static struct vm_operations_struct packet_mmap_ops = { - .open = packet_mm_open, - .close =packet_mm_close, +static const struct vm_operations_struct packet_mmap_ops = { + .open = packet_mm_open, + .close = packet_mm_close, }; static void free_pg_vec(char **pg_vec, unsigned int order, unsigned int len) @@ -2239,8 +2234,8 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, skb_queue_purge(rb_queue); #undef XC if (atomic_read(&po->mapped)) - printk(KERN_DEBUG "packet_mmap: vma is busy: %d\n", - atomic_read(&po->mapped)); + pr_err("packet_mmap: vma is busy: %d\n", + atomic_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); @@ -2303,7 +2298,7 @@ static int packet_mmap(struct file *file, struct socket *sock, int pg_num; for (pg_num = 0; pg_num < rb->pg_vec_pages; - pg_num++,page++) { + pg_num++, page++) { err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; @@ -2372,7 +2367,7 @@ static struct net_proto_family packet_family_ops = { }; static struct notifier_block packet_netdev_notifier = { - .notifier_call =packet_notifier, + .notifier_call = packet_notifier, }; #ifdef CONFIG_PROC_FS @@ -2402,7 +2397,7 @@ static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; return (v == SEQ_START_TOKEN) ? sk_head(&net->packet.sklist) - : sk_next((struct sock*)v) ; + : sk_next((struct sock *)v) ; } static void packet_seq_stop(struct seq_file *seq, void *v) @@ -2430,7 +2425,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) po->running, atomic_read(&s->sk_rmem_alloc), sock_i_uid(s), - sock_i_ino(s) ); + sock_i_ino(s)); } return 0; diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index a662e62a99c..f60c0c2aacb 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -168,6 +168,12 @@ static int pn_send(struct sk_buff *skb, struct net_device *dev, goto drop; } + /* Broadcast sending is not implemented */ + if (pn_addr(dst) == PNADDR_BROADCAST) { + err = -EOPNOTSUPP; + goto drop; + } + skb_reset_transport_header(skb); WARN_ON(skb_headroom(skb) & 1); /* HW assumes word alignment */ skb_push(skb, sizeof(struct phonethdr)); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index e087862ed7e..ef5c75c372e 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -159,8 +159,11 @@ out_nofree: static int pn_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int err = sock_queue_rcv_skb(sk, skb); - if (err < 0) + if (err < 0) { kfree_skb(skb); + if (err == -ENOMEM) + atomic_inc(&sk->sk_drops); + } return err ? NET_RX_DROP : NET_RX_SUCCESS; } diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index 480839dfc56..d183509d3fa 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; @@ -195,7 +195,7 @@ static int gprs_xmit(struct sk_buff *skb, struct net_device *dev) break; default: dev_kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } skb_orphan(skb); @@ -215,7 +215,7 @@ static int gprs_xmit(struct sk_buff *skb, struct net_device *dev) netif_stop_queue(dev); if (pep_writeable(sk)) netif_wake_queue(dev); - return 0; + return NETDEV_TX_OK; } static int gprs_set_mtu(struct net_device *dev, int new_mtu) diff --git a/net/phonet/pep.c b/net/phonet/pep.c index eef833ea6d7..5f32d217535 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -346,8 +346,10 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) break; case PNS_PEP_CTRL_REQ: - if (skb_queue_len(&pn->ctrlreq_queue) >= PNPIPE_CTRLREQ_MAX) + if (skb_queue_len(&pn->ctrlreq_queue) >= PNPIPE_CTRLREQ_MAX) { + atomic_inc(&sk->sk_drops); break; + } __skb_pull(skb, 4); queue = &pn->ctrlreq_queue; goto queue; @@ -358,10 +360,13 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) err = sock_queue_rcv_skb(sk, skb); if (!err) return 0; + if (err == -ENOMEM) + atomic_inc(&sk->sk_drops); break; } if (pn->rx_credits == 0) { + atomic_inc(&sk->sk_drops); err = -ENOBUFS; break; } @@ -737,7 +742,7 @@ static int pep_init(struct sock *sk) } static int pep_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct pep_sock *pn = pep_sk(sk); int val = 0, err = 0; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index c2b77a69869..5f42f30dd16 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -27,6 +27,8 @@ #include <linux/net.h> #include <linux/netdevice.h> #include <linux/phonet.h> +#include <linux/proc_fs.h> +#include <linux/if_arp.h> #include <net/sock.h> #include <net/netns/generic.h> #include <net/phonet/pn_dev.h> @@ -194,14 +196,44 @@ found: return err; } +/* automatically configure a Phonet device, if supported */ +static int phonet_device_autoconf(struct net_device *dev) +{ + struct if_phonet_req req; + int ret; + + if (!dev->netdev_ops->ndo_do_ioctl) + return -EOPNOTSUPP; + + ret = dev->netdev_ops->ndo_do_ioctl(dev, (struct ifreq *)&req, + SIOCPNGAUTOCONF); + if (ret < 0) + return ret; + + ASSERT_RTNL(); + ret = phonet_address_add(dev, req.ifr_phonet_autoconf.device); + if (ret) + return ret; + phonet_address_notify(RTM_NEWADDR, dev, + req.ifr_phonet_autoconf.device); + return 0; +} + /* notify Phonet of device events */ static int phonet_device_notify(struct notifier_block *me, unsigned long what, void *arg) { struct net_device *dev = arg; - if (what == NETDEV_UNREGISTER) + switch (what) { + case NETDEV_REGISTER: + if (dev->type == ARPHRD_PHONET) + phonet_device_autoconf(dev); + break; + case NETDEV_UNREGISTER: phonet_device_destroy(dev); + break; + } return 0; } @@ -218,6 +250,11 @@ static int phonet_init_net(struct net *net) if (!pnn) return -ENOMEM; + if (!proc_net_fops_create(net, "phonet", 0, &pn_sock_seq_fops)) { + kfree(pnn); + return -ENOMEM; + } + INIT_LIST_HEAD(&pnn->pndevs.list); spin_lock_init(&pnn->pndevs.lock); net_assign_generic(net, phonet_net_id, pnn); @@ -233,6 +270,8 @@ static void phonet_exit_net(struct net *net) for_each_netdev(net, dev) phonet_device_destroy(dev); rtnl_unlock(); + + proc_net_remove(net, "phonet"); kfree(pnn); } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index f8b4cee434c..d21fd357661 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -147,7 +147,7 @@ static int getaddr_dumpit(struct sk_buff *skb, struct netlink_callback *cb) if (fill_addr(skb, pnd->netdev, addr << 2, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWADDR)) + cb->nlh->nlmsg_seq, RTM_NEWADDR) < 0) goto out; } } diff --git a/net/phonet/socket.c b/net/phonet/socket.c index ada2a35bf7a..aa5b5a972bf 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -113,6 +113,8 @@ void pn_sock_unhash(struct sock *sk) } EXPORT_SYMBOL(pn_sock_unhash); +static DEFINE_MUTEX(port_mutex); + static int pn_socket_bind(struct socket *sock, struct sockaddr *addr, int len) { struct sock *sk = sock->sk; @@ -140,9 +142,11 @@ static int pn_socket_bind(struct socket *sock, struct sockaddr *addr, int len) err = -EINVAL; /* attempt to rebind */ goto out; } + WARN_ON(sk_hashed(sk)); + mutex_lock(&port_mutex); err = sk->sk_prot->get_port(sk, pn_port(handle)); if (err) - goto out; + goto out_port; /* get_port() sets the port, bind() sets the address if applicable */ pn->sobject = pn_object(saddr, pn_port(pn->sobject)); @@ -150,6 +154,8 @@ static int pn_socket_bind(struct socket *sock, struct sockaddr *addr, int len) /* Enable RX on the socket */ sk->sk_prot->hash(sk); +out_port: + mutex_unlock(&port_mutex); out: release_sock(sk); return err; @@ -357,8 +363,6 @@ const struct proto_ops phonet_stream_ops = { }; EXPORT_SYMBOL(phonet_stream_ops); -static DEFINE_MUTEX(port_mutex); - /* allocate port for a socket */ int pn_sock_get_port(struct sock *sk, unsigned short sport) { @@ -370,9 +374,7 @@ int pn_sock_get_port(struct sock *sk, unsigned short sport) memset(&try_sa, 0, sizeof(struct sockaddr_pn)); try_sa.spn_family = AF_PHONET; - - mutex_lock(&port_mutex); - + WARN_ON(!mutex_is_locked(&port_mutex)); if (!sport) { /* search free port */ int port, pmin, pmax; @@ -401,14 +403,110 @@ int pn_sock_get_port(struct sock *sk, unsigned short sport) else sock_put(tmpsk); } - mutex_unlock(&port_mutex); - /* the port must be in use already */ return -EADDRINUSE; found: - mutex_unlock(&port_mutex); pn->sobject = pn_object(pn_addr(pn->sobject), sport); return 0; } 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); + struct hlist_node *node; + struct sock *sknode; + + sk_for_each(sknode, node, &pnsocks.hlist) { + if (!net_eq(net, sock_net(sknode))) + continue; + if (!pos) + return sknode; + pos--; + } + return NULL; +} + +static struct sock *pn_sock_get_next(struct seq_file *seq, struct sock *sk) +{ + struct net *net = seq_file_net(seq); + + do + sk = sk_next(sk); + while (sk && !net_eq(net, sock_net(sk))); + + return sk; +} + +static void *pn_sock_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(pnsocks.lock) +{ + spin_lock_bh(&pnsocks.lock); + return *pos ? pn_sock_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; +} + +static void *pn_sock_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct sock *sk; + + if (v == SEQ_START_TOKEN) + sk = pn_sock_get_idx(seq, 0); + else + sk = pn_sock_get_next(seq, v); + (*pos)++; + return sk; +} + +static void pn_sock_seq_stop(struct seq_file *seq, void *v) + __releases(pnsocks.lock) +{ + spin_unlock_bh(&pnsocks.lock); +} + +static int pn_sock_seq_show(struct seq_file *seq, void *v) +{ + int len; + + if (v == SEQ_START_TOKEN) + seq_printf(seq, "%s%n", "pt loc rem rs st tx_queue rx_queue " + " uid inode ref pointer drops", &len); + else { + struct sock *sk = v; + struct pn_sock *pn = pn_sk(sk); + + seq_printf(seq, "%2d %04X:%04X:%02X %02X %08X:%08X %5d %lu " + "%d %p %d%n", + sk->sk_protocol, pn->sobject, 0, pn->resource, + sk->sk_state, + sk_wmem_alloc_get(sk), sk_rmem_alloc_get(sk), + sock_i_uid(sk), sock_i_ino(sk), + atomic_read(&sk->sk_refcnt), sk, + atomic_read(&sk->sk_drops), &len); + } + seq_printf(seq, "%*s\n", 127 - len, ""); + return 0; +} + +static const struct seq_operations pn_sock_seq_ops = { + .start = pn_sock_seq_start, + .next = pn_sock_seq_next, + .stop = pn_sock_seq_stop, + .show = pn_sock_seq_show, +}; + +static int pn_sock_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &pn_sock_seq_ops, + sizeof(struct seq_net_private)); +} + +const struct file_operations pn_sock_seq_fops = { + .owner = THIS_MODULE, + .open = pn_sock_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; +#endif diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index 7b5749ee276..2220f332232 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -56,7 +56,7 @@ void phonet_get_local_port_range(int *min, int *max) } while (read_seqretry(&local_port_range_lock, seq)); } -static int proc_local_port_range(ctl_table *table, int write, struct file *filp, +static int proc_local_port_range(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -70,7 +70,7 @@ static int proc_local_port_range(ctl_table *table, int write, struct file *filp, .extra2 = &local_port_range_max, }; - ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { if (range[1] < range[0]) diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 796773b5df9..ec753b3ae72 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 51f27585fa0..b46eca10968 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 b11e7e52786..98e05382fd3 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); @@ -249,7 +248,7 @@ static int rds_cong_monitor(struct rds_sock *rs, char __user *optval, } static int rds_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct rds_sock *rs = rds_sk_to_rs(sock->sk); int ret; @@ -360,7 +359,7 @@ static struct proto rds_proto = { .obj_size = sizeof(struct rds_sock), }; -static struct proto_ops rds_proto_ops = { +static const struct proto_ops rds_proto_ops = { .family = AF_RDS, .owner = THIS_MODULE, .release = rds_release, @@ -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 c17cc39160c..5d95fc007f1 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 710e4599d76..dd2711df640 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 d14445c4830..cc8b568c0c8 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -126,7 +126,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp, int is_outgoing) { - struct rds_connection *conn, *tmp, *parent = NULL; + struct rds_connection *conn, *parent = NULL; struct hlist_head *head = rds_conn_bucket(laddr, faddr); unsigned long flags; int ret; @@ -155,7 +155,6 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, } INIT_HLIST_NODE(&conn->c_hash_node); - conn->c_version = RDS_PROTOCOL_3_0; conn->c_laddr = laddr; conn->c_faddr = faddr; spin_lock_init(&conn->c_lock); @@ -211,26 +210,40 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, trans->t_name ? trans->t_name : "[unknown]", is_outgoing ? "(outgoing)" : ""); + /* + * Since we ran without holding the conn lock, someone could + * have created the same conn (either normal or passive) in the + * interim. We check while holding the lock. If we won, we complete + * init and return our conn. If we lost, we rollback and return the + * other one. + */ spin_lock_irqsave(&rds_conn_lock, flags); - if (parent == NULL) { - tmp = rds_conn_lookup(head, laddr, faddr, trans); - if (tmp == NULL) - hlist_add_head(&conn->c_hash_node, head); - } else { - tmp = parent->c_passive; - if (!tmp) + if (parent) { + /* Creating passive conn */ + if (parent->c_passive) { + trans->conn_free(conn->c_transport_data); + kmem_cache_free(rds_conn_slab, conn); + conn = parent->c_passive; + } else { parent->c_passive = conn; - } - - if (tmp) { - trans->conn_free(conn->c_transport_data); - kmem_cache_free(rds_conn_slab, conn); - conn = tmp; + rds_cong_add_conn(conn); + rds_conn_count++; + } } else { - rds_cong_add_conn(conn); - rds_conn_count++; + /* Creating normal conn */ + struct rds_connection *found; + + found = rds_conn_lookup(head, laddr, faddr, trans); + if (found) { + trans->conn_free(conn->c_transport_data); + kmem_cache_free(rds_conn_slab, conn); + conn = found; + } else { + hlist_add_head(&conn->c_hash_node, head); + rds_cong_add_conn(conn); + rds_conn_count++; + } } - spin_unlock_irqrestore(&rds_conn_lock, flags); out: @@ -242,12 +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) { @@ -290,6 +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, @@ -393,6 +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) @@ -468,6 +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 b9bcd32431e..536ebe5d3f6 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -43,11 +43,14 @@ unsigned int fmr_pool_size = RDS_FMR_POOL_SIZE; unsigned int fmr_message_size = RDS_FMR_SIZE + 1; /* +1 allows for unaligned MRs */ +unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT; module_param(fmr_pool_size, int, 0444); MODULE_PARM_DESC(fmr_pool_size, " Max number of fmr per HCA"); module_param(fmr_message_size, int, 0444); MODULE_PARM_DESC(fmr_message_size, " Max size of a RDMA transfer"); +module_param(rds_ib_retry_count, int, 0444); +MODULE_PARM_DESC(rds_ib_retry_count, " Number of hw retries before reporting an error"); struct list_head rds_ib_devices; @@ -82,9 +85,6 @@ void rds_ib_add_one(struct ib_device *device) rds_ibdev->max_wrs = dev_attr->max_qp_wr; rds_ibdev->max_sge = min(dev_attr->max_sge, RDS_IB_MAX_SGE); - rds_ibdev->fmr_page_shift = max(9, ffs(dev_attr->page_size_cap) - 1); - rds_ibdev->fmr_page_size = 1 << rds_ibdev->fmr_page_shift; - rds_ibdev->fmr_page_mask = ~((u64) rds_ibdev->fmr_page_size - 1); rds_ibdev->fmr_max_remaps = dev_attr->max_map_per_fmr?: 32; rds_ibdev->max_fmrs = dev_attr->max_fmr ? min_t(unsigned int, dev_attr->max_fmr, fmr_pool_size) : @@ -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/ib.h b/net/rds/ib.h index 455ae73047f..1378b854cac 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -15,6 +15,8 @@ #define RDS_IB_DEFAULT_RECV_WR 1024 #define RDS_IB_DEFAULT_SEND_WR 256 +#define RDS_IB_DEFAULT_RETRY_COUNT 2 + #define RDS_IB_SUPPORTED_PROTOCOLS 0x00000003 /* minor versions supported */ extern struct list_head rds_ib_devices; @@ -157,9 +159,6 @@ struct rds_ib_device { struct ib_pd *pd; struct ib_mr *mr; struct rds_ib_mr_pool *mr_pool; - int fmr_page_shift; - int fmr_page_size; - u64 fmr_page_mask; unsigned int fmr_max_remaps; unsigned int max_fmrs; int max_sge; @@ -247,6 +246,7 @@ extern struct ib_client rds_ib_client; extern unsigned int fmr_pool_size; extern unsigned int fmr_message_size; +extern unsigned int rds_ib_retry_count; extern spinlock_t ib_nodev_conns_lock; extern struct list_head ib_nodev_conns; @@ -355,17 +355,25 @@ extern ctl_table rds_ib_sysctl_table[]; /* * Helper functions for getting/setting the header and data SGEs in * RDS packets (not RDMA) + * + * From version 3.1 onwards, header is in front of data in the sge. */ static inline struct ib_sge * rds_ib_header_sge(struct rds_ib_connection *ic, struct ib_sge *sge) { - return &sge[0]; + if (ic->conn->c_version > RDS_PROTOCOL_3_0) + return &sge[0]; + else + return &sge[1]; } static inline struct ib_sge * rds_ib_data_sge(struct rds_ib_connection *ic, struct ib_sge *sge) { - return &sge[1]; + if (ic->conn->c_version > RDS_PROTOCOL_3_0) + return &sge[1]; + else + return &sge[0]; } #endif diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index f8e40e1a603..c2d372f13db 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -98,21 +98,34 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even struct ib_qp_attr qp_attr; int err; - if (event->param.conn.private_data_len) { + if (event->param.conn.private_data_len >= sizeof(*dp)) { dp = event->param.conn.private_data; - rds_ib_set_protocol(conn, + /* make sure it isn't empty data */ + if (dp->dp_protocol_major) { + rds_ib_set_protocol(conn, RDS_PROTOCOL(dp->dp_protocol_major, - dp->dp_protocol_minor)); - rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit)); + dp->dp_protocol_minor)); + rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit)); + } } printk(KERN_NOTICE "RDS/IB: connected to %pI4 version %u.%u%s\n", - &conn->c_laddr, + &conn->c_faddr, RDS_PROTOCOL_MAJOR(conn->c_version), RDS_PROTOCOL_MINOR(conn->c_version), ic->i_flowctl ? ", flow control" : ""); + /* + * Init rings and fill recv. this needs to wait until protocol negotiation + * is complete, since ring layout is different from 3.0 to 3.1. + */ + rds_ib_send_init_ring(ic); + rds_ib_recv_init_ring(ic); + /* Post receive buffers - as a side effect, this will update + * the posted credit count. */ + rds_ib_recv_refill(conn, GFP_KERNEL, GFP_HIGHUSER, 1); + /* Tune RNR behavior */ rds_ib_tune_rnr(ic, &qp_attr); @@ -145,7 +158,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, /* XXX tune these? */ conn_param->responder_resources = 1; conn_param->initiator_depth = 1; - conn_param->retry_count = 7; + conn_param->retry_count = min_t(unsigned int, rds_ib_retry_count, 7); conn_param->rnr_retry_count = 7; if (dp) { @@ -190,9 +203,9 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data) rdma_notify(ic->i_cm_id, IB_EVENT_COMM_EST); break; default: - printk(KERN_WARNING "RDS/ib: unhandled QP event %u " - "on connection to %pI4\n", event->event, - &conn->c_faddr); + rds_ib_conn_error(conn, "RDS/IB: Fatal QP Event %u " + "- connection %pI4->%pI4, reconnecting\n", + event->event, &conn->c_laddr, &conn->c_faddr); break; } } @@ -321,7 +334,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) rdsdebug("send allocation failed\n"); goto out; } - rds_ib_send_init_ring(ic); + memset(ic->i_sends, 0, ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work)); ic->i_recvs = vmalloc(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work)); if (ic->i_recvs == NULL) { @@ -329,14 +342,10 @@ static int rds_ib_setup_qp(struct rds_connection *conn) rdsdebug("recv allocation failed\n"); goto out; } + memset(ic->i_recvs, 0, ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work)); - rds_ib_recv_init_ring(ic); rds_ib_recv_init_ack(ic); - /* Post receive buffers - as a side effect, this will update - * the posted credit count. */ - rds_ib_recv_refill(conn, GFP_KERNEL, GFP_HIGHUSER, 1); - rdsdebug("conn %p pd %p mr %p cq %p %p\n", conn, ic->i_pd, ic->i_mr, ic->i_send_cq, ic->i_recv_cq); @@ -344,19 +353,32 @@ out: return ret; } -static u32 rds_ib_protocol_compatible(const struct rds_ib_connect_private *dp) +static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event) { + const struct rds_ib_connect_private *dp = event->param.conn.private_data; u16 common; u32 version = 0; - /* rdma_cm private data is odd - when there is any private data in the + /* + * rdma_cm private data is odd - when there is any private data in the * request, we will be given a pretty large buffer without telling us the * original size. The only way to tell the difference is by looking at * the contents, which are initialized to zero. * If the protocol version fields aren't set, this is a connection attempt * from an older version. This could could be 3.0 or 2.0 - we can't tell. - * We really should have changed this for OFED 1.3 :-( */ - if (dp->dp_protocol_major == 0) + * We really should have changed this for OFED 1.3 :-( + */ + + /* Be paranoid. RDS always has privdata */ + if (!event->param.conn.private_data_len) { + printk(KERN_NOTICE "RDS incoming connection has no private data, " + "rejecting\n"); + return 0; + } + + /* Even if len is crap *now* I still want to check it. -ASG */ + if (event->param.conn.private_data_len < sizeof (*dp) + || dp->dp_protocol_major == 0) return RDS_PROTOCOL_3_0; common = be16_to_cpu(dp->dp_protocol_minor_mask) & RDS_IB_SUPPORTED_PROTOCOLS; @@ -388,7 +410,7 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, int err, destroy = 1; /* Check whether the remote protocol version matches ours. */ - version = rds_ib_protocol_compatible(dp); + version = rds_ib_protocol_compatible(event); if (!version) goto out; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 81033af9302..ef3ab5b7283 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -211,7 +211,7 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev) pool->fmr_attr.max_pages = fmr_message_size; pool->fmr_attr.max_maps = rds_ibdev->fmr_max_remaps; - pool->fmr_attr.page_shift = rds_ibdev->fmr_page_shift; + pool->fmr_attr.page_shift = PAGE_SHIFT; pool->max_free_pinned = rds_ibdev->max_fmrs * fmr_message_size / 4; /* We never allow more than max_items MRs to be allocated. @@ -349,13 +349,13 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibm unsigned int dma_len = ib_sg_dma_len(dev, &scat[i]); u64 dma_addr = ib_sg_dma_address(dev, &scat[i]); - if (dma_addr & ~rds_ibdev->fmr_page_mask) { + if (dma_addr & ~PAGE_MASK) { if (i > 0) return -EINVAL; else ++page_cnt; } - if ((dma_addr + dma_len) & ~rds_ibdev->fmr_page_mask) { + if ((dma_addr + dma_len) & ~PAGE_MASK) { if (i < sg_dma_len - 1) return -EINVAL; else @@ -365,7 +365,7 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibm len += dma_len; } - page_cnt += len >> rds_ibdev->fmr_page_shift; + page_cnt += len >> PAGE_SHIFT; if (page_cnt > fmr_message_size) return -EINVAL; @@ -378,9 +378,9 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibm unsigned int dma_len = ib_sg_dma_len(dev, &scat[i]); u64 dma_addr = ib_sg_dma_address(dev, &scat[i]); - for (j = 0; j < dma_len; j += rds_ibdev->fmr_page_size) + for (j = 0; j < dma_len; j += PAGE_SIZE) dma_pages[page_cnt++] = - (dma_addr & rds_ibdev->fmr_page_mask) + j; + (dma_addr & PAGE_MASK) + j; } ret = ib_map_phys_fmr(ibmr->fmr, diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 5709bad2832..cd7a6cfcab0 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -555,6 +555,47 @@ u64 rds_ib_piggyb_ack(struct rds_ib_connection *ic) return rds_ib_get_ack(ic); } +static struct rds_header *rds_ib_get_header(struct rds_connection *conn, + struct rds_ib_recv_work *recv, + u32 data_len) +{ + struct rds_ib_connection *ic = conn->c_transport_data; + void *hdr_buff = &ic->i_recv_hdrs[recv - ic->i_recvs]; + void *addr; + u32 misplaced_hdr_bytes; + + /* + * Support header at the front (RDS 3.1+) as well as header-at-end. + * + * Cases: + * 1) header all in header buff (great!) + * 2) header all in data page (copy all to header buff) + * 3) header split across hdr buf + data page + * (move bit in hdr buff to end before copying other bit from data page) + */ + if (conn->c_version > RDS_PROTOCOL_3_0 || data_len == RDS_FRAG_SIZE) + return hdr_buff; + + if (data_len <= (RDS_FRAG_SIZE - sizeof(struct rds_header))) { + addr = kmap_atomic(recv->r_frag->f_page, KM_SOFTIRQ0); + memcpy(hdr_buff, + addr + recv->r_frag->f_offset + data_len, + sizeof(struct rds_header)); + kunmap_atomic(addr, KM_SOFTIRQ0); + return hdr_buff; + } + + misplaced_hdr_bytes = (sizeof(struct rds_header) - (RDS_FRAG_SIZE - data_len)); + + memmove(hdr_buff + misplaced_hdr_bytes, hdr_buff, misplaced_hdr_bytes); + + addr = kmap_atomic(recv->r_frag->f_page, KM_SOFTIRQ0); + memcpy(hdr_buff, addr + recv->r_frag->f_offset + data_len, + sizeof(struct rds_header) - misplaced_hdr_bytes); + kunmap_atomic(addr, KM_SOFTIRQ0); + return hdr_buff; +} + /* * It's kind of lame that we're copying from the posted receive pages into * long-lived bitmaps. We could have posted the bitmaps and rdma written into @@ -645,7 +686,7 @@ struct rds_ib_ack_state { }; static void rds_ib_process_recv(struct rds_connection *conn, - struct rds_ib_recv_work *recv, u32 byte_len, + struct rds_ib_recv_work *recv, u32 data_len, struct rds_ib_ack_state *state) { struct rds_ib_connection *ic = conn->c_transport_data; @@ -655,9 +696,9 @@ static void rds_ib_process_recv(struct rds_connection *conn, /* XXX shut down the connection if port 0,0 are seen? */ rdsdebug("ic %p ibinc %p recv %p byte len %u\n", ic, ibinc, recv, - byte_len); + data_len); - if (byte_len < sizeof(struct rds_header)) { + if (data_len < sizeof(struct rds_header)) { rds_ib_conn_error(conn, "incoming message " "from %pI4 didn't inclue a " "header, disconnecting and " @@ -665,9 +706,9 @@ static void rds_ib_process_recv(struct rds_connection *conn, &conn->c_faddr); return; } - byte_len -= sizeof(struct rds_header); + data_len -= sizeof(struct rds_header); - ihdr = &ic->i_recv_hdrs[recv - ic->i_recvs]; + ihdr = rds_ib_get_header(conn, recv, data_len); /* Validate the checksum. */ if (!rds_message_verify_checksum(ihdr)) { @@ -687,7 +728,7 @@ static void rds_ib_process_recv(struct rds_connection *conn, if (ihdr->h_credit) rds_ib_send_add_credits(conn, ihdr->h_credit); - if (ihdr->h_sport == 0 && ihdr->h_dport == 0 && byte_len == 0) { + if (ihdr->h_sport == 0 && ihdr->h_dport == 0 && data_len == 0) { /* This is an ACK-only packet. The fact that it gets * special treatment here is that historically, ACKs * were rather special beasts. diff --git a/net/rds/ib_stats.c b/net/rds/ib_stats.c index 02e3e3d50d4..d2c904dd6fb 100644 --- a/net/rds/ib_stats.c +++ b/net/rds/ib_stats.c @@ -37,9 +37,9 @@ #include "rds.h" #include "ib.h" -DEFINE_PER_CPU(struct rds_ib_statistics, rds_ib_stats) ____cacheline_aligned; +DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_ib_statistics, rds_ib_stats); -static char *rds_ib_stat_names[] = { +static const char *const rds_ib_stat_names[] = { "ib_connect_raced", "ib_listen_closed_stale", "ib_tx_cq_call", diff --git a/net/rds/ib_sysctl.c b/net/rds/ib_sysctl.c index d87830db93a..84b5ffcb280 100644 --- a/net/rds/ib_sysctl.c +++ b/net/rds/ib_sysctl.c @@ -53,7 +53,17 @@ unsigned long rds_ib_sysctl_max_unsig_bytes = (16 << 20); static unsigned long rds_ib_sysctl_max_unsig_bytes_min = 1; static unsigned long rds_ib_sysctl_max_unsig_bytes_max = ~0UL; -unsigned int rds_ib_sysctl_flow_control = 1; +/* + * This sysctl does nothing. + * + * Backwards compatibility with RDS 3.0 wire protocol + * disables initial FC credit exchange. + * If it's ever possible to drop 3.0 support, + * setting this to 1 and moving init/refill of send/recv + * rings from ib_cm_connect_complete() back into ib_setup_qp() + * will cause credits to be added before protocol negotiation. + */ +unsigned int rds_ib_sysctl_flow_control = 0; ctl_table rds_ib_sysctl_table[] = { { diff --git a/net/rds/info.c b/net/rds/info.c index 62aeef37aef..814a91a6f4a 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 d16e1cbc8e8..db224f7c293 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -83,23 +83,16 @@ void rds_iw_add_one(struct ib_device *device) rds_iwdev->max_wrs = dev_attr->max_qp_wr; rds_iwdev->max_sge = min(dev_attr->max_sge, RDS_IW_MAX_SGE); - rds_iwdev->page_shift = max(PAGE_SHIFT, ffs(dev_attr->page_size_cap) - 1); - rds_iwdev->dev = device; rds_iwdev->pd = ib_alloc_pd(device); if (IS_ERR(rds_iwdev->pd)) goto free_dev; if (!rds_iwdev->dma_local_lkey) { - if (device->node_type != RDMA_NODE_RNIC) { - rds_iwdev->mr = ib_get_dma_mr(rds_iwdev->pd, - IB_ACCESS_LOCAL_WRITE); - } else { - rds_iwdev->mr = ib_get_dma_mr(rds_iwdev->pd, - IB_ACCESS_REMOTE_READ | - IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_LOCAL_WRITE); - } + rds_iwdev->mr = ib_get_dma_mr(rds_iwdev->pd, + IB_ACCESS_REMOTE_READ | + IB_ACCESS_REMOTE_WRITE | + IB_ACCESS_LOCAL_WRITE); if (IS_ERR(rds_iwdev->mr)) goto err_pd; } else @@ -291,6 +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/iw.h b/net/rds/iw.h index 0715dde323e..dd72b62bd50 100644 --- a/net/rds/iw.h +++ b/net/rds/iw.h @@ -181,7 +181,6 @@ struct rds_iw_device { struct ib_pd *pd; struct ib_mr *mr; struct rds_iw_mr_pool *mr_pool; - int page_shift; int max_sge; unsigned int max_wrs; unsigned int dma_local_lkey:1; diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index dcdb37da80f..de4a1b16bf7 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -263,18 +263,12 @@ static void rds_iw_set_scatterlist(struct rds_iw_scatterlist *sg, } static u64 *rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev, - struct rds_iw_scatterlist *sg, - unsigned int dma_page_shift) + struct rds_iw_scatterlist *sg) { struct ib_device *dev = rds_iwdev->dev; u64 *dma_pages = NULL; - u64 dma_mask; - unsigned int dma_page_size; int i, j, ret; - dma_page_size = 1 << dma_page_shift; - dma_mask = dma_page_size - 1; - WARN_ON(sg->dma_len); sg->dma_len = ib_dma_map_sg(dev, sg->list, sg->len, DMA_BIDIRECTIONAL); @@ -295,18 +289,18 @@ static u64 *rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev, sg->bytes += dma_len; end_addr = dma_addr + dma_len; - if (dma_addr & dma_mask) { + if (dma_addr & PAGE_MASK) { if (i > 0) goto out_unmap; - dma_addr &= ~dma_mask; + dma_addr &= ~PAGE_MASK; } - if (end_addr & dma_mask) { + if (end_addr & PAGE_MASK) { if (i < sg->dma_len - 1) goto out_unmap; - end_addr = (end_addr + dma_mask) & ~dma_mask; + end_addr = (end_addr + PAGE_MASK) & ~PAGE_MASK; } - sg->dma_npages += (end_addr - dma_addr) >> dma_page_shift; + sg->dma_npages += (end_addr - dma_addr) >> PAGE_SHIFT; } /* Now gather the dma addrs into one list */ @@ -325,8 +319,8 @@ static u64 *rds_iw_map_scatterlist(struct rds_iw_device *rds_iwdev, u64 end_addr; end_addr = dma_addr + dma_len; - dma_addr &= ~dma_mask; - for (; dma_addr < end_addr; dma_addr += dma_page_size) + dma_addr &= ~PAGE_MASK; + for (; dma_addr < end_addr; dma_addr += PAGE_SIZE) dma_pages[j++] = dma_addr; BUG_ON(j > sg->dma_npages); } @@ -727,7 +721,7 @@ static int rds_iw_rdma_build_fastreg(struct rds_iw_mapping *mapping) f_wr.wr.fast_reg.rkey = mapping->m_rkey; f_wr.wr.fast_reg.page_list = ibmr->page_list; f_wr.wr.fast_reg.page_list_len = mapping->m_sg.dma_len; - f_wr.wr.fast_reg.page_shift = ibmr->device->page_shift; + f_wr.wr.fast_reg.page_shift = PAGE_SHIFT; f_wr.wr.fast_reg.access_flags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE; @@ -780,9 +774,7 @@ static int rds_iw_map_fastreg(struct rds_iw_mr_pool *pool, rds_iw_set_scatterlist(&mapping->m_sg, sg, sg_len); - dma_pages = rds_iw_map_scatterlist(rds_iwdev, - &mapping->m_sg, - rds_iwdev->page_shift); + dma_pages = rds_iw_map_scatterlist(rds_iwdev, &mapping->m_sg); if (IS_ERR(dma_pages)) { ret = PTR_ERR(dma_pages); dma_pages = NULL; diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 44a6a0551f2..1f5abe3cf2b 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -779,7 +779,7 @@ static void rds_iw_build_send_fastreg(struct rds_iw_device *rds_iwdev, struct rd send->s_wr.wr.fast_reg.rkey = send->s_mr->rkey; send->s_wr.wr.fast_reg.page_list = send->s_page_list; send->s_wr.wr.fast_reg.page_list_len = nent; - send->s_wr.wr.fast_reg.page_shift = rds_iwdev->page_shift; + send->s_wr.wr.fast_reg.page_shift = PAGE_SHIFT; send->s_wr.wr.fast_reg.access_flags = IB_ACCESS_REMOTE_WRITE; send->s_wr.wr.fast_reg.iova_start = sg_addr; diff --git a/net/rds/iw_stats.c b/net/rds/iw_stats.c index ccc7e8f0bf0..5fe67f6a1d8 100644 --- a/net/rds/iw_stats.c +++ b/net/rds/iw_stats.c @@ -37,9 +37,9 @@ #include "rds.h" #include "iw.h" -DEFINE_PER_CPU(struct rds_iw_statistics, rds_iw_stats) ____cacheline_aligned; +DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_iw_statistics, rds_iw_stats); -static char *rds_iw_stat_names[] = { +static const char *const rds_iw_stat_names[] = { "iw_connect_raced", "iw_listen_closed_stale", "iw_tx_cq_call", diff --git a/net/rds/message.c b/net/rds/message.c index 5a15dc8d0cd..ca50a8ec974 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 c460743a89a..36790122dfd 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -39,7 +39,7 @@ struct rds_page_remainder { unsigned long r_offset; }; -DEFINE_PER_CPU(struct rds_page_remainder, rds_page_remainders) ____cacheline_aligned; +DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders); /* * returns 0 on success or -errno on failure. @@ -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 7d0f901c93d..9ece910ea39 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -101,7 +101,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_DISCONNECTED: - printk(KERN_WARNING "RDS/IW: DISCONNECT event - dropping connection " + printk(KERN_WARNING "RDS/RDMA: DISCONNECT event - dropping connection " "%pI4->%pI4\n", &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); @@ -132,12 +132,12 @@ static int __init rds_rdma_listen_init(void) cm_id = rdma_create_id(rds_rdma_cm_event_handler, NULL, RDMA_PS_TCP); if (IS_ERR(cm_id)) { ret = PTR_ERR(cm_id); - printk(KERN_ERR "RDS/IW: failed to setup listener, " + printk(KERN_ERR "RDS/RDMA: failed to setup listener, " "rdma_create_id() returned %d\n", ret); goto out; } - sin.sin_family = PF_INET, + sin.sin_family = AF_INET, sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY); sin.sin_port = (__force u16)htons(RDS_PORT); @@ -147,14 +147,14 @@ static int __init rds_rdma_listen_init(void) */ ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); if (ret) { - printk(KERN_ERR "RDS/IW: failed to setup listener, " + printk(KERN_ERR "RDS/RDMA: failed to setup listener, " "rdma_bind_addr() returned %d\n", ret); goto out; } ret = rdma_listen(cm_id, 128); if (ret) { - printk(KERN_ERR "RDS/IW: failed to setup listener, " + printk(KERN_ERR "RDS/RDMA: failed to setup listener, " "rdma_listen() returned %d\n", ret); goto out; } @@ -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 dbe11123678..85d6f897ecc 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); @@ -652,7 +658,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); int __init rds_stats_init(void); void rds_stats_exit(void); void rds_stats_info_copy(struct rds_info_iterator *iter, - uint64_t *values, char **names, size_t nr); + uint64_t *values, const char *const *names, + size_t nr); /* sysctl.c */ int __init rds_sysctl_init(void); diff --git a/net/rds/recv.c b/net/rds/recv.c index f2118c51cfa..fdff33c7b43 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 @@ -409,18 +413,18 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, if (msg_flags & MSG_OOB) goto out; - /* If there are pending notifications, do those - and nothing else */ - if (!list_empty(&rs->rs_notify_queue)) { - ret = rds_notify_queue_get(rs, msg); - goto out; - } + while (1) { + /* If there are pending notifications, do those - and nothing else */ + if (!list_empty(&rs->rs_notify_queue)) { + ret = rds_notify_queue_get(rs, msg); + break; + } - if (rs->rs_cong_notify) { - ret = rds_notify_cong(rs, msg); - goto out; - } + if (rs->rs_cong_notify) { + ret = rds_notify_cong(rs, msg); + break; + } - while (1) { if (!rds_next_incoming(rs, &inc)) { if (nonblock) { ret = -EAGAIN; @@ -428,7 +432,9 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, } timeo = wait_event_interruptible_timeout(*sk->sk_sleep, - rds_next_incoming(rs, &inc), + (!list_empty(&rs->rs_notify_queue) + || rs->rs_cong_notify + || rds_next_incoming(rs, &inc)), timeo); rdsdebug("recvmsg woke inc %p timeo %ld\n", inc, timeo); diff --git a/net/rds/send.c b/net/rds/send.c index a4a7f428cd7..28c88ff3d03 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 637146893cf..7598eb07cfb 100644 --- a/net/rds/stats.c +++ b/net/rds/stats.c @@ -37,10 +37,11 @@ #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 */ -static char *rds_stat_names[] = { +static const char *const rds_stat_names[] = { "conn_reset", "recv_drop_bad_checksum", "recv_drop_old_seq", @@ -77,7 +78,7 @@ static char *rds_stat_names[] = { }; void rds_stats_info_copy(struct rds_info_iterator *iter, - uint64_t *values, char **names, size_t nr) + uint64_t *values, const char *const *names, size_t nr) { struct rds_info_counter ctr; size_t i; @@ -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 00000000000..b5198aee45d --- /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 00000000000..844fa6b9cf5 --- /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 00000000000..211522f9a9a --- /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 00000000000..24b743eb0b1 --- /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 00000000000..c00dafffbb5 --- /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 00000000000..ab545e0cd5d --- /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 00000000000..d5898d03cd6 --- /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 828a1bf9ea9..dd7e0cad1e7 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 767da61ad2f..7e106790135 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/rfkill/core.c b/net/rfkill/core.c index 2fc4a1724eb..a001f7c1f71 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -27,6 +27,7 @@ #include <linux/list.h> #include <linux/mutex.h> #include <linux/rfkill.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/miscdevice.h> #include <linux/wait.h> @@ -589,11 +590,13 @@ static const char *rfkill_get_type_str(enum rfkill_type type) return "wimax"; case RFKILL_TYPE_WWAN: return "wwan"; + case RFKILL_TYPE_GPS: + return "gps"; default: BUG(); } - BUILD_BUG_ON(NUM_RFKILL_TYPES != RFKILL_TYPE_WWAN + 1); + BUILD_BUG_ON(NUM_RFKILL_TYPES != RFKILL_TYPE_GPS + 1); } static ssize_t rfkill_type_show(struct device *dev, @@ -1091,10 +1094,16 @@ static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, struct rfkill_event ev; /* we don't need the 'hard' variable but accept it */ - if (count < sizeof(ev) - 1) + if (count < RFKILL_EVENT_SIZE_V1 - 1) return -EINVAL; - if (copy_from_user(&ev, buf, sizeof(ev) - 1)) + /* + * Copy as much data as we can accept into our 'ev' buffer, + * but tell userspace how much we've copied so it can determine + * our API version even in a write() call, if it cares. + */ + count = min(count, sizeof(ev)); + if (copy_from_user(&ev, buf, count)) return -EFAULT; if (ev.op != RFKILL_OP_CHANGE && ev.op != RFKILL_OP_CHANGE_ALL) @@ -1180,6 +1189,7 @@ static long rfkill_fop_ioctl(struct file *file, unsigned int cmd, #endif static const struct file_operations rfkill_fops = { + .owner = THIS_MODULE, .open = rfkill_fop_open, .read = rfkill_fop_read, .write = rfkill_fop_write, diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index e5f478ca3d6..502cce76621 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -63,7 +63,7 @@ int sysctl_rose_window_size = ROSE_DEFAULT_WINDOW_SIZE; static HLIST_HEAD(rose_list); static DEFINE_SPINLOCK(rose_list_lock); -static struct proto_ops rose_proto_ops; +static const struct proto_ops rose_proto_ops; ax25_address rose_callsign; @@ -370,7 +370,7 @@ void rose_destroy_socket(struct sock *sk) */ static int rose_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); @@ -1515,7 +1515,7 @@ static struct net_proto_family rose_family_ops = { .owner = THIS_MODULE, }; -static struct proto_ops rose_proto_ops = { +static const struct proto_ops rose_proto_ops = { .family = PF_ROSE, .owner = THIS_MODULE, .release = rose_release, diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c index 389d6e0d774..424b893d145 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; @@ -141,7 +141,7 @@ static int rose_xmit(struct sk_buff *skb, struct net_device *dev) } dev_kfree_skb(skb); stats->tx_errors++; - return 0; + return NETDEV_TX_OK; } static const struct header_ops rose_header_ops = { diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 9478d9b3d97..f3e21989b88 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -578,18 +578,18 @@ static int rose_clear_routes(void) /* * Check that the device given is a valid AX.25 interface that is "up". + * called whith RTNL */ -static struct net_device *rose_ax25_dev_get(char *devname) +static struct net_device *rose_ax25_dev_find(char *devname) { struct net_device *dev; - if ((dev = dev_get_by_name(&init_net, devname)) == NULL) + if ((dev = __dev_get_by_name(&init_net, devname)) == NULL) return NULL; if ((dev->flags & IFF_UP) && dev->type == ARPHRD_AX25) return dev; - dev_put(dev); return NULL; } @@ -720,27 +720,23 @@ int rose_rt_ioctl(unsigned int cmd, void __user *arg) case SIOCADDRT: if (copy_from_user(&rose_route, arg, sizeof(struct rose_route_struct))) return -EFAULT; - if ((dev = rose_ax25_dev_get(rose_route.device)) == NULL) + if ((dev = rose_ax25_dev_find(rose_route.device)) == NULL) return -EINVAL; - if (rose_dev_exists(&rose_route.address)) { /* Can't add routes to ourself */ - dev_put(dev); + if (rose_dev_exists(&rose_route.address)) /* Can't add routes to ourself */ return -EINVAL; - } if (rose_route.mask > 10) /* Mask can't be more than 10 digits */ return -EINVAL; if (rose_route.ndigis > AX25_MAX_DIGIS) return -EINVAL; err = rose_add_node(&rose_route, dev); - dev_put(dev); return err; case SIOCDELRT: if (copy_from_user(&rose_route, arg, sizeof(struct rose_route_struct))) return -EFAULT; - if ((dev = rose_ax25_dev_get(rose_route.device)) == NULL) + if ((dev = rose_ax25_dev_find(rose_route.device)) == NULL) return -EINVAL; err = rose_del_node(&rose_route, dev); - dev_put(dev); return err; case SIOCRSCLRRT: diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index bfe493ebf27..a86afceaa94 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -507,7 +507,7 @@ out: * set RxRPC socket options */ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); unsigned min_sec_level; diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index 3ac1672e107..b4a22097703 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -20,7 +20,7 @@ static unsigned rxrpc_ack_defer = 1; -static const char *rxrpc_acks[] = { +static const char *const rxrpc_acks[] = { "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", "IDL", "-?-" }; @@ -40,7 +40,7 @@ static const s8 rxrpc_ack_priority[] = { /* * propose an ACK be sent */ -void __rxrpc_propose_ACK(struct rxrpc_call *call, uint8_t ack_reason, +void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, __be32 serial, bool immediate) { unsigned long expiry; @@ -120,7 +120,7 @@ cancel_timer: /* * propose an ACK be sent, locking the call structure */ -void rxrpc_propose_ACK(struct rxrpc_call *call, uint8_t ack_reason, +void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, __be32 serial, bool immediate) { s8 prior = rxrpc_ack_priority[ack_reason]; @@ -520,7 +520,7 @@ static void rxrpc_zap_tx_window(struct rxrpc_call *call) struct rxrpc_skb_priv *sp; struct sk_buff *skb; unsigned long _skb, *acks_window; - uint8_t winsz = call->acks_winsz; + u8 winsz = call->acks_winsz; int tail; acks_window = call->acks_window; diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c index d9231245a79..bc0019f704f 100644 --- a/net/rxrpc/ar-call.c +++ b/net/rxrpc/ar-call.c @@ -96,7 +96,7 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) } /* - * allocate a new client call and attempt to to get a connection slot for it + * allocate a new client call and attempt to get a connection slot for it */ static struct rxrpc_call *rxrpc_alloc_client_call( struct rxrpc_sock *rx, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 3e7318c1343..7043b294bb6 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -229,7 +229,7 @@ struct rxrpc_conn_bundle { int debug_id; /* debug ID for printks */ unsigned short num_conns; /* number of connections in this bundle */ __be16 service_id; /* service ID */ - uint8_t security_ix; /* security type */ + u8 security_ix; /* security type */ }; /* @@ -370,10 +370,10 @@ struct rxrpc_call { u8 channel; /* connection channel occupied by this call */ /* transmission-phase ACK management */ - uint8_t acks_head; /* offset into window of first entry */ - uint8_t acks_tail; /* offset into window of last entry */ - uint8_t acks_winsz; /* size of un-ACK'd window */ - uint8_t acks_unacked; /* lowest unacked packet in last ACK received */ + u8 acks_head; /* offset into window of first entry */ + u8 acks_tail; /* offset into window of last entry */ + u8 acks_winsz; /* size of un-ACK'd window */ + u8 acks_unacked; /* lowest unacked packet in last ACK received */ int acks_latest; /* serial number of latest ACK received */ rxrpc_seq_t acks_hard; /* highest definitively ACK'd msg seq */ unsigned long *acks_window; /* sent packet window @@ -388,7 +388,7 @@ struct rxrpc_call { rxrpc_seq_t rx_first_oos; /* first packet in rx_oos_queue (or 0) */ rxrpc_seq_t ackr_win_top; /* top of ACK window (rx_data_eaten is bottom) */ rxrpc_seq_net_t ackr_prev_seq; /* previous sequence number received */ - uint8_t ackr_reason; /* reason to ACK */ + u8 ackr_reason; /* reason to ACK */ __be32 ackr_serial; /* serial of packet being ACK'd */ atomic_t ackr_not_idle; /* number of packets in Rx queue */ @@ -402,22 +402,6 @@ struct rxrpc_call { }; /* - * RxRPC key for Kerberos (type-2 security) - */ -struct rxkad_key { - u16 security_index; /* RxRPC header security index */ - u16 ticket_len; /* length of ticket[] */ - u32 expiry; /* time at which expires */ - u32 kvno; /* key version number */ - u8 session_key[8]; /* DES session key */ - u8 ticket[0]; /* the encrypted ticket */ -}; - -struct rxrpc_key_payload { - struct rxkad_key k; -}; - -/* * locally abort an RxRPC call */ static inline void rxrpc_abort_call(struct rxrpc_call *call, u32 abort_code) @@ -450,8 +434,8 @@ extern int rxrpc_reject_call(struct rxrpc_sock *); /* * ar-ack.c */ -extern void __rxrpc_propose_ACK(struct rxrpc_call *, uint8_t, __be32, bool); -extern void rxrpc_propose_ACK(struct rxrpc_call *, uint8_t, __be32, bool); +extern void __rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool); +extern void rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool); extern void rxrpc_process_call(struct work_struct *); /* diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index ad8c7a782da..74697b20049 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -17,6 +17,7 @@ #include <linux/skbuff.h> #include <linux/key-type.h> #include <linux/crypto.h> +#include <linux/ctype.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <keys/rxrpc-type.h> @@ -28,6 +29,7 @@ static int rxrpc_instantiate_s(struct key *, const void *, size_t); static void rxrpc_destroy(struct key *); static void rxrpc_destroy_s(struct key *); static void rxrpc_describe(const struct key *, struct seq_file *); +static long rxrpc_read(const struct key *, char __user *, size_t); /* * rxrpc defined keys take an arbitrary string as the description and an @@ -39,6 +41,7 @@ struct key_type key_type_rxrpc = { .match = user_match, .destroy = rxrpc_destroy, .describe = rxrpc_describe, + .read = rxrpc_read, }; EXPORT_SYMBOL(key_type_rxrpc); @@ -55,6 +58,595 @@ struct key_type key_type_rxrpc_s = { }; /* + * parse an RxKAD type XDR format token + * - the caller guarantees we have at least 4 words + */ +static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr, + unsigned toklen) +{ + struct rxrpc_key_token *token, **pptoken; + size_t plen; + u32 tktlen; + int ret; + + _enter(",{%x,%x,%x,%x},%u", + ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]), + toklen); + + if (toklen <= 8 * 4) + return -EKEYREJECTED; + tktlen = ntohl(xdr[7]); + _debug("tktlen: %x", tktlen); + if (tktlen > AFSTOKEN_RK_TIX_MAX) + return -EKEYREJECTED; + if (8 * 4 + tktlen != toklen) + return -EKEYREJECTED; + + plen = sizeof(*token) + sizeof(*token->kad) + tktlen; + ret = key_payload_reserve(key, key->datalen + plen); + if (ret < 0) + return ret; + + plen -= sizeof(*token); + token = kmalloc(sizeof(*token), GFP_KERNEL); + if (!token) + return -ENOMEM; + + token->kad = kmalloc(plen, GFP_KERNEL); + if (!token->kad) { + kfree(token); + return -ENOMEM; + } + + token->security_index = RXRPC_SECURITY_RXKAD; + token->kad->ticket_len = tktlen; + token->kad->vice_id = ntohl(xdr[0]); + token->kad->kvno = ntohl(xdr[1]); + token->kad->start = ntohl(xdr[4]); + token->kad->expiry = ntohl(xdr[5]); + token->kad->primary_flag = ntohl(xdr[6]); + memcpy(&token->kad->session_key, &xdr[2], 8); + memcpy(&token->kad->ticket, &xdr[8], tktlen); + + _debug("SCIX: %u", token->security_index); + _debug("TLEN: %u", token->kad->ticket_len); + _debug("EXPY: %x", token->kad->expiry); + _debug("KVNO: %u", token->kad->kvno); + _debug("PRIM: %u", token->kad->primary_flag); + _debug("SKEY: %02x%02x%02x%02x%02x%02x%02x%02x", + token->kad->session_key[0], token->kad->session_key[1], + token->kad->session_key[2], token->kad->session_key[3], + token->kad->session_key[4], token->kad->session_key[5], + token->kad->session_key[6], token->kad->session_key[7]); + if (token->kad->ticket_len >= 8) + _debug("TCKT: %02x%02x%02x%02x%02x%02x%02x%02x", + token->kad->ticket[0], token->kad->ticket[1], + token->kad->ticket[2], token->kad->ticket[3], + token->kad->ticket[4], token->kad->ticket[5], + token->kad->ticket[6], token->kad->ticket[7]); + + /* count the number of tokens attached */ + key->type_data.x[0]++; + + /* attach the data */ + for (pptoken = (struct rxrpc_key_token **)&key->payload.data; + *pptoken; + pptoken = &(*pptoken)->next) + continue; + *pptoken = token; + if (token->kad->expiry < key->expiry) + key->expiry = token->kad->expiry; + + _leave(" = 0"); + return 0; +} + +static void rxrpc_free_krb5_principal(struct krb5_principal *princ) +{ + int loop; + + if (princ->name_parts) { + for (loop = princ->n_name_parts - 1; loop >= 0; loop--) + kfree(princ->name_parts[loop]); + kfree(princ->name_parts); + } + kfree(princ->realm); +} + +static void rxrpc_free_krb5_tagged(struct krb5_tagged_data *td) +{ + kfree(td->data); +} + +/* + * free up an RxK5 token + */ +static void rxrpc_rxk5_free(struct rxk5_key *rxk5) +{ + int loop; + + rxrpc_free_krb5_principal(&rxk5->client); + rxrpc_free_krb5_principal(&rxk5->server); + rxrpc_free_krb5_tagged(&rxk5->session); + + if (rxk5->addresses) { + for (loop = rxk5->n_addresses - 1; loop >= 0; loop--) + rxrpc_free_krb5_tagged(&rxk5->addresses[loop]); + kfree(rxk5->addresses); + } + if (rxk5->authdata) { + for (loop = rxk5->n_authdata - 1; loop >= 0; loop--) + rxrpc_free_krb5_tagged(&rxk5->authdata[loop]); + kfree(rxk5->authdata); + } + + kfree(rxk5->ticket); + kfree(rxk5->ticket2); + kfree(rxk5); +} + +/* + * extract a krb5 principal + */ +static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, + const __be32 **_xdr, + unsigned *_toklen) +{ + const __be32 *xdr = *_xdr; + unsigned toklen = *_toklen, n_parts, loop, tmp; + + /* there must be at least one name, and at least #names+1 length + * words */ + if (toklen <= 12) + return -EINVAL; + + _enter(",{%x,%x,%x},%u", + ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), toklen); + + n_parts = ntohl(*xdr++); + toklen -= 4; + if (n_parts <= 0 || n_parts > AFSTOKEN_K5_COMPONENTS_MAX) + return -EINVAL; + princ->n_name_parts = n_parts; + + if (toklen <= (n_parts + 1) * 4) + return -EINVAL; + + princ->name_parts = kcalloc(sizeof(char *), n_parts, GFP_KERNEL); + if (!princ->name_parts) + return -ENOMEM; + + for (loop = 0; loop < n_parts; loop++) { + if (toklen < 4) + return -EINVAL; + tmp = ntohl(*xdr++); + toklen -= 4; + if (tmp <= 0 || tmp > AFSTOKEN_STRING_MAX) + return -EINVAL; + if (tmp > toklen) + return -EINVAL; + princ->name_parts[loop] = kmalloc(tmp + 1, GFP_KERNEL); + if (!princ->name_parts[loop]) + return -ENOMEM; + memcpy(princ->name_parts[loop], xdr, tmp); + princ->name_parts[loop][tmp] = 0; + tmp = (tmp + 3) & ~3; + toklen -= tmp; + xdr += tmp >> 2; + } + + if (toklen < 4) + return -EINVAL; + tmp = ntohl(*xdr++); + toklen -= 4; + if (tmp <= 0 || tmp > AFSTOKEN_K5_REALM_MAX) + return -EINVAL; + if (tmp > toklen) + return -EINVAL; + princ->realm = kmalloc(tmp + 1, GFP_KERNEL); + if (!princ->realm) + return -ENOMEM; + memcpy(princ->realm, xdr, tmp); + princ->realm[tmp] = 0; + tmp = (tmp + 3) & ~3; + toklen -= tmp; + xdr += tmp >> 2; + + _debug("%s/...@%s", princ->name_parts[0], princ->realm); + + *_xdr = xdr; + *_toklen = toklen; + _leave(" = 0 [toklen=%u]", toklen); + return 0; +} + +/* + * extract a piece of krb5 tagged data + */ +static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td, + size_t max_data_size, + const __be32 **_xdr, + unsigned *_toklen) +{ + const __be32 *xdr = *_xdr; + unsigned toklen = *_toklen, len; + + /* there must be at least one tag and one length word */ + if (toklen <= 8) + return -EINVAL; + + _enter(",%zu,{%x,%x},%u", + max_data_size, ntohl(xdr[0]), ntohl(xdr[1]), toklen); + + td->tag = ntohl(*xdr++); + len = ntohl(*xdr++); + toklen -= 8; + if (len > max_data_size) + return -EINVAL; + td->data_len = len; + + if (len > 0) { + td->data = kmalloc(len, GFP_KERNEL); + if (!td->data) + return -ENOMEM; + memcpy(td->data, xdr, len); + len = (len + 3) & ~3; + toklen -= len; + xdr += len >> 2; + } + + _debug("tag %x len %x", td->tag, td->data_len); + + *_xdr = xdr; + *_toklen = toklen; + _leave(" = 0 [toklen=%u]", toklen); + return 0; +} + +/* + * extract an array of tagged data + */ +static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td, + u8 *_n_elem, + u8 max_n_elem, + size_t max_elem_size, + const __be32 **_xdr, + unsigned *_toklen) +{ + struct krb5_tagged_data *td; + const __be32 *xdr = *_xdr; + unsigned toklen = *_toklen, n_elem, loop; + int ret; + + /* there must be at least one count */ + if (toklen < 4) + return -EINVAL; + + _enter(",,%u,%zu,{%x},%u", + max_n_elem, max_elem_size, ntohl(xdr[0]), toklen); + + n_elem = ntohl(*xdr++); + toklen -= 4; + if (n_elem < 0 || n_elem > max_n_elem) + return -EINVAL; + *_n_elem = n_elem; + if (n_elem > 0) { + if (toklen <= (n_elem + 1) * 4) + return -EINVAL; + + _debug("n_elem %d", n_elem); + + td = kcalloc(sizeof(struct krb5_tagged_data), n_elem, + GFP_KERNEL); + if (!td) + return -ENOMEM; + *_td = td; + + for (loop = 0; loop < n_elem; loop++) { + ret = rxrpc_krb5_decode_tagged_data(&td[loop], + max_elem_size, + &xdr, &toklen); + if (ret < 0) + return ret; + } + } + + *_xdr = xdr; + *_toklen = toklen; + _leave(" = 0 [toklen=%u]", toklen); + return 0; +} + +/* + * extract a krb5 ticket + */ +static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, + const __be32 **_xdr, unsigned *_toklen) +{ + const __be32 *xdr = *_xdr; + unsigned toklen = *_toklen, len; + + /* there must be at least one length word */ + if (toklen <= 4) + return -EINVAL; + + _enter(",{%x},%u", ntohl(xdr[0]), toklen); + + len = ntohl(*xdr++); + toklen -= 4; + if (len > AFSTOKEN_K5_TIX_MAX) + return -EINVAL; + *_tktlen = len; + + _debug("ticket len %u", len); + + if (len > 0) { + *_ticket = kmalloc(len, GFP_KERNEL); + if (!*_ticket) + return -ENOMEM; + memcpy(*_ticket, xdr, len); + len = (len + 3) & ~3; + toklen -= len; + xdr += len >> 2; + } + + *_xdr = xdr; + *_toklen = toklen; + _leave(" = 0 [toklen=%u]", toklen); + return 0; +} + +/* + * parse an RxK5 type XDR format token + * - the caller guarantees we have at least 4 words + */ +static int rxrpc_instantiate_xdr_rxk5(struct key *key, const __be32 *xdr, + unsigned toklen) +{ + struct rxrpc_key_token *token, **pptoken; + struct rxk5_key *rxk5; + const __be32 *end_xdr = xdr + (toklen >> 2); + int ret; + + _enter(",{%x,%x,%x,%x},%u", + ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]), + toklen); + + /* reserve some payload space for this subkey - the length of the token + * is a reasonable approximation */ + ret = key_payload_reserve(key, key->datalen + toklen); + if (ret < 0) + return ret; + + token = kzalloc(sizeof(*token), GFP_KERNEL); + if (!token) + return -ENOMEM; + + rxk5 = kzalloc(sizeof(*rxk5), GFP_KERNEL); + if (!rxk5) { + kfree(token); + return -ENOMEM; + } + + token->security_index = RXRPC_SECURITY_RXK5; + token->k5 = rxk5; + + /* extract the principals */ + ret = rxrpc_krb5_decode_principal(&rxk5->client, &xdr, &toklen); + if (ret < 0) + goto error; + ret = rxrpc_krb5_decode_principal(&rxk5->server, &xdr, &toklen); + if (ret < 0) + goto error; + + /* extract the session key and the encoding type (the tag field -> + * ENCTYPE_xxx) */ + ret = rxrpc_krb5_decode_tagged_data(&rxk5->session, AFSTOKEN_DATA_MAX, + &xdr, &toklen); + if (ret < 0) + goto error; + + if (toklen < 4 * 8 + 2 * 4) + goto inval; + rxk5->authtime = be64_to_cpup((const __be64 *) xdr); + xdr += 2; + rxk5->starttime = be64_to_cpup((const __be64 *) xdr); + xdr += 2; + rxk5->endtime = be64_to_cpup((const __be64 *) xdr); + xdr += 2; + rxk5->renew_till = be64_to_cpup((const __be64 *) xdr); + xdr += 2; + rxk5->is_skey = ntohl(*xdr++); + rxk5->flags = ntohl(*xdr++); + toklen -= 4 * 8 + 2 * 4; + + _debug("times: a=%llx s=%llx e=%llx rt=%llx", + rxk5->authtime, rxk5->starttime, rxk5->endtime, + rxk5->renew_till); + _debug("is_skey=%x flags=%x", rxk5->is_skey, rxk5->flags); + + /* extract the permitted client addresses */ + ret = rxrpc_krb5_decode_tagged_array(&rxk5->addresses, + &rxk5->n_addresses, + AFSTOKEN_K5_ADDRESSES_MAX, + AFSTOKEN_DATA_MAX, + &xdr, &toklen); + if (ret < 0) + goto error; + + ASSERTCMP((end_xdr - xdr) << 2, ==, toklen); + + /* extract the tickets */ + ret = rxrpc_krb5_decode_ticket(&rxk5->ticket, &rxk5->ticket_len, + &xdr, &toklen); + if (ret < 0) + goto error; + ret = rxrpc_krb5_decode_ticket(&rxk5->ticket2, &rxk5->ticket2_len, + &xdr, &toklen); + if (ret < 0) + goto error; + + ASSERTCMP((end_xdr - xdr) << 2, ==, toklen); + + /* extract the typed auth data */ + ret = rxrpc_krb5_decode_tagged_array(&rxk5->authdata, + &rxk5->n_authdata, + AFSTOKEN_K5_AUTHDATA_MAX, + AFSTOKEN_BDATALN_MAX, + &xdr, &toklen); + if (ret < 0) + goto error; + + ASSERTCMP((end_xdr - xdr) << 2, ==, toklen); + + if (toklen != 0) + goto inval; + + /* attach the payload to the key */ + for (pptoken = (struct rxrpc_key_token **)&key->payload.data; + *pptoken; + pptoken = &(*pptoken)->next) + continue; + *pptoken = token; + if (token->kad->expiry < key->expiry) + key->expiry = token->kad->expiry; + + _leave(" = 0"); + return 0; + +inval: + ret = -EINVAL; +error: + rxrpc_rxk5_free(rxk5); + kfree(token); + _leave(" = %d", ret); + return ret; +} + +/* + * attempt to parse the data as the XDR format + * - the caller guarantees we have more than 7 words + */ +static int rxrpc_instantiate_xdr(struct key *key, const void *data, size_t datalen) +{ + const __be32 *xdr = data, *token; + const char *cp; + unsigned len, tmp, loop, ntoken, toklen, sec_ix; + int ret; + + _enter(",{%x,%x,%x,%x},%zu", + ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]), + datalen); + + if (datalen > AFSTOKEN_LENGTH_MAX) + goto not_xdr; + + /* XDR is an array of __be32's */ + if (datalen & 3) + goto not_xdr; + + /* the flags should be 0 (the setpag bit must be handled by + * userspace) */ + if (ntohl(*xdr++) != 0) + goto not_xdr; + datalen -= 4; + + /* check the cell name */ + len = ntohl(*xdr++); + if (len < 1 || len > AFSTOKEN_CELL_MAX) + goto not_xdr; + datalen -= 4; + tmp = (len + 3) & ~3; + if (tmp > datalen) + goto not_xdr; + + cp = (const char *) xdr; + for (loop = 0; loop < len; loop++) + if (!isprint(cp[loop])) + goto not_xdr; + if (len < tmp) + for (; loop < tmp; loop++) + if (cp[loop]) + goto not_xdr; + _debug("cellname: [%u/%u] '%*.*s'", + len, tmp, len, len, (const char *) xdr); + datalen -= tmp; + xdr += tmp >> 2; + + /* get the token count */ + if (datalen < 12) + goto not_xdr; + ntoken = ntohl(*xdr++); + datalen -= 4; + _debug("ntoken: %x", ntoken); + if (ntoken < 1 || ntoken > AFSTOKEN_MAX) + goto not_xdr; + + /* check each token wrapper */ + token = xdr; + loop = ntoken; + do { + if (datalen < 8) + goto not_xdr; + toklen = ntohl(*xdr++); + sec_ix = ntohl(*xdr); + datalen -= 4; + _debug("token: [%x/%zx] %x", toklen, datalen, sec_ix); + if (toklen < 20 || toklen > datalen) + goto not_xdr; + datalen -= (toklen + 3) & ~3; + xdr += (toklen + 3) >> 2; + + } while (--loop > 0); + + _debug("remainder: %zu", datalen); + if (datalen != 0) + goto not_xdr; + + /* okay: we're going to assume it's valid XDR format + * - we ignore the cellname, relying on the key to be correctly named + */ + do { + xdr = token; + toklen = ntohl(*xdr++); + token = xdr + ((toklen + 3) >> 2); + sec_ix = ntohl(*xdr++); + toklen -= 4; + + _debug("TOKEN type=%u [%p-%p]", sec_ix, xdr, token); + + switch (sec_ix) { + case RXRPC_SECURITY_RXKAD: + ret = rxrpc_instantiate_xdr_rxkad(key, xdr, toklen); + if (ret != 0) + goto error; + break; + + case RXRPC_SECURITY_RXK5: + ret = rxrpc_instantiate_xdr_rxk5(key, xdr, toklen); + if (ret != 0) + goto error; + break; + + default: + ret = -EPROTONOSUPPORT; + goto error; + } + + } while (--ntoken > 0); + + _leave(" = 0"); + return 0; + +not_xdr: + _leave(" = -EPROTO"); + return -EPROTO; +error: + _leave(" = %d", ret); + return ret; +} + +/* * instantiate an rxrpc defined key * data should be of the form: * OFFSET LEN CONTENT @@ -70,8 +662,8 @@ struct key_type key_type_rxrpc_s = { */ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen) { - const struct rxkad_key *tsec; - struct rxrpc_key_payload *upayload; + const struct rxrpc_key_data_v1 *v1; + struct rxrpc_key_token *token, **pp; size_t plen; u32 kver; int ret; @@ -82,6 +674,13 @@ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen) if (!data && datalen == 0) return 0; + /* determine if the XDR payload format is being used */ + if (datalen > 7 * 4) { + ret = rxrpc_instantiate_xdr(key, data, datalen); + if (ret != -EPROTO) + return ret; + } + /* get the key interface version number */ ret = -EINVAL; if (datalen <= 4 || !data) @@ -98,53 +697,67 @@ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen) /* deal with a version 1 key */ ret = -EINVAL; - if (datalen < sizeof(*tsec)) + if (datalen < sizeof(*v1)) goto error; - tsec = data; - if (datalen != sizeof(*tsec) + tsec->ticket_len) + v1 = data; + if (datalen != sizeof(*v1) + v1->ticket_length) goto error; - _debug("SCIX: %u", tsec->security_index); - _debug("TLEN: %u", tsec->ticket_len); - _debug("EXPY: %x", tsec->expiry); - _debug("KVNO: %u", tsec->kvno); + _debug("SCIX: %u", v1->security_index); + _debug("TLEN: %u", v1->ticket_length); + _debug("EXPY: %x", v1->expiry); + _debug("KVNO: %u", v1->kvno); _debug("SKEY: %02x%02x%02x%02x%02x%02x%02x%02x", - tsec->session_key[0], tsec->session_key[1], - tsec->session_key[2], tsec->session_key[3], - tsec->session_key[4], tsec->session_key[5], - tsec->session_key[6], tsec->session_key[7]); - if (tsec->ticket_len >= 8) + v1->session_key[0], v1->session_key[1], + v1->session_key[2], v1->session_key[3], + v1->session_key[4], v1->session_key[5], + v1->session_key[6], v1->session_key[7]); + if (v1->ticket_length >= 8) _debug("TCKT: %02x%02x%02x%02x%02x%02x%02x%02x", - tsec->ticket[0], tsec->ticket[1], - tsec->ticket[2], tsec->ticket[3], - tsec->ticket[4], tsec->ticket[5], - tsec->ticket[6], tsec->ticket[7]); + v1->ticket[0], v1->ticket[1], + v1->ticket[2], v1->ticket[3], + v1->ticket[4], v1->ticket[5], + v1->ticket[6], v1->ticket[7]); ret = -EPROTONOSUPPORT; - if (tsec->security_index != 2) + if (v1->security_index != RXRPC_SECURITY_RXKAD) goto error; - key->type_data.x[0] = tsec->security_index; - - plen = sizeof(*upayload) + tsec->ticket_len; - ret = key_payload_reserve(key, plen); + plen = sizeof(*token->kad) + v1->ticket_length; + ret = key_payload_reserve(key, plen + sizeof(*token)); if (ret < 0) goto error; ret = -ENOMEM; - upayload = kmalloc(plen, GFP_KERNEL); - if (!upayload) + token = kmalloc(sizeof(*token), GFP_KERNEL); + if (!token) goto error; + token->kad = kmalloc(plen, GFP_KERNEL); + if (!token->kad) + goto error_free; + + token->security_index = RXRPC_SECURITY_RXKAD; + token->kad->ticket_len = v1->ticket_length; + token->kad->expiry = v1->expiry; + token->kad->kvno = v1->kvno; + memcpy(&token->kad->session_key, &v1->session_key, 8); + memcpy(&token->kad->ticket, v1->ticket, v1->ticket_length); /* attach the data */ - memcpy(&upayload->k, tsec, sizeof(*tsec)); - memcpy(&upayload->k.ticket, (void *)tsec + sizeof(*tsec), - tsec->ticket_len); - key->payload.data = upayload; - key->expiry = tsec->expiry; + key->type_data.x[0]++; + + pp = (struct rxrpc_key_token **)&key->payload.data; + while (*pp) + pp = &(*pp)->next; + *pp = token; + if (token->kad->expiry < key->expiry) + key->expiry = token->kad->expiry; + token = NULL; ret = 0; +error_free: + kfree(token); error: return ret; } @@ -184,7 +797,26 @@ static int rxrpc_instantiate_s(struct key *key, const void *data, */ static void rxrpc_destroy(struct key *key) { - kfree(key->payload.data); + struct rxrpc_key_token *token; + + while ((token = key->payload.data)) { + key->payload.data = token->next; + switch (token->security_index) { + case RXRPC_SECURITY_RXKAD: + kfree(token->kad); + break; + case RXRPC_SECURITY_RXK5: + if (token->k5) + rxrpc_rxk5_free(token->k5); + break; + default: + printk(KERN_ERR "Unknown token type %x on rxrpc key\n", + token->security_index); + BUG(); + } + + kfree(token); + } } /* @@ -293,7 +925,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *conn, struct { u32 kver; - struct rxkad_key tsec; + struct rxrpc_key_data_v1 v1; } data; _enter(""); @@ -308,13 +940,12 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *conn, _debug("key %d", key_serial(key)); data.kver = 1; - data.tsec.security_index = 2; - data.tsec.ticket_len = 0; - data.tsec.expiry = expiry; - data.tsec.kvno = 0; + data.v1.security_index = RXRPC_SECURITY_RXKAD; + data.v1.ticket_length = 0; + data.v1.expiry = expiry; + data.v1.kvno = 0; - memcpy(&data.tsec.session_key, session_key, - sizeof(data.tsec.session_key)); + memcpy(&data.v1.session_key, session_key, sizeof(data.v1.session_key)); ret = key_instantiate_and_link(key, &data, sizeof(data), NULL, NULL); if (ret < 0) @@ -360,3 +991,210 @@ struct key *rxrpc_get_null_key(const char *keyname) return key; } EXPORT_SYMBOL(rxrpc_get_null_key); + +/* + * read the contents of an rxrpc key + * - this returns the result in XDR form + */ +static long rxrpc_read(const struct key *key, + char __user *buffer, size_t buflen) +{ + const struct rxrpc_key_token *token; + const struct krb5_principal *princ; + size_t size; + __be32 __user *xdr, *oldxdr; + u32 cnlen, toksize, ntoks, tok, zero; + u16 toksizes[AFSTOKEN_MAX]; + int loop; + + _enter(""); + + /* we don't know what form we should return non-AFS keys in */ + if (memcmp(key->description, "afs@", 4) != 0) + return -EOPNOTSUPP; + cnlen = strlen(key->description + 4); + +#define RND(X) (((X) + 3) & ~3) + + /* AFS keys we return in XDR form, so we need to work out the size of + * the XDR */ + size = 2 * 4; /* flags, cellname len */ + size += RND(cnlen); /* cellname */ + size += 1 * 4; /* token count */ + + ntoks = 0; + for (token = key->payload.data; token; token = token->next) { + toksize = 4; /* sec index */ + + switch (token->security_index) { + case RXRPC_SECURITY_RXKAD: + toksize += 8 * 4; /* viceid, kvno, key*2, begin, + * end, primary, tktlen */ + toksize += RND(token->kad->ticket_len); + break; + + case RXRPC_SECURITY_RXK5: + princ = &token->k5->client; + toksize += 4 + princ->n_name_parts * 4; + for (loop = 0; loop < princ->n_name_parts; loop++) + toksize += RND(strlen(princ->name_parts[loop])); + toksize += 4 + RND(strlen(princ->realm)); + + princ = &token->k5->server; + toksize += 4 + princ->n_name_parts * 4; + for (loop = 0; loop < princ->n_name_parts; loop++) + toksize += RND(strlen(princ->name_parts[loop])); + toksize += 4 + RND(strlen(princ->realm)); + + toksize += 8 + RND(token->k5->session.data_len); + + toksize += 4 * 8 + 2 * 4; + + toksize += 4 + token->k5->n_addresses * 8; + for (loop = 0; loop < token->k5->n_addresses; loop++) + toksize += RND(token->k5->addresses[loop].data_len); + + toksize += 4 + RND(token->k5->ticket_len); + toksize += 4 + RND(token->k5->ticket2_len); + + toksize += 4 + token->k5->n_authdata * 8; + for (loop = 0; loop < token->k5->n_authdata; loop++) + toksize += RND(token->k5->authdata[loop].data_len); + break; + + default: /* we have a ticket we can't encode */ + BUG(); + continue; + } + + _debug("token[%u]: toksize=%u", ntoks, toksize); + ASSERTCMP(toksize, <=, AFSTOKEN_LENGTH_MAX); + + toksizes[ntoks++] = toksize; + size += toksize + 4; /* each token has a length word */ + } + +#undef RND + + if (!buffer || buflen < size) + return size; + + xdr = (__be32 __user *) buffer; + zero = 0; +#define ENCODE(x) \ + do { \ + __be32 y = htonl(x); \ + if (put_user(y, xdr++) < 0) \ + goto fault; \ + } while(0) +#define ENCODE_DATA(l, s) \ + do { \ + u32 _l = (l); \ + ENCODE(l); \ + if (copy_to_user(xdr, (s), _l) != 0) \ + goto fault; \ + if (_l & 3 && \ + copy_to_user((u8 *)xdr + _l, &zero, 4 - (_l & 3)) != 0) \ + goto fault; \ + xdr += (_l + 3) >> 2; \ + } while(0) +#define ENCODE64(x) \ + do { \ + __be64 y = cpu_to_be64(x); \ + if (copy_to_user(xdr, &y, 8) != 0) \ + goto fault; \ + xdr += 8 >> 2; \ + } while(0) +#define ENCODE_STR(s) \ + do { \ + const char *_s = (s); \ + ENCODE_DATA(strlen(_s), _s); \ + } while(0) + + ENCODE(0); /* flags */ + ENCODE_DATA(cnlen, key->description + 4); /* cellname */ + ENCODE(ntoks); + + tok = 0; + for (token = key->payload.data; token; token = token->next) { + toksize = toksizes[tok++]; + ENCODE(toksize); + oldxdr = xdr; + ENCODE(token->security_index); + + switch (token->security_index) { + case RXRPC_SECURITY_RXKAD: + ENCODE(token->kad->vice_id); + ENCODE(token->kad->kvno); + ENCODE_DATA(8, token->kad->session_key); + ENCODE(token->kad->start); + ENCODE(token->kad->expiry); + ENCODE(token->kad->primary_flag); + ENCODE_DATA(token->kad->ticket_len, token->kad->ticket); + break; + + case RXRPC_SECURITY_RXK5: + princ = &token->k5->client; + ENCODE(princ->n_name_parts); + for (loop = 0; loop < princ->n_name_parts; loop++) + ENCODE_STR(princ->name_parts[loop]); + ENCODE_STR(princ->realm); + + princ = &token->k5->server; + ENCODE(princ->n_name_parts); + for (loop = 0; loop < princ->n_name_parts; loop++) + ENCODE_STR(princ->name_parts[loop]); + ENCODE_STR(princ->realm); + + ENCODE(token->k5->session.tag); + ENCODE_DATA(token->k5->session.data_len, + token->k5->session.data); + + ENCODE64(token->k5->authtime); + ENCODE64(token->k5->starttime); + ENCODE64(token->k5->endtime); + ENCODE64(token->k5->renew_till); + ENCODE(token->k5->is_skey); + ENCODE(token->k5->flags); + + ENCODE(token->k5->n_addresses); + for (loop = 0; loop < token->k5->n_addresses; loop++) { + ENCODE(token->k5->addresses[loop].tag); + ENCODE_DATA(token->k5->addresses[loop].data_len, + token->k5->addresses[loop].data); + } + + ENCODE_DATA(token->k5->ticket_len, token->k5->ticket); + ENCODE_DATA(token->k5->ticket2_len, token->k5->ticket2); + + ENCODE(token->k5->n_authdata); + for (loop = 0; loop < token->k5->n_authdata; loop++) { + ENCODE(token->k5->authdata[loop].tag); + ENCODE_DATA(token->k5->authdata[loop].data_len, + token->k5->authdata[loop].data); + } + break; + + default: + BUG(); + break; + } + + ASSERTCMP((unsigned long)xdr - (unsigned long)oldxdr, ==, + toksize); + } + +#undef ENCODE_STR +#undef ENCODE_DATA +#undef ENCODE64 +#undef ENCODE + + ASSERTCMP(tok, ==, ntoks); + ASSERTCMP((char __user *) xdr - buffer, ==, size); + _leave(" = %zu", size); + return size; + +fault: + _leave(" = -EFAULT"); + return -EFAULT; +} diff --git a/net/rxrpc/ar-security.c b/net/rxrpc/ar-security.c index dc62920ee19..49b3cc31ee1 100644 --- a/net/rxrpc/ar-security.c +++ b/net/rxrpc/ar-security.c @@ -16,6 +16,7 @@ #include <linux/crypto.h> #include <net/sock.h> #include <net/af_rxrpc.h> +#include <keys/rxrpc-type.h> #include "ar-internal.h" static LIST_HEAD(rxrpc_security_methods); @@ -122,6 +123,7 @@ EXPORT_SYMBOL_GPL(rxrpc_unregister_security); */ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) { + struct rxrpc_key_token *token; struct rxrpc_security *sec; struct key *key = conn->key; int ret; @@ -135,7 +137,11 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) if (ret < 0) return ret; - sec = rxrpc_security_lookup(key->type_data.x[0]); + if (!key->payload.data) + return -EKEYREJECTED; + token = key->payload.data; + + sec = rxrpc_security_lookup(token->security_index); if (!sec) return -EKEYREJECTED; conn->security = sec; diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index ef8f91030a1..713ac593e2e 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -18,6 +18,7 @@ #include <linux/ctype.h> #include <net/sock.h> #include <net/af_rxrpc.h> +#include <keys/rxrpc-type.h> #define rxrpc_debug rxkad_debug #include "ar-internal.h" @@ -42,7 +43,7 @@ struct rxkad_level2_hdr { __be32 checksum; /* decrypted data checksum */ }; -MODULE_DESCRIPTION("RxRPC network protocol type-2 security (Kerberos)"); +MODULE_DESCRIPTION("RxRPC network protocol type-2 security (Kerberos 4)"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); @@ -59,14 +60,14 @@ static DEFINE_MUTEX(rxkad_ci_mutex); */ static int rxkad_init_connection_security(struct rxrpc_connection *conn) { - struct rxrpc_key_payload *payload; struct crypto_blkcipher *ci; + struct rxrpc_key_token *token; int ret; _enter("{%d},{%x}", conn->debug_id, key_serial(conn->key)); - payload = conn->key->payload.data; - conn->security_ix = payload->k.security_index; + token = conn->key->payload.data; + conn->security_ix = token->security_index; ci = crypto_alloc_blkcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(ci)) { @@ -75,8 +76,8 @@ static int rxkad_init_connection_security(struct rxrpc_connection *conn) goto error; } - if (crypto_blkcipher_setkey(ci, payload->k.session_key, - sizeof(payload->k.session_key)) < 0) + if (crypto_blkcipher_setkey(ci, token->kad->session_key, + sizeof(token->kad->session_key)) < 0) BUG(); switch (conn->security_level) { @@ -110,7 +111,7 @@ error: */ static void rxkad_prime_packet_security(struct rxrpc_connection *conn) { - struct rxrpc_key_payload *payload; + struct rxrpc_key_token *token; struct blkcipher_desc desc; struct scatterlist sg[2]; struct rxrpc_crypt iv; @@ -123,8 +124,8 @@ static void rxkad_prime_packet_security(struct rxrpc_connection *conn) if (!conn->key) return; - payload = conn->key->payload.data; - memcpy(&iv, payload->k.session_key, sizeof(iv)); + token = conn->key->payload.data; + memcpy(&iv, token->kad->session_key, sizeof(iv)); desc.tfm = conn->cipher; desc.info = iv.x; @@ -197,7 +198,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, u32 data_size, void *sechdr) { - const struct rxrpc_key_payload *payload; + const struct rxrpc_key_token *token; struct rxkad_level2_hdr rxkhdr __attribute__((aligned(8))); /* must be all on one page */ struct rxrpc_skb_priv *sp; @@ -219,8 +220,8 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, rxkhdr.checksum = 0; /* encrypt from the session key */ - payload = call->conn->key->payload.data; - memcpy(&iv, payload->k.session_key, sizeof(iv)); + token = call->conn->key->payload.data; + memcpy(&iv, token->kad->session_key, sizeof(iv)); desc.tfm = call->conn->cipher; desc.info = iv.x; desc.flags = 0; @@ -400,7 +401,7 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call, struct sk_buff *skb, u32 *_abort_code) { - const struct rxrpc_key_payload *payload; + const struct rxrpc_key_token *token; struct rxkad_level2_hdr sechdr; struct rxrpc_skb_priv *sp; struct blkcipher_desc desc; @@ -431,8 +432,8 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call, skb_to_sgvec(skb, sg, 0, skb->len); /* decrypt from the session key */ - payload = call->conn->key->payload.data; - memcpy(&iv, payload->k.session_key, sizeof(iv)); + token = call->conn->key->payload.data; + memcpy(&iv, token->kad->session_key, sizeof(iv)); desc.tfm = call->conn->cipher; desc.info = iv.x; desc.flags = 0; @@ -506,7 +507,7 @@ static int rxkad_verify_packet(const struct rxrpc_call *call, if (!call->conn->cipher) return 0; - if (sp->hdr.securityIndex != 2) { + if (sp->hdr.securityIndex != RXRPC_SECURITY_RXKAD) { *_abort_code = RXKADINCONSISTENCY; _leave(" = -EPROTO [not rxkad]"); return -EPROTO; @@ -737,7 +738,7 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, struct sk_buff *skb, u32 *_abort_code) { - const struct rxrpc_key_payload *payload; + const struct rxrpc_key_token *token; struct rxkad_challenge challenge; struct rxkad_response resp __attribute__((aligned(8))); /* must be aligned for crypto */ @@ -778,7 +779,7 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, if (conn->security_level < min_level) goto protocol_error; - payload = conn->key->payload.data; + token = conn->key->payload.data; /* build the response packet */ memset(&resp, 0, sizeof(resp)); @@ -797,13 +798,13 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, (conn->channels[3] ? conn->channels[3]->call_id : 0); resp.encrypted.inc_nonce = htonl(nonce + 1); resp.encrypted.level = htonl(conn->security_level); - resp.kvno = htonl(payload->k.kvno); - resp.ticket_len = htonl(payload->k.ticket_len); + resp.kvno = htonl(token->kad->kvno); + resp.ticket_len = htonl(token->kad->ticket_len); /* calculate the response checksum and then do the encryption */ rxkad_calc_response_checksum(&resp); - rxkad_encrypt_response(conn, &resp, &payload->k); - return rxkad_send_response(conn, &sp->hdr, &resp, &payload->k); + rxkad_encrypt_response(conn, &resp, token->kad); + return rxkad_send_response(conn, &sp->hdr, &resp, token->kad); protocol_error: *_abort_code = abort_code; @@ -1122,7 +1123,7 @@ static void rxkad_clear(struct rxrpc_connection *conn) static struct rxrpc_security rxkad = { .owner = THIS_MODULE, .name = "rxkad", - .security_index = RXKAD_VERSION, + .security_index = RXRPC_SECURITY_RXKAD, .init_connection_security = rxkad_init_connection_security, .prime_packet_security = rxkad_prime_packet_security, .secure_packet = rxkad_secure_packet, diff --git a/net/sched/Makefile b/net/sched/Makefile index 54d950cd4b8..f14e71bfa58 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/act_api.c b/net/sched/act_api.c index 9d03cc33b6c..2dfb3e7a040 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1011,7 +1011,7 @@ replay: } static struct nlattr * -find_dump_kind(struct nlmsghdr *n) +find_dump_kind(const struct nlmsghdr *n) { struct nlattr *tb1, *tb2[TCA_ACT_MAX+1]; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 96c0ed115e2..6b0359a500e 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -34,7 +34,7 @@ static struct tcf_hashinfo pedit_hash_info = { }; static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { - [TCA_PEDIT_PARMS] = { .len = sizeof(struct tcf_pedit) }, + [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, }; static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 09cdcdfe7e9..7cf6c0fbc7a 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); @@ -348,7 +350,7 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, tcm = NLMSG_DATA(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; - tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; tcm->tcm_parent = tp->classid; tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); @@ -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 fdb694e9f75..903e4188b6c 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; @@ -720,6 +693,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (new && i > 0) atomic_inc(&new->refcnt); + if (!ingress) + qdisc_destroy(old); + } + + if (!ingress) { + notify_and_destroy(skb, n, classid, dev->qdisc, new); + if (new && !new->ops->attach) + atomic_inc(&new->refcnt); + dev->qdisc = new ? : &noop_qdisc; + } else { notify_and_destroy(skb, n, classid, old, new); } @@ -728,14 +711,14 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, } 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 +738,8 @@ 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]; @@ -825,31 +809,28 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, stab = qdisc_get_stab(tca[TCA_STAB]); if (IS_ERR(stab)) { err = PTR_ERR(stab); - goto err_out3; + goto err_out4; } sch->stab = stab; } 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); @@ -857,7 +838,6 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, return sch; } err_out3: - qdisc_put_stab(sch->stab); dev_put(dev); kfree((char *) sch - sch->padded); err_out2: @@ -865,6 +845,16 @@ 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. + */ + qdisc_put_stab(sch->stab); + if (ops->destroy) + ops->destroy(sch); + goto err_out3; } static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) @@ -889,13 +879,16 @@ 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 +967,7 @@ 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 +1035,7 @@ 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 +1112,23 @@ 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 { + struct netdev_queue *dev_queue; + + if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue) + dev_queue = p->ops->cl_ops->select_queue(p, tcm); + else if (p) + dev_queue = p->dev_queue; + else + dev_queue = netdev_get_tx_queue(dev, 0); + + q = qdisc_create(dev, dev_queue, p, tcm->tcm_parent, tcm->tcm_handle, tca, &err); + } if (q == NULL) { if (err == -EAGAIN) goto replay; @@ -1291,8 +1290,7 @@ 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 +1321,6 @@ 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 +1358,6 @@ 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 +1368,7 @@ 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 +1379,7 @@ 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 +1413,9 @@ 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 +1429,9 @@ 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); @@ -1586,8 +1586,7 @@ 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; @@ -1707,6 +1706,7 @@ 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_cbq.c b/net/sched/sch_cbq.c index d5798e17a83..5b132c47326 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -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 12b2fb04b29..5a888af7e5d 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -274,8 +274,10 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct tc_drr_stats xstats; memset(&xstats, 0, sizeof(xstats)); - if (cl->qdisc->q.qlen) + if (cl->qdisc->q.qlen) { xstats.deficit = cl->deficit; + cl->qdisc->qstats.qlen = cl->qdisc->q.qlen; + } if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 27d03816ec3..4ae6aa562f2 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -37,15 +37,11 @@ * - updates to tree and tree walking are only done under the rtnl mutex. */ -static inline int qdisc_qlen(struct Qdisc *q) -{ - return q->q.qlen; -} - static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) { q->gso_skb = skb; q->qstats.requeues++; + q->q.qlen++; /* it's still part of the queue */ __netif_schedule(q); return 0; @@ -61,9 +57,11 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q) /* check the reason of requeuing without tx lock first */ txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); - if (!netif_tx_queue_stopped(txq) && !netif_tx_queue_frozen(txq)) + if (!netif_tx_queue_stopped(txq) && + !netif_tx_queue_frozen(txq)) { q->gso_skb = NULL; - else + q->q.qlen--; + } else skb = NULL; } else { skb = q->dequeue(q); @@ -103,44 +101,23 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb, } /* - * NOTE: Called under qdisc_lock(q) with locally disabled BH. - * - * __QDISC_STATE_RUNNING guarantees only one CPU can process - * this qdisc at a time. qdisc_lock(q) serializes queue accesses for - * this queue. - * - * netif_tx_lock serializes accesses to device driver. - * - * qdisc_lock(q) and netif_tx_lock are mutually exclusive, - * if one is grabbed, another must be free. - * - * Note, that this procedure can be called by a watchdog timer + * Transmit one skb, and handle the return status as required. Holding the + * __QDISC_STATE_RUNNING bit guarantees that only one CPU can execute this + * function. * * Returns to the caller: * 0 - queue is empty or throttled. * >0 - queue is not empty. - * */ -static inline int qdisc_restart(struct Qdisc *q) +int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, struct netdev_queue *txq, + spinlock_t *root_lock) { - struct netdev_queue *txq; int ret = NETDEV_TX_BUSY; - struct net_device *dev; - spinlock_t *root_lock; - struct sk_buff *skb; - - /* Dequeue packet */ - if (unlikely((skb = dequeue_skb(q)) == NULL)) - return 0; - - root_lock = qdisc_lock(q); /* And release qdisc */ spin_unlock(root_lock); - dev = qdisc_dev(q); - txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); - HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_tx_queue_stopped(txq) && !netif_tx_queue_frozen(txq)) @@ -177,6 +154,44 @@ static inline int qdisc_restart(struct Qdisc *q) return ret; } +/* + * NOTE: Called under qdisc_lock(q) with locally disabled BH. + * + * __QDISC_STATE_RUNNING guarantees only one CPU can process + * this qdisc at a time. qdisc_lock(q) serializes queue accesses for + * this queue. + * + * netif_tx_lock serializes accesses to device driver. + * + * qdisc_lock(q) and netif_tx_lock are mutually exclusive, + * if one is grabbed, another must be free. + * + * Note, that this procedure can be called by a watchdog timer + * + * Returns to the caller: + * 0 - queue is empty or throttled. + * >0 - queue is not empty. + * + */ +static inline int qdisc_restart(struct Qdisc *q) +{ + struct netdev_queue *txq; + struct net_device *dev; + spinlock_t *root_lock; + struct sk_buff *skb; + + /* Dequeue packet */ + skb = dequeue_skb(q); + if (unlikely(!skb)) + return 0; + + root_lock = qdisc_lock(q); + dev = qdisc_dev(q); + txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); + + return sch_direct_xmit(skb, q, dev, txq, root_lock); +} + void __qdisc_run(struct Qdisc *q) { unsigned long start_time = jiffies; @@ -391,18 +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); } @@ -412,14 +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; @@ -427,12 +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]; - for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { - if (!skb_queue_empty(list + prio)) - return skb_peek(list + prio); + if (band >= 0) { + struct sk_buff_head *list = band2list(priv, band); + + return skb_peek(list); } return NULL; @@ -441,11 +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; } @@ -465,17 +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, @@ -547,8 +588,11 @@ void qdisc_reset(struct Qdisc *qdisc) if (ops->reset) ops->reset(qdisc); - kfree_skb(qdisc->gso_skb); - qdisc->gso_skb = NULL; + if (qdisc->gso_skb) { + kfree_skb(qdisc->gso_skb); + qdisc->gso_skb = NULL; + qdisc->q.qlen = 0; + } } EXPORT_SYMBOL(qdisc_reset); @@ -579,17 +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, @@ -605,12 +661,35 @@ static void attach_one_default_qdisc(struct net_device *dev, printk(KERN_INFO "%s: activation failed\n", dev->name); return; } + + /* Can by-pass the queue discipline for default qdisc */ + qdisc->flags |= TCQ_F_CAN_BYPASS; } else { qdisc = &noqueue_qdisc; } 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) @@ -638,8 +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 */ @@ -730,6 +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); @@ -755,5 +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 dad0144423d..2c5c76be18f 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -77,7 +77,7 @@ * The service curve parameters are converted to the internal * representation. The slope values are scaled to avoid overflow. * the inverse slope values as well as the y-projection of the 1st - * segment are kept in order to to avoid 64-bit divide operations + * segment are kept in order to avoid 64-bit divide operations * that are expensive on 32-bit architectures. */ @@ -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 ec4d46399d5..85acab9dc6f 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -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 4a2b7737435..a9e646bdb60 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 00000000000..d1dea3d5dc9 --- /dev/null +++ b/net/sched/sch_mq.c @@ -0,0 +1,241 @@ +/* + * 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 struct netdev_queue *mq_select_queue(struct Qdisc *sch, + struct tcmsg *tcm) +{ + unsigned int ntx = TC_H_MIN(tcm->tcm_parent); + struct netdev_queue *dev_queue = mq_queue_get(sch, ntx); + + if (!dev_queue) { + struct net_device *dev = qdisc_dev(sch); + + return netdev_get_tx_queue(dev, 0); + } + return dev_queue; +} + +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; + sch->qstats.qlen = sch->q.qlen; + 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 91273120304..7db2c88ce58 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; } @@ -388,6 +359,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; + cl_q->qstats.qlen = cl_q->q.qlen; if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 || gnet_stats_copy_queue(d, &cl_q->qstats) < 0) return -1; @@ -430,8 +402,6 @@ 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 94cecef7014..93285cecb24 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; } @@ -350,6 +322,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; + cl_q->qstats.qlen = cl_q->q.qlen; if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 || gnet_stats_copy_queue(d, &cl_q->qstats) < 0) return -1; @@ -392,8 +365,6 @@ 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 2bdf241f631..072cdf442f8 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 8706920a6d4..cb21380c060 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 e22dfe85e43..8fb8107ab18 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 9c002b6e053..5a002c24723 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); @@ -307,14 +307,14 @@ 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); netif_wake_queue(dev); txq->tx_packets++; txq->tx_bytes += length; - return 0; + return NETDEV_TX_OK; } __netif_tx_unlock(slave_txq); } @@ -323,7 +323,7 @@ restart: break; case 1: master->slaves = NEXT_SLAVE(q); - return 0; + return NETDEV_TX_OK; default: nores = 1; break; @@ -345,7 +345,7 @@ restart: drop: txq->tx_dropped++; dev_kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } static int teql_master_open(struct net_device *dev) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 525864bf4f0..7eed77a39d0 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); @@ -1401,32 +1447,51 @@ 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 * local endpoint and the remote peer. */ int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, - gfp_t gfp) + sctp_scope_t scope, gfp_t gfp) { - sctp_scope_t scope; int flags; /* Use scoping rules to determine the subset of addresses from * the endpoint. */ - scope = sctp_scope(&asoc->peer.active_path->ipaddr); flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; if (asoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 6d5944a745d..13a6fba4107 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 1748ef90950..acf7c4d128f 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/debug.c b/net/sctp/debug.c index 7ff548a30cf..bf24fa697de 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -52,7 +52,7 @@ int sctp_debug_flag = 1; /* Initially enable DEBUG */ #endif /* SCTP_DEBUG */ /* These are printable forms of Chunk ID's from section 3.1. */ -static const char *sctp_cid_tbl[SCTP_NUM_BASE_CHUNK_TYPES] = { +static const char *const sctp_cid_tbl[SCTP_NUM_BASE_CHUNK_TYPES] = { "DATA", "INIT", "INIT_ACK", @@ -97,7 +97,7 @@ const char *sctp_cname(const sctp_subtype_t cid) } /* These are printable forms of the states. */ -const char *sctp_state_tbl[SCTP_STATE_NUM_STATES] = { +const char *const sctp_state_tbl[SCTP_STATE_NUM_STATES] = { "STATE_EMPTY", "STATE_CLOSED", "STATE_COOKIE_WAIT", @@ -110,7 +110,7 @@ const char *sctp_state_tbl[SCTP_STATE_NUM_STATES] = { }; /* Events that could change the state of an association. */ -const char *sctp_evttype_tbl[] = { +const char *const sctp_evttype_tbl[] = { "EVENT_T_unknown", "EVENT_T_CHUNK", "EVENT_T_TIMEOUT", @@ -119,7 +119,7 @@ const char *sctp_evttype_tbl[] = { }; /* Return value of a state function */ -const char *sctp_status_tbl[] = { +const char *const sctp_status_tbl[] = { "DISPOSITION_DISCARD", "DISPOSITION_CONSUME", "DISPOSITION_NOMEM", @@ -132,7 +132,7 @@ const char *sctp_status_tbl[] = { }; /* Printable forms of primitives */ -static const char *sctp_primitive_tbl[SCTP_NUM_PRIMITIVE_TYPES] = { +static const char *const sctp_primitive_tbl[SCTP_NUM_PRIMITIVE_TYPES] = { "PRIMITIVE_ASSOCIATE", "PRIMITIVE_SHUTDOWN", "PRIMITIVE_ABORT", @@ -149,7 +149,7 @@ const char *sctp_pname(const sctp_subtype_t id) return "unknown_primitive"; } -static const char *sctp_other_tbl[] = { +static const char *const sctp_other_tbl[] = { "NO_PENDING_TSN", "ICMP_PROTO_UNREACH", }; @@ -162,7 +162,7 @@ const char *sctp_oname(const sctp_subtype_t id) return "unknown 'other' event"; } -static const char *sctp_timer_tbl[] = { +static const char *const sctp_timer_tbl[] = { "TIMEOUT_NONE", "TIMEOUT_T1_COOKIE", "TIMEOUT_T1_INIT", diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 6a4b1909414..bb280e60e00 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -949,7 +949,7 @@ static int sctp6_rcv(struct sk_buff *skb) return sctp_rcv(skb) ? -1 : 0; } -static struct inet6_protocol sctpv6_protocol = { +static const struct inet6_protocol sctpv6_protocol = { .handler = sctp6_rcv, .err_handler = sctp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, diff --git a/net/sctp/output.c b/net/sctp/output.c index b94c2119056..5cbda8f1ddf 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 d765fc53e74..23e5e97aa61 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)); @@ -422,16 +423,6 @@ void sctp_retransmit_mark(struct sctp_outq *q, if ((reason == SCTP_RTXR_FAST_RTX && (chunk->fast_retransmit == SCTP_NEED_FRTX)) || (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { - /* If this chunk was sent less then 1 rto ago, do not - * retransmit this chunk, but give the peer time - * to acknowlege it. Do this only when - * retransmitting due to T3 timeout. - */ - if (reason == SCTP_RTXR_T3_RTX && - time_before(jiffies, chunk->sent_at + - transport->last_rto)) - continue; - /* RFC 2960 6.2.1 Processing a Received SACK * * C) Any time a DATA chunk is marked for @@ -443,7 +434,8 @@ 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 +1302,7 @@ 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 +1336,9 @@ 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 +1372,20 @@ 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 +1399,6 @@ 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 +1438,6 @@ 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 +1493,8 @@ 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 +1564,14 @@ 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 +1600,7 @@ 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 f268910620b..d093cbfeaac 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 a76da657244..612dc878e05 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -431,16 +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; @@ -926,7 +924,7 @@ static struct inet_protosw sctp_stream_protosw = { }; /* Register with IP layer. */ -static struct net_protocol sctp_protocol = { +static const struct net_protocol sctp_protocol = { .handler = sctp_rcv, .err_handler = sctp_v4_err, .no_policy = 1, @@ -1186,10 +1184,10 @@ SCTP_STATIC __init int sctp_init(void) /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. */ - if (num_physpages >= (128 * 1024)) - goal = num_physpages >> (22 - PAGE_SHIFT); + if (totalram_pages >= (128 * 1024)) + goal = totalram_pages >> (22 - PAGE_SHIFT); else - goal = num_physpages >> (24 - PAGE_SHIFT); + goal = totalram_pages >> (24 - PAGE_SHIFT); for (order = 0; (1UL << order) < goal; order++) ; @@ -1259,6 +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 61cc6075b0d..9d881a61ac0 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 86426aac160..efa516b47e8 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, @@ -468,7 +480,6 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, * that indicates that we have an outstanding HB. */ if (!is_hb || transport->hb_sent) { - transport->last_rto = transport->rto; transport->rto = min((transport->rto * 2), transport->asoc->rto_max); } } @@ -931,6 +942,27 @@ 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 +1532,8 @@ 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 +1608,13 @@ 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 +1632,9 @@ 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 7288192f7df..d4df45022ff 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, @@ -375,6 +384,11 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, if (!new_asoc) goto nomem; + if (sctp_assoc_set_bind_addr_from_ep(new_asoc, + sctp_scope(sctp_source(chunk)), + GFP_ATOMIC) < 0) + goto nomem_init; + /* The call, sctp_process_init(), can fail on memory allocation. */ if (!sctp_process_init(new_asoc, chunk->chunk_hdr->type, sctp_source(chunk), @@ -392,9 +406,6 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, len = ntohs(err_chunk->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); - if (sctp_assoc_set_bind_addr_from_ep(new_asoc, GFP_ATOMIC) < 0) - goto nomem_init; - repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); if (!repl) goto nomem_init; @@ -962,7 +973,7 @@ 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 +1117,8 @@ 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); @@ -1442,6 +1454,10 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( if (!new_asoc) goto nomem; + if (sctp_assoc_set_bind_addr_from_ep(new_asoc, + sctp_scope(sctp_source(chunk)), GFP_ATOMIC) < 0) + goto nomem; + /* In the outbound INIT ACK the endpoint MUST copy its current * Verification Tag and Peers Verification tag into a reserved * place (local tie-tag and per tie-tag) within the state cookie. @@ -1478,9 +1494,6 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( sizeof(sctp_chunkhdr_t); } - if (sctp_assoc_set_bind_addr_from_ep(new_asoc, GFP_ATOMIC) < 0) - goto nomem; - repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); if (!repl) goto nomem; @@ -2561,6 +2574,12 @@ 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 +2643,7 @@ 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 +2655,19 @@ 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 +2894,9 @@ 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 +3007,9 @@ 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 +3552,12 @@ 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 +4585,9 @@ 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 +5886,9 @@ 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 +6028,10 @@ 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 +6041,8 @@ 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 +6055,18 @@ 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 971890dbfea..3a95fcb17a9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1080,6 +1080,13 @@ static int __sctp_connect(struct sock* sk, err = -ENOMEM; goto out_free; } + + err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, + GFP_KERNEL); + if (err < 0) { + goto out_free; + } + } /* Prime the peer's transport structures. */ @@ -1095,11 +1102,6 @@ static int __sctp_connect(struct sock* sk, walk_size += af->sockaddr_len; } - err = sctp_assoc_set_bind_addr_from_ep(asoc, GFP_KERNEL); - if (err < 0) { - goto out_free; - } - /* In case the user of sctp_connectx() wants an association * id back, assign one now. */ @@ -1274,22 +1276,30 @@ SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk, } /* - * New (hopefully final) interface for the API. The option buffer is used - * both for the returned association id and the addresses. + * New (hopefully final) interface for the API. + * We use the sctp_getaddrs_old structure so that use-space library + * can avoid any unnecessary allocations. The only defferent part + * is that we store the actual length of the address buffer into the + * addrs_num structure member. That way we can re-use the existing + * code. */ SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len, char __user *optval, int __user *optlen) { + struct sctp_getaddrs_old param; sctp_assoc_t assoc_id = 0; int err = 0; - if (len < sizeof(assoc_id)) + if (len < sizeof(param)) return -EINVAL; + if (copy_from_user(¶m, optval, sizeof(param))) + return -EFAULT; + err = __sctp_setsockopt_connectx(sk, - (struct sockaddr __user *)(optval + sizeof(assoc_id)), - len - sizeof(assoc_id), &assoc_id); + (struct sockaddr __user *)param.addrs, + param.addr_num, &assoc_id); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) @@ -1361,6 +1371,7 @@ 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; @@ -1688,6 +1699,11 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, goto out_unlock; } asoc = new_asoc; + err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL); + if (err < 0) { + err = -ENOMEM; + goto out_free; + } /* If the SCTP_INIT ancillary data is specified, set all * the association init values accordingly. @@ -1717,11 +1733,6 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, err = -ENOMEM; goto out_free; } - err = sctp_assoc_set_bind_addr_from_ep(asoc, GFP_KERNEL); - if (err < 0) { - err = -ENOMEM; - goto out_free; - } } /* ASSERT: we have a valid association at this point. */ @@ -1813,20 +1824,22 @@ 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 @@ -2024,7 +2037,8 @@ out: * instead a error will be indicated to the user. */ static int sctp_setsockopt_disable_fragments(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { int val; @@ -2040,7 +2054,7 @@ static int sctp_setsockopt_disable_fragments(struct sock *sk, } static int sctp_setsockopt_events(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; @@ -2061,7 +2075,7 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval, * association is closed. */ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); @@ -2240,7 +2254,7 @@ 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; } @@ -2315,7 +2329,8 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } static int sctp_setsockopt_peer_addr_params(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_paddrparams params; struct sctp_transport *trans = NULL; @@ -2427,7 +2442,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, */ static int sctp_setsockopt_delayed_ack(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sctp_sack_info params; struct sctp_transport *trans = NULL; @@ -2543,7 +2558,7 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, * by the change). With TCP-style sockets, this option is inherited by * sockets derived from a listener socket. */ -static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_initmsg sinit; struct sctp_sock *sp = sctp_sk(sk); @@ -2580,7 +2595,8 @@ static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, int opt * to this call if the caller is using the UDP model. */ static int sctp_setsockopt_default_send_param(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_sndrcvinfo info; struct sctp_association *asoc; @@ -2619,7 +2635,7 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, * association peer's addresses. */ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_prim prim; struct sctp_transport *trans; @@ -2648,7 +2664,7 @@ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, * integer boolean flag. */ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { int val; @@ -2673,7 +2689,8 @@ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval, * be changed. * */ -static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, int optlen) { +static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigned int optlen) +{ struct sctp_rtoinfo rtoinfo; struct sctp_association *asoc; @@ -2725,7 +2742,7 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, int opt * See [SCTP] for more information. * */ -static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_assocparams assocparams; @@ -2797,7 +2814,7 @@ static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int o * addresses and a user will receive both PF_INET6 and PF_INET type * addresses on the socket. */ -static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsigned int optlen) { int val; struct sctp_sock *sp = sctp_sk(sk); @@ -2841,7 +2858,7 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, int op * changed (effecting future associations only). * assoc_value: This parameter specifies the maximum size in bytes. */ -static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; @@ -2877,15 +2894,10 @@ 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; @@ -2901,7 +2913,7 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optl * set primary request: */ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -2952,7 +2964,7 @@ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optva } static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_setadaptation adaptation; @@ -2981,7 +2993,7 @@ static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval * saved with outbound messages. */ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_assoc_value params; struct sctp_sock *sp; @@ -3032,7 +3044,7 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, */ static int sctp_setsockopt_fragment_interleave(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { int val; @@ -3065,7 +3077,7 @@ static int sctp_setsockopt_fragment_interleave(struct sock *sk, */ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { u32 val; @@ -3098,7 +3110,7 @@ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, */ static int sctp_setsockopt_maxburst(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_assoc_value params; struct sctp_sock *sp; @@ -3142,8 +3154,8 @@ static int sctp_setsockopt_maxburst(struct sock *sk, * will only effect future associations on the socket. */ static int sctp_setsockopt_auth_chunk(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authchunk val; @@ -3174,8 +3186,8 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, * endpoint requires the peer to use. */ static int sctp_setsockopt_hmac_ident(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_hmacalgo *hmacs; u32 idents; @@ -3217,7 +3229,7 @@ out: */ static int sctp_setsockopt_auth_key(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_authkey *authkey; struct sctp_association *asoc; @@ -3262,8 +3274,8 @@ out: * the association shared key. */ static int sctp_setsockopt_active_key(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authkeyid val; struct sctp_association *asoc; @@ -3290,8 +3302,8 @@ static int sctp_setsockopt_active_key(struct sock *sk, * This set option will delete a shared secret key from use. */ static int sctp_setsockopt_del_key(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authkeyid val; struct sctp_association *asoc; @@ -3334,7 +3346,7 @@ static int sctp_setsockopt_del_key(struct sock *sk, * optlen - the size of the buffer. */ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int retval = 0; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 63eabbc7129..ab7151da120 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 e5dde45c79d..37a1184d789 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -74,7 +74,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, * given destination transport address, set RTO to the protocol * parameter 'RTO.Initial'. */ - peer->last_rto = peer->rto = msecs_to_jiffies(sctp_rto_initial); + peer->rto = msecs_to_jiffies(sctp_rto_initial); peer->rtt = 0; peer->rttvar = 0; peer->srtt = 0; @@ -308,7 +308,8 @@ void sctp_transport_route(struct sctp_transport *transport, /* Initialize sk->sk_rcv_saddr, if the transport is the * association's active path for getsockname(). */ - if (asoc && (transport == asoc->peer.active_path)) + if (asoc && (!asoc->peer.primary_path || + (transport == asoc->peer.active_path))) opt->pf->af->to_sk_saddr(&transport->saddr, asoc->base.sk); } else @@ -385,7 +386,6 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) tp->rto = tp->asoc->rto_max; tp->rtt = rtt; - tp->last_rto = tp->rto; /* Reset rto_pending so that a new RTT measurement is started when a * new data chunk is sent. @@ -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: @@ -598,7 +601,7 @@ void sctp_transport_reset(struct sctp_transport *t) */ t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); t->ssthresh = asoc->peer.i.a_rwnd; - t->last_rto = t->rto = asoc->rto_initial; + t->rto = asoc->rto_initial; t->rtt = 0; t->srtt = 0; t->rttvar = 0; diff --git a/net/socket.c b/net/socket.c index 6d471655904..75655365b5f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -86,6 +86,7 @@ #include <linux/audit.h> #include <linux/wireless.h> #include <linux/nsproxy.h> +#include <linux/magic.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -235,8 +236,6 @@ int move_addr_to_user(struct sockaddr *kaddr, int klen, void __user *uaddr, return __put_user(klen, ulen); } -#define SOCKFS_MAGIC 0x534F434B - static struct kmem_cache *sock_inode_cachep __read_mostly; static struct inode *sock_alloc_inode(struct super_block *sb) @@ -285,7 +284,7 @@ static int init_inodecache(void) return 0; } -static struct super_operations sockfs_ops = { +static const struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, .destroy_inode =sock_destroy_inode, .statfs = simple_statfs, @@ -489,6 +488,7 @@ static struct socket *sock_alloc(void) sock = SOCKET_I(inode); + kmemcheck_annotate_bitfield(sock, type); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); @@ -2098,12 +2098,17 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) unsigned long a[6]; unsigned long a0, a1; int err; + unsigned int len; if (call < 1 || call > SYS_ACCEPT4) return -EINVAL; + len = nargs[call]; + if (len > sizeof(a)) + return -EINVAL; + /* copy_from_user should be SMP safe. */ - if (copy_from_user(a, args, nargs[call])) + if (copy_from_user(a, args, len)) return -EFAULT; audit_socketcall(nargs[call] / sizeof(unsigned long), a); @@ -2386,7 +2391,7 @@ int kernel_getsockopt(struct socket *sock, int level, int optname, } int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, int optlen) + char *optval, unsigned int optlen) { mm_segment_t oldfs = get_fs(); int err; diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index db73fd2a3f0..9d2fca5ad14 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ auth.o auth_null.o auth_unix.o auth_generic.o \ svc.o svcsock.o svcauth.o svcauth_unix.o \ - rpcb_clnt.o timer.o xdr.o \ + addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ svc_xprt.o sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c new file mode 100644 index 00000000000..c7450c8f0a7 --- /dev/null +++ b/net/sunrpc/addr.c @@ -0,0 +1,362 @@ +/* + * Copyright 2009, Oracle. All rights reserved. + * + * Convert socket addresses to presentation addresses and universal + * addresses, and vice versa. + * + * Universal addresses are introduced by RFC 1833 and further refined by + * recent RFCs describing NFSv4. The universal address format is part + * of the external (network) interface provided by rpcbind version 3 + * and 4, and by NFSv4. Such an address is a string containing a + * presentation format IP address followed by a port number in + * "hibyte.lobyte" format. + * + * IPv6 addresses can also include a scope ID, typically denoted by + * a '%' followed by a device name or a non-negative integer. Refer to + * RFC 4291, Section 2.2 for details on IPv6 presentation formats. + */ + +#include <net/ipv6.h> +#include <linux/sunrpc/clnt.h> + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + +static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, + char *buf, const int buflen) +{ + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + const struct in6_addr *addr = &sin6->sin6_addr; + + /* + * RFC 4291, Section 2.2.2 + * + * Shorthanded ANY address + */ + if (ipv6_addr_any(addr)) + return snprintf(buf, buflen, "::"); + + /* + * RFC 4291, Section 2.2.2 + * + * Shorthanded loopback address + */ + if (ipv6_addr_loopback(addr)) + return snprintf(buf, buflen, "::1"); + + /* + * RFC 4291, Section 2.2.3 + * + * Special presentation address format for mapped v4 + * addresses. + */ + if (ipv6_addr_v4mapped(addr)) + return snprintf(buf, buflen, "::ffff:%pI4", + &addr->s6_addr32[3]); + + /* + * RFC 4291, Section 2.2.1 + * + * To keep the result as short as possible, especially + * since we don't shorthand, we don't want leading zeros + * in each halfword, so avoid %pI6. + */ + return snprintf(buf, buflen, "%x:%x:%x:%x:%x:%x:%x:%x", + ntohs(addr->s6_addr16[0]), ntohs(addr->s6_addr16[1]), + ntohs(addr->s6_addr16[2]), ntohs(addr->s6_addr16[3]), + ntohs(addr->s6_addr16[4]), ntohs(addr->s6_addr16[5]), + ntohs(addr->s6_addr16[6]), ntohs(addr->s6_addr16[7])); +} + +static size_t rpc_ntop6(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + char scopebuf[IPV6_SCOPE_ID_LEN]; + size_t len; + int rc; + + len = rpc_ntop6_noscopeid(sap, buf, buflen); + if (unlikely(len == 0)) + return len; + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL)) + return len; + + rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u", + IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id); + if (unlikely((size_t)rc > sizeof(scopebuf))) + return 0; + + len += rc; + if (unlikely(len > buflen)) + return 0; + + strcat(buf, scopebuf); + return len; +} + +#else /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */ + +static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, + char *buf, const int buflen) +{ + return 0; +} + +static size_t rpc_ntop6(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + return 0; +} + +#endif /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */ + +static int rpc_ntop4(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + const struct sockaddr_in *sin = (struct sockaddr_in *)sap; + + return snprintf(buf, buflen, "%pI4", &sin->sin_addr); +} + +/** + * rpc_ntop - construct a presentation address in @buf + * @sap: socket address + * @buf: construction area + * @buflen: size of @buf, in bytes + * + * Plants a %NUL-terminated string in @buf and returns the length + * of the string, excluding the %NUL. Otherwise zero is returned. + */ +size_t rpc_ntop(const struct sockaddr *sap, char *buf, const size_t buflen) +{ + switch (sap->sa_family) { + case AF_INET: + return rpc_ntop4(sap, buf, buflen); + case AF_INET6: + return rpc_ntop6(sap, buf, buflen); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rpc_ntop); + +static size_t rpc_pton4(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + u8 *addr = (u8 *)&sin->sin_addr.s_addr; + + if (buflen > INET_ADDRSTRLEN || salen < sizeof(struct sockaddr_in)) + return 0; + + memset(sap, 0, sizeof(struct sockaddr_in)); + + if (in4_pton(buf, buflen, addr, '\0', NULL) == 0) + return 0; + + sin->sin_family = AF_INET; + return sizeof(struct sockaddr_in);; +} + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static int rpc_parse_scope_id(const char *buf, const size_t buflen, + const char *delim, struct sockaddr_in6 *sin6) +{ + char *p; + size_t len; + + if ((buf + buflen) == delim) + return 1; + + if (*delim != IPV6_SCOPE_DELIMITER) + return 0; + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL)) + return 0; + + len = (buf + buflen) - delim - 1; + p = kstrndup(delim + 1, len, GFP_KERNEL); + if (p) { + unsigned long scope_id = 0; + struct net_device *dev; + + dev = dev_get_by_name(&init_net, p); + if (dev != NULL) { + scope_id = dev->ifindex; + dev_put(dev); + } else { + if (strict_strtoul(p, 10, &scope_id) == 0) { + kfree(p); + return 0; + } + } + + kfree(p); + + sin6->sin6_scope_id = scope_id; + return 1; + } + + return 0; +} + +static size_t rpc_pton6(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + u8 *addr = (u8 *)&sin6->sin6_addr.in6_u; + const char *delim; + + if (buflen > (INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN) || + salen < sizeof(struct sockaddr_in6)) + return 0; + + memset(sap, 0, sizeof(struct sockaddr_in6)); + + if (in6_pton(buf, buflen, addr, IPV6_SCOPE_DELIMITER, &delim) == 0) + return 0; + + if (!rpc_parse_scope_id(buf, buflen, delim, sin6)) + return 0; + + sin6->sin6_family = AF_INET6; + return sizeof(struct sockaddr_in6); +} +#else +static size_t rpc_pton6(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + return 0; +} +#endif + +/** + * rpc_pton - Construct a sockaddr in @sap + * @buf: C string containing presentation format IP address + * @buflen: length of presentation address in bytes + * @sap: buffer into which to plant socket address + * @salen: size of buffer in bytes + * + * Returns the size of the socket address if successful; otherwise + * zero is returned. + * + * Plants a socket address in @sap and returns the size of the + * socket address, if successful. Returns zero if an error + * occurred. + */ +size_t rpc_pton(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + unsigned int i; + + for (i = 0; i < buflen; i++) + if (buf[i] == ':') + return rpc_pton6(buf, buflen, sap, salen); + return rpc_pton4(buf, buflen, sap, salen); +} +EXPORT_SYMBOL_GPL(rpc_pton); + +/** + * rpc_sockaddr2uaddr - Construct a universal address string from @sap. + * @sap: socket address + * + * Returns a %NUL-terminated string in dynamically allocated memory; + * otherwise NULL is returned if an error occurred. Caller must + * free the returned string. + */ +char *rpc_sockaddr2uaddr(const struct sockaddr *sap) +{ + char portbuf[RPCBIND_MAXUADDRPLEN]; + char addrbuf[RPCBIND_MAXUADDRLEN]; + unsigned short port; + + switch (sap->sa_family) { + case AF_INET: + if (rpc_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0) + return NULL; + port = ntohs(((struct sockaddr_in *)sap)->sin_port); + break; + case AF_INET6: + if (rpc_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0) + return NULL; + port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port); + break; + default: + return NULL; + } + + if (snprintf(portbuf, sizeof(portbuf), + ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf)) + return NULL; + + if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) + return NULL; + + return kstrdup(addrbuf, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr); + +/** + * rpc_uaddr2sockaddr - convert a universal address to a socket address. + * @uaddr: C string containing universal address to convert + * @uaddr_len: length of universal address string + * @sap: buffer into which to plant socket address + * @salen: size of buffer + * + * @uaddr does not have to be '\0'-terminated, but strict_strtoul() and + * rpc_pton() require proper string termination to be successful. + * + * Returns the size of the socket address if successful; otherwise + * zero is returned. + */ +size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len, + struct sockaddr *sap, const size_t salen) +{ + char *c, buf[RPCBIND_MAXUADDRLEN + sizeof('\0')]; + unsigned long portlo, porthi; + unsigned short port; + + if (uaddr_len > RPCBIND_MAXUADDRLEN) + return 0; + + memcpy(buf, uaddr, uaddr_len); + + buf[uaddr_len] = '\0'; + c = strrchr(buf, '.'); + if (unlikely(c == NULL)) + return 0; + if (unlikely(strict_strtoul(c + 1, 10, &portlo) != 0)) + return 0; + if (unlikely(portlo > 255)) + return 0; + + *c = '\0'; + c = strrchr(buf, '.'); + if (unlikely(c == NULL)) + return 0; + if (unlikely(strict_strtoul(c + 1, 10, &porthi) != 0)) + return 0; + if (unlikely(porthi > 255)) + return 0; + + port = (unsigned short)((porthi << 8) | portlo); + + *c = '\0'; + if (rpc_pton(buf, strlen(buf), sap, salen) == 0) + return 0; + + switch (sap->sa_family) { + case AF_INET: + ((struct sockaddr_in *)sap)->sin_port = htons(port); + return sizeof(struct sockaddr_in); + case AF_INET6: + ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); + return sizeof(struct sockaddr_in6); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rpc_uaddr2sockaddr); diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 0c431c277af..54a4e042f10 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -385,7 +385,7 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred, EXPORT_SYMBOL_GPL(rpcauth_init_cred); void -rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred) +rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags) { task->tk_msg.rpc_cred = get_rpccred(cred); dprintk("RPC: %5u holding %s cred %p\n", task->tk_pid, @@ -394,7 +394,7 @@ rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred) EXPORT_SYMBOL_GPL(rpcauth_generic_bind_cred); static void -rpcauth_bind_root_cred(struct rpc_task *task) +rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { @@ -405,7 +405,7 @@ rpcauth_bind_root_cred(struct rpc_task *task) dprintk("RPC: %5u looking up %s cred\n", task->tk_pid, task->tk_client->cl_auth->au_ops->au_name); - ret = auth->au_ops->lookup_cred(auth, &acred, 0); + ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags); if (!IS_ERR(ret)) task->tk_msg.rpc_cred = ret; else @@ -413,14 +413,14 @@ rpcauth_bind_root_cred(struct rpc_task *task) } static void -rpcauth_bind_new_cred(struct rpc_task *task) +rpcauth_bind_new_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct rpc_cred *ret; dprintk("RPC: %5u looking up %s cred\n", task->tk_pid, auth->au_ops->au_name); - ret = rpcauth_lookupcred(auth, 0); + ret = rpcauth_lookupcred(auth, lookupflags); if (!IS_ERR(ret)) task->tk_msg.rpc_cred = ret; else @@ -430,12 +430,16 @@ rpcauth_bind_new_cred(struct rpc_task *task) void rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags) { + int lookupflags = 0; + + if (flags & RPC_TASK_ASYNC) + lookupflags |= RPCAUTH_LOOKUP_NEW; if (cred != NULL) - cred->cr_ops->crbind(task, cred); + cred->cr_ops->crbind(task, cred, lookupflags); else if (flags & RPC_TASK_ROOTCREDS) - rpcauth_bind_root_cred(task); + rpcauth_bind_root_cred(task, lookupflags); else - rpcauth_bind_new_cred(task); + rpcauth_bind_new_cred(task, lookupflags); } void diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 4028502f052..bf88bf8e936 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -55,13 +55,13 @@ struct rpc_cred *rpc_lookup_machine_cred(void) EXPORT_SYMBOL_GPL(rpc_lookup_machine_cred); static void -generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred) +generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred *acred = &container_of(cred, struct generic_cred, gc_base)->acred; struct rpc_cred *ret; - ret = auth->au_ops->lookup_cred(auth, acred, 0); + ret = auth->au_ops->lookup_cred(auth, acred, lookupflags); if (!IS_ERR(ret)) task->tk_msg.rpc_cred = ret; else diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 66d458fc692..fc6a43ccd95 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -89,8 +89,8 @@ static struct rpc_wait_queue pipe_version_rpc_waitqueue; static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue); static void gss_free_ctx(struct gss_cl_ctx *); -static struct rpc_pipe_ops gss_upcall_ops_v0; -static struct rpc_pipe_ops gss_upcall_ops_v1; +static const struct rpc_pipe_ops gss_upcall_ops_v0; +static const struct rpc_pipe_ops gss_upcall_ops_v1; static inline struct gss_cl_ctx * gss_get_ctx(struct gss_cl_ctx *ctx) @@ -777,7 +777,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) * that we supported only the old pipe. So we instead create * the new pipe first. */ - gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_dentry, + gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_path.dentry, "gssd", clnt, &gss_upcall_ops_v1, RPC_PIPE_WAIT_FOR_OPEN); @@ -786,7 +786,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) goto err_put_mech; } - gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_dentry, + gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_path.dentry, gss_auth->mech->gm_name, clnt, &gss_upcall_ops_v0, RPC_PIPE_WAIT_FOR_OPEN); @@ -1507,7 +1507,7 @@ static const struct rpc_credops gss_nullops = { .crunwrap_resp = gss_unwrap_resp, }; -static struct rpc_pipe_ops gss_upcall_ops_v0 = { +static const struct rpc_pipe_ops gss_upcall_ops_v0 = { .upcall = gss_pipe_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, @@ -1515,7 +1515,7 @@ static struct rpc_pipe_ops gss_upcall_ops_v0 = { .release_pipe = gss_pipe_release, }; -static struct rpc_pipe_ops gss_upcall_ops_v1 = { +static const struct rpc_pipe_ops gss_upcall_ops_v1 = { .upcall = gss_pipe_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 2278a50c644..f6c51e562a0 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -181,6 +181,11 @@ static void rsi_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int rsi_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, rsi_request); +} + static int rsi_parse(struct cache_detail *cd, char *mesg, int mlen) @@ -270,7 +275,7 @@ static struct cache_detail rsi_cache = { .hash_table = rsi_table, .name = "auth.rpcsec.init", .cache_put = rsi_put, - .cache_request = rsi_request, + .cache_upcall = rsi_upcall, .cache_parse = rsi_parse, .match = rsi_match, .init = rsi_init, @@ -1369,8 +1374,10 @@ svcauth_gss_release(struct svc_rqst *rqstp) if (stat) goto out_err; break; - default: - goto out_err; + /* + * For any other gc_svc value, svcauth_gss_accept() already set + * the auth_error appropriately; just fall through: + */ } out: diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index c70dd7f5258..1db618f56ec 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -8,7 +8,6 @@ #include <linux/types.h> #include <linux/module.h> -#include <linux/utsname.h> #include <linux/sunrpc/clnt.h> #ifdef RPC_DEBUG diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index ff0c23053d2..d6eee291a0e 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -27,10 +27,12 @@ #include <linux/net.h> #include <linux/workqueue.h> #include <linux/mutex.h> +#include <linux/pagemap.h> #include <asm/ioctls.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/cache.h> #include <linux/sunrpc/stats.h> +#include <linux/sunrpc/rpc_pipe_fs.h> #define RPCDBG_FACILITY RPCDBG_CACHE @@ -101,23 +103,21 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, EXPORT_SYMBOL_GPL(sunrpc_cache_lookup); -static void queue_loose(struct cache_detail *detail, struct cache_head *ch); +static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch); -static int cache_fresh_locked(struct cache_head *head, time_t expiry) +static void cache_fresh_locked(struct cache_head *head, time_t expiry) { head->expiry_time = expiry; head->last_refresh = get_seconds(); - return !test_and_set_bit(CACHE_VALID, &head->flags); + set_bit(CACHE_VALID, &head->flags); } static void cache_fresh_unlocked(struct cache_head *head, - struct cache_detail *detail, int new) + struct cache_detail *detail) { - if (new) - cache_revisit_request(head); if (test_and_clear_bit(CACHE_PENDING, &head->flags)) { cache_revisit_request(head); - queue_loose(detail, head); + cache_dequeue(detail, head); } } @@ -130,7 +130,6 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, */ struct cache_head **head; struct cache_head *tmp; - int is_new; if (!test_bit(CACHE_VALID, &old->flags)) { write_lock(&detail->hash_lock); @@ -139,9 +138,9 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, set_bit(CACHE_NEGATIVE, &old->flags); else detail->update(old, new); - is_new = cache_fresh_locked(old, new->expiry_time); + cache_fresh_locked(old, new->expiry_time); write_unlock(&detail->hash_lock); - cache_fresh_unlocked(old, detail, is_new); + cache_fresh_unlocked(old, detail); return old; } write_unlock(&detail->hash_lock); @@ -165,17 +164,39 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, *head = tmp; detail->entries++; cache_get(tmp); - is_new = cache_fresh_locked(tmp, new->expiry_time); + cache_fresh_locked(tmp, new->expiry_time); cache_fresh_locked(old, 0); write_unlock(&detail->hash_lock); - cache_fresh_unlocked(tmp, detail, is_new); - cache_fresh_unlocked(old, detail, 0); + cache_fresh_unlocked(tmp, detail); + cache_fresh_unlocked(old, detail); cache_put(old, detail); return tmp; } EXPORT_SYMBOL_GPL(sunrpc_cache_update); -static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h); +static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h) +{ + if (!cd->cache_upcall) + return -EINVAL; + return cd->cache_upcall(cd, h); +} + +static inline int cache_is_valid(struct cache_detail *detail, struct cache_head *h) +{ + if (!test_bit(CACHE_VALID, &h->flags) || + h->expiry_time < get_seconds()) + return -EAGAIN; + else if (detail->flush_time > h->last_refresh) + return -EAGAIN; + else { + /* entry is valid */ + if (test_bit(CACHE_NEGATIVE, &h->flags)) + return -ENOENT; + else + return 0; + } +} + /* * This is the generic cache management routine for all * the authentication caches. @@ -184,8 +205,10 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h); * * * Returns 0 if the cache_head can be used, or cache_puts it and returns - * -EAGAIN if upcall is pending, - * -ETIMEDOUT if upcall failed and should be retried, + * -EAGAIN if upcall is pending and request has been queued + * -ETIMEDOUT if upcall failed or request could not be queue or + * upcall completed but item is still invalid (implying that + * the cache item has been replaced with a newer one). * -ENOENT if cache entry was negative */ int cache_check(struct cache_detail *detail, @@ -195,17 +218,7 @@ int cache_check(struct cache_detail *detail, long refresh_age, age; /* First decide return status as best we can */ - if (!test_bit(CACHE_VALID, &h->flags) || - h->expiry_time < get_seconds()) - rv = -EAGAIN; - else if (detail->flush_time > h->last_refresh) - rv = -EAGAIN; - else { - /* entry is valid */ - if (test_bit(CACHE_NEGATIVE, &h->flags)) - rv = -ENOENT; - else rv = 0; - } + rv = cache_is_valid(detail, h); /* now see if we want to start an upcall */ refresh_age = (h->expiry_time - h->last_refresh); @@ -221,10 +234,11 @@ int cache_check(struct cache_detail *detail, switch (cache_make_upcall(detail, h)) { case -EINVAL: clear_bit(CACHE_PENDING, &h->flags); + cache_revisit_request(h); if (rv == -EAGAIN) { set_bit(CACHE_NEGATIVE, &h->flags); - cache_fresh_unlocked(h, detail, - cache_fresh_locked(h, get_seconds()+CACHE_NEW_EXPIRY)); + cache_fresh_locked(h, get_seconds()+CACHE_NEW_EXPIRY); + cache_fresh_unlocked(h, detail); rv = -ENOENT; } break; @@ -237,10 +251,14 @@ int cache_check(struct cache_detail *detail, } } - if (rv == -EAGAIN) - if (cache_defer_req(rqstp, h) != 0) - rv = -ETIMEDOUT; - + if (rv == -EAGAIN) { + if (cache_defer_req(rqstp, h) < 0) { + /* Request is not deferred */ + rv = cache_is_valid(detail, h); + if (rv == -EAGAIN) + rv = -ETIMEDOUT; + } + } if (rv) cache_put(h, detail); return rv; @@ -284,76 +302,11 @@ static DEFINE_SPINLOCK(cache_list_lock); static struct cache_detail *current_detail; static int current_index; -static const struct file_operations cache_file_operations; -static const struct file_operations content_file_operations; -static const struct file_operations cache_flush_operations; - static void do_cache_clean(struct work_struct *work); static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean); -static void remove_cache_proc_entries(struct cache_detail *cd) +static void sunrpc_init_cache_detail(struct cache_detail *cd) { - if (cd->proc_ent == NULL) - return; - if (cd->flush_ent) - remove_proc_entry("flush", cd->proc_ent); - if (cd->channel_ent) - remove_proc_entry("channel", cd->proc_ent); - if (cd->content_ent) - remove_proc_entry("content", cd->proc_ent); - cd->proc_ent = NULL; - remove_proc_entry(cd->name, proc_net_rpc); -} - -#ifdef CONFIG_PROC_FS -static int create_cache_proc_entries(struct cache_detail *cd) -{ - struct proc_dir_entry *p; - - cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc); - if (cd->proc_ent == NULL) - goto out_nomem; - cd->channel_ent = cd->content_ent = NULL; - - p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &cache_flush_operations, cd); - cd->flush_ent = p; - if (p == NULL) - goto out_nomem; - - if (cd->cache_request || cd->cache_parse) { - p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &cache_file_operations, cd); - cd->channel_ent = p; - if (p == NULL) - goto out_nomem; - } - if (cd->cache_show) { - p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &content_file_operations, cd); - cd->content_ent = p; - if (p == NULL) - goto out_nomem; - } - return 0; -out_nomem: - remove_cache_proc_entries(cd); - return -ENOMEM; -} -#else /* CONFIG_PROC_FS */ -static int create_cache_proc_entries(struct cache_detail *cd) -{ - return 0; -} -#endif - -int cache_register(struct cache_detail *cd) -{ - int ret; - - ret = create_cache_proc_entries(cd); - if (ret) - return ret; rwlock_init(&cd->hash_lock); INIT_LIST_HEAD(&cd->queue); spin_lock(&cache_list_lock); @@ -367,11 +320,9 @@ int cache_register(struct cache_detail *cd) /* start the cleaning process */ schedule_delayed_work(&cache_cleaner, 0); - return 0; } -EXPORT_SYMBOL_GPL(cache_register); -void cache_unregister(struct cache_detail *cd) +static void sunrpc_destroy_cache_detail(struct cache_detail *cd) { cache_purge(cd); spin_lock(&cache_list_lock); @@ -386,7 +337,6 @@ void cache_unregister(struct cache_detail *cd) list_del_init(&cd->others); write_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); - remove_cache_proc_entries(cd); if (list_empty(&cache_list)) { /* module must be being unloaded so its safe to kill the worker */ cancel_delayed_work_sync(&cache_cleaner); @@ -395,7 +345,6 @@ void cache_unregister(struct cache_detail *cd) out: printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name); } -EXPORT_SYMBOL_GPL(cache_unregister); /* clean cache tries to find something to clean * and cleans it. @@ -457,7 +406,7 @@ static int cache_clean(void) ) continue; if (test_and_clear_bit(CACHE_PENDING, &ch->flags)) - queue_loose(current_detail, ch); + cache_dequeue(current_detail, ch); if (atomic_read(&ch->ref.refcount) == 1) break; @@ -473,8 +422,10 @@ static int cache_clean(void) if (!ch) current_index ++; spin_unlock(&cache_list_lock); - if (ch) + if (ch) { + cache_revisit_request(ch); cache_put(ch, d); + } } else spin_unlock(&cache_list_lock); @@ -549,7 +500,7 @@ static int cache_defer_cnt; static int cache_defer_req(struct cache_req *req, struct cache_head *item) { - struct cache_deferred_req *dreq; + struct cache_deferred_req *dreq, *discard; int hash = DFR_HASH(item); if (cache_defer_cnt >= DFR_MAX) { @@ -557,11 +508,11 @@ static int cache_defer_req(struct cache_req *req, struct cache_head *item) * or continue and drop the oldest below */ if (net_random()&1) - return -ETIMEDOUT; + return -ENOMEM; } dreq = req->defer(req); if (dreq == NULL) - return -ETIMEDOUT; + return -ENOMEM; dreq->item = item; @@ -574,23 +525,24 @@ static int cache_defer_req(struct cache_req *req, struct cache_head *item) list_add(&dreq->hash, &cache_defer_hash[hash]); /* it is in, now maybe clean up */ - dreq = NULL; + discard = NULL; if (++cache_defer_cnt > DFR_MAX) { - dreq = list_entry(cache_defer_list.prev, - struct cache_deferred_req, recent); - list_del(&dreq->recent); - list_del(&dreq->hash); + discard = list_entry(cache_defer_list.prev, + struct cache_deferred_req, recent); + list_del_init(&discard->recent); + list_del_init(&discard->hash); cache_defer_cnt--; } spin_unlock(&cache_defer_lock); - if (dreq) { + if (discard) /* there was one too many */ - dreq->revisit(dreq, 1); - } + discard->revisit(discard, 1); + if (!test_bit(CACHE_PENDING, &item->flags)) { /* must have just been validated... */ cache_revisit_request(item); + return -EAGAIN; } return 0; } @@ -612,7 +564,7 @@ static void cache_revisit_request(struct cache_head *item) dreq = list_entry(lp, struct cache_deferred_req, hash); lp = lp->next; if (dreq->item == item) { - list_del(&dreq->hash); + list_del_init(&dreq->hash); list_move(&dreq->recent, &pending); cache_defer_cnt--; } @@ -638,7 +590,7 @@ void cache_clean_deferred(void *owner) list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) { if (dreq->owner == owner) { - list_del(&dreq->hash); + list_del_init(&dreq->hash); list_move(&dreq->recent, &pending); cache_defer_cnt--; } @@ -687,18 +639,18 @@ struct cache_reader { int offset; /* if non-0, we have a refcnt on next request */ }; -static ssize_t -cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) +static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, + loff_t *ppos, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; struct cache_request *rq; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct inode *inode = filp->f_path.dentry->d_inode; int err; if (count == 0) return 0; - mutex_lock(&queue_io_mutex); /* protect against multiple concurrent + mutex_lock(&inode->i_mutex); /* protect against multiple concurrent * readers on this file */ again: spin_lock(&queue_lock); @@ -711,7 +663,7 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (rp->q.list.next == &cd->queue) { spin_unlock(&queue_lock); - mutex_unlock(&queue_io_mutex); + mutex_unlock(&inode->i_mutex); BUG_ON(rp->offset); return 0; } @@ -758,49 +710,90 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (err == -EAGAIN) goto again; - mutex_unlock(&queue_io_mutex); + mutex_unlock(&inode->i_mutex); return err ? err : count; } -static char write_buf[8192]; /* protected by queue_io_mutex */ +static ssize_t cache_do_downcall(char *kaddr, const char __user *buf, + size_t count, struct cache_detail *cd) +{ + ssize_t ret; + + if (copy_from_user(kaddr, buf, count)) + return -EFAULT; + kaddr[count] = '\0'; + ret = cd->cache_parse(cd, kaddr, count); + if (!ret) + ret = count; + return ret; +} -static ssize_t -cache_write(struct file *filp, const char __user *buf, size_t count, - loff_t *ppos) +static ssize_t cache_slow_downcall(const char __user *buf, + size_t count, struct cache_detail *cd) { - int err; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + static char write_buf[8192]; /* protected by queue_io_mutex */ + ssize_t ret = -EINVAL; - if (count == 0) - return 0; if (count >= sizeof(write_buf)) - return -EINVAL; - + goto out; mutex_lock(&queue_io_mutex); + ret = cache_do_downcall(write_buf, buf, count, cd); + mutex_unlock(&queue_io_mutex); +out: + return ret; +} - if (copy_from_user(write_buf, buf, count)) { - mutex_unlock(&queue_io_mutex); - return -EFAULT; - } - write_buf[count] = '\0'; - if (cd->cache_parse) - err = cd->cache_parse(cd, write_buf, count); - else - err = -EINVAL; +static ssize_t cache_downcall(struct address_space *mapping, + const char __user *buf, + size_t count, struct cache_detail *cd) +{ + struct page *page; + char *kaddr; + ssize_t ret = -ENOMEM; + + if (count >= PAGE_CACHE_SIZE) + goto out_slow; + + page = find_or_create_page(mapping, 0, GFP_KERNEL); + if (!page) + goto out_slow; + + kaddr = kmap(page); + ret = cache_do_downcall(kaddr, buf, count, cd); + kunmap(page); + unlock_page(page); + page_cache_release(page); + return ret; +out_slow: + return cache_slow_downcall(buf, count, cd); +} - mutex_unlock(&queue_io_mutex); - return err ? err : count; +static ssize_t cache_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos, + struct cache_detail *cd) +{ + struct address_space *mapping = filp->f_mapping; + struct inode *inode = filp->f_path.dentry->d_inode; + ssize_t ret = -EINVAL; + + if (!cd->cache_parse) + goto out; + + mutex_lock(&inode->i_mutex); + ret = cache_downcall(mapping, buf, count, cd); + mutex_unlock(&inode->i_mutex); +out: + return ret; } static DECLARE_WAIT_QUEUE_HEAD(queue_wait); -static unsigned int -cache_poll(struct file *filp, poll_table *wait) +static unsigned int cache_poll(struct file *filp, poll_table *wait, + struct cache_detail *cd) { unsigned int mask; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; poll_wait(filp, &queue_wait, wait); @@ -822,14 +815,13 @@ cache_poll(struct file *filp, poll_table *wait) return mask; } -static int -cache_ioctl(struct inode *ino, struct file *filp, - unsigned int cmd, unsigned long arg) +static int cache_ioctl(struct inode *ino, struct file *filp, + unsigned int cmd, unsigned long arg, + struct cache_detail *cd) { int len = 0; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; - struct cache_detail *cd = PDE(ino)->data; if (cmd != FIONREAD || !rp) return -EINVAL; @@ -852,15 +844,15 @@ cache_ioctl(struct inode *ino, struct file *filp, return put_user(len, (int __user *)arg); } -static int -cache_open(struct inode *inode, struct file *filp) +static int cache_open(struct inode *inode, struct file *filp, + struct cache_detail *cd) { struct cache_reader *rp = NULL; + if (!cd || !try_module_get(cd->owner)) + return -EACCES; nonseekable_open(inode, filp); if (filp->f_mode & FMODE_READ) { - struct cache_detail *cd = PDE(inode)->data; - rp = kmalloc(sizeof(*rp), GFP_KERNEL); if (!rp) return -ENOMEM; @@ -875,11 +867,10 @@ cache_open(struct inode *inode, struct file *filp) return 0; } -static int -cache_release(struct inode *inode, struct file *filp) +static int cache_release(struct inode *inode, struct file *filp, + struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; - struct cache_detail *cd = PDE(inode)->data; if (rp) { spin_lock(&queue_lock); @@ -903,24 +894,13 @@ cache_release(struct inode *inode, struct file *filp) cd->last_close = get_seconds(); atomic_dec(&cd->readers); } + module_put(cd->owner); return 0; } -static const struct file_operations cache_file_operations = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .read = cache_read, - .write = cache_write, - .poll = cache_poll, - .ioctl = cache_ioctl, /* for FIONREAD */ - .open = cache_open, - .release = cache_release, -}; - - -static void queue_loose(struct cache_detail *detail, struct cache_head *ch) +static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch) { struct cache_queue *cq; spin_lock(&queue_lock); @@ -1020,15 +1000,21 @@ static void warn_no_listener(struct cache_detail *detail) if (detail->last_warn != detail->last_close) { detail->last_warn = detail->last_close; if (detail->warn_no_listener) - detail->warn_no_listener(detail); + detail->warn_no_listener(detail, detail->last_close != 0); } } /* - * register an upcall request to user-space. + * register an upcall request to user-space and queue it up for read() by the + * upcall daemon. + * * Each request is at most one page long. */ -static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) +int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, + void (*cache_request)(struct cache_detail *, + struct cache_head *, + char **, + int *)) { char *buf; @@ -1036,9 +1022,6 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) char *bp; int len; - if (detail->cache_request == NULL) - return -EINVAL; - if (atomic_read(&detail->readers) == 0 && detail->last_close < get_seconds() - 30) { warn_no_listener(detail); @@ -1057,7 +1040,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) bp = buf; len = PAGE_SIZE; - detail->cache_request(detail, h, &bp, &len); + cache_request(detail, h, &bp, &len); if (len < 0) { kfree(buf); @@ -1075,6 +1058,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) wake_up(&queue_wait); return 0; } +EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall); /* * parse a message from user-space and pass it @@ -1242,11 +1226,13 @@ static const struct seq_operations cache_content_op = { .show = c_show, }; -static int content_open(struct inode *inode, struct file *file) +static int content_open(struct inode *inode, struct file *file, + struct cache_detail *cd) { struct handle *han; - struct cache_detail *cd = PDE(inode)->data; + if (!cd || !try_module_get(cd->owner)) + return -EACCES; han = __seq_open_private(file, &cache_content_op, sizeof(*han)); if (han == NULL) return -ENOMEM; @@ -1255,17 +1241,33 @@ static int content_open(struct inode *inode, struct file *file) return 0; } -static const struct file_operations content_file_operations = { - .open = content_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; +static int content_release(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + int ret = seq_release_private(inode, file); + module_put(cd->owner); + return ret; +} + +static int open_flush(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + if (!cd || !try_module_get(cd->owner)) + return -EACCES; + return nonseekable_open(inode, file); +} + +static int release_flush(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + module_put(cd->owner); + return 0; +} static ssize_t read_flush(struct file *file, char __user *buf, - size_t count, loff_t *ppos) + size_t count, loff_t *ppos, + struct cache_detail *cd) { - struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data; char tbuf[20]; unsigned long p = *ppos; size_t len; @@ -1283,10 +1285,10 @@ static ssize_t read_flush(struct file *file, char __user *buf, return len; } -static ssize_t write_flush(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t write_flush(struct file *file, const char __user *buf, + size_t count, loff_t *ppos, + struct cache_detail *cd) { - struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data; char tbuf[20]; char *ep; long flushtime; @@ -1307,8 +1309,343 @@ static ssize_t write_flush(struct file * file, const char __user * buf, return count; } -static const struct file_operations cache_flush_operations = { - .open = nonseekable_open, - .read = read_flush, - .write = write_flush, +static ssize_t cache_read_procfs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_read(filp, buf, count, ppos, cd); +} + +static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_write(filp, buf, count, ppos, cd); +} + +static unsigned int cache_poll_procfs(struct file *filp, poll_table *wait) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_poll(filp, wait, cd); +} + +static int cache_ioctl_procfs(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_ioctl(inode, filp, cmd, arg, cd); +} + +static int cache_open_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_open(inode, filp, cd); +} + +static int cache_release_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_release(inode, filp, cd); +} + +static const struct file_operations cache_file_operations_procfs = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = cache_read_procfs, + .write = cache_write_procfs, + .poll = cache_poll_procfs, + .ioctl = cache_ioctl_procfs, /* for FIONREAD */ + .open = cache_open_procfs, + .release = cache_release_procfs, +}; + +static int content_open_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return content_open(inode, filp, cd); +} + +static int content_release_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return content_release(inode, filp, cd); +} + +static const struct file_operations content_file_operations_procfs = { + .open = content_open_procfs, + .read = seq_read, + .llseek = seq_lseek, + .release = content_release_procfs, }; + +static int open_flush_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return open_flush(inode, filp, cd); +} + +static int release_flush_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return release_flush(inode, filp, cd); +} + +static ssize_t read_flush_procfs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return read_flush(filp, buf, count, ppos, cd); +} + +static ssize_t write_flush_procfs(struct file *filp, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return write_flush(filp, buf, count, ppos, cd); +} + +static const struct file_operations cache_flush_operations_procfs = { + .open = open_flush_procfs, + .read = read_flush_procfs, + .write = write_flush_procfs, + .release = release_flush_procfs, +}; + +static void remove_cache_proc_entries(struct cache_detail *cd) +{ + if (cd->u.procfs.proc_ent == NULL) + return; + if (cd->u.procfs.flush_ent) + remove_proc_entry("flush", cd->u.procfs.proc_ent); + if (cd->u.procfs.channel_ent) + remove_proc_entry("channel", cd->u.procfs.proc_ent); + if (cd->u.procfs.content_ent) + remove_proc_entry("content", cd->u.procfs.proc_ent); + cd->u.procfs.proc_ent = NULL; + remove_proc_entry(cd->name, proc_net_rpc); +} + +#ifdef CONFIG_PROC_FS +static int create_cache_proc_entries(struct cache_detail *cd) +{ + struct proc_dir_entry *p; + + cd->u.procfs.proc_ent = proc_mkdir(cd->name, proc_net_rpc); + if (cd->u.procfs.proc_ent == NULL) + goto out_nomem; + cd->u.procfs.channel_ent = NULL; + cd->u.procfs.content_ent = NULL; + + p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &cache_flush_operations_procfs, cd); + cd->u.procfs.flush_ent = p; + if (p == NULL) + goto out_nomem; + + if (cd->cache_upcall || cd->cache_parse) { + p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &cache_file_operations_procfs, cd); + cd->u.procfs.channel_ent = p; + if (p == NULL) + goto out_nomem; + } + if (cd->cache_show) { + p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &content_file_operations_procfs, cd); + cd->u.procfs.content_ent = p; + if (p == NULL) + goto out_nomem; + } + return 0; +out_nomem: + remove_cache_proc_entries(cd); + return -ENOMEM; +} +#else /* CONFIG_PROC_FS */ +static int create_cache_proc_entries(struct cache_detail *cd) +{ + return 0; +} +#endif + +int cache_register(struct cache_detail *cd) +{ + int ret; + + sunrpc_init_cache_detail(cd); + ret = create_cache_proc_entries(cd); + if (ret) + sunrpc_destroy_cache_detail(cd); + return ret; +} +EXPORT_SYMBOL_GPL(cache_register); + +void cache_unregister(struct cache_detail *cd) +{ + remove_cache_proc_entries(cd); + sunrpc_destroy_cache_detail(cd); +} +EXPORT_SYMBOL_GPL(cache_unregister); + +static ssize_t cache_read_pipefs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_read(filp, buf, count, ppos, cd); +} + +static ssize_t cache_write_pipefs(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_write(filp, buf, count, ppos, cd); +} + +static unsigned int cache_poll_pipefs(struct file *filp, poll_table *wait) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_poll(filp, wait, cd); +} + +static int cache_ioctl_pipefs(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_ioctl(inode, filp, cmd, arg, cd); +} + +static int cache_open_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_open(inode, filp, cd); +} + +static int cache_release_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_release(inode, filp, cd); +} + +const struct file_operations cache_file_operations_pipefs = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = cache_read_pipefs, + .write = cache_write_pipefs, + .poll = cache_poll_pipefs, + .ioctl = cache_ioctl_pipefs, /* for FIONREAD */ + .open = cache_open_pipefs, + .release = cache_release_pipefs, +}; + +static int content_open_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return content_open(inode, filp, cd); +} + +static int content_release_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return content_release(inode, filp, cd); +} + +const struct file_operations content_file_operations_pipefs = { + .open = content_open_pipefs, + .read = seq_read, + .llseek = seq_lseek, + .release = content_release_pipefs, +}; + +static int open_flush_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return open_flush(inode, filp, cd); +} + +static int release_flush_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return release_flush(inode, filp, cd); +} + +static ssize_t read_flush_pipefs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return read_flush(filp, buf, count, ppos, cd); +} + +static ssize_t write_flush_pipefs(struct file *filp, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return write_flush(filp, buf, count, ppos, cd); +} + +const struct file_operations cache_flush_operations_pipefs = { + .open = open_flush_pipefs, + .read = read_flush_pipefs, + .write = write_flush_pipefs, + .release = release_flush_pipefs, +}; + +int sunrpc_cache_register_pipefs(struct dentry *parent, + const char *name, mode_t umode, + struct cache_detail *cd) +{ + struct qstr q; + struct dentry *dir; + int ret = 0; + + sunrpc_init_cache_detail(cd); + q.name = name; + q.len = strlen(name); + q.hash = full_name_hash(q.name, q.len); + dir = rpc_create_cache_dir(parent, &q, umode, cd); + if (!IS_ERR(dir)) + cd->u.pipefs.dir = dir; + else { + sunrpc_destroy_cache_detail(cd); + ret = PTR_ERR(dir); + } + return ret; +} +EXPORT_SYMBOL_GPL(sunrpc_cache_register_pipefs); + +void sunrpc_cache_unregister_pipefs(struct cache_detail *cd) +{ + rpc_remove_cache_dir(cd->u.pipefs.dir); + cd->u.pipefs.dir = NULL; + sunrpc_destroy_cache_detail(cd); +} +EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs); + diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index df1039f077c..38829e20500 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -27,6 +27,8 @@ #include <linux/types.h> #include <linux/kallsyms.h> #include <linux/mm.h> +#include <linux/namei.h> +#include <linux/mount.h> #include <linux/slab.h> #include <linux/utsname.h> #include <linux/workqueue.h> @@ -97,33 +99,49 @@ static int rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name) { static uint32_t clntid; + struct nameidata nd; + struct path path; + char name[15]; + struct qstr q = { + .name = name, + }; int error; - clnt->cl_vfsmnt = ERR_PTR(-ENOENT); - clnt->cl_dentry = ERR_PTR(-ENOENT); + clnt->cl_path.mnt = ERR_PTR(-ENOENT); + clnt->cl_path.dentry = ERR_PTR(-ENOENT); if (dir_name == NULL) return 0; - clnt->cl_vfsmnt = rpc_get_mount(); - if (IS_ERR(clnt->cl_vfsmnt)) - return PTR_ERR(clnt->cl_vfsmnt); + path.mnt = rpc_get_mount(); + if (IS_ERR(path.mnt)) + return PTR_ERR(path.mnt); + error = vfs_path_lookup(path.mnt->mnt_root, path.mnt, dir_name, 0, &nd); + if (error) + goto err; for (;;) { - snprintf(clnt->cl_pathname, sizeof(clnt->cl_pathname), - "%s/clnt%x", dir_name, - (unsigned int)clntid++); - clnt->cl_pathname[sizeof(clnt->cl_pathname) - 1] = '\0'; - clnt->cl_dentry = rpc_mkdir(clnt->cl_pathname, clnt); - if (!IS_ERR(clnt->cl_dentry)) - return 0; - error = PTR_ERR(clnt->cl_dentry); + q.len = snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++); + name[sizeof(name) - 1] = '\0'; + q.hash = full_name_hash(q.name, q.len); + path.dentry = rpc_create_client_dir(nd.path.dentry, &q, clnt); + if (!IS_ERR(path.dentry)) + break; + error = PTR_ERR(path.dentry); if (error != -EEXIST) { - printk(KERN_INFO "RPC: Couldn't create pipefs entry %s, error %d\n", - clnt->cl_pathname, error); - rpc_put_mount(); - return error; + printk(KERN_INFO "RPC: Couldn't create pipefs entry" + " %s/%s, error %d\n", + dir_name, name, error); + goto err_path_put; } } + path_put(&nd.path); + clnt->cl_path = path; + return 0; +err_path_put: + path_put(&nd.path); +err: + rpc_put_mount(); + return error; } static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, struct rpc_xprt *xprt) @@ -231,8 +249,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru return clnt; out_no_auth: - if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_dentry); + if (!IS_ERR(clnt->cl_path.dentry)) { + rpc_remove_client_dir(clnt->cl_path.dentry); rpc_put_mount(); } out_no_path: @@ -270,6 +288,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) .srcaddr = args->saddress, .dstaddr = args->address, .addrlen = args->addrsize, + .bc_xprt = args->bc_xprt, }; char servername[48]; @@ -423,8 +442,8 @@ rpc_free_client(struct kref *kref) dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); - if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_dentry); + if (!IS_ERR(clnt->cl_path.dentry)) { + rpc_remove_client_dir(clnt->cl_path.dentry); rpc_put_mount(); } if (clnt->cl_parent != clnt) { @@ -621,10 +640,11 @@ EXPORT_SYMBOL_GPL(rpc_call_async); /** * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run * rpc_execute against it - * @ops: RPC call ops + * @req: RPC request + * @tk_ops: RPC call ops */ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, - const struct rpc_call_ops *tk_ops) + const struct rpc_call_ops *tk_ops) { struct rpc_task *task; struct xdr_buf *xbufp = &req->rq_snd_buf; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 9ced0628d69..49278f83036 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -26,6 +26,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/workqueue.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include <linux/sunrpc/cache.h> static struct vfsmount *rpc_mount __read_mostly; static int rpc_mount_count; @@ -125,7 +126,7 @@ static void rpc_close_pipes(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); - struct rpc_pipe_ops *ops; + const struct rpc_pipe_ops *ops; int need_release; mutex_lock(&inode->i_mutex); @@ -398,66 +399,12 @@ static const struct file_operations rpc_info_operations = { /* - * We have a single directory with 1 node in it. - */ -enum { - RPCAUTH_Root = 1, - RPCAUTH_lockd, - RPCAUTH_mount, - RPCAUTH_nfs, - RPCAUTH_portmap, - RPCAUTH_statd, - RPCAUTH_nfsd4_cb, - RPCAUTH_RootEOF -}; - -/* * Description of fs contents. */ struct rpc_filelist { - char *name; + const char *name; const struct file_operations *i_fop; - int mode; -}; - -static struct rpc_filelist files[] = { - [RPCAUTH_lockd] = { - .name = "lockd", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_mount] = { - .name = "mount", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_nfs] = { - .name = "nfs", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_portmap] = { - .name = "portmap", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_statd] = { - .name = "statd", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_nfsd4_cb] = { - .name = "nfsd4_cb", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, -}; - -enum { - RPCAUTH_info = 2, - RPCAUTH_EOF -}; - -static struct rpc_filelist authfiles[] = { - [RPCAUTH_info] = { - .name = "info", - .i_fop = &rpc_info_operations, - .mode = S_IFREG | S_IRUSR, - }, + umode_t mode; }; struct vfsmount *rpc_get_mount(void) @@ -469,11 +416,13 @@ struct vfsmount *rpc_get_mount(void) return ERR_PTR(err); return rpc_mount; } +EXPORT_SYMBOL_GPL(rpc_get_mount); void rpc_put_mount(void) { simple_release_fs(&rpc_mount, &rpc_mount_count); } +EXPORT_SYMBOL_GPL(rpc_put_mount); static int rpc_delete_dentry(struct dentry *dentry) { @@ -484,39 +433,8 @@ static const struct dentry_operations rpc_dentry_operations = { .d_delete = rpc_delete_dentry, }; -static int -rpc_lookup_parent(char *path, struct nameidata *nd) -{ - struct vfsmount *mnt; - - if (path[0] == '\0') - return -ENOENT; - - mnt = rpc_get_mount(); - if (IS_ERR(mnt)) { - printk(KERN_WARNING "%s: %s failed to mount " - "pseudofilesystem \n", __FILE__, __func__); - return PTR_ERR(mnt); - } - - if (vfs_path_lookup(mnt->mnt_root, mnt, path, LOOKUP_PARENT, nd)) { - printk(KERN_WARNING "%s: %s failed to find path %s\n", - __FILE__, __func__, path); - rpc_put_mount(); - return -ENOENT; - } - return 0; -} - -static void -rpc_release_path(struct nameidata *nd) -{ - path_put(&nd->path); - rpc_put_mount(); -} - static struct inode * -rpc_get_inode(struct super_block *sb, int mode) +rpc_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (!inode) @@ -534,212 +452,274 @@ rpc_get_inode(struct super_block *sb, int mode) return inode; } -/* - * FIXME: This probably has races. - */ -static void rpc_depopulate(struct dentry *parent, - unsigned long start, unsigned long eof) +static int __rpc_create_common(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *dir = parent->d_inode; - struct list_head *pos, *next; - struct dentry *dentry, *dvec[10]; - int n = 0; + struct inode *inode; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD); -repeat: - spin_lock(&dcache_lock); - list_for_each_safe(pos, next, &parent->d_subdirs) { - dentry = list_entry(pos, struct dentry, d_u.d_child); - if (!dentry->d_inode || - dentry->d_inode->i_ino < start || - dentry->d_inode->i_ino >= eof) - continue; - spin_lock(&dentry->d_lock); - if (!d_unhashed(dentry)) { - dget_locked(dentry); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - dvec[n++] = dentry; - if (n == ARRAY_SIZE(dvec)) - break; - } else - spin_unlock(&dentry->d_lock); - } - spin_unlock(&dcache_lock); - if (n) { - do { - dentry = dvec[--n]; - if (S_ISREG(dentry->d_inode->i_mode)) - simple_unlink(dir, dentry); - else if (S_ISDIR(dentry->d_inode->i_mode)) - simple_rmdir(dir, dentry); - d_delete(dentry); - dput(dentry); - } while (n); - goto repeat; - } - mutex_unlock(&dir->i_mutex); + BUG_ON(!d_unhashed(dentry)); + inode = rpc_get_inode(dir->i_sb, mode); + if (!inode) + goto out_err; + inode->i_ino = iunique(dir->i_sb, 100); + if (i_fop) + inode->i_fop = i_fop; + if (private) + rpc_inode_setowner(inode, private); + d_add(dentry, inode); + return 0; +out_err: + printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n", + __FILE__, __func__, dentry->d_name.name); + dput(dentry); + return -ENOMEM; } -static int -rpc_populate(struct dentry *parent, - struct rpc_filelist *files, - int start, int eof) +static int __rpc_create(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *inode, *dir = parent->d_inode; - void *private = RPC_I(dir)->private; - struct dentry *dentry; - int mode, i; + int err; - mutex_lock(&dir->i_mutex); - for (i = start; i < eof; i++) { - dentry = d_alloc_name(parent, files[i].name); - if (!dentry) - goto out_bad; - dentry->d_op = &rpc_dentry_operations; - mode = files[i].mode; - inode = rpc_get_inode(dir->i_sb, mode); - if (!inode) { - dput(dentry); - goto out_bad; - } - inode->i_ino = i; - if (files[i].i_fop) - inode->i_fop = files[i].i_fop; - if (private) - rpc_inode_setowner(inode, private); - if (S_ISDIR(mode)) - inc_nlink(dir); - d_add(dentry, inode); - fsnotify_create(dir, dentry); - } - mutex_unlock(&dir->i_mutex); + err = __rpc_create_common(dir, dentry, S_IFREG | mode, i_fop, private); + if (err) + return err; + fsnotify_create(dir, dentry); return 0; -out_bad: - mutex_unlock(&dir->i_mutex); - printk(KERN_WARNING "%s: %s failed to populate directory %s\n", - __FILE__, __func__, parent->d_name.name); - return -ENOMEM; } -static int -__rpc_mkdir(struct inode *dir, struct dentry *dentry) +static int __rpc_mkdir(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *inode; + int err; - inode = rpc_get_inode(dir->i_sb, S_IFDIR | S_IRUGO | S_IXUGO); - if (!inode) - goto out_err; - inode->i_ino = iunique(dir->i_sb, 100); - d_instantiate(dentry, inode); + err = __rpc_create_common(dir, dentry, S_IFDIR | mode, i_fop, private); + if (err) + return err; inc_nlink(dir); fsnotify_mkdir(dir, dentry); return 0; -out_err: - printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n", - __FILE__, __func__, dentry->d_name.name); - return -ENOMEM; } -static int -__rpc_rmdir(struct inode *dir, struct dentry *dentry) +static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private, + const struct rpc_pipe_ops *ops, + int flags) { - int error; - error = simple_rmdir(dir, dentry); - if (!error) - d_delete(dentry); - return error; + struct rpc_inode *rpci; + int err; + + err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private); + if (err) + return err; + rpci = RPC_I(dentry->d_inode); + rpci->nkern_readwriters = 1; + rpci->private = private; + rpci->flags = flags; + rpci->ops = ops; + fsnotify_create(dir, dentry); + return 0; } -static struct dentry * -rpc_lookup_create(struct dentry *parent, const char *name, int len, int exclusive) +static int __rpc_rmdir(struct inode *dir, struct dentry *dentry) +{ + int ret; + + dget(dentry); + ret = simple_rmdir(dir, dentry); + d_delete(dentry); + dput(dentry); + return ret; +} + +static int __rpc_unlink(struct inode *dir, struct dentry *dentry) +{ + int ret; + + dget(dentry); + ret = simple_unlink(dir, dentry); + d_delete(dentry); + dput(dentry); + return ret; +} + +static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + struct rpc_inode *rpci = RPC_I(inode); + + rpci->nkern_readwriters--; + if (rpci->nkern_readwriters != 0) + return 0; + rpc_close_pipes(inode); + return __rpc_unlink(dir, dentry); +} + +static struct dentry *__rpc_lookup_create(struct dentry *parent, + struct qstr *name) { - struct inode *dir = parent->d_inode; struct dentry *dentry; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(name, parent, len); - if (IS_ERR(dentry)) - goto out_err; + dentry = d_lookup(parent, name); + if (!dentry) { + dentry = d_alloc(parent, name); + if (!dentry) { + dentry = ERR_PTR(-ENOMEM); + goto out_err; + } + } if (!dentry->d_inode) dentry->d_op = &rpc_dentry_operations; - else if (exclusive) { - dput(dentry); - dentry = ERR_PTR(-EEXIST); - goto out_err; - } - return dentry; out_err: - mutex_unlock(&dir->i_mutex); return dentry; } -static struct dentry * -rpc_lookup_negative(char *path, struct nameidata *nd) +static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, + struct qstr *name) { struct dentry *dentry; - int error; - if ((error = rpc_lookup_parent(path, nd)) != 0) - return ERR_PTR(error); - dentry = rpc_lookup_create(nd->path.dentry, nd->last.name, nd->last.len, - 1); - if (IS_ERR(dentry)) - rpc_release_path(nd); - return dentry; + dentry = __rpc_lookup_create(parent, name); + if (dentry->d_inode == NULL) + return dentry; + dput(dentry); + return ERR_PTR(-EEXIST); } -/** - * rpc_mkdir - Create a new directory in rpc_pipefs - * @path: path from the rpc_pipefs root to the new directory - * @rpc_client: rpc client to associate with this directory - * - * This creates a directory at the given @path associated with - * @rpc_clnt, which will contain a file named "info" with some basic - * information about the client, together with any "pipes" that may - * later be created using rpc_mkpipe(). +/* + * FIXME: This probably has races. */ -struct dentry * -rpc_mkdir(char *path, struct rpc_clnt *rpc_client) +static void __rpc_depopulate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof) { - struct nameidata nd; + struct inode *dir = parent->d_inode; struct dentry *dentry; - struct inode *dir; + struct qstr name; + int i; + + for (i = start; i < eof; i++) { + name.name = files[i].name; + name.len = strlen(files[i].name); + name.hash = full_name_hash(name.name, name.len); + dentry = d_lookup(parent, &name); + + if (dentry == NULL) + continue; + if (dentry->d_inode == NULL) + goto next; + switch (dentry->d_inode->i_mode & S_IFMT) { + default: + BUG(); + case S_IFREG: + __rpc_unlink(dir, dentry); + break; + case S_IFDIR: + __rpc_rmdir(dir, dentry); + } +next: + dput(dentry); + } +} + +static void rpc_depopulate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof) +{ + struct inode *dir = parent->d_inode; + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD); + __rpc_depopulate(parent, files, start, eof); + mutex_unlock(&dir->i_mutex); +} + +static int rpc_populate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof, + void *private) +{ + struct inode *dir = parent->d_inode; + struct dentry *dentry; + int i, err; + + mutex_lock(&dir->i_mutex); + for (i = start; i < eof; i++) { + struct qstr q; + + q.name = files[i].name; + q.len = strlen(files[i].name); + q.hash = full_name_hash(q.name, q.len); + dentry = __rpc_lookup_create_exclusive(parent, &q); + err = PTR_ERR(dentry); + if (IS_ERR(dentry)) + goto out_bad; + switch (files[i].mode & S_IFMT) { + default: + BUG(); + case S_IFREG: + err = __rpc_create(dir, dentry, + files[i].mode, + files[i].i_fop, + private); + break; + case S_IFDIR: + err = __rpc_mkdir(dir, dentry, + files[i].mode, + NULL, + private); + } + if (err != 0) + goto out_bad; + } + mutex_unlock(&dir->i_mutex); + return 0; +out_bad: + __rpc_depopulate(parent, files, start, eof); + mutex_unlock(&dir->i_mutex); + printk(KERN_WARNING "%s: %s failed to populate directory %s\n", + __FILE__, __func__, parent->d_name.name); + return err; +} + +static struct dentry *rpc_mkdir_populate(struct dentry *parent, + struct qstr *name, umode_t mode, void *private, + int (*populate)(struct dentry *, void *), void *args_populate) +{ + struct dentry *dentry; + struct inode *dir = parent->d_inode; int error; - dentry = rpc_lookup_negative(path, &nd); + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create_exclusive(parent, name); if (IS_ERR(dentry)) - return dentry; - dir = nd.path.dentry->d_inode; - if ((error = __rpc_mkdir(dir, dentry)) != 0) - goto err_dput; - RPC_I(dentry->d_inode)->private = rpc_client; - error = rpc_populate(dentry, authfiles, - RPCAUTH_info, RPCAUTH_EOF); - if (error) - goto err_depopulate; - dget(dentry); + goto out; + error = __rpc_mkdir(dir, dentry, mode, NULL, private); + if (error != 0) + goto out_err; + if (populate != NULL) { + error = populate(dentry, args_populate); + if (error) + goto err_rmdir; + } out: mutex_unlock(&dir->i_mutex); - rpc_release_path(&nd); return dentry; -err_depopulate: - rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); +err_rmdir: __rpc_rmdir(dir, dentry); -err_dput: - dput(dentry); - printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %d)\n", - __FILE__, __func__, path, error); +out_err: dentry = ERR_PTR(error); goto out; } -/** - * rpc_rmdir - Remove a directory created with rpc_mkdir() - * @dentry: directory to remove - */ -int -rpc_rmdir(struct dentry *dentry) +static int rpc_rmdir_depopulate(struct dentry *dentry, + void (*depopulate)(struct dentry *)) { struct dentry *parent; struct inode *dir; @@ -748,9 +728,9 @@ rpc_rmdir(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); + if (depopulate != NULL) + depopulate(dentry); error = __rpc_rmdir(dir, dentry); - dput(dentry); mutex_unlock(&dir->i_mutex); dput(parent); return error; @@ -776,50 +756,54 @@ rpc_rmdir(struct dentry *dentry) * The @private argument passed here will be available to all these methods * from the file pointer, via RPC_I(file->f_dentry->d_inode)->private. */ -struct dentry * -rpc_mkpipe(struct dentry *parent, const char *name, void *private, struct rpc_pipe_ops *ops, int flags) +struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, + void *private, const struct rpc_pipe_ops *ops, + int flags) { struct dentry *dentry; - struct inode *dir, *inode; - struct rpc_inode *rpci; + struct inode *dir = parent->d_inode; + umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR; + struct qstr q; + int err; + + if (ops->upcall == NULL) + umode &= ~S_IRUGO; + if (ops->downcall == NULL) + umode &= ~S_IWUGO; - dentry = rpc_lookup_create(parent, name, strlen(name), 0); + q.name = name; + q.len = strlen(name); + q.hash = full_name_hash(q.name, q.len), + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create(parent, &q); if (IS_ERR(dentry)) - return dentry; - dir = parent->d_inode; + goto out; if (dentry->d_inode) { - rpci = RPC_I(dentry->d_inode); + struct rpc_inode *rpci = RPC_I(dentry->d_inode); if (rpci->private != private || rpci->ops != ops || rpci->flags != flags) { dput (dentry); - dentry = ERR_PTR(-EBUSY); + err = -EBUSY; + goto out_err; } rpci->nkern_readwriters++; goto out; } - inode = rpc_get_inode(dir->i_sb, S_IFIFO | S_IRUSR | S_IWUSR); - if (!inode) - goto err_dput; - inode->i_ino = iunique(dir->i_sb, 100); - inode->i_fop = &rpc_pipe_fops; - d_instantiate(dentry, inode); - rpci = RPC_I(inode); - rpci->private = private; - rpci->flags = flags; - rpci->ops = ops; - rpci->nkern_readwriters = 1; - fsnotify_create(dir, dentry); - dget(dentry); + + err = __rpc_mkpipe(dir, dentry, umode, &rpc_pipe_fops, + private, ops, flags); + if (err) + goto out_err; out: mutex_unlock(&dir->i_mutex); return dentry; -err_dput: - dput(dentry); - dentry = ERR_PTR(-ENOMEM); +out_err: + dentry = ERR_PTR(err); printk(KERN_WARNING "%s: %s() failed to create pipe %s/%s (errno = %d)\n", __FILE__, __func__, parent->d_name.name, name, - -ENOMEM); + err); goto out; } EXPORT_SYMBOL_GPL(rpc_mkpipe); @@ -842,23 +826,112 @@ rpc_unlink(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - if (--RPC_I(dentry->d_inode)->nkern_readwriters == 0) { - rpc_close_pipes(dentry->d_inode); - error = simple_unlink(dir, dentry); - if (!error) - d_delete(dentry); - } - dput(dentry); + error = __rpc_rmpipe(dir, dentry); mutex_unlock(&dir->i_mutex); dput(parent); return error; } EXPORT_SYMBOL_GPL(rpc_unlink); +enum { + RPCAUTH_info, + RPCAUTH_EOF +}; + +static const struct rpc_filelist authfiles[] = { + [RPCAUTH_info] = { + .name = "info", + .i_fop = &rpc_info_operations, + .mode = S_IFREG | S_IRUSR, + }, +}; + +static int rpc_clntdir_populate(struct dentry *dentry, void *private) +{ + return rpc_populate(dentry, + authfiles, RPCAUTH_info, RPCAUTH_EOF, + private); +} + +static void rpc_clntdir_depopulate(struct dentry *dentry) +{ + rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF); +} + +/** + * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs + * @dentry: dentry from the rpc_pipefs root to the new directory + * @name: &struct qstr for the name + * @rpc_client: rpc client to associate with this directory + * + * This creates a directory at the given @path associated with + * @rpc_clnt, which will contain a file named "info" with some basic + * information about the client, together with any "pipes" that may + * later be created using rpc_mkpipe(). + */ +struct dentry *rpc_create_client_dir(struct dentry *dentry, + struct qstr *name, + struct rpc_clnt *rpc_client) +{ + return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, NULL, + rpc_clntdir_populate, rpc_client); +} + +/** + * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() + * @dentry: directory to remove + */ +int rpc_remove_client_dir(struct dentry *dentry) +{ + return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate); +} + +static const struct rpc_filelist cache_pipefs_files[3] = { + [0] = { + .name = "channel", + .i_fop = &cache_file_operations_pipefs, + .mode = S_IFREG|S_IRUSR|S_IWUSR, + }, + [1] = { + .name = "content", + .i_fop = &content_file_operations_pipefs, + .mode = S_IFREG|S_IRUSR, + }, + [2] = { + .name = "flush", + .i_fop = &cache_flush_operations_pipefs, + .mode = S_IFREG|S_IRUSR|S_IWUSR, + }, +}; + +static int rpc_cachedir_populate(struct dentry *dentry, void *private) +{ + return rpc_populate(dentry, + cache_pipefs_files, 0, 3, + private); +} + +static void rpc_cachedir_depopulate(struct dentry *dentry) +{ + rpc_depopulate(dentry, cache_pipefs_files, 0, 3); +} + +struct dentry *rpc_create_cache_dir(struct dentry *parent, struct qstr *name, + mode_t umode, struct cache_detail *cd) +{ + return rpc_mkdir_populate(parent, name, umode, NULL, + rpc_cachedir_populate, cd); +} + +void rpc_remove_cache_dir(struct dentry *dentry) +{ + rpc_rmdir_depopulate(dentry, rpc_cachedir_depopulate); +} + /* * populate the filesystem */ -static struct super_operations s_ops = { +static const struct super_operations s_ops = { .alloc_inode = rpc_alloc_inode, .destroy_inode = rpc_destroy_inode, .statfs = simple_statfs, @@ -866,6 +939,51 @@ static struct super_operations s_ops = { #define RPCAUTH_GSSMAGIC 0x67596969 +/* + * We have a single directory with 1 node in it. + */ +enum { + RPCAUTH_lockd, + RPCAUTH_mount, + RPCAUTH_nfs, + RPCAUTH_portmap, + RPCAUTH_statd, + RPCAUTH_nfsd4_cb, + RPCAUTH_cache, + RPCAUTH_RootEOF +}; + +static const struct rpc_filelist files[] = { + [RPCAUTH_lockd] = { + .name = "lockd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_mount] = { + .name = "mount", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_nfs] = { + .name = "nfs", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_portmap] = { + .name = "portmap", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_statd] = { + .name = "statd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_nfsd4_cb] = { + .name = "nfsd4_cb", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_cache] = { + .name = "cache", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, +}; + static int rpc_fill_super(struct super_block *sb, void *data, int silent) { @@ -886,7 +1004,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) iput(inode); return -ENOMEM; } - if (rpc_populate(root, files, RPCAUTH_Root + 1, RPCAUTH_RootEOF)) + if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL)) goto out; sb->s_root = root; return 0; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index beee6da3303..830faf4d999 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -75,6 +75,37 @@ enum { #define RPCB_OWNER_STRING "0" #define RPCB_MAXOWNERLEN sizeof(RPCB_OWNER_STRING) +/* + * XDR data type sizes + */ +#define RPCB_program_sz (1) +#define RPCB_version_sz (1) +#define RPCB_protocol_sz (1) +#define RPCB_port_sz (1) +#define RPCB_boolean_sz (1) + +#define RPCB_netid_sz (1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN)) +#define RPCB_addr_sz (1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) +#define RPCB_ownerstring_sz (1 + XDR_QUADLEN(RPCB_MAXOWNERLEN)) + +/* + * XDR argument and result sizes + */ +#define RPCB_mappingargs_sz (RPCB_program_sz + RPCB_version_sz + \ + RPCB_protocol_sz + RPCB_port_sz) +#define RPCB_getaddrargs_sz (RPCB_program_sz + RPCB_version_sz + \ + RPCB_netid_sz + RPCB_addr_sz + \ + RPCB_ownerstring_sz) + +#define RPCB_getportres_sz RPCB_port_sz +#define RPCB_setres_sz RPCB_boolean_sz + +/* + * Note that RFC 1833 does not put any size restrictions on the + * address string returned by the remote rpcbind database. + */ +#define RPCB_getaddrres_sz RPCB_addr_sz + static void rpcb_getport_done(struct rpc_task *, void *); static void rpcb_map_release(void *data); static struct rpc_program rpcb_program; @@ -122,6 +153,7 @@ static void rpcb_map_release(void *data) rpcb_wake_rpcbind_waiters(map->r_xprt, map->r_status); xprt_put(map->r_xprt); + kfree(map->r_addr); kfree(map); } @@ -268,12 +300,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap, const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin->sin_port); - char buf[32]; + int result; - /* Construct AF_INET universal address */ - snprintf(buf, sizeof(buf), "%pI4.%u.%u", - &sin->sin_addr.s_addr, port >> 8, port & 0xff); - map->r_addr = buf; + map->r_addr = rpc_sockaddr2uaddr(sap); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -284,7 +313,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(RPCBVERS_4, msg); + kfree(map->r_addr); + return result; } /* @@ -296,16 +327,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap, const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin6->sin6_port); - char buf[64]; + int result; - /* Construct AF_INET6 universal address */ - if (ipv6_addr_any(&sin6->sin6_addr)) - snprintf(buf, sizeof(buf), "::.%u.%u", - port >> 8, port & 0xff); - else - snprintf(buf, sizeof(buf), "%pI6.%u.%u", - &sin6->sin6_addr, port >> 8, port & 0xff); - map->r_addr = buf; + map->r_addr = rpc_sockaddr2uaddr(sap); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -316,7 +340,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(RPCBVERS_4, msg); + kfree(map->r_addr); + return result; } static int rpcb_unregister_all_protofamilies(struct rpc_message *msg) @@ -428,7 +454,7 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot) struct rpc_message msg = { .rpc_proc = &rpcb_procedures2[RPCBPROC_GETPORT], .rpc_argp = &map, - .rpc_resp = &map.r_port, + .rpc_resp = &map, }; struct rpc_clnt *rpcb_clnt; int status; @@ -458,7 +484,7 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi struct rpc_message msg = { .rpc_proc = proc, .rpc_argp = map, - .rpc_resp = &map->r_port, + .rpc_resp = map, }; struct rpc_task_setup task_setup_data = { .rpc_client = rpcb_clnt, @@ -539,6 +565,7 @@ void rpcb_getport_async(struct rpc_task *task) goto bailout_nofree; } + /* Parent transport's destination address */ salen = rpc_peeraddr(clnt, sap, sizeof(addr)); /* Don't ever use rpcbind v2 for AF_INET6 requests */ @@ -589,11 +616,22 @@ void rpcb_getport_async(struct rpc_task *task) map->r_prot = xprt->prot; map->r_port = 0; map->r_xprt = xprt_get(xprt); - map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); - map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR); - map->r_owner = ""; map->r_status = -EIO; + switch (bind_version) { + case RPCBVERS_4: + case RPCBVERS_3: + map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); + map->r_addr = rpc_sockaddr2uaddr(sap); + map->r_owner = ""; + break; + case RPCBVERS_2: + map->r_addr = NULL; + break; + default: + BUG(); + } + child = rpcb_call_async(rpcb_clnt, map, proc); rpc_release_client(rpcb_clnt); if (IS_ERR(child)) { @@ -656,176 +694,278 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) * XDR functions for rpcbind */ -static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p, - struct rpcbind_args *rpcb) +static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, + const struct rpcbind_args *rpcb) { - dprintk("RPC: encoding rpcb request (%u, %u, %d, %u)\n", + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + + p = xdr_reserve_space(&xdr, sizeof(__be32) * RPCB_mappingargs_sz); + if (unlikely(p == NULL)) + return -EIO; + *p++ = htonl(rpcb->r_prog); *p++ = htonl(rpcb->r_vers); *p++ = htonl(rpcb->r_prot); - *p++ = htonl(rpcb->r_port); + *p = htonl(rpcb->r_port); - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); return 0; } -static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p, - unsigned short *portp) +static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, + struct rpcbind_args *rpcb) { - *portp = (unsigned short) ntohl(*p++); - dprintk("RPC: rpcb getport result: %u\n", - *portp); + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + unsigned long port; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + rpcb->r_port = 0; + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + return -EIO; + + port = ntohl(*p); + dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid, + task->tk_msg.rpc_proc->p_name, port); + if (unlikely(port > USHORT_MAX)) + return -EIO; + + rpcb->r_port = port; return 0; } -static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, - unsigned int *boolp) +static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, + unsigned int *boolp) { - *boolp = (unsigned int) ntohl(*p++); - dprintk("RPC: rpcb set/unset call %s\n", + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + return -EIO; + + *boolp = 0; + if (*p) + *boolp = 1; + + dprintk("RPC: %5u RPCB_%s call %s\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, (*boolp ? "succeeded" : "failed")); return 0; } -static int rpcb_encode_getaddr(struct rpc_rqst *req, __be32 *p, - struct rpcbind_args *rpcb) +static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, + const u32 maxstrlen) { - dprintk("RPC: encoding rpcb request (%u, %u, %s)\n", - rpcb->r_prog, rpcb->r_vers, rpcb->r_addr); - *p++ = htonl(rpcb->r_prog); - *p++ = htonl(rpcb->r_vers); + u32 len; + __be32 *p; - p = xdr_encode_string(p, rpcb->r_netid); - p = xdr_encode_string(p, rpcb->r_addr); - p = xdr_encode_string(p, rpcb->r_owner); + if (unlikely(string == NULL)) + return -EIO; + len = strlen(string); + if (unlikely(len > maxstrlen)) + return -EIO; - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); + p = xdr_reserve_space(xdr, sizeof(__be32) + len); + if (unlikely(p == NULL)) + return -EIO; + xdr_encode_opaque(p, string, len); return 0; } -static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p, - unsigned short *portp) +static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p, + const struct rpcbind_args *rpcb) { - char *addr; - u32 addr_len; - int c, i, f, first, val; + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; - *portp = 0; - addr_len = ntohl(*p++); + dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, + rpcb->r_prog, rpcb->r_vers, + rpcb->r_netid, rpcb->r_addr); - if (addr_len == 0) { - dprintk("RPC: rpcb_decode_getaddr: " - "service is not registered\n"); - return 0; - } + xdr_init_encode(&xdr, &req->rq_snd_buf, p); - /* - * Simple sanity check. - */ - if (addr_len > RPCBIND_MAXUADDRLEN) - goto out_err; - - /* - * Start at the end and walk backwards until the first dot - * is encountered. When the second dot is found, we have - * both parts of the port number. - */ - addr = (char *)p; - val = 0; - first = 1; - f = 1; - for (i = addr_len - 1; i > 0; i--) { - c = addr[i]; - if (c >= '0' && c <= '9') { - val += (c - '0') * f; - f *= 10; - } else if (c == '.') { - if (first) { - *portp = val; - val = first = 0; - f = 1; - } else { - *portp |= (val << 8); - break; - } - } - } + p = xdr_reserve_space(&xdr, + sizeof(__be32) * (RPCB_program_sz + RPCB_version_sz)); + if (unlikely(p == NULL)) + return -EIO; + *p++ = htonl(rpcb->r_prog); + *p = htonl(rpcb->r_vers); - /* - * Simple sanity check. If we never saw a dot in the reply, - * then this was probably just garbage. - */ - if (first) - goto out_err; + if (encode_rpcb_string(&xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN)) + return -EIO; + if (encode_rpcb_string(&xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN)) + return -EIO; + if (encode_rpcb_string(&xdr, rpcb->r_owner, RPCB_MAXOWNERLEN)) + return -EIO; - dprintk("RPC: rpcb_decode_getaddr port=%u\n", *portp); return 0; - -out_err: - dprintk("RPC: rpcbind server returned malformed reply\n"); - return -EIO; } -#define RPCB_program_sz (1u) -#define RPCB_version_sz (1u) -#define RPCB_protocol_sz (1u) -#define RPCB_port_sz (1u) -#define RPCB_boolean_sz (1u) +static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, + struct rpcbind_args *rpcb) +{ + struct sockaddr_storage address; + struct sockaddr *sap = (struct sockaddr *)&address; + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + u32 len; -#define RPCB_netid_sz (1+XDR_QUADLEN(RPCBIND_MAXNETIDLEN)) -#define RPCB_addr_sz (1+XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) -#define RPCB_ownerstring_sz (1+XDR_QUADLEN(RPCB_MAXOWNERLEN)) + rpcb->r_port = 0; -#define RPCB_mappingargs_sz RPCB_program_sz+RPCB_version_sz+ \ - RPCB_protocol_sz+RPCB_port_sz -#define RPCB_getaddrargs_sz RPCB_program_sz+RPCB_version_sz+ \ - RPCB_netid_sz+RPCB_addr_sz+ \ - RPCB_ownerstring_sz + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); -#define RPCB_setres_sz RPCB_boolean_sz -#define RPCB_getportres_sz RPCB_port_sz - -/* - * Note that RFC 1833 does not put any size restrictions on the - * address string returned by the remote rpcbind database. - */ -#define RPCB_getaddrres_sz RPCB_addr_sz + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + goto out_fail; + len = ntohl(*p); -#define PROC(proc, argtype, restype) \ - [RPCBPROC_##proc] = { \ - .p_proc = RPCBPROC_##proc, \ - .p_encode = (kxdrproc_t) rpcb_encode_##argtype, \ - .p_decode = (kxdrproc_t) rpcb_decode_##restype, \ - .p_arglen = RPCB_##argtype##args_sz, \ - .p_replen = RPCB_##restype##res_sz, \ - .p_statidx = RPCBPROC_##proc, \ - .p_timer = 0, \ - .p_name = #proc, \ + /* + * If the returned universal address is a null string, + * the requested RPC service was not registered. + */ + if (len == 0) { + dprintk("RPC: %5u RPCB reply: program not registered\n", + task->tk_pid); + return 0; } + if (unlikely(len > RPCBIND_MAXUADDRLEN)) + goto out_fail; + + p = xdr_inline_decode(&xdr, len); + if (unlikely(p == NULL)) + goto out_fail; + dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid, + task->tk_msg.rpc_proc->p_name, (char *)p); + + if (rpc_uaddr2sockaddr((char *)p, len, sap, sizeof(address)) == 0) + goto out_fail; + rpcb->r_port = rpc_get_port(sap); + + return 0; + +out_fail: + dprintk("RPC: %5u malformed RPCB_%s reply\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name); + return -EIO; +} + /* * Not all rpcbind procedures described in RFC 1833 are implemented * since the Linux kernel RPC code requires only these. */ + static struct rpc_procinfo rpcb_procedures2[] = { - PROC(SET, mapping, set), - PROC(UNSET, mapping, set), - PROC(GETPORT, mapping, getport), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETPORT] = { + .p_proc = RPCBPROC_GETPORT, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_getport, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_getportres_sz, + .p_statidx = RPCBPROC_GETPORT, + .p_timer = 0, + .p_name = "GETPORT", + }, }; static struct rpc_procinfo rpcb_procedures3[] = { - PROC(SET, getaddr, set), - PROC(UNSET, getaddr, set), - PROC(GETADDR, getaddr, getaddr), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETADDR] = { + .p_proc = RPCBPROC_GETADDR, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_getaddrres_sz, + .p_statidx = RPCBPROC_GETADDR, + .p_timer = 0, + .p_name = "GETADDR", + }, }; static struct rpc_procinfo rpcb_procedures4[] = { - PROC(SET, getaddr, set), - PROC(UNSET, getaddr, set), - PROC(GETADDR, getaddr, getaddr), - PROC(GETVERSADDR, getaddr, getaddr), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETADDR] = { + .p_proc = RPCBPROC_GETADDR, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_getaddrres_sz, + .p_statidx = RPCBPROC_GETADDR, + .p_timer = 0, + .p_name = "GETADDR", + }, }; static struct rpcb_info rpcb_next_version[] = { diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 8f459abe97c..cef74ba0666 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -21,6 +21,8 @@ #include <linux/sunrpc/clnt.h> +#include "sunrpc.h" + #ifdef RPC_DEBUG #define RPCDBG_FACILITY RPCDBG_SCHED #define RPC_TASK_MAGIC_ID 0xf00baa @@ -711,11 +713,6 @@ static void rpc_async_schedule(struct work_struct *work) __rpc_execute(container_of(work, struct rpc_task, u.tk_work)); } -struct rpc_buffer { - size_t len; - char data[]; -}; - /** * rpc_malloc - allocate an RPC buffer * @task: RPC task that will use this buffer diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index 5d9dd742264..90c292e2738 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -27,11 +27,25 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #ifndef _NET_SUNRPC_SUNRPC_H #define _NET_SUNRPC_SUNRPC_H +#include <linux/net.h> + +/* + * Header for dynamically allocated rpc buffers. + */ +struct rpc_buffer { + size_t len; + char data[]; +}; + static inline int rpc_reply_expected(struct rpc_task *task) { return (task->tk_msg.rpc_proc != NULL) && (task->tk_msg.rpc_proc->p_decode != NULL); } +int svc_send_common(struct socket *sock, struct xdr_buf *xdr, + struct page *headpage, unsigned long headoffset, + struct page *tailpage, unsigned long tailoffset); + #endif /* _NET_SUNRPC_SUNRPC_H */ diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index adaa81982f7..8cce9218901 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -69,5 +69,5 @@ cleanup_sunrpc(void) rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_LICENSE("GPL"); -module_init(init_sunrpc); +fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */ module_exit(cleanup_sunrpc); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 27d44332f01..df124f78ee4 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -160,6 +160,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt, mutex_init(&xprt->xpt_mutex); spin_lock_init(&xprt->xpt_lock); set_bit(XPT_BUSY, &xprt->xpt_flags); + rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending"); } EXPORT_SYMBOL_GPL(svc_xprt_init); @@ -710,10 +711,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) spin_unlock_bh(&pool->sp_lock); len = 0; - if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) { - dprintk("svc_recv: found XPT_CLOSE\n"); - svc_delete_xprt(xprt); - } else if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) { + if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) { struct svc_xprt *newxpt; newxpt = xprt->xpt_ops->xpo_accept(xprt); if (newxpt) { @@ -739,7 +737,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) svc_xprt_received(newxpt); } svc_xprt_received(xprt); - } else { + } else if (!test_bit(XPT_CLOSE, &xprt->xpt_flags)) { dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", rqstp, pool->sp_id, xprt, atomic_read(&xprt->xpt_ref.refcount)); @@ -752,6 +750,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) dprintk("svc: got len=%d\n", len); } + if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) { + dprintk("svc_recv: found XPT_CLOSE\n"); + svc_delete_xprt(xprt); + } + /* No data, incomplete (TCP) read, or accept() */ if (len == 0 || len == -EAGAIN) { rqstp->rq_res.len = 0; @@ -808,6 +811,7 @@ int svc_send(struct svc_rqst *rqstp) else len = xprt->xpt_ops->xpo_sendto(rqstp); mutex_unlock(&xprt->xpt_mutex); + rpc_wake_up(&xprt->xpt_bc_pending); svc_xprt_release(rqstp); if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN) @@ -1166,11 +1170,6 @@ static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos) dprintk("svc_pool_stats_start, *pidx=%u\n", pidx); - lock_kernel(); - /* bump up the pseudo refcount while traversing */ - svc_get(serv); - unlock_kernel(); - if (!pidx) return SEQ_START_TOKEN; return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]); @@ -1198,12 +1197,6 @@ static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos) static void svc_pool_stats_stop(struct seq_file *m, void *p) { - struct svc_serv *serv = m->private; - - lock_kernel(); - /* this function really, really should have been called svc_put() */ - svc_destroy(serv); - unlock_kernel(); } static int svc_pool_stats_show(struct seq_file *m, void *p) diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 5c865e2d299..117f68a8aa4 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -171,6 +171,11 @@ static void ip_map_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, ip_map_request); +} + static struct ip_map *ip_map_lookup(char *class, struct in6_addr *addr); static int ip_map_update(struct ip_map *ipm, struct unix_domain *udom, time_t expiry); @@ -289,7 +294,7 @@ struct cache_detail ip_map_cache = { .hash_table = ip_table, .name = "auth.unix.ip", .cache_put = ip_map_put, - .cache_request = ip_map_request, + .cache_upcall = ip_map_upcall, .cache_parse = ip_map_parse, .cache_show = ip_map_show, .match = ip_map_match, @@ -523,6 +528,11 @@ static void unix_gid_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int unix_gid_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, unix_gid_request); +} + static struct unix_gid *unix_gid_lookup(uid_t uid); extern struct cache_detail unix_gid_cache; @@ -622,7 +632,7 @@ struct cache_detail unix_gid_cache = { .hash_table = gid_table, .name = "auth.unix.gid", .cache_put = unix_gid_put, - .cache_request = unix_gid_request, + .cache_upcall = unix_gid_upcall, .cache_parse = unix_gid_parse, .cache_show = unix_gid_show, .match = unix_gid_match, @@ -658,6 +668,7 @@ static int unix_gid_find(uid_t uid, struct group_info **gip, case 0: *gip = ug->gi; get_group_info(*gip); + cache_put(&ug->h, &unix_gid_cache); return 0; default: return -EAGAIN; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 23128ee191a..1c246a4f491 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -49,6 +49,7 @@ #include <linux/sunrpc/msg_prot.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/stats.h> +#include <linux/sunrpc/xprt.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -110,7 +111,7 @@ static void svc_release_skb(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; dprintk("svc: service %p, releasing skb %p\n", rqstp, skb); - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); } } @@ -153,49 +154,27 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh) } /* - * Generic sendto routine + * send routine intended to be shared by the fore- and back-channel */ -static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) +int svc_send_common(struct socket *sock, struct xdr_buf *xdr, + struct page *headpage, unsigned long headoffset, + struct page *tailpage, unsigned long tailoffset) { - struct svc_sock *svsk = - container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); - struct socket *sock = svsk->sk_sock; - int slen; - union { - struct cmsghdr hdr; - long all[SVC_PKTINFO_SPACE / sizeof(long)]; - } buffer; - struct cmsghdr *cmh = &buffer.hdr; - int len = 0; int result; int size; struct page **ppage = xdr->pages; size_t base = xdr->page_base; unsigned int pglen = xdr->page_len; unsigned int flags = MSG_MORE; - RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); + int slen; + int len = 0; slen = xdr->len; - if (rqstp->rq_prot == IPPROTO_UDP) { - struct msghdr msg = { - .msg_name = &rqstp->rq_addr, - .msg_namelen = rqstp->rq_addrlen, - .msg_control = cmh, - .msg_controllen = sizeof(buffer), - .msg_flags = MSG_MORE, - }; - - svc_set_cmsg_data(rqstp, cmh); - - if (sock_sendmsg(sock, &msg, 0) < 0) - goto out; - } - /* send head */ if (slen == xdr->head[0].iov_len) flags = 0; - len = kernel_sendpage(sock, rqstp->rq_respages[0], 0, + len = kernel_sendpage(sock, headpage, headoffset, xdr->head[0].iov_len, flags); if (len != xdr->head[0].iov_len) goto out; @@ -219,16 +198,58 @@ static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) base = 0; ppage++; } + /* send tail */ if (xdr->tail[0].iov_len) { - result = kernel_sendpage(sock, rqstp->rq_respages[0], - ((unsigned long)xdr->tail[0].iov_base) - & (PAGE_SIZE-1), - xdr->tail[0].iov_len, 0); - + result = kernel_sendpage(sock, tailpage, tailoffset, + xdr->tail[0].iov_len, 0); if (result > 0) len += result; } + +out: + return len; +} + + +/* + * Generic sendto routine + */ +static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) +{ + struct svc_sock *svsk = + container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); + struct socket *sock = svsk->sk_sock; + union { + struct cmsghdr hdr; + long all[SVC_PKTINFO_SPACE / sizeof(long)]; + } buffer; + struct cmsghdr *cmh = &buffer.hdr; + int len = 0; + unsigned long tailoff; + unsigned long headoff; + RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); + + if (rqstp->rq_prot == IPPROTO_UDP) { + struct msghdr msg = { + .msg_name = &rqstp->rq_addr, + .msg_namelen = rqstp->rq_addrlen, + .msg_control = cmh, + .msg_controllen = sizeof(buffer), + .msg_flags = MSG_MORE, + }; + + svc_set_cmsg_data(rqstp, cmh); + + if (sock_sendmsg(sock, &msg, 0) < 0) + goto out; + } + + tailoff = ((unsigned long)xdr->tail[0].iov_base) & (PAGE_SIZE-1); + headoff = 0; + len = svc_send_common(sock, xdr, rqstp->rq_respages[0], headoff, + rqstp->rq_respages[0], tailoff); + out: dprintk("svc: socket %p sendto([%p %Zu... ], %d) = %d (addr %s)\n", svsk, xdr->head[0].iov_base, xdr->head[0].iov_len, @@ -432,29 +453,49 @@ static void svc_tcp_write_space(struct sock *sk) } /* + * See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo + */ +static int svc_udp_get_dest_address4(struct svc_rqst *rqstp, + struct cmsghdr *cmh) +{ + struct in_pktinfo *pki = CMSG_DATA(cmh); + if (cmh->cmsg_type != IP_PKTINFO) + return 0; + rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr; + return 1; +} + +/* + * See net/ipv6/datagram.c : datagram_recv_ctl + */ +static int svc_udp_get_dest_address6(struct svc_rqst *rqstp, + struct cmsghdr *cmh) +{ + struct in6_pktinfo *pki = CMSG_DATA(cmh); + if (cmh->cmsg_type != IPV6_PKTINFO) + return 0; + ipv6_addr_copy(&rqstp->rq_daddr.addr6, &pki->ipi6_addr); + return 1; +} + +/* * Copy the UDP datagram's destination address to the rqstp structure. * The 'destination' address in this case is the address to which the * peer sent the datagram, i.e. our local address. For multihomed * hosts, this can change from msg to msg. Note that only the IP * address changes, the port number should remain the same. */ -static void svc_udp_get_dest_address(struct svc_rqst *rqstp, - struct cmsghdr *cmh) +static int svc_udp_get_dest_address(struct svc_rqst *rqstp, + struct cmsghdr *cmh) { - struct svc_sock *svsk = - container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); - switch (svsk->sk_sk->sk_family) { - case AF_INET: { - struct in_pktinfo *pki = CMSG_DATA(cmh); - rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr; - break; - } - case AF_INET6: { - struct in6_pktinfo *pki = CMSG_DATA(cmh); - ipv6_addr_copy(&rqstp->rq_daddr.addr6, &pki->ipi6_addr); - break; - } + switch (cmh->cmsg_level) { + case SOL_IP: + return svc_udp_get_dest_address4(rqstp, cmh); + case SOL_IPV6: + return svc_udp_get_dest_address6(rqstp, cmh); } + + return 0; } /* @@ -531,16 +572,15 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_prot = IPPROTO_UDP; - if (cmh->cmsg_level != IPPROTO_IP || - cmh->cmsg_type != IP_PKTINFO) { + if (!svc_udp_get_dest_address(rqstp, cmh)) { if (net_ratelimit()) - printk("rpcsvc: received unknown control message:" - "%d/%d\n", - cmh->cmsg_level, cmh->cmsg_type); - skb_free_datagram(svsk->sk_sk, skb); + printk(KERN_WARNING + "svc: received unknown control message %d/%d; " + "dropping RPC reply datagram\n", + cmh->cmsg_level, cmh->cmsg_type); + skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } - svc_udp_get_dest_address(rqstp, cmh); if (skb_is_nonlinear(skb)) { /* we have to copy */ @@ -548,18 +588,18 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) { local_bh_enable(); /* checksum error */ - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } local_bh_enable(); - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); } else { /* we can use it in-place */ rqstp->rq_arg.head[0].iov_base = skb->data + sizeof(struct udphdr); rqstp->rq_arg.head[0].iov_len = len; if (skb_checksum_complete(skb)) { - skb_free_datagram(svsk->sk_sk, skb); + skb_free_datagram_locked(svsk->sk_sk, skb); return 0; } rqstp->rq_xprt_ctxt = skb; @@ -651,8 +691,7 @@ static struct svc_xprt_class svc_udp_class = { static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) { - int one = 1; - mm_segment_t oldfs; + int err, level, optname, one = 1; svc_xprt_init(&svc_udp_class, &svsk->sk_xprt, serv); clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags); @@ -671,12 +710,22 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags); - oldfs = get_fs(); - set_fs(KERNEL_DS); /* make sure we get destination address info */ - svsk->sk_sock->ops->setsockopt(svsk->sk_sock, IPPROTO_IP, IP_PKTINFO, - (char __user *)&one, sizeof(one)); - set_fs(oldfs); + switch (svsk->sk_sk->sk_family) { + case AF_INET: + level = SOL_IP; + optname = IP_PKTINFO; + break; + case AF_INET6: + level = SOL_IPV6; + optname = IPV6_RECVPKTINFO; + break; + default: + BUG(); + } + err = kernel_setsockopt(svsk->sk_sock, level, optname, + (char *)&one, sizeof(one)); + dprintk("svc: kernel_setsockopt returned %d\n", err); } /* @@ -826,21 +875,15 @@ failed: } /* - * Receive data from a TCP socket. + * Receive data. + * If we haven't gotten the record length yet, get the next four bytes. + * Otherwise try to gobble up as much as possible up to the complete + * record length. */ -static int svc_tcp_recvfrom(struct svc_rqst *rqstp) +static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) { - struct svc_sock *svsk = - container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); struct svc_serv *serv = svsk->sk_xprt.xpt_server; - int len; - struct kvec *vec; - int pnum, vlen; - - dprintk("svc: tcp_recv %p data %d conn %d close %d\n", - svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags), - test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags), - test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)); + int len; if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags)) /* sndbuf needs to have room for one request @@ -861,10 +904,6 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - /* Receive data. If we haven't got the record length yet, get - * the next four bytes. Otherwise try to gobble up as much as - * possible up to the complete record length. - */ if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) { int want = sizeof(rpc_fraghdr) - svsk->sk_tcplen; struct kvec iov; @@ -879,7 +918,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) dprintk("svc: short recvfrom while reading record " "length (%d of %d)\n", len, want); svc_xprt_received(&svsk->sk_xprt); - return -EAGAIN; /* record header not complete */ + goto err_again; /* record header not complete */ } svsk->sk_reclen = ntohl(svsk->sk_reclen); @@ -894,6 +933,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) "per record not supported\n"); goto err_delete; } + svsk->sk_reclen &= RPC_FRAGMENT_SIZE_MASK; dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen); if (svsk->sk_reclen > serv->sv_max_mesg) { @@ -914,17 +954,121 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) dprintk("svc: incomplete TCP record (%d of %d)\n", len, svsk->sk_reclen); svc_xprt_received(&svsk->sk_xprt); - return -EAGAIN; /* record not complete */ + goto err_again; /* record not complete */ } len = svsk->sk_reclen; set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); + return len; + error: + if (len == -EAGAIN) { + dprintk("RPC: TCP recv_record got EAGAIN\n"); + svc_xprt_received(&svsk->sk_xprt); + } + return len; + err_delete: + set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); + err_again: + return -EAGAIN; +} + +static int svc_process_calldir(struct svc_sock *svsk, struct svc_rqst *rqstp, + struct rpc_rqst **reqpp, struct kvec *vec) +{ + struct rpc_rqst *req = NULL; + u32 *p; + u32 xid; + u32 calldir; + int len; + + len = svc_recvfrom(rqstp, vec, 1, 8); + if (len < 0) + goto error; + + p = (u32 *)rqstp->rq_arg.head[0].iov_base; + xid = *p++; + calldir = *p; + + if (calldir == 0) { + /* REQUEST is the most common case */ + vec[0] = rqstp->rq_arg.head[0]; + } else { + /* REPLY */ + if (svsk->sk_bc_xprt) + req = xprt_lookup_rqst(svsk->sk_bc_xprt, xid); + + if (!req) { + printk(KERN_NOTICE + "%s: Got unrecognized reply: " + "calldir 0x%x sk_bc_xprt %p xid %08x\n", + __func__, ntohl(calldir), + svsk->sk_bc_xprt, xid); + vec[0] = rqstp->rq_arg.head[0]; + goto out; + } + + memcpy(&req->rq_private_buf, &req->rq_rcv_buf, + sizeof(struct xdr_buf)); + /* copy the xid and call direction */ + memcpy(req->rq_private_buf.head[0].iov_base, + rqstp->rq_arg.head[0].iov_base, 8); + vec[0] = req->rq_private_buf.head[0]; + } + out: + vec[0].iov_base += 8; + vec[0].iov_len -= 8; + len = svsk->sk_reclen - 8; + error: + *reqpp = req; + return len; +} + +/* + * Receive data from a TCP socket. + */ +static int svc_tcp_recvfrom(struct svc_rqst *rqstp) +{ + struct svc_sock *svsk = + container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); + struct svc_serv *serv = svsk->sk_xprt.xpt_server; + int len; + struct kvec *vec; + int pnum, vlen; + struct rpc_rqst *req = NULL; + + dprintk("svc: tcp_recv %p data %d conn %d close %d\n", + svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags), + test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags), + test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)); + + len = svc_tcp_recv_record(svsk, rqstp); + if (len < 0) + goto error; + vec = rqstp->rq_vec; vec[0] = rqstp->rq_arg.head[0]; vlen = PAGE_SIZE; + + /* + * We have enough data for the whole tcp record. Let's try and read the + * first 8 bytes to get the xid and the call direction. We can use this + * to figure out if this is a call or a reply to a callback. If + * sk_reclen is < 8 (xid and calldir), then this is a malformed packet. + * In that case, don't bother with the calldir and just read the data. + * It will be rejected in svc_process. + */ + if (len >= 8) { + len = svc_process_calldir(svsk, rqstp, &req, vec); + if (len < 0) + goto err_again; + vlen -= 8; + } + pnum = 1; while (vlen < len) { - vec[pnum].iov_base = page_address(rqstp->rq_pages[pnum]); + vec[pnum].iov_base = (req) ? + page_address(req->rq_private_buf.pages[pnum - 1]) : + page_address(rqstp->rq_pages[pnum]); vec[pnum].iov_len = PAGE_SIZE; pnum++; vlen += PAGE_SIZE; @@ -934,8 +1078,18 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) /* Now receive data */ len = svc_recvfrom(rqstp, vec, pnum, len); if (len < 0) - goto error; + goto err_again; + /* + * Account for the 8 bytes we read earlier + */ + len += 8; + + if (req) { + xprt_complete_rqst(req->rq_task, len); + len = 0; + goto out; + } dprintk("svc: TCP complete record (%d bytes)\n", len); rqstp->rq_arg.len = len; rqstp->rq_arg.page_base = 0; @@ -949,6 +1103,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; rqstp->rq_prot = IPPROTO_TCP; +out: /* Reset TCP read info */ svsk->sk_reclen = 0; svsk->sk_tcplen = 0; @@ -960,21 +1115,19 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) return len; - err_delete: - set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); - return -EAGAIN; - - error: +err_again: if (len == -EAGAIN) { dprintk("RPC: TCP recvfrom got EAGAIN\n"); svc_xprt_received(&svsk->sk_xprt); - } else { + return len; + } +error: + if (len != -EAGAIN) { printk(KERN_NOTICE "%s: recvfrom returned errno %d\n", svsk->sk_xprt.xpt_server->sv_name, -len); - goto err_delete; + set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); } - - return len; + return -EAGAIN; } /* diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 5231f7aaac0..42f9748ae09 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -56,7 +56,7 @@ rpc_unregister_sysctl(void) } } -static int proc_do_xprt(ctl_table *table, int write, struct file *file, +static int proc_do_xprt(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[256]; @@ -71,7 +71,7 @@ static int proc_do_xprt(ctl_table *table, int write, struct file *file, } static int -proc_dodebug(ctl_table *table, int write, struct file *file, +proc_dodebug(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[20], c, *s; diff --git a/net/sunrpc/timer.c b/net/sunrpc/timer.c index 31becbf0926..dd824341c34 100644 --- a/net/sunrpc/timer.c +++ b/net/sunrpc/timer.c @@ -25,8 +25,13 @@ #define RPC_RTO_INIT (HZ/5) #define RPC_RTO_MIN (HZ/10) -void -rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) +/** + * rpc_init_rtt - Initialize an RPC RTT estimator context + * @rt: context to initialize + * @timeo: initial timeout value, in jiffies + * + */ +void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) { unsigned long init = 0; unsigned i; @@ -43,12 +48,16 @@ rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) } EXPORT_SYMBOL_GPL(rpc_init_rtt); -/* +/** + * rpc_update_rtt - Update an RPC RTT estimator context + * @rt: context to update + * @timer: timer array index (request type) + * @m: recent actual RTT, in jiffies + * * NB: When computing the smoothed RTT and standard deviation, * be careful not to produce negative intermediate results. */ -void -rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) +void rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) { long *srtt, *sdrtt; @@ -79,21 +88,25 @@ rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) } EXPORT_SYMBOL_GPL(rpc_update_rtt); -/* - * Estimate rto for an nfs rpc sent via. an unreliable datagram. - * Use the mean and mean deviation of rtt for the appropriate type of rpc - * for the frequent rpcs and a default for the others. - * The justification for doing "other" this way is that these rpcs - * happen so infrequently that timer est. would probably be stale. - * Also, since many of these rpcs are - * non-idempotent, a conservative timeout is desired. +/** + * rpc_calc_rto - Provide an estimated timeout value + * @rt: context to use for calculation + * @timer: timer array index (request type) + * + * Estimate RTO for an NFS RPC sent via an unreliable datagram. Use + * the mean and mean deviation of RTT for the appropriate type of RPC + * for frequently issued RPCs, and a fixed default for the others. + * + * The justification for doing "other" this way is that these RPCs + * happen so infrequently that timer estimation would probably be + * stale. Also, since many of these RPCs are non-idempotent, a + * conservative timeout is desired. + * * getattr, lookup, * read, write, commit - A+4D * other - timeo */ - -unsigned long -rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) +unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) { unsigned long res; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 406e26de584..8bd690c48b6 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -24,7 +24,7 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj) unsigned int quadlen = XDR_QUADLEN(obj->len); p[quadlen] = 0; /* zero trailing bytes */ - *p++ = htonl(obj->len); + *p++ = cpu_to_be32(obj->len); memcpy(p, obj->data, obj->len); return p + XDR_QUADLEN(obj->len); } @@ -35,7 +35,7 @@ xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj) { unsigned int len; - if ((len = ntohl(*p++)) > XDR_MAX_NETOBJ) + if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ) return NULL; obj->len = len; obj->data = (u8 *) p; @@ -83,7 +83,7 @@ EXPORT_SYMBOL_GPL(xdr_encode_opaque_fixed); */ __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int nbytes) { - *p++ = htonl(nbytes); + *p++ = cpu_to_be32(nbytes); return xdr_encode_opaque_fixed(p, ptr, nbytes); } EXPORT_SYMBOL_GPL(xdr_encode_opaque); @@ -101,7 +101,7 @@ xdr_decode_string_inplace(__be32 *p, char **sp, { u32 len; - len = ntohl(*p++); + len = be32_to_cpu(*p++); if (len > maxlen) return NULL; *lenp = len; @@ -771,7 +771,7 @@ xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj) status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj)); if (status) return status; - *obj = ntohl(raw); + *obj = be32_to_cpu(raw); return 0; } EXPORT_SYMBOL_GPL(xdr_decode_word); @@ -779,7 +779,7 @@ EXPORT_SYMBOL_GPL(xdr_decode_word); int xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj) { - __be32 raw = htonl(obj); + __be32 raw = cpu_to_be32(obj); return write_bytes_to_xdr_buf(buf, base, &raw, sizeof(obj)); } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index f412a852bc7..fd46d42afa8 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -832,6 +832,11 @@ static void xprt_timer(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); } +static inline int xprt_has_timer(struct rpc_xprt *xprt) +{ + return xprt->idle_timeout != 0; +} + /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request @@ -1013,7 +1018,7 @@ void xprt_release(struct rpc_task *task) if (!list_empty(&req->rq_list)) list_del(&req->rq_list); xprt->last_used = jiffies; - if (list_empty(&xprt->recv)) + if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); spin_unlock_bh(&xprt->transport_lock); @@ -1082,8 +1087,11 @@ found: #endif /* CONFIG_NFS_V4_1 */ INIT_WORK(&xprt->task_cleanup, xprt_autoclose); - setup_timer(&xprt->timer, xprt_init_autodisconnect, - (unsigned long)xprt); + if (xprt_has_timer(xprt)) + setup_timer(&xprt->timer, xprt_init_autodisconnect, + (unsigned long)xprt); + else + init_timer(&xprt->timer); xprt->last_used = jiffies; xprt->cwnd = RPC_INITCWND; xprt->bind_index = 0; @@ -1102,7 +1110,6 @@ found: dprintk("RPC: created transport %p with %u slots\n", xprt, xprt->max_reqs); - return xprt; } diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 87101177825..35fb68b9c8e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -80,7 +80,7 @@ struct kmem_cache *svc_rdma_ctxt_cachep; * current value. */ static int read_reset_stat(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { atomic_t *stat = (atomic_t *)table->data; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 5151f9f6c57..3fa5751af0e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -42,6 +42,7 @@ #include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/debug.h> #include <linux/sunrpc/rpc_rdma.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> @@ -730,12 +731,12 @@ static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt) goto err; mr = ib_alloc_fast_reg_mr(xprt->sc_pd, RPCSVC_MAXPAGES); - if (!mr) + if (IS_ERR(mr)) goto err_free_frmr; pl = ib_alloc_fast_reg_page_list(xprt->sc_cm_id->device, RPCSVC_MAXPAGES); - if (!pl) + if (IS_ERR(pl)) goto err_free_mr; frmr->mr = mr; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 1dd6123070e..9a63f669ece 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -168,47 +168,25 @@ static struct rpc_xprt_ops xprt_rdma_procs; /* forward reference */ static void xprt_rdma_format_addresses(struct rpc_xprt *xprt) { - struct sockaddr_in *addr = (struct sockaddr_in *) + struct sockaddr *sap = (struct sockaddr *) &rpcx_to_rdmad(xprt).addr; - char *buf; + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + char buf[64]; - buf = kzalloc(20, GFP_KERNEL); - if (buf) - snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr); - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) - snprintf(buf, 8, "%u", ntohs(addr->sin_port)); - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; - buf = kzalloc(48, GFP_KERNEL); - if (buf) - snprintf(buf, 48, "addr=%pI4 port=%u proto=%s", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), "rdma"); - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(10, GFP_KERNEL); - if (buf) - snprintf(buf, 10, "%02x%02x%02x%02x", - NIPQUAD(addr->sin_addr.s_addr)); - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) - snprintf(buf, 8, "%4hx", ntohs(addr->sin_port)); - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(30, GFP_KERNEL); - if (buf) - snprintf(buf, 30, "%pI4.%u.%u", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port) >> 8, - ntohs(addr->sin_port) & 0xff); - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); /* netid */ xprt->address_strings[RPC_DISPLAY_NETID] = "rdma"; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 83c73c4d017..37c5475ba25 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -32,6 +32,7 @@ #include <linux/tcp.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/sched.h> +#include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/xprtsock.h> #include <linux/file.h> #ifdef CONFIG_NFS_V4_1 @@ -43,6 +44,7 @@ #include <net/udp.h> #include <net/tcp.h> +#include "sunrpc.h" /* * xprtsock tunables */ @@ -248,8 +250,8 @@ struct sock_xprt { * Connection of transports */ struct delayed_work connect_worker; - struct sockaddr_storage addr; - unsigned short port; + struct sockaddr_storage srcaddr; + unsigned short srcport; /* * UDP socket buffer size parameters @@ -296,117 +298,60 @@ static inline struct sockaddr_in6 *xs_addr_in6(struct rpc_xprt *xprt) return (struct sockaddr_in6 *) &xprt->addr; } -static void xs_format_ipv4_peer_addresses(struct rpc_xprt *xprt, - const char *protocol, - const char *netid) +static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) { - struct sockaddr_in *addr = xs_addr_in(xprt); - char *buf; + struct sockaddr *sap = xs_addr(xprt); + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + char buf[128]; - buf = kzalloc(20, GFP_KERNEL); - if (buf) { - snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr); - } - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%u", - ntohs(addr->sin_port)); - } - xprt->address_strings[RPC_DISPLAY_PORT] = buf; - - xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; - - buf = kzalloc(48, GFP_KERNEL); - if (buf) { - snprintf(buf, 48, "addr=%pI4 port=%u proto=%s", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), - protocol); - } - xprt->address_strings[RPC_DISPLAY_ALL] = buf; + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(10, GFP_KERNEL); - if (buf) { - snprintf(buf, 10, "%02x%02x%02x%02x", - NIPQUAD(addr->sin_addr.s_addr)); - } - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%4hx", - ntohs(addr->sin_port)); - } - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(30, GFP_KERNEL); - if (buf) { - snprintf(buf, 30, "%pI4.%u.%u", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port) >> 8, - ntohs(addr->sin_port) & 0xff); + switch (sap->sa_family) { + case AF_INET: + sin = xs_addr_in(xprt); + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + break; + case AF_INET6: + sin6 = xs_addr_in6(xprt); + (void)snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); + break; + default: + BUG(); } - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; - - xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); } -static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt, - const char *protocol, - const char *netid) +static void xs_format_common_peer_ports(struct rpc_xprt *xprt) { - struct sockaddr_in6 *addr = xs_addr_in6(xprt); - char *buf; + struct sockaddr *sap = xs_addr(xprt); + char buf[128]; - buf = kzalloc(40, GFP_KERNEL); - if (buf) { - snprintf(buf, 40, "%pI6",&addr->sin6_addr); - } - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%u", - ntohs(addr->sin6_port)); - } - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); +} +static void xs_format_peer_addresses(struct rpc_xprt *xprt, + const char *protocol, + const char *netid) +{ xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; + xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xs_format_common_peer_addresses(xprt); + xs_format_common_peer_ports(xprt); +} - buf = kzalloc(64, GFP_KERNEL); - if (buf) { - snprintf(buf, 64, "addr=%pI6 port=%u proto=%s", - &addr->sin6_addr, - ntohs(addr->sin6_port), - protocol); - } - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(36, GFP_KERNEL); - if (buf) - snprintf(buf, 36, "%pi6", &addr->sin6_addr); - - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%4hx", - ntohs(addr->sin6_port)); - } - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(50, GFP_KERNEL); - if (buf) { - snprintf(buf, 50, "%pI6.%u.%u", - &addr->sin6_addr, - ntohs(addr->sin6_port) >> 8, - ntohs(addr->sin6_port) & 0xff); - } - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; +static void xs_update_peer_port(struct rpc_xprt *xprt) +{ + kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]); + kfree(xprt->address_strings[RPC_DISPLAY_PORT]); - xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xs_format_common_peer_ports(xprt); } static void xs_free_peer_addresses(struct rpc_xprt *xprt) @@ -828,6 +773,7 @@ static void xs_close(struct rpc_xprt *xprt) dprintk("RPC: xs_close xprt %p\n", xprt); xs_reset_transport(transport); + xprt->reestablish_timeout = 0; smp_mb__before_clear_bit(); clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); @@ -1319,6 +1265,12 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) if (xprt->shutdown) goto out; + /* Any data means we had a useful conversation, so + * the we don't need to delay the next reconnect + */ + if (xprt->reestablish_timeout) + xprt->reestablish_timeout = 0; + /* We use rd_desc to pass struct xprt to xs_tcp_data_recv */ rd_desc.arg.data = xprt; do { @@ -1587,25 +1539,15 @@ static unsigned short xs_get_random_port(void) */ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port) { - struct sockaddr *addr = xs_addr(xprt); - dprintk("RPC: setting port for xprt %p to %u\n", xprt, port); - switch (addr->sa_family) { - case AF_INET: - ((struct sockaddr_in *)addr)->sin_port = htons(port); - break; - case AF_INET6: - ((struct sockaddr_in6 *)addr)->sin6_port = htons(port); - break; - default: - BUG(); - } + rpc_set_port(xs_addr(xprt), port); + xs_update_peer_port(xprt); } static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock) { - unsigned short port = transport->port; + unsigned short port = transport->srcport; if (port == 0 && transport->xprt.resvport) port = xs_get_random_port(); @@ -1614,8 +1556,8 @@ static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port) { - if (transport->port != 0) - transport->port = 0; + if (transport->srcport != 0) + transport->srcport = 0; if (!transport->xprt.resvport) return 0; if (port <= xprt_min_resvport || port > xprt_max_resvport) @@ -1633,7 +1575,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock) unsigned short port = xs_get_srcport(transport, sock); unsigned short last; - sa = (struct sockaddr_in *)&transport->addr; + sa = (struct sockaddr_in *)&transport->srcaddr; myaddr.sin_addr = sa->sin_addr; do { myaddr.sin_port = htons(port); @@ -1642,7 +1584,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock) if (port == 0) break; if (err == 0) { - transport->port = port; + transport->srcport = port; break; } last = port; @@ -1666,7 +1608,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock) unsigned short port = xs_get_srcport(transport, sock); unsigned short last; - sa = (struct sockaddr_in6 *)&transport->addr; + sa = (struct sockaddr_in6 *)&transport->srcaddr; myaddr.sin6_addr = sa->sin6_addr; do { myaddr.sin6_port = htons(port); @@ -1675,7 +1617,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock) if (port == 0) break; if (err == 0) { - transport->port = port; + transport->srcport = port; break; } last = port; @@ -1780,8 +1722,11 @@ static void xs_udp_connect_worker4(struct work_struct *work) goto out; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); status = 0; @@ -1822,8 +1767,11 @@ static void xs_udp_connect_worker6(struct work_struct *work) goto out; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); status = 0; @@ -1948,8 +1896,11 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt, goto out_eagain; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); status = xs_tcp_finish_connecting(xprt, sock); dprintk("RPC: %p connect status %d connected %d sock state %d\n", @@ -2090,6 +2041,8 @@ static void xs_connect(struct rpc_task *task) &transport->connect_worker, xprt->reestablish_timeout); xprt->reestablish_timeout <<= 1; + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO) xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO; } else { @@ -2120,7 +2073,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %Lu %Lu\n", - transport->port, + transport->srcport, xprt->stat.bind_count, xprt->stat.sends, xprt->stat.recvs, @@ -2144,7 +2097,7 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) idle_time = (long)(jiffies - xprt->last_used) / HZ; seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu\n", - transport->port, + transport->srcport, xprt->stat.bind_count, xprt->stat.connect_count, xprt->stat.connect_time, @@ -2156,6 +2109,134 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) xprt->stat.bklog_u); } +/* + * Allocate a bunch of pages for a scratch buffer for the rpc code. The reason + * we allocate pages instead doing a kmalloc like rpc_malloc is because we want + * to use the server side send routines. + */ +void *bc_malloc(struct rpc_task *task, size_t size) +{ + struct page *page; + struct rpc_buffer *buf; + + BUG_ON(size > PAGE_SIZE - sizeof(struct rpc_buffer)); + page = alloc_page(GFP_KERNEL); + + if (!page) + return NULL; + + buf = page_address(page); + buf->len = PAGE_SIZE; + + return buf->data; +} + +/* + * Free the space allocated in the bc_alloc routine + */ +void bc_free(void *buffer) +{ + struct rpc_buffer *buf; + + if (!buffer) + return; + + buf = container_of(buffer, struct rpc_buffer, data); + free_page((unsigned long)buf); +} + +/* + * Use the svc_sock to send the callback. Must be called with svsk->sk_mutex + * held. Borrows heavily from svc_tcp_sendto and xs_tcp_send_request. + */ +static int bc_sendto(struct rpc_rqst *req) +{ + int len; + struct xdr_buf *xbufp = &req->rq_snd_buf; + struct rpc_xprt *xprt = req->rq_xprt; + struct sock_xprt *transport = + container_of(xprt, struct sock_xprt, xprt); + struct socket *sock = transport->sock; + unsigned long headoff; + unsigned long tailoff; + + /* + * Set up the rpc header and record marker stuff + */ + xs_encode_tcp_record_marker(xbufp); + + tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK; + headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK; + len = svc_send_common(sock, xbufp, + virt_to_page(xbufp->head[0].iov_base), headoff, + xbufp->tail[0].iov_base, tailoff); + + if (len != xbufp->len) { + printk(KERN_NOTICE "Error sending entire callback!\n"); + len = -EAGAIN; + } + + return len; +} + +/* + * The send routine. Borrows from svc_send + */ +static int bc_send_request(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + struct svc_xprt *xprt; + struct svc_sock *svsk; + u32 len; + + dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid)); + /* + * Get the server socket associated with this callback xprt + */ + xprt = req->rq_xprt->bc_xprt; + svsk = container_of(xprt, struct svc_sock, sk_xprt); + + /* + * Grab the mutex to serialize data as the connection is shared + * with the fore channel + */ + if (!mutex_trylock(&xprt->xpt_mutex)) { + rpc_sleep_on(&xprt->xpt_bc_pending, task, NULL); + if (!mutex_trylock(&xprt->xpt_mutex)) + return -EAGAIN; + rpc_wake_up_queued_task(&xprt->xpt_bc_pending, task); + } + if (test_bit(XPT_DEAD, &xprt->xpt_flags)) + len = -ENOTCONN; + else + len = bc_sendto(req); + mutex_unlock(&xprt->xpt_mutex); + + if (len > 0) + len = 0; + + return len; +} + +/* + * The close routine. Since this is client initiated, we do nothing + */ + +static void bc_close(struct rpc_xprt *xprt) +{ + return; +} + +/* + * The xprt destroy routine. Again, because this connection is client + * initiated, we do nothing + */ + +static void bc_destroy(struct rpc_xprt *xprt) +{ + return; +} + static struct rpc_xprt_ops xs_udp_ops = { .set_buffer_size = xs_udp_set_buffer_size, .reserve_xprt = xprt_reserve_xprt_cong, @@ -2192,6 +2273,22 @@ static struct rpc_xprt_ops xs_tcp_ops = { .print_stats = xs_tcp_print_stats, }; +/* + * The rpc_xprt_ops for the server backchannel + */ + +static struct rpc_xprt_ops bc_tcp_ops = { + .reserve_xprt = xprt_reserve_xprt, + .release_xprt = xprt_release_xprt, + .buf_alloc = bc_malloc, + .buf_free = bc_free, + .send_request = bc_send_request, + .set_retrans_timeout = xprt_set_retrans_timeout_def, + .close = bc_close, + .destroy = bc_destroy, + .print_stats = xs_tcp_print_stats, +}; + static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, unsigned int slot_table_size) { @@ -2223,7 +2320,7 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, memcpy(&xprt->addr, args->dstaddr, args->addrlen); xprt->addrlen = args->addrlen; if (args->srcaddr) - memcpy(&new->addr, args->srcaddr, args->addrlen); + memcpy(&new->srcaddr, args->srcaddr, args->addrlen); return xprt; } @@ -2272,7 +2369,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker4); - xs_format_ipv4_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP); + xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP); break; case AF_INET6: if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) @@ -2280,15 +2377,22 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker6); - xs_format_ipv6_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6); + xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6); break; default: kfree(xprt); return ERR_PTR(-EAFNOSUPPORT); } - dprintk("RPC: set up transport to address %s\n", - xprt->address_strings[RPC_DISPLAY_ALL]); + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); if (try_module_get(THIS_MODULE)) return xprt; @@ -2337,23 +2441,33 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) if (((struct sockaddr_in *)addr)->sin_port != htons(0)) xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker4); - xs_format_ipv4_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_connect_worker4); + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); break; case AF_INET6: if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker6); - xs_format_ipv6_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_connect_worker6); + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); break; default: kfree(xprt); return ERR_PTR(-EAFNOSUPPORT); } - dprintk("RPC: set up transport to address %s\n", - xprt->address_strings[RPC_DISPLAY_ALL]); + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); + if (try_module_get(THIS_MODULE)) return xprt; @@ -2363,11 +2477,93 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) return ERR_PTR(-EINVAL); } +/** + * xs_setup_bc_tcp - Set up transport to use a TCP backchannel socket + * @args: rpc transport creation arguments + * + */ +static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) +{ + struct sockaddr *addr = args->dstaddr; + struct rpc_xprt *xprt; + struct sock_xprt *transport; + struct svc_sock *bc_sock; + + if (!args->bc_xprt) + ERR_PTR(-EINVAL); + + xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries); + if (IS_ERR(xprt)) + return xprt; + transport = container_of(xprt, struct sock_xprt, xprt); + + xprt->prot = IPPROTO_TCP; + xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32); + xprt->max_payload = RPC_MAX_FRAGMENT_SIZE; + xprt->timeout = &xs_tcp_default_timeout; + + /* backchannel */ + xprt_set_bound(xprt); + xprt->bind_timeout = 0; + xprt->connect_timeout = 0; + xprt->reestablish_timeout = 0; + xprt->idle_timeout = 0; + + /* + * The backchannel uses the same socket connection as the + * forechannel + */ + xprt->bc_xprt = args->bc_xprt; + bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt); + bc_sock->sk_bc_xprt = xprt; + transport->sock = bc_sock->sk_sock; + transport->inet = bc_sock->sk_sk; + + xprt->ops = &bc_tcp_ops; + + switch (addr->sa_family) { + case AF_INET: + xs_format_peer_addresses(xprt, "tcp", + RPCBIND_NETID_TCP); + break; + case AF_INET6: + xs_format_peer_addresses(xprt, "tcp", + RPCBIND_NETID_TCP6); + break; + default: + kfree(xprt); + return ERR_PTR(-EAFNOSUPPORT); + } + + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); + + /* + * Since we don't want connections for the backchannel, we set + * the xprt status to connected + */ + xprt_set_connected(xprt); + + + if (try_module_get(THIS_MODULE)) + return xprt; + kfree(xprt->slot); + kfree(xprt); + return ERR_PTR(-EINVAL); +} + static struct xprt_class xs_udp_transport = { .list = LIST_HEAD_INIT(xs_udp_transport.list), .name = "udp", .owner = THIS_MODULE, - .ident = IPPROTO_UDP, + .ident = XPRT_TRANSPORT_UDP, .setup = xs_setup_udp, }; @@ -2375,10 +2571,18 @@ static struct xprt_class xs_tcp_transport = { .list = LIST_HEAD_INIT(xs_tcp_transport.list), .name = "tcp", .owner = THIS_MODULE, - .ident = IPPROTO_TCP, + .ident = XPRT_TRANSPORT_TCP, .setup = xs_setup_tcp, }; +static struct xprt_class xs_bc_tcp_transport = { + .list = LIST_HEAD_INIT(xs_bc_tcp_transport.list), + .name = "tcp NFSv4.1 backchannel", + .owner = THIS_MODULE, + .ident = XPRT_TRANSPORT_BC_TCP, + .setup = xs_setup_bc_tcp, +}; + /** * init_socket_xprt - set up xprtsock's sysctls, register with RPC client * @@ -2392,6 +2596,7 @@ int init_socket_xprt(void) xprt_register_transport(&xs_udp_transport); xprt_register_transport(&xs_tcp_transport); + xprt_register_transport(&xs_bc_tcp_transport); return 0; } @@ -2411,4 +2616,57 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_udp_transport); xprt_unregister_transport(&xs_tcp_transport); + xprt_unregister_transport(&xs_bc_tcp_transport); +} + +static int param_set_uint_minmax(const char *val, struct kernel_param *kp, + unsigned int min, unsigned int max) +{ + unsigned long num; + int ret; + + if (!val) + return -EINVAL; + ret = strict_strtoul(val, 0, &num); + if (ret == -EINVAL || num < min || num > max) + return -EINVAL; + *((unsigned int *)kp->arg) = num; + return 0; +} + +static int param_set_portnr(const char *val, struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_RESVPORT, + RPC_MAX_RESVPORT); } + +static int param_get_portnr(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_portnr(name, p) \ + __param_check(name, p, unsigned int); + +module_param_named(min_resvport, xprt_min_resvport, portnr, 0644); +module_param_named(max_resvport, xprt_max_resvport, portnr, 0644); + +static int param_set_slot_table_size(const char *val, struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_SLOT_TABLE, + RPC_MAX_SLOT_TABLE); +} + +static int param_get_slot_table_size(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_slot_table_size(name, p) \ + __param_check(name, p, unsigned int); + +module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries, + slot_table_size, 0644); +module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries, + slot_table_size, 0644); + diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a7a36779b9b..327011fcc40 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/tipc/netlink.c b/net/tipc/netlink.c index 3c57005e44d..7bda8e3d139 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -62,7 +62,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) rep_nlh = nlmsg_hdr(rep_buf); memcpy(rep_nlh, req_nlh, hdr_space); rep_nlh->nlmsg_len = rep_buf->len; - genlmsg_unicast(rep_buf, NETLINK_CB(skb).pid); + genlmsg_unicast(&init_net, rep_buf, NETLINK_CB(skb).pid); } return 0; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1848693ebb8..e6d9abf7440 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1658,7 +1658,7 @@ restart: */ static int setsockopt(struct socket *sock, - int lvl, int opt, char __user *ov, int ol) + int lvl, int opt, char __user *ov, unsigned int ol) { struct sock *sk = sock->sk; struct tipc_port *tport = tipc_sk_port(sk); @@ -1748,6 +1748,12 @@ static int getsockopt(struct socket *sock, value = jiffies_to_msecs(sk->sk_rcvtimeo); /* no need to set "res", since already 0 at this point */ break; + case TIPC_NODE_RECVQ_DEPTH: + value = (u32)atomic_read(&tipc_queue_size); + break; + case TIPC_SOCK_RECVQ_DEPTH: + value = skb_queue_len(&sk->sk_receive_queue); + break; default: res = -EINVAL; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index fc3ebb90691..fc820cd7545 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1074,6 +1074,8 @@ restart: err = -ECONNREFUSED; if (other->sk_state != TCP_LISTEN) goto out_unlock; + if (other->sk_shutdown & RCV_SHUTDOWN) + goto out_unlock; if (unix_recvq_full(other)) { err = -EAGAIN; @@ -1501,6 +1503,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sk_buff *skb; int sent = 0; struct scm_cookie tmp_scm; + bool fds_sent = false; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1562,12 +1565,14 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, size = min_t(int, size, skb_tailroom(skb)); memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); - if (siocb->scm->fp) { + /* Only send the fds in the first buffer */ + if (siocb->scm->fp && !fds_sent) { err = unix_attach_fds(siocb->scm, skb); if (err) { kfree_skb(skb); goto out_err; } + fds_sent = true; } err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 4428dd5e911..abf7ca3f9ff 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -1,6 +1,47 @@ 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" + depends on CFG80211 + help + The nl80211 testmode command helps implementing things like + factory calibration or validation tools for wireless chips. + + Select this option ONLY for kernels that are specifically + built for such purposes. + + Debugging tools that are supposed to end up in the hands of + users should better be implemented with debugfs. + + 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" @@ -8,9 +49,29 @@ config CFG80211_REG_DEBUG 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. +config CFG80211_DEFAULT_PS + bool "enable powersave by default" + depends on CFG80211 + default y + help + This option enables powersave mode by default. + + If this causes your applications to misbehave you should fix your + applications instead -- they need to register their network + latency requirement, see Documentation/power/pm_qos_interface.txt. + +config CFG80211_DEFAULT_PS_VALUE + int + default 1 if CFG80211_DEFAULT_PS + default 0 + config CFG80211_DEBUGFS bool "cfg80211 DebugFS entries" depends on CFG80211 && DEBUG_FS @@ -35,19 +96,13 @@ config WIRELESS_OLD_REGULATORY config WIRELESS_EXT bool "Wireless extensions" - default n + default y ---help--- This option enables the legacy wireless extensions (wireless network interface configuration via ioctls.) - Wireless extensions will be replaced by cfg80211 and - will be required only by legacy drivers that implement - wireless extension handlers. This option does not - affect the wireless-extension backward compatibility - code in cfg80211. - - Say N (if you can) unless you know you need wireless - extensions for external modules. + Say Y unless you've upgraded all your userspace to use + nl80211 instead of wireless extensions. config WIRELESS_EXT_SYSFS bool "Wireless extensions sysfs files" diff --git a/net/wireless/Makefile b/net/wireless/Makefile index f78c4832a9c..3ecaa917997 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -5,8 +5,9 @@ obj-$(CONFIG_LIB80211_CRYPT_WEP) += lib80211_crypt_wep.o obj-$(CONFIG_LIB80211_CRYPT_CCMP) += lib80211_crypt_ccmp.o obj-$(CONFIG_LIB80211_CRYPT_TKIP) += lib80211_crypt_tkip.o -cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o mlme.o ibss.o +cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o +cfg80211-y += mlme.o ibss.o sme.o chan.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o -cfg80211-$(CONFIG_WIRELESS_EXT) += wext-compat.o +cfg80211-$(CONFIG_WIRELESS_EXT) += wext-compat.o wext-sme.o ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/wireless/chan.c b/net/wireless/chan.c new file mode 100644 index 00000000000..a46ac6c9b36 --- /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 d5850292b3d..a595f712b5b 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -12,13 +12,16 @@ #include <linux/debugfs.h> #include <linux/notifier.h> #include <linux/device.h> +#include <linux/etherdevice.h> #include <linux/rtnetlink.h> +#include <linux/sched.h> #include <net/genetlink.h> #include <net/cfg80211.h> #include "nl80211.h" #include "core.h" #include "sysfs.h" #include "debugfs.h" +#include "wext-compat.h" /* name for sysfs, %d is appended */ #define PHY_NAME "phy" @@ -30,12 +33,11 @@ MODULE_DESCRIPTION("wireless configuration support"); /* RCU might be appropriate here since we usually * only read the list, and that can happen quite * often because we need to do it for each command */ -LIST_HEAD(cfg80211_drv_list); +LIST_HEAD(cfg80211_rdev_list); +int cfg80211_rdev_list_generation; /* - * This is used to protect the cfg80211_drv_list, cfg80211_regdomain, - * country_ie_regdomain, the reg_beacon_list and the the last regulatory - * request receipt (last_request). + * This is used to protect the cfg80211_rdev_list */ DEFINE_MUTEX(cfg80211_mutex); @@ -43,18 +45,18 @@ DEFINE_MUTEX(cfg80211_mutex); static struct dentry *ieee80211_debugfs_dir; /* requires cfg80211_mutex to be held! */ -struct cfg80211_registered_device *cfg80211_drv_by_wiphy_idx(int wiphy_idx) +struct cfg80211_registered_device *cfg80211_rdev_by_wiphy_idx(int wiphy_idx) { - struct cfg80211_registered_device *result = NULL, *drv; + struct cfg80211_registered_device *result = NULL, *rdev; if (!wiphy_idx_valid(wiphy_idx)) return NULL; assert_cfg80211_lock(); - list_for_each_entry(drv, &cfg80211_drv_list, list) { - if (drv->wiphy_idx == wiphy_idx) { - result = drv; + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + if (rdev->wiphy_idx == wiphy_idx) { + result = rdev; break; } } @@ -64,32 +66,32 @@ struct cfg80211_registered_device *cfg80211_drv_by_wiphy_idx(int wiphy_idx) int get_wiphy_idx(struct wiphy *wiphy) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; if (!wiphy) return WIPHY_IDX_STALE; - drv = wiphy_to_dev(wiphy); - return drv->wiphy_idx; + rdev = wiphy_to_dev(wiphy); + return rdev->wiphy_idx; } -/* requires cfg80211_drv_mutex to be held! */ +/* requires cfg80211_rdev_mutex to be held! */ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; if (!wiphy_idx_valid(wiphy_idx)) return NULL; assert_cfg80211_lock(); - drv = cfg80211_drv_by_wiphy_idx(wiphy_idx); - if (!drv) + rdev = cfg80211_rdev_by_wiphy_idx(wiphy_idx); + if (!rdev) return NULL; - return &drv->wiphy; + return &rdev->wiphy; } /* requires cfg80211_mutex to be held! */ struct cfg80211_registered_device * -__cfg80211_drv_from_info(struct genl_info *info) +__cfg80211_rdev_from_info(struct genl_info *info) { int ifindex; struct cfg80211_registered_device *bywiphyidx = NULL, *byifidx = NULL; @@ -99,14 +101,14 @@ __cfg80211_drv_from_info(struct genl_info *info) assert_cfg80211_lock(); if (info->attrs[NL80211_ATTR_WIPHY]) { - bywiphyidx = cfg80211_drv_by_wiphy_idx( + bywiphyidx = cfg80211_rdev_by_wiphy_idx( nla_get_u32(info->attrs[NL80211_ATTR_WIPHY])); err = -ENODEV; } if (info->attrs[NL80211_ATTR_IFINDEX]) { ifindex = nla_get_u32(info->attrs[NL80211_ATTR_IFINDEX]); - dev = dev_get_by_index(&init_net, ifindex); + dev = dev_get_by_index(genl_info_net(info), ifindex); if (dev) { if (dev->ieee80211_ptr) byifidx = @@ -134,54 +136,48 @@ __cfg80211_drv_from_info(struct genl_info *info) struct cfg80211_registered_device * cfg80211_get_dev_from_info(struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; mutex_lock(&cfg80211_mutex); - drv = __cfg80211_drv_from_info(info); + rdev = __cfg80211_rdev_from_info(info); /* if it is not an error we grab the lock on * it to assure it won't be going away while * we operate on it */ - if (!IS_ERR(drv)) - mutex_lock(&drv->mtx); + if (!IS_ERR(rdev)) + mutex_lock(&rdev->mtx); mutex_unlock(&cfg80211_mutex); - return drv; + return rdev; } struct cfg80211_registered_device * -cfg80211_get_dev_from_ifindex(int ifindex) +cfg80211_get_dev_from_ifindex(struct net *net, int ifindex) { - struct cfg80211_registered_device *drv = ERR_PTR(-ENODEV); + struct cfg80211_registered_device *rdev = ERR_PTR(-ENODEV); struct net_device *dev; mutex_lock(&cfg80211_mutex); - dev = dev_get_by_index(&init_net, ifindex); + dev = dev_get_by_index(net, ifindex); if (!dev) goto out; if (dev->ieee80211_ptr) { - drv = wiphy_to_dev(dev->ieee80211_ptr->wiphy); - mutex_lock(&drv->mtx); + rdev = wiphy_to_dev(dev->ieee80211_ptr->wiphy); + mutex_lock(&rdev->mtx); } else - drv = ERR_PTR(-ENODEV); + rdev = ERR_PTR(-ENODEV); dev_put(dev); out: mutex_unlock(&cfg80211_mutex); - return drv; -} - -void cfg80211_put_dev(struct cfg80211_registered_device *drv) -{ - BUG_ON(IS_ERR(drv)); - mutex_unlock(&drv->mtx); + return rdev; } /* requires cfg80211_mutex to be held */ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, char *newname) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev2; int wiphy_idx, taken = -1, result, digits; assert_cfg80211_lock(); @@ -207,8 +203,8 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, return 0; /* Ensure another device does not already have this name. */ - list_for_each_entry(drv, &cfg80211_drv_list, list) - if (strcmp(newname, dev_name(&drv->wiphy.dev)) == 0) + list_for_each_entry(rdev2, &cfg80211_rdev_list, list) + if (strcmp(newname, dev_name(&rdev2->wiphy.dev)) == 0) return -EINVAL; result = device_rename(&rdev->wiphy.dev, newname); @@ -228,28 +224,64 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, return 0; } +int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, + struct net *net) +{ + struct wireless_dev *wdev; + int err = 0; + + if (!rdev->wiphy.netnsok) + return -EOPNOTSUPP; + + list_for_each_entry(wdev, &rdev->netdev_list, list) { + wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + err = dev_change_net_namespace(wdev->netdev, net, "wlan%d"); + if (err) + break; + wdev->netdev->features |= NETIF_F_NETNS_LOCAL; + } + + if (err) { + /* failed -- clean up to old netns */ + net = wiphy_net(&rdev->wiphy); + + list_for_each_entry_continue_reverse(wdev, &rdev->netdev_list, + list) { + wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + err = dev_change_net_namespace(wdev->netdev, net, + "wlan%d"); + WARN_ON(err); + wdev->netdev->features |= NETIF_F_NETNS_LOCAL; + } + } + + wiphy_net_set(&rdev->wiphy, net); + + return err; +} + static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data) { - struct cfg80211_registered_device *drv = data; + struct cfg80211_registered_device *rdev = data; - drv->ops->rfkill_poll(&drv->wiphy); + rdev->ops->rfkill_poll(&rdev->wiphy); } static int cfg80211_rfkill_set_block(void *data, bool blocked) { - struct cfg80211_registered_device *drv = data; + struct cfg80211_registered_device *rdev = data; struct wireless_dev *wdev; if (!blocked) return 0; rtnl_lock(); - mutex_lock(&drv->devlist_mtx); + mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &drv->netdev_list, list) + list_for_each_entry(wdev, &rdev->netdev_list, list) dev_close(wdev->netdev); - mutex_unlock(&drv->devlist_mtx); + mutex_unlock(&rdev->devlist_mtx); rtnl_unlock(); return 0; @@ -257,10 +289,25 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked) static void cfg80211_rfkill_sync_work(struct work_struct *work) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; - drv = container_of(work, struct cfg80211_registered_device, rfkill_sync); - cfg80211_rfkill_set_block(drv, rfkill_blocked(drv->rfkill)); + rdev = container_of(work, struct cfg80211_registered_device, rfkill_sync); + cfg80211_rfkill_set_block(rdev, rfkill_blocked(rdev->rfkill)); +} + +static void cfg80211_event_work(struct work_struct *work) +{ + struct cfg80211_registered_device *rdev; + + rdev = container_of(work, struct cfg80211_registered_device, + event_work); + + rtnl_lock(); + cfg80211_lock_rdev(rdev); + + cfg80211_process_rdev_events(rdev); + cfg80211_unlock_rdev(rdev); + rtnl_unlock(); } /* exported functions */ @@ -269,76 +316,90 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) { static int wiphy_counter; - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int alloc_size; - WARN_ON(!ops->add_key && ops->del_key); - WARN_ON(ops->add_key && !ops->del_key); + WARN_ON(ops->add_key && (!ops->del_key || !ops->set_default_key)); + WARN_ON(ops->auth && (!ops->assoc || !ops->deauth || !ops->disassoc)); + WARN_ON(ops->connect && !ops->disconnect); + WARN_ON(ops->join_ibss && !ops->leave_ibss); + WARN_ON(ops->add_virtual_intf && !ops->del_virtual_intf); + WARN_ON(ops->add_station && !ops->del_station); + WARN_ON(ops->add_mpath && !ops->del_mpath); - alloc_size = sizeof(*drv) + sizeof_priv; + alloc_size = sizeof(*rdev) + sizeof_priv; - drv = kzalloc(alloc_size, GFP_KERNEL); - if (!drv) + rdev = kzalloc(alloc_size, GFP_KERNEL); + if (!rdev) return NULL; - drv->ops = ops; + rdev->ops = ops; mutex_lock(&cfg80211_mutex); - drv->wiphy_idx = wiphy_counter++; + rdev->wiphy_idx = wiphy_counter++; - if (unlikely(!wiphy_idx_valid(drv->wiphy_idx))) { + if (unlikely(!wiphy_idx_valid(rdev->wiphy_idx))) { wiphy_counter--; mutex_unlock(&cfg80211_mutex); /* ugh, wrapped! */ - kfree(drv); + kfree(rdev); return NULL; } mutex_unlock(&cfg80211_mutex); /* give it a proper name */ - dev_set_name(&drv->wiphy.dev, PHY_NAME "%d", drv->wiphy_idx); + dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx); - mutex_init(&drv->mtx); - mutex_init(&drv->devlist_mtx); - INIT_LIST_HEAD(&drv->netdev_list); - spin_lock_init(&drv->bss_lock); - INIT_LIST_HEAD(&drv->bss_list); + mutex_init(&rdev->mtx); + mutex_init(&rdev->devlist_mtx); + INIT_LIST_HEAD(&rdev->netdev_list); + spin_lock_init(&rdev->bss_lock); + INIT_LIST_HEAD(&rdev->bss_list); + INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done); - device_initialize(&drv->wiphy.dev); - drv->wiphy.dev.class = &ieee80211_class; - drv->wiphy.dev.platform_data = drv; + device_initialize(&rdev->wiphy.dev); + rdev->wiphy.dev.class = &ieee80211_class; + rdev->wiphy.dev.platform_data = rdev; - drv->rfkill_ops.set_block = cfg80211_rfkill_set_block; - drv->rfkill = rfkill_alloc(dev_name(&drv->wiphy.dev), - &drv->wiphy.dev, RFKILL_TYPE_WLAN, - &drv->rfkill_ops, drv); + rdev->wiphy.ps_default = CONFIG_CFG80211_DEFAULT_PS_VALUE; - if (!drv->rfkill) { - kfree(drv); + wiphy_net_set(&rdev->wiphy, &init_net); + + rdev->rfkill_ops.set_block = cfg80211_rfkill_set_block; + rdev->rfkill = rfkill_alloc(dev_name(&rdev->wiphy.dev), + &rdev->wiphy.dev, RFKILL_TYPE_WLAN, + &rdev->rfkill_ops, rdev); + + if (!rdev->rfkill) { + kfree(rdev); return NULL; } - INIT_WORK(&drv->rfkill_sync, cfg80211_rfkill_sync_work); + INIT_WORK(&rdev->rfkill_sync, cfg80211_rfkill_sync_work); + 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 * special -1 value. */ - drv->wiphy.retry_short = 7; - drv->wiphy.retry_long = 4; - drv->wiphy.frag_threshold = (u32) -1; - drv->wiphy.rts_threshold = (u32) -1; + rdev->wiphy.retry_short = 7; + rdev->wiphy.retry_long = 4; + rdev->wiphy.frag_threshold = (u32) -1; + rdev->wiphy.rts_threshold = (u32) -1; - return &drv->wiphy; + return &rdev->wiphy; } EXPORT_SYMBOL(wiphy_new); int wiphy_register(struct wiphy *wiphy) { - struct cfg80211_registered_device *drv = wiphy_to_dev(wiphy); + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); int res; enum ieee80211_band band; struct ieee80211_supported_band *sband; @@ -346,9 +407,6 @@ int wiphy_register(struct wiphy *wiphy) int i; u16 ifmodes = wiphy->interface_modes; - if (WARN_ON(wiphy->max_scan_ssids < 1)) - return -EINVAL; - /* sanity check ifmodes */ WARN_ON(!ifmodes); ifmodes &= ((1 << __NL80211_IFTYPE_AFTER_LAST) - 1) & ~1; @@ -395,11 +453,11 @@ int wiphy_register(struct wiphy *wiphy) /* check and set up bitrates */ ieee80211_set_bitrate_flags(wiphy); - res = device_add(&drv->wiphy.dev); + res = device_add(&rdev->wiphy.dev); if (res) return res; - res = rfkill_register(drv->rfkill); + res = rfkill_register(rdev->rfkill); if (res) goto out_rm_dev; @@ -408,16 +466,17 @@ int wiphy_register(struct wiphy *wiphy) /* set up regulatory info */ wiphy_update_regulatory(wiphy, NL80211_REGDOM_SET_BY_CORE); - list_add(&drv->list, &cfg80211_drv_list); + list_add(&rdev->list, &cfg80211_rdev_list); + cfg80211_rdev_list_generation++; mutex_unlock(&cfg80211_mutex); /* add to debugfs */ - drv->wiphy.debugfsdir = - debugfs_create_dir(wiphy_name(&drv->wiphy), + rdev->wiphy.debugfsdir = + debugfs_create_dir(wiphy_name(&rdev->wiphy), ieee80211_debugfs_dir); - if (IS_ERR(drv->wiphy.debugfsdir)) - drv->wiphy.debugfsdir = NULL; + if (IS_ERR(rdev->wiphy.debugfsdir)) + rdev->wiphy.debugfsdir = NULL; if (wiphy->custom_regulatory) { struct regulatory_request request; @@ -430,83 +489,101 @@ int wiphy_register(struct wiphy *wiphy) nl80211_send_reg_change_event(&request); } - cfg80211_debugfs_drv_add(drv); + cfg80211_debugfs_rdev_add(rdev); return 0; out_rm_dev: - device_del(&drv->wiphy.dev); + device_del(&rdev->wiphy.dev); return res; } EXPORT_SYMBOL(wiphy_register); void wiphy_rfkill_start_polling(struct wiphy *wiphy) { - struct cfg80211_registered_device *drv = wiphy_to_dev(wiphy); + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - if (!drv->ops->rfkill_poll) + if (!rdev->ops->rfkill_poll) return; - drv->rfkill_ops.poll = cfg80211_rfkill_poll; - rfkill_resume_polling(drv->rfkill); + rdev->rfkill_ops.poll = cfg80211_rfkill_poll; + rfkill_resume_polling(rdev->rfkill); } EXPORT_SYMBOL(wiphy_rfkill_start_polling); void wiphy_rfkill_stop_polling(struct wiphy *wiphy) { - struct cfg80211_registered_device *drv = wiphy_to_dev(wiphy); + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - rfkill_pause_polling(drv->rfkill); + rfkill_pause_polling(rdev->rfkill); } EXPORT_SYMBOL(wiphy_rfkill_stop_polling); void wiphy_unregister(struct wiphy *wiphy) { - struct cfg80211_registered_device *drv = wiphy_to_dev(wiphy); + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - rfkill_unregister(drv->rfkill); + rfkill_unregister(rdev->rfkill); /* protect the device list */ mutex_lock(&cfg80211_mutex); - BUG_ON(!list_empty(&drv->netdev_list)); + 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 drv->mtx. If a command is still in progress, + * Try to grab rdev->mtx. If a command is still in progress, * hopefully the driver will refuse it since it's tearing * 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(&drv->mtx); - /* unlock again before freeing */ - mutex_unlock(&drv->mtx); - - cfg80211_debugfs_drv_del(drv); + 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(&drv->list); - device_del(&drv->wiphy.dev); - debugfs_remove(drv->wiphy.debugfsdir); + 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); + flush_work(&rdev->event_work); } EXPORT_SYMBOL(wiphy_unregister); -void cfg80211_dev_free(struct cfg80211_registered_device *drv) +void cfg80211_dev_free(struct cfg80211_registered_device *rdev) { struct cfg80211_internal_bss *scan, *tmp; - rfkill_destroy(drv->rfkill); - mutex_destroy(&drv->mtx); - mutex_destroy(&drv->devlist_mtx); - list_for_each_entry_safe(scan, tmp, &drv->bss_list, list) + rfkill_destroy(rdev->rfkill); + mutex_destroy(&rdev->mtx); + mutex_destroy(&rdev->devlist_mtx); + list_for_each_entry_safe(scan, tmp, &rdev->bss_list, list) cfg80211_put_bss(&scan->pub); - kfree(drv); + kfree(rdev); } void wiphy_free(struct wiphy *wiphy) @@ -517,68 +594,181 @@ EXPORT_SYMBOL(wiphy_free); void wiphy_rfkill_set_hw_state(struct wiphy *wiphy, bool blocked) { - struct cfg80211_registered_device *drv = wiphy_to_dev(wiphy); + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - if (rfkill_set_hw_state(drv->rfkill, blocked)) - schedule_work(&drv->rfkill_sync); + if (rfkill_set_hw_state(rdev->rfkill, blocked)) + schedule_work(&rdev->rfkill_sync); } 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) { struct net_device *dev = ndev; + struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; - if (!dev->ieee80211_ptr) + if (!wdev) return NOTIFY_DONE; - rdev = wiphy_to_dev(dev->ieee80211_ptr->wiphy); + rdev = wiphy_to_dev(wdev->wiphy); - WARN_ON(dev->ieee80211_ptr->iftype == NL80211_IFTYPE_UNSPECIFIED); + WARN_ON(wdev->iftype == NL80211_IFTYPE_UNSPECIFIED); 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(&dev->ieee80211_ptr->list, &rdev->netdev_list); + list_add(&wdev->list, &rdev->netdev_list); + rdev->devlist_generation++; + /* can only change netns with wiphy */ + dev->features |= NETIF_F_NETNS_LOCAL; + if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, "phy80211")) { printk(KERN_ERR "wireless: failed to add phy80211 " "symlink to netdev!\n"); } - dev->ieee80211_ptr->netdev = dev; + wdev->netdev = dev; + wdev->sme_state = CFG80211_SME_IDLE; + mutex_unlock(&rdev->devlist_mtx); #ifdef CONFIG_WIRELESS_EXT - dev->ieee80211_ptr->wext.default_key = -1; - dev->ieee80211_ptr->wext.default_mgmt_key = -1; + if (!dev->wireless_handlers) + dev->wireless_handlers = &cfg80211_wext_handler; + wdev->wext.default_key = -1; + wdev->wext.default_mgmt_key = -1; + wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; + 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, + wdev->wext.ps, + wdev->wext.ps_timeout)) { + /* assume this means it's off */ + wdev->wext.ps = false; + } #endif - mutex_unlock(&rdev->devlist_mtx); break; case NETDEV_GOING_DOWN: - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) + switch (wdev->iftype) { + case NL80211_IFTYPE_ADHOC: + cfg80211_leave_ibss(rdev, dev, true); break; - if (!dev->ieee80211_ptr->ssid_len) + case NL80211_IFTYPE_STATION: + wdev_lock(wdev); +#ifdef CONFIG_WIRELESS_EXT + kfree(wdev->wext.ie); + wdev->wext.ie = NULL; + wdev->wext.ie_len = 0; + wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; +#endif + __cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, true); + cfg80211_mlme_down(rdev, dev); + wdev_unlock(wdev); + break; + default: break; - cfg80211_leave_ibss(rdev, dev, true); + } + 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 - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) + cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->devlist_mtx); + wdev_lock(wdev); + switch (wdev->iftype) { + case NL80211_IFTYPE_ADHOC: + cfg80211_ibss_wext_join(rdev, wdev); break; - if (!dev->ieee80211_ptr->wext.ibss.ssid_len) + case NL80211_IFTYPE_STATION: + cfg80211_mgd_wext_connect(rdev, wdev); break; - cfg80211_join_ibss(rdev, dev, &dev->ieee80211_ptr->wext.ibss); - break; + default: + 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); - if (!list_empty(&dev->ieee80211_ptr->list)) { + /* + * It is possible to get NETDEV_UNREGISTER + * multiple times. To detect that, check + * that the interface is still on the list + * of registered interfaces, and only then + * remove and clean it up. + */ + if (!list_empty(&wdev->list)) { sysfs_remove_link(&dev->dev.kobj, "phy80211"); - list_del_init(&dev->ieee80211_ptr->list); + list_del_init(&wdev->list); + rdev->devlist_generation++; +#ifdef CONFIG_WIRELESS_EXT + kfree(wdev->wext.keys); +#endif } mutex_unlock(&rdev->devlist_mtx); break; case NETDEV_PRE_UP: + if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype))) + return notifier_from_errno(-EOPNOTSUPP); if (rfkill_blocked(rdev->rfkill)) return notifier_from_errno(-ERFKILL); break; @@ -591,10 +781,32 @@ static struct notifier_block cfg80211_netdev_notifier = { .notifier_call = cfg80211_netdev_notifier_call, }; -static int cfg80211_init(void) +static void __net_exit cfg80211_pernet_exit(struct net *net) +{ + struct cfg80211_registered_device *rdev; + + rtnl_lock(); + mutex_lock(&cfg80211_mutex); + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + if (net_eq(wiphy_net(&rdev->wiphy), net)) + WARN_ON(cfg80211_switch_netns(rdev, &init_net)); + } + mutex_unlock(&cfg80211_mutex); + rtnl_unlock(); +} + +static struct pernet_operations cfg80211_pernet_ops = { + .exit = cfg80211_pernet_exit, +}; + +static int __init cfg80211_init(void) { int err; + err = register_pernet_device(&cfg80211_pernet_ops); + if (err) + goto out_fail_pernet; + err = wiphy_sysfs_init(); if (err) goto out_fail_sysfs; @@ -622,9 +834,10 @@ out_fail_nl80211: out_fail_notifier: wiphy_sysfs_exit(); out_fail_sysfs: + unregister_pernet_device(&cfg80211_pernet_ops); +out_fail_pernet: return err; } - subsys_initcall(cfg80211_init); static void cfg80211_exit(void) @@ -634,5 +847,6 @@ static void cfg80211_exit(void) unregister_netdevice_notifier(&cfg80211_netdev_notifier); wiphy_sysfs_exit(); regulatory_exit(); + unregister_pernet_device(&cfg80211_pernet_ops); } module_exit(cfg80211_exit); diff --git a/net/wireless/core.h b/net/wireless/core.h index bfa340c7abb..68b321997d4 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; @@ -57,6 +60,17 @@ struct cfg80211_registered_device { u32 bss_generation; struct cfg80211_scan_request *scan_req; /* protected by RTNL */ unsigned long suspend_at; + struct work_struct scan_done_wk; + +#ifdef CONFIG_NL80211_TESTMODE + struct genl_info *testmode_info; +#endif + + struct work_struct conn_work; + struct work_struct event_work; + + /* current channel */ + struct ieee80211_channel *channel; #ifdef CONFIG_CFG80211_DEBUGFS /* Debugfs entries */ @@ -89,13 +103,14 @@ bool wiphy_idx_valid(int wiphy_idx) } extern struct mutex cfg80211_mutex; -extern struct list_head cfg80211_drv_list; +extern struct list_head cfg80211_rdev_list; +extern int cfg80211_rdev_list_generation; #define assert_cfg80211_lock() WARN_ON(!mutex_is_locked(&cfg80211_mutex)) /* * You can use this to mark a wiphy_idx as not having an associated wiphy. - * It guarantees cfg80211_drv_by_wiphy_idx(wiphy_idx) will return NULL + * It guarantees cfg80211_rdev_by_wiphy_idx(wiphy_idx) will return NULL */ #define WIPHY_IDX_STALE -1 @@ -104,17 +119,40 @@ struct cfg80211_internal_bss { struct rb_node rbn; unsigned long ts; struct kref ref; - bool hold, ies_allocated; + atomic_t hold; + bool ies_allocated; /* must be last because of priv member */ struct cfg80211_bss pub; }; -struct cfg80211_registered_device *cfg80211_drv_by_wiphy_idx(int wiphy_idx); +static inline struct cfg80211_internal_bss *bss_from_pub(struct cfg80211_bss *pub) +{ + return container_of(pub, struct cfg80211_internal_bss, pub); +} + +static inline void cfg80211_ref_bss(struct cfg80211_internal_bss *bss) +{ + kref_get(&bss->ref); +} + +static inline void cfg80211_hold_bss(struct cfg80211_internal_bss *bss) +{ + atomic_inc(&bss->hold); +} + +static inline void cfg80211_unhold_bss(struct cfg80211_internal_bss *bss) +{ + int r = atomic_dec_return(&bss->hold); + WARN_ON(r < 0); +} + + +struct cfg80211_registered_device *cfg80211_rdev_by_wiphy_idx(int wiphy_idx); int get_wiphy_idx(struct wiphy *wiphy); struct cfg80211_registered_device * -__cfg80211_drv_from_info(struct genl_info *info); +__cfg80211_rdev_from_info(struct genl_info *info); /* * This function returns a pointer to the driver @@ -122,12 +160,12 @@ __cfg80211_drv_from_info(struct genl_info *info); * If successful, it returns non-NULL and also locks * the driver's mutex! * - * This means that you need to call cfg80211_put_dev() + * This means that you need to call cfg80211_unlock_rdev() * before being allowed to acquire &cfg80211_mutex! * * This is necessary because we need to lock the global * mutex to get an item off the list safely, and then - * we lock the drv mutex so it doesn't go away under us. + * we lock the rdev mutex so it doesn't go away under us. * * We don't want to keep cfg80211_mutex locked * for all the time in order to allow requests on @@ -139,19 +177,93 @@ __cfg80211_drv_from_info(struct genl_info *info); extern struct cfg80211_registered_device * cfg80211_get_dev_from_info(struct genl_info *info); -/* requires cfg80211_drv_mutex to be held! */ +/* requires cfg80211_rdev_mutex to be held! */ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx); /* identical to cfg80211_get_dev_from_info but only operate on ifindex */ extern struct cfg80211_registered_device * -cfg80211_get_dev_from_ifindex(int ifindex); +cfg80211_get_dev_from_ifindex(struct net *net, int ifindex); + +int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, + struct net *net); + +static inline void cfg80211_lock_rdev(struct cfg80211_registered_device *rdev) +{ + mutex_lock(&rdev->mtx); +} + +static inline void cfg80211_unlock_rdev(struct cfg80211_registered_device *rdev) +{ + BUG_ON(IS_ERR(rdev) || !rdev); + mutex_unlock(&rdev->mtx); +} + +static inline void wdev_lock(struct wireless_dev *wdev) + __acquires(wdev) +{ + mutex_lock(&wdev->mtx); + __acquire(wdev->mtx); +} + +static inline void wdev_unlock(struct wireless_dev *wdev) + __releases(wdev) +{ + __release(wdev->mtx); + mutex_unlock(&wdev->mtx); +} + +#define ASSERT_RDEV_LOCK(rdev) WARN_ON(!mutex_is_locked(&(rdev)->mtx)); +#define ASSERT_WDEV_LOCK(wdev) WARN_ON(!mutex_is_locked(&(wdev)->mtx)); + +enum cfg80211_event_type { + EVENT_CONNECT_RESULT, + EVENT_ROAMED, + EVENT_DISCONNECTED, + EVENT_IBSS_JOINED, +}; + +struct cfg80211_event { + struct list_head list; + enum cfg80211_event_type type; + + union { + struct { + u8 bssid[ETH_ALEN]; + const u8 *req_ie; + const u8 *resp_ie; + size_t req_ie_len; + size_t resp_ie_len; + u16 status; + } cr; + struct { + u8 bssid[ETH_ALEN]; + const u8 *req_ie; + const u8 *resp_ie; + size_t req_ie_len; + size_t resp_ie_len; + } rm; + struct { + const u8 *ie; + size_t ie_len; + u16 reason; + } dc; + struct { + u8 bssid[ETH_ALEN]; + } ij; + }; +}; + +struct cfg80211_cached_keys { + struct key_params params[6]; + u8 data[6][WLAN_MAX_KEY_LEN]; + int def, defmgmt; +}; -extern void cfg80211_put_dev(struct cfg80211_registered_device *drv); /* free object */ -extern void cfg80211_dev_free(struct cfg80211_registered_device *drv); +extern void cfg80211_dev_free(struct cfg80211_registered_device *rdev); -extern int cfg80211_dev_rename(struct cfg80211_registered_device *drv, +extern int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, char *newname); void ieee80211_set_bitrate_flags(struct wiphy *wiphy); @@ -163,15 +275,125 @@ void cfg80211_bss_age(struct cfg80211_registered_device *dev, unsigned long age_secs); /* IBSS */ +int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ibss_params *params, + struct cfg80211_cached_keys *connkeys); int cfg80211_join_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev, - struct cfg80211_ibss_params *params); + struct cfg80211_ibss_params *params, + struct cfg80211_cached_keys *connkeys); void cfg80211_clear_ibss(struct net_device *dev, bool nowext); int cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev, bool nowext); +void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid); +int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev); + +/* MLME */ +int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct ieee80211_channel *chan, + enum nl80211_auth_type auth_type, + const u8 *bssid, + const u8 *ssid, int ssid_len, + const u8 *ie, int ie_len, + const u8 *key, int key_len, int key_idx); +int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, + struct net_device *dev, struct ieee80211_channel *chan, + enum nl80211_auth_type auth_type, const u8 *bssid, + const u8 *ssid, int ssid_len, + const u8 *ie, int ie_len, + const u8 *key, int key_len, int key_idx); +int __cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct ieee80211_channel *chan, + const u8 *bssid, const u8 *prev_bssid, + const u8 *ssid, int ssid_len, + const u8 *ie, int ie_len, bool use_mfp, + struct cfg80211_crypto_settings *crypt); +int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, struct ieee80211_channel *chan, + const u8 *bssid, const u8 *prev_bssid, + const u8 *ssid, int ssid_len, + const u8 *ie, int ie_len, bool use_mfp, + struct cfg80211_crypto_settings *crypt); +int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *bssid, + const u8 *ie, int ie_len, u16 reason); +int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *bssid, + const u8 *ie, int ie_len, u16 reason); +int cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *bssid, + const u8 *ie, int ie_len, u16 reason); +void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, + struct net_device *dev); +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, + u16 status, bool wextev, + struct cfg80211_bss *bss); + +/* SME */ +int __cfg80211_connect(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_connect_params *connect, + 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, + struct cfg80211_cached_keys *connkeys); +int __cfg80211_disconnect(struct cfg80211_registered_device *rdev, + struct net_device *dev, u16 reason, + bool wextev); +int cfg80211_disconnect(struct cfg80211_registered_device *rdev, + struct net_device *dev, u16 reason, + bool wextev); +void __cfg80211_roamed(struct wireless_dev *wdev, const u8 *bssid, + const u8 *req_ie, size_t req_ie_len, + const u8 *resp_ie, size_t resp_ie_len); +int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev); + +void cfg80211_conn_work(struct work_struct *work); +void cfg80211_sme_failed_assoc(struct wireless_dev *wdev); +bool cfg80211_sme_failed_reassoc(struct wireless_dev *wdev); /* internal helpers */ -int cfg80211_validate_key_settings(struct key_params *params, int key_idx, +int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, + struct key_params *params, int key_idx, const u8 *mac_addr); +void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, + size_t ie_len, u16 reason, bool from_ap); +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/debugfs.c b/net/wireless/debugfs.c index 679ddfcec1e..13d93d84f90 100644 --- a/net/wireless/debugfs.c +++ b/net/wireless/debugfs.c @@ -104,15 +104,15 @@ static const struct file_operations ht40allow_map_ops = { }; #define DEBUGFS_ADD(name) \ - drv->debugfs.name = debugfs_create_file(#name, S_IRUGO, phyd, \ - &drv->wiphy, &name## _ops); + rdev->debugfs.name = debugfs_create_file(#name, S_IRUGO, phyd, \ + &rdev->wiphy, &name## _ops); #define DEBUGFS_DEL(name) \ - debugfs_remove(drv->debugfs.name); \ - drv->debugfs.name = NULL; + debugfs_remove(rdev->debugfs.name); \ + rdev->debugfs.name = NULL; -void cfg80211_debugfs_drv_add(struct cfg80211_registered_device *drv) +void cfg80211_debugfs_rdev_add(struct cfg80211_registered_device *rdev) { - struct dentry *phyd = drv->wiphy.debugfsdir; + struct dentry *phyd = rdev->wiphy.debugfsdir; DEBUGFS_ADD(rts_threshold); DEBUGFS_ADD(fragmentation_threshold); @@ -121,7 +121,7 @@ void cfg80211_debugfs_drv_add(struct cfg80211_registered_device *drv) DEBUGFS_ADD(ht40allow_map); } -void cfg80211_debugfs_drv_del(struct cfg80211_registered_device *drv) +void cfg80211_debugfs_rdev_del(struct cfg80211_registered_device *rdev) { DEBUGFS_DEL(rts_threshold); DEBUGFS_DEL(fragmentation_threshold); diff --git a/net/wireless/debugfs.h b/net/wireless/debugfs.h index c226983ae66..6419b6d6ce3 100644 --- a/net/wireless/debugfs.h +++ b/net/wireless/debugfs.h @@ -2,13 +2,13 @@ #define __CFG80211_DEBUGFS_H #ifdef CONFIG_CFG80211_DEBUGFS -void cfg80211_debugfs_drv_add(struct cfg80211_registered_device *drv); -void cfg80211_debugfs_drv_del(struct cfg80211_registered_device *drv); +void cfg80211_debugfs_rdev_add(struct cfg80211_registered_device *rdev); +void cfg80211_debugfs_rdev_del(struct cfg80211_registered_device *rdev); #else static inline -void cfg80211_debugfs_drv_add(struct cfg80211_registered_device *drv) {} +void cfg80211_debugfs_rdev_add(struct cfg80211_registered_device *rdev) {} static inline -void cfg80211_debugfs_drv_del(struct cfg80211_registered_device *drv) {} +void cfg80211_debugfs_rdev_del(struct cfg80211_registered_device *rdev) {} #endif #endif /* __CFG80211_DEBUGFS_H */ diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index a4a1c3498ff..c8833891197 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -7,10 +7,11 @@ #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <net/cfg80211.h> +#include "wext-compat.h" #include "nl80211.h" -void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) +void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_bss *bss; @@ -21,10 +22,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) return; - if (WARN_ON(!wdev->ssid_len)) - return; - - if (memcmp(bssid, wdev->bssid, ETH_ALEN) == 0) + if (!wdev->ssid_len) return; bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, @@ -36,39 +34,76 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) if (wdev->current_bss) { cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->current_bss); + cfg80211_put_bss(&wdev->current_bss->pub); } - cfg80211_hold_bss(bss); - wdev->current_bss = bss; - memcpy(wdev->bssid, bssid, ETH_ALEN); + cfg80211_hold_bss(bss_from_pub(bss)); + wdev->current_bss = bss_from_pub(bss); + + cfg80211_upload_connect_keys(wdev); - nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid, gfp); + nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid, + GFP_KERNEL); #ifdef CONFIG_WIRELESS_EXT memset(&wrqu, 0, sizeof(wrqu)); memcpy(wrqu.ap_addr.sa_data, bssid, ETH_ALEN); wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); #endif } + +void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct cfg80211_event *ev; + unsigned long flags; + + CFG80211_DEV_WARN_ON(!wdev->ssid_len); + + ev = kzalloc(sizeof(*ev), gfp); + if (!ev) + return; + + ev->type = EVENT_IBSS_JOINED; + memcpy(ev->cr.bssid, bssid, ETH_ALEN); + + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + schedule_work(&rdev->event_work); +} EXPORT_SYMBOL(cfg80211_ibss_joined); -int cfg80211_join_ibss(struct cfg80211_registered_device *rdev, - struct net_device *dev, - struct cfg80211_ibss_params *params) +int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ibss_params *params, + 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; + if (WARN_ON(wdev->connect_keys)) + kfree(wdev->connect_keys); + wdev->connect_keys = connkeys; + #ifdef CONFIG_WIRELESS_EXT wdev->wext.ibss.channel = params->channel; #endif err = rdev->ops->join_ibss(&rdev->wiphy, dev, params); - - if (err) + if (err) { + wdev->connect_keys = NULL; return err; + } memcpy(wdev->ssid, params->ssid, params->ssid_len); wdev->ssid_len = params->ssid_len; @@ -76,45 +111,107 @@ int cfg80211_join_ibss(struct cfg80211_registered_device *rdev, return 0; } -void cfg80211_clear_ibss(struct net_device *dev, bool nowext) +int cfg80211_join_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ibss_params *params, + struct cfg80211_cached_keys *connkeys) +{ + 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; +} + +static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + int i; + + ASSERT_WDEV_LOCK(wdev); + + kfree(wdev->connect_keys); + wdev->connect_keys = NULL; + + /* + * Delete all the keys ... pairwise keys can't really + * exist any more anyway, but default keys might. + */ + if (rdev->ops->del_key) + for (i = 0; i < 6; i++) + rdev->ops->del_key(wdev->wiphy, dev, i, NULL); if (wdev->current_bss) { cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->current_bss); + cfg80211_put_bss(&wdev->current_bss->pub); } wdev->current_bss = NULL; wdev->ssid_len = 0; - memset(wdev->bssid, 0, ETH_ALEN); #ifdef CONFIG_WIRELESS_EXT if (!nowext) wdev->wext.ibss.ssid_len = 0; #endif } -int cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, - struct net_device *dev, bool nowext) +void cfg80211_clear_ibss(struct net_device *dev, bool nowext) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + wdev_lock(wdev); + __cfg80211_clear_ibss(dev, nowext); + wdev_unlock(wdev); +} + +static int __cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev, bool nowext) { + struct wireless_dev *wdev = dev->ieee80211_ptr; int err; + ASSERT_WDEV_LOCK(wdev); + + if (!wdev->ssid_len) + return -ENOLINK; + err = rdev->ops->leave_ibss(&rdev->wiphy, dev); if (err) return err; - cfg80211_clear_ibss(dev, nowext); + __cfg80211_clear_ibss(dev, nowext); return 0; } +int cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev, bool nowext) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + wdev_lock(wdev); + err = __cfg80211_leave_ibss(rdev, dev, nowext); + wdev_unlock(wdev); + + return err; +} + #ifdef CONFIG_WIRELESS_EXT -static int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev) +int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) { + struct cfg80211_cached_keys *ck = NULL; enum ieee80211_band band; - int i; + int i, err; + + ASSERT_WDEV_LOCK(wdev); if (!wdev->wext.ibss.beacon_interval) wdev->wext.ibss.beacon_interval = 100; @@ -154,43 +251,66 @@ static int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, if (!netif_running(wdev->netdev)) return 0; - return cfg80211_join_ibss(wiphy_to_dev(wdev->wiphy), - wdev->netdev, &wdev->wext.ibss); + if (wdev->wext.keys) + wdev->wext.keys->def = wdev->wext.default_key; + + wdev->wext.ibss.privacy = wdev->wext.default_key != -1; + + if (wdev->wext.keys) { + ck = kmemdup(wdev->wext.keys, sizeof(*ck), GFP_KERNEL); + if (!ck) + return -ENOMEM; + for (i = 0; i < 6; i++) + ck->params[i].key = ck->data[i]; + } + err = __cfg80211_join_ibss(rdev, wdev->netdev, + &wdev->wext.ibss, ck); + if (err) + kfree(ck); + + return err; } 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; - if (wdev->ssid_len) { - err = cfg80211_leave_ibss(wiphy_to_dev(wdev->wiphy), - dev, true); - if (err) - return err; - } + wdev_lock(wdev); + err = 0; + if (wdev->ssid_len) + err = __cfg80211_leave_ibss(rdev, dev, true); + wdev_unlock(wdev); + + if (err) + return err; if (chan) { wdev->wext.ibss.channel = chan; @@ -200,10 +320,14 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, wdev->wext.ibss.channel_fixed = false; } - return cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); + mutex_lock(&rdev->devlist_mtx); + wdev_lock(wdev); + err = cfg80211_ibss_wext_join(rdev, wdev); + wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); + + return err; } -/* temporary symbol - mark GPL - in the future the handler won't be */ -EXPORT_SYMBOL_GPL(cfg80211_ibss_wext_siwfreq); int cfg80211_ibss_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, @@ -216,10 +340,12 @@ int cfg80211_ibss_wext_giwfreq(struct net_device *dev, if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) return -EINVAL; + wdev_lock(wdev); if (wdev->current_bss) - chan = wdev->current_bss->channel; + chan = wdev->current_bss->pub.channel; else if (wdev->wext.ibss.channel) chan = wdev->wext.ibss.channel; + wdev_unlock(wdev); if (chan) { freq->m = chan->center_freq; @@ -230,14 +356,13 @@ int cfg80211_ibss_wext_giwfreq(struct net_device *dev, /* no channel if not joining */ return -EINVAL; } -/* temporary symbol - mark GPL - in the future the handler won't be */ -EXPORT_SYMBOL_GPL(cfg80211_ibss_wext_giwfreq); int cfg80211_ibss_wext_siwessid(struct net_device *dev, struct iw_request_info *info, 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; @@ -245,15 +370,17 @@ 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; - if (wdev->ssid_len) { - err = cfg80211_leave_ibss(wiphy_to_dev(wdev->wiphy), - dev, true); - if (err) - return err; - } + wdev_lock(wdev); + err = 0; + if (wdev->ssid_len) + err = __cfg80211_leave_ibss(rdev, dev, true); + wdev_unlock(wdev); + + if (err) + return err; /* iwconfig uses nul termination in SSID.. */ if (len > 0 && ssid[len - 1] == '\0') @@ -263,10 +390,14 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev, memcpy(wdev->wext.ibss.ssid, ssid, len); wdev->wext.ibss.ssid_len = len; - return cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); + mutex_lock(&rdev->devlist_mtx); + wdev_lock(wdev); + err = cfg80211_ibss_wext_join(rdev, wdev); + wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); + + return err; } -/* temporary symbol - mark GPL - in the future the handler won't be */ -EXPORT_SYMBOL_GPL(cfg80211_ibss_wext_siwessid); int cfg80211_ibss_wext_giwessid(struct net_device *dev, struct iw_request_info *info, @@ -280,6 +411,7 @@ int cfg80211_ibss_wext_giwessid(struct net_device *dev, data->flags = 0; + wdev_lock(wdev); if (wdev->ssid_len) { data->flags = 1; data->length = wdev->ssid_len; @@ -289,17 +421,17 @@ int cfg80211_ibss_wext_giwessid(struct net_device *dev, data->length = wdev->wext.ibss.ssid_len; memcpy(ssid, wdev->wext.ibss.ssid, data->length); } + wdev_unlock(wdev); return 0; } -/* temporary symbol - mark GPL - in the future the handler won't be */ -EXPORT_SYMBOL_GPL(cfg80211_ibss_wext_giwessid); int cfg80211_ibss_wext_siwap(struct net_device *dev, struct iw_request_info *info, 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; @@ -307,7 +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) @@ -326,12 +458,14 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev, compare_ether_addr(bssid, wdev->wext.ibss.bssid) == 0) return 0; - if (wdev->ssid_len) { - err = cfg80211_leave_ibss(wiphy_to_dev(wdev->wiphy), - dev, true); - if (err) - return err; - } + wdev_lock(wdev); + err = 0; + if (wdev->ssid_len) + err = __cfg80211_leave_ibss(rdev, dev, true); + wdev_unlock(wdev); + + if (err) + return err; if (bssid) { memcpy(wdev->wext.bssid, bssid, ETH_ALEN); @@ -339,10 +473,14 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev, } else wdev->wext.ibss.bssid = NULL; - return cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); + mutex_lock(&rdev->devlist_mtx); + wdev_lock(wdev); + err = cfg80211_ibss_wext_join(rdev, wdev); + wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); + + return err; } -/* temporary symbol - mark GPL - in the future the handler won't be */ -EXPORT_SYMBOL_GPL(cfg80211_ibss_wext_siwap); int cfg80211_ibss_wext_giwap(struct net_device *dev, struct iw_request_info *info, @@ -356,14 +494,16 @@ int cfg80211_ibss_wext_giwap(struct net_device *dev, ap_addr->sa_family = ARPHRD_ETHER; - if (wdev->wext.ibss.bssid) { + wdev_lock(wdev); + if (wdev->current_bss) + memcpy(ap_addr->sa_data, wdev->current_bss->pub.bssid, ETH_ALEN); + else if (wdev->wext.ibss.bssid) memcpy(ap_addr->sa_data, wdev->wext.ibss.bssid, ETH_ALEN); - return 0; - } + else + memset(ap_addr->sa_data, 0, ETH_ALEN); + + wdev_unlock(wdev); - memcpy(ap_addr->sa_data, wdev->bssid, ETH_ALEN); return 0; } -/* temporary symbol - mark GPL - in the future the handler won't be */ -EXPORT_SYMBOL_GPL(cfg80211_ibss_wext_giwap); #endif diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 42184361a10..0a6b7a0eca6 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -8,75 +8,661 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/nl80211.h> +#include <linux/wireless.h> #include <net/cfg80211.h> +#include <net/iw_handler.h> #include "core.h" #include "nl80211.h" void cfg80211_send_rx_auth(struct net_device *dev, const u8 *buf, size_t len) { - struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_rx_auth(rdev, dev, buf, len); + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; + u8 *bssid = mgmt->bssid; + int i; + u16 status = le16_to_cpu(mgmt->u.auth.status_code); + bool done = false; + + wdev_lock(wdev); + + for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (wdev->authtry_bsses[i] && + memcmp(wdev->authtry_bsses[i]->pub.bssid, bssid, + ETH_ALEN) == 0) { + if (status == WLAN_STATUS_SUCCESS) { + wdev->auth_bsses[i] = wdev->authtry_bsses[i]; + } else { + cfg80211_unhold_bss(wdev->authtry_bsses[i]); + cfg80211_put_bss(&wdev->authtry_bsses[i]->pub); + } + wdev->authtry_bsses[i] = NULL; + done = true; + break; + } + } + + WARN_ON(!done); + + nl80211_send_rx_auth(rdev, dev, buf, len, GFP_KERNEL); + cfg80211_sme_rx_auth(dev, buf, len); + + wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_rx_auth); void cfg80211_send_rx_assoc(struct net_device *dev, const u8 *buf, size_t len) { - struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + u16 status_code; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_rx_assoc(rdev, dev, buf, len); + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; + u8 *ie = mgmt->u.assoc_resp.variable; + int i, ieoffs = offsetof(struct ieee80211_mgmt, u.assoc_resp.variable); + struct cfg80211_internal_bss *bss = NULL; + bool need_connect_result = true; + + wdev_lock(wdev); + + 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) { + for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (!wdev->auth_bsses[i]) + continue; + if (memcmp(wdev->auth_bsses[i]->pub.bssid, mgmt->bssid, + ETH_ALEN) == 0) { + bss = wdev->auth_bsses[i]; + wdev->auth_bsses[i] = NULL; + /* additional reference to drop hold */ + cfg80211_ref_bss(bss); + break; + } + } + + WARN_ON(!bss); + } else if (wdev->conn) { + cfg80211_sme_failed_assoc(wdev); + need_connect_result = false; + /* + * do not call connect_result() now because the + * sme will schedule work that does it later. + */ + goto out; + } + + 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, + status_code == WLAN_STATUS_SUCCESS, + bss ? &bss->pub : NULL); + /* drop hold now, and also reference acquired above */ + if (bss) { + cfg80211_unhold_bss(bss); + cfg80211_put_bss(&bss->pub); + } + + out: + wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_rx_assoc); -void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len) +static void __cfg80211_send_deauth(struct net_device *dev, + const u8 *buf, size_t len) { - struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_deauth(rdev, dev, buf, len); + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; + const u8 *bssid = mgmt->bssid; + int i; + bool done = false; + + ASSERT_WDEV_LOCK(wdev); + + nl80211_send_deauth(rdev, dev, buf, len, GFP_KERNEL); + + if (wdev->current_bss && + memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) { + done = true; + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(&wdev->current_bss->pub); + wdev->current_bss = NULL; + } else for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (wdev->auth_bsses[i] && + memcmp(wdev->auth_bsses[i]->pub.bssid, bssid, ETH_ALEN) == 0) { + cfg80211_unhold_bss(wdev->auth_bsses[i]); + cfg80211_put_bss(&wdev->auth_bsses[i]->pub); + wdev->auth_bsses[i] = NULL; + done = true; + break; + } + if (wdev->authtry_bsses[i] && + memcmp(wdev->authtry_bsses[i]->pub.bssid, bssid, ETH_ALEN) == 0) { + cfg80211_unhold_bss(wdev->authtry_bsses[i]); + cfg80211_put_bss(&wdev->authtry_bsses[i]->pub); + wdev->authtry_bsses[i] = NULL; + done = true; + break; + } + } + + WARN_ON(!done); + + if (wdev->sme_state == CFG80211_SME_CONNECTED) { + u16 reason_code; + bool from_ap; + + reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); + + 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, + WLAN_STATUS_UNSPECIFIED_FAILURE, + false, NULL); + } +} + + +void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len, + void *cookie) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + BUG_ON(cookie && wdev != cookie); + + if (cookie) { + /* called within callback */ + __cfg80211_send_deauth(dev, buf, len); + } else { + wdev_lock(wdev); + __cfg80211_send_deauth(dev, buf, len); + wdev_unlock(wdev); + } } EXPORT_SYMBOL(cfg80211_send_deauth); -void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len) +static void __cfg80211_send_disassoc(struct net_device *dev, + const u8 *buf, size_t len) { - struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_disassoc(rdev, dev, buf, len); + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; + const u8 *bssid = mgmt->bssid; + int i; + u16 reason_code; + bool from_ap; + bool done = false; + + ASSERT_WDEV_LOCK(wdev); + + nl80211_send_disassoc(rdev, dev, buf, len, GFP_KERNEL); + + if (wdev->sme_state != CFG80211_SME_CONNECTED) + return; + + if (wdev->current_bss && + 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; + wdev->auth_bsses[i] = wdev->current_bss; + wdev->current_bss = NULL; + done = true; + cfg80211_sme_disassoc(dev, i); + break; + } + WARN_ON(!done); + } else + WARN_ON(1); + + + reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code); + + from_ap = memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) != 0; + __cfg80211_disconnected(dev, NULL, 0, reason_code, from_ap); } -EXPORT_SYMBOL(cfg80211_send_disassoc); -static void cfg80211_wext_disconnected(struct net_device *dev) +void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len, + void *cookie) { -#ifdef CONFIG_WIRELESS_EXT - union iwreq_data wrqu; - memset(&wrqu, 0, sizeof(wrqu)); - wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); -#endif + struct wireless_dev *wdev = dev->ieee80211_ptr; + + BUG_ON(cookie && wdev != cookie); + + if (cookie) { + /* called within callback */ + __cfg80211_send_disassoc(dev, buf, len); + } else { + wdev_lock(wdev); + __cfg80211_send_disassoc(dev, buf, len); + wdev_unlock(wdev); + } } +EXPORT_SYMBOL(cfg80211_send_disassoc); void cfg80211_send_auth_timeout(struct net_device *dev, const u8 *addr) { - struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_auth_timeout(rdev, dev, addr); - cfg80211_wext_disconnected(dev); + int i; + bool done = false; + + wdev_lock(wdev); + + nl80211_send_auth_timeout(rdev, dev, addr, GFP_KERNEL); + if (wdev->sme_state == CFG80211_SME_CONNECTING) + __cfg80211_connect_result(dev, addr, NULL, 0, NULL, 0, + WLAN_STATUS_UNSPECIFIED_FAILURE, + false, NULL); + + for (i = 0; addr && i < MAX_AUTH_BSSES; i++) { + if (wdev->authtry_bsses[i] && + memcmp(wdev->authtry_bsses[i]->pub.bssid, + addr, ETH_ALEN) == 0) { + cfg80211_unhold_bss(wdev->authtry_bsses[i]); + cfg80211_put_bss(&wdev->authtry_bsses[i]->pub); + wdev->authtry_bsses[i] = NULL; + done = true; + break; + } + } + + WARN_ON(!done); + + wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_auth_timeout); void cfg80211_send_assoc_timeout(struct net_device *dev, const u8 *addr) { - struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_assoc_timeout(rdev, dev, addr); - cfg80211_wext_disconnected(dev); + int i; + bool done = false; + + wdev_lock(wdev); + + nl80211_send_assoc_timeout(rdev, dev, addr, GFP_KERNEL); + if (wdev->sme_state == CFG80211_SME_CONNECTING) + __cfg80211_connect_result(dev, addr, NULL, 0, NULL, 0, + WLAN_STATUS_UNSPECIFIED_FAILURE, + false, NULL); + + for (i = 0; addr && i < MAX_AUTH_BSSES; i++) { + if (wdev->auth_bsses[i] && + memcmp(wdev->auth_bsses[i]->pub.bssid, + addr, ETH_ALEN) == 0) { + cfg80211_unhold_bss(wdev->auth_bsses[i]); + cfg80211_put_bss(&wdev->auth_bsses[i]->pub); + wdev->auth_bsses[i] = NULL; + done = true; + break; + } + } + + WARN_ON(!done); + + wdev_unlock(wdev); } EXPORT_SYMBOL(cfg80211_send_assoc_timeout); void cfg80211_michael_mic_failure(struct net_device *dev, const u8 *addr, enum nl80211_key_type key_type, int key_id, - const u8 *tsc) + const u8 *tsc, gfp_t gfp) { struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_michael_mic_failure(rdev, dev, addr, key_type, key_id, tsc); +#ifdef CONFIG_WIRELESS_EXT + union iwreq_data wrqu; + char *buf = kmalloc(128, gfp); + + if (buf) { + sprintf(buf, "MLME-MICHAELMICFAILURE.indication(" + "keyid=%d %scast addr=%pM)", key_id, + key_type == NL80211_KEYTYPE_GROUP ? "broad" : "uni", + addr); + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.data.length = strlen(buf); + wireless_send_event(dev, IWEVCUSTOM, &wrqu, buf); + kfree(buf); + } +#endif + + nl80211_michael_mic_failure(rdev, dev, addr, key_type, key_id, tsc, gfp); } EXPORT_SYMBOL(cfg80211_michael_mic_failure); + +/* some MLME handling for userspace SME */ +int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct ieee80211_channel *chan, + enum nl80211_auth_type auth_type, + const u8 *bssid, + const u8 *ssid, int ssid_len, + const u8 *ie, int ie_len, + const u8 *key, int key_len, int key_idx) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_auth_request req; + struct cfg80211_internal_bss *bss; + int i, err, slot = -1, nfree = 0; + + ASSERT_WDEV_LOCK(wdev); + + if (auth_type == NL80211_AUTHTYPE_SHARED_KEY) + if (!key || !key_len || key_idx < 0 || key_idx > 4) + return -EINVAL; + + if (wdev->current_bss && + memcmp(bssid, wdev->current_bss->pub.bssid, ETH_ALEN) == 0) + return -EALREADY; + + for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (wdev->authtry_bsses[i] && + memcmp(bssid, wdev->authtry_bsses[i]->pub.bssid, + ETH_ALEN) == 0) + return -EALREADY; + if (wdev->auth_bsses[i] && + memcmp(bssid, wdev->auth_bsses[i]->pub.bssid, + ETH_ALEN) == 0) + return -EALREADY; + } + + memset(&req, 0, sizeof(req)); + + req.ie = ie; + req.ie_len = ie_len; + req.auth_type = auth_type; + req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len, + WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS); + req.key = key; + req.key_len = key_len; + req.key_idx = key_idx; + if (!req.bss) + return -ENOENT; + + bss = bss_from_pub(req.bss); + + for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (!wdev->auth_bsses[i] && !wdev->authtry_bsses[i]) { + slot = i; + nfree++; + } + } + + /* we need one free slot for disassoc and one for this auth */ + if (nfree < 2) { + err = -ENOSPC; + goto out; + } + + wdev->authtry_bsses[slot] = bss; + cfg80211_hold_bss(bss); + + err = rdev->ops->auth(&rdev->wiphy, dev, &req); + if (err) { + wdev->authtry_bsses[slot] = NULL; + cfg80211_unhold_bss(bss); + } + + out: + if (err) + cfg80211_put_bss(req.bss); + return err; +} + +int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, + struct net_device *dev, struct ieee80211_channel *chan, + enum nl80211_auth_type auth_type, const u8 *bssid, + const u8 *ssid, int ssid_len, + const u8 *ie, int ie_len, + const u8 *key, int key_len, int key_idx) +{ + int err; + + wdev_lock(dev->ieee80211_ptr); + err = __cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, + ssid, ssid_len, ie, ie_len, + key, key_len, key_idx); + wdev_unlock(dev->ieee80211_ptr); + + return err; +} + +int __cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct ieee80211_channel *chan, + const u8 *bssid, const u8 *prev_bssid, + const u8 *ssid, int ssid_len, + const u8 *ie, int ie_len, bool use_mfp, + struct cfg80211_crypto_settings *crypt) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_assoc_request req; + struct cfg80211_internal_bss *bss; + int i, err, slot = -1; + + ASSERT_WDEV_LOCK(wdev); + + memset(&req, 0, sizeof(req)); + + if (wdev->current_bss) + return -EALREADY; + + req.ie = ie; + req.ie_len = ie_len; + memcpy(&req.crypto, crypt, sizeof(req.crypto)); + req.use_mfp = use_mfp; + req.prev_bssid = prev_bssid; + req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len, + WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS); + if (!req.bss) + return -ENOENT; + + bss = bss_from_pub(req.bss); + + for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (bss == wdev->auth_bsses[i]) { + slot = i; + break; + } + } + + if (slot < 0) { + err = -ENOTCONN; + goto out; + } + + err = rdev->ops->assoc(&rdev->wiphy, dev, &req); + out: + /* still a reference in wdev->auth_bsses[slot] */ + cfg80211_put_bss(req.bss); + return err; +} + +int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct ieee80211_channel *chan, + const u8 *bssid, const u8 *prev_bssid, + const u8 *ssid, int ssid_len, + const u8 *ie, int ie_len, bool use_mfp, + struct cfg80211_crypto_settings *crypt) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + wdev_lock(wdev); + err = __cfg80211_mlme_assoc(rdev, dev, chan, bssid, prev_bssid, + ssid, ssid_len, ie, ie_len, use_mfp, crypt); + wdev_unlock(wdev); + + return err; +} + +int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *bssid, + const u8 *ie, int ie_len, u16 reason) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_deauth_request req; + int i; + + ASSERT_WDEV_LOCK(wdev); + + memset(&req, 0, sizeof(req)); + req.reason_code = reason; + req.ie = ie; + req.ie_len = ie_len; + if (wdev->current_bss && + memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) { + req.bss = &wdev->current_bss->pub; + } else for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (wdev->auth_bsses[i] && + memcmp(bssid, wdev->auth_bsses[i]->pub.bssid, ETH_ALEN) == 0) { + req.bss = &wdev->auth_bsses[i]->pub; + break; + } + if (wdev->authtry_bsses[i] && + memcmp(bssid, wdev->authtry_bsses[i]->pub.bssid, ETH_ALEN) == 0) { + req.bss = &wdev->authtry_bsses[i]->pub; + break; + } + } + + if (!req.bss) + return -ENOTCONN; + + return rdev->ops->deauth(&rdev->wiphy, dev, &req, wdev); +} + +int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *bssid, + const u8 *ie, int ie_len, u16 reason) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + wdev_lock(wdev); + err = __cfg80211_mlme_deauth(rdev, dev, bssid, ie, ie_len, reason); + wdev_unlock(wdev); + + return err; +} + +static int __cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *bssid, + const u8 *ie, int ie_len, u16 reason) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_disassoc_request req; + + ASSERT_WDEV_LOCK(wdev); + + if (wdev->sme_state != CFG80211_SME_CONNECTED) + return -ENOTCONN; + + if (WARN_ON(!wdev->current_bss)) + return -ENOTCONN; + + memset(&req, 0, sizeof(req)); + req.reason_code = reason; + req.ie = ie; + req.ie_len = ie_len; + if (memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) + req.bss = &wdev->current_bss->pub; + else + return -ENOTCONN; + + return rdev->ops->disassoc(&rdev->wiphy, dev, &req, wdev); +} + +int cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *bssid, + const u8 *ie, int ie_len, u16 reason) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + wdev_lock(wdev); + err = __cfg80211_mlme_disassoc(rdev, dev, bssid, ie, ie_len, reason); + wdev_unlock(wdev); + + return err; +} + +void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_deauth_request req; + int i; + + ASSERT_WDEV_LOCK(wdev); + + if (!rdev->ops->deauth) + return; + + memset(&req, 0, sizeof(req)); + req.reason_code = WLAN_REASON_DEAUTH_LEAVING; + req.ie = NULL; + req.ie_len = 0; + + if (wdev->current_bss) { + req.bss = &wdev->current_bss->pub; + rdev->ops->deauth(&rdev->wiphy, dev, &req, wdev); + if (wdev->current_bss) { + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(&wdev->current_bss->pub); + wdev->current_bss = NULL; + } + } + + for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (wdev->auth_bsses[i]) { + req.bss = &wdev->auth_bsses[i]->pub; + rdev->ops->deauth(&rdev->wiphy, dev, &req, wdev); + if (wdev->auth_bsses[i]) { + cfg80211_unhold_bss(wdev->auth_bsses[i]); + cfg80211_put_bss(&wdev->auth_bsses[i]->pub); + wdev->auth_bsses[i] = NULL; + } + } + if (wdev->authtry_bsses[i]) { + req.bss = &wdev->authtry_bsses[i]->pub; + rdev->ops->deauth(&rdev->wiphy, dev, &req, wdev); + if (wdev->authtry_bsses[i]) { + cfg80211_unhold_bss(wdev->authtry_bsses[i]); + cfg80211_put_bss(&wdev->authtry_bsses[i]->pub); + wdev->authtry_bsses[i] = NULL; + } + } + } +} diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 634496b3ed7..ca3c92a0a14 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14,8 +14,10 @@ #include <linux/rtnetlink.h> #include <linux/netlink.h> #include <linux/etherdevice.h> +#include <net/net_namespace.h> #include <net/genetlink.h> #include <net/cfg80211.h> +#include <net/sock.h> #include "core.h" #include "nl80211.h" #include "reg.h" @@ -27,27 +29,29 @@ static struct genl_family nl80211_fam = { .hdrsize = 0, /* no private header */ .version = 1, /* no particular meaning now */ .maxattr = NL80211_ATTR_MAX, + .netnsok = true, }; -/* internal helper: get drv and dev */ -static int get_drv_dev_by_info_ifindex(struct nlattr **attrs, - struct cfg80211_registered_device **drv, +/* internal helper: get rdev and dev */ +static int get_rdev_dev_by_info_ifindex(struct genl_info *info, + struct cfg80211_registered_device **rdev, struct net_device **dev) { + struct nlattr **attrs = info->attrs; int ifindex; if (!attrs[NL80211_ATTR_IFINDEX]) return -EINVAL; ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); - *dev = dev_get_by_index(&init_net, ifindex); + *dev = dev_get_by_index(genl_info_net(info), ifindex); if (!*dev) return -ENODEV; - *drv = cfg80211_get_dev_from_ifindex(ifindex); - if (IS_ERR(*drv)) { + *rdev = cfg80211_get_dev_from_ifindex(genl_info_net(info), ifindex); + if (IS_ERR(*rdev)) { dev_put(*dev); - return PTR_ERR(*drv); + return PTR_ERR(*rdev); } return 0; @@ -71,7 +75,9 @@ static struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] __read_mostly = { [NL80211_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 }, [NL80211_ATTR_MAC] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [NL80211_ATTR_PREV_BSSID] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [NL80211_ATTR_KEY] = { .type = NLA_NESTED, }, [NL80211_ATTR_KEY_DATA] = { .type = NLA_BINARY, .len = WLAN_MAX_KEY_LEN }, [NL80211_ATTR_KEY_IDX] = { .type = NLA_U8 }, @@ -128,6 +134,21 @@ static struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] __read_mostly = { .len = sizeof(struct nl80211_sta_flag_update), }, [NL80211_ATTR_CONTROL_PORT] = { .type = NLA_FLAG }, + [NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG }, + [NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 }, + [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, + [NL80211_ATTR_PID] = { .type = NLA_U32 }, +}; + +/* policy for the attributes */ +static struct nla_policy +nl80211_key_policy[NL80211_KEY_MAX + 1] __read_mostly = { + [NL80211_KEY_DATA] = { .type = NLA_BINARY, .len = WLAN_MAX_KEY_LEN }, + [NL80211_KEY_IDX] = { .type = NLA_U8 }, + [NL80211_KEY_CIPHER] = { .type = NLA_U32 }, + [NL80211_KEY_SEQ] = { .type = NLA_BINARY, .len = 8 }, + [NL80211_KEY_DEFAULT] = { .type = NLA_FLAG }, + [NL80211_KEY_DEFAULT_MGMT] = { .type = NLA_FLAG }, }; /* IE validation */ @@ -194,6 +215,177 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, /* netlink command implementations */ +struct key_parse { + struct key_params p; + int idx; + bool def, defmgmt; +}; + +static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k) +{ + struct nlattr *tb[NL80211_KEY_MAX + 1]; + int err = nla_parse_nested(tb, NL80211_KEY_MAX, key, + nl80211_key_policy); + if (err) + return err; + + k->def = !!tb[NL80211_KEY_DEFAULT]; + k->defmgmt = !!tb[NL80211_KEY_DEFAULT_MGMT]; + + if (tb[NL80211_KEY_IDX]) + k->idx = nla_get_u8(tb[NL80211_KEY_IDX]); + + if (tb[NL80211_KEY_DATA]) { + k->p.key = nla_data(tb[NL80211_KEY_DATA]); + k->p.key_len = nla_len(tb[NL80211_KEY_DATA]); + } + + if (tb[NL80211_KEY_SEQ]) { + k->p.seq = nla_data(tb[NL80211_KEY_SEQ]); + k->p.seq_len = nla_len(tb[NL80211_KEY_SEQ]); + } + + if (tb[NL80211_KEY_CIPHER]) + k->p.cipher = nla_get_u32(tb[NL80211_KEY_CIPHER]); + + return 0; +} + +static int nl80211_parse_key_old(struct genl_info *info, struct key_parse *k) +{ + if (info->attrs[NL80211_ATTR_KEY_DATA]) { + k->p.key = nla_data(info->attrs[NL80211_ATTR_KEY_DATA]); + k->p.key_len = nla_len(info->attrs[NL80211_ATTR_KEY_DATA]); + } + + if (info->attrs[NL80211_ATTR_KEY_SEQ]) { + k->p.seq = nla_data(info->attrs[NL80211_ATTR_KEY_SEQ]); + k->p.seq_len = nla_len(info->attrs[NL80211_ATTR_KEY_SEQ]); + } + + if (info->attrs[NL80211_ATTR_KEY_IDX]) + k->idx = nla_get_u8(info->attrs[NL80211_ATTR_KEY_IDX]); + + if (info->attrs[NL80211_ATTR_KEY_CIPHER]) + k->p.cipher = nla_get_u32(info->attrs[NL80211_ATTR_KEY_CIPHER]); + + k->def = !!info->attrs[NL80211_ATTR_KEY_DEFAULT]; + k->defmgmt = !!info->attrs[NL80211_ATTR_KEY_DEFAULT_MGMT]; + + return 0; +} + +static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) +{ + int err; + + memset(k, 0, sizeof(*k)); + k->idx = -1; + + if (info->attrs[NL80211_ATTR_KEY]) + err = nl80211_parse_key_new(info->attrs[NL80211_ATTR_KEY], k); + else + err = nl80211_parse_key_old(info, k); + + if (err) + return err; + + if (k->def && k->defmgmt) + return -EINVAL; + + if (k->idx != -1) { + if (k->defmgmt) { + if (k->idx < 4 || k->idx > 5) + return -EINVAL; + } else if (k->def) { + if (k->idx < 0 || k->idx > 3) + return -EINVAL; + } else { + if (k->idx < 0 || k->idx > 5) + return -EINVAL; + } + } + + return 0; +} + +static struct cfg80211_cached_keys * +nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, + struct nlattr *keys) +{ + struct key_parse parse; + struct nlattr *key; + struct cfg80211_cached_keys *result; + int rem, err, def = 0; + + result = kzalloc(sizeof(*result), GFP_KERNEL); + if (!result) + return ERR_PTR(-ENOMEM); + + result->def = -1; + result->defmgmt = -1; + + nla_for_each_nested(key, keys, rem) { + memset(&parse, 0, sizeof(parse)); + parse.idx = -1; + + err = nl80211_parse_key_new(key, &parse); + if (err) + goto error; + err = -EINVAL; + if (!parse.p.key) + goto error; + if (parse.idx < 0 || parse.idx > 4) + goto error; + if (parse.def) { + if (def) + goto error; + def = 1; + result->def = parse.idx; + } else if (parse.defmgmt) + goto error; + err = cfg80211_validate_key_settings(rdev, &parse.p, + parse.idx, NULL); + if (err) + goto error; + result->params[parse.idx].cipher = parse.p.cipher; + result->params[parse.idx].key_len = parse.p.key_len; + result->params[parse.idx].key = result->data[parse.idx]; + memcpy(result->data[parse.idx], parse.p.key, parse.p.key_len); + } + + return result; + error: + kfree(result); + return ERR_PTR(err); +} + +static int nl80211_key_allowed(struct wireless_dev *wdev) +{ + ASSERT_WDEV_LOCK(wdev); + + if (!netif_running(wdev->netdev)) + return -ENETDOWN; + + switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + break; + case NL80211_IFTYPE_ADHOC: + if (!wdev->current_bss) + return -ENOLINK; + break; + case NL80211_IFTYPE_STATION: + if (wdev->sme_state != CFG80211_SME_CONNECTED) + return -ENOLINK; + break; + default: + return -EINVAL; + } + + return 0; +} + static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, struct cfg80211_registered_device *dev) { @@ -216,6 +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, @@ -345,8 +540,23 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, CMD(deauth, DEAUTHENTICATE); CMD(disassoc, DISASSOCIATE); CMD(join_ibss, JOIN_IBSS); + if (dev->wiphy.netnsok) { + i++; + NLA_PUT_U32(msg, i, NL80211_CMD_SET_WIPHY_NETNS); + } #undef CMD + + if (dev->ops->connect || dev->ops->auth) { + i++; + NLA_PUT_U32(msg, i, NL80211_CMD_CONNECT); + } + + if (dev->ops->disconnect || dev->ops->deauth) { + i++; + NLA_PUT_U32(msg, i, NL80211_CMD_DISCONNECT); + } + nla_nest_end(msg, nl_cmds); return genlmsg_end(msg, hdr); @@ -363,7 +573,9 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) struct cfg80211_registered_device *dev; mutex_lock(&cfg80211_mutex); - list_for_each_entry(dev, &cfg80211_drv_list, list) { + list_for_each_entry(dev, &cfg80211_rdev_list, list) { + if (!net_eq(wiphy_net(&dev->wiphy), sock_net(skb->sk))) + continue; if (++idx <= start) continue; if (nl80211_send_wiphy(skb, NETLINK_CB(cb->skb).pid, @@ -396,14 +608,14 @@ static int nl80211_get_wiphy(struct sk_buff *skb, struct genl_info *info) if (nl80211_send_wiphy(msg, info->snd_pid, info->snd_seq, 0, dev) < 0) goto out_free; - cfg80211_put_dev(dev); + cfg80211_unlock_rdev(dev); - return genlmsg_unicast(msg, info->snd_pid); + return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); out_err: - cfg80211_put_dev(dev); + cfg80211_unlock_rdev(dev); return -ENOBUFS; } @@ -445,7 +657,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) mutex_lock(&cfg80211_mutex); - rdev = __cfg80211_drv_from_info(info); + rdev = __cfg80211_rdev_from_info(info); if (IS_ERR(rdev)) { mutex_unlock(&cfg80211_mutex); result = PTR_ERR(rdev); @@ -492,15 +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]) { @@ -514,38 +719,10 @@ 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; } @@ -651,6 +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: @@ -664,32 +846,34 @@ 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_drv_list, list) { + 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++; continue; } 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++; } @@ -709,7 +893,7 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info) struct net_device *netdev; int err; - err = get_drv_dev_by_info_ifindex(info->attrs, &dev, &netdev); + err = get_rdev_dev_by_info_ifindex(info, &dev, &netdev); if (err) return err; @@ -722,15 +906,15 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info) goto out_free; dev_put(netdev); - cfg80211_put_dev(dev); + cfg80211_unlock_rdev(dev); - return genlmsg_unicast(msg, info->snd_pid); + return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); out_err: dev_put(netdev); - cfg80211_put_dev(dev); + cfg80211_unlock_rdev(dev); return -ENOBUFS; } @@ -765,9 +949,9 @@ static int parse_monitor_flags(struct nlattr *nla, u32 *mntrflags) static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct vif_params params; - int err, ifindex; + int err; enum nl80211_iftype otype, ntype; struct net_device *dev; u32 _flags, *flags = NULL; @@ -777,13 +961,11 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - ifindex = dev->ifindex; otype = ntype = dev->ieee80211_ptr->iftype; - dev_put(dev); if (info->attrs[NL80211_ATTR_IFTYPE]) { ntype = nla_get_u32(info->attrs[NL80211_ATTR_IFTYPE]); @@ -795,12 +977,6 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) } } - if (!drv->ops->change_virtual_intf || - !(drv->wiphy.interface_modes & (1 << ntype))) { - err = -EOPNOTSUPP; - goto unlock; - } - if (info->attrs[NL80211_ATTR_MESH_ID]) { if (ntype != NL80211_IFTYPE_MESH_POINT) { err = -EINVAL; @@ -826,21 +1002,13 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) } if (change) - err = drv->ops->change_virtual_intf(&drv->wiphy, ifindex, - ntype, flags, ¶ms); + err = cfg80211_change_iface(rdev, dev, ntype, flags, ¶ms); else err = 0; - dev = __dev_get_by_index(&init_net, ifindex); - WARN_ON(!dev || (!err && dev->ieee80211_ptr->iftype != ntype)); - - if (dev && !err && (ntype != otype)) { - if (otype == NL80211_IFTYPE_ADHOC) - cfg80211_clear_ibss(dev, false); - } - unlock: - cfg80211_put_dev(drv); + dev_put(dev); + cfg80211_unlock_rdev(rdev); unlock_rtnl: rtnl_unlock(); return err; @@ -848,7 +1016,7 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct vif_params params; int err; enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED; @@ -867,14 +1035,14 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - drv = cfg80211_get_dev_from_info(info); - if (IS_ERR(drv)) { - err = PTR_ERR(drv); + rdev = cfg80211_get_dev_from_info(info); + if (IS_ERR(rdev)) { + err = PTR_ERR(rdev); goto unlock_rtnl; } - if (!drv->ops->add_virtual_intf || - !(drv->wiphy.interface_modes & (1 << type))) { + if (!rdev->ops->add_virtual_intf || + !(rdev->wiphy.interface_modes & (1 << type))) { err = -EOPNOTSUPP; goto unlock; } @@ -888,12 +1056,12 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) err = parse_monitor_flags(type == NL80211_IFTYPE_MONITOR ? info->attrs[NL80211_ATTR_MNTR_FLAGS] : NULL, &flags); - err = drv->ops->add_virtual_intf(&drv->wiphy, + err = rdev->ops->add_virtual_intf(&rdev->wiphy, nla_data(info->attrs[NL80211_ATTR_IFNAME]), type, err ? NULL : &flags, ¶ms); unlock: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); unlock_rtnl: rtnl_unlock(); return err; @@ -901,27 +1069,26 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; - int ifindex, err; + struct cfg80211_registered_device *rdev; + int err; struct net_device *dev; rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - ifindex = dev->ifindex; - dev_put(dev); - if (!drv->ops->del_virtual_intf) { + if (!rdev->ops->del_virtual_intf) { err = -EOPNOTSUPP; goto out; } - err = drv->ops->del_virtual_intf(&drv->wiphy, ifindex); + err = rdev->ops->del_virtual_intf(&rdev->wiphy, dev); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); + dev_put(dev); unlock_rtnl: rtnl_unlock(); return err; @@ -930,10 +1097,12 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) struct get_key_cookie { struct sk_buff *msg; int error; + int idx; }; static void get_key_callback(void *c, struct key_params *params) { + struct nlattr *key; struct get_key_cookie *cookie = c; if (params->key) @@ -948,6 +1117,26 @@ static void get_key_callback(void *c, struct key_params *params) NLA_PUT_U32(cookie->msg, NL80211_ATTR_KEY_CIPHER, params->cipher); + key = nla_nest_start(cookie->msg, NL80211_ATTR_KEY); + if (!key) + goto nla_put_failure; + + if (params->key) + NLA_PUT(cookie->msg, NL80211_KEY_DATA, + params->key_len, params->key); + + if (params->seq) + NLA_PUT(cookie->msg, NL80211_KEY_SEQ, + params->seq_len, params->seq); + + if (params->cipher) + NLA_PUT_U32(cookie->msg, NL80211_KEY_CIPHER, + params->cipher); + + NLA_PUT_U8(cookie->msg, NL80211_ATTR_KEY_IDX, cookie->idx); + + nla_nest_end(cookie->msg, key); + return; nla_put_failure: cookie->error = 1; @@ -955,7 +1144,7 @@ static void get_key_callback(void *c, struct key_params *params) static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; u8 key_idx = 0; @@ -977,11 +1166,11 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->get_key) { + if (!rdev->ops->get_key) { err = -EOPNOTSUPP; goto out; } @@ -1001,13 +1190,14 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) } cookie.msg = msg; + cookie.idx = key_idx; NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); NLA_PUT_U8(msg, NL80211_ATTR_KEY_IDX, key_idx); if (mac_addr) NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr); - err = drv->ops->get_key(&drv->wiphy, dev, key_idx, mac_addr, + err = rdev->ops->get_key(&rdev->wiphy, dev, key_idx, mac_addr, &cookie, get_key_callback); if (err) @@ -1017,7 +1207,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) goto nla_put_failure; genlmsg_end(msg, hdr); - err = genlmsg_unicast(msg, info->snd_pid); + err = genlmsg_reply(msg, info); goto out; nla_put_failure: @@ -1025,7 +1215,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) free_msg: nlmsg_free(msg); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); @@ -1035,57 +1225,57 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; + struct key_parse key; int err; struct net_device *dev; - u8 key_idx; int (*func)(struct wiphy *wiphy, struct net_device *netdev, u8 key_index); - if (!info->attrs[NL80211_ATTR_KEY_IDX]) - return -EINVAL; - - key_idx = nla_get_u8(info->attrs[NL80211_ATTR_KEY_IDX]); + err = nl80211_parse_key(info, &key); + if (err) + return err; - if (info->attrs[NL80211_ATTR_KEY_DEFAULT_MGMT]) { - if (key_idx < 4 || key_idx > 5) - return -EINVAL; - } else if (key_idx > 3) + if (key.idx < 0) return -EINVAL; - /* currently only support setting default key */ - if (!info->attrs[NL80211_ATTR_KEY_DEFAULT] && - !info->attrs[NL80211_ATTR_KEY_DEFAULT_MGMT]) + /* only support setting default key */ + if (!key.def && !key.defmgmt) return -EINVAL; rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (info->attrs[NL80211_ATTR_KEY_DEFAULT]) - func = drv->ops->set_default_key; + if (key.def) + func = rdev->ops->set_default_key; else - func = drv->ops->set_default_mgmt_key; + func = rdev->ops->set_default_mgmt_key; if (!func) { err = -EOPNOTSUPP; goto out; } - err = func(&drv->wiphy, dev, key_idx); + wdev_lock(dev->ieee80211_ptr); + err = nl80211_key_allowed(dev->ieee80211_ptr); + if (!err) + err = func(&rdev->wiphy, dev, key.idx); + #ifdef CONFIG_WIRELESS_EXT if (!err) { - if (func == drv->ops->set_default_key) - dev->ieee80211_ptr->wext.default_key = key_idx; + if (func == rdev->ops->set_default_key) + dev->ieee80211_ptr->wext.default_key = key.idx; else - dev->ieee80211_ptr->wext.default_mgmt_key = key_idx; + dev->ieee80211_ptr->wext.default_mgmt_key = key.idx; } #endif + wdev_unlock(dev->ieee80211_ptr); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: @@ -1096,62 +1286,47 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; - int err, i; + struct cfg80211_registered_device *rdev; + int err; struct net_device *dev; - struct key_params params; - u8 key_idx = 0; + struct key_parse key; u8 *mac_addr = NULL; - memset(¶ms, 0, sizeof(params)); + err = nl80211_parse_key(info, &key); + if (err) + return err; - if (!info->attrs[NL80211_ATTR_KEY_CIPHER]) + if (!key.p.key) return -EINVAL; - if (info->attrs[NL80211_ATTR_KEY_DATA]) { - params.key = nla_data(info->attrs[NL80211_ATTR_KEY_DATA]); - params.key_len = nla_len(info->attrs[NL80211_ATTR_KEY_DATA]); - } - - if (info->attrs[NL80211_ATTR_KEY_SEQ]) { - params.seq = nla_data(info->attrs[NL80211_ATTR_KEY_SEQ]); - params.seq_len = nla_len(info->attrs[NL80211_ATTR_KEY_SEQ]); - } - - if (info->attrs[NL80211_ATTR_KEY_IDX]) - key_idx = nla_get_u8(info->attrs[NL80211_ATTR_KEY_IDX]); - - params.cipher = nla_get_u32(info->attrs[NL80211_ATTR_KEY_CIPHER]); - if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - if (cfg80211_validate_key_settings(¶ms, key_idx, mac_addr)) - return -EINVAL; - rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - for (i = 0; i < drv->wiphy.n_cipher_suites; i++) - if (params.cipher == drv->wiphy.cipher_suites[i]) - break; - if (i == drv->wiphy.n_cipher_suites) { - err = -EINVAL; + if (!rdev->ops->add_key) { + err = -EOPNOTSUPP; goto out; } - if (!drv->ops->add_key) { - err = -EOPNOTSUPP; + if (cfg80211_validate_key_settings(rdev, &key.p, key.idx, mac_addr)) { + err = -EINVAL; goto out; } - err = drv->ops->add_key(&drv->wiphy, dev, key_idx, mac_addr, ¶ms); + wdev_lock(dev->ieee80211_ptr); + err = nl80211_key_allowed(dev->ieee80211_ptr); + if (!err) + err = rdev->ops->add_key(&rdev->wiphy, dev, key.idx, + mac_addr, &key.p); + wdev_unlock(dev->ieee80211_ptr); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); @@ -1161,45 +1336,47 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; - u8 key_idx = 0; u8 *mac_addr = NULL; + struct key_parse key; - if (info->attrs[NL80211_ATTR_KEY_IDX]) - key_idx = nla_get_u8(info->attrs[NL80211_ATTR_KEY_IDX]); - - if (key_idx > 5) - return -EINVAL; + err = nl80211_parse_key(info, &key); + if (err) + return err; if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->del_key) { + if (!rdev->ops->del_key) { err = -EOPNOTSUPP; goto out; } - err = drv->ops->del_key(&drv->wiphy, dev, key_idx, mac_addr); + wdev_lock(dev->ieee80211_ptr); + err = nl80211_key_allowed(dev->ieee80211_ptr); + if (!err) + err = rdev->ops->del_key(&rdev->wiphy, dev, key.idx, mac_addr); #ifdef CONFIG_WIRELESS_EXT if (!err) { - if (key_idx == dev->ieee80211_ptr->wext.default_key) + if (key.idx == dev->ieee80211_ptr->wext.default_key) dev->ieee80211_ptr->wext.default_key = -1; - else if (key_idx == dev->ieee80211_ptr->wext.default_mgmt_key) + else if (key.idx == dev->ieee80211_ptr->wext.default_mgmt_key) dev->ieee80211_ptr->wext.default_mgmt_key = -1; } #endif + wdev_unlock(dev->ieee80211_ptr); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: @@ -1212,7 +1389,7 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) { int (*call)(struct wiphy *wiphy, struct net_device *dev, struct beacon_parameters *info); - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; struct beacon_parameters params; @@ -1223,7 +1400,7 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; @@ -1242,10 +1419,10 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) goto out; } - call = drv->ops->add_beacon; + call = rdev->ops->add_beacon; break; case NL80211_CMD_SET_BEACON: - call = drv->ops->set_beacon; + call = rdev->ops->set_beacon; break; default: WARN_ON(1); @@ -1291,10 +1468,10 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) goto out; } - err = call(&drv->wiphy, dev, ¶ms); + err = call(&rdev->wiphy, dev, ¶ms); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); @@ -1304,17 +1481,17 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) static int nl80211_del_beacon(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->del_beacon) { + if (!rdev->ops->del_beacon) { err = -EOPNOTSUPP; goto out; } @@ -1323,10 +1500,10 @@ static int nl80211_del_beacon(struct sk_buff *skb, struct genl_info *info) err = -EOPNOTSUPP; goto out; } - err = drv->ops->del_beacon(&drv->wiphy, dev); + err = rdev->ops->del_beacon(&rdev->wiphy, dev); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); @@ -1433,6 +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; @@ -1520,13 +1699,13 @@ static int nl80211_dump_station(struct sk_buff *skb, rtnl_lock(); - netdev = __dev_get_by_index(&init_net, ifidx); + netdev = __dev_get_by_index(sock_net(skb->sk), ifidx); if (!netdev) { err = -ENODEV; goto out_rtnl; } - dev = cfg80211_get_dev_from_ifindex(ifidx); + dev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_rtnl; @@ -1560,7 +1739,7 @@ static int nl80211_dump_station(struct sk_buff *skb, cb->args[1] = sta_idx; err = skb->len; out_err: - cfg80211_put_dev(dev); + cfg80211_unlock_rdev(dev); out_rtnl: rtnl_unlock(); @@ -1569,7 +1748,7 @@ static int nl80211_dump_station(struct sk_buff *skb, static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; struct station_info sinfo; @@ -1585,16 +1764,16 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - if (!drv->ops->get_station) { + if (!rdev->ops->get_station) { err = -EOPNOTSUPP; goto out; } - err = drv->ops->get_station(&drv->wiphy, dev, mac_addr, &sinfo); + err = rdev->ops->get_station(&rdev->wiphy, dev, mac_addr, &sinfo); if (err) goto out; @@ -1606,13 +1785,13 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) dev, mac_addr, &sinfo) < 0) goto out_free; - err = genlmsg_unicast(msg, info->snd_pid); + err = genlmsg_reply(msg, info); goto out; out_free: nlmsg_free(msg); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -1623,14 +1802,16 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) /* * Get vlan interface making sure it is on the right wiphy. */ -static int get_vlan(struct nlattr *vlanattr, +static int get_vlan(struct genl_info *info, struct cfg80211_registered_device *rdev, struct net_device **vlan) { + struct nlattr *vlanattr = info->attrs[NL80211_ATTR_STA_VLAN]; *vlan = NULL; if (vlanattr) { - *vlan = dev_get_by_index(&init_net, nla_get_u32(vlanattr)); + *vlan = dev_get_by_index(genl_info_net(info), + nla_get_u32(vlanattr)); if (!*vlan) return -ENODEV; if (!(*vlan)->ieee80211_ptr) @@ -1643,7 +1824,7 @@ static int get_vlan(struct nlattr *vlanattr, static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; struct station_parameters params; @@ -1685,11 +1866,11 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - err = get_vlan(info->attrs[NL80211_ATTR_STA_VLAN], drv, ¶ms.vlan); + err = get_vlan(info, rdev, ¶ms.vlan); if (err) goto out; @@ -1738,17 +1919,17 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) if (err) goto out; - if (!drv->ops->change_station) { + if (!rdev->ops->change_station) { err = -EOPNOTSUPP; goto out; } - err = drv->ops->change_station(&drv->wiphy, dev, mac_addr, ¶ms); + err = rdev->ops->change_station(&rdev->wiphy, dev, mac_addr, ¶ms); out: if (params.vlan) dev_put(params.vlan); - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -1758,7 +1939,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; struct station_parameters params; @@ -1798,11 +1979,11 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - err = get_vlan(info->attrs[NL80211_ATTR_STA_VLAN], drv, ¶ms.vlan); + err = get_vlan(info, rdev, ¶ms.vlan); if (err) goto out; @@ -1838,7 +2019,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (err) goto out; - if (!drv->ops->add_station) { + if (!rdev->ops->add_station) { err = -EOPNOTSUPP; goto out; } @@ -1848,12 +2029,12 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) goto out; } - err = drv->ops->add_station(&drv->wiphy, dev, mac_addr, ¶ms); + err = rdev->ops->add_station(&rdev->wiphy, dev, mac_addr, ¶ms); out: if (params.vlan) dev_put(params.vlan); - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -1863,7 +2044,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; u8 *mac_addr = NULL; @@ -1873,7 +2054,7 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; @@ -1884,15 +2065,15 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!drv->ops->del_station) { + if (!rdev->ops->del_station) { err = -EOPNOTSUPP; goto out; } - err = drv->ops->del_station(&drv->wiphy, dev, mac_addr); + err = rdev->ops->del_station(&rdev->wiphy, dev, mac_addr); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -1916,6 +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; @@ -1979,13 +2162,13 @@ static int nl80211_dump_mpath(struct sk_buff *skb, rtnl_lock(); - netdev = __dev_get_by_index(&init_net, ifidx); + netdev = __dev_get_by_index(sock_net(skb->sk), ifidx); if (!netdev) { err = -ENODEV; goto out_rtnl; } - dev = cfg80211_get_dev_from_ifindex(ifidx); + dev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_rtnl; @@ -1998,7 +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) { @@ -2023,7 +2206,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, cb->args[1] = path_idx; err = skb->len; out_err: - cfg80211_put_dev(dev); + cfg80211_unlock_rdev(dev); out_rtnl: rtnl_unlock(); @@ -2032,7 +2215,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; struct mpath_info pinfo; @@ -2049,11 +2232,11 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - if (!drv->ops->get_mpath) { + if (!rdev->ops->get_mpath) { err = -EOPNOTSUPP; goto out; } @@ -2063,7 +2246,7 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) goto out; } - err = drv->ops->get_mpath(&drv->wiphy, dev, dst, next_hop, &pinfo); + err = rdev->ops->get_mpath(&rdev->wiphy, dev, dst, next_hop, &pinfo); if (err) goto out; @@ -2075,13 +2258,13 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) dev, dst, next_hop, &pinfo) < 0) goto out_free; - err = genlmsg_unicast(msg, info->snd_pid); + err = genlmsg_reply(msg, info); goto out; out_free: nlmsg_free(msg); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -2091,7 +2274,7 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) static int nl80211_set_mpath(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; u8 *dst = NULL; @@ -2108,11 +2291,11 @@ static int nl80211_set_mpath(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - if (!drv->ops->change_mpath) { + if (!rdev->ops->change_mpath) { err = -EOPNOTSUPP; goto out; } @@ -2127,10 +2310,10 @@ static int nl80211_set_mpath(struct sk_buff *skb, struct genl_info *info) goto out; } - err = drv->ops->change_mpath(&drv->wiphy, dev, dst, next_hop); + err = rdev->ops->change_mpath(&rdev->wiphy, dev, dst, next_hop); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -2139,7 +2322,7 @@ static int nl80211_set_mpath(struct sk_buff *skb, struct genl_info *info) } static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; u8 *dst = NULL; @@ -2156,11 +2339,11 @@ static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - if (!drv->ops->add_mpath) { + if (!rdev->ops->add_mpath) { err = -EOPNOTSUPP; goto out; } @@ -2175,10 +2358,10 @@ static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) goto out; } - err = drv->ops->add_mpath(&drv->wiphy, dev, dst, next_hop); + err = rdev->ops->add_mpath(&rdev->wiphy, dev, dst, next_hop); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -2188,7 +2371,7 @@ static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; u8 *dst = NULL; @@ -2198,19 +2381,19 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - if (!drv->ops->del_mpath) { + if (!rdev->ops->del_mpath) { err = -EOPNOTSUPP; goto out; } - err = drv->ops->del_mpath(&drv->wiphy, dev, dst); + err = rdev->ops->del_mpath(&rdev->wiphy, dev, dst); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -2220,7 +2403,7 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; int err; struct net_device *dev; struct bss_parameters params; @@ -2249,11 +2432,11 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - if (!drv->ops->change_bss) { + if (!rdev->ops->change_bss) { err = -EOPNOTSUPP; goto out; } @@ -2263,10 +2446,10 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) goto out; } - err = drv->ops->change_bss(&drv->wiphy, dev, ¶ms); + err = rdev->ops->change_bss(&rdev->wiphy, dev, ¶ms); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -2357,7 +2540,7 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) static int nl80211_get_mesh_params(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct mesh_config cur_params; int err; struct net_device *dev; @@ -2368,17 +2551,17 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, rtnl_lock(); /* Look up our device */ - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - if (!drv->ops->get_mesh_params) { + if (!rdev->ops->get_mesh_params) { err = -EOPNOTSUPP; goto out; } /* Get the mesh params */ - err = drv->ops->get_mesh_params(&drv->wiphy, dev, &cur_params); + err = rdev->ops->get_mesh_params(&rdev->wiphy, dev, &cur_params); if (err) goto out; @@ -2424,7 +2607,7 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, cur_params.dot11MeshHWMPnetDiameterTraversalTime); nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); - err = genlmsg_unicast(msg, info->snd_pid); + err = genlmsg_reply(msg, info); goto out; nla_put_failure: @@ -2432,7 +2615,7 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, err = -EMSGSIZE; out: /* Cleanup */ - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -2470,7 +2653,7 @@ static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info) { int err; u32 mask; - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct net_device *dev; struct mesh_config cfg; struct nlattr *tb[NL80211_MESHCONF_ATTR_MAX + 1]; @@ -2485,11 +2668,11 @@ static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - if (!drv->ops->set_mesh_params) { + if (!rdev->ops->set_mesh_params) { err = -EOPNOTSUPP; goto out; } @@ -2534,11 +2717,11 @@ static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info) nla_get_u16); /* Apply changes */ - err = drv->ops->set_mesh_params(&drv->wiphy, dev, &cfg, mask); + err = rdev->ops->set_mesh_params(&rdev->wiphy, dev, &cfg, mask); out: /* cleanup */ - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -2612,7 +2795,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) nla_nest_end(msg, nl_reg_rules); genlmsg_end(msg, hdr); - err = genlmsg_unicast(msg, info->snd_pid); + err = genlmsg_reply(msg, info); goto out; nla_put_failure: @@ -2698,16 +2881,41 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) return r; } +static int validate_scan_freqs(struct nlattr *freqs) +{ + struct nlattr *attr1, *attr2; + int n_channels = 0, tmp1, tmp2; + + nla_for_each_nested(attr1, freqs, tmp1) { + n_channels++; + /* + * Some hardware has a limited channel list for + * scanning, and it is pretty much nonsensical + * to scan for a channel twice, so disallow that + * and don't require drivers to check that the + * channel list they get isn't longer than what + * they can scan, as long as they can scan all + * the channels they registered at once. + */ + nla_for_each_nested(attr2, freqs, tmp2) + if (attr1 != attr2 && + nla_get_u32(attr1) == nla_get_u32(attr2)) + return 0; + } + + return n_channels; +} + static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct net_device *dev; struct cfg80211_scan_request *request; struct cfg80211_ssid *ssid; struct ieee80211_channel *channel; struct nlattr *attr; struct wiphy *wiphy; - int err, tmp, n_ssids = 0, n_channels = 0, i; + int err, tmp, n_ssids = 0, n_channels, i; enum ieee80211_band band; size_t ie_len; @@ -2716,13 +2924,13 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto out_rtnl; - wiphy = &drv->wiphy; + wiphy = &rdev->wiphy; - if (!drv->ops->scan) { + if (!rdev->ops->scan) { err = -EOPNOTSUPP; goto out; } @@ -2732,19 +2940,21 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) goto out; } - if (drv->scan_req) { + if (rdev->scan_req) { err = -EBUSY; goto out; } if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { - nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_FREQUENCIES], tmp) - n_channels++; + n_channels = validate_scan_freqs( + info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]); if (!n_channels) { err = -EINVAL; goto out; } } else { + n_channels = 0; + for (band = 0; band < IEEE80211_NUM_BANDS; band++) if (wiphy->bands[band]) n_channels += wiphy->bands[band]->n_channels; @@ -2778,10 +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) @@ -2836,19 +3045,24 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) request->ie_len); } - request->ifidx = dev->ifindex; - request->wiphy = &drv->wiphy; + request->dev = dev; + request->wiphy = &rdev->wiphy; + + rdev->scan_req = request; + err = rdev->ops->scan(&rdev->wiphy, dev, request); - drv->scan_req = request; - err = drv->ops->scan(&drv->wiphy, dev, request); + if (!err) { + nl80211_send_scan_start(rdev, dev); + dev_hold(dev); + } out_free: if (err) { - drv->scan_req = NULL; + rdev->scan_req = NULL; kfree(request); } out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); out_rtnl: rtnl_unlock(); @@ -2858,20 +3072,23 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, struct cfg80211_registered_device *rdev, - struct net_device *dev, - struct cfg80211_bss *res) + struct wireless_dev *wdev, + struct cfg80211_internal_bss *intbss) { + struct cfg80211_bss *res = &intbss->pub; void *hdr; struct nlattr *bss; + int i; + + ASSERT_WDEV_LOCK(wdev); hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_SCAN_RESULTS); if (!hdr) return -1; - NLA_PUT_U32(msg, NL80211_ATTR_SCAN_GENERATION, - rdev->bss_generation); - NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); + 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); if (!bss) @@ -2900,6 +3117,28 @@ static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, break; } + switch (wdev->iftype) { + case NL80211_IFTYPE_STATION: + if (intbss == wdev->current_bss) + NLA_PUT_U32(msg, NL80211_BSS_STATUS, + NL80211_BSS_STATUS_ASSOCIATED); + else for (i = 0; i < MAX_AUTH_BSSES; i++) { + if (intbss != wdev->auth_bsses[i]) + continue; + NLA_PUT_U32(msg, NL80211_BSS_STATUS, + NL80211_BSS_STATUS_AUTHENTICATED); + break; + } + break; + case NL80211_IFTYPE_ADHOC: + if (intbss == wdev->current_bss) + NLA_PUT_U32(msg, NL80211_BSS_STATUS, + NL80211_BSS_STATUS_IBSS_JOINED); + break; + default: + break; + } + nla_nest_end(msg, bss); return genlmsg_end(msg, hdr); @@ -2912,9 +3151,10 @@ static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) { - struct cfg80211_registered_device *dev; - struct net_device *netdev; + struct cfg80211_registered_device *rdev; + struct net_device *dev; struct cfg80211_internal_bss *scan; + struct wireless_dev *wdev; int ifidx = cb->args[0]; int start = cb->args[1], idx = 0; int err; @@ -2935,58 +3175,83 @@ static int nl80211_dump_scan(struct sk_buff *skb, cb->args[0] = ifidx; } - netdev = dev_get_by_index(&init_net, ifidx); - if (!netdev) + dev = dev_get_by_index(sock_net(skb->sk), ifidx); + if (!dev) return -ENODEV; - dev = cfg80211_get_dev_from_ifindex(ifidx); - if (IS_ERR(dev)) { - err = PTR_ERR(dev); + rdev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); + if (IS_ERR(rdev)) { + err = PTR_ERR(rdev); goto out_put_netdev; } - spin_lock_bh(&dev->bss_lock); - cfg80211_bss_expire(dev); + wdev = dev->ieee80211_ptr; + + wdev_lock(wdev); + spin_lock_bh(&rdev->bss_lock); + cfg80211_bss_expire(rdev); - list_for_each_entry(scan, &dev->bss_list, list) { + list_for_each_entry(scan, &rdev->bss_list, list) { if (++idx <= start) continue; if (nl80211_send_bss(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - dev, netdev, &scan->pub) < 0) { + rdev, wdev, scan) < 0) { idx--; goto out; } } out: - spin_unlock_bh(&dev->bss_lock); + spin_unlock_bh(&rdev->bss_lock); + wdev_unlock(wdev); cb->args[1] = idx; err = skb->len; - cfg80211_put_dev(dev); + cfg80211_unlock_rdev(rdev); out_put_netdev: - dev_put(netdev); + dev_put(dev); return err; } static bool nl80211_valid_auth_type(enum nl80211_auth_type auth_type) { - return auth_type == NL80211_AUTHTYPE_OPEN_SYSTEM || - auth_type == NL80211_AUTHTYPE_SHARED_KEY || - auth_type == NL80211_AUTHTYPE_FT || - auth_type == NL80211_AUTHTYPE_NETWORK_EAP; + return auth_type <= NL80211_AUTHTYPE_MAX; } +static bool nl80211_valid_wpa_versions(u32 wpa_versions) +{ + return !(wpa_versions & ~(NL80211_WPA_VERSION_1 | + NL80211_WPA_VERSION_2)); +} + +static bool nl80211_valid_akm_suite(u32 akm) +{ + return akm == WLAN_AKM_SUITE_8021X || + akm == WLAN_AKM_SUITE_PSK; +} + +static bool nl80211_valid_cipher_suite(u32 cipher) +{ + return cipher == WLAN_CIPHER_SUITE_WEP40 || + cipher == WLAN_CIPHER_SUITE_WEP104 || + cipher == WLAN_CIPHER_SUITE_TKIP || + cipher == WLAN_CIPHER_SUITE_CCMP || + cipher == WLAN_CIPHER_SUITE_AES_CMAC; +} + + static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct net_device *dev; - struct cfg80211_auth_request req; - struct wiphy *wiphy; - int err; + struct ieee80211_channel *chan; + const u8 *bssid, *ssid, *ie = NULL; + int err, ssid_len, ie_len = 0; + enum nl80211_auth_type auth_type; + struct key_parse key; if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -2997,13 +3262,38 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_AUTH_TYPE]) return -EINVAL; + if (!info->attrs[NL80211_ATTR_SSID]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_WIPHY_FREQ]) + return -EINVAL; + + err = nl80211_parse_key(info, &key); + if (err) + return err; + + if (key.idx >= 0) { + if (!key.p.key || !key.p.key_len) + return -EINVAL; + if ((key.p.cipher != WLAN_CIPHER_SUITE_WEP40 || + key.p.key_len != WLAN_KEY_LEN_WEP40) && + (key.p.cipher != WLAN_CIPHER_SUITE_WEP104 || + key.p.key_len != WLAN_KEY_LEN_WEP104)) + return -EINVAL; + if (key.idx > 4) + return -EINVAL; + } else { + key.p.key_len = 0; + key.p.key = NULL; + } + rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->auth) { + if (!rdev->ops->auth) { err = -EOPNOTSUPP; goto out; } @@ -3018,69 +3308,130 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) goto out; } - wiphy = &drv->wiphy; - memset(&req, 0, sizeof(req)); - - req.peer_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - - if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - req.chan = ieee80211_get_channel( - wiphy, - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); - if (!req.chan) { - err = -EINVAL; - goto out; - } + bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); + chan = ieee80211_get_channel(&rdev->wiphy, + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); + if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED)) { + err = -EINVAL; + goto out; } - if (info->attrs[NL80211_ATTR_SSID]) { - req.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); - req.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - } + ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); + ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); if (info->attrs[NL80211_ATTR_IE]) { - req.ie = nla_data(info->attrs[NL80211_ATTR_IE]); - req.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + ie = nla_data(info->attrs[NL80211_ATTR_IE]); + ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } - req.auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); - if (!nl80211_valid_auth_type(req.auth_type)) { + auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); + if (!nl80211_valid_auth_type(auth_type)) { err = -EINVAL; goto out; } - err = drv->ops->auth(&drv->wiphy, dev, &req); + err = cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, + ssid, ssid_len, ie, ie_len, + key.p.key, key.p.key_len, key.idx); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); return err; } +static int nl80211_crypto_settings(struct genl_info *info, + struct cfg80211_crypto_settings *settings, + int cipher_limit) +{ + memset(settings, 0, sizeof(*settings)); + + settings->control_port = info->attrs[NL80211_ATTR_CONTROL_PORT]; + + if (info->attrs[NL80211_ATTR_CIPHER_SUITES_PAIRWISE]) { + void *data; + int len, i; + + data = nla_data(info->attrs[NL80211_ATTR_CIPHER_SUITES_PAIRWISE]); + len = nla_len(info->attrs[NL80211_ATTR_CIPHER_SUITES_PAIRWISE]); + settings->n_ciphers_pairwise = len / sizeof(u32); + + if (len % sizeof(u32)) + return -EINVAL; + + if (settings->n_ciphers_pairwise > cipher_limit) + return -EINVAL; + + memcpy(settings->ciphers_pairwise, data, len); + + for (i = 0; i < settings->n_ciphers_pairwise; i++) + if (!nl80211_valid_cipher_suite( + settings->ciphers_pairwise[i])) + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_CIPHER_SUITE_GROUP]) { + settings->cipher_group = + nla_get_u32(info->attrs[NL80211_ATTR_CIPHER_SUITE_GROUP]); + if (!nl80211_valid_cipher_suite(settings->cipher_group)) + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_WPA_VERSIONS]) { + settings->wpa_versions = + nla_get_u32(info->attrs[NL80211_ATTR_WPA_VERSIONS]); + if (!nl80211_valid_wpa_versions(settings->wpa_versions)) + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_AKM_SUITES]) { + void *data; + int len, i; + + data = nla_data(info->attrs[NL80211_ATTR_AKM_SUITES]); + len = nla_len(info->attrs[NL80211_ATTR_AKM_SUITES]); + settings->n_akm_suites = len / sizeof(u32); + + if (len % sizeof(u32)) + return -EINVAL; + + memcpy(settings->akm_suites, data, len); + + for (i = 0; i < settings->n_ciphers_pairwise; i++) + if (!nl80211_valid_akm_suite(settings->akm_suites[i])) + return -EINVAL; + } + + return 0; +} + static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct net_device *dev; - struct cfg80211_assoc_request req; - struct wiphy *wiphy; - int err; + struct cfg80211_crypto_settings crypto; + 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; if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; if (!info->attrs[NL80211_ATTR_MAC] || - !info->attrs[NL80211_ATTR_SSID]) + !info->attrs[NL80211_ATTR_SSID] || + !info->attrs[NL80211_ATTR_WIPHY_FREQ]) return -EINVAL; rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->assoc) { + if (!rdev->ops->assoc) { err = -EOPNOTSUPP; goto out; } @@ -3095,46 +3446,54 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto out; } - wiphy = &drv->wiphy; - memset(&req, 0, sizeof(req)); + bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - req.peer_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); + chan = ieee80211_get_channel(&rdev->wiphy, + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); + if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED)) { + err = -EINVAL; + goto out; + } - if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - req.chan = ieee80211_get_channel( - wiphy, - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); - if (!req.chan) { - err = -EINVAL; - 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); - req.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); - req.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); + ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); if (info->attrs[NL80211_ATTR_IE]) { - req.ie = nla_data(info->attrs[NL80211_ATTR_IE]); - req.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + ie = nla_data(info->attrs[NL80211_ATTR_IE]); + ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } if (info->attrs[NL80211_ATTR_USE_MFP]) { - enum nl80211_mfp use_mfp = + enum nl80211_mfp mfp = nla_get_u32(info->attrs[NL80211_ATTR_USE_MFP]); - if (use_mfp == NL80211_MFP_REQUIRED) - req.use_mfp = true; - else if (use_mfp != NL80211_MFP_NO) { + if (mfp == NL80211_MFP_REQUIRED) + use_mfp = true; + else if (mfp != NL80211_MFP_NO) { err = -EINVAL; goto out; } } - req.control_port = info->attrs[NL80211_ATTR_CONTROL_PORT]; + if (info->attrs[NL80211_ATTR_PREV_BSSID]) + prev_bssid = nla_data(info->attrs[NL80211_ATTR_PREV_BSSID]); - err = drv->ops->assoc(&drv->wiphy, dev, &req); + err = nl80211_crypto_settings(info, &crypto, 1); + if (!err) + err = cfg80211_mlme_assoc(rdev, dev, chan, bssid, prev_bssid, + ssid, ssid_len, ie, ie_len, use_mfp, + &crypto); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); @@ -3143,11 +3502,11 @@ unlock_rtnl: static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct net_device *dev; - struct cfg80211_deauth_request req; - struct wiphy *wiphy; - int err; + const u8 *ie = NULL, *bssid; + int err, ie_len = 0; + u16 reason_code; if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -3160,11 +3519,11 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->deauth) { + if (!rdev->ops->deauth) { err = -EOPNOTSUPP; goto out; } @@ -3179,27 +3538,24 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) goto out; } - wiphy = &drv->wiphy; - memset(&req, 0, sizeof(req)); + bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - req.peer_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - - req.reason_code = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); - if (req.reason_code == 0) { + reason_code = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); + if (reason_code == 0) { /* Reason Code 0 is reserved */ err = -EINVAL; goto out; } if (info->attrs[NL80211_ATTR_IE]) { - req.ie = nla_data(info->attrs[NL80211_ATTR_IE]); - req.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + ie = nla_data(info->attrs[NL80211_ATTR_IE]); + ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } - err = drv->ops->deauth(&drv->wiphy, dev, &req); + err = cfg80211_mlme_deauth(rdev, dev, bssid, ie, ie_len, reason_code); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); @@ -3208,11 +3564,11 @@ unlock_rtnl: static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct net_device *dev; - struct cfg80211_disassoc_request req; - struct wiphy *wiphy; - int err; + const u8 *ie = NULL, *bssid; + int err, ie_len = 0; + u16 reason_code; if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -3225,11 +3581,11 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->disassoc) { + if (!rdev->ops->disassoc) { err = -EOPNOTSUPP; goto out; } @@ -3244,27 +3600,24 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) goto out; } - wiphy = &drv->wiphy; - memset(&req, 0, sizeof(req)); + bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - req.peer_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - - req.reason_code = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); - if (req.reason_code == 0) { + reason_code = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); + if (reason_code == 0) { /* Reason Code 0 is reserved */ err = -EINVAL; goto out; } if (info->attrs[NL80211_ATTR_IE]) { - req.ie = nla_data(info->attrs[NL80211_ATTR_IE]); - req.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + ie = nla_data(info->attrs[NL80211_ATTR_IE]); + ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } - err = drv->ops->disassoc(&drv->wiphy, dev, &req); + err = cfg80211_mlme_disassoc(rdev, dev, bssid, ie, ie_len, reason_code); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); @@ -3273,10 +3626,11 @@ unlock_rtnl: static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct net_device *dev; struct cfg80211_ibss_params ibss; struct wiphy *wiphy; + struct cfg80211_cached_keys *connkeys = NULL; int err; memset(&ibss, 0, sizeof(ibss)); @@ -3300,11 +3654,11 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->join_ibss) { + if (!rdev->ops->join_ibss) { err = -EOPNOTSUPP; goto out; } @@ -3319,7 +3673,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) goto out; } - wiphy = &drv->wiphy; + wiphy = &rdev->wiphy; if (info->attrs[NL80211_ATTR_MAC]) ibss.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3341,30 +3695,43 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) } ibss.channel_fixed = !!info->attrs[NL80211_ATTR_FREQ_FIXED]; + ibss.privacy = !!info->attrs[NL80211_ATTR_PRIVACY]; + + if (ibss.privacy && info->attrs[NL80211_ATTR_KEYS]) { + connkeys = nl80211_parse_connkeys(rdev, + info->attrs[NL80211_ATTR_KEYS]); + if (IS_ERR(connkeys)) { + err = PTR_ERR(connkeys); + connkeys = NULL; + goto out; + } + } - err = cfg80211_join_ibss(drv, dev, &ibss); + err = cfg80211_join_ibss(rdev, dev, &ibss, connkeys); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: + if (err) + kfree(connkeys); rtnl_unlock(); return err; } static int nl80211_leave_ibss(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct net_device *dev; int err; rtnl_lock(); - err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); if (err) goto unlock_rtnl; - if (!drv->ops->leave_ibss) { + if (!rdev->ops->leave_ibss) { err = -EOPNOTSUPP; goto out; } @@ -3379,16 +3746,314 @@ static int nl80211_leave_ibss(struct sk_buff *skb, struct genl_info *info) goto out; } - err = cfg80211_leave_ibss(drv, dev, false); + err = cfg80211_leave_ibss(rdev, dev, false); + +out: + cfg80211_unlock_rdev(rdev); + dev_put(dev); +unlock_rtnl: + rtnl_unlock(); + return err; +} + +#ifdef CONFIG_NL80211_TESTMODE +static struct genl_multicast_group nl80211_testmode_mcgrp = { + .name = "testmode", +}; + +static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev; + int err; + + if (!info->attrs[NL80211_ATTR_TESTDATA]) + return -EINVAL; + + rtnl_lock(); + + rdev = cfg80211_get_dev_from_info(info); + if (IS_ERR(rdev)) { + err = PTR_ERR(rdev); + goto unlock_rtnl; + } + + err = -EOPNOTSUPP; + if (rdev->ops->testmode_cmd) { + rdev->testmode_info = info; + err = rdev->ops->testmode_cmd(&rdev->wiphy, + nla_data(info->attrs[NL80211_ATTR_TESTDATA]), + nla_len(info->attrs[NL80211_ATTR_TESTDATA])); + rdev->testmode_info = NULL; + } + + cfg80211_unlock_rdev(rdev); + + unlock_rtnl: + rtnl_unlock(); + return err; +} + +static struct sk_buff * +__cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev, + int approxlen, u32 pid, u32 seq, gfp_t gfp) +{ + struct sk_buff *skb; + void *hdr; + struct nlattr *data; + + skb = nlmsg_new(approxlen + 100, gfp); + if (!skb) + return NULL; + + hdr = nl80211hdr_put(skb, pid, seq, 0, NL80211_CMD_TESTMODE); + if (!hdr) { + kfree_skb(skb); + return NULL; + } + + NLA_PUT_U32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + data = nla_nest_start(skb, NL80211_ATTR_TESTDATA); + + ((void **)skb->cb)[0] = rdev; + ((void **)skb->cb)[1] = hdr; + ((void **)skb->cb)[2] = data; + + return skb; + + nla_put_failure: + kfree_skb(skb); + return NULL; +} + +struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy, + int approxlen) +{ + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + if (WARN_ON(!rdev->testmode_info)) + return NULL; + + return __cfg80211_testmode_alloc_skb(rdev, approxlen, + rdev->testmode_info->snd_pid, + rdev->testmode_info->snd_seq, + GFP_KERNEL); +} +EXPORT_SYMBOL(cfg80211_testmode_alloc_reply_skb); + +int cfg80211_testmode_reply(struct sk_buff *skb) +{ + struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0]; + void *hdr = ((void **)skb->cb)[1]; + struct nlattr *data = ((void **)skb->cb)[2]; + + if (WARN_ON(!rdev->testmode_info)) { + kfree_skb(skb); + return -EINVAL; + } + + nla_nest_end(skb, data); + genlmsg_end(skb, hdr); + return genlmsg_reply(skb, rdev->testmode_info); +} +EXPORT_SYMBOL(cfg80211_testmode_reply); + +struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy, + int approxlen, gfp_t gfp) +{ + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + return __cfg80211_testmode_alloc_skb(rdev, approxlen, 0, 0, gfp); +} +EXPORT_SYMBOL(cfg80211_testmode_alloc_event_skb); + +void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp) +{ + void *hdr = ((void **)skb->cb)[1]; + struct nlattr *data = ((void **)skb->cb)[2]; + + nla_nest_end(skb, data); + genlmsg_end(skb, hdr); + genlmsg_multicast(skb, 0, nl80211_testmode_mcgrp.id, gfp); +} +EXPORT_SYMBOL(cfg80211_testmode_event); +#endif + +static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev; + struct net_device *dev; + struct cfg80211_connect_params connect; + struct wiphy *wiphy; + struct cfg80211_cached_keys *connkeys = NULL; + int err; + + memset(&connect, 0, sizeof(connect)); + + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_SSID] || + !nla_len(info->attrs[NL80211_ATTR_SSID])) + return -EINVAL; + + if (info->attrs[NL80211_ATTR_AUTH_TYPE]) { + connect.auth_type = + nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); + if (!nl80211_valid_auth_type(connect.auth_type)) + return -EINVAL; + } else + connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; + + connect.privacy = info->attrs[NL80211_ATTR_PRIVACY]; + + err = nl80211_crypto_settings(info, &connect.crypto, + NL80211_MAX_NR_CIPHER_SUITES); + if (err) + return err; + rtnl_lock(); + + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); + if (err) + goto unlock_rtnl; + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { + err = -EOPNOTSUPP; + goto out; + } + + if (!netif_running(dev)) { + err = -ENETDOWN; + goto out; + } + + wiphy = &rdev->wiphy; + + if (info->attrs[NL80211_ATTR_MAC]) + connect.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); + connect.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); + connect.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + + if (info->attrs[NL80211_ATTR_IE]) { + connect.ie = nla_data(info->attrs[NL80211_ATTR_IE]); + connect.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + } + + if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { + connect.channel = + ieee80211_get_channel(wiphy, + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); + if (!connect.channel || + connect.channel->flags & IEEE80211_CHAN_DISABLED) { + err = -EINVAL; + goto out; + } + } + + if (connect.privacy && info->attrs[NL80211_ATTR_KEYS]) { + connkeys = nl80211_parse_connkeys(rdev, + info->attrs[NL80211_ATTR_KEYS]); + if (IS_ERR(connkeys)) { + err = PTR_ERR(connkeys); + connkeys = NULL; + goto out; + } + } + + err = cfg80211_connect(rdev, dev, &connect, connkeys); + +out: + cfg80211_unlock_rdev(rdev); + dev_put(dev); +unlock_rtnl: + if (err) + kfree(connkeys); + rtnl_unlock(); + return err; +} + +static int nl80211_disconnect(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev; + struct net_device *dev; + int err; + u16 reason; + + if (!info->attrs[NL80211_ATTR_REASON_CODE]) + reason = WLAN_REASON_DEAUTH_LEAVING; + else + reason = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); + + if (reason == 0) + return -EINVAL; + + rtnl_lock(); + + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); + if (err) + goto unlock_rtnl; + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { + err = -EOPNOTSUPP; + goto out; + } + + if (!netif_running(dev)) { + err = -ENETDOWN; + goto out; + } + + err = cfg80211_disconnect(rdev, dev, reason, true); out: - cfg80211_put_dev(drv); + cfg80211_unlock_rdev(rdev); dev_put(dev); unlock_rtnl: rtnl_unlock(); return err; } +static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev; + struct net *net; + int err; + u32 pid; + + if (!info->attrs[NL80211_ATTR_PID]) + return -EINVAL; + + pid = nla_get_u32(info->attrs[NL80211_ATTR_PID]); + + rtnl_lock(); + + rdev = cfg80211_get_dev_from_info(info); + if (IS_ERR(rdev)) { + err = PTR_ERR(rdev); + goto out_rtnl; + } + + net = get_net_ns_by_pid(pid); + if (IS_ERR(net)) { + err = PTR_ERR(net); + goto out; + } + + err = 0; + + /* check if anything to do */ + if (net_eq(wiphy_net(&rdev->wiphy), net)) + goto out_put_net; + + err = cfg80211_switch_netns(rdev, net); + out_put_net: + put_net(net); + out: + cfg80211_unlock_rdev(rdev); + out_rtnl: + rtnl_unlock(); + return err; +} + static struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_WIPHY, @@ -3602,6 +4267,32 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, }, +#ifdef CONFIG_NL80211_TESTMODE + { + .cmd = NL80211_CMD_TESTMODE, + .doit = nl80211_testmode_do, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, +#endif + { + .cmd = NL80211_CMD_CONNECT, + .doit = nl80211_connect, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = NL80211_CMD_DISCONNECT, + .doit = nl80211_disconnect, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = NL80211_CMD_SET_WIPHY_NETNS, + .doit = nl80211_wiphy_netns, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { .name = "mlme", @@ -3633,7 +4324,8 @@ void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev) return; } - genlmsg_multicast(msg, 0, nl80211_config_mcgrp.id, GFP_KERNEL); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_config_mcgrp.id, GFP_KERNEL); } static int nl80211_add_scan_req(struct sk_buff *msg, @@ -3643,6 +4335,8 @@ static int nl80211_add_scan_req(struct sk_buff *msg, struct nlattr *nest; int i; + ASSERT_RDEV_LOCK(rdev); + if (WARN_ON(!req)) return 0; @@ -3668,11 +4362,11 @@ static int nl80211_add_scan_req(struct sk_buff *msg, return -ENOBUFS; } -static int nl80211_send_scan_donemsg(struct sk_buff *msg, - struct cfg80211_registered_device *rdev, - struct net_device *netdev, - u32 pid, u32 seq, int flags, - u32 cmd) +static int nl80211_send_scan_msg(struct sk_buff *msg, + struct cfg80211_registered_device *rdev, + struct net_device *netdev, + u32 pid, u32 seq, int flags, + u32 cmd) { void *hdr; @@ -3693,6 +4387,25 @@ static int nl80211_send_scan_donemsg(struct sk_buff *msg, return -EMSGSIZE; } +void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, + struct net_device *netdev) +{ + struct sk_buff *msg; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return; + + if (nl80211_send_scan_msg(msg, rdev, netdev, 0, 0, 0, + NL80211_CMD_TRIGGER_SCAN) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_scan_mcgrp.id, GFP_KERNEL); +} + void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, struct net_device *netdev) { @@ -3702,13 +4415,14 @@ void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, if (!msg) return; - if (nl80211_send_scan_donemsg(msg, rdev, netdev, 0, 0, 0, - NL80211_CMD_NEW_SCAN_RESULTS) < 0) { + if (nl80211_send_scan_msg(msg, rdev, netdev, 0, 0, 0, + NL80211_CMD_NEW_SCAN_RESULTS) < 0) { nlmsg_free(msg); return; } - genlmsg_multicast(msg, 0, nl80211_scan_mcgrp.id, GFP_KERNEL); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_scan_mcgrp.id, GFP_KERNEL); } void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, @@ -3720,13 +4434,14 @@ void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, if (!msg) return; - if (nl80211_send_scan_donemsg(msg, rdev, netdev, 0, 0, 0, - NL80211_CMD_SCAN_ABORTED) < 0) { + if (nl80211_send_scan_msg(msg, rdev, netdev, 0, 0, 0, + NL80211_CMD_SCAN_ABORTED) < 0) { nlmsg_free(msg); return; } - genlmsg_multicast(msg, 0, nl80211_scan_mcgrp.id, GFP_KERNEL); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_scan_mcgrp.id, GFP_KERNEL); } /* @@ -3775,7 +4490,10 @@ void nl80211_send_reg_change_event(struct regulatory_request *request) return; } - genlmsg_multicast(msg, 0, nl80211_regulatory_mcgrp.id, GFP_KERNEL); + rcu_read_lock(); + genlmsg_multicast_allns(msg, 0, nl80211_regulatory_mcgrp.id, + GFP_ATOMIC); + rcu_read_unlock(); return; @@ -3787,12 +4505,12 @@ nla_put_failure: static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, - enum nl80211_commands cmd) + enum nl80211_commands cmd, gfp_t gfp) { struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -3811,7 +4529,8 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, return; } - genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, GFP_ATOMIC); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); return; nla_put_failure: @@ -3820,42 +4539,45 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, } void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *buf, size_t len) + struct net_device *netdev, const u8 *buf, + size_t len, gfp_t gfp) { nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_AUTHENTICATE); + NL80211_CMD_AUTHENTICATE, gfp); } void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, - size_t len) + size_t len, gfp_t gfp) { - nl80211_send_mlme_event(rdev, netdev, buf, len, NL80211_CMD_ASSOCIATE); + nl80211_send_mlme_event(rdev, netdev, buf, len, + NL80211_CMD_ASSOCIATE, gfp); } void nl80211_send_deauth(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *buf, size_t len) + struct net_device *netdev, const u8 *buf, + size_t len, gfp_t gfp) { nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_DEAUTHENTICATE); + NL80211_CMD_DEAUTHENTICATE, gfp); } void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, - size_t len) + size_t len, gfp_t gfp) { nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_DISASSOCIATE); + NL80211_CMD_DISASSOCIATE, gfp); } static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev, struct net_device *netdev, int cmd, - const u8 *addr) + const u8 *addr, gfp_t gfp) { struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -3875,7 +4597,8 @@ static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev, return; } - genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, GFP_ATOMIC); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); return; nla_put_failure: @@ -3884,16 +4607,145 @@ static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev, } void nl80211_send_auth_timeout(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *addr) + struct net_device *netdev, const u8 *addr, + gfp_t gfp) { nl80211_send_mlme_timeout(rdev, netdev, NL80211_CMD_AUTHENTICATE, - addr); + addr, gfp); } void nl80211_send_assoc_timeout(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *addr) + struct net_device *netdev, const u8 *addr, + gfp_t gfp) +{ + nl80211_send_mlme_timeout(rdev, netdev, NL80211_CMD_ASSOCIATE, + addr, gfp); +} + +void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid, + const u8 *req_ie, size_t req_ie_len, + const u8 *resp_ie, size_t resp_ie_len, + u16 status, gfp_t gfp) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_CONNECT); + if (!hdr) { + nlmsg_free(msg); + return; + } + + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + if (bssid) + NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid); + NLA_PUT_U16(msg, NL80211_ATTR_STATUS_CODE, status); + if (req_ie) + NLA_PUT(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie); + if (resp_ie) + NLA_PUT(msg, NL80211_ATTR_RESP_IE, resp_ie_len, resp_ie); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); + +} + +void nl80211_send_roamed(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid, + const u8 *req_ie, size_t req_ie_len, + const u8 *resp_ie, size_t resp_ie_len, gfp_t gfp) { - nl80211_send_mlme_timeout(rdev, netdev, NL80211_CMD_ASSOCIATE, addr); + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_ROAM); + if (!hdr) { + nlmsg_free(msg); + return; + } + + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid); + if (req_ie) + NLA_PUT(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie); + if (resp_ie) + NLA_PUT(msg, NL80211_ATTR_RESP_IE, resp_ie_len, resp_ie); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); + +} + +void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u16 reason, + const u8 *ie, size_t ie_len, bool from_ap) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_DISCONNECT); + if (!hdr) { + nlmsg_free(msg); + return; + } + + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + if (from_ap && reason) + NLA_PUT_U16(msg, NL80211_ATTR_REASON_CODE, reason); + if (from_ap) + NLA_PUT_FLAG(msg, NL80211_ATTR_DISCONNECTED_BY_AP); + if (ie) + NLA_PUT(msg, NL80211_ATTR_IE, ie_len, ie); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, GFP_KERNEL); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); + } void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, @@ -3922,7 +4774,8 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, return; } - genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, gfp); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); return; nla_put_failure: @@ -3933,12 +4786,12 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *addr, enum nl80211_key_type key_type, int key_id, - const u8 *tsc) + const u8 *tsc, gfp_t gfp) { struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; @@ -3962,7 +4815,8 @@ void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, return; } - genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, GFP_ATOMIC); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); return; nla_put_failure: @@ -4015,7 +4869,10 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, return; } - genlmsg_multicast(msg, 0, nl80211_regulatory_mcgrp.id, GFP_ATOMIC); + rcu_read_lock(); + genlmsg_multicast_allns(msg, 0, nl80211_regulatory_mcgrp.id, + GFP_ATOMIC); + rcu_read_unlock(); return; @@ -4051,6 +4908,12 @@ int nl80211_init(void) if (err) goto err_out; +#ifdef CONFIG_NL80211_TESTMODE + err = genl_register_mc_group(&nl80211_fam, &nl80211_testmode_mcgrp); + if (err) + goto err_out; +#endif + return 0; err_out: genl_unregister_family(&nl80211_fam); diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 5c12ad13499..44cc2a76a1b 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -3,39 +3,54 @@ #include "core.h" -extern int nl80211_init(void); -extern void nl80211_exit(void); -extern void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev); -extern void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, - struct net_device *netdev); -extern void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, - struct net_device *netdev); -extern void nl80211_send_reg_change_event(struct regulatory_request *request); -extern void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, - struct net_device *netdev, - const u8 *buf, size_t len); -extern void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, - struct net_device *netdev, - const u8 *buf, size_t len); -extern void nl80211_send_deauth(struct cfg80211_registered_device *rdev, +int nl80211_init(void); +void nl80211_exit(void); +void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev); +void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, + struct net_device *netdev); +void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, + struct net_device *netdev); +void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, + struct net_device *netdev); +void nl80211_send_reg_change_event(struct regulatory_request *request); +void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + const u8 *buf, size_t len, gfp_t gfp); +void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + const u8 *buf, size_t len, gfp_t gfp); +void nl80211_send_deauth(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + const u8 *buf, size_t len, gfp_t gfp); +void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + const u8 *buf, size_t len, gfp_t gfp); +void nl80211_send_auth_timeout(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + const u8 *addr, gfp_t gfp); +void nl80211_send_assoc_timeout(struct cfg80211_registered_device *rdev, struct net_device *netdev, - const u8 *buf, size_t len); -extern void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, - struct net_device *netdev, - const u8 *buf, size_t len); -extern void nl80211_send_auth_timeout(struct cfg80211_registered_device *rdev, - struct net_device *netdev, - const u8 *addr); -extern void nl80211_send_assoc_timeout(struct cfg80211_registered_device *rdev, - struct net_device *netdev, - const u8 *addr); -extern void + const u8 *addr, gfp_t gfp); +void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid, + const u8 *req_ie, size_t req_ie_len, + const u8 *resp_ie, size_t resp_ie_len, + u16 status, gfp_t gfp); +void nl80211_send_roamed(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid, + const u8 *req_ie, size_t req_ie_len, + const u8 *resp_ie, size_t resp_ie_len, gfp_t gfp); +void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u16 reason, + const u8 *ie, size_t ie_len, bool from_ap); + +void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *addr, enum nl80211_key_type key_type, - int key_id, const u8 *tsc); + int key_id, const u8 *tsc, gfp_t gfp); -extern void +void nl80211_send_beacon_hint_event(struct wiphy *wiphy, struct ieee80211_channel *channel_before, struct ieee80211_channel *channel_after); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 75a406d3361..f256dfffbf4 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -62,6 +62,16 @@ const struct ieee80211_regdomain *cfg80211_regdomain; */ static const struct ieee80211_regdomain *country_ie_regdomain; +/* + * Protects static reg.c components: + * - cfg80211_world_regdom + * - cfg80211_regdom + * - country_ie_regdomain + * - last_request + */ +DEFINE_MUTEX(reg_mutex); +#define assert_reg_lock() WARN_ON(!mutex_is_locked(®_mutex)) + /* Used to queue up regulatory hints */ static LIST_HEAD(reg_requests_list); static spinlock_t reg_requests_lock; @@ -113,11 +123,7 @@ static const struct ieee80211_regdomain world_regdom = { static const struct ieee80211_regdomain *cfg80211_world_regdom = &world_regdom; -#ifdef CONFIG_WIRELESS_OLD_REGULATORY -static char *ieee80211_regdom = "US"; -#else static char *ieee80211_regdom = "00"; -#endif module_param(ieee80211_regdom, charp, 0444); MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code"); @@ -1012,7 +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; @@ -1021,7 +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)); @@ -1061,10 +1065,10 @@ static bool ignore_reg_update(struct wiphy *wiphy, static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; - list_for_each_entry(drv, &cfg80211_drv_list, list) - wiphy_update_regulatory(&drv->wiphy, initiator); + list_for_each_entry(rdev, &cfg80211_rdev_list, list) + wiphy_update_regulatory(&rdev->wiphy, initiator); } static void handle_reg_beacon(struct wiphy *wiphy, @@ -1298,7 +1302,7 @@ static void handle_channel_custom(struct wiphy *wiphy, struct ieee80211_supported_band *sband; struct ieee80211_channel *chan; - assert_cfg80211_lock(); + assert_reg_lock(); sband = wiphy->bands[band]; BUG_ON(chan_idx >= sband->n_channels); @@ -1323,7 +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); } @@ -1347,14 +1350,14 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, enum ieee80211_band band; unsigned int bands_set = 0; - mutex_lock(&cfg80211_mutex); + mutex_lock(®_mutex); for (band = 0; band < IEEE80211_NUM_BANDS; band++) { if (!wiphy->bands[band]) continue; handle_band_custom(wiphy, band, regd); bands_set++; } - mutex_unlock(&cfg80211_mutex); + mutex_unlock(®_mutex); /* * no point in calling this if it won't have any effect @@ -1421,7 +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. */ @@ -1500,7 +1503,7 @@ static int ignore_request(struct wiphy *wiphy, * Returns zero if all went fine, %-EALREADY if a regulatory domain had * already been set or other standard error codes. * - * Caller must hold &cfg80211_mutex + * Caller must hold &cfg80211_mutex and ®_mutex */ static int __regulatory_hint(struct wiphy *wiphy, struct regulatory_request *pending_request) @@ -1575,6 +1578,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) BUG_ON(!reg_request->alpha2); mutex_lock(&cfg80211_mutex); + mutex_lock(®_mutex); if (wiphy_idx_valid(reg_request->wiphy_idx)) wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx); @@ -1590,6 +1594,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) if (r == -EALREADY && wiphy && wiphy->strict_regulatory) wiphy_update_regulatory(wiphy, reg_request->initiator); out: + mutex_unlock(®_mutex); mutex_unlock(&cfg80211_mutex); } @@ -1615,9 +1620,13 @@ static void reg_process_pending_hints(void) /* Processes beacon hints -- this has nothing to do with country IEs */ static void reg_process_pending_beacon_hints(void) { - struct cfg80211_registered_device *drv; + struct cfg80211_registered_device *rdev; struct reg_beacon *pending_beacon, *tmp; + /* + * No need to hold the reg_mutex here as we just touch wiphys + * and do not read or access regulatory variables. + */ mutex_lock(&cfg80211_mutex); /* This goes through the _pending_ beacon list */ @@ -1634,8 +1643,8 @@ static void reg_process_pending_beacon_hints(void) list_del_init(&pending_beacon->list); /* Applies the beacon hint to current wiphys */ - list_for_each_entry(drv, &cfg80211_drv_list, list) - wiphy_update_new_beacon(&drv->wiphy, pending_beacon); + list_for_each_entry(rdev, &cfg80211_rdev_list, list) + wiphy_update_new_beacon(&rdev->wiphy, pending_beacon); /* Remembers the beacon hint for new wiphys or reg changes */ list_add_tail(&pending_beacon->list, ®_beacon_list); @@ -1739,12 +1748,13 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2) } EXPORT_SYMBOL(regulatory_hint); +/* Caller must hold reg_mutex */ static bool reg_same_country_ie_hint(struct wiphy *wiphy, u32 country_ie_checksum) { struct wiphy *request_wiphy; - assert_cfg80211_lock(); + assert_reg_lock(); if (unlikely(last_request->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE)) @@ -1767,6 +1777,10 @@ static bool reg_same_country_ie_hint(struct wiphy *wiphy, return false; } +/* + * We hold wdev_lock() here so we cannot hold cfg80211_mutex() and + * therefore cannot iterate over the rdev list here. + */ void regulatory_hint_11d(struct wiphy *wiphy, u8 *country_ie, u8 country_ie_len) @@ -1777,12 +1791,10 @@ void regulatory_hint_11d(struct wiphy *wiphy, enum environment_cap env = ENVIRON_ANY; struct regulatory_request *request; - mutex_lock(&cfg80211_mutex); + mutex_lock(®_mutex); - if (unlikely(!last_request)) { - mutex_unlock(&cfg80211_mutex); - return; - } + if (unlikely(!last_request)) + goto out; /* IE len must be evenly divisible by 2 */ if (country_ie_len & 0x01) @@ -1808,54 +1820,14 @@ void regulatory_hint_11d(struct wiphy *wiphy, env = ENVIRON_OUTDOOR; /* - * We will run this for *every* beacon processed for the BSSID, so - * we optimize an early check to exit out early if we don't have to - * do anything + * We will run this only upon a successful connection on cfg80211. + * We leave conflict resolution to the workqueue, where can hold + * cfg80211_mutex. */ if (likely(last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && - wiphy_idx_valid(last_request->wiphy_idx))) { - struct cfg80211_registered_device *drv_last_ie; - - drv_last_ie = - cfg80211_drv_by_wiphy_idx(last_request->wiphy_idx); - - /* - * Lets keep this simple -- we trust the first AP - * after we intersect with CRDA - */ - if (likely(&drv_last_ie->wiphy == wiphy)) { - /* - * Ignore IEs coming in on this wiphy with - * the same alpha2 and environment cap - */ - if (likely(alpha2_equal(drv_last_ie->country_ie_alpha2, - alpha2) && - env == drv_last_ie->env)) { - goto out; - } - /* - * the wiphy moved on to another BSSID or the AP - * was reconfigured. XXX: We need to deal with the - * case where the user suspends and goes to goes - * to another country, and then gets IEs from an - * AP with different settings - */ - goto out; - } else { - /* - * Ignore IEs coming in on two separate wiphys with - * the same alpha2 and environment cap - */ - if (likely(alpha2_equal(drv_last_ie->country_ie_alpha2, - alpha2) && - env == drv_last_ie->env)) { - goto out; - } - /* We could potentially intersect though */ - goto out; - } - } + wiphy_idx_valid(last_request->wiphy_idx))) + goto out; rd = country_ie_2_rd(country_ie, country_ie_len, &checksum); if (!rd) @@ -1890,7 +1862,7 @@ void regulatory_hint_11d(struct wiphy *wiphy, request->country_ie_checksum = checksum; request->country_ie_env = env; - mutex_unlock(&cfg80211_mutex); + mutex_unlock(®_mutex); queue_regulatory_request(request); @@ -1899,9 +1871,8 @@ void regulatory_hint_11d(struct wiphy *wiphy, free_rd_out: kfree(rd); out: - mutex_unlock(&cfg80211_mutex); + mutex_unlock(®_mutex); } -EXPORT_SYMBOL(regulatory_hint_11d); static bool freq_is_chan_12_13_14(u16 freq) { @@ -1996,14 +1967,14 @@ static void print_regdomain(const struct ieee80211_regdomain *rd) if (last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) { - struct cfg80211_registered_device *drv; - drv = cfg80211_drv_by_wiphy_idx( + struct cfg80211_registered_device *rdev; + rdev = cfg80211_rdev_by_wiphy_idx( last_request->wiphy_idx); - if (drv) { + if (rdev) { printk(KERN_INFO "cfg80211: Current regulatory " "domain updated by AP to: %c%c\n", - drv->country_ie_alpha2[0], - drv->country_ie_alpha2[1]); + rdev->country_ie_alpha2[0], + rdev->country_ie_alpha2[1]); } else printk(KERN_INFO "cfg80211: Current regulatory " "domain intersected: \n"); @@ -2064,7 +2035,7 @@ static inline void reg_country_ie_process_debug( static int __set_regdom(const struct ieee80211_regdomain *rd) { const struct ieee80211_regdomain *intersected_rd = NULL; - struct cfg80211_registered_device *drv = NULL; + struct cfg80211_registered_device *rdev = NULL; struct wiphy *request_wiphy; /* Some basic sanity checks first */ @@ -2203,11 +2174,11 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) if (!intersected_rd) return -EINVAL; - drv = wiphy_to_dev(request_wiphy); + rdev = wiphy_to_dev(request_wiphy); - drv->country_ie_alpha2[0] = rd->alpha2[0]; - drv->country_ie_alpha2[1] = rd->alpha2[1]; - drv->env = last_request->country_ie_env; + rdev->country_ie_alpha2[0] = rd->alpha2[0]; + rdev->country_ie_alpha2[1] = rd->alpha2[1]; + rdev->env = last_request->country_ie_env; BUG_ON(intersected_rd == rd); @@ -2232,10 +2203,13 @@ int set_regdom(const struct ieee80211_regdomain *rd) assert_cfg80211_lock(); + mutex_lock(®_mutex); + /* Note that this doesn't update the wiphys, this is done below */ r = __set_regdom(rd); if (r) { kfree(rd); + mutex_unlock(®_mutex); return r; } @@ -2250,6 +2224,8 @@ int set_regdom(const struct ieee80211_regdomain *rd) nl80211_send_reg_change_event(last_request); + mutex_unlock(®_mutex); + return r; } @@ -2260,16 +2236,20 @@ void reg_device_remove(struct wiphy *wiphy) assert_cfg80211_lock(); + mutex_lock(®_mutex); + kfree(wiphy->regd); if (last_request) request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); if (!request_wiphy || request_wiphy != wiphy) - return; + goto out; last_request->wiphy_idx = WIPHY_IDX_STALE; last_request->country_ie_env = ENVIRON_ANY; +out: + mutex_unlock(®_mutex); } int regulatory_init(void) @@ -2288,22 +2268,12 @@ int regulatory_init(void) printk(KERN_INFO "cfg80211: Using static regulatory domain info\n"); print_regdomain_info(cfg80211_regdomain); - /* - * The old code still requests for a new regdomain and if - * you have CRDA you get it updated, otherwise you get - * stuck with the static values. Since "EU" is not a valid - * ISO / IEC 3166 alpha2 code we can't expect userpace to - * give us a regulatory domain for it. We need last_request - * iniitalized though so lets just send a request which we - * know will be ignored... this crap will be removed once - * OLD_REG dies. - */ - err = regulatory_hint_core(ieee80211_regdom); #else cfg80211_regdomain = cfg80211_world_regdom; - err = regulatory_hint_core(ieee80211_regdom); #endif + /* We always try to get an update for the static regdomain */ + err = regulatory_hint_core(cfg80211_regdomain->alpha2); if (err) { if (err == -ENOMEM) return err; @@ -2322,6 +2292,13 @@ int regulatory_init(void) #endif } + /* + * Finally, if the user set the module parameter treat it + * as a user hint. + */ + if (!is_world_regdom(ieee80211_regdom)) + regulatory_hint_user(ieee80211_regdom); + return 0; } @@ -2333,6 +2310,7 @@ void regulatory_exit(void) cancel_work_sync(®_work); mutex_lock(&cfg80211_mutex); + mutex_lock(®_mutex); reset_regdomains(); @@ -2371,5 +2349,6 @@ void regulatory_exit(void) } spin_unlock(®_requests_lock); + mutex_unlock(®_mutex); mutex_unlock(&cfg80211_mutex); } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 4e167a8e11b..3362c7c069b 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -37,4 +37,19 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy, struct ieee80211_channel *beacon_chan, gfp_t gfp); +/** + * regulatory_hint_11d - hints a country IE as a regulatory domain + * @wiphy: the wireless device giving the hint (used only for reporting + * conflicts) + * @country_ie: pointer to the country IE + * @country_ie_len: length of the country IE + * + * We will intersect the rd with the what CRDA tells us should apply + * for the alpha2 this country IE belongs to, this prevents APs from + * sending us incorrect or outdated information against a country. + */ +void regulatory_hint_11d(struct wiphy *wiphy, + u8 *country_ie, + u8 country_ie_len); + #endif /* __NET_WIRELESS_REG_H */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 7e595ce24ee..e5f92ee758f 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -14,29 +14,41 @@ #include <net/iw_handler.h> #include "core.h" #include "nl80211.h" +#include "wext-compat.h" -#define IEEE80211_SCAN_RESULT_EXPIRE (10 * HZ) +#define IEEE80211_SCAN_RESULT_EXPIRE (15 * HZ) -void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) +void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) { + struct cfg80211_scan_request *request; struct net_device *dev; #ifdef CONFIG_WIRELESS_EXT union iwreq_data wrqu; #endif - dev = dev_get_by_index(&init_net, request->ifidx); - if (!dev) - goto out; + ASSERT_RDEV_LOCK(rdev); - WARN_ON(request != wiphy_to_dev(request->wiphy)->scan_req); + request = rdev->scan_req; + + if (!request) + return; + + dev = request->dev; - if (aborted) - nl80211_send_scan_aborted(wiphy_to_dev(request->wiphy), dev); + /* + * This must be before sending the other events! + * Otherwise, wpa_supplicant gets completely confused with + * wext events. + */ + cfg80211_sme_scan_done(dev); + + if (request->aborted) + 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 (!aborted) { + if (!request->aborted) { memset(&wrqu, 0, sizeof(wrqu)); wireless_send_event(dev, SIOCGIWSCAN, &wrqu, NULL); @@ -45,9 +57,38 @@ void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) dev_put(dev); - out: - wiphy_to_dev(request->wiphy)->scan_req = NULL; - kfree(request); + 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); +} + +void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) +{ + WARN_ON(request != wiphy_to_dev(request->wiphy)->scan_req); + + request->aborted = aborted; + schedule_work(&wiphy_to_dev(request->wiphy)->scan_done_wk); } EXPORT_SYMBOL(cfg80211_scan_done); @@ -62,6 +103,8 @@ static void bss_release(struct kref *ref) if (bss->ies_allocated) kfree(bss->pub.information_elements); + BUG_ON(atomic_read(&bss->hold)); + kfree(bss); } @@ -84,8 +127,9 @@ void cfg80211_bss_expire(struct cfg80211_registered_device *dev) bool expired = false; list_for_each_entry_safe(bss, tmp, &dev->bss_list, list) { - if (bss->hold || - !time_after(jiffies, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE)) + if (atomic_read(&bss->hold)) + continue; + if (!time_after(jiffies, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE)) continue; list_del(&bss->list); rb_erase(&bss->rbn, &dev->bss_tree); @@ -97,7 +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; @@ -539,6 +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); @@ -547,30 +592,6 @@ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub) } EXPORT_SYMBOL(cfg80211_unlink_bss); -void cfg80211_hold_bss(struct cfg80211_bss *pub) -{ - struct cfg80211_internal_bss *bss; - - if (!pub) - return; - - bss = container_of(pub, struct cfg80211_internal_bss, pub); - bss->hold = true; -} -EXPORT_SYMBOL(cfg80211_hold_bss); - -void cfg80211_unhold_bss(struct cfg80211_bss *pub) -{ - struct cfg80211_internal_bss *bss; - - if (!pub) - return; - - bss = container_of(pub, struct cfg80211_internal_bss, pub); - bss->hold = false; -} -EXPORT_SYMBOL(cfg80211_unhold_bss); - #ifdef CONFIG_WIRELESS_EXT int cfg80211_wext_siwscan(struct net_device *dev, struct iw_request_info *info, @@ -586,7 +607,10 @@ int cfg80211_wext_siwscan(struct net_device *dev, if (!netif_running(dev)) return -ENETDOWN; - rdev = cfg80211_get_dev_from_ifindex(dev->ifindex); + 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)) return PTR_ERR(rdev); @@ -598,9 +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 *), @@ -611,28 +640,52 @@ int cfg80211_wext_siwscan(struct net_device *dev, } creq->wiphy = wiphy; - creq->ifidx = dev->ifindex; - creq->ssids = (void *)(creq + 1); - creq->channels = (void *)(creq->ssids + 1); + creq->dev = dev; + /* 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 = cfg80211_wext_freq(wiphy, &wreq->channel_list[k]); + 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: ; } } + /* No channels found? */ + if (!i) { + err = -EINVAL; + goto out; + } - /* 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; @@ -648,9 +701,12 @@ int cfg80211_wext_siwscan(struct net_device *dev, if (err) { rdev->scan_req = NULL; kfree(creq); + } else { + nl80211_send_scan_start(rdev, dev); + dev_hold(dev); } out: - cfg80211_put_dev(rdev); + cfg80211_unlock_rdev(rdev); return err; } EXPORT_SYMBOL_GPL(cfg80211_wext_siwscan); @@ -941,7 +997,7 @@ int cfg80211_wext_giwscan(struct net_device *dev, if (!netif_running(dev)) return -ENETDOWN; - rdev = cfg80211_get_dev_from_ifindex(dev->ifindex); + rdev = cfg80211_get_dev_from_ifindex(dev_net(dev), dev->ifindex); if (IS_ERR(rdev)) return PTR_ERR(rdev); @@ -959,7 +1015,7 @@ int cfg80211_wext_giwscan(struct net_device *dev, } out: - cfg80211_put_dev(rdev); + cfg80211_unlock_rdev(rdev); return res; } EXPORT_SYMBOL_GPL(cfg80211_wext_giwscan); diff --git a/net/wireless/sme.c b/net/wireless/sme.c new file mode 100644 index 00000000000..9f0b2800a9d --- /dev/null +++ b/net/wireless/sme.c @@ -0,0 +1,957 @@ +/* + * SME code for cfg80211's connect emulation. + * + * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2009 Intel Corporation. All rights reserved. + */ + +#include <linux/etherdevice.h> +#include <linux/if_arp.h> +#include <linux/workqueue.h> +#include <linux/wireless.h> +#include <net/iw_handler.h> +#include <net/cfg80211.h> +#include <net/rtnetlink.h> +#include "nl80211.h" +#include "reg.h" + +struct cfg80211_conn { + struct cfg80211_connect_params params; + /* these are sub-states of the _CONNECTING sme_state */ + enum { + CFG80211_CONN_IDLE, + CFG80211_CONN_SCANNING, + CFG80211_CONN_SCAN_AGAIN, + CFG80211_CONN_AUTHENTICATE_NEXT, + CFG80211_CONN_AUTHENTICATING, + CFG80211_CONN_ASSOCIATE_NEXT, + CFG80211_CONN_ASSOCIATING, + CFG80211_CONN_DEAUTH_ASSOC_FAIL, + } state; + u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; + u8 *ie; + size_t ie_len; + bool auto_auth, prev_bssid_valid; +}; + + +static int cfg80211_conn_scan(struct wireless_dev *wdev) +{ + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct cfg80211_scan_request *request; + int n_channels, err; + + ASSERT_RTNL(); + ASSERT_RDEV_LOCK(rdev); + ASSERT_WDEV_LOCK(wdev); + + if (rdev->scan_req) + return -EBUSY; + + if (wdev->conn->params.channel) { + n_channels = 1; + } else { + enum ieee80211_band band; + n_channels = 0; + + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + if (!wdev->wiphy->bands[band]) + continue; + n_channels += wdev->wiphy->bands[band]->n_channels; + } + } + request = kzalloc(sizeof(*request) + sizeof(request->ssids[0]) + + sizeof(request->channels[0]) * n_channels, + GFP_KERNEL); + if (!request) + return -ENOMEM; + + if (wdev->conn->params.channel) + request->channels[0] = wdev->conn->params.channel; + else { + int i = 0, j; + enum ieee80211_band band; + + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + if (!wdev->wiphy->bands[band]) + continue; + for (j = 0; j < wdev->wiphy->bands[band]->n_channels; + i++, j++) + request->channels[i] = + &wdev->wiphy->bands[band]->channels[j]; + } + } + request->n_channels = n_channels; + request->ssids = (void *)&request->channels[n_channels]; + request->n_ssids = 1; + + memcpy(request->ssids[0].ssid, wdev->conn->params.ssid, + wdev->conn->params.ssid_len); + request->ssids[0].ssid_len = wdev->conn->params.ssid_len; + + request->dev = wdev->netdev; + request->wiphy = &rdev->wiphy; + + rdev->scan_req = request; + + err = rdev->ops->scan(wdev->wiphy, wdev->netdev, request); + if (!err) { + wdev->conn->state = CFG80211_CONN_SCANNING; + nl80211_send_scan_start(rdev, wdev->netdev); + dev_hold(wdev->netdev); + } else { + rdev->scan_req = NULL; + kfree(request); + } + return err; +} + +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); + + if (!wdev->conn) + return 0; + + params = &wdev->conn->params; + + switch (wdev->conn->state) { + case CFG80211_CONN_SCAN_AGAIN: + return cfg80211_conn_scan(wdev); + case CFG80211_CONN_AUTHENTICATE_NEXT: + BUG_ON(!rdev->ops->auth); + wdev->conn->state = CFG80211_CONN_AUTHENTICATING; + return __cfg80211_mlme_auth(rdev, wdev->netdev, + params->channel, params->auth_type, + params->bssid, + params->ssid, params->ssid_len, + NULL, 0, + params->key, params->key_len, + params->key_idx); + case CFG80211_CONN_ASSOCIATE_NEXT: + BUG_ON(!rdev->ops->assoc); + wdev->conn->state = CFG80211_CONN_ASSOCIATING; + if (wdev->conn->prev_bssid_valid) + prev_bssid = wdev->conn->prev_bssid; + err = __cfg80211_mlme_assoc(rdev, wdev->netdev, + params->channel, params->bssid, + prev_bssid, + params->ssid, params->ssid_len, + params->ie, params->ie_len, + false, ¶ms->crypto); + if (err) + __cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, + NULL, 0, + WLAN_REASON_DEAUTH_LEAVING); + return err; + case CFG80211_CONN_DEAUTH_ASSOC_FAIL: + __cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, + NULL, 0, + WLAN_REASON_DEAUTH_LEAVING); + /* return an error so that we call __cfg80211_connect_result() */ + return -EINVAL; + default: + return 0; + } +} + +void cfg80211_conn_work(struct work_struct *work) +{ + struct cfg80211_registered_device *rdev = + container_of(work, struct cfg80211_registered_device, conn_work); + struct wireless_dev *wdev; + u8 bssid_buf[ETH_ALEN], *bssid = NULL; + + rtnl_lock(); + cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->devlist_mtx); + + list_for_each_entry(wdev, &rdev->netdev_list, list) { + wdev_lock(wdev); + if (!netif_running(wdev->netdev)) { + wdev_unlock(wdev); + continue; + } + if (wdev->sme_state != CFG80211_SME_CONNECTING) { + wdev_unlock(wdev); + continue; + } + if (wdev->conn->params.bssid) { + memcpy(bssid_buf, wdev->conn->params.bssid, ETH_ALEN); + bssid = bssid_buf; + } + if (cfg80211_conn_do_work(wdev)) + __cfg80211_connect_result( + wdev->netdev, bssid, + NULL, 0, NULL, 0, + WLAN_STATUS_UNSPECIFIED_FAILURE, + false, NULL); + wdev_unlock(wdev); + } + + mutex_unlock(&rdev->devlist_mtx); + cfg80211_unlock_rdev(rdev); + rtnl_unlock(); +} + +static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) +{ + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct cfg80211_bss *bss; + u16 capa = WLAN_CAPABILITY_ESS; + + ASSERT_WDEV_LOCK(wdev); + + if (wdev->conn->params.privacy) + capa |= WLAN_CAPABILITY_PRIVACY; + + bss = cfg80211_get_bss(wdev->wiphy, NULL, wdev->conn->params.bssid, + wdev->conn->params.ssid, + wdev->conn->params.ssid_len, + WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_PRIVACY, + capa); + if (!bss) + return NULL; + + memcpy(wdev->conn->bssid, bss->bssid, ETH_ALEN); + wdev->conn->params.bssid = wdev->conn->bssid; + wdev->conn->params.channel = bss->channel; + wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; + schedule_work(&rdev->conn_work); + + return bss; +} + +static void __cfg80211_sme_scan_done(struct net_device *dev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct cfg80211_bss *bss; + + ASSERT_WDEV_LOCK(wdev); + + if (wdev->sme_state != CFG80211_SME_CONNECTING) + return; + + if (!wdev->conn) + return; + + if (wdev->conn->state != CFG80211_CONN_SCANNING && + wdev->conn->state != CFG80211_CONN_SCAN_AGAIN) + return; + + bss = cfg80211_get_conn_bss(wdev); + if (bss) { + cfg80211_put_bss(bss); + } else { + /* not found */ + if (wdev->conn->state == CFG80211_CONN_SCAN_AGAIN) + schedule_work(&rdev->conn_work); + else + __cfg80211_connect_result( + wdev->netdev, + wdev->conn->params.bssid, + NULL, 0, NULL, 0, + WLAN_STATUS_UNSPECIFIED_FAILURE, + false, NULL); + } +} + +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, + const u8 *buf, size_t len) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; + u16 status_code = le16_to_cpu(mgmt->u.auth.status_code); + + ASSERT_WDEV_LOCK(wdev); + + /* should only RX auth frames when connecting */ + if (wdev->sme_state != CFG80211_SME_CONNECTING) + return; + + if (WARN_ON(!wdev->conn)) + return; + + if (status_code == WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG && + wdev->conn->auto_auth && + wdev->conn->params.auth_type != NL80211_AUTHTYPE_NETWORK_EAP) { + /* select automatically between only open, shared, leap */ + switch (wdev->conn->params.auth_type) { + case NL80211_AUTHTYPE_OPEN_SYSTEM: + if (wdev->connect_keys) + wdev->conn->params.auth_type = + NL80211_AUTHTYPE_SHARED_KEY; + else + wdev->conn->params.auth_type = + NL80211_AUTHTYPE_NETWORK_EAP; + break; + case NL80211_AUTHTYPE_SHARED_KEY: + wdev->conn->params.auth_type = + NL80211_AUTHTYPE_NETWORK_EAP; + break; + default: + /* huh? */ + wdev->conn->params.auth_type = + NL80211_AUTHTYPE_OPEN_SYSTEM; + break; + } + wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; + schedule_work(&rdev->conn_work); + } else if (status_code != WLAN_STATUS_SUCCESS) { + __cfg80211_connect_result(dev, mgmt->bssid, NULL, 0, NULL, 0, + status_code, false, NULL); + } else if (wdev->sme_state == CFG80211_SME_CONNECTING && + wdev->conn->state == CFG80211_CONN_AUTHENTICATING) { + wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; + schedule_work(&rdev->conn_work); + } +} + +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_sme_failed_assoc(struct wireless_dev *wdev) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + wdev->conn->state = CFG80211_CONN_DEAUTH_ASSOC_FAIL; + schedule_work(&rdev->conn_work); +} + +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, + u16 status, bool wextev, + struct cfg80211_bss *bss) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + u8 *country_ie; +#ifdef CONFIG_WIRELESS_EXT + union iwreq_data wrqu; +#endif + + ASSERT_WDEV_LOCK(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return; + + 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, + status, GFP_KERNEL); + +#ifdef CONFIG_WIRELESS_EXT + if (wextev) { + if (req_ie && status == WLAN_STATUS_SUCCESS) { + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.data.length = req_ie_len; + wireless_send_event(dev, IWEVASSOCREQIE, &wrqu, req_ie); + } + + if (resp_ie && status == WLAN_STATUS_SUCCESS) { + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.data.length = resp_ie_len; + wireless_send_event(dev, IWEVASSOCRESPIE, &wrqu, resp_ie); + } + + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.ap_addr.sa_family = ARPHRD_ETHER; + 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 + + if (wdev->current_bss) { + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(&wdev->current_bss->pub); + wdev->current_bss = NULL; + } + + 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); + wdev->connect_keys = NULL; + wdev->ssid_len = 0; + return; + } + + if (!bss) + bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, + wdev->ssid, wdev->ssid_len, + WLAN_CAPABILITY_ESS, + WLAN_CAPABILITY_ESS); + + if (WARN_ON(!bss)) + return; + + cfg80211_hold_bss(bss_from_pub(bss)); + wdev->current_bss = bss_from_pub(bss); + + wdev->sme_state = CFG80211_SME_CONNECTED; + cfg80211_upload_connect_keys(wdev); + + country_ie = (u8 *) ieee80211_bss_get_ie(bss, WLAN_EID_COUNTRY); + + if (!country_ie) + return; + + /* + * ieee80211_bss_get_ie() ensures we can access: + * - country_ie + 2, the start of the country ie data, and + * - and country_ie[1] which is the IE length + */ + regulatory_hint_11d(wdev->wiphy, + country_ie + 2, + country_ie[1]); +} + +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, + u16 status, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + 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; + 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); + ev->cr.resp_ie = ((u8 *)ev) + sizeof(*ev) + req_ie_len; + ev->cr.resp_ie_len = resp_ie_len; + memcpy((void *)ev->cr.resp_ie, resp_ie, resp_ie_len); + ev->cr.status = status; + + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + schedule_work(&rdev->event_work); +} +EXPORT_SYMBOL(cfg80211_connect_result); + +void __cfg80211_roamed(struct wireless_dev *wdev, const u8 *bssid, + const u8 *req_ie, size_t req_ie_len, + const u8 *resp_ie, size_t resp_ie_len) +{ + struct cfg80211_bss *bss; +#ifdef CONFIG_WIRELESS_EXT + union iwreq_data wrqu; +#endif + + ASSERT_WDEV_LOCK(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return; + + if (wdev->sme_state != CFG80211_SME_CONNECTED) + return; + + /* internal error -- how did we get to CONNECTED w/o BSS? */ + if (WARN_ON(!wdev->current_bss)) { + return; + } + + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(&wdev->current_bss->pub); + wdev->current_bss = NULL; + + bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, + wdev->ssid, wdev->ssid_len, + WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS); + + if (WARN_ON(!bss)) + return; + + cfg80211_hold_bss(bss_from_pub(bss)); + wdev->current_bss = bss_from_pub(bss); + + nl80211_send_roamed(wiphy_to_dev(wdev->wiphy), wdev->netdev, bssid, + req_ie, req_ie_len, resp_ie, resp_ie_len, + GFP_KERNEL); + +#ifdef CONFIG_WIRELESS_EXT + if (req_ie) { + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.data.length = req_ie_len; + wireless_send_event(wdev->netdev, IWEVASSOCREQIE, + &wrqu, req_ie); + } + + if (resp_ie) { + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.data.length = resp_ie_len; + wireless_send_event(wdev->netdev, IWEVASSOCRESPIE, + &wrqu, resp_ie); + } + + 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 +} + +void cfg80211_roamed(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, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + 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; + + ev->type = EVENT_ROAMED; + memcpy(ev->rm.bssid, bssid, ETH_ALEN); + ev->rm.req_ie = ((u8 *)ev) + sizeof(*ev); + ev->rm.req_ie_len = req_ie_len; + memcpy((void *)ev->rm.req_ie, req_ie, req_ie_len); + ev->rm.resp_ie = ((u8 *)ev) + sizeof(*ev) + req_ie_len; + ev->rm.resp_ie_len = resp_ie_len; + memcpy((void *)ev->rm.resp_ie, resp_ie, resp_ie_len); + + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + schedule_work(&rdev->event_work); +} +EXPORT_SYMBOL(cfg80211_roamed); + +void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, + size_t ie_len, u16 reason, bool from_ap) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + int i; +#ifdef CONFIG_WIRELESS_EXT + union iwreq_data wrqu; +#endif + + ASSERT_WDEV_LOCK(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return; + + if (wdev->sme_state != CFG80211_SME_CONNECTED) + return; + + if (wdev->current_bss) { + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(&wdev->current_bss->pub); + } + + wdev->current_bss = NULL; + wdev->sme_state = CFG80211_SME_IDLE; + 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); + + /* + * Delete all the keys ... pairwise keys can't really + * exist any more anyway, but default keys might. + */ + if (rdev->ops->del_key) + for (i = 0; i < 6; i++) + rdev->ops->del_key(wdev->wiphy, dev, i, NULL); + +#ifdef CONFIG_WIRELESS_EXT + memset(&wrqu, 0, sizeof(wrqu)); + wrqu.ap_addr.sa_family = ARPHRD_ETHER; + wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); +#endif +} + +void cfg80211_disconnected(struct net_device *dev, u16 reason, + u8 *ie, size_t ie_len, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + 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; + + ev->type = EVENT_DISCONNECTED; + ev->dc.ie = ((u8 *)ev) + sizeof(*ev); + ev->dc.ie_len = ie_len; + memcpy((void *)ev->dc.ie, ie, ie_len); + ev->dc.reason = reason; + + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + schedule_work(&rdev->event_work); +} +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, + const u8 *prev_bssid) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct ieee80211_channel *chan; + struct cfg80211_bss *bss = NULL; + int err; + + ASSERT_WDEV_LOCK(wdev); + + 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; + } + + 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 (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; + } + } + } + + if (!rdev->ops->connect) { + if (!rdev->ops->auth || !rdev->ops->assoc) + return -EOPNOTSUPP; + + if (WARN_ON(wdev->conn)) + return -EINPROGRESS; + + wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL); + if (!wdev->conn) + return -ENOMEM; + + /* + * Copy all parameters, and treat explicitly IEs, BSSID, SSID. + */ + memcpy(&wdev->conn->params, connect, sizeof(*connect)); + if (connect->bssid) { + wdev->conn->params.bssid = wdev->conn->bssid; + memcpy(wdev->conn->bssid, connect->bssid, ETH_ALEN); + } + + if (connect->ie) { + wdev->conn->ie = kmemdup(connect->ie, connect->ie_len, + GFP_KERNEL); + wdev->conn->params.ie = wdev->conn->ie; + if (!wdev->conn->ie) { + kfree(wdev->conn); + wdev->conn = NULL; + return -ENOMEM; + } + } + + if (connect->auth_type == NL80211_AUTHTYPE_AUTOMATIC) { + wdev->conn->auto_auth = true; + /* start with open system ... should mostly work */ + wdev->conn->params.auth_type = + NL80211_AUTHTYPE_OPEN_SYSTEM; + } else { + wdev->conn->auto_auth = false; + } + + memcpy(wdev->ssid, connect->ssid, connect->ssid_len); + wdev->ssid_len = connect->ssid_len; + wdev->conn->params.ssid = wdev->ssid; + wdev->conn->params.ssid_len = connect->ssid_len; + + /* see if we have the bss already */ + bss = cfg80211_get_conn_bss(wdev); + + 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 a matching bss struct */ + if (bss) { + wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; + err = cfg80211_conn_do_work(wdev); + cfg80211_put_bss(bss); + } else { + /* otherwise we'll need to scan for the AP first */ + err = cfg80211_conn_scan(wdev); + /* + * If we can't scan right now, then we need to scan again + * after the current scan finished, since the parameters + * changed (unless we find a good AP anyway). + */ + if (err == -EBUSY) { + err = 0; + wdev->conn->state = CFG80211_CONN_SCAN_AGAIN; + } + } + if (err) { + kfree(wdev->conn->ie); + kfree(wdev->conn); + wdev->conn = NULL; + wdev->sme_state = CFG80211_SME_IDLE; + wdev->connect_keys = NULL; + wdev->ssid_len = 0; + } + + return err; + } else { + wdev->sme_state = CFG80211_SME_CONNECTING; + wdev->connect_keys = connkeys; + err = rdev->ops->connect(&rdev->wiphy, dev, connect); + if (err) { + wdev->connect_keys = NULL; + wdev->sme_state = CFG80211_SME_IDLE; + return err; + } + + memcpy(wdev->ssid, connect->ssid, connect->ssid_len); + wdev->ssid_len = connect->ssid_len; + + return 0; + } +} + +int cfg80211_connect(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_connect_params *connect, + struct cfg80211_cached_keys *connkeys) +{ + int err; + + mutex_lock(&rdev->devlist_mtx); + wdev_lock(dev->ieee80211_ptr); + err = __cfg80211_connect(rdev, dev, connect, connkeys, NULL); + wdev_unlock(dev->ieee80211_ptr); + mutex_unlock(&rdev->devlist_mtx); + + return err; +} + +int __cfg80211_disconnect(struct cfg80211_registered_device *rdev, + struct net_device *dev, u16 reason, bool wextev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + ASSERT_WDEV_LOCK(wdev); + + if (wdev->sme_state == CFG80211_SME_IDLE) + return -EINVAL; + + kfree(wdev->connect_keys); + wdev->connect_keys = NULL; + + if (!rdev->ops->disconnect) { + if (!rdev->ops->deauth) + return -EOPNOTSUPP; + + /* was it connected by userspace SME? */ + if (!wdev->conn) { + cfg80211_mlme_down(rdev, dev); + return 0; + } + + if (wdev->sme_state == CFG80211_SME_CONNECTING && + (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; + return 0; + } + + /* wdev->conn->params.bssid must be set if > SCANNING */ + err = __cfg80211_mlme_deauth(rdev, dev, + wdev->conn->params.bssid, + NULL, 0, reason); + if (err) + return err; + } else { + err = rdev->ops->disconnect(&rdev->wiphy, dev, reason); + if (err) + return err; + } + + if (wdev->sme_state == CFG80211_SME_CONNECTED) + __cfg80211_disconnected(dev, NULL, 0, 0, false); + else if (wdev->sme_state == CFG80211_SME_CONNECTING) + __cfg80211_connect_result(dev, NULL, NULL, 0, NULL, 0, + WLAN_STATUS_UNSPECIFIED_FAILURE, + wextev, NULL); + + return 0; +} + +int cfg80211_disconnect(struct cfg80211_registered_device *rdev, + struct net_device *dev, + u16 reason, bool wextev) +{ + int err; + + wdev_lock(dev->ieee80211_ptr); + err = __cfg80211_disconnect(rdev, dev, reason, wextev); + wdev_unlock(dev->ieee80211_ptr); + + return err; +} + +void cfg80211_sme_disassoc(struct net_device *dev, int idx) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + u8 bssid[ETH_ALEN]; + + ASSERT_WDEV_LOCK(wdev); + + if (!wdev->conn) + return; + + if (wdev->conn->state == CFG80211_CONN_IDLE) + return; + + /* + * Ok, so the association was made by this SME -- we don't + * want it any more so deauthenticate too. + */ + + if (!wdev->auth_bsses[idx]) + return; + + memcpy(bssid, wdev->auth_bsses[idx]->pub.bssid, ETH_ALEN); + if (__cfg80211_mlme_deauth(rdev, dev, bssid, + NULL, 0, WLAN_REASON_DEAUTH_LEAVING)) { + /* whatever -- assume gone anyway */ + cfg80211_unhold_bss(wdev->auth_bsses[idx]); + cfg80211_put_bss(&wdev->auth_bsses[idx]->pub); + wdev->auth_bsses[idx] = NULL; + } +} diff --git a/net/wireless/util.c b/net/wireless/util.c index 25550692dda..3fc2df86278 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -141,9 +141,12 @@ void ieee80211_set_bitrate_flags(struct wiphy *wiphy) set_mandatory_flags_band(wiphy->bands[band], band); } -int cfg80211_validate_key_settings(struct key_params *params, int key_idx, +int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, + struct key_params *params, int key_idx, const u8 *mac_addr) { + int i; + if (key_idx > 5) return -EINVAL; @@ -197,6 +200,12 @@ int cfg80211_validate_key_settings(struct key_params *params, int key_idx, } } + for (i = 0; i < rdev->wiphy.n_cipher_suites; i++) + if (params->cipher == rdev->wiphy.cipher_suites[i]) + break; + if (i == rdev->wiphy.n_cipher_suites) + return -EINVAL; + return 0; } @@ -265,11 +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; @@ -324,10 +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) @@ -502,3 +519,166 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb) return dscp >> 5; } EXPORT_SYMBOL(cfg80211_classify8021d); + +const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 ie) +{ + u8 *end, *pos; + + pos = bss->information_elements; + if (pos == NULL) + return NULL; + end = pos + bss->len_information_elements; + + while (pos + 1 < end) { + if (pos + 2 + pos[1] > end) + break; + if (pos[0] == ie) + return pos; + pos += 2 + pos[1]; + } + + return NULL; +} +EXPORT_SYMBOL(ieee80211_bss_get_ie); + +void cfg80211_upload_connect_keys(struct wireless_dev *wdev) +{ + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct net_device *dev = wdev->netdev; + int i; + + if (!wdev->connect_keys) + return; + + for (i = 0; i < 6; i++) { + if (!wdev->connect_keys->params[i].cipher) + continue; + if (rdev->ops->add_key(wdev->wiphy, dev, i, NULL, + &wdev->connect_keys->params[i])) { + printk(KERN_ERR "%s: failed to set key %d\n", + dev->name, i); + continue; + } + if (wdev->connect_keys->def == i) + if (rdev->ops->set_default_key(wdev->wiphy, dev, i)) { + printk(KERN_ERR "%s: failed to set defkey %d\n", + dev->name, i); + continue; + } + if (wdev->connect_keys->defmgmt == i) + if (rdev->ops->set_default_mgmt_key(wdev->wiphy, dev, i)) + printk(KERN_ERR "%s: failed to set mgtdef %d\n", + dev->name, i); + } + + 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 d030c531567..561a45cf2a6 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -14,6 +14,7 @@ #include <linux/etherdevice.h> #include <net/iw_handler.h> #include <net/cfg80211.h> +#include "wext-compat.h" #include "core.h" int cfg80211_wext_giwname(struct net_device *dev, @@ -69,18 +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; @@ -103,9 +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->ifindex, 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; } @@ -154,7 +145,7 @@ int cfg80211_wext_giwrange(struct net_device *dev, struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_range *range = (struct iw_range *) extra; enum ieee80211_band band; - int c = 0; + int i, c = 0; if (!wdev) return -EOPNOTSUPP; @@ -173,9 +164,6 @@ int cfg80211_wext_giwrange(struct net_device *dev, range->min_frag = 256; range->max_frag = 2346; - range->encoding_size[0] = 5; - range->encoding_size[1] = 13; - range->num_encoding_sizes = 2; range->max_encoding_tokens = 4; range->max_qual.updated = IW_QUAL_NOISE_INVALID; @@ -204,11 +192,31 @@ int cfg80211_wext_giwrange(struct net_device *dev, range->avg_qual.noise = range->max_qual.noise / 2; range->avg_qual.updated = range->max_qual.updated; - range->enc_capa = IW_ENC_CAPA_WPA | IW_ENC_CAPA_WPA2 | - IW_ENC_CAPA_CIPHER_TKIP | IW_ENC_CAPA_CIPHER_CCMP; + for (i = 0; i < wdev->wiphy->n_cipher_suites; i++) { + switch (wdev->wiphy->cipher_suites[i]) { + case WLAN_CIPHER_SUITE_TKIP: + range->enc_capa |= (IW_ENC_CAPA_CIPHER_TKIP | + IW_ENC_CAPA_WPA); + break; + + case WLAN_CIPHER_SUITE_CCMP: + range->enc_capa |= (IW_ENC_CAPA_CIPHER_CCMP | + IW_ENC_CAPA_WPA2); + break; + + case WLAN_CIPHER_SUITE_WEP40: + range->encoding_size[range->num_encoding_sizes++] = + WLAN_KEY_LEN_WEP40; + break; + + case WLAN_CIPHER_SUITE_WEP104: + range->encoding_size[range->num_encoding_sizes++] = + WLAN_KEY_LEN_WEP104; + break; + } + } for (band = 0; band < IEEE80211_NUM_BANDS; band ++) { - int i; struct ieee80211_supported_band *sband; sband = wdev->wiphy->bands[band]; @@ -236,97 +244,40 @@ int cfg80211_wext_giwrange(struct net_device *dev, IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWAP); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWSCAN); - range->scan_capa |= IW_SCAN_CAPA_ESSID; + if (wdev->wiphy->max_scan_ssids > 0) + range->scan_capa |= IW_SCAN_CAPA_ESSID; return 0; } EXPORT_SYMBOL_GPL(cfg80211_wext_giwrange); -int cfg80211_wext_siwmlme(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *data, char *extra) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - struct iw_mlme *mlme = (struct iw_mlme *)extra; - struct cfg80211_registered_device *rdev; - union { - struct cfg80211_disassoc_request disassoc; - struct cfg80211_deauth_request deauth; - } cmd; - - if (!wdev) - return -EOPNOTSUPP; - - rdev = wiphy_to_dev(wdev->wiphy); - - if (wdev->iftype != NL80211_IFTYPE_STATION) - return -EINVAL; - - if (mlme->addr.sa_family != ARPHRD_ETHER) - return -EINVAL; - - memset(&cmd, 0, sizeof(cmd)); - - switch (mlme->cmd) { - case IW_MLME_DEAUTH: - if (!rdev->ops->deauth) - return -EOPNOTSUPP; - cmd.deauth.peer_addr = mlme->addr.sa_data; - cmd.deauth.reason_code = mlme->reason_code; - return rdev->ops->deauth(wdev->wiphy, dev, &cmd.deauth); - case IW_MLME_DISASSOC: - if (!rdev->ops->disassoc) - return -EOPNOTSUPP; - cmd.disassoc.peer_addr = mlme->addr.sa_data; - cmd.disassoc.reason_code = mlme->reason_code; - return rdev->ops->disassoc(wdev->wiphy, dev, &cmd.disassoc); - default: - return -EOPNOTSUPP; - } -} -EXPORT_SYMBOL_GPL(cfg80211_wext_siwmlme); - /** * cfg80211_wext_freq - get wext frequency for non-"auto" * @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; } -EXPORT_SYMBOL_GPL(cfg80211_wext_freq); int cfg80211_wext_siwrts(struct net_device *dev, struct iw_request_info *info, @@ -479,15 +430,32 @@ int cfg80211_wext_giwretry(struct net_device *dev, } EXPORT_SYMBOL_GPL(cfg80211_wext_giwretry); -static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, - struct net_device *dev, const u8 *addr, - bool remove, bool tx_key, int idx, - struct key_params *params) +static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *addr, + bool remove, bool tx_key, int idx, + struct key_params *params) { struct wireless_dev *wdev = dev->ieee80211_ptr; - int err; + int err, i; + + if (!wdev->wext.keys) { + wdev->wext.keys = kzalloc(sizeof(*wdev->wext.keys), + GFP_KERNEL); + if (!wdev->wext.keys) + return -ENOMEM; + for (i = 0; i < 6; i++) + wdev->wext.keys->params[i].key = + wdev->wext.keys->data[i]; + } + + if (wdev->iftype != NL80211_IFTYPE_ADHOC && + wdev->iftype != NL80211_IFTYPE_STATION) + return -EOPNOTSUPP; if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC) { + if (!wdev->current_bss) + return -ENOLINK; + if (!rdev->ops->set_default_mgmt_key) return -EOPNOTSUPP; @@ -497,8 +465,14 @@ static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, return -EINVAL; if (remove) { - err = rdev->ops->del_key(&rdev->wiphy, dev, idx, addr); + err = 0; + if (wdev->current_bss) + err = rdev->ops->del_key(&rdev->wiphy, dev, idx, addr); if (!err) { + if (!addr) { + wdev->wext.keys->params[idx].key_len = 0; + wdev->wext.keys->params[idx].cipher = 0; + } if (idx == wdev->wext.default_key) wdev->wext.default_key = -1; else if (idx == wdev->wext.default_mgmt_key) @@ -512,36 +486,65 @@ static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, return 0; return err; - } else { - if (addr) - tx_key = false; + } - if (cfg80211_validate_key_settings(params, idx, addr)) - return -EINVAL; + if (addr) + tx_key = false; + if (cfg80211_validate_key_settings(rdev, params, idx, addr)) + return -EINVAL; + + err = 0; + if (wdev->current_bss) err = rdev->ops->add_key(&rdev->wiphy, dev, idx, addr, params); - if (err) - return err; + if (err) + return err; + + if (!addr) { + wdev->wext.keys->params[idx] = *params; + memcpy(wdev->wext.keys->data[idx], + params->key, params->key_len); + wdev->wext.keys->params[idx].key = + wdev->wext.keys->data[idx]; + } - if (tx_key || (!addr && wdev->wext.default_key == -1)) { + if ((params->cipher == WLAN_CIPHER_SUITE_WEP40 || + params->cipher == WLAN_CIPHER_SUITE_WEP104) && + (tx_key || (!addr && wdev->wext.default_key == -1))) { + if (wdev->current_bss) err = rdev->ops->set_default_key(&rdev->wiphy, dev, idx); - if (!err) - wdev->wext.default_key = idx; - return err; - } + if (!err) + wdev->wext.default_key = idx; + return err; + } - if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC && - (tx_key || (!addr && wdev->wext.default_mgmt_key == -1))) { + if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC && + (tx_key || (!addr && wdev->wext.default_mgmt_key == -1))) { + if (wdev->current_bss) err = rdev->ops->set_default_mgmt_key(&rdev->wiphy, dev, idx); - if (!err) - wdev->wext.default_mgmt_key = idx; - return err; - } - - return 0; + if (!err) + wdev->wext.default_mgmt_key = idx; + return err; } + + return 0; +} + +static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *addr, + bool remove, bool tx_key, int idx, + struct key_params *params) +{ + int err; + + wdev_lock(dev->ieee80211_ptr); + err = __cfg80211_set_encryption(rdev, dev, addr, remove, + tx_key, idx, params); + wdev_unlock(dev->ieee80211_ptr); + + return err; } int cfg80211_wext_siwencode(struct net_device *dev, @@ -554,6 +557,10 @@ int cfg80211_wext_siwencode(struct net_device *dev, bool remove = false; struct key_params params; + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_ADHOC) + return -EOPNOTSUPP; + /* no use -- only MFP (set_default_mgmt_key) is optional */ if (!rdev->ops->del_key || !rdev->ops->add_key || @@ -574,9 +581,14 @@ int cfg80211_wext_siwencode(struct net_device *dev, remove = true; else if (erq->length == 0) { /* No key data - just set the default TX key index */ - err = rdev->ops->set_default_key(&rdev->wiphy, dev, idx); + err = 0; + wdev_lock(wdev); + if (wdev->current_bss) + err = rdev->ops->set_default_key(&rdev->wiphy, + dev, idx); if (!err) wdev->wext.default_key = idx; + wdev_unlock(wdev); return err; } @@ -609,6 +621,10 @@ int cfg80211_wext_siwencodeext(struct net_device *dev, struct key_params params; u32 cipher; + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_ADHOC) + return -EOPNOTSUPP; + /* no use -- only MFP (set_default_mgmt_key) is optional */ if (!rdev->ops->del_key || !rdev->ops->add_key || @@ -682,37 +698,15 @@ int cfg80211_wext_siwencodeext(struct net_device *dev, } EXPORT_SYMBOL_GPL(cfg80211_wext_siwencodeext); -struct giwencode_cookie { - size_t buflen; - char *keybuf; -}; - -static void giwencode_get_key_cb(void *cookie, struct key_params *params) -{ - struct giwencode_cookie *data = cookie; - - if (!params->key) { - data->buflen = 0; - return; - } - - data->buflen = min_t(size_t, data->buflen, params->key_len); - memcpy(data->keybuf, params->key, data->buflen); -} - int cfg80211_wext_giwencode(struct net_device *dev, struct iw_request_info *info, struct iw_point *erq, char *keybuf) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); - int idx, err; - struct giwencode_cookie data = { - .keybuf = keybuf, - .buflen = erq->length, - }; + int idx; - if (!rdev->ops->get_key) + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; idx = erq->flags & IW_ENCODE_INDEX; @@ -727,24 +721,70 @@ int cfg80211_wext_giwencode(struct net_device *dev, erq->flags = idx + 1; - err = rdev->ops->get_key(&rdev->wiphy, dev, idx, NULL, &data, - giwencode_get_key_cb); - if (!err) { - erq->length = data.buflen; - erq->flags |= IW_ENCODE_ENABLED; - return 0; - } - - if (err == -ENOENT) { + if (!wdev->wext.keys || !wdev->wext.keys->params[idx].cipher) { erq->flags |= IW_ENCODE_DISABLED; erq->length = 0; return 0; } - return err; + erq->length = min_t(size_t, erq->length, + wdev->wext.keys->params[idx].key_len); + memcpy(keybuf, wdev->wext.keys->params[idx].key, erq->length); + erq->flags |= IW_ENCODE_ENABLED; + + return 0; } EXPORT_SYMBOL_GPL(cfg80211_wext_giwencode); +int cfg80211_wext_siwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *wextfreq, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + int freq, err; + + switch (wdev->iftype) { + case NL80211_IFTYPE_STATION: + return cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); + case NL80211_IFTYPE_ADHOC: + return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); + default: + freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); + if (freq < 0) + return freq; + if (freq == 0) + return -EINVAL; + 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); + +int cfg80211_wext_giwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + + switch (wdev->iftype) { + case NL80211_IFTYPE_STATION: + return cfg80211_mgd_wext_giwfreq(dev, info, freq, extra); + case NL80211_IFTYPE_ADHOC: + return cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); + default: + if (!rdev->channel) + return -EINVAL; + freq->m = rdev->channel->center_freq; + freq->e = 6; + return 0; + } +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwfreq); + int cfg80211_wext_siwtxpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *data, char *extra) @@ -794,7 +834,7 @@ int cfg80211_wext_siwtxpower(struct net_device *dev, return 0; } - return rdev->ops->set_tx_power(wdev->wiphy, type, dbm);; + return rdev->ops->set_tx_power(wdev->wiphy, type, dbm); } EXPORT_SYMBOL_GPL(cfg80211_wext_siwtxpower); @@ -827,3 +867,547 @@ int cfg80211_wext_giwtxpower(struct net_device *dev, return 0; } EXPORT_SYMBOL_GPL(cfg80211_wext_giwtxpower); + +static int cfg80211_set_auth_alg(struct wireless_dev *wdev, + s32 auth_alg) +{ + int nr_alg = 0; + + if (!auth_alg) + return -EINVAL; + + if (auth_alg & ~(IW_AUTH_ALG_OPEN_SYSTEM | + IW_AUTH_ALG_SHARED_KEY | + IW_AUTH_ALG_LEAP)) + return -EINVAL; + + if (auth_alg & IW_AUTH_ALG_OPEN_SYSTEM) { + nr_alg++; + wdev->wext.connect.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; + } + + if (auth_alg & IW_AUTH_ALG_SHARED_KEY) { + nr_alg++; + wdev->wext.connect.auth_type = NL80211_AUTHTYPE_SHARED_KEY; + } + + if (auth_alg & IW_AUTH_ALG_LEAP) { + nr_alg++; + wdev->wext.connect.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; + } + + if (nr_alg > 1) + wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; + + return 0; +} + +static int cfg80211_set_wpa_version(struct wireless_dev *wdev, u32 wpa_versions) +{ + wdev->wext.connect.crypto.wpa_versions = 0; + + if (wpa_versions & ~(IW_AUTH_WPA_VERSION_WPA | + IW_AUTH_WPA_VERSION_WPA2| + IW_AUTH_WPA_VERSION_DISABLED)) + return -EINVAL; + + if ((wpa_versions & IW_AUTH_WPA_VERSION_DISABLED) && + (wpa_versions & (IW_AUTH_WPA_VERSION_WPA| + IW_AUTH_WPA_VERSION_WPA2))) + return -EINVAL; + + if (wpa_versions & IW_AUTH_WPA_VERSION_DISABLED) + wdev->wext.connect.crypto.wpa_versions &= + ~(NL80211_WPA_VERSION_1|NL80211_WPA_VERSION_2); + + if (wpa_versions & IW_AUTH_WPA_VERSION_WPA) + wdev->wext.connect.crypto.wpa_versions |= + NL80211_WPA_VERSION_1; + + if (wpa_versions & IW_AUTH_WPA_VERSION_WPA2) + wdev->wext.connect.crypto.wpa_versions |= + NL80211_WPA_VERSION_2; + + return 0; +} + +static int cfg80211_set_cipher_group(struct wireless_dev *wdev, u32 cipher) +{ + wdev->wext.connect.crypto.cipher_group = 0; + + if (cipher & IW_AUTH_CIPHER_WEP40) + wdev->wext.connect.crypto.cipher_group = + WLAN_CIPHER_SUITE_WEP40; + else if (cipher & IW_AUTH_CIPHER_WEP104) + wdev->wext.connect.crypto.cipher_group = + WLAN_CIPHER_SUITE_WEP104; + else if (cipher & IW_AUTH_CIPHER_TKIP) + wdev->wext.connect.crypto.cipher_group = + WLAN_CIPHER_SUITE_TKIP; + else if (cipher & IW_AUTH_CIPHER_CCMP) + wdev->wext.connect.crypto.cipher_group = + WLAN_CIPHER_SUITE_CCMP; + else if (cipher & IW_AUTH_CIPHER_AES_CMAC) + wdev->wext.connect.crypto.cipher_group = + WLAN_CIPHER_SUITE_AES_CMAC; + else + return -EINVAL; + + return 0; +} + +static int cfg80211_set_cipher_pairwise(struct wireless_dev *wdev, u32 cipher) +{ + int nr_ciphers = 0; + u32 *ciphers_pairwise = wdev->wext.connect.crypto.ciphers_pairwise; + + if (cipher & IW_AUTH_CIPHER_WEP40) { + ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_WEP40; + nr_ciphers++; + } + + if (cipher & IW_AUTH_CIPHER_WEP104) { + ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_WEP104; + nr_ciphers++; + } + + if (cipher & IW_AUTH_CIPHER_TKIP) { + ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_TKIP; + nr_ciphers++; + } + + if (cipher & IW_AUTH_CIPHER_CCMP) { + ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_CCMP; + nr_ciphers++; + } + + if (cipher & IW_AUTH_CIPHER_AES_CMAC) { + ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_AES_CMAC; + nr_ciphers++; + } + + BUILD_BUG_ON(NL80211_MAX_NR_CIPHER_SUITES < 5); + + wdev->wext.connect.crypto.n_ciphers_pairwise = nr_ciphers; + + return 0; +} + + +static int cfg80211_set_key_mgt(struct wireless_dev *wdev, u32 key_mgt) +{ + int nr_akm_suites = 0; + + if (key_mgt & ~(IW_AUTH_KEY_MGMT_802_1X | + IW_AUTH_KEY_MGMT_PSK)) + return -EINVAL; + + if (key_mgt & IW_AUTH_KEY_MGMT_802_1X) { + wdev->wext.connect.crypto.akm_suites[nr_akm_suites] = + WLAN_AKM_SUITE_8021X; + nr_akm_suites++; + } + + if (key_mgt & IW_AUTH_KEY_MGMT_PSK) { + wdev->wext.connect.crypto.akm_suites[nr_akm_suites] = + WLAN_AKM_SUITE_PSK; + nr_akm_suites++; + } + + wdev->wext.connect.crypto.n_akm_suites = nr_akm_suites; + + return 0; +} + +int cfg80211_wext_siwauth(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *data, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + if (wdev->iftype != NL80211_IFTYPE_STATION) + return -EOPNOTSUPP; + + switch (data->flags & IW_AUTH_INDEX) { + case IW_AUTH_PRIVACY_INVOKED: + wdev->wext.connect.privacy = data->value; + return 0; + case IW_AUTH_WPA_VERSION: + return cfg80211_set_wpa_version(wdev, data->value); + case IW_AUTH_CIPHER_GROUP: + return cfg80211_set_cipher_group(wdev, data->value); + case IW_AUTH_KEY_MGMT: + return cfg80211_set_key_mgt(wdev, data->value); + case IW_AUTH_CIPHER_PAIRWISE: + return cfg80211_set_cipher_pairwise(wdev, data->value); + case IW_AUTH_80211_AUTH_ALG: + return cfg80211_set_auth_alg(wdev, data->value); + case IW_AUTH_WPA_ENABLED: + case IW_AUTH_RX_UNENCRYPTED_EAPOL: + case IW_AUTH_DROP_UNENCRYPTED: + case IW_AUTH_MFP: + return 0; + default: + return -EOPNOTSUPP; + } +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwauth); + +int cfg80211_wext_giwauth(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *data, char *extra) +{ + /* XXX: what do we need? */ + + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwauth); + +int cfg80211_wext_siwpower(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *wrq, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + bool ps = wdev->wext.ps; + int timeout = wdev->wext.ps_timeout; + int err; + + if (wdev->iftype != NL80211_IFTYPE_STATION) + return -EINVAL; + + if (!rdev->ops->set_power_mgmt) + return -EOPNOTSUPP; + + if (wrq->disabled) { + ps = false; + } else { + switch (wrq->flags & IW_POWER_MODE) { + case IW_POWER_ON: /* If not specified */ + case IW_POWER_MODE: /* If set all mask */ + case IW_POWER_ALL_R: /* If explicitely state all */ + ps = true; + break; + default: /* Otherwise we ignore */ + return -EINVAL; + } + + if (wrq->flags & ~(IW_POWER_MODE | IW_POWER_TIMEOUT)) + return -EINVAL; + + if (wrq->flags & IW_POWER_TIMEOUT) + timeout = wrq->value / 1000; + } + + err = rdev->ops->set_power_mgmt(wdev->wiphy, dev, ps, timeout); + if (err) + return err; + + wdev->wext.ps = ps; + wdev->wext.ps_timeout = timeout; + + return 0; + +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwpower); + +int cfg80211_wext_giwpower(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *wrq, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + wrq->disabled = !wdev->wext.ps; + + return 0; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwpower); + +static int cfg80211_wds_wext_siwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *addr, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + int err; + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS)) + return -EINVAL; + + if (addr->sa_family != ARPHRD_ETHER) + return -EINVAL; + + if (netif_running(dev)) + return -EBUSY; + + if (!rdev->ops->set_wds_peer) + return -EOPNOTSUPP; + + err = rdev->ops->set_wds_peer(wdev->wiphy, dev, (u8 *) &addr->sa_data); + if (err) + return err; + + memcpy(&wdev->wext.bssid, (u8 *) &addr->sa_data, ETH_ALEN); + + return 0; +} + +static int cfg80211_wds_wext_giwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *addr, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS)) + return -EINVAL; + + addr->sa_family = ARPHRD_ETHER; + memcpy(&addr->sa_data, wdev->wext.bssid, ETH_ALEN); + + return 0; +} + +int cfg80211_wext_siwrate(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *rate, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct cfg80211_bitrate_mask mask; + + if (!rdev->ops->set_bitrate_mask) + return -EOPNOTSUPP; + + mask.fixed = 0; + mask.maxrate = 0; + + if (rate->value < 0) { + /* nothing */ + } else if (rate->fixed) { + mask.fixed = rate->value / 1000; /* kbps */ + } else { + mask.maxrate = rate->value / 1000; /* kbps */ + } + + return rdev->ops->set_bitrate_mask(wdev->wiphy, dev, NULL, &mask); +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwrate); + +int cfg80211_wext_giwrate(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *rate, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + /* we are under RTNL - globally locked - so can use a static struct */ + static struct station_info sinfo; + u8 addr[ETH_ALEN]; + int err; + + if (wdev->iftype != NL80211_IFTYPE_STATION) + return -EOPNOTSUPP; + + if (!rdev->ops->get_station) + return -EOPNOTSUPP; + + err = 0; + wdev_lock(wdev); + if (wdev->current_bss) + memcpy(addr, wdev->current_bss->pub.bssid, ETH_ALEN); + else + err = -EOPNOTSUPP; + wdev_unlock(wdev); + if (err) + return err; + + err = rdev->ops->get_station(&rdev->wiphy, dev, addr, &sinfo); + if (err) + return err; + + if (!(sinfo.filled & STATION_INFO_TX_BITRATE)) + return -EOPNOTSUPP; + + rate->value = 0; + + if (!(sinfo.txrate.flags & RATE_INFO_FLAGS_MCS)) + rate->value = 100000 * sinfo.txrate.legacy; + + return 0; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwrate); + +/* Get wireless statistics. Called by /proc/net/wireless and by SIOCGIWSTATS */ +struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + /* we are under RTNL - globally locked - so can use static structs */ + static struct iw_statistics wstats; + static struct station_info sinfo; + u8 bssid[ETH_ALEN]; + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) + return NULL; + + if (!rdev->ops->get_station) + return NULL; + + /* Grab BSSID of current BSS, if any */ + wdev_lock(wdev); + if (!wdev->current_bss) { + wdev_unlock(wdev); + return NULL; + } + memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN); + wdev_unlock(wdev); + + if (rdev->ops->get_station(&rdev->wiphy, dev, bssid, &sinfo)) + return NULL; + + memset(&wstats, 0, sizeof(wstats)); + + switch (rdev->wiphy.signal_type) { + case CFG80211_SIGNAL_TYPE_MBM: + if (sinfo.filled & STATION_INFO_SIGNAL) { + int sig = sinfo.signal; + wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; + wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; + wstats.qual.updated |= IW_QUAL_DBM; + wstats.qual.level = sig; + if (sig < -110) + sig = -110; + else if (sig > -40) + sig = -40; + wstats.qual.qual = sig + 110; + break; + } + case CFG80211_SIGNAL_TYPE_UNSPEC: + if (sinfo.filled & STATION_INFO_SIGNAL) { + wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; + wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; + wstats.qual.level = sinfo.signal; + wstats.qual.qual = sinfo.signal; + break; + } + default: + wstats.qual.updated |= IW_QUAL_LEVEL_INVALID; + wstats.qual.updated |= IW_QUAL_QUAL_INVALID; + } + + wstats.qual.updated |= IW_QUAL_NOISE_INVALID; + + return &wstats; +} +EXPORT_SYMBOL_GPL(cfg80211_wireless_stats); + +int cfg80211_wext_siwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + switch (wdev->iftype) { + case NL80211_IFTYPE_ADHOC: + return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); + case NL80211_IFTYPE_STATION: + return cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); + case NL80211_IFTYPE_WDS: + return cfg80211_wds_wext_siwap(dev, info, ap_addr, extra); + default: + return -EOPNOTSUPP; + } +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwap); + +int cfg80211_wext_giwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + switch (wdev->iftype) { + case NL80211_IFTYPE_ADHOC: + return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); + case NL80211_IFTYPE_STATION: + return cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); + case NL80211_IFTYPE_WDS: + return cfg80211_wds_wext_giwap(dev, info, ap_addr, extra); + default: + return -EOPNOTSUPP; + } +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwap); + +int cfg80211_wext_siwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + switch (wdev->iftype) { + case NL80211_IFTYPE_ADHOC: + return cfg80211_ibss_wext_siwessid(dev, info, data, ssid); + case NL80211_IFTYPE_STATION: + return cfg80211_mgd_wext_siwessid(dev, info, data, ssid); + default: + return -EOPNOTSUPP; + } +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwessid); + +int cfg80211_wext_giwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + switch (wdev->iftype) { + case NL80211_IFTYPE_ADHOC: + return cfg80211_ibss_wext_giwessid(dev, info, data, ssid); + case NL80211_IFTYPE_STATION: + return cfg80211_mgd_wext_giwessid(dev, info, data, ssid); + default: + return -EOPNOTSUPP; + } +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwessid); + +static const iw_handler cfg80211_handlers[] = { + [IW_IOCTL_IDX(SIOCGIWNAME)] = (iw_handler) cfg80211_wext_giwname, + [IW_IOCTL_IDX(SIOCSIWFREQ)] = (iw_handler) cfg80211_wext_siwfreq, + [IW_IOCTL_IDX(SIOCGIWFREQ)] = (iw_handler) cfg80211_wext_giwfreq, + [IW_IOCTL_IDX(SIOCSIWMODE)] = (iw_handler) cfg80211_wext_siwmode, + [IW_IOCTL_IDX(SIOCGIWMODE)] = (iw_handler) cfg80211_wext_giwmode, + [IW_IOCTL_IDX(SIOCGIWRANGE)] = (iw_handler) cfg80211_wext_giwrange, + [IW_IOCTL_IDX(SIOCSIWAP)] = (iw_handler) cfg80211_wext_siwap, + [IW_IOCTL_IDX(SIOCGIWAP)] = (iw_handler) cfg80211_wext_giwap, + [IW_IOCTL_IDX(SIOCSIWMLME)] = (iw_handler) cfg80211_wext_siwmlme, + [IW_IOCTL_IDX(SIOCSIWSCAN)] = (iw_handler) cfg80211_wext_siwscan, + [IW_IOCTL_IDX(SIOCGIWSCAN)] = (iw_handler) cfg80211_wext_giwscan, + [IW_IOCTL_IDX(SIOCSIWESSID)] = (iw_handler) cfg80211_wext_siwessid, + [IW_IOCTL_IDX(SIOCGIWESSID)] = (iw_handler) cfg80211_wext_giwessid, + [IW_IOCTL_IDX(SIOCSIWRATE)] = (iw_handler) cfg80211_wext_siwrate, + [IW_IOCTL_IDX(SIOCGIWRATE)] = (iw_handler) cfg80211_wext_giwrate, + [IW_IOCTL_IDX(SIOCSIWRTS)] = (iw_handler) cfg80211_wext_siwrts, + [IW_IOCTL_IDX(SIOCGIWRTS)] = (iw_handler) cfg80211_wext_giwrts, + [IW_IOCTL_IDX(SIOCSIWFRAG)] = (iw_handler) cfg80211_wext_siwfrag, + [IW_IOCTL_IDX(SIOCGIWFRAG)] = (iw_handler) cfg80211_wext_giwfrag, + [IW_IOCTL_IDX(SIOCSIWTXPOW)] = (iw_handler) cfg80211_wext_siwtxpower, + [IW_IOCTL_IDX(SIOCGIWTXPOW)] = (iw_handler) cfg80211_wext_giwtxpower, + [IW_IOCTL_IDX(SIOCSIWRETRY)] = (iw_handler) cfg80211_wext_siwretry, + [IW_IOCTL_IDX(SIOCGIWRETRY)] = (iw_handler) cfg80211_wext_giwretry, + [IW_IOCTL_IDX(SIOCSIWENCODE)] = (iw_handler) cfg80211_wext_siwencode, + [IW_IOCTL_IDX(SIOCGIWENCODE)] = (iw_handler) cfg80211_wext_giwencode, + [IW_IOCTL_IDX(SIOCSIWPOWER)] = (iw_handler) cfg80211_wext_siwpower, + [IW_IOCTL_IDX(SIOCGIWPOWER)] = (iw_handler) cfg80211_wext_giwpower, + [IW_IOCTL_IDX(SIOCSIWGENIE)] = (iw_handler) cfg80211_wext_siwgenie, + [IW_IOCTL_IDX(SIOCSIWAUTH)] = (iw_handler) cfg80211_wext_siwauth, + [IW_IOCTL_IDX(SIOCGIWAUTH)] = (iw_handler) cfg80211_wext_giwauth, + [IW_IOCTL_IDX(SIOCSIWENCODEEXT)]= (iw_handler) cfg80211_wext_siwencodeext, +}; + +const struct iw_handler_def cfg80211_wext_handler = { + .num_standard = ARRAY_SIZE(cfg80211_handlers), + .standard = cfg80211_handlers, + .get_wireless_stats = cfg80211_wireless_stats, +}; diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h new file mode 100644 index 00000000000..20b3daef696 --- /dev/null +++ b/net/wireless/wext-compat.h @@ -0,0 +1,49 @@ +#ifndef __WEXT_COMPAT +#define __WEXT_COMPAT + +#include <net/iw_handler.h> +#include <linux/wireless.h> + +int cfg80211_ibss_wext_siwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra); +int cfg80211_ibss_wext_giwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra); +int cfg80211_ibss_wext_siwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra); +int cfg80211_ibss_wext_giwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra); +int cfg80211_ibss_wext_siwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid); +int cfg80211_ibss_wext_giwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid); + +int cfg80211_mgd_wext_siwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra); +int cfg80211_mgd_wext_giwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra); +int cfg80211_mgd_wext_siwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra); +int cfg80211_mgd_wext_giwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra); +int cfg80211_mgd_wext_siwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid); +int cfg80211_mgd_wext_giwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid); + +int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq); + + +extern const struct iw_handler_def cfg80211_wext_handler; +#endif /* __WEXT_COMPAT */ diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c new file mode 100644 index 00000000000..5615a880253 --- /dev/null +++ b/net/wireless/wext-sme.c @@ -0,0 +1,402 @@ +/* + * cfg80211 wext compat for managed mode. + * + * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2009 Intel Corporation. All rights reserved. + */ + +#include <linux/etherdevice.h> +#include <linux/if_arp.h> +#include <net/cfg80211.h> +#include "wext-compat.h" +#include "nl80211.h" + +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); + ASSERT_WDEV_LOCK(wdev); + + if (!netif_running(wdev->netdev)) + return 0; + + wdev->wext.connect.ie = wdev->wext.ie; + wdev->wext.connect.ie_len = wdev->wext.ie_len; + + if (wdev->wext.keys) { + wdev->wext.keys->def = wdev->wext.default_key; + wdev->wext.keys->defmgmt = wdev->wext.default_mgmt_key; + if (wdev->wext.default_key != -1) + wdev->wext.connect.privacy = true; + } + + if (!wdev->wext.connect.ssid_len) + return 0; + + if (wdev->wext.keys) { + ck = kmemdup(wdev->wext.keys, sizeof(*ck), GFP_KERNEL); + if (!ck) + return -ENOMEM; + 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, prev_bssid); + if (err) + kfree(ck); + + return err; +} + +int cfg80211_mgd_wext_siwfreq(struct net_device *dev, + struct iw_request_info *info, + 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 = NULL; + int err, freq; + + /* call only for station! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return -EINVAL; + + freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); + if (freq < 0) + return freq; + + 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) { + bool event = true; + + if (wdev->wext.connect.channel == chan) { + err = 0; + goto out; + } + + /* if SSID set, we'll try right again, avoid event */ + if (wdev->wext.connect.ssid_len) + event = false; + err = __cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, event); + if (err) + goto out; + } + + + wdev->wext.connect.channel = chan; + + /* SSID is not set, we just want to switch channel */ + 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(rdev, wdev); + out: + wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); + cfg80211_unlock_rdev(rdev); + return err; +} + +int cfg80211_mgd_wext_giwfreq(struct net_device *dev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct ieee80211_channel *chan = NULL; + + /* call only for station! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return -EINVAL; + + wdev_lock(wdev); + if (wdev->current_bss) + chan = wdev->current_bss->pub.channel; + else if (wdev->wext.connect.channel) + chan = wdev->wext.connect.channel; + wdev_unlock(wdev); + + if (chan) { + freq->m = chan->center_freq; + freq->e = 6; + return 0; + } + + /* no channel if not joining */ + return -EINVAL; +} + +int cfg80211_mgd_wext_siwessid(struct net_device *dev, + struct iw_request_info *info, + 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; + + /* call only for station! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return -EINVAL; + + if (!data->flags) + len = 0; + + /* iwconfig uses nul termination in SSID.. */ + if (len > 0 && ssid[len - 1] == '\0') + len--; + + cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->devlist_mtx); + wdev_lock(wdev); + + err = 0; + + if (wdev->sme_state != CFG80211_SME_IDLE) { + bool event = true; + + if (wdev->wext.connect.ssid && len && + len == wdev->wext.connect.ssid_len && + memcmp(wdev->wext.connect.ssid, ssid, len) == 0) + goto out; + + /* if SSID set now, we'll try to connect, avoid event */ + if (len) + event = false; + 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(rdev, wdev); + out: + wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); + cfg80211_unlock_rdev(rdev); + return err; +} + +int cfg80211_mgd_wext_giwessid(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *ssid) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + /* call only for station! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return -EINVAL; + + data->flags = 0; + + wdev_lock(wdev); + 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); + } + wdev_unlock(wdev); + + return 0; +} + +int cfg80211_mgd_wext_siwap(struct net_device *dev, + struct iw_request_info *info, + 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; + + /* call only for station! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return -EINVAL; + + if (ap_addr->sa_family != ARPHRD_ETHER) + return -EINVAL; + + /* automatic mode */ + if (is_zero_ether_addr(bssid) || is_broadcast_ether_addr(bssid)) + bssid = NULL; + + cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->devlist_mtx); + wdev_lock(wdev); + + if (wdev->sme_state != CFG80211_SME_IDLE) { + err = 0; + /* both automatic */ + if (!bssid && !wdev->wext.connect.bssid) + goto out; + + /* fixed already - and no change */ + if (wdev->wext.connect.bssid && bssid && + compare_ether_addr(bssid, wdev->wext.connect.bssid) == 0) + goto out; + + err = __cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, false); + if (err) + goto out; + } + + if (bssid) { + memcpy(wdev->wext.bssid, bssid, ETH_ALEN); + wdev->wext.connect.bssid = wdev->wext.bssid; + } else + wdev->wext.connect.bssid = NULL; + + err = cfg80211_mgd_wext_connect(rdev, wdev); + out: + wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); + cfg80211_unlock_rdev(rdev); + return err; +} + +int cfg80211_mgd_wext_giwap(struct net_device *dev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + /* call only for station! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return -EINVAL; + + ap_addr->sa_family = ARPHRD_ETHER; + + wdev_lock(wdev); + if (wdev->current_bss) + memcpy(ap_addr->sa_data, wdev->current_bss->pub.bssid, ETH_ALEN); + else + memset(ap_addr->sa_data, 0, ETH_ALEN); + wdev_unlock(wdev); + + return 0; +} + +int cfg80211_wext_siwgenie(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + u8 *ie = extra; + int ie_len = data->length, err; + + if (wdev->iftype != NL80211_IFTYPE_STATION) + return -EOPNOTSUPP; + + if (!ie_len) + ie = NULL; + + wdev_lock(wdev); + + /* no change */ + err = 0; + if (wdev->wext.ie_len == ie_len && + memcmp(wdev->wext.ie, ie, ie_len) == 0) + goto out; + + if (ie_len) { + ie = kmemdup(extra, ie_len, GFP_KERNEL); + if (!ie) { + err = -ENOMEM; + goto out; + } + } else + ie = NULL; + + kfree(wdev->wext.ie); + wdev->wext.ie = ie; + wdev->wext.ie_len = ie_len; + + if (wdev->sme_state != CFG80211_SME_IDLE) { + err = __cfg80211_disconnect(rdev, dev, + WLAN_REASON_DEAUTH_LEAVING, false); + if (err) + goto out; + } + + /* userspace better not think we'll reconnect */ + err = 0; + out: + wdev_unlock(wdev); + return err; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwgenie); + +int cfg80211_wext_siwmlme(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct iw_mlme *mlme = (struct iw_mlme *)extra; + struct cfg80211_registered_device *rdev; + int err; + + if (!wdev) + return -EOPNOTSUPP; + + rdev = wiphy_to_dev(wdev->wiphy); + + if (wdev->iftype != NL80211_IFTYPE_STATION) + return -EINVAL; + + if (mlme->addr.sa_family != ARPHRD_ETHER) + return -EINVAL; + + wdev_lock(wdev); + switch (mlme->cmd) { + case IW_MLME_DEAUTH: + case IW_MLME_DISASSOC: + err = __cfg80211_disconnect(rdev, dev, mlme->reason_code, + true); + break; + default: + err = -EOPNOTSUPP; + break; + } + wdev_unlock(wdev); + + return err; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwmlme); diff --git a/net/wireless/wext.c b/net/wireless/wext.c index 252c2010c2e..60fe57761ca 100644 --- a/net/wireless/wext.c +++ b/net/wireless/wext.c @@ -417,6 +417,21 @@ static const int event_type_size[] = { IW_EV_QUAL_LEN, /* IW_HEADER_TYPE_QUAL */ }; +#ifdef CONFIG_COMPAT +static const int compat_event_type_size[] = { + IW_EV_COMPAT_LCP_LEN, /* IW_HEADER_TYPE_NULL */ + 0, + IW_EV_COMPAT_CHAR_LEN, /* IW_HEADER_TYPE_CHAR */ + 0, + IW_EV_COMPAT_UINT_LEN, /* IW_HEADER_TYPE_UINT */ + IW_EV_COMPAT_FREQ_LEN, /* IW_HEADER_TYPE_FREQ */ + IW_EV_COMPAT_ADDR_LEN, /* IW_HEADER_TYPE_ADDR */ + 0, + IW_EV_COMPAT_POINT_LEN, /* Without variable payload */ + IW_EV_COMPAT_PARAM_LEN, /* IW_HEADER_TYPE_PARAM */ + IW_EV_COMPAT_QUAL_LEN, /* IW_HEADER_TYPE_QUAL */ +}; +#endif /************************ COMMON SUBROUTINES ************************/ /* @@ -455,7 +470,7 @@ static iw_handler get_handler(struct net_device *dev, unsigned int cmd) /* * Get statistics out of the driver */ -static struct iw_statistics *get_wireless_stats(struct net_device *dev) +struct iw_statistics *get_wireless_stats(struct net_device *dev) { /* New location */ if ((dev->wireless_handlers != NULL) && @@ -610,6 +625,11 @@ static void wireless_seq_printf_stats(struct seq_file *seq, { /* Get stats from the driver */ struct iw_statistics *stats = get_wireless_stats(dev); + static struct iw_statistics nullstats = {}; + + /* show device if it's wireless regardless of current stats */ + if (!stats && dev->wireless_handlers) + stats = &nullstats; if (stats) { seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " @@ -628,7 +648,9 @@ static void wireless_seq_printf_stats(struct seq_file *seq, stats->discard.nwid, stats->discard.code, stats->discard.fragment, stats->discard.retries, stats->discard.misc, stats->miss.beacon); - stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; + + if (stats != &nullstats) + stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; } } @@ -751,10 +773,13 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, essid_compat = 1; else if (IW_IS_SET(cmd) && (iwp->length != 0)) { char essid[IW_ESSID_MAX_SIZE + 1]; + unsigned int len; + len = iwp->length * descr->token_size; - err = copy_from_user(essid, iwp->pointer, - iwp->length * - descr->token_size); + if (len > IW_ESSID_MAX_SIZE) + return -EFAULT; + + err = copy_from_user(essid, iwp->pointer, len); if (err) return -EFAULT; @@ -1250,65 +1275,57 @@ int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, } #endif -/************************* EVENT PROCESSING *************************/ -/* - * Process events generated by the wireless layer or the driver. - * Most often, the event will be propagated through rtnetlink - */ +static int __net_init wext_pernet_init(struct net *net) +{ + skb_queue_head_init(&net->wext_nlevents); + return 0; +} -/* ---------------------------------------------------------------- */ -/* - * Locking... - * ---------- - * - * Thanks to Herbert Xu <herbert@gondor.apana.org.au> for fixing - * the locking issue in here and implementing this code ! - * - * The issue : wireless_send_event() is often called in interrupt context, - * while the Netlink layer can never be called in interrupt context. - * The fully formed RtNetlink events are queued, and then a tasklet is run - * to feed those to Netlink. - * The skb_queue is interrupt safe, and its lock is not held while calling - * Netlink, so there is no possibility of dealock. - * Jean II - */ +static void __net_exit wext_pernet_exit(struct net *net) +{ + skb_queue_purge(&net->wext_nlevents); +} -static struct sk_buff_head wireless_nlevent_queue; +static struct pernet_operations wext_pernet_ops = { + .init = wext_pernet_init, + .exit = wext_pernet_exit, +}; static int __init wireless_nlevent_init(void) { - skb_queue_head_init(&wireless_nlevent_queue); - return 0; + return register_pernet_subsys(&wext_pernet_ops); } subsys_initcall(wireless_nlevent_init); -static void wireless_nlevent_process(unsigned long data) +/* Process events generated by the wireless layer or the driver. */ +static void wireless_nlevent_process(struct work_struct *work) { struct sk_buff *skb; + struct net *net; + + rtnl_lock(); - while ((skb = skb_dequeue(&wireless_nlevent_queue))) - rtnl_notify(skb, &init_net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); + for_each_net(net) { + while ((skb = skb_dequeue(&net->wext_nlevents))) + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, + GFP_KERNEL); + } + + rtnl_unlock(); } -static DECLARE_TASKLET(wireless_nlevent_tasklet, wireless_nlevent_process, 0); +static DECLARE_WORK(wireless_nlevent_work, wireless_nlevent_process); -/* ---------------------------------------------------------------- */ -/* - * Fill a rtnetlink message with our event data. - * Note that we propage only the specified event and don't dump the - * current wireless config. Dumping the wireless config is far too - * expensive (for each parameter, the driver need to query the hardware). - */ -static int rtnetlink_fill_iwinfo(struct sk_buff *skb, struct net_device *dev, - int type, char *event, int event_len) +static struct nlmsghdr *rtnetlink_ifinfo_prep(struct net_device *dev, + struct sk_buff *skb) { struct ifinfomsg *r; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, 0, 0, type, sizeof(*r), 0); - if (nlh == NULL) - return -EMSGSIZE; + nlh = nlmsg_put(skb, 0, 0, RTM_NEWLINK, sizeof(*r), 0); + if (!nlh) + return NULL; r = nlmsg_data(nlh); r->ifi_family = AF_UNSPEC; @@ -1319,48 +1336,14 @@ static int rtnetlink_fill_iwinfo(struct sk_buff *skb, struct net_device *dev, r->ifi_change = 0; /* Wireless changes don't affect those flags */ NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); - /* Add the wireless events in the netlink packet */ - NLA_PUT(skb, IFLA_WIRELESS, event_len, event); - - return nlmsg_end(skb, nlh); -nla_put_failure: + return nlh; + nla_put_failure: nlmsg_cancel(skb, nlh); - return -EMSGSIZE; + return NULL; } -/* ---------------------------------------------------------------- */ -/* - * Create and broadcast and send it on the standard rtnetlink socket - * This is a pure clone rtmsg_ifinfo() in net/core/rtnetlink.c - * Andrzej Krzysztofowicz mandated that I used a IFLA_XXX field - * within a RTM_NEWLINK event. - */ -static void rtmsg_iwinfo(struct net_device *dev, char *event, int event_len) -{ - struct sk_buff *skb; - int err; - - if (!net_eq(dev_net(dev), &init_net)) - return; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); - if (!skb) - return; - - err = rtnetlink_fill_iwinfo(skb, dev, RTM_NEWLINK, event, event_len); - if (err < 0) { - WARN_ON(err == -EMSGSIZE); - kfree_skb(skb); - return; - } - - NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - skb_queue_tail(&wireless_nlevent_queue, skb); - tasklet_schedule(&wireless_nlevent_tasklet); -} - -/* ---------------------------------------------------------------- */ /* * Main event dispatcher. Called from other parts and drivers. * Send the event on the appropriate channels. @@ -1369,7 +1352,7 @@ static void rtmsg_iwinfo(struct net_device *dev, char *event, int event_len) void wireless_send_event(struct net_device * dev, unsigned int cmd, union iwreq_data * wrqu, - char * extra) + const char * extra) { const struct iw_ioctl_description * descr = NULL; int extra_len = 0; @@ -1379,6 +1362,25 @@ void wireless_send_event(struct net_device * dev, int wrqu_off = 0; /* Offset in wrqu */ /* Don't "optimise" the following variable, it will crash */ unsigned cmd_index; /* *MUST* be unsigned */ + struct sk_buff *skb; + struct nlmsghdr *nlh; + struct nlattr *nla; +#ifdef CONFIG_COMPAT + struct __compat_iw_event *compat_event; + struct compat_iw_point compat_wrqu; + struct sk_buff *compskb; +#endif + + /* + * Nothing in the kernel sends scan events with data, be safe. + * This is necessary because we cannot fix up scan event data + * for compat, due to being contained in 'extra', but normally + * applications are required to retrieve the scan data anyway + * and no data is included in the event, this codifies that + * practice. + */ + if (WARN_ON(cmd == SIOCGIWSCAN && extra)) + extra = NULL; /* Get the description of the Event */ if (cmd <= SIOCIWLAST) { @@ -1426,25 +1428,107 @@ void wireless_send_event(struct net_device * dev, hdr_len = event_type_size[descr->header_type]; event_len = hdr_len + extra_len; - /* Create temporary buffer to hold the event */ - event = kmalloc(event_len, GFP_ATOMIC); - if (event == NULL) + /* + * The problem for 64/32 bit. + * + * On 64-bit, a regular event is laid out as follows: + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | event.len | event.cmd | p a d d i n g | + * | wrqu data ... (with the correct size) | + * + * This padding exists because we manipulate event->u, + * and 'event' is not packed. + * + * An iw_point event is laid out like this instead: + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | event.len | event.cmd | p a d d i n g | + * | iwpnt.len | iwpnt.flg | p a d d i n g | + * | extra data ... + * + * The second padding exists because struct iw_point is extended, + * but this depends on the platform... + * + * On 32-bit, all the padding shouldn't be there. + */ + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!skb) + return; + + /* Send via the RtNetlink event channel */ + nlh = rtnetlink_ifinfo_prep(dev, skb); + if (WARN_ON(!nlh)) { + kfree_skb(skb); return; + } - /* Fill event */ + /* Add the wireless events in the netlink packet */ + nla = nla_reserve(skb, IFLA_WIRELESS, event_len); + if (!nla) { + kfree_skb(skb); + return; + } + event = nla_data(nla); + + /* Fill event - first clear to avoid data leaking */ + memset(event, 0, hdr_len); event->len = event_len; event->cmd = cmd; memcpy(&event->u, ((char *) wrqu) + wrqu_off, hdr_len - IW_EV_LCP_LEN); - if (extra) + if (extra_len) memcpy(((char *) event) + hdr_len, extra, extra_len); + nlmsg_end(skb, nlh); +#ifdef CONFIG_COMPAT + hdr_len = compat_event_type_size[descr->header_type]; + event_len = hdr_len + extra_len; + + compskb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!compskb) { + kfree_skb(skb); + return; + } + /* Send via the RtNetlink event channel */ - rtmsg_iwinfo(dev, (char *) event, event_len); + nlh = rtnetlink_ifinfo_prep(dev, compskb); + if (WARN_ON(!nlh)) { + kfree_skb(skb); + kfree_skb(compskb); + return; + } - /* Cleanup */ - kfree(event); + /* Add the wireless events in the netlink packet */ + nla = nla_reserve(compskb, IFLA_WIRELESS, event_len); + if (!nla) { + kfree_skb(skb); + kfree_skb(compskb); + return; + } + compat_event = nla_data(nla); - return; /* Always success, I guess ;-) */ + compat_event->len = event_len; + compat_event->cmd = cmd; + if (descr->header_type == IW_HEADER_TYPE_POINT) { + compat_wrqu.length = wrqu->data.length; + compat_wrqu.flags = wrqu->data.flags; + memcpy(&compat_event->pointer, + ((char *) &compat_wrqu) + IW_EV_COMPAT_POINT_OFF, + hdr_len - IW_EV_COMPAT_LCP_LEN); + if (extra_len) + memcpy(((char *) compat_event) + hdr_len, + extra, extra_len); + } else { + /* extra_len must be zero, so no if (extra) needed */ + memcpy(&compat_event->pointer, wrqu, + hdr_len - IW_EV_COMPAT_LCP_LEN); + } + + nlmsg_end(compskb, nlh); + + skb_shinfo(skb)->frag_list = compskb; +#endif + skb_queue_tail(&dev_net(dev)->wext_nlevents, skb); + schedule_work(&wireless_nlevent_work); } EXPORT_SYMBOL(wireless_send_event); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5e6c072c64d..7fa9c7ad3d3 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -409,7 +409,7 @@ static void x25_destroy_socket(struct sock *sk) */ static int x25_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int opt; struct sock *sk = sock->sk; diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index a2adb51849a..fef8db553e8 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, |