diff options
Diffstat (limited to 'net')
374 files changed, 16510 insertions, 7521 deletions
diff --git a/net/802/fddi.c b/net/802/fddi.c index 539e6064e6d..3ef0ab0a543 100644 --- a/net/802/fddi.c +++ b/net/802/fddi.c @@ -185,10 +185,6 @@ static const struct header_ops fddi_header_ops = { static void fddi_setup(struct net_device *dev) { dev->header_ops = &fddi_header_ops; -#ifdef CONFIG_COMPAT_NET_DEV_OPS - dev->change_mtu = fddi_change_mtu, -#endif - dev->type = ARPHRD_FDDI; dev->hard_header_len = FDDI_K_SNAP_HLEN+3; /* Assume 802.2 SNAP hdr len + 3 pad bytes */ dev->mtu = FDDI_K_SNAP_DLEN; /* Assume max payload of 802.2 SNAP frame */ diff --git a/net/802/hippi.c b/net/802/hippi.c index 313b9ebf92e..cd3e8e92952 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -193,11 +193,6 @@ static const struct header_ops hippi_header_ops = { static void hippi_setup(struct net_device *dev) { -#ifdef CONFIG_COMPAT_NET_DEV_OPS - dev->change_mtu = hippi_change_mtu; - dev->set_mac_address = hippi_mac_addr; - dev->neigh_setup = hippi_neigh_setup_dev; -#endif dev->header_ops = &hippi_header_ops; /* diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index d1e10546eb8..fe649081fbd 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -378,13 +378,13 @@ static void vlan_sync_address(struct net_device *dev, * the new address */ if (compare_ether_addr(vlandev->dev_addr, vlan->real_dev_addr) && !compare_ether_addr(vlandev->dev_addr, dev->dev_addr)) - dev_unicast_delete(dev, vlandev->dev_addr, ETH_ALEN); + dev_unicast_delete(dev, vlandev->dev_addr); /* vlan address was equal to the old address and is different from * the new address */ if (!compare_ether_addr(vlandev->dev_addr, vlan->real_dev_addr) && compare_ether_addr(vlandev->dev_addr, dev->dev_addr)) - dev_unicast_add(dev, vlandev->dev_addr, ETH_ALEN); + dev_unicast_add(dev, vlandev->dev_addr); memcpy(vlan->real_dev_addr, dev->dev_addr, ETH_ALEN); } @@ -758,7 +758,7 @@ static void __exit vlan_cleanup_module(void) BUG_ON(!hlist_empty(&vlan_group_hash[i])); unregister_pernet_gen_device(vlan_net_id, &vlan_net_ops); - synchronize_net(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_gvrp_uninit(); } diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index c67fe6f7565..7f7de1a04de 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -114,9 +114,9 @@ int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, EXPORT_SYMBOL(vlan_gro_receive); int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct napi_gro_fraginfo *info) + unsigned int vlan_tci) { - struct sk_buff *skb = napi_fraginfo_skb(napi, info); + struct sk_buff *skb = napi_frags_skb(napi); if (!skb) return NET_RX_DROP; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index b4b9068e55a..96bad8f233e 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -290,7 +290,7 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, static int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { - struct net_device_stats *stats = &dev->stats; + struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); /* Handle non-VLAN frames if they are sent to us, for example by DHCP. @@ -309,7 +309,7 @@ static int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb); skb = __vlan_put_tag(skb, vlan_tci); if (!skb) { - stats->tx_dropped++; + txq->tx_dropped++; return NETDEV_TX_OK; } @@ -317,8 +317,8 @@ static int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) vlan_dev_info(dev)->cnt_inc_headroom_on_tx++; } - stats->tx_packets++; - stats->tx_bytes += skb->len; + txq->tx_packets++; + txq->tx_bytes += skb->len; skb->dev = vlan_dev_info(dev)->real_dev; dev_queue_xmit(skb); @@ -328,15 +328,15 @@ static int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) static int vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { - struct net_device_stats *stats = &dev->stats; + struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); u16 vlan_tci; 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); - stats->tx_packets++; - stats->tx_bytes += skb->len; + txq->tx_packets++; + txq->tx_bytes += skb->len; skb->dev = vlan_dev_info(dev)->real_dev; dev_queue_xmit(skb); @@ -441,7 +441,7 @@ static int vlan_dev_open(struct net_device *dev) return -ENETDOWN; if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) { - err = dev_unicast_add(real_dev, dev->dev_addr, ETH_ALEN); + err = dev_unicast_add(real_dev, dev->dev_addr); if (err < 0) goto out; } @@ -470,7 +470,7 @@ clear_allmulti: dev_set_allmulti(real_dev, -1); del_unicast: if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) - dev_unicast_delete(real_dev, dev->dev_addr, ETH_ALEN); + dev_unicast_delete(real_dev, dev->dev_addr); out: netif_carrier_off(dev); return err; @@ -492,7 +492,7 @@ static int vlan_dev_stop(struct net_device *dev) dev_set_promiscuity(real_dev, -1); if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) - dev_unicast_delete(real_dev, dev->dev_addr, dev->addr_len); + dev_unicast_delete(real_dev, dev->dev_addr); netif_carrier_off(dev); return 0; @@ -511,13 +511,13 @@ static int vlan_dev_set_mac_address(struct net_device *dev, void *p) goto out; if (compare_ether_addr(addr->sa_data, real_dev->dev_addr)) { - err = dev_unicast_add(real_dev, addr->sa_data, ETH_ALEN); + err = dev_unicast_add(real_dev, addr->sa_data); if (err < 0) return err; } if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) - dev_unicast_delete(real_dev, dev->dev_addr, ETH_ALEN); + dev_unicast_delete(real_dev, dev->dev_addr); out: memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); @@ -644,7 +644,6 @@ static int vlan_dev_init(struct net_device *dev) dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN; dev->netdev_ops = &vlan_netdev_ops; } - netdev_resync_ops(dev); if (is_vlan_dev(real_dev)) subclass = 1; @@ -671,13 +670,7 @@ static int vlan_ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { const struct vlan_dev_info *vlan = vlan_dev_info(dev); - struct net_device *real_dev = vlan->real_dev; - - if (!real_dev->ethtool_ops || - !real_dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; - - return real_dev->ethtool_ops->get_settings(real_dev, cmd); + return dev_ethtool_get_settings(vlan->real_dev, cmd); } static void vlan_ethtool_get_drvinfo(struct net_device *dev, @@ -691,24 +684,13 @@ static void vlan_ethtool_get_drvinfo(struct net_device *dev, static u32 vlan_ethtool_get_rx_csum(struct net_device *dev) { const struct vlan_dev_info *vlan = vlan_dev_info(dev); - struct net_device *real_dev = vlan->real_dev; - - if (real_dev->ethtool_ops == NULL || - real_dev->ethtool_ops->get_rx_csum == NULL) - return 0; - return real_dev->ethtool_ops->get_rx_csum(real_dev); + return dev_ethtool_get_rx_csum(vlan->real_dev); } static u32 vlan_ethtool_get_flags(struct net_device *dev) { const struct vlan_dev_info *vlan = vlan_dev_info(dev); - struct net_device *real_dev = vlan->real_dev; - - if (!(real_dev->features & NETIF_F_HW_VLAN_RX) || - real_dev->ethtool_ops == NULL || - real_dev->ethtool_ops->get_flags == NULL) - return 0; - return real_dev->ethtool_ops->get_flags(real_dev); + return dev_ethtool_get_flags(vlan->real_dev); } static const struct ethtool_ops vlan_ethtool_ops = { @@ -756,6 +738,7 @@ void vlan_setup(struct net_device *dev) ether_setup(dev); dev->priv_flags |= IFF_802_1Q_VLAN; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->tx_queue_len = 0; dev->netdev_ops = &vlan_netdev_ops; diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 3628e0a81b4..b55a091a33d 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -279,13 +279,14 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset) { struct net_device *vlandev = (struct net_device *) seq->private; const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev); - struct net_device_stats *stats = &vlandev->stats; + const struct net_device_stats *stats; static const char fmt[] = "%30s %12lu\n"; int i; if (!is_vlan_dev(vlandev)) return 0; + stats = dev_get_stats(vlandev); seq_printf(seq, "%s VID: %d REORDER_HDR: %i dev->priv_flags: %hx\n", vlandev->name, dev_info->vlan_id, diff --git a/net/9p/client.c b/net/9p/client.c index dd43a8289b0..5bf5f227dbe 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -60,9 +60,9 @@ static struct p9_req_t * p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...); /** - * v9fs_parse_options - parse mount options into session structure - * @options: options string passed from mount - * @v9ses: existing v9fs session information + * parse_options - parse mount options into client structure + * @opts: options string passed from mount + * @clnt: existing v9fs client information * * Return 0 upon success, -ERRNO upon failure */ @@ -117,9 +117,6 @@ static int parse_opts(char *opts, struct p9_client *clnt) } } - if (!clnt->trans_mod) - clnt->trans_mod = v9fs_get_default_trans(); - kfree(options); return ret; } @@ -235,7 +232,7 @@ EXPORT_SYMBOL(p9_tag_lookup); /** * p9_tag_init - setup tags structure and contents - * @tags: tags structure from the client struct + * @c: v9fs client struct * * This initializes the tags structure for each client instance. * @@ -261,7 +258,7 @@ error: /** * p9_tag_cleanup - cleans up tags structure and reclaims resources - * @tags: tags structure from the client struct + * @c: v9fs client struct * * This frees resources associated with the tags structure * @@ -414,14 +411,9 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) if (c->dotu) err = -ecode; - if (!err) { + if (!err || !IS_ERR_VALUE(err)) err = p9_errstr2errno(ename, strlen(ename)); - /* string match failed */ - if (!err) - err = -ESERVERFAULT; - } - P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode, ename); kfree(ename); @@ -433,8 +425,8 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) /** * p9_client_flush - flush (cancel) a request - * c: client state - * req: request to cancel + * @c: client state + * @oldreq: request to cancel * * This sents a flush for a particular requests and links * the flush request to the original request. The current @@ -689,6 +681,9 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) if (err < 0) goto error; + if (!clnt->trans_mod) + clnt->trans_mod = v9fs_get_default_trans(); + if (clnt->trans_mod == NULL) { err = -EPROTONOSUPPORT; P9_DPRINTK(P9_DEBUG_ERROR, @@ -1098,7 +1093,6 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, if (data) { memmove(data, dataptr, count); - data += count; } if (udata) { @@ -1192,9 +1186,9 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) err = p9pdu_readf(req->rc, clnt->dotu, "wS", &ignored, ret); if (err) { - ret = ERR_PTR(err); p9pdu_dump(1, req->rc); - goto free_and_error; + p9_free_req(clnt, req); + goto error; } P9_DPRINTK(P9_DEBUG_9P, @@ -1211,8 +1205,6 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) p9_free_req(clnt, req); return ret; -free_and_error: - p9_free_req(clnt, req); error: kfree(ret); return ERR_PTR(err); diff --git a/net/9p/error.c b/net/9p/error.c index fdebe431406..52518512a93 100644 --- a/net/9p/error.c +++ b/net/9p/error.c @@ -239,7 +239,7 @@ int p9_errstr2errno(char *errstr, int len) errstr[len] = 0; printk(KERN_ERR "%s: server reported unknown error %s\n", __func__, errstr); - errno = 1; + errno = ESERVERFAULT; } return -errno; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index a2a1814c7a8..8d934dd7fd5 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -119,8 +119,8 @@ struct p9_poll_wait { * @wpos: write position for current frame * @wsize: amount of data to write for current frame * @wbuf: current write buffer + * @poll_pending_link: pending links to be polled per conn * @poll_wait: array of wait_q's for various worker threads - * @poll_waddr: ???? * @pt: poll state * @rq: current read work * @wq: current write work @@ -700,9 +700,9 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req) } /** - * parse_options - parse mount options into session structure - * @options: options string passed from mount - * @opts: transport-specific structure to parse options into + * parse_opts - parse mount options into p9_fd_opts structure + * @params: options string passed from mount + * @opts: fd transport-specific structure to parse options into * * Returns 0 upon success, -ERRNO upon failure */ @@ -735,12 +735,14 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) if (!*p) continue; token = match_token(p, tokens, args); - r = match_int(&args[0], &option); - if (r < 0) { - P9_DPRINTK(P9_DEBUG_ERROR, - "integer field, but no integer?\n"); - ret = r; - continue; + if (token != Opt_err) { + r = match_int(&args[0], &option); + if (r < 0) { + P9_DPRINTK(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); + ret = r; + continue; + } } switch (token) { case Opt_port: diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index ac4990041eb..65cb29db03f 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -67,14 +67,15 @@ * @pd: Protection Domain pointer * @qp: Queue Pair pointer * @cq: Completion Queue pointer + * @dm_mr: DMA Memory Region pointer * @lkey: The local access only memory region key * @timeout: Number of uSecs to wait for connection management events * @sq_depth: The depth of the Send Queue * @sq_sem: Semaphore for the SQ * @rq_depth: The depth of the Receive Queue. + * @rq_count: Count of requests in the Receive Queue. * @addr: The remote peer's address * @req_lock: Protects the active request list - * @send_wait: Wait list when the SQ fills up * @cm_done: Completion event for connection management tracking */ struct p9_trans_rdma { @@ -154,9 +155,9 @@ static match_table_t tokens = { }; /** - * parse_options - parse mount options into session structure - * @options: options string passed from mount - * @opts: transport-specific structure to parse options into + * parse_opts - parse mount options into rdma options structure + * @params: options string passed from mount + * @opts: rdma transport-specific structure to parse options into * * Returns 0 upon success, -ERRNO upon failure */ diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index bb8579a141a..9bf0b737aa5 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -57,11 +57,9 @@ static int chan_index; * @initialized: whether the channel is initialized * @inuse: whether the channel is in use * @lock: protects multiple elements within this structure + * @client: client instance * @vdev: virtio dev associated with this channel * @vq: virtio queue associated with this channel - * @tagpool: accounting for tag ids (and request slots) - * @reqs: array of request slots - * @max_tag: current number of request_slots allocated * @sg: scatter gather list which is used to pack a request (protected?) * * We keep all per-channel information in a structure. @@ -92,7 +90,7 @@ static unsigned int rest_of_page(void *data) /** * p9_virtio_close - reclaim resources of a channel - * @trans: transport state + * @client: client instance * * This reclaims a channel by freeing its resources and * reseting its inuse flag. @@ -181,9 +179,8 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req) /** * p9_virtio_request - issue a request - * @t: transport state - * @tc: &p9_fcall request to transmit - * @rc: &p9_fcall to put reponse into + * @client: client instance issuing the request + * @req: request to be issued * */ @@ -246,7 +243,7 @@ static int p9_virtio_probe(struct virtio_device *vdev) chan->vdev = vdev; /* We expect one virtqueue, for requests. */ - chan->vq = vdev->config->find_vq(vdev, 0, req_done); + chan->vq = virtio_find_single_vq(vdev, req_done, "requests"); if (IS_ERR(chan->vq)) { err = PTR_ERR(chan->vq); goto out_free_vq; @@ -261,7 +258,7 @@ static int p9_virtio_probe(struct virtio_device *vdev) return 0; out_free_vq: - vdev->config->del_vq(chan->vq); + vdev->config->del_vqs(vdev); fail: mutex_lock(&virtio_9p_lock); chan_index--; @@ -332,7 +329,7 @@ static void p9_virtio_remove(struct virtio_device *vdev) BUG_ON(chan->inuse); if (chan->initialized) { - vdev->config->del_vq(chan->vq); + vdev->config->del_vqs(vdev); chan->initialized = false; } } diff --git a/net/Kconfig b/net/Kconfig index c19f549c8e7..7051b971067 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -179,6 +179,7 @@ source "net/lapb/Kconfig" source "net/econet/Kconfig" source "net/wanrouter/Kconfig" source "net/phonet/Kconfig" +source "net/ieee802154/Kconfig" source "net/sched/Kconfig" source "net/dcb/Kconfig" diff --git a/net/Makefile b/net/Makefile index 9e00a55a901..ba324aefda7 100644 --- a/net/Makefile +++ b/net/Makefile @@ -60,6 +60,7 @@ obj-$(CONFIG_NET_9P) += 9p/ ifneq ($(CONFIG_DCB),) obj-y += dcb/ endif +obj-y += ieee802154/ ifeq ($(CONFIG_NET),y) obj-$(CONFIG_SYSCTL) += sysctl_net.o diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c index fd8e0847b25..80caad1a31a 100644 --- a/net/appletalk/atalk_proc.c +++ b/net/appletalk/atalk_proc.c @@ -204,8 +204,8 @@ static int atalk_seq_socket_show(struct seq_file *seq, void *v) "%02X %d\n", s->sk_type, ntohs(at->src_net), at->src_node, at->src_port, ntohs(at->dest_net), at->dest_node, at->dest_port, - atomic_read(&s->sk_wmem_alloc), - atomic_read(&s->sk_rmem_alloc), + sk_wmem_alloc_get(s), + sk_rmem_alloc_get(s), s->sk_state, SOCK_INODE(s->sk_socket)->i_uid); out: return 0; diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index d6a9243641a..875eda5dbad 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -54,6 +54,7 @@ #include <linux/capability.h> #include <linux/module.h> #include <linux/if_arp.h> +#include <linux/smp_lock.h> #include <linux/termios.h> /* For TIOCOUTQ/INQ */ #include <net/datalink.h> #include <net/psnap.h> @@ -162,8 +163,7 @@ static void atalk_destroy_timer(unsigned long data) { struct sock *sk = (struct sock *)data; - if (atomic_read(&sk->sk_wmem_alloc) || - atomic_read(&sk->sk_rmem_alloc)) { + if (sk_has_allocations(sk)) { sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME; add_timer(&sk->sk_timer); } else @@ -175,8 +175,7 @@ static inline void atalk_destroy_socket(struct sock *sk) atalk_remove_socket(sk); skb_queue_purge(&sk->sk_receive_queue); - if (atomic_read(&sk->sk_wmem_alloc) || - atomic_read(&sk->sk_rmem_alloc)) { + if (sk_has_allocations(sk)) { setup_timer(&sk->sk_timer, atalk_destroy_timer, (unsigned long)sk); sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME; @@ -939,6 +938,7 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, int len, unsigned long sum) { int start = skb_headlen(skb); + struct sk_buff *frag_iter; int i, copy; /* checksum stuff in header space */ @@ -977,26 +977,22 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; + skb_walk_frags(skb, frag_iter) { + int end; - WARN_ON(start > offset + len); + WARN_ON(start > offset + len); - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - sum = atalk_sum_skb(list, offset - start, - copy, sum); - if ((len -= copy) == 0) - return sum; - offset += copy; - } - start = end; + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + sum = atalk_sum_skb(frag_iter, offset - start, + copy, sum); + if ((len -= copy) == 0) + return sum; + offset += copy; } + start = end; } BUG_ON(len > 0); @@ -1242,6 +1238,7 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, return -ENOBUFS; *uaddr_len = sizeof(struct sockaddr_at); + memset(&sat.sat_zero, 0, sizeof(sat.sat_zero)); if (peer) { if (sk->sk_state != TCP_ESTABLISHED) @@ -1753,8 +1750,7 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) switch (cmd) { /* Protocol layer */ case TIOCOUTQ: { - long amount = sk->sk_sndbuf - - atomic_read(&sk->sk_wmem_alloc); + long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; diff --git a/net/appletalk/dev.c b/net/appletalk/dev.c index 72277d70c98..6c8016f6186 100644 --- a/net/appletalk/dev.c +++ b/net/appletalk/dev.c @@ -9,21 +9,10 @@ #include <linux/if_arp.h> #include <linux/if_ltalk.h> -#ifdef CONFIG_COMPAT_NET_DEV_OPS -static int ltalk_change_mtu(struct net_device *dev, int mtu) -{ - return -EINVAL; -} -#endif - static void ltalk_setup(struct net_device *dev) { /* Fill in the fields of the device structure with localtalk-generic values. */ -#ifdef CONFIG_COMPAT_NET_DEV_OPS - dev->change_mtu = ltalk_change_mtu; -#endif - dev->type = ARPHRD_LOCALTLK; dev->hard_header_len = LTALK_HLEN; dev->mtu = LTALK_MTU; diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 3100a8940af..2912665fc58 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -228,7 +228,7 @@ static int br2684_start_xmit(struct sk_buff *skb, struct net_device *dev) struct br2684_dev *brdev = BRPRIV(dev); struct br2684_vcc *brvcc; - pr_debug("br2684_start_xmit, skb->dst=%p\n", skb->dst); + pr_debug("br2684_start_xmit, skb_dst(skb)=%p\n", skb_dst(skb)); read_lock(&devs_lock); brvcc = pick_outgoing_vcc(skb, brdev); if (brvcc == NULL) { @@ -445,9 +445,10 @@ free_skb: */ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) { + struct sk_buff_head queue; int err; struct br2684_vcc *brvcc; - struct sk_buff *skb; + struct sk_buff *skb, *tmp; struct sk_buff_head *rq; struct br2684_dev *brdev; struct net_device *net_dev; @@ -505,29 +506,20 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) barrier(); atmvcc->push = br2684_push; + __skb_queue_head_init(&queue); rq = &sk_atm(atmvcc)->sk_receive_queue; spin_lock_irqsave(&rq->lock, flags); - if (skb_queue_empty(rq)) { - skb = NULL; - } else { - /* NULL terminate the list. */ - rq->prev->next = NULL; - skb = rq->next; - } - rq->prev = rq->next = (struct sk_buff *)rq; - rq->qlen = 0; + skb_queue_splice_init(rq, &queue); spin_unlock_irqrestore(&rq->lock, flags); - while (skb) { - struct sk_buff *next = skb->next; + skb_queue_walk_safe(&queue, skb, tmp) { + struct net_device *dev = skb->dev; - skb->next = skb->prev = NULL; - br2684_push(atmvcc, skb); - skb->dev->stats.rx_bytes -= skb->len; - skb->dev->stats.rx_packets--; + dev->stats.rx_bytes -= skb->len; + dev->stats.rx_packets--; - skb = next; + br2684_push(atmvcc, skb); } __module_get(THIS_MODULE); return 0; diff --git a/net/atm/clip.c b/net/atm/clip.c index 3dc0a3a42a5..e65a3b1477f 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -369,16 +369,16 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned long flags; pr_debug("clip_start_xmit (skb %p)\n", skb); - if (!skb->dst) { - printk(KERN_ERR "clip_start_xmit: skb->dst == NULL\n"); + if (!skb_dst(skb)) { + printk(KERN_ERR "clip_start_xmit: skb_dst(skb) == NULL\n"); dev_kfree_skb(skb); dev->stats.tx_dropped++; return 0; } - if (!skb->dst->neighbour) { + if (!skb_dst(skb)->neighbour) { #if 0 - skb->dst->neighbour = clip_find_neighbour(skb->dst, 1); - if (!skb->dst->neighbour) { + skb_dst(skb)->neighbour = clip_find_neighbour(skb_dst(skb), 1); + if (!skb_dst(skb)->neighbour) { dev_kfree_skb(skb); /* lost that one */ dev->stats.tx_dropped++; return 0; @@ -389,7 +389,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_dropped++; return 0; } - entry = NEIGH2ENTRY(skb->dst->neighbour); + entry = NEIGH2ENTRY(skb_dst(skb)->neighbour); if (!entry->vccs) { if (time_after(jiffies, entry->expires)) { /* should be resolved */ @@ -406,7 +406,7 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) } pr_debug("neigh %p, vccs %p\n", entry, entry->vccs); ATM_SKB(skb)->vcc = vcc = entry->vccs->vcc; - pr_debug("using neighbour %p, vcc %p\n", skb->dst->neighbour, vcc); + pr_debug("using neighbour %p, vcc %p\n", skb_dst(skb)->neighbour, vcc); if (entry->vccs->encap) { void *here; @@ -445,9 +445,9 @@ static int clip_start_xmit(struct sk_buff *skb, struct net_device *dev) static int clip_mkip(struct atm_vcc *vcc, int timeout) { + struct sk_buff_head *rq, queue; struct clip_vcc *clip_vcc; - struct sk_buff *skb; - struct sk_buff_head *rq; + struct sk_buff *skb, *tmp; unsigned long flags; if (!vcc->push) @@ -469,39 +469,28 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout) vcc->push = clip_push; vcc->pop = clip_pop; + __skb_queue_head_init(&queue); rq = &sk_atm(vcc)->sk_receive_queue; spin_lock_irqsave(&rq->lock, flags); - if (skb_queue_empty(rq)) { - skb = NULL; - } else { - /* NULL terminate the list. */ - rq->prev->next = NULL; - skb = rq->next; - } - rq->prev = rq->next = (struct sk_buff *)rq; - rq->qlen = 0; + skb_queue_splice_init(rq, &queue); spin_unlock_irqrestore(&rq->lock, flags); /* re-process everything received between connection setup and MKIP */ - while (skb) { - struct sk_buff *next = skb->next; - - skb->next = skb->prev = NULL; + skb_queue_walk_safe(&queue, skb, tmp) { if (!clip_devs) { atm_return(vcc, skb->truesize); kfree_skb(skb); } else { + struct net_device *dev = skb->dev; unsigned int len = skb->len; skb_get(skb); clip_push(vcc, skb); - skb->dev->stats.rx_packets--; - skb->dev->stats.rx_bytes -= len; + dev->stats.rx_packets--; + dev->stats.rx_bytes -= len; kfree_skb(skb); } - - skb = next; } return 0; } @@ -568,6 +557,7 @@ static void clip_setup(struct net_device *dev) /* without any more elaborate queuing. 100 is a reasonable */ /* compromise between decent burst-tolerance and protection */ /* against memory hogs. */ + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } static int clip_create(int number) diff --git a/net/atm/common.c b/net/atm/common.c index d34edbe754c..8c4d843eb17 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -62,15 +62,15 @@ static struct sk_buff *alloc_tx(struct atm_vcc *vcc,unsigned int size) struct sk_buff *skb; struct sock *sk = sk_atm(vcc); - if (atomic_read(&sk->sk_wmem_alloc) && !atm_may_send(vcc, size)) { + if (sk_wmem_alloc_get(sk) && !atm_may_send(vcc, size)) { pr_debug("Sorry: wmem_alloc = %d, size = %d, sndbuf = %d\n", - atomic_read(&sk->sk_wmem_alloc), size, + sk_wmem_alloc_get(sk), size, sk->sk_sndbuf); return NULL; } - while (!(skb = alloc_skb(size,GFP_KERNEL))) schedule(); - pr_debug("AlTx %d += %d\n", atomic_read(&sk->sk_wmem_alloc), - skb->truesize); + while (!(skb = alloc_skb(size, GFP_KERNEL))) + schedule(); + pr_debug("AlTx %d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); atomic_add(skb->truesize, &sk->sk_wmem_alloc); return skb; } @@ -92,7 +92,7 @@ static void vcc_sock_destruct(struct sock *sk) static void vcc_def_wakeup(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up(sk->sk_sleep); read_unlock(&sk->sk_callback_lock); } @@ -110,7 +110,7 @@ static void vcc_write_space(struct sock *sk) read_lock(&sk->sk_callback_lock); if (vcc_writable(sk)) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible(sk->sk_sleep); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); @@ -145,7 +145,7 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family) memset(&vcc->local,0,sizeof(struct sockaddr_atmsvc)); memset(&vcc->remote,0,sizeof(struct sockaddr_atmsvc)); vcc->qos.txtp.max_sdu = 1 << 16; /* for meta VCs */ - atomic_set(&sk->sk_wmem_alloc, 0); + atomic_set(&sk->sk_wmem_alloc, 1); atomic_set(&sk->sk_rmem_alloc, 0); vcc->push = NULL; vcc->pop = NULL; @@ -594,7 +594,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait) struct atm_vcc *vcc; unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; vcc = ATM_SD(sock); diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 76ed3c8d26e..4da8892ced5 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -63,8 +63,7 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg error = -EINVAL; goto done; } - error = put_user(sk->sk_sndbuf - - atomic_read(&sk->sk_wmem_alloc), + error = put_user(sk->sk_sndbuf - sk_wmem_alloc_get(sk), (int __user *) argp) ? -EFAULT : 0; goto done; case SIOCINQ: diff --git a/net/atm/lec.c b/net/atm/lec.c index 199b6bb79f4..ff2e594dca9 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -34,7 +34,6 @@ /* Proxy LEC knows about bridging */ #if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) -#include <linux/if_bridge.h> #include "../bridge/br_private.h" static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 }; @@ -271,7 +270,8 @@ static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev) printk("%s:No lecd attached\n", dev->name); dev->stats.tx_errors++; netif_stop_queue(dev); - return -EUNATCH; + kfree_skb(skb); + return NETDEV_TX_OK; } pr_debug("skbuff head:%lx data:%lx tail:%lx end:%lx\n", @@ -518,18 +518,14 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) case l_should_bridge: #if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) { - struct net_bridge_fdb_entry *f; - pr_debug("%s: bridge zeppelin asks about %pM\n", dev->name, mesg->content.proxy.mac_addr); - if (br_fdb_get_hook == NULL || dev->br_port == NULL) + if (br_fdb_test_addr_hook == NULL) break; - f = br_fdb_get_hook(dev->br_port->br, - mesg->content.proxy.mac_addr); - if (f != NULL && f->dst->dev != dev - && f->dst->state == BR_STATE_FORWARDING) { + if (br_fdb_test_addr_hook(dev, + mesg->content.proxy.mac_addr)) { /* hit from bridge table, send LE_ARP_RESPONSE */ struct sk_buff *skb2; struct sock *sk; @@ -540,10 +536,8 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) skb2 = alloc_skb(sizeof(struct atmlec_msg), GFP_ATOMIC); - if (skb2 == NULL) { - br_fdb_put_hook(f); + if (skb2 == NULL) break; - } skb2->len = sizeof(struct atmlec_msg); skb_copy_to_linear_data(skb2, mesg, sizeof(*mesg)); @@ -552,8 +546,6 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) skb_queue_tail(&sk->sk_receive_queue, skb2); sk->sk_data_ready(sk, skb2->len); } - if (f != NULL) - br_fdb_put_hook(f); } #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ break; diff --git a/net/atm/proc.c b/net/atm/proc.c index e7b3b273907..38de5ff61ec 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -204,8 +204,8 @@ static void vcc_info(struct seq_file *seq, struct atm_vcc *vcc) seq_printf(seq, "%3d", sk->sk_family); } seq_printf(seq, " %04lx %5d %7d/%7d %7d/%7d [%d]\n", vcc->flags, sk->sk_err, - atomic_read(&sk->sk_wmem_alloc), sk->sk_sndbuf, - atomic_read(&sk->sk_rmem_alloc), sk->sk_rcvbuf, + sk_wmem_alloc_get(sk), sk->sk_sndbuf, + sk_rmem_alloc_get(sk), sk->sk_rcvbuf, atomic_read(&sk->sk_refcnt)); } diff --git a/net/atm/raw.c b/net/atm/raw.c index b0a2d8cb674..cbfcc71a17b 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -33,7 +33,7 @@ static void atm_pop_raw(struct atm_vcc *vcc,struct sk_buff *skb) struct sock *sk = sk_atm(vcc); pr_debug("APopR (%d) %d -= %d\n", vcc->vci, - atomic_read(&sk->sk_wmem_alloc), skb->truesize); + sk_wmem_alloc_get(sk), skb->truesize); atomic_sub(skb->truesize, &sk->sk_wmem_alloc); dev_kfree_skb_any(skb); sk->sk_write_space(sk); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index fd9d06f291d..da0f64f82b5 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -330,8 +330,7 @@ void ax25_destroy_socket(ax25_cb *ax25) } if (ax25->sk != NULL) { - if (atomic_read(&ax25->sk->sk_wmem_alloc) || - atomic_read(&ax25->sk->sk_rmem_alloc)) { + if (sk_has_allocations(ax25->sk)) { /* Defer: outstanding buffers */ setup_timer(&ax25->dtimer, ax25_destroy_timer, (unsigned long)ax25); @@ -1691,7 +1690,8 @@ static int ax25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) switch (cmd) { case TIOCOUTQ: { long amount; - amount = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + + amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; res = put_user(amount, (int __user *)argp); @@ -1781,8 +1781,8 @@ 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 = atomic_read(&sk->sk_rmem_alloc); - ax25_info.snd_q = atomic_read(&sk->sk_wmem_alloc); + ax25_info.rcv_q = sk_wmem_alloc_get(sk); + ax25_info.snd_q = sk_rmem_alloc_get(sk); ax25_info.vs = ax25->vs; ax25_info.vr = ax25->vr; ax25_info.va = ax25->va; @@ -1922,8 +1922,8 @@ static int ax25_info_show(struct seq_file *seq, void *v) if (ax25->sk != NULL) { seq_printf(seq, " %d %d %lu\n", - atomic_read(&ax25->sk->sk_wmem_alloc), - atomic_read(&ax25->sk->sk_rmem_alloc), + sk_wmem_alloc_get(ax25->sk), + sk_rmem_alloc_get(ax25->sk), sock_i_ino(ax25->sk)); } else { seq_puts(seq, " * * *\n"); diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c index 5f1d2107a1d..de56d3983de 100644 --- a/net/ax25/ax25_in.c +++ b/net/ax25/ax25_in.c @@ -437,8 +437,7 @@ free: int ax25_kiss_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { - skb->sk = NULL; /* Initially we don't know who it's for */ - skb->destructor = NULL; /* Who initializes this, dammit?! */ + skb_orphan(skb); if (!net_eq(dev_net(dev), &init_net)) { kfree_skb(skb); diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 7725da95a76..59fdb1d2e8e 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -3,8 +3,9 @@ # menuconfig BT - depends on NET && !S390 tristate "Bluetooth subsystem support" + depends on NET && !S390 + depends on RFKILL || !RFKILL help Bluetooth is low-cost, low-power, short-range wireless technology. It was designed as a replacement for cables and other short-range diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 02b9baa1930..0250e060015 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -337,7 +337,7 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (sk->sk_state == BT_LISTEN) return -EINVAL; - amount = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; err = put_user(amount, (int __user *) arg); diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index 78958c0f9a4..97f8d68d574 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -382,7 +382,7 @@ static void cmtp_reset_ctr(struct capi_ctr *ctrl) BT_DBG("ctrl %p", ctrl); - capi_ctr_reseted(ctrl); + capi_ctr_down(ctrl); atomic_inc(&session->terminate); cmtp_schedule(session); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index cd061510b6b..406ad07cdea 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -39,6 +39,7 @@ #include <linux/skbuff.h> #include <linux/interrupt.h> #include <linux/notifier.h> +#include <linux/rfkill.h> #include <net/sock.h> #include <asm/system.h> @@ -476,6 +477,11 @@ int hci_dev_open(__u16 dev) hci_req_lock(hdev); + if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) { + ret = -ERFKILL; + goto done; + } + if (test_bit(HCI_UP, &hdev->flags)) { ret = -EALREADY; goto done; @@ -813,6 +819,24 @@ int hci_get_dev_info(void __user *arg) /* ---- Interface to HCI drivers ---- */ +static int hci_rfkill_set_block(void *data, bool blocked) +{ + struct hci_dev *hdev = data; + + BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); + + if (!blocked) + return 0; + + hci_dev_do_close(hdev); + + return 0; +} + +static const struct rfkill_ops hci_rfkill_ops = { + .set_block = hci_rfkill_set_block, +}; + /* Alloc HCI device */ struct hci_dev *hci_alloc_dev(void) { @@ -844,7 +868,8 @@ int hci_register_dev(struct hci_dev *hdev) struct list_head *head = &hci_dev_list, *p; int i, id = 0; - BT_DBG("%p name %s type %d owner %p", hdev, hdev->name, hdev->type, hdev->owner); + BT_DBG("%p name %s type %d owner %p", hdev, hdev->name, + hdev->type, hdev->owner); if (!hdev->open || !hdev->close || !hdev->destruct) return -EINVAL; @@ -900,6 +925,15 @@ int hci_register_dev(struct hci_dev *hdev) hci_register_sysfs(hdev); + hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, + RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, hdev); + if (hdev->rfkill) { + if (rfkill_register(hdev->rfkill) < 0) { + rfkill_destroy(hdev->rfkill); + hdev->rfkill = NULL; + } + } + hci_notify(hdev, HCI_DEV_REG); return id; @@ -924,6 +958,11 @@ int hci_unregister_dev(struct hci_dev *hdev) hci_notify(hdev, HCI_DEV_UNREG); + if (hdev->rfkill) { + rfkill_unregister(hdev->rfkill); + rfkill_destroy(hdev->rfkill); + } + hci_unregister_sysfs(hdev); __hci_dev_put(hdev); diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index ca4d3b40d5c..bd0a4c1bced 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -40,10 +40,10 @@ #include <linux/skbuff.h> #include <linux/list.h> #include <linux/device.h> +#include <linux/uaccess.h> #include <net/sock.h> #include <asm/system.h> -#include <asm/uaccess.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -52,7 +52,7 @@ #define VERSION "2.13" -static u32 l2cap_feat_mask = 0x0080; +static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN; static u8 l2cap_fixed_chan[8] = { 0x02, }; static const struct proto_ops l2cap_sock_ops; @@ -134,7 +134,8 @@ static inline struct sock *l2cap_get_chan_by_scid(struct l2cap_chan_list *l, u16 struct sock *s; read_lock(&l->lock); s = __l2cap_get_chan_by_scid(l, cid); - if (s) bh_lock_sock(s); + if (s) + bh_lock_sock(s); read_unlock(&l->lock); return s; } @@ -154,17 +155,18 @@ static inline struct sock *l2cap_get_chan_by_ident(struct l2cap_chan_list *l, u8 struct sock *s; read_lock(&l->lock); s = __l2cap_get_chan_by_ident(l, ident); - if (s) bh_lock_sock(s); + if (s) + bh_lock_sock(s); read_unlock(&l->lock); return s; } static u16 l2cap_alloc_cid(struct l2cap_chan_list *l) { - u16 cid = 0x0040; + u16 cid = L2CAP_CID_DYN_START; - for (; cid < 0xffff; cid++) { - if(!__l2cap_get_chan_by_scid(l, cid)) + for (; cid < L2CAP_CID_DYN_END; cid++) { + if (!__l2cap_get_chan_by_scid(l, cid)) return cid; } @@ -204,7 +206,8 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct sock *sk, struct so { struct l2cap_chan_list *l = &conn->chan_list; - BT_DBG("conn %p, psm 0x%2.2x, dcid 0x%4.4x", conn, l2cap_pi(sk)->psm, l2cap_pi(sk)->dcid); + BT_DBG("conn %p, psm 0x%2.2x, dcid 0x%4.4x", conn, + l2cap_pi(sk)->psm, l2cap_pi(sk)->dcid); conn->disc_reason = 0x13; @@ -215,13 +218,13 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct sock *sk, struct so l2cap_pi(sk)->scid = l2cap_alloc_cid(l); } else if (sk->sk_type == SOCK_DGRAM) { /* Connectionless socket */ - l2cap_pi(sk)->scid = 0x0002; - l2cap_pi(sk)->dcid = 0x0002; + l2cap_pi(sk)->scid = L2CAP_CID_CONN_LESS; + l2cap_pi(sk)->dcid = L2CAP_CID_CONN_LESS; l2cap_pi(sk)->omtu = L2CAP_DEFAULT_MTU; } else { /* Raw socket can send/recv signalling messages only */ - l2cap_pi(sk)->scid = 0x0001; - l2cap_pi(sk)->dcid = 0x0001; + l2cap_pi(sk)->scid = L2CAP_CID_SIGNALING; + l2cap_pi(sk)->dcid = L2CAP_CID_SIGNALING; l2cap_pi(sk)->omtu = L2CAP_DEFAULT_MTU; } @@ -272,7 +275,7 @@ static inline int l2cap_check_security(struct sock *sk) if (l2cap_pi(sk)->sec_level == BT_SECURITY_HIGH) auth_type = HCI_AT_NO_BONDING_MITM; else - auth_type = HCI_AT_NO_BONDING; + auth_type = HCI_AT_NO_BONDING; if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW) l2cap_pi(sk)->sec_level = BT_SECURITY_SDP; @@ -588,7 +591,8 @@ static inline struct sock *l2cap_get_sock_by_psm(int state, __le16 psm, bdaddr_t struct sock *s; read_lock(&l2cap_sk_list.lock); s = __l2cap_get_sock_by_psm(state, psm, src); - if (s) bh_lock_sock(s); + if (s) + bh_lock_sock(s); read_unlock(&l2cap_sk_list.lock); return s; } @@ -808,7 +812,7 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) goto done; } - if (la.l2_psm && btohs(la.l2_psm) < 0x1001 && + if (la.l2_psm && __le16_to_cpu(la.l2_psm) < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) { err = -EACCES; goto done; @@ -825,7 +829,8 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) l2cap_pi(sk)->sport = la.l2_psm; sk->sk_state = BT_BOUND; - if (btohs(la.l2_psm) == 0x0001 || btohs(la.l2_psm) == 0x0003) + if (__le16_to_cpu(la.l2_psm) == 0x0001 || + __le16_to_cpu(la.l2_psm) == 0x0003) l2cap_pi(sk)->sec_level = BT_SECURITY_SDP; } @@ -844,12 +849,13 @@ static int l2cap_do_connect(struct sock *sk) struct hci_conn *hcon; struct hci_dev *hdev; __u8 auth_type; - int err = 0; + int err; BT_DBG("%s -> %s psm 0x%2.2x", batostr(src), batostr(dst), l2cap_pi(sk)->psm); - if (!(hdev = hci_get_route(dst, src))) + hdev = hci_get_route(dst, src); + if (!hdev) return -EHOSTUNREACH; hci_dev_lock_bh(hdev); @@ -950,7 +956,7 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al goto done; } - switch(sk->sk_state) { + switch (sk->sk_state) { case BT_CONNECT: case BT_CONNECT2: case BT_CONFIG: @@ -975,7 +981,8 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al bacpy(&bt_sk(sk)->dst, &la.l2_bdaddr); l2cap_pi(sk)->psm = la.l2_psm; - if ((err = l2cap_do_connect(sk))) + err = l2cap_do_connect(sk); + if (err) goto done; wait: @@ -1009,9 +1016,9 @@ static int l2cap_sock_listen(struct socket *sock, int backlog) write_lock_bh(&l2cap_sk_list.lock); for (psm = 0x1001; psm < 0x1100; psm += 2) - if (!__l2cap_get_sock_by_addr(htobs(psm), src)) { - l2cap_pi(sk)->psm = htobs(psm); - l2cap_pi(sk)->sport = htobs(psm); + if (!__l2cap_get_sock_by_addr(cpu_to_le16(psm), src)) { + l2cap_pi(sk)->psm = cpu_to_le16(psm); + l2cap_pi(sk)->sport = cpu_to_le16(psm); err = 0; break; } @@ -1100,11 +1107,11 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *l if (peer) { la->l2_psm = l2cap_pi(sk)->psm; bacpy(&la->l2_bdaddr, &bt_sk(sk)->dst); - la->l2_cid = htobs(l2cap_pi(sk)->dcid); + la->l2_cid = cpu_to_le16(l2cap_pi(sk)->dcid); } else { la->l2_psm = l2cap_pi(sk)->sport; bacpy(&la->l2_bdaddr, &bt_sk(sk)->src); - la->l2_cid = htobs(l2cap_pi(sk)->scid); + la->l2_cid = cpu_to_le16(l2cap_pi(sk)->scid); } return 0; @@ -1114,7 +1121,7 @@ static inline int l2cap_do_send(struct sock *sk, struct msghdr *msg, int len) { struct l2cap_conn *conn = l2cap_pi(sk)->conn; struct sk_buff *skb, **frag; - int err, hlen, count, sent=0; + int err, hlen, count, sent = 0; struct l2cap_hdr *lh; BT_DBG("sk %p len %d", sk, len); @@ -1167,8 +1174,8 @@ static inline int l2cap_do_send(struct sock *sk, struct msghdr *msg, int len) frag = &(*frag)->next; } - - if ((err = hci_send_acl(conn->hcon, skb, 0)) < 0) + err = hci_send_acl(conn->hcon, skb, 0); + if (err < 0) goto fail; return sent; @@ -1556,7 +1563,7 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) { struct l2cap_chan_list *l = &conn->chan_list; struct sk_buff *nskb; - struct sock * sk; + struct sock *sk; BT_DBG("conn %p", conn); @@ -1568,8 +1575,8 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) /* Don't send frame to the socket it came from */ if (skb->sk == sk) continue; - - if (!(nskb = skb_clone(skb, GFP_ATOMIC))) + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) continue; if (sock_queue_rcv_skb(sk, nskb)) @@ -1587,7 +1594,8 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, struct l2cap_hdr *lh; int len, count; - BT_DBG("conn %p, code 0x%2.2x, ident 0x%2.2x, len %d", conn, code, ident, dlen); + BT_DBG("conn %p, code 0x%2.2x, ident 0x%2.2x, len %d", + conn, code, ident, dlen); len = L2CAP_HDR_SIZE + L2CAP_CMD_HDR_SIZE + dlen; count = min_t(unsigned int, conn->mtu, len); @@ -1598,7 +1606,7 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); lh->len = cpu_to_le16(L2CAP_CMD_HDR_SIZE + dlen); - lh->cid = cpu_to_le16(0x0001); + lh->cid = cpu_to_le16(L2CAP_CID_SIGNALING); cmd = (struct l2cap_cmd_hdr *) skb_put(skb, L2CAP_CMD_HDR_SIZE); cmd->code = code; @@ -1739,8 +1747,8 @@ static int l2cap_parse_conf_req(struct sock *sk, void *data) while (len >= L2CAP_CONF_OPT_SIZE) { len -= l2cap_get_conf_opt(&req, &type, &olen, &val); - hint = type & 0x80; - type &= 0x7f; + hint = type & L2CAP_CONF_HINT; + type &= L2CAP_CONF_MASK; switch (type) { case L2CAP_CONF_MTU: @@ -1966,10 +1974,12 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd BT_DBG("dcid 0x%4.4x scid 0x%4.4x result 0x%2.2x status 0x%2.2x", dcid, scid, result, status); if (scid) { - if (!(sk = l2cap_get_chan_by_scid(&conn->chan_list, scid))) + sk = l2cap_get_chan_by_scid(&conn->chan_list, scid); + if (!sk) return 0; } else { - if (!(sk = l2cap_get_chan_by_ident(&conn->chan_list, cmd->ident))) + sk = l2cap_get_chan_by_ident(&conn->chan_list, cmd->ident); + if (!sk) return 0; } @@ -2012,7 +2022,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr BT_DBG("dcid 0x%4.4x flags 0x%2.2x", dcid, flags); - if (!(sk = l2cap_get_chan_by_scid(&conn->chan_list, dcid))) + sk = l2cap_get_chan_by_scid(&conn->chan_list, dcid); + if (!sk) return -ENOENT; if (sk->sk_state == BT_DISCONN) @@ -2079,9 +2090,11 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr flags = __le16_to_cpu(rsp->flags); result = __le16_to_cpu(rsp->result); - BT_DBG("scid 0x%4.4x flags 0x%2.2x result 0x%2.2x", scid, flags, result); + BT_DBG("scid 0x%4.4x flags 0x%2.2x result 0x%2.2x", + scid, flags, result); - if (!(sk = l2cap_get_chan_by_scid(&conn->chan_list, scid))) + sk = l2cap_get_chan_by_scid(&conn->chan_list, scid); + if (!sk) return 0; switch (result) { @@ -2142,7 +2155,8 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid); - if (!(sk = l2cap_get_chan_by_scid(&conn->chan_list, dcid))) + sk = l2cap_get_chan_by_scid(&conn->chan_list, dcid); + if (!sk) return 0; rsp.dcid = cpu_to_le16(l2cap_pi(sk)->scid); @@ -2169,7 +2183,8 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid); - if (!(sk = l2cap_get_chan_by_scid(&conn->chan_list, scid))) + sk = l2cap_get_chan_by_scid(&conn->chan_list, scid); + if (!sk) return 0; l2cap_chan_del(sk, 0); @@ -2230,7 +2245,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm if (type == L2CAP_IT_FEAT_MASK) { conn->feat_mask = get_unaligned_le32(rsp->data); - if (conn->feat_mask & 0x0080) { + if (conn->feat_mask & L2CAP_FEAT_FIXED_CHAN) { struct l2cap_info_req req; req.type = cpu_to_le16(L2CAP_IT_FIXED_CHAN); @@ -2403,7 +2418,8 @@ drop: kfree_skb(skb); done: - if (sk) bh_unlock_sock(sk); + if (sk) + bh_unlock_sock(sk); return 0; } @@ -2420,11 +2436,11 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("len %d, cid 0x%4.4x", len, cid); switch (cid) { - case 0x0001: + case L2CAP_CID_SIGNALING: l2cap_sig_channel(conn, skb); break; - case 0x0002: + case L2CAP_CID_CONN_LESS: psm = get_unaligned((__le16 *) skb->data); skb_pull(skb, 2); l2cap_conless_channel(conn, psm, skb); @@ -2650,7 +2666,8 @@ static int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 fl } /* Allocate skb for the complete frame (with header) */ - if (!(conn->rx_skb = bt_skb_alloc(len, GFP_ATOMIC))) + conn->rx_skb = bt_skb_alloc(len, GFP_ATOMIC); + if (!conn->rx_skb) goto drop; skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), @@ -2704,13 +2721,13 @@ static ssize_t l2cap_sysfs_show(struct class *dev, char *buf) str += sprintf(str, "%s %s %d %d 0x%4.4x 0x%4.4x %d %d %d\n", batostr(&bt_sk(sk)->src), batostr(&bt_sk(sk)->dst), - sk->sk_state, btohs(pi->psm), pi->scid, pi->dcid, - pi->imtu, pi->omtu, pi->sec_level); + sk->sk_state, __le16_to_cpu(pi->psm), pi->scid, + pi->dcid, pi->imtu, pi->omtu, pi->sec_level); } read_unlock_bh(&l2cap_sk_list.lock); - return (str - buf); + return str - buf; } static CLASS_ATTR(l2cap, S_IRUGO, l2cap_sysfs_show, NULL); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 374536e050a..94b3388c188 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -679,7 +679,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst bacpy(&addr.l2_bdaddr, dst); addr.l2_family = AF_BLUETOOTH; - addr.l2_psm = htobs(RFCOMM_PSM); + addr.l2_psm = cpu_to_le16(RFCOMM_PSM); addr.l2_cid = 0; *err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK); if (*err == 0 || *err == -EINPROGRESS) @@ -852,9 +852,9 @@ static int rfcomm_send_pn(struct rfcomm_session *s, int cr, struct rfcomm_dlc *d } if (cr && channel_mtu >= 0) - pn->mtu = htobs(channel_mtu); + pn->mtu = cpu_to_le16(channel_mtu); else - pn->mtu = htobs(d->mtu); + pn->mtu = cpu_to_le16(d->mtu); *ptr = __fcs(buf); ptr++; @@ -1056,7 +1056,7 @@ static void rfcomm_make_uih(struct sk_buff *skb, u8 addr) if (len > 127) { hdr = (void *) skb_push(skb, 4); - put_unaligned(htobs(__len16(len)), (__le16 *) &hdr->len); + put_unaligned(cpu_to_le16(__len16(len)), (__le16 *) &hdr->len); } else { hdr = (void *) skb_push(skb, 3); hdr->len = __len8(len); @@ -1289,7 +1289,7 @@ static int rfcomm_apply_pn(struct rfcomm_dlc *d, int cr, struct rfcomm_pn *pn) d->priority = pn->priority; - d->mtu = btohs(pn->mtu); + d->mtu = __le16_to_cpu(pn->mtu); if (cr && d->mtu > s->mtu) d->mtu = s->mtu; @@ -1922,7 +1922,7 @@ static int rfcomm_add_listener(bdaddr_t *ba) /* Bind socket */ bacpy(&addr.l2_bdaddr, ba); addr.l2_family = AF_BLUETOOTH; - addr.l2_psm = htobs(RFCOMM_PSM); + addr.l2_psm = cpu_to_le16(RFCOMM_PSM); addr.l2_cid = 0; err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr)); if (err < 0) { @@ -2080,28 +2080,41 @@ static CLASS_ATTR(rfcomm_dlc, S_IRUGO, rfcomm_dlc_sysfs_show, NULL); /* ---- Initialization ---- */ static int __init rfcomm_init(void) { + int ret; + l2cap_load(); hci_register_cb(&rfcomm_cb); rfcomm_thread = kthread_run(rfcomm_run, NULL, "krfcommd"); if (IS_ERR(rfcomm_thread)) { - hci_unregister_cb(&rfcomm_cb); - return PTR_ERR(rfcomm_thread); + ret = PTR_ERR(rfcomm_thread); + goto out_thread; } if (class_create_file(bt_class, &class_attr_rfcomm_dlc) < 0) BT_ERR("Failed to create RFCOMM info file"); - rfcomm_init_sockets(); + ret = rfcomm_init_ttys(); + if (ret) + goto out_tty; -#ifdef CONFIG_BT_RFCOMM_TTY - rfcomm_init_ttys(); -#endif + ret = rfcomm_init_sockets(); + if (ret) + goto out_sock; BT_INFO("RFCOMM ver %s", VERSION); return 0; + +out_sock: + rfcomm_cleanup_ttys(); +out_tty: + kthread_stop(rfcomm_thread); +out_thread: + hci_unregister_cb(&rfcomm_cb); + + return ret; } static void __exit rfcomm_exit(void) @@ -2112,9 +2125,7 @@ static void __exit rfcomm_exit(void) kthread_stop(rfcomm_thread); -#ifdef CONFIG_BT_RFCOMM_TTY rfcomm_cleanup_ttys(); -#endif rfcomm_cleanup_sockets(); } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 7f482784e9f..0b85e811685 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -1132,7 +1132,7 @@ error: return err; } -void __exit rfcomm_cleanup_sockets(void) +void rfcomm_cleanup_sockets(void) { class_remove_file(bt_class, &class_attr_rfcomm); diff --git a/net/bridge/br.c b/net/bridge/br.c index 4d2c1f1cb52..e1241c76239 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -65,8 +65,9 @@ static int __init br_init(void) brioctl_set(br_ioctl_deviceless_stub); br_handle_frame_hook = br_handle_frame; - br_fdb_get_hook = br_fdb_get; - br_fdb_put_hook = br_fdb_put; +#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) + br_fdb_test_addr_hook = br_fdb_test_addr; +#endif return 0; err_out4: @@ -92,11 +93,12 @@ static void __exit br_deinit(void) unregister_pernet_subsys(&br_net_ops); - synchronize_net(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ br_netfilter_fini(); - br_fdb_get_hook = NULL; - br_fdb_put_hook = NULL; +#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) + br_fdb_test_addr_hook = NULL; +#endif br_handle_frame_hook = NULL; br_fdb_fini(); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index a48f5efdb6b..57bf05c353b 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -71,10 +71,17 @@ static inline int br_mac_hash(const unsigned char *mac) return jhash_1word(key, fdb_salt) & (BR_HASH_SIZE - 1); } +static void fdb_rcu_free(struct rcu_head *head) +{ + struct net_bridge_fdb_entry *ent + = container_of(head, struct net_bridge_fdb_entry, rcu); + kmem_cache_free(br_fdb_cache, ent); +} + static inline void fdb_delete(struct net_bridge_fdb_entry *f) { hlist_del_rcu(&f->hlist); - br_fdb_put(f); + call_rcu(&f->rcu, fdb_rcu_free); } void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) @@ -226,33 +233,26 @@ struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, return NULL; } -/* Interface used by ATM hook that keeps a ref count */ -struct net_bridge_fdb_entry *br_fdb_get(struct net_bridge *br, - unsigned char *addr) +#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +/* Interface used by ATM LANE hook to test + * if an addr is on some other bridge port */ +int br_fdb_test_addr(struct net_device *dev, unsigned char *addr) { struct net_bridge_fdb_entry *fdb; + int ret; + + if (!dev->br_port) + return 0; rcu_read_lock(); - fdb = __br_fdb_get(br, addr); - if (fdb && !atomic_inc_not_zero(&fdb->use_count)) - fdb = NULL; + fdb = __br_fdb_get(dev->br_port->br, addr); + ret = fdb && fdb->dst->dev != dev && + fdb->dst->state == BR_STATE_FORWARDING; rcu_read_unlock(); - return fdb; -} - -static void fdb_rcu_free(struct rcu_head *head) -{ - struct net_bridge_fdb_entry *ent - = container_of(head, struct net_bridge_fdb_entry, rcu); - kmem_cache_free(br_fdb_cache, ent); -} -/* Set entry up for deletion with RCU */ -void br_fdb_put(struct net_bridge_fdb_entry *ent) -{ - if (atomic_dec_and_test(&ent->use_count)) - call_rcu(&ent->rcu, fdb_rcu_free); + return ret; } +#endif /* CONFIG_ATM_LANE */ /* * Fill buffer with forwarding table records in @@ -326,7 +326,6 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC); if (fdb) { memcpy(fdb->addr.addr, addr, ETH_ALEN); - atomic_set(&fdb->use_count, 1); hlist_add_head_rcu(&fdb->hlist, head); fdb->dst = source; @@ -398,7 +397,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, if (unlikely(fdb->is_local)) { if (net_ratelimit()) printk(KERN_WARNING "%s: received packet with " - " own address as source address\n", + "own address as source address\n", source->dev->name); } else { /* fastpath: update of existing entry */ diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 8a96672e2c5..eb404dc3ed6 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -424,7 +424,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) err2: br_fdb_delete_by_port(br, p, 1); err1: - kobject_del(&p->kobj); + kobject_put(&p->kobj); err0: dev_set_promiscuity(dev, -1); put_back: diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index e4a418fcb35..d22f611e400 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -228,6 +228,7 @@ int nf_bridge_copy_header(struct sk_buff *skb) static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct rtable *rt; if (nf_bridge->mask & BRNF_PKT_TYPE) { skb->pkt_type = PACKET_OTHERHOST; @@ -235,12 +236,13 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - skb->rtable = bridge_parent_rtable(nf_bridge->physindev); - if (!skb->rtable) { + rt = bridge_parent_rtable(nf_bridge->physindev); + if (!rt) { kfree_skb(skb); return 0; } - dst_hold(&skb->rtable->u.dst); + dst_hold(&rt->u.dst); + skb_dst_set(skb, &rt->u.dst); skb->dev = nf_bridge->physindev; nf_bridge_push_encap_header(skb); @@ -320,7 +322,7 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) skb->dev = bridge_parent(skb->dev); if (skb->dev) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); nf_bridge_pull_encap_header(skb); @@ -338,6 +340,7 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) struct net_device *dev = skb->dev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct rtable *rt; int err; if (nf_bridge->mask & BRNF_PKT_TYPE) { @@ -347,7 +350,6 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; if (dnat_took_place(skb)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { - struct rtable *rt; struct flowi fl = { .nl_u = { .ip4_u = { @@ -373,7 +375,7 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ if (((struct dst_entry *)rt)->dev == dev) { - skb->dst = (struct dst_entry *)rt; + skb_dst_set(skb, (struct dst_entry *)rt); goto bridged_dnat; } /* we are sure that forwarding is disabled, so printing @@ -387,7 +389,7 @@ free_skb: kfree_skb(skb); return 0; } else { - if (skb->dst->dev == dev) { + if (skb_dst(skb)->dev == dev) { bridged_dnat: /* Tell br_nf_local_out this is a * bridged frame */ @@ -404,12 +406,13 @@ bridged_dnat: skb->pkt_type = PACKET_HOST; } } else { - skb->rtable = bridge_parent_rtable(nf_bridge->physindev); - if (!skb->rtable) { + rt = bridge_parent_rtable(nf_bridge->physindev); + if (!rt) { kfree_skb(skb); return 0; } - dst_hold(&skb->rtable->u.dst); + dst_hold(&rt->u.dst); + skb_dst_set(skb, &rt->u.dst); } skb->dev = nf_bridge->physindev; @@ -628,10 +631,10 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (skb->rtable && skb->rtable == bridge_parent_rtable(in)) { - dst_release(&skb->rtable->u.dst); - skb->rtable = NULL; - } + struct rtable *rt = skb_rtable(skb); + + if (rt && rt == bridge_parent_rtable(in)) + skb_dst_drop(skb); return NF_ACCEPT; } @@ -846,7 +849,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, return NF_ACCEPT; #ifdef CONFIG_NETFILTER_DEBUG - if (skb->dst == NULL) { + if (skb_dst(skb) == NULL) { printk(KERN_INFO "br_netfilter post_routing: skb->dst == NULL\n"); goto print_error; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b6c3b71974d..d5b5537272b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -51,7 +51,6 @@ struct net_bridge_fdb_entry struct net_bridge_port *dst; struct rcu_head rcu; - atomic_t use_count; unsigned long ageing_timer; mac_addr addr; unsigned char is_local; @@ -154,9 +153,7 @@ extern void br_fdb_delete_by_port(struct net_bridge *br, const struct net_bridge_port *p, int do_all); extern struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, const unsigned char *addr); -extern struct net_bridge_fdb_entry *br_fdb_get(struct net_bridge *br, - unsigned char *addr); -extern void br_fdb_put(struct net_bridge_fdb_entry *ent); +extern int br_fdb_test_addr(struct net_device *dev, unsigned char *addr); extern int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long count, unsigned long off); extern int br_fdb_insert(struct net_bridge *br, @@ -242,10 +239,9 @@ extern void br_stp_port_timer_init(struct net_bridge_port *p); extern unsigned long br_timer_value(const struct timer_list *timer); /* br.c */ -extern struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br, - unsigned char *addr); -extern void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent); - +#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr); +#endif /* br_netlink.c */ extern int br_netlink_init(void); diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 603d89248e7..ee4820aa184 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -172,7 +172,8 @@ static ssize_t store_stp_state(struct device *d, if (endp == buf) return -EINVAL; - rtnl_lock(); + if (!rtnl_trylock()) + return restart_syscall(); br_stp_set_enabled(br, val); rtnl_unlock(); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 02b2d50cce4..4a3cdf8f381 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -189,7 +189,8 @@ static ssize_t brport_store(struct kobject * kobj, val = simple_strtoul(buf, &endp, 0); if (endp != buf) { - rtnl_lock(); + if (!rtnl_trylock()) + return restart_syscall(); if (p->dev && p->br && brport_attr->store) { spin_lock_bh(&p->br->lock); ret = brport_attr->store(p, val); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 820252aee81..37928d5f284 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -142,6 +142,12 @@ static inline int ebt_basic_match(struct ebt_entry *e, struct ethhdr *h, return 0; } +static inline __pure +struct ebt_entry *ebt_next_entry(const struct ebt_entry *entry) +{ + return (void *)entry + entry->next_offset; +} + /* Do some firewalling */ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -164,7 +170,7 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, mtpar.in = tgpar.in = in; mtpar.out = tgpar.out = out; mtpar.hotdrop = &hotdrop; - tgpar.hooknum = hook; + mtpar.hooknum = tgpar.hooknum = hook; read_lock_bh(&table->lock); private = table->private; @@ -249,8 +255,7 @@ letsreturn: /* jump to a udc */ cs[sp].n = i + 1; cs[sp].chaininfo = chaininfo; - cs[sp].e = (struct ebt_entry *) - (((char *)point) + point->next_offset); + cs[sp].e = ebt_next_entry(point); i = 0; chaininfo = (struct ebt_entries *) (base + verdict); #ifdef CONFIG_NETFILTER_DEBUG @@ -266,8 +271,7 @@ letsreturn: sp++; continue; letscontinue: - point = (struct ebt_entry *) - (((char *)point) + point->next_offset); + point = ebt_next_entry(point); i++; } @@ -787,7 +791,7 @@ static int check_chainloops(struct ebt_entries *chain, struct ebt_cl_stack *cl_s /* this can't be 0, so the loop test is correct */ cl_s[i].cs.n = pos + 1; pos = 0; - cl_s[i].cs.e = ((void *)e + e->next_offset); + cl_s[i].cs.e = ebt_next_entry(e); e = (struct ebt_entry *)(hlp2->data); nentries = hlp2->nentries; cl_s[i].from = chain_nr; @@ -797,7 +801,7 @@ static int check_chainloops(struct ebt_entries *chain, struct ebt_cl_stack *cl_s continue; } letscontinue: - e = (void *)e + e->next_offset; + e = ebt_next_entry(e); pos++; } return 0; diff --git a/net/can/af_can.c b/net/can/af_can.c index 10f0528c3bf..e733725b11d 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -903,6 +903,8 @@ static __exit void can_exit(void) } spin_unlock(&can_rcvlists_lock); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ + kmem_cache_destroy(rcv_cache); } diff --git a/net/can/bcm.c b/net/can/bcm.c index 95d7f32643a..72720c71035 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -75,6 +75,7 @@ static __initdata const char banner[] = KERN_INFO MODULE_DESCRIPTION("PF_CAN broadcast manager protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); +MODULE_ALIAS("can-proto-2"); /* easy access to can_frame payload */ static inline u64 GET_U64(const struct can_frame *cp) @@ -1469,6 +1470,9 @@ static int bcm_release(struct socket *sock) bo->ifindex = 0; } + sock_orphan(sk); + sock->sk = NULL; + release_sock(sk); sock_put(sk); diff --git a/net/can/raw.c b/net/can/raw.c index 6aa154e806a..db3152df7d2 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -62,6 +62,7 @@ static __initdata const char banner[] = MODULE_DESCRIPTION("PF_CAN raw protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); +MODULE_ALIAS("can-proto-1"); #define MASK_ALL 0 @@ -306,6 +307,9 @@ static int raw_release(struct socket *sock) ro->bound = 0; ro->count = 0; + sock_orphan(sk); + sock->sk = NULL; + release_sock(sk); sock_put(sk); @@ -397,6 +401,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, if (peer) return -EOPNOTSUPP; + memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = ro->ifindex; diff --git a/net/core/datagram.c b/net/core/datagram.c index b01a76abe1d..b0fe69211ee 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -260,7 +260,9 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) spin_unlock_bh(&sk->sk_receive_queue.lock); } - skb_free_datagram(sk, skb); + kfree_skb(skb); + sk_mem_reclaim_partial(sk); + return err; } @@ -280,6 +282,7 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; /* Copy header. */ if (copy > 0) { @@ -320,28 +323,24 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_datagram_iovec(list, - offset - start, - to, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_iovec(frag_iter, + offset - start, + to, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; } + start = end; } if (!len) return 0; @@ -351,30 +350,124 @@ fault: } /** + * skb_copy_datagram_const_iovec - Copy a datagram to an iovec. + * @skb: buffer to copy + * @offset: offset in the buffer to start copying from + * @to: io vector to copy to + * @to_offset: offset in the io vector to start copying to + * @len: amount of data to copy from buffer to iovec + * + * Returns 0 or -EFAULT. + * Note: the iovec is not modified during the copy. + */ +int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset, + const struct iovec *to, int to_offset, + int len) +{ + int start = skb_headlen(skb); + int i, copy = start - offset; + struct sk_buff *frag_iter; + + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to_offset += copy; + } + + /* Copy paged appendix. Hmm... why does this look so complicated? */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + + WARN_ON(start > offset + len); + + end = start + skb_shinfo(skb)->frags[i].size; + if ((copy = end - offset) > 0) { + int err; + u8 *vaddr; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = frag->page; + + if (copy > len) + copy = len; + vaddr = kmap(page); + err = memcpy_toiovecend(to, vaddr + frag->page_offset + + offset - start, to_offset, copy); + kunmap(page); + if (err) + goto fault; + if (!(len -= copy)) + return 0; + offset += copy; + to_offset += copy; + } + start = end; + } + + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_const_iovec(frag_iter, + offset - start, + to, to_offset, + copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to_offset += copy; + } + start = end; + } + if (!len) + return 0; + +fault: + return -EFAULT; +} +EXPORT_SYMBOL(skb_copy_datagram_const_iovec); + +/** * skb_copy_datagram_from_iovec - Copy a datagram from an iovec. * @skb: buffer to copy * @offset: offset in the buffer to start copying to * @from: io vector to copy to + * @from_offset: offset in the io vector to start copying from * @len: amount of data to copy to buffer from iovec * * Returns 0 or -EFAULT. - * Note: the iovec is modified during the copy. + * Note: the iovec is not modified during the copy. */ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, - struct iovec *from, int len) + const struct iovec *from, int from_offset, + int len) { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; - if (memcpy_fromiovec(skb->data + offset, from, copy)) + if (memcpy_fromiovecend(skb->data + offset, from, from_offset, + copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; + from_offset += copy; } /* Copy paged appendix. Hmm... why does this look so complicated? */ @@ -393,8 +486,9 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, if (copy > len) copy = len; vaddr = kmap(page); - err = memcpy_fromiovec(vaddr + frag->page_offset + - offset - start, from, copy); + err = memcpy_fromiovecend(vaddr + frag->page_offset + + offset - start, + from, from_offset, copy); kunmap(page); if (err) goto fault; @@ -402,32 +496,32 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, if (!(len -= copy)) return 0; offset += copy; + from_offset += copy; } start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_datagram_from_iovec(list, - offset - start, - from, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_from_iovec(frag_iter, + offset - start, + from, + from_offset, + copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + from_offset += copy; } + start = end; } if (!len) return 0; @@ -442,8 +536,9 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, __wsum *csump) { int start = skb_headlen(skb); - int pos = 0; int i, copy = start - offset; + struct sk_buff *frag_iter; + int pos = 0; /* Copy header. */ if (copy > 0) { @@ -494,33 +589,29 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list=list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - __wsum csum2 = 0; - if (copy > len) - copy = len; - if (skb_copy_and_csum_datagram(list, - offset - start, - to, copy, - &csum2)) - goto fault; - *csump = csum_block_add(*csump, csum2, pos); - if ((len -= copy) == 0) - return 0; - offset += copy; - to += copy; - pos += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + __wsum csum2 = 0; + if (copy > len) + copy = len; + if (skb_copy_and_csum_datagram(frag_iter, + offset - start, + to, copy, + &csum2)) + goto fault; + *csump = csum_block_add(*csump, csum2, pos); + if ((len -= copy) == 0) + return 0; + offset += copy; + to += copy; + pos += copy; } + start = end; } if (!len) return 0; @@ -621,7 +712,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; /* exceptional events? */ diff --git a/net/core/dev.c b/net/core/dev.c index e2e9e4af3ac..6a94475aee8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -126,6 +126,7 @@ #include <linux/in.h> #include <linux/jhash.h> #include <linux/random.h> +#include <trace/events/napi.h> #include "net-sysfs.h" @@ -268,7 +269,8 @@ 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_VOID, ARPHRD_NONE}; + ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_IEEE802154_PHY, + ARPHRD_VOID, ARPHRD_NONE}; static const char *netdev_lock_name[] = {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", @@ -285,7 +287,8 @@ 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_VOID", "_xmit_NONE"}; + "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_IEEE802154_PHY", + "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -1047,7 +1050,7 @@ void dev_load(struct net *net, const char *name) int dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; - int ret = 0; + int ret; ASSERT_RTNL(); @@ -1064,6 +1067,11 @@ int dev_open(struct net_device *dev) if (!netif_device_present(dev)) return -ENODEV; + ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); + ret = notifier_to_errno(ret); + if (ret) + return ret; + /* * Call device private open method */ @@ -1688,7 +1696,16 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, goto gso; } + /* + * If device doesnt need skb->dst, release it right now while + * its hot in this cpu cache + */ + if (dev->priv_flags & IFF_XMIT_DST_RELEASE) + skb_dst_drop(skb); + rc = ops->ndo_start_xmit(skb, dev); + if (rc == 0) + txq_trans_update(txq); /* * TODO: if skb_orphan() was called by * dev->hard_start_xmit() (for example, the unmodified @@ -1718,6 +1735,7 @@ gso: skb->next = nskb; return rc; } + txq_trans_update(txq); if (unlikely(netif_tx_queue_stopped(txq) && skb->next)) return NETDEV_TX_BUSY; } while (skb->next); @@ -1735,8 +1753,12 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) { u32 hash; - if (skb_rx_queue_recorded(skb)) - return skb_get_rx_queue(skb) % dev->real_num_tx_queues; + if (skb_rx_queue_recorded(skb)) { + hash = skb_get_rx_queue(skb); + while (unlikely (hash >= dev->real_num_tx_queues)) + hash -= dev->real_num_tx_queues; + return hash; + } if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; @@ -1800,7 +1822,7 @@ int dev_queue_xmit(struct sk_buff *skb) if (netif_needs_gso(dev, skb)) goto gso; - if (skb_shinfo(skb)->frag_list && + if (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST) && __skb_linearize(skb)) goto out_kfree_skb; @@ -2049,11 +2071,13 @@ static inline int deliver_skb(struct sk_buff *skb, } #if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE) -/* These hooks defined here for ATM */ -struct net_bridge; -struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br, - unsigned char *addr); -void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent) __read_mostly; + +#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +/* 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); +#endif /* * If bridge module is loaded call bridging hook. @@ -2061,6 +2085,8 @@ void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent) __read_mostly; */ struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff *skb) __read_mostly; +EXPORT_SYMBOL(br_handle_frame_hook); + static inline struct sk_buff *handle_bridge(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) @@ -2284,8 +2310,6 @@ ncls: if (!skb) goto out; - skb_orphan(skb); - type = skb->protocol; list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { @@ -2374,26 +2398,6 @@ void napi_gro_flush(struct napi_struct *napi) } EXPORT_SYMBOL(napi_gro_flush); -void *skb_gro_header(struct sk_buff *skb, unsigned int hlen) -{ - unsigned int offset = skb_gro_offset(skb); - - hlen += offset; - if (hlen <= skb_headlen(skb)) - return skb->data + offset; - - if (unlikely(!skb_shinfo(skb)->nr_frags || - skb_shinfo(skb)->frags[0].size <= - hlen - skb_headlen(skb) || - PageHighMem(skb_shinfo(skb)->frags[0].page))) - return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL; - - return page_address(skb_shinfo(skb)->frags[0].page) + - skb_shinfo(skb)->frags[0].page_offset + - offset - skb_headlen(skb); -} -EXPORT_SYMBOL(skb_gro_header); - int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; @@ -2407,7 +2411,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) if (!(skb->dev->features & NETIF_F_GRO)) goto normal; - if (skb_is_gso(skb) || skb_shinfo(skb)->frag_list) + if (skb_is_gso(skb) || skb_has_frags(skb)) goto normal; rcu_read_lock(); @@ -2456,10 +2460,25 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) ret = GRO_HELD; pull: - if (unlikely(!pskb_may_pull(skb, skb_gro_offset(skb)))) { - if (napi->gro_list == skb) - napi->gro_list = skb->next; - ret = GRO_DROP; + if (skb_headlen(skb) < skb_gro_offset(skb)) { + int grow = skb_gro_offset(skb) - skb_headlen(skb); + + BUG_ON(skb->end - skb->tail < grow); + + memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); + + skb->tail += grow; + skb->data_len -= grow; + + skb_shinfo(skb)->frags[0].page_offset += grow; + skb_shinfo(skb)->frags[0].size -= grow; + + if (unlikely(!skb_shinfo(skb)->frags[0].size)) { + put_page(skb_shinfo(skb)->frags[0].page); + memmove(skb_shinfo(skb)->frags, + skb_shinfo(skb)->frags + 1, + --skb_shinfo(skb)->nr_frags); + } } ok: @@ -2509,6 +2528,22 @@ int napi_skb_finish(int ret, struct sk_buff *skb) } EXPORT_SYMBOL(napi_skb_finish); +void skb_gro_reset_offset(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->data_offset = 0; + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; + + if (skb->mac_header == skb->tail && + !PageHighMem(skb_shinfo(skb)->frags[0].page)) { + NAPI_GRO_CB(skb)->frag0 = + page_address(skb_shinfo(skb)->frags[0].page) + + skb_shinfo(skb)->frags[0].page_offset; + NAPI_GRO_CB(skb)->frag0_len = skb_shinfo(skb)->frags[0].size; + } +} +EXPORT_SYMBOL(skb_gro_reset_offset); + int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { skb_gro_reset_offset(skb); @@ -2526,16 +2561,10 @@ void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) } EXPORT_SYMBOL(napi_reuse_skb); -struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi, - struct napi_gro_fraginfo *info) +struct sk_buff *napi_get_frags(struct napi_struct *napi) { struct net_device *dev = napi->dev; struct sk_buff *skb = napi->skb; - struct ethhdr *eth; - skb_frag_t *frag; - int i; - - napi->skb = NULL; if (!skb) { skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN); @@ -2543,47 +2572,14 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi, goto out; skb_reserve(skb, NET_IP_ALIGN); - } - - BUG_ON(info->nr_frags > MAX_SKB_FRAGS); - frag = info->frags; - for (i = 0; i < info->nr_frags; i++) { - skb_fill_page_desc(skb, i, frag->page, frag->page_offset, - frag->size); - frag++; + napi->skb = skb; } - skb_shinfo(skb)->nr_frags = info->nr_frags; - - skb->data_len = info->len; - skb->len += info->len; - skb->truesize += info->len; - - skb_reset_mac_header(skb); - skb_gro_reset_offset(skb); - - eth = skb_gro_header(skb, sizeof(*eth)); - if (!eth) { - napi_reuse_skb(napi, skb); - skb = NULL; - goto out; - } - - skb_gro_pull(skb, sizeof(*eth)); - - /* - * This works because the only protocols we care about don't require - * special handling. We'll fix it up properly at the end. - */ - skb->protocol = eth->h_proto; - - skb->ip_summed = info->ip_summed; - skb->csum = info->csum; out: return skb; } -EXPORT_SYMBOL(napi_fraginfo_skb); +EXPORT_SYMBOL(napi_get_frags); int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret) { @@ -2613,9 +2609,46 @@ int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret) } EXPORT_SYMBOL(napi_frags_finish); -int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info) +struct sk_buff *napi_frags_skb(struct napi_struct *napi) { - struct sk_buff *skb = napi_fraginfo_skb(napi, info); + struct sk_buff *skb = napi->skb; + struct ethhdr *eth; + unsigned int hlen; + unsigned int off; + + napi->skb = NULL; + + skb_reset_mac_header(skb); + skb_gro_reset_offset(skb); + + off = skb_gro_offset(skb); + hlen = off + sizeof(*eth); + eth = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + eth = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!eth)) { + napi_reuse_skb(napi, skb); + skb = NULL; + goto out; + } + } + + skb_gro_pull(skb, sizeof(*eth)); + + /* + * This works because the only protocols we care about don't require + * special handling. We'll fix it up properly at the end. + */ + skb->protocol = eth->h_proto; + +out: + return skb; +} +EXPORT_SYMBOL(napi_frags_skb); + +int napi_gro_frags(struct napi_struct *napi) +{ + struct sk_buff *skb = napi_frags_skb(napi); if (!skb) return NET_RX_DROP; @@ -2719,7 +2752,7 @@ void netif_napi_del(struct napi_struct *napi) struct sk_buff *skb, *next; list_del_init(&napi->dev_list); - kfree_skb(napi->skb); + napi_free_frags(napi); for (skb = napi->gro_list; skb; skb = next) { next = skb->next; @@ -2773,8 +2806,10 @@ static void net_rx_action(struct softirq_action *h) * accidently calling ->poll() when NAPI is not scheduled. */ work = 0; - if (test_bit(NAPI_STATE_SCHED, &n->state)) + if (test_bit(NAPI_STATE_SCHED, &n->state)) { work = n->poll(n, weight); + trace_napi_poll(n); + } WARN_ON_ONCE(work > weight); @@ -2788,9 +2823,11 @@ static void net_rx_action(struct softirq_action *h) * move the instance around on the list at-will. */ if (unlikely(work == weight)) { - if (unlikely(napi_disable_pending(n))) - __napi_complete(n); - else + if (unlikely(napi_disable_pending(n))) { + local_irq_enable(); + napi_complete(n); + local_irq_disable(); + } else list_move_tail(&n->poll_list, list); } @@ -3424,10 +3461,10 @@ void __dev_set_rx_mode(struct net_device *dev) /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ - if (dev->uc_count > 0 && !dev->uc_promisc) { + if (dev->uc.count > 0 && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1); dev->uc_promisc = 1; - } else if (dev->uc_count == 0 && dev->uc_promisc) { + } else if (dev->uc.count == 0 && dev->uc_promisc) { __dev_set_promiscuity(dev, -1); dev->uc_promisc = 0; } @@ -3444,6 +3481,316 @@ void dev_set_rx_mode(struct net_device *dev) netif_addr_unlock_bh(dev); } +/* hw addresses list handling functions */ + +static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, + int addr_len, unsigned char addr_type) +{ + struct netdev_hw_addr *ha; + int alloc_size; + + if (addr_len > MAX_ADDR_LEN) + return -EINVAL; + + list_for_each_entry(ha, &list->list, list) { + if (!memcmp(ha->addr, addr, addr_len) && + ha->type == addr_type) { + ha->refcount++; + return 0; + } + } + + + alloc_size = sizeof(*ha); + if (alloc_size < L1_CACHE_BYTES) + alloc_size = L1_CACHE_BYTES; + ha = kmalloc(alloc_size, GFP_ATOMIC); + if (!ha) + return -ENOMEM; + memcpy(ha->addr, addr, addr_len); + ha->type = addr_type; + ha->refcount = 1; + ha->synced = false; + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + return 0; +} + +static void ha_rcu_free(struct rcu_head *head) +{ + struct netdev_hw_addr *ha; + + ha = container_of(head, struct netdev_hw_addr, rcu_head); + kfree(ha); +} + +static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, + int addr_len, unsigned char addr_type) +{ + struct netdev_hw_addr *ha; + + list_for_each_entry(ha, &list->list, list) { + if (!memcmp(ha->addr, addr, addr_len) && + (ha->type == addr_type || !addr_type)) { + if (--ha->refcount) + return 0; + list_del_rcu(&ha->list); + call_rcu(&ha->rcu_head, ha_rcu_free); + list->count--; + return 0; + } + } + return -ENOENT; +} + +static int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, + unsigned char addr_type) +{ + int err; + struct netdev_hw_addr *ha, *ha2; + unsigned char type; + + list_for_each_entry(ha, &from_list->list, list) { + type = addr_type ? addr_type : ha->type; + err = __hw_addr_add(to_list, ha->addr, addr_len, type); + if (err) + goto unroll; + } + return 0; + +unroll: + list_for_each_entry(ha2, &from_list->list, list) { + if (ha2 == ha) + break; + type = addr_type ? addr_type : ha2->type; + __hw_addr_del(to_list, ha2->addr, addr_len, type); + } + return err; +} + +static void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, + unsigned char addr_type) +{ + struct netdev_hw_addr *ha; + unsigned char type; + + list_for_each_entry(ha, &from_list->list, list) { + type = addr_type ? addr_type : ha->type; + __hw_addr_del(to_list, ha->addr, addr_len, addr_type); + } +} + +static int __hw_addr_sync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) +{ + int err = 0; + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &from_list->list, list) { + if (!ha->synced) { + err = __hw_addr_add(to_list, ha->addr, + addr_len, ha->type); + if (err) + break; + ha->synced = true; + ha->refcount++; + } else if (ha->refcount == 1) { + __hw_addr_del(to_list, ha->addr, addr_len, ha->type); + __hw_addr_del(from_list, ha->addr, addr_len, ha->type); + } + } + return err; +} + +static void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &from_list->list, list) { + if (ha->synced) { + __hw_addr_del(to_list, ha->addr, + addr_len, ha->type); + ha->synced = false; + __hw_addr_del(from_list, ha->addr, + addr_len, ha->type); + } + } +} + +static void __hw_addr_flush(struct netdev_hw_addr_list *list) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &list->list, list) { + list_del_rcu(&ha->list); + call_rcu(&ha->rcu_head, ha_rcu_free); + } + list->count = 0; +} + +static void __hw_addr_init(struct netdev_hw_addr_list *list) +{ + INIT_LIST_HEAD(&list->list); + list->count = 0; +} + +/* Device addresses handling functions */ + +static void dev_addr_flush(struct net_device *dev) +{ + /* rtnl_mutex must be held here */ + + __hw_addr_flush(&dev->dev_addrs); + dev->dev_addr = NULL; +} + +static int dev_addr_init(struct net_device *dev) +{ + unsigned char addr[MAX_ADDR_LEN]; + struct netdev_hw_addr *ha; + int err; + + /* rtnl_mutex must be held here */ + + __hw_addr_init(&dev->dev_addrs); + memset(addr, 0, sizeof(addr)); + err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), + NETDEV_HW_ADDR_T_LAN); + if (!err) { + /* + * Get the first (previously created) address from the list + * and set dev_addr pointer to this location. + */ + ha = list_first_entry(&dev->dev_addrs.list, + struct netdev_hw_addr, list); + dev->dev_addr = ha->addr; + } + return err; +} + +/** + * dev_addr_add - Add a device address + * @dev: device + * @addr: address to add + * @addr_type: address type + * + * Add a device address to the device or increase the reference count if + * it already exists. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_add(struct net_device *dev, unsigned char *addr, + unsigned char addr_type) +{ + int err; + + ASSERT_RTNL(); + + err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); + if (!err) + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return err; +} +EXPORT_SYMBOL(dev_addr_add); + +/** + * dev_addr_del - Release a device address. + * @dev: device + * @addr: address to delete + * @addr_type: address type + * + * Release reference to a device address and remove it from the device + * if the reference count drops to zero. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_del(struct net_device *dev, unsigned char *addr, + unsigned char addr_type) +{ + int err; + struct netdev_hw_addr *ha; + + ASSERT_RTNL(); + + /* + * We can not remove the first address from the list because + * dev->dev_addr points to that. + */ + ha = list_first_entry(&dev->dev_addrs.list, + struct netdev_hw_addr, list); + if (ha->addr == dev->dev_addr && ha->refcount == 1) + return -ENOENT; + + err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, + addr_type); + if (!err) + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return err; +} +EXPORT_SYMBOL(dev_addr_del); + +/** + * dev_addr_add_multiple - Add device addresses from another device + * @to_dev: device to which addresses will be added + * @from_dev: device from which addresses will be added + * @addr_type: address type - 0 means type will be used from from_dev + * + * Add device addresses of the one device to another. + ** + * The caller must hold the rtnl_mutex. + */ +int dev_addr_add_multiple(struct net_device *to_dev, + struct net_device *from_dev, + unsigned char addr_type) +{ + int err; + + ASSERT_RTNL(); + + if (from_dev->addr_len != to_dev->addr_len) + return -EINVAL; + err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, + to_dev->addr_len, addr_type); + if (!err) + call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); + return err; +} +EXPORT_SYMBOL(dev_addr_add_multiple); + +/** + * dev_addr_del_multiple - Delete device addresses by another device + * @to_dev: device where the addresses will be deleted + * @from_dev: device by which addresses the addresses will be deleted + * @addr_type: address type - 0 means type will used from from_dev + * + * Deletes addresses in to device by the list of addresses in from device. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_del_multiple(struct net_device *to_dev, + struct net_device *from_dev, + unsigned char addr_type) +{ + ASSERT_RTNL(); + + if (from_dev->addr_len != to_dev->addr_len) + return -EINVAL; + __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, + to_dev->addr_len, addr_type); + call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); + return 0; +} +EXPORT_SYMBOL(dev_addr_del_multiple); + +/* multicast addresses handling functions */ + int __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int glbl) { @@ -3506,21 +3853,21 @@ int __dev_addr_add(struct dev_addr_list **list, int *count, * dev_unicast_delete - Release secondary unicast address. * @dev: device * @addr: address to delete - * @alen: length of @addr * * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. * * The caller must hold the rtnl_mutex. */ -int dev_unicast_delete(struct net_device *dev, void *addr, int alen) +int dev_unicast_delete(struct net_device *dev, void *addr) { int err; ASSERT_RTNL(); netif_addr_lock_bh(dev); - err = __dev_addr_delete(&dev->uc_list, &dev->uc_count, addr, alen, 0); + err = __hw_addr_del(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); @@ -3532,21 +3879,21 @@ EXPORT_SYMBOL(dev_unicast_delete); * dev_unicast_add - add a secondary unicast address * @dev: device * @addr: address to add - * @alen: length of @addr * * Add a secondary unicast address to the device or increase * the reference count if it already exists. * * The caller must hold the rtnl_mutex. */ -int dev_unicast_add(struct net_device *dev, void *addr, int alen) +int dev_unicast_add(struct net_device *dev, void *addr) { int err; ASSERT_RTNL(); netif_addr_lock_bh(dev); - err = __dev_addr_add(&dev->uc_list, &dev->uc_count, addr, alen, 0); + err = __hw_addr_add(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); @@ -3616,9 +3963,11 @@ int dev_unicast_sync(struct net_device *to, struct net_device *from) { int err = 0; + if (to->addr_len != from->addr_len) + return -EINVAL; + netif_addr_lock_bh(to); - err = __dev_addr_sync(&to->uc_list, &to->uc_count, - &from->uc_list, &from->uc_count); + err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock_bh(to); @@ -3637,18 +3986,31 @@ EXPORT_SYMBOL(dev_unicast_sync); */ void dev_unicast_unsync(struct net_device *to, struct net_device *from) { + if (to->addr_len != from->addr_len) + return; + netif_addr_lock_bh(from); netif_addr_lock(to); - - __dev_addr_unsync(&to->uc_list, &to->uc_count, - &from->uc_list, &from->uc_count); + __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); - netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_unicast_unsync); +static void dev_unicast_flush(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __hw_addr_flush(&dev->uc); + netif_addr_unlock_bh(dev); +} + +static void dev_unicast_init(struct net_device *dev) +{ + __hw_addr_init(&dev->uc); +} + + static void __dev_addr_discard(struct dev_addr_list **list) { struct dev_addr_list *tmp; @@ -3667,9 +4029,6 @@ static void dev_addr_discard(struct net_device *dev) { netif_addr_lock_bh(dev); - __dev_addr_discard(&dev->uc_list); - dev->uc_count = 0; - __dev_addr_discard(&dev->mc_list); dev->mc_count = 0; @@ -3853,7 +4212,7 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm switch (cmd) { case SIOCGIFFLAGS: /* Get interface flags */ - ifr->ifr_flags = dev_get_flags(dev); + ifr->ifr_flags = (short) dev_get_flags(dev); return 0; case SIOCGIFMETRIC: /* Get the metric on the interface @@ -4262,6 +4621,7 @@ static void rollback_registered(struct net_device *dev) /* * Flush the unicast and multicast chains */ + dev_unicast_flush(dev); dev_addr_discard(dev); if (dev->netdev_ops->ndo_uninit) @@ -4333,39 +4693,6 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) } EXPORT_SYMBOL(netdev_fix_features); -/* Some devices need to (re-)set their netdev_ops inside - * ->init() or similar. If that happens, we have to setup - * the compat pointers again. - */ -void netdev_resync_ops(struct net_device *dev) -{ -#ifdef CONFIG_COMPAT_NET_DEV_OPS - const struct net_device_ops *ops = dev->netdev_ops; - - dev->init = ops->ndo_init; - dev->uninit = ops->ndo_uninit; - dev->open = ops->ndo_open; - dev->change_rx_flags = ops->ndo_change_rx_flags; - dev->set_rx_mode = ops->ndo_set_rx_mode; - dev->set_multicast_list = ops->ndo_set_multicast_list; - dev->set_mac_address = ops->ndo_set_mac_address; - dev->validate_addr = ops->ndo_validate_addr; - dev->do_ioctl = ops->ndo_do_ioctl; - dev->set_config = ops->ndo_set_config; - dev->change_mtu = ops->ndo_change_mtu; - dev->neigh_setup = ops->ndo_neigh_setup; - dev->tx_timeout = ops->ndo_tx_timeout; - dev->get_stats = ops->ndo_get_stats; - dev->vlan_rx_register = ops->ndo_vlan_rx_register; - dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid; - dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid; -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ops->ndo_poll_controller; -#endif -#endif -} -EXPORT_SYMBOL(netdev_resync_ops); - /** * register_netdevice - register a network device * @dev: device to register @@ -4405,23 +4732,6 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; -#ifdef CONFIG_COMPAT_NET_DEV_OPS - /* Netdevice_ops API compatibility support. - * This is temporary until all network devices are converted. - */ - if (dev->netdev_ops) { - netdev_resync_ops(dev); - } else { - char drivername[64]; - pr_info("%s (%s): not using net_device_ops yet\n", - dev->name, netdev_drivername(dev, drivername, 64)); - - /* This works only because net_device_ops and the - compatibility structure are the same. */ - dev->netdev_ops = (void *) &(dev->init); - } -#endif - /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -4707,13 +5017,30 @@ void netdev_run_todo(void) * the internal statistics structure is used. */ const struct net_device_stats *dev_get_stats(struct net_device *dev) - { +{ const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_get_stats) return ops->ndo_get_stats(dev); - else - return &dev->stats; + else { + unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0; + struct net_device_stats *stats = &dev->stats; + unsigned int i; + struct netdev_queue *txq; + + for (i = 0; i < dev->num_tx_queues; i++) { + txq = netdev_get_tx_queue(dev, i); + tx_bytes += txq->tx_bytes; + tx_packets += txq->tx_packets; + tx_dropped += txq->tx_dropped; + } + if (tx_bytes || tx_packets || tx_dropped) { + stats->tx_bytes = tx_bytes; + stats->tx_packets = tx_packets; + stats->tx_dropped = tx_dropped; + } + return stats; + } } EXPORT_SYMBOL(dev_get_stats); @@ -4748,18 +5075,18 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, struct netdev_queue *tx; struct net_device *dev; size_t alloc_size; - void *p; + struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ - alloc_size = (alloc_size + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST; + alloc_size = ALIGN(alloc_size, NETDEV_ALIGN); alloc_size += sizeof_priv; } /* ensure 32-byte alignment of whole construct */ - alloc_size += NETDEV_ALIGN_CONST; + alloc_size += NETDEV_ALIGN - 1; p = kzalloc(alloc_size, GFP_KERNEL); if (!p) { @@ -4771,13 +5098,17 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, if (!tx) { printk(KERN_ERR "alloc_netdev: Unable to allocate " "tx qdiscs.\n"); - kfree(p); - return NULL; + goto free_p; } - dev = (struct net_device *) - (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST); + dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; + + if (dev_addr_init(dev)) + goto free_tx; + + dev_unicast_init(dev); + dev_net_set(dev, &init_net); dev->_tx = tx; @@ -4789,9 +5120,17 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, netdev_init_queues(dev); INIT_LIST_HEAD(&dev->napi_list); + dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); strcpy(dev->name, name); return dev; + +free_tx: + kfree(tx); + +free_p: + kfree(p); + return NULL; } EXPORT_SYMBOL(alloc_netdev_mq); @@ -4811,6 +5150,9 @@ void free_netdev(struct net_device *dev) kfree(dev->_tx); + /* Flush device addresses */ + dev_addr_flush(dev); + list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); @@ -4970,6 +5312,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* * Flush the unicast and multicast chains */ + dev_unicast_flush(dev); dev_addr_discard(dev); netdev_unregister_kobject(dev); @@ -5325,12 +5668,6 @@ EXPORT_SYMBOL(net_enable_timestamp); EXPORT_SYMBOL(net_disable_timestamp); EXPORT_SYMBOL(dev_get_flags); -#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) -EXPORT_SYMBOL(br_handle_frame_hook); -EXPORT_SYMBOL(br_fdb_get_hook); -EXPORT_SYMBOL(br_fdb_put_hook); -#endif - 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 9fd0dc3cca9..9d66fa953ab 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -22,8 +22,10 @@ #include <linux/timer.h> #include <linux/bitops.h> #include <net/genetlink.h> +#include <net/netevent.h> -#include <trace/skb.h> +#include <trace/events/skb.h> +#include <trace/events/napi.h> #include <asm/unaligned.h> @@ -38,7 +40,8 @@ static void send_dm_alert(struct work_struct *unused); * and the work handle that will send up * netlink alerts */ -struct sock *dm_sock; +static int trace_state = TRACE_OFF; +static spinlock_t trace_state_lock = SPIN_LOCK_UNLOCKED; struct per_cpu_dm_data { struct work_struct dm_alert_work; @@ -47,11 +50,18 @@ struct per_cpu_dm_data { struct timer_list send_timer; }; +struct dm_hw_stat_delta { + struct net_device *dev; + struct list_head list; + struct rcu_head rcu; + unsigned long last_drop_val; +}; + static struct genl_family net_drop_monitor_family = { .id = GENL_ID_GENERATE, .hdrsize = 0, .name = "NET_DM", - .version = 1, + .version = 2, .maxattr = NET_DM_CMD_MAX, }; @@ -59,19 +69,24 @@ static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); static int dm_hit_limit = 64; static int dm_delay = 1; - +static unsigned long dm_hw_check_delta = 2*HZ; +static LIST_HEAD(hw_stats_list); static void reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; + struct nlattr *nla; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); + al += sizeof(struct nlattr); + data->skb = genlmsg_new(al, GFP_KERNEL); genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); - msg = __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_alert_msg)); + nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); + msg = nla_data(nla); memset(msg, 0, al); atomic_set(&data->dm_hit_count, dm_hit_limit); } @@ -111,10 +126,11 @@ static void sched_send_work(unsigned long unused) schedule_work(&data->dm_alert_work); } -static void trace_kfree_skb_hit(struct sk_buff *skb, void *location) +static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; struct nlmsghdr *nlh; + struct nlattr *nla; int i; struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); @@ -127,7 +143,8 @@ static void trace_kfree_skb_hit(struct sk_buff *skb, void *location) } nlh = (struct nlmsghdr *)data->skb->data; - msg = genlmsg_data(nlmsg_data(nlh)); + nla = genlmsg_data(nlmsg_data(nlh)); + msg = nla_data(nla); for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { msg->points[i].count++; @@ -139,6 +156,7 @@ static void trace_kfree_skb_hit(struct sk_buff *skb, void *location) * We need to create a new entry */ __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point)); + nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); msg->points[msg->entries].count = 1; msg->entries++; @@ -152,24 +170,80 @@ out: return; } +static void trace_kfree_skb_hit(struct sk_buff *skb, void *location) +{ + trace_drop_common(skb, location); +} + +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 + */ + if (!time_after(jiffies, napi->dev->last_rx + dm_hw_check_delta)) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(new_stat, &hw_stats_list, list) { + if ((new_stat->dev == napi->dev) && + (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; + break; + } + } + rcu_read_unlock(); +} + + +static void free_dm_hw_stat(struct rcu_head *head) +{ + struct dm_hw_stat_delta *n; + n = container_of(head, struct dm_hw_stat_delta, rcu); + kfree(n); +} + static int set_all_monitor_traces(int state) { int rc = 0; + struct dm_hw_stat_delta *new_stat = NULL; + struct dm_hw_stat_delta *temp; + + spin_lock(&trace_state_lock); switch (state) { case TRACE_ON: rc |= register_trace_kfree_skb(trace_kfree_skb_hit); + rc |= register_trace_napi_poll(trace_napi_poll_hit); break; case TRACE_OFF: rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit); + rc |= unregister_trace_napi_poll(trace_napi_poll_hit); tracepoint_synchronize_unregister(); + + /* + * Clean the device list + */ + list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { + if (new_stat->dev == NULL) { + list_del_rcu(&new_stat->list); + call_rcu(&new_stat->rcu, free_dm_hw_stat); + } + } break; default: rc = 1; break; } + if (!rc) + trace_state = state; + + spin_unlock(&trace_state_lock); + if (rc) return -EINPROGRESS; return rc; @@ -197,6 +271,44 @@ static int net_dm_cmd_trace(struct sk_buff *skb, return -ENOTSUPP; } +static int dropmon_net_event(struct notifier_block *ev_block, + unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct dm_hw_stat_delta *new_stat = NULL; + struct dm_hw_stat_delta *tmp; + + switch (event) { + case NETDEV_REGISTER: + new_stat = kzalloc(sizeof(struct dm_hw_stat_delta), GFP_KERNEL); + + if (!new_stat) + goto out; + + new_stat->dev = dev; + INIT_RCU_HEAD(&new_stat->rcu); + spin_lock(&trace_state_lock); + list_add_rcu(&new_stat->list, &hw_stats_list); + spin_unlock(&trace_state_lock); + break; + case NETDEV_UNREGISTER: + spin_lock(&trace_state_lock); + list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { + if (new_stat->dev == dev) { + new_stat->dev = NULL; + if (trace_state == TRACE_OFF) { + list_del_rcu(&new_stat->list); + call_rcu(&new_stat->rcu, free_dm_hw_stat); + break; + } + } + } + spin_unlock(&trace_state_lock); + break; + } +out: + return NOTIFY_DONE; +} static struct genl_ops dropmon_ops[] = { { @@ -213,6 +325,10 @@ static struct genl_ops dropmon_ops[] = { }, }; +static struct notifier_block dropmon_net_notifier = { + .notifier_call = dropmon_net_event +}; + static int __init init_net_drop_monitor(void) { int cpu; @@ -236,12 +352,18 @@ static int __init init_net_drop_monitor(void) ret = genl_register_ops(&net_drop_monitor_family, &dropmon_ops[i]); if (ret) { - printk(KERN_CRIT "failed to register operation %d\n", + printk(KERN_CRIT "Failed to register operation %d\n", dropmon_ops[i].cmd); goto out_unreg; } } + rc = register_netdevice_notifier(&dropmon_net_notifier); + if (rc < 0) { + printk(KERN_CRIT "Failed to register netdevice notifier\n"); + goto out_unreg; + } + rc = 0; for_each_present_cpu(cpu) { @@ -252,6 +374,7 @@ static int __init init_net_drop_monitor(void) data->send_timer.data = cpu; data->send_timer.function = sched_send_work; } + goto out; out_unreg: diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 98691e1466b..bd309384f8b 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -299,7 +299,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) } else if (rule->action == FR_ACT_GOTO) goto errout_free; - err = ops->configure(rule, skb, nlh, frh, tb); + err = ops->configure(rule, skb, frh, tb); if (err < 0) goto errout_free; @@ -500,7 +500,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (rule->target) NLA_PUT_U32(skb, FRA_GOTO, rule->target); - if (ops->fill(rule, skb, nlh, frh) < 0) + if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; return nlmsg_end(skb, nlh); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 6d62d4618cf..493775f4f2f 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -81,7 +81,7 @@ struct gen_estimator { struct list_head list; - struct gnet_stats_basic *bstats; + struct gnet_stats_basic_packed *bstats; struct gnet_stats_rate_est *rate_est; spinlock_t *stats_lock; int ewma_log; @@ -128,12 +128,12 @@ static void est_timer(unsigned long arg) npackets = e->bstats->packets; brate = (nbytes - e->last_bytes)<<(7 - idx); e->last_bytes = nbytes; - e->avbps += ((s64)(brate - e->avbps)) >> e->ewma_log; + e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log); e->rate_est->bps = (e->avbps+0xF)>>5; rate = (npackets - e->last_packets)<<(12 - idx); e->last_packets = npackets; - e->avpps += ((long)rate - (long)e->avpps) >> e->ewma_log; + e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log); e->rate_est->pps = (e->avpps+0x1FF)>>10; skip: read_unlock(&est_lock); @@ -165,7 +165,7 @@ static void gen_add_node(struct gen_estimator *est) } static -struct gen_estimator *gen_find_node(const struct gnet_stats_basic *bstats, +struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est *rate_est) { struct rb_node *p = est_root.rb_node; @@ -202,7 +202,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic *bstats, * * NOTE: Called under rtnl_mutex */ -int gen_new_estimator(struct gnet_stats_basic *bstats, +int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct nlattr *opt) @@ -262,7 +262,7 @@ static void __gen_kill_estimator(struct rcu_head *head) * * NOTE: Called under rtnl_mutex */ -void gen_kill_estimator(struct gnet_stats_basic *bstats, +void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est) { struct gen_estimator *e; @@ -292,7 +292,7 @@ EXPORT_SYMBOL(gen_kill_estimator); * * Returns 0 on success or a negative error code. */ -int gen_replace_estimator(struct gnet_stats_basic *bstats, +int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct nlattr *opt) { @@ -308,7 +308,7 @@ EXPORT_SYMBOL(gen_replace_estimator); * * Returns true if estimator is active, and false if not. */ -bool gen_estimator_active(const struct gnet_stats_basic *bstats, +bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est *rate_est) { ASSERT_RTNL(); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index c3d0ffeac24..8569310268a 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -106,16 +106,21 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic *b) +gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) { if (d->compat_tc_stats) { d->tc_stats.bytes = b->bytes; d->tc_stats.packets = b->packets; } - if (d->tail) - return gnet_stats_copy(d, TCA_STATS_BASIC, b, sizeof(*b)); + if (d->tail) { + struct gnet_stats_basic sb; + memset(&sb, 0, sizeof(sb)); + sb.bytes = b->bytes; + sb.packets = b->packets; + return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb)); + } return 0; } diff --git a/net/core/iovec.c b/net/core/iovec.c index 4c9c0121c9d..16ad45d4882 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -98,6 +98,31 @@ int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len) } /* + * Copy kernel to iovec. Returns -EFAULT on error. + */ + +int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, + int offset, int len) +{ + int copy; + for (; len > 0; ++iov) { + /* Skip over the finished iovecs */ + if (unlikely(offset >= iov->iov_len)) { + offset -= iov->iov_len; + continue; + } + copy = min_t(unsigned int, iov->iov_len - offset, len); + if (copy_to_user(iov->iov_base + offset, kdata, copy)) + return -EFAULT; + offset = 0; + kdata += copy; + len -= copy; + } + + return 0; +} + +/* * Copy iovec to kernel. Returns -EFAULT on error. * * Note: this modifies the original iovec. @@ -122,10 +147,11 @@ int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) } /* - * For use with ip_build_xmit + * Copy iovec from kernel. Returns -EFAULT on error. */ -int memcpy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset, - int len) + +int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, + int offset, int len) { /* Skip over the finished iovecs */ while (offset >= iov->iov_len) { @@ -236,3 +262,4 @@ EXPORT_SYMBOL(csum_partial_copy_fromiovecend); EXPORT_SYMBOL(memcpy_fromiovec); EXPORT_SYMBOL(memcpy_fromiovecend); EXPORT_SYMBOL(memcpy_toiovec); +EXPORT_SYMBOL(memcpy_toiovecend); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a1cbce7fdae..163b4f5b036 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -771,6 +771,28 @@ static __inline__ int neigh_max_probes(struct neighbour *n) p->ucast_probes + p->app_probes + p->mcast_probes); } +static void neigh_invalidate(struct neighbour *neigh) +{ + struct sk_buff *skb; + + NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); + NEIGH_PRINTK2("neigh %p is failed.\n", neigh); + neigh->updated = jiffies; + + /* It is very thin place. report_unreachable is very complicated + routine. Particularly, it can hit the same neighbour entry! + + So that, we try to be accurate and avoid dead loop. --ANK + */ + while (neigh->nud_state == NUD_FAILED && + (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { + write_unlock(&neigh->lock); + neigh->ops->error_report(neigh, skb); + write_lock(&neigh->lock); + } + skb_queue_purge(&neigh->arp_queue); +} + /* Called when a timer expires for a neighbour entry. */ static void neigh_timer_handler(unsigned long arg) @@ -835,26 +857,9 @@ static void neigh_timer_handler(unsigned long arg) if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) { - struct sk_buff *skb; - neigh->nud_state = NUD_FAILED; - neigh->updated = jiffies; notify = 1; - NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); - NEIGH_PRINTK2("neigh %p is failed.\n", neigh); - - /* It is very thin place. report_unreachable is very complicated - routine. Particularly, it can hit the same neighbour entry! - - So that, we try to be accurate and avoid dead loop. --ANK - */ - while (neigh->nud_state == NUD_FAILED && - (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { - write_unlock(&neigh->lock); - neigh->ops->error_report(neigh, skb); - write_lock(&neigh->lock); - } - skb_queue_purge(&neigh->arp_queue); + neigh_invalidate(neigh); } if (neigh->nud_state & NUD_IN_TIMER) { @@ -1001,6 +1006,11 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->nud_state = new; err = 0; notify = old & NUD_VALID; + if ((old & (NUD_INCOMPLETE | NUD_PROBE)) && + (new & NUD_FAILED)) { + neigh_invalidate(neigh); + notify = 1; + } goto out; } @@ -1088,8 +1098,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, struct neighbour *n1 = neigh; write_unlock_bh(&neigh->lock); /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (skb->dst && skb->dst->neighbour) - n1 = skb->dst->neighbour; + if (skb_dst(skb) && skb_dst(skb)->neighbour) + n1 = skb_dst(skb)->neighbour; n1->output(skb); write_lock_bh(&neigh->lock); } @@ -1182,7 +1192,7 @@ EXPORT_SYMBOL(neigh_compat_output); int neigh_resolve_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh; int rc = 0; @@ -1229,7 +1239,7 @@ EXPORT_SYMBOL(neigh_resolve_output); int neigh_connected_output(struct sk_buff *skb) { int err; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; @@ -1298,8 +1308,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, if (time_before(tbl->proxy_timer.expires, sched_next)) sched_next = tbl->proxy_timer.expires; } - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); mod_timer(&tbl->proxy_timer, sched_next); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 2da59a0ac4a..3994680c08b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -78,7 +78,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, goto err; if (!rtnl_trylock()) - return -ERESTARTSYS; + return restart_syscall(); if (dev_isalive(net)) { if ((ret = (*set)(net, new)) == 0) @@ -225,7 +225,8 @@ static ssize_t store_ifalias(struct device *dev, struct device_attribute *attr, if (len > 0 && buf[len - 1] == '\n') --count; - rtnl_lock(); + if (!rtnl_trylock()) + return restart_syscall(); ret = dev_set_alias(netdev, buf, count); rtnl_unlock(); @@ -238,7 +239,8 @@ static ssize_t show_ifalias(struct device *dev, const struct net_device *netdev = to_net_dev(dev); ssize_t ret = 0; - rtnl_lock(); + if (!rtnl_trylock()) + return restart_syscall(); if (netdev->ifalias) ret = sprintf(buf, "%s\n", netdev->ifalias); rtnl_unlock(); @@ -497,7 +499,6 @@ int netdev_register_kobject(struct net_device *net) dev->platform_data = net; dev->groups = groups; - BUILD_BUG_ON(BUS_ID_SIZE < IFNAMSIZ); dev_set_name(dev, "%s", net->name); #ifdef CONFIG_SYSFS diff --git a/net/core/net-traces.c b/net/core/net-traces.c index c8fb45665e4..f1e982c508b 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -19,11 +19,14 @@ #include <linux/workqueue.h> #include <linux/netlink.h> #include <linux/net_dropmon.h> -#include <trace/skb.h> #include <asm/unaligned.h> #include <asm/bitops.h> +#define CREATE_TRACE_POINTS +#include <trace/events/skb.h> +#include <trace/events/napi.h> -DEFINE_TRACE(kfree_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); + +EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index e3bebd36f05..197283072cc 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -115,41 +115,34 @@ static void net_free(struct net *net) kmem_cache_free(net_cachep, net); } -struct net *copy_net_ns(unsigned long flags, struct net *old_net) +static struct net *net_create(void) { - struct net *new_net = NULL; - int err; - - get_net(old_net); - - if (!(flags & CLONE_NEWNET)) - return old_net; - - err = -ENOMEM; - new_net = net_alloc(); - if (!new_net) - goto out_err; + struct net *net; + int rv; + net = net_alloc(); + if (!net) + return ERR_PTR(-ENOMEM); mutex_lock(&net_mutex); - err = setup_net(new_net); - if (!err) { + rv = setup_net(net); + if (rv == 0) { rtnl_lock(); - list_add_tail(&new_net->list, &net_namespace_list); + list_add_tail(&net->list, &net_namespace_list); rtnl_unlock(); } mutex_unlock(&net_mutex); + if (rv < 0) { + net_free(net); + return ERR_PTR(rv); + } + return net; +} - if (err) - goto out_free; -out: - put_net(old_net); - return new_net; - -out_free: - net_free(new_net); -out_err: - new_net = ERR_PTR(err); - goto out; +struct net *copy_net_ns(unsigned long flags, struct net *old_net) +{ + if (!(flags & CLONE_NEWNET)) + return get_net(old_net); + return net_create(); } static void cleanup_net(struct work_struct *work) @@ -203,9 +196,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) static int __init net_ns_init(void) { struct net_generic *ng; - int err; - printk(KERN_INFO "net_namespace: %zd bytes\n", sizeof(struct net)); #ifdef CONFIG_NET_NS net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), SMP_CACHE_BYTES, @@ -224,15 +215,14 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); mutex_lock(&net_mutex); - err = setup_net(&init_net); + if (setup_net(&init_net)) + panic("Could not setup the initial network namespace"); rtnl_lock(); list_add_tail(&init_net.list, &net_namespace_list); rtnl_unlock(); mutex_unlock(&net_mutex); - if (err) - panic("Could not setup the initial network namespace"); return 0; } @@ -498,7 +488,7 @@ int net_assign_generic(struct net *net, int id, void *data) */ ng->len = id; - memcpy(&ng->ptr, &old_ng->ptr, old_ng->len); + memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); rcu_assign_pointer(net->gen, ng); call_rcu(&old_ng->rcu, net_generic_release); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 64f51eec657..1b76eb11deb 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -24,6 +24,7 @@ #include <net/tcp.h> #include <net/udp.h> #include <asm/unaligned.h> +#include <trace/events/napi.h> /* * We maintain a small pool of fully-sized skbs, to make sure the @@ -137,6 +138,7 @@ static int poll_one_napi(struct netpoll_info *npinfo, set_bit(NAPI_STATE_NPSVC, &napi->state); work = napi->poll(napi, budget); + trace_napi_poll(napi); clear_bit(NAPI_STATE_NPSVC, &napi->state); atomic_dec(&trapped); @@ -300,8 +302,11 @@ static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; tries > 0; --tries) { if (__netif_tx_trylock(txq)) { - if (!netif_tx_queue_stopped(txq)) + if (!netif_tx_queue_stopped(txq)) { status = ops->ndo_start_xmit(skb, dev); + if (status == NETDEV_TX_OK) + txq_trans_update(txq); + } __netif_tx_unlock(txq); if (status == NETDEV_TX_OK) @@ -314,6 +319,11 @@ static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) udelay(USEC_PER_POLL); } + + WARN_ONCE(!irqs_disabled(), + "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n", + dev->name, ops->ndo_start_xmit); + local_irq_restore(flags); } @@ -735,7 +745,7 @@ int netpoll_setup(struct netpoll *np) np->name); break; } - cond_resched(); + msleep(1); } /* If carrier appears to come up instantly, we don't diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 0666a827bc6..19b8c20e98a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3438,6 +3438,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) retry_now: 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++; @@ -3690,8 +3691,7 @@ out1: #ifdef CONFIG_XFRM free_SAs(pkt_dev); #endif - if (pkt_dev->flows) - vfree(pkt_dev->flows); + vfree(pkt_dev->flows); kfree(pkt_dev); return err; } @@ -3790,8 +3790,7 @@ static int pktgen_remove_device(struct pktgen_thread *t, #ifdef CONFIG_XFRM free_SAs(pkt_dev); #endif - if (pkt_dev->flows) - vfree(pkt_dev->flows); + vfree(pkt_dev->flows); kfree(pkt_dev); return 0; } diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c index 86234923a3b..79687dfd695 100644 --- a/net/core/skb_dma_map.c +++ b/net/core/skb_dma_map.c @@ -20,7 +20,7 @@ int skb_dma_map(struct device *dev, struct sk_buff *skb, if (dma_mapping_error(dev, map)) goto out_err; - sp->dma_maps[0] = map; + sp->dma_head = map; for (i = 0; i < sp->nr_frags; i++) { skb_frag_t *fp = &sp->frags[i]; @@ -28,9 +28,8 @@ int skb_dma_map(struct device *dev, struct sk_buff *skb, fp->size, dir); if (dma_mapping_error(dev, map)) goto unwind; - sp->dma_maps[i + 1] = map; + sp->dma_maps[i] = map; } - sp->num_dma_maps = i + 1; return 0; @@ -38,10 +37,10 @@ unwind: while (--i >= 0) { skb_frag_t *fp = &sp->frags[i]; - dma_unmap_page(dev, sp->dma_maps[i + 1], + dma_unmap_page(dev, sp->dma_maps[i], fp->size, dir); } - dma_unmap_single(dev, sp->dma_maps[0], + dma_unmap_single(dev, sp->dma_head, skb_headlen(skb), dir); out_err: return -ENOMEM; @@ -54,12 +53,12 @@ void skb_dma_unmap(struct device *dev, struct sk_buff *skb, struct skb_shared_info *sp = skb_shinfo(skb); int i; - dma_unmap_single(dev, sp->dma_maps[0], + dma_unmap_single(dev, sp->dma_head, skb_headlen(skb), dir); for (i = 0; i < sp->nr_frags; i++) { skb_frag_t *fp = &sp->frags[i]; - dma_unmap_page(dev, sp->dma_maps[i + 1], + dma_unmap_page(dev, sp->dma_maps[i], fp->size, dir); } } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e505b5392e1..9e0597d189b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -39,6 +39,7 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/kmemcheck.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> @@ -65,7 +66,7 @@ #include <asm/uaccess.h> #include <asm/system.h> -#include <trace/skb.h> +#include <trace/events/skb.h> #include "kmap_skb.h" @@ -201,6 +202,12 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; + kmemcheck_annotate_bitfield(skb, flags1); + kmemcheck_annotate_bitfield(skb, flags2); +#ifdef NET_SKBUFF_DATA_USES_OFFSET + skb->mac_header = ~0U; +#endif + /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); atomic_set(&shinfo->dataref, 1); @@ -210,13 +217,15 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, shinfo->gso_type = 0; shinfo->ip6_frag_id = 0; shinfo->tx_flags.flags = 0; - shinfo->frag_list = NULL; + skb_frag_list_init(skb); memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps)); if (fclone) { struct sk_buff *child = skb + 1; atomic_t *fclone_ref = (atomic_t *) (child + 1); + kmemcheck_annotate_bitfield(child, flags1); + kmemcheck_annotate_bitfield(child, flags2); skb->fclone = SKB_FCLONE_ORIG; atomic_set(fclone_ref, 1); @@ -323,7 +332,7 @@ static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; - for (list = skb_shinfo(skb)->frag_list; list; list = list->next) + skb_walk_frags(skb, list) skb_get(list); } @@ -338,7 +347,7 @@ static void skb_release_data(struct sk_buff *skb) put_page(skb_shinfo(skb)->frags[i].page); } - if (skb_shinfo(skb)->frag_list) + if (skb_has_frags(skb)) skb_drop_fraglist(skb); kfree(skb->head); @@ -381,7 +390,7 @@ static void kfree_skbmem(struct sk_buff *skb) static void skb_release_head_state(struct sk_buff *skb) { - dst_release(skb->dst); + skb_dst_drop(skb); #ifdef CONFIG_XFRM secpath_put(skb->sp); #endif @@ -503,7 +512,7 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size) shinfo->gso_type = 0; shinfo->ip6_frag_id = 0; shinfo->tx_flags.flags = 0; - shinfo->frag_list = NULL; + skb_frag_list_init(skb); memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps)); memset(skb, 0, offsetof(struct sk_buff, tail)); @@ -521,13 +530,12 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->transport_header = old->transport_header; new->network_header = old->network_header; new->mac_header = old->mac_header; - new->dst = dst_clone(old->dst); + skb_dst_set(new, dst_clone(skb_dst(old))); #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif memcpy(new->cb, old->cb, sizeof(old->cb)); - new->csum_start = old->csum_start; - new->csum_offset = old->csum_offset; + new->csum = old->csum; new->local_df = old->local_df; new->pkt_type = old->pkt_type; new->ip_summed = old->ip_summed; @@ -538,6 +546,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif new->protocol = old->protocol; new->mark = old->mark; + new->iif = old->iif; __nf_copy(new, old); #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) @@ -550,10 +559,17 @@ 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); } +/* + * You should not add any new code to this function. Add it to + * __copy_skb_header above instead. + */ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) { #define C(x) n->x = skb->x @@ -569,16 +585,11 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->cloned = 1; n->nohdr = 0; n->destructor = NULL; - C(iif); C(tail); C(end); C(head); C(data); C(truesize); -#if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE) - C(do_not_encrypt); - C(requeue); -#endif atomic_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); @@ -633,6 +644,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; + + kmemcheck_annotate_bitfield(n, flags1); + kmemcheck_annotate_bitfield(n, flags2); n->fclone = SKB_FCLONE_UNAVAILABLE; } @@ -655,7 +669,8 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) /* {transport,network,mac}_header are relative to skb->head */ new->transport_header += offset; new->network_header += offset; - new->mac_header += offset; + if (skb_mac_header_was_set(new)) + new->mac_header += offset; #endif skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; @@ -755,7 +770,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) skb_shinfo(n)->nr_frags = i; } - if (skb_shinfo(skb)->frag_list) { + if (skb_has_frags(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } @@ -818,7 +833,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) get_page(skb_shinfo(skb)->frags[i].page); - if (skb_shinfo(skb)->frag_list) + if (skb_has_frags(skb)) skb_clone_fraglist(skb); skb_release_data(skb); @@ -837,7 +852,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->tail += off; skb->transport_header += off; skb->network_header += off; - skb->mac_header += off; + if (skb_mac_header_was_set(skb)) + skb->mac_header += off; skb->csum_start += nhead; skb->cloned = 0; skb->hdr_len = 0; @@ -929,7 +945,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, #ifdef NET_SKBUFF_DATA_USES_OFFSET n->transport_header += off; n->network_header += off; - n->mac_header += off; + if (skb_mac_header_was_set(skb)) + n->mac_header += off; #endif return n; @@ -1090,7 +1107,7 @@ drop_pages: for (; i < nfrags; i++) put_page(skb_shinfo(skb)->frags[i].page); - if (skb_shinfo(skb)->frag_list) + if (skb_has_frags(skb)) skb_drop_fraglist(skb); goto done; } @@ -1185,7 +1202,7 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ - if (!skb_shinfo(skb)->frag_list) + if (!skb_has_frags(skb)) goto pull_pages; /* Estimate size of pulled pages. */ @@ -1282,8 +1299,9 @@ EXPORT_SYMBOL(__pskb_pull_tail); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { - int i, copy; int start = skb_headlen(skb); + struct sk_buff *frag_iter; + int i, copy; if (offset > (int)skb->len - len) goto fault; @@ -1325,28 +1343,23 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_bits(list, offset - start, - to, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - to += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_bits(frag_iter, offset - start, to, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to += copy; } + start = end; } if (!len) return 0; @@ -1531,6 +1544,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, }; + struct sk_buff *frag_iter; struct sock *sk = skb->sk; /* @@ -1545,13 +1559,11 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, /* * now see if we have a frag_list to map */ - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list && tlen; list = list->next) { - if (__skb_splice_bits(list, &offset, &tlen, &spd, sk)) - break; - } + skb_walk_frags(skb, frag_iter) { + if (!tlen) + break; + if (__skb_splice_bits(frag_iter, &offset, &tlen, &spd, sk)) + break; } done: @@ -1590,8 +1602,9 @@ done: int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { - int i, copy; int start = skb_headlen(skb); + struct sk_buff *frag_iter; + int i, copy; if (offset > (int)skb->len - len) goto fault; @@ -1632,28 +1645,24 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_store_bits(list, offset - start, - from, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - from += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_store_bits(frag_iter, offset - start, + from, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + from += copy; } + start = end; } if (!len) return 0; @@ -1670,6 +1679,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; int pos = 0; /* Checksum header. */ @@ -1709,29 +1719,25 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - __wsum csum2; - if (copy > len) - copy = len; - csum2 = skb_checksum(list, offset - start, - copy, 0); - csum = csum_block_add(csum, csum2, pos); - if ((len -= copy) == 0) - return csum; - offset += copy; - pos += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + __wsum csum2; + if (copy > len) + copy = len; + csum2 = skb_checksum(frag_iter, offset - start, + copy, 0); + csum = csum_block_add(csum, csum2, pos); + if ((len -= copy) == 0) + return csum; + offset += copy; + pos += copy; } + start = end; } BUG_ON(len); @@ -1746,6 +1752,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; int pos = 0; /* Copy header. */ @@ -1790,31 +1797,27 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + __wsum csum2; + int end; - for (; list; list = list->next) { - __wsum csum2; - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - csum2 = skb_copy_and_csum_bits(list, - offset - start, - to, copy, 0); - csum = csum_block_add(csum, csum2, pos); - if ((len -= copy) == 0) - return csum; - offset += copy; - to += copy; - pos += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + csum2 = skb_copy_and_csum_bits(frag_iter, + offset - start, + to, copy, 0); + csum = csum_block_add(csum, csum2, pos); + if ((len -= copy) == 0) + return csum; + offset += copy; + to += copy; + pos += copy; } + start = end; } BUG_ON(len); return csum; @@ -2324,8 +2327,7 @@ next_skb: st->frag_data = NULL; } - if (st->root_skb == st->cur_skb && - skb_shinfo(st->root_skb)->frag_list) { + if (st->root_skb == st->cur_skb && skb_has_frags(st->root_skb)) { st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; @@ -2636,7 +2638,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) } else skb_get(fskb2); - BUG_ON(skb_shinfo(nskb)->frag_list); + SKB_FRAG_ASSERT(nskb); skb_shinfo(nskb)->frag_list = fskb2; } @@ -2661,30 +2663,40 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) { struct sk_buff *p = *head; struct sk_buff *nskb; + struct skb_shared_info *skbinfo = skb_shinfo(skb); + struct skb_shared_info *pinfo = skb_shinfo(p); unsigned int headroom; unsigned int len = skb_gro_len(skb); + unsigned int offset = skb_gro_offset(skb); + unsigned int headlen = skb_headlen(skb); if (p->len + len >= 65536) return -E2BIG; - if (skb_shinfo(p)->frag_list) + if (pinfo->frag_list) goto merge; - else if (skb_headlen(skb) <= skb_gro_offset(skb)) { - if (skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags > - MAX_SKB_FRAGS) + else if (headlen <= offset) { + skb_frag_t *frag; + skb_frag_t *frag2; + int i = skbinfo->nr_frags; + int nr_frags = pinfo->nr_frags + i; + + offset -= headlen; + + if (nr_frags > MAX_SKB_FRAGS) return -E2BIG; - skb_shinfo(skb)->frags[0].page_offset += - skb_gro_offset(skb) - skb_headlen(skb); - skb_shinfo(skb)->frags[0].size -= - skb_gro_offset(skb) - skb_headlen(skb); + pinfo->nr_frags = nr_frags; + skbinfo->nr_frags = 0; - memcpy(skb_shinfo(p)->frags + skb_shinfo(p)->nr_frags, - skb_shinfo(skb)->frags, - skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t)); + frag = pinfo->frags + nr_frags; + frag2 = skbinfo->frags + i; + do { + *--frag = *--frag2; + } while (--i); - skb_shinfo(p)->nr_frags += skb_shinfo(skb)->nr_frags; - skb_shinfo(skb)->nr_frags = 0; + frag->page_offset += offset; + frag->size -= offset; skb->truesize -= skb->data_len; skb->len -= skb->data_len; @@ -2715,7 +2727,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) *NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p); skb_shinfo(nskb)->frag_list = p; - skb_shinfo(nskb)->gso_size = skb_shinfo(p)->gso_size; + skb_shinfo(nskb)->gso_size = pinfo->gso_size; skb_header_release(p); nskb->prev = p; @@ -2730,16 +2742,13 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) p = nskb; merge: - if (skb_gro_offset(skb) > skb_headlen(skb)) { - skb_shinfo(skb)->frags[0].page_offset += - skb_gro_offset(skb) - skb_headlen(skb); - skb_shinfo(skb)->frags[0].size -= - skb_gro_offset(skb) - skb_headlen(skb); - skb_gro_reset_offset(skb); - skb_gro_pull(skb, skb_headlen(skb)); + if (offset > headlen) { + skbinfo->frags[0].page_offset += offset - headlen; + skbinfo->frags[0].size -= offset - headlen; + offset = headlen; } - __skb_pull(skb, skb_gro_offset(skb)); + __skb_pull(skb, offset); p->prev->next = skb; p->prev = skb; @@ -2786,6 +2795,7 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; int elt = 0; if (copy > 0) { @@ -2819,26 +2829,22 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; + skb_walk_frags(skb, frag_iter) { + int end; - WARN_ON(start > offset + len); + WARN_ON(start > offset + len); - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - elt += __skb_to_sgvec(list, sg+elt, offset - start, - copy); - if ((len -= copy) == 0) - return elt; - offset += copy; - } - start = end; + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + elt += __skb_to_sgvec(frag_iter, sg+elt, offset - start, + copy); + if ((len -= copy) == 0) + return elt; + offset += copy; } + start = end; } BUG_ON(len); return elt; @@ -2886,7 +2892,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) return -ENOMEM; /* Easy case. Most of packets will go this way. */ - if (!skb_shinfo(skb)->frag_list) { + if (!skb_has_frags(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more @@ -2921,7 +2927,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) if (skb1->next == NULL && tailbits) { if (skb_shinfo(skb1)->nr_frags || - skb_shinfo(skb1)->frag_list || + skb_has_frags(skb1) || skb_tailroom(skb1) < tailbits) ntail = tailbits + 128; } @@ -2930,7 +2936,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) skb_cloned(skb1) || ntail || skb_shinfo(skb1)->nr_frags || - skb_shinfo(skb1)->frag_list) { + skb_has_frags(skb1)) { struct sk_buff *skb2; /* Fuck, we are miserable poor guys... */ @@ -3016,12 +3022,12 @@ EXPORT_SYMBOL_GPL(skb_tstamp_tx); */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { - if (unlikely(start > skb->len - 2) || - unlikely((int)start + off > skb->len - 2)) { + if (unlikely(start > skb_headlen(skb)) || + unlikely((int)start + off > skb_headlen(skb) - 2)) { if (net_ratelimit()) printk(KERN_WARNING "bad partial csum: csum=%u/%u len=%u\n", - start, off, skb->len); + start, off, skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; diff --git a/net/core/sock.c b/net/core/sock.c index 7dbf3ffb35c..bbb25be7ddf 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -155,6 +155,7 @@ static const char *af_family_key_strings[AF_MAX+1] = { "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , + "sk_lock-AF_IEEE802154", "sk_lock-AF_MAX" }; static const char *af_family_slock_key_strings[AF_MAX+1] = { @@ -170,6 +171,7 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-27" , "slock-28" , "slock-AF_CAN" , "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , + "slock-AF_IEEE802154", "slock-AF_MAX" }; static const char *af_family_clock_key_strings[AF_MAX+1] = { @@ -185,6 +187,7 @@ static const char *af_family_clock_key_strings[AF_MAX+1] = { "clock-27" , "clock-28" , "clock-AF_CAN" , "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , + "clock-AF_IEEE802154", "clock-AF_MAX" }; @@ -212,6 +215,7 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; /* Maximal space eaten by iovec or ancilliary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); +EXPORT_SYMBOL(sysctl_optmem_max); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -444,7 +448,7 @@ 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) { - struct sock *sk=sock->sk; + struct sock *sk = sock->sk; int val; int valbool; struct linger ling; @@ -463,15 +467,15 @@ int sock_setsockopt(struct socket *sock, int level, int optname, if (get_user(val, (int __user *)optval)) return -EFAULT; - valbool = val?1:0; + valbool = val ? 1 : 0; lock_sock(sk); - switch(optname) { + switch (optname) { case SO_DEBUG: - if (val && !capable(CAP_NET_ADMIN)) { + if (val && !capable(CAP_NET_ADMIN)) ret = -EACCES; - } else + else sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: @@ -582,7 +586,7 @@ set_rcvbuf: ret = -EINVAL; /* 1003.1g */ break; } - if (copy_from_user(&ling,optval,sizeof(ling))) { + if (copy_from_user(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } @@ -627,7 +631,7 @@ set_rcvbuf: case SO_TIMESTAMPING: if (val & ~SOF_TIMESTAMPING_MASK) { - ret = EINVAL; + ret = -EINVAL; break; } sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE, @@ -690,9 +694,8 @@ set_rcvbuf: case SO_MARK: if (!capable(CAP_NET_ADMIN)) ret = -EPERM; - else { + else sk->sk_mark = val; - } break; /* We implement the SO_SNDLOWAT etc to @@ -704,6 +707,7 @@ set_rcvbuf: release_sock(sk); return ret; } +EXPORT_SYMBOL(sock_setsockopt); int sock_getsockopt(struct socket *sock, int level, int optname, @@ -727,7 +731,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, memset(&v, 0, sizeof(v)); - switch(optname) { + switch (optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); break; @@ -762,7 +766,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_ERROR: v.val = -sock_error(sk); - if (v.val==0) + if (v.val == 0) v.val = xchg(&sk->sk_err_soft, 0); break; @@ -816,7 +820,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_RCVTIMEO: - lv=sizeof(struct timeval); + lv = sizeof(struct timeval); if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { v.tm.tv_sec = 0; v.tm.tv_usec = 0; @@ -827,7 +831,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_SNDTIMEO: - lv=sizeof(struct timeval); + lv = sizeof(struct timeval); if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { v.tm.tv_sec = 0; v.tm.tv_usec = 0; @@ -842,7 +846,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_SNDLOWAT: - v.val=1; + v.val = 1; break; case SO_PASSCRED: @@ -915,13 +919,19 @@ static inline void sock_lock_init(struct sock *sk) af_family_keys + sk->sk_family); } +/* + * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, + * even temporarly, because of RCU lookups. sk_node should also be left as is. + */ static void sock_copy(struct sock *nsk, const struct sock *osk) { #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif - - memcpy(nsk, osk, osk->sk_prot->obj_size); + BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) != + sizeof(osk->sk_node) + sizeof(osk->sk_refcnt)); + memcpy(&nsk->sk_copy_start, &osk->sk_copy_start, + osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start)); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); @@ -935,12 +945,29 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, struct kmem_cache *slab; slab = prot->slab; - if (slab != NULL) - sk = kmem_cache_alloc(slab, priority); + if (slab != NULL) { + sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); + if (!sk) + return sk; + if (priority & __GFP_ZERO) { + /* + * caches using SLAB_DESTROY_BY_RCU should let + * sk_node.next un-modified. Special care is taken + * when initializing object to zero. + */ + if (offsetof(struct sock, sk_node.next) != 0) + memset(sk, 0, offsetof(struct sock, sk_node.next)); + memset(&sk->sk_node.pprev, 0, + prot->obj_size - offsetof(struct sock, + sk_node.pprev)); + } + } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { + kmemcheck_annotate_bitfield(sk, flags); + if (security_sk_alloc(sk, family, priority)) goto out_free; @@ -1002,8 +1029,9 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, return sk; } +EXPORT_SYMBOL(sk_alloc); -void sk_free(struct sock *sk) +static void __sk_free(struct sock *sk) { struct sk_filter *filter; @@ -1027,6 +1055,18 @@ void sk_free(struct sock *sk) sk_prot_free(sk->sk_prot_creator, sk); } +void sk_free(struct sock *sk) +{ + /* + * We substract one from sk_wmem_alloc and can know if + * some packets are still in some tx queue. + * If not null, sock_wfree() will call __sk_free(sk) later + */ + if (atomic_dec_and_test(&sk->sk_wmem_alloc)) + __sk_free(sk); +} +EXPORT_SYMBOL(sk_free); + /* * Last sock_put should drop referrence to sk->sk_net. It has already * been dropped in sk_change_net. Taking referrence to stopping namespace @@ -1065,7 +1105,10 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; atomic_set(&newsk->sk_rmem_alloc, 0); - atomic_set(&newsk->sk_wmem_alloc, 0); + /* + * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) + */ + atomic_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); skb_queue_head_init(&newsk->sk_receive_queue); skb_queue_head_init(&newsk->sk_write_queue); @@ -1103,6 +1146,11 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) newsk->sk_err = 0; newsk->sk_priority = 0; + /* + * Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.txt for details) + */ + smp_wmb(); atomic_set(&newsk->sk_refcnt, 2); /* @@ -1126,7 +1174,6 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) out: return newsk; } - EXPORT_SYMBOL_GPL(sk_clone); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) @@ -1170,13 +1217,20 @@ void __init sk_init(void) void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; + int res; /* In case it might be waiting for more memory. */ - atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + res = atomic_sub_return(skb->truesize, &sk->sk_wmem_alloc); if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) sk->sk_write_space(sk); - sock_put(sk); + /* + * if sk_wmem_alloc reached 0, we are last user and should + * free this sock, as sk_free() call could not do it. + */ + if (res == 0) + __sk_free(sk); } +EXPORT_SYMBOL(sock_wfree); /* * Read buffer destructor automatically called from kfree_skb. @@ -1188,6 +1242,7 @@ void sock_rfree(struct sk_buff *skb) atomic_sub(skb->truesize, &sk->sk_rmem_alloc); sk_mem_uncharge(skb->sk, skb->truesize); } +EXPORT_SYMBOL(sock_rfree); int sock_i_uid(struct sock *sk) @@ -1199,6 +1254,7 @@ int sock_i_uid(struct sock *sk) read_unlock(&sk->sk_callback_lock); return uid; } +EXPORT_SYMBOL(sock_i_uid); unsigned long sock_i_ino(struct sock *sk) { @@ -1209,6 +1265,7 @@ unsigned long sock_i_ino(struct sock *sk) read_unlock(&sk->sk_callback_lock); return ino; } +EXPORT_SYMBOL(sock_i_ino); /* * Allocate a skb from the socket's send buffer. @@ -1217,7 +1274,7 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { - struct sk_buff * skb = alloc_skb(size, priority); + struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); return skb; @@ -1225,6 +1282,7 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, } return NULL; } +EXPORT_SYMBOL(sock_wmalloc); /* * Allocate a skb from the socket's receive buffer. @@ -1261,6 +1319,7 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) } return NULL; } +EXPORT_SYMBOL(sock_kmalloc); /* * Free an option memory block. @@ -1270,11 +1329,12 @@ void sock_kfree_s(struct sock *sk, void *mem, int size) kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } +EXPORT_SYMBOL(sock_kfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ -static long sock_wait_for_wmem(struct sock * sk, long timeo) +static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); @@ -1392,6 +1452,7 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, { return sock_alloc_send_pskb(sk, size, 0, noblock, errcode); } +EXPORT_SYMBOL(sock_alloc_send_skb); static void __lock_sock(struct sock *sk) { @@ -1460,7 +1521,6 @@ int sk_wait_data(struct sock *sk, long *timeo) finish_wait(sk->sk_sleep, &wait); return rc; } - EXPORT_SYMBOL(sk_wait_data); /** @@ -1541,7 +1601,6 @@ suppress_allocation: atomic_sub(amt, prot->memory_allocated); return 0; } - EXPORT_SYMBOL(__sk_mem_schedule); /** @@ -1560,7 +1619,6 @@ void __sk_mem_reclaim(struct sock *sk) (atomic_read(prot->memory_allocated) < prot->sysctl_mem[0])) *prot->memory_pressure = 0; } - EXPORT_SYMBOL(__sk_mem_reclaim); @@ -1575,78 +1633,92 @@ int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_bind); int sock_no_connect(struct socket *sock, struct sockaddr *saddr, int len, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int *len, int peer) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_getname); -unsigned int sock_no_poll(struct file * file, struct socket *sock, poll_table *pt) +unsigned int sock_no_poll(struct file *file, struct socket *sock, poll_table *pt) { return 0; } +EXPORT_SYMBOL(sock_no_poll); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_shutdown); int sock_no_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_setsockopt); int sock_no_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_getsockopt); int sock_no_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } +EXPORT_SYMBOL(sock_no_mmap); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -1660,6 +1732,7 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, siz kunmap(page); return res; } +EXPORT_SYMBOL(sock_no_sendpage); /* * Default Socket Callbacks @@ -1668,7 +1741,7 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, siz static void sock_def_wakeup(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_all(sk->sk_sleep); read_unlock(&sk->sk_callback_lock); } @@ -1676,7 +1749,7 @@ static void sock_def_wakeup(struct sock *sk) static void sock_def_error_report(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_poll(sk->sk_sleep, POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); read_unlock(&sk->sk_callback_lock); @@ -1685,7 +1758,7 @@ static void sock_def_error_report(struct sock *sk) static void sock_def_readable(struct sock *sk, int len) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); @@ -1700,7 +1773,7 @@ static void sock_def_write_space(struct sock *sk) * progress. --DaveM */ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND); @@ -1723,6 +1796,7 @@ void sk_send_sigurg(struct sock *sk) if (send_sigurg(&sk->sk_socket->file->f_owner)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } +EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) @@ -1730,7 +1804,6 @@ void sk_reset_timer(struct sock *sk, struct timer_list* timer, if (!mod_timer(timer, expires)) sock_hold(sk); } - EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) @@ -1738,7 +1811,6 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer) if (timer_pending(timer) && del_timer(timer)) __sock_put(sk); } - EXPORT_SYMBOL(sk_stop_timer); void sock_init_data(struct socket *sock, struct sock *sk) @@ -1794,9 +1866,16 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); + /* + * Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.txt for details) + */ + smp_wmb(); atomic_set(&sk->sk_refcnt, 1); + atomic_set(&sk->sk_wmem_alloc, 1); atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { @@ -1812,7 +1891,6 @@ void lock_sock_nested(struct sock *sk, int subclass) mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); } - EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) @@ -1895,7 +1973,6 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname, return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(sock_common_getsockopt); #ifdef CONFIG_COMPAT @@ -1925,7 +2002,6 @@ int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, msg->msg_namelen = addr_len; return err; } - EXPORT_SYMBOL(sock_common_recvmsg); /* @@ -1938,7 +2014,6 @@ int sock_common_setsockopt(struct socket *sock, int level, int optname, return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(sock_common_setsockopt); #ifdef CONFIG_COMPAT @@ -1989,7 +2064,6 @@ void sk_common_release(struct sock *sk) sk_refcnt_debug_release(sk); sock_put(sk); } - EXPORT_SYMBOL(sk_common_release); static DEFINE_RWLOCK(proto_list_lock); @@ -2171,7 +2245,6 @@ out_free_sock_slab: out: return -ENOBUFS; } - EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) @@ -2198,7 +2271,6 @@ void proto_unregister(struct proto *prot) prot->twsk_prot->twsk_slab = NULL; } } - EXPORT_SYMBOL(proto_unregister); #ifdef CONFIG_PROC_FS @@ -2324,33 +2396,3 @@ static int __init proto_init(void) subsys_initcall(proto_init); #endif /* PROC_FS */ - -EXPORT_SYMBOL(sk_alloc); -EXPORT_SYMBOL(sk_free); -EXPORT_SYMBOL(sk_send_sigurg); -EXPORT_SYMBOL(sock_alloc_send_skb); -EXPORT_SYMBOL(sock_init_data); -EXPORT_SYMBOL(sock_kfree_s); -EXPORT_SYMBOL(sock_kmalloc); -EXPORT_SYMBOL(sock_no_accept); -EXPORT_SYMBOL(sock_no_bind); -EXPORT_SYMBOL(sock_no_connect); -EXPORT_SYMBOL(sock_no_getname); -EXPORT_SYMBOL(sock_no_getsockopt); -EXPORT_SYMBOL(sock_no_ioctl); -EXPORT_SYMBOL(sock_no_listen); -EXPORT_SYMBOL(sock_no_mmap); -EXPORT_SYMBOL(sock_no_poll); -EXPORT_SYMBOL(sock_no_recvmsg); -EXPORT_SYMBOL(sock_no_sendmsg); -EXPORT_SYMBOL(sock_no_sendpage); -EXPORT_SYMBOL(sock_no_setsockopt); -EXPORT_SYMBOL(sock_no_shutdown); -EXPORT_SYMBOL(sock_no_socketpair); -EXPORT_SYMBOL(sock_rfree); -EXPORT_SYMBOL(sock_setsockopt); -EXPORT_SYMBOL(sock_wfree); -EXPORT_SYMBOL(sock_wmalloc); -EXPORT_SYMBOL(sock_i_uid); -EXPORT_SYMBOL(sock_i_ino); -EXPORT_SYMBOL(sysctl_optmem_max); diff --git a/net/core/stream.c b/net/core/stream.c index 8727cead64a..a37debfeb1b 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -33,7 +33,8 @@ void sk_stream_write_space(struct sock *sk) clear_bit(SOCK_NOSPACE, &sock->flags); if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | + POLLWRNORM | POLLWRBAND); if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); } diff --git a/net/core/user_dma.c b/net/core/user_dma.c index 164b090d5ac..25d717ebc92 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -51,6 +51,7 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; dma_cookie_t cookie = 0; /* Copy header. */ @@ -94,31 +95,28 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - copy = end - offset; - if (copy > 0) { - if (copy > len) - copy = len; - cookie = dma_skb_copy_datagram_iovec(chan, list, - offset - start, to, copy, - pinned_list); - if (cookie < 0) - goto fault; - len -= copy; - if (len == 0) - goto end; - offset += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + copy = end - offset; + if (copy > 0) { + if (copy > len) + copy = len; + cookie = dma_skb_copy_datagram_iovec(chan, frag_iter, + offset - start, + to, copy, + pinned_list); + if (cookie < 0) + goto fault; + len -= copy; + if (len == 0) + goto end; + offset += copy; } + start = end; } end: diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d1dd95289b8..a0a36c9e6cc 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -452,7 +452,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; - struct flowi fl = { .oif = skb->rtable->rt_iif, + struct flowi fl = { .oif = skb_rtable(skb)->rt_iif, .nl_u = { .ip4_u = { .daddr = ip_hdr(skb)->saddr, .saddr = ip_hdr(skb)->daddr, @@ -507,14 +507,14 @@ static void dccp_v4_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) const struct iphdr *rxiph; struct sk_buff *skb; struct dst_entry *dst; - struct net *net = dev_net(rxskb->dst->dev); + struct net *net = dev_net(skb_dst(rxskb)->dev); struct sock *ctl_sk = net->dccp.v4_ctl_sk; /* Never send a reset in response to a reset. */ if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; - if (rxskb->rtable->rt_type != RTN_LOCAL) + if (skb_rtable(rxskb)->rt_type != RTN_LOCAL) return; dst = dccp_v4_route_skb(net, ctl_sk, rxskb); @@ -528,7 +528,7 @@ static void dccp_v4_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) rxiph = ip_hdr(rxskb); dccp_hdr(skb)->dccph_checksum = dccp_v4_csum_finish(skb, rxiph->saddr, rxiph->daddr); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); bh_lock_sock(ctl_sk); err = ip_build_and_send_pkt(skb, ctl_sk, @@ -567,7 +567,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); /* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */ - if (skb->rtable->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return 0; /* discard, don't send a reset here */ if (dccp_bad_service_code(sk, service)) { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index b963f35c65f..3e70faab298 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -85,7 +85,7 @@ static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) } static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); @@ -314,8 +314,9 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) struct ipv6hdr *rxip6h; struct sk_buff *skb; struct flowi fl; - struct net *net = dev_net(rxskb->dst->dev); + struct net *net = dev_net(skb_dst(rxskb)->dev); struct sock *ctl_sk = net->dccp.v6_ctl_sk; + struct dst_entry *dst; if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; @@ -342,8 +343,9 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) security_skb_classify_flow(rxskb, &fl); /* sk = NULL, but it is safe for now. RST socket required. */ - if (!ip6_dst_lookup(ctl_sk, &skb->dst, &fl)) { - if (xfrm_lookup(net, &skb->dst, &fl, NULL, 0) >= 0) { + if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { + if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { + skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl, NULL, 0); DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); diff --git a/net/dccp/output.c b/net/dccp/output.c index 36bcc00654d..c96119fda68 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -196,7 +196,7 @@ void dccp_write_space(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible(sk->sk_sleep); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) @@ -350,7 +350,7 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, /* Reserve space for headers. */ skb_reserve(skb, sk->sk_prot->max_header); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); dreq = dccp_rsk(req); if (inet_rsk(req)->acked) /* increase ISS upon retransmission */ diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 314a1b5c033..1bca9205104 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -311,7 +311,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, unsigned int mask; struct sock *sk = sock->sk; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); if (sk->sk_state == DCCP_LISTEN) return inet_csk_listen_poll(sk); @@ -1066,7 +1066,7 @@ static int __init dccp_init(void) (dccp_hashinfo.ehash_size - 1)) dccp_hashinfo.ehash_size--; dccp_hashinfo.ehash = (struct inet_ehash_bucket *) - __get_free_pages(GFP_ATOMIC, ehash_order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order); } while (!dccp_hashinfo.ehash && --ehash_order > 0); if (!dccp_hashinfo.ehash) { @@ -1091,7 +1091,7 @@ static int __init dccp_init(void) bhash_order > 0) continue; dccp_hashinfo.bhash = (struct inet_bind_hashbucket *) - __get_free_pages(GFP_ATOMIC, bhash_order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order); } while (!dccp_hashinfo.bhash && --bhash_order >= 0); if (!dccp_hashinfo.bhash) { @@ -1159,6 +1159,7 @@ static void __exit dccp_fini(void) kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); + percpu_counter_destroy(&dccp_orphan_count); } module_init(dccp_init); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 9647d911f91..77d40289653 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1075,6 +1075,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) int err = 0; unsigned char type; long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + struct dst_entry *dst; lock_sock(sk); @@ -1102,8 +1103,9 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) } release_sock(sk); - dst_release(xchg(&newsk->sk_dst_cache, skb->dst)); - skb->dst = NULL; + dst = skb_dst(skb); + dst_release(xchg(&newsk->sk_dst_cache, dst)); + skb_dst_set(skb, NULL); DN_SK(newsk)->state = DN_CR; DN_SK(newsk)->addrrem = cb->src_port; @@ -1238,7 +1240,7 @@ static int dn_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return val; case TIOCOUTQ: - amount = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; err = put_user(amount, (int __user *)arg); @@ -1250,14 +1252,8 @@ static int dn_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (skb) { amount = skb->len; } else { - skb = sk->sk_receive_queue.next; - for (;;) { - if (skb == - (struct sk_buff *)&sk->sk_receive_queue) - break; + skb_queue_walk(&sk->sk_receive_queue, skb) amount += skb->len; - skb = skb->next; - } } release_sock(sk); err = put_user(amount, (int __user *)arg); @@ -1644,13 +1640,13 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us static int dn_data_ready(struct sock *sk, struct sk_buff_head *q, int flags, int target) { - struct sk_buff *skb = q->next; + struct sk_buff *skb; int len = 0; if (flags & MSG_OOB) return !skb_queue_empty(q) ? 1 : 0; - while(skb != (struct sk_buff *)q) { + skb_queue_walk(q, skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); len += skb->len; @@ -1666,8 +1662,6 @@ static int dn_data_ready(struct sock *sk, struct sk_buff_head *q, int flags, int /* minimum data length for read exceeded */ if (len >= target) return 1; - - skb = skb->next; } return 0; @@ -1683,7 +1677,7 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock, size_t target = size > 1 ? 1 : 0; size_t copied = 0; int rv = 0; - struct sk_buff *skb, *nskb; + struct sk_buff *skb, *n; struct dn_skb_cb *cb = NULL; unsigned char eor = 0; long timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); @@ -1758,7 +1752,7 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock, finish_wait(sk->sk_sleep, &wait); } - for(skb = queue->next; skb != (struct sk_buff *)queue; skb = nskb) { + skb_queue_walk_safe(queue, skb, n) { unsigned int chunk = skb->len; cb = DN_SKB_CB(skb); @@ -1775,7 +1769,6 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock, skb_pull(skb, chunk); eor = cb->nsp_flags & 0x40; - nskb = skb->next; if (skb->len == 0) { skb_unlink(skb, queue); @@ -2420,6 +2413,8 @@ static void __exit decnet_exit(void) proc_net_remove(&init_net, "decnet"); proto_unregister(&dn_proto); + + rcu_barrier_bh(); /* Wait for completion of call_rcu_bh()'s */ } module_exit(decnet_exit); #endif diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 05b5aa05e50..923786bd6d0 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -204,7 +204,7 @@ static void dn_short_error_report(struct neighbour *neigh, struct sk_buff *skb) static int dn_neigh_output_packet(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; @@ -224,7 +224,7 @@ static int dn_neigh_output_packet(struct sk_buff *skb) static int dn_long_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_long_packet) + 3; @@ -270,7 +270,7 @@ static int dn_long_output(struct sk_buff *skb) static int dn_short_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; @@ -313,7 +313,7 @@ static int dn_short_output(struct sk_buff *skb) */ static int dn_phase3_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index 5d8a2a56fd3..932408dca86 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -578,6 +578,7 @@ out: static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig, struct sk_buff_head *queue) { int err; + int skb_len; /* Cast skb->rcvbuf to unsigned... It's pointless, but reduces number of warnings when compiling with -W --ANK @@ -592,22 +593,12 @@ static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig if (err) goto out; + skb_len = skb->len; skb_set_owner_r(skb, sk); skb_queue_tail(queue, skb); - /* This code only runs from BH or BH protected context. - * Therefore the plain read_lock is ok here. -DaveM - */ - read_lock(&sk->sk_callback_lock); - if (!sock_flag(sk, SOCK_DEAD)) { - struct socket *sock = sk->sk_socket; - wake_up_interruptible(sk->sk_sleep); - if (sock && sock->fasync_list && - !test_bit(SOCK_ASYNC_WAITDATA, &sock->flags)) - __kill_fasync(sock->fasync_list, sig, - (sig == SIGURG) ? POLL_PRI : POLL_IN); - } - read_unlock(&sk->sk_callback_lock); + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_data_ready(sk, skb_len); out: return err; } diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 2013c25b7f5..a65e929ce76 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -85,7 +85,7 @@ static void dn_nsp_send(struct sk_buff *skb) dst = sk_dst_check(sk, 0); if (dst) { try_again: - skb->dst = dst; + skb_dst_set(skb, dst); dst_output(skb); return; } @@ -382,7 +382,7 @@ int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb, struct sk_buff { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb2, *list, *ack = NULL; + struct sk_buff *skb2, *n, *ack = NULL; int wakeup = 0; int try_retrans = 0; unsigned long reftime = cb->stamp; @@ -390,9 +390,7 @@ int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb, struct sk_buff unsigned short xmit_count; unsigned short segnum; - skb2 = q->next; - list = (struct sk_buff *)q; - while(list != skb2) { + skb_queue_walk_safe(q, skb2, n) { struct dn_skb_cb *cb2 = DN_SKB_CB(skb2); if (dn_before_or_equal(cb2->segnum, acknum)) @@ -400,8 +398,6 @@ int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb, struct sk_buff /* printk(KERN_DEBUG "ack: %s %04x %04x\n", ack ? "ACK" : "SKIP", (int)cb2->segnum, (int)acknum); */ - skb2 = skb2->next; - if (ack == NULL) continue; @@ -586,7 +582,7 @@ static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, * to be able to send disc packets out which have no socket * associations. */ - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); dst_output(skb); } @@ -615,7 +611,7 @@ void dn_nsp_return_disc(struct sk_buff *skb, unsigned char msgflg, int ddl = 0; gfp_t gfp = GFP_ATOMIC; - dn_nsp_do_disc(NULL, msgflg, reason, gfp, skb->dst, ddl, + dn_nsp_do_disc(NULL, msgflg, reason, gfp, skb_dst(skb), ddl, NULL, cb->src_port, cb->dst_port); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 0cc4394117d..1d6ca8a98dc 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -678,7 +678,7 @@ out: static int dn_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; struct net_device *dev = dst->dev; struct dn_skb_cb *cb = DN_SKB_CB(skb); @@ -717,7 +717,7 @@ error: static int dn_forward(struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct dn_dev *dn_db = dst->dev->dn_ptr; struct dn_route *rt; struct neighbour *neigh = dst->neighbour; @@ -730,7 +730,7 @@ static int dn_forward(struct sk_buff *skb) goto drop; /* Ensure that we have enough space for headers */ - rt = (struct dn_route *)skb->dst; + rt = (struct dn_route *)skb_dst(skb); header_len = dn_db->use_long ? 21 : 6; if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+header_len)) goto drop; @@ -1392,7 +1392,8 @@ make_route: goto e_neighbour; hash = dn_hash(rt->fl.fld_src, rt->fl.fld_dst); - dn_insert_route(rt, hash, (struct dn_route **)&skb->dst); + dn_insert_route(rt, hash, &rt); + skb_dst_set(skb, &rt->u.dst); done: if (neigh) @@ -1424,7 +1425,7 @@ static int dn_route_input(struct sk_buff *skb) struct dn_skb_cb *cb = DN_SKB_CB(skb); unsigned hash = dn_hash(cb->src, cb->dst); - if (skb->dst) + if (skb_dst(skb)) return 0; rcu_read_lock(); @@ -1437,7 +1438,7 @@ static int dn_route_input(struct sk_buff *skb) (rt->fl.iif == cb->iif)) { dst_use(&rt->u.dst, jiffies); rcu_read_unlock(); - skb->dst = (struct dst_entry *)rt; + skb_dst_set(skb, (struct dst_entry *)rt); return 0; } } @@ -1449,7 +1450,7 @@ static int dn_route_input(struct sk_buff *skb) static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, int nowait, unsigned int flags) { - struct dn_route *rt = (struct dn_route *)skb->dst; + struct dn_route *rt = (struct dn_route *)skb_dst(skb); struct rtmsg *r; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); @@ -1554,7 +1555,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void err = dn_route_input(skb); local_bh_enable(); memset(cb, 0, sizeof(struct dn_skb_cb)); - rt = (struct dn_route *)skb->dst; + rt = (struct dn_route *)skb_dst(skb); if (!err && -rt->u.dst.error) err = rt->u.dst.error; } else { @@ -1570,7 +1571,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void skb->dev = NULL; if (err) goto out_free; - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; @@ -1622,15 +1623,15 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) rt = rcu_dereference(rt->u.dst.dn_next), idx++) { if (idx < s_idx) continue; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); rcu_read_unlock_bh(); goto done; } - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); } rcu_read_unlock_bh(); } diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 14fbca55e90..72495f25269 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -115,7 +115,7 @@ static int dn_fib_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) } static int dn_fib_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_rule_hdr *frh, + struct fib_rule_hdr *frh, struct nlattr **tb) { int err = -EINVAL; @@ -192,7 +192,7 @@ unsigned dnet_addr_type(__le16 addr) } static int dn_fib_rule_fill(struct fib_rule *rule, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_rule_hdr *frh) + struct fib_rule_hdr *frh) { struct dn_fib_rule *r = (struct dn_fib_rule *)rule; diff --git a/net/dsa/mv88e6xxx.c b/net/dsa/mv88e6xxx.c index 4e4d8b5ad03..efe661a9def 100644 --- a/net/dsa/mv88e6xxx.c +++ b/net/dsa/mv88e6xxx.c @@ -418,7 +418,7 @@ static int mv88e6xxx_stats_wait(struct dsa_switch *ds) int i; for (i = 0; i < 10; i++) { - ret = REG_READ(REG_GLOBAL2, 0x1d); + ret = REG_READ(REG_GLOBAL, 0x1d); if ((ret & 0x8000) == 0) return 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ed131181215..2175e6d5cc8 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -67,7 +67,7 @@ static int dsa_slave_open(struct net_device *dev) return -ENETDOWN; if (compare_ether_addr(dev->dev_addr, master->dev_addr)) { - err = dev_unicast_add(master, dev->dev_addr, ETH_ALEN); + err = dev_unicast_add(master, dev->dev_addr); if (err < 0) goto out; } @@ -90,7 +90,7 @@ clear_allmulti: dev_set_allmulti(master, -1); del_unicast: if (compare_ether_addr(dev->dev_addr, master->dev_addr)) - dev_unicast_delete(master, dev->dev_addr, ETH_ALEN); + dev_unicast_delete(master, dev->dev_addr); out: return err; } @@ -108,7 +108,7 @@ static int dsa_slave_close(struct net_device *dev) dev_set_promiscuity(master, -1); if (compare_ether_addr(dev->dev_addr, master->dev_addr)) - dev_unicast_delete(master, dev->dev_addr, ETH_ALEN); + dev_unicast_delete(master, dev->dev_addr); return 0; } @@ -147,13 +147,13 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a) goto out; if (compare_ether_addr(addr->sa_data, master->dev_addr)) { - err = dev_unicast_add(master, addr->sa_data, ETH_ALEN); + err = dev_unicast_add(master, addr->sa_data); if (err < 0) return err; } if (compare_ether_addr(dev->dev_addr, master->dev_addr)) - dev_unicast_delete(master, dev->dev_addr, ETH_ALEN); + dev_unicast_delete(master, dev->dev_addr); out: memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index 6f479fa522c..f0bbc57926c 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -520,6 +520,7 @@ static int econet_getname(struct socket *sock, struct sockaddr *uaddr, if (peer) return -EOPNOTSUPP; + memset(sec, 0, sizeof(*sec)); mutex_lock(&econet_mutex); sk = sock->sk; @@ -540,8 +541,7 @@ static void econet_destroy_timer(unsigned long data) { struct sock *sk=(struct sock *)data; - if (!atomic_read(&sk->sk_wmem_alloc) && - !atomic_read(&sk->sk_rmem_alloc)) { + if (!sk_has_allocations(sk)) { sk_free(sk); return; } @@ -579,8 +579,7 @@ static int econet_release(struct socket *sock) skb_queue_purge(&sk->sk_receive_queue); - if (atomic_read(&sk->sk_rmem_alloc) || - atomic_read(&sk->sk_wmem_alloc)) { + if (sk_has_allocations(sk)) { sk->sk_timer.data = (unsigned long)sk; sk->sk_timer.expires = jiffies + HZ; sk->sk_timer.function = econet_destroy_timer; @@ -901,15 +900,10 @@ static void aun_tx_ack(unsigned long seq, int result) struct ec_cb *eb; spin_lock_irqsave(&aun_queue_lock, flags); - skb = skb_peek(&aun_queue); - while (skb && skb != (struct sk_buff *)&aun_queue) - { - struct sk_buff *newskb = skb->next; + skb_queue_walk(&aun_queue, skb) { eb = (struct ec_cb *)&skb->cb; if (eb->seq == seq) goto foundit; - - skb = newskb; } spin_unlock_irqrestore(&aun_queue_lock, flags); printk(KERN_DEBUG "AUN: unknown sequence %ld\n", seq); @@ -982,23 +976,18 @@ static void aun_data_available(struct sock *sk, int slen) static void ab_cleanup(unsigned long h) { - struct sk_buff *skb; + struct sk_buff *skb, *n; unsigned long flags; spin_lock_irqsave(&aun_queue_lock, flags); - skb = skb_peek(&aun_queue); - while (skb && skb != (struct sk_buff *)&aun_queue) - { - struct sk_buff *newskb = skb->next; + skb_queue_walk_safe(&aun_queue, skb, n) { struct ec_cb *eb = (struct ec_cb *)&skb->cb; - if ((jiffies - eb->start) > eb->timeout) - { + if ((jiffies - eb->start) > eb->timeout) { tx_result(skb->sk, eb->cookie, ECTYPE_TRANSMIT_NOT_PRESENT); skb_unlink(skb, &aun_queue); kfree_skb(skb); } - skb = newskb; } spin_unlock_irqrestore(&aun_queue_lock, flags); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 280352aba40..5a883affecd 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -337,11 +337,6 @@ const struct header_ops eth_header_ops ____cacheline_aligned = { void ether_setup(struct net_device *dev) { dev->header_ops = ð_header_ops; -#ifdef CONFIG_COMPAT_NET_DEV_OPS - dev->change_mtu = eth_change_mtu; - dev->set_mac_address = eth_mac_addr; - dev->validate_addr = eth_validate_addr; -#endif dev->type = ARPHRD_ETHER; dev->hard_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig new file mode 100644 index 00000000000..1c1de97d264 --- /dev/null +++ b/net/ieee802154/Kconfig @@ -0,0 +1,12 @@ +config IEEE802154 + tristate "IEEE Std 802.15.4 Low-Rate Wireless Personal Area Networks support (EXPERIMENTAL)" + depends on EXPERIMENTAL + ---help--- + IEEE Std 802.15.4 defines a low data rate, low power and low + complexity short range wireless personal area networks. It was + designed to organise networks of sensors, switches, etc automation + devices. Maximum allowed data rate is 250 kb/s and typical personal + operating space around 10m. + + Say Y here to compile LR-WPAN support into the kernel or say M to + compile it as modules. diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile new file mode 100644 index 00000000000..f99338a2610 --- /dev/null +++ b/net/ieee802154/Makefile @@ -0,0 +1,5 @@ +obj-$(CONFIG_IEEE802154) += nl802154.o af_802154.o +nl802154-y := netlink.o nl_policy.o +af_802154-y := af_ieee802154.o raw.o dgram.o + +ccflags-y += -Wall -DDEBUG diff --git a/net/ieee802154/af802154.h b/net/ieee802154/af802154.h new file mode 100644 index 00000000000..b1ec5253752 --- /dev/null +++ b/net/ieee802154/af802154.h @@ -0,0 +1,36 @@ +/* + * Internal interfaces for ieee 802.15.4 address family. + * + * Copyright 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. + * + * Written by: + * Sergey Lapin <slapin@ossfans.org> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + */ + +#ifndef AF802154_H +#define AF802154_H + +struct sk_buff; +struct net_devce; +extern struct proto ieee802154_raw_prot; +extern struct proto ieee802154_dgram_prot; +void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb); +int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb); +struct net_device *ieee802154_get_dev(struct net *net, + struct ieee802154_addr *addr); + +#endif diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c new file mode 100644 index 00000000000..af661805b9f --- /dev/null +++ b/net/ieee802154/af_ieee802154.c @@ -0,0 +1,368 @@ +/* + * IEEE802154.4 socket interface + * + * Copyright 2007, 2008 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. + * + * Written by: + * Sergey Lapin <slapin@ossfans.org> + * Maxim Gorbachyov <maxim.gorbachev@siemens.com> + */ + +#include <linux/net.h> +#include <linux/capability.h> +#include <linux/module.h> +#include <linux/if_arp.h> +#include <linux/if.h> +#include <linux/termios.h> /* For TIOCOUTQ/INQ */ +#include <linux/list.h> +#include <net/datalink.h> +#include <net/psnap.h> +#include <net/sock.h> +#include <net/tcp_states.h> +#include <net/route.h> + +#include <net/ieee802154/af_ieee802154.h> +#include <net/ieee802154/netdevice.h> + +#include "af802154.h" + +/* + * Utility function for families + */ +struct net_device *ieee802154_get_dev(struct net *net, + struct ieee802154_addr *addr) +{ + struct net_device *dev = NULL; + struct net_device *tmp; + u16 pan_id, short_addr; + + switch (addr->addr_type) { + case IEEE802154_ADDR_LONG: + rtnl_lock(); + dev = dev_getbyhwaddr(net, ARPHRD_IEEE802154, addr->hwaddr); + if (dev) + dev_hold(dev); + rtnl_unlock(); + break; + case IEEE802154_ADDR_SHORT: + if (addr->pan_id == 0xffff || + addr->short_addr == IEEE802154_ADDR_UNDEF || + addr->short_addr == 0xffff) + break; + + rtnl_lock(); + + for_each_netdev(net, tmp) { + if (tmp->type != ARPHRD_IEEE802154) + continue; + + pan_id = ieee802154_mlme_ops(tmp)->get_pan_id(tmp); + short_addr = + ieee802154_mlme_ops(tmp)->get_short_addr(tmp); + + if (pan_id == addr->pan_id && + short_addr == addr->short_addr) { + dev = tmp; + dev_hold(dev); + break; + } + } + + rtnl_unlock(); + break; + default: + pr_warning("Unsupported ieee802154 address type: %d\n", + addr->addr_type); + break; + } + + return dev; +} + +static int ieee802154_sock_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + + if (sk) { + sock->sk = NULL; + sk->sk_prot->close(sk, 0); + } + return 0; +} +static int ieee802154_sock_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len) +{ + struct sock *sk = sock->sk; + + return sk->sk_prot->sendmsg(iocb, sk, msg, len); +} + +static int ieee802154_sock_bind(struct socket *sock, struct sockaddr *uaddr, + int addr_len) +{ + struct sock *sk = sock->sk; + + if (sk->sk_prot->bind) + return sk->sk_prot->bind(sk, uaddr, addr_len); + + return sock_no_bind(sock, uaddr, addr_len); +} + +static int ieee802154_sock_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags) +{ + struct sock *sk = sock->sk; + + if (uaddr->sa_family == AF_UNSPEC) + return sk->sk_prot->disconnect(sk, flags); + + return sk->sk_prot->connect(sk, uaddr, addr_len); +} + +static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, + unsigned int cmd) +{ + struct ifreq ifr; + int ret = -ENOIOCTLCMD; + struct net_device *dev; + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + + ifr.ifr_name[IFNAMSIZ-1] = 0; + + 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) + ret = dev->netdev_ops->ndo_do_ioctl(dev, &ifr, cmd); + + if (!ret && copy_to_user(arg, &ifr, sizeof(struct ifreq))) + ret = -EFAULT; + dev_put(dev); + + return ret; +} + +static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + struct sock *sk = sock->sk; + + switch (cmd) { + case SIOCGSTAMP: + return sock_get_timestamp(sk, (struct timeval __user *)arg); + case SIOCGSTAMPNS: + return sock_get_timestampns(sk, (struct timespec __user *)arg); + case SIOCGIFADDR: + case SIOCSIFADDR: + return ieee802154_dev_ioctl(sk, (struct ifreq __user *)arg, + cmd); + default: + if (!sk->sk_prot->ioctl) + return -ENOIOCTLCMD; + return sk->sk_prot->ioctl(sk, cmd, arg); + } +} + +static const struct proto_ops ieee802154_raw_ops = { + .family = PF_IEEE802154, + .owner = THIS_MODULE, + .release = ieee802154_sock_release, + .bind = ieee802154_sock_bind, + .connect = ieee802154_sock_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = ieee802154_sock_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = ieee802154_sock_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif +}; + +static const struct proto_ops ieee802154_dgram_ops = { + .family = PF_IEEE802154, + .owner = THIS_MODULE, + .release = ieee802154_sock_release, + .bind = ieee802154_sock_bind, + .connect = ieee802154_sock_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = ieee802154_sock_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = ieee802154_sock_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif +}; + + +/* + * Create a socket. Initialise the socket, blank the addresses + * set the state. + */ +static int ieee802154_create(struct net *net, struct socket *sock, + int protocol) +{ + struct sock *sk; + int rc; + struct proto *proto; + const struct proto_ops *ops; + + if (net != &init_net) + return -EAFNOSUPPORT; + + switch (sock->type) { + case SOCK_RAW: + proto = &ieee802154_raw_prot; + ops = &ieee802154_raw_ops; + break; + case SOCK_DGRAM: + proto = &ieee802154_dgram_prot; + ops = &ieee802154_dgram_ops; + break; + default: + rc = -ESOCKTNOSUPPORT; + goto out; + } + + rc = -ENOMEM; + sk = sk_alloc(net, PF_IEEE802154, GFP_KERNEL, proto); + if (!sk) + goto out; + rc = 0; + + sock->ops = ops; + + sock_init_data(sock, sk); + /* FIXME: sk->sk_destruct */ + sk->sk_family = PF_IEEE802154; + + /* Checksums on by default */ + sock_set_flag(sk, SOCK_ZAPPED); + + if (sk->sk_prot->hash) + sk->sk_prot->hash(sk); + + if (sk->sk_prot->init) { + rc = sk->sk_prot->init(sk); + if (rc) + sk_common_release(sk); + } +out: + return rc; +} + +static struct net_proto_family ieee802154_family_ops = { + .family = PF_IEEE802154, + .create = ieee802154_create, + .owner = THIS_MODULE, +}; + +static int ieee802154_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + if (!netif_running(dev)) + return -ENODEV; + pr_debug("got frame, type %d, dev %p\n", dev->type, dev); +#ifdef DEBUG + print_hex_dump_bytes("ieee802154_rcv ", DUMP_PREFIX_NONE, skb->data, skb->len); +#endif + + if (!net_eq(dev_net(dev), &init_net)) + goto drop; + + ieee802154_raw_deliver(dev, skb); + + if (dev->type != ARPHRD_IEEE802154) + goto drop; + + if (skb->pkt_type != PACKET_OTHERHOST) + return ieee802154_dgram_deliver(dev, skb); + +drop: + kfree_skb(skb); + return NET_RX_DROP; +} + + +static struct packet_type ieee802154_packet_type = { + .type = __constant_htons(ETH_P_IEEE802154), + .func = ieee802154_rcv, +}; + +static int __init af_ieee802154_init(void) +{ + int rc = -EINVAL; + + rc = proto_register(&ieee802154_raw_prot, 1); + if (rc) + goto out; + + rc = proto_register(&ieee802154_dgram_prot, 1); + if (rc) + goto err_dgram; + + /* Tell SOCKET that we are alive */ + rc = sock_register(&ieee802154_family_ops); + if (rc) + goto err_sock; + dev_add_pack(&ieee802154_packet_type); + + rc = 0; + goto out; + +err_sock: + proto_unregister(&ieee802154_dgram_prot); +err_dgram: + proto_unregister(&ieee802154_raw_prot); +out: + return rc; +} +static void __exit af_ieee802154_remove(void) +{ + dev_remove_pack(&ieee802154_packet_type); + sock_unregister(PF_IEEE802154); + proto_unregister(&ieee802154_dgram_prot); + proto_unregister(&ieee802154_raw_prot); +} + +module_init(af_ieee802154_init); +module_exit(af_ieee802154_remove); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETPROTO(PF_IEEE802154); diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c new file mode 100644 index 00000000000..ba8b214dda8 --- /dev/null +++ b/net/ieee802154/dgram.c @@ -0,0 +1,409 @@ +/* + * ZigBee socket interface + * + * Copyright 2007, 2008 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. + * + * Written by: + * Sergey Lapin <slapin@ossfans.org> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + */ + +#include <linux/net.h> +#include <linux/module.h> +#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 <asm/ioctls.h> + +#include "af802154.h" + +static HLIST_HEAD(dgram_head); +static DEFINE_RWLOCK(dgram_lock); + +struct dgram_sock { + struct sock sk; + + int bound; + struct ieee802154_addr src_addr; + struct ieee802154_addr dst_addr; +}; + +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); + sk_add_node(sk, &dgram_head); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + write_unlock_bh(&dgram_lock); +} + +static void dgram_unhash(struct sock *sk) +{ + write_lock_bh(&dgram_lock); + if (sk_del_node_init(sk)) + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + write_unlock_bh(&dgram_lock); +} + +static int dgram_init(struct sock *sk) +{ + struct dgram_sock *ro = dgram_sk(sk); + + ro->dst_addr.addr_type = IEEE802154_ADDR_LONG; + ro->dst_addr.pan_id = 0xffff; + memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr)); + return 0; +} + +static void dgram_close(struct sock *sk, long timeout) +{ + sk_common_release(sk); +} + +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; + struct net_device *dev; + + ro->bound = 0; + + if (len < sizeof(*addr)) + return -EINVAL; + + if (addr->family != AF_IEEE802154) + return -EINVAL; + + lock_sock(sk); + + dev = ieee802154_get_dev(sock_net(sk), &addr->addr); + if (!dev) { + err = -ENODEV; + goto out; + } + + if (dev->type != ARPHRD_IEEE802154) { + err = -ENODEV; + goto out_put; + } + + memcpy(&ro->src_addr, &addr->addr, sizeof(struct ieee802154_addr)); + + ro->bound = 1; +out_put: + dev_put(dev); +out: + release_sock(sk); + + return err; +} + +static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg) +{ + switch (cmd) { + case SIOCOUTQ: + { + int amount = sk_wmem_alloc_get(sk); + + return put_user(amount, (int __user *)arg); + } + + case SIOCINQ: + { + struct sk_buff *skb; + unsigned long amount; + + amount = 0; + spin_lock_bh(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + if (skb != NULL) { + /* + * We will only return the amount + * of this packet since that is all + * that will be read. + */ + /* FIXME: parse the header for more correct value */ + amount = skb->len - (3+8+8); + } + spin_unlock_bh(&sk->sk_receive_queue.lock); + return put_user(amount, (int __user *)arg); + } + + } + return -ENOIOCTLCMD; +} + +/* FIXME: autobind */ +static int dgram_connect(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; + + if (len < sizeof(*addr)) + return -EINVAL; + + if (addr->family != AF_IEEE802154) + return -EINVAL; + + lock_sock(sk); + + if (!ro->bound) { + err = -ENETUNREACH; + goto out; + } + + memcpy(&ro->dst_addr, &addr->addr, sizeof(struct ieee802154_addr)); + +out: + release_sock(sk); + return err; +} + +static int dgram_disconnect(struct sock *sk, int flags) +{ + struct dgram_sock *ro = dgram_sk(sk); + + lock_sock(sk); + + ro->dst_addr.addr_type = IEEE802154_ADDR_LONG; + memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr)); + + release_sock(sk); + + return 0; +} + +static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t size) +{ + struct net_device *dev; + unsigned mtu; + struct sk_buff *skb; + struct dgram_sock *ro = dgram_sk(sk); + int err; + + if (msg->msg_flags & MSG_OOB) { + pr_debug("msg->msg_flags = 0x%x\n", msg->msg_flags); + return -EOPNOTSUPP; + } + + if (!ro->bound) + dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154); + else + dev = ieee802154_get_dev(sock_net(sk), &ro->src_addr); + + if (!dev) { + pr_debug("no dev\n"); + err = -ENXIO; + goto out; + } + mtu = dev->mtu; + pr_debug("name = %s, mtu = %u\n", dev->name, mtu); + + skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + size, + msg->msg_flags & MSG_DONTWAIT, + &err); + if (!skb) + goto out_dev; + + skb_reserve(skb, LL_RESERVED_SPACE(dev)); + + skb_reset_network_header(skb); + + mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA | 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); + if (err < 0) + goto out_skb; + + skb_reset_mac_header(skb); + + err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); + if (err < 0) + goto out_skb; + + if (size > mtu) { + pr_debug("size = %Zu, mtu = %u\n", size, mtu); + err = -EINVAL; + goto out_skb; + } + + skb->dev = dev; + skb->sk = sk; + skb->protocol = htons(ETH_P_IEEE802154); + + dev_put(dev); + + err = dev_queue_xmit(skb); + if (err > 0) + err = net_xmit_errno(err); + + return err ?: size; + +out_skb: + kfree_skb(skb); +out_dev: + dev_put(dev); +out: + return err; +} + +static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t len, int noblock, int flags, + int *addr_len) +{ + size_t copied = 0; + int err = -EOPNOTSUPP; + struct sk_buff *skb; + + skb = skb_recv_datagram(sk, flags, noblock, &err); + if (!skb) + goto out; + + copied = skb->len; + if (len < copied) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + + /* FIXME: skip headers if necessary ?! */ + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto done; + + sock_recv_timestamp(msg, sk, skb); + + if (flags & MSG_TRUNC) + copied = skb->len; +done: + skb_free_datagram(sk, skb); +out: + if (err) + return err; + return copied; +} + +static int dgram_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + if (sock_queue_rcv_skb(sk, skb) < 0) { + atomic_inc(&sk->sk_drops); + kfree_skb(skb); + return NET_RX_DROP; + } + + return NET_RX_SUCCESS; +} + +static inline int ieee802154_match_sock(u8 *hw_addr, u16 pan_id, + u16 short_addr, struct dgram_sock *ro) +{ + if (!ro->bound) + return 1; + + if (ro->src_addr.addr_type == IEEE802154_ADDR_LONG && + !memcmp(ro->src_addr.hwaddr, hw_addr, IEEE802154_ADDR_LEN)) + return 1; + + if (ro->src_addr.addr_type == IEEE802154_ADDR_SHORT && + pan_id == ro->src_addr.pan_id && + short_addr == ro->src_addr.short_addr) + return 1; + + return 0; +} + +int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) +{ + struct sock *sk, *prev = NULL; + struct hlist_node *node; + int ret = NET_RX_SUCCESS; + u16 pan_id, short_addr; + + /* Data frame processing */ + BUG_ON(dev->type != ARPHRD_IEEE802154); + + pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev); + + read_lock(&dgram_lock); + sk_for_each(sk, node, &dgram_head) { + if (ieee802154_match_sock(dev->dev_addr, pan_id, short_addr, + dgram_sk(sk))) { + if (prev) { + struct sk_buff *clone; + clone = skb_clone(skb, GFP_ATOMIC); + if (clone) + dgram_rcv_skb(prev, clone); + } + + prev = sk; + } + } + + if (prev) + dgram_rcv_skb(prev, skb); + else { + kfree_skb(skb); + ret = NET_RX_DROP; + } + read_unlock(&dgram_lock); + + return ret; +} + +static int dgram_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + return -EOPNOTSUPP; +} + +static int dgram_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user optlen) +{ + return -EOPNOTSUPP; +} + +struct proto ieee802154_dgram_prot = { + .name = "IEEE-802.15.4-MAC", + .owner = THIS_MODULE, + .obj_size = sizeof(struct dgram_sock), + .init = dgram_init, + .close = dgram_close, + .bind = dgram_bind, + .sendmsg = dgram_sendmsg, + .recvmsg = dgram_recvmsg, + .hash = dgram_hash, + .unhash = dgram_unhash, + .connect = dgram_connect, + .disconnect = dgram_disconnect, + .ioctl = dgram_ioctl, + .getsockopt = dgram_getsockopt, + .setsockopt = dgram_setsockopt, +}; + diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c new file mode 100644 index 00000000000..27eda9fdf3c --- /dev/null +++ b/net/ieee802154/netlink.c @@ -0,0 +1,529 @@ +/* + * Netlink inteface for IEEE 802.15.4 stack + * + * Copyright 2007, 2008 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. + * + * Written by: + * Sergey Lapin <slapin@ossfans.org> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + */ + +#include <linux/kernel.h> +#include <linux/if_arp.h> +#include <linux/netdevice.h> +#include <net/netlink.h> +#include <net/genetlink.h> +#include <linux/nl802154.h> +#include <net/ieee802154/af_ieee802154.h> +#include <net/ieee802154/nl802154.h> +#include <net/ieee802154/netdevice.h> + +static unsigned int ieee802154_seq_num; + +static struct genl_family ieee802154_coordinator_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = IEEE802154_NL_NAME, + .version = 1, + .maxattr = IEEE802154_ATTR_MAX, +}; + +static struct genl_multicast_group ieee802154_coord_mcgrp = { + .name = IEEE802154_MCAST_COORD_NAME, +}; + +static struct genl_multicast_group ieee802154_beacon_mcgrp = { + .name = IEEE802154_MCAST_BEACON_NAME, +}; + +/* Requests to userspace */ +static struct sk_buff *ieee802154_nl_create(int flags, u8 req) +{ + void *hdr; + struct sk_buff *msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + + if (!msg) + return NULL; + + hdr = genlmsg_put(msg, 0, ieee802154_seq_num++, + &ieee802154_coordinator_family, flags, req); + if (!hdr) { + nlmsg_free(msg); + return NULL; + } + + return msg; +} + +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)) + goto out; + + return genlmsg_multicast(msg, 0, ieee802154_coord_mcgrp.id, + GFP_ATOMIC); +out: + nlmsg_free(msg); + return -ENOBUFS; +} + +int ieee802154_nl_assoc_indic(struct net_device *dev, + struct ieee802154_addr *addr, u8 cap) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + if (addr->addr_type != IEEE802154_ADDR_LONG) { + pr_err("%s: received non-long source address!\n", __func__); + return -EINVAL; + } + + msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_INDIC); + 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(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, + addr->hwaddr); + + NLA_PUT_U8(msg, IEEE802154_ATTR_CAPABILITY, cap); + + return ieee802154_nl_finish(msg); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_assoc_indic); + +int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr, + u8 status) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_ASSOCIATE_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_U16(msg, IEEE802154_ATTR_SHORT_ADDR, short_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_assoc_confirm); + +int ieee802154_nl_disassoc_indic(struct net_device *dev, + struct ieee802154_addr *addr, u8 reason) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_INDIC); + 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); + + if (addr->addr_type == IEEE802154_ADDR_LONG) + NLA_PUT(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, + addr->hwaddr); + else + NLA_PUT_U16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, + addr->short_addr); + + NLA_PUT_U8(msg, IEEE802154_ATTR_REASON, reason); + + return ieee802154_nl_finish(msg); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_disassoc_indic); + +int ieee802154_nl_disassoc_confirm(struct net_device *dev, u8 status) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_DISASSOCIATE_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_disassoc_confirm); + +int ieee802154_nl_beacon_indic(struct net_device *dev, + u16 panid, u16 coord_addr) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_BEACON_NOTIFY_INDIC); + 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_U16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr); + NLA_PUT_U16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid); + + return ieee802154_nl_finish(msg); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_beacon_indic); + +int ieee802154_nl_scan_confirm(struct net_device *dev, + u8 status, u8 scan_type, u32 unscanned, + u8 *edl/* , struct list_head *pan_desc_list */) +{ + struct sk_buff *msg; + + pr_debug("%s\n", __func__); + + msg = ieee802154_nl_create(0, IEEE802154_SCAN_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); + NLA_PUT_U8(msg, IEEE802154_ATTR_SCAN_TYPE, scan_type); + NLA_PUT_U32(msg, IEEE802154_ATTR_CHANNELS, unscanned); + + if (edl) + NLA_PUT(msg, IEEE802154_ATTR_ED_LIST, 27, edl); + + return ieee802154_nl_finish(msg); + +nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(ieee802154_nl_scan_confirm); + +/* Requests from userspace */ +static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) +{ + struct net_device *dev; + + if (info->attrs[IEEE802154_ATTR_DEV_NAME]) { + char name[IFNAMSIZ + 1]; + nla_strlcpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME], + sizeof(name)); + 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])); + else + return NULL; + + if (!dev) + return NULL; + + if (dev->type != ARPHRD_IEEE802154) { + dev_put(dev); + return NULL; + } + + return dev; +} + +static int ieee802154_associate_req(struct sk_buff *skb, + struct genl_info *info) +{ + struct net_device *dev; + struct ieee802154_addr addr; + int ret = -EINVAL; + + if (!info->attrs[IEEE802154_ATTR_CHANNEL] || + !info->attrs[IEEE802154_ATTR_COORD_PAN_ID] || + (!info->attrs[IEEE802154_ATTR_COORD_HW_ADDR] && + !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]) || + !info->attrs[IEEE802154_ATTR_CAPABILITY]) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + if (info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]) { + addr.addr_type = IEEE802154_ADDR_LONG; + nla_memcpy(addr.hwaddr, + info->attrs[IEEE802154_ATTR_COORD_HW_ADDR], + IEEE802154_ADDR_LEN); + } else { + addr.addr_type = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_u16( + info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); + } + addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + + ret = ieee802154_mlme_ops(dev)->assoc_req(dev, &addr, + nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]), + nla_get_u8(info->attrs[IEEE802154_ATTR_CAPABILITY])); + + dev_put(dev); + return ret; +} + +static int ieee802154_associate_resp(struct sk_buff *skb, + struct genl_info *info) +{ + struct net_device *dev; + struct ieee802154_addr addr; + int ret = -EINVAL; + + if (!info->attrs[IEEE802154_ATTR_STATUS] || + !info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] || + !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + addr.addr_type = IEEE802154_ADDR_LONG; + nla_memcpy(addr.hwaddr, info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], + IEEE802154_ADDR_LEN); + addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + + + ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr, + nla_get_u16(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), + nla_get_u8(info->attrs[IEEE802154_ATTR_STATUS])); + + dev_put(dev); + return ret; +} + +static int ieee802154_disassociate_req(struct sk_buff *skb, + struct genl_info *info) +{ + struct net_device *dev; + struct ieee802154_addr addr; + int ret = -EINVAL; + + if ((!info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] && + !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) || + !info->attrs[IEEE802154_ATTR_REASON]) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + if (info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]) { + addr.addr_type = IEEE802154_ADDR_LONG; + nla_memcpy(addr.hwaddr, + info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], + IEEE802154_ADDR_LEN); + } else { + addr.addr_type = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_u16( + info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]); + } + addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + + ret = ieee802154_mlme_ops(dev)->disassoc_req(dev, &addr, + nla_get_u8(info->attrs[IEEE802154_ATTR_REASON])); + + dev_put(dev); + return ret; +} + +/* + * PANid, channel, beacon_order = 15, superframe_order = 15, + * PAN_coordinator, battery_life_extension = 0, + * coord_realignment = 0, security_enable = 0 +*/ +static int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *dev; + struct ieee802154_addr addr; + + u8 channel, bcn_ord, sf_ord; + int pan_coord, blx, coord_realign; + int ret; + + if (!info->attrs[IEEE802154_ATTR_COORD_PAN_ID] || + !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR] || + !info->attrs[IEEE802154_ATTR_CHANNEL] || + !info->attrs[IEEE802154_ATTR_BCN_ORD] || + !info->attrs[IEEE802154_ATTR_SF_ORD] || + !info->attrs[IEEE802154_ATTR_PAN_COORD] || + !info->attrs[IEEE802154_ATTR_BAT_EXT] || + !info->attrs[IEEE802154_ATTR_COORD_REALIGN] + ) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + addr.addr_type = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_u16( + info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); + addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + + channel = nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]); + bcn_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_BCN_ORD]); + sf_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_SF_ORD]); + pan_coord = nla_get_u8(info->attrs[IEEE802154_ATTR_PAN_COORD]); + 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, + bcn_ord, sf_ord, pan_coord, blx, coord_realign); + + dev_put(dev); + return ret; +} + +static int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *dev; + int ret; + u8 type; + u32 channels; + u8 duration; + + if (!info->attrs[IEEE802154_ATTR_SCAN_TYPE] || + !info->attrs[IEEE802154_ATTR_CHANNELS] || + !info->attrs[IEEE802154_ATTR_DURATION]) + return -EINVAL; + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + type = nla_get_u8(info->attrs[IEEE802154_ATTR_SCAN_TYPE]); + 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, + duration); + + dev_put(dev); + return ret; +} + +#define IEEE802154_OP(_cmd, _func) \ + { \ + .cmd = _cmd, \ + .policy = ieee802154_policy, \ + .doit = _func, \ + .dumpit = NULL, \ + .flags = GENL_ADMIN_PERM, \ + } + +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), +}; + +static int __init ieee802154_nl_init(void) +{ + int rc; + int i; + + rc = genl_register_family(&ieee802154_coordinator_family); + if (rc) + goto fail; + + rc = genl_register_mc_group(&ieee802154_coordinator_family, + &ieee802154_coord_mcgrp); + if (rc) + goto fail; + + rc = genl_register_mc_group(&ieee802154_coordinator_family, + &ieee802154_beacon_mcgrp); + if (rc) + goto fail; + + + for (i = 0; i < ARRAY_SIZE(ieee802154_coordinator_ops); i++) { + rc = genl_register_ops(&ieee802154_coordinator_family, + &ieee802154_coordinator_ops[i]); + if (rc) + goto fail; + } + + return 0; + +fail: + genl_unregister_family(&ieee802154_coordinator_family); + return rc; +} +module_init(ieee802154_nl_init); + +static void __exit ieee802154_nl_exit(void) +{ + genl_unregister_family(&ieee802154_coordinator_family); +} +module_exit(ieee802154_nl_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("ieee 802.15.4 configuration interface"); + diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c new file mode 100644 index 00000000000..c7d71d1adca --- /dev/null +++ b/net/ieee802154/nl_policy.c @@ -0,0 +1,52 @@ +/* + * nl802154.h + * + * Copyright (C) 2007, 2008 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 <net/netlink.h> +#include <linux/nl802154.h> + +#define NLA_HW_ADDR NLA_U64 + +struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { + [IEEE802154_ATTR_DEV_NAME] = { .type = NLA_STRING, }, + [IEEE802154_ATTR_DEV_INDEX] = { .type = NLA_U32, }, + + [IEEE802154_ATTR_STATUS] = { .type = NLA_U8, }, + [IEEE802154_ATTR_SHORT_ADDR] = { .type = NLA_U16, }, + [IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, }, + [IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, }, + [IEEE802154_ATTR_CHANNEL] = { .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, }, + [IEEE802154_ATTR_SRC_SHORT_ADDR] = { .type = NLA_U16, }, + [IEEE802154_ATTR_SRC_HW_ADDR] = { .type = NLA_HW_ADDR, }, + [IEEE802154_ATTR_SRC_PAN_ID] = { .type = NLA_U16, }, + [IEEE802154_ATTR_DEST_SHORT_ADDR] = { .type = NLA_U16, }, + [IEEE802154_ATTR_DEST_HW_ADDR] = { .type = NLA_HW_ADDR, }, + [IEEE802154_ATTR_DEST_PAN_ID] = { .type = NLA_U16, }, + + [IEEE802154_ATTR_CAPABILITY] = { .type = NLA_U8, }, + [IEEE802154_ATTR_REASON] = { .type = NLA_U8, }, + [IEEE802154_ATTR_SCAN_TYPE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CHANNELS] = { .type = NLA_U32, }, + [IEEE802154_ATTR_DURATION] = { .type = NLA_U8, }, + [IEEE802154_ATTR_ED_LIST] = { .len = 27 }, +}; diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c new file mode 100644 index 00000000000..9315977c4c6 --- /dev/null +++ b/net/ieee802154/raw.c @@ -0,0 +1,268 @@ +/* + * Raw IEEE 802.15.4 sockets + * + * Copyright 2007, 2008 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. + * + * Written by: + * Sergey Lapin <slapin@ossfans.org> + * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> + */ + +#include <linux/net.h> +#include <linux/module.h> +#include <linux/if_arp.h> +#include <linux/list.h> +#include <net/sock.h> +#include <net/ieee802154/af_ieee802154.h> + +#include "af802154.h" + +static HLIST_HEAD(raw_head); +static DEFINE_RWLOCK(raw_lock); + +static void raw_hash(struct sock *sk) +{ + write_lock_bh(&raw_lock); + sk_add_node(sk, &raw_head); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + write_unlock_bh(&raw_lock); +} + +static void raw_unhash(struct sock *sk) +{ + write_lock_bh(&raw_lock); + if (sk_del_node_init(sk)) + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + write_unlock_bh(&raw_lock); +} + +static void raw_close(struct sock *sk, long timeout) +{ + sk_common_release(sk); +} + +static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int len) +{ + struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; + int err = 0; + struct net_device *dev = NULL; + + if (len < sizeof(*addr)) + return -EINVAL; + + if (addr->family != AF_IEEE802154) + return -EINVAL; + + lock_sock(sk); + + dev = ieee802154_get_dev(sock_net(sk), &addr->addr); + if (!dev) { + err = -ENODEV; + goto out; + } + + if (dev->type != ARPHRD_IEEE802154_PHY && + dev->type != ARPHRD_IEEE802154) { + err = -ENODEV; + goto out_put; + } + + sk->sk_bound_dev_if = dev->ifindex; + sk_dst_reset(sk); + +out_put: + dev_put(dev); +out: + release_sock(sk); + + return err; +} + +static int raw_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + return -ENOTSUPP; +} + +static int raw_disconnect(struct sock *sk, int flags) +{ + return 0; +} + +static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t size) +{ + struct net_device *dev; + unsigned mtu; + struct sk_buff *skb; + int err; + + if (msg->msg_flags & MSG_OOB) { + pr_debug("msg->msg_flags = 0x%x\n", msg->msg_flags); + return -EOPNOTSUPP; + } + + lock_sock(sk); + if (!sk->sk_bound_dev_if) + dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154); + else + dev = dev_get_by_index(sock_net(sk), sk->sk_bound_dev_if); + release_sock(sk); + + if (!dev) { + pr_debug("no dev\n"); + err = -ENXIO; + goto out; + } + + mtu = dev->mtu; + pr_debug("name = %s, mtu = %u\n", dev->name, mtu); + + if (size > mtu) { + pr_debug("size = %Zu, mtu = %u\n", size, mtu); + err = -EINVAL; + goto out_dev; + } + + skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + size, + msg->msg_flags & MSG_DONTWAIT, &err); + if (!skb) + goto out_dev; + + skb_reserve(skb, LL_RESERVED_SPACE(dev)); + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + + err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); + if (err < 0) + goto out_skb; + + skb->dev = dev; + skb->sk = sk; + skb->protocol = htons(ETH_P_IEEE802154); + + dev_put(dev); + + err = dev_queue_xmit(skb); + if (err > 0) + err = net_xmit_errno(err); + + return err ?: size; + +out_skb: + kfree_skb(skb); +out_dev: + dev_put(dev); +out: + return err; +} + +static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len, int noblock, int flags, int *addr_len) +{ + size_t copied = 0; + int err = -EOPNOTSUPP; + struct sk_buff *skb; + + skb = skb_recv_datagram(sk, flags, noblock, &err); + if (!skb) + goto out; + + copied = skb->len; + if (len < copied) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto done; + + sock_recv_timestamp(msg, sk, skb); + + if (flags & MSG_TRUNC) + copied = skb->len; +done: + skb_free_datagram(sk, skb); +out: + if (err) + return err; + return copied; +} + +static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + if (sock_queue_rcv_skb(sk, skb) < 0) { + atomic_inc(&sk->sk_drops); + kfree_skb(skb); + return NET_RX_DROP; + } + + return NET_RX_SUCCESS; +} + + +void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb) +{ + struct sock *sk; + struct hlist_node *node; + + read_lock(&raw_lock); + sk_for_each(sk, node, &raw_head) { + bh_lock_sock(sk); + if (!sk->sk_bound_dev_if || + sk->sk_bound_dev_if == dev->ifindex) { + + struct sk_buff *clone; + + clone = skb_clone(skb, GFP_ATOMIC); + if (clone) + raw_rcv_skb(sk, clone); + } + bh_unlock_sock(sk); + } + read_unlock(&raw_lock); +} + +static int raw_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + return -EOPNOTSUPP; +} + +static int raw_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user optlen) +{ + return -EOPNOTSUPP; +} + +struct proto ieee802154_raw_prot = { + .name = "IEEE-802.15.4-RAW", + .owner = THIS_MODULE, + .obj_size = sizeof(struct sock), + .close = raw_close, + .bind = raw_bind, + .sendmsg = raw_sendmsg, + .recvmsg = raw_recvmsg, + .hash = raw_hash, + .unhash = raw_unhash, + .connect = raw_connect, + .disconnect = raw_disconnect, + .getsockopt = raw_getsockopt, + .setsockopt = raw_setsockopt, +}; + diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 5b919f7b45d..70491d9035e 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -273,29 +273,20 @@ config IP_PIMSM_V2 you want to play with it. config ARPD - bool "IP: ARP daemon support (EXPERIMENTAL)" - depends on EXPERIMENTAL + bool "IP: ARP daemon support" ---help--- - Normally, the kernel maintains an internal cache which maps IP - addresses to hardware addresses on the local network, so that - Ethernet/Token Ring/ etc. frames are sent to the proper address on - the physical networking layer. For small networks having a few - hundred directly connected hosts or less, keeping this address - resolution (ARP) cache inside the kernel works well. However, - maintaining an internal ARP cache does not work well for very large - switched networks, and will use a lot of kernel memory if TCP/IP - connections are made to many machines on the network. - - If you say Y here, the kernel's internal ARP cache will never grow - to more than 256 entries (the oldest entries are expired in a LIFO - manner) and communication will be attempted with the user space ARP - daemon arpd. Arpd then answers the address resolution request either - from its own cache or by asking the net. - - This code is experimental and also obsolete. If you want to use it, - you need to find a version of the daemon arpd on the net somewhere, - and you should also say Y to "Kernel/User network link driver", - below. If unsure, say N. + The kernel maintains an internal cache which maps IP addresses to + hardware addresses on the local network, so that Ethernet/Token Ring/ + etc. frames are sent to the proper address on the physical networking + layer. Normally, kernel uses the ARP protocol to resolve these + mappings. + + Saying Y here adds support to have an user space daemon to do this + resolution instead. This is useful for implementing an alternate + address resolution protocol (e.g. NHRP on mGRE tunnels) and also for + testing purposes. + + If unsure, say N. config SYN_COOKIES bool "IP: TCP syncookie support (disabled per default)" diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 7f03373b8c0..566ea6c4321 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -116,7 +116,6 @@ #include <linux/mroute.h> #endif -extern void ip_mc_drop_socket(struct sock *sk); /* The inetsw table contains everything that inet_create needs to * build a new socket. @@ -375,6 +374,7 @@ lookup_protocol: inet->uc_ttl = -1; inet->mc_loop = 1; inet->mc_ttl = 1; + inet->mc_all = 1; inet->mc_index = 0; inet->mc_list = NULL; @@ -1003,8 +1003,6 @@ void inet_register_protosw(struct inet_protosw *p) out: spin_unlock_bh(&inetsw_lock); - synchronize_net(); - return; out_permanent: @@ -1248,13 +1246,20 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff **pp = NULL; struct sk_buff *p; struct iphdr *iph; + unsigned int hlen; + unsigned int off; + unsigned int id; int flush = 1; int proto; - int id; - iph = skb_gro_header(skb, sizeof(*iph)); - if (unlikely(!iph)) - goto out; + off = skb_gro_offset(skb); + hlen = off + sizeof(*iph); + iph = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + iph = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!iph)) + goto out; + } proto = iph->protocol & (MAX_INET_PROTOS - 1); @@ -1269,9 +1274,9 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) goto out_unlock; - flush = ntohs(iph->tot_len) != skb_gro_len(skb) || - iph->frag_off != htons(IP_DF); - id = ntohs(iph->id); + id = ntohl(*(u32 *)&iph->id); + flush = (u16)((ntohl(*(u32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF)); + id >>= 16; for (p = *head; p; p = p->next) { struct iphdr *iph2; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f11931c1838..090e9991ac2 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -468,13 +468,13 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) __be32 paddr; struct neighbour *n; - if (!skb->dst) { + if (!skb_dst(skb)) { printk(KERN_DEBUG "arp_find is called with dst==NULL\n"); kfree_skb(skb); return 1; } - paddr = skb->rtable->rt_gateway; + paddr = skb_rtable(skb)->rt_gateway; if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr, paddr, dev)) return 0; @@ -801,11 +801,8 @@ static int arp_process(struct sk_buff *skb) * cache. */ - /* - * Special case: IPv4 duplicate address detection packet (RFC2131) - * and Gratuitous ARP/ARP Announce. (RFC3927, Section 2.4) - */ - if (sip == 0 || tip == sip) { + /* Special case: IPv4 duplicate address detection packet (RFC2131) */ + if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type(net, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) @@ -817,7 +814,7 @@ static int arp_process(struct sk_buff *skb) if (arp->ar_op == htons(ARPOP_REQUEST) && ip_route_input(skb, tip, sip, 0, dev) == 0) { - rt = skb->rtable; + rt = skb_rtable(skb); addr_type = rt->rt_type; if (addr_type == RTN_LOCAL) { @@ -1307,7 +1304,9 @@ static void arp_format_neigh_entry(struct seq_file *seq, hbuffer[k++] = hex_asc_lo(n->ha[j]); hbuffer[k++] = ':'; } - hbuffer[--k] = 0; + if (k != 0) + --k; + hbuffer[k] = 0; #if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) } #endif diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 126bb911880..3863c3a4223 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1347,7 +1347,8 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, struct net *net = ctl->extra2; if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { - rtnl_lock(); + if (!rtnl_trylock()) + return restart_syscall(); if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) { inet_forward_change(net); } else if (*valp) { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index cafcc49d099..e2f95059256 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -40,7 +40,6 @@ #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> -#include <net/icmp.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/rtnetlink.h> diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index ded8c44fb84..ecd39454235 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -263,7 +263,6 @@ fn_hash_lookup(struct fib_table *tb, const struct flowi *flp, struct fib_result err = fib_semantic_match(&f->fn_alias, flp, res, - f->fn_key, fz->fz_mask, fz->fz_order); if (err <= 0) goto out; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 2c1623d2768..637b133973b 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -22,8 +22,7 @@ struct fib_alias { /* Exported by fib_semantics.c */ extern int fib_semantic_match(struct list_head *head, const struct flowi *flp, - struct fib_result *res, __be32 zone, __be32 mask, - int prefixlen); + struct fib_result *res, int prefixlen); extern void fib_release_info(struct fib_info *); extern struct fib_info *fib_create_info(struct fib_config *cfg); extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 6080d712082..92d9d97ec5e 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -134,7 +134,7 @@ static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { }; static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_rule_hdr *frh, + struct fib_rule_hdr *frh, struct nlattr **tb) { struct net *net = sock_net(skb->sk); @@ -209,7 +209,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, } static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_rule_hdr *frh) + struct fib_rule_hdr *frh) { struct fib4_rule *rule4 = (struct fib4_rule *) rule; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f831df50090..9b096d6ff3f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -866,8 +866,7 @@ failure: /* Note! fib_semantic_match intentionally uses RCU list functions. */ int fib_semantic_match(struct list_head *head, const struct flowi *flp, - struct fib_result *res, __be32 zone, __be32 mask, - int prefixlen) + struct fib_result *res, int prefixlen) { struct fib_alias *fa; int nh_sel = 0; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 33c7c85dfe4..63c2fa7b68c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -123,6 +123,7 @@ struct tnode { union { struct rcu_head rcu; struct work_struct work; + struct tnode *tnode_free; }; struct node *child[0]; }; @@ -161,6 +162,8 @@ static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, static struct node *resize(struct trie *t, struct tnode *tn); 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 struct kmem_cache *fn_alias_kmem __read_mostly; static struct kmem_cache *trie_leaf_kmem __read_mostly; @@ -313,8 +316,8 @@ 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 = 8; -static const int inflate_threshold_root = 15; +static const int halve_threshold_root = 15; +static const int inflate_threshold_root = 25; static void __alias_free_mem(struct rcu_head *head) @@ -385,6 +388,24 @@ static inline void tnode_free(struct tnode *tn) call_rcu(&tn->rcu, __tnode_free_rcu); } +static void tnode_free_safe(struct tnode *tn) +{ + BUG_ON(IS_LEAF(tn)); + tn->tnode_free = tnode_free_head; + tnode_free_head = tn; +} + +static void tnode_free_flush(void) +{ + struct tnode *tn; + + while ((tn = tnode_free_head)) { + tnode_free_head = tn->tnode_free; + tn->tnode_free = NULL; + tnode_free(tn); + } +} + static struct leaf *leaf_new(void) { struct leaf *l = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); @@ -495,7 +516,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* No children */ if (tn->empty_children == tnode_child_length(tn)) { - tnode_free(tn); + tnode_free_safe(tn); return NULL; } /* One child */ @@ -509,7 +530,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* compress one level */ node_set_parent(n, NULL); - tnode_free(tn); + tnode_free_safe(tn); return n; } /* @@ -670,7 +691,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* compress one level */ node_set_parent(n, NULL); - tnode_free(tn); + tnode_free_safe(tn); return n; } @@ -756,7 +777,7 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) put_child(t, tn, 2*i, inode->child[0]); put_child(t, tn, 2*i+1, inode->child[1]); - tnode_free(inode); + tnode_free_safe(inode); continue; } @@ -801,9 +822,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) put_child(t, tn, 2*i, resize(t, left)); put_child(t, tn, 2*i+1, resize(t, right)); - tnode_free(inode); + tnode_free_safe(inode); } - tnode_free(oldtnode); + tnode_free_safe(oldtnode); return tn; nomem: { @@ -885,7 +906,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) put_child(t, newBinNode, 1, right); put_child(t, tn, i/2, resize(t, newBinNode)); } - tnode_free(oldtnode); + tnode_free_safe(oldtnode); return tn; nomem: { @@ -983,13 +1004,12 @@ fib_find_node(struct trie *t, u32 key) return NULL; } -static struct node *trie_rebalance(struct trie *t, struct tnode *tn) +static void trie_rebalance(struct trie *t, struct tnode *tn) { int wasfull; t_key cindex, key; struct tnode *tp; - preempt_disable(); key = tn->key; while (tn != NULL && (tp = node_parent((struct node *)tn)) != NULL) { @@ -1002,6 +1022,10 @@ static struct node *trie_rebalance(struct trie *t, struct tnode *tn) tp = node_parent((struct node *) tn); if (!tp) + rcu_assign_pointer(t->trie, (struct node *)tn); + + tnode_free_flush(); + if (!tp) break; tn = tp; } @@ -1010,8 +1034,10 @@ static struct node *trie_rebalance(struct trie *t, struct tnode *tn) if (IS_TNODE(tn)) tn = (struct tnode *)resize(t, (struct tnode *)tn); - preempt_enable(); - return (struct node *)tn; + rcu_assign_pointer(t->trie, (struct node *)tn); + tnode_free_flush(); + + return; } /* only used from updater-side */ @@ -1159,7 +1185,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) /* Rebalance the trie */ - rcu_assign_pointer(t->trie, trie_rebalance(t, tp)); + trie_rebalance(t, tp); done: return fa_head; } @@ -1351,8 +1377,7 @@ static int check_leaf(struct trie *t, struct leaf *l, if (l->key != (key & ntohl(mask))) continue; - err = fib_semantic_match(&li->falh, flp, res, - htonl(l->key), mask, plen); + err = fib_semantic_match(&li->falh, flp, res, plen); #ifdef CONFIG_IP_FIB_TRIE_STATS if (err <= 0) @@ -1579,7 +1604,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) if (tp) { t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits); put_child(t, (struct tnode *)tp, cindex, NULL); - rcu_assign_pointer(t->trie, trie_rebalance(t, tp)); + trie_rebalance(t, tp); } else rcu_assign_pointer(t->trie, NULL); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 3f50807237e..97c410e8438 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -356,7 +356,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { struct ipcm_cookie ipc; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->u.dst.dev); struct sock *sk; struct inet_sock *inet; @@ -416,7 +416,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) struct iphdr *iph; int room; struct icmp_bxm icmp_param; - struct rtable *rt = skb_in->rtable; + struct rtable *rt = skb_rtable(skb_in); struct ipcm_cookie ipc; __be32 saddr; u8 tos; @@ -591,13 +591,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) goto relookup_failed; /* Ugh! */ - odst = skb_in->dst; + odst = skb_dst(skb_in); err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src, RT_TOS(tos), rt2->u.dst.dev); dst_release(&rt2->u.dst); - rt2 = skb_in->rtable; - skb_in->dst = odst; + rt2 = skb_rtable(skb_in); + skb_dst_set(skb_in, odst); } if (err) @@ -659,7 +659,7 @@ static void icmp_unreach(struct sk_buff *skb) u32 info = 0; struct net *net; - net = dev_net(skb->dst->dev); + net = dev_net(skb_dst(skb)->dev); /* * Incomplete header ? @@ -822,7 +822,7 @@ static void icmp_echo(struct sk_buff *skb) { struct net *net; - net = dev_net(skb->dst->dev); + net = dev_net(skb_dst(skb)->dev); if (!net->ipv4.sysctl_icmp_echo_ignore_all) { struct icmp_bxm icmp_param; @@ -873,7 +873,7 @@ static void icmp_timestamp(struct sk_buff *skb) out: return; out_err: - ICMP_INC_STATS_BH(dev_net(skb->dst->dev), ICMP_MIB_INERRORS); + ICMP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS); goto out; } @@ -926,7 +926,7 @@ static void icmp_address(struct sk_buff *skb) static void icmp_address_reply(struct sk_buff *skb) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct net_device *dev = skb->dev; struct in_device *in_dev; struct in_ifaddr *ifa; @@ -970,7 +970,7 @@ static void icmp_discard(struct sk_buff *skb) int icmp_rcv(struct sk_buff *skb) { struct icmphdr *icmph; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->u.dst.dev); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 9eb6219af61..01b4284ed69 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -311,7 +311,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) return NULL; } - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); skb->dev = dev; skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -659,7 +659,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, return -1; } - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -948,7 +948,7 @@ int igmp_rcv(struct sk_buff *skb) case IGMPV2_HOST_MEMBERSHIP_REPORT: case IGMPV3_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ - if (skb->rtable->fl.iif == 0) + if (skb_rtable(skb)->fl.iif == 0) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || @@ -2196,7 +2196,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) break; } if (!pmc) - return 1; + return inet->mc_all; psl = pmc->sflist; if (!psl) return pmc->sfmode == MCAST_EXCLUDE; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 588a7796e3e..a706a47f4db 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -156,10 +156,10 @@ static int inet_csk_diag_fill(struct sock *sk, r->idiag_inode = sock_i_ino(sk); if (minfo) { - minfo->idiag_rmem = atomic_read(&sk->sk_rmem_alloc); + minfo->idiag_rmem = sk_rmem_alloc_get(sk); minfo->idiag_wmem = sk->sk_wmem_queued; minfo->idiag_fmem = sk->sk_forward_alloc; - minfo->idiag_tmem = atomic_read(&sk->sk_wmem_alloc); + minfo->idiag_tmem = sk_wmem_alloc_get(sk); } handler->idiag_get_info(sk, r, info); @@ -198,8 +198,6 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, tmo = 0; r->idiag_family = tw->tw_family; - r->idiag_state = tw->tw_state; - r->idiag_timer = 0; r->idiag_retrans = 0; r->id.idiag_if = tw->tw_bound_dev_if; r->id.idiag_cookie[0] = (u32)(unsigned long)tw; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 8554d0ea171..61283f92882 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -9,6 +9,7 @@ */ #include <linux/kernel.h> +#include <linux/kmemcheck.h> #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/ip.h> @@ -49,19 +50,22 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, inet_twsk_put(tw); } -void inet_twsk_put(struct inet_timewait_sock *tw) +static noinline void inet_twsk_free(struct inet_timewait_sock *tw) { - if (atomic_dec_and_test(&tw->tw_refcnt)) { - struct module *owner = tw->tw_prot->owner; - twsk_destructor((struct sock *)tw); + struct module *owner = tw->tw_prot->owner; + twsk_destructor((struct sock *)tw); #ifdef SOCK_REFCNT_DEBUG - printk(KERN_DEBUG "%s timewait_sock %p released\n", - tw->tw_prot->name, tw); + pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw); #endif - release_net(twsk_net(tw)); - kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw); - module_put(owner); - } + release_net(twsk_net(tw)); + kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw); + module_put(owner); +} + +void inet_twsk_put(struct inet_timewait_sock *tw) +{ + if (atomic_dec_and_test(&tw->tw_refcnt)) + inet_twsk_free(tw); } EXPORT_SYMBOL_GPL(inet_twsk_put); @@ -117,6 +121,8 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat if (tw != NULL) { const struct inet_sock *inet = inet_sk(sk); + kmemcheck_annotate_bitfield(tw, flags); + /* Give us an identity. */ tw->tw_daddr = inet->daddr; tw->tw_rcv_saddr = inet->rcv_saddr; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index df3fe50bbf0..a2991bc8e32 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -42,7 +42,7 @@ static int ip_forward_finish(struct sk_buff *skb) { struct ip_options * opt = &(IPCB(skb)->opt); - IP_INC_STATS_BH(dev_net(skb->dst->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); if (unlikely(opt->optlen)) ip_forward_options(skb); @@ -81,7 +81,7 @@ int ip_forward(struct sk_buff *skb) if (!xfrm4_route_forward(skb)) goto drop; - rt = skb->rtable; + rt = skb_rtable(skb); if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway) goto sr_failed; @@ -123,7 +123,7 @@ sr_failed: too_many_hops: /* Tell the sender its packet died... */ - IP_INC_STATS_BH(dev_net(skb->dst->dev), IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); drop: kfree_skb(skb); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 7985346653b..575f9bd51cc 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -507,7 +507,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ - if (skb_shinfo(head)->frag_list) { + if (skb_has_frags(head)) { struct sk_buff *clone; int i, plen = 0; @@ -516,7 +516,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, clone->next = head->next; head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_shinfo(head)->frag_list = NULL; + skb_frag_list_init(head); for (i=0; i<skb_shinfo(head)->nr_frags; i++) plen += skb_shinfo(head)->frags[i].size; clone->len = clone->data_len = head->data_len - plen; @@ -573,7 +573,7 @@ int ip_defrag(struct sk_buff *skb, u32 user) struct ipq *qp; struct net *net; - net = skb->dev ? dev_net(skb->dev) : dev_net(skb->dst->dev); + net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); /* Start by cleaning up the memory. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index e62510d5ea5..82c11dd10a6 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -602,7 +602,7 @@ static int ipgre_rcv(struct sk_buff *skb) #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { /* Looped back packet, drop it! */ - if (skb->rtable->fl.iif == 0) + if (skb_rtable(skb)->fl.iif == 0) goto drop; stats->multicast++; skb->pkt_type = PACKET_BROADCAST; @@ -643,8 +643,7 @@ static int ipgre_rcv(struct sk_buff *skb) stats->rx_packets++; stats->rx_bytes += len; skb->dev = tunnel->dev; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); skb_reset_network_header(skb); @@ -698,13 +697,13 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if ((dst = tiph->daddr) == 0) { /* NBMA tunnel */ - if (skb->dst == NULL) { + if (skb_dst(skb) == NULL) { stats->tx_fifo_errors++; goto tx_error; } if (skb->protocol == htons(ETH_P_IP)) { - rt = skb->rtable; + rt = skb_rtable(skb); if ((dst = rt->rt_gateway) == 0) goto tx_error_icmp; } @@ -712,7 +711,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) else if (skb->protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; int addr_type; - struct neighbour *neigh = skb->dst->neighbour; + struct neighbour *neigh = skb_dst(skb)->neighbour; if (neigh == NULL) goto tx_error; @@ -736,10 +735,10 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } tos = tiph->tos; - if (tos&1) { + if (tos == 1) { + tos = 0; if (skb->protocol == htons(ETH_P_IP)) tos = old_iph->tos; - tos &= ~1; } { @@ -766,10 +765,10 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (df) mtu = dst_mtu(&rt->u.dst) - dev->hard_header_len - tunnel->hlen; else - mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu; + mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (skb->protocol == htons(ETH_P_IP)) { df |= (old_iph->frag_off&htons(IP_DF)); @@ -783,14 +782,14 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } #ifdef CONFIG_IPV6 else if (skb->protocol == htons(ETH_P_IPV6)) { - struct rt6_info *rt6 = (struct rt6_info *)skb->dst; + struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); - if (rt6 && mtu < dst_mtu(skb->dst) && mtu >= IPV6_MIN_MTU) { + if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { if ((tunnel->parms.iph.daddr && !ipv4_is_multicast(tunnel->parms.iph.daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; - skb->dst->metrics[RTAX_MTU-1] = mtu; + skb_dst(skb)->metrics[RTAX_MTU-1] = mtu; } } @@ -837,8 +836,8 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. @@ -952,7 +951,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) addend += 4; } dev->needed_headroom = addend + hlen; - mtu -= dev->hard_header_len - addend; + mtu -= dev->hard_header_len + addend; if (mtu < 68) mtu = 68; @@ -1238,6 +1237,7 @@ static void ipgre_tunnel_setup(struct net_device *dev) dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } static int ipgre_tunnel_init(struct net_device *dev) diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1a58a6fa1dc..db46b4b5b2b 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -329,7 +329,7 @@ static int ip_rcv_finish(struct sk_buff *skb) * Initialise the virtual path cache for the packet. It describes * how the packet travels inside Linux networking. */ - if (skb->dst == NULL) { + if (skb_dst(skb) == NULL) { int err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, skb->dev); if (unlikely(err)) { @@ -344,9 +344,9 @@ static int ip_rcv_finish(struct sk_buff *skb) } #ifdef CONFIG_NET_CLS_ROUTE - if (unlikely(skb->dst->tclassid)) { + if (unlikely(skb_dst(skb)->tclassid)) { struct ip_rt_acct *st = per_cpu_ptr(ip_rt_acct, smp_processor_id()); - u32 idx = skb->dst->tclassid; + u32 idx = skb_dst(skb)->tclassid; st[idx&0xFF].o_packets++; st[idx&0xFF].o_bytes += skb->len; st[(idx>>16)&0xFF].i_packets++; @@ -357,11 +357,13 @@ static int ip_rcv_finish(struct sk_buff *skb) if (iph->ihl > 5 && ip_rcv_options(skb)) goto drop; - rt = skb->rtable; - if (rt->rt_type == RTN_MULTICAST) - IP_INC_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INMCASTPKTS); - else if (rt->rt_type == RTN_BROADCAST) - IP_INC_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INBCASTPKTS); + rt = skb_rtable(skb); + if (rt->rt_type == RTN_MULTICAST) { + IP_UPD_PO_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INMCAST, + skb->len); + } else if (rt->rt_type == RTN_BROADCAST) + IP_UPD_PO_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INBCAST, + skb->len); return dst_input(skb); @@ -384,7 +386,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, if (skb->pkt_type == PACKET_OTHERHOST) goto drop; - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INRECEIVES); + + IP_UPD_PO_STATS_BH(dev_net(dev), IPSTATS_MIB_IN, skb->len); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); @@ -437,6 +440,9 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Remove any debris in the socket control block */ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + /* Must drop socket now because of tproxy. */ + skb_orphan(skb); + return NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, dev, NULL, ip_rcv_finish); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 2c88da6e786..94bf105ef3c 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -102,7 +102,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) sptr = skb_network_header(skb); dptr = dopt->__data; - daddr = skb->rtable->rt_spec_dst; + daddr = skb_rtable(skb)->rt_spec_dst; if (sopt->rr) { optlen = sptr[sopt->rr+1]; @@ -143,7 +143,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) __be32 addr; memcpy(&addr, sptr+soffset-1, 4); - if (inet_addr_type(dev_net(skb->dst->dev), addr) != RTN_LOCAL) { + if (inet_addr_type(dev_net(skb_dst(skb)->dev), addr) != RTN_LOCAL) { dopt->ts_needtime = 1; soffset += 8; } @@ -257,7 +257,7 @@ int ip_options_compile(struct net *net, struct rtable *rt = NULL; if (skb != NULL) { - rt = skb->rtable; + rt = skb_rtable(skb); optptr = (unsigned char *)&(ip_hdr(skb)[1]); } else optptr = opt->__data; @@ -550,7 +550,7 @@ void ip_forward_options(struct sk_buff *skb) { struct ip_options * opt = &(IPCB(skb)->opt); unsigned char * optptr; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); unsigned char *raw = skb_network_header(skb); if (opt->rr_needaddr) { @@ -598,7 +598,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) __be32 nexthop; struct iphdr *iph = ip_hdr(skb); unsigned char *optptr = skb_network_header(skb) + opt->srr; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct rtable *rt2; int err; @@ -623,13 +623,13 @@ int ip_options_rcv_srr(struct sk_buff *skb) } memcpy(&nexthop, &optptr[srrptr-1], 4); - rt = skb->rtable; - skb->rtable = NULL; + rt = skb_rtable(skb); + skb_dst_set(skb, NULL); err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); - rt2 = skb->rtable; + rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { ip_rt_put(rt2); - skb->rtable = rt; + skb_dst_set(skb, &rt->u.dst); return -EINVAL; } ip_rt_put(rt); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 3e7e910c7c0..7ffcd96fe59 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -95,7 +95,7 @@ int __ip_local_out(struct sk_buff *skb) iph->tot_len = htons(skb->len); ip_send_check(iph); - return nf_hook(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, skb->dst->dev, + return nf_hook(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, dst_output); } @@ -118,7 +118,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) __skb_pull(newskb, skb_network_offset(newskb)); newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!newskb->dst); + WARN_ON(!skb_dst(newskb)); netif_rx(newskb); return 0; } @@ -140,7 +140,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options *opt) { struct inet_sock *inet = inet_sk(sk); - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct iphdr *iph; /* Build the IP header. */ @@ -176,15 +176,15 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static inline int ip_finish_output2(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); - if (rt->rt_type == RTN_MULTICAST) - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_OUTMCASTPKTS); - else if (rt->rt_type == RTN_BROADCAST) - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_OUTBCASTPKTS); + if (rt->rt_type == RTN_MULTICAST) { + IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len); + } else if (rt->rt_type == RTN_BROADCAST) + IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTBCAST, skb->len); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { @@ -217,14 +217,14 @@ static inline int ip_skb_dst_mtu(struct sk_buff *skb) struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL; return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ? - skb->dst->dev->mtu : dst_mtu(skb->dst); + skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); } static int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ - if (skb->dst->xfrm != NULL) { + if (skb_dst(skb)->xfrm != NULL) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(skb); } @@ -238,13 +238,13 @@ static int ip_finish_output(struct sk_buff *skb) int ip_mc_output(struct sk_buff *skb) { struct sock *sk = skb->sk; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->u.dst.dev; /* * If the indicated interface is up and running, send the packet. */ - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_OUTREQUESTS); + IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); @@ -296,9 +296,9 @@ int ip_mc_output(struct sk_buff *skb) int ip_output(struct sk_buff *skb) { - struct net_device *dev = skb->dst->dev; + struct net_device *dev = skb_dst(skb)->dev; - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_OUTREQUESTS); + IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); @@ -319,7 +319,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ - rt = skb->rtable; + rt = skb_rtable(skb); if (rt != NULL) goto packet_routed; @@ -355,7 +355,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) } sk_setup_caps(sk, &rt->u.dst); } - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); packet_routed: if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) @@ -401,8 +401,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; - dst_release(to->dst); - to->dst = dst_clone(from->dst); + skb_dst_drop(to); + skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; to->mark = from->mark; @@ -440,7 +440,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) unsigned int mtu, hlen, left, len, ll_rs, pad; int offset; __be16 not_last_frag; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); int err = 0; dev = rt->u.dst.dev; @@ -474,7 +474,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) * LATER: this step can be merged to real generation of fragments, * we can switch to copy when see the first bad fragment. */ - if (skb_shinfo(skb)->frag_list) { + if (skb_has_frags(skb)) { struct sk_buff *frag; int first_len = skb_pagelen(skb); int truesizes = 0; @@ -485,7 +485,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_cloned(skb)) goto slow_path; - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) { + skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || @@ -498,7 +498,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) BUG_ON(frag->sk); if (skb->sk) { - sock_hold(skb->sk); frag->sk = skb->sk; frag->destructor = sock_wfree; truesizes += frag->truesize; @@ -510,7 +509,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) err = 0; offset = 0; frag = skb_shinfo(skb)->frag_list; - skb_shinfo(skb)->frag_list = NULL; + skb_frag_list_init(skb); skb->data_len = first_len - skb_headlen(skb); skb->truesize -= truesizes; skb->len = first_len; @@ -814,6 +813,8 @@ int ip_append_data(struct sock *sk, inet->cork.addr = ipc->addr; } rt = *rtp; + if (unlikely(!rt)) + return -EFAULT; /* * We steal reference to this route, caller should not release it */ @@ -1244,7 +1245,6 @@ int ip_push_pending_frames(struct sock *sk) skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; - __sock_put(tmp_skb->sk); tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } @@ -1294,7 +1294,7 @@ int ip_push_pending_frames(struct sock *sk) * on dst refcount */ inet->cork.dst = NULL; - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); if (iph->protocol == IPPROTO_ICMP) icmp_out_count(net, ((struct icmphdr *) @@ -1362,7 +1362,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar } replyopts; struct ipcm_cookie ipc; __be32 daddr; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); if (ip_options_echo(&replyopts.opt, skb)) return; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 43c05854d75..fc7993e9061 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -57,7 +57,7 @@ static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct in_pktinfo info; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); info.ipi_addr.s_addr = ip_hdr(skb)->daddr; if (rt) { @@ -157,38 +157,39 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) /* Ordered by supposed usage frequency */ if (flags & 1) ip_cmsg_recv_pktinfo(msg, skb); - if ((flags>>=1) == 0) + if ((flags >>= 1) == 0) return; if (flags & 1) ip_cmsg_recv_ttl(msg, skb); - if ((flags>>=1) == 0) + if ((flags >>= 1) == 0) return; if (flags & 1) ip_cmsg_recv_tos(msg, skb); - if ((flags>>=1) == 0) + if ((flags >>= 1) == 0) return; if (flags & 1) ip_cmsg_recv_opts(msg, skb); - if ((flags>>=1) == 0) + if ((flags >>= 1) == 0) return; if (flags & 1) ip_cmsg_recv_retopts(msg, skb); - if ((flags>>=1) == 0) + if ((flags >>= 1) == 0) return; if (flags & 1) ip_cmsg_recv_security(msg, skb); - if ((flags>>=1) == 0) + if ((flags >>= 1) == 0) return; if (flags & 1) ip_cmsg_recv_dstaddr(msg, skb); } +EXPORT_SYMBOL(ip_cmsg_recv); int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) { @@ -203,7 +204,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); - err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); + err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), + err < 40 ? err : 40); if (err) return err; break; @@ -238,7 +240,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) struct ip_ra_chain *ip_ra_chain; DEFINE_RWLOCK(ip_ra_lock); -int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)) +int ip_ra_control(struct sock *sk, unsigned char on, + void (*destructor)(struct sock *)) { struct ip_ra_chain *ra, *new_ra, **rap; @@ -248,7 +251,7 @@ int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct s new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; write_lock_bh(&ip_ra_lock); - for (rap = &ip_ra_chain; (ra=*rap) != NULL; rap = &ra->next) { + for (rap = &ip_ra_chain; (ra = *rap) != NULL; rap = &ra->next) { if (ra->sk == sk) { if (on) { write_unlock_bh(&ip_ra_lock); @@ -416,7 +419,8 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) /* Reset and regenerate socket error */ spin_lock_bh(&sk->sk_error_queue.lock); sk->sk_err = 0; - if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { + skb2 = skb_peek(&sk->sk_error_queue); + if (skb2 != NULL) { sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; spin_unlock_bh(&sk->sk_error_queue.lock); sk->sk_error_report(sk); @@ -431,8 +435,8 @@ out: /* - * Socket option code for IP. This is the end of the line after any TCP,UDP etc options on - * an IP socket. + * Socket option code for IP. This is the end of the line after any + * TCP,UDP etc options on an IP socket. */ static int do_ip_setsockopt(struct sock *sk, int level, @@ -449,6 +453,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT))) || optname == IP_MULTICAST_TTL || + optname == IP_MULTICAST_ALL || optname == IP_MULTICAST_LOOP || optname == IP_RECVORIGDSTADDR) { if (optlen >= sizeof(int)) { @@ -474,7 +479,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, switch (optname) { case IP_OPTIONS: { - struct ip_options * opt = NULL; + struct ip_options *opt = NULL; if (optlen > 40 || optlen < 0) goto e_inval; err = ip_options_get_from_user(sock_net(sk), &opt, @@ -556,9 +561,9 @@ static int do_ip_setsockopt(struct sock *sk, int level, } break; case IP_TTL: - if (optlen<1) + if (optlen < 1) goto e_inval; - if (val != -1 && (val < 1 || val>255)) + if (val != -1 && (val < 0 || val > 255)) goto e_inval; inet->uc_ttl = val; break; @@ -570,7 +575,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->hdrincl = val ? 1 : 0; break; case IP_MTU_DISCOVER: - if (val<0 || val>3) + if (val < 0 || val > 3) goto e_inval; inet->pmtudisc = val; break; @@ -582,7 +587,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_MULTICAST_TTL: if (sk->sk_type == SOCK_STREAM) goto e_inval; - if (optlen<1) + if (optlen < 1) goto e_inval; if (val == -1) val = 1; @@ -591,7 +596,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->mc_ttl = val; break; case IP_MULTICAST_LOOP: - if (optlen<1) + if (optlen < 1) goto e_inval; inet->mc_loop = !!val; break; @@ -613,7 +618,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, } else { memset(&mreq, 0, sizeof(mreq)); if (optlen >= sizeof(struct in_addr) && - copy_from_user(&mreq.imr_address, optval, sizeof(struct in_addr))) + copy_from_user(&mreq.imr_address, optval, + sizeof(struct in_addr))) break; } @@ -677,7 +683,6 @@ static int do_ip_setsockopt(struct sock *sk, int level, } case IP_MSFILTER: { - extern int sysctl_igmp_max_msf; struct ip_msfilter *msf; if (optlen < IP_MSFILTER_SIZE(0)) @@ -831,7 +836,6 @@ static int do_ip_setsockopt(struct sock *sk, int level, } case MCAST_MSFILTER: { - extern int sysctl_igmp_max_msf; struct sockaddr_in *psin; struct ip_msfilter *msf = NULL; struct group_filter *gsf = NULL; @@ -849,9 +853,9 @@ static int do_ip_setsockopt(struct sock *sk, int level, break; } err = -EFAULT; - if (copy_from_user(gsf, optval, optlen)) { + if (copy_from_user(gsf, optval, optlen)) goto mc_msf_out; - } + /* numsrc >= (4G-140)/128 overflow in 32 bits */ if (gsf->gf_numsrc >= 0x1ffffff || gsf->gf_numsrc > sysctl_igmp_max_msf) { @@ -879,7 +883,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, msf->imsf_fmode = gsf->gf_fmode; msf->imsf_numsrc = gsf->gf_numsrc; err = -EADDRNOTAVAIL; - for (i=0; i<gsf->gf_numsrc; ++i) { + for (i = 0; i < gsf->gf_numsrc; ++i) { psin = (struct sockaddr_in *)&gsf->gf_slist[i]; if (psin->sin_family != AF_INET) @@ -890,17 +894,24 @@ static int do_ip_setsockopt(struct sock *sk, int level, gsf = NULL; err = ip_mc_msfilter(sk, msf, ifindex); - mc_msf_out: +mc_msf_out: kfree(msf); kfree(gsf); break; } + case IP_MULTICAST_ALL: + if (optlen < 1) + goto e_inval; + if (val != 0 && val != 1) + goto e_inval; + inet->mc_all = val; + break; case IP_ROUTER_ALERT: err = ip_ra_control(sk, val ? 1 : 0, NULL); break; case IP_FREEBIND: - if (optlen<1) + if (optlen < 1) goto e_inval; inet->freebind = !!val; break; @@ -957,6 +968,7 @@ int ip_setsockopt(struct sock *sk, int level, #endif return err; } +EXPORT_SYMBOL(ip_setsockopt); #ifdef CONFIG_COMPAT int compat_ip_setsockopt(struct sock *sk, int level, int optname, @@ -986,13 +998,12 @@ int compat_ip_setsockopt(struct sock *sk, int level, int optname, #endif return err; } - EXPORT_SYMBOL(compat_ip_setsockopt); #endif /* - * Get the options. Note for future reference. The GET of IP options gets the - * _received_ ones. The set sets the _sent_ ones. + * Get the options. Note for future reference. The GET of IP options gets + * the _received_ ones. The set sets the _sent_ ones. */ static int do_ip_getsockopt(struct sock *sk, int level, int optname, @@ -1143,10 +1154,14 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; } err = ip_mc_gsfget(sk, &gsf, - (struct group_filter __user *)optval, optlen); + (struct group_filter __user *)optval, + optlen); release_sock(sk); return err; } + case IP_MULTICAST_ALL: + val = inet->mc_all; + break; case IP_PKTOPTIONS: { struct msghdr msg; @@ -1187,7 +1202,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, } release_sock(sk); - if (len < sizeof(int) && len > 0 && val>=0 && val<=255) { + if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) { unsigned char ucval = (unsigned char)val; len = 1; if (put_user(len, optlen)) @@ -1230,6 +1245,7 @@ int ip_getsockopt(struct sock *sk, int level, #endif return err; } +EXPORT_SYMBOL(ip_getsockopt); #ifdef CONFIG_COMPAT int compat_ip_getsockopt(struct sock *sk, int level, int optname, @@ -1262,11 +1278,5 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, #endif return err; } - EXPORT_SYMBOL(compat_ip_getsockopt); #endif - -EXPORT_SYMBOL(ip_cmsg_recv); - -EXPORT_SYMBOL(ip_getsockopt); -EXPORT_SYMBOL(ip_setsockopt); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 88bf051d0cb..f8d04c25645 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -160,6 +160,9 @@ static char user_dev_name[IFNAMSIZ] __initdata = { 0, }; /* Protocols supported by available interfaces */ static int ic_proto_have_if __initdata = 0; +/* MTU for boot device */ +static int ic_dev_mtu __initdata = 0; + #ifdef IPCONFIG_DYNAMIC static DEFINE_SPINLOCK(ic_recv_lock); static volatile int ic_got_reply __initdata = 0; /* Proto(s) that replied */ @@ -286,7 +289,7 @@ set_sockaddr(struct sockaddr_in *sin, __be32 addr, __be16 port) sin->sin_port = port; } -static int __init ic_dev_ioctl(unsigned int cmd, struct ifreq *arg) +static int __init ic_devinet_ioctl(unsigned int cmd, struct ifreq *arg) { int res; @@ -297,6 +300,17 @@ static int __init ic_dev_ioctl(unsigned int cmd, struct ifreq *arg) return res; } +static int __init ic_dev_ioctl(unsigned int cmd, struct ifreq *arg) +{ + int res; + + mm_segment_t oldfs = get_fs(); + set_fs(get_ds()); + res = dev_ioctl(&init_net, cmd, (struct ifreq __user *) arg); + set_fs(oldfs); + return res; +} + static int __init ic_route_ioctl(unsigned int cmd, struct rtentry *arg) { int res; @@ -321,20 +335,31 @@ static int __init ic_setup_if(void) memset(&ir, 0, sizeof(ir)); strcpy(ir.ifr_ifrn.ifrn_name, ic_dev->name); set_sockaddr(sin, ic_myaddr, 0); - if ((err = ic_dev_ioctl(SIOCSIFADDR, &ir)) < 0) { + if ((err = ic_devinet_ioctl(SIOCSIFADDR, &ir)) < 0) { printk(KERN_ERR "IP-Config: Unable to set interface address (%d).\n", err); return -1; } set_sockaddr(sin, ic_netmask, 0); - if ((err = ic_dev_ioctl(SIOCSIFNETMASK, &ir)) < 0) { + if ((err = ic_devinet_ioctl(SIOCSIFNETMASK, &ir)) < 0) { printk(KERN_ERR "IP-Config: Unable to set interface netmask (%d).\n", err); return -1; } set_sockaddr(sin, ic_myaddr | ~ic_netmask, 0); - if ((err = ic_dev_ioctl(SIOCSIFBRDADDR, &ir)) < 0) { + if ((err = ic_devinet_ioctl(SIOCSIFBRDADDR, &ir)) < 0) { printk(KERN_ERR "IP-Config: Unable to set interface broadcast address (%d).\n", err); return -1; } + /* Handle the case where we need non-standard MTU on the boot link (a network + * using jumbo frames, for instance). If we can't set the mtu, don't error + * out, we'll try to muddle along. + */ + if (ic_dev_mtu != 0) { + strcpy(ir.ifr_name, ic_dev->name); + ir.ifr_mtu = ic_dev_mtu; + if ((err = ic_dev_ioctl(SIOCSIFMTU, &ir)) < 0) + printk(KERN_ERR "IP-Config: Unable to set interface mtu to %d (%d).\n", + ic_dev_mtu, err); + } return 0; } @@ -623,6 +648,7 @@ ic_dhcp_init_options(u8 *options) 12, /* Host name */ 15, /* Domain name */ 17, /* Boot path */ + 26, /* MTU */ 40, /* NIS domain name */ }; @@ -798,6 +824,7 @@ static void __init ic_do_bootp_ext(u8 *ext) { u8 servers; int i; + u16 mtu; #ifdef IPCONFIG_DEBUG u8 *c; @@ -837,6 +864,10 @@ static void __init ic_do_bootp_ext(u8 *ext) if (!root_server_path[0]) ic_bootp_string(root_server_path, ext+1, *ext, sizeof(root_server_path)); break; + case 26: /* Interface MTU */ + memcpy(&mtu, ext+1, sizeof(mtu)); + ic_dev_mtu = ntohs(mtu); + break; case 40: /* NIS Domain name (_not_ DNS) */ ic_bootp_string(utsname()->domainname, ext+1, *ext, __NEW_UTS_LEN); break; @@ -1403,6 +1434,8 @@ static int __init ip_auto_config(void) printk(",\n bootserver=%pI4", &ic_servaddr); printk(", rootserver=%pI4", &root_server_addr); printk(", rootpath=%s", root_server_path); + if (ic_dev_mtu) + printk(", mtu=%d", ic_dev_mtu); printk("\n"); #endif /* !SILENT */ diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 9054139795a..93e2b787da2 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -370,8 +370,7 @@ static int ipip_rcv(struct sk_buff *skb) tunnel->dev->stats.rx_packets++; tunnel->dev->stats.rx_bytes += skb->len; skb->dev = tunnel->dev; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); ipip_ecn_decapsulate(iph, skb); netif_rx(skb); @@ -416,7 +415,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (!dst) { /* NBMA tunnel */ - if ((rt = skb->rtable) == NULL) { + if ((rt = skb_rtable(skb)) == NULL) { stats->tx_fifo_errors++; goto tx_error; } @@ -447,15 +446,15 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (tiph->frag_off) mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); else - mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu; + 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->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); df |= (old_iph->frag_off&htons(IP_DF)); @@ -502,8 +501,8 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. @@ -713,6 +712,7 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } static void ipip_tunnel_init(struct net_device *dev) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 13e9dd3012b..9a8da5ed92b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -226,9 +226,10 @@ static void reg_vif_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops, dev->destructor = free_netdev; + dev->features |= NETIF_F_NETNS_LOCAL; } -static struct net_device *ipmr_reg_vif(void) +static struct net_device *ipmr_reg_vif(struct net *net) { struct net_device *dev; struct in_device *in_dev; @@ -238,6 +239,8 @@ static struct net_device *ipmr_reg_vif(void) if (dev == NULL) return NULL; + dev_net_set(dev, net); + if (register_netdevice(dev)) { free_netdev(dev); return NULL; @@ -448,7 +451,7 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) */ if (net->ipv4.mroute_reg_vif_num >= 0) return -EADDRINUSE; - dev = ipmr_reg_vif(); + dev = ipmr_reg_vif(net); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); @@ -651,7 +654,7 @@ static int ipmr_cache_report(struct net *net, ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */ msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; - skb->dst = dst_clone(pkt->dst); + skb_dst_set(skb, dst_clone(skb_dst(pkt))); /* * Add our header @@ -1031,16 +1034,6 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int if (v != net->ipv4.mroute_do_pim) { net->ipv4.mroute_do_pim = v; net->ipv4.mroute_do_assert = v; -#ifdef CONFIG_IP_PIMSM_V2 - if (net->ipv4.mroute_do_pim) - ret = inet_add_protocol(&pim_protocol, - IPPROTO_PIM); - else - ret = inet_del_protocol(&pim_protocol, - IPPROTO_PIM); - if (ret < 0) - ret = -EAGAIN; -#endif } rtnl_unlock(); return ret; @@ -1201,7 +1194,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(iph, skb->dst, NULL); + ip_select_ident(iph, skb_dst(skb), NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -1212,7 +1205,7 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) { struct ip_options * opt = &(IPCB(skb)->opt); - IP_INC_STATS_BH(dev_net(skb->dst->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); if (unlikely(opt->optlen)) ip_forward_options(skb); @@ -1290,8 +1283,8 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) vif->pkt_out++; vif->bytes_out += skb->len; - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); ip_decrease_ttl(ip_hdr(skb)); /* FIXME: forward and output firewalls used to be called here. @@ -1354,7 +1347,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local if (net->ipv4.vif_table[vif].dev != skb->dev) { int true_vifi; - if (skb->rtable->fl.iif == 0) { + if (skb_rtable(skb)->fl.iif == 0) { /* It is our own packet, looped back. Very complicated situation... @@ -1430,7 +1423,7 @@ int ip_mr_input(struct sk_buff *skb) { struct mfc_cache *cache; struct net *net = dev_net(skb->dev); - int local = skb->rtable->rt_flags&RTCF_LOCAL; + int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; /* Packet is looped back after forward, it should not be forwarded second time, but still can be delivered locally. @@ -1543,8 +1536,7 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) skb->protocol = htons(ETH_P_IP); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); reg_dev->stats.rx_bytes += skb->len; reg_dev->stats.rx_packets++; nf_reset(skb); @@ -1646,7 +1638,7 @@ int ipmr_get_route(struct net *net, { int err; struct mfc_cache *cache; - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); read_lock(&mrt_lock); cache = ipmr_cache_find(net, rt->rt_src, rt->rt_dst); @@ -1955,6 +1947,7 @@ static const struct file_operations ipmr_mfc_fops = { #ifdef CONFIG_IP_PIMSM_V2 static struct net_protocol pim_protocol = { .handler = pim_rcv, + .netns_ok = 1, }; #endif @@ -2041,8 +2034,19 @@ int __init ip_mr_init(void) err = register_netdevice_notifier(&ip_mr_notifier); if (err) goto reg_notif_fail; +#ifdef CONFIG_IP_PIMSM_V2 + if (inet_add_protocol(&pim_protocol, IPPROTO_PIM) < 0) { + printk(KERN_ERR "ip_mr_init: can't add PIM protocol\n"); + err = -EAGAIN; + goto add_proto_fail; + } +#endif return 0; +#ifdef CONFIG_IP_PIMSM_V2 +add_proto_fail: + unregister_netdevice_notifier(&ip_mr_notifier); +#endif reg_notif_fail: del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ipmr_net_ops); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index fdf6811c31a..1725dc0ef68 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -12,7 +12,7 @@ /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) { - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi fl = {}; @@ -41,8 +41,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) return -1; /* Drop old route. */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); } else { /* non-local src, find valid iif to satisfy * rp-filter when calling ip_route_input. */ @@ -50,7 +50,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) if (ip_route_output_key(net, &rt, &fl) != 0) return -1; - odst = skb->dst; + odst = skb_dst(skb); if (ip_route_input(skb, iph->daddr, iph->saddr, RT_TOS(iph->tos), rt->u.dst.dev) != 0) { dst_release(&rt->u.dst); @@ -60,18 +60,22 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) dst_release(odst); } - if (skb->dst->error) + if (skb_dst(skb)->error) return -1; #ifdef CONFIG_XFRM if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && - xfrm_decode_session(skb, &fl, AF_INET) == 0) - if (xfrm_lookup(net, &skb->dst, &fl, skb->sk, 0)) + xfrm_decode_session(skb, &fl, AF_INET) == 0) { + struct dst_entry *dst = skb_dst(skb); + skb_dst_set(skb, NULL); + if (xfrm_lookup(net, &dst, &fl, skb->sk, 0)) return -1; + skb_dst_set(skb, dst); + } #endif /* Change in oif may mean change in hh_len. */ - hh_len = skb->dst->dev->hard_header_len; + hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -1; @@ -92,7 +96,7 @@ int ip_xfrm_me_harder(struct sk_buff *skb) if (xfrm_decode_session(skb, &fl, AF_INET) < 0) return -1; - dst = skb->dst; + dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; dst_hold(dst); @@ -100,11 +104,11 @@ int ip_xfrm_me_harder(struct sk_buff *skb) if (xfrm_lookup(dev_net(dst->dev), &dst, &fl, skb->sk, 0) < 0) return -1; - dst_release(skb->dst); - skb->dst = dst; + skb_dst_drop(skb); + skb_dst_set(skb, dst); /* Change in oif may mean change in hh_len. */ - hh_len = skb->dst->dev->hard_header_len; + hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -1; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 831fe1879dc..7505dff4ffd 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -231,6 +231,12 @@ static inline struct arpt_entry *get_entry(void *base, unsigned int offset) return (struct arpt_entry *)(base + offset); } +static inline __pure +struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) +{ + return (void *)entry + entry->next_offset; +} + unsigned int arpt_do_table(struct sk_buff *skb, unsigned int hook, const struct net_device *in, @@ -267,67 +273,64 @@ unsigned int arpt_do_table(struct sk_buff *skb, arp = arp_hdr(skb); do { - if (arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) { - struct arpt_entry_target *t; - int hdr_len; - - hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) + - (2 * skb->dev->addr_len); + struct arpt_entry_target *t; + int hdr_len; - ADD_COUNTER(e->counters, hdr_len, 1); + if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) { + e = arpt_next_entry(e); + continue; + } - t = arpt_get_target(e); + hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) + + (2 * skb->dev->addr_len); + ADD_COUNTER(e->counters, hdr_len, 1); - /* Standard target? */ - if (!t->u.kernel.target->target) { - int v; + t = arpt_get_target(e); - v = ((struct arpt_standard_target *)t)->verdict; - if (v < 0) { - /* Pop from stack? */ - if (v != ARPT_RETURN) { - verdict = (unsigned)(-v) - 1; - break; - } - e = back; - back = get_entry(table_base, - back->comefrom); - continue; - } - if (table_base + v - != (void *)e + e->next_offset) { - /* Save old back ptr in next entry */ - struct arpt_entry *next - = (void *)e + e->next_offset; - next->comefrom = - (void *)back - table_base; - - /* set back pointer to next entry */ - back = next; - } + /* Standard target? */ + if (!t->u.kernel.target->target) { + int v; - e = get_entry(table_base, v); - } else { - /* Targets which reenter must return - * abs. verdicts - */ - tgpar.target = t->u.kernel.target; - tgpar.targinfo = t->data; - verdict = t->u.kernel.target->target(skb, - &tgpar); - - /* Target might have changed stuff. */ - arp = arp_hdr(skb); - - if (verdict == ARPT_CONTINUE) - e = (void *)e + e->next_offset; - else - /* Verdict */ + v = ((struct arpt_standard_target *)t)->verdict; + if (v < 0) { + /* Pop from stack? */ + if (v != ARPT_RETURN) { + verdict = (unsigned)(-v) - 1; break; + } + e = back; + back = get_entry(table_base, back->comefrom); + continue; } - } else { - e = (void *)e + e->next_offset; + if (table_base + v + != arpt_next_entry(e)) { + /* Save old back ptr in next entry */ + struct arpt_entry *next = arpt_next_entry(e); + next->comefrom = (void *)back - table_base; + + /* set back pointer to next entry */ + back = next; + } + + e = get_entry(table_base, v); + continue; } + + /* Targets which reenter must return + * abs. verdicts + */ + tgpar.target = t->u.kernel.target; + tgpar.targinfo = t->data; + verdict = t->u.kernel.target->target(skb, &tgpar); + + /* Target might have changed stuff. */ + arp = arp_hdr(skb); + + if (verdict == ARPT_CONTINUE) + e = arpt_next_entry(e); + else + /* Verdict */ + break; } while (!hotdrop); xt_info_rdunlock_bh(); diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index 5f22c91c6e1..c156db21598 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -596,7 +596,7 @@ static int __init ip_queue_init(void) #ifdef CONFIG_SYSCTL ipq_sysctl_header = register_sysctl_paths(net_ipv4_ctl_path, ipq_table); #endif - status = nf_register_queue_handler(PF_INET, &nfqh); + status = nf_register_queue_handler(NFPROTO_IPV4, &nfqh); if (status < 0) { printk(KERN_ERR "ip_queue: failed to register queue handler\n"); goto cleanup_sysctl; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2ec8d7290c4..fdefae6b5df 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -238,8 +238,8 @@ static struct nf_loginfo trace_loginfo = { /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e, - char *hookname, char **chainname, - char **comment, unsigned int *rulenum) + const char *hookname, const char **chainname, + const char **comment, unsigned int *rulenum) { struct ipt_standard_target *t = (void *)ipt_get_target(s); @@ -257,8 +257,8 @@ get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e, && unconditional(&s->ip)) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname - ? (char *)comments[NF_IP_TRACE_COMMENT_POLICY] - : (char *)comments[NF_IP_TRACE_COMMENT_RETURN]; + ? comments[NF_IP_TRACE_COMMENT_POLICY] + : comments[NF_IP_TRACE_COMMENT_RETURN]; } return 1; } else @@ -277,14 +277,14 @@ static void trace_packet(struct sk_buff *skb, { void *table_base; const struct ipt_entry *root; - char *hookname, *chainname, *comment; + const char *hookname, *chainname, *comment; unsigned int rulenum = 0; - table_base = (void *)private->entries[smp_processor_id()]; + table_base = private->entries[smp_processor_id()]; root = get_entry(table_base, private->hook_entry[hook]); - hookname = chainname = (char *)hooknames[hook]; - comment = (char *)comments[NF_IP_TRACE_COMMENT_RULE]; + hookname = chainname = hooknames[hook]; + comment = comments[NF_IP_TRACE_COMMENT_RULE]; IPT_ENTRY_ITERATE(root, private->size - private->hook_entry[hook], @@ -297,6 +297,12 @@ static void trace_packet(struct sk_buff *skb, } #endif +static inline __pure +struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) +{ + return (void *)entry + entry->next_offset; +} + /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ipt_do_table(struct sk_buff *skb, @@ -305,6 +311,8 @@ ipt_do_table(struct sk_buff *skb, const struct net_device *out, struct xt_table *table) { +#define tb_comefrom ((struct ipt_entry *)table_base)->comefrom + static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; u_int16_t datalen; @@ -335,7 +343,7 @@ ipt_do_table(struct sk_buff *skb, mtpar.in = tgpar.in = in; mtpar.out = tgpar.out = out; mtpar.family = tgpar.family = NFPROTO_IPV4; - tgpar.hooknum = hook; + mtpar.hooknum = tgpar.hooknum = hook; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); xt_info_rdlock_bh(); @@ -348,92 +356,84 @@ ipt_do_table(struct sk_buff *skb, back = get_entry(table_base, private->underflow[hook]); do { + struct ipt_entry_target *t; + IP_NF_ASSERT(e); IP_NF_ASSERT(back); - if (ip_packet_match(ip, indev, outdev, - &e->ip, mtpar.fragoff)) { - struct ipt_entry_target *t; - - if (IPT_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) - goto no_match; + if (!ip_packet_match(ip, indev, outdev, + &e->ip, mtpar.fragoff) || + IPT_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) { + e = ipt_next_entry(e); + continue; + } - ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1); + ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1); - t = ipt_get_target(e); - IP_NF_ASSERT(t->u.kernel.target); + t = ipt_get_target(e); + IP_NF_ASSERT(t->u.kernel.target); #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) - /* The packet is traced: log it */ - if (unlikely(skb->nf_trace)) - trace_packet(skb, hook, in, out, - table->name, private, e); + /* The packet is traced: log it */ + if (unlikely(skb->nf_trace)) + trace_packet(skb, hook, in, out, + table->name, private, e); #endif - /* Standard target? */ - if (!t->u.kernel.target->target) { - int v; - - v = ((struct ipt_standard_target *)t)->verdict; - if (v < 0) { - /* Pop from stack? */ - if (v != IPT_RETURN) { - verdict = (unsigned)(-v) - 1; - break; - } - e = back; - back = get_entry(table_base, - back->comefrom); - continue; - } - if (table_base + v != (void *)e + e->next_offset - && !(e->ip.flags & IPT_F_GOTO)) { - /* Save old back ptr in next entry */ - struct ipt_entry *next - = (void *)e + e->next_offset; - next->comefrom - = (void *)back - table_base; - /* set back pointer to next entry */ - back = next; + /* Standard target? */ + if (!t->u.kernel.target->target) { + int v; + + v = ((struct ipt_standard_target *)t)->verdict; + if (v < 0) { + /* Pop from stack? */ + if (v != IPT_RETURN) { + verdict = (unsigned)(-v) - 1; + break; } + e = back; + back = get_entry(table_base, back->comefrom); + continue; + } + if (table_base + v != ipt_next_entry(e) + && !(e->ip.flags & IPT_F_GOTO)) { + /* Save old back ptr in next entry */ + struct ipt_entry *next = ipt_next_entry(e); + next->comefrom = (void *)back - table_base; + /* set back pointer to next entry */ + back = next; + } + + e = get_entry(table_base, v); + continue; + } + + /* Targets which reenter must return + abs. verdicts */ + tgpar.target = t->u.kernel.target; + tgpar.targinfo = t->data; + - e = get_entry(table_base, v); - } else { - /* Targets which reenter must return - abs. verdicts */ - tgpar.target = t->u.kernel.target; - tgpar.targinfo = t->data; #ifdef CONFIG_NETFILTER_DEBUG - ((struct ipt_entry *)table_base)->comefrom - = 0xeeeeeeec; + tb_comefrom = 0xeeeeeeec; #endif - verdict = t->u.kernel.target->target(skb, - &tgpar); + verdict = t->u.kernel.target->target(skb, &tgpar); #ifdef CONFIG_NETFILTER_DEBUG - if (((struct ipt_entry *)table_base)->comefrom - != 0xeeeeeeec - && verdict == IPT_CONTINUE) { - printk("Target %s reentered!\n", - t->u.kernel.target->name); - verdict = NF_DROP; - } - ((struct ipt_entry *)table_base)->comefrom - = 0x57acc001; + if (tb_comefrom != 0xeeeeeeec && verdict == IPT_CONTINUE) { + printk("Target %s reentered!\n", + t->u.kernel.target->name); + verdict = NF_DROP; + } + tb_comefrom = 0x57acc001; #endif - /* Target might have changed stuff. */ - ip = ip_hdr(skb); - datalen = skb->len - ip->ihl * 4; - - if (verdict == IPT_CONTINUE) - e = (void *)e + e->next_offset; - else - /* Verdict */ - break; - } - } else { + /* Target might have changed stuff. */ + ip = ip_hdr(skb); + datalen = skb->len - ip->ihl * 4; - no_match: - e = (void *)e + e->next_offset; - } + if (verdict == IPT_CONTINUE) + e = ipt_next_entry(e); + else + /* Verdict */ + break; } while (!hotdrop); xt_info_rdunlock_bh(); @@ -444,6 +444,8 @@ ipt_do_table(struct sk_buff *skb, return NF_DROP; else return verdict; #endif + +#undef tb_comefrom } /* Figures out from what hook each rule can be called: returns 0 if @@ -2158,7 +2160,7 @@ static bool icmp_checkentry(const struct xt_mtchk_param *par) static struct xt_target ipt_standard_target __read_mostly = { .name = IPT_STANDARD_TARGET, .targetsize = sizeof(int), - .family = AF_INET, + .family = NFPROTO_IPV4, #ifdef CONFIG_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, @@ -2170,7 +2172,7 @@ static struct xt_target ipt_error_target __read_mostly = { .name = IPT_ERROR_TARGET, .target = ipt_error, .targetsize = IPT_FUNCTION_MAXNAMELEN, - .family = AF_INET, + .family = NFPROTO_IPV4, }; static struct nf_sockopt_ops ipt_sockopts = { @@ -2196,17 +2198,17 @@ static struct xt_match icmp_matchstruct __read_mostly = { .matchsize = sizeof(struct ipt_icmp), .checkentry = icmp_checkentry, .proto = IPPROTO_ICMP, - .family = AF_INET, + .family = NFPROTO_IPV4, }; static int __net_init ip_tables_net_init(struct net *net) { - return xt_proto_init(net, AF_INET); + return xt_proto_init(net, NFPROTO_IPV4); } static void __net_exit ip_tables_net_exit(struct net *net) { - xt_proto_fini(net, AF_INET); + xt_proto_fini(net, NFPROTO_IPV4); } static struct pernet_operations ip_tables_net_ops = { diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index f389f60cb10..dada0863946 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -27,9 +27,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("Xtables: automatic-address SNAT"); -/* Lock protects masq region inside conntrack */ -static DEFINE_RWLOCK(masq_lock); - /* FIXME: Multiple targets. --RR */ static bool masquerade_tg_check(const struct xt_tgchk_param *par) { @@ -72,16 +69,14 @@ masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par) return NF_ACCEPT; mr = par->targinfo; - rt = skb->rtable; + rt = skb_rtable(skb); newsrc = inet_select_addr(par->out, rt->rt_gateway, RT_SCOPE_UNIVERSE); if (!newsrc) { printk("MASQUERADE: %s ate my IP address\n", par->out->name); return NF_DROP; } - write_lock_bh(&masq_lock); nat->masq_index = par->out->ifindex; - write_unlock_bh(&masq_lock); /* Transfer from original range. */ newrange = ((struct nf_nat_range) @@ -97,16 +92,11 @@ static int device_cmp(struct nf_conn *i, void *ifindex) { const struct nf_conn_nat *nat = nfct_nat(i); - int ret; if (!nat) return 0; - read_lock_bh(&masq_lock); - ret = (nat->masq_index == (int)(long)ifindex); - read_unlock_bh(&masq_lock); - - return ret; + return nat->masq_index == (int)(long)ifindex; } static int masq_device_event(struct notifier_block *this, diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 0b4b6e0ff2b..c93ae44bff2 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -108,17 +108,16 @@ static void send_reset(struct sk_buff *oldskb, int hook) addr_type = RTN_LOCAL; /* ip_route_me_harder expects skb->dst to be set */ - dst_hold(oldskb->dst); - nskb->dst = oldskb->dst; + skb_dst_set(nskb, dst_clone(skb_dst(oldskb))); if (ip_route_me_harder(nskb, addr_type)) goto free_nskb; - niph->ttl = dst_metric(nskb->dst, RTAX_HOPLIMIT); + niph->ttl = dst_metric(skb_dst(nskb), RTAX_HOPLIMIT); nskb->ip_summed = CHECKSUM_NONE; /* "Never happens" */ - if (nskb->len > dst_mtu(nskb->dst)) + if (nskb->len > dst_mtu(skb_dst(nskb))) goto free_nskb; nf_ct_attach(nskb, oldskb); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 23b2c2ee869..d71ba767734 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -82,18 +82,10 @@ static int icmp_packet(struct nf_conn *ct, u_int8_t pf, unsigned int hooknum) { - /* Try to delete connection immediately after all replies: - won't actually vanish as we still have skb, and del_timer - means this will only run once even if count hits zero twice - (theoretically possible with SMP) */ - if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) { - if (atomic_dec_and_test(&ct->proto.icmp.count)) - nf_ct_kill_acct(ct, ctinfo, skb); - } else { - atomic_inc(&ct->proto.icmp.count); - nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct); - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout); - } + /* Do not immediately delete the connection after the first + successful reply to avoid excessive conntrackd traffic + and also to handle correctly ICMP echo reply duplicates. */ + nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout); return NF_ACCEPT; } @@ -117,7 +109,6 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple); return false; } - atomic_set(&ct->proto.icmp.count, 0); return true; } diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index cf7a42bf982..09172a65d9b 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -140,7 +140,7 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct iphdr *iph; struct tcphdr *tcph; int oldlen, datalen; @@ -191,7 +191,8 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb, ct, ctinfo); /* Tell TCP window tracking about seq change */ nf_conntrack_tcp_update(skb, ip_hdrlen(skb), - ct, CTINFO2DIR(ctinfo)); + ct, CTINFO2DIR(ctinfo), + (int)rep_len - (int)match_len); nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); } @@ -218,7 +219,7 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct iphdr *iph; struct udphdr *udph; int datalen, oldlen; @@ -377,6 +378,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, struct tcphdr *tcph; int dir; __be32 newseq, newack; + s16 seqoff, ackoff; struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way, *other_way; @@ -390,15 +392,18 @@ nf_nat_seq_adjust(struct sk_buff *skb, tcph = (void *)skb->data + ip_hdrlen(skb); if (after(ntohl(tcph->seq), this_way->correction_pos)) - newseq = htonl(ntohl(tcph->seq) + this_way->offset_after); + seqoff = this_way->offset_after; else - newseq = htonl(ntohl(tcph->seq) + this_way->offset_before); + seqoff = this_way->offset_before; if (after(ntohl(tcph->ack_seq) - other_way->offset_before, other_way->correction_pos)) - newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_after); + ackoff = other_way->offset_after; else - newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_before); + ackoff = other_way->offset_before; + + newseq = htonl(ntohl(tcph->seq) + seqoff); + newack = htonl(ntohl(tcph->ack_seq) - ackoff); inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); @@ -413,7 +418,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, if (!nf_nat_sack_adjust(skb, tcph, ct, ctinfo)) return 0; - nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir); + nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir, seqoff); return 1; } diff --git a/net/ipv4/netfilter/nf_nat_proto_sctp.c b/net/ipv4/netfilter/nf_nat_proto_sctp.c index 65e470bc612..3fc598eeeb1 100644 --- a/net/ipv4/netfilter/nf_nat_proto_sctp.c +++ b/net/ipv4/netfilter/nf_nat_proto_sctp.c @@ -33,6 +33,7 @@ sctp_manip_pkt(struct sk_buff *skb, enum nf_nat_manip_type maniptype) { const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); + struct sk_buff *frag; sctp_sctphdr_t *hdr; unsigned int hdroff = iphdroff + iph->ihl*4; __be32 oldip, newip; @@ -57,8 +58,8 @@ sctp_manip_pkt(struct sk_buff *skb, } crc32 = sctp_start_cksum((u8 *)hdr, skb_headlen(skb) - hdroff); - for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) - crc32 = sctp_update_cksum((u8 *)skb->data, skb_headlen(skb), + skb_walk_frags(skb, frag) + crc32 = sctp_update_cksum((u8 *)frag->data, skb_headlen(frag), crc32); crc32 = sctp_end_cksum(crc32); hdr->checksum = crc32; diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index b7dd695691a..5567bd0d075 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -167,10 +167,9 @@ nf_nat_in(unsigned int hooknum, ret = nf_nat_fn(hooknum, skb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN && - daddr != ip_hdr(skb)->daddr) { - dst_release(skb->dst); - skb->dst = NULL; - } + daddr != ip_hdr(skb)->daddr) + skb_dst_drop(skb); + return ret; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index cf0cdeeb1db..f25542c48b7 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -90,14 +90,14 @@ static const struct file_operations sockstat_seq_fops = { /* snmp items */ static const struct snmp_mib snmp4_ipstats_list[] = { - SNMP_MIB_ITEM("InReceives", IPSTATS_MIB_INRECEIVES), + SNMP_MIB_ITEM("InReceives", IPSTATS_MIB_INPKTS), SNMP_MIB_ITEM("InHdrErrors", IPSTATS_MIB_INHDRERRORS), SNMP_MIB_ITEM("InAddrErrors", IPSTATS_MIB_INADDRERRORS), SNMP_MIB_ITEM("ForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS), SNMP_MIB_ITEM("InUnknownProtos", IPSTATS_MIB_INUNKNOWNPROTOS), SNMP_MIB_ITEM("InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("InDelivers", IPSTATS_MIB_INDELIVERS), - SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTREQUESTS), + SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTPKTS), SNMP_MIB_ITEM("OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -118,6 +118,12 @@ static const struct snmp_mib snmp4_ipextstats_list[] = { SNMP_MIB_ITEM("OutMcastPkts", IPSTATS_MIB_OUTMCASTPKTS), SNMP_MIB_ITEM("InBcastPkts", IPSTATS_MIB_INBCASTPKTS), SNMP_MIB_ITEM("OutBcastPkts", IPSTATS_MIB_OUTBCASTPKTS), + SNMP_MIB_ITEM("InOctets", IPSTATS_MIB_INOCTETS), + SNMP_MIB_ITEM("OutOctets", IPSTATS_MIB_OUTOCTETS), + SNMP_MIB_ITEM("InMcastOctets", IPSTATS_MIB_INMCASTOCTETS), + SNMP_MIB_ITEM("OutMcastOctets", IPSTATS_MIB_OUTMCASTOCTETS), + SNMP_MIB_ITEM("InBcastOctets", IPSTATS_MIB_INBCASTOCTETS), + SNMP_MIB_ITEM("OutBcastOctets", IPSTATS_MIB_OUTBCASTOCTETS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index f774651f0a4..2979f14bb18 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -343,7 +343,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); skb_reset_network_header(skb); iph = ip_hdr(skb); @@ -799,7 +799,8 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: { - int amount = atomic_read(&sk->sk_wmem_alloc); + int amount = sk_wmem_alloc_get(sk); + return put_user(amount, (int __user *)arg); } case SIOCINQ: { @@ -935,8 +936,8 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) seq_printf(seq, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", i, src, srcp, dest, destp, sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 28205e5bfa9..278f46f5011 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -131,8 +131,8 @@ static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ; static int rt_chain_length_max __read_mostly = 20; -static void rt_worker_func(struct work_struct *work); -static DECLARE_DELAYED_WORK(expires_work, rt_worker_func); +static struct delayed_work expires_work; +static unsigned long expires_ljiffies; /* * Interface to generic destination cache. @@ -787,9 +787,12 @@ static void rt_check_expire(void) struct rtable *rth, *aux, **rthp; unsigned long samples = 0; unsigned long sum = 0, sum2 = 0; + unsigned long delta; u64 mult; - mult = ((u64)ip_rt_gc_interval) << rt_hash_log; + delta = jiffies - expires_ljiffies; + expires_ljiffies = jiffies; + mult = ((u64)delta) << rt_hash_log; if (ip_rt_gc_timeout > 1) do_div(mult, ip_rt_gc_timeout); goal = (unsigned int)mult; @@ -1064,7 +1067,8 @@ work_done: out: return 0; } -static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp) +static int rt_intern_hash(unsigned hash, struct rtable *rt, + struct rtable **rp, struct sk_buff *skb) { struct rtable *rth, **rthp; unsigned long now; @@ -1081,8 +1085,35 @@ restart: now = jiffies; if (!rt_caching(dev_net(rt->u.dst.dev))) { - rt_drop(rt); - return 0; + /* + * If we're not caching, just tell the caller we + * were successful and don't touch the route. The + * caller hold the sole reference to the cache entry, and + * it will be released when the caller is done with it. + * If we drop it here, the callers have no way to resolve routes + * when we're not caching. Instead, just point *rp at rt, so + * the caller gets a single use out of the route + * Note that we do rt_free on this new route entry, so that + * once its refcount hits zero, we are still able to reap it + * (Thanks Alexey) + * Note also the rt_free uses call_rcu. We don't actually + * need rcu protection here, this is just our path to get + * on the route gc list. + */ + + if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { + int err = arp_bind_neighbour(&rt->u.dst); + if (err) { + if (net_ratelimit()) + printk(KERN_WARNING + "Neighbour table failure & not caching routes.\n"); + rt_drop(rt); + return err; + } + } + + rt_free(rt); + goto skip_hashing; } rthp = &rt_hash_table[hash].chain; @@ -1114,7 +1145,10 @@ restart: spin_unlock_bh(rt_hash_lock_addr(hash)); rt_drop(rt); - *rp = rth; + if (rp) + *rp = rth; + else + skb_dst_set(skb, &rth->u.dst); return 0; } @@ -1196,7 +1230,8 @@ restart: #if RT_CACHE_DEBUG >= 2 if (rt->u.dst.rt_next) { struct rtable *trt; - printk(KERN_DEBUG "rt_cache @%02x: %pI4", hash, &rt->rt_dst); + printk(KERN_DEBUG "rt_cache @%02x: %pI4", + hash, &rt->rt_dst); for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next) printk(" . %pI4", &trt->rt_dst); printk("\n"); @@ -1210,7 +1245,12 @@ restart: rcu_assign_pointer(rt_hash_table[hash].chain, rt); spin_unlock_bh(rt_hash_lock_addr(hash)); - *rp = rt; + +skip_hashing: + if (rp) + *rp = rt; + else + skb_dst_set(skb, &rt->u.dst); return 0; } @@ -1407,7 +1447,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, &netevent); rt_del(hash, rth); - if (!rt_intern_hash(hash, rt, &rt)) + if (!rt_intern_hash(hash, rt, &rt, NULL)) ip_rt_put(rt); goto do_next; } @@ -1473,7 +1513,7 @@ 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; + struct rtable *rt = skb_rtable(skb); struct in_device *in_dev = in_dev_get(rt->u.dst.dev); if (!in_dev) @@ -1521,7 +1561,7 @@ out: static int ip_error(struct sk_buff *skb) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); unsigned long now; int code; @@ -1698,7 +1738,7 @@ static void ipv4_link_failure(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); - rt = skb->rtable; + rt = skb_rtable(skb); if (rt) dst_set_expires(&rt->u.dst, 0); } @@ -1858,7 +1898,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, in_dev_put(in_dev); hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); - return rt_intern_hash(hash, rth, &skb->rtable); + return rt_intern_hash(hash, rth, NULL, skb); e_nobufs: in_dev_put(in_dev); @@ -2019,7 +2059,7 @@ static int ip_mkroute_input(struct sk_buff *skb, /* put it into the cache */ hash = rt_hash(daddr, saddr, fl->iif, rt_genid(dev_net(rth->u.dst.dev))); - return rt_intern_hash(hash, rth, &skb->rtable); + return rt_intern_hash(hash, rth, NULL, skb); } /* @@ -2175,7 +2215,7 @@ local_input: } rth->rt_type = res.type; hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net)); - err = rt_intern_hash(hash, rth, &skb->rtable); + err = rt_intern_hash(hash, rth, NULL, skb); goto done; no_route: @@ -2244,7 +2284,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(in_hit); rcu_read_unlock(); - skb->rtable = rth; + skb_dst_set(skb, &rth->u.dst); return 0; } RT_CACHE_STAT_INC(in_hlist_search); @@ -2420,7 +2460,7 @@ static int ip_mkroute_output(struct rtable **rp, if (err == 0) { hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif, rt_genid(dev_net(dev_out))); - err = rt_intern_hash(hash, rth, rp); + err = rt_intern_hash(hash, rth, rp, NULL); } return err; @@ -2763,7 +2803,7 @@ static int rt_fill_info(struct net *net, struct sk_buff *skb, u32 pid, u32 seq, int event, int nowait, unsigned int flags) { - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; long expires; @@ -2907,7 +2947,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev); local_bh_enable(); - rt = skb->rtable; + rt = skb_rtable(skb); if (err == 0 && rt->u.dst.error) err = -rt->u.dst.error; } else { @@ -2927,7 +2967,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void if (err) goto errout_free; - skb->rtable = rt; + skb_dst_set(skb, &rt->u.dst); if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; @@ -2968,15 +3008,15 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; if (rt_is_expired(rt)) continue; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); rcu_read_unlock_bh(); goto done; } - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); } rcu_read_unlock_bh(); } @@ -3390,6 +3430,8 @@ int __init ip_rt_init(void) /* All the timers, started at system startup tend to synchronize. Perturb it a bit. */ + INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); + expires_ljiffies = jiffies; schedule_delayed_work(&expires_work, net_random() % ip_rt_gc_interval + ip_rt_gc_interval); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b35a950d2e0..cd2b97f1b6e 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -161,13 +161,12 @@ static __u16 const msstab[] = { */ __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) { - struct tcp_sock *tp = tcp_sk(sk); const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); int mssind; const __u16 mss = *mssp; - tp->last_synq_overflow = jiffies; + tcp_synq_overflow(sk); /* XXX sort msstab[] by probability? Binary search? */ for (mssind = 0; mss > msstab[mssind + 1]; mssind++) @@ -268,7 +267,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, if (!sysctl_tcp_syncookies || !th->ack) goto out; - if (time_after(jiffies, tp->last_synq_overflow + TCP_TIMEOUT_INIT) || + if (tcp_synq_no_recent_overflow(sk) || (mss = cookie_check(skb, cookie)) == 0) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED); goto out; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7a0f0b27bf1..91145244ea6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -339,7 +339,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) struct sock *sk = sock->sk; struct tcp_sock *tp = tcp_sk(sk); - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); if (sk->sk_state == TCP_LISTEN) return inet_csk_listen_poll(sk); @@ -439,12 +439,14 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { + struct sk_buff *skb; + answ = tp->rcv_nxt - tp->copied_seq; /* Subtract 1, if FIN is in queue. */ - if (answ && !skb_queue_empty(&sk->sk_receive_queue)) - answ -= - tcp_hdr((struct sk_buff *)sk->sk_receive_queue.prev)->fin; + skb = skb_peek_tail(&sk->sk_receive_queue); + if (answ && skb) + answ -= tcp_hdr(skb)->fin; } else answ = tp->urg_seq - tp->copied_seq; release_sock(sk); @@ -901,13 +903,17 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, iov++; while (seglen > 0) { - int copy; + int copy = 0; + int max = size_goal; skb = tcp_write_queue_tail(sk); + if (tcp_send_head(sk)) { + if (skb->ip_summed == CHECKSUM_NONE) + max = mss_now; + copy = max - skb->len; + } - if (!tcp_send_head(sk) || - (copy = size_goal - skb->len) <= 0) { - + if (copy <= 0) { new_segment: /* Allocate new segment. If the interface is SG, * allocate skb fitting to single page. @@ -928,6 +934,7 @@ new_segment: skb_entail(sk, skb); copy = size_goal; + max = size_goal; } /* Try to append data to the end of skb. */ @@ -1026,7 +1033,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len < size_goal || (flags & MSG_OOB)) + if (skb->len < max || (flags & MSG_OOB)) continue; if (forced_push(tp)) { @@ -1382,11 +1389,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* Next get a buffer. */ - skb = skb_peek(&sk->sk_receive_queue); - do { - if (!skb) - break; - + skb_queue_walk(&sk->sk_receive_queue, skb) { /* Now that we have two receive queues this * shouldn't happen. */ @@ -1403,8 +1406,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (tcp_hdr(skb)->fin) goto found_fin_ok; WARN_ON(!(flags & MSG_PEEK)); - skb = skb->next; - } while (skb != (struct sk_buff *)&sk->sk_receive_queue); + } /* Well, if we have backlog, try to process it now yet. */ @@ -2518,20 +2520,30 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) unsigned int thlen; unsigned int flags; unsigned int mss = 1; + unsigned int hlen; + unsigned int off; int flush = 1; int i; - th = skb_gro_header(skb, sizeof(*th)); - if (unlikely(!th)) - goto out; + off = skb_gro_offset(skb); + hlen = off + sizeof(*th); + th = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + th = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!th)) + goto out; + } thlen = th->doff * 4; if (thlen < sizeof(*th)) goto out; - th = skb_gro_header(skb, thlen); - if (unlikely(!th)) - goto out; + hlen = off + thlen; + if (skb_gro_header_hard(skb, hlen)) { + th = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!th)) + goto out; + } skb_gro_pull(skb, thlen); @@ -2544,7 +2556,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) th2 = tcp_hdr(p); - if ((th->source ^ th2->source) | (th->dest ^ th2->dest)) { + if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { NAPI_GRO_CB(p)->same_flow = 0; continue; } @@ -2559,14 +2571,14 @@ found: flush |= flags & TCP_FLAG_CWR; flush |= (flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH); - flush |= (th->ack_seq ^ th2->ack_seq) | (th->window ^ th2->window); - for (i = sizeof(*th); !flush && i < thlen; i += 4) + flush |= th->ack_seq ^ th2->ack_seq; + for (i = sizeof(*th); i < thlen; i += 4) flush |= *(u32 *)((u8 *)th + i) ^ *(u32 *)((u8 *)th2 + i); mss = skb_shinfo(p)->gso_size; - flush |= (len > mss) | !len; + flush |= (len - 1) >= mss; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); if (flush || skb_gro_receive(head, skb)) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eec3e6f9956..2bdb0da237e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -77,7 +77,7 @@ int sysctl_tcp_window_scaling __read_mostly = 1; int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly = 1; int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; -int sysctl_tcp_ecn __read_mostly; +int sysctl_tcp_ecn __read_mostly = 2; int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 2; @@ -4426,7 +4426,7 @@ drop: } __skb_queue_head(&tp->out_of_order_queue, skb); } else { - struct sk_buff *skb1 = tp->out_of_order_queue.prev; + struct sk_buff *skb1 = skb_peek_tail(&tp->out_of_order_queue); u32 seq = TCP_SKB_CB(skb)->seq; u32 end_seq = TCP_SKB_CB(skb)->end_seq; @@ -4443,15 +4443,18 @@ drop: } /* Find place to insert this segment. */ - do { + while (1) { if (!after(TCP_SKB_CB(skb1)->seq, seq)) break; - } while ((skb1 = skb1->prev) != - (struct sk_buff *)&tp->out_of_order_queue); + if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { + skb1 = NULL; + break; + } + skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); + } /* Do skb overlap to previous one? */ - if (skb1 != (struct sk_buff *)&tp->out_of_order_queue && - before(seq, TCP_SKB_CB(skb1)->end_seq)) { + if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ __kfree_skb(skb); @@ -4463,15 +4466,26 @@ drop: tcp_dsack_set(sk, seq, TCP_SKB_CB(skb1)->end_seq); } else { - skb1 = skb1->prev; + if (skb_queue_is_first(&tp->out_of_order_queue, + skb1)) + skb1 = NULL; + else + skb1 = skb_queue_prev( + &tp->out_of_order_queue, + skb1); } } - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); + if (!skb1) + __skb_queue_head(&tp->out_of_order_queue, skb); + else + __skb_queue_after(&tp->out_of_order_queue, skb1, skb); /* And clean segments covered by new one as whole. */ - while ((skb1 = skb->next) != - (struct sk_buff *)&tp->out_of_order_queue && - after(end_seq, TCP_SKB_CB(skb1)->seq)) { + while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { + skb1 = skb_queue_next(&tp->out_of_order_queue, skb); + + if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) + break; if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, end_seq); @@ -4492,7 +4506,10 @@ add_sack: static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, struct sk_buff_head *list) { - struct sk_buff *next = skb->next; + struct sk_buff *next = NULL; + + if (!skb_queue_is_last(list, skb)) + next = skb_queue_next(list, skb); __skb_unlink(skb, list); __kfree_skb(skb); @@ -4503,6 +4520,9 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, /* Collapse contiguous sequence of skbs head..tail with * sequence numbers start..end. + * + * If tail is NULL, this means until the end of the list. + * * Segments with FIN/SYN are not collapsed (only because this * simplifies code) */ @@ -4511,15 +4531,23 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct sk_buff *head, struct sk_buff *tail, u32 start, u32 end) { - struct sk_buff *skb; + struct sk_buff *skb, *n; + bool end_of_skbs; /* First, check that queue is collapsible and find * the point where collapsing can be useful. */ - for (skb = head; skb != tail;) { + skb = head; +restart: + end_of_skbs = true; + skb_queue_walk_from_safe(list, skb, n) { + if (skb == tail) + break; /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { skb = tcp_collapse_one(sk, skb, list); - continue; + if (!skb) + break; + goto restart; } /* The first skb to collapse is: @@ -4529,16 +4557,24 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, */ if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin && (tcp_win_from_space(skb->truesize) > skb->len || - before(TCP_SKB_CB(skb)->seq, start) || - (skb->next != tail && - TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb->next)->seq))) + before(TCP_SKB_CB(skb)->seq, start))) { + end_of_skbs = false; break; + } + + if (!skb_queue_is_last(list, skb)) { + struct sk_buff *next = skb_queue_next(list, skb); + if (next != tail && + TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(next)->seq) { + end_of_skbs = false; + break; + } + } /* Decided to skip this, advance start seq. */ start = TCP_SKB_CB(skb)->end_seq; - skb = skb->next; } - if (skb == tail || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin) + if (end_of_skbs || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin) return; while (before(start, end)) { @@ -4583,7 +4619,8 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, } if (!before(start, TCP_SKB_CB(skb)->end_seq)) { skb = tcp_collapse_one(sk, skb, list); - if (skb == tail || + if (!skb || + skb == tail || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin) return; @@ -4610,17 +4647,21 @@ static void tcp_collapse_ofo_queue(struct sock *sk) head = skb; for (;;) { - skb = skb->next; + struct sk_buff *next = NULL; + + if (!skb_queue_is_last(&tp->out_of_order_queue, skb)) + next = skb_queue_next(&tp->out_of_order_queue, skb); + skb = next; /* Segment is terminated when we see gap or when * we are at the end of all the queue. */ - if (skb == (struct sk_buff *)&tp->out_of_order_queue || + if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { tcp_collapse(sk, &tp->out_of_order_queue, head, skb, start, end); head = skb; - if (skb == (struct sk_buff *)&tp->out_of_order_queue) + if (!skb) break; /* Start new segment */ start = TCP_SKB_CB(skb)->seq; @@ -4681,10 +4722,11 @@ static int tcp_prune_queue(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); tcp_collapse_ofo_queue(sk); - tcp_collapse(sk, &sk->sk_receive_queue, - sk->sk_receive_queue.next, - (struct sk_buff *)&sk->sk_receive_queue, - tp->copied_seq, tp->rcv_nxt); + if (!skb_queue_empty(&sk->sk_receive_queue)) + tcp_collapse(sk, &sk->sk_receive_queue, + skb_peek(&sk->sk_receive_queue), + NULL, + tp->copied_seq, tp->rcv_nxt); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5d427f86b41..6d88219c5e2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -546,7 +546,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) if (th->rst) return; - if (skb->rtable->rt_type != RTN_LOCAL) + if (skb_rtable(skb)->rt_type != RTN_LOCAL) return; /* Swap the send and the receive. */ @@ -590,7 +590,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; - net = dev_net(skb->dst->dev); + net = dev_net(skb_dst(skb)->dev); ip_send_reply(net->ipv4.tcp_sock, skb, &arg, arg.iov[0].iov_len); @@ -617,7 +617,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, ]; } rep; struct ip_reply_arg arg; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -1160,6 +1160,7 @@ 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 = { .md5_lookup = tcp_v4_reqsk_md5_lookup, + .calc_md5_hash = tcp_v4_md5_hash_skb, }; #endif @@ -1185,7 +1186,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) #endif /* Never answer to SYNs send to broadcast or multicast */ - if (skb->rtable->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; /* TW buckets are converted to open requests without @@ -1373,7 +1374,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); if (newkey != NULL) - tcp_v4_md5_do_add(newsk, inet_sk(sk)->daddr, + tcp_v4_md5_do_add(newsk, newinet->daddr, newkey, key->keylen); newsk->sk_route_caps &= ~NETIF_F_GSO_MASK; } @@ -1593,7 +1594,7 @@ process: #endif { if (!tcp_prequeue(sk, skb)) - ret = tcp_v4_do_rcv(sk, skb); + ret = tcp_v4_do_rcv(sk, skb); } } else sk_add_backlog(sk, skb); @@ -2343,7 +2344,7 @@ void tcp4_proc_exit(void) struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - struct iphdr *iph = ip_hdr(skb); + struct iphdr *iph = skb_gro_network_header(skb); switch (skb->ip_summed) { case CHECKSUM_COMPLETE: diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 43bbba7926e..f8d67ccc64f 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -128,7 +128,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, goto kill_with_rst; /* Dup ACK? */ - if (!after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) || + if (!th->ack || + !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) || TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) { inet_twsk_put(tw); return TCP_TW_SUCCESS; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 59aec609cec..bd62712848f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -288,7 +288,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); tp->ecn_flags = 0; - if (sysctl_tcp_ecn) { + if (sysctl_tcp_ecn == 1) { TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE | TCPCB_FLAG_CWR; tp->ecn_flags = TCP_ECN_OK; } @@ -725,7 +725,8 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || !sk_can_gso(sk)) { + if (skb->len <= mss_now || !sk_can_gso(sk) || + skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -2202,7 +2203,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); mss = dst_metric(dst, RTAX_ADVMSS); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) @@ -2260,7 +2261,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) { - tp->af_specific->calc_md5_hash(md5_hash_location, + tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location, md5, NULL, req, skb); } #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7a1d1ce22e6..80e3812837a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -328,7 +328,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, if (unlikely(sk = skb_steal_sock(skb))) return sk; else - return __udp4_lib_lookup(dev_net(skb->dst->dev), iph->saddr, sport, + return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), udptable); } @@ -840,7 +840,8 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) switch (cmd) { case SIOCOUTQ: { - int amount = atomic_read(&sk->sk_wmem_alloc); + int amount = sk_wmem_alloc_get(sk); + return put_user(amount, (int __user *)arg); } @@ -1237,7 +1238,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct sock *sk; struct udphdr *uh; unsigned short ulen; - struct rtable *rt = (struct rtable*)skb->dst; + struct rtable *rt = skb_rtable(skb); __be32 saddr, daddr; struct net *net = dev_net(skb->dev); @@ -1721,8 +1722,8 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n", bucket, src, srcp, dest, destp, sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops), len); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 4ec2162a437..f9f922a0ba8 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -23,7 +23,7 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) { - if (skb->dst == NULL) { + if (skb_dst(skb) == NULL) { const struct iphdr *iph = ip_hdr(skb); if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 7135279f3f8..3444f3b34ec 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -28,7 +28,7 @@ static inline void ipip_ecn_decapsulate(struct sk_buff *skb) */ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct iphdr *top_iph; int flags; @@ -41,7 +41,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ihl = 5; top_iph->version = 4; - top_iph->protocol = xfrm_af2proto(skb->dst->ops->family); + top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family); /* DS disclosed */ top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos, diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 8c3180adddb..c908bd99bcb 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -29,7 +29,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df) goto out; - dst = skb->dst; + dst = skb_dst(skb); mtu = dst_mtu(dst); if (skb->len > mtu) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); @@ -72,7 +72,7 @@ EXPORT_SYMBOL(xfrm4_prepare_output); static int xfrm4_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER - if (!skb->dst->xfrm) { + if (!skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(skb); } @@ -87,6 +87,6 @@ static int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, - NULL, skb->dst->dev, xfrm4_output_finish, + NULL, skb_dst(skb)->dev, xfrm4_output_finish, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 60d918c96a4..0071ee6f441 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -136,7 +136,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: - if (pskb_may_pull(skb, xprth + 4 - skb->data)) { + if (xprth + 4 < skb->data || + pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ports = (__be16 *)xprth; fl->fl_ip_sport = ports[!!reverse]; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ca8cb326d1d..ead6c7a42f4 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -168,7 +168,7 @@ config IPV6_SIT into IPv4 packets. This is useful if you want to connect two IPv6 networks over an IPv4-only path. - Saying M here will produce a module called sit.ko. If unsure, say Y. + Saying M here will produce a module called sit. If unsure, say Y. config IPV6_NDISC_NODETYPE bool diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a8218bc1806..43b3c9f89c1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -503,7 +503,7 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) return 0; if (!rtnl_trylock()) - return -ERESTARTSYS; + return restart_syscall(); if (p == &net->ipv6.devconf_all->forwarding) { __s32 newf = net->ipv6.devconf_all->forwarding; @@ -591,7 +591,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, { struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; - struct net *net = dev_net(idev->dev); int hash; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -608,7 +607,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, goto out2; } - if (idev->cnf.disable_ipv6 || net->ipv6.devconf_all->disable_ipv6) { + if (idev->cnf.disable_ipv6) { err = -EACCES; goto out2; } @@ -1520,6 +1519,8 @@ static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev) int __ipv6_isatap_ifid(u8 *eui, __be32 addr) { + if (addr == 0) + return -1; eui[0] = (ipv4_is_zeronet(addr) || ipv4_is_private_10(addr) || ipv4_is_loopback(addr) || ipv4_is_linklocal_169(addr) || ipv4_is_private_172(addr) || ipv4_is_test_192(addr) || @@ -1750,6 +1751,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) __u32 prefered_lft; int addr_type; struct inet6_dev *in6_dev; + struct net *net = dev_net(dev); pinfo = (struct prefix_info *) opt; @@ -1807,7 +1809,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (addrconf_finite_timeout(rt_expires)) rt_expires *= HZ; - rt = rt6_lookup(dev_net(dev), &pinfo->prefix, NULL, + rt = rt6_lookup(net, &pinfo->prefix, NULL, dev->ifindex, 1); if (rt && addrconf_is_prefix_route(rt)) { @@ -1844,7 +1846,6 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) struct inet6_ifaddr * ifp; struct in6_addr addr; int create = 0, update_lft = 0; - struct net *net = dev_net(dev); if (pinfo->prefix_len == 64) { memcpy(&addr, &pinfo->prefix, 8); @@ -1915,8 +1916,32 @@ ok: update_lft = 1; else if (stored_lft <= MIN_VALID_LIFETIME) { /* valid_lft <= stored_lft is always true */ - /* XXX: IPsec */ - update_lft = 0; + /* + * RFC 4862 Section 5.5.3e: + * "Note that the preferred lifetime of + * the corresponding address is always + * reset to the Preferred Lifetime in + * the received Prefix Information + * option, regardless of whether the + * valid lifetime is also reset or + * ignored." + * + * So if the preferred lifetime in + * this advertisement is different + * than what we have stored, but the + * valid lifetime is invalid, just + * reset prefered_lft. + * + * We must set the valid lifetime + * to the stored lifetime since we'll + * be updating the timestamp below, + * else we'll set it back to the + * minumum. + */ + if (prefered_lft != ifp->prefered_lft) { + valid_lft = stored_lft; + update_lft = 1; + } } else { valid_lft = MIN_VALID_LIFETIME; if (valid_lft < prefered_lft) @@ -2765,7 +2790,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) spin_unlock_bh(&ifp->lock); read_unlock_bh(&idev->lock); /* - * If the defice is not ready: + * If the device is not ready: * - keep it tentative if it is a permanent address. * - otherwise, kill it. */ @@ -3084,7 +3109,7 @@ restart: spin_unlock(&ifp->lock); continue; } else if (age >= ifp->prefered_lft) { - /* jiffies - ifp->tsamp > age >= ifp->prefered_lft */ + /* jiffies - ifp->tstamp > age >= ifp->prefered_lft */ int deprecate = 0; if (!(ifp->flags&IFA_F_DEPRECATED)) { @@ -3361,7 +3386,10 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, valid = ifa->valid_lft; if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - ifa->tstamp)/HZ; - preferred -= tval; + if (preferred > tval) + preferred -= tval; + else + preferred = 0; if (valid != INFINITY_LIFE_TIME) valid -= tval; } @@ -3986,6 +4014,75 @@ static int addrconf_sysctl_forward_strategy(ctl_table *table, return addrconf_fixup_forwarding(table, valp, val); } +static void dev_disable_change(struct inet6_dev *idev) +{ + if (!idev || !idev->dev) + return; + + if (idev->cnf.disable_ipv6) + addrconf_notify(NULL, NETDEV_DOWN, idev->dev); + else + addrconf_notify(NULL, NETDEV_UP, idev->dev); +} + +static void addrconf_disable_change(struct net *net, __s32 newf) +{ + struct net_device *dev; + struct inet6_dev *idev; + + read_lock(&dev_base_lock); + for_each_netdev(net, dev) { + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { + int changed = (!idev->cnf.disable_ipv6) ^ (!newf); + idev->cnf.disable_ipv6 = newf; + if (changed) + dev_disable_change(idev); + } + rcu_read_unlock(); + } + read_unlock(&dev_base_lock); +} + +static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old) +{ + struct net *net; + + net = (struct net *)table->extra2; + + if (p == &net->ipv6.devconf_dflt->disable_ipv6) + return 0; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (p == &net->ipv6.devconf_all->disable_ipv6) { + __s32 newf = net->ipv6.devconf_all->disable_ipv6; + net->ipv6.devconf_dflt->disable_ipv6 = newf; + addrconf_disable_change(net, newf); + } else if ((!*p) ^ (!old)) + dev_disable_change((struct inet6_dev *)table->extra1); + + rtnl_unlock(); + return 0; +} + +static +int addrconf_sysctl_disable(ctl_table *ctl, int write, struct file * filp, + 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); + + if (write) + ret = addrconf_disable_ipv6(ctl, valp, val); + return ret; +} + static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; @@ -4223,7 +4320,8 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.disable_ipv6, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = addrconf_sysctl_disable, + .strategy = sysctl_intvec, }, { .ctl_name = CTL_UNNUMBERED, @@ -4344,6 +4442,10 @@ static int addrconf_init_net(struct net *net) dflt = kmemdup(dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); if (dflt == NULL) goto err_alloc_dflt; + } else { + /* these will be inherited by all namespaces */ + dflt->autoconf = ipv6_defaults.autoconf; + dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; } net->ipv6.devconf_all = all; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 61f55386a23..45f9a2a42d5 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -72,9 +72,21 @@ MODULE_LICENSE("GPL"); static struct list_head inetsw6[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw6_lock); -static int disable_ipv6 = 0; -module_param_named(disable, disable_ipv6, int, 0); -MODULE_PARM_DESC(disable, "Disable IPv6 such that it is non-functional"); +struct ipv6_params ipv6_defaults = { + .disable_ipv6 = 0, + .autoconf = 1, +}; + +static int disable_ipv6_mod = 0; + +module_param_named(disable, disable_ipv6_mod, int, 0444); +MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional"); + +module_param_named(disable_ipv6, ipv6_defaults.disable_ipv6, int, 0444); +MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces"); + +module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444); +MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces"); static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { @@ -294,8 +306,10 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) v4addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && - chk_addr_ret != RTN_BROADCAST) + chk_addr_ret != RTN_BROADCAST) { + err = -EADDRNOTAVAIL; goto out; + } } else { if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; @@ -817,13 +831,20 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, struct sk_buff *p; struct ipv6hdr *iph; unsigned int nlen; + unsigned int hlen; + unsigned int off; int flush = 1; int proto; __wsum csum; - iph = skb_gro_header(skb, sizeof(*iph)); - if (unlikely(!iph)) - goto out; + off = skb_gro_offset(skb); + hlen = off + sizeof(*iph); + iph = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + iph = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!iph)) + goto out; + } skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); @@ -1031,7 +1052,7 @@ static int __init inet6_init(void) for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); - if (disable_ipv6) { + if (disable_ipv6_mod) { printk(KERN_INFO "IPv6: Loaded, but administratively disabled, " "reboot required to enable\n"); @@ -1220,7 +1241,7 @@ module_init(inet6_init); static void __exit inet6_exit(void) { - if (disable_ipv6) + if (disable_ipv6_mod) return; /* First of all disallow new sockets creation. */ @@ -1265,6 +1286,8 @@ static void __exit inet6_exit(void) proto_unregister(&udplitev6_prot); proto_unregister(&udpv6_prot); proto_unregister(&tcpv6_prot); + + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } module_exit(inet6_exit); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 52449f7a1b7..86f42a288c4 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -405,7 +405,7 @@ out: } static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index c2f250150db..678bb95b152 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -354,7 +354,7 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) } static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 1c7f400a3cf..4aae658e550 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -277,7 +277,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - IP6_INC_STATS_BH(dev_net(skb->dst->dev), ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; @@ -288,7 +288,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) dstbuf = opt->dst1; #endif - dst = dst_clone(skb->dst); + dst = dst_clone(skb_dst(skb)); if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { dst_release(dst); skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; @@ -333,7 +333,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; @@ -343,7 +343,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) || skb->pkt_type != PACKET_HOST) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -358,7 +358,7 @@ looped_back: * processed by own */ if (!addr) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -384,7 +384,7 @@ looped_back: goto unknown_rh; /* Silently discard invalid RTH type 2 */ if (hdr->hdrlen != 2 || hdr->segments_left != 1) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; @@ -403,7 +403,7 @@ looped_back: n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - @@ -417,7 +417,7 @@ looped_back: if (skb_cloned(skb)) { /* the copy is a forwarded packet */ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -1; @@ -440,13 +440,13 @@ looped_back: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, IPPROTO_ROUTING) < 0) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } - if (!ipv6_chk_home_addr(dev_net(skb->dst->dev), addr)) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + if (!ipv6_chk_home_addr(dev_net(skb_dst(skb)->dev), addr)) { + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -458,7 +458,7 @@ looped_back: } if (ipv6_addr_is_multicast(addr)) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -468,17 +468,17 @@ looped_back: ipv6_addr_copy(addr, &ipv6_hdr(skb)->daddr); ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &daddr); - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); ip6_route_input(skb); - if (skb->dst->error) { + if (skb_dst(skb)->error) { skb_push(skb, skb->data - skb_network_header(skb)); dst_input(skb); return -1; } - if (skb->dst->dev->flags&IFF_LOOPBACK) { + if (skb_dst(skb)->dev->flags&IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0, skb->dev); @@ -494,7 +494,7 @@ looped_back: return -1; unknown_rh: - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb_network_header(skb)); return -1; @@ -552,11 +552,11 @@ void ipv6_exthdrs_exit(void) **********************************/ /* - * Note: we cannot rely on skb->dst before we assign it in ip6_route_input(). + * Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input(). */ static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb) { - return skb->dst ? ip6_dst_idev(skb->dst) : __in6_dev_get(skb->dev); + return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev); } /* Router Alert as of RFC 2711 */ @@ -581,7 +581,7 @@ static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); u32 pkt_len; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index f5de3f9dc69..00a7a5e4ac9 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -151,7 +151,7 @@ static const struct nla_policy fib6_rule_policy[FRA_MAX+1] = { }; static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_rule_hdr *frh, + struct fib_rule_hdr *frh, struct nlattr **tb) { int err = -EINVAL; @@ -211,7 +211,7 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, } static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_rule_hdr *frh) + struct fib_rule_hdr *frh) { struct fib6_rule *rule6 = (struct fib6_rule *) rule; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 36dff880718..eab62a7a8f0 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -117,7 +117,7 @@ static __inline__ void icmpv6_xmit_unlock(struct sock *sk) /* * Slightly more convenient version of icmpv6_send. */ -void icmpv6_param_prob(struct sk_buff *skb, int code, int pos) +void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev); kfree_skb(skb); @@ -161,7 +161,7 @@ static int is_ineligible(struct sk_buff *skb) /* * Check the ICMP output rate limit */ -static inline int icmpv6_xrlim_allow(struct sock *sk, int type, +static inline int icmpv6_xrlim_allow(struct sock *sk, u8 type, struct flowi *fl) { struct dst_entry *dst; @@ -305,7 +305,7 @@ static inline void mip6_addr_swap(struct sk_buff *skb) {} /* * Send an ICMP message in response to a packet in error */ -void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, +void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, struct net_device *dev) { struct net *net = dev_net(skb->dev); @@ -590,7 +590,7 @@ out: icmpv6_xmit_unlock(sk); } -static void icmpv6_notify(struct sk_buff *skb, int type, int code, __be32 info) +static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { struct inet6_protocol *ipprot; int inner_offset; @@ -643,7 +643,7 @@ static int icmpv6_rcv(struct sk_buff *skb) struct in6_addr *saddr, *daddr; struct ipv6hdr *orig_hdr; struct icmp6hdr *hdr; - int type; + u8 type; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); @@ -914,7 +914,7 @@ static const struct icmp6_err { }, }; -int icmpv6_err_convert(int type, int code, int *err) +int icmpv6_err_convert(u8 type, u8 code, int *err) { int fatal = 0; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 3c3732d50c1..cc4797dd832 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -228,7 +228,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) __inet6_csk_dst_store(sk, dst, NULL, NULL); } - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); /* Restore final destination back after routing done */ ipv6_addr_copy(&fl.fl6_dst, &np->daddr); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 8f04bd9da27..6d6a4277c67 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -48,7 +48,7 @@ inline int ip6_rcv_finish( struct sk_buff *skb) { - if (skb->dst == NULL) + if (skb_dst(skb) == NULL) ip6_route_input(skb); return dst_input(skb); @@ -70,7 +70,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt idev = __in6_dev_get(skb->dev); - IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INRECEIVES); + IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_IN, skb->len); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || !idev || unlikely(idev->cnf.disable_ipv6)) { @@ -91,7 +91,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt * arrived via the sending interface (ethX), because of the * nature of scoping architecture. --yoshfuji */ - IP6CB(skb)->iif = skb->dst ? ip6_dst_idev(skb->dst)->dev->ifindex : dev->ifindex; + IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; @@ -139,6 +139,9 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt rcu_read_unlock(); + /* Must drop socket now because of tproxy. */ + skb_orphan(skb); + return NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish); err: @@ -161,7 +164,7 @@ static int ip6_input_finish(struct sk_buff *skb) int nexthdr, raw; u8 hash; struct inet6_dev *idev; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); /* * Parse extension headers @@ -169,7 +172,7 @@ static int ip6_input_finish(struct sk_buff *skb) rcu_read_lock(); resubmit: - idev = ip6_dst_idev(skb->dst); + idev = ip6_dst_idev(skb_dst(skb)); if (!pskb_pull(skb, skb_transport_offset(skb))) goto discard; nhoff = IP6CB(skb)->nhoff; @@ -242,8 +245,9 @@ int ip6_mc_input(struct sk_buff *skb) struct ipv6hdr *hdr; int deliver; - IP6_INC_STATS_BH(dev_net(skb->dst->dev), - ip6_dst_idev(skb->dst), IPSTATS_MIB_INMCASTPKTS); + IP6_UPD_PO_STATS_BH(dev_net(skb_dst(skb)->dev), + ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST, + skb->len); hdr = ipv6_hdr(skb); deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 9fb49c3b518..87f8419a68f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -78,7 +78,7 @@ int __ip6_local_out(struct sk_buff *skb) len = 0; ipv6_hdr(skb)->payload_len = htons(len); - return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dst->dev, + return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, dst_output); } @@ -96,7 +96,7 @@ EXPORT_SYMBOL_GPL(ip6_local_out); static int ip6_output_finish(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); if (dst->hh) return neigh_hh_output(dst->hh, skb); @@ -117,7 +117,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) __skb_pull(newskb, skb_network_offset(newskb)); newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!newskb->dst); + WARN_ON(!skb_dst(newskb)); netif_rx(newskb); return 0; @@ -126,7 +126,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) static int ip6_output2(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); @@ -134,7 +134,7 @@ static int ip6_output2(struct sk_buff *skb) if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL; - struct inet6_dev *idev = ip6_dst_idev(skb->dst); + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && ((mroute6_socket(dev_net(dev)) && @@ -159,7 +159,8 @@ static int ip6_output2(struct sk_buff *skb) } } - IP6_INC_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCASTPKTS); + IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST, + skb->len); } return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dev, @@ -171,21 +172,21 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb) struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ? - skb->dst->dev->mtu : dst_mtu(skb->dst); + skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); } int ip6_output(struct sk_buff *skb) { - struct inet6_dev *idev = ip6_dst_idev(skb->dst); + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (unlikely(idev->cnf.disable_ipv6)) { - IP6_INC_STATS(dev_net(skb->dst->dev), idev, + IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || - dst_allfrag(skb->dst)) + dst_allfrag(skb_dst(skb))) return ip6_fragment(skb, ip6_output2); else return ip6_output2(skb); @@ -201,7 +202,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl->fl6_dst; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr; u8 proto = fl->proto; int seg_len = skb->len; @@ -221,7 +222,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if (skb_headroom(skb) < head_room) { struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); if (skb2 == NULL) { - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -ENOBUFS; @@ -275,8 +276,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) { - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), - IPSTATS_MIB_OUTREQUESTS); + IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUT, skb->len); return NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, dst_output); } @@ -285,7 +286,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n"); skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } @@ -415,7 +416,7 @@ static inline int ip6_forward_finish(struct sk_buff *skb) int ip6_forward(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); @@ -484,7 +485,7 @@ int ip6_forward(struct sk_buff *skb) IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } - dst = skb->dst; + dst = skb_dst(skb); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. @@ -565,8 +566,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; - dst_release(to->dst); - to->dst = dst_clone(from->dst); + skb_dst_drop(to); + skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; to->mark = from->mark; @@ -623,7 +624,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; - struct rt6_info *rt = (struct rt6_info*)skb->dst; + struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; @@ -631,7 +632,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; @@ -643,9 +644,9 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) * check should be redundant, but it's free.) */ if (!skb->local_df) { - skb->dev = skb->dst->dev; + skb->dev = skb_dst(skb)->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; @@ -657,7 +658,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) } mtu -= hlen + sizeof(struct frag_hdr); - if (skb_shinfo(skb)->frag_list) { + if (skb_has_frags(skb)) { int first_len = skb_pagelen(skb); int truesizes = 0; @@ -666,7 +667,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_cloned(skb)) goto slow_path; - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) { + skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || @@ -679,7 +680,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) BUG_ON(frag->sk); if (skb->sk) { - sock_hold(skb->sk); frag->sk = skb->sk; frag->destructor = sock_wfree; truesizes += frag->truesize; @@ -689,13 +689,13 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) err = 0; offset = 0; frag = skb_shinfo(skb)->frag_list; - skb_shinfo(skb)->frag_list = NULL; + skb_frag_list_init(skb); /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); return -ENOMEM; } @@ -808,7 +808,7 @@ slow_path: if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; @@ -872,16 +872,16 @@ slow_path: if (err) goto fail; - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGCREATES); } - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); kfree_skb(skb); return err; fail: - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; @@ -1484,7 +1484,6 @@ int ip6_push_pending_frames(struct sock *sk) skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; - __sock_put(tmp_skb->sk); tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } @@ -1515,10 +1514,10 @@ int ip6_push_pending_frames(struct sock *sk) skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb->dst = dst_clone(&rt->u.dst); - IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); + skb_dst_set(skb, dst_clone(&rt->u.dst)); + IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { - struct inet6_dev *idev = ip6_dst_idev(skb->dst); + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type); ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); @@ -1544,8 +1543,8 @@ void ip6_flush_pending_frames(struct sock *sk) struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) { - if (skb->dst) - IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb->dst), + if (skb_dst(skb)) + IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index d994c55a5b1..51f410e7775 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -394,13 +394,13 @@ parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw) static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, - int *type, int *code, int *msg, __u32 *info, int offset) + u8 *type, u8 *code, int *msg, __u32 *info, int offset) { struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data; struct ip6_tnl *t; int rel_msg = 0; - int rel_type = ICMPV6_DEST_UNREACH; - int rel_code = ICMPV6_ADDR_UNREACH; + u8 rel_type = ICMPV6_DEST_UNREACH; + u8 rel_code = ICMPV6_ADDR_UNREACH; __u32 rel_info = 0; __u16 len; int err = -ENOENT; @@ -488,11 +488,11 @@ out: static int ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { int rel_msg = 0; - int rel_type = type; - int rel_code = code; + u8 rel_type = type; + u8 rel_code = code; __u32 rel_info = ntohl(info); int err; struct sk_buff *skb2; @@ -532,8 +532,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!skb2) return 0; - dst_release(skb2->dst); - skb2->dst = NULL; + skb_dst_drop(skb2); + skb_pull(skb2, offset); skb_reset_network_header(skb2); eiph = ip_hdr(skb2); @@ -560,21 +560,21 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ip_rt_put(rt); goto out; } - skb2->dst = (struct dst_entry *)rt; + skb_dst_set(skb2, (struct dst_entry *)rt); } else { ip_rt_put(rt); if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || - skb2->dst->dev->type != ARPHRD_TUNNEL) + skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) goto out; } /* change mtu on this route */ if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) { - if (rel_info > dst_mtu(skb2->dst)) + if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb2->dst->ops->update_pmtu(skb2->dst, rel_info); + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -586,11 +586,11 @@ out: static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { int rel_msg = 0; - int rel_type = type; - int rel_code = code; + u8 rel_type = type; + u8 rel_code = code; __u32 rel_info = ntohl(info); int err; @@ -606,8 +606,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!skb2) return 0; - dst_release(skb2->dst); - skb2->dst = NULL; + skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); @@ -720,8 +719,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, skb->pkt_type = PACKET_HOST; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); skb->dev = t->dev; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); dscp_ecn_decapsulate(t, ipv6h, skb); @@ -885,8 +883,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (skb->len > mtu) { *pmtu = mtu; err = -EMSGSIZE; @@ -910,8 +908,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, kfree_skb(skb); skb = new_skb; } - dst_release(skb->dst); - skb->dst = dst_clone(dst); + skb_dst_drop(skb); + skb_dst_set(skb, dst_clone(dst)); skb->transport_header = skb->network_header; @@ -1100,8 +1098,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct ip6_tnl_parm *p = &t->parms; struct flowi *fl = &t->fl; - memcpy(&dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); - memcpy(&dev->broadcast, &p->raddr, sizeof(struct in6_addr)); + memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ ipv6_addr_copy(&fl->fl6_src, &p->laddr); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 228be551e9c..c769f155c69 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -398,10 +398,9 @@ static int pim6_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; - dst_release(skb->dst); + skb_dst_drop(skb); reg_dev->stats.rx_bytes += skb->len; reg_dev->stats.rx_packets++; - skb->dst = NULL; nf_reset(skb); netif_rx(skb); dev_put(reg_dev); @@ -442,6 +441,7 @@ static void reg_vif_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->destructor = free_netdev; + dev->features |= NETIF_F_NETNS_LOCAL; } static struct net_device *ip6mr_reg_vif(struct net *net) @@ -849,7 +849,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); - skb->dst = dst_clone(pkt->dst); + skb_dst_set(skb, dst_clone(skb_dst(pkt))); skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -1078,7 +1078,18 @@ int __init ip6_mr_init(void) err = register_netdevice_notifier(&ip6_mr_notifier); if (err) goto reg_notif_fail; +#ifdef CONFIG_IPV6_PIMSM_V2 + if (inet6_add_protocol(&pim6_protocol, IPPROTO_PIM) < 0) { + printk(KERN_ERR "ip6_mr_init: can't add PIM protocol\n"); + err = -EAGAIN; + goto add_proto_fail; + } +#endif return 0; +#ifdef CONFIG_IPV6_PIMSM_V2 +add_proto_fail: + unregister_netdevice_notifier(&ip6_mr_notifier); +#endif reg_notif_fail: del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ip6mr_net_ops); @@ -1364,14 +1375,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int if (v != net->ipv6.mroute_do_pim) { net->ipv6.mroute_do_pim = v; net->ipv6.mroute_do_assert = v; - if (net->ipv6.mroute_do_pim) - ret = inet6_add_protocol(&pim6_protocol, - IPPROTO_PIM); - else - ret = inet6_del_protocol(&pim6_protocol, - IPPROTO_PIM); - if (ret < 0) - ret = -EAGAIN; } rtnl_unlock(); return ret; @@ -1487,7 +1490,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) static inline int ip6mr_forward2_finish(struct sk_buff *skb) { - IP6_INC_STATS_BH(dev_net(skb->dst->dev), ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); return dst_output(skb); } @@ -1532,8 +1535,8 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) if (!dst) goto out_free; - dst_release(skb->dst); - skb->dst = dst; + skb_dst_drop(skb); + skb_dst_set(skb, dst); /* * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally @@ -1722,7 +1725,7 @@ int ip6mr_get_route(struct net *net, { int err; struct mfc6_cache *cache; - struct rt6_info *rt = (struct rt6_info *)skb->dst; + struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); read_lock(&mrt_lock); cache = ip6mr_cache_find(net, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 3a0b3be7ece..79c172f1ff0 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -51,7 +51,7 @@ #include <linux/mutex.h> static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { __be32 spi; struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index a51fb33e686..4b264ed40a8 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1448,8 +1448,10 @@ static void mld_sendpack(struct sk_buff *skb) struct net *net = dev_net(skb->dev); int err; struct flowi fl; + struct dst_entry *dst; + + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb->tail - skb->network_header) - sizeof(*pip6); mldlen = skb->tail - skb->transport_header; pip6->payload_len = htons(payload_len); @@ -1458,9 +1460,9 @@ static void mld_sendpack(struct sk_buff *skb) IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), mldlen, 0)); - skb->dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); + dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); - if (!skb->dst) { + if (!dst) { err = -ENOMEM; goto err_out; } @@ -1469,17 +1471,20 @@ static void mld_sendpack(struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(net, &skb->dst, &fl, NULL, 0); + err = xfrm_lookup(net, &dst, &fl, NULL, 0); + skb_dst_set(skb, dst); if (err) goto err_out; + payload_len = skb->len; + err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); - IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTMCASTPKTS); + IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); } else IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS); @@ -1772,11 +1777,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct flowi fl; + struct dst_entry *dst; - rcu_read_lock(); - IP6_INC_STATS(net, __in6_dev_get(dev), - IPSTATS_MIB_OUTREQUESTS); - rcu_read_unlock(); if (type == ICMPV6_MGM_REDUCTION) snd_addr = &in6addr_linklocal_allrouters; else @@ -1786,6 +1788,11 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) payload_len = len + sizeof(ra); full_len = sizeof(struct ipv6hdr) + payload_len; + rcu_read_lock(); + IP6_UPD_PO_STATS(net, __in6_dev_get(dev), + IPSTATS_MIB_OUT, full_len); + rcu_read_unlock(); + skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + full_len, 1, &err); if (skb == NULL) { @@ -1824,8 +1831,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) idev = in6_dev_get(skb->dev); - skb->dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); - if (!skb->dst) { + dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); + if (!dst) { err = -ENOMEM; goto err_out; } @@ -1834,17 +1841,18 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(net, &skb->dst, &fl, NULL, 0); + err = xfrm_lookup(net, &dst, &fl, NULL, 0); if (err) goto err_out; + skb_dst_set(skb, dst); err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTMCASTPKTS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index f995e19c87a..f797e8c6f3b 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -54,7 +54,7 @@ static inline void *mip6_padn(__u8 *data, __u8 padlen) return data + padlen; } -static inline void mip6_param_prob(struct sk_buff *skb, int code, int pos) +static inline void mip6_param_prob(struct sk_buff *skb, u8 code, int pos) { icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9f061d1adbc..9eb68e92cc1 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -465,8 +465,8 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, 1, &err); if (!skb) { ND_PRINTK0(KERN_ERR - "ICMPv6 ND: %s() failed to allocate an skb.\n", - __func__); + "ICMPv6 ND: %s() failed to allocate an skb, err=%d.\n", + __func__, err); return NULL; } @@ -530,10 +530,10 @@ void ndisc_send_skb(struct sk_buff *skb, return; } - skb->dst = dst; + skb_dst_set(skb, dst); idev = in6_dev_get(dst->dev); - IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, dst_output); @@ -658,6 +658,7 @@ 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) @@ -1561,8 +1562,8 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, 1, &err); if (buff == NULL) { ND_PRINTK0(KERN_ERR - "ICMPv6 Redirect: %s() failed to allocate an skb.\n", - __func__); + "ICMPv6 Redirect: %s() failed to allocate an skb, err=%d.\n", + __func__, err); goto release; } @@ -1611,9 +1612,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, len, IPPROTO_ICMPV6, csum_partial(icmph, len, 0)); - buff->dst = dst; + skb_dst_set(buff, dst); idev = in6_dev_get(dst->dev); - IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev, dst_output); if (!err) { diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 834cea69fb5..d5ed92b1434 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -12,7 +12,7 @@ int ip6_route_me_harder(struct sk_buff *skb) { - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); struct ipv6hdr *iph = ipv6_hdr(skb); struct dst_entry *dst; struct flowi fl = { @@ -28,9 +28,15 @@ int ip6_route_me_harder(struct sk_buff *skb) #ifdef CONFIG_XFRM if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - xfrm_decode_session(skb, &fl, AF_INET6) == 0) - if (xfrm_lookup(net, &skb->dst, &fl, skb->sk, 0)) + xfrm_decode_session(skb, &fl, AF_INET6) == 0) { + struct dst_entry *dst2 = skb_dst(skb); + + if (xfrm_lookup(net, &dst2, &fl, skb->sk, 0)) { + skb_dst_set(skb, NULL); return -1; + } + skb_dst_set(skb, dst2); + } #endif if (dst->error) { @@ -41,9 +47,9 @@ int ip6_route_me_harder(struct sk_buff *skb) } /* Drop old route. */ - dst_release(skb->dst); + skb_dst_drop(skb); - skb->dst = dst; + skb_dst_set(skb, dst); return 0; } EXPORT_SYMBOL(ip6_route_me_harder); diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index b693f841aeb..1cf3f0c6a95 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -598,7 +598,7 @@ static int __init ip6_queue_init(void) #ifdef CONFIG_SYSCTL ipq_sysctl_header = register_sysctl_paths(net_ipv6_ctl_path, ipq_table); #endif - status = nf_register_queue_handler(PF_INET6, &nfqh); + status = nf_register_queue_handler(NFPROTO_IPV6, &nfqh); if (status < 0) { printk(KERN_ERR "ip6_queue: failed to register queue handler\n"); goto cleanup_sysctl; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 219e165aea1..ced1f2c0cb6 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -270,8 +270,8 @@ static struct nf_loginfo trace_loginfo = { /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, - char *hookname, char **chainname, - char **comment, unsigned int *rulenum) + const char *hookname, const char **chainname, + const char **comment, unsigned int *rulenum) { struct ip6t_standard_target *t = (void *)ip6t_get_target(s); @@ -289,8 +289,8 @@ get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, && unconditional(&s->ipv6)) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname - ? (char *)comments[NF_IP6_TRACE_COMMENT_POLICY] - : (char *)comments[NF_IP6_TRACE_COMMENT_RETURN]; + ? comments[NF_IP6_TRACE_COMMENT_POLICY] + : comments[NF_IP6_TRACE_COMMENT_RETURN]; } return 1; } else @@ -309,14 +309,14 @@ static void trace_packet(struct sk_buff *skb, { void *table_base; const struct ip6t_entry *root; - char *hookname, *chainname, *comment; + const char *hookname, *chainname, *comment; unsigned int rulenum = 0; - table_base = (void *)private->entries[smp_processor_id()]; + table_base = private->entries[smp_processor_id()]; root = get_entry(table_base, private->hook_entry[hook]); - hookname = chainname = (char *)hooknames[hook]; - comment = (char *)comments[NF_IP6_TRACE_COMMENT_RULE]; + hookname = chainname = hooknames[hook]; + comment = comments[NF_IP6_TRACE_COMMENT_RULE]; IP6T_ENTRY_ITERATE(root, private->size - private->hook_entry[hook], @@ -329,6 +329,12 @@ static void trace_packet(struct sk_buff *skb, } #endif +static inline __pure struct ip6t_entry * +ip6t_next_entry(const struct ip6t_entry *entry) +{ + return (void *)entry + entry->next_offset; +} + /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ip6t_do_table(struct sk_buff *skb, @@ -337,6 +343,8 @@ ip6t_do_table(struct sk_buff *skb, const struct net_device *out, struct xt_table *table) { +#define tb_comefrom ((struct ip6t_entry *)table_base)->comefrom + static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); bool hotdrop = false; /* Initializing verdict to NF_DROP keeps gcc happy. */ @@ -361,7 +369,7 @@ ip6t_do_table(struct sk_buff *skb, mtpar.in = tgpar.in = in; mtpar.out = tgpar.out = out; mtpar.family = tgpar.family = NFPROTO_IPV6; - tgpar.hooknum = hook; + mtpar.hooknum = tgpar.hooknum = hook; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); @@ -375,96 +383,86 @@ ip6t_do_table(struct sk_buff *skb, back = get_entry(table_base, private->underflow[hook]); do { + struct ip6t_entry_target *t; + IP_NF_ASSERT(e); IP_NF_ASSERT(back); - if (ip6_packet_match(skb, indev, outdev, &e->ipv6, - &mtpar.thoff, &mtpar.fragoff, &hotdrop)) { - struct ip6t_entry_target *t; - - if (IP6T_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) - goto no_match; + if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, + &mtpar.thoff, &mtpar.fragoff, &hotdrop) || + IP6T_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) { + e = ip6t_next_entry(e); + continue; + } - ADD_COUNTER(e->counters, - ntohs(ipv6_hdr(skb)->payload_len) + - sizeof(struct ipv6hdr), 1); + ADD_COUNTER(e->counters, + ntohs(ipv6_hdr(skb)->payload_len) + + sizeof(struct ipv6hdr), 1); - t = ip6t_get_target(e); - IP_NF_ASSERT(t->u.kernel.target); + t = ip6t_get_target(e); + IP_NF_ASSERT(t->u.kernel.target); #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) - /* The packet is traced: log it */ - if (unlikely(skb->nf_trace)) - trace_packet(skb, hook, in, out, - table->name, private, e); + /* The packet is traced: log it */ + if (unlikely(skb->nf_trace)) + trace_packet(skb, hook, in, out, + table->name, private, e); #endif - /* Standard target? */ - if (!t->u.kernel.target->target) { - int v; - - v = ((struct ip6t_standard_target *)t)->verdict; - if (v < 0) { - /* Pop from stack? */ - if (v != IP6T_RETURN) { - verdict = (unsigned)(-v) - 1; - break; - } - e = back; - back = get_entry(table_base, - back->comefrom); - continue; - } - if (table_base + v != (void *)e + e->next_offset - && !(e->ipv6.flags & IP6T_F_GOTO)) { - /* Save old back ptr in next entry */ - struct ip6t_entry *next - = (void *)e + e->next_offset; - next->comefrom - = (void *)back - table_base; - /* set back pointer to next entry */ - back = next; + /* Standard target? */ + if (!t->u.kernel.target->target) { + int v; + + v = ((struct ip6t_standard_target *)t)->verdict; + if (v < 0) { + /* Pop from stack? */ + if (v != IP6T_RETURN) { + verdict = (unsigned)(-v) - 1; + break; } + e = back; + back = get_entry(table_base, back->comefrom); + continue; + } + if (table_base + v != ip6t_next_entry(e) + && !(e->ipv6.flags & IP6T_F_GOTO)) { + /* Save old back ptr in next entry */ + struct ip6t_entry *next = ip6t_next_entry(e); + next->comefrom = (void *)back - table_base; + /* set back pointer to next entry */ + back = next; + } - e = get_entry(table_base, v); - } else { - /* Targets which reenter must return - abs. verdicts */ - tgpar.target = t->u.kernel.target; - tgpar.targinfo = t->data; + e = get_entry(table_base, v); + continue; + } -#ifdef CONFIG_NETFILTER_DEBUG - ((struct ip6t_entry *)table_base)->comefrom - = 0xeeeeeeec; -#endif - verdict = t->u.kernel.target->target(skb, - &tgpar); + /* Targets which reenter must return + abs. verdicts */ + tgpar.target = t->u.kernel.target; + tgpar.targinfo = t->data; #ifdef CONFIG_NETFILTER_DEBUG - if (((struct ip6t_entry *)table_base)->comefrom - != 0xeeeeeeec - && verdict == IP6T_CONTINUE) { - printk("Target %s reentered!\n", - t->u.kernel.target->name); - verdict = NF_DROP; - } - ((struct ip6t_entry *)table_base)->comefrom - = 0x57acc001; + tb_comefrom = 0xeeeeeeec; #endif - if (verdict == IP6T_CONTINUE) - e = (void *)e + e->next_offset; - else - /* Verdict */ - break; - } - } else { + verdict = t->u.kernel.target->target(skb, &tgpar); - no_match: - e = (void *)e + e->next_offset; +#ifdef CONFIG_NETFILTER_DEBUG + if (tb_comefrom != 0xeeeeeeec && verdict == IP6T_CONTINUE) { + printk("Target %s reentered!\n", + t->u.kernel.target->name); + verdict = NF_DROP; } + tb_comefrom = 0x57acc001; +#endif + if (verdict == IP6T_CONTINUE) + e = ip6t_next_entry(e); + else + /* Verdict */ + break; } while (!hotdrop); #ifdef CONFIG_NETFILTER_DEBUG - ((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON; + tb_comefrom = NETFILTER_LINK_POISON; #endif xt_info_rdunlock_bh(); @@ -475,6 +473,8 @@ ip6t_do_table(struct sk_buff *skb, return NF_DROP; else return verdict; #endif + +#undef tb_comefrom } /* Figures out from what hook each rule can be called: returns 0 if @@ -2191,7 +2191,7 @@ static bool icmp6_checkentry(const struct xt_mtchk_param *par) static struct xt_target ip6t_standard_target __read_mostly = { .name = IP6T_STANDARD_TARGET, .targetsize = sizeof(int), - .family = AF_INET6, + .family = NFPROTO_IPV6, #ifdef CONFIG_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, @@ -2203,7 +2203,7 @@ static struct xt_target ip6t_error_target __read_mostly = { .name = IP6T_ERROR_TARGET, .target = ip6t_error, .targetsize = IP6T_FUNCTION_MAXNAMELEN, - .family = AF_INET6, + .family = NFPROTO_IPV6, }; static struct nf_sockopt_ops ip6t_sockopts = { @@ -2229,17 +2229,17 @@ static struct xt_match icmp6_matchstruct __read_mostly = { .matchsize = sizeof(struct ip6t_icmp), .checkentry = icmp6_checkentry, .proto = IPPROTO_ICMPV6, - .family = AF_INET6, + .family = NFPROTO_IPV6, }; static int __net_init ip6_tables_net_init(struct net *net) { - return xt_proto_init(net, AF_INET6); + return xt_proto_init(net, NFPROTO_IPV6); } static void __net_exit ip6_tables_net_exit(struct net *net) { - xt_proto_fini(net, AF_INET6); + xt_proto_fini(net, NFPROTO_IPV6); } static struct pernet_operations ip6_tables_net_ops = { diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 5a2d0a41694..5a7f00cd15c 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -112,7 +112,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) return; } - nskb->dst = dst; + skb_dst_set(nskb, dst); skb_reserve(nskb, hh_len + dst->header_len); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 9903227bf37..642dcb127ba 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -95,18 +95,10 @@ static int icmpv6_packet(struct nf_conn *ct, u_int8_t pf, unsigned int hooknum) { - /* Try to delete connection immediately after all replies: - won't actually vanish as we still have skb, and del_timer - means this will only run once even if count hits zero twice - (theoretically possible with SMP) */ - if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) { - if (atomic_dec_and_test(&ct->proto.icmp.count)) - nf_ct_kill_acct(ct, ctinfo, skb); - } else { - atomic_inc(&ct->proto.icmp.count); - nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct); - nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout); - } + /* Do not immediately delete the connection after the first + successful reply to avoid excessive conntrackd traffic + and also to handle correctly ICMP echo reply duplicates. */ + nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout); return NF_ACCEPT; } @@ -132,7 +124,6 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, type + 128); return false; } - atomic_set(&ct->proto.icmp.count, 0); return true; } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 058a5e4a60c..f3aba255ad9 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -409,7 +409,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ - if (skb_shinfo(head)->frag_list) { + if (skb_has_frags(head)) { struct sk_buff *clone; int i, plen = 0; @@ -420,7 +420,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) clone->next = head->next; head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_shinfo(head)->frag_list = NULL; + skb_frag_list_init(head); for (i=0; i<skb_shinfo(head)->nr_frags; i++) plen += skb_shinfo(head)->frags[i].size; clone->len = clone->data_len = head->data_len - plen; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 97c17fdd6f7..590ddefb7ff 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -61,7 +61,7 @@ static const struct file_operations sockstat6_seq_fops = { static struct snmp_mib snmp6_ipstats_list[] = { /* ipv6 mib according to RFC 2465 */ - SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INRECEIVES), + SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INPKTS), SNMP_MIB_ITEM("Ip6InHdrErrors", IPSTATS_MIB_INHDRERRORS), SNMP_MIB_ITEM("Ip6InTooBigErrors", IPSTATS_MIB_INTOOBIGERRORS), SNMP_MIB_ITEM("Ip6InNoRoutes", IPSTATS_MIB_INNOROUTES), @@ -71,7 +71,7 @@ static struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("Ip6InDelivers", IPSTATS_MIB_INDELIVERS), SNMP_MIB_ITEM("Ip6OutForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS), - SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTREQUESTS), + SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTPKTS), SNMP_MIB_ITEM("Ip6OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("Ip6OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("Ip6ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -83,6 +83,12 @@ static struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6FragCreates", IPSTATS_MIB_FRAGCREATES), SNMP_MIB_ITEM("Ip6InMcastPkts", IPSTATS_MIB_INMCASTPKTS), SNMP_MIB_ITEM("Ip6OutMcastPkts", IPSTATS_MIB_OUTMCASTPKTS), + SNMP_MIB_ITEM("Ip6InOctets", IPSTATS_MIB_INOCTETS), + SNMP_MIB_ITEM("Ip6OutOctets", IPSTATS_MIB_OUTOCTETS), + SNMP_MIB_ITEM("Ip6InMcastOctets", IPSTATS_MIB_INMCASTOCTETS), + SNMP_MIB_ITEM("Ip6OutMcastOctets", IPSTATS_MIB_OUTMCASTOCTETS), + SNMP_MIB_ITEM("Ip6InBcastOctets", IPSTATS_MIB_INBCASTOCTETS), + SNMP_MIB_ITEM("Ip6OutBcastOctets", IPSTATS_MIB_OUTBCASTOCTETS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 61f6827e590..d6c3c1c34b2 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -310,7 +310,7 @@ out: static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -343,7 +343,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, - int type, int code, int inner_offset, __be32 info) + u8 type, u8 code, int inner_offset, __be32 info) { struct sock *sk; int hash; @@ -625,7 +625,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb->dst = dst_clone(&rt->u.dst); + skb_dst_set(skb, dst_clone(&rt->u.dst)); skb_put(skb, length); skb_reset_network_header(skb); @@ -638,7 +638,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, if (err) goto error_fault; - IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); + IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) @@ -1130,7 +1130,8 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) switch(cmd) { case SIOCOUTQ: { - int amount = atomic_read(&sk->sk_wmem_alloc); + int amount = sk_wmem_alloc_get(sk); + return put_user(amount, (int __user *)arg); } case SIOCINQ: @@ -1236,8 +1237,8 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index e9ac7a12f59..2642a41a853 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -267,7 +267,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev, *next; struct net_device *dev; int offset, end; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); if (fq->q.last_in & INET_FRAG_COMPLETE) goto err; @@ -277,7 +277,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((u8 *)&fhdr->frag_off - @@ -310,7 +310,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, /* RFC2460 says always send parameter problem in * this case. -DaveM */ - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, payload_len)); @@ -434,7 +434,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, return -1; err: - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; @@ -494,7 +494,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ - if (skb_shinfo(head)->frag_list) { + if (skb_has_frags(head)) { struct sk_buff *clone; int i, plen = 0; @@ -503,7 +503,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, clone->next = head->next; head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_shinfo(head)->frag_list = NULL; + skb_frag_list_init(head); for (i=0; i<skb_shinfo(head)->nr_frags; i++) plen += skb_shinfo(head)->frags[i].size; clone->len = clone->data_len = head->data_len - plen; @@ -576,9 +576,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr = ipv6_hdr(skb); - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMREQDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); /* Jumbo payload inhibits frag. header */ if (hdr->payload_len==0) @@ -595,17 +595,17 @@ static int ipv6_frag_rcv(struct sk_buff *skb) /* It is not a fragmented frame */ skb->transport_header += sizeof(struct frag_hdr); IP6_INC_STATS_BH(net, - ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMOKS); + ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS); IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); return 1; } if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh) - ip6_evictor(net, ip6_dst_idev(skb->dst)); + ip6_evictor(net, ip6_dst_idev(skb_dst(skb))); if ((fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, - ip6_dst_idev(skb->dst))) != NULL) { + ip6_dst_idev(skb_dst(skb)))) != NULL) { int ret; spin_lock(&fq->q.lock); @@ -617,12 +617,12 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return ret; } - IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; fail_hdr: - IP6_INC_STATS(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb)); return -1; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 032a5ec391c..1473ee0a1f5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -800,7 +800,7 @@ void ip6_route_input(struct sk_buff *skb) if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; - skb->dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input); + skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input)); } static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, @@ -911,7 +911,7 @@ static void ip6_link_failure(struct sk_buff *skb) icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev); - rt = (struct rt6_info *) skb->dst; + rt = (struct rt6_info *) skb_dst(skb); if (rt) { if (rt->rt6i_flags&RTF_CACHE) { dst_set_expires(&rt->u.dst, 0); @@ -1865,10 +1865,10 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) * Drop the packet on the floor */ -static int ip6_pkt_drop(struct sk_buff *skb, int code, int ipstats_mib_noroutes) +static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { int type; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); @@ -1895,7 +1895,7 @@ static int ip6_pkt_discard(struct sk_buff *skb) static int ip6_pkt_discard_out(struct sk_buff *skb) { - skb->dev = skb->dst->dev; + skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } @@ -1908,7 +1908,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb) static int ip6_pkt_prohibit_out(struct sk_buff *skb) { - skb->dev = skb->dst->dev; + skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } @@ -2366,7 +2366,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl); - skb->dst = &rt->u.dst; + skb_dst_set(skb, &rt->u.dst); err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 664ab82e03b..98b7327d094 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -15,6 +15,7 @@ * 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> @@ -80,7 +81,7 @@ struct sit_net { static DEFINE_RWLOCK(ipip6_lock); static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, - __be32 remote, __be32 local) + struct net_device *dev, __be32 remote, __be32 local) { unsigned h0 = HASH(remote); unsigned h1 = HASH(local); @@ -89,18 +90,25 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, for (t = sitn->tunnels_r_l[h0^h1]; t; t = t->next) { if (local == t->parms.iph.saddr && - remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) + remote == t->parms.iph.daddr && + (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (t->dev->flags & IFF_UP)) return t; } for (t = sitn->tunnels_r[h0]; t; t = t->next) { - if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) + if (remote == t->parms.iph.daddr && + (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (t->dev->flags & IFF_UP)) return t; } for (t = sitn->tunnels_l[h1]; t; t = t->next) { - if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) + if (local == t->parms.iph.saddr && + (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (t->dev->flags & IFF_UP)) return t; } - if ((t = sitn->tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP)) + t = sitn->tunnels_wc[0]; + if ((t != NULL) && (t->dev->flags & IFF_UP)) return t; return NULL; } @@ -165,8 +173,14 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, struct sit_net *sitn = net_generic(net, sit_net_id); for (tp = __ipip6_bucket(sitn, parms); (t = *tp) != NULL; tp = &t->next) { - if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) - return t; + if (local == t->parms.iph.saddr && + remote == t->parms.iph.daddr && + parms->link == t->parms.link) { + if (create) + return NULL; + else + return t; + } } if (!create) goto failed; @@ -209,6 +223,44 @@ 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) { @@ -267,6 +319,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, 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; @@ -316,11 +369,23 @@ 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; @@ -339,6 +404,9 @@ 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; @@ -349,13 +417,16 @@ 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--; } } out: write_unlock(&ipip6_lock); - return 0; + return err; } static int @@ -446,7 +517,10 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = -ENOENT; read_lock(&ipip6_lock); - t = ipip6_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); + t = ipip6_tunnel_lookup(dev_net(skb->dev), + skb->dev, + iph->daddr, + iph->saddr); if (t == NULL || t->parms.iph.daddr == 0) goto out; @@ -481,8 +555,9 @@ static int ipip6_rcv(struct sk_buff *skb) iph = ip_hdr(skb); read_lock(&ipip6_lock); - if ((tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), - iph->saddr, iph->daddr)) != NULL) { + tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, + iph->saddr, iph->daddr); + if (tunnel != NULL) { secpath_reset(skb); skb->mac_header = skb->network_header; skb_reset_network_header(skb); @@ -500,8 +575,7 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel->dev->stats.rx_packets++; tunnel->dev->stats.rx_bytes += skb->len; skb->dev = tunnel->dev; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); nf_reset(skb); ipip6_ecn_decapsulate(iph, skb); netif_rx(skb); @@ -563,8 +637,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (dev->priv_flags & IFF_ISATAP) { struct neighbour *neigh = NULL; - if (skb->dst) - neigh = skb->dst->neighbour; + if (skb_dst(skb)) + neigh = skb_dst(skb)->neighbour; if (neigh == NULL) { if (net_ratelimit()) @@ -588,8 +662,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (!dst) { struct neighbour *neigh = NULL; - if (skb->dst) - neigh = skb->dst->neighbour; + if (skb_dst(skb)) + neigh = skb_dst(skb)->neighbour; if (neigh == NULL) { if (net_ratelimit()) @@ -639,7 +713,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (tiph->frag_off) mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); else - mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu; + mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (mtu < 68) { stats->collisions++; @@ -648,8 +722,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (tunnel->parms.iph.daddr && skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (tunnel->parms.iph.daddr && skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); @@ -693,8 +767,8 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags = 0; - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. @@ -944,6 +1018,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr); dev->flags = IFF_NOARP; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 711175e0571..8c2513982b6 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -131,7 +131,7 @@ __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) int mssind; const __u16 mss = *mssp; - tcp_sk(sk)->last_synq_overflow = jiffies; + tcp_synq_overflow(sk); for (mssind = 0; mss > msstab[mssind + 1]; mssind++) ; @@ -175,7 +175,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) if (!sysctl_tcp_syncookies || !th->ack) goto out; - if (time_after(jiffies, tp->last_synq_overflow + TCP_TIMEOUT_INIT) || + if (tcp_synq_no_recent_overflow(sk) || (mss = cookie_check(skb, cookie)) == 0) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED); goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4b5aa185426..d849dd53b78 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -317,7 +317,7 @@ failure: } static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); @@ -896,6 +896,7 @@ 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 = { .md5_lookup = tcp_v6_reqsk_md5_lookup, + .calc_md5_hash = tcp_v6_md5_hash_skb, }; #endif @@ -941,9 +942,10 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb) return 0; } -struct sk_buff **tcp6_gro_receive(struct sk_buff **head, struct sk_buff *skb) +static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) { - struct ipv6hdr *iph = ipv6_hdr(skb); + struct ipv6hdr *iph = skb_gro_network_header(skb); switch (skb->ip_summed) { case CHECKSUM_COMPLETE: @@ -961,9 +963,8 @@ struct sk_buff **tcp6_gro_receive(struct sk_buff **head, struct sk_buff *skb) return tcp_gro_receive(head, skb); } -EXPORT_SYMBOL(tcp6_gro_receive); -int tcp6_gro_complete(struct sk_buff *skb) +static int tcp6_gro_complete(struct sk_buff *skb) { struct ipv6hdr *iph = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); @@ -974,7 +975,6 @@ int tcp6_gro_complete(struct sk_buff *skb) return tcp_gro_complete(skb); } -EXPORT_SYMBOL(tcp6_gro_complete); static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, struct tcp_md5sig_key *key, int rst) @@ -982,9 +982,10 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, struct tcphdr *th = tcp_hdr(skb), *t1; struct sk_buff *buff; struct flowi fl; - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); + struct dst_entry *dst; __be32 *topt; if (ts) @@ -1053,8 +1054,9 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, * Underlying function will use this to retrieve the network * namespace */ - if (!ip6_dst_lookup(ctl_sk, &buff->dst, &fl)) { - if (xfrm_lookup(net, &buff->dst, &fl, NULL, 0) >= 0) { + if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { + if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { + skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl, NULL, 0); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); if (rst) @@ -1440,7 +1442,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); if (newkey != NULL) - tcp_v6_md5_do_add(newsk, &inet6_sk(sk)->daddr, + tcp_v6_md5_do_add(newsk, &newnp->daddr, newkey, key->keylen); } #endif diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 669f280989c..633ad789eff 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -124,7 +124,7 @@ drop: } static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8905712cfbb..33b59bd92c4 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -177,10 +177,9 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, if (unlikely(sk = skb_steal_sock(skb))) return sk; - else - return __udp6_lib_lookup(dev_net(skb->dst->dev), &iph->saddr, sport, - &iph->daddr, dport, inet6_iif(skb), - udptable); + return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport, + &iph->daddr, dport, inet6_iif(skb), + udptable); } /* @@ -313,7 +312,7 @@ csum_copy_err: } void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info, + u8 type, u8 code, int offset, __be32 info, struct udp_table *udptable) { struct ipv6_pinfo *np; @@ -347,8 +346,8 @@ out: } static __inline__ void udpv6_err(struct sk_buff *skb, - struct inet6_skb_parm *opt, int type, - int code, int offset, __be32 info ) + struct inet6_skb_parm *opt, u8 type, + u8 code, int offset, __be32 info ) { __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } @@ -1062,8 +1061,8 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 23779208c33..6bb303471e2 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -9,7 +9,7 @@ extern int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int ); extern void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, - int , int , int , __be32 , struct udp_table *); + u8 , u8 , int , __be32 , struct udp_table *); extern int udp_v6_get_port(struct sock *sk, unsigned short snum); diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index ba162a82458..4818c48688f 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -20,7 +20,7 @@ static int udplitev6_rcv(struct sk_buff *skb) static void udplitev6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table); } diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index e20529b4c82..3927832227b 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -31,7 +31,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) */ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *top_iph; int dsfield; @@ -45,7 +45,7 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl, sizeof(top_iph->flow_lbl)); - top_iph->nexthdr = xfrm_af2proto(skb->dst->ops->family); + top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family); dsfield = XFRM_MODE_SKB_CB(skb)->tos; dsfield = INET_ECN_encapsulate(dsfield, dsfield); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 5ee5a031bc9..c4f4eef032a 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -30,7 +30,7 @@ EXPORT_SYMBOL(xfrm6_find_1stfragopt); static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); mtu = dst_mtu(dst); if (mtu < IPV6_MIN_MTU) @@ -90,6 +90,6 @@ static int xfrm6_output_finish(struct sk_buff *skb) int xfrm6_output(struct sk_buff *skb) { - return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb->dst->dev, + return NF_HOOK(PF_INET6, NF_INET_POST_ROUTING, skb, NULL, skb_dst(skb)->dev, xfrm6_output_finish); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index b4b16a43f27..3a3c677bc0f 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -157,7 +157,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr); ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr); - while (pskb_may_pull(skb, nh + offset + 1 - skb->data)) { + while (nh + offset + 1 < skb->data || + pskb_may_pull(skb, nh + offset + 1 - skb->data)) { nh = skb_network_header(skb); exthdr = (struct ipv6_opt_hdr *)(nh + offset); @@ -177,7 +178,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: - if (!onlyproto && pskb_may_pull(skb, nh + offset + 4 - skb->data)) { + if (!onlyproto && (nh + offset + 4 < skb->data || + pskb_may_pull(skb, nh + offset + 4 - skb->data))) { __be16 *ports = (__be16 *)exthdr; fl->fl_ip_sport = ports[!!reverse]; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 80193db224d..81a95c00e50 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -262,7 +262,7 @@ static int xfrm6_tunnel_rcv(struct sk_buff *skb) } static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { /* xfrm6_tunnel native err handling */ switch (type) { diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 1627050e29f..f1118d92a19 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -41,6 +41,7 @@ #include <linux/netdevice.h> #include <linux/uio.h> #include <linux/skbuff.h> +#include <linux/smp_lock.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/string.h> @@ -1835,7 +1836,7 @@ static int ipx_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) switch (cmd) { case TIOCOUTQ: - amount = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; rc = put_user(amount, (int __user *)argp); diff --git a/net/ipx/ipx_proc.c b/net/ipx/ipx_proc.c index 5ed97ad0e2e..576178482f8 100644 --- a/net/ipx/ipx_proc.c +++ b/net/ipx/ipx_proc.c @@ -280,8 +280,8 @@ static int ipx_seq_socket_show(struct seq_file *seq, void *v) } seq_printf(seq, "%08X %08X %02X %03d\n", - atomic_read(&s->sk_wmem_alloc), - atomic_read(&s->sk_rmem_alloc), + sk_wmem_alloc_get(s), + sk_rmem_alloc_get(s), s->sk_state, SOCK_INODE(s->sk_socket)->i_uid); out: return 0; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 3eb5bcc75f9..50b43c57d5d 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -45,6 +45,7 @@ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> +#include <linux/smp_lock.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/init.h> @@ -714,6 +715,7 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); + memset(&saddr, 0, sizeof(saddr)); if (peer) { if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; @@ -913,9 +915,6 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) /* Clean up the original one to keep it in listen state */ irttp_listen(self->tsap); - /* Wow ! What is that ? Jean II */ - skb->sk = NULL; - skb->destructor = NULL; kfree_skb(skb); sk->sk_ack_backlog--; @@ -1762,7 +1761,8 @@ static int irda_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) switch (cmd) { case TIOCOUTQ: { long amount; - amount = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + + amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; if (put_user(amount, (unsigned int __user *)arg)) diff --git a/net/irda/ircomm/ircomm_lmp.c b/net/irda/ircomm/ircomm_lmp.c index 67c99d20857..7ba96618660 100644 --- a/net/irda/ircomm/ircomm_lmp.c +++ b/net/irda/ircomm/ircomm_lmp.c @@ -196,6 +196,7 @@ static int ircomm_lmp_data_request(struct ircomm_cb *self, /* Don't forget to refcount it - see ircomm_tty_do_softint() */ skb_get(skb); + skb_orphan(skb); skb->destructor = ircomm_lmp_flow_control; if ((self->pkt_count++ > 7) && (self->flow_status == FLOW_START)) { diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c index 2562ebc1b22..7af2e74deda 100644 --- a/net/irda/irlap_frame.c +++ b/net/irda/irlap_frame.c @@ -982,17 +982,12 @@ void irlap_resend_rejected_frames(struct irlap_cb *self, int command) { struct sk_buff *tx_skb; struct sk_buff *skb; - int count; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == LAP_MAGIC, return;); - /* Initialize variables */ - count = skb_queue_len(&self->wx_list); - /* Resend unacknowledged frame(s) */ - skb = skb_peek(&self->wx_list); - while (skb != NULL) { + skb_queue_walk(&self->wx_list, skb) { irlap_wait_min_turn_around(self, &self->qos_tx); /* We copy the skb to be retransmitted since we will have to @@ -1011,21 +1006,12 @@ void irlap_resend_rejected_frames(struct irlap_cb *self, int command) /* * Set poll bit on the last frame retransmitted */ - if (count-- == 1) + if (skb_queue_is_last(&self->wx_list, skb)) tx_skb->data[1] |= PF_BIT; /* Set p/f bit */ else tx_skb->data[1] &= ~PF_BIT; /* Clear p/f bit */ irlap_send_i_frame(self, tx_skb, command); - - /* - * If our skb is the last buffer in the list, then - * we are finished, if not, move to the next sk-buffer - */ - if (skb == skb_peek_tail(&self->wx_list)) - skb = NULL; - else - skb = skb->next; } #if 0 /* Not yet */ /* diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index bccf4d0059f..b001c361ad3 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -241,7 +241,6 @@ #include <linux/module.h> #include <linux/kernel.h> -#include <linux/smp_lock.h> #include <linux/skbuff.h> #include <linux/tty.h> #include <linux/proc_fs.h> diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 6d8ae03c14f..68cbcb19cbd 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -13,6 +13,7 @@ * 2) as a control channel (write commands, read events) */ +#include <linux/smp_lock.h> #include "irnet_ppp.h" /* Private header */ /* Please put other headers in irnet.h - Thanks */ diff --git a/net/irda/irnetlink.c b/net/irda/irnetlink.c index 2f05ec1037a..8dd7ed7e7c1 100644 --- a/net/irda/irnetlink.c +++ b/net/irda/irnetlink.c @@ -87,7 +87,7 @@ static int irda_nl_get_mode(struct sk_buff *skb, struct genl_info *info) if (!dev) return -ENODEV; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { dev_put(dev); return -ENOMEM; @@ -148,21 +148,8 @@ static struct genl_ops irda_nl_ops[] = { int irda_nl_register(void) { - int err, i; - - err = genl_register_family(&irda_nl_family); - if (err) - return err; - - for (i = 0; i < ARRAY_SIZE(irda_nl_ops); i++) { - err = genl_register_ops(&irda_nl_family, &irda_nl_ops[i]); - if (err) - goto err_out; - } - return 0; - err_out: - genl_unregister_family(&irda_nl_family); - return err; + return genl_register_family_with_ops(&irda_nl_family, + irda_nl_ops, ARRAY_SIZE(irda_nl_ops)); } void irda_nl_unregister(void) diff --git a/net/irda/irttp.c b/net/irda/irttp.c index ecf4eb2717c..9cb79f95bf6 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -1453,6 +1453,7 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance) } /* Dup */ memcpy(new, orig, sizeof(struct tsap_cb)); + spin_lock_init(&new->lock); /* We don't need the old instance any more */ spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index b51c9187c34..49c15b48408 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1,11 +1,12 @@ /* - * linux/net/iucv/af_iucv.c - * * IUCV protocol stack for Linux on zSeries * - * Copyright 2006 IBM Corporation + * Copyright IBM Corp. 2006, 2009 * * Author(s): Jennifer Hunt <jenhunt@us.ibm.com> + * Hendrik Brueckner <brueckner@linux.vnet.ibm.com> + * PM functions: + * Ursula Braun <ursula.braun@de.ibm.com> */ #define KMSG_COMPONENT "af_iucv" @@ -29,10 +30,7 @@ #include <net/iucv/iucv.h> #include <net/iucv/af_iucv.h> -#define CONFIG_IUCV_SOCK_DEBUG 1 - -#define IPRMDATA 0x80 -#define VERSION "1.0" +#define VERSION "1.1" static char iucv_userid[80]; @@ -44,6 +42,51 @@ static struct proto iucv_proto = { .obj_size = sizeof(struct iucv_sock), }; +/* special AF_IUCV IPRM messages */ +static const u8 iprm_shutdown[8] = + {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}; + +#define TRGCLS_SIZE (sizeof(((struct iucv_message *)0)->class)) + +/* macros to set/get socket control buffer at correct offset */ +#define CB_TAG(skb) ((skb)->cb) /* iucv message tag */ +#define CB_TAG_LEN (sizeof(((struct iucv_message *) 0)->tag)) +#define CB_TRGCLS(skb) ((skb)->cb + CB_TAG_LEN) /* iucv msg target class */ +#define CB_TRGCLS_LEN (TRGCLS_SIZE) + +#define __iucv_sock_wait(sk, condition, timeo, ret) \ +do { \ + DEFINE_WAIT(__wait); \ + long __timeo = timeo; \ + ret = 0; \ + while (!(condition)) { \ + prepare_to_wait(sk->sk_sleep, &__wait, TASK_INTERRUPTIBLE); \ + if (!__timeo) { \ + ret = -EAGAIN; \ + break; \ + } \ + if (signal_pending(current)) { \ + ret = sock_intr_errno(__timeo); \ + break; \ + } \ + release_sock(sk); \ + __timeo = schedule_timeout(__timeo); \ + lock_sock(sk); \ + ret = sock_error(sk); \ + if (ret) \ + break; \ + } \ + finish_wait(sk->sk_sleep, &__wait); \ +} while (0) + +#define iucv_sock_wait(sk, condition, timeo) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __iucv_sock_wait(sk, condition, timeo, __ret); \ + __ret; \ +}) + static void iucv_sock_kill(struct sock *sk); static void iucv_sock_close(struct sock *sk); @@ -54,6 +97,7 @@ static void iucv_callback_connack(struct iucv_path *, u8 ipuser[16]); static int iucv_callback_connreq(struct iucv_path *, u8 ipvmid[8], u8 ipuser[16]); static void iucv_callback_connrej(struct iucv_path *, u8 ipuser[16]); +static void iucv_callback_shutdown(struct iucv_path *, u8 ipuser[16]); static struct iucv_sock_list iucv_sk_list = { .lock = __RW_LOCK_UNLOCKED(iucv_sk_list.lock), @@ -65,7 +109,8 @@ static struct iucv_handler af_iucv_handler = { .path_complete = iucv_callback_connack, .path_severed = iucv_callback_connrej, .message_pending = iucv_callback_rx, - .message_complete = iucv_callback_txdone + .message_complete = iucv_callback_txdone, + .path_quiesced = iucv_callback_shutdown, }; static inline void high_nmcpy(unsigned char *dst, char *src) @@ -78,6 +123,195 @@ static inline void low_nmcpy(unsigned char *dst, char *src) memcpy(&dst[8], src, 8); } +static int afiucv_pm_prepare(struct device *dev) +{ +#ifdef CONFIG_PM_DEBUG + printk(KERN_WARNING "afiucv_pm_prepare\n"); +#endif + return 0; +} + +static void afiucv_pm_complete(struct device *dev) +{ +#ifdef CONFIG_PM_DEBUG + printk(KERN_WARNING "afiucv_pm_complete\n"); +#endif + return; +} + +/** + * afiucv_pm_freeze() - Freeze PM callback + * @dev: AFIUCV dummy device + * + * Sever all established IUCV communication pathes + */ +static int afiucv_pm_freeze(struct device *dev) +{ + struct iucv_sock *iucv; + struct sock *sk; + struct hlist_node *node; + int err = 0; + +#ifdef CONFIG_PM_DEBUG + printk(KERN_WARNING "afiucv_pm_freeze\n"); +#endif + read_lock(&iucv_sk_list.lock); + sk_for_each(sk, node, &iucv_sk_list.head) { + iucv = iucv_sk(sk); + skb_queue_purge(&iucv->send_skb_q); + skb_queue_purge(&iucv->backlog_skb_q); + switch (sk->sk_state) { + case IUCV_SEVERED: + case IUCV_DISCONN: + case IUCV_CLOSING: + case IUCV_CONNECTED: + if (iucv->path) { + err = iucv_path_sever(iucv->path, NULL); + iucv_path_free(iucv->path); + iucv->path = NULL; + } + break; + case IUCV_OPEN: + case IUCV_BOUND: + case IUCV_LISTEN: + case IUCV_CLOSED: + default: + break; + } + } + read_unlock(&iucv_sk_list.lock); + return err; +} + +/** + * afiucv_pm_restore_thaw() - Thaw and restore PM callback + * @dev: AFIUCV dummy device + * + * socket clean up after freeze + */ +static int afiucv_pm_restore_thaw(struct device *dev) +{ + struct iucv_sock *iucv; + struct sock *sk; + struct hlist_node *node; + +#ifdef CONFIG_PM_DEBUG + printk(KERN_WARNING "afiucv_pm_restore_thaw\n"); +#endif + read_lock(&iucv_sk_list.lock); + sk_for_each(sk, node, &iucv_sk_list.head) { + iucv = iucv_sk(sk); + switch (sk->sk_state) { + case IUCV_CONNECTED: + sk->sk_err = EPIPE; + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + break; + case IUCV_DISCONN: + case IUCV_SEVERED: + case IUCV_CLOSING: + case IUCV_LISTEN: + case IUCV_BOUND: + case IUCV_OPEN: + default: + break; + } + } + read_unlock(&iucv_sk_list.lock); + return 0; +} + +static struct dev_pm_ops afiucv_pm_ops = { + .prepare = afiucv_pm_prepare, + .complete = afiucv_pm_complete, + .freeze = afiucv_pm_freeze, + .thaw = afiucv_pm_restore_thaw, + .restore = afiucv_pm_restore_thaw, +}; + +static struct device_driver af_iucv_driver = { + .owner = THIS_MODULE, + .name = "afiucv", + .bus = &iucv_bus, + .pm = &afiucv_pm_ops, +}; + +/* dummy device used as trigger for PM functions */ +static struct device *af_iucv_dev; + +/** + * iucv_msg_length() - Returns the length of an iucv message. + * @msg: Pointer to struct iucv_message, MUST NOT be NULL + * + * The function returns the length of the specified iucv message @msg of data + * stored in a buffer and of data stored in the parameter list (PRMDATA). + * + * For IUCV_IPRMDATA, AF_IUCV uses the following convention to transport socket + * data: + * PRMDATA[0..6] socket data (max 7 bytes); + * PRMDATA[7] socket data length value (len is 0xff - PRMDATA[7]) + * + * The socket data length is computed by substracting the socket data length + * value from 0xFF. + * If the socket data len is greater 7, then PRMDATA can be used for special + * notifications (see iucv_sock_shutdown); and further, + * if the socket data len is > 7, the function returns 8. + * + * Use this function to allocate socket buffers to store iucv message data. + */ +static inline size_t iucv_msg_length(struct iucv_message *msg) +{ + size_t datalen; + + if (msg->flags & IUCV_IPRMDATA) { + datalen = 0xff - msg->rmmsg[7]; + return (datalen < 8) ? datalen : 8; + } + return msg->length; +} + +/** + * iucv_sock_in_state() - check for specific states + * @sk: sock structure + * @state: first iucv sk state + * @state: second iucv sk state + * + * Returns true if the socket in either in the first or second state. + */ +static int iucv_sock_in_state(struct sock *sk, int state, int state2) +{ + return (sk->sk_state == state || sk->sk_state == state2); +} + +/** + * iucv_below_msglim() - function to check if messages can be sent + * @sk: sock structure + * + * Returns true if the send queue length is lower than the message limit. + * Always returns true if the socket is not connected (no iucv path for + * checking the message limit). + */ +static inline int iucv_below_msglim(struct sock *sk) +{ + struct iucv_sock *iucv = iucv_sk(sk); + + if (sk->sk_state != IUCV_CONNECTED) + return 1; + return (skb_queue_len(&iucv->send_skb_q) < iucv->path->msglim); +} + +/** + * iucv_sock_wake_msglim() - Wake up thread waiting on msg limit + */ +static void iucv_sock_wake_msglim(struct sock *sk) +{ + read_lock(&sk->sk_callback_lock); + if (sk_has_sleeper(sk)) + wake_up_interruptible_all(sk->sk_sleep); + sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + read_unlock(&sk->sk_callback_lock); +} + /* Timers */ static void iucv_sock_timeout(unsigned long arg) { @@ -169,7 +403,9 @@ static void iucv_sock_close(struct sock *sk) timeo = sk->sk_lingertime; else timeo = IUCV_DISCONN_TIMEOUT; - err = iucv_sock_wait_state(sk, IUCV_CLOSED, 0, timeo); + err = iucv_sock_wait(sk, + iucv_sock_in_state(sk, IUCV_CLOSED, 0), + timeo); } case IUCV_CLOSING: /* fall through */ @@ -225,6 +461,8 @@ static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio) spin_lock_init(&iucv_sk(sk)->message_q.lock); skb_queue_head_init(&iucv_sk(sk)->backlog_skb_q); iucv_sk(sk)->send_tag = 0; + iucv_sk(sk)->flags = 0; + iucv_sk(sk)->msglimit = IUCV_QUEUELEN_DEFAULT; iucv_sk(sk)->path = NULL; memset(&iucv_sk(sk)->src_user_id , 0, 32); @@ -248,11 +486,22 @@ static int iucv_sock_create(struct net *net, struct socket *sock, int protocol) { struct sock *sk; - if (sock->type != SOCK_STREAM) - return -ESOCKTNOSUPPORT; + if (protocol && protocol != PF_IUCV) + return -EPROTONOSUPPORT; sock->state = SS_UNCONNECTED; - sock->ops = &iucv_sock_ops; + + switch (sock->type) { + case SOCK_STREAM: + sock->ops = &iucv_sock_ops; + break; + case SOCK_SEQPACKET: + /* currently, proto ops can handle both sk types */ + sock->ops = &iucv_sock_ops; + break; + default: + return -ESOCKTNOSUPPORT; + } sk = iucv_sock_alloc(sock, protocol, GFP_KERNEL); if (!sk) @@ -337,39 +586,6 @@ struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock) return NULL; } -int iucv_sock_wait_state(struct sock *sk, int state, int state2, - unsigned long timeo) -{ - DECLARE_WAITQUEUE(wait, current); - int err = 0; - - add_wait_queue(sk->sk_sleep, &wait); - while (sk->sk_state != state && sk->sk_state != state2) { - set_current_state(TASK_INTERRUPTIBLE); - - if (!timeo) { - err = -EAGAIN; - break; - } - - if (signal_pending(current)) { - err = sock_intr_errno(timeo); - break; - } - - release_sock(sk); - timeo = schedule_timeout(timeo); - lock_sock(sk); - - err = sock_error(sk); - if (err) - break; - } - set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); - return err; -} - /* Bind an unbound socket */ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) @@ -463,11 +679,9 @@ static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, if (sk->sk_state != IUCV_OPEN && sk->sk_state != IUCV_BOUND) return -EBADFD; - if (sk->sk_type != SOCK_STREAM) + if (sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_SEQPACKET) return -EINVAL; - iucv = iucv_sk(sk); - if (sk->sk_state == IUCV_OPEN) { err = iucv_sock_autobind(sk); if (unlikely(err)) @@ -486,8 +700,8 @@ static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, iucv = iucv_sk(sk); /* Create path. */ - iucv->path = iucv_path_alloc(IUCV_QUEUELEN_DEFAULT, - IPRMDATA, GFP_KERNEL); + iucv->path = iucv_path_alloc(iucv->msglimit, + IUCV_IPRMDATA, GFP_KERNEL); if (!iucv->path) { err = -ENOMEM; goto done; @@ -516,13 +730,13 @@ static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, } if (sk->sk_state != IUCV_CONNECTED) { - err = iucv_sock_wait_state(sk, IUCV_CONNECTED, IUCV_DISCONN, - sock_sndtimeo(sk, flags & O_NONBLOCK)); + err = iucv_sock_wait(sk, iucv_sock_in_state(sk, IUCV_CONNECTED, + IUCV_DISCONN), + sock_sndtimeo(sk, flags & O_NONBLOCK)); } if (sk->sk_state == IUCV_DISCONN) { - release_sock(sk); - return -ECONNREFUSED; + err = -ECONNREFUSED; } if (err) { @@ -545,7 +759,10 @@ static int iucv_sock_listen(struct socket *sock, int backlog) lock_sock(sk); err = -EINVAL; - if (sk->sk_state != IUCV_BOUND || sock->type != SOCK_STREAM) + if (sk->sk_state != IUCV_BOUND) + goto done; + + if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) goto done; sk->sk_max_ack_backlog = backlog; @@ -636,6 +853,30 @@ static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr, return 0; } +/** + * iucv_send_iprm() - Send socket data in parameter list of an iucv message. + * @path: IUCV path + * @msg: Pointer to a struct iucv_message + * @skb: The socket data to send, skb->len MUST BE <= 7 + * + * Send the socket data in the parameter list in the iucv message + * (IUCV_IPRMDATA). The socket data is stored at index 0 to 6 in the parameter + * list and the socket data len at index 7 (last byte). + * See also iucv_msg_length(). + * + * Returns the error code from the iucv_message_send() call. + */ +static int iucv_send_iprm(struct iucv_path *path, struct iucv_message *msg, + struct sk_buff *skb) +{ + u8 prmdata[8]; + + memcpy(prmdata, (void *) skb->data, skb->len); + prmdata[7] = 0xff - (u8) skb->len; + return iucv_message_send(path, msg, IUCV_IPRMDATA, 0, + (void *) prmdata, 8); +} + static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { @@ -643,9 +884,13 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct iucv_sock *iucv = iucv_sk(sk); struct sk_buff *skb; struct iucv_message txmsg; + struct cmsghdr *cmsg; + int cmsg_done; + long timeo; char user_id[9]; char appl_id[9]; int err; + int noblock = msg->msg_flags & MSG_DONTWAIT; err = sock_error(sk); if (err) @@ -654,6 +899,10 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; + /* SOCK_SEQPACKET: we do not support segmented records */ + if (sk->sk_type == SOCK_SEQPACKET && !(msg->msg_flags & MSG_EOR)) + return -EOPNOTSUPP; + lock_sock(sk); if (sk->sk_shutdown & SEND_SHUTDOWN) { @@ -661,42 +910,119 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, goto out; } - if (sk->sk_state == IUCV_CONNECTED) { - if (!(skb = sock_alloc_send_skb(sk, len, - msg->msg_flags & MSG_DONTWAIT, - &err))) + /* Return if the socket is not in connected state */ + if (sk->sk_state != IUCV_CONNECTED) { + err = -ENOTCONN; + goto out; + } + + /* initialize defaults */ + cmsg_done = 0; /* check for duplicate headers */ + txmsg.class = 0; + + /* iterate over control messages */ + for (cmsg = CMSG_FIRSTHDR(msg); cmsg; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + + if (!CMSG_OK(msg, cmsg)) { + err = -EINVAL; goto out; + } - if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { - err = -EFAULT; - goto fail; + if (cmsg->cmsg_level != SOL_IUCV) + continue; + + if (cmsg->cmsg_type & cmsg_done) { + err = -EINVAL; + goto out; } + cmsg_done |= cmsg->cmsg_type; - txmsg.class = 0; - memcpy(&txmsg.class, skb->data, skb->len >= 4 ? 4 : skb->len); - txmsg.tag = iucv->send_tag++; - memcpy(skb->cb, &txmsg.tag, 4); - skb_queue_tail(&iucv->send_skb_q, skb); - err = iucv_message_send(iucv->path, &txmsg, 0, 0, - (void *) skb->data, skb->len); - if (err) { - if (err == 3) { - user_id[8] = 0; - memcpy(user_id, iucv->dst_user_id, 8); - appl_id[8] = 0; - memcpy(appl_id, iucv->dst_name, 8); - pr_err("Application %s on z/VM guest %s" - " exceeds message limit\n", - user_id, appl_id); + switch (cmsg->cmsg_type) { + case SCM_IUCV_TRGCLS: + if (cmsg->cmsg_len != CMSG_LEN(TRGCLS_SIZE)) { + err = -EINVAL; + goto out; } + + /* set iucv message target class */ + memcpy(&txmsg.class, + (void *) CMSG_DATA(cmsg), TRGCLS_SIZE); + + break; + + default: + err = -EINVAL; + goto out; + break; + } + } + + /* allocate one skb for each iucv message: + * this is fine for SOCK_SEQPACKET (unless we want to support + * segmented records using the MSG_EOR flag), but + * for SOCK_STREAM we might want to improve it in future */ + skb = sock_alloc_send_skb(sk, len, noblock, &err); + if (!skb) + goto out; + if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { + err = -EFAULT; + goto fail; + } + + /* wait if outstanding messages for iucv path has reached */ + timeo = sock_sndtimeo(sk, noblock); + err = iucv_sock_wait(sk, iucv_below_msglim(sk), timeo); + if (err) + goto fail; + + /* return -ECONNRESET if the socket is no longer connected */ + if (sk->sk_state != IUCV_CONNECTED) { + err = -ECONNRESET; + goto fail; + } + + /* increment and save iucv message tag for msg_completion cbk */ + txmsg.tag = iucv->send_tag++; + memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN); + skb_queue_tail(&iucv->send_skb_q, skb); + + if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags) + && skb->len <= 7) { + err = iucv_send_iprm(iucv->path, &txmsg, skb); + + /* on success: there is no message_complete callback + * for an IPRMDATA msg; remove skb from send queue */ + if (err == 0) { + skb_unlink(skb, &iucv->send_skb_q); + kfree_skb(skb); + } + + /* this error should never happen since the + * IUCV_IPRMDATA path flag is set... sever path */ + if (err == 0x15) { + iucv_path_sever(iucv->path, NULL); skb_unlink(skb, &iucv->send_skb_q); err = -EPIPE; goto fail; } - - } else { - err = -ENOTCONN; - goto out; + } else + err = iucv_message_send(iucv->path, &txmsg, 0, 0, + (void *) skb->data, skb->len); + if (err) { + if (err == 3) { + user_id[8] = 0; + memcpy(user_id, iucv->dst_user_id, 8); + appl_id[8] = 0; + memcpy(appl_id, iucv->dst_name, 8); + pr_err("Application %s on z/VM guest %s" + " exceeds message limit\n", + appl_id, user_id); + err = -EAGAIN; + } else + err = -EPIPE; + skb_unlink(skb, &iucv->send_skb_q); + goto fail; } release_sock(sk); @@ -725,6 +1051,10 @@ static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len) if (!nskb) return -ENOMEM; + /* copy target class to control buffer of new skb */ + memcpy(CB_TRGCLS(nskb), CB_TRGCLS(skb), CB_TRGCLS_LEN); + + /* copy data fragment */ memcpy(nskb->data, skb->data + copied, size); copied += size; dataleft -= size; @@ -744,19 +1074,33 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, struct iucv_message *msg) { int rc; + unsigned int len; + + len = iucv_msg_length(msg); - if (msg->flags & IPRMDATA) { - skb->data = NULL; - skb->len = 0; + /* store msg target class in the second 4 bytes of skb ctrl buffer */ + /* Note: the first 4 bytes are reserved for msg tag */ + memcpy(CB_TRGCLS(skb), &msg->class, CB_TRGCLS_LEN); + + /* check for special IPRM messages (e.g. iucv_sock_shutdown) */ + if ((msg->flags & IUCV_IPRMDATA) && len > 7) { + if (memcmp(msg->rmmsg, iprm_shutdown, 8) == 0) { + skb->data = NULL; + skb->len = 0; + } } else { - rc = iucv_message_receive(path, msg, 0, skb->data, - msg->length, NULL); + rc = iucv_message_receive(path, msg, msg->flags & IUCV_IPRMDATA, + skb->data, len, NULL); if (rc) { kfree_skb(skb); return; } - if (skb->truesize >= sk->sk_rcvbuf / 4) { - rc = iucv_fragment_skb(sk, skb, msg->length); + /* we need to fragment iucv messages for SOCK_STREAM only; + * for SOCK_SEQPACKET, it is only relevant if we support + * record segmentation using MSG_EOR (see also recvmsg()) */ + if (sk->sk_type == SOCK_STREAM && + skb->truesize >= sk->sk_rcvbuf / 4) { + rc = iucv_fragment_skb(sk, skb, len); kfree_skb(skb); skb = NULL; if (rc) { @@ -767,7 +1111,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, } else { skb_reset_transport_header(skb); skb_reset_network_header(skb); - skb->len = msg->length; + skb->len = len; } } @@ -782,7 +1126,7 @@ static void iucv_process_message_q(struct sock *sk) struct sock_msg_q *p, *n; list_for_each_entry_safe(p, n, &iucv->message_q.list, list) { - skb = alloc_skb(p->msg.length, GFP_ATOMIC | GFP_DMA); + skb = alloc_skb(iucv_msg_length(&p->msg), GFP_ATOMIC | GFP_DMA); if (!skb) break; iucv_process_message(sk, skb, p->path, &p->msg); @@ -799,7 +1143,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); - int target, copied = 0; + unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; int err = 0; @@ -812,8 +1156,6 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags & (MSG_OOB)) return -EOPNOTSUPP; - target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - /* receive/dequeue next skb: * the function understands MSG_PEEK and, thus, does not dequeue skb */ skb = skb_recv_datagram(sk, flags, noblock, &err); @@ -823,25 +1165,45 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return err; } - copied = min_t(unsigned int, skb->len, len); + rlen = skb->len; /* real length of skb */ + copied = min_t(unsigned int, rlen, len); cskb = skb; if (memcpy_toiovec(msg->msg_iov, cskb->data, copied)) { - skb_queue_head(&sk->sk_receive_queue, skb); - if (copied == 0) - return -EFAULT; - goto done; + if (!(flags & MSG_PEEK)) + skb_queue_head(&sk->sk_receive_queue, skb); + return -EFAULT; + } + + /* SOCK_SEQPACKET: set MSG_TRUNC if recv buf size is too small */ + if (sk->sk_type == SOCK_SEQPACKET) { + if (copied < rlen) + msg->msg_flags |= MSG_TRUNC; + /* each iucv message contains a complete record */ + msg->msg_flags |= MSG_EOR; } - len -= copied; + /* create control message to store iucv msg target class: + * get the trgcls from the control buffer of the skb due to + * fragmentation of original iucv message. */ + err = put_cmsg(msg, SOL_IUCV, SCM_IUCV_TRGCLS, + CB_TRGCLS_LEN, CB_TRGCLS(skb)); + if (err) { + if (!(flags & MSG_PEEK)) + skb_queue_head(&sk->sk_receive_queue, skb); + return err; + } /* Mark read part of skb as used */ if (!(flags & MSG_PEEK)) { - skb_pull(skb, copied); - if (skb->len) { - skb_queue_head(&sk->sk_receive_queue, skb); - goto done; + /* SOCK_STREAM: re-queue skb if it contains unreceived data */ + if (sk->sk_type == SOCK_STREAM) { + skb_pull(skb, copied); + if (skb->len) { + skb_queue_head(&sk->sk_receive_queue, skb); + goto done; + } } kfree_skb(skb); @@ -866,7 +1228,11 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, } done: - return err ? : copied; + /* SOCK_SEQPACKET: return real length if MSG_TRUNC is set */ + if (sk->sk_type == SOCK_SEQPACKET && (flags & MSG_TRUNC)) + copied = rlen; + + return copied; } static inline unsigned int iucv_accept_poll(struct sock *parent) @@ -890,7 +1256,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; unsigned int mask = 0; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); if (sk->sk_state == IUCV_LISTEN) return iucv_accept_poll(sk); @@ -928,7 +1294,6 @@ static int iucv_sock_shutdown(struct socket *sock, int how) struct iucv_sock *iucv = iucv_sk(sk); struct iucv_message txmsg; int err = 0; - u8 prmmsg[8] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}; how++; @@ -953,7 +1318,7 @@ static int iucv_sock_shutdown(struct socket *sock, int how) txmsg.class = 0; txmsg.tag = 0; err = iucv_message_send(iucv->path, &txmsg, IUCV_IPRMDATA, 0, - (void *) prmmsg, 8); + (void *) iprm_shutdown, 8); if (err) { switch (err) { case 1: @@ -1007,6 +1372,98 @@ static int iucv_sock_release(struct socket *sock) return err; } +/* getsockopt and setsockopt */ +static int iucv_sock_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, int optlen) +{ + struct sock *sk = sock->sk; + struct iucv_sock *iucv = iucv_sk(sk); + int val; + int rc; + + if (level != SOL_IUCV) + return -ENOPROTOOPT; + + if (optlen < sizeof(int)) + return -EINVAL; + + if (get_user(val, (int __user *) optval)) + return -EFAULT; + + rc = 0; + + lock_sock(sk); + switch (optname) { + case SO_IPRMDATA_MSG: + if (val) + iucv->flags |= IUCV_IPRMDATA; + else + iucv->flags &= ~IUCV_IPRMDATA; + break; + case SO_MSGLIMIT: + switch (sk->sk_state) { + case IUCV_OPEN: + case IUCV_BOUND: + if (val < 1 || val > (u16)(~0)) + rc = -EINVAL; + else + iucv->msglimit = val; + break; + default: + rc = -EINVAL; + break; + } + break; + default: + rc = -ENOPROTOOPT; + break; + } + release_sock(sk); + + return rc; +} + +static int iucv_sock_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = sock->sk; + struct iucv_sock *iucv = iucv_sk(sk); + int val, len; + + if (level != SOL_IUCV) + return -ENOPROTOOPT; + + if (get_user(len, optlen)) + return -EFAULT; + + if (len < 0) + return -EINVAL; + + len = min_t(unsigned int, len, sizeof(int)); + + switch (optname) { + case SO_IPRMDATA_MSG: + val = (iucv->flags & IUCV_IPRMDATA) ? 1 : 0; + break; + case SO_MSGLIMIT: + lock_sock(sk); + val = (iucv->path != NULL) ? iucv->path->msglim /* connected */ + : iucv->msglimit; /* default */ + release_sock(sk); + break; + default: + return -ENOPROTOOPT; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + + /* Callback wrappers - called from iucv base support */ static int iucv_callback_connreq(struct iucv_path *path, u8 ipvmid[8], u8 ipuser[16]) @@ -1060,7 +1517,7 @@ static int iucv_callback_connreq(struct iucv_path *path, } /* Create the new socket */ - nsk = iucv_sock_alloc(NULL, SOCK_STREAM, GFP_ATOMIC); + nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC); if (!nsk) { err = iucv_path_sever(path, user_data); iucv_path_free(path); @@ -1083,7 +1540,9 @@ static int iucv_callback_connreq(struct iucv_path *path, memcpy(nuser_data + 8, niucv->src_name, 8); ASCEBC(nuser_data + 8, 8); - path->msglim = IUCV_QUEUELEN_DEFAULT; + /* set message limit for path based on msglimit of accepting socket */ + niucv->msglimit = iucv->msglimit; + path->msglim = iucv->msglimit; err = iucv_path_accept(path, &af_iucv_handler, nuser_data, nsk); if (err) { err = iucv_path_sever(path, user_data); @@ -1131,19 +1590,17 @@ static void iucv_callback_rx(struct iucv_path *path, struct iucv_message *msg) goto save_message; len = atomic_read(&sk->sk_rmem_alloc); - len += msg->length + sizeof(struct sk_buff); + len += iucv_msg_length(msg) + sizeof(struct sk_buff); if (len > sk->sk_rcvbuf) goto save_message; - skb = alloc_skb(msg->length, GFP_ATOMIC | GFP_DMA); + skb = alloc_skb(iucv_msg_length(msg), GFP_ATOMIC | GFP_DMA); if (!skb) goto save_message; iucv_process_message(sk, skb, path, msg); goto out_unlock; - return; - save_message: save_msg = kzalloc(sizeof(struct sock_msg_q), GFP_ATOMIC | GFP_DMA); if (!save_msg) @@ -1170,7 +1627,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (!memcmp(&msg->tag, list_skb->cb, 4)) { + if (!memcmp(&msg->tag, CB_TAG(list_skb), CB_TAG_LEN)) { this = list_skb; break; } @@ -1181,7 +1638,11 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_unlock_irqrestore(&list->lock, flags); - kfree_skb(this); + if (this) { + kfree_skb(this); + /* wake up any process waiting for sending */ + iucv_sock_wake_msglim(sk); + } } BUG_ON(!this); @@ -1206,6 +1667,21 @@ static void iucv_callback_connrej(struct iucv_path *path, u8 ipuser[16]) sk->sk_state_change(sk); } +/* called if the other communication side shuts down its RECV direction; + * in turn, the callback sets SEND_SHUTDOWN to disable sending of data. + */ +static void iucv_callback_shutdown(struct iucv_path *path, u8 ipuser[16]) +{ + struct sock *sk = path->private; + + bh_lock_sock(sk); + if (sk->sk_state != IUCV_CLOSED) { + sk->sk_shutdown |= SEND_SHUTDOWN; + sk->sk_state_change(sk); + } + bh_unlock_sock(sk); +} + static struct proto_ops iucv_sock_ops = { .family = PF_IUCV, .owner = THIS_MODULE, @@ -1222,8 +1698,8 @@ static struct proto_ops iucv_sock_ops = { .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = iucv_sock_shutdown, - .setsockopt = sock_no_setsockopt, - .getsockopt = sock_no_getsockopt + .setsockopt = iucv_sock_setsockopt, + .getsockopt = iucv_sock_getsockopt, }; static struct net_proto_family iucv_sock_family_ops = { @@ -1258,8 +1734,30 @@ static int __init afiucv_init(void) err = sock_register(&iucv_sock_family_ops); if (err) goto out_proto; + /* establish dummy device */ + err = driver_register(&af_iucv_driver); + if (err) + goto out_sock; + af_iucv_dev = kzalloc(sizeof(struct device), GFP_KERNEL); + if (!af_iucv_dev) { + err = -ENOMEM; + goto out_driver; + } + dev_set_name(af_iucv_dev, "af_iucv"); + af_iucv_dev->bus = &iucv_bus; + af_iucv_dev->parent = iucv_root; + af_iucv_dev->release = (void (*)(struct device *))kfree; + af_iucv_dev->driver = &af_iucv_driver; + err = device_register(af_iucv_dev); + if (err) + goto out_driver; + return 0; +out_driver: + driver_unregister(&af_iucv_driver); +out_sock: + sock_unregister(PF_IUCV); out_proto: proto_unregister(&iucv_proto); out_iucv: @@ -1270,6 +1768,8 @@ out: static void __exit afiucv_exit(void) { + device_unregister(af_iucv_dev); + driver_unregister(&af_iucv_driver); sock_unregister(PF_IUCV); proto_unregister(&iucv_proto); iucv_unregister(&af_iucv_handler, 0); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index a35240f61ec..c833481d32e 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1,7 +1,8 @@ /* * IUCV base infrastructure. * - * Copyright 2001, 2006 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2001, 2009 + * * Author(s): * Original source: * Alan Altmark (Alan_Altmark@us.ibm.com) Sept. 2000 @@ -10,6 +11,8 @@ * Fritz Elfert (elfert@de.ibm.com, felfert@millenux.com) * Rewritten for af_iucv: * Martin Schwidefsky <schwidefsky@de.ibm.com> + * PM functions: + * Ursula Braun (ursula.braun@de.ibm.com) * * Documentation used: * The original source @@ -45,6 +48,7 @@ #include <linux/err.h> #include <linux/device.h> #include <linux/cpu.h> +#include <linux/reboot.h> #include <net/iucv/iucv.h> #include <asm/atomic.h> #include <asm/ebcdic.h> @@ -75,9 +79,24 @@ static int iucv_bus_match(struct device *dev, struct device_driver *drv) return 0; } +static int iucv_pm_prepare(struct device *); +static void iucv_pm_complete(struct device *); +static int iucv_pm_freeze(struct device *); +static int iucv_pm_thaw(struct device *); +static int iucv_pm_restore(struct device *); + +static struct dev_pm_ops iucv_pm_ops = { + .prepare = iucv_pm_prepare, + .complete = iucv_pm_complete, + .freeze = iucv_pm_freeze, + .thaw = iucv_pm_thaw, + .restore = iucv_pm_restore, +}; + struct bus_type iucv_bus = { .name = "iucv", .match = iucv_bus_match, + .pm = &iucv_pm_ops, }; EXPORT_SYMBOL(iucv_bus); @@ -147,6 +166,7 @@ enum iucv_command_codes { IUCV_RESUME = 14, IUCV_SEVER = 15, IUCV_SETMASK = 16, + IUCV_SETCONTROLMASK = 17, }; /* @@ -280,6 +300,7 @@ union iucv_param { * Anchor for per-cpu IUCV command parameter block. */ static union iucv_param *iucv_param[NR_CPUS]; +static union iucv_param *iucv_param_irq[NR_CPUS]; /** * iucv_call_b2f0 @@ -358,11 +379,23 @@ static void iucv_allow_cpu(void *data) * 0x10 - Flag to allow priority message completion interrupts * 0x08 - Flag to allow IUCV control interrupts */ - parm = iucv_param[cpu]; + parm = iucv_param_irq[cpu]; memset(parm, 0, sizeof(union iucv_param)); parm->set_mask.ipmask = 0xf8; iucv_call_b2f0(IUCV_SETMASK, parm); + /* + * Enable all iucv control interrupts. + * ipmask contains bits for the different interrupts + * 0x80 - Flag to allow pending connections interrupts + * 0x40 - Flag to allow connection complete interrupts + * 0x20 - Flag to allow connection severed interrupts + * 0x10 - Flag to allow connection quiesced interrupts + * 0x08 - Flag to allow connection resumed interrupts + */ + memset(parm, 0, sizeof(union iucv_param)); + parm->set_mask.ipmask = 0xf8; + iucv_call_b2f0(IUCV_SETCONTROLMASK, parm); /* Set indication that iucv interrupts are allowed for this cpu. */ cpu_set(cpu, iucv_irq_cpumask); } @@ -379,7 +412,7 @@ static void iucv_block_cpu(void *data) union iucv_param *parm; /* Disable all iucv interrupts. */ - parm = iucv_param[cpu]; + parm = iucv_param_irq[cpu]; memset(parm, 0, sizeof(union iucv_param)); iucv_call_b2f0(IUCV_SETMASK, parm); @@ -388,6 +421,31 @@ static void iucv_block_cpu(void *data) } /** + * iucv_block_cpu_almost + * @data: unused + * + * Allow connection-severed interrupts only on this cpu. + */ +static void iucv_block_cpu_almost(void *data) +{ + int cpu = smp_processor_id(); + union iucv_param *parm; + + /* Allow iucv control interrupts only */ + parm = iucv_param_irq[cpu]; + memset(parm, 0, sizeof(union iucv_param)); + parm->set_mask.ipmask = 0x08; + iucv_call_b2f0(IUCV_SETMASK, parm); + /* Allow iucv-severed interrupt only */ + memset(parm, 0, sizeof(union iucv_param)); + parm->set_mask.ipmask = 0x20; + iucv_call_b2f0(IUCV_SETCONTROLMASK, parm); + + /* Clear indication that iucv interrupts are allowed for this cpu. */ + cpu_clear(cpu, iucv_irq_cpumask); +} + +/** * iucv_declare_cpu * @data: unused * @@ -403,7 +461,7 @@ static void iucv_declare_cpu(void *data) return; /* Declare interrupt buffer. */ - parm = iucv_param[cpu]; + parm = iucv_param_irq[cpu]; memset(parm, 0, sizeof(union iucv_param)); parm->db.ipbfadr1 = virt_to_phys(iucv_irq_data[cpu]); rc = iucv_call_b2f0(IUCV_DECLARE_BUFFER, parm); @@ -460,7 +518,7 @@ static void iucv_retrieve_cpu(void *data) iucv_block_cpu(NULL); /* Retrieve interrupt buffer. */ - parm = iucv_param[cpu]; + parm = iucv_param_irq[cpu]; iucv_call_b2f0(IUCV_RETRIEVE_BUFFER, parm); /* Clear indication that an iucv buffer exists for this cpu. */ @@ -574,11 +632,22 @@ static int __cpuinit iucv_cpu_notify(struct notifier_block *self, iucv_irq_data[cpu] = NULL; return NOTIFY_BAD; } + iucv_param_irq[cpu] = kmalloc_node(sizeof(union iucv_param), + GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); + if (!iucv_param_irq[cpu]) { + kfree(iucv_param[cpu]); + iucv_param[cpu] = NULL; + kfree(iucv_irq_data[cpu]); + iucv_irq_data[cpu] = NULL; + return NOTIFY_BAD; + } break; case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: + kfree(iucv_param_irq[cpu]); + iucv_param_irq[cpu] = NULL; kfree(iucv_param[cpu]); iucv_param[cpu] = NULL; kfree(iucv_irq_data[cpu]); @@ -625,7 +694,7 @@ static int iucv_sever_pathid(u16 pathid, u8 userdata[16]) { union iucv_param *parm; - parm = iucv_param[smp_processor_id()]; + parm = iucv_param_irq[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); if (userdata) memcpy(parm->ctrl.ipuser, userdata, sizeof(parm->ctrl.ipuser)); @@ -746,6 +815,28 @@ void iucv_unregister(struct iucv_handler *handler, int smp) } EXPORT_SYMBOL(iucv_unregister); +static int iucv_reboot_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + int i, rc; + + get_online_cpus(); + on_each_cpu(iucv_block_cpu, NULL, 1); + preempt_disable(); + for (i = 0; i < iucv_max_pathid; i++) { + if (iucv_path_table[i]) + rc = iucv_sever_pathid(i, NULL); + } + preempt_enable(); + put_online_cpus(); + iucv_disable(); + return NOTIFY_DONE; +} + +static struct notifier_block iucv_reboot_notifier = { + .notifier_call = iucv_reboot_event, +}; + /** * iucv_path_accept * @path: address of iucv path structure @@ -765,6 +856,10 @@ 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)) { + rc = -EIO; + goto out; + } /* Prepare parameter block. */ parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); @@ -780,6 +875,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, path->msglim = parm->ctrl.ipmsglim; path->flags = parm->ctrl.ipflags1; } +out: local_bh_enable(); return rc; } @@ -809,6 +905,10 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); parm->ctrl.ipmsglim = path->msglim; @@ -843,6 +943,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, rc = -EIO; } } +out: spin_unlock_bh(&iucv_table_lock); return rc; } @@ -864,12 +965,17 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); if (userdata) memcpy(parm->ctrl.ipuser, userdata, sizeof(parm->ctrl.ipuser)); parm->ctrl.ippathid = path->pathid; rc = iucv_call_b2f0(IUCV_QUIESCE, parm); +out: local_bh_enable(); return rc; } @@ -891,12 +997,17 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); if (userdata) memcpy(parm->ctrl.ipuser, userdata, sizeof(parm->ctrl.ipuser)); parm->ctrl.ippathid = path->pathid; rc = iucv_call_b2f0(IUCV_RESUME, parm); +out: local_bh_enable(); return rc; } @@ -915,15 +1026,18 @@ int iucv_path_sever(struct iucv_path *path, u8 userdata[16]) int rc; preempt_disable(); + if (!cpu_isset(smp_processor_id(), iucv_buffer_cpumask)) { + rc = -EIO; + goto out; + } if (iucv_active_cpu != smp_processor_id()) spin_lock_bh(&iucv_table_lock); rc = iucv_sever_pathid(path->pathid, userdata); - if (!rc) { - iucv_path_table[path->pathid] = NULL; - list_del_init(&path->list); - } + iucv_path_table[path->pathid] = NULL; + list_del_init(&path->list); if (iucv_active_cpu != smp_processor_id()) spin_unlock_bh(&iucv_table_lock); +out: preempt_enable(); return rc; } @@ -946,6 +1060,10 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); parm->purge.ippathid = path->pathid; @@ -957,6 +1075,7 @@ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg, msg->audit = (*(u32 *) &parm->purge.ipaudit) >> 8; msg->tag = parm->purge.ipmsgtag; } +out: local_bh_enable(); return rc; } @@ -1033,6 +1152,10 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); parm->db.ipbfadr1 = (u32)(addr_t) buffer; @@ -1048,6 +1171,7 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, if (residual) *residual = parm->db.ipbfln1f; } +out: return rc; } EXPORT_SYMBOL(__iucv_message_receive); @@ -1101,6 +1225,10 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); parm->db.ippathid = path->pathid; @@ -1108,6 +1236,7 @@ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg) parm->db.iptrgcls = msg->class; parm->db.ipflags1 = (IUCV_IPTRGCLS | IUCV_IPFGMID | IUCV_IPFGPID); rc = iucv_call_b2f0(IUCV_REJECT, parm); +out: local_bh_enable(); return rc; } @@ -1135,6 +1264,10 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); if (flags & IUCV_IPRMDATA) { @@ -1152,6 +1285,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, parm->db.iptrgcls = msg->class; } rc = iucv_call_b2f0(IUCV_REPLY, parm); +out: local_bh_enable(); return rc; } @@ -1180,6 +1314,10 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); if (flags & IUCV_IPRMDATA) { @@ -1202,6 +1340,7 @@ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, rc = iucv_call_b2f0(IUCV_SEND, parm); if (!rc) msg->id = parm->db.ipmsgid; +out: return rc; } EXPORT_SYMBOL(__iucv_message_send); @@ -1262,6 +1401,10 @@ 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)) { + rc = -EIO; + goto out; + } parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); if (flags & IUCV_IPRMDATA) { @@ -1287,6 +1430,7 @@ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, rc = iucv_call_b2f0(IUCV_SEND, parm); if (!rc) msg->id = parm->db.ipmsgid; +out: local_bh_enable(); return rc; } @@ -1378,6 +1522,8 @@ static void iucv_path_complete(struct iucv_irq_data *data) struct iucv_path_complete *ipc = (void *) data; struct iucv_path *path = iucv_path_table[ipc->ippathid]; + if (path) + path->flags = ipc->ipflags1; if (path && path->handler && path->handler->path_complete) path->handler->path_complete(path, ipc->ipuser); } @@ -1413,7 +1559,7 @@ static void iucv_path_severed(struct iucv_irq_data *data) else { iucv_sever_pathid(path->pathid, NULL); iucv_path_table[path->pathid] = NULL; - list_del_init(&path->list); + list_del(&path->list); iucv_path_free(path); } } @@ -1675,6 +1821,130 @@ static void iucv_external_interrupt(u16 code) spin_unlock(&iucv_queue_lock); } +static int iucv_pm_prepare(struct device *dev) +{ + int rc = 0; + +#ifdef CONFIG_PM_DEBUG + printk(KERN_INFO "iucv_pm_prepare\n"); +#endif + if (dev->driver && dev->driver->pm && dev->driver->pm->prepare) + rc = dev->driver->pm->prepare(dev); + return rc; +} + +static void iucv_pm_complete(struct device *dev) +{ +#ifdef CONFIG_PM_DEBUG + printk(KERN_INFO "iucv_pm_complete\n"); +#endif + if (dev->driver && dev->driver->pm && dev->driver->pm->complete) + dev->driver->pm->complete(dev); +} + +/** + * iucv_path_table_empty() - determine if iucv path table is empty + * + * Returns 0 if there are still iucv pathes defined + * 1 if there are no iucv pathes defined + */ +int iucv_path_table_empty(void) +{ + int i; + + for (i = 0; i < iucv_max_pathid; i++) { + if (iucv_path_table[i]) + return 0; + } + return 1; +} + +/** + * iucv_pm_freeze() - Freeze PM callback + * @dev: iucv-based device + * + * disable iucv interrupts + * invoke callback function of the iucv-based driver + * shut down iucv, if no iucv-pathes are established anymore + */ +static int iucv_pm_freeze(struct device *dev) +{ + int cpu; + int rc = 0; + +#ifdef CONFIG_PM_DEBUG + printk(KERN_WARNING "iucv_pm_freeze\n"); +#endif + 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) + rc = dev->driver->pm->freeze(dev); + if (iucv_path_table_empty()) + iucv_disable(); + return rc; +} + +/** + * iucv_pm_thaw() - Thaw PM callback + * @dev: iucv-based device + * + * make iucv ready for use again: allocate path table, declare interrupt buffers + * and enable iucv interrupts + * invoke callback function of the iucv-based driver + */ +static int iucv_pm_thaw(struct device *dev) +{ + int rc = 0; + +#ifdef CONFIG_PM_DEBUG + printk(KERN_WARNING "iucv_pm_thaw\n"); +#endif + if (!iucv_path_table) { + rc = iucv_enable(); + if (rc) + goto out; + } + if (cpus_empty(iucv_irq_cpumask)) { + if (iucv_nonsmp_handler) + /* enable interrupts on one cpu */ + iucv_allow_cpu(NULL); + else + /* enable interrupts on all cpus */ + iucv_setmask_mp(); + } + if (dev->driver && dev->driver->pm && dev->driver->pm->thaw) + rc = dev->driver->pm->thaw(dev); +out: + return rc; +} + +/** + * iucv_pm_restore() - Restore PM callback + * @dev: iucv-based device + * + * make iucv ready for use again: allocate path table, declare interrupt buffers + * and enable iucv interrupts + * invoke callback function of the iucv-based driver + */ +static int iucv_pm_restore(struct device *dev) +{ + int rc = 0; + +#ifdef CONFIG_PM_DEBUG + printk(KERN_WARNING "iucv_pm_restore %p\n", iucv_path_table); +#endif + if (cpus_empty(iucv_irq_cpumask)) { + rc = iucv_query_maxconn(); + rc = iucv_enable(); + if (rc) + goto out; + } + if (dev->driver && dev->driver->pm && dev->driver->pm->restore) + rc = dev->driver->pm->restore(dev); +out: + return rc; +} + /** * iucv_init * @@ -1717,23 +1987,37 @@ static int __init iucv_init(void) rc = -ENOMEM; goto out_free; } + iucv_param_irq[cpu] = kmalloc_node(sizeof(union iucv_param), + GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); + if (!iucv_param_irq[cpu]) { + rc = -ENOMEM; + goto out_free; + } + } rc = register_hotcpu_notifier(&iucv_cpu_notifier); if (rc) goto out_free; + rc = register_reboot_notifier(&iucv_reboot_notifier); + if (rc) + goto out_cpu; ASCEBC(iucv_error_no_listener, 16); ASCEBC(iucv_error_no_memory, 16); ASCEBC(iucv_error_pathid, 16); iucv_available = 1; rc = bus_register(&iucv_bus); if (rc) - goto out_cpu; + goto out_reboot; return 0; +out_reboot: + unregister_reboot_notifier(&iucv_reboot_notifier); out_cpu: unregister_hotcpu_notifier(&iucv_cpu_notifier); out_free: for_each_possible_cpu(cpu) { + kfree(iucv_param_irq[cpu]); + iucv_param_irq[cpu] = NULL; kfree(iucv_param[cpu]); iucv_param[cpu] = NULL; kfree(iucv_irq_data[cpu]); @@ -1762,8 +2046,11 @@ static void __exit iucv_exit(void) list_for_each_entry_safe(p, n, &iucv_work_queue, list) kfree(p); spin_unlock_irq(&iucv_queue_lock); + unregister_reboot_notifier(&iucv_reboot_notifier); unregister_hotcpu_notifier(&iucv_cpu_notifier); for_each_possible_cpu(cpu) { + kfree(iucv_param_irq[cpu]); + iucv_param_irq[cpu] = NULL; kfree(iucv_param[cpu]); iucv_param[cpu] = NULL; kfree(iucv_irq_data[cpu]); diff --git a/net/key/af_key.c b/net/key/af_key.c index 643c1be2d02..dba9abd27f9 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3662,8 +3662,8 @@ static int pfkey_seq_show(struct seq_file *f, void *v) seq_printf(f ,"%p %-6d %-6u %-6u %-6u %-6lu\n", s, atomic_read(&s->sk_refcnt), - atomic_read(&s->sk_rmem_alloc), - atomic_read(&s->sk_wmem_alloc), + sk_rmem_alloc_get(s), + sk_wmem_alloc_get(s), sock_i_uid(s), sock_i_ino(s) ); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index febae702685..c45eee1c0e8 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -914,6 +914,7 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, struct llc_sock *llc = llc_sk(sk); int rc = 0; + memset(&sllc, 0, sizeof(sllc)); lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) goto out; @@ -935,7 +936,7 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, if (llc->dev) { sllc.sllc_arphrd = llc->dev->type; - memcpy(&sllc.sllc_mac, &llc->dev->dev_addr, + memcpy(&sllc.sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); } } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 3477624a490..c6bab39b018 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -79,10 +79,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) if (unlikely(!ev->ind_prim && !ev->cfm_prim)) { /* indicate or confirm not required */ - /* XXX this is not very pretty, perhaps we should store - * XXX indicate/confirm-needed state in the llc_conn_state_ev - * XXX control block of the SKB instead? -DaveM - */ if (!skb->next) goto out_kfree_skb; goto out_skb_put; diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index d208b3396d9..f97be471fe2 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -134,8 +134,8 @@ static int llc_seq_socket_show(struct seq_file *seq, void *v) seq_printf(seq, "@%02X ", llc->sap->laddr.lsap); llc_ui_format_mac(seq, llc->daddr.mac); seq_printf(seq, "@%02X %8d %8d %2d %3d %4d\n", llc->daddr.lsap, - atomic_read(&sk->sk_wmem_alloc), - atomic_read(&sk->sk_rmem_alloc) - llc->copied_seq, + sk_wmem_alloc_get(sk), + sk_rmem_alloc_get(sk) - llc->copied_seq, sk->sk_state, sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : -1, llc->link); diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index ecc3faf9f11..7836ee92898 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -1,16 +1,35 @@ config MAC80211 tristate "Generic IEEE 802.11 Networking Stack (mac80211)" + depends on CFG80211 select CRYPTO select CRYPTO_ECB select CRYPTO_ARC4 select CRYPTO_AES select CRC32 select WIRELESS_EXT - select CFG80211 ---help--- This option enables the hardware independent IEEE 802.11 networking stack. +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 @@ -64,6 +83,7 @@ endmenu 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 diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 07656d830bc..bc064d7933f 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -16,12 +16,12 @@ #include <linux/ieee80211.h> #include <net/mac80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, u16 initiator, u16 reason) { struct ieee80211_local *local = sta->local; - struct ieee80211_hw *hw = &local->hw; int i; /* check if TID is in operational state */ @@ -41,8 +41,8 @@ void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, sta->sta.addr, tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ - if (local->ops->ampdu_action(hw, IEEE80211_AMPDU_RX_STOP, - &sta->sta, tid, NULL)) + if (drv_ampdu_action(local, IEEE80211_AMPDU_RX_STOP, + &sta->sta, tid, NULL)) printk(KERN_DEBUG "HW problem - can not stop rx " "aggregation for tid %d\n", tid); @@ -68,6 +68,7 @@ void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, spin_lock_bh(&sta->lock); /* free resources */ kfree(sta->ampdu_mlme.tid_rx[tid]->reorder_buf); + kfree(sta->ampdu_mlme.tid_rx[tid]->reorder_time); if (!sta->ampdu_mlme.tid_rx[tid]->shutdown) { kfree(sta->ampdu_mlme.tid_rx[tid]); @@ -268,19 +269,23 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, /* prepare reordering buffer */ tid_agg_rx->reorder_buf = kcalloc(buf_size, sizeof(struct sk_buff *), GFP_ATOMIC); - if (!tid_agg_rx->reorder_buf) { + tid_agg_rx->reorder_time = + kcalloc(buf_size, sizeof(unsigned long), GFP_ATOMIC); + if (!tid_agg_rx->reorder_buf || !tid_agg_rx->reorder_time) { #ifdef CONFIG_MAC80211_HT_DEBUG if (net_ratelimit()) printk(KERN_ERR "can not allocate reordering buffer " "to tid %d\n", tid); #endif + kfree(tid_agg_rx->reorder_buf); + kfree(tid_agg_rx->reorder_time); kfree(sta->ampdu_mlme.tid_rx[tid]); + sta->ampdu_mlme.tid_rx[tid] = NULL; goto end; } - if (local->ops->ampdu_action) - ret = local->ops->ampdu_action(hw, IEEE80211_AMPDU_RX_START, - &sta->sta, tid, &start_seq_num); + ret = drv_ampdu_action(local, IEEE80211_AMPDU_RX_START, + &sta->sta, tid, &start_seq_num); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "Rx A-MPDU request on tid %d result %d\n", tid, ret); #endif /* CONFIG_MAC80211_HT_DEBUG */ diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 947aaaad35d..a24e59816b9 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -16,6 +16,7 @@ #include <linux/ieee80211.h> #include <net/mac80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "wme.h" /** @@ -131,11 +132,14 @@ static int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, state = &sta->ampdu_mlme.tid_state_tx[tid]; + if (*state == HT_AGG_STATE_OPERATIONAL) + sta->ampdu_mlme.addba_req_num[tid] = 0; + *state = HT_AGG_STATE_REQ_STOP_BA_MSK | (initiator << HT_AGG_STATE_INITIATOR_SHIFT); - ret = local->ops->ampdu_action(&local->hw, IEEE80211_AMPDU_TX_STOP, - &sta->sta, tid, NULL); + ret = drv_ampdu_action(local, IEEE80211_AMPDU_TX_STOP, + &sta->sta, tid, NULL); /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { @@ -306,8 +310,8 @@ int ieee80211_start_tx_ba_session(struct ieee80211_hw *hw, u8 *ra, u16 tid) start_seq_num = sta->tid_seq[tid]; - ret = local->ops->ampdu_action(hw, IEEE80211_AMPDU_TX_START, - &sta->sta, tid, &start_seq_num); + ret = drv_ampdu_action(local, IEEE80211_AMPDU_TX_START, + &sta->sta, tid, &start_seq_num); if (ret) { #ifdef CONFIG_MAC80211_HT_DEBUG @@ -336,6 +340,7 @@ int ieee80211_start_tx_ba_session(struct ieee80211_hw *hw, u8 *ra, u16 tid) sta->ampdu_mlme.tid_tx[tid]->dialog_token, sta->ampdu_mlme.tid_tx[tid]->ssn, 0x40, 5000); + sta->ampdu_mlme.addba_req_num[tid]++; /* activate the timer for the recipient's addBA response */ sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer.expires = jiffies + ADDBA_RESP_INTERVAL; @@ -376,6 +381,14 @@ static void ieee80211_agg_splice_packets(struct ieee80211_local *local, &local->hw, queue, IEEE80211_QUEUE_STOP_REASON_AGGREGATION); + if (!(sta->ampdu_mlme.tid_state_tx[tid] & HT_ADDBA_REQUESTED_MSK)) + return; + + if (WARN(!sta->ampdu_mlme.tid_tx[tid], + "TID %d gone but expected when splicing aggregates from" + "the pending queue\n", tid)) + return; + if (!skb_queue_empty(&sta->ampdu_mlme.tid_tx[tid]->pending)) { spin_lock_irqsave(&local->queue_stop_reason_lock, flags); /* mark queue as pending, it is stopped already */ @@ -418,8 +431,8 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, ieee80211_agg_splice_finish(local, sta, tid); spin_unlock(&local->ampdu_lock); - local->ops->ampdu_action(&local->hw, IEEE80211_AMPDU_TX_OPERATIONAL, - &sta->sta, tid, NULL); + drv_ampdu_action(local, IEEE80211_AMPDU_TX_OPERATIONAL, + &sta->sta, tid, NULL); } void ieee80211_start_tx_ba_cb(struct ieee80211_hw *hw, u8 *ra, u16 tid) @@ -605,7 +618,6 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_hw *hw, u8 *ra, u8 tid) *state = HT_AGG_STATE_IDLE; /* from now on packets are no longer put onto sta->pending */ - sta->ampdu_mlme.addba_req_num[tid] = 0; kfree(sta->ampdu_mlme.tid_tx[tid]); sta->ampdu_mlme.tid_tx[tid] = NULL; @@ -688,7 +700,6 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, sta->ampdu_mlme.addba_req_num[tid] = 0; } else { - sta->ampdu_mlme.addba_req_num[tid]++; ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR); } spin_unlock_bh(&sta->lock); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index e677b751d46..3f47276caeb 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -13,6 +13,7 @@ #include <linux/rcupdate.h> #include <net/cfg80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "cfg.h" #include "rate.h" #include "mesh.h" @@ -111,7 +112,7 @@ static int ieee80211_change_iface(struct wiphy *wiphy, int ifindex, } static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, - u8 key_idx, u8 *mac_addr, + u8 key_idx, const u8 *mac_addr, struct key_params *params) { struct ieee80211_sub_if_data *sdata; @@ -140,7 +141,8 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; } - key = ieee80211_key_alloc(alg, key_idx, params->key_len, params->key); + key = ieee80211_key_alloc(alg, key_idx, params->key_len, params->key, + params->seq_len, params->seq); if (!key) return -ENOMEM; @@ -165,7 +167,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, } static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, - u8 key_idx, u8 *mac_addr) + u8 key_idx, const u8 *mac_addr) { struct ieee80211_sub_if_data *sdata; struct sta_info *sta; @@ -207,7 +209,7 @@ static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, } static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, - u8 key_idx, u8 *mac_addr, void *cookie, + u8 key_idx, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params *params)) { @@ -245,12 +247,10 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, iv32 = key->u.tkip.tx.iv32; iv16 = key->u.tkip.tx.iv16; - if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && - sdata->local->ops->get_tkip_seq) - sdata->local->ops->get_tkip_seq( - local_to_hw(sdata->local), - key->conf.hw_key_idx, - &iv32, &iv16); + if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) + drv_get_tkip_seq(sdata->local, + key->conf.hw_key_idx, + &iv32, &iv16); seq[0] = iv16 & 0xff; seq[1] = (iv16 >> 8) & 0xff; @@ -451,18 +451,11 @@ static int ieee80211_config_beacon(struct ieee80211_sub_if_data *sdata, * This is a kludge. beacon interval should really be part * of the beacon information. */ - if (params->interval && (sdata->local->hw.conf.beacon_int != - params->interval)) { - sdata->local->hw.conf.beacon_int = params->interval; - err = ieee80211_hw_config(sdata->local, - IEEE80211_CONF_CHANGE_BEACON_INTERVAL); - if (err < 0) - return err; - /* - * We updated some parameter so if below bails out - * it's not an error. - */ - err = 0; + if (params->interval && + (sdata->vif.bss_conf.beacon_int != params->interval)) { + sdata->vif.bss_conf.beacon_int = params->interval; + ieee80211_bss_info_change_notify(sdata, + BSS_CHANGED_BEACON_INT); } /* Need to have a beacon head if we don't have one yet */ @@ -528,8 +521,9 @@ static int ieee80211_config_beacon(struct ieee80211_sub_if_data *sdata, kfree(old); - return ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON | - IEEE80211_IFCC_BEACON_ENABLED); + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED | + BSS_CHANGED_BEACON); + return 0; } static int ieee80211_add_beacon(struct wiphy *wiphy, struct net_device *dev, @@ -580,7 +574,8 @@ static int ieee80211_del_beacon(struct wiphy *wiphy, struct net_device *dev) synchronize_rcu(); kfree(old); - return ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON_ENABLED); + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); + return 0; } /* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */ @@ -635,34 +630,45 @@ static void sta_apply_parameters(struct ieee80211_local *local, int i, j; struct ieee80211_supported_band *sband; struct ieee80211_sub_if_data *sdata = sta->sdata; + u32 mask, set; sband = local->hw.wiphy->bands[local->oper_channel->band]; - /* - * FIXME: updating the flags is racy when this function is - * called from ieee80211_change_station(), this will - * be resolved in a future patch. - */ + spin_lock_bh(&sta->lock); + mask = params->sta_flags_mask; + set = params->sta_flags_set; - if (params->station_flags & STATION_FLAG_CHANGED) { - spin_lock_bh(&sta->lock); + if (mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { sta->flags &= ~WLAN_STA_AUTHORIZED; - if (params->station_flags & STATION_FLAG_AUTHORIZED) + if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) sta->flags |= WLAN_STA_AUTHORIZED; + } + if (mask & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) { sta->flags &= ~WLAN_STA_SHORT_PREAMBLE; - if (params->station_flags & STATION_FLAG_SHORT_PREAMBLE) + if (set & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) sta->flags |= WLAN_STA_SHORT_PREAMBLE; + } + if (mask & BIT(NL80211_STA_FLAG_WME)) { sta->flags &= ~WLAN_STA_WME; - if (params->station_flags & STATION_FLAG_WME) + if (set & BIT(NL80211_STA_FLAG_WME)) sta->flags |= WLAN_STA_WME; + } + if (mask & BIT(NL80211_STA_FLAG_MFP)) { sta->flags &= ~WLAN_STA_MFP; - if (params->station_flags & STATION_FLAG_MFP) + if (set & BIT(NL80211_STA_FLAG_MFP)) sta->flags |= WLAN_STA_MFP; - spin_unlock_bh(&sta->lock); } + spin_unlock_bh(&sta->lock); + + /* + * cfg80211 validates this (1-2007) and allows setting the AID + * only when creating a new station entry + */ + if (params->aid) + sta->sta.aid = params->aid; /* * FIXME: updating the following information is racy when this @@ -671,12 +677,6 @@ static void sta_apply_parameters(struct ieee80211_local *local, * maybe we should just reject attemps to change it. */ - if (params->aid) { - sta->sta.aid = params->aid; - if (sta->sta.aid > IEEE80211_MAX_AID) - sta->sta.aid = 0; /* XXX: should this be an error? */ - } - if (params->listen_interval >= 0) sta->listen_interval = params->listen_interval; @@ -1120,10 +1120,10 @@ static int ieee80211_set_txq_params(struct wiphy *wiphy, p.cw_max = params->cwmax; p.cw_min = params->cwmin; p.txop = params->txop; - if (local->ops->conf_tx(local_to_hw(local), params->queue, &p)) { + if (drv_conf_tx(local, params->queue, &p)) { printk(KERN_DEBUG "%s: failed to set TX queue " - "parameters for queue %d\n", local->mdev->name, - params->queue); + "parameters for queue %d\n", + wiphy_name(local->hw.wiphy), params->queue); return -EINVAL; } @@ -1167,7 +1167,8 @@ static int ieee80211_scan(struct wiphy *wiphy, if (sdata->vif.type != NL80211_IFTYPE_STATION && sdata->vif.type != NL80211_IFTYPE_ADHOC && - sdata->vif.type != NL80211_IFTYPE_MESH_POINT) + sdata->vif.type != NL80211_IFTYPE_MESH_POINT && + (sdata->vif.type != NL80211_IFTYPE_AP || sdata->u.ap.beacon)) return -EOPNOTSUPP; return ieee80211_request_scan(sdata, req); @@ -1255,9 +1256,22 @@ static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, sdata->u.mgd.flags |= IEEE80211_STA_AUTO_SSID_SEL; ret = ieee80211_sta_set_extra_ie(sdata, req->ie, req->ie_len); - if (ret) + 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); @@ -1267,25 +1281,106 @@ static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_deauth(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_deauth_request *req) { - struct ieee80211_sub_if_data *sdata; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - /* TODO: req->ie */ + /* TODO: req->ie, req->peer_addr */ return ieee80211_sta_deauthenticate(sdata, req->reason_code); } static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_disassoc_request *req) { - struct ieee80211_sub_if_data *sdata; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - /* TODO: req->ie */ + /* TODO: req->ie, req->peer_addr */ return ieee80211_sta_disassociate(sdata, req->reason_code); } +static int ieee80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_ibss_params *params) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + return ieee80211_ibss_join(sdata, params); +} + +static int ieee80211_leave_ibss(struct wiphy *wiphy, struct net_device *dev) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + return ieee80211_ibss_leave(sdata); +} + +static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + int err; + + if (changed & WIPHY_PARAM_RTS_THRESHOLD) { + err = drv_set_rts_threshold(local, wiphy->rts_threshold); + + if (err) + return err; + } + + if (changed & WIPHY_PARAM_RETRY_SHORT) + local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; + if (changed & WIPHY_PARAM_RETRY_LONG) + local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; + if (changed & + (WIPHY_PARAM_RETRY_SHORT | WIPHY_PARAM_RETRY_LONG)) + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_RETRY_LIMITS); + + return 0; +} + +static int ieee80211_set_tx_power(struct wiphy *wiphy, + enum tx_power_setting type, int dbm) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_channel *chan = local->hw.conf.channel; + u32 changes = 0; + + switch (type) { + case TX_POWER_AUTOMATIC: + local->user_power_level = -1; + break; + case TX_POWER_LIMITED: + if (dbm < 0) + return -EINVAL; + local->user_power_level = dbm; + break; + case TX_POWER_FIXED: + if (dbm < 0) + return -EINVAL; + /* TODO: move to cfg80211 when it knows the channel */ + if (dbm > chan->max_power) + return -EINVAL; + local->user_power_level = dbm; + break; + } + + ieee80211_hw_config(local, changes); + + return 0; +} + +static int ieee80211_get_tx_power(struct wiphy *wiphy, int *dbm) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + + *dbm = local->hw.conf.power_level; + + return 0; +} + +static void ieee80211_rfkill_poll(struct wiphy *wiphy) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + + drv_rfkill_poll(local); +} + struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -1322,4 +1417,10 @@ struct cfg80211_ops mac80211_config_ops = { .assoc = ieee80211_assoc, .deauth = ieee80211_deauth, .disassoc = ieee80211_disassoc, + .join_ibss = ieee80211_join_ibss, + .leave_ibss = ieee80211_leave_ibss, + .set_wiphy_params = ieee80211_set_wiphy_params, + .set_tx_power = ieee80211_set_tx_power, + .get_tx_power = ieee80211_get_tx_power, + .rfkill_poll = ieee80211_rfkill_poll, }; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 210b9b6fecd..6c439cd5cce 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -10,6 +10,7 @@ #include <linux/debugfs.h> #include <linux/rtnetlink.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "rate.h" #include "debugfs.h" @@ -51,14 +52,6 @@ static const struct file_operations name## _ops = { \ DEBUGFS_READONLY_FILE(frequency, 20, "%d", local->hw.conf.channel->center_freq); -DEBUGFS_READONLY_FILE(rts_threshold, 20, "%d", - local->rts_threshold); -DEBUGFS_READONLY_FILE(fragmentation_threshold, 20, "%d", - local->fragmentation_threshold); -DEBUGFS_READONLY_FILE(short_retry_limit, 20, "%d", - local->hw.conf.short_frame_max_tx_count); -DEBUGFS_READONLY_FILE(long_retry_limit, 20, "%d", - local->hw.conf.long_frame_max_tx_count); DEBUGFS_READONLY_FILE(total_ps_buffered, 20, "%d", local->total_ps_buffered); DEBUGFS_READONLY_FILE(wep_iv, 20, "%#08x", @@ -70,11 +63,10 @@ static ssize_t tsf_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct ieee80211_local *local = file->private_data; - u64 tsf = 0; + u64 tsf; char buf[100]; - if (local->ops->get_tsf) - tsf = local->ops->get_tsf(local_to_hw(local)); + tsf = drv_get_tsf(local); snprintf(buf, sizeof(buf), "0x%016llx\n", (unsigned long long) tsf); @@ -97,13 +89,13 @@ static ssize_t tsf_write(struct file *file, if (strncmp(buf, "reset", 5) == 0) { if (local->ops->reset_tsf) { - local->ops->reset_tsf(local_to_hw(local)); + drv_reset_tsf(local); printk(KERN_INFO "%s: debugfs reset TSF\n", wiphy_name(local->hw.wiphy)); } } else { tsf = simple_strtoul(buf, NULL, 0); if (local->ops->set_tsf) { - local->ops->set_tsf(local_to_hw(local), tsf); + drv_set_tsf(local, tsf); printk(KERN_INFO "%s: debugfs set TSF to %#018llx\n", wiphy_name(local->hw.wiphy), tsf); } } @@ -135,6 +127,65 @@ static const struct file_operations reset_ops = { .open = mac80211_open_file_generic, }; +static ssize_t noack_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + int res; + char buf[10]; + + res = scnprintf(buf, sizeof(buf), "%d\n", local->wifi_wme_noack_test); + + return simple_read_from_buffer(user_buf, count, ppos, buf, res); +} + +static ssize_t noack_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + char buf[10]; + size_t len; + + len = min(count, sizeof(buf) - 1); + if (copy_from_user(buf, user_buf, len)) + return -EFAULT; + buf[len] = '\0'; + + local->wifi_wme_noack_test = !!simple_strtoul(buf, NULL, 0); + + return count; +} + +static const struct file_operations noack_ops = { + .read = noack_read, + .write = noack_write, + .open = mac80211_open_file_generic +}; + +static ssize_t queues_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + unsigned long flags; + char buf[IEEE80211_MAX_QUEUES * 20]; + int q, res = 0; + + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + 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)); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + return simple_read_from_buffer(user_buf, count, ppos, buf, res); +} + +static const struct file_operations queues_ops = { + .read = queues_read, + .open = mac80211_open_file_generic +}; + /* statistics stuff */ #define DEBUGFS_STATS_FILE(name, buflen, fmt, value...) \ @@ -150,14 +201,12 @@ static ssize_t format_devstat_counter(struct ieee80211_local *local, char buf[20]; int res; - if (!local->ops->get_stats) - return -EOPNOTSUPP; - rtnl_lock(); - res = local->ops->get_stats(local_to_hw(local), &stats); + res = drv_get_stats(local, &stats); rtnl_unlock(); - if (!res) - res = printvalue(&stats, buf, sizeof(buf)); + if (res) + return res; + res = printvalue(&stats, buf, sizeof(buf)); return simple_read_from_buffer(userbuf, count, ppos, buf, res); } @@ -269,14 +318,12 @@ void debugfs_hw_add(struct ieee80211_local *local) local->debugfs.keys = debugfs_create_dir("keys", phyd); DEBUGFS_ADD(frequency); - DEBUGFS_ADD(rts_threshold); - DEBUGFS_ADD(fragmentation_threshold); - DEBUGFS_ADD(short_retry_limit); - DEBUGFS_ADD(long_retry_limit); DEBUGFS_ADD(total_ps_buffered); DEBUGFS_ADD(wep_iv); DEBUGFS_ADD(tsf); + DEBUGFS_ADD(queues); DEBUGFS_ADD_MODE(reset, 0200); + DEBUGFS_ADD(noack); statsd = debugfs_create_dir("statistics", phyd); local->debugfs.statistics = statsd; @@ -324,14 +371,12 @@ void debugfs_hw_add(struct ieee80211_local *local) void debugfs_hw_del(struct ieee80211_local *local) { DEBUGFS_DEL(frequency); - DEBUGFS_DEL(rts_threshold); - DEBUGFS_DEL(fragmentation_threshold); - DEBUGFS_DEL(short_retry_limit); - DEBUGFS_DEL(long_retry_limit); DEBUGFS_DEL(total_ps_buffered); DEBUGFS_DEL(wep_iv); DEBUGFS_DEL(tsf); + DEBUGFS_DEL(queues); DEBUGFS_DEL(reset); + DEBUGFS_DEL(noack); DEBUGFS_STATS_DEL(transmitted_fragment_count); DEBUGFS_STATS_DEL(multicast_transmitted_frame_count); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h new file mode 100644 index 00000000000..b13446afd48 --- /dev/null +++ b/net/mac80211/driver-ops.h @@ -0,0 +1,191 @@ +#ifndef __MAC80211_DRIVER_OPS +#define __MAC80211_DRIVER_OPS + +#include <net/mac80211.h> +#include "ieee80211_i.h" + +static inline int drv_tx(struct ieee80211_local *local, struct sk_buff *skb) +{ + return local->ops->tx(&local->hw, skb); +} + +static inline int drv_start(struct ieee80211_local *local) +{ + return local->ops->start(&local->hw); +} + +static inline void drv_stop(struct ieee80211_local *local) +{ + local->ops->stop(&local->hw); +} + +static inline int drv_add_interface(struct ieee80211_local *local, + struct ieee80211_if_init_conf *conf) +{ + return local->ops->add_interface(&local->hw, conf); +} + +static inline void drv_remove_interface(struct ieee80211_local *local, + struct ieee80211_if_init_conf *conf) +{ + local->ops->remove_interface(&local->hw, conf); +} + +static inline int drv_config(struct ieee80211_local *local, u32 changed) +{ + return local->ops->config(&local->hw, changed); +} + +static inline void drv_bss_info_changed(struct ieee80211_local *local, + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *info, + u32 changed) +{ + if (local->ops->bss_info_changed) + local->ops->bss_info_changed(&local->hw, vif, info, changed); +} + +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) +{ + local->ops->configure_filter(&local->hw, changed_flags, total_flags, + mc_count, mc_list); +} + +static inline int drv_set_tim(struct ieee80211_local *local, + struct ieee80211_sta *sta, bool set) +{ + if (local->ops->set_tim) + return local->ops->set_tim(&local->hw, sta, set); + return 0; +} + +static inline int drv_set_key(struct ieee80211_local *local, + enum set_key_cmd cmd, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key) +{ + return local->ops->set_key(&local->hw, cmd, vif, sta, key); +} + +static inline void drv_update_tkip_key(struct ieee80211_local *local, + struct ieee80211_key_conf *conf, + const u8 *address, u32 iv32, + u16 *phase1key) +{ + if (local->ops->update_tkip_key) + local->ops->update_tkip_key(&local->hw, conf, address, + iv32, phase1key); +} + +static inline int drv_hw_scan(struct ieee80211_local *local, + struct cfg80211_scan_request *req) +{ + return local->ops->hw_scan(&local->hw, req); +} + +static inline void drv_sw_scan_start(struct ieee80211_local *local) +{ + if (local->ops->sw_scan_start) + local->ops->sw_scan_start(&local->hw); +} + +static inline void drv_sw_scan_complete(struct ieee80211_local *local) +{ + if (local->ops->sw_scan_complete) + local->ops->sw_scan_complete(&local->hw); +} + +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); +} + +static inline void drv_get_tkip_seq(struct ieee80211_local *local, + u8 hw_key_idx, u32 *iv32, u16 *iv16) +{ + if (local->ops->get_tkip_seq) + local->ops->get_tkip_seq(&local->hw, hw_key_idx, iv32, iv16); +} + +static inline int drv_set_rts_threshold(struct ieee80211_local *local, + u32 value) +{ + if (local->ops->set_rts_threshold) + return local->ops->set_rts_threshold(&local->hw, value); + return 0; +} + +static inline void drv_sta_notify(struct ieee80211_local *local, + struct ieee80211_vif *vif, + enum sta_notify_cmd cmd, + struct ieee80211_sta *sta) +{ + if (local->ops->sta_notify) + local->ops->sta_notify(&local->hw, vif, cmd, sta); +} + +static inline int drv_conf_tx(struct ieee80211_local *local, u16 queue, + const struct ieee80211_tx_queue_params *params) +{ + if (local->ops->conf_tx) + return local->ops->conf_tx(&local->hw, queue, params); + return -EOPNOTSUPP; +} + +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); +} + +static inline u64 drv_get_tsf(struct ieee80211_local *local) +{ + if (local->ops->get_tsf) + return local->ops->get_tsf(&local->hw); + return -1ULL; +} + +static inline void drv_set_tsf(struct ieee80211_local *local, u64 tsf) +{ + if (local->ops->set_tsf) + local->ops->set_tsf(&local->hw, tsf); +} + +static inline void drv_reset_tsf(struct ieee80211_local *local) +{ + if (local->ops->reset_tsf) + local->ops->reset_tsf(&local->hw); +} + +static inline int drv_tx_last_beacon(struct ieee80211_local *local) +{ + if (local->ops->tx_last_beacon) + return local->ops->tx_last_beacon(&local->hw); + return 1; +} + +static inline int drv_ampdu_action(struct ieee80211_local *local, + enum ieee80211_ampdu_mlme_action action, + struct ieee80211_sta *sta, u16 tid, + u16 *ssn) +{ + if (local->ops->ampdu_action) + return local->ops->ampdu_action(&local->hw, action, + sta, tid, ssn); + return -EOPNOTSUPP; +} + + +static inline void drv_rfkill_poll(struct ieee80211_local *local) +{ + if (local->ops->rfkill_poll) + local->ops->rfkill_poll(&local->hw); +} +#endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/event.c b/net/mac80211/event.c index 0d95561c0ee..f288d01a634 100644 --- a/net/mac80211/event.c +++ b/net/mac80211/event.c @@ -12,12 +12,12 @@ #include "ieee80211_i.h" /* - * indicate a failed Michael MIC to userspace; the passed packet - * (in the variable hdr) must be long enough to extract the TKIP - * fields like TSC + * Indicate a failed Michael MIC to userspace. If the caller knows the TSC of + * the frame that generated the MIC failure (i.e., if it was provided by the + * 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) + struct ieee80211_hdr *hdr, const u8 *tsc) { union iwreq_data wrqu; char *buf = kmalloc(128, GFP_ATOMIC); @@ -34,8 +34,9 @@ void mac80211_ev_michael_mic_failure(struct ieee80211_sub_if_data *sdata, int ke kfree(buf); } - /* - * TODO: re-add support for sending MIC failure indication - * with all info via nl80211 - */ + cfg80211_michael_mic_failure(sdata->dev, hdr->addr2, + (hdr->addr1[0] & 0x01) ? + NL80211_KEYTYPE_GROUP : + NL80211_KEYTYPE_PAIRWISE, + keyidx, tsc); } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 4e3c72f20de..0891bfb0699 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -14,7 +14,6 @@ */ #include <linux/ieee80211.h> -#include <net/wireless.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "rate.h" @@ -83,89 +82,6 @@ void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_supported_band *sband, ht_cap->mcs.rx_mask[32/8] |= 1; } -/* - * ieee80211_enable_ht should be called only after the operating band - * has been determined as ht configuration depends on the hw's - * HT abilities for a specific band. - */ -u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, - struct ieee80211_ht_info *hti, - 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 ieee80211_bss_ht_conf ht; - struct sta_info *sta; - u32 changed = 0; - bool enable_ht = true, ht_changed; - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - - memset(&ht, 0, sizeof(ht)); - - /* HT is not supported */ - if (!sband->ht_cap.ht_supported) - enable_ht = false; - - /* check that channel matches the right operating channel */ - if (local->hw.conf.channel->center_freq != - ieee80211_channel_to_frequency(hti->control_chan)) - enable_ht = false; - - if (enable_ht) { - channel_type = NL80211_CHAN_HT20; - - if (!(ap_ht_cap_flags & IEEE80211_HT_CAP_40MHZ_INTOLERANT) && - (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) && - (hti->ht_param & IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)) { - switch(hti->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { - case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: - channel_type = NL80211_CHAN_HT40PLUS; - break; - case IEEE80211_HT_PARAM_CHA_SEC_BELOW: - channel_type = NL80211_CHAN_HT40MINUS; - break; - } - } - } - - ht_changed = conf_is_ht(&local->hw.conf) != enable_ht || - channel_type != local->hw.conf.channel_type; - - local->oper_channel_type = channel_type; - - if (ht_changed) { - /* channel_type change automatically detected */ - ieee80211_hw_config(local, 0); - - rcu_read_lock(); - - sta = sta_info_get(local, ifmgd->bssid); - if (sta) - rate_control_rate_update(local, sband, sta, - IEEE80211_RC_HT_CHANGED); - - rcu_read_unlock(); - - } - - /* disable HT */ - if (!enable_ht) - return 0; - - ht.operation_mode = le16_to_cpu(hti->operation_mode); - - /* if bss configuration changed store the new one */ - if (memcmp(&sdata->vif.bss_conf.ht, &ht, sizeof(ht))) { - changed |= BSS_CHANGED_HT; - sdata->vif.bss_conf.ht = ht; - } - - return changed; -} - void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta) { int i; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 3201e1f9636..0b30277eb36 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -22,6 +22,7 @@ #include <asm/unaligned.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "rate.h" #define IEEE80211_SCAN_INTERVAL (2 * HZ) @@ -59,74 +60,65 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, sdata->u.ibss.bssid, 0); } -static int __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, - const u8 *bssid, const int beacon_int, - const int freq, - const size_t supp_rates_len, - const u8 *supp_rates, - const u16 capability, u64 tsf) +static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, + const u8 *bssid, const int beacon_int, + struct ieee80211_channel *chan, + const u32 basic_rates, + const u16 capability, u64 tsf) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_local *local = sdata->local; - int res = 0, rates, i, j; + int rates, i; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; u8 *pos; struct ieee80211_supported_band *sband; - union iwreq_data wrqu; + u32 bss_change; + u8 supp_rates[IEEE80211_MAX_SUPP_RATES]; - if (local->ops->reset_tsf) { - /* Reset own TSF to allow time synchronization work. */ - local->ops->reset_tsf(local_to_hw(local)); - } + /* Reset own TSF to allow time synchronization work. */ + drv_reset_tsf(local); - if ((ifibss->flags & IEEE80211_IBSS_PREV_BSSID_SET) && - memcmp(ifibss->bssid, bssid, ETH_ALEN) == 0) - return res; + skb = ifibss->skb; + rcu_assign_pointer(ifibss->presp, NULL); + synchronize_rcu(); + skb->data = skb->head; + skb->len = 0; + skb_reset_tail_pointer(skb); + skb_reserve(skb, sdata->local->hw.extra_tx_headroom); - skb = dev_alloc_skb(local->hw.extra_tx_headroom + 400); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for probe " - "response\n", sdata->dev->name); - return -ENOMEM; - } - - if (!(ifibss->flags & IEEE80211_IBSS_PREV_BSSID_SET)) { - /* Remove possible STA entries from other IBSS networks. */ - sta_info_flush_delayed(sdata); - } + if (memcmp(ifibss->bssid, bssid, ETH_ALEN)) + sta_info_flush(sdata->local, sdata); memcpy(ifibss->bssid, bssid, ETH_ALEN); - res = ieee80211_if_config(sdata, IEEE80211_IFCC_BSSID); - if (res) - return res; - - local->hw.conf.beacon_int = beacon_int >= 10 ? beacon_int : 10; - sdata->drop_unencrypted = capability & - WLAN_CAPABILITY_PRIVACY ? 1 : 0; + sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0; - res = ieee80211_set_freq(sdata, freq); + local->oper_channel = chan; + local->oper_channel_type = NL80211_CHAN_NO_HT; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - if (res) - return res; + sband = local->hw.wiphy->bands[chan->band]; - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + /* build supported rates array */ + pos = supp_rates; + for (i = 0; i < sband->n_bitrates; i++) { + int rate = sband->bitrates[i].bitrate; + u8 basic = 0; + if (basic_rates & BIT(i)) + basic = 0x80; + *pos++ = basic | (u8) (rate / 5); + } /* Build IBSS probe response */ - - skb_reserve(skb, local->hw.extra_tx_headroom); - - mgmt = (struct ieee80211_mgmt *) - skb_put(skb, 24 + sizeof(mgmt->u.beacon)); + mgmt = (void *) skb_put(skb, 24 + sizeof(mgmt->u.beacon)); memset(mgmt, 0, 24 + sizeof(mgmt->u.beacon)); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP); memset(mgmt->da, 0xff, ETH_ALEN); memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN); memcpy(mgmt->bssid, ifibss->bssid, ETH_ALEN); - mgmt->u.beacon.beacon_int = - cpu_to_le16(local->hw.conf.beacon_int); + mgmt->u.beacon.beacon_int = cpu_to_le16(beacon_int); mgmt->u.beacon.timestamp = cpu_to_le64(tsf); mgmt->u.beacon.capab_info = cpu_to_le16(capability); @@ -135,7 +127,7 @@ static int __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, *pos++ = ifibss->ssid_len; memcpy(pos, ifibss->ssid, ifibss->ssid_len); - rates = supp_rates_len; + rates = sband->n_bitrates; if (rates > 8) rates = 8; pos = skb_put(skb, 2 + rates); @@ -147,7 +139,7 @@ static int __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, 2 + 1); *pos++ = WLAN_EID_DS_PARAMS; *pos++ = 1; - *pos++ = ieee80211_frequency_to_channel(freq); + *pos++ = ieee80211_frequency_to_channel(chan->center_freq); } pos = skb_put(skb, 2 + 2); @@ -157,51 +149,73 @@ static int __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, *pos++ = 0; *pos++ = 0; - if (supp_rates_len > 8) { - rates = supp_rates_len - 8; + if (sband->n_bitrates > 8) { + rates = sband->n_bitrates - 8; pos = skb_put(skb, 2 + rates); *pos++ = WLAN_EID_EXT_SUPP_RATES; *pos++ = rates; memcpy(pos, &supp_rates[8], rates); } - ifibss->probe_resp = skb; + if (ifibss->ie_len) + memcpy(skb_put(skb, ifibss->ie_len), + ifibss->ie, ifibss->ie_len); - ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON | - IEEE80211_IFCC_BEACON_ENABLED); + rcu_assign_pointer(ifibss->presp, skb); + sdata->vif.bss_conf.beacon_int = beacon_int; + bss_change = BSS_CHANGED_BEACON_INT; + bss_change |= ieee80211_reset_erp_info(sdata); + bss_change |= BSS_CHANGED_BSSID; + bss_change |= BSS_CHANGED_BEACON; + bss_change |= BSS_CHANGED_BEACON_ENABLED; + ieee80211_bss_info_change_notify(sdata, bss_change); - rates = 0; - for (i = 0; i < supp_rates_len; i++) { - int bitrate = (supp_rates[i] & 0x7f) * 5; - for (j = 0; j < sband->n_bitrates; j++) - if (sband->bitrates[j].bitrate == bitrate) - rates |= BIT(j); - } + ieee80211_sta_def_wmm_params(sdata, sband->n_bitrates, supp_rates); - ieee80211_sta_def_wmm_params(sdata, supp_rates_len, supp_rates); - - ifibss->flags |= IEEE80211_IBSS_PREV_BSSID_SET; ifibss->state = IEEE80211_IBSS_MLME_JOINED; - mod_timer(&ifibss->timer, jiffies + IEEE80211_IBSS_MERGE_INTERVAL); - - memset(&wrqu, 0, sizeof(wrqu)); - memcpy(wrqu.ap_addr.sa_data, bssid, ETH_ALEN); - wireless_send_event(sdata->dev, SIOCGIWAP, &wrqu, NULL); + mod_timer(&ifibss->timer, + round_jiffies(jiffies + IEEE80211_IBSS_MERGE_INTERVAL)); - return res; + cfg80211_inform_bss_frame(local->hw.wiphy, local->hw.conf.channel, + mgmt, skb->len, 0, GFP_KERNEL); + cfg80211_ibss_joined(sdata->dev, ifibss->bssid, GFP_KERNEL); } -static int ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, - struct ieee80211_bss *bss) +static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, + struct ieee80211_bss *bss) { - return __ieee80211_sta_join_ibss(sdata, - bss->cbss.bssid, - bss->cbss.beacon_interval, - bss->cbss.channel->center_freq, - bss->supp_rates_len, bss->supp_rates, - bss->cbss.capability, - bss->cbss.tsf); + struct ieee80211_supported_band *sband; + u32 basic_rates; + int i, j; + u16 beacon_int = bss->cbss.beacon_interval; + + if (beacon_int < 10) + beacon_int = 10; + + sband = sdata->local->hw.wiphy->bands[bss->cbss.channel->band]; + + basic_rates = 0; + + for (i = 0; i < bss->supp_rates_len; i++) { + int rate = (bss->supp_rates[i] & 0x7f) * 5; + bool is_basic = !!(bss->supp_rates[i] & 0x80); + + for (j = 0; j < sband->n_bitrates; j++) { + if (sband->bitrates[j].bitrate == rate) { + if (is_basic) + basic_rates |= BIT(j); + break; + } + } + } + + __ieee80211_sta_join_ibss(sdata, bss->cbss.bssid, + beacon_int, + bss->cbss.channel, + basic_rates, + bss->cbss.capability, + bss->cbss.tsf); } static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, @@ -277,7 +291,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, goto put_bss; /* we use a fixed BSSID */ - if (sdata->u.ibss.flags & IEEE80211_IBSS_BSSID_SET) + if (sdata->u.ibss.bssid) goto put_bss; /* not an IBSS */ @@ -322,12 +336,13 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, bitrates[rx_status->rate_idx].bitrate; rx_timestamp = rx_status->mactime + (24 * 8 * 10 / rate); - } else if (local && local->ops && local->ops->get_tsf) - /* second best option: get current TSF */ - rx_timestamp = local->ops->get_tsf(local_to_hw(local)); - else - /* can't merge without knowing the TSF */ - rx_timestamp = -1LLU; + } else { + /* + * second best option: get current TSF + * (will return -1 if not supported) + */ + rx_timestamp = drv_get_tsf(local); + } #ifdef CONFIG_MAC80211_IBSS_DEBUG printk(KERN_DEBUG "RX beacon SA=%pM BSSID=" @@ -369,13 +384,14 @@ struct sta_info *ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; int band = local->hw.conf.channel->band; - /* TODO: Could consider removing the least recently used entry and - * allow new one to be added. */ + /* + * XXX: Consider removing the least recently used entry and + * allow new one to be added. + */ if (local->num_sta >= IEEE80211_IBSS_MAX_STA_ENTRIES) { - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: No room for a new IBSS STA " - "entry %pM\n", sdata->dev->name, addr); - } + if (net_ratelimit()) + printk(KERN_DEBUG "%s: No room for a new IBSS STA entry %pM\n", + sdata->dev->name, addr); return NULL; } @@ -432,41 +448,33 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - mod_timer(&ifibss->timer, jiffies + IEEE80211_IBSS_MERGE_INTERVAL); + mod_timer(&ifibss->timer, + round_jiffies(jiffies + IEEE80211_IBSS_MERGE_INTERVAL)); ieee80211_sta_expire(sdata, IEEE80211_IBSS_INACTIVITY_LIMIT); + if (ieee80211_sta_active_ibss(sdata)) return; - if ((ifibss->flags & IEEE80211_IBSS_BSSID_SET) && - (!(ifibss->flags & IEEE80211_IBSS_AUTO_CHANNEL_SEL))) + if (ifibss->fixed_channel) return; printk(KERN_DEBUG "%s: No active IBSS STAs - trying to scan for other " "IBSS networks with same SSID (merge)\n", sdata->dev->name); - /* XXX maybe racy? */ - if (sdata->local->scan_req) - return; - - memcpy(sdata->local->int_scan_req.ssids[0].ssid, - ifibss->ssid, IEEE80211_MAX_SSID_LEN); - sdata->local->int_scan_req.ssids[0].ssid_len = ifibss->ssid_len; - ieee80211_request_scan(sdata, &sdata->local->int_scan_req); + ieee80211_request_internal_scan(sdata, ifibss->ssid, ifibss->ssid_len); } -static int ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) +static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; - u8 *pos; u8 bssid[ETH_ALEN]; - u8 supp_rates[IEEE80211_MAX_SUPP_RATES]; u16 capability; int i; - if (ifibss->flags & IEEE80211_IBSS_BSSID_SET) { + if (ifibss->fixed_bssid) { memcpy(bssid, ifibss->bssid, ETH_ALEN); } else { /* Generate random, not broadcast, locally administered BSSID. Mix in @@ -482,10 +490,7 @@ static int ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) printk(KERN_DEBUG "%s: Creating new IBSS network, BSSID %pM\n", sdata->dev->name, bssid); - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - - if (local->hw.conf.beacon_int == 0) - local->hw.conf.beacon_int = 100; + sband = local->hw.wiphy->bands[ifibss->channel->band]; capability = WLAN_CAPABILITY_IBSS; @@ -494,29 +499,20 @@ static int ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) else sdata->drop_unencrypted = 0; - pos = supp_rates; - for (i = 0; i < sband->n_bitrates; i++) { - int rate = sband->bitrates[i].bitrate; - *pos++ = (u8) (rate / 5); - } - - return __ieee80211_sta_join_ibss(sdata, - bssid, local->hw.conf.beacon_int, - local->hw.conf.channel->center_freq, - sband->n_bitrates, supp_rates, - capability, 0); + __ieee80211_sta_join_ibss(sdata, bssid, sdata->vif.bss_conf.beacon_int, + ifibss->channel, 3, /* first two are basic */ + capability, 0); } -static int ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) +static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_local *local = sdata->local; struct ieee80211_bss *bss; + struct ieee80211_channel *chan = NULL; const u8 *bssid = NULL; int active_ibss; - - if (ifibss->ssid_len == 0) - return -EINVAL; + u16 capability; active_ibss = ieee80211_sta_active_ibss(sdata); #ifdef CONFIG_MAC80211_IBSS_DEBUG @@ -525,14 +521,23 @@ static int ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) #endif /* CONFIG_MAC80211_IBSS_DEBUG */ if (active_ibss) - return 0; + return; - if (ifibss->flags & IEEE80211_IBSS_BSSID_SET) + capability = WLAN_CAPABILITY_IBSS; + if (sdata->default_key) + capability |= WLAN_CAPABILITY_PRIVACY; + + if (ifibss->fixed_bssid) bssid = ifibss->bssid; - bss = (void *)cfg80211_get_bss(local->hw.wiphy, NULL, bssid, + if (ifibss->fixed_channel) + chan = ifibss->channel; + if (!is_zero_ether_addr(ifibss->bssid)) + bssid = ifibss->bssid; + bss = (void *)cfg80211_get_bss(local->hw.wiphy, chan, bssid, ifibss->ssid, ifibss->ssid_len, - WLAN_CAPABILITY_IBSS, - WLAN_CAPABILITY_IBSS); + WLAN_CAPABILITY_IBSS | + WLAN_CAPABILITY_PRIVACY, + capability); #ifdef CONFIG_MAC80211_IBSS_DEBUG if (bss) @@ -540,18 +545,14 @@ static int ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) "%pM\n", bss->cbss.bssid, ifibss->bssid); #endif /* CONFIG_MAC80211_IBSS_DEBUG */ - if (bss && - (!(ifibss->flags & IEEE80211_IBSS_PREV_BSSID_SET) || - memcmp(ifibss->bssid, bss->cbss.bssid, ETH_ALEN))) { - int ret; - + 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); - ret = ieee80211_sta_join_ibss(sdata, bss); + ieee80211_sta_join_ibss(sdata, bss); ieee80211_rx_bss_put(local, bss); - return ret; + return; } else if (bss) ieee80211_rx_bss_put(local, bss); @@ -562,29 +563,24 @@ static int ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) /* Selected IBSS not found in current scan results - try to scan */ if (ifibss->state == IEEE80211_IBSS_MLME_JOINED && !ieee80211_sta_active_ibss(sdata)) { - mod_timer(&ifibss->timer, jiffies + - IEEE80211_IBSS_MERGE_INTERVAL); - } else if (time_after(jiffies, local->last_scan_completed + + mod_timer(&ifibss->timer, + round_jiffies(jiffies + IEEE80211_IBSS_MERGE_INTERVAL)); + } else if (time_after(jiffies, ifibss->last_scan_completed + IEEE80211_SCAN_INTERVAL)) { printk(KERN_DEBUG "%s: Trigger new scan to find an IBSS to " "join\n", sdata->dev->name); - /* XXX maybe racy? */ - if (local->scan_req) - return -EBUSY; - - memcpy(local->int_scan_req.ssids[0].ssid, - ifibss->ssid, IEEE80211_MAX_SSID_LEN); - local->int_scan_req.ssids[0].ssid_len = ifibss->ssid_len; - return ieee80211_request_scan(sdata, &local->int_scan_req); + ieee80211_request_internal_scan(sdata, ifibss->ssid, + ifibss->ssid_len); } else if (ifibss->state != IEEE80211_IBSS_MLME_JOINED) { int interval = IEEE80211_SCAN_INTERVAL; if (time_after(jiffies, ifibss->ibss_join_req + IEEE80211_IBSS_JOIN_TIMEOUT)) { - if (!(local->oper_channel->flags & - IEEE80211_CHAN_NO_IBSS)) - return ieee80211_sta_create_ibss(sdata); + if (!(local->oper_channel->flags & IEEE80211_CHAN_NO_IBSS)) { + ieee80211_sta_create_ibss(sdata); + return; + } printk(KERN_DEBUG "%s: IBSS not allowed on" " %d MHz\n", sdata->dev->name, local->hw.conf.channel->center_freq); @@ -595,11 +591,9 @@ static int ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) } ifibss->state = IEEE80211_IBSS_MLME_SEARCH; - mod_timer(&ifibss->timer, jiffies + interval); - return 0; + mod_timer(&ifibss->timer, + round_jiffies(jiffies + interval)); } - - return 0; } static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, @@ -614,13 +608,10 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, u8 *pos, *end; if (ifibss->state != IEEE80211_IBSS_MLME_JOINED || - len < 24 + 2 || !ifibss->probe_resp) + len < 24 + 2 || !ifibss->presp) return; - if (local->ops->tx_last_beacon) - tx_last_beacon = local->ops->tx_last_beacon(local_to_hw(local)); - else - tx_last_beacon = 1; + tx_last_beacon = drv_tx_last_beacon(local); #ifdef CONFIG_MAC80211_IBSS_DEBUG printk(KERN_DEBUG "%s: RX ProbeReq SA=%pM DA=%pM BSSID=%pM" @@ -649,13 +640,13 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, } if (pos[1] != 0 && (pos[1] != ifibss->ssid_len || - memcmp(pos + 2, ifibss->ssid, ifibss->ssid_len) != 0)) { + !memcmp(pos + 2, ifibss->ssid, ifibss->ssid_len))) { /* Ignore ProbeReq for foreign SSID */ return; } /* Reply with ProbeResp */ - skb = skb_copy(ifibss->probe_resp, GFP_KERNEL); + skb = skb_copy(ifibss->presp, GFP_KERNEL); if (!skb) return; @@ -746,6 +737,9 @@ static void ieee80211_ibss_work(struct work_struct *work) struct ieee80211_if_ibss *ifibss; struct sk_buff *skb; + if (WARN_ON(local->suspended)) + return; + if (!netif_running(sdata->dev)) return; @@ -782,101 +776,63 @@ static void ieee80211_ibss_timer(unsigned long data) struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_local *local = sdata->local; + if (local->quiescing) { + ifibss->timer_running = true; + return; + } + set_bit(IEEE80211_IBSS_REQ_RUN, &ifibss->request); queue_work(local->hw.workqueue, &ifibss->work); } -void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata) +#ifdef CONFIG_PM +void ieee80211_ibss_quiesce(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - INIT_WORK(&ifibss->work, ieee80211_ibss_work); - setup_timer(&ifibss->timer, ieee80211_ibss_timer, - (unsigned long) sdata); - skb_queue_head_init(&ifibss->skb_queue); - - ifibss->flags |= IEEE80211_IBSS_AUTO_BSSID_SEL | - IEEE80211_IBSS_AUTO_CHANNEL_SEL; + cancel_work_sync(&ifibss->work); + if (del_timer_sync(&ifibss->timer)) + ifibss->timer_running = true; } -int ieee80211_ibss_commit(struct ieee80211_sub_if_data *sdata) +void ieee80211_ibss_restart(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - ifibss->flags &= ~IEEE80211_IBSS_PREV_BSSID_SET; - - if (ifibss->ssid_len) - ifibss->flags |= IEEE80211_IBSS_SSID_SET; - else - ifibss->flags &= ~IEEE80211_IBSS_SSID_SET; - - ifibss->ibss_join_req = jiffies; - ifibss->state = IEEE80211_IBSS_MLME_SEARCH; - set_bit(IEEE80211_IBSS_REQ_RUN, &ifibss->request); - - return 0; -} - -int ieee80211_ibss_set_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size_t len) -{ - struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - - if (len > IEEE80211_MAX_SSID_LEN) - return -EINVAL; - - if (ifibss->ssid_len != len || memcmp(ifibss->ssid, ssid, len) != 0) { - memset(ifibss->ssid, 0, sizeof(ifibss->ssid)); - memcpy(ifibss->ssid, ssid, len); - ifibss->ssid_len = len; + if (ifibss->timer_running) { + add_timer(&ifibss->timer); + ifibss->timer_running = false; } - - return ieee80211_ibss_commit(sdata); -} - -int ieee80211_ibss_get_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size_t *len) -{ - struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - - memcpy(ssid, ifibss->ssid, ifibss->ssid_len); - *len = ifibss->ssid_len; - - return 0; } +#endif -int ieee80211_ibss_set_bssid(struct ieee80211_sub_if_data *sdata, u8 *bssid) +void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - if (is_valid_ether_addr(bssid)) { - memcpy(ifibss->bssid, bssid, ETH_ALEN); - ifibss->flags |= IEEE80211_IBSS_BSSID_SET; - } else { - memset(ifibss->bssid, 0, ETH_ALEN); - ifibss->flags &= ~IEEE80211_IBSS_BSSID_SET; - } - - if (netif_running(sdata->dev)) { - if (ieee80211_if_config(sdata, IEEE80211_IFCC_BSSID)) { - printk(KERN_DEBUG "%s: Failed to config new BSSID to " - "the low-level driver\n", sdata->dev->name); - } - } - - return ieee80211_ibss_commit(sdata); + INIT_WORK(&ifibss->work, ieee80211_ibss_work); + setup_timer(&ifibss->timer, ieee80211_ibss_timer, + (unsigned long) sdata); + skb_queue_head_init(&ifibss->skb_queue); } /* scan finished notification */ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local) { - struct ieee80211_sub_if_data *sdata = local->scan_sdata; - struct ieee80211_if_ibss *ifibss; - - if (sdata && sdata->vif.type == NL80211_IFTYPE_ADHOC) { - ifibss = &sdata->u.ibss; - if ((!(ifibss->flags & IEEE80211_IBSS_PREV_BSSID_SET)) || - !ieee80211_sta_active_ibss(sdata)) - ieee80211_sta_find_ibss(sdata); + struct ieee80211_sub_if_data *sdata; + + 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_ADHOC) + continue; + if (!sdata->u.ibss.ssid_len) + continue; + sdata->u.ibss.last_scan_completed = jiffies; + ieee80211_sta_find_ibss(sdata); } + mutex_unlock(&local->iflist_mtx); } ieee80211_rx_result @@ -906,3 +862,86 @@ ieee80211_ibss_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, return RX_DROP_MONITOR; } + +int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, + struct cfg80211_ibss_params *params) +{ + struct sk_buff *skb; + + if (params->bssid) { + memcpy(sdata->u.ibss.bssid, params->bssid, ETH_ALEN); + sdata->u.ibss.fixed_bssid = true; + } else + sdata->u.ibss.fixed_bssid = false; + + sdata->vif.bss_conf.beacon_int = params->beacon_interval; + + sdata->u.ibss.channel = params->channel; + sdata->u.ibss.fixed_channel = params->channel_fixed; + + if (params->ie) { + sdata->u.ibss.ie = kmemdup(params->ie, params->ie_len, + GFP_KERNEL); + if (sdata->u.ibss.ie) + sdata->u.ibss.ie_len = params->ie_len; + } + + skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + + 36 /* bitrates */ + + 34 /* SSID */ + + 3 /* DS params */ + + 4 /* IBSS params */ + + params->ie_len); + if (!skb) + return -ENOMEM; + + sdata->u.ibss.skb = skb; + sdata->u.ibss.state = IEEE80211_IBSS_MLME_SEARCH; + sdata->u.ibss.ibss_join_req = jiffies; + + memcpy(sdata->u.ibss.ssid, params->ssid, IEEE80211_MAX_SSID_LEN); + + /* + * The ssid_len setting below is used to see whether + * we are active, and we need all other settings + * before that may get visible. + */ + mb(); + + sdata->u.ibss.ssid_len = params->ssid_len; + + 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); + + return 0; +} + +int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) +{ + struct sk_buff *skb; + + del_timer_sync(&sdata->u.ibss.timer); + clear_bit(IEEE80211_IBSS_REQ_RUN, &sdata->u.ibss.request); + cancel_work_sync(&sdata->u.ibss.work); + clear_bit(IEEE80211_IBSS_REQ_RUN, &sdata->u.ibss.request); + + sta_info_flush(sdata->local, sdata); + + /* remove beacon */ + kfree(sdata->u.ibss.ie); + skb = sdata->u.ibss.presp; + rcu_assign_pointer(sdata->u.ibss.presp, NULL); + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); + synchronize_rcu(); + kfree_skb(skb); + + skb_queue_purge(&sdata->u.ibss.skb_queue); + memset(sdata->u.ibss.bssid, 0, ETH_ALEN); + sdata->u.ibss.ssid_len = 0; + + ieee80211_recalc_idle(sdata->local); + + return 0; +} diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index e6ed78cb16b..68eb5052179 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/wireless.h> #include <net/iw_handler.h> #include <net/mac80211.h> #include "key.h" @@ -236,7 +235,7 @@ struct mesh_preq_queue { #define IEEE80211_STA_ASSOCIATED BIT(4) #define IEEE80211_STA_PROBEREQ_POLL BIT(5) #define IEEE80211_STA_CREATE_IBSS BIT(6) -/* hole at 7, please re-use */ +#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) @@ -249,9 +248,8 @@ struct mesh_preq_queue { #define IEEE80211_STA_EXT_SME BIT(17) /* flags for MLME request */ #define IEEE80211_STA_REQ_SCAN 0 -#define IEEE80211_STA_REQ_DIRECT_PROBE 1 -#define IEEE80211_STA_REQ_AUTH 2 -#define IEEE80211_STA_REQ_RUN 3 +#define IEEE80211_STA_REQ_AUTH 1 +#define IEEE80211_STA_REQ_RUN 2 /* bitfield of allowed auth algs */ #define IEEE80211_AUTH_ALG_OPEN BIT(0) @@ -295,6 +293,9 @@ struct ieee80211_if_managed { 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; @@ -306,6 +307,8 @@ struct ieee80211_if_managed { int auth_alg; /* currently used IEEE 802.11 authentication algorithm */ int auth_transaction; + u32 beacon_crc; + enum { IEEE80211_MFP_DISABLED, IEEE80211_MFP_OPTIONAL, @@ -319,14 +322,6 @@ struct ieee80211_if_managed { size_t sme_auth_ie_len; }; -enum ieee80211_ibss_flags { - IEEE80211_IBSS_AUTO_CHANNEL_SEL = BIT(0), - IEEE80211_IBSS_AUTO_BSSID_SEL = BIT(1), - IEEE80211_IBSS_BSSID_SET = BIT(2), - IEEE80211_IBSS_PREV_BSSID_SET = BIT(3), - IEEE80211_IBSS_SSID_SET = BIT(4), -}; - enum ieee80211_ibss_request { IEEE80211_IBSS_REQ_RUN = 0, }; @@ -337,17 +332,23 @@ struct ieee80211_if_ibss { struct sk_buff_head skb_queue; - u8 ssid[IEEE80211_MAX_SSID_LEN]; - u8 ssid_len; + unsigned long request; + unsigned long last_scan_completed; - u32 flags; + bool timer_running; - u8 bssid[ETH_ALEN]; + bool fixed_bssid; + bool fixed_channel; - unsigned long request; + u8 bssid[ETH_ALEN]; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len, ie_len; + u8 *ie; + struct ieee80211_channel *channel; unsigned long ibss_join_req; - struct sk_buff *probe_resp; /* ProbeResp template for IBSS */ + /* probe response/beacon for IBSS */ + struct sk_buff *presp, *skb; enum { IEEE80211_IBSS_MLME_SEARCH, @@ -361,6 +362,8 @@ struct ieee80211_if_mesh { struct timer_list mesh_path_timer; struct sk_buff_head skb_queue; + unsigned long timers_running; + bool housekeeping; u8 mesh_id[IEEE80211_MAX_MESH_ID_LEN]; @@ -430,6 +433,12 @@ struct ieee80211_sub_if_data { int drop_unencrypted; + /* + * keep track of whether the HT opmode (stored in + * vif.bss_info.ht_operation_mode) is valid. + */ + bool ht_opmode_valid; + /* Fragment table for host-based reassembly */ struct ieee80211_fragment_entry fragments[IEEE80211_FRAGMENT_MAX]; unsigned int fragment_next; @@ -580,6 +589,7 @@ enum queue_stop_reason { 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 { @@ -606,6 +616,21 @@ struct ieee80211_local { unsigned int filter_flags; /* FIF_* */ struct iw_statistics wstats; bool tim_in_locked_section; /* see ieee80211_beacon_get() */ + + /* + * suspended is true if we finished all the suspend _and_ we have + * not yet come up from resume. This is to be used by mac80211 + * to ensure driver sanity during suspend and mac80211's own + * sanity. It can eventually be used for WoW as well. + */ + bool suspended; + + /* + * quiescing is true during the suspend process _only_ to + * ease timer cancelling etc. + */ + bool quiescing; + int tx_headroom; /* required headroom for hardware/radiotap */ /* Tasklet and skb queue to process calls from IRQ mode. All frames @@ -626,8 +651,6 @@ struct ieee80211_local { spinlock_t sta_lock; unsigned long num_sta; struct list_head sta_list; - struct list_head sta_flush_list; - struct work_struct sta_flush_work; struct sta_info *sta_hash[STA_HASH_SIZE]; struct timer_list sta_cleanup; @@ -647,9 +670,6 @@ struct ieee80211_local { struct rate_control_ref *rate_ctrl; - int rts_threshold; - int fragmentation_threshold; - struct crypto_blkcipher *wep_tx_tfm; struct crypto_blkcipher *wep_rx_tfm; u32 wep_iv; @@ -666,15 +686,18 @@ struct ieee80211_local { /* Scanning and BSS list */ + struct mutex scan_mtx; bool sw_scanning, hw_scanning; struct cfg80211_ssid scan_ssid; struct cfg80211_scan_request int_scan_req; struct cfg80211_scan_request *scan_req; struct ieee80211_channel *scan_channel; + const u8 *orig_ies; + int orig_ies_len; int scan_channel_idx; + int scan_ies_len; enum { SCAN_SET_CHANNEL, SCAN_SEND_PROBE } scan_state; - unsigned long last_scan_completed; struct delayed_work scan_work; struct ieee80211_sub_if_data *scan_sdata; enum nl80211_channel_type oper_channel_type; @@ -736,28 +759,33 @@ struct ieee80211_local { int wifi_wme_noack_test; unsigned int wmm_acm; /* bit field of ACM bits (BIT(802.1D tag)) */ - bool powersave; bool pspolling; + /* + * PS can only be enabled when we have exactly one managed + * interface (and monitors) in PS, this then points there. + */ + struct ieee80211_sub_if_data *ps_sdata; struct work_struct dynamic_ps_enable_work; struct work_struct dynamic_ps_disable_work; struct timer_list dynamic_ps_timer; + struct notifier_block network_latency_notifier; int user_power_level; /* in dBm */ int power_constr_level; /* in dBm */ + struct work_struct restart_work; + #ifdef CONFIG_MAC80211_DEBUGFS struct local_debugfsdentries { struct dentry *rcdir; struct dentry *rcname; struct dentry *frequency; - struct dentry *rts_threshold; - struct dentry *fragmentation_threshold; - struct dentry *short_retry_limit; - struct dentry *long_retry_limit; struct dentry *total_ps_buffered; struct dentry *wep_iv; struct dentry *tsf; + struct dentry *queues; struct dentry *reset; + struct dentry *noack; struct dentry *statistics; struct local_debugfsdentries_statsdentries { struct dentry *transmitted_fragment_count; @@ -830,7 +858,7 @@ struct ieee802_11_elems { u8 *fh_params; u8 *ds_params; u8 *cf_params; - u8 *tim; + struct ieee80211_tim_ie *tim; u8 *ibss_params; u8 *challenge; u8 *wpa; @@ -903,7 +931,6 @@ static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr) int ieee80211_hw_config(struct ieee80211_local *local, u32 changed); -int ieee80211_if_config(struct ieee80211_sub_if_data *sdata, u32 changed); void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx); void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, u32 changed); @@ -927,12 +954,16 @@ int ieee80211_sta_deauthenticate(struct ieee80211_sub_if_data *sdata, u16 reason int ieee80211_sta_disassociate(struct ieee80211_sub_if_data *sdata, u16 reason); void ieee80211_send_pspoll(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); +void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency); +int ieee80211_max_network_latency(struct notifier_block *nb, + unsigned long data, void *dummy); +void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel_sw_ie *sw_elem, + struct ieee80211_bss *bss); +void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata); +void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata); /* IBSS code */ -int ieee80211_ibss_commit(struct ieee80211_sub_if_data *sdata); -int ieee80211_ibss_set_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size_t len); -int ieee80211_ibss_get_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size_t *len); -int ieee80211_ibss_set_bssid(struct ieee80211_sub_if_data *sdata, u8 *bssid); void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local); void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata); ieee80211_rx_result @@ -940,14 +971,22 @@ ieee80211_ibss_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct ieee80211_rx_status *rx_status); 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, + struct cfg80211_ibss_params *params); +int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata); +void ieee80211_ibss_quiesce(struct ieee80211_sub_if_data *sdata); +void ieee80211_ibss_restart(struct ieee80211_sub_if_data *sdata); /* scan/BSS handling */ void ieee80211_scan_work(struct work_struct *work); +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, @@ -956,9 +995,6 @@ int ieee80211_sta_set_extra_ie(struct ieee80211_sub_if_data *sdata, const char *ie, size_t len); void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local); -void ieee80211_scan_failed(struct ieee80211_local *local); -int ieee80211_start_scan(struct ieee80211_sub_if_data *scan_sdata, - struct cfg80211_scan_request *req); struct ieee80211_bss * ieee80211_bss_info_update(struct ieee80211_local *local, struct ieee80211_rx_status *rx_status, @@ -983,6 +1019,8 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype type); void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata); void ieee80211_remove_interfaces(struct ieee80211_local *local); +u32 __ieee80211_recalc_idle(struct ieee80211_local *local); +void ieee80211_recalc_idle(struct ieee80211_local *local); /* tx handling */ void ieee80211_clear_tx_pending(struct ieee80211_local *local); @@ -995,9 +1033,6 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_supported_band *sband, struct ieee80211_ht_cap *ht_cap_ie, struct ieee80211_sta_ht_cap *ht_cap); -u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, - struct ieee80211_ht_info *hti, - u16 ap_ht_cap_flags); void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u16 ssn); void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata, const u8 *da, u16 tid, @@ -1027,24 +1062,23 @@ int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len); -void ieee80211_chswitch_timer(unsigned long data); -void ieee80211_chswitch_work(struct work_struct *work); -void ieee80211_process_chanswitch(struct ieee80211_sub_if_data *sdata, - struct ieee80211_channel_sw_ie *sw_elem, - struct ieee80211_bss *bss); -void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, - u16 capab_info, u8 *pwr_constr_elem, - u8 pwr_constr_elem_len); - -/* Suspend/resume */ + +/* Suspend/resume and hw reconfiguration */ +int ieee80211_reconfig(struct ieee80211_local *local); + #ifdef CONFIG_PM int __ieee80211_suspend(struct ieee80211_hw *hw); -int __ieee80211_resume(struct ieee80211_hw *hw); + +static inline int __ieee80211_resume(struct ieee80211_hw *hw) +{ + return ieee80211_reconfig(hw_to_local(hw)); +} #else static inline int __ieee80211_suspend(struct ieee80211_hw *hw) { return 0; } + static inline int __ieee80211_resume(struct ieee80211_hw *hw) { return 0; @@ -1053,20 +1087,20 @@ static inline int __ieee80211_resume(struct ieee80211_hw *hw) /* utility functions/constants */ extern void *mac80211_wiphy_privid; /* for wiphy privid */ -extern const unsigned char rfc1042_header[6]; -extern const unsigned char bridge_tunnel_header[6]; u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, enum nl80211_iftype type); 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); + struct ieee80211_hdr *hdr, const u8 *tsc); 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); void ieee802_11_parse_elems(u8 *start, size_t len, struct ieee802_11_elems *elems); -int ieee80211_set_freq(struct ieee80211_sub_if_data *sdata, int freq); +u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, + struct ieee802_11_elems *elems, + u64 filter, u32 crc); u32 ieee80211_mandatory_rates(struct ieee80211_local *local, enum ieee80211_band band); @@ -1088,14 +1122,20 @@ void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason); void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason); +void ieee80211_add_pending_skb(struct ieee80211_local *local, + struct sk_buff *skb); +int ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs); 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); +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, - u8 *ssid, size_t ssid_len, - u8 *ie, size_t ie_len); + const u8 *ssid, size_t ssid_len, + const u8 *ie, size_t ie_len); void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, const size_t supp_rates_len, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 91e8e1bacaa..b7c8a448429 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -20,6 +20,7 @@ #include "debugfs_netdev.h" #include "mesh.h" #include "led.h" +#include "driver-ops.h" /** * DOC: Interface list locking @@ -164,14 +165,12 @@ static int ieee80211_open(struct net_device *dev) } if (local->open_count == 0) { - res = 0; - if (local->ops->start) - res = local->ops->start(local_to_hw(local)); + res = drv_start(local); if (res) goto err_del_bss; /* we're brought up, everything changes */ hw_reconf_flags = ~0; - ieee80211_led_radio(local, local->hw.conf.radio_enabled); + ieee80211_led_radio(local, true); } /* @@ -199,8 +198,8 @@ static int ieee80211_open(struct net_device *dev) * Validate the MAC address for this device. */ if (!is_valid_ether_addr(dev->dev_addr)) { - if (!local->open_count && local->ops->stop) - local->ops->stop(local_to_hw(local)); + if (!local->open_count) + drv_stop(local); return -EADDRNOTAVAIL; } @@ -235,17 +234,13 @@ static int ieee80211_open(struct net_device *dev) netif_addr_unlock_bh(local->mdev); break; case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_ADHOC: - if (sdata->vif.type == NL80211_IFTYPE_STATION) - sdata->u.mgd.flags &= ~IEEE80211_STA_PREV_BSSID_SET; - else - sdata->u.ibss.flags &= ~IEEE80211_IBSS_PREV_BSSID_SET; + sdata->u.mgd.flags &= ~IEEE80211_STA_PREV_BSSID_SET; /* fall through */ default: conf.vif = &sdata->vif; conf.type = sdata->vif.type; conf.mac_addr = dev->dev_addr; - res = local->ops->add_interface(local_to_hw(local), &conf); + res = drv_add_interface(local, &conf); if (res) goto err_stop; @@ -306,6 +301,8 @@ static int ieee80211_open(struct net_device *dev) if (sdata->flags & IEEE80211_SDATA_PROMISC) atomic_inc(&local->iff_promiscs); + hw_reconf_flags |= __ieee80211_recalc_idle(local); + local->open_count++; if (hw_reconf_flags) { ieee80211_hw_config(local, hw_reconf_flags); @@ -317,6 +314,8 @@ static int ieee80211_open(struct net_device *dev) ieee80211_set_wmm_default(sdata); } + ieee80211_recalc_ps(local, -1); + /* * ieee80211_sta_work is disabled while network interface * is down. Therefore, some configuration changes may not @@ -325,17 +324,15 @@ static int ieee80211_open(struct net_device *dev) */ if (sdata->vif.type == NL80211_IFTYPE_STATION) queue_work(local->hw.workqueue, &sdata->u.mgd.work); - else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - queue_work(local->hw.workqueue, &sdata->u.ibss.work); netif_tx_start_all_queues(dev); return 0; err_del_interface: - local->ops->remove_interface(local_to_hw(local), &conf); + drv_remove_interface(local, &conf); err_stop: - if (!local->open_count && local->ops->stop) - local->ops->stop(local_to_hw(local)); + if (!local->open_count) + drv_stop(local); err_del_bss: sdata->bss = NULL; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) @@ -497,7 +494,6 @@ static int ieee80211_stop(struct net_device *dev) /* fall through */ case NL80211_IFTYPE_ADHOC: if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { - memset(sdata->u.ibss.bssid, 0, ETH_ALEN); del_timer_sync(&sdata->u.ibss.timer); cancel_work_sync(&sdata->u.ibss.work); synchronize_rcu(); @@ -549,19 +545,22 @@ static int ieee80211_stop(struct net_device *dev) conf.mac_addr = dev->dev_addr; /* disable all keys for as long as this netdev is down */ ieee80211_disable_keys(sdata); - local->ops->remove_interface(local_to_hw(local), &conf); + drv_remove_interface(local, &conf); } sdata->bss = NULL; + hw_reconf_flags |= __ieee80211_recalc_idle(local); + + ieee80211_recalc_ps(local, -1); + if (local->open_count == 0) { if (netif_running(local->mdev)) dev_close(local->mdev); - if (local->ops->stop) - local->ops->stop(local_to_hw(local)); + drv_stop(local); - ieee80211_led_radio(local, 0); + ieee80211_led_radio(local, false); flush_workqueue(local->hw.workqueue); @@ -649,7 +648,8 @@ static void ieee80211_teardown_sdata(struct net_device *dev) mesh_rmc_free(sdata); break; case NL80211_IFTYPE_ADHOC: - kfree_skb(sdata->u.ibss.probe_resp); + if (WARN_ON(sdata->u.ibss.presp)) + kfree_skb(sdata->u.ibss.presp); break; case NL80211_IFTYPE_STATION: kfree(sdata->u.mgd.extra_ie); @@ -896,3 +896,74 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) unregister_netdevice(sdata->dev); } } + +static u32 ieee80211_idle_off(struct ieee80211_local *local, + const char *reason) +{ + if (!(local->hw.conf.flags & IEEE80211_CONF_IDLE)) + return 0; + +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG + printk(KERN_DEBUG "%s: device no longer idle - %s\n", + wiphy_name(local->hw.wiphy), reason); +#endif + + local->hw.conf.flags &= ~IEEE80211_CONF_IDLE; + return IEEE80211_CONF_CHANGE_IDLE; +} + +static u32 ieee80211_idle_on(struct ieee80211_local *local) +{ + if (local->hw.conf.flags & IEEE80211_CONF_IDLE) + return 0; + +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG + printk(KERN_DEBUG "%s: device now idle\n", + wiphy_name(local->hw.wiphy)); +#endif + + local->hw.conf.flags |= IEEE80211_CONF_IDLE; + return IEEE80211_CONF_CHANGE_IDLE; +} + +u32 __ieee80211_recalc_idle(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + int count = 0; + + if (local->hw_scanning || local->sw_scanning) + return ieee80211_idle_off(local, "scanning"); + + list_for_each_entry(sdata, &local->interfaces, list) { + if (!netif_running(sdata->dev)) + continue; + /* do not count disabled managed interfaces */ + if (sdata->vif.type == NL80211_IFTYPE_STATION && + sdata->u.mgd.state == IEEE80211_STA_MLME_DISABLED) + continue; + /* do not count unused IBSS interfaces */ + if (sdata->vif.type == NL80211_IFTYPE_ADHOC && + !sdata->u.ibss.ssid_len) + continue; + /* count everything else */ + count++; + } + + if (!count) + return ieee80211_idle_on(local); + else + return ieee80211_idle_off(local, "in use"); + + return 0; +} + +void ieee80211_recalc_idle(struct ieee80211_local *local) +{ + u32 chg; + + mutex_lock(&local->iflist_mtx); + chg = __ieee80211_recalc_idle(local); + mutex_unlock(&local->iflist_mtx); + if (chg) + ieee80211_hw_config(local, chg); +} diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 687acf23054..659a42d529e 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -16,6 +16,7 @@ #include <linux/rtnetlink.h> #include <net/mac80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "debugfs_key.h" #include "aes_ccm.h" #include "aes_cmac.h" @@ -66,6 +67,8 @@ static DECLARE_WORK(todo_work, key_todo); * * @key: key to add to do item for * @flag: todo flag(s) + * + * Must be called with IRQs or softirqs disabled. */ static void add_todo(struct ieee80211_key *key, u32 flag) { @@ -136,13 +139,12 @@ static void ieee80211_key_enable_hw_accel(struct ieee80211_key *key) struct ieee80211_sub_if_data, u.ap); - ret = key->local->ops->set_key(local_to_hw(key->local), SET_KEY, - &sdata->vif, sta, &key->conf); + ret = drv_set_key(key->local, SET_KEY, &sdata->vif, sta, &key->conf); if (!ret) { - spin_lock(&todo_lock); + spin_lock_bh(&todo_lock); key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; - spin_unlock(&todo_lock); + spin_unlock_bh(&todo_lock); } if (ret && ret != -ENOSPC && ret != -EOPNOTSUPP) @@ -164,12 +166,12 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) if (!key || !key->local->ops->set_key) return; - spin_lock(&todo_lock); + spin_lock_bh(&todo_lock); if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) { - spin_unlock(&todo_lock); + spin_unlock_bh(&todo_lock); return; } - spin_unlock(&todo_lock); + spin_unlock_bh(&todo_lock); sta = get_sta_for_key(key); sdata = key->sdata; @@ -179,8 +181,8 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) struct ieee80211_sub_if_data, u.ap); - ret = key->local->ops->set_key(local_to_hw(key->local), DISABLE_KEY, - &sdata->vif, sta, &key->conf); + ret = drv_set_key(key->local, DISABLE_KEY, &sdata->vif, + sta, &key->conf); if (ret) printk(KERN_ERR "mac80211-%s: failed to remove key " @@ -188,9 +190,9 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) wiphy_name(key->local->hw.wiphy), key->conf.keyidx, sta ? sta->addr : bcast_addr, ret); - spin_lock(&todo_lock); + spin_lock_bh(&todo_lock); key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; - spin_unlock(&todo_lock); + spin_unlock_bh(&todo_lock); } static void __ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, @@ -290,9 +292,11 @@ static void __ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct ieee80211_key *ieee80211_key_alloc(enum ieee80211_key_alg alg, int idx, size_t key_len, - const u8 *key_data) + const u8 *key_data, + size_t seq_len, const u8 *seq) { struct ieee80211_key *key; + int i, j; BUG_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS); @@ -318,14 +322,31 @@ struct ieee80211_key *ieee80211_key_alloc(enum ieee80211_key_alg alg, case ALG_TKIP: key->conf.iv_len = TKIP_IV_LEN; key->conf.icv_len = TKIP_ICV_LEN; + if (seq) { + for (i = 0; i < NUM_RX_DATA_QUEUES; i++) { + key->u.tkip.rx[i].iv32 = + get_unaligned_le32(&seq[2]); + key->u.tkip.rx[i].iv16 = + get_unaligned_le16(seq); + } + } break; case ALG_CCMP: key->conf.iv_len = CCMP_HDR_LEN; key->conf.icv_len = CCMP_MIC_LEN; + if (seq) { + for (i = 0; i < NUM_RX_DATA_QUEUES; i++) + for (j = 0; j < CCMP_PN_LEN; j++) + key->u.ccmp.rx_pn[i][j] = + seq[CCMP_PN_LEN - j - 1]; + } break; case ALG_AES_CMAC: key->conf.iv_len = 0; key->conf.icv_len = sizeof(struct ieee80211_mmie); + if (seq) + for (j = 0; j < 6; j++) + key->u.aes_cmac.rx_pn[j] = seq[6 - j - 1]; break; } memcpy(key->conf.key, key_data, key_len); @@ -418,14 +439,14 @@ void ieee80211_key_link(struct ieee80211_key *key, __ieee80211_key_replace(sdata, sta, old_key, key); - spin_unlock_irqrestore(&sdata->local->key_lock, flags); - /* free old key later */ add_todo(old_key, KEY_FLAG_TODO_DELETE); add_todo(key, KEY_FLAG_TODO_ADD_DEBUGFS); if (netif_running(sdata->dev)) add_todo(key, KEY_FLAG_TODO_HWACCEL_ADD); + + spin_unlock_irqrestore(&sdata->local->key_lock, flags); } static void __ieee80211_key_free(struct ieee80211_key *key) @@ -528,7 +549,7 @@ static void __ieee80211_key_todo(void) */ synchronize_rcu(); - spin_lock(&todo_lock); + spin_lock_bh(&todo_lock); while (!list_empty(&todo_list)) { key = list_first_entry(&todo_list, struct ieee80211_key, todo); list_del_init(&key->todo); @@ -539,7 +560,7 @@ static void __ieee80211_key_todo(void) KEY_FLAG_TODO_HWACCEL_REMOVE | KEY_FLAG_TODO_DELETE); key->flags &= ~todoflags; - spin_unlock(&todo_lock); + spin_unlock_bh(&todo_lock); work_done = false; @@ -572,9 +593,9 @@ static void __ieee80211_key_todo(void) WARN_ON(!work_done); - spin_lock(&todo_lock); + spin_lock_bh(&todo_lock); } - spin_unlock(&todo_lock); + spin_unlock_bh(&todo_lock); } void ieee80211_key_todo(void) diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 215d3ef42a4..9572e00f532 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -144,7 +144,8 @@ struct ieee80211_key { struct ieee80211_key *ieee80211_key_alloc(enum ieee80211_key_alg alg, int idx, size_t key_len, - const u8 *key_data); + const u8 *key_data, + size_t seq_len, const u8 *seq); /* * Insert a key into data structures (sdata, sta if necessary) * to make it used, free old key. diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 14134193cd1..092a017b237 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -21,10 +21,12 @@ #include <linux/wireless.h> #include <linux/rtnetlink.h> #include <linux/bitmap.h> +#include <linux/pm_qos_params.h> #include <net/net_namespace.h> #include <net/cfg80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "rate.h" #include "mesh.h" #include "wep.h" @@ -80,10 +82,9 @@ void ieee80211_configure_filter(struct ieee80211_local *local) /* be a bit nasty */ new_flags |= (1<<31); - local->ops->configure_filter(local_to_hw(local), - changed_flags, &new_flags, - local->mdev->mc_count, - local->mdev->mc_list); + drv_configure_filter(local, changed_flags, &new_flags, + local->mdev->mc_count, + local->mdev->mc_list); WARN_ON(new_flags & (1<<31)); @@ -151,93 +152,19 @@ static void ieee80211_master_set_multicast_list(struct net_device *dev) ieee80211_configure_filter(local); } -/* everything else */ - -int ieee80211_if_config(struct ieee80211_sub_if_data *sdata, u32 changed) -{ - struct ieee80211_local *local = sdata->local; - struct ieee80211_if_conf conf; - - if (WARN_ON(!netif_running(sdata->dev))) - return 0; - - memset(&conf, 0, sizeof(conf)); - - if (sdata->vif.type == NL80211_IFTYPE_STATION) - conf.bssid = sdata->u.mgd.bssid; - else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - conf.bssid = sdata->u.ibss.bssid; - else if (sdata->vif.type == NL80211_IFTYPE_AP) - conf.bssid = sdata->dev->dev_addr; - else if (ieee80211_vif_is_mesh(&sdata->vif)) { - static const u8 zero[ETH_ALEN] = { 0 }; - conf.bssid = zero; - } else { - WARN_ON(1); - return -EINVAL; - } - - if (!local->ops->config_interface) - return 0; - - switch (sdata->vif.type) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_MESH_POINT: - break; - default: - /* do not warn to simplify caller in scan.c */ - changed &= ~IEEE80211_IFCC_BEACON_ENABLED; - if (WARN_ON(changed & IEEE80211_IFCC_BEACON)) - return -EINVAL; - changed &= ~IEEE80211_IFCC_BEACON; - break; - } - - if (changed & IEEE80211_IFCC_BEACON_ENABLED) { - if (local->sw_scanning) { - conf.enable_beacon = false; - } else { - /* - * Beacon should be enabled, but AP mode must - * check whether there is a beacon configured. - */ - switch (sdata->vif.type) { - case NL80211_IFTYPE_AP: - conf.enable_beacon = - !!rcu_dereference(sdata->u.ap.beacon); - break; - case NL80211_IFTYPE_ADHOC: - conf.enable_beacon = !!sdata->u.ibss.probe_resp; - break; - case NL80211_IFTYPE_MESH_POINT: - conf.enable_beacon = true; - break; - default: - /* not reached */ - WARN_ON(1); - break; - } - } - } - - conf.changed = changed; - - return local->ops->config_interface(local_to_hw(local), - &sdata->vif, &conf); -} - int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) { - struct ieee80211_channel *chan; + struct ieee80211_channel *chan, *scan_chan; int ret = 0; int power; enum nl80211_channel_type channel_type; might_sleep(); - if (local->sw_scanning) { - chan = local->scan_channel; + scan_chan = local->scan_channel; + + if (scan_chan) { + chan = scan_chan; channel_type = NL80211_CHAN_NO_HT; } else { chan = local->oper_channel; @@ -251,7 +178,7 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) changed |= IEEE80211_CONF_CHANGE_CHANNEL; } - if (local->sw_scanning) + if (scan_chan) power = chan->max_power; else power = local->power_constr_level ? @@ -267,7 +194,7 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) } if (changed && local->open_count) { - ret = local->ops->config(local_to_hw(local), changed); + ret = drv_config(local, changed); /* * Goal: * HW reconfiguration should never fail, the driver has told @@ -292,18 +219,78 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, u32 changed) { struct ieee80211_local *local = sdata->local; + static const u8 zero[ETH_ALEN] = { 0 }; - if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) + if (!changed) return; - if (!changed) + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + /* + * While not associated, claim a BSSID of all-zeroes + * so that drivers don't do any weird things with the + * BSSID at that time. + */ + if (sdata->vif.bss_conf.assoc) + sdata->vif.bss_conf.bssid = sdata->u.mgd.bssid; + else + sdata->vif.bss_conf.bssid = zero; + } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) + sdata->vif.bss_conf.bssid = sdata->u.ibss.bssid; + else if (sdata->vif.type == NL80211_IFTYPE_AP) + sdata->vif.bss_conf.bssid = sdata->dev->dev_addr; + else if (ieee80211_vif_is_mesh(&sdata->vif)) { + sdata->vif.bss_conf.bssid = zero; + } else { + WARN_ON(1); return; + } + + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: + break; + default: + /* do not warn to simplify caller in scan.c */ + changed &= ~BSS_CHANGED_BEACON_ENABLED; + if (WARN_ON(changed & BSS_CHANGED_BEACON)) + return; + break; + } + + if (changed & BSS_CHANGED_BEACON_ENABLED) { + if (local->sw_scanning) { + sdata->vif.bss_conf.enable_beacon = false; + } else { + /* + * Beacon should be enabled, but AP mode must + * check whether there is a beacon configured. + */ + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP: + sdata->vif.bss_conf.enable_beacon = + !!rcu_dereference(sdata->u.ap.beacon); + break; + case NL80211_IFTYPE_ADHOC: + sdata->vif.bss_conf.enable_beacon = + !!rcu_dereference(sdata->u.ibss.presp); + break; + case NL80211_IFTYPE_MESH_POINT: + sdata->vif.bss_conf.enable_beacon = true; + break; + default: + /* not reached */ + WARN_ON(1); + break; + } + } + } + + drv_bss_info_changed(local, &sdata->vif, + &sdata->vif.bss_conf, changed); - if (local->ops->bss_info_changed) - local->ops->bss_info_changed(local_to_hw(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) @@ -382,60 +369,12 @@ static void ieee80211_tasklet_handler(unsigned long data) } } -/* Remove added headers (e.g., QoS control), encryption header/MIC, etc. to - * make a prepared TX frame (one that has been given to hw) to look like brand - * new IEEE 802.11 frame that is ready to go through TX processing again. - */ -static void ieee80211_remove_tx_extra(struct ieee80211_local *local, - struct ieee80211_key *key, - struct sk_buff *skb) -{ - unsigned int hdrlen, iv_len, mic_len; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - - hdrlen = ieee80211_hdrlen(hdr->frame_control); - - if (!key) - goto no_key; - - switch (key->conf.alg) { - case ALG_WEP: - iv_len = WEP_IV_LEN; - mic_len = WEP_ICV_LEN; - break; - case ALG_TKIP: - iv_len = TKIP_IV_LEN; - mic_len = TKIP_ICV_LEN; - break; - case ALG_CCMP: - iv_len = CCMP_HDR_LEN; - mic_len = CCMP_MIC_LEN; - break; - default: - goto no_key; - } - - if (skb->len >= hdrlen + mic_len && - !(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) - skb_trim(skb, skb->len - mic_len); - if (skb->len >= hdrlen + iv_len) { - memmove(skb->data + iv_len, skb->data, hdrlen); - hdr = (struct ieee80211_hdr *)skb_pull(skb, iv_len); - } - -no_key: - if (ieee80211_is_data_qos(hdr->frame_control)) { - hdr->frame_control &= ~cpu_to_le16(IEEE80211_STYPE_QOS_DATA); - memmove(skb->data + IEEE80211_QOS_CTL_LEN, skb->data, - hdrlen - IEEE80211_QOS_CTL_LEN); - skb_pull(skb, IEEE80211_QOS_CTL_LEN); - } -} - static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct sta_info *sta, struct sk_buff *skb) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + sta->tx_filtered_count++; /* @@ -477,16 +416,15 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, */ if (test_sta_flags(sta, WLAN_STA_PS) && skb_queue_len(&sta->tx_filtered) < STA_MAX_TX_BUFFER) { - ieee80211_remove_tx_extra(local, sta->key, skb); skb_queue_tail(&sta->tx_filtered, skb); return; } - if (!test_sta_flags(sta, WLAN_STA_PS) && !skb->requeue) { + if (!test_sta_flags(sta, WLAN_STA_PS) && + !(info->flags & IEEE80211_TX_INTFL_RETRIED)) { /* Software retry the packet once */ - skb->requeue = 1; - ieee80211_remove_tx_extra(local, sta->key, skb); - dev_queue_xmit(skb); + info->flags |= IEEE80211_TX_INTFL_RETRIED; + ieee80211_add_pending_skb(local, skb); return; } @@ -696,6 +634,28 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) } EXPORT_SYMBOL(ieee80211_tx_status); +static void ieee80211_restart_work(struct work_struct *work) +{ + struct ieee80211_local *local = + container_of(work, struct ieee80211_local, restart_work); + + rtnl_lock(); + ieee80211_reconfig(local); + rtnl_unlock(); +} + +void ieee80211_restart_hw(struct ieee80211_hw *hw) +{ + struct ieee80211_local *local = hw_to_local(hw); + + /* use this reason, __ieee80211_resume will unblock it */ + ieee80211_stop_queues_by_reason(hw, + IEEE80211_QUEUE_STOP_REASON_SUSPEND); + + schedule_work(&local->restart_work); +} +EXPORT_SYMBOL(ieee80211_restart_hw); + struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, const struct ieee80211_ops *ops) { @@ -718,9 +678,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, * +-------------------------+ * */ - priv_size = ((sizeof(struct ieee80211_local) + - NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST) + - priv_data_len; + priv_size = ALIGN(sizeof(*local), NETDEV_ALIGN) + priv_data_len; wiphy = wiphy_new(&mac80211_config_ops, priv_size); @@ -728,17 +686,16 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, return NULL; wiphy->privid = mac80211_wiphy_privid; - wiphy->max_scan_ssids = 4; + /* Yes, putting cfg80211_bss into ieee80211_bss is a hack */ wiphy->bss_priv_size = sizeof(struct ieee80211_bss) - sizeof(struct cfg80211_bss); local = wiphy_priv(wiphy); + local->hw.wiphy = wiphy; - local->hw.priv = (char *)local + - ((sizeof(struct ieee80211_local) + - NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST); + local->hw.priv = (char *)local + ALIGN(sizeof(*local), NETDEV_ALIGN); BUG_ON(!ops->tx); BUG_ON(!ops->start); @@ -752,15 +709,14 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, /* set up some defaults */ local->hw.queues = 1; local->hw.max_rates = 1; - local->rts_threshold = IEEE80211_MAX_RTS_THRESHOLD; - local->fragmentation_threshold = IEEE80211_MAX_FRAG_THRESHOLD; - local->hw.conf.long_frame_max_tx_count = 4; - local->hw.conf.short_frame_max_tx_count = 7; + 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); mutex_init(&local->iflist_mtx); + mutex_init(&local->scan_mtx); spin_lock_init(&local->key_lock); @@ -768,6 +724,8 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, INIT_DELAYED_WORK(&local->scan_work, ieee80211_scan_work); + INIT_WORK(&local->restart_work, ieee80211_restart_work); + INIT_WORK(&local->dynamic_ps_enable_work, ieee80211_dynamic_ps_enable_work); INIT_WORK(&local->dynamic_ps_disable_work, @@ -821,7 +779,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) enum ieee80211_band band; struct net_device *mdev; struct ieee80211_master_priv *mpriv; - int channels, i, j; + int channels, i, j, max_bitrates; + bool supp_ht; + static const u32 cipher_suites[] = { + WLAN_CIPHER_SUITE_WEP40, + WLAN_CIPHER_SUITE_WEP104, + WLAN_CIPHER_SUITE_TKIP, + WLAN_CIPHER_SUITE_CCMP, + + /* keep last -- depends on hw flags! */ + WLAN_CIPHER_SUITE_AES_CMAC + }; /* * generic code guarantees at least one band, @@ -829,18 +797,25 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) * that hw.conf.channel is assigned */ channels = 0; + max_bitrates = 0; + supp_ht = false; for (band = 0; band < IEEE80211_NUM_BANDS; band++) { struct ieee80211_supported_band *sband; sband = local->hw.wiphy->bands[band]; - if (sband && !local->oper_channel) { + if (!sband) + continue; + if (!local->oper_channel) { /* init channel we're on */ local->hw.conf.channel = - local->oper_channel = - local->scan_channel = &sband->channels[0]; + local->oper_channel = &sband->channels[0]; + local->hw.conf.channel_type = NL80211_CHAN_NO_HT; } - if (sband) - channels += sband->n_channels; + channels += sband->n_channels; + + if (max_bitrates < sband->n_bitrates) + max_bitrates = sband->n_bitrates; + supp_ht = supp_ht || sband->ht_cap.ht_supported; } local->int_scan_req.n_channels = channels; @@ -860,6 +835,37 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) else if (local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC) local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC; + /* + * Calculate scan IE length -- we need this to alloc + * memory and to subtract from the driver limit. It + * includes the (extended) supported rates and HT + * information -- SSID is the driver's responsibility. + */ + local->scan_ies_len = 4 + max_bitrates; /* (ext) supp rates */ + if (supp_ht) + local->scan_ies_len += 2 + sizeof(struct ieee80211_ht_cap); + + if (!local->ops->hw_scan) { + /* For hw_scan, driver needs to set these up. */ + local->hw.wiphy->max_scan_ssids = 4; + local->hw.wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN; + } + + /* + * If the driver supports any scan IEs, then assume the + * limit includes the IEs mac80211 will add, otherwise + * leave it at zero and let the driver sort it out; we + * still pass our IEs to the driver but userspace will + * not be allowed to in that case. + */ + if (local->hw.wiphy->max_scan_ie_len) + local->hw.wiphy->max_scan_ie_len -= local->scan_ies_len; + + local->hw.wiphy->cipher_suites = cipher_suites; + local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites); + if (!(local->hw.flags & IEEE80211_HW_MFP_CAPABLE)) + local->hw.wiphy->n_cipher_suites--; + result = wiphy_register(local->hw.wiphy); if (result < 0) goto fail_wiphy_register; @@ -898,9 +904,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) debugfs_hw_add(local); - if (local->hw.conf.beacon_int < 10) - local->hw.conf.beacon_int = 100; - if (local->hw.max_listen_interval == 0) local->hw.max_listen_interval = 1; @@ -965,25 +968,38 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } } + local->network_latency_notifier.notifier_call = + ieee80211_max_network_latency; + result = pm_qos_add_notifier(PM_QOS_NETWORK_LATENCY, + &local->network_latency_notifier); + + if (result) { + rtnl_lock(); + goto fail_pm_qos; + } + return 0; -fail_rate: + fail_pm_qos: + ieee80211_led_exit(local); + ieee80211_remove_interfaces(local); + fail_rate: unregister_netdevice(local->mdev); local->mdev = NULL; -fail_dev: + fail_dev: rtnl_unlock(); ieee80211_wep_free(local); -fail_wep: + fail_wep: sta_info_stop(local); -fail_sta_info: + fail_sta_info: debugfs_hw_del(local); destroy_workqueue(local->hw.workqueue); -fail_workqueue: + fail_workqueue: if (local->mdev) free_netdev(local->mdev); -fail_mdev_alloc: + fail_mdev_alloc: wiphy_unregister(local->hw.wiphy); -fail_wiphy_register: + fail_wiphy_register: kfree(local->int_scan_req.channels); return result; } @@ -996,6 +1012,9 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) tasklet_kill(&local->tx_pending_tasklet); tasklet_kill(&local->tasklet); + pm_qos_remove_notifier(PM_QOS_NETWORK_LATENCY, + &local->network_latency_notifier); + rtnl_lock(); /* @@ -1038,6 +1057,7 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) struct ieee80211_local *local = hw_to_local(hw); mutex_destroy(&local->iflist_mtx); + mutex_destroy(&local->scan_mtx); wiphy_free(local->hw.wiphy); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 9a3e5de0410..11cf45bce38 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -21,6 +21,9 @@ #define CAPAB_OFFSET 17 #define ACCEPT_PLINKS 0x80 +#define TMR_RUNNING_HK 0 +#define TMR_RUNNING_MP 1 + int mesh_allocated; static struct kmem_cache *rm_cache; @@ -45,6 +48,12 @@ static void ieee80211_mesh_housekeeping_timer(unsigned long data) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; ifmsh->housekeeping = true; + + if (local->quiescing) { + set_bit(TMR_RUNNING_HK, &ifmsh->timers_running); + return; + } + queue_work(local->hw.workqueue, &ifmsh->work); } @@ -343,6 +352,11 @@ static void ieee80211_mesh_path_timer(unsigned long data) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_local *local = sdata->local; + if (local->quiescing) { + set_bit(TMR_RUNNING_MP, &ifmsh->timers_running); + return; + } + queue_work(local->hw.workqueue, &ifmsh->work); } @@ -417,13 +431,39 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata, free_plinks = mesh_plink_availables(sdata); if (free_plinks != sdata->u.mesh.accepting_plinks) - ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON); + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); ifmsh->housekeeping = false; mod_timer(&ifmsh->housekeeping_timer, round_jiffies(jiffies + IEEE80211_MESH_HOUSEKEEPING_INTERVAL)); } +#ifdef CONFIG_PM +void ieee80211_mesh_quiesce(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + + /* might restart the timer but that doesn't matter */ + cancel_work_sync(&ifmsh->work); + + /* use atomic bitops in case both timers fire at the same time */ + + if (del_timer_sync(&ifmsh->housekeeping_timer)) + set_bit(TMR_RUNNING_HK, &ifmsh->timers_running); + if (del_timer_sync(&ifmsh->mesh_path_timer)) + set_bit(TMR_RUNNING_MP, &ifmsh->timers_running); +} + +void ieee80211_mesh_restart(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + + if (test_and_clear_bit(TMR_RUNNING_HK, &ifmsh->timers_running)) + add_timer(&ifmsh->housekeeping_timer); + if (test_and_clear_bit(TMR_RUNNING_MP, &ifmsh->timers_running)) + add_timer(&ifmsh->mesh_path_timer); +} +#endif void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) { @@ -432,8 +472,8 @@ void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) ifmsh->housekeeping = true; queue_work(local->hw.workqueue, &ifmsh->work); - ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON | - IEEE80211_IFCC_BEACON_ENABLED); + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON | + BSS_CHANGED_BEACON_ENABLED); } void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) @@ -454,7 +494,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) * should it be using the interface and enqueuing * frames at this very time on another CPU. */ - synchronize_rcu(); + rcu_barrier(); /* Wait for RX path and call_rcu()'s */ skb_queue_purge(&sdata->u.mesh.skb_queue); } diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index d891d7ddccd..c7d72819cdd 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -191,12 +191,8 @@ struct mesh_rmc { #define PLINK_CATEGORY 30 #define MESH_PATH_SEL_CATEGORY 32 -/* Mesh Header Flags */ -#define IEEE80211S_FLAGS_AE 0x3 - /* Public interfaces */ /* Various */ -int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); int ieee80211_new_mesh_header(struct ieee80211s_hdr *meshhdr, struct ieee80211_sub_if_data *sdata); int mesh_rmc_check(u8 *addr, struct ieee80211s_hdr *mesh_hdr, @@ -267,6 +263,8 @@ void mesh_path_timer(unsigned long data); void mesh_path_flush_by_nexthop(struct sta_info *sta); void mesh_path_discard_frame(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata); +void mesh_path_quiesce(struct ieee80211_sub_if_data *sdata); +void mesh_path_restart(struct ieee80211_sub_if_data *sdata); #ifdef CONFIG_MAC80211_MESH extern int mesh_allocated; @@ -294,10 +292,20 @@ static inline void mesh_path_activate(struct mesh_path *mpath) void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local); +void ieee80211_mesh_quiesce(struct ieee80211_sub_if_data *sdata); +void ieee80211_mesh_restart(struct ieee80211_sub_if_data *sdata); +void mesh_plink_quiesce(struct sta_info *sta); +void mesh_plink_restart(struct sta_info *sta); #else #define mesh_allocated 0 static inline void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) {} +static inline void ieee80211_mesh_quiesce(struct ieee80211_sub_if_data *sdata) +{} +static inline void ieee80211_mesh_restart(struct ieee80211_sub_if_data *sdata) +{} +static inline void mesh_plink_quiesce(struct sta_info *sta) {} +static inline void mesh_plink_restart(struct sta_info *sta) {} #endif #endif /* IEEE80211S_H */ diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 60b35accda9..f49ef288e2e 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -637,7 +637,7 @@ static void mesh_queue_preq(struct mesh_path *mpath, u8 flags) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct mesh_preq_queue *preq_node; - preq_node = kmalloc(sizeof(struct mesh_preq_queue), GFP_KERNEL); + preq_node = kmalloc(sizeof(struct mesh_preq_queue), GFP_ATOMIC); if (!preq_node) { printk(KERN_DEBUG "Mesh HWMP: could not allocate PREQ node\n"); return; @@ -836,8 +836,14 @@ void mesh_path_timer(unsigned long data) mpath = rcu_dereference(mpath); if (!mpath) goto endmpathtimer; - spin_lock_bh(&mpath->state_lock); sdata = mpath->sdata; + + if (sdata->local->quiescing) { + rcu_read_unlock(); + return; + } + + spin_lock_bh(&mpath->state_lock); if (mpath->flags & MESH_PATH_RESOLVED || (!(mpath->flags & MESH_PATH_RESOLVING))) mpath->flags &= ~(MESH_PATH_RESOLVING | MESH_PATH_RESOLVED); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 3c72557df45..479597e8858 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -175,6 +175,8 @@ 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; @@ -265,6 +267,7 @@ 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 */ @@ -491,8 +494,10 @@ void mesh_path_tx_pending(struct mesh_path *mpath) * @skb: frame to discard * @sdata: network subif the frame was to be sent through * - * If the frame was beign forwarded from another MP, a PERR frame will be sent - * to the precursor. + * If the frame was being forwarded from another MP, a PERR frame will be sent + * to the precursor. The precursor's address (i.e. the previous hop) was saved + * in addr1 of the frame-to-be-forwarded, and would only be overwritten once + * the destination is successfully resolved. * * Locking: the function must me called within a rcu_read_lock region */ @@ -507,7 +512,7 @@ void mesh_path_discard_frame(struct sk_buff *skb, u8 *ra, *da; da = hdr->addr3; - ra = hdr->addr2; + ra = hdr->addr1; mpath = mesh_path_lookup(da, sdata); if (mpath) dsn = ++mpath->dsn; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index a8bbdeca013..cb14253587f 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -266,6 +266,11 @@ static void mesh_plink_timer(unsigned long data) */ sta = (struct sta_info *) data; + if (sta->sdata->local->quiescing) { + sta->plink_timer_was_running = true; + return; + } + spin_lock_bh(&sta->lock); if (sta->ignore_plink_timer) { sta->ignore_plink_timer = false; @@ -322,6 +327,22 @@ static void mesh_plink_timer(unsigned long data) } } +#ifdef CONFIG_PM +void mesh_plink_quiesce(struct sta_info *sta) +{ + if (del_timer_sync(&sta->plink_timer)) + sta->plink_timer_was_running = true; +} + +void mesh_plink_restart(struct sta_info *sta) +{ + if (sta->plink_timer_was_running) { + add_timer(&sta->plink_timer); + sta->plink_timer_was_running = false; + } +} +#endif + static inline void mesh_plink_timer_set(struct sta_info *sta, int timeout) { sta->plink_timer.expires = jiffies + (HZ * timeout / 1000); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 132938b073d..07e7e41816b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -17,10 +17,13 @@ #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> +#include <linux/pm_qos_params.h> +#include <linux/crc32.h> #include <net/mac80211.h> #include <asm/unaligned.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "rate.h" #include "led.h" @@ -30,9 +33,13 @@ #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 TMR_RUNNING_TIMER 0 +#define TMR_RUNNING_CHANSW 1 + /* utils */ static int ecw2cw(int ecw) { @@ -80,6 +87,92 @@ static int ieee80211_compatible_rates(struct ieee80211_bss *bss, return count; } +/* + * ieee80211_enable_ht should be called only after the operating band + * has been determined as ht configuration depends on the hw's + * HT abilities for a specific band. + */ +static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, + struct ieee80211_ht_info *hti, + 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; + bool enable_ht = true, ht_changed; + enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; + + sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + + /* HT is not supported */ + if (!sband->ht_cap.ht_supported) + enable_ht = false; + + /* check that channel matches the right operating channel */ + if (local->hw.conf.channel->center_freq != + ieee80211_channel_to_frequency(hti->control_chan)) + enable_ht = false; + + if (enable_ht) { + channel_type = NL80211_CHAN_HT20; + + if (!(ap_ht_cap_flags & IEEE80211_HT_CAP_40MHZ_INTOLERANT) && + (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) && + (hti->ht_param & IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)) { + switch(hti->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { + case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: + if (!(local->hw.conf.channel->flags & + IEEE80211_CHAN_NO_HT40PLUS)) + channel_type = NL80211_CHAN_HT40PLUS; + break; + case IEEE80211_HT_PARAM_CHA_SEC_BELOW: + if (!(local->hw.conf.channel->flags & + IEEE80211_CHAN_NO_HT40MINUS)) + channel_type = NL80211_CHAN_HT40MINUS; + break; + } + } + } + + ht_changed = conf_is_ht(&local->hw.conf) != enable_ht || + channel_type != local->hw.conf.channel_type; + + local->oper_channel_type = channel_type; + + if (ht_changed) { + /* channel_type change automatically detected */ + ieee80211_hw_config(local, 0); + + rcu_read_lock(); + + sta = sta_info_get(local, ifmgd->bssid); + if (sta) + rate_control_rate_update(local, sband, sta, + IEEE80211_RC_HT_CHANGED); + + rcu_read_unlock(); + } + + /* disable HT */ + if (!enable_ht) + return 0; + + ht_opmode = le16_to_cpu(hti->operation_mode); + + /* if bss configuration changed store the new one */ + if (!sdata->ht_opmode_valid || + sdata->vif.bss_conf.ht_operation_mode != ht_opmode) { + changed |= BSS_CHANGED_HT; + sdata->vif.bss_conf.ht_operation_mode = ht_opmode; + sdata->ht_opmode_valid = true; + } + + return changed; +} + /* frame sending functions */ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) @@ -263,13 +356,13 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) switch (ht_info->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: - if (flags & IEEE80211_CHAN_NO_FAT_ABOVE) { + if (flags & IEEE80211_CHAN_NO_HT40PLUS) { cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; cap &= ~IEEE80211_HT_CAP_SGI_40; } break; case IEEE80211_HT_PARAM_CHA_SEC_BELOW: - if (flags & IEEE80211_CHAN_NO_FAT_BELOW) { + if (flags & IEEE80211_CHAN_NO_HT40MINUS) { cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; cap &= ~IEEE80211_HT_CAP_SGI_40; } @@ -325,6 +418,10 @@ static void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, /* 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); + else + cfg80211_send_disassoc(sdata->dev, (u8 *) mgmt, skb->len); ieee80211_tx_skb(sdata, skb, ifmgd->flags & IEEE80211_STA_MFP_ENABLED); } @@ -359,6 +456,277 @@ void ieee80211_send_pspoll(struct ieee80211_local *local, ieee80211_tx_skb(sdata, skb, 0); } +void ieee80211_send_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + int powersave) +{ + struct sk_buff *skb; + struct ieee80211_hdr *nullfunc; + __le16 fc; + + if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) + return; + + skb = dev_alloc_skb(local->hw.extra_tx_headroom + 24); + if (!skb) { + printk(KERN_DEBUG "%s: failed to allocate buffer for nullfunc " + "frame\n", sdata->dev->name); + return; + } + skb_reserve(skb, local->hw.extra_tx_headroom); + + nullfunc = (struct ieee80211_hdr *) skb_put(skb, 24); + memset(nullfunc, 0, 24); + fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | + IEEE80211_FCTL_TODS); + if (powersave) + fc |= cpu_to_le16(IEEE80211_FCTL_PM); + nullfunc->frame_control = fc; + memcpy(nullfunc->addr1, sdata->u.mgd.bssid, ETH_ALEN); + memcpy(nullfunc->addr2, sdata->dev->dev_addr, ETH_ALEN); + memcpy(nullfunc->addr3, sdata->u.mgd.bssid, ETH_ALEN); + + ieee80211_tx_skb(sdata, skb, 0); +} + +/* spectrum management related things */ +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; + + sdata->local->oper_channel = sdata->local->csa_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; + + 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); +} + +static void ieee80211_chswitch_timer(unsigned long data) +{ + struct ieee80211_sub_if_data *sdata = + (struct ieee80211_sub_if_data *) data; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + if (sdata->local->quiescing) { + set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running); + return; + } + + queue_work(sdata->local->hw.workqueue, &ifmgd->chswitch_work); +} + +void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel_sw_ie *sw_elem, + struct ieee80211_bss *bss) +{ + struct ieee80211_channel *new_ch; + 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) + return; + + if (sdata->local->sw_scanning || sdata->local->hw_scanning) + return; + + /* Disregard subsequent beacons if we are already running a timer + processing a CSA */ + + if (ifmgd->flags & IEEE80211_STA_CSA_RECEIVED) + return; + + new_ch = ieee80211_get_channel(sdata->local->hw.wiphy, new_freq); + if (!new_ch || new_ch->flags & IEEE80211_CHAN_DISABLED) + return; + + sdata->local->csa_channel = new_ch; + + if (sw_elem->count <= 1) { + queue_work(sdata->local->hw.workqueue, &ifmgd->chswitch_work); + } else { + ieee80211_stop_queues_by_reason(&sdata->local->hw, + IEEE80211_QUEUE_STOP_REASON_CSA); + ifmgd->flags |= IEEE80211_STA_CSA_RECEIVED; + mod_timer(&ifmgd->chswitch_timer, + jiffies + + msecs_to_jiffies(sw_elem->count * + bss->cbss.beacon_interval)); + } +} + +static void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, + u16 capab_info, u8 *pwr_constr_elem, + u8 pwr_constr_elem_len) +{ + struct ieee80211_conf *conf = &sdata->local->hw.conf; + + if (!(capab_info & WLAN_CAPABILITY_SPECTRUM_MGMT)) + return; + + /* Power constraint IE length should be 1 octet */ + if (pwr_constr_elem_len != 1) + return; + + if ((*pwr_constr_elem <= conf->channel->max_power) && + (*pwr_constr_elem != sdata->local->power_constr_level)) { + sdata->local->power_constr_level = *pwr_constr_elem; + ieee80211_hw_config(sdata->local, 0); + } +} + +/* powersave */ +static void ieee80211_enable_ps(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_conf *conf = &local->hw.conf; + + /* + * If we are scanning right now then the parameters will + * take effect when scan finishes. + */ + if (local->hw_scanning || local->sw_scanning) + return; + + if (conf->dynamic_ps_timeout > 0 && + !(local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS)) { + mod_timer(&local->dynamic_ps_timer, jiffies + + msecs_to_jiffies(conf->dynamic_ps_timeout)); + } else { + if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) + ieee80211_send_nullfunc(local, sdata, 1); + conf->flags |= IEEE80211_CONF_PS; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); + } +} + +static void ieee80211_change_ps(struct ieee80211_local *local) +{ + struct ieee80211_conf *conf = &local->hw.conf; + + if (local->ps_sdata) { + ieee80211_enable_ps(local, local->ps_sdata); + } else if (conf->flags & IEEE80211_CONF_PS) { + conf->flags &= ~IEEE80211_CONF_PS; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); + del_timer_sync(&local->dynamic_ps_timer); + cancel_work_sync(&local->dynamic_ps_enable_work); + } +} + +/* need to hold RTNL or interface lock */ +void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) +{ + struct ieee80211_sub_if_data *sdata, *found = NULL; + int count = 0; + + if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) { + local->ps_sdata = NULL; + return; + } + + list_for_each_entry(sdata, &local->interfaces, list) { + if (!netif_running(sdata->dev)) + continue; + if (sdata->vif.type != NL80211_IFTYPE_STATION) + continue; + found = sdata; + count++; + } + + if (count == 1 && found->u.mgd.powersave && + (found->u.mgd.flags & IEEE80211_STA_ASSOCIATED) && + !(found->u.mgd.flags & IEEE80211_STA_PROBEREQ_POLL)) { + s32 beaconint_us; + + if (latency < 0) + latency = pm_qos_requirement(PM_QOS_NETWORK_LATENCY); + + beaconint_us = ieee80211_tu_to_usec( + found->vif.bss_conf.beacon_int); + + if (beaconint_us > latency) { + local->ps_sdata = NULL; + } else { + u8 dtimper = found->vif.bss_conf.dtim_period; + int maxslp = 1; + + if (dtimper > 1) + maxslp = min_t(int, dtimper, + latency / beaconint_us); + + local->hw.conf.max_sleep_period = maxslp; + local->ps_sdata = found; + } + } else { + local->ps_sdata = NULL; + } + + ieee80211_change_ps(local); +} + +void ieee80211_dynamic_ps_disable_work(struct work_struct *work) +{ + struct ieee80211_local *local = + container_of(work, struct ieee80211_local, + dynamic_ps_disable_work); + + if (local->hw.conf.flags & IEEE80211_CONF_PS) { + local->hw.conf.flags &= ~IEEE80211_CONF_PS; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); + } + + ieee80211_wake_queues_by_reason(&local->hw, + IEEE80211_QUEUE_STOP_REASON_PS); +} + +void ieee80211_dynamic_ps_enable_work(struct work_struct *work) +{ + struct ieee80211_local *local = + container_of(work, struct ieee80211_local, + dynamic_ps_enable_work); + struct ieee80211_sub_if_data *sdata = local->ps_sdata; + + /* can only happen when PS was just disabled anyway */ + if (!sdata) + return; + + if (local->hw.conf.flags & IEEE80211_CONF_PS) + return; + + if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) + ieee80211_send_nullfunc(local, sdata, 1); + + local->hw.conf.flags |= IEEE80211_CONF_PS; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); +} + +void ieee80211_dynamic_ps_timer(unsigned long data) +{ + struct ieee80211_local *local = (void *) data; + + if (local->quiescing || local->suspended) + return; + + queue_work(local->hw.workqueue, &local->dynamic_ps_enable_work); +} + /* MLME */ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, struct ieee80211_if_managed *ifmgd, @@ -424,41 +792,16 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, #ifdef CONFIG_MAC80211_VERBOSE_DEBUG printk(KERN_DEBUG "%s: WMM queue=%d aci=%d acm=%d aifs=%d " "cWmin=%d cWmax=%d txop=%d\n", - local->mdev->name, queue, aci, acm, params.aifs, params.cw_min, - params.cw_max, params.txop); + wiphy_name(local->hw.wiphy), queue, aci, acm, + params.aifs, params.cw_min, params.cw_max, params.txop); #endif - if (local->ops->conf_tx && - local->ops->conf_tx(local_to_hw(local), queue, ¶ms)) { + if (drv_conf_tx(local, queue, ¶ms) && local->ops->conf_tx) printk(KERN_DEBUG "%s: failed to set TX queue " - "parameters for queue %d\n", local->mdev->name, queue); - } + "parameters for queue %d\n", + wiphy_name(local->hw.wiphy), queue); } } -static bool ieee80211_check_tim(struct ieee802_11_elems *elems, u16 aid) -{ - u8 mask; - u8 index, indexn1, indexn2; - struct ieee80211_tim_ie *tim = (struct ieee80211_tim_ie *) elems->tim; - - if (unlikely(!tim || elems->tim_len < 4)) - return false; - - aid &= 0x3fff; - index = aid / 8; - mask = 1 << (aid & 7); - - indexn1 = tim->bitmap_ctrl & 0xfe; - indexn2 = elems->tim_len + indexn1 - 4; - - if (index < indexn1 || index > indexn2) - return false; - - index -= indexn1; - - return !!(tim->virtual_map[index] & mask); -} - static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, u16 capab, bool erp_valid, u8 erp) { @@ -610,6 +953,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, 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); @@ -632,20 +976,17 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, * changed or not. */ bss_info_changed |= BSS_CHANGED_BASIC_RATES; + + /* And the BSSID changed - we're associated now */ + bss_info_changed |= BSS_CHANGED_BSSID; + ieee80211_bss_info_change_notify(sdata, bss_info_changed); - if (local->powersave) { - if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS) && - local->hw.conf.dynamic_ps_timeout > 0) { - mod_timer(&local->dynamic_ps_timer, jiffies + - msecs_to_jiffies( - local->hw.conf.dynamic_ps_timeout)); - } else { - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) - ieee80211_send_nullfunc(local, sdata, 1); - conf->flags |= IEEE80211_CONF_PS; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); - } + /* will be same as sdata */ + if (local->ps_sdata) { + mutex_lock(&local->iflist_mtx); + ieee80211_recalc_ps(local, -1); + mutex_unlock(&local->iflist_mtx); } netif_tx_start_all_queues(sdata->dev); @@ -664,7 +1005,8 @@ static void ieee80211_direct_probe(struct ieee80211_sub_if_data *sdata) printk(KERN_DEBUG "%s: direct probe to AP %pM timed out\n", sdata->dev->name, ifmgd->bssid); ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_sta_send_apinfo(sdata); + ieee80211_recalc_idle(local); + cfg80211_send_auth_timeout(sdata->dev, ifmgd->bssid); /* * Most likely AP is not in the range so remove the @@ -689,8 +1031,6 @@ static void ieee80211_direct_probe(struct ieee80211_sub_if_data *sdata) ifmgd->state = IEEE80211_STA_MLME_DIRECT_PROBE; - set_bit(IEEE80211_STA_REQ_DIRECT_PROBE, &ifmgd->request); - /* Direct probe is sent to broadcast address as some APs * will not answer to direct packet in unassociated state. */ @@ -714,7 +1054,8 @@ static void ieee80211_authenticate(struct ieee80211_sub_if_data *sdata) " timed out\n", sdata->dev->name, ifmgd->bssid); ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_sta_send_apinfo(sdata); + 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); @@ -761,14 +1102,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; u32 changed = 0, config_changed = 0; - rcu_read_lock(); - - sta = sta_info_get(local, ifmgd->bssid); - if (!sta) { - rcu_read_unlock(); - return; - } - if (deauth) { ifmgd->direct_probe_tries = 0; ifmgd->auth_tries = 0; @@ -779,7 +1112,11 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, netif_tx_stop_all_queues(sdata->dev); netif_carrier_off(sdata->dev); - ieee80211_sta_tear_down_BA_sessions(sta); + rcu_read_lock(); + sta = sta_info_get(local, ifmgd->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, @@ -815,11 +1152,16 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ifmgd->ssid, ifmgd->ssid_len); } - rcu_read_unlock(); + ieee80211_set_wmm_default(sdata); + + ieee80211_recalc_idle(local); /* channel(_type) changes are handled by ieee80211_hw_config */ local->oper_channel_type = NL80211_CHAN_NO_HT; + /* on the next assoc, re-program HT parameters */ + sdata->ht_opmode_valid = false; + local->power_constr_level = 0; del_timer_sync(&local->dynamic_ps_timer); @@ -831,6 +1173,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, } ieee80211_hw_config(local, config_changed); + + /* And the BSSID changed -- not very interesting here */ + changed |= BSS_CHANGED_BSSID; ieee80211_bss_info_change_notify(sdata, changed); rcu_read_lock(); @@ -897,7 +1242,8 @@ static void ieee80211_associate(struct ieee80211_sub_if_data *sdata) " timed out\n", sdata->dev->name, ifmgd->bssid); ifmgd->state = IEEE80211_STA_MLME_DISABLED; - ieee80211_sta_send_apinfo(sdata); + 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); @@ -917,6 +1263,7 @@ static void ieee80211_associate(struct ieee80211_sub_if_data *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; } @@ -948,6 +1295,17 @@ void ieee80211_beacon_loss_work(struct work_struct *work) 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) + return; + #ifdef CONFIG_MAC80211_VERBOSE_DEBUG if (net_ratelimit()) { printk(KERN_DEBUG "%s: driver reports beacon loss from AP %pM " @@ -957,10 +1315,15 @@ void ieee80211_beacon_loss_work(struct work_struct *work) #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_MONITORING_INTERVAL); + mod_timer(&ifmgd->timer, jiffies + IEEE80211_PROBE_WAIT); } void ieee80211_beacon_loss(struct ieee80211_vif *vif) @@ -977,6 +1340,7 @@ static void ieee80211_associated(struct ieee80211_sub_if_data *sdata) 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; /* TODO: start monitoring current AP signal quality and number of @@ -993,17 +1357,21 @@ static void ieee80211_associated(struct ieee80211_sub_if_data *sdata) printk(KERN_DEBUG "%s: No STA entry for own AP %pM\n", sdata->dev->name, ifmgd->bssid); disassoc = true; - goto unlock; + rcu_read_unlock(); + goto out; } + last_rx = sta->last_rx; + rcu_read_unlock(); + if ((ifmgd->flags & IEEE80211_STA_PROBEREQ_POLL) && - time_after(jiffies, sta->last_rx + IEEE80211_MONITORING_INTERVAL)) { + 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 unlock; + goto out; } /* @@ -1022,27 +1390,31 @@ static void ieee80211_associated(struct ieee80211_sub_if_data *sdata) } #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); - goto unlock; - + mod_timer(&ifmgd->timer, jiffies + IEEE80211_PROBE_WAIT); + goto out; } - if (time_after(jiffies, sta->last_rx + IEEE80211_PROBE_IDLE_TIME)) { + 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); } - unlock: - rcu_read_unlock(); - - if (disassoc) + out: + if (!disassoc) + mod_timer(&ifmgd->timer, + jiffies + IEEE80211_MONITORING_INTERVAL); + else ieee80211_set_disassoc(sdata, true, true, WLAN_REASON_PREV_AUTH_NOT_VALID); - else - mod_timer(&ifmgd->timer, jiffies + - IEEE80211_MONITORING_INTERVAL); } @@ -1055,6 +1427,7 @@ static void ieee80211_auth_completed(struct ieee80211_sub_if_data *sdata) 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); } @@ -1187,7 +1560,7 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, true, false, 0); ifmgd->flags &= ~IEEE80211_STA_AUTHENTICATED; - cfg80211_send_rx_deauth(sdata->dev, (u8 *) mgmt, len); + cfg80211_send_deauth(sdata->dev, (u8 *) mgmt, len); } @@ -1218,7 +1591,7 @@ static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, } ieee80211_set_disassoc(sdata, false, false, reason_code); - cfg80211_send_rx_disassoc(sdata->dev, (u8 *) mgmt, len); + cfg80211_send_disassoc(sdata->dev, (u8 *) mgmt, len); } @@ -1287,6 +1660,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, * 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; } @@ -1340,8 +1719,9 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, * 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 | - WLAN_STA_AUTHORIZED); + 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); rates = 0; basic_rates = 0; @@ -1421,6 +1801,8 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, if (elems.wmm_param) ieee80211_sta_wmm_params(local, ifmgd, elems.wmm_param, elems.wmm_param_len); + else + ieee80211_set_wmm_default(sdata); if (elems.ht_info_elem && elems.wmm_param && (ifmgd->flags & IEEE80211_STA_WMM_ENABLED) && @@ -1476,7 +1858,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, (memcmp(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN) == 0)) { struct ieee80211_channel_sw_ie *sw_elem = (struct ieee80211_channel_sw_ie *)elems->ch_switch_elem; - ieee80211_process_chanswitch(sdata, sw_elem, bss); + ieee80211_sta_process_chanswitch(sdata, sw_elem, bss); } ieee80211_rx_bss_put(local, bss); @@ -1507,57 +1889,98 @@ 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 (test_and_clear_bit(IEEE80211_STA_REQ_DIRECT_PROBE, - &ifmgd->request)) { + if (ifmgd->state == IEEE80211_STA_MLME_DIRECT_PROBE) { printk(KERN_DEBUG "%s direct probe responded\n", sdata->dev->name); ieee80211_authenticate(sdata); } - if (ifmgd->flags & IEEE80211_STA_PROBEREQ_POLL) + if (ifmgd->flags & IEEE80211_STA_PROBEREQ_POLL) { ifmgd->flags &= ~IEEE80211_STA_PROBEREQ_POLL; + mutex_lock(&sdata->local->iflist_mtx); + ieee80211_recalc_ps(sdata->local, -1); + mutex_unlock(&sdata->local->iflist_mtx); + } } +/* + * This is the canonical list of information elements we care about, + * the filter code also gives us all changes to the Microsoft OUI + * (00:50:F2) vendor IE which is used for WMM which we need to track. + * + * We implement beacon filtering in software since that means we can + * avoid processing the frame here and in cfg80211, and userspace + * will not be able to tell whether the hardware supports it or not. + * + * XXX: This list needs to be dynamic -- userspace needs to be able to + * add items it requires. It also needs to be able to tell us to + * look out for other vendor IEs. + */ +static const u64 care_about_ies = + (1ULL << WLAN_EID_COUNTRY) | + (1ULL << WLAN_EID_ERP_INFO) | + (1ULL << WLAN_EID_CHANNEL_SWITCH) | + (1ULL << WLAN_EID_PWR_CONSTRAINT) | + (1ULL << WLAN_EID_HT_CAPABILITY) | + (1ULL << WLAN_EID_HT_INFORMATION); + static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status) { - struct ieee80211_if_managed *ifmgd; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; size_t baselen; struct ieee802_11_elems elems; struct ieee80211_local *local = sdata->local; u32 changed = 0; - bool erp_valid, directed_tim; + bool erp_valid, directed_tim = false; u8 erp_value = 0; + u32 ncrc; /* Process beacon from the current BSS */ baselen = (u8 *) mgmt->u.beacon.variable - (u8 *) mgmt; if (baselen > len) return; - ieee802_11_parse_elems(mgmt->u.beacon.variable, len - baselen, &elems); - - ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, true); - - if (sdata->vif.type != NL80211_IFTYPE_STATION) + if (rx_status->freq != local->hw.conf.channel->center_freq) return; - ifmgd = &sdata->u.mgd; - if (!(ifmgd->flags & IEEE80211_STA_ASSOCIATED) || memcmp(ifmgd->bssid, mgmt->bssid, ETH_ALEN) != 0) return; - if (rx_status->freq != local->hw.conf.channel->center_freq) - return; + if (ifmgd->flags & IEEE80211_STA_PROBEREQ_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; + mutex_lock(&local->iflist_mtx); + ieee80211_recalc_ps(local, -1); + mutex_unlock(&local->iflist_mtx); + } - ieee80211_sta_wmm_params(local, ifmgd, elems.wmm_param, - elems.wmm_param_len); + ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4); + ncrc = ieee802_11_parse_elems_crc(mgmt->u.beacon.variable, + len - baselen, &elems, + care_about_ies, ncrc); - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) { - directed_tim = ieee80211_check_tim(&elems, ifmgd->aid); + if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) + directed_tim = ieee80211_check_tim(elems.tim, elems.tim_len, + ifmgd->aid); + if (ncrc != ifmgd->beacon_crc) { + ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, + true); + + ieee80211_sta_wmm_params(local, ifmgd, elems.wmm_param, + elems.wmm_param_len); + } + + if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) { if (directed_tim) { if (local->hw.conf.dynamic_ps_timeout > 0) { local->hw.conf.flags &= ~IEEE80211_CONF_PS; @@ -1580,6 +2003,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } } + if (ncrc == ifmgd->beacon_crc) + return; + ifmgd->beacon_crc = ncrc; + if (elems.erp_info && elems.erp_info_len >= 1) { erp_valid = true; erp_value = elems.erp_info[0]; @@ -1714,6 +2141,11 @@ static void ieee80211_sta_timer(unsigned long data) struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; + if (local->quiescing) { + set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running); + return; + } + set_bit(IEEE80211_STA_REQ_RUN, &ifmgd->request); queue_work(local->hw.workqueue, &ifmgd->work); } @@ -1723,10 +2155,8 @@ static void ieee80211_sta_reset_auth(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - if (local->ops->reset_tsf) { - /* Reset own TSF to allow time synchronization work. */ - local->ops->reset_tsf(local_to_hw(local)); - } + /* Reset own TSF to allow time synchronization work. */ + drv_reset_tsf(local); ifmgd->wmm_last_param_set = -1; /* allow any WMM update */ @@ -1787,7 +2217,10 @@ static int ieee80211_sta_config_auth(struct ieee80211_sub_if_data *sdata) capa_mask, capa_val); if (bss) { - ieee80211_set_freq(sdata, bss->cbss.channel->center_freq); + local->oper_channel = bss->cbss.channel; + local->oper_channel_type = NL80211_CHAN_NO_HT; + ieee80211_hw_config(local, 0); + if (!(ifmgd->flags & IEEE80211_STA_SSID_SET)) ieee80211_sta_set_ssid(sdata, bss->ssid, bss->ssid_len); @@ -1814,25 +2247,18 @@ static int ieee80211_sta_config_auth(struct ieee80211_sub_if_data *sdata) return 0; } else { if (ifmgd->assoc_scan_tries < IEEE80211_ASSOC_SCANS_MAX_TRIES) { + ifmgd->assoc_scan_tries++; - /* XXX maybe racy? */ - if (local->scan_req) - return -1; - memcpy(local->int_scan_req.ssids[0].ssid, - ifmgd->ssid, IEEE80211_MAX_SSID_LEN); - if (ifmgd->flags & IEEE80211_STA_AUTO_SSID_SEL) - local->int_scan_req.ssids[0].ssid_len = 0; - else - local->int_scan_req.ssids[0].ssid_len = ifmgd->ssid_len; - if (ieee80211_start_scan(sdata, &local->int_scan_req)) - ieee80211_scan_failed(local); + ieee80211_request_internal_scan(sdata, ifmgd->ssid, + ssid_len); 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); } } return -1; @@ -1855,6 +2281,17 @@ static void ieee80211_sta_work(struct work_struct *work) 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)) + return; + ifmgd = &sdata->u.mgd; while ((skb = skb_dequeue(&ifmgd->skb_queue))) @@ -1864,14 +2301,8 @@ static void ieee80211_sta_work(struct work_struct *work) ifmgd->state != IEEE80211_STA_MLME_AUTHENTICATE && ifmgd->state != IEEE80211_STA_MLME_ASSOCIATE && test_and_clear_bit(IEEE80211_STA_REQ_SCAN, &ifmgd->request)) { - /* - * The call to ieee80211_start_scan can fail but ieee80211_request_scan - * (which queued ieee80211_sta_work) did not return an error. Thus, call - * ieee80211_scan_failed here if ieee80211_start_scan fails in order to - * notify the scan requester. - */ - if (ieee80211_start_scan(sdata, local->scan_req)) - ieee80211_scan_failed(local); + queue_delayed_work(local->hw.workqueue, &local->scan_work, + round_jiffies_relative(0)); return; } @@ -1882,6 +2313,8 @@ static void ieee80211_sta_work(struct work_struct *work) } else if (!test_and_clear_bit(IEEE80211_STA_REQ_RUN, &ifmgd->request)) return; + ieee80211_recalc_idle(local); + switch (ifmgd->state) { case IEEE80211_STA_MLME_DISABLED: break; @@ -1926,10 +2359,43 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) } } +#ifdef CONFIG_PM +void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + /* + * we need to use atomic bitops for the running bits + * only because both timers might fire at the same + * time -- the code here is properly synchronised. + */ + + cancel_work_sync(&ifmgd->work); + cancel_work_sync(&ifmgd->beacon_loss_work); + if (del_timer_sync(&ifmgd->timer)) + set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running); + + cancel_work_sync(&ifmgd->chswitch_work); + if (del_timer_sync(&ifmgd->chswitch_timer)) + set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running); +} + +void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + if (test_and_clear_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running)) + add_timer(&ifmgd->timer); + if (test_and_clear_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running)) + add_timer(&ifmgd->chswitch_timer); +} +#endif + /* interface setup */ 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); @@ -1949,6 +2415,13 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) IEEE80211_STA_AUTO_CHANNEL_SEL; if (sdata->local->hw.queues >= 4) ifmgd->flags |= IEEE80211_STA_WMM_ENABLED; + + hw_flags = sdata->local->hw.flags; + + if (hw_flags & IEEE80211_HW_SUPPORTS_PS) { + ifmgd->powersave = CONFIG_MAC80211_DEFAULT_PS_VALUE; + sdata->local->hw.conf.dynamic_ps_timeout = 500; + } } /* configuration hooks */ @@ -1969,6 +2442,14 @@ void ieee80211_sta_req_auth(struct ieee80211_sub_if_data *sdata) ieee80211_set_disassoc(sdata, true, true, WLAN_REASON_DEAUTH_LEAVING); + if (ifmgd->ssid_len == 0) { + /* + * Only allow association to be started if a valid SSID + * is configured. + */ + return; + } + if (!(ifmgd->flags & IEEE80211_STA_EXT_SME) || ifmgd->state != IEEE80211_STA_MLME_ASSOCIATE) set_bit(IEEE80211_STA_REQ_AUTH, &ifmgd->request); @@ -2000,6 +2481,10 @@ int ieee80211_sta_set_ssid(struct ieee80211_sub_if_data *sdata, char *ssid, size ifmgd = &sdata->u.mgd; 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); + /* * Do not use reassociation if SSID is changed (different ESS). */ @@ -2024,6 +2509,11 @@ int ieee80211_sta_set_bssid(struct ieee80211_sub_if_data *sdata, u8 *bssid) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + if (compare_ether_addr(bssid, ifmgd->bssid) != 0 && + ifmgd->state == IEEE80211_STA_MLME_ASSOCIATED) + ieee80211_set_disassoc(sdata, true, true, + WLAN_REASON_DEAUTH_LEAVING); + if (is_valid_ether_addr(bssid)) { memcpy(ifmgd->bssid, bssid, ETH_ALEN); ifmgd->flags |= IEEE80211_STA_BSSID_SET; @@ -2032,13 +2522,6 @@ int ieee80211_sta_set_bssid(struct ieee80211_sub_if_data *sdata, u8 *bssid) ifmgd->flags &= ~IEEE80211_STA_BSSID_SET; } - if (netif_running(sdata->dev)) { - if (ieee80211_if_config(sdata, IEEE80211_IFCC_BSSID)) { - printk(KERN_DEBUG "%s: Failed to config new BSSID to " - "the low-level driver\n", sdata->dev->name); - } - } - return ieee80211_sta_commit(sdata); } @@ -2047,6 +2530,13 @@ int ieee80211_sta_set_extra_ie(struct ieee80211_sub_if_data *sdata, { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + if (len == 0 && ifmgd->extra_ie_len == 0) + return -EALREADY; + + if (len == ifmgd->extra_ie_len && ifmgd->extra_ie && + memcmp(ifmgd->extra_ie, ie, len) == 0) + return -EALREADY; + kfree(ifmgd->extra_ie); if (len == 0) { ifmgd->extra_ie = NULL; @@ -2068,9 +2558,6 @@ 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); - if (sdata->vif.type != NL80211_IFTYPE_STATION) - return -EINVAL; - ieee80211_set_disassoc(sdata, true, true, reason); return 0; } @@ -2082,9 +2569,6 @@ int ieee80211_sta_disassociate(struct ieee80211_sub_if_data *sdata, u16 reason) printk(KERN_DEBUG "%s: disassociating by local choice (reason=%d)\n", sdata->dev->name, reason); - if (sdata->vif.type != NL80211_IFTYPE_STATION) - return -EINVAL; - if (!(ifmgd->flags & IEEE80211_STA_ASSOCIATED)) return -ENOLINK; @@ -2104,75 +2588,17 @@ void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) rcu_read_unlock(); } -void ieee80211_dynamic_ps_disable_work(struct work_struct *work) -{ - struct ieee80211_local *local = - container_of(work, struct ieee80211_local, - dynamic_ps_disable_work); - - if (local->hw.conf.flags & IEEE80211_CONF_PS) { - local->hw.conf.flags &= ~IEEE80211_CONF_PS; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); - } - - ieee80211_wake_queues_by_reason(&local->hw, - IEEE80211_QUEUE_STOP_REASON_PS); -} - -void ieee80211_dynamic_ps_enable_work(struct work_struct *work) +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(work, struct ieee80211_local, - dynamic_ps_enable_work); - /* XXX: using scan_sdata is completely broken! */ - struct ieee80211_sub_if_data *sdata = local->scan_sdata; - - if (local->hw.conf.flags & IEEE80211_CONF_PS) - return; - - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK && sdata) - ieee80211_send_nullfunc(local, sdata, 1); + container_of(nb, struct ieee80211_local, + network_latency_notifier); - local->hw.conf.flags |= IEEE80211_CONF_PS; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); -} - -void ieee80211_dynamic_ps_timer(unsigned long data) -{ - struct ieee80211_local *local = (void *) data; - - queue_work(local->hw.workqueue, &local->dynamic_ps_enable_work); -} - -void ieee80211_send_nullfunc(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - int powersave) -{ - struct sk_buff *skb; - struct ieee80211_hdr *nullfunc; - __le16 fc; + mutex_lock(&local->iflist_mtx); + ieee80211_recalc_ps(local, latency_usec); + mutex_unlock(&local->iflist_mtx); - if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) - return; - - skb = dev_alloc_skb(local->hw.extra_tx_headroom + 24); - if (!skb) { - printk(KERN_DEBUG "%s: failed to allocate buffer for nullfunc " - "frame\n", sdata->dev->name); - return; - } - skb_reserve(skb, local->hw.extra_tx_headroom); - - nullfunc = (struct ieee80211_hdr *) skb_put(skb, 24); - memset(nullfunc, 0, 24); - fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | - IEEE80211_FCTL_TODS); - if (powersave) - fc |= cpu_to_le16(IEEE80211_FCTL_PM); - nullfunc->frame_control = fc; - memcpy(nullfunc->addr1, sdata->u.mgd.bssid, ETH_ALEN); - memcpy(nullfunc->addr2, sdata->dev->dev_addr, ETH_ALEN); - memcpy(nullfunc->addr3, sdata->u.mgd.bssid, ETH_ALEN); - - ieee80211_tx_skb(sdata, skb, 0); + return 0; } diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 81985d27cbd..5e3d476972f 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -2,6 +2,8 @@ #include <net/rtnetlink.h> #include "ieee80211_i.h" +#include "mesh.h" +#include "driver-ops.h" #include "led.h" int __ieee80211_suspend(struct ieee80211_hw *hw) @@ -12,11 +14,30 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) struct sta_info *sta; unsigned long flags; + ieee80211_scan_cancel(local); + ieee80211_stop_queues_by_reason(hw, IEEE80211_QUEUE_STOP_REASON_SUSPEND); + /* flush out all packets */ + synchronize_net(); + + local->quiescing = true; + /* make quiescing visible to timers everywhere */ + mb(); + flush_workqueue(local->hw.workqueue); + /* Don't try to run timers while suspended. */ + del_timer_sync(&local->sta_cleanup); + + /* + * Note that this particular timer doesn't need to be + * restarted at resume. + */ + cancel_work_sync(&local->dynamic_ps_enable_work); + del_timer_sync(&local->dynamic_ps_timer); + /* disable keys */ list_for_each_entry(sdata, &local->interfaces, list) ieee80211_disable_keys(sdata); @@ -35,156 +56,75 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) rcu_read_unlock(); /* remove STAs */ - if (local->ops->sta_notify) { - spin_lock_irqsave(&local->sta_lock, flags); - list_for_each_entry(sta, &local->sta_list, list) { + spin_lock_irqsave(&local->sta_lock, flags); + list_for_each_entry(sta, &local->sta_list, list) { + if (local->ops->sta_notify) { + sdata = sta->sdata; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); - local->ops->sta_notify(hw, &sdata->vif, - STA_NOTIFY_REMOVE, &sta->sta); - } - spin_unlock_irqrestore(&local->sta_lock, flags); - } - - /* remove all interfaces */ - list_for_each_entry(sdata, &local->interfaces, list) { - if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && - sdata->vif.type != NL80211_IFTYPE_MONITOR && - netif_running(sdata->dev)) { - conf.vif = &sdata->vif; - conf.type = sdata->vif.type; - conf.mac_addr = sdata->dev->dev_addr; - local->ops->remove_interface(hw, &conf); + drv_sta_notify(local, &sdata->vif, STA_NOTIFY_REMOVE, + &sta->sta); } - } - - /* flush again, in case driver queued work */ - flush_workqueue(local->hw.workqueue); - - /* stop hardware */ - if (local->open_count) { - ieee80211_led_radio(local, false); - local->ops->stop(hw); - } - return 0; -} -int __ieee80211_resume(struct ieee80211_hw *hw) -{ - struct ieee80211_local *local = hw_to_local(hw); - struct ieee80211_sub_if_data *sdata; - struct ieee80211_if_init_conf conf; - struct sta_info *sta; - unsigned long flags; - int res; - - /* restart hardware */ - if (local->open_count) { - res = local->ops->start(hw); - - ieee80211_led_radio(local, hw->conf.radio_enabled); + mesh_plink_quiesce(sta); } + spin_unlock_irqrestore(&local->sta_lock, flags); - /* add interfaces */ - list_for_each_entry(sdata, &local->interfaces, list) { - if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && - sdata->vif.type != NL80211_IFTYPE_MONITOR && - netif_running(sdata->dev)) { - conf.vif = &sdata->vif; - conf.type = sdata->vif.type; - conf.mac_addr = sdata->dev->dev_addr; - res = local->ops->add_interface(hw, &conf); - } - } - - /* add STAs back */ - if (local->ops->sta_notify) { - spin_lock_irqsave(&local->sta_lock, flags); - list_for_each_entry(sta, &local->sta_list, list) { - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - sdata = container_of(sdata->bss, - struct ieee80211_sub_if_data, - u.ap); - - local->ops->sta_notify(hw, &sdata->vif, - STA_NOTIFY_ADD, &sta->sta); - } - spin_unlock_irqrestore(&local->sta_lock, flags); - } - - /* Clear Suspend state so that ADDBA requests can be processed */ - - rcu_read_lock(); - - if (hw->flags & IEEE80211_HW_AMPDU_AGGREGATION) { - list_for_each_entry_rcu(sta, &local->sta_list, list) { - clear_sta_flags(sta, WLAN_STA_SUSPEND); - } - } - - rcu_read_unlock(); - - /* add back keys */ - list_for_each_entry(sdata, &local->interfaces, list) - if (netif_running(sdata->dev)) - ieee80211_enable_keys(sdata); - - /* setup RTS threshold */ - if (local->ops->set_rts_threshold) - local->ops->set_rts_threshold(hw, local->rts_threshold); - - /* 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 */ + /* remove all interfaces */ list_for_each_entry(sdata, &local->interfaces, list) { - u32 changed = ~0; - if (!netif_running(sdata->dev)) - continue; - switch (sdata->vif.type) { + switch(sdata->vif.type) { case NL80211_IFTYPE_STATION: - /* disable beacon change bits */ - changed &= ~IEEE80211_IFCC_BEACON; - /* fall through */ + ieee80211_sta_quiesce(sdata); + break; case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_MESH_POINT: - /* - * Driver's config_interface can fail if rfkill is - * enabled. Accommodate this return code. - * FIXME: When mac80211 has knowledge of rfkill - * state the code below can change back to: - * WARN(ieee80211_if_config(sdata, changed)); - * ieee80211_bss_info_change_notify(sdata, ~0); - */ - if (ieee80211_if_config(sdata, changed)) - printk(KERN_DEBUG "%s: failed to configure interface during resume\n", - sdata->dev->name); - else - ieee80211_bss_info_change_notify(sdata, ~0); + ieee80211_ibss_quiesce(sdata); break; - case NL80211_IFTYPE_WDS: + case NL80211_IFTYPE_MESH_POINT: + ieee80211_mesh_quiesce(sdata); break; case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: - /* ignore virtual */ - break; - case NL80211_IFTYPE_UNSPECIFIED: - case __NL80211_IFTYPE_AFTER_LAST: - WARN_ON(1); + /* don't tell driver about this */ + continue; + default: break; } + + if (!netif_running(sdata->dev)) + continue; + + conf.vif = &sdata->vif; + conf.type = sdata->vif.type; + conf.mac_addr = sdata->dev->dev_addr; + drv_remove_interface(local, &conf); } - ieee80211_wake_queues_by_reason(hw, - IEEE80211_QUEUE_STOP_REASON_SUSPEND); + /* 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); + + local->suspended = true; + /* need suspended to be visible before quiescing is false */ + barrier(); + local->quiescing = false; return 0; } + +/* + * __ieee80211_resume() is a static inline which just calls + * ieee80211_reconfig(), which is also needed for hardware + * hang/firmware failure/etc. recovery. + */ diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index d9233ec5061..37771abd8f5 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -66,7 +66,7 @@ rix_to_ndx(struct minstrel_sta_info *mi, int rix) for (i = rix; i >= 0; i--) if (mi->r[i].rix == rix) break; - WARN_ON(mi->r[i].rix != rix); + WARN_ON(i < 0); return i; } @@ -80,8 +80,7 @@ use_low_rate(struct sk_buff *skb) fc = le16_to_cpu(hdr->frame_control); return ((info->flags & IEEE80211_TX_CTL_NO_ACK) || - (fc & IEEE80211_FCTL_FTYPE) != IEEE80211_FTYPE_DATA || - is_multicast_ether_addr(hdr->addr1)); + (fc & IEEE80211_FCTL_FTYPE) != IEEE80211_FTYPE_DATA); } @@ -182,6 +181,9 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, break; ndx = rix_to_ndx(mi, ar[i].idx); + if (ndx < 0) + continue; + mi->r[ndx].attempts += ar[i].count; if ((i != IEEE80211_TX_MAX_RATES - 1) && (ar[i + 1].idx < 0)) @@ -216,7 +218,7 @@ minstrel_get_next_sample(struct minstrel_sta_info *mi) unsigned int sample_ndx; sample_ndx = SAMPLE_TBL(mi, mi->sample_idx, mi->sample_column); mi->sample_idx++; - if (mi->sample_idx > (mi->n_rates - 2)) { + if ((int) mi->sample_idx > (mi->n_rates - 2)) { mi->sample_idx = 0; mi->sample_column++; if (mi->sample_column >= SAMPLE_COLUMNS) @@ -245,7 +247,10 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, if (!sta || !mi || use_low_rate(skb)) { ar[0].idx = rate_lowest_index(sband, sta); - ar[0].count = mp->max_retry; + if (info->flags & IEEE80211_TX_CTL_NO_ACK) + ar[0].count = 1; + else + ar[0].count = mp->max_retry; return; } diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c index 8bef9a1262f..a0bef767ceb 100644 --- a/net/mac80211/rc80211_pid_algo.c +++ b/net/mac80211/rc80211_pid_algo.c @@ -289,13 +289,15 @@ rate_control_pid_get_rate(void *priv, struct ieee80211_sta *sta, info->control.rates[0].count = txrc->hw->conf.short_frame_max_tx_count; - /* Send management frames and broadcast/multicast data using lowest - * rate. */ + /* 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 || - is_multicast_ether_addr(hdr->addr1)) { + 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; + return; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 9776f73c51a..0936fc24942 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -19,6 +19,7 @@ #include <net/ieee80211_radiotap.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "led.h" #include "mesh.h" #include "wep.h" @@ -629,15 +630,6 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) * possible. */ - if (!ieee80211_has_protected(hdr->frame_control)) { - if (!ieee80211_is_mgmt(hdr->frame_control) || - rx->sta == NULL || !test_sta_flags(rx->sta, WLAN_STA_MFP)) - return RX_CONTINUE; - mmie_keyidx = ieee80211_get_mmie_keyidx(rx->skb); - if (mmie_keyidx < 0) - return RX_CONTINUE; - } - /* * No point in finding a key and decrypting if the frame is neither * addressed to us nor a multicast frame. @@ -648,8 +640,14 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) if (rx->sta) stakey = rcu_dereference(rx->sta->key); + if (!ieee80211_has_protected(hdr->frame_control)) + mmie_keyidx = ieee80211_get_mmie_keyidx(rx->skb); + if (!is_multicast_ether_addr(hdr->addr1) && stakey) { rx->key = stakey; + /* Skip decryption if the frame is not protected. */ + if (!ieee80211_has_protected(hdr->frame_control)) + return RX_CONTINUE; } else if (mmie_keyidx >= 0) { /* Broadcast/multicast robust management frame / BIP */ if ((rx->status->flag & RX_FLAG_DECRYPTED) && @@ -660,6 +658,21 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) mmie_keyidx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) return RX_DROP_MONITOR; /* unexpected BIP keyidx */ rx->key = rcu_dereference(rx->sdata->keys[mmie_keyidx]); + } else if (!ieee80211_has_protected(hdr->frame_control)) { + /* + * The frame was not protected, so skip decryption. However, we + * need to set rx->key if there is a key that could have been + * used so that the frame may be dropped if encryption would + * have been expected. + */ + struct ieee80211_key *key = NULL; + if (ieee80211_is_mgmt(hdr->frame_control) && + is_multicast_ether_addr(hdr->addr1) && + (key = rcu_dereference(rx->sdata->default_mgmt_key))) + rx->key = key; + else if ((key = rcu_dereference(rx->sdata->default_key))) + rx->key = key; + return RX_CONTINUE; } else { /* * The device doesn't give us the IV so we won't be @@ -773,9 +786,7 @@ static void ap_sta_ps_start(struct sta_info *sta) atomic_inc(&sdata->bss->num_sta_ps); set_and_clear_sta_flags(sta, WLAN_STA_PS, WLAN_STA_PSPOLL); - if (local->ops->sta_notify) - local->ops->sta_notify(local_to_hw(local), &sdata->vif, - STA_NOTIFY_SLEEP, &sta->sta); + 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", sdata->dev->name, sta->sta.addr, sta->sta.aid); @@ -786,15 +797,12 @@ static int ap_sta_ps_end(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - struct sk_buff *skb; - int sent = 0; + int sent, buffered; atomic_dec(&sdata->bss->num_sta_ps); clear_sta_flags(sta, WLAN_STA_PS | WLAN_STA_PSPOLL); - if (local->ops->sta_notify) - local->ops->sta_notify(local_to_hw(local), &sdata->vif, - STA_NOTIFY_AWAKE, &sta->sta); + drv_sta_notify(local, &sdata->vif, STA_NOTIFY_AWAKE, &sta->sta); if (!skb_queue_empty(&sta->ps_tx_buf)) sta_info_clear_tim_bit(sta); @@ -805,22 +813,16 @@ static int ap_sta_ps_end(struct sta_info *sta) #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ /* Send all buffered frames to the station */ - while ((skb = skb_dequeue(&sta->tx_filtered)) != NULL) { - sent++; - skb->requeue = 1; - dev_queue_xmit(skb); - } - while ((skb = skb_dequeue(&sta->ps_tx_buf)) != NULL) { - local->total_ps_buffered--; - sent++; + sent = ieee80211_add_pending_skbs(local, &sta->tx_filtered); + buffered = ieee80211_add_pending_skbs(local, &sta->ps_tx_buf); + sent += buffered; + local->total_ps_buffered -= buffered; + #ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG - printk(KERN_DEBUG "%s: STA %pM aid %d send PS frame " - "since STA not sleeping anymore\n", sdata->dev->name, - sta->sta.addr, sta->sta.aid); + printk(KERN_DEBUG "%s: STA %pM aid %d sending %d filtered/%d PS frames " + "since STA not sleeping anymore\n", sdata->dev->name, + sta->sta.addr, sta->sta.aid, sent - buffered, buffered); #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ - skb->requeue = 1; - dev_queue_xmit(skb); - } return sent; } @@ -1212,109 +1214,38 @@ ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && !ieee80211_is_nullfunc(fc) && - (!ieee80211_is_mgmt(fc) || - (ieee80211_is_unicast_robust_mgmt_frame(rx->skb) && - rx->sta && test_sta_flags(rx->sta, WLAN_STA_MFP))) && - (rx->key || rx->sdata->drop_unencrypted))) - return -EACCES; - /* BIP does not use Protected field, so need to check MMIE */ - if (unlikely(rx->sta && test_sta_flags(rx->sta, WLAN_STA_MFP) && - ieee80211_is_multicast_robust_mgmt_frame(rx->skb) && - ieee80211_get_mmie_keyidx(rx->skb) < 0 && + ieee80211_is_data(fc) && (rx->key || rx->sdata->drop_unencrypted))) return -EACCES; + if (rx->sta && test_sta_flags(rx->sta, WLAN_STA_MFP)) { + if (unlikely(ieee80211_is_unicast_robust_mgmt_frame(rx->skb) && + rx->key)) + return -EACCES; + /* BIP does not use Protected field, so need to check MMIE */ + if (unlikely(ieee80211_is_multicast_robust_mgmt_frame(rx->skb) + && ieee80211_get_mmie_keyidx(rx->skb) < 0 && + rx->key)) + return -EACCES; + /* + * When using MFP, Action frames are not allowed prior to + * having configured keys. + */ + if (unlikely(ieee80211_is_action(fc) && !rx->key && + ieee80211_is_robust_mgmt_frame( + (struct ieee80211_hdr *) rx->skb->data))) + return -EACCES; + } return 0; } static int -ieee80211_data_to_8023(struct ieee80211_rx_data *rx) +__ieee80211_data_to_8023(struct ieee80211_rx_data *rx) { struct net_device *dev = rx->dev; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) rx->skb->data; - u16 hdrlen, ethertype; - u8 *payload; - u8 dst[ETH_ALEN]; - u8 src[ETH_ALEN] __aligned(2); - struct sk_buff *skb = rx->skb; struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) - return -1; - - hdrlen = ieee80211_hdrlen(hdr->frame_control); - - /* convert IEEE 802.11 header + possible LLC headers into Ethernet - * header - * IEEE 802.11 address fields: - * ToDS FromDS Addr1 Addr2 Addr3 Addr4 - * 0 0 DA SA BSSID n/a - * 0 1 DA BSSID SA n/a - * 1 0 BSSID SA DA n/a - * 1 1 RA TA DA SA - */ - memcpy(dst, ieee80211_get_DA(hdr), ETH_ALEN); - memcpy(src, ieee80211_get_SA(hdr), ETH_ALEN); - - switch (hdr->frame_control & - cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) { - case cpu_to_le16(IEEE80211_FCTL_TODS): - if (unlikely(sdata->vif.type != NL80211_IFTYPE_AP && - sdata->vif.type != NL80211_IFTYPE_AP_VLAN)) - return -1; - break; - case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS): - if (unlikely(sdata->vif.type != NL80211_IFTYPE_WDS && - sdata->vif.type != NL80211_IFTYPE_MESH_POINT)) - return -1; - if (ieee80211_vif_is_mesh(&sdata->vif)) { - struct ieee80211s_hdr *meshdr = (struct ieee80211s_hdr *) - (skb->data + hdrlen); - hdrlen += ieee80211_get_mesh_hdrlen(meshdr); - if (meshdr->flags & MESH_FLAGS_AE_A5_A6) { - memcpy(dst, meshdr->eaddr1, ETH_ALEN); - memcpy(src, meshdr->eaddr2, ETH_ALEN); - } - } - break; - case cpu_to_le16(IEEE80211_FCTL_FROMDS): - if (sdata->vif.type != NL80211_IFTYPE_STATION || - (is_multicast_ether_addr(dst) && - !compare_ether_addr(src, dev->dev_addr))) - return -1; - break; - case cpu_to_le16(0): - if (sdata->vif.type != NL80211_IFTYPE_ADHOC) - return -1; - break; - } - - if (unlikely(skb->len - hdrlen < 8)) - return -1; - - payload = skb->data + hdrlen; - ethertype = (payload[6] << 8) | payload[7]; - - if (likely((compare_ether_addr(payload, rfc1042_header) == 0 && - ethertype != ETH_P_AARP && ethertype != ETH_P_IPX) || - compare_ether_addr(payload, bridge_tunnel_header) == 0)) { - /* remove RFC1042 or Bridge-Tunnel encapsulation and - * replace EtherType */ - skb_pull(skb, hdrlen + 6); - memcpy(skb_push(skb, ETH_ALEN), src, ETH_ALEN); - memcpy(skb_push(skb, ETH_ALEN), dst, ETH_ALEN); - } else { - struct ethhdr *ehdr; - __be16 len; - - skb_pull(skb, hdrlen); - len = htons(skb->len); - ehdr = (struct ethhdr *) skb_push(skb, sizeof(struct ethhdr)); - memcpy(ehdr->h_dest, dst, ETH_ALEN); - memcpy(ehdr->h_source, src, ETH_ALEN); - ehdr->h_proto = len; - } - return 0; + return ieee80211_data_to_8023(rx->skb, dev->dev_addr, sdata->vif.type); } /* @@ -1397,7 +1328,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) * mac80211. That also explains the __skb_push() * below. */ - align = (unsigned long)skb->data & 3; + align = ((unsigned long)(skb->data + sizeof(struct ethhdr))) & 3; if (align) { if (WARN_ON(skb_headroom(skb) < 3)) { dev_kfree_skb(skb); @@ -1453,7 +1384,7 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) if (!(rx->flags & IEEE80211_RX_AMSDU)) return RX_CONTINUE; - err = ieee80211_data_to_8023(rx); + err = __ieee80211_data_to_8023(rx); if (unlikely(err)) return RX_DROP_UNUSABLE; @@ -1639,7 +1570,7 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) return RX_DROP_MONITOR; - err = ieee80211_data_to_8023(rx); + err = __ieee80211_data_to_8023(rx); if (unlikely(err)) return RX_DROP_UNUSABLE; @@ -1827,6 +1758,9 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) sizeof(mgmt->u.action.u.chan_switch))) return RX_DROP_MONITOR; + if (sdata->vif.type != NL80211_IFTYPE_STATION) + return RX_DROP_MONITOR; + if (memcmp(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN)) return RX_DROP_MONITOR; @@ -1837,7 +1771,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) if (!bss) return RX_DROP_MONITOR; - ieee80211_process_chanswitch(sdata, + ieee80211_sta_process_chanswitch(sdata, &mgmt->u.action.u.chan_switch.sw_elem, bss); ieee80211_rx_bss_put(local, bss); break; @@ -1932,7 +1866,7 @@ 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); + mac80211_ev_michael_mic_failure(rx->sdata, keyidx, hdr, NULL); ignore: dev_kfree_skb(rx->skb); rx->skb = NULL; @@ -2287,6 +2221,43 @@ static inline u16 seq_sub(u16 sq1, u16 sq2) } +static void ieee80211_release_reorder_frame(struct ieee80211_hw *hw, + struct tid_ampdu_rx *tid_agg_rx, + int index) +{ + struct ieee80211_supported_band *sband; + struct ieee80211_rate *rate; + struct ieee80211_rx_status status; + + if (!tid_agg_rx->reorder_buf[index]) + goto no_frame; + + /* 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) + 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); + tid_agg_rx->stored_mpdu_num--; + tid_agg_rx->reorder_buf[index] = NULL; + +no_frame: + tid_agg_rx->head_seq_num = seq_inc(tid_agg_rx->head_seq_num); +} + + +/* + * Timeout (in jiffies) for skb's that are waiting in the RX reorder buffer. If + * the skb was added to the buffer longer than this time ago, the earlier + * frames that have not yet been received are assumed to be lost and the skb + * can be released for processing. This may also release other skb's from the + * reorder buffer if there are no additional gaps between the frames. + */ +#define HT_RX_REORDER_BUF_TIMEOUT (HZ / 10) + /* * As it function blongs to Rx path it must be called with * the proper rcu_read_lock protection for its flow. @@ -2298,12 +2269,8 @@ static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, u16 mpdu_seq_num, int bar_req) { - struct ieee80211_local *local = hw_to_local(hw); - struct ieee80211_rx_status status; u16 head_seq_num, buf_size; int index; - struct ieee80211_supported_band *sband; - struct ieee80211_rate *rate; buf_size = tid_agg_rx->buf_size; head_seq_num = tid_agg_rx->head_seq_num; @@ -2328,28 +2295,8 @@ static u8 ieee80211_sta_manage_reorder_buf(struct ieee80211_hw *hw, index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) % tid_agg_rx->buf_size; - - if (tid_agg_rx->reorder_buf[index]) { - /* release the reordered frames to stack */ - memcpy(&status, - tid_agg_rx->reorder_buf[index]->cb, - sizeof(status)); - sband = local->hw.wiphy->bands[status.band]; - if (status.flag & RX_FLAG_HT) { - /* TODO: HT rates */ - rate = sband->bitrates; - } else { - rate = &sband->bitrates - [status.rate_idx]; - } - __ieee80211_rx_handle_packet(hw, - tid_agg_rx->reorder_buf[index], - &status, rate); - tid_agg_rx->stored_mpdu_num--; - tid_agg_rx->reorder_buf[index] = NULL; - } - tid_agg_rx->head_seq_num = - seq_inc(tid_agg_rx->head_seq_num); + ieee80211_release_reorder_frame(hw, tid_agg_rx, + index); } if (bar_req) return 1; @@ -2376,26 +2323,50 @@ 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) % tid_agg_rx->buf_size; - while (tid_agg_rx->reorder_buf[index]) { - /* release the reordered frame back to stack */ - memcpy(&status, tid_agg_rx->reorder_buf[index]->cb, - sizeof(status)); - sband = local->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); - tid_agg_rx->stored_mpdu_num--; - tid_agg_rx->reorder_buf[index] = NULL; - tid_agg_rx->head_seq_num = seq_inc(tid_agg_rx->head_seq_num); + if (!tid_agg_rx->reorder_buf[index] && + tid_agg_rx->stored_mpdu_num > 1) { + /* + * No buffers ready to be released, but check whether any + * frames in the reorder buffer have timed out. + */ + int j; + int skipped = 1; + for (j = (index + 1) % tid_agg_rx->buf_size; j != index; + j = (j + 1) % tid_agg_rx->buf_size) { + if (tid_agg_rx->reorder_buf[j] == NULL) { + skipped++; + continue; + } + if (!time_after(jiffies, tid_agg_rx->reorder_time[j] + + HZ / 10)) + break; + +#ifdef CONFIG_MAC80211_HT_DEBUG + if (net_ratelimit()) + printk(KERN_DEBUG "%s: release an RX reorder " + "frame due to timeout on earlier " + "frames\n", + wiphy_name(hw->wiphy)); +#endif + ieee80211_release_reorder_frame(hw, tid_agg_rx, j); + + /* + * Increment the head seq# also for the skipped slots. + */ + tid_agg_rx->head_seq_num = + (tid_agg_rx->head_seq_num + skipped) & + SEQ_MASK; + skipped = 0; + } + } else while (tid_agg_rx->reorder_buf[index]) { + ieee80211_release_reorder_frame(hw, tid_agg_rx, index); index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) % tid_agg_rx->buf_size; } @@ -2482,6 +2453,18 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb, return; } + /* + * If we're suspending, it is possible although not too likely + * that we'd be receiving frames after having already partially + * quiesced the stack. We can't process such frames then since + * 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 (status->flag & RX_FLAG_HT) { /* rate_idx is MCS index */ if (WARN_ON(status->rate_idx < 0 || @@ -2517,6 +2500,18 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb, return; } + /* + * In theory, the block ack reordering should happen after duplicate + * removal (ieee80211_rx_h_check(), which is an RX handler). As such, + * the call to ieee80211_rx_reorder_ampdu() should really be moved to + * happen as a new RX handler between ieee80211_rx_h_check and + * ieee80211_rx_h_decrypt. This cleanup may eventually happen, but for + * the time being, the call can be here since RX reorder buf processing + * will implicitly skip duplicates. We could, in theory at least, + * process frames that ieee80211_rx_h_passive_scan would drop (e.g., + * 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); diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 3bf9839f591..2a8d09ad17f 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -21,6 +21,7 @@ #include <net/iw_handler.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "mesh.h" #define IEEE80211_PROBE_DELAY (HZ / 33) @@ -202,18 +203,6 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, return RX_QUEUED; } -void ieee80211_scan_failed(struct ieee80211_local *local) -{ - if (WARN_ON(!local->scan_req)) - return; - - /* notify cfg80211 about the failed scan */ - if (local->scan_req != &local->int_scan_req) - cfg80211_scan_done(local->scan_req, true); - - local->scan_req = NULL; -} - /* * inform AP that we will go to sleep so that it will buffer the frames * while we scan @@ -253,7 +242,7 @@ static void ieee80211_scan_ps_disable(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; - if (!local->powersave) + if (!local->ps_sdata) ieee80211_send_nullfunc(local, sdata, 0); else { /* @@ -274,51 +263,62 @@ static void ieee80211_scan_ps_disable(struct ieee80211_sub_if_data *sdata) } } +static void ieee80211_restore_scan_ies(struct ieee80211_local *local) +{ + kfree(local->scan_req->ie); + local->scan_req->ie = local->orig_ies; + local->scan_req->ie_len = local->orig_ies_len; +} + void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; + bool was_hw_scan; - if (WARN_ON(!local->hw_scanning && !local->sw_scanning)) + mutex_lock(&local->scan_mtx); + + if (WARN_ON(!local->hw_scanning && !local->sw_scanning)) { + mutex_unlock(&local->scan_mtx); return; + } - if (WARN_ON(!local->scan_req)) + if (WARN_ON(!local->scan_req)) { + mutex_unlock(&local->scan_mtx); return; + } + + if (local->hw_scanning) + ieee80211_restore_scan_ies(local); if (local->scan_req != &local->int_scan_req) cfg80211_scan_done(local->scan_req, aborted); local->scan_req = NULL; - local->last_scan_completed = jiffies; + was_hw_scan = local->hw_scanning; + local->hw_scanning = false; + local->sw_scanning = false; + local->scan_channel = NULL; - if (local->hw_scanning) { - local->hw_scanning = false; - /* - * Somebody might have requested channel change during scan - * that we won't have acted upon, try now. ieee80211_hw_config - * will set the flag based on actual changes. - */ - ieee80211_hw_config(local, 0); - goto done; - } + /* we only have to protect scan_req and hw/sw scan */ + mutex_unlock(&local->scan_mtx); - local->sw_scanning = false; ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + if (was_hw_scan) + goto done; netif_tx_lock_bh(local->mdev); netif_addr_lock(local->mdev); local->filter_flags &= ~FIF_BCN_PRBRESP_PROMISC; - local->ops->configure_filter(local_to_hw(local), - FIF_BCN_PRBRESP_PROMISC, - &local->filter_flags, - local->mdev->mc_count, - local->mdev->mc_list); + 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); - if (local->ops->sw_scan_complete) - local->ops->sw_scan_complete(local_to_hw(local)); + drv_sw_scan_complete(local); mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { @@ -338,18 +338,160 @@ void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) if (sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_ADHOC || sdata->vif.type == NL80211_IFTYPE_MESH_POINT) - ieee80211_if_config(sdata, - IEEE80211_IFCC_BEACON_ENABLED); + ieee80211_bss_info_change_notify( + sdata, BSS_CHANGED_BEACON_ENABLED); } mutex_unlock(&local->iflist_mtx); done: + ieee80211_recalc_idle(local); ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); ieee80211_mesh_notify_scan_completed(local); } EXPORT_SYMBOL(ieee80211_scan_completed); +static int ieee80211_start_sw_scan(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + + /* + * Hardware/driver doesn't support hw_scan, so use software + * scanning instead. First send a nullfunc frame with power save + * bit on so that AP will buffer the frames for us while we are not + * listening, then send probe requests to each channel and wait for + * the responses. After all channels are scanned, tune back to the + * original channel and send a nullfunc frame with power save bit + * off to trigger the AP to send us all the buffered frames. + * + * Note that while local->sw_scanning is true everything else but + * nullfunc frames and probe requests will be dropped in + * ieee80211_tx_h_check_assoc(). + */ + drv_sw_scan_start(local); + + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata, &local->interfaces, list) { + if (!netif_running(sdata->dev)) + continue; + + /* disable beaconing */ + if (sdata->vif.type == NL80211_IFTYPE_AP || + sdata->vif.type == NL80211_IFTYPE_ADHOC || + sdata->vif.type == NL80211_IFTYPE_MESH_POINT) + 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 + netif_tx_stop_all_queues(sdata->dev); + } + mutex_unlock(&local->iflist_mtx); + + local->scan_state = SCAN_SET_CHANNEL; + 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); + + /* TODO: start scan as soon as all nullfunc frames are ACKed */ + queue_delayed_work(local->hw.workqueue, &local->scan_work, + IEEE80211_CHANNEL_TIME); + + return 0; +} + + +static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, + struct cfg80211_scan_request *req) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + int rc; + + if (local->scan_req) + return -EBUSY; + + if (local->ops->hw_scan) { + u8 *ies; + int ielen; + + ies = kmalloc(2 + IEEE80211_MAX_SSID_LEN + + local->scan_ies_len + req->ie_len, GFP_KERNEL); + if (!ies) + return -ENOMEM; + + ielen = ieee80211_build_preq_ies(local, ies, + req->ie, req->ie_len); + local->orig_ies = req->ie; + local->orig_ies_len = req->ie_len; + req->ie = ies; + req->ie_len = ielen; + } + + local->scan_req = req; + local->scan_sdata = sdata; + + 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 */ + set_bit(IEEE80211_STA_REQ_SCAN, &ifmgd->request); + return 0; + } + + if (local->ops->hw_scan) + local->hw_scanning = true; + else + local->sw_scanning = true; + /* + * Kicking off the scan need not be protected, + * only the scan variable stuff, since now + * local->scan_req is assigned and other callers + * will abort their scan attempts. + * + * This avoids getting a scan_mtx -> iflist_mtx + * dependency, so that the scan completed calls + * have more locking freedom. + */ + + ieee80211_recalc_idle(local); + mutex_unlock(&local->scan_mtx); + + if (local->ops->hw_scan) + rc = drv_hw_scan(local, local->scan_req); + else + rc = ieee80211_start_sw_scan(local); + + mutex_lock(&local->scan_mtx); + + if (rc) { + if (local->ops->hw_scan) { + local->hw_scanning = false; + ieee80211_restore_scan_ies(local); + } else + local->sw_scanning = false; + + ieee80211_recalc_idle(local); + + local->scan_req = NULL; + local->scan_sdata = NULL; + } + + return rc; +} + void ieee80211_scan_work(struct work_struct *work) { struct ieee80211_local *local = @@ -359,17 +501,41 @@ void ieee80211_scan_work(struct work_struct *work) int skip, i; unsigned long next_delay = 0; + mutex_lock(&local->scan_mtx); + if (!sdata || !local->scan_req) { + mutex_unlock(&local->scan_mtx); + return; + } + + if (local->scan_req && !(local->sw_scanning || local->hw_scanning)) { + struct cfg80211_scan_request *req = local->scan_req; + int rc; + + local->scan_req = NULL; + + rc = __ieee80211_start_scan(sdata, req); + mutex_unlock(&local->scan_mtx); + + if (rc) + ieee80211_scan_completed(&local->hw, true); + return; + } + + mutex_unlock(&local->scan_mtx); + /* * Avoid re-scheduling when the sdata is going away. */ - if (!netif_running(sdata->dev)) + if (!netif_running(sdata->dev)) { + ieee80211_scan_completed(&local->hw, true); 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_to_hw(local), false); + ieee80211_scan_completed(&local->hw, false); return; } skip = 0; @@ -393,24 +559,39 @@ void ieee80211_scan_work(struct work_struct *work) if (skip) break; - next_delay = IEEE80211_PROBE_DELAY + - usecs_to_jiffies(local->hw.channel_change_time); + /* + * 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; + break; + } + + next_delay = IEEE80211_PROBE_DELAY; local->scan_state = SCAN_SEND_PROBE; break; case SCAN_SEND_PROBE: - next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; - local->scan_state = SCAN_SET_CHANNEL; - - if (local->scan_channel->flags & IEEE80211_CHAN_PASSIVE_SCAN || - !local->scan_req->n_ssids) - break; 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; } @@ -418,150 +599,53 @@ void ieee80211_scan_work(struct work_struct *work) next_delay); } - -int ieee80211_start_scan(struct ieee80211_sub_if_data *scan_sdata, - struct cfg80211_scan_request *req) +int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, + struct cfg80211_scan_request *req) { - struct ieee80211_local *local = scan_sdata->local; - struct ieee80211_sub_if_data *sdata; - - if (!req) - return -EINVAL; - - if (local->scan_req && local->scan_req != req) - return -EBUSY; - - local->scan_req = req; - - /* MLME-SCAN.request (page 118) page 144 (11.1.3.1) - * BSSType: INFRASTRUCTURE, INDEPENDENT, ANY_BSS - * BSSID: MACAddress - * SSID - * ScanType: ACTIVE, PASSIVE - * ProbeDelay: delay (in microseconds) to be used prior to transmitting - * a Probe frame during active scanning - * ChannelList - * MinChannelTime (>= ProbeDelay), in TU - * MaxChannelTime: (>= MinChannelTime), in TU - */ - - /* MLME-SCAN.confirm - * BSSDescriptionSet - * ResultCode: SUCCESS, INVALID_PARAMETERS - */ - - if (local->sw_scanning || local->hw_scanning) { - if (local->scan_sdata == scan_sdata) - return 0; - return -EBUSY; - } - - if (local->ops->hw_scan) { - int rc; - - local->hw_scanning = true; - rc = local->ops->hw_scan(local_to_hw(local), req); - if (rc) { - local->hw_scanning = false; - return rc; - } - local->scan_sdata = scan_sdata; - return 0; - } - - /* - * Hardware/driver doesn't support hw_scan, so use software - * scanning instead. First send a nullfunc frame with power save - * bit on so that AP will buffer the frames for us while we are not - * listening, then send probe requests to each channel and wait for - * the responses. After all channels are scanned, tune back to the - * original channel and send a nullfunc frame with power save bit - * off to trigger the AP to send us all the buffered frames. - * - * Note that while local->sw_scanning is true everything else but - * nullfunc frames and probe requests will be dropped in - * ieee80211_tx_h_check_assoc(). - */ - local->sw_scanning = true; - if (local->ops->sw_scan_start) - local->ops->sw_scan_start(local_to_hw(local)); + int res; - mutex_lock(&local->iflist_mtx); - list_for_each_entry(sdata, &local->interfaces, list) { - if (!netif_running(sdata->dev)) - continue; + mutex_lock(&sdata->local->scan_mtx); + res = __ieee80211_start_scan(sdata, req); + mutex_unlock(&sdata->local->scan_mtx); - /* disable beaconing */ - if (sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_ADHOC || - sdata->vif.type == NL80211_IFTYPE_MESH_POINT) - ieee80211_if_config(sdata, - IEEE80211_IFCC_BEACON_ENABLED); + return res; +} - 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 - netif_tx_stop_all_queues(sdata->dev); - } - mutex_unlock(&local->iflist_mtx); +int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, + const u8 *ssid, u8 ssid_len) +{ + struct ieee80211_local *local = sdata->local; + int ret = -EBUSY; - local->scan_state = SCAN_SET_CHANNEL; - local->scan_channel_idx = 0; - local->scan_sdata = scan_sdata; - local->scan_req = req; + mutex_lock(&local->scan_mtx); - netif_addr_lock_bh(local->mdev); - local->filter_flags |= FIF_BCN_PRBRESP_PROMISC; - local->ops->configure_filter(local_to_hw(local), - FIF_BCN_PRBRESP_PROMISC, - &local->filter_flags, - local->mdev->mc_count, - local->mdev->mc_list); - netif_addr_unlock_bh(local->mdev); + /* busy scanning */ + if (local->scan_req) + goto unlock; - /* TODO: start scan as soon as all nullfunc frames are ACKed */ - queue_delayed_work(local->hw.workqueue, &local->scan_work, - IEEE80211_CHANNEL_TIME); + memcpy(local->int_scan_req.ssids[0].ssid, ssid, IEEE80211_MAX_SSID_LEN); + local->int_scan_req.ssids[0].ssid_len = ssid_len; - return 0; + ret = __ieee80211_start_scan(sdata, &sdata->local->int_scan_req); + unlock: + mutex_unlock(&local->scan_mtx); + return ret; } - -int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, - struct cfg80211_scan_request *req) +void ieee80211_scan_cancel(struct ieee80211_local *local) { - struct ieee80211_local *local = sdata->local; - struct ieee80211_if_managed *ifmgd; - - if (!req) - return -EINVAL; + bool swscan; - if (local->scan_req && local->scan_req != req) - return -EBUSY; - - local->scan_req = req; - - if (sdata->vif.type != NL80211_IFTYPE_STATION) - return ieee80211_start_scan(sdata, req); + cancel_delayed_work_sync(&local->scan_work); /* - * STA has a state machine that might need to defer scanning - * while it's trying to associate/authenticate, therefore we - * queue it up to the state machine in that case. + * Only call this function when a scan can't be + * queued -- mostly at suspend under RTNL. */ + mutex_lock(&local->scan_mtx); + swscan = local->sw_scanning; + mutex_unlock(&local->scan_mtx); - if (local->sw_scanning || local->hw_scanning) { - if (local->scan_sdata == sdata) - return 0; - return -EBUSY; - } - - ifmgd = &sdata->u.mgd; - set_bit(IEEE80211_STA_REQ_SCAN, &ifmgd->request); - queue_work(local->hw.workqueue, &ifmgd->work); - - return 0; + if (swscan) + ieee80211_scan_completed(&local->hw, true); } diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 5f7a2624ed7..68953033403 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -15,7 +15,7 @@ */ #include <linux/ieee80211.h> -#include <net/wireless.h> +#include <net/cfg80211.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "sta_info.h" @@ -84,104 +84,3 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, mgmt->sa, mgmt->bssid, mgmt->u.action.u.measurement.dialog_token); } - -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; - - sdata->local->oper_channel = sdata->local->csa_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; - - 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); -} - -void ieee80211_chswitch_timer(unsigned long data) -{ - struct ieee80211_sub_if_data *sdata = - (struct ieee80211_sub_if_data *) data; - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - - queue_work(sdata->local->hw.workqueue, &ifmgd->chswitch_work); -} - -void ieee80211_process_chanswitch(struct ieee80211_sub_if_data *sdata, - struct ieee80211_channel_sw_ie *sw_elem, - struct ieee80211_bss *bss) -{ - struct ieee80211_channel *new_ch; - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num); - - /* FIXME: Handle ADHOC later */ - if (sdata->vif.type != NL80211_IFTYPE_STATION) - return; - - if (ifmgd->state != IEEE80211_STA_MLME_ASSOCIATED) - return; - - if (sdata->local->sw_scanning || sdata->local->hw_scanning) - return; - - /* Disregard subsequent beacons if we are already running a timer - processing a CSA */ - - if (ifmgd->flags & IEEE80211_STA_CSA_RECEIVED) - return; - - new_ch = ieee80211_get_channel(sdata->local->hw.wiphy, new_freq); - if (!new_ch || new_ch->flags & IEEE80211_CHAN_DISABLED) - return; - - sdata->local->csa_channel = new_ch; - - if (sw_elem->count <= 1) { - queue_work(sdata->local->hw.workqueue, &ifmgd->chswitch_work); - } else { - ieee80211_stop_queues_by_reason(&sdata->local->hw, - IEEE80211_QUEUE_STOP_REASON_CSA); - ifmgd->flags |= IEEE80211_STA_CSA_RECEIVED; - mod_timer(&ifmgd->chswitch_timer, - jiffies + - msecs_to_jiffies(sw_elem->count * - bss->cbss.beacon_interval)); - } -} - -void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, - u16 capab_info, u8 *pwr_constr_elem, - u8 pwr_constr_elem_len) -{ - struct ieee80211_conf *conf = &sdata->local->hw.conf; - - if (!(capab_info & WLAN_CAPABILITY_SPECTRUM_MGMT)) - return; - - /* Power constraint IE length should be 1 octet */ - if (pwr_constr_elem_len != 1) - return; - - if ((*pwr_constr_elem <= conf->channel->max_power) && - (*pwr_constr_elem != sdata->local->power_constr_level)) { - sdata->local->power_constr_level = *pwr_constr_elem; - ieee80211_hw_config(sdata->local, 0); - } -} - diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index c5f14e6bbde..a360bceeba5 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -19,6 +19,7 @@ #include <net/mac80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "rate.h" #include "sta_info.h" #include "debugfs_sta.h" @@ -43,6 +44,15 @@ * When the insertion fails (sta_info_insert()) returns non-zero), the * structure will have been freed by sta_info_insert()! * + * sta entries are added by mac80211 when you establish a link with a + * peer. This means different things for the different type of interfaces + * we support. For a regular station this mean we add the AP sta when we + * receive an assocation response from the AP. For IBSS this occurs when + * we receive a probe response or a beacon from target IBSS network. For + * WDS we add the sta for the peer imediately upon device open. When using + * AP mode we add stations for each respective station upon request from + * userspace through nl80211. + * * Because there are debugfs entries for each station, and adding those * must be able to sleep, it is also possible to "pin" a station entry, * that means it can be removed from the hash table but not be freed. @@ -292,6 +302,9 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, skb_queue_head_init(&sta->ps_tx_buf); skb_queue_head_init(&sta->tx_filtered); + for (i = 0; i < NUM_RX_DATA_QUEUES; i++) + sta->last_seq_ctrl[i] = cpu_to_le16(USHORT_MAX); + #ifdef CONFIG_MAC80211_VERBOSE_DEBUG printk(KERN_DEBUG "%s: Allocated STA %pM\n", wiphy_name(local->hw.wiphy), sta->sta.addr); @@ -346,8 +359,7 @@ int sta_info_insert(struct sta_info *sta) struct ieee80211_sub_if_data, u.ap); - local->ops->sta_notify(local_to_hw(local), &sdata->vif, - STA_NOTIFY_ADD, &sta->sta); + drv_sta_notify(local, &sdata->vif, STA_NOTIFY_ADD, &sta->sta); } #ifdef CONFIG_MAC80211_VERBOSE_DEBUG @@ -405,8 +417,7 @@ static void __sta_info_set_tim_bit(struct ieee80211_if_ap *bss, if (sta->local->ops->set_tim) { sta->local->tim_in_locked_section = true; - sta->local->ops->set_tim(local_to_hw(sta->local), - &sta->sta, true); + drv_set_tim(sta->local, &sta->sta, true); sta->local->tim_in_locked_section = false; } } @@ -431,8 +442,7 @@ static void __sta_info_clear_tim_bit(struct ieee80211_if_ap *bss, if (sta->local->ops->set_tim) { sta->local->tim_in_locked_section = true; - sta->local->ops->set_tim(local_to_hw(sta->local), - &sta->sta, false); + drv_set_tim(sta->local, &sta->sta, false); sta->local->tim_in_locked_section = false; } } @@ -482,8 +492,8 @@ static void __sta_info_unlink(struct sta_info **sta) struct ieee80211_sub_if_data, u.ap); - local->ops->sta_notify(local_to_hw(local), &sdata->vif, - STA_NOTIFY_REMOVE, &(*sta)->sta); + drv_sta_notify(local, &sdata->vif, STA_NOTIFY_REMOVE, + &(*sta)->sta); } if (ieee80211_vif_is_mesh(&sdata->vif)) { @@ -543,9 +553,8 @@ void sta_info_unlink(struct sta_info **sta) spin_unlock_irqrestore(&local->sta_lock, flags); } -static inline int sta_info_buffer_expired(struct ieee80211_local *local, - struct sta_info *sta, - struct sk_buff *skb) +static int sta_info_buffer_expired(struct sta_info *sta, + struct sk_buff *skb) { struct ieee80211_tx_info *info; int timeout; @@ -556,8 +565,9 @@ static inline int sta_info_buffer_expired(struct ieee80211_local *local, info = IEEE80211_SKB_CB(skb); /* Timeout: (2 * listen_interval * beacon_int * 1024 / 1000000) sec */ - timeout = (sta->listen_interval * local->hw.conf.beacon_int * 32 / - 15625) * HZ; + timeout = (sta->listen_interval * + sta->sdata->vif.bss_conf.beacon_int * + 32 / 15625) * HZ; if (timeout < STA_TX_BUFFER_EXPIRE) timeout = STA_TX_BUFFER_EXPIRE; return time_after(jiffies, info->control.jiffies + timeout); @@ -577,7 +587,7 @@ static void sta_info_cleanup_expire_buffered(struct ieee80211_local *local, for (;;) { spin_lock_irqsave(&sta->ps_tx_buf.lock, flags); skb = skb_peek(&sta->ps_tx_buf); - if (sta_info_buffer_expired(local, sta, skb)) + if (sta_info_buffer_expired(sta, skb)) skb = __skb_dequeue(&sta->ps_tx_buf); else skb = NULL; @@ -610,6 +620,9 @@ static void sta_info_cleanup(unsigned long data) sta_info_cleanup_expire_buffered(local, sta); rcu_read_unlock(); + if (local->quiescing) + return; + local->sta_cleanup.expires = round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL); add_timer(&local->sta_cleanup); @@ -686,41 +699,10 @@ static void sta_info_debugfs_add_work(struct work_struct *work) } #endif -static void __ieee80211_run_pending_flush(struct ieee80211_local *local) -{ - struct sta_info *sta; - unsigned long flags; - - ASSERT_RTNL(); - - spin_lock_irqsave(&local->sta_lock, flags); - while (!list_empty(&local->sta_flush_list)) { - sta = list_first_entry(&local->sta_flush_list, - struct sta_info, list); - list_del(&sta->list); - spin_unlock_irqrestore(&local->sta_lock, flags); - sta_info_destroy(sta); - spin_lock_irqsave(&local->sta_lock, flags); - } - spin_unlock_irqrestore(&local->sta_lock, flags); -} - -static void ieee80211_sta_flush_work(struct work_struct *work) -{ - struct ieee80211_local *local = - container_of(work, struct ieee80211_local, sta_flush_work); - - rtnl_lock(); - __ieee80211_run_pending_flush(local); - rtnl_unlock(); -} - void sta_info_init(struct ieee80211_local *local) { spin_lock_init(&local->sta_lock); INIT_LIST_HEAD(&local->sta_list); - INIT_LIST_HEAD(&local->sta_flush_list); - INIT_WORK(&local->sta_flush_work, ieee80211_sta_flush_work); setup_timer(&local->sta_cleanup, sta_info_cleanup, (unsigned long)local); @@ -741,7 +723,6 @@ int sta_info_start(struct ieee80211_local *local) void sta_info_stop(struct ieee80211_local *local) { del_timer(&local->sta_cleanup); - cancel_work_sync(&local->sta_flush_work); #ifdef CONFIG_MAC80211_DEBUGFS /* * Make sure the debugfs adding work isn't pending after this @@ -752,10 +733,7 @@ void sta_info_stop(struct ieee80211_local *local) cancel_work_sync(&local->sta_debugfs_add); #endif - rtnl_lock(); sta_info_flush(local, NULL); - __ieee80211_run_pending_flush(local); - rtnl_unlock(); } /** @@ -767,7 +745,7 @@ void sta_info_stop(struct ieee80211_local *local) * @sdata: matching rule for the net device (sta->dev) or %NULL to match all STAs */ int sta_info_flush(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) + struct ieee80211_sub_if_data *sdata) { struct sta_info *sta, *tmp; LIST_HEAD(tmp_list); @@ -775,7 +753,6 @@ int sta_info_flush(struct ieee80211_local *local, unsigned long flags; might_sleep(); - ASSERT_RTNL(); spin_lock_irqsave(&local->sta_lock, flags); list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { @@ -795,39 +772,6 @@ int sta_info_flush(struct ieee80211_local *local, return ret; } -/** - * sta_info_flush_delayed - flush matching STA entries from the STA table - * - * This function unlinks all stations for a given interface and queues - * them for freeing. Note that the workqueue function scheduled here has - * to run before any new keys can be added to the system to avoid set_key() - * callback ordering issues. - * - * @sdata: the interface - */ -void sta_info_flush_delayed(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_local *local = sdata->local; - struct sta_info *sta, *tmp; - unsigned long flags; - bool work = false; - - spin_lock_irqsave(&local->sta_lock, flags); - list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { - if (sdata == sta->sdata) { - __sta_info_unlink(&sta); - if (sta) { - list_add_tail(&sta->list, - &local->sta_flush_list); - work = true; - } - } - } - if (work) - schedule_work(&local->sta_flush_work); - spin_unlock_irqrestore(&local->sta_lock, flags); -} - void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, unsigned long exp_time) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 5534d489f50..49a1a1f7651 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -88,6 +88,7 @@ struct tid_ampdu_tx { * struct tid_ampdu_rx - TID aggregation information (Rx). * * @reorder_buf: buffer to reorder incoming aggregated MPDUs + * @reorder_time: jiffies when skb was added * @session_timer: check if peer keeps Tx-ing on the TID (by timeout value) * @head_seq_num: head sequence number in reordering buffer. * @stored_mpdu_num: number of MPDUs in reordering buffer @@ -99,6 +100,7 @@ struct tid_ampdu_tx { */ struct tid_ampdu_rx { struct sk_buff **reorder_buf; + unsigned long *reorder_time; struct timer_list session_timer; u16 head_seq_num; u16 stored_mpdu_num; @@ -214,6 +216,7 @@ struct sta_ampdu_mlme { * @plink_state: peer link state * @plink_timeout: timeout of peer link * @plink_timer: peer link watch timer + * @plink_timer_was_running: used by suspend/resume to restore timers * @debugfs: debug filesystem info * @sta: station information we share with the driver */ @@ -291,6 +294,7 @@ struct sta_info { __le16 reason; u8 plink_retries; bool ignore_plink_timer; + bool plink_timer_was_running; enum plink_state plink_state; u32 plink_timeout; struct timer_list plink_timer; @@ -442,8 +446,7 @@ void sta_info_init(struct ieee80211_local *local); int sta_info_start(struct ieee80211_local *local); void sta_info_stop(struct ieee80211_local *local); int sta_info_flush(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata); -void sta_info_flush_delayed(struct ieee80211_sub_if_data *sdata); + struct ieee80211_sub_if_data *sdata); void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, unsigned long exp_time); diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c index 38fa111d2dc..964b7faa7f1 100644 --- a/net/mac80211/tkip.c +++ b/net/mac80211/tkip.c @@ -13,6 +13,7 @@ #include <asm/unaligned.h> #include <net/mac80211.h> +#include "driver-ops.h" #include "key.h" #include "tkip.h" #include "wep.h" @@ -307,9 +308,8 @@ int ieee80211_tkip_decrypt_data(struct crypto_blkcipher *tfm, if (is_multicast_ether_addr(ra)) sta_addr = bcast; - key->local->ops->update_tkip_key( - local_to_hw(key->local), &key->conf, - sta_addr, iv32, key->u.tkip.rx[queue].p1k); + drv_update_tkip_key(key->local, &key->conf, sta_addr, + iv32, key->u.tkip.rx[queue].p1k); } } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 63656266d56..3a8922cd103 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -25,6 +25,7 @@ #include <asm/unaligned.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "led.h" #include "mesh.h" #include "wep.h" @@ -399,6 +400,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta_info_set_tim_bit(sta); info->control.jiffies = jiffies; + info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; skb_queue_tail(&sta->ps_tx_buf, tx->skb); return TX_QUEUED; } @@ -409,8 +411,24 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta->sta.addr); } #endif /* CONFIG_MAC80211_VERBOSE_PS_DEBUG */ - clear_sta_flags(sta, WLAN_STA_PSPOLL); + 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; } @@ -429,7 +447,7 @@ ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx) static ieee80211_tx_result debug_noinline ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) { - struct ieee80211_key *key; + struct ieee80211_key *key = NULL; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; @@ -500,7 +518,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) sband = tx->local->hw.wiphy->bands[tx->channel->band]; len = min_t(int, tx->skb->len + FCS_LEN, - tx->local->fragmentation_threshold); + tx->local->hw.wiphy->frag_threshold); /* set up the tx rate control struct we give the RC algo */ txrc.hw = local_to_hw(tx->local); @@ -511,8 +529,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) txrc.max_rate_idx = tx->sdata->max_ratectrl_rateidx; /* set up RTS protection if desired */ - if (tx->local->rts_threshold < IEEE80211_MAX_RTS_THRESHOLD && - len > tx->local->rts_threshold) { + if (len > tx->local->hw.wiphy->rts_threshold) { txrc.rts = rts = true; } @@ -542,6 +559,10 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) if (unlikely(!info->control.rates[0].count)) info->control.rates[0].count = 1; + if (WARN_ON_ONCE((info->control.rates[0].count > 1) && + (info->flags & IEEE80211_TX_CTL_NO_ACK))) + info->control.rates[0].count = 1; + if (is_multicast_ether_addr(hdr->addr1)) { /* * XXX: verify the rate is in the basic rateset @@ -754,7 +775,7 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) struct sk_buff *skb = tx->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; - int frag_threshold = tx->local->fragmentation_threshold; + int frag_threshold = tx->local->hw.wiphy->frag_threshold; int hdrlen; int fragnum; @@ -852,6 +873,8 @@ ieee80211_tx_h_calculate_duration(struct ieee80211_tx_data *tx) do { hdr = (void *) skb->data; + if (unlikely(ieee80211_is_pspoll(hdr->frame_control))) + break; /* must not overwrite AID */ next_len = skb->next ? skb->next->len : 0; group_addr = is_multicast_ether_addr(hdr->addr1); @@ -885,9 +908,8 @@ ieee80211_tx_h_stats(struct ieee80211_tx_data *tx) * deal with packet injection down monitor interface * with Radiotap Header -- only called for monitor mode interface */ -static ieee80211_tx_result -__ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, - struct sk_buff *skb) +static bool __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, + struct sk_buff *skb) { /* * this is the moment to interpret and discard the radiotap header that @@ -938,7 +960,7 @@ __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, * on transmission */ if (skb->len < (iterator.max_length + FCS_LEN)) - return TX_DROP; + return false; skb_trim(skb, skb->len - FCS_LEN); } @@ -960,7 +982,7 @@ __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, } if (ret != -ENOENT) /* ie, if we didn't simply run out of fields */ - return TX_DROP; + return false; /* * remove the radiotap header @@ -969,7 +991,7 @@ __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, */ skb_pull(skb, iterator.max_length); - return TX_CONTINUE; + return true; } /* @@ -1003,7 +1025,7 @@ __ieee80211_tx_prepare(struct ieee80211_tx_data *tx, /* 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) == TX_DROP) + if (!__ieee80211_parse_tx_radiotap(tx, skb)) return TX_DROP; /* @@ -1067,12 +1089,15 @@ __ieee80211_tx_prepare(struct ieee80211_tx_data *tx, info->flags |= IEEE80211_TX_CTL_NO_ACK; } else { tx->flags |= IEEE80211_TX_UNICAST; - info->flags &= ~IEEE80211_TX_CTL_NO_ACK; + if (unlikely(local->wifi_wme_noack_test)) + info->flags |= IEEE80211_TX_CTL_NO_ACK; + else + info->flags &= ~IEEE80211_TX_CTL_NO_ACK; } if (tx->flags & IEEE80211_TX_FRAGMENTED) { if ((tx->flags & IEEE80211_TX_UNICAST) && - skb->len + FCS_LEN > local->fragmentation_threshold && + skb->len + FCS_LEN > local->hw.wiphy->frag_threshold && !(info->flags & IEEE80211_TX_CTL_AMPDU)) tx->flags |= IEEE80211_TX_FRAGMENTED; else @@ -1147,7 +1172,7 @@ static int __ieee80211_tx(struct ieee80211_local *local, next = skb->next; len = skb->len; - ret = local->ops->tx(local_to_hw(local), skb); + ret = drv_tx(local, skb); if (WARN_ON(ret != NETDEV_TX_OK && skb->len != len)) { dev_kfree_skb(skb); ret = NETDEV_TX_OK; @@ -1213,7 +1238,6 @@ static void ieee80211_tx(struct net_device *dev, struct sk_buff *skb, bool txpending) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct sta_info *sta; struct ieee80211_tx_data tx; ieee80211_tx_result res_prepare; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -1245,7 +1269,6 @@ static void ieee80211_tx(struct net_device *dev, struct sk_buff *skb, return; } - sta = tx.sta; tx.channel = local->hw.conf.channel; info->band = tx.channel->band; @@ -1392,7 +1415,8 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) } if ((local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) && - local->hw.conf.dynamic_ps_timeout > 0) { + local->hw.conf.dynamic_ps_timeout > 0 && + !local->sw_scanning && !local->hw_scanning && local->ps_sdata) { if (local->hw.conf.flags & IEEE80211_CONF_PS) { ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_QUEUE_STOP_REASON_PS); @@ -1431,7 +1455,7 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) monitor_iface = UNKNOWN_ADDRESS; len_rthdr = ieee80211_get_radiotap_len(skb->data); - hdr = (struct ieee80211_hdr *)skb->data + len_rthdr; + hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr); hdrlen = ieee80211_hdrlen(hdr->frame_control); /* check the header is complete in the frame */ @@ -1591,7 +1615,7 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; - int ret = 1, head_need; + int ret = NETDEV_TX_BUSY, head_need; u16 ethertype, hdrlen, meshhdrlen = 0; __le16 fc; struct ieee80211_hdr hdr; @@ -2086,18 +2110,18 @@ struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_hdr *hdr; + struct sk_buff *presp = rcu_dereference(ifibss->presp); - if (!ifibss->probe_resp) + if (!presp) goto out; - skb = skb_copy(ifibss->probe_resp, GFP_ATOMIC); + skb = skb_copy(presp, GFP_ATOMIC); if (!skb) goto out; hdr = (struct ieee80211_hdr *) skb->data; hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); - } else if (ieee80211_vif_is_mesh(&sdata->vif)) { struct ieee80211_mgmt *mgmt; u8 *pos; @@ -2117,7 +2141,7 @@ struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, memcpy(mgmt->sa, sdata->dev->dev_addr, ETH_ALEN); /* BSSID is left zeroed, wildcard value */ mgmt->u.beacon.beacon_int = - cpu_to_le16(local->hw.conf.beacon_int); + cpu_to_le16(sdata->vif.bss_conf.beacon_int); mgmt->u.beacon.capab_info = 0x0; /* 0x0 for MPs */ pos = skb_put(skb, 2); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index fdf432f1455..915e7776931 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -20,27 +20,21 @@ #include <linux/if_arp.h> #include <linux/wireless.h> #include <linux/bitmap.h> +#include <linux/crc32.h> #include <net/net_namespace.h> #include <net/cfg80211.h> #include <net/rtnetlink.h> #include "ieee80211_i.h" +#include "driver-ops.h" #include "rate.h" #include "mesh.h" #include "wme.h" +#include "led.h" /* privid for wiphys to determine whether they belong to us or not */ void *mac80211_wiphy_privid = &mac80211_wiphy_privid; -/* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ -/* Ethernet-II snap header (RFC1042 for most EtherTypes) */ -const unsigned char rfc1042_header[] __aligned(2) = - { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; - -/* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */ -const unsigned char bridge_tunnel_header[] __aligned(2) = - { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; - struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy) { struct ieee80211_local *local; @@ -100,70 +94,6 @@ u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, return NULL; } -unsigned int ieee80211_hdrlen(__le16 fc) -{ - unsigned int hdrlen = 24; - - if (ieee80211_is_data(fc)) { - if (ieee80211_has_a4(fc)) - hdrlen = 30; - if (ieee80211_is_data_qos(fc)) - hdrlen += IEEE80211_QOS_CTL_LEN; - goto out; - } - - if (ieee80211_is_ctl(fc)) { - /* - * ACK and CTS are 10 bytes, all others 16. To see how - * to get this condition consider - * subtype mask: 0b0000000011110000 (0x00F0) - * ACK subtype: 0b0000000011010000 (0x00D0) - * CTS subtype: 0b0000000011000000 (0x00C0) - * bits that matter: ^^^ (0x00E0) - * value of those: 0b0000000011000000 (0x00C0) - */ - if ((fc & cpu_to_le16(0x00E0)) == cpu_to_le16(0x00C0)) - hdrlen = 10; - else - hdrlen = 16; - } -out: - return hdrlen; -} -EXPORT_SYMBOL(ieee80211_hdrlen); - -unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb) -{ - const struct ieee80211_hdr *hdr = (const struct ieee80211_hdr *)skb->data; - unsigned int hdrlen; - - if (unlikely(skb->len < 10)) - return 0; - hdrlen = ieee80211_hdrlen(hdr->frame_control); - if (unlikely(hdrlen > skb->len)) - return 0; - return hdrlen; -} -EXPORT_SYMBOL(ieee80211_get_hdrlen_from_skb); - -int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) -{ - int ae = meshhdr->flags & IEEE80211S_FLAGS_AE; - /* 7.1.3.5a.2 */ - switch (ae) { - case 0: - return 6; - case 1: - return 12; - case 2: - return 18; - case 3: - return 24; - default: - return 6; - } -} - void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx) { struct sk_buff *skb = tx->skb; @@ -411,6 +341,52 @@ void ieee80211_stop_queue(struct ieee80211_hw *hw, int queue) } EXPORT_SYMBOL(ieee80211_stop_queue); +void ieee80211_add_pending_skb(struct ieee80211_local *local, + struct sk_buff *skb) +{ + struct ieee80211_hw *hw = &local->hw; + unsigned long flags; + int queue = skb_get_queue_mapping(skb); + + 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); + __ieee80211_wake_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); +} + +int ieee80211_add_pending_skbs(struct ieee80211_local *local, + struct sk_buff_head *skbs) +{ + struct ieee80211_hw *hw = &local->hw; + struct sk_buff *skb; + unsigned long flags; + int queue, ret = 0, i; + + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + for (i = 0; i < hw->queues; i++) + __ieee80211_stop_queue(hw, i, + IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + + while ((skb = skb_dequeue(skbs))) { + ret++; + queue = skb_get_queue_mapping(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); + __ieee80211_wake_queue(hw, i, + IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + } + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + return ret; +} + void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, enum queue_stop_reason reason) { @@ -536,8 +512,16 @@ EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); void ieee802_11_parse_elems(u8 *start, size_t len, struct ieee802_11_elems *elems) { + ieee802_11_parse_elems_crc(start, len, elems, 0, 0); +} + +u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, + struct ieee802_11_elems *elems, + u64 filter, u32 crc) +{ size_t left = len; u8 *pos = start; + bool calc_crc = filter != 0; memset(elems, 0, sizeof(*elems)); elems->ie_start = start; @@ -551,7 +535,10 @@ void ieee802_11_parse_elems(u8 *start, size_t len, left -= 2; if (elen > left) - return; + break; + + if (calc_crc && id < 64 && (filter & BIT(id))) + crc = crc32_be(crc, pos - 2, elen + 2); switch (id) { case WLAN_EID_SSID: @@ -575,8 +562,10 @@ void ieee802_11_parse_elems(u8 *start, size_t len, elems->cf_params_len = elen; break; case WLAN_EID_TIM: - elems->tim = pos; - elems->tim_len = elen; + if (elen >= sizeof(struct ieee80211_tim_ie)) { + elems->tim = (void *)pos; + elems->tim_len = elen; + } break; case WLAN_EID_IBSS_PARAMS: elems->ibss_params = pos; @@ -586,15 +575,20 @@ void ieee802_11_parse_elems(u8 *start, size_t len, elems->challenge = pos; elems->challenge_len = elen; break; - case WLAN_EID_WPA: + case WLAN_EID_VENDOR_SPECIFIC: if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 && pos[2] == 0xf2) { /* Microsoft OUI (00:50:F2) */ + + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + if (pos[3] == 1) { /* OUI Type 1 - WPA IE */ elems->wpa = pos; elems->wpa_len = elen; } else if (elen >= 5 && pos[3] == 2) { + /* OUI Type 2 - WMM IE */ if (pos[4] == 0) { elems->wmm_info = pos; elems->wmm_info_len = elen; @@ -679,32 +673,70 @@ void ieee802_11_parse_elems(u8 *start, size_t len, left -= elen; pos += elen; } + + return crc; } void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_queue_params qparam; - int i; + int queue; + bool use_11b; + int aCWmin, aCWmax; if (!local->ops->conf_tx) return; memset(&qparam, 0, sizeof(qparam)); - qparam.aifs = 2; - - if (local->hw.conf.channel->band == IEEE80211_BAND_2GHZ && - !(sdata->flags & IEEE80211_SDATA_OPERATING_GMODE)) - qparam.cw_min = 31; - else - qparam.cw_min = 15; + use_11b = (local->hw.conf.channel->band == IEEE80211_BAND_2GHZ) && + !(sdata->flags & IEEE80211_SDATA_OPERATING_GMODE); - qparam.cw_max = 1023; - qparam.txop = 0; + for (queue = 0; queue < local_to_hw(local)->queues; queue++) { + /* Set defaults according to 802.11-2007 Table 7-37 */ + aCWmax = 1023; + if (use_11b) + aCWmin = 31; + else + aCWmin = 15; + + switch (queue) { + case 3: /* AC_BK */ + qparam.cw_max = aCWmax; + qparam.cw_min = aCWmin; + qparam.txop = 0; + qparam.aifs = 7; + break; + default: /* never happens but let's not leave undefined */ + case 2: /* AC_BE */ + qparam.cw_max = aCWmax; + qparam.cw_min = aCWmin; + qparam.txop = 0; + qparam.aifs = 3; + break; + case 1: /* AC_VI */ + qparam.cw_max = aCWmin; + qparam.cw_min = (aCWmin + 1) / 2 - 1; + if (use_11b) + qparam.txop = 6016/32; + else + qparam.txop = 3008/32; + qparam.aifs = 2; + break; + case 0: /* AC_VO */ + qparam.cw_max = (aCWmin + 1) / 2 - 1; + qparam.cw_min = (aCWmin + 1) / 4 - 1; + if (use_11b) + qparam.txop = 3264/32; + else + qparam.txop = 1504/32; + qparam.aifs = 2; + break; + } - for (i = 0; i < local_to_hw(local)->queues; i++) - local->ops->conf_tx(local_to_hw(local), i, &qparam); + drv_conf_tx(local, queue, &qparam); + } } void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, @@ -742,31 +774,6 @@ void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, dev_queue_xmit(skb); } -int ieee80211_set_freq(struct ieee80211_sub_if_data *sdata, int freqMHz) -{ - int ret = -EINVAL; - struct ieee80211_channel *chan; - struct ieee80211_local *local = sdata->local; - - chan = ieee80211_get_channel(local->hw.wiphy, freqMHz); - - if (chan && !(chan->flags & IEEE80211_CHAN_DISABLED)) { - if (sdata->vif.type == NL80211_IFTYPE_ADHOC && - chan->flags & IEEE80211_CHAN_NO_IBSS) - return ret; - local->oper_channel = chan; - local->oper_channel_type = NL80211_CHAN_NO_HT; - - if (local->sw_scanning || local->hw_scanning) - ret = 0; - else - ret = ieee80211_hw_config( - local, IEEE80211_CONF_CHANGE_CHANNEL); - } - - return ret; -} - u32 ieee80211_mandatory_rates(struct ieee80211_local *local, enum ieee80211_band band) { @@ -831,16 +838,73 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, ieee80211_tx_skb(sdata, skb, encrypt); } +int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, + const u8 *ie, size_t ie_len) +{ + struct ieee80211_supported_band *sband; + u8 *pos, *supp_rates_len, *esupp_rates_len = NULL; + int i; + + sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + + pos = buffer; + + *pos++ = WLAN_EID_SUPP_RATES; + supp_rates_len = pos; + *pos++ = 0; + + for (i = 0; i < sband->n_bitrates; i++) { + struct ieee80211_rate *rate = &sband->bitrates[i]; + + if (esupp_rates_len) { + *esupp_rates_len += 1; + } else if (*supp_rates_len == 8) { + *pos++ = WLAN_EID_EXT_SUPP_RATES; + esupp_rates_len = pos; + *pos++ = 1; + } else + *supp_rates_len += 1; + + *pos++ = rate->bitrate / 5; + } + + if (sband->ht_cap.ht_supported) { + __le16 tmp = cpu_to_le16(sband->ht_cap.cap); + + *pos++ = WLAN_EID_HT_CAPABILITY; + *pos++ = sizeof(struct ieee80211_ht_cap); + memset(pos, 0, sizeof(struct ieee80211_ht_cap)); + memcpy(pos, &tmp, sizeof(u16)); + pos += sizeof(u16); + /* TODO: needs a define here for << 2 */ + *pos++ = sband->ht_cap.ampdu_factor | + (sband->ht_cap.ampdu_density << 2); + memcpy(pos, &sband->ht_cap.mcs, sizeof(sband->ht_cap.mcs)); + pos += sizeof(sband->ht_cap.mcs); + pos += 2 + 4 + 1; /* ext info, BF cap, antsel */ + } + + /* + * If adding more here, adjust code in main.c + * that calculates local->scan_ies_len. + */ + + if (ie) { + memcpy(pos, ie, ie_len); + pos += ie_len; + } + + return pos - buffer; +} + void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, - u8 *ssid, size_t ssid_len, - u8 *ie, size_t ie_len) + const u8 *ssid, size_t ssid_len, + const u8 *ie, size_t ie_len) { struct ieee80211_local *local = sdata->local; - struct ieee80211_supported_band *sband; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; - u8 *pos, *supp_rates, *esupp_rates = NULL; - int i; + u8 *pos; skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*mgmt) + 200 + ie_len); @@ -867,31 +931,9 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, *pos++ = WLAN_EID_SSID; *pos++ = ssid_len; memcpy(pos, ssid, ssid_len); + pos += ssid_len; - supp_rates = skb_put(skb, 2); - supp_rates[0] = WLAN_EID_SUPP_RATES; - supp_rates[1] = 0; - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; - - for (i = 0; i < sband->n_bitrates; i++) { - struct ieee80211_rate *rate = &sband->bitrates[i]; - if (esupp_rates) { - pos = skb_put(skb, 1); - esupp_rates[1]++; - } else if (supp_rates[1] == 8) { - esupp_rates = skb_put(skb, 3); - esupp_rates[0] = WLAN_EID_EXT_SUPP_RATES; - esupp_rates[1] = 1; - pos = &esupp_rates[2]; - } else { - pos = skb_put(skb, 1); - supp_rates[1]++; - } - *pos = rate->bitrate / 5; - } - - if (ie) - memcpy(skb_put(skb, ie_len), ie, ie_len); + skb_put(skb, ieee80211_build_preq_ies(local, pos, ie, ie_len)); ieee80211_tx_skb(sdata, skb, 0); } @@ -931,3 +973,151 @@ u32 ieee80211_sta_get_rates(struct ieee80211_local *local, } return supp_rates; } + +int ieee80211_reconfig(struct ieee80211_local *local) +{ + struct ieee80211_hw *hw = &local->hw; + struct ieee80211_sub_if_data *sdata; + struct ieee80211_if_init_conf conf; + 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; + + /* restart hardware */ + if (local->open_count) { + res = drv_start(local); + + ieee80211_led_radio(local, true); + } + + /* add interfaces */ + list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && + sdata->vif.type != NL80211_IFTYPE_MONITOR && + netif_running(sdata->dev)) { + conf.vif = &sdata->vif; + conf.type = sdata->vif.type; + conf.mac_addr = sdata->dev->dev_addr; + res = drv_add_interface(local, &conf); + } + } + + /* add STAs back */ + if (local->ops->sta_notify) { + spin_lock_irqsave(&local->sta_lock, flags); + list_for_each_entry(sta, &local->sta_list, list) { + sdata = sta->sdata; + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + sdata = container_of(sdata->bss, + struct ieee80211_sub_if_data, + u.ap); + + drv_sta_notify(local, &sdata->vif, STA_NOTIFY_ADD, + &sta->sta); + } + spin_unlock_irqrestore(&local->sta_lock, flags); + } + + /* Clear Suspend state so that ADDBA requests can be processed */ + + rcu_read_lock(); + + if (hw->flags & IEEE80211_HW_AMPDU_AGGREGATION) { + list_for_each_entry_rcu(sta, &local->sta_list, list) { + clear_sta_flags(sta, WLAN_STA_SUSPEND); + } + } + + rcu_read_unlock(); + + /* setup RTS threshold */ + drv_set_rts_threshold(local, hw->wiphy->rts_threshold); + + /* 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) { + u32 changed = ~0; + if (!netif_running(sdata->dev)) + continue; + switch (sdata->vif.type) { + case NL80211_IFTYPE_STATION: + /* disable beacon change bits */ + changed &= ~(BSS_CHANGED_BEACON | + BSS_CHANGED_BEACON_ENABLED); + /* fall through */ + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_MESH_POINT: + ieee80211_bss_info_change_notify(sdata, changed); + break; + case NL80211_IFTYPE_WDS: + break; + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MONITOR: + /* ignore virtual */ + break; + case NL80211_IFTYPE_UNSPECIFIED: + case __NL80211_IFTYPE_AFTER_LAST: + WARN_ON(1); + break; + } + } + + /* add back keys */ + list_for_each_entry(sdata, &local->interfaces, list) + if (netif_running(sdata->dev)) + ieee80211_enable_keys(sdata); + + ieee80211_wake_queues_by_reason(hw, + IEEE80211_QUEUE_STOP_REASON_SUSPEND); + + /* + * If this is for hw restart things are still running. + * We may want to change that later, however. + */ + if (!from_suspend) + return 0; + +#ifdef CONFIG_PM + local->suspended = false; + + list_for_each_entry(sdata, &local->interfaces, list) { + switch(sdata->vif.type) { + case NL80211_IFTYPE_STATION: + ieee80211_sta_restart(sdata); + break; + case NL80211_IFTYPE_ADHOC: + ieee80211_ibss_restart(sdata); + break; + case NL80211_IFTYPE_MESH_POINT: + ieee80211_mesh_restart(sdata); + break; + default: + break; + } + } + + add_timer(&local->sta_cleanup); + + spin_lock_irqsave(&local->sta_lock, flags); + list_for_each_entry(sta, &local->sta_list, list) + mesh_plink_restart(sta); + spin_unlock_irqrestore(&local->sta_lock, flags); +#else + WARN_ON(1); +#endif + return 0; +} diff --git a/net/mac80211/wext.c b/net/mac80211/wext.c index 959aa8379cc..1da81f45674 100644 --- a/net/mac80211/wext.c +++ b/net/mac80211/wext.c @@ -27,100 +27,6 @@ #include "aes_ccm.h" -static int ieee80211_set_encryption(struct ieee80211_sub_if_data *sdata, u8 *sta_addr, - int idx, int alg, int remove, - int set_tx_key, const u8 *_key, - size_t key_len) -{ - struct ieee80211_local *local = sdata->local; - struct sta_info *sta; - struct ieee80211_key *key; - int err; - - if (alg == ALG_AES_CMAC) { - if (idx < NUM_DEFAULT_KEYS || - idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) { - printk(KERN_DEBUG "%s: set_encrypt - invalid idx=%d " - "(BIP)\n", sdata->dev->name, idx); - return -EINVAL; - } - } else if (idx < 0 || idx >= NUM_DEFAULT_KEYS) { - printk(KERN_DEBUG "%s: set_encrypt - invalid idx=%d\n", - sdata->dev->name, idx); - return -EINVAL; - } - - if (remove) { - rcu_read_lock(); - - err = 0; - - if (is_broadcast_ether_addr(sta_addr)) { - key = sdata->keys[idx]; - } else { - sta = sta_info_get(local, sta_addr); - if (!sta) { - err = -ENOENT; - goto out_unlock; - } - key = sta->key; - } - - ieee80211_key_free(key); - } else { - key = ieee80211_key_alloc(alg, idx, key_len, _key); - if (!key) - return -ENOMEM; - - sta = NULL; - err = 0; - - rcu_read_lock(); - - if (!is_broadcast_ether_addr(sta_addr)) { - set_tx_key = 0; - /* - * According to the standard, the key index of a - * pairwise key must be zero. However, some AP are - * broken when it comes to WEP key indices, so we - * work around this. - */ - if (idx != 0 && alg != ALG_WEP) { - ieee80211_key_free(key); - err = -EINVAL; - goto out_unlock; - } - - sta = sta_info_get(local, sta_addr); - if (!sta) { - ieee80211_key_free(key); - err = -ENOENT; - goto out_unlock; - } - } - - if (alg == ALG_WEP && - key_len != LEN_WEP40 && key_len != LEN_WEP104) { - ieee80211_key_free(key); - err = -EINVAL; - goto out_unlock; - } - - ieee80211_key_link(key, sdata, sta); - - if (set_tx_key || (!sta && !sdata->default_key && key)) - ieee80211_set_default_key(sdata, idx); - if (alg == ALG_AES_CMAC && - (set_tx_key || (!sta && !sdata->default_mgmt_key && key))) - ieee80211_set_default_mgmt_key(sdata, idx); - } - - out_unlock: - rcu_read_unlock(); - - return err; -} - static int ieee80211_ioctl_siwgenie(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *extra) @@ -131,11 +37,13 @@ static int ieee80211_ioctl_siwgenie(struct net_device *dev, if (sdata->vif.type == NL80211_IFTYPE_STATION) { int ret = ieee80211_sta_set_extra_ie(sdata, extra, data->length); - if (ret) + if (ret && ret != -EALREADY) return ret; sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_BSSID_SEL; sdata->u.mgd.flags &= ~IEEE80211_STA_EXT_SME; - ieee80211_sta_req_auth(sdata); + sdata->u.mgd.flags &= ~IEEE80211_STA_CONTROL_PORT; + if (ret != -EALREADY) + ieee80211_sta_req_auth(sdata); return 0; } @@ -147,34 +55,54 @@ static int ieee80211_ioctl_siwfreq(struct net_device *dev, 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) - sdata->u.ibss.flags &= ~IEEE80211_IBSS_AUTO_CHANNEL_SEL; + 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_ADHOC) - sdata->u.ibss.flags |= - IEEE80211_IBSS_AUTO_CHANNEL_SEL; - else if (sdata->vif.type == NL80211_IFTYPE_STATION) + if (sdata->vif.type == NL80211_IFTYPE_STATION) sdata->u.mgd.flags |= IEEE80211_STA_AUTO_CHANNEL_SEL; return 0; } else - return ieee80211_set_freq(sdata, + 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 ieee80211_set_freq(sdata, freq->m / div); - else + 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; } @@ -183,8 +111,12 @@ static int ieee80211_ioctl_giwfreq(struct net_device *dev, 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); - freq->m = local->hw.conf.channel->center_freq; + 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; @@ -195,15 +127,17 @@ 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; + 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--; - sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (sdata->vif.type == NL80211_IFTYPE_STATION) { if (data->flags) sdata->u.mgd.flags &= ~IEEE80211_STA_AUTO_SSID_SEL; @@ -215,10 +149,10 @@ static int ieee80211_ioctl_siwessid(struct net_device *dev, 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_ADHOC) - return ieee80211_ibss_set_ssid(sdata, ssid, len); + } return -EOPNOTSUPP; } @@ -229,9 +163,13 @@ static int ieee80211_ioctl_giwessid(struct net_device *dev, 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) { @@ -240,14 +178,6 @@ static int ieee80211_ioctl_giwessid(struct net_device *dev, } else data->flags = 0; return res; - } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { - int res = ieee80211_ibss_get_ssid(sdata, ssid, &len); - if (res == 0) { - data->length = len; - data->flags = 1; - } else - data->flags = 0; - return res; } return -EOPNOTSUPP; @@ -258,9 +188,11 @@ 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; + 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); - sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (sdata->vif.type == NL80211_IFTYPE_STATION) { int ret; @@ -275,18 +207,9 @@ static int ieee80211_ioctl_siwap(struct net_device *dev, 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_ADHOC) { - if (is_zero_ether_addr((u8 *) &ap_addr->sa_data)) - sdata->u.ibss.flags |= IEEE80211_IBSS_AUTO_BSSID_SEL | - IEEE80211_IBSS_AUTO_CHANNEL_SEL; - else if (is_broadcast_ether_addr((u8 *) &ap_addr->sa_data)) - sdata->u.ibss.flags |= IEEE80211_IBSS_AUTO_BSSID_SEL; - else - sdata->u.ibss.flags &= ~IEEE80211_IBSS_AUTO_BSSID_SEL; - - return ieee80211_ibss_set_bssid(sdata, (u8 *) &ap_addr->sa_data); } else if (sdata->vif.type == NL80211_IFTYPE_WDS) { /* * If it is necessary to update the WDS peer address @@ -312,9 +235,11 @@ 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; + 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); - sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (sdata->vif.type == NL80211_IFTYPE_STATION) { if (sdata->u.mgd.state == IEEE80211_STA_MLME_ASSOCIATED) { ap_addr->sa_family = ARPHRD_ETHER; @@ -322,13 +247,6 @@ static int ieee80211_ioctl_giwap(struct net_device *dev, } else memset(&ap_addr->sa_data, 0, ETH_ALEN); return 0; - } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { - if (sdata->u.ibss.state == IEEE80211_IBSS_MLME_JOINED) { - ap_addr->sa_family = ARPHRD_ETHER; - memcpy(&ap_addr->sa_data, sdata->u.ibss.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); @@ -411,334 +329,6 @@ static int ieee80211_ioctl_giwrate(struct net_device *dev, return 0; } -static int ieee80211_ioctl_siwtxpower(struct net_device *dev, - struct iw_request_info *info, - union iwreq_data *data, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_channel* chan = local->hw.conf.channel; - bool reconf = false; - u32 reconf_flags = 0; - int new_power_level; - - if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) - return -EINVAL; - if (data->txpower.flags & IW_TXPOW_RANGE) - return -EINVAL; - if (!chan) - return -EINVAL; - - /* only change when not disabling */ - if (!data->txpower.disabled) { - if (data->txpower.fixed) { - if (data->txpower.value < 0) - return -EINVAL; - new_power_level = data->txpower.value; - /* - * Debatable, but we cannot do a fixed power - * level above the regulatory constraint. - * Use "iwconfig wlan0 txpower 15dBm" instead. - */ - if (new_power_level > chan->max_power) - return -EINVAL; - } else { - /* - * Automatic power level setting, max being the value - * passed in from userland. - */ - if (data->txpower.value < 0) - new_power_level = -1; - else - new_power_level = data->txpower.value; - } - - reconf = true; - - /* - * ieee80211_hw_config() will limit to the channel's - * max power and possibly power constraint from AP. - */ - local->user_power_level = new_power_level; - } - - if (local->hw.conf.radio_enabled != !(data->txpower.disabled)) { - local->hw.conf.radio_enabled = !(data->txpower.disabled); - reconf_flags |= IEEE80211_CONF_CHANGE_RADIO_ENABLED; - ieee80211_led_radio(local, local->hw.conf.radio_enabled); - } - - if (reconf || reconf_flags) - ieee80211_hw_config(local, reconf_flags); - - return 0; -} - -static int ieee80211_ioctl_giwtxpower(struct net_device *dev, - struct iw_request_info *info, - union iwreq_data *data, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - - data->txpower.fixed = 1; - data->txpower.disabled = !(local->hw.conf.radio_enabled); - data->txpower.value = local->hw.conf.power_level; - data->txpower.flags = IW_TXPOW_DBM; - - return 0; -} - -static int ieee80211_ioctl_siwrts(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *rts, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - - if (rts->disabled) - local->rts_threshold = IEEE80211_MAX_RTS_THRESHOLD; - else if (!rts->fixed) - /* if the rts value is not fixed, then take default */ - local->rts_threshold = IEEE80211_MAX_RTS_THRESHOLD; - else if (rts->value < 0 || rts->value > IEEE80211_MAX_RTS_THRESHOLD) - return -EINVAL; - else - local->rts_threshold = rts->value; - - /* If the wlan card performs RTS/CTS in hardware/firmware, - * configure it here */ - - if (local->ops->set_rts_threshold) - local->ops->set_rts_threshold(local_to_hw(local), - local->rts_threshold); - - return 0; -} - -static int ieee80211_ioctl_giwrts(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *rts, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - - rts->value = local->rts_threshold; - rts->disabled = (rts->value >= IEEE80211_MAX_RTS_THRESHOLD); - rts->fixed = 1; - - return 0; -} - - -static int ieee80211_ioctl_siwfrag(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *frag, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - - if (frag->disabled) - local->fragmentation_threshold = IEEE80211_MAX_FRAG_THRESHOLD; - else if (!frag->fixed) - local->fragmentation_threshold = IEEE80211_MAX_FRAG_THRESHOLD; - else if (frag->value < 256 || - frag->value > IEEE80211_MAX_FRAG_THRESHOLD) - return -EINVAL; - else { - /* Fragment length must be even, so strip LSB. */ - local->fragmentation_threshold = frag->value & ~0x1; - } - - return 0; -} - -static int ieee80211_ioctl_giwfrag(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *frag, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - - frag->value = local->fragmentation_threshold; - frag->disabled = (frag->value >= IEEE80211_MAX_FRAG_THRESHOLD); - frag->fixed = 1; - - return 0; -} - - -static int ieee80211_ioctl_siwretry(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *retry, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - - if (retry->disabled || - (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT) - return -EINVAL; - - if (retry->flags & IW_RETRY_MAX) { - local->hw.conf.long_frame_max_tx_count = retry->value; - } else if (retry->flags & IW_RETRY_MIN) { - local->hw.conf.short_frame_max_tx_count = retry->value; - } else { - local->hw.conf.long_frame_max_tx_count = retry->value; - local->hw.conf.short_frame_max_tx_count = retry->value; - } - - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_RETRY_LIMITS); - - return 0; -} - - -static int ieee80211_ioctl_giwretry(struct net_device *dev, - struct iw_request_info *info, - struct iw_param *retry, char *extra) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - - retry->disabled = 0; - if (retry->flags == 0 || retry->flags & IW_RETRY_MIN) { - /* first return min value, iwconfig will ask max value - * later if needed */ - retry->flags |= IW_RETRY_LIMIT; - retry->value = local->hw.conf.short_frame_max_tx_count; - if (local->hw.conf.long_frame_max_tx_count != - local->hw.conf.short_frame_max_tx_count) - retry->flags |= IW_RETRY_MIN; - return 0; - } - if (retry->flags & IW_RETRY_MAX) { - retry->flags = IW_RETRY_LIMIT | IW_RETRY_MAX; - retry->value = local->hw.conf.long_frame_max_tx_count; - } - - return 0; -} - -static int ieee80211_ioctl_siwmlme(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *data, char *extra) -{ - struct ieee80211_sub_if_data *sdata; - struct iw_mlme *mlme = (struct iw_mlme *) extra; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - if (!(sdata->vif.type == NL80211_IFTYPE_STATION)) - return -EINVAL; - - switch (mlme->cmd) { - case IW_MLME_DEAUTH: - /* TODO: mlme->addr.sa_data */ - return ieee80211_sta_deauthenticate(sdata, mlme->reason_code); - case IW_MLME_DISASSOC: - /* TODO: mlme->addr.sa_data */ - return ieee80211_sta_disassociate(sdata, mlme->reason_code); - default: - return -EOPNOTSUPP; - } -} - - -static int ieee80211_ioctl_siwencode(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *erq, char *keybuf) -{ - struct ieee80211_sub_if_data *sdata; - int idx, i, alg = ALG_WEP; - u8 bcaddr[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; - int remove = 0, ret; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - idx = erq->flags & IW_ENCODE_INDEX; - if (idx == 0) { - if (sdata->default_key) - for (i = 0; i < NUM_DEFAULT_KEYS; i++) { - if (sdata->default_key == sdata->keys[i]) { - idx = i; - break; - } - } - } else if (idx < 1 || idx > 4) - return -EINVAL; - else - idx--; - - if (erq->flags & IW_ENCODE_DISABLED) - remove = 1; - else if (erq->length == 0) { - /* No key data - just set the default TX key index */ - ieee80211_set_default_key(sdata, idx); - return 0; - } - - ret = ieee80211_set_encryption( - sdata, bcaddr, - idx, alg, remove, - !sdata->default_key, - keybuf, erq->length); - - if (!ret) { - if (remove) - sdata->u.mgd.flags &= ~IEEE80211_STA_TKIP_WEP_USED; - else - sdata->u.mgd.flags |= IEEE80211_STA_TKIP_WEP_USED; - } - - return ret; -} - - -static int ieee80211_ioctl_giwencode(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *erq, char *key) -{ - struct ieee80211_sub_if_data *sdata; - int idx, i; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - idx = erq->flags & IW_ENCODE_INDEX; - if (idx < 1 || idx > 4) { - idx = -1; - if (!sdata->default_key) - idx = 0; - else for (i = 0; i < NUM_DEFAULT_KEYS; i++) { - if (sdata->default_key == sdata->keys[i]) { - idx = i; - break; - } - } - if (idx < 0) - return -EINVAL; - } else - idx--; - - erq->flags = idx + 1; - - if (!sdata->keys[idx]) { - erq->length = 0; - erq->flags |= IW_ENCODE_DISABLED; - return 0; - } - - memcpy(key, sdata->keys[idx]->conf.key, - min_t(int, erq->length, sdata->keys[idx]->conf.keylen)); - erq->length = sdata->keys[idx]->conf.keylen; - erq->flags |= IW_ENCODE_ENABLED; - - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - switch (sdata->u.mgd.auth_alg) { - case WLAN_AUTH_OPEN: - case WLAN_AUTH_LEAP: - erq->flags |= IW_ENCODE_OPEN; - break; - case WLAN_AUTH_SHARED_KEY: - erq->flags |= IW_ENCODE_RESTRICTED; - break; - } - } - - return 0; -} - static int ieee80211_ioctl_siwpower(struct net_device *dev, struct iw_request_info *info, struct iw_param *wrq, @@ -747,7 +337,7 @@ static int ieee80211_ioctl_siwpower(struct net_device *dev, 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 ret = 0, timeout = 0; + int timeout = 0; bool ps; if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) @@ -779,42 +369,18 @@ static int ieee80211_ioctl_siwpower(struct net_device *dev, timeout = wrq->value / 1000; set: - if (ps == local->powersave && timeout == conf->dynamic_ps_timeout) - return ret; + if (ps == sdata->u.mgd.powersave && timeout == conf->dynamic_ps_timeout) + return 0; - local->powersave = ps; + sdata->u.mgd.powersave = ps; conf->dynamic_ps_timeout = timeout; if (local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS) - ret = ieee80211_hw_config(local, - IEEE80211_CONF_CHANGE_DYNPS_TIMEOUT); + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); - if (!(sdata->u.mgd.flags & IEEE80211_STA_ASSOCIATED)) - return ret; + ieee80211_recalc_ps(local, -1); - if (conf->dynamic_ps_timeout > 0 && - !(local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_PS)) { - mod_timer(&local->dynamic_ps_timer, jiffies + - msecs_to_jiffies(conf->dynamic_ps_timeout)); - } else { - if (local->powersave) { - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) - ieee80211_send_nullfunc(local, sdata, 1); - conf->flags |= IEEE80211_CONF_PS; - ret = ieee80211_hw_config(local, - IEEE80211_CONF_CHANGE_PS); - } else { - conf->flags &= ~IEEE80211_CONF_PS; - ret = ieee80211_hw_config(local, - IEEE80211_CONF_CHANGE_PS); - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) - ieee80211_send_nullfunc(local, sdata, 0); - del_timer_sync(&local->dynamic_ps_timer); - cancel_work_sync(&local->dynamic_ps_enable_work); - } - } - - return ret; + return 0; } static int ieee80211_ioctl_giwpower(struct net_device *dev, @@ -822,9 +388,9 @@ static int ieee80211_ioctl_giwpower(struct net_device *dev, union iwreq_data *wrqu, char *extra) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - wrqu->power.disabled = !local->powersave; + wrqu->power.disabled = !sdata->u.mgd.powersave; return 0; } @@ -997,82 +563,6 @@ static int ieee80211_ioctl_giwauth(struct net_device *dev, } -static int ieee80211_ioctl_siwencodeext(struct net_device *dev, - struct iw_request_info *info, - struct iw_point *erq, char *extra) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct iw_encode_ext *ext = (struct iw_encode_ext *) extra; - int uninitialized_var(alg), idx, i, remove = 0; - - switch (ext->alg) { - case IW_ENCODE_ALG_NONE: - remove = 1; - break; - case IW_ENCODE_ALG_WEP: - alg = ALG_WEP; - break; - case IW_ENCODE_ALG_TKIP: - alg = ALG_TKIP; - break; - case IW_ENCODE_ALG_CCMP: - alg = ALG_CCMP; - break; - case IW_ENCODE_ALG_AES_CMAC: - alg = ALG_AES_CMAC; - break; - default: - return -EOPNOTSUPP; - } - - if (erq->flags & IW_ENCODE_DISABLED) - remove = 1; - - idx = erq->flags & IW_ENCODE_INDEX; - if (alg == ALG_AES_CMAC) { - if (idx < NUM_DEFAULT_KEYS + 1 || - idx > NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) { - idx = -1; - if (!sdata->default_mgmt_key) - idx = 0; - else for (i = NUM_DEFAULT_KEYS; - i < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS; - i++) { - if (sdata->default_mgmt_key == sdata->keys[i]) - { - idx = i; - break; - } - } - if (idx < 0) - return -EINVAL; - } else - idx--; - } else { - if (idx < 1 || idx > 4) { - idx = -1; - if (!sdata->default_key) - idx = 0; - else for (i = 0; i < NUM_DEFAULT_KEYS; i++) { - if (sdata->default_key == sdata->keys[i]) { - idx = i; - break; - } - } - if (idx < 0) - return -EINVAL; - } else - idx--; - } - - return ieee80211_set_encryption(sdata, ext->addr.sa_data, idx, alg, - remove, - ext->ext_flags & - IW_ENCODE_EXT_SET_TX_KEY, - ext->key, ext->key_len); -} - - /* Structures to export the Wireless Handlers */ static const iw_handler ieee80211_handler[] = @@ -1099,7 +589,7 @@ static const iw_handler ieee80211_handler[] = (iw_handler) NULL, /* SIOCGIWTHRSPY */ (iw_handler) ieee80211_ioctl_siwap, /* SIOCSIWAP */ (iw_handler) ieee80211_ioctl_giwap, /* SIOCGIWAP */ - (iw_handler) ieee80211_ioctl_siwmlme, /* SIOCSIWMLME */ + (iw_handler) cfg80211_wext_siwmlme, /* SIOCSIWMLME */ (iw_handler) NULL, /* SIOCGIWAPLIST */ (iw_handler) cfg80211_wext_siwscan, /* SIOCSIWSCAN */ (iw_handler) cfg80211_wext_giwscan, /* SIOCGIWSCAN */ @@ -1111,16 +601,16 @@ static const iw_handler ieee80211_handler[] = (iw_handler) NULL, /* -- hole -- */ (iw_handler) ieee80211_ioctl_siwrate, /* SIOCSIWRATE */ (iw_handler) ieee80211_ioctl_giwrate, /* SIOCGIWRATE */ - (iw_handler) ieee80211_ioctl_siwrts, /* SIOCSIWRTS */ - (iw_handler) ieee80211_ioctl_giwrts, /* SIOCGIWRTS */ - (iw_handler) ieee80211_ioctl_siwfrag, /* SIOCSIWFRAG */ - (iw_handler) ieee80211_ioctl_giwfrag, /* SIOCGIWFRAG */ - (iw_handler) ieee80211_ioctl_siwtxpower, /* SIOCSIWTXPOW */ - (iw_handler) ieee80211_ioctl_giwtxpower, /* SIOCGIWTXPOW */ - (iw_handler) ieee80211_ioctl_siwretry, /* SIOCSIWRETRY */ - (iw_handler) ieee80211_ioctl_giwretry, /* SIOCGIWRETRY */ - (iw_handler) ieee80211_ioctl_siwencode, /* SIOCSIWENCODE */ - (iw_handler) ieee80211_ioctl_giwencode, /* SIOCGIWENCODE */ + (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 -- */ @@ -1129,7 +619,7 @@ static const iw_handler ieee80211_handler[] = (iw_handler) NULL, /* SIOCGIWGENIE */ (iw_handler) ieee80211_ioctl_siwauth, /* SIOCSIWAUTH */ (iw_handler) ieee80211_ioctl_giwauth, /* SIOCGIWAUTH */ - (iw_handler) ieee80211_ioctl_siwencodeext, /* SIOCSIWENCODEEXT */ + (iw_handler) cfg80211_wext_siwencodeext, /* SIOCSIWENCODEEXT */ (iw_handler) NULL, /* SIOCGIWENCODEEXT */ (iw_handler) NULL, /* SIOCSIWPMKSA */ (iw_handler) NULL, /* -- hole -- */ diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 0b8ad1f4ecd..116a923b14d 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -23,34 +23,6 @@ */ const int ieee802_1d_to_ac[8] = { 2, 3, 3, 2, 1, 1, 0, 0 }; -static const char llc_ip_hdr[8] = {0xAA, 0xAA, 0x3, 0, 0, 0, 0x08, 0}; - -/* Given a data frame determine the 802.1p/1d tag to use. */ -static unsigned int classify_1d(struct sk_buff *skb) -{ - unsigned int dscp; - - /* skb->priority values from 256->263 are magic values to - * directly indicate a specific 802.1d priority. This is used - * to allow 802.1d priority to be passed directly in from VLAN - * tags, etc. - */ - if (skb->priority >= 256 && skb->priority <= 263) - return skb->priority - 256; - - switch (skb->protocol) { - case htons(ETH_P_IP): - dscp = ip_hdr(skb)->tos & 0xfc; - break; - - default: - return 0; - } - - return dscp >> 5; -} - - static int wme_downgrade_ac(struct sk_buff *skb) { switch (skb->priority) { @@ -94,7 +66,7 @@ static u16 classify80211(struct ieee80211_local *local, struct sk_buff *skb) /* use the data classifier to determine what 802.1d tag the * data frame has */ - skb->priority = classify_1d(skb); + skb->priority = cfg80211_classify8021d(skb); /* in case we are a client verify acm is not set for this ac */ while (unlikely(local->wmm_acm & BIT(skb->priority))) { @@ -129,11 +101,11 @@ u16 ieee80211_select_queue(struct net_device *dev, struct sk_buff *skb) * Now we know the 1d priority, fill in the QoS header if * there is one (and we haven't done this before). */ - if (!skb->requeue && ieee80211_is_data_qos(hdr->frame_control)) { + if (ieee80211_is_data_qos(hdr->frame_control)) { u8 *p = ieee80211_get_qos_ctl(hdr); u8 ack_policy = 0; tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; - if (local->wifi_wme_noack_test) + if (unlikely(local->wifi_wme_noack_test)) ack_policy |= QOS_CONTROL_ACK_POLICY_NOACK << QOS_CONTROL_ACK_POLICY_SHIFT; /* qos header is 2 bytes, second reserved */ diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 4f8bfea278f..dcfae8884b8 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -122,7 +122,7 @@ 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); + (void *) skb->data, NULL); return RX_DROP_UNUSABLE; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index cb3ad741ebf..634d14affc8 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -327,7 +327,7 @@ config NETFILTER_XT_TARGET_CONNMARK If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. The module will be called - ipt_CONNMARK.ko. If unsure, say `N'. + ipt_CONNMARK. If unsure, say `N'. config NETFILTER_XT_TARGET_CONNSECMARK tristate '"CONNSECMARK" target support' @@ -584,7 +584,7 @@ config NETFILTER_XT_MATCH_CONNMARK If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. The module will be called - ipt_connmark.ko. If unsure, say `N'. + ipt_connmark. If unsure, say `N'. config NETFILTER_XT_MATCH_CONNTRACK tristate '"conntrack" connection tracking match support' @@ -917,6 +917,19 @@ config NETFILTER_XT_MATCH_U32 Details and examples are in the kernel module source. +config NETFILTER_XT_MATCH_OSF + tristate '"osf" Passive OS fingerprint match' + depends on NETFILTER_ADVANCED && NETFILTER_NETLINK + help + This option selects the Passive OS Fingerprinting match module + that allows to passively match the remote operating system by + analyzing incoming TCP SYN packets. + + Rules and loading software can be downloaded from + http://www.ioremap.net/projects/osf + + To compile it as a module, choose M here. If unsure, say N. + endif # NETFILTER_XTABLES endmenu diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 6282060fbda..49f62ee4e9f 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o obj-$(CONFIG_NETFILTER_XT_MATCH_MARK) += xt_mark.o obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o +obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e01061f49cd..7c1333c67ff 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3345,22 +3345,8 @@ static struct genl_ops ip_vs_genl_ops[] __read_mostly = { static int __init ip_vs_genl_register(void) { - int ret, i; - - ret = genl_register_family(&ip_vs_genl_family); - if (ret) - return ret; - - for (i = 0; i < ARRAY_SIZE(ip_vs_genl_ops); i++) { - ret = genl_register_ops(&ip_vs_genl_family, &ip_vs_genl_ops[i]); - if (ret) - goto err_out; - } - return 0; - -err_out: - genl_unregister_family(&ip_vs_genl_family); - return ret; + return genl_register_family_with_ops(&ip_vs_genl_family, + ip_vs_genl_ops, ARRAY_SIZE(ip_vs_genl_ops)); } static void ip_vs_genl_unregister(void) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 425ab144f15..5874657af7f 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -260,8 +260,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_send_check(ip_hdr(skb)); /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -324,8 +324,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -388,8 +388,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) @@ -465,8 +465,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) @@ -553,8 +553,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_RL("ip_vs_tunnel_xmit(): mtu less than 68\n"); goto tx_error; } - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); df |= (old_iph->frag_off & htons(IP_DF)); @@ -596,8 +596,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. @@ -665,8 +665,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_RL("ip_vs_tunnel_xmit_v6(): mtu less than 1280\n"); goto tx_error; } - if (skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); @@ -702,8 +702,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* * Push down and install the IPIP header. @@ -775,8 +775,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_send_check(ip_hdr(skb)); /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -828,8 +828,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* drop old route */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -900,8 +900,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* drop the old route when skb is not shared */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); ip_vs_nat_icmp(skb, pp, cp, 0); @@ -975,8 +975,8 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* drop the old route when skb is not shared */ - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb_dst_drop(skb); + skb_dst_set(skb, &rt->u.dst); ip_vs_nat_icmp_v6(skb, pp, cp, 0); diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index 9fe8982bd7c..4a1d94aac20 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -116,7 +116,7 @@ int nf_conntrack_acct_init(struct net *net) if (net_eq(net, &init_net)) { #ifdef CONFIG_NF_CT_ACCT printk(KERN_WARNING "CONFIG_NF_CT_ACCT is deprecated and will be removed soon. Please use\n"); - printk(KERN_WARNING "nf_conntrack.acct=1 kernel paramater, acct=1 nf_conntrack module option or\n"); + printk(KERN_WARNING "nf_conntrack.acct=1 kernel parameter, acct=1 nf_conntrack module option or\n"); printk(KERN_WARNING "sysctl net.netfilter.nf_conntrack_acct=1 to enable it.\n"); #endif diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 8020db6274b..b5869b9574b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -39,6 +39,7 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_acct.h> +#include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> @@ -182,10 +183,6 @@ destroy_conntrack(struct nf_conntrack *nfct) NF_CT_ASSERT(atomic_read(&nfct->use) == 0); NF_CT_ASSERT(!timer_pending(&ct->timeout)); - if (!test_bit(IPS_DYING_BIT, &ct->status)) - nf_conntrack_event(IPCT_DESTROY, ct); - set_bit(IPS_DYING_BIT, &ct->status); - /* To make sure we don't get any weird locking issues here: * destroy_conntrack() MUST NOT be called with a write lock * to nf_conntrack_lock!!! -HW */ @@ -219,27 +216,70 @@ destroy_conntrack(struct nf_conntrack *nfct) nf_conntrack_free(ct); } -static void death_by_timeout(unsigned long ul_conntrack) +void nf_ct_delete_from_lists(struct nf_conn *ct) { - struct nf_conn *ct = (void *)ul_conntrack; struct net *net = nf_ct_net(ct); - struct nf_conn_help *help = nfct_help(ct); - struct nf_conntrack_helper *helper; - - if (help) { - rcu_read_lock(); - helper = rcu_dereference(help->helper); - if (helper && helper->destroy) - helper->destroy(ct); - rcu_read_unlock(); - } + nf_ct_helper_destroy(ct); spin_lock_bh(&nf_conntrack_lock); /* Inside lock so preempt is disabled on module removal path. * Otherwise we can get spurious warnings. */ NF_CT_STAT_INC(net, delete_list); clean_from_lists(ct); spin_unlock_bh(&nf_conntrack_lock); +} +EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists); + +static void death_by_event(unsigned long ul_conntrack) +{ + struct nf_conn *ct = (void *)ul_conntrack; + struct net *net = nf_ct_net(ct); + + if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) { + /* bad luck, let's retry again */ + ct->timeout.expires = jiffies + + (random32() % net->ct.sysctl_events_retry_timeout); + add_timer(&ct->timeout); + return; + } + /* we've got the event delivered, now it's dying */ + set_bit(IPS_DYING_BIT, &ct->status); + spin_lock(&nf_conntrack_lock); + hlist_nulls_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + spin_unlock(&nf_conntrack_lock); + nf_ct_put(ct); +} + +void nf_ct_insert_dying_list(struct nf_conn *ct) +{ + struct net *net = nf_ct_net(ct); + + /* add this conntrack to the dying list */ + spin_lock_bh(&nf_conntrack_lock); + hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &net->ct.dying); + spin_unlock_bh(&nf_conntrack_lock); + /* set a new timer to retry event delivery */ + setup_timer(&ct->timeout, death_by_event, (unsigned long)ct); + ct->timeout.expires = jiffies + + (random32() % net->ct.sysctl_events_retry_timeout); + add_timer(&ct->timeout); +} +EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list); + +static void death_by_timeout(unsigned long ul_conntrack) +{ + struct nf_conn *ct = (void *)ul_conntrack; + + if (!test_bit(IPS_DYING_BIT, &ct->status) && + unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) { + /* destroy event was not delivered */ + nf_ct_delete_from_lists(ct); + nf_ct_insert_dying_list(ct); + return; + } + set_bit(IPS_DYING_BIT, &ct->status); + nf_ct_delete_from_lists(ct); nf_ct_put(ct); } @@ -295,7 +335,8 @@ begin: h = __nf_conntrack_find(net, tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); - if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + if (unlikely(nf_ct_is_dying(ct) || + !atomic_inc_not_zero(&ct->ct_general.use))) h = NULL; else { if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) { @@ -385,7 +426,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* Remove from unconfirmed list */ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); - __nf_conntrack_hash_insert(ct, hash, repl_hash); /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ @@ -393,16 +433,20 @@ __nf_conntrack_confirm(struct sk_buff *skb) add_timer(&ct->timeout); atomic_inc(&ct->ct_general.use); set_bit(IPS_CONFIRMED_BIT, &ct->status); + + /* Since the lookup is lockless, hash insertion must be done after + * starting the timer and setting the CONFIRMED bit. The RCU barriers + * guarantee that no other CPU can find the conntrack before the above + * stores are visible. + */ + __nf_conntrack_hash_insert(ct, hash, repl_hash); NF_CT_STAT_INC(net, insert); spin_unlock_bh(&nf_conntrack_lock); + help = nfct_help(ct); if (help && help->helper) nf_conntrack_event_cache(IPCT_HELPER, ct); -#ifdef CONFIG_NF_NAT_NEEDED - if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) || - test_bit(IPS_DST_NAT_DONE_BIT, &ct->status)) - nf_conntrack_event_cache(IPCT_NATINFO, ct); -#endif + nf_conntrack_event_cache(master_ct(ct) ? IPCT_RELATED : IPCT_NEW, ct); return NF_ACCEPT; @@ -467,7 +511,8 @@ static noinline int early_drop(struct net *net, unsigned int hash) cnt++; } - if (ct && unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + if (ct && unlikely(nf_ct_is_dying(ct) || + !atomic_inc_not_zero(&ct->ct_general.use))) ct = NULL; if (ct || cnt >= NF_CT_EVICTION_RANGE) break; @@ -516,22 +561,38 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, } } - ct = kmem_cache_zalloc(nf_conntrack_cachep, gfp); + /* + * Do not use kmem_cache_zalloc(), as this cache uses + * SLAB_DESTROY_BY_RCU. + */ + ct = kmem_cache_alloc(nf_conntrack_cachep, gfp); if (ct == NULL) { pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n"); atomic_dec(&net->ct.count); return ERR_PTR(-ENOMEM); } - - atomic_set(&ct->ct_general.use, 1); + /* + * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next + * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged. + */ + memset(&ct->tuplehash[IP_CT_DIR_MAX], 0, + sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX])); + spin_lock_init(&ct->lock); ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig; + ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL; ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl; + ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL; /* Don't set timer yet: wait for confirmation */ setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct); #ifdef CONFIG_NET_NS ct->ct_net = net; #endif + /* + * changes to lookup keys must be done before setting refcnt to 1 + */ + smp_wmb(); + atomic_set(&ct->ct_general.use, 1); return ct; } EXPORT_SYMBOL_GPL(nf_conntrack_alloc); @@ -580,6 +641,7 @@ init_conntrack(struct net *net, } nf_ct_acct_ext_add(ct, GFP_ATOMIC); + nf_ct_ecache_ext_add(ct, GFP_ATOMIC); spin_lock_bh(&nf_conntrack_lock); exp = nf_ct_find_expectation(net, tuple); @@ -807,13 +869,9 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, unsigned long extra_jiffies, int do_acct) { - int event = 0; - NF_CT_ASSERT(ct->timeout.data == (unsigned long)ct); NF_CT_ASSERT(skb); - spin_lock_bh(&nf_conntrack_lock); - /* Only update if this is not a fixed timeout */ if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) goto acct; @@ -821,19 +879,14 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, /* If not in hash table, timer will not be active yet */ if (!nf_ct_is_confirmed(ct)) { ct->timeout.expires = extra_jiffies; - event = IPCT_REFRESH; } else { unsigned long newtime = jiffies + extra_jiffies; /* Only update the timeout if the new timeout is at least HZ jiffies from the old timeout. Need del_timer for race avoidance (may already be dying). */ - if (newtime - ct->timeout.expires >= HZ - && del_timer(&ct->timeout)) { - ct->timeout.expires = newtime; - add_timer(&ct->timeout); - event = IPCT_REFRESH; - } + if (newtime - ct->timeout.expires >= HZ) + mod_timer_pending(&ct->timeout, newtime); } acct: @@ -842,17 +895,13 @@ acct: acct = nf_conn_acct_find(ct); if (acct) { + spin_lock_bh(&ct->lock); acct[CTINFO2DIR(ctinfo)].packets++; acct[CTINFO2DIR(ctinfo)].bytes += skb->len - skb_network_offset(skb); + spin_unlock_bh(&ct->lock); } } - - spin_unlock_bh(&nf_conntrack_lock); - - /* must be unlocked when calling event cache */ - if (event) - nf_conntrack_event_cache(event, ct); } EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct); @@ -864,14 +913,14 @@ bool __nf_ct_kill_acct(struct nf_conn *ct, if (do_acct) { struct nf_conn_counter *acct; - spin_lock_bh(&nf_conntrack_lock); acct = nf_conn_acct_find(ct); if (acct) { + spin_lock_bh(&ct->lock); acct[CTINFO2DIR(ctinfo)].packets++; acct[CTINFO2DIR(ctinfo)].bytes += skb->len - skb_network_offset(skb); + spin_unlock_bh(&ct->lock); } - spin_unlock_bh(&nf_conntrack_lock); } if (del_timer(&ct->timeout)) { @@ -1001,15 +1050,22 @@ struct __nf_ct_flush_report { int report; }; -static int kill_all(struct nf_conn *i, void *data) +static int kill_report(struct nf_conn *i, void *data) { struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data; - /* get_next_corpse sets the dying bit for us */ - nf_conntrack_event_report(IPCT_DESTROY, - i, - fr->pid, - fr->report); + /* If we fail to deliver the event, death_by_timeout() will retry */ + if (nf_conntrack_event_report(IPCT_DESTROY, i, + fr->pid, fr->report) < 0) + return 1; + + /* Avoid the delivery of the destroy event in death_by_timeout(). */ + set_bit(IPS_DYING_BIT, &i->status); + return 1; +} + +static int kill_all(struct nf_conn *i, void *data) +{ return 1; } @@ -1023,15 +1079,30 @@ void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size) } EXPORT_SYMBOL_GPL(nf_ct_free_hashtable); -void nf_conntrack_flush(struct net *net, u32 pid, int report) +void nf_conntrack_flush_report(struct net *net, u32 pid, int report) { struct __nf_ct_flush_report fr = { .pid = pid, .report = report, }; - nf_ct_iterate_cleanup(net, kill_all, &fr); + nf_ct_iterate_cleanup(net, kill_report, &fr); +} +EXPORT_SYMBOL_GPL(nf_conntrack_flush_report); + +static void nf_ct_release_dying_list(void) +{ + 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) { + ct = nf_ct_tuplehash_to_ctrack(h); + /* never fails to remove them, no listeners at this point */ + nf_ct_kill(ct); + } + spin_unlock_bh(&nf_conntrack_lock); } -EXPORT_SYMBOL_GPL(nf_conntrack_flush); static void nf_conntrack_cleanup_init_net(void) { @@ -1042,10 +1113,9 @@ static void nf_conntrack_cleanup_init_net(void) static void nf_conntrack_cleanup_net(struct net *net) { - nf_ct_event_cache_flush(net); - nf_conntrack_ecache_fini(net); i_see_dead_people: - nf_conntrack_flush(net, 0, 0); + nf_ct_iterate_cleanup(net, kill_all, NULL); + nf_ct_release_dying_list(); if (atomic_read(&net->ct.count) != 0) { schedule(); goto i_see_dead_people; @@ -1056,6 +1126,7 @@ static void nf_conntrack_cleanup_net(struct net *net) nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, nf_conntrack_htable_size); + nf_conntrack_ecache_fini(net); nf_conntrack_acct_fini(net); nf_conntrack_expect_fini(net); free_percpu(net->ct.stat); @@ -1220,20 +1291,24 @@ err_cache: return ret; } +/* + * We need to use special "null" values, not used in hash table + */ +#define UNCONFIRMED_NULLS_VAL ((1<<30)+0) +#define DYING_NULLS_VAL ((1<<30)+1) + static int nf_conntrack_init_net(struct net *net) { int ret; atomic_set(&net->ct.count, 0); - INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, 0); + INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL); net->ct.stat = alloc_percpu(struct ip_conntrack_stat); if (!net->ct.stat) { ret = -ENOMEM; goto err_stat; } - ret = nf_conntrack_ecache_init(net); - if (ret < 0) - goto err_ecache; net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, &net->ct.hash_vmalloc, 1); if (!net->ct.hash) { @@ -1247,6 +1322,9 @@ static int nf_conntrack_init_net(struct net *net) ret = nf_conntrack_acct_init(net); if (ret < 0) goto err_acct; + ret = nf_conntrack_ecache_init(net); + if (ret < 0) + goto err_ecache; /* Set up fake conntrack: - to never be deleted, not in any hashes */ @@ -1259,14 +1337,14 @@ static int nf_conntrack_init_net(struct net *net) return 0; +err_ecache: + nf_conntrack_acct_fini(net); err_acct: nf_conntrack_expect_fini(net); err_expect: nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, nf_conntrack_htable_size); err_hash: - nf_conntrack_ecache_fini(net); -err_ecache: free_percpu(net->ct.stat); err_stat: return ret; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index dee4190209c..aee560b4768 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -16,121 +16,245 @@ #include <linux/stddef.h> #include <linux/err.h> #include <linux/percpu.h> -#include <linux/notifier.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_extend.h> -ATOMIC_NOTIFIER_HEAD(nf_conntrack_chain); -EXPORT_SYMBOL_GPL(nf_conntrack_chain); +static DEFINE_MUTEX(nf_ct_ecache_mutex); -ATOMIC_NOTIFIER_HEAD(nf_ct_expect_chain); -EXPORT_SYMBOL_GPL(nf_ct_expect_chain); +struct nf_ct_event_notifier *nf_conntrack_event_cb __read_mostly; +EXPORT_SYMBOL_GPL(nf_conntrack_event_cb); + +struct nf_exp_event_notifier *nf_expect_event_cb __read_mostly; +EXPORT_SYMBOL_GPL(nf_expect_event_cb); /* deliver cached events and clear cache entry - must be called with locally * disabled softirqs */ -static inline void -__nf_ct_deliver_cached_events(struct nf_conntrack_ecache *ecache) +void nf_ct_deliver_cached_events(struct nf_conn *ct) { - if (nf_ct_is_confirmed(ecache->ct) && !nf_ct_is_dying(ecache->ct) - && ecache->events) { + unsigned long events; + struct nf_ct_event_notifier *notify; + struct nf_conntrack_ecache *e; + + rcu_read_lock(); + notify = rcu_dereference(nf_conntrack_event_cb); + if (notify == NULL) + goto out_unlock; + + e = nf_ct_ecache_find(ct); + if (e == NULL) + goto out_unlock; + + events = xchg(&e->cache, 0); + + if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct) && events) { struct nf_ct_event item = { - .ct = ecache->ct, + .ct = ct, .pid = 0, .report = 0 }; + int ret; + /* We make a copy of the missed event cache without taking + * the lock, thus we may send missed events twice. However, + * this does not harm and it happens very rarely. */ + unsigned long missed = e->missed; - atomic_notifier_call_chain(&nf_conntrack_chain, - ecache->events, - &item); + ret = notify->fcn(events | missed, &item); + if (unlikely(ret < 0 || missed)) { + spin_lock_bh(&ct->lock); + if (ret < 0) + e->missed |= events; + else + e->missed &= ~missed; + spin_unlock_bh(&ct->lock); + } } - ecache->events = 0; - nf_ct_put(ecache->ct); - ecache->ct = NULL; +out_unlock: + rcu_read_unlock(); } +EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events); -/* Deliver all cached events for a particular conntrack. This is called - * by code prior to async packet handling for freeing the skb */ -void nf_ct_deliver_cached_events(const struct nf_conn *ct) +int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new) { - struct net *net = nf_ct_net(ct); - struct nf_conntrack_ecache *ecache; - - local_bh_disable(); - ecache = per_cpu_ptr(net->ct.ecache, raw_smp_processor_id()); - if (ecache->ct == ct) - __nf_ct_deliver_cached_events(ecache); - local_bh_enable(); + int ret = 0; + struct nf_ct_event_notifier *notify; + + mutex_lock(&nf_ct_ecache_mutex); + notify = rcu_dereference(nf_conntrack_event_cb); + if (notify != NULL) { + ret = -EBUSY; + goto out_unlock; + } + rcu_assign_pointer(nf_conntrack_event_cb, new); + mutex_unlock(&nf_ct_ecache_mutex); + return ret; + +out_unlock: + mutex_unlock(&nf_ct_ecache_mutex); + return ret; } -EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events); +EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier); -/* Deliver cached events for old pending events, if current conntrack != old */ -void __nf_ct_event_cache_init(struct nf_conn *ct) +void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new) { - struct net *net = nf_ct_net(ct); - struct nf_conntrack_ecache *ecache; - - /* take care of delivering potentially old events */ - ecache = per_cpu_ptr(net->ct.ecache, raw_smp_processor_id()); - BUG_ON(ecache->ct == ct); - if (ecache->ct) - __nf_ct_deliver_cached_events(ecache); - /* initialize for this conntrack/packet */ - ecache->ct = ct; - nf_conntrack_get(&ct->ct_general); + struct nf_ct_event_notifier *notify; + + mutex_lock(&nf_ct_ecache_mutex); + notify = rcu_dereference(nf_conntrack_event_cb); + BUG_ON(notify != new); + rcu_assign_pointer(nf_conntrack_event_cb, NULL); + mutex_unlock(&nf_ct_ecache_mutex); } -EXPORT_SYMBOL_GPL(__nf_ct_event_cache_init); +EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); -/* flush the event cache - touches other CPU's data and must not be called - * while packets are still passing through the code */ -void nf_ct_event_cache_flush(struct net *net) +int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new) { - struct nf_conntrack_ecache *ecache; - int cpu; + int ret = 0; + struct nf_exp_event_notifier *notify; - for_each_possible_cpu(cpu) { - ecache = per_cpu_ptr(net->ct.ecache, cpu); - if (ecache->ct) - nf_ct_put(ecache->ct); + mutex_lock(&nf_ct_ecache_mutex); + notify = rcu_dereference(nf_expect_event_cb); + if (notify != NULL) { + ret = -EBUSY; + goto out_unlock; } + rcu_assign_pointer(nf_expect_event_cb, new); + mutex_unlock(&nf_ct_ecache_mutex); + return ret; + +out_unlock: + mutex_unlock(&nf_ct_ecache_mutex); + return ret; } +EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier); -int nf_conntrack_ecache_init(struct net *net) +void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new) { - net->ct.ecache = alloc_percpu(struct nf_conntrack_ecache); - if (!net->ct.ecache) - return -ENOMEM; - return 0; + struct nf_exp_event_notifier *notify; + + mutex_lock(&nf_ct_ecache_mutex); + notify = rcu_dereference(nf_expect_event_cb); + BUG_ON(notify != new); + rcu_assign_pointer(nf_expect_event_cb, NULL); + mutex_unlock(&nf_ct_ecache_mutex); } +EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); -void nf_conntrack_ecache_fini(struct net *net) +#define NF_CT_EVENTS_DEFAULT 1 +static int nf_ct_events __read_mostly = NF_CT_EVENTS_DEFAULT; +static int nf_ct_events_retry_timeout __read_mostly = 15*HZ; + +#ifdef CONFIG_SYSCTL +static struct ctl_table event_sysctl_table[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nf_conntrack_events", + .data = &init_net.ct.sysctl_events, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nf_conntrack_events_retry_timeout", + .data = &init_net.ct.sysctl_events_retry_timeout, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + {} +}; +#endif /* CONFIG_SYSCTL */ + +static struct nf_ct_ext_type event_extend __read_mostly = { + .len = sizeof(struct nf_conntrack_ecache), + .align = __alignof__(struct nf_conntrack_ecache), + .id = NF_CT_EXT_ECACHE, +}; + +#ifdef CONFIG_SYSCTL +static int nf_conntrack_event_init_sysctl(struct net *net) { - free_percpu(net->ct.ecache); + struct ctl_table *table; + + table = kmemdup(event_sysctl_table, sizeof(event_sysctl_table), + GFP_KERNEL); + if (!table) + goto out; + + table[0].data = &net->ct.sysctl_events; + table[1].data = &net->ct.sysctl_events_retry_timeout; + + net->ct.event_sysctl_header = + register_net_sysctl_table(net, + nf_net_netfilter_sysctl_path, table); + if (!net->ct.event_sysctl_header) { + printk(KERN_ERR "nf_ct_event: can't register to sysctl.\n"); + goto out_register; + } + return 0; + +out_register: + kfree(table); +out: + return -ENOMEM; } -int nf_conntrack_register_notifier(struct notifier_block *nb) +static void nf_conntrack_event_fini_sysctl(struct net *net) { - return atomic_notifier_chain_register(&nf_conntrack_chain, nb); + struct ctl_table *table; + + table = net->ct.event_sysctl_header->ctl_table_arg; + unregister_net_sysctl_table(net->ct.event_sysctl_header); + kfree(table); +} +#else +static int nf_conntrack_event_init_sysctl(struct net *net) +{ + return 0; } -EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier); -int nf_conntrack_unregister_notifier(struct notifier_block *nb) +static void nf_conntrack_event_fini_sysctl(struct net *net) { - return atomic_notifier_chain_unregister(&nf_conntrack_chain, nb); } -EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); +#endif /* CONFIG_SYSCTL */ -int nf_ct_expect_register_notifier(struct notifier_block *nb) +int nf_conntrack_ecache_init(struct net *net) { - return atomic_notifier_chain_register(&nf_ct_expect_chain, nb); + int ret; + + net->ct.sysctl_events = nf_ct_events; + net->ct.sysctl_events_retry_timeout = nf_ct_events_retry_timeout; + + if (net_eq(net, &init_net)) { + ret = nf_ct_extend_register(&event_extend); + if (ret < 0) { + printk(KERN_ERR "nf_ct_event: Unable to register " + "event extension.\n"); + goto out_extend_register; + } + } + + ret = nf_conntrack_event_init_sysctl(net); + if (ret < 0) + goto out_sysctl; + + return 0; + +out_sysctl: + if (net_eq(net, &init_net)) + nf_ct_extend_unregister(&event_extend); +out_extend_register: + return ret; } -EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier); -int nf_ct_expect_unregister_notifier(struct notifier_block *nb) +void nf_conntrack_ecache_fini(struct net *net) { - return atomic_notifier_chain_unregister(&nf_ct_expect_chain, nb); + nf_conntrack_event_fini_sysctl(net); + if (net_eq(net, &init_net)) + nf_ct_extend_unregister(&event_extend); } -EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index afde8f99164..2032dfe25ca 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -617,8 +617,10 @@ err1: void nf_conntrack_expect_fini(struct net *net) { exp_proc_remove(net); - if (net_eq(net, &init_net)) + if (net_eq(net, &init_net)) { + rcu_barrier(); /* Wait for call_rcu() before destroy */ kmem_cache_destroy(nf_ct_expect_cachep); + } nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc, nf_ct_expect_hsize); } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 4b2c769d555..fef95be334b 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -186,6 +186,6 @@ void nf_ct_extend_unregister(struct nf_ct_ext_type *type) rcu_assign_pointer(nf_ct_ext_types[type->id], NULL); update_alloc_size(type); mutex_unlock(&nf_ct_ext_type_mutex); - synchronize_rcu(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } EXPORT_SYMBOL_GPL(nf_ct_extend_unregister); diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 00fecc385f9..5509dd1f14c 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -338,11 +338,9 @@ static void update_nl_seq(struct nf_conn *ct, u32 nl_seq, if (info->seq_aft_nl_num[dir] < NUM_SEQ_TO_REMEMBER) { info->seq_aft_nl[dir][info->seq_aft_nl_num[dir]++] = nl_seq; - nf_conntrack_event_cache(IPCT_HELPINFO_VOLATILE, ct); } else if (oldest != NUM_SEQ_TO_REMEMBER && after(nl_seq, info->seq_aft_nl[dir][oldest])) { info->seq_aft_nl[dir][oldest] = nl_seq; - nf_conntrack_event_cache(IPCT_HELPINFO_VOLATILE, ct); } } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 0fa5a422959..65c2a7bc3af 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -136,6 +136,20 @@ static inline int unhelp(struct nf_conntrack_tuple_hash *i, return 0; } +void nf_ct_helper_destroy(struct nf_conn *ct) +{ + struct nf_conn_help *help = nfct_help(ct); + struct nf_conntrack_helper *helper; + + if (help) { + rcu_read_lock(); + helper = rcu_dereference(help->helper); + if (helper && helper->destroy) + helper->destroy(ct); + rcu_read_unlock(); + } +} + int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { unsigned int h = helper_hash(&me->tuple); diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c index 8a3875e36ec..497b2224536 100644 --- a/net/netfilter/nf_conntrack_netbios_ns.c +++ b/net/netfilter/nf_conntrack_netbios_ns.c @@ -48,7 +48,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, { struct nf_conntrack_expect *exp; struct iphdr *iph = ip_hdr(skb); - struct rtable *rt = skb->rtable; + struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; __be32 mask = 0; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c523f0b8cee..49479d19457 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -27,7 +27,6 @@ #include <linux/netlink.h> #include <linux/spinlock.h> #include <linux/interrupt.h> -#include <linux/notifier.h> #include <linux/netfilter.h> #include <net/netlink.h> @@ -144,7 +143,7 @@ nla_put_failure: } static inline int -ctnetlink_dump_protoinfo(struct sk_buff *skb, const struct nf_conn *ct) +ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conntrack_l4proto *l4proto; struct nlattr *nest_proto; @@ -346,23 +345,21 @@ nla_put_failure: return -1; } -#define tuple(ct, dir) (&(ct)->tuplehash[dir].tuple) - static int ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, - int event, int nowait, - const struct nf_conn *ct) + int event, struct nf_conn *ct) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; - unsigned char *b = skb_tail_pointer(skb); + unsigned int flags = pid ? NLM_F_MULTI : 0; event |= NFNL_SUBSYS_CTNETLINK << 8; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg)); - nfmsg = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; - nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0; + nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = nf_ct_l3num(ct); nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; @@ -370,14 +367,14 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; - if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) + if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; - if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0) + if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); @@ -395,132 +392,109 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, ctnetlink_dump_nat_seq_adj(skb, ct) < 0) goto nla_put_failure; - nlh->nlmsg_len = skb_tail_pointer(skb) - b; + nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_cancel(skb, nlh); return -1; } #ifdef CONFIG_NF_CONNTRACK_EVENTS -/* - * The general structure of a ctnetlink event is - * - * CTA_TUPLE_ORIG - * <l3/l4-proto-attributes> - * CTA_TUPLE_REPLY - * <l3/l4-proto-attributes> - * CTA_ID - * ... - * CTA_PROTOINFO - * <l4-proto-attributes> - * CTA_TUPLE_MASTER - * <l3/l4-proto-attributes> - * - * Therefore the formular is - * - * size = sizeof(headers) + sizeof(generic_nlas) + 3 * sizeof(tuple_nlas) - * + sizeof(protoinfo_nlas) - */ -static struct sk_buff * -ctnetlink_alloc_skb(const struct nf_conntrack_tuple *tuple, gfp_t gfp) +static inline size_t +ctnetlink_proto_size(const struct nf_conn *ct) { struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; - int len; - -#define NLA_TYPE_SIZE(type) nla_total_size(sizeof(type)) - - /* proto independant part */ - len = NLMSG_SPACE(sizeof(struct nfgenmsg)) - + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ - + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ - + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ - + 3 * NLA_TYPE_SIZE(u_int8_t) /* CTA_PROTO_NUM */ - + NLA_TYPE_SIZE(u_int32_t) /* CTA_ID */ - + NLA_TYPE_SIZE(u_int32_t) /* CTA_STATUS */ + size_t len = 0; + + rcu_read_lock(); + l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); + len += l3proto->nla_size; + + l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); + len += l4proto->nla_size; + rcu_read_unlock(); + + return len; +} + +static inline size_t +ctnetlink_nlmsg_size(const struct nf_conn *ct) +{ + return NLMSG_ALIGN(sizeof(struct nfgenmsg)) + + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ #ifdef CONFIG_NF_CT_ACCT - + 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */ - + 2 * NLA_TYPE_SIZE(uint64_t) /* CTA_COUNTERS_PACKETS */ - + 2 * NLA_TYPE_SIZE(uint64_t) /* CTA_COUNTERS_BYTES */ + + 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */ + + 2 * nla_total_size(sizeof(uint64_t)) /* CTA_COUNTERS_PACKETS */ + + 2 * nla_total_size(sizeof(uint64_t)) /* CTA_COUNTERS_BYTES */ #endif - + NLA_TYPE_SIZE(u_int32_t) /* CTA_TIMEOUT */ - + nla_total_size(0) /* CTA_PROTOINFO */ - + nla_total_size(0) /* CTA_HELP */ - + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + + nla_total_size(0) /* CTA_PROTOINFO */ + + nla_total_size(0) /* CTA_HELP */ + + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ #ifdef CONFIG_NF_CONNTRACK_SECMARK - + NLA_TYPE_SIZE(u_int32_t) /* CTA_SECMARK */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_SECMARK */ #endif #ifdef CONFIG_NF_NAT_NEEDED - + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ - + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_POS */ - + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_BEFORE */ - + 2 * NLA_TYPE_SIZE(u_int32_t) /* CTA_NAT_SEQ_CORRECTION_AFTER */ + + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK - + NLA_TYPE_SIZE(u_int32_t) /* CTA_MARK */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif - ; - -#undef NLA_TYPE_SIZE - - rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(tuple->src.l3num); - len += l3proto->nla_size; - - l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum); - len += l4proto->nla_size; - rcu_read_unlock(); - - return alloc_skb(len, gfp); + + ctnetlink_proto_size(ct) + ; } -static int ctnetlink_conntrack_event(struct notifier_block *this, - unsigned long events, void *ptr) +static int +ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; - struct nf_ct_event *item = (struct nf_ct_event *)ptr; struct nf_conn *ct = item->ct; struct sk_buff *skb; unsigned int type; - sk_buff_data_t b; unsigned int flags = 0, group; + int err; /* ignore our fake conntrack entry */ if (ct == &nf_conntrack_untracked) - return NOTIFY_DONE; + return 0; - if (events & IPCT_DESTROY) { + if (events & (1 << IPCT_DESTROY)) { type = IPCTNL_MSG_CT_DELETE; group = NFNLGRP_CONNTRACK_DESTROY; - } else if (events & (IPCT_NEW | IPCT_RELATED)) { + } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { type = IPCTNL_MSG_CT_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_NEW; - } else if (events & (IPCT_STATUS | IPCT_PROTOINFO)) { + } else if (events) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else - return NOTIFY_DONE; + return 0; if (!item->report && !nfnetlink_has_listeners(group)) - return NOTIFY_DONE; + return 0; - skb = ctnetlink_alloc_skb(tuple(ct, IP_CT_DIR_ORIGINAL), GFP_ATOMIC); - if (!skb) + skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC); + if (skb == NULL) goto errout; - b = skb->tail; - type |= NFNL_SUBSYS_CTNETLINK << 8; - nlh = NLMSG_PUT(skb, item->pid, 0, type, sizeof(struct nfgenmsg)); - nfmsg = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; - nlh->nlmsg_flags = flags; + nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = nf_ct_l3num(ct); nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; @@ -529,14 +503,14 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; - if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) + if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; - if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0) + if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); @@ -546,7 +520,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; - if (events & IPCT_DESTROY) { + if (events & (1 << IPCT_DESTROY)) { if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0) goto nla_put_failure; @@ -554,47 +528,51 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, if (ctnetlink_dump_timeout(skb, ct) < 0) goto nla_put_failure; - if (events & IPCT_PROTOINFO + if (events & (1 << IPCT_PROTOINFO) && ctnetlink_dump_protoinfo(skb, ct) < 0) goto nla_put_failure; - if ((events & IPCT_HELPER || nfct_help(ct)) + if ((events & (1 << IPCT_HELPER) || nfct_help(ct)) && ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK - if ((events & IPCT_SECMARK || ct->secmark) + if ((events & (1 << IPCT_SECMARK) || ct->secmark) && ctnetlink_dump_secmark(skb, ct) < 0) goto nla_put_failure; #endif - if (events & IPCT_RELATED && + if (events & (1 << IPCT_RELATED) && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; - if (events & IPCT_NATSEQADJ && + if (events & (1 << IPCT_NATSEQADJ) && ctnetlink_dump_nat_seq_adj(skb, ct) < 0) goto nla_put_failure; } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((events & IPCT_MARK || ct->mark) + if ((events & (1 << IPCT_MARK) || ct->mark) && ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif rcu_read_unlock(); - nlh->nlmsg_len = skb->tail - b; - nfnetlink_send(skb, item->pid, group, item->report); - return NOTIFY_DONE; + nlmsg_end(skb, nlh); + err = nfnetlink_send(skb, item->pid, group, item->report, GFP_ATOMIC); + if (err == -ENOBUFS || err == -EAGAIN) + return -ENOBUFS; + + return 0; nla_put_failure: rcu_read_unlock(); + nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: nfnetlink_set_err(0, group, -ENOBUFS); - return NOTIFY_DONE; + return 0; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ @@ -611,7 +589,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); + struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; rcu_read_lock(); @@ -637,8 +615,7 @@ restart: } if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, - IPCTNL_MSG_CT_NEW, - 1, ct) < 0) { + IPCTNL_MSG_CT_NEW, ct) < 0) { cb->args[1] = (unsigned long)ct; goto out; } @@ -792,7 +769,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conn *ct; - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; int err = 0; @@ -802,9 +779,9 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3); else { /* Flush the whole table */ - nf_conntrack_flush(&init_net, - NETLINK_CB(skb).pid, - nlmsg_report(nlh)); + nf_conntrack_flush_report(&init_net, + NETLINK_CB(skb).pid, + nlmsg_report(nlh)); return 0; } @@ -825,10 +802,15 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, } } - nf_conntrack_event_report(IPCT_DESTROY, - ct, - NETLINK_CB(skb).pid, - nlmsg_report(nlh)); + if (nf_conntrack_event_report(IPCT_DESTROY, ct, + NETLINK_CB(skb).pid, + nlmsg_report(nlh)) < 0) { + nf_ct_delete_from_lists(ct); + /* we failed to report the event, try later */ + nf_ct_insert_dying_list(ct); + nf_ct_put(ct); + return 0; + } /* death_by_timeout would report the event again */ set_bit(IPS_DYING_BIT, &ct->status); @@ -847,7 +829,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple tuple; struct nf_conn *ct; struct sk_buff *skb2 = NULL; - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; int err = 0; @@ -872,15 +854,15 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, ct = nf_ct_tuplehash_to_ctrack(h); err = -ENOMEM; - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb2) { + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) { nf_ct_put(ct); return -ENOMEM; } rcu_read_lock(); err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, - IPCTNL_MSG_CT_NEW, 1, ct); + IPCTNL_MSG_CT_NEW, ct); rcu_read_unlock(); nf_ct_put(ct); if (err <= 0) @@ -1280,6 +1262,7 @@ ctnetlink_create_conntrack(struct nlattr *cda[], } nf_ct_acct_ext_add(ct, GFP_ATOMIC); + nf_ct_ecache_ext_add(ct, GFP_ATOMIC); #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) @@ -1325,7 +1308,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, { struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; int err = 0; @@ -1367,13 +1350,13 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, else events = IPCT_NEW; - nf_conntrack_event_report(IPCT_STATUS | - IPCT_HELPER | - IPCT_PROTOINFO | - IPCT_NATSEQADJ | - IPCT_MARK | events, - ct, NETLINK_CB(skb).pid, - nlmsg_report(nlh)); + nf_conntrack_eventmask_report((1 << IPCT_STATUS) | + (1 << IPCT_HELPER) | + (1 << IPCT_PROTOINFO) | + (1 << IPCT_NATSEQADJ) | + (1 << IPCT_MARK) | events, + ct, NETLINK_CB(skb).pid, + nlmsg_report(nlh)); nf_ct_put(ct); } else spin_unlock_bh(&nf_conntrack_lock); @@ -1392,13 +1375,13 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err == 0) { nf_conntrack_get(&ct->ct_general); spin_unlock_bh(&nf_conntrack_lock); - nf_conntrack_event_report(IPCT_STATUS | - IPCT_HELPER | - IPCT_PROTOINFO | - IPCT_NATSEQADJ | - IPCT_MARK, - ct, NETLINK_CB(skb).pid, - nlmsg_report(nlh)); + nf_conntrack_eventmask_report((1 << IPCT_STATUS) | + (1 << IPCT_HELPER) | + (1 << IPCT_PROTOINFO) | + (1 << IPCT_NATSEQADJ) | + (1 << IPCT_MARK), + ct, NETLINK_CB(skb).pid, + nlmsg_report(nlh)); nf_ct_put(ct); } else spin_unlock_bh(&nf_conntrack_lock); @@ -1503,19 +1486,18 @@ nla_put_failure: static int ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq, - int event, - int nowait, - const struct nf_conntrack_expect *exp) + int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned char *b = skb_tail_pointer(skb); + unsigned int flags = pid ? NLM_F_MULTI : 0; event |= NFNL_SUBSYS_CTNETLINK_EXP << 8; - nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg)); - nfmsg = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; - nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0; + nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = exp->tuple.src.l3num; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; @@ -1523,49 +1505,46 @@ ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq, if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; - nlh->nlmsg_len = skb_tail_pointer(skb) - b; + nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_cancel(skb, nlh); return -1; } #ifdef CONFIG_NF_CONNTRACK_EVENTS -static int ctnetlink_expect_event(struct notifier_block *this, - unsigned long events, void *ptr) +static int +ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - struct nf_exp_event *item = (struct nf_exp_event *)ptr; struct nf_conntrack_expect *exp = item->exp; struct sk_buff *skb; unsigned int type; - sk_buff_data_t b; int flags = 0; - if (events & IPEXP_NEW) { + if (events & (1 << IPEXP_NEW)) { type = IPCTNL_MSG_EXP_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; } else - return NOTIFY_DONE; + return 0; if (!item->report && !nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW)) - return NOTIFY_DONE; + return 0; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); - if (!skb) + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (skb == NULL) goto errout; - b = skb->tail; - type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; - nlh = NLMSG_PUT(skb, item->pid, 0, type, sizeof(struct nfgenmsg)); - nfmsg = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; - nlh->nlmsg_flags = flags; + nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = exp->tuple.src.l3num; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; @@ -1575,17 +1554,19 @@ static int ctnetlink_expect_event(struct notifier_block *this, goto nla_put_failure; rcu_read_unlock(); - nlh->nlmsg_len = skb->tail - b; - nfnetlink_send(skb, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, item->report); - return NOTIFY_DONE; + nlmsg_end(skb, nlh); + nfnetlink_send(skb, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, + item->report, GFP_ATOMIC); + return 0; nla_put_failure: rcu_read_unlock(); + nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: nfnetlink_set_err(0, 0, -ENOBUFS); - return NOTIFY_DONE; + return 0; } #endif static int ctnetlink_exp_done(struct netlink_callback *cb) @@ -1600,7 +1581,7 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = &init_net; struct nf_conntrack_expect *exp, *last; - struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); + struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct hlist_node *n; u_int8_t l3proto = nfmsg->nfgen_family; @@ -1617,10 +1598,11 @@ restart: continue; cb->args[1] = 0; } - if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).pid, + if (ctnetlink_exp_fill_info(skb, + NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, - 1, exp) < 0) { + exp) < 0) { if (!atomic_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; @@ -1652,7 +1634,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct sk_buff *skb2; - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; int err = 0; @@ -1683,14 +1665,13 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, } err = -ENOMEM; - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb2) + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) goto out; rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid, - nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, - 1, exp); + nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); if (err <= 0) goto free; @@ -1713,7 +1694,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nf_conntrack_helper *h; - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct hlist_node *n, *next; u_int8_t u3 = nfmsg->nfgen_family; unsigned int i; @@ -1854,7 +1835,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; - struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; int err = 0; @@ -1891,12 +1872,12 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, } #ifdef CONFIG_NF_CONNTRACK_EVENTS -static struct notifier_block ctnl_notifier = { - .notifier_call = ctnetlink_conntrack_event, +static struct nf_ct_event_notifier ctnl_notifier = { + .fcn = ctnetlink_conntrack_event, }; -static struct notifier_block ctnl_notifier_exp = { - .notifier_call = ctnetlink_expect_event, +static struct nf_exp_event_notifier ctnl_notifier_exp = { + .fcn = ctnetlink_expect_event, }; #endif diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index aee0d6bea30..1b816a2ea81 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -25,8 +25,6 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_log.h> -static DEFINE_RWLOCK(dccp_lock); - /* Timeouts are based on values from RFC4340: * * - REQUEST: @@ -492,7 +490,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, return NF_ACCEPT; } - write_lock_bh(&dccp_lock); + spin_lock_bh(&ct->lock); role = ct->proto.dccp.role[dir]; old_state = ct->proto.dccp.state; @@ -536,13 +534,13 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.dccp.last_dir = dir; ct->proto.dccp.last_pkt = type; - write_unlock_bh(&dccp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_DCCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_dccp: invalid packet ignored "); return NF_ACCEPT; case CT_DCCP_INVALID: - write_unlock_bh(&dccp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_DCCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_dccp: invalid state transition "); @@ -552,7 +550,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.dccp.last_dir = dir; ct->proto.dccp.last_pkt = type; ct->proto.dccp.state = new_state; - write_unlock_bh(&dccp_lock); + spin_unlock_bh(&ct->lock); if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); @@ -621,36 +619,39 @@ static int dccp_print_tuple(struct seq_file *s, ntohs(tuple->dst.u.dccp.port)); } -static int dccp_print_conntrack(struct seq_file *s, const struct nf_conn *ct) +static int dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { return seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]); } #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, - const struct nf_conn *ct) + struct nf_conn *ct) { struct nlattr *nest_parms; - read_lock_bh(&dccp_lock); + spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state); NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_ROLE, ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]); + NLA_PUT_BE64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ, + cpu_to_be64(ct->proto.dccp.handshake_seq)); nla_nest_end(skb, nest_parms); - read_unlock_bh(&dccp_lock); + spin_unlock_bh(&ct->lock); return 0; nla_put_failure: - read_unlock_bh(&dccp_lock); + spin_unlock_bh(&ct->lock); return -1; } static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = { [CTA_PROTOINFO_DCCP_STATE] = { .type = NLA_U8 }, [CTA_PROTOINFO_DCCP_ROLE] = { .type = NLA_U8 }, + [CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ] = { .type = NLA_U64 }, }; static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) @@ -674,7 +675,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) return -EINVAL; } - write_lock_bh(&dccp_lock); + spin_lock_bh(&ct->lock); ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]); if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) { ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; @@ -683,7 +684,11 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT; } - write_unlock_bh(&dccp_lock); + if (tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]) { + ct->proto.dccp.handshake_seq = + be64_to_cpu(nla_get_be64(tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ])); + } + spin_unlock_bh(&ct->lock); return 0; } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 117b80112fc..a54a0af0edb 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -176,7 +176,7 @@ static bool gre_invert_tuple(struct nf_conntrack_tuple *tuple, static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) { - struct net *net = dev_net(skb->dev ? skb->dev : skb->dst->dev); + struct net *net = dev_net(skb->dev ? skb->dev : skb_dst(skb)->dev); const struct gre_hdr_pptp *pgrehdr; struct gre_hdr_pptp _pgrehdr; __be16 srckey; @@ -219,8 +219,7 @@ static int gre_print_tuple(struct seq_file *s, } /* print private data for conntrack */ -static int gre_print_conntrack(struct seq_file *s, - const struct nf_conn *ct) +static int gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) { return seq_printf(s, "timeout=%u, stream_timeout=%u ", (ct->proto.gre.timeout / HZ), diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 101b4ad9e81..c10e6f36e31 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -25,9 +25,6 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_ecache.h> -/* Protects ct->proto.sctp */ -static DEFINE_RWLOCK(sctp_lock); - /* FIXME: Examine ipfilter's timeouts and conntrack transitions more closely. They're more complex. --RR @@ -164,13 +161,13 @@ static int sctp_print_tuple(struct seq_file *s, } /* Print out the private part of the conntrack. */ -static int sctp_print_conntrack(struct seq_file *s, const struct nf_conn *ct) +static int sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { enum sctp_conntrack state; - read_lock_bh(&sctp_lock); + spin_lock_bh(&ct->lock); state = ct->proto.sctp.state; - read_unlock_bh(&sctp_lock); + spin_unlock_bh(&ct->lock); return seq_printf(s, "%s ", sctp_conntrack_names[state]); } @@ -318,7 +315,7 @@ static int sctp_packet(struct nf_conn *ct, } old_state = new_state = SCTP_CONNTRACK_NONE; - write_lock_bh(&sctp_lock); + spin_lock_bh(&ct->lock); for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Special cases of Verification tag check (Sec 8.5.1) */ if (sch->type == SCTP_CID_INIT) { @@ -371,7 +368,7 @@ static int sctp_packet(struct nf_conn *ct, if (old_state != new_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); } - write_unlock_bh(&sctp_lock); + spin_unlock_bh(&ct->lock); nf_ct_refresh_acct(ct, ctinfo, skb, sctp_timeouts[new_state]); @@ -386,7 +383,7 @@ static int sctp_packet(struct nf_conn *ct, return NF_ACCEPT; out_unlock: - write_unlock_bh(&sctp_lock); + spin_unlock_bh(&ct->lock); out: return -NF_ACCEPT; } @@ -469,11 +466,11 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, #include <linux/netfilter/nfnetlink_conntrack.h> static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, - const struct nf_conn *ct) + struct nf_conn *ct) { struct nlattr *nest_parms; - read_lock_bh(&sctp_lock); + spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_SCTP | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; @@ -488,14 +485,14 @@ static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, CTA_PROTOINFO_SCTP_VTAG_REPLY, ct->proto.sctp.vtag[IP_CT_DIR_REPLY]); - read_unlock_bh(&sctp_lock); + spin_unlock_bh(&ct->lock); nla_nest_end(skb, nest_parms); return 0; nla_put_failure: - read_unlock_bh(&sctp_lock); + spin_unlock_bh(&ct->lock); return -1; } @@ -527,13 +524,13 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct) !tb[CTA_PROTOINFO_SCTP_VTAG_REPLY]) return -EINVAL; - write_lock_bh(&sctp_lock); + spin_lock_bh(&ct->lock); ct->proto.sctp.state = nla_get_u8(tb[CTA_PROTOINFO_SCTP_STATE]); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_ORIGINAL]); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_REPLY]); - write_unlock_bh(&sctp_lock); + spin_unlock_bh(&ct->lock); return 0; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 97a6e93d742..97a82ba7537 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -29,9 +29,6 @@ #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> -/* Protects ct->proto.tcp */ -static DEFINE_RWLOCK(tcp_lock); - /* "Be conservative in what you do, be liberal in what you accept from others." If it's non-zero, we mark only out of window RST segments as INVALID. */ @@ -59,7 +56,7 @@ static const char *const tcp_conntrack_names[] = { "LAST_ACK", "TIME_WAIT", "CLOSE", - "LISTEN" + "SYN_SENT2", }; #define SECS * HZ @@ -82,6 +79,7 @@ static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = { [TCP_CONNTRACK_LAST_ACK] = 30 SECS, [TCP_CONNTRACK_TIME_WAIT] = 2 MINS, [TCP_CONNTRACK_CLOSE] = 10 SECS, + [TCP_CONNTRACK_SYN_SENT2] = 2 MINS, }; #define sNO TCP_CONNTRACK_NONE @@ -93,7 +91,7 @@ static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = { #define sLA TCP_CONNTRACK_LAST_ACK #define sTW TCP_CONNTRACK_TIME_WAIT #define sCL TCP_CONNTRACK_CLOSE -#define sLI TCP_CONNTRACK_LISTEN +#define sS2 TCP_CONNTRACK_SYN_SENT2 #define sIV TCP_CONNTRACK_MAX #define sIG TCP_CONNTRACK_IGNORE @@ -123,6 +121,7 @@ enum tcp_bit_set { * * NONE: initial state * SYN_SENT: SYN-only packet seen + * SYN_SENT2: SYN-only packet seen from reply dir, simultaneous open * SYN_RECV: SYN-ACK packet seen * ESTABLISHED: ACK packet seen * FIN_WAIT: FIN packet seen @@ -131,26 +130,24 @@ enum tcp_bit_set { * TIME_WAIT: last ACK seen * CLOSE: closed connection (RST) * - * LISTEN state is not used. - * * Packets marked as IGNORED (sIG): * if they may be either invalid or valid * and the receiver may send back a connection * closing RST or a SYN/ACK. * * Packets marked as INVALID (sIV): - * if they are invalid - * or we do not support the request (simultaneous open) + * if we regard them as truly invalid packets */ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*syn*/ { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*syn*/ { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sS2 }, /* * sNO -> sSS Initialize a new connection * sSS -> sSS Retransmitted SYN - * sSR -> sIG Late retransmitted SYN? + * sS2 -> sS2 Late retransmitted SYN + * sSR -> sIG * sES -> sIG Error: SYNs in window outside the SYN_SENT state * are errors. Receiver will reply with RST * and close the connection. @@ -161,22 +158,30 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sSS Reopened connection (RFC 1122). * sCL -> sSS */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*synack*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*synack*/ { sIV, sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, sSR }, /* - * A SYN/ACK from the client is always invalid: - * - either it tries to set up a simultaneous open, which is - * not supported; - * - or the firewall has just been inserted between the two hosts - * during the session set-up. The SYN will be retransmitted - * by the true client (or it'll time out). + * sNO -> sIV Too late and no reason to do anything + * sSS -> sIV Client can't send SYN and then SYN/ACK + * sS2 -> sSR SYN/ACK sent to SYN2 in simultaneous open + * sSR -> sIG + * sES -> sIG Error: SYNs in window outside the SYN_SENT state + * are errors. Receiver will reply with RST + * and close the connection. + * Or we are not in sync and hold a dead connection. + * sFW -> sIG + * sCW -> sIG + * sLA -> sIG + * sTW -> sIG + * sCL -> sIG */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV }, /* * sNO -> sIV Too late and no reason to do anything... * sSS -> sIV Client migth not send FIN in this state: * we enforce waiting for a SYN/ACK reply first. + * sS2 -> sIV * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions, waiting for @@ -187,11 +192,12 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sTW * sCL -> sCL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*ack*/ { sES, sIV, sES, sES, sCW, sCW, sTW, sTW, sCL, sIV }, /* * sNO -> sES Assumed. * sSS -> sIV ACK is invalid: we haven't seen a SYN/ACK yet. + * sS2 -> sIV * sSR -> sES Established state is reached. * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. @@ -200,29 +206,31 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sTW Retransmitted last ACK. Remain in the same state. * sCL -> sCL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } }, { /* REPLY */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*syn*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*syn*/ { sIV, sS2, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sS2 }, /* * sNO -> sIV Never reached. - * sSS -> sIV Simultaneous open, not supported - * sSR -> sIV Simultaneous open, not supported. - * sES -> sIV Server may not initiate a connection. + * sSS -> sS2 Simultaneous open + * sS2 -> sS2 Retransmitted simultaneous SYN + * sSR -> sIV Invalid SYN packets sent by the server + * sES -> sIV * sFW -> sIV * sCW -> sIV * sLA -> sIV * sTW -> sIV Reopened connection, but server may not do it. * sCL -> sIV */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sSR }, /* * sSS -> sSR Standard open. + * sS2 -> sSR Simultaneous open * sSR -> sSR Retransmitted SYN/ACK. * sES -> sIG Late retransmitted SYN/ACK? * sFW -> sIG Might be SYN/ACK answering ignored SYN @@ -231,10 +239,11 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sIG * sCL -> sIG */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ /*fin*/ { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV }, /* * sSS -> sIV Server might not send FIN in this state. + * sS2 -> sIV * sSR -> sFW Close started. * sES -> sFW * sFW -> sLA FIN seen in both directions. @@ -243,10 +252,11 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sTW * sCL -> sCL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*ack*/ { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*ack*/ { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIG }, /* * sSS -> sIG Might be a half-open connection. + * sS2 -> sIG * sSR -> sSR Might answer late resent SYN. * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. @@ -255,8 +265,8 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sTW -> sTW Retransmitted last ACK. * sCL -> sCL */ -/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI */ -/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV }, +/* sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2 */ +/*rst*/ { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL }, /*none*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV } } }; @@ -296,13 +306,13 @@ static int tcp_print_tuple(struct seq_file *s, } /* Print out the private part of the conntrack. */ -static int tcp_print_conntrack(struct seq_file *s, const struct nf_conn *ct) +static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { enum tcp_conntrack state; - read_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); state = ct->proto.tcp.state; - read_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); return seq_printf(s, "%s ", tcp_conntrack_names[state]); } @@ -521,13 +531,14 @@ static bool tcp_in_window(const struct nf_conn *ct, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); - if (sender->td_end == 0) { + if (sender->td_maxwin == 0) { /* * Initialize sender data. */ - if (tcph->syn && tcph->ack) { + if (tcph->syn) { /* - * Outgoing SYN-ACK in reply to a SYN. + * SYN-ACK in reply to a SYN + * or SYN from reply direction in simultaneous open. */ sender->td_end = sender->td_maxend = end; @@ -543,6 +554,9 @@ static bool tcp_in_window(const struct nf_conn *ct, && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) sender->td_scale = receiver->td_scale = 0; + if (!tcph->ack) + /* Simultaneous open */ + return true; } else { /* * We are in the middle of a connection, @@ -706,8 +720,8 @@ static bool tcp_in_window(const struct nf_conn *ct, /* 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) + 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]; @@ -716,14 +730,14 @@ void nf_conntrack_tcp_update(const struct sk_buff *skb, end = segment_seq_plus_len(ntohl(tcph->seq), skb->len, dataoff, tcph); - write_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); /* * We have to worry for the ack in the reply packet only... */ - if (after(end, ct->proto.tcp.seen[dir].td_end)) + if (ct->proto.tcp.seen[dir].td_end + offset == end) ct->proto.tcp.seen[dir].td_end = end; ct->proto.tcp.last_end = end; - write_unlock_bh(&tcp_lock); + 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, @@ -832,7 +846,7 @@ static int tcp_packet(struct nf_conn *ct, th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph); BUG_ON(th == NULL); - write_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); old_state = ct->proto.tcp.state; dir = CTINFO2DIR(ctinfo); index = get_conntrack_index(th); @@ -862,7 +876,7 @@ static int tcp_packet(struct nf_conn *ct, && ct->proto.tcp.last_index == TCP_RST_SET)) { /* Attempt to reopen a closed/aborted connection. * Delete this connection and look up again. */ - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); /* Only repeat if we can actually remove the timer. * Destruction may already be in progress in process @@ -898,7 +912,7 @@ static int tcp_packet(struct nf_conn *ct, * that the client cannot but retransmit its SYN and * thus initiate a clean new session. */ - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: killing out of sync session "); @@ -911,7 +925,7 @@ static int tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid packet ignored "); @@ -920,7 +934,7 @@ static int tcp_packet(struct nf_conn *ct, /* Invalid packet */ pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n", dir, get_conntrack_index(th), old_state); - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid state "); @@ -930,7 +944,7 @@ static int tcp_packet(struct nf_conn *ct, && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) { /* Invalid RST */ - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid RST "); @@ -961,7 +975,7 @@ static int tcp_packet(struct nf_conn *ct, if (!tcp_in_window(ct, &ct->proto.tcp, dir, index, skb, dataoff, th, pf)) { - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); return -NF_ACCEPT; } in_window: @@ -990,9 +1004,8 @@ static int tcp_packet(struct nf_conn *ct, timeout = nf_ct_tcp_timeout_unacknowledged; else timeout = tcp_timeouts[new_state]; - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); - nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct); if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); @@ -1086,7 +1099,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.tcp.seen[1].td_end = 0; ct->proto.tcp.seen[1].td_maxend = 0; - ct->proto.tcp.seen[1].td_maxwin = 1; + ct->proto.tcp.seen[1].td_maxwin = 0; ct->proto.tcp.seen[1].td_scale = 0; /* tcp_packet will set them */ @@ -1108,12 +1121,12 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, #include <linux/netfilter/nfnetlink_conntrack.h> static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, - const struct nf_conn *ct) + struct nf_conn *ct) { struct nlattr *nest_parms; struct nf_ct_tcp_flags tmp = {}; - read_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; @@ -1133,14 +1146,14 @@ static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, tmp.flags = ct->proto.tcp.seen[1].flags; NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY, sizeof(struct nf_ct_tcp_flags), &tmp); - read_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); nla_nest_end(skb, nest_parms); return 0; nla_put_failure: - read_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); return -1; } @@ -1171,7 +1184,7 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX) return -EINVAL; - write_lock_bh(&tcp_lock); + spin_lock_bh(&ct->lock); if (tb[CTA_PROTOINFO_TCP_STATE]) ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]); @@ -1198,7 +1211,7 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) ct->proto.tcp.seen[1].td_scale = nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_REPLY]); } - write_unlock_bh(&tcp_lock); + spin_unlock_bh(&ct->lock); return 0; } @@ -1328,6 +1341,13 @@ static struct ctl_table tcp_compat_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, { + .procname = "ip_conntrack_tcp_timeout_syn_sent2", + .data = &tcp_timeouts[TCP_CONNTRACK_SYN_SENT2], + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { .procname = "ip_conntrack_tcp_timeout_syn_recv", .data = &tcp_timeouts[TCP_CONNTRACK_SYN_RECV], .maxlen = sizeof(unsigned int), diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index beb37311e1a..4e620305f28 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -47,7 +47,6 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger) mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { - int i; for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) list_add_tail(&(logger->list[i]), &(nf_loggers_l[i])); } else { @@ -216,7 +215,7 @@ static const struct file_operations nflog_file_ops = { #endif /* PROC_FS */ #ifdef CONFIG_SYSCTL -struct ctl_path nf_log_sysctl_path[] = { +static struct ctl_path nf_log_sysctl_path[] = { { .procname = "net", .ctl_name = CTL_NET, }, { .procname = "netfilter", .ctl_name = NET_NETFILTER, }, { .procname = "nf_log", .ctl_name = CTL_UNNUMBERED, }, @@ -228,19 +227,26 @@ 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, - void *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; + char buf[NFLOGGER_NAME_LEN]; + size_t size = *lenp; int r = 0; int tindex = (unsigned long)table->extra1; if (write) { - if (!strcmp(buffer, "NONE")) { + if (size > sizeof(buf)) + size = sizeof(buf); + if (copy_from_user(buf, buffer, size)) + return -EFAULT; + + if (!strcmp(buf, "NONE")) { nf_log_unbind_pf(tindex); return 0; } mutex_lock(&nf_log_mutex); - logger = __find_logger(tindex, buffer); + logger = __find_logger(tindex, buf); if (logger == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; @@ -248,14 +254,14 @@ static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp, rcu_assign_pointer(nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { - rcu_read_lock(); - logger = rcu_dereference(nf_loggers[tindex]); + mutex_lock(&nf_log_mutex); + logger = nf_loggers[tindex]; if (!logger) table->data = "NONE"; else table->data = logger->name; r = proc_dostring(table, write, filp, buffer, lenp, ppos); - rcu_read_unlock(); + mutex_unlock(&nf_log_mutex); } return r; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 4f2310c93e0..3a6fd77f776 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -204,10 +204,10 @@ int nf_queue(struct sk_buff *skb, queuenum); switch (pf) { - case AF_INET: + case NFPROTO_IPV4: skb->protocol = htons(ETH_P_IP); break; - case AF_INET6: + case NFPROTO_IPV6: skb->protocol = htons(ETH_P_IPV6); break; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index b8ab37ad7ed..92761a98837 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -107,9 +107,10 @@ int nfnetlink_has_listeners(unsigned int group) } EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); -int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo) +int nfnetlink_send(struct sk_buff *skb, u32 pid, + unsigned group, int echo, gfp_t flags) { - return nlmsg_notify(nfnl, skb, pid, group, echo, gfp_any()); + return nlmsg_notify(nfnl, skb, pid, group, echo, flags); } EXPORT_SYMBOL_GPL(nfnetlink_send); @@ -136,7 +137,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EPERM; /* All the messages must at least contain nfgenmsg */ - if (nlh->nlmsg_len < NLMSG_SPACE(sizeof(struct nfgenmsg))) + if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct nfgenmsg))) return 0; type = nlh->nlmsg_type; @@ -160,19 +161,14 @@ replay: { int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg)); u_int8_t cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); - u_int16_t attr_count = ss->cb[cb_id].attr_count; - struct nlattr *cda[attr_count+1]; - - if (likely(nlh->nlmsg_len >= min_len)) { - struct nlattr *attr = (void *)nlh + NLMSG_ALIGN(min_len); - int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len); - - err = nla_parse(cda, attr_count, attr, attrlen, - ss->cb[cb_id].policy); - if (err < 0) - return err; - } else - return -EINVAL; + struct nlattr *cda[ss->cb[cb_id].attr_count + 1]; + struct nlattr *attr = (void *)nlh + min_len; + int attrlen = nlh->nlmsg_len - min_len; + + err = nla_parse(cda, ss->cb[cb_id].attr_count, + attr, attrlen, ss->cb[cb_id].policy); + if (err < 0) + return err; err = nc->call(nfnl, skb, nlh, cda); if (err == -EAGAIN) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 8c860112ce0..71daa0934b6 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1,6 +1,6 @@ /* * This is a module which is used for queueing packets and communicating with - * userspace via nfetlink. + * userspace via nfnetlink. * * (C) 2005 by Harald Welte <laforge@netfilter.org> * (C) 2007 by Patrick McHardy <kaber@trash.net> @@ -932,6 +932,8 @@ static void __exit nfnetlink_queue_fini(void) #endif nfnetlink_subsys_unregister(&nfqnl_subsys); netlink_unregister_notifier(&nfqnl_rtnl_notifier); + + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_DESCRIPTION("netfilter packet queue handler"); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 150e5cf62f8..025d1a0af78 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -329,6 +329,32 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target, } EXPORT_SYMBOL_GPL(xt_find_revision); +static char *textify_hooks(char *buf, size_t size, unsigned int mask) +{ + static const char *const names[] = { + "PREROUTING", "INPUT", "FORWARD", + "OUTPUT", "POSTROUTING", "BROUTING", + }; + unsigned int i; + char *p = buf; + bool np = false; + int res; + + *p = '\0'; + for (i = 0; i < ARRAY_SIZE(names); ++i) { + if (!(mask & (1 << i))) + continue; + res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); + if (res > 0) { + size -= res; + p += res; + } + np = true; + } + + return buf; +} + int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { @@ -338,26 +364,30 @@ int xt_check_match(struct xt_mtchk_param *par, * ebt_among is exempt from centralized matchsize checking * because it uses a dynamic-size data set. */ - printk("%s_tables: %s match: invalid size %Zu != %u\n", + pr_err("%s_tables: %s match: invalid size %Zu != %u\n", xt_prefix[par->family], par->match->name, XT_ALIGN(par->match->matchsize), size); return -EINVAL; } if (par->match->table != NULL && strcmp(par->match->table, par->table) != 0) { - printk("%s_tables: %s match: only valid in %s table, not %s\n", + pr_err("%s_tables: %s match: only valid in %s table, not %s\n", xt_prefix[par->family], par->match->name, par->match->table, par->table); return -EINVAL; } if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) { - printk("%s_tables: %s match: bad hook_mask %#x/%#x\n", + char used[64], allow[64]; + + pr_err("%s_tables: %s match: used from hooks %s, but only " + "valid from %s\n", xt_prefix[par->family], par->match->name, - par->hook_mask, par->match->hooks); + textify_hooks(used, sizeof(used), par->hook_mask), + textify_hooks(allow, sizeof(allow), par->match->hooks)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { - printk("%s_tables: %s match: only valid for protocol %u\n", + pr_err("%s_tables: %s match: only valid for protocol %u\n", xt_prefix[par->family], par->match->name, par->match->proto); return -EINVAL; @@ -484,26 +514,30 @@ int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { if (XT_ALIGN(par->target->targetsize) != size) { - printk("%s_tables: %s target: invalid size %Zu != %u\n", + pr_err("%s_tables: %s target: invalid size %Zu != %u\n", xt_prefix[par->family], par->target->name, XT_ALIGN(par->target->targetsize), size); return -EINVAL; } if (par->target->table != NULL && strcmp(par->target->table, par->table) != 0) { - printk("%s_tables: %s target: only valid in %s table, not %s\n", + pr_err("%s_tables: %s target: only valid in %s table, not %s\n", xt_prefix[par->family], par->target->name, par->target->table, par->table); return -EINVAL; } if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) { - printk("%s_tables: %s target: bad hook_mask %#x/%#x\n", + char used[64], allow[64]; + + pr_err("%s_tables: %s target: used from hooks %s, but only " + "usable from %s\n", xt_prefix[par->family], par->target->name, - par->hook_mask, par->target->hooks); + textify_hooks(used, sizeof(used), par->hook_mask), + textify_hooks(allow, sizeof(allow), par->target->hooks)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { - printk("%s_tables: %s target: only valid for protocol %u\n", + pr_err("%s_tables: %s target: only valid for protocol %u\n", xt_prefix[par->family], par->target->name, par->target->proto); return -EINVAL; diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index f9977b3311f..f28f6a5fc02 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -11,6 +11,10 @@ #include <linux/module.h> #include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/jhash.h> + #include <linux/netfilter.h> #include <linux/netfilter_arp.h> #include <linux/netfilter/x_tables.h> @@ -23,6 +27,8 @@ MODULE_ALIAS("ipt_NFQUEUE"); MODULE_ALIAS("ip6t_NFQUEUE"); MODULE_ALIAS("arpt_NFQUEUE"); +static u32 jhash_initval __read_mostly; + static unsigned int nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par) { @@ -31,32 +37,105 @@ nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par) return NF_QUEUE_NR(tinfo->queuenum); } +static u32 hash_v4(const struct sk_buff *skb) +{ + const struct iphdr *iph = ip_hdr(skb); + __be32 ipaddr; + + /* packets in either direction go into same queue */ + ipaddr = iph->saddr ^ iph->daddr; + + return jhash_2words((__force u32)ipaddr, iph->protocol, jhash_initval); +} + +static unsigned int +nfqueue_tg4_v1(struct sk_buff *skb, const struct xt_target_param *par) +{ + const struct xt_NFQ_info_v1 *info = par->targinfo; + u32 queue = info->queuenum; + + if (info->queues_total > 1) + queue = hash_v4(skb) % info->queues_total + queue; + return NF_QUEUE_NR(queue); +} + +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +static u32 hash_v6(const struct sk_buff *skb) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + __be32 addr[4]; + + addr[0] = ip6h->saddr.s6_addr32[0] ^ ip6h->daddr.s6_addr32[0]; + addr[1] = ip6h->saddr.s6_addr32[1] ^ ip6h->daddr.s6_addr32[1]; + addr[2] = ip6h->saddr.s6_addr32[2] ^ ip6h->daddr.s6_addr32[2]; + addr[3] = ip6h->saddr.s6_addr32[3] ^ ip6h->daddr.s6_addr32[3]; + + return jhash2((__force u32 *)addr, ARRAY_SIZE(addr), jhash_initval); +} + +static unsigned int +nfqueue_tg6_v1(struct sk_buff *skb, const struct xt_target_param *par) +{ + const struct xt_NFQ_info_v1 *info = par->targinfo; + u32 queue = info->queuenum; + + if (info->queues_total > 1) + queue = hash_v6(skb) % info->queues_total + queue; + return NF_QUEUE_NR(queue); +} +#endif + +static bool nfqueue_tg_v1_check(const struct xt_tgchk_param *par) +{ + const struct xt_NFQ_info_v1 *info = par->targinfo; + u32 maxid; + + if (info->queues_total == 0) { + pr_err("NFQUEUE: number of total queues is 0\n"); + return false; + } + maxid = info->queues_total - 1 + info->queuenum; + if (maxid > 0xffff) { + pr_err("NFQUEUE: number of queues (%u) out of range (got %u)\n", + info->queues_total, maxid); + return false; + } + return true; +} + static struct xt_target nfqueue_tg_reg[] __read_mostly = { { .name = "NFQUEUE", - .family = NFPROTO_IPV4, + .family = NFPROTO_UNSPEC, .target = nfqueue_tg, .targetsize = sizeof(struct xt_NFQ_info), .me = THIS_MODULE, }, { .name = "NFQUEUE", - .family = NFPROTO_IPV6, - .target = nfqueue_tg, - .targetsize = sizeof(struct xt_NFQ_info), + .revision = 1, + .family = NFPROTO_IPV4, + .checkentry = nfqueue_tg_v1_check, + .target = nfqueue_tg4_v1, + .targetsize = sizeof(struct xt_NFQ_info_v1), .me = THIS_MODULE, }, +#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) { .name = "NFQUEUE", - .family = NFPROTO_ARP, - .target = nfqueue_tg, - .targetsize = sizeof(struct xt_NFQ_info), + .revision = 1, + .family = NFPROTO_IPV6, + .checkentry = nfqueue_tg_v1_check, + .target = nfqueue_tg6_v1, + .targetsize = sizeof(struct xt_NFQ_info_v1), .me = THIS_MODULE, }, +#endif }; static int __init nfqueue_tg_init(void) { + get_random_bytes(&jhash_initval, sizeof(jhash_initval)); return xt_register_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg)); } diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 43f5676b1af..d80b8192e0d 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -74,7 +74,7 @@ static unsigned int xt_rateest_tg(struct sk_buff *skb, const struct xt_target_param *par) { const struct xt_rateest_target_info *info = par->targinfo; - struct gnet_stats_basic *stats = &info->est->bstats; + struct gnet_stats_basic_packed *stats = &info->est->bstats; spin_lock_bh(&info->est->lock); stats->bytes += skb->len; diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 4f3b1f80879..eda64c1cb1e 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -73,11 +73,11 @@ tcpmss_mangle_packet(struct sk_buff *skb, } if (info->mss == XT_TCPMSS_CLAMP_PMTU) { - if (dst_mtu(skb->dst) <= minlen) { + if (dst_mtu(skb_dst(skb)) <= minlen) { if (net_ratelimit()) printk(KERN_ERR "xt_TCPMSS: " "unknown or invalid path-MTU (%u)\n", - dst_mtu(skb->dst)); + dst_mtu(skb_dst(skb))); return -1; } if (in_mtu <= minlen) { @@ -86,7 +86,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, "invalid path-MTU (%u)\n", in_mtu); return -1; } - newmss = min(dst_mtu(skb->dst), in_mtu) - minlen; + newmss = min(dst_mtu(skb_dst(skb)), in_mtu) - minlen; } else newmss = info->mss; diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index 69a639f3540..225ee3ecd69 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -15,14 +15,14 @@ #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/xt_cluster.h> -static inline u_int32_t nf_ct_orig_ipv4_src(const struct nf_conn *ct) +static inline u32 nf_ct_orig_ipv4_src(const struct nf_conn *ct) { - return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; + return (__force u32)ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; } -static inline const void *nf_ct_orig_ipv6_src(const struct nf_conn *ct) +static inline const u32 *nf_ct_orig_ipv6_src(const struct nf_conn *ct) { - return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip6; + return (__force u32 *)ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip6; } static inline u_int32_t diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 0b7139f3dd7..fc581800698 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -129,7 +129,7 @@ conntrack_addrcmp(const union nf_inet_addr *kaddr, static inline bool conntrack_mt_origsrc(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3, @@ -138,7 +138,7 @@ conntrack_mt_origsrc(const struct nf_conn *ct, static inline bool conntrack_mt_origdst(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3, @@ -147,7 +147,7 @@ conntrack_mt_origdst(const struct nf_conn *ct, static inline bool conntrack_mt_replsrc(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3, @@ -156,7 +156,7 @@ conntrack_mt_replsrc(const struct nf_conn *ct, static inline bool conntrack_mt_repldst(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3, @@ -164,7 +164,7 @@ conntrack_mt_repldst(const struct nf_conn *ct, } static inline bool -ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info, +ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info, const struct nf_conn *ct) { const struct nf_conntrack_tuple *tuple; @@ -204,7 +204,7 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info, static bool conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) { - const struct xt_conntrack_mtinfo1 *info = par->matchinfo; + const struct xt_conntrack_mtinfo2 *info = par->matchinfo; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; unsigned int statebit; @@ -278,6 +278,16 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } +static bool +conntrack_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) +{ + const struct xt_conntrack_mtinfo2 *const *info = par->matchinfo; + struct xt_match_param newpar = *par; + + newpar.matchinfo = *info; + return conntrack_mt(skb, &newpar); +} + static bool conntrack_mt_check(const struct xt_mtchk_param *par) { if (nf_ct_l3proto_try_module_get(par->family) < 0) { @@ -288,11 +298,45 @@ static bool conntrack_mt_check(const struct xt_mtchk_param *par) return true; } +static bool conntrack_mt_check_v1(const struct xt_mtchk_param *par) +{ + struct xt_conntrack_mtinfo1 *info = par->matchinfo; + struct xt_conntrack_mtinfo2 *up; + int ret = conntrack_mt_check(par); + + if (ret < 0) + return ret; + + up = kmalloc(sizeof(*up), GFP_KERNEL); + if (up == NULL) { + nf_ct_l3proto_module_put(par->family); + return -ENOMEM; + } + + /* + * The strategy here is to minimize the overhead of v1 matching, + * by prebuilding a v2 struct and putting the pointer into the + * v1 dataspace. + */ + memcpy(up, info, offsetof(typeof(*info), state_mask)); + up->state_mask = info->state_mask; + up->status_mask = info->status_mask; + *(void **)info = up; + return true; +} + static void conntrack_mt_destroy(const struct xt_mtdtor_param *par) { nf_ct_l3proto_module_put(par->family); } +static void conntrack_mt_destroy_v1(const struct xt_mtdtor_param *par) +{ + struct xt_conntrack_mtinfo2 **info = par->matchinfo; + kfree(*info); + conntrack_mt_destroy(par); +} + #ifdef CONFIG_COMPAT struct compat_xt_conntrack_info { @@ -363,6 +407,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = { .revision = 1, .family = NFPROTO_UNSPEC, .matchsize = sizeof(struct xt_conntrack_mtinfo1), + .match = conntrack_mt_v1, + .checkentry = conntrack_mt_check_v1, + .destroy = conntrack_mt_destroy_v1, + .me = THIS_MODULE, + }, + { + .name = "conntrack", + .revision = 2, + .family = NFPROTO_UNSPEC, + .matchsize = sizeof(struct xt_conntrack_mtinfo2), .match = conntrack_mt, .checkentry = conntrack_mt_check, .destroy = conntrack_mt_destroy, diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c new file mode 100644 index 00000000000..0f482e2440b --- /dev/null +++ b/net/netfilter/xt_osf.c @@ -0,0 +1,429 @@ +/* + * Copyright (c) 2003+ Evgeniy Polyakov <zbr@ioremap.net> + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/module.h> +#include <linux/kernel.h> + +#include <linux/if.h> +#include <linux/inetdevice.h> +#include <linux/ip.h> +#include <linux/list.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/tcp.h> + +#include <net/ip.h> +#include <net/tcp.h> + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_log.h> +#include <linux/netfilter/xt_osf.h> + +struct xt_osf_finger { + struct rcu_head rcu_head; + struct list_head finger_entry; + struct xt_osf_user_finger finger; +}; + +enum osf_fmatch_states { + /* Packet does not match the fingerprint */ + FMATCH_WRONG = 0, + /* Packet matches the fingerprint */ + FMATCH_OK, + /* Options do not match the fingerprint, but header does */ + FMATCH_OPT_WRONG, +}; + +/* + * Indexed by dont-fragment bit. + * It is the only constant value in the fingerprint. + */ +static struct list_head xt_osf_fingers[2]; + +static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = { + [OSF_ATTR_FINGER] = { .len = sizeof(struct xt_osf_user_finger) }, +}; + +static void xt_osf_finger_free_rcu(struct rcu_head *rcu_head) +{ + struct xt_osf_finger *f = container_of(rcu_head, struct xt_osf_finger, rcu_head); + + kfree(f); +} + +static int xt_osf_add_callback(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nlattr *osf_attrs[]) +{ + struct xt_osf_user_finger *f; + struct xt_osf_finger *kf = NULL, *sf; + int err = 0; + + if (!osf_attrs[OSF_ATTR_FINGER]) + return -EINVAL; + + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + return -EINVAL; + + f = nla_data(osf_attrs[OSF_ATTR_FINGER]); + + kf = kmalloc(sizeof(struct xt_osf_finger), GFP_KERNEL); + if (!kf) + return -ENOMEM; + + memcpy(&kf->finger, f, sizeof(struct xt_osf_user_finger)); + + list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) { + if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger))) + continue; + + kfree(kf); + kf = NULL; + + if (nlh->nlmsg_flags & NLM_F_EXCL) + err = -EEXIST; + break; + } + + /* + * We are protected by nfnl mutex. + */ + if (kf) + list_add_tail_rcu(&kf->finger_entry, &xt_osf_fingers[!!f->df]); + + return err; +} + +static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nlattr *osf_attrs[]) +{ + struct xt_osf_user_finger *f; + struct xt_osf_finger *sf; + int err = ENOENT; + + if (!osf_attrs[OSF_ATTR_FINGER]) + return -EINVAL; + + f = nla_data(osf_attrs[OSF_ATTR_FINGER]); + + list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) { + if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger))) + continue; + + /* + * We are protected by nfnl mutex. + */ + list_del_rcu(&sf->finger_entry); + call_rcu(&sf->rcu_head, xt_osf_finger_free_rcu); + + err = 0; + break; + } + + return err; +} + +static const struct nfnl_callback xt_osf_nfnetlink_callbacks[OSF_MSG_MAX] = { + [OSF_MSG_ADD] = { + .call = xt_osf_add_callback, + .attr_count = OSF_ATTR_MAX, + .policy = xt_osf_policy, + }, + [OSF_MSG_REMOVE] = { + .call = xt_osf_remove_callback, + .attr_count = OSF_ATTR_MAX, + .policy = xt_osf_policy, + }, +}; + +static const struct nfnetlink_subsystem xt_osf_nfnetlink = { + .name = "osf", + .subsys_id = NFNL_SUBSYS_OSF, + .cb_count = OSF_MSG_MAX, + .cb = xt_osf_nfnetlink_callbacks, +}; + +static inline int xt_osf_ttl(const struct sk_buff *skb, const struct xt_osf_info *info, + unsigned char f_ttl) +{ + const struct iphdr *ip = ip_hdr(skb); + + if (info->flags & XT_OSF_TTL) { + if (info->ttl == XT_OSF_TTL_TRUE) + return ip->ttl == f_ttl; + if (info->ttl == XT_OSF_TTL_NOCHECK) + return 1; + else if (ip->ttl <= f_ttl) + return 1; + else { + struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + int ret = 0; + + for_ifa(in_dev) { + if (inet_ifa_match(ip->saddr, ifa)) { + ret = (ip->ttl == f_ttl); + break; + } + } + endfor_ifa(in_dev); + + return ret; + } + } + + return ip->ttl == f_ttl; +} + +static bool xt_osf_match_packet(const struct sk_buff *skb, + const struct xt_match_param *p) +{ + const struct xt_osf_info *info = p->matchinfo; + const struct iphdr *ip = ip_hdr(skb); + const struct tcphdr *tcp; + struct tcphdr _tcph; + int fmatch = FMATCH_WRONG, fcount = 0; + unsigned int optsize = 0, check_WSS = 0; + u16 window, totlen, mss = 0; + bool df; + const unsigned char *optp = NULL, *_optp = NULL; + unsigned char opts[MAX_IPOPTLEN]; + const struct xt_osf_finger *kf; + const struct xt_osf_user_finger *f; + + if (!info) + return false; + + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); + if (!tcp) + return false; + + if (!tcp->syn) + return false; + + totlen = ntohs(ip->tot_len); + df = ntohs(ip->frag_off) & IP_DF; + window = ntohs(tcp->window); + + if (tcp->doff * 4 > sizeof(struct tcphdr)) { + optsize = tcp->doff * 4 - sizeof(struct tcphdr); + + _optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) + + sizeof(struct tcphdr), optsize, opts); + } + + rcu_read_lock(); + list_for_each_entry_rcu(kf, &xt_osf_fingers[df], finger_entry) { + f = &kf->finger; + + if (!(info->flags & XT_OSF_LOG) && strcmp(info->genre, f->genre)) + continue; + + optp = _optp; + fmatch = FMATCH_WRONG; + + if (totlen == f->ss && xt_osf_ttl(skb, info, f->ttl)) { + int foptsize, optnum; + + /* + * Should not happen if userspace parser was written correctly. + */ + if (f->wss.wc >= OSF_WSS_MAX) + continue; + + /* Check options */ + + foptsize = 0; + for (optnum = 0; optnum < f->opt_num; ++optnum) + foptsize += f->opt[optnum].length; + + if (foptsize > MAX_IPOPTLEN || + optsize > MAX_IPOPTLEN || + optsize != foptsize) + continue; + + check_WSS = f->wss.wc; + + for (optnum = 0; optnum < f->opt_num; ++optnum) { + if (f->opt[optnum].kind == (*optp)) { + __u32 len = f->opt[optnum].length; + const __u8 *optend = optp + len; + int loop_cont = 0; + + fmatch = FMATCH_OK; + + switch (*optp) { + case OSFOPT_MSS: + mss = optp[3]; + mss <<= 8; + mss |= optp[2]; + + mss = ntohs(mss); + break; + case OSFOPT_TS: + loop_cont = 1; + break; + } + + optp = optend; + } else + fmatch = FMATCH_OPT_WRONG; + + if (fmatch != FMATCH_OK) + break; + } + + if (fmatch != FMATCH_OPT_WRONG) { + fmatch = FMATCH_WRONG; + + switch (check_WSS) { + case OSF_WSS_PLAIN: + if (f->wss.val == 0 || window == f->wss.val) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MSS: + /* + * Some smart modems decrease mangle MSS to + * SMART_MSS_2, so we check standard, decreased + * and the one provided in the fingerprint MSS + * values. + */ +#define SMART_MSS_1 1460 +#define SMART_MSS_2 1448 + if (window == f->wss.val * mss || + window == f->wss.val * SMART_MSS_1 || + window == f->wss.val * SMART_MSS_2) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MTU: + if (window == f->wss.val * (mss + 40) || + window == f->wss.val * (SMART_MSS_1 + 40) || + window == f->wss.val * (SMART_MSS_2 + 40)) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MODULO: + if ((window % f->wss.val) == 0) + fmatch = FMATCH_OK; + break; + } + } + + if (fmatch != FMATCH_OK) + continue; + + fcount++; + + if (info->flags & XT_OSF_LOG) + nf_log_packet(p->family, p->hooknum, skb, + p->in, p->out, NULL, + "%s [%s:%s] : %pi4:%d -> %pi4:%d hops=%d\n", + f->genre, f->version, f->subtype, + &ip->saddr, ntohs(tcp->source), + &ip->daddr, ntohs(tcp->dest), + f->ttl - ip->ttl); + + if ((info->flags & XT_OSF_LOG) && + info->loglevel == XT_OSF_LOGLEVEL_FIRST) + break; + } + } + rcu_read_unlock(); + + if (!fcount && (info->flags & XT_OSF_LOG)) + nf_log_packet(p->family, p->hooknum, skb, p->in, p->out, NULL, + "Remote OS is not known: %pi4:%u -> %pi4:%u\n", + &ip->saddr, ntohs(tcp->source), + &ip->daddr, ntohs(tcp->dest)); + + if (fcount) + fmatch = FMATCH_OK; + + return fmatch == FMATCH_OK; +} + +static struct xt_match xt_osf_match = { + .name = "osf", + .revision = 0, + .family = NFPROTO_IPV4, + .proto = IPPROTO_TCP, + .hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_FORWARD), + .match = xt_osf_match_packet, + .matchsize = sizeof(struct xt_osf_info), + .me = THIS_MODULE, +}; + +static int __init xt_osf_init(void) +{ + int err = -EINVAL; + int i; + + for (i=0; i<ARRAY_SIZE(xt_osf_fingers); ++i) + INIT_LIST_HEAD(&xt_osf_fingers[i]); + + err = nfnetlink_subsys_register(&xt_osf_nfnetlink); + if (err < 0) { + printk(KERN_ERR "Failed (%d) to register OSF nsfnetlink helper.\n", err); + goto err_out_exit; + } + + err = xt_register_match(&xt_osf_match); + if (err) { + printk(KERN_ERR "Failed (%d) to register OS fingerprint " + "matching module.\n", err); + goto err_out_remove; + } + + return 0; + +err_out_remove: + nfnetlink_subsys_unregister(&xt_osf_nfnetlink); +err_out_exit: + return err; +} + +static void __exit xt_osf_fini(void) +{ + struct xt_osf_finger *f; + int i; + + nfnetlink_subsys_unregister(&xt_osf_nfnetlink); + xt_unregister_match(&xt_osf_match); + + rcu_read_lock(); + for (i=0; i<ARRAY_SIZE(xt_osf_fingers); ++i) { + + list_for_each_entry_rcu(f, &xt_osf_fingers[i], finger_entry) { + list_del_rcu(&f->finger_entry); + call_rcu(&f->rcu_head, xt_osf_finger_free_rcu); + } + } + rcu_read_unlock(); + + rcu_barrier(); +} + +module_init(xt_osf_init); +module_exit(xt_osf_fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>"); +MODULE_DESCRIPTION("Passive OS fingerprint matching."); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c index 328bd20ddd2..4cbfebda8fa 100644 --- a/net/netfilter/xt_policy.c +++ b/net/netfilter/xt_policy.c @@ -86,7 +86,7 @@ match_policy_out(const struct sk_buff *skb, const struct xt_policy_info *info, unsigned short family) { const struct xt_policy_elem *e; - const struct dst_entry *dst = skb->dst; + const struct dst_entry *dst = skb_dst(skb); int strict = info->flags & XT_POLICY_MATCH_STRICT; int i, pos; diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c index 01dd07b764e..390b7d09fe5 100644 --- a/net/netfilter/xt_quota.c +++ b/net/netfilter/xt_quota.c @@ -52,8 +52,9 @@ static bool quota_mt_check(const struct xt_mtchk_param *par) q->master = kmalloc(sizeof(*q->master), GFP_KERNEL); if (q->master == NULL) - return -ENOMEM; + return false; + q->master->quota = q->quota; return true; } diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c index 220a1d588ee..4fc6a917f6d 100644 --- a/net/netfilter/xt_rateest.c +++ b/net/netfilter/xt_rateest.c @@ -66,7 +66,7 @@ xt_rateest_mt(const struct sk_buff *skb, const struct xt_match_param *par) if (info->flags & XT_RATEEST_MATCH_BPS) ret &= bps1 == bps2; if (info->flags & XT_RATEEST_MATCH_PPS) - ret &= pps2 == pps2; + ret &= pps1 == pps2; break; } diff --git a/net/netfilter/xt_realm.c b/net/netfilter/xt_realm.c index 67419287bc7..484d1689bfd 100644 --- a/net/netfilter/xt_realm.c +++ b/net/netfilter/xt_realm.c @@ -25,7 +25,7 @@ static bool realm_mt(const struct sk_buff *skb, const struct xt_match_param *par) { const struct xt_realm_info *info = par->matchinfo; - const struct dst_entry *dst = skb->dst; + const struct dst_entry *dst = skb_dst(skb); return (info->id == (dst->tclassid & info->mask)) ^ info->invert; } diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 1acc089be7e..ebf00ad5b19 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -22,6 +22,8 @@ #include <net/netfilter/nf_tproxy_core.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> +#include <linux/netfilter/xt_socket.h> + #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #define XT_SOCKET_HAVE_CONNTRACK 1 #include <net/netfilter/nf_conntrack.h> @@ -86,7 +88,8 @@ extract_icmp_fields(const struct sk_buff *skb, static bool -socket_mt(const struct sk_buff *skb, const struct xt_match_param *par) +socket_match(const struct sk_buff *skb, const struct xt_match_param *par, + const struct xt_socket_mtinfo1 *info) { const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp = NULL; @@ -141,10 +144,24 @@ socket_mt(const struct sk_buff *skb, const struct xt_match_param *par) sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, sport, dport, par->in, false); if (sk != NULL) { - bool wildcard = (sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->rcv_saddr == 0); + bool wildcard; + bool transparent = true; + + /* Ignore sockets listening on INADDR_ANY */ + wildcard = (sk->sk_state != TCP_TIME_WAIT && + inet_sk(sk)->rcv_saddr == 0); + + /* Ignore non-transparent sockets, + if XT_SOCKET_TRANSPARENT is used */ + if (info && info->flags & XT_SOCKET_TRANSPARENT) + transparent = ((sk->sk_state != TCP_TIME_WAIT && + inet_sk(sk)->transparent) || + (sk->sk_state == TCP_TIME_WAIT && + inet_twsk(sk)->tw_transparent)); nf_tproxy_put_sock(sk); - if (wildcard) + + if (wildcard || !transparent) sk = NULL; } @@ -157,23 +174,47 @@ socket_mt(const struct sk_buff *skb, const struct xt_match_param *par) return (sk != NULL); } -static struct xt_match socket_mt_reg __read_mostly = { - .name = "socket", - .family = AF_INET, - .match = socket_mt, - .hooks = 1 << NF_INET_PRE_ROUTING, - .me = THIS_MODULE, +static bool +socket_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) +{ + return socket_match(skb, par, NULL); +} + +static bool +socket_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) +{ + return socket_match(skb, par, par->matchinfo); +} + +static struct xt_match socket_mt_reg[] __read_mostly = { + { + .name = "socket", + .revision = 0, + .family = NFPROTO_IPV4, + .match = socket_mt_v0, + .hooks = 1 << NF_INET_PRE_ROUTING, + .me = THIS_MODULE, + }, + { + .name = "socket", + .revision = 1, + .family = NFPROTO_IPV4, + .match = socket_mt_v1, + .matchsize = sizeof(struct xt_socket_mtinfo1), + .hooks = 1 << NF_INET_PRE_ROUTING, + .me = THIS_MODULE, + }, }; static int __init socket_mt_init(void) { nf_defrag_ipv4_enable(); - return xt_register_match(&socket_mt_reg); + return xt_register_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } static void __exit socket_mt_exit(void) { - xt_unregister_match(&socket_mt_reg); + xt_unregister_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg)); } module_init(socket_mt_init); diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index bf1ab1a6790..e639298bc9c 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -785,18 +785,6 @@ static struct genl_ops netlbl_cipsov4_ops[] = { */ int __init netlbl_cipsov4_genl_init(void) { - int ret_val, i; - - ret_val = genl_register_family(&netlbl_cipsov4_gnl_family); - if (ret_val != 0) - return ret_val; - - for (i = 0; i < ARRAY_SIZE(netlbl_cipsov4_ops); i++) { - ret_val = genl_register_ops(&netlbl_cipsov4_gnl_family, - &netlbl_cipsov4_ops[i]); - if (ret_val != 0) - return ret_val; - } - - return 0; + return genl_register_family_with_ops(&netlbl_cipsov4_gnl_family, + netlbl_cipsov4_ops, ARRAY_SIZE(netlbl_cipsov4_ops)); } diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index b0e582f2d37..16e6c4378ff 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -151,7 +151,7 @@ int netlbl_cfg_unlbl_map_add(const char *domain, addr6 = addr; mask6 = mask; map6 = kzalloc(sizeof(*map6), GFP_ATOMIC); - if (map4 == NULL) + if (map6 == NULL) goto cfg_unlbl_map_add_failure; map6->type = NETLBL_NLTYPE_UNLABELED; ipv6_addr_copy(&map6->list.addr, addr6); diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 1821c5d50fb..8203623e65a 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -779,18 +779,6 @@ static struct genl_ops netlbl_mgmt_genl_ops[] = { */ int __init netlbl_mgmt_genl_init(void) { - int ret_val, i; - - ret_val = genl_register_family(&netlbl_mgmt_gnl_family); - if (ret_val != 0) - return ret_val; - - for (i = 0; i < ARRAY_SIZE(netlbl_mgmt_genl_ops); i++) { - ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, - &netlbl_mgmt_genl_ops[i]); - if (ret_val != 0) - return ret_val; - } - - return 0; + return genl_register_family_with_ops(&netlbl_mgmt_gnl_family, + netlbl_mgmt_genl_ops, ARRAY_SIZE(netlbl_mgmt_genl_ops)); } diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index f3c5c68c684..fb357f01018 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1478,20 +1478,8 @@ static struct genl_ops netlbl_unlabel_genl_ops[] = { */ int __init netlbl_unlabel_genl_init(void) { - int ret_val, i; - - ret_val = genl_register_family(&netlbl_unlabel_gnl_family); - if (ret_val != 0) - return ret_val; - - for (i = 0; i < ARRAY_SIZE(netlbl_unlabel_genl_ops); i++) { - ret_val = genl_register_ops(&netlbl_unlabel_gnl_family, - &netlbl_unlabel_genl_ops[i]); - if (ret_val != 0) - return ret_val; - } - - return 0; + return genl_register_family_with_ops(&netlbl_unlabel_gnl_family, + netlbl_unlabel_genl_ops, ARRAY_SIZE(netlbl_unlabel_genl_ops)); } /* diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8b6bbb3032b..2936fa3b6dc 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1914,8 +1914,8 @@ static int netlink_seq_show(struct seq_file *seq, void *v) s->sk_protocol, nlk->pid, nlk->groups ? (u32)nlk->groups[0] : 0, - atomic_read(&s->sk_rmem_alloc), - atomic_read(&s->sk_wmem_alloc), + sk_rmem_alloc_get(s), + sk_wmem_alloc_get(s), nlk->cb, atomic_read(&s->sk_refcnt), atomic_read(&s->sk_drops) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1d3dd30099d..eed4c6a8afc 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -384,6 +384,52 @@ errout: } /** + * genl_register_family_with_ops - register a generic netlink family + * @family: generic netlink family + * @ops: operations to be registered + * @n_ops: number of elements to register + * + * Registers the specified family and operations from the specified table. + * Only one family may be registered with the same family name or identifier. + * + * The family id may equal GENL_ID_GENERATE causing an unique id to + * be automatically generated and assigned. + * + * Either a doit or dumpit callback must be specified for every registered + * operation or the function will fail. Only one operation structure per + * command identifier may be registered. + * + * See include/net/genetlink.h for more documenation on the operations + * structure. + * + * This is equivalent to calling genl_register_family() followed by + * genl_register_ops() for every operation entry in the table taking + * care to unregister the family on error path. + * + * Return 0 on success or a negative error code. + */ +int genl_register_family_with_ops(struct genl_family *family, + struct genl_ops *ops, size_t n_ops) +{ + int err, i; + + err = genl_register_family(family); + if (err) + return err; + + for (i = 0; i < n_ops; ++i, ++ops) { + err = genl_register_ops(family, ops); + if (err) + goto err_out; + } + return 0; +err_out: + genl_unregister_family(family); + return err; +} +EXPORT_SYMBOL(genl_register_family_with_ops); + +/** * genl_unregister_family - unregister generic netlink family * @family: generic netlink family * diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 3be0e016ab7..ce1a34b99c2 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -286,8 +286,7 @@ void nr_destroy_socket(struct sock *sk) kfree_skb(skb); } - if (atomic_read(&sk->sk_wmem_alloc) || - atomic_read(&sk->sk_rmem_alloc)) { + if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ sk->sk_timer.function = nr_destroy_timer; sk->sk_timer.expires = jiffies + 2 * HZ; @@ -848,6 +847,7 @@ static int nr_getname(struct socket *sock, struct sockaddr *uaddr, sax->fsa_ax25.sax25_family = AF_NETROM; sax->fsa_ax25.sax25_ndigis = 1; sax->fsa_ax25.sax25_call = nr->user_addr; + memset(sax->fsa_digipeater, 0, sizeof(sax->fsa_digipeater)); sax->fsa_digipeater[0] = nr->dest_addr; *uaddr_len = sizeof(struct full_sockaddr_ax25); } else { @@ -1206,7 +1206,7 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) long amount; lock_sock(sk); - amount = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; release_sock(sk); @@ -1342,8 +1342,8 @@ static int nr_info_show(struct seq_file *seq, void *v) nr->n2count, nr->n2, nr->window, - atomic_read(&s->sk_wmem_alloc), - atomic_read(&s->sk_rmem_alloc), + sk_wmem_alloc_get(s), + sk_rmem_alloc_get(s), s->sk_socket ? SOCK_INODE(s->sk_socket)->i_ino : 0L); bh_unlock_sock(s); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index e943c16552a..4eb1ac9a767 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -630,23 +630,23 @@ out: return dev; } -static ax25_digi *nr_call_to_digi(int ndigis, ax25_address *digipeaters) +static ax25_digi *nr_call_to_digi(ax25_digi *digi, int ndigis, + ax25_address *digipeaters) { - static ax25_digi ax25_digi; int i; if (ndigis == 0) return NULL; for (i = 0; i < ndigis; i++) { - ax25_digi.calls[i] = digipeaters[i]; - ax25_digi.repeated[i] = 0; + digi->calls[i] = digipeaters[i]; + digi->repeated[i] = 0; } - ax25_digi.ndigi = ndigis; - ax25_digi.lastrepeat = -1; + digi->ndigi = ndigis; + digi->lastrepeat = -1; - return &ax25_digi; + return digi; } /* @@ -656,6 +656,7 @@ int nr_rt_ioctl(unsigned int cmd, void __user *arg) { struct nr_route_struct nr_route; struct net_device *dev; + ax25_digi digi; int ret; switch (cmd) { @@ -673,13 +674,15 @@ int nr_rt_ioctl(unsigned int cmd, void __user *arg) ret = nr_add_node(&nr_route.callsign, nr_route.mnemonic, &nr_route.neighbour, - nr_call_to_digi(nr_route.ndigis, nr_route.digipeaters), + nr_call_to_digi(&digi, nr_route.ndigis, + nr_route.digipeaters), dev, nr_route.quality, nr_route.obs_count); break; case NETROM_NEIGH: ret = nr_add_neigh(&nr_route.callsign, - nr_call_to_digi(nr_route.ndigis, nr_route.digipeaters), + nr_call_to_digi(&digi, nr_route.ndigis, + nr_route.digipeaters), dev, nr_route.quality); break; default: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f546e81acc4..ebe5718baa3 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -39,6 +39,7 @@ * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. + * Johann Baudy : Added TX RING. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -157,7 +158,25 @@ struct packet_mreq_max }; #ifdef CONFIG_PACKET_MMAP -static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing); +static int packet_set_ring(struct sock *sk, struct tpacket_req *req, + int closing, int tx_ring); + +struct packet_ring_buffer { + char * *pg_vec; + unsigned int head; + unsigned int frames_per_block; + unsigned int frame_size; + unsigned int frame_max; + + unsigned int pg_vec_order; + unsigned int pg_vec_pages; + unsigned int pg_vec_len; + + atomic_t pending; +}; + +struct packet_sock; +static int tpacket_snd(struct packet_sock *po, struct msghdr *msg); #endif static void packet_flush_mclist(struct sock *sk); @@ -167,11 +186,8 @@ struct packet_sock { struct sock sk; struct tpacket_stats stats; #ifdef CONFIG_PACKET_MMAP - char * *pg_vec; - unsigned int head; - unsigned int frames_per_block; - unsigned int frame_size; - unsigned int frame_max; + struct packet_ring_buffer rx_ring; + struct packet_ring_buffer tx_ring; int copy_thresh; #endif struct packet_type prot_hook; @@ -185,12 +201,10 @@ struct packet_sock { struct packet_mclist *mclist; #ifdef CONFIG_PACKET_MMAP atomic_t mapped; - unsigned int pg_vec_order; - unsigned int pg_vec_pages; - unsigned int pg_vec_len; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; + unsigned int tp_loss:1; #endif }; @@ -206,36 +220,33 @@ struct packet_skb_cb { #ifdef CONFIG_PACKET_MMAP -static void *packet_lookup_frame(struct packet_sock *po, unsigned int position, - int status) +static void __packet_set_status(struct packet_sock *po, void *frame, int status) { - unsigned int pg_vec_pos, frame_offset; union { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; void *raw; } h; - pg_vec_pos = position / po->frames_per_block; - frame_offset = position % po->frames_per_block; - - h.raw = po->pg_vec[pg_vec_pos] + (frame_offset * po->frame_size); + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - if (status != (h.h1->tp_status ? TP_STATUS_USER : - TP_STATUS_KERNEL)) - return NULL; + h.h1->tp_status = status; + flush_dcache_page(virt_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - if (status != (h.h2->tp_status ? TP_STATUS_USER : - TP_STATUS_KERNEL)) - return NULL; + h.h2->tp_status = status; + flush_dcache_page(virt_to_page(&h.h2->tp_status)); break; + default: + printk(KERN_ERR "TPACKET version not supported\n"); + BUG(); } - return h.raw; + + smp_wmb(); } -static void __packet_set_status(struct packet_sock *po, void *frame, int status) +static int __packet_get_status(struct packet_sock *po, void *frame) { union { struct tpacket_hdr *h1; @@ -243,16 +254,66 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) void *raw; } h; + smp_rmb(); + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; - break; + flush_dcache_page(virt_to_page(&h.h1->tp_status)); + return h.h1->tp_status; case TPACKET_V2: - h.h2->tp_status = status; - break; + flush_dcache_page(virt_to_page(&h.h2->tp_status)); + return h.h2->tp_status; + default: + printk(KERN_ERR "TPACKET version not supported\n"); + BUG(); + return 0; } } + +static void *packet_lookup_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + unsigned int position, + int status) +{ + unsigned int pg_vec_pos, frame_offset; + union { + struct tpacket_hdr *h1; + struct tpacket2_hdr *h2; + void *raw; + } h; + + pg_vec_pos = position / rb->frames_per_block; + frame_offset = position % rb->frames_per_block; + + h.raw = rb->pg_vec[pg_vec_pos] + (frame_offset * rb->frame_size); + + if (status != __packet_get_status(po, h.raw)) + return NULL; + + return h.raw; +} + +static inline void *packet_current_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status) +{ + return packet_lookup_frame(po, rb, rb->head, status); +} + +static inline void *packet_previous_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status) +{ + unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; + return packet_lookup_frame(po, rb, previous, status); +} + +static inline void packet_increment_head(struct packet_ring_buffer *buff) +{ + buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; +} + #endif static inline struct packet_sock *pkt_sk(struct sock *sk) @@ -311,8 +372,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct goto oom; /* drop any routing info */ - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); /* drop conntrack reference */ nf_reset(skb); @@ -560,8 +620,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet skb_set_owner_r(skb, sk); skb->dev = NULL; - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); /* drop conntrack reference */ nf_reset(skb); @@ -648,7 +707,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe macoff = netoff - maclen; } - if (macoff + snaplen > po->frame_size) { + if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && atomic_read(&sk->sk_rmem_alloc) + skb->truesize < (unsigned)sk->sk_rcvbuf) { @@ -661,16 +720,16 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe if (copy_skb) skb_set_owner_r(copy_skb, sk); } - snaplen = po->frame_size - macoff; + snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) snaplen = 0; } spin_lock(&sk->sk_receive_queue.lock); - h.raw = packet_lookup_frame(po, po->head, TP_STATUS_KERNEL); + h.raw = packet_current_frame(po, &po->rx_ring, TP_STATUS_KERNEL); if (!h.raw) goto ring_is_full; - po->head = po->head != po->frame_max ? po->head+1 : 0; + packet_increment_head(&po->rx_ring); po->stats.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; @@ -727,7 +786,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe __packet_set_status(po, h.raw, status); smp_mb(); - { struct page *p_start, *p_end; u8 *h_end = h.raw + macoff + snaplen - 1; @@ -760,10 +818,249 @@ ring_is_full: goto drop_n_restore; } -#endif +static void tpacket_destruct_skb(struct sk_buff *skb) +{ + struct packet_sock *po = pkt_sk(skb->sk); + void * ph; + BUG_ON(skb == NULL); -static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, + if (likely(po->tx_ring.pg_vec)) { + ph = skb_shinfo(skb)->destructor_arg; + BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING); + BUG_ON(atomic_read(&po->tx_ring.pending) == 0); + atomic_dec(&po->tx_ring.pending); + __packet_set_status(po, ph, TP_STATUS_AVAILABLE); + } + + 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) +{ + union { + struct tpacket_hdr *h1; + struct tpacket2_hdr *h2; + void *raw; + } ph; + int to_write, offset, len, tp_len, nr_frags, len_max; + struct socket *sock = po->sk.sk_socket; + struct page *page; + void *data; + int err; + + ph.raw = frame; + + skb->protocol = proto; + skb->dev = dev; + skb->priority = po->sk.sk_priority; + skb_shinfo(skb)->destructor_arg = ph.raw; + + switch (po->tp_version) { + case TPACKET_V2: + tp_len = ph.h2->tp_len; + break; + default: + tp_len = ph.h1->tp_len; + break; + } + if (unlikely(tp_len > size_max)) { + printk(KERN_ERR "packet size is too long (%d > %d)\n", + tp_len, size_max); + return -EMSGSIZE; + } + + skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reset_network_header(skb); + + data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll); + to_write = tp_len; + + if (sock->type == SOCK_DGRAM) { + err = dev_hard_header(skb, dev, ntohs(proto), addr, + NULL, tp_len); + if (unlikely(err < 0)) + return -EINVAL; + } 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); + return -EINVAL; + } + + skb_push(skb, dev->hard_header_len); + err = skb_store_bits(skb, 0, data, + dev->hard_header_len); + if (unlikely(err)) + return err; + + data += dev->hard_header_len; + to_write -= dev->hard_header_len; + } + + err = -EFAULT; + page = virt_to_page(data); + offset = offset_in_page(data); + len_max = PAGE_SIZE - offset; + len = ((to_write > len_max) ? len_max : to_write); + + skb->data_len = to_write; + skb->len += to_write; + skb->truesize += to_write; + atomic_add(to_write, &po->sk.sk_wmem_alloc); + + while (likely(to_write)) { + 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); + return -EFAULT; + } + + flush_dcache_page(page); + get_page(page); + skb_fill_page_desc(skb, + nr_frags, + page++, offset, len); + to_write -= len; + offset = 0; + len_max = PAGE_SIZE; + len = ((to_write > len_max) ? len_max : to_write); + } + + return tp_len; +} + +static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) +{ + struct socket *sock; + struct sk_buff *skb; + struct net_device *dev; + __be16 proto; + int ifindex, err, reserve = 0; + void * ph; + struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name; + int tp_len, size_max; + unsigned char *addr; + int len_sum = 0; + int status = 0; + + sock = po->sk.sk_socket; + + mutex_lock(&po->pg_vec_lock); + + err = -EBUSY; + if (saddr == NULL) { + ifindex = po->ifindex; + proto = po->num; + addr = NULL; + } else { + err = -EINVAL; + if (msg->msg_namelen < sizeof(struct sockaddr_ll)) + goto out; + if (msg->msg_namelen < (saddr->sll_halen + + offsetof(struct sockaddr_ll, + sll_addr))) + goto out; + ifindex = saddr->sll_ifindex; + proto = saddr->sll_protocol; + addr = saddr->sll_addr; + } + + dev = dev_get_by_index(sock_net(&po->sk), ifindex); + err = -ENXIO; + if (unlikely(dev == NULL)) + goto out; + + reserve = dev->hard_header_len; + + err = -ENETDOWN; + if (unlikely(!(dev->flags & IFF_UP))) + 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); + + if (size_max > dev->mtu + reserve) + size_max = dev->mtu + reserve; + + do { + ph = packet_current_frame(po, &po->tx_ring, + TP_STATUS_SEND_REQUEST); + + if (unlikely(ph == NULL)) { + schedule(); + continue; + } + + status = TP_STATUS_SEND_REQUEST; + skb = sock_alloc_send_skb(&po->sk, + LL_ALLOCATED_SPACE(dev) + + sizeof(struct sockaddr_ll), + 0, &err); + + if (unlikely(skb == NULL)) + goto out_status; + + tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, + addr); + + if (unlikely(tp_len < 0)) { + if (po->tp_loss) { + __packet_set_status(po, ph, + TP_STATUS_AVAILABLE); + packet_increment_head(&po->tx_ring); + kfree_skb(skb); + continue; + } else { + status = TP_STATUS_WRONG_FORMAT; + err = tp_len; + goto out_status; + } + } + + skb->destructor = tpacket_destruct_skb; + __packet_set_status(po, ph, TP_STATUS_SENDING); + atomic_inc(&po->tx_ring.pending); + + status = TP_STATUS_SEND_REQUEST; + err = dev_queue_xmit(skb); + if (unlikely(err > 0 && (err = net_xmit_errno(err)) != 0)) + goto out_xmit; + packet_increment_head(&po->tx_ring); + len_sum += tp_len; + } + while (likely((ph != NULL) || ((!(msg->msg_flags & MSG_DONTWAIT)) + && (atomic_read(&po->tx_ring.pending)))) + ); + + err = len_sum; + goto out_put; + +out_xmit: + skb->destructor = sock_wfree; + atomic_dec(&po->tx_ring.pending); +out_status: + __packet_set_status(po, ph, status); + kfree_skb(skb); +out_put: + dev_put(dev); +out: + mutex_unlock(&po->pg_vec_lock); + return err; +} +#endif + +static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; @@ -854,6 +1151,19 @@ out: return err; } +static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len) +{ +#ifdef CONFIG_PACKET_MMAP + struct sock *sk = sock->sk; + struct packet_sock *po = pkt_sk(sk); + if (po->tx_ring.pg_vec) + return tpacket_snd(po, msg); + else +#endif + return packet_snd(sock, msg, len); +} + /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. @@ -864,6 +1174,9 @@ static int packet_release(struct socket *sock) struct sock *sk = sock->sk; struct packet_sock *po; struct net *net; +#ifdef CONFIG_PACKET_MMAP + struct tpacket_req req; +#endif if (!sk) return 0; @@ -893,11 +1206,13 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); #ifdef CONFIG_PACKET_MMAP - if (po->pg_vec) { - struct tpacket_req req; - memset(&req, 0, sizeof(req)); - packet_set_ring(sk, &req, 1); - } + memset(&req, 0, sizeof(req)); + + if (po->rx_ring.pg_vec) + packet_set_ring(sk, &req, 1, 0); + + if (po->tx_ring.pg_vec) + packet_set_ring(sk, &req, 1, 1); #endif /* @@ -1253,9 +1568,9 @@ static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, switch (i->type) { case PACKET_MR_MULTICAST: if (what > 0) - dev_mc_add(dev, i->addr, i->alen, 0); + return dev_mc_add(dev, i->addr, i->alen, 0); else - dev_mc_delete(dev, i->addr, i->alen, 0); + return dev_mc_delete(dev, i->addr, i->alen, 0); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); @@ -1263,6 +1578,12 @@ static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); break; + case PACKET_MR_UNICAST: + if (what > 0) + return dev_unicast_add(dev, i->addr); + else + return dev_unicast_delete(dev, i->addr); + break; default:; } return 0; @@ -1391,7 +1712,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (level != SOL_PACKET) return -ENOPROTOOPT; - switch(optname) { + switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { @@ -1415,6 +1736,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv #ifdef CONFIG_PACKET_MMAP case PACKET_RX_RING: + case PACKET_TX_RING: { struct tpacket_req req; @@ -1422,7 +1744,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return -EINVAL; if (copy_from_user(&req,optval,sizeof(req))) return -EFAULT; - return packet_set_ring(sk, &req, 0); + return packet_set_ring(sk, &req, 0, optname == PACKET_TX_RING); } case PACKET_COPY_THRESH: { @@ -1442,7 +1764,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->pg_vec) + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; @@ -1461,13 +1783,26 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->pg_vec) + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; po->tp_reserve = val; return 0; } + case PACKET_LOSS: + { + unsigned int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) + return -EBUSY; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + po->tp_loss = !!val; + return 0; + } #endif case PACKET_AUXDATA: { @@ -1517,7 +1852,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, if (len < 0) return -EINVAL; - switch(optname) { + switch (optname) { case PACKET_STATISTICS: if (len > sizeof(struct tpacket_stats)) len = sizeof(struct tpacket_stats); @@ -1573,6 +1908,12 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, val = po->tp_reserve; data = &val; break; + case PACKET_LOSS: + if (len > sizeof(unsigned int)) + len = sizeof(unsigned int); + val = po->tp_loss; + data = &val; + break; #endif default: return -ENOPROTOOPT; @@ -1643,10 +1984,11 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd, { struct sock *sk = sock->sk; - switch(cmd) { + switch (cmd) { case SIOCOUTQ: { - int amount = atomic_read(&sk->sk_wmem_alloc); + int amount = sk_wmem_alloc_get(sk); + return put_user(amount, (int __user *)arg); } case SIOCINQ: @@ -1705,13 +2047,17 @@ static unsigned int packet_poll(struct file * file, struct socket *sock, unsigned int mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); - if (po->pg_vec) { - unsigned last = po->head ? po->head-1 : po->frame_max; - - if (packet_lookup_frame(po, last, TP_STATUS_USER)) + if (po->rx_ring.pg_vec) { + if (!packet_previous_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= POLLIN | POLLRDNORM; } spin_unlock_bh(&sk->sk_receive_queue.lock); + spin_lock_bh(&sk->sk_write_queue.lock); + if (po->tx_ring.pg_vec) { + if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) + mask |= POLLOUT | POLLWRNORM; + } + spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } @@ -1788,21 +2134,33 @@ out_free_pgvec: goto out; } -static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing) +static int packet_set_ring(struct sock *sk, struct tpacket_req *req, + int closing, int tx_ring) { char **pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); int was_running, order = 0; + struct packet_ring_buffer *rb; + struct sk_buff_head *rb_queue; __be16 num; - int err = 0; + int err; - if (req->tp_block_nr) { - int i; + rb = tx_ring ? &po->tx_ring : &po->rx_ring; + rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; - /* Sanity tests and some calculations */ + err = -EBUSY; + if (!closing) { + if (atomic_read(&po->mapped)) + goto out; + if (atomic_read(&rb->pending)) + goto out; + } - if (unlikely(po->pg_vec)) - return -EBUSY; + if (req->tp_block_nr) { + /* Sanity tests and some calculations */ + err = -EBUSY; + if (unlikely(rb->pg_vec)) + goto out; switch (po->tp_version) { case TPACKET_V1: @@ -1813,42 +2171,35 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing break; } + err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) - return -EINVAL; + goto out; if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) - return -EINVAL; + goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + - po->tp_reserve)) - return -EINVAL; + po->tp_reserve)) + goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) - return -EINVAL; + goto out; - po->frames_per_block = req->tp_block_size/req->tp_frame_size; - if (unlikely(po->frames_per_block <= 0)) - return -EINVAL; - if (unlikely((po->frames_per_block * req->tp_block_nr) != - req->tp_frame_nr)) - return -EINVAL; + rb->frames_per_block = req->tp_block_size/req->tp_frame_size; + if (unlikely(rb->frames_per_block <= 0)) + goto out; + if (unlikely((rb->frames_per_block * req->tp_block_nr) != + req->tp_frame_nr)) + goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; - - for (i = 0; i < req->tp_block_nr; i++) { - void *ptr = pg_vec[i]; - int k; - - for (k = 0; k < po->frames_per_block; k++) { - __packet_set_status(po, ptr, TP_STATUS_KERNEL); - ptr += req->tp_frame_size; - } - } - /* Done */ - } else { + } + /* Done */ + else { + err = -EINVAL; if (unlikely(req->tp_frame_nr)) - return -EINVAL; + goto out; } lock_sock(sk); @@ -1872,23 +2223,24 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing if (closing || atomic_read(&po->mapped) == 0) { err = 0; #define XC(a, b) ({ __typeof__ ((a)) __t; __t = (a); (a) = (b); __t; }) - - spin_lock_bh(&sk->sk_receive_queue.lock); - pg_vec = XC(po->pg_vec, pg_vec); - po->frame_max = (req->tp_frame_nr - 1); - po->head = 0; - po->frame_size = req->tp_frame_size; - spin_unlock_bh(&sk->sk_receive_queue.lock); - - order = XC(po->pg_vec_order, order); - req->tp_block_nr = XC(po->pg_vec_len, req->tp_block_nr); - - po->pg_vec_pages = req->tp_block_size/PAGE_SIZE; - po->prot_hook.func = po->pg_vec ? tpacket_rcv : packet_rcv; - skb_queue_purge(&sk->sk_receive_queue); + spin_lock_bh(&rb_queue->lock); + pg_vec = XC(rb->pg_vec, pg_vec); + rb->frame_max = (req->tp_frame_nr - 1); + rb->head = 0; + rb->frame_size = req->tp_frame_size; + spin_unlock_bh(&rb_queue->lock); + + order = XC(rb->pg_vec_order, order); + req->tp_block_nr = XC(rb->pg_vec_len, req->tp_block_nr); + + rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; + po->prot_hook.func = (po->rx_ring.pg_vec) ? + tpacket_rcv : packet_rcv; + 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)); + printk(KERN_DEBUG "packet_mmap: vma is busy: %d\n", + atomic_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); @@ -1909,11 +2261,13 @@ out: return err; } -static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) +static int packet_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - unsigned long size; + unsigned long size, expected_size; + struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; @@ -1921,26 +2275,43 @@ static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_st if (vma->vm_pgoff) return -EINVAL; - size = vma->vm_end - vma->vm_start; - mutex_lock(&po->pg_vec_lock); - if (po->pg_vec == NULL) + + expected_size = 0; + for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { + if (rb->pg_vec) { + expected_size += rb->pg_vec_len + * rb->pg_vec_pages + * PAGE_SIZE; + } + } + + if (expected_size == 0) goto out; - if (size != po->pg_vec_len*po->pg_vec_pages*PAGE_SIZE) + + size = vma->vm_end - vma->vm_start; + if (size != expected_size) goto out; start = vma->vm_start; - for (i = 0; i < po->pg_vec_len; i++) { - struct page *page = virt_to_page(po->pg_vec[i]); - int pg_num; - - for (pg_num = 0; pg_num < po->pg_vec_pages; pg_num++, page++) { - err = vm_insert_page(vma, start, page); - if (unlikely(err)) - goto out; - start += PAGE_SIZE; + for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { + if (rb->pg_vec == NULL) + continue; + + for (i = 0; i < rb->pg_vec_len; i++) { + struct page *page = virt_to_page(rb->pg_vec[i]); + int pg_num; + + for (pg_num = 0; pg_num < rb->pg_vec_pages; + pg_num++,page++) { + err = vm_insert_page(vma, start, page); + if (unlikely(err)) + goto out; + start += PAGE_SIZE; + } } } + atomic_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index 4aa888584d2..480839dfc56 100644 --- a/net/phonet/pep-gprs.c +++ b/net/phonet/pep-gprs.c @@ -115,10 +115,10 @@ static int gprs_recv(struct gprs_dev *gp, struct sk_buff *skb) rskb->truesize += rskb->len; /* Avoid nested fragments */ - for (fs = skb_shinfo(skb)->frag_list; fs; fs = fs->next) + skb_walk_frags(skb, fs) flen += fs->len; skb->next = skb_shinfo(skb)->frag_list; - skb_shinfo(skb)->frag_list = NULL; + skb_frag_list_init(skb); skb->len -= flen; skb->data_len -= flen; skb->truesize -= flen; @@ -212,8 +212,9 @@ static int gprs_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_bytes += len; } - if (!pep_writeable(sk)) - netif_stop_queue(dev); + netif_stop_queue(dev); + if (pep_writeable(sk)) + netif_wake_queue(dev); return 0; } diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 8ad2b533388..eef833ea6d7 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -940,10 +940,10 @@ int pep_write(struct sock *sk, struct sk_buff *skb) rskb->truesize += rskb->len; /* Avoid nested fragments */ - for (fs = skb_shinfo(skb)->frag_list; fs; fs = fs->next) + skb_walk_frags(skb, fs) flen += fs->len; skb->next = skb_shinfo(skb)->frag_list; - skb_shinfo(skb)->frag_list = NULL; + skb_frag_list_init(skb); skb->len -= flen; skb->data_len -= flen; skb->truesize -= flen; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 80a322d7790..c2b77a69869 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -69,17 +69,34 @@ static struct phonet_device *__phonet_get(struct net_device *dev) return NULL; } -static void __phonet_device_free(struct phonet_device *pnd) +static void phonet_device_destroy(struct net_device *dev) { - list_del(&pnd->list); - kfree(pnd); + struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); + struct phonet_device *pnd; + + ASSERT_RTNL(); + + spin_lock_bh(&pndevs->lock); + pnd = __phonet_get(dev); + if (pnd) + list_del(&pnd->list); + spin_unlock_bh(&pndevs->lock); + + if (pnd) { + u8 addr; + + for (addr = find_first_bit(pnd->addrs, 64); addr < 64; + addr = find_next_bit(pnd->addrs, 64, 1+addr)) + phonet_address_notify(RTM_DELADDR, dev, addr); + kfree(pnd); + } } struct net_device *phonet_device_get(struct net *net) { struct phonet_device_list *pndevs = phonet_device_list(net); struct phonet_device *pnd; - struct net_device *dev; + struct net_device *dev = NULL; spin_lock_bh(&pndevs->lock); list_for_each_entry(pnd, &pndevs->list, list) { @@ -126,8 +143,10 @@ int phonet_address_del(struct net_device *dev, u8 addr) pnd = __phonet_get(dev); if (!pnd || !test_and_clear_bit(addr >> 2, pnd->addrs)) err = -EADDRNOTAVAIL; - else if (bitmap_empty(pnd->addrs, 64)) - __phonet_device_free(pnd); + else if (bitmap_empty(pnd->addrs, 64)) { + list_del(&pnd->list); + kfree(pnd); + } spin_unlock_bh(&pndevs->lock); return err; } @@ -181,18 +200,8 @@ static int phonet_device_notify(struct notifier_block *me, unsigned long what, { struct net_device *dev = arg; - if (what == NETDEV_UNREGISTER) { - struct phonet_device_list *pndevs; - struct phonet_device *pnd; - - /* Destroy phonet-specific device data */ - pndevs = phonet_device_list(dev_net(dev)); - spin_lock_bh(&pndevs->lock); - pnd = __phonet_get(dev); - if (pnd) - __phonet_device_free(pnd); - spin_unlock_bh(&pndevs->lock); - } + if (what == NETDEV_UNREGISTER) + phonet_device_destroy(dev); return 0; } @@ -218,11 +227,12 @@ static int phonet_init_net(struct net *net) static void phonet_exit_net(struct net *net) { struct phonet_net *pnn = net_generic(net, phonet_net_id); - struct phonet_device *pnd, *n; - - list_for_each_entry_safe(pnd, n, &pnn->pndevs.list, list) - __phonet_device_free(pnd); + struct net_device *dev; + rtnl_lock(); + for_each_netdev(net, dev) + phonet_device_destroy(dev); + rtnl_unlock(); kfree(pnn); } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index cec4e595168..f8b4cee434c 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -32,7 +32,7 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, u32 pid, u32 seq, int event); -static void rtmsg_notify(int event, struct net_device *dev, u8 addr) +void phonet_address_notify(int event, struct net_device *dev, u8 addr) { struct sk_buff *skb; int err = -ENOBUFS; @@ -94,7 +94,7 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr) else err = phonet_address_del(dev, pnaddr); if (!err) - rtmsg_notify(nlh->nlmsg_type, dev, pnaddr); + phonet_address_notify(nlh->nlmsg_type, dev, pnaddr); return err; } diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 20cf16fc572..b11e7e52786 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -35,7 +35,6 @@ #include <linux/kernel.h> #include <linux/in.h> #include <linux/poll.h> -#include <linux/version.h> #include <net/sock.h> #include "rds.h" diff --git a/net/rds/connection.c b/net/rds/connection.c index 273f064930a..d14445c4830 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -148,14 +148,12 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, if (conn) goto out; - conn = kmem_cache_alloc(rds_conn_slab, gfp); + conn = kmem_cache_zalloc(rds_conn_slab, gfp); if (conn == NULL) { conn = ERR_PTR(-ENOMEM); goto out; } - memset(conn, 0, sizeof(*conn)); - INIT_HLIST_NODE(&conn->c_hash_node); conn->c_version = RDS_PROTOCOL_3_0; conn->c_laddr = laddr; diff --git a/net/rds/ib.c b/net/rds/ib.c index 4933b380985..b9bcd32431e 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -224,8 +224,8 @@ static int rds_ib_laddr_check(__be32 addr) * IB and iWARP capable NICs. */ cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP); - if (!cm_id) - return -EADDRNOTAVAIL; + if (IS_ERR(cm_id)) + return PTR_ERR(cm_id); memset(&sin, 0, sizeof(sin)); sin.sin_family = AF_INET; diff --git a/net/rds/ib.h b/net/rds/ib.h index 069206cae73..455ae73047f 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -333,7 +333,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rds_rdma_op *op); void rds_ib_send_add_credits(struct rds_connection *conn, unsigned int credits); void rds_ib_advertise_credits(struct rds_connection *conn, unsigned int posted); int rds_ib_send_grab_credits(struct rds_ib_connection *ic, u32 wanted, - u32 *adv_credits, int need_posted); + u32 *adv_credits, int need_posted, int max_posted); /* ib_stats.c */ DECLARE_PER_CPU(struct rds_ib_statistics, rds_ib_stats); diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 36d931573ff..5709bad2832 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -524,7 +524,7 @@ void rds_ib_attempt_ack(struct rds_ib_connection *ic) } /* Can we get a send credit? */ - if (!rds_ib_send_grab_credits(ic, 1, &adv_credits, 0)) { + if (!rds_ib_send_grab_credits(ic, 1, &adv_credits, 0, RDS_MAX_ADV_CREDIT)) { rds_ib_stats_inc(s_ib_tx_throttle); clear_bit(IB_ACK_IN_FLIGHT, &ic->i_ack_flags); return; diff --git a/net/rds/ib_ring.c b/net/rds/ib_ring.c index 99a6ccae964..ff97e8eda85 100644 --- a/net/rds/ib_ring.c +++ b/net/rds/ib_ring.c @@ -137,7 +137,7 @@ int rds_ib_ring_empty(struct rds_ib_work_ring *ring) int rds_ib_ring_low(struct rds_ib_work_ring *ring) { - return __rds_ib_ring_used(ring) <= (ring->w_nr >> 2); + return __rds_ib_ring_used(ring) <= (ring->w_nr >> 1); } /* diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index cb6c52cb1c4..23bf830db2d 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -311,7 +311,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) * and using atomic_cmpxchg when updating the two counters. */ int rds_ib_send_grab_credits(struct rds_ib_connection *ic, - u32 wanted, u32 *adv_credits, int need_posted) + u32 wanted, u32 *adv_credits, int need_posted, int max_posted) { unsigned int avail, posted, got = 0, advertise; long oldval, newval; @@ -351,7 +351,7 @@ try_again: * available. */ if (posted && (got || need_posted)) { - advertise = min_t(unsigned int, posted, RDS_MAX_ADV_CREDIT); + advertise = min_t(unsigned int, posted, max_posted); newval -= IB_SET_POST_CREDITS(advertise); } @@ -498,7 +498,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, credit_alloc = work_alloc; if (ic->i_flowctl) { - credit_alloc = rds_ib_send_grab_credits(ic, work_alloc, &posted, 0); + credit_alloc = rds_ib_send_grab_credits(ic, work_alloc, &posted, 0, RDS_MAX_ADV_CREDIT); adv_credits += posted; if (credit_alloc < work_alloc) { rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc - credit_alloc); @@ -506,7 +506,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, flow_controlled++; } if (work_alloc == 0) { - rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc); + set_bit(RDS_LL_SEND_FULL, &conn->c_flags); rds_ib_stats_inc(s_ib_tx_throttle); ret = -ENOMEM; goto out; @@ -571,7 +571,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, /* * Update adv_credits since we reset the ACK_REQUIRED bit. */ - rds_ib_send_grab_credits(ic, 0, &posted, 1); + rds_ib_send_grab_credits(ic, 0, &posted, 1, RDS_MAX_ADV_CREDIT - adv_credits); adv_credits += posted; BUG_ON(adv_credits > 255); } else if (ic->i_rm != rm) diff --git a/net/rds/info.c b/net/rds/info.c index 1d885535214..62aeef37aef 100644 --- a/net/rds/info.c +++ b/net/rds/info.c @@ -188,10 +188,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval, ret = -ENOMEM; goto out; } - down_read(¤t->mm->mmap_sem); - ret = get_user_pages(current, current->mm, start, nr_pages, 1, 0, - pages, NULL); - up_read(¤t->mm->mmap_sem); + ret = get_user_pages_fast(start, nr_pages, 1, pages); if (ret != nr_pages) { if (ret > 0) nr_pages = ret; diff --git a/net/rds/iw.c b/net/rds/iw.c index b732efb5b63..d16e1cbc8e8 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -233,8 +233,8 @@ static int rds_iw_laddr_check(__be32 addr) * IB and iWARP capable NICs. */ cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP); - if (!cm_id) - return -EADDRNOTAVAIL; + if (IS_ERR(cm_id)) + return PTR_ERR(cm_id); memset(&sin, 0, sizeof(sin)); sin.sin_family = AF_INET; diff --git a/net/rds/iw.h b/net/rds/iw.h index b4fb2725289..0715dde323e 100644 --- a/net/rds/iw.h +++ b/net/rds/iw.h @@ -361,7 +361,7 @@ int rds_iw_xmit_rdma(struct rds_connection *conn, struct rds_rdma_op *op); void rds_iw_send_add_credits(struct rds_connection *conn, unsigned int credits); void rds_iw_advertise_credits(struct rds_connection *conn, unsigned int posted); int rds_iw_send_grab_credits(struct rds_iw_connection *ic, u32 wanted, - u32 *adv_credits, int need_posted); + u32 *adv_credits, int need_posted, int max_posted); /* ib_stats.c */ DECLARE_PER_CPU(struct rds_iw_statistics, rds_iw_stats); diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c index fde470fa50d..8683f5f66c4 100644 --- a/net/rds/iw_recv.c +++ b/net/rds/iw_recv.c @@ -524,7 +524,7 @@ void rds_iw_attempt_ack(struct rds_iw_connection *ic) } /* Can we get a send credit? */ - if (!rds_iw_send_grab_credits(ic, 1, &adv_credits, 0)) { + if (!rds_iw_send_grab_credits(ic, 1, &adv_credits, 0, RDS_MAX_ADV_CREDIT)) { rds_iw_stats_inc(s_iw_tx_throttle); clear_bit(IB_ACK_IN_FLIGHT, &ic->i_ack_flags); return; diff --git a/net/rds/iw_ring.c b/net/rds/iw_ring.c index d422d4b5dee..da8e3b63f66 100644 --- a/net/rds/iw_ring.c +++ b/net/rds/iw_ring.c @@ -137,7 +137,7 @@ int rds_iw_ring_empty(struct rds_iw_work_ring *ring) int rds_iw_ring_low(struct rds_iw_work_ring *ring) { - return __rds_iw_ring_used(ring) <= (ring->w_nr >> 2); + return __rds_iw_ring_used(ring) <= (ring->w_nr >> 1); } diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 22dd38ffd60..44a6a0551f2 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -347,7 +347,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context) * and using atomic_cmpxchg when updating the two counters. */ int rds_iw_send_grab_credits(struct rds_iw_connection *ic, - u32 wanted, u32 *adv_credits, int need_posted) + u32 wanted, u32 *adv_credits, int need_posted, int max_posted) { unsigned int avail, posted, got = 0, advertise; long oldval, newval; @@ -387,7 +387,7 @@ try_again: * available. */ if (posted && (got || need_posted)) { - advertise = min_t(unsigned int, posted, RDS_MAX_ADV_CREDIT); + advertise = min_t(unsigned int, posted, max_posted); newval -= IB_SET_POST_CREDITS(advertise); } @@ -541,7 +541,7 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, credit_alloc = work_alloc; if (ic->i_flowctl) { - credit_alloc = rds_iw_send_grab_credits(ic, work_alloc, &posted, 0); + credit_alloc = rds_iw_send_grab_credits(ic, work_alloc, &posted, 0, RDS_MAX_ADV_CREDIT); adv_credits += posted; if (credit_alloc < work_alloc) { rds_iw_ring_unalloc(&ic->i_send_ring, work_alloc - credit_alloc); @@ -549,7 +549,7 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, flow_controlled++; } if (work_alloc == 0) { - rds_iw_ring_unalloc(&ic->i_send_ring, work_alloc); + set_bit(RDS_LL_SEND_FULL, &conn->c_flags); rds_iw_stats_inc(s_iw_tx_throttle); ret = -ENOMEM; goto out; @@ -614,7 +614,7 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, /* * Update adv_credits since we reset the ACK_REQUIRED bit. */ - rds_iw_send_grab_credits(ic, 0, &posted, 1); + rds_iw_send_grab_credits(ic, 0, &posted, 1, RDS_MAX_ADV_CREDIT - adv_credits); adv_credits += posted; BUG_ON(adv_credits > 255); } else if (ic->i_rm != rm) diff --git a/net/rds/rdma.c b/net/rds/rdma.c index eaeeb91e111..8dc83d2caa5 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -150,12 +150,9 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, { int ret; - down_read(¤t->mm->mmap_sem); - ret = get_user_pages(current, current->mm, user_addr, - nr_pages, write, 0, pages, NULL); - up_read(¤t->mm->mmap_sem); + ret = get_user_pages_fast(user_addr, nr_pages, write, pages); - if (0 <= ret && (unsigned) ret < nr_pages) { + if (ret >= 0 && ret < nr_pages) { while (ret--) put_page(pages[ret]); ret = -EFAULT; diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 7b19024f970..7d0f901c93d 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -34,7 +34,7 @@ #include "rdma_transport.h" -static struct rdma_cm_id *rds_iw_listen_id; +static struct rdma_cm_id *rds_rdma_listen_id; int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) @@ -161,7 +161,7 @@ static int __init rds_rdma_listen_init(void) rdsdebug("cm %p listening on port %u\n", cm_id, RDS_PORT); - rds_iw_listen_id = cm_id; + rds_rdma_listen_id = cm_id; cm_id = NULL; out: if (cm_id) @@ -171,10 +171,10 @@ out: static void rds_rdma_listen_stop(void) { - if (rds_iw_listen_id) { - rdsdebug("cm %p\n", rds_iw_listen_id); - rdma_destroy_id(rds_iw_listen_id); - rds_iw_listen_id = NULL; + if (rds_rdma_listen_id) { + rdsdebug("cm %p\n", rds_rdma_listen_id); + rdma_destroy_id(rds_rdma_listen_id); + rds_rdma_listen_id = NULL; } } diff --git a/net/rds/rds.h b/net/rds/rds.h index 71794449ca4..dbe11123678 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -132,7 +132,7 @@ struct rds_connection { #define RDS_FLAG_CONG_BITMAP 0x01 #define RDS_FLAG_ACK_REQUIRED 0x02 #define RDS_FLAG_RETRANSMITTED 0x04 -#define RDS_MAX_ADV_CREDIT 127 +#define RDS_MAX_ADV_CREDIT 255 /* * Maximum space available for extension headers. diff --git a/net/rds/send.c b/net/rds/send.c index 104fe033203..a4a7f428cd7 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -854,11 +854,6 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rm->m_daddr = daddr; - /* Parse any control messages the user may have included. */ - ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); - if (ret) - goto out; - /* rds_conn_create has a spinlock that runs with IRQ off. * Caching the conn in the socket helps a lot. */ if (rs->rs_conn && rs->rs_conn->c_faddr == daddr) @@ -874,6 +869,11 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rs->rs_conn = conn; } + /* Parse any control messages the user may have included. */ + ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); + if (ret) + goto out; + if ((rm->m_rdma_cookie || rm->m_rdma_op) && conn->c_trans->xmit_rdma == NULL) { if (printk_ratelimit()) diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig index 7f807b30cfb..eaf76587645 100644 --- a/net/rfkill/Kconfig +++ b/net/rfkill/Kconfig @@ -10,22 +10,15 @@ menuconfig RFKILL To compile this driver as a module, choose M here: the module will be called rfkill. -config RFKILL_INPUT - tristate "Input layer to RF switch connector" - depends on RFKILL && INPUT - help - Say Y here if you want kernel automatically toggle state - of RF switches on and off when user presses appropriate - button or a key on the keyboard. Without this module you - need a some kind of userspace application to control - state of the switches. - - To compile this driver as a module, choose M here: the - module will be called rfkill-input. - # LED trigger support config RFKILL_LEDS bool - depends on RFKILL && LEDS_TRIGGERS + depends on RFKILL + depends on LEDS_TRIGGERS = y || RFKILL = LEDS_TRIGGERS default y +config RFKILL_INPUT + bool "RF switch input support" if EMBEDDED + depends on RFKILL + depends on INPUT = y || RFKILL = INPUT + default y if !EMBEDDED diff --git a/net/rfkill/Makefile b/net/rfkill/Makefile index b38c430be05..66210535269 100644 --- a/net/rfkill/Makefile +++ b/net/rfkill/Makefile @@ -2,5 +2,6 @@ # Makefile for the RF switch subsystem. # -obj-$(CONFIG_RFKILL) += rfkill.o -obj-$(CONFIG_RFKILL_INPUT) += rfkill-input.o +rfkill-y += core.o +rfkill-$(CONFIG_RFKILL_INPUT) += input.o +obj-$(CONFIG_RFKILL) += rfkill.o diff --git a/net/rfkill/core.c b/net/rfkill/core.c new file mode 100644 index 00000000000..2fc4a1724eb --- /dev/null +++ b/net/rfkill/core.c @@ -0,0 +1,1240 @@ +/* + * Copyright (C) 2006 - 2007 Ivo van Doorn + * Copyright (C) 2007 Dmitry Torokhov + * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * 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., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/workqueue.h> +#include <linux/capability.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/rfkill.h> +#include <linux/spinlock.h> +#include <linux/miscdevice.h> +#include <linux/wait.h> +#include <linux/poll.h> +#include <linux/fs.h> + +#include "rfkill.h" + +#define POLL_INTERVAL (5 * HZ) + +#define RFKILL_BLOCK_HW BIT(0) +#define RFKILL_BLOCK_SW BIT(1) +#define RFKILL_BLOCK_SW_PREV BIT(2) +#define RFKILL_BLOCK_ANY (RFKILL_BLOCK_HW |\ + RFKILL_BLOCK_SW |\ + RFKILL_BLOCK_SW_PREV) +#define RFKILL_BLOCK_SW_SETCALL BIT(31) + +struct rfkill { + spinlock_t lock; + + const char *name; + enum rfkill_type type; + + unsigned long state; + + u32 idx; + + bool registered; + bool persistent; + + const struct rfkill_ops *ops; + void *data; + +#ifdef CONFIG_RFKILL_LEDS + struct led_trigger led_trigger; + const char *ledtrigname; +#endif + + struct device dev; + struct list_head node; + + struct delayed_work poll_work; + struct work_struct uevent_work; + struct work_struct sync_work; +}; +#define to_rfkill(d) container_of(d, struct rfkill, dev) + +struct rfkill_int_event { + struct list_head list; + struct rfkill_event ev; +}; + +struct rfkill_data { + struct list_head list; + struct list_head events; + struct mutex mtx; + wait_queue_head_t read_wait; + bool input_handler; +}; + + +MODULE_AUTHOR("Ivo van Doorn <IvDoorn@gmail.com>"); +MODULE_AUTHOR("Johannes Berg <johannes@sipsolutions.net>"); +MODULE_DESCRIPTION("RF switch support"); +MODULE_LICENSE("GPL"); + + +/* + * The locking here should be made much smarter, we currently have + * a bit of a stupid situation because drivers might want to register + * the rfkill struct under their own lock, and take this lock during + * rfkill method calls -- which will cause an AB-BA deadlock situation. + * + * To fix that, we need to rework this code here to be mostly lock-free + * and only use the mutex for list manipulations, not to protect the + * various other global variables. Then we can avoid holding the mutex + * around driver operations, and all is happy. + */ +static LIST_HEAD(rfkill_list); /* list of registered rf switches */ +static DEFINE_MUTEX(rfkill_global_mutex); +static LIST_HEAD(rfkill_fds); /* list of open fds of /dev/rfkill */ + +static unsigned int rfkill_default_state = 1; +module_param_named(default_state, rfkill_default_state, uint, 0444); +MODULE_PARM_DESC(default_state, + "Default initial state for all radio types, 0 = radio off"); + +static struct { + bool cur, sav; +} rfkill_global_states[NUM_RFKILL_TYPES]; + +static bool rfkill_epo_lock_active; + + +#ifdef CONFIG_RFKILL_LEDS +static void rfkill_led_trigger_event(struct rfkill *rfkill) +{ + struct led_trigger *trigger; + + if (!rfkill->registered) + return; + + trigger = &rfkill->led_trigger; + + if (rfkill->state & RFKILL_BLOCK_ANY) + led_trigger_event(trigger, LED_OFF); + else + led_trigger_event(trigger, LED_FULL); +} + +static void rfkill_led_trigger_activate(struct led_classdev *led) +{ + struct rfkill *rfkill; + + rfkill = container_of(led->trigger, struct rfkill, led_trigger); + + rfkill_led_trigger_event(rfkill); +} + +const char *rfkill_get_led_trigger_name(struct rfkill *rfkill) +{ + return rfkill->led_trigger.name; +} +EXPORT_SYMBOL(rfkill_get_led_trigger_name); + +void rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name) +{ + BUG_ON(!rfkill); + + rfkill->ledtrigname = name; +} +EXPORT_SYMBOL(rfkill_set_led_trigger_name); + +static int rfkill_led_trigger_register(struct rfkill *rfkill) +{ + rfkill->led_trigger.name = rfkill->ledtrigname + ? : dev_name(&rfkill->dev); + rfkill->led_trigger.activate = rfkill_led_trigger_activate; + return led_trigger_register(&rfkill->led_trigger); +} + +static void rfkill_led_trigger_unregister(struct rfkill *rfkill) +{ + led_trigger_unregister(&rfkill->led_trigger); +} +#else +static void rfkill_led_trigger_event(struct rfkill *rfkill) +{ +} + +static inline int rfkill_led_trigger_register(struct rfkill *rfkill) +{ + return 0; +} + +static inline void rfkill_led_trigger_unregister(struct rfkill *rfkill) +{ +} +#endif /* CONFIG_RFKILL_LEDS */ + +static void rfkill_fill_event(struct rfkill_event *ev, struct rfkill *rfkill, + enum rfkill_operation op) +{ + unsigned long flags; + + ev->idx = rfkill->idx; + ev->type = rfkill->type; + ev->op = op; + + spin_lock_irqsave(&rfkill->lock, flags); + ev->hard = !!(rfkill->state & RFKILL_BLOCK_HW); + ev->soft = !!(rfkill->state & (RFKILL_BLOCK_SW | + RFKILL_BLOCK_SW_PREV)); + spin_unlock_irqrestore(&rfkill->lock, flags); +} + +static void rfkill_send_events(struct rfkill *rfkill, enum rfkill_operation op) +{ + struct rfkill_data *data; + struct rfkill_int_event *ev; + + list_for_each_entry(data, &rfkill_fds, list) { + ev = kzalloc(sizeof(*ev), GFP_KERNEL); + if (!ev) + continue; + rfkill_fill_event(&ev->ev, rfkill, op); + mutex_lock(&data->mtx); + list_add_tail(&ev->list, &data->events); + mutex_unlock(&data->mtx); + wake_up_interruptible(&data->read_wait); + } +} + +static void rfkill_event(struct rfkill *rfkill) +{ + if (!rfkill->registered) + return; + + kobject_uevent(&rfkill->dev.kobj, KOBJ_CHANGE); + + /* also send event to /dev/rfkill */ + rfkill_send_events(rfkill, RFKILL_OP_CHANGE); +} + +static bool __rfkill_set_hw_state(struct rfkill *rfkill, + bool blocked, bool *change) +{ + unsigned long flags; + bool prev, any; + + BUG_ON(!rfkill); + + spin_lock_irqsave(&rfkill->lock, flags); + prev = !!(rfkill->state & RFKILL_BLOCK_HW); + if (blocked) + rfkill->state |= RFKILL_BLOCK_HW; + else + rfkill->state &= ~RFKILL_BLOCK_HW; + *change = prev != blocked; + any = rfkill->state & RFKILL_BLOCK_ANY; + spin_unlock_irqrestore(&rfkill->lock, flags); + + rfkill_led_trigger_event(rfkill); + + return any; +} + +/** + * rfkill_set_block - wrapper for set_block method + * + * @rfkill: the rfkill struct to use + * @blocked: the new software state + * + * Calls the set_block method (when applicable) and handles notifications + * etc. as well. + */ +static void rfkill_set_block(struct rfkill *rfkill, bool blocked) +{ + unsigned long flags; + int err; + + if (unlikely(rfkill->dev.power.power_state.event & PM_EVENT_SLEEP)) + return; + + /* + * Some platforms (...!) generate input events which affect the + * _hard_ kill state -- whenever something tries to change the + * current software state query the hardware state too. + */ + if (rfkill->ops->query) + rfkill->ops->query(rfkill, rfkill->data); + + spin_lock_irqsave(&rfkill->lock, flags); + if (rfkill->state & RFKILL_BLOCK_SW) + rfkill->state |= RFKILL_BLOCK_SW_PREV; + else + rfkill->state &= ~RFKILL_BLOCK_SW_PREV; + + if (blocked) + rfkill->state |= RFKILL_BLOCK_SW; + else + rfkill->state &= ~RFKILL_BLOCK_SW; + + rfkill->state |= RFKILL_BLOCK_SW_SETCALL; + spin_unlock_irqrestore(&rfkill->lock, flags); + + err = rfkill->ops->set_block(rfkill->data, blocked); + + spin_lock_irqsave(&rfkill->lock, flags); + if (err) { + /* + * Failed -- reset status to _prev, this may be different + * from what set set _PREV to earlier in this function + * if rfkill_set_sw_state was invoked. + */ + if (rfkill->state & RFKILL_BLOCK_SW_PREV) + rfkill->state |= RFKILL_BLOCK_SW; + else + rfkill->state &= ~RFKILL_BLOCK_SW; + } + rfkill->state &= ~RFKILL_BLOCK_SW_SETCALL; + rfkill->state &= ~RFKILL_BLOCK_SW_PREV; + spin_unlock_irqrestore(&rfkill->lock, flags); + + rfkill_led_trigger_event(rfkill); + rfkill_event(rfkill); +} + +#ifdef CONFIG_RFKILL_INPUT +static atomic_t rfkill_input_disabled = ATOMIC_INIT(0); + +/** + * __rfkill_switch_all - Toggle state of all switches of given type + * @type: type of interfaces to be affected + * @state: the new state + * + * This function sets the state of all switches of given type, + * unless a specific switch is claimed by userspace (in which case, + * that switch is left alone) or suspended. + * + * Caller must have acquired rfkill_global_mutex. + */ +static void __rfkill_switch_all(const enum rfkill_type type, bool blocked) +{ + struct rfkill *rfkill; + + rfkill_global_states[type].cur = blocked; + list_for_each_entry(rfkill, &rfkill_list, node) { + if (rfkill->type != type) + continue; + + rfkill_set_block(rfkill, blocked); + } +} + +/** + * rfkill_switch_all - Toggle state of all switches of given type + * @type: type of interfaces to be affected + * @state: the new state + * + * Acquires rfkill_global_mutex and calls __rfkill_switch_all(@type, @state). + * Please refer to __rfkill_switch_all() for details. + * + * Does nothing if the EPO lock is active. + */ +void rfkill_switch_all(enum rfkill_type type, bool blocked) +{ + if (atomic_read(&rfkill_input_disabled)) + return; + + mutex_lock(&rfkill_global_mutex); + + if (!rfkill_epo_lock_active) + __rfkill_switch_all(type, blocked); + + mutex_unlock(&rfkill_global_mutex); +} + +/** + * rfkill_epo - emergency power off all transmitters + * + * This kicks all non-suspended rfkill devices to RFKILL_STATE_SOFT_BLOCKED, + * ignoring everything in its path but rfkill_global_mutex and rfkill->mutex. + * + * The global state before the EPO is saved and can be restored later + * using rfkill_restore_states(). + */ +void rfkill_epo(void) +{ + struct rfkill *rfkill; + int i; + + if (atomic_read(&rfkill_input_disabled)) + return; + + mutex_lock(&rfkill_global_mutex); + + rfkill_epo_lock_active = true; + list_for_each_entry(rfkill, &rfkill_list, node) + rfkill_set_block(rfkill, true); + + for (i = 0; i < NUM_RFKILL_TYPES; i++) { + rfkill_global_states[i].sav = rfkill_global_states[i].cur; + rfkill_global_states[i].cur = true; + } + + mutex_unlock(&rfkill_global_mutex); +} + +/** + * rfkill_restore_states - restore global states + * + * Restore (and sync switches to) the global state from the + * states in rfkill_default_states. This can undo the effects of + * a call to rfkill_epo(). + */ +void rfkill_restore_states(void) +{ + int i; + + if (atomic_read(&rfkill_input_disabled)) + return; + + mutex_lock(&rfkill_global_mutex); + + rfkill_epo_lock_active = false; + for (i = 0; i < NUM_RFKILL_TYPES; i++) + __rfkill_switch_all(i, rfkill_global_states[i].sav); + mutex_unlock(&rfkill_global_mutex); +} + +/** + * rfkill_remove_epo_lock - unlock state changes + * + * Used by rfkill-input manually unlock state changes, when + * the EPO switch is deactivated. + */ +void rfkill_remove_epo_lock(void) +{ + if (atomic_read(&rfkill_input_disabled)) + return; + + mutex_lock(&rfkill_global_mutex); + rfkill_epo_lock_active = false; + mutex_unlock(&rfkill_global_mutex); +} + +/** + * rfkill_is_epo_lock_active - returns true EPO is active + * + * Returns 0 (false) if there is NOT an active EPO contidion, + * and 1 (true) if there is an active EPO contition, which + * locks all radios in one of the BLOCKED states. + * + * Can be called in atomic context. + */ +bool rfkill_is_epo_lock_active(void) +{ + return rfkill_epo_lock_active; +} + +/** + * rfkill_get_global_sw_state - returns global state for a type + * @type: the type to get the global state of + * + * Returns the current global state for a given wireless + * device type. + */ +bool rfkill_get_global_sw_state(const enum rfkill_type type) +{ + return rfkill_global_states[type].cur; +} +#endif + + +bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked) +{ + bool ret, change; + + ret = __rfkill_set_hw_state(rfkill, blocked, &change); + + if (!rfkill->registered) + return ret; + + if (change) + schedule_work(&rfkill->uevent_work); + + return ret; +} +EXPORT_SYMBOL(rfkill_set_hw_state); + +static void __rfkill_set_sw_state(struct rfkill *rfkill, bool blocked) +{ + u32 bit = RFKILL_BLOCK_SW; + + /* if in a ops->set_block right now, use other bit */ + if (rfkill->state & RFKILL_BLOCK_SW_SETCALL) + bit = RFKILL_BLOCK_SW_PREV; + + if (blocked) + rfkill->state |= bit; + else + rfkill->state &= ~bit; +} + +bool rfkill_set_sw_state(struct rfkill *rfkill, bool blocked) +{ + unsigned long flags; + bool prev, hwblock; + + BUG_ON(!rfkill); + + spin_lock_irqsave(&rfkill->lock, flags); + prev = !!(rfkill->state & RFKILL_BLOCK_SW); + __rfkill_set_sw_state(rfkill, blocked); + hwblock = !!(rfkill->state & RFKILL_BLOCK_HW); + blocked = blocked || hwblock; + spin_unlock_irqrestore(&rfkill->lock, flags); + + if (!rfkill->registered) + return blocked; + + if (prev != blocked && !hwblock) + schedule_work(&rfkill->uevent_work); + + rfkill_led_trigger_event(rfkill); + + return blocked; +} +EXPORT_SYMBOL(rfkill_set_sw_state); + +void rfkill_init_sw_state(struct rfkill *rfkill, bool blocked) +{ + unsigned long flags; + + BUG_ON(!rfkill); + BUG_ON(rfkill->registered); + + spin_lock_irqsave(&rfkill->lock, flags); + __rfkill_set_sw_state(rfkill, blocked); + rfkill->persistent = true; + spin_unlock_irqrestore(&rfkill->lock, flags); +} +EXPORT_SYMBOL(rfkill_init_sw_state); + +void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw) +{ + unsigned long flags; + bool swprev, hwprev; + + BUG_ON(!rfkill); + + spin_lock_irqsave(&rfkill->lock, flags); + + /* + * No need to care about prev/setblock ... this is for uevent only + * and that will get triggered by rfkill_set_block anyway. + */ + swprev = !!(rfkill->state & RFKILL_BLOCK_SW); + hwprev = !!(rfkill->state & RFKILL_BLOCK_HW); + __rfkill_set_sw_state(rfkill, sw); + if (hw) + rfkill->state |= RFKILL_BLOCK_HW; + else + rfkill->state &= ~RFKILL_BLOCK_HW; + + spin_unlock_irqrestore(&rfkill->lock, flags); + + if (!rfkill->registered) { + rfkill->persistent = true; + } else { + if (swprev != sw || hwprev != hw) + schedule_work(&rfkill->uevent_work); + + rfkill_led_trigger_event(rfkill); + } +} +EXPORT_SYMBOL(rfkill_set_states); + +static ssize_t rfkill_name_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct rfkill *rfkill = to_rfkill(dev); + + return sprintf(buf, "%s\n", rfkill->name); +} + +static const char *rfkill_get_type_str(enum rfkill_type type) +{ + switch (type) { + case RFKILL_TYPE_WLAN: + return "wlan"; + case RFKILL_TYPE_BLUETOOTH: + return "bluetooth"; + case RFKILL_TYPE_UWB: + return "ultrawideband"; + case RFKILL_TYPE_WIMAX: + return "wimax"; + case RFKILL_TYPE_WWAN: + return "wwan"; + default: + BUG(); + } + + BUILD_BUG_ON(NUM_RFKILL_TYPES != RFKILL_TYPE_WWAN + 1); +} + +static ssize_t rfkill_type_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct rfkill *rfkill = to_rfkill(dev); + + return sprintf(buf, "%s\n", rfkill_get_type_str(rfkill->type)); +} + +static ssize_t rfkill_idx_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct rfkill *rfkill = to_rfkill(dev); + + return sprintf(buf, "%d\n", rfkill->idx); +} + +static ssize_t rfkill_persistent_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct rfkill *rfkill = to_rfkill(dev); + + return sprintf(buf, "%d\n", rfkill->persistent); +} + +static u8 user_state_from_blocked(unsigned long state) +{ + if (state & RFKILL_BLOCK_HW) + return RFKILL_USER_STATE_HARD_BLOCKED; + if (state & RFKILL_BLOCK_SW) + return RFKILL_USER_STATE_SOFT_BLOCKED; + + return RFKILL_USER_STATE_UNBLOCKED; +} + +static ssize_t rfkill_state_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct rfkill *rfkill = to_rfkill(dev); + unsigned long flags; + u32 state; + + spin_lock_irqsave(&rfkill->lock, flags); + state = rfkill->state; + spin_unlock_irqrestore(&rfkill->lock, flags); + + return sprintf(buf, "%d\n", user_state_from_blocked(state)); +} + +static ssize_t rfkill_state_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct rfkill *rfkill = to_rfkill(dev); + unsigned long state; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + err = strict_strtoul(buf, 0, &state); + if (err) + return err; + + if (state != RFKILL_USER_STATE_SOFT_BLOCKED && + state != RFKILL_USER_STATE_UNBLOCKED) + return -EINVAL; + + mutex_lock(&rfkill_global_mutex); + rfkill_set_block(rfkill, state == RFKILL_USER_STATE_SOFT_BLOCKED); + mutex_unlock(&rfkill_global_mutex); + + return err ?: count; +} + +static ssize_t rfkill_claim_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", 0); +} + +static ssize_t rfkill_claim_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + return -EOPNOTSUPP; +} + +static struct device_attribute rfkill_dev_attrs[] = { + __ATTR(name, S_IRUGO, rfkill_name_show, NULL), + __ATTR(type, S_IRUGO, rfkill_type_show, NULL), + __ATTR(index, S_IRUGO, rfkill_idx_show, NULL), + __ATTR(persistent, S_IRUGO, rfkill_persistent_show, NULL), + __ATTR(state, S_IRUGO|S_IWUSR, rfkill_state_show, rfkill_state_store), + __ATTR(claim, S_IRUGO|S_IWUSR, rfkill_claim_show, rfkill_claim_store), + __ATTR_NULL +}; + +static void rfkill_release(struct device *dev) +{ + struct rfkill *rfkill = to_rfkill(dev); + + kfree(rfkill); +} + +static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct rfkill *rfkill = to_rfkill(dev); + unsigned long flags; + u32 state; + int error; + + error = add_uevent_var(env, "RFKILL_NAME=%s", rfkill->name); + if (error) + return error; + error = add_uevent_var(env, "RFKILL_TYPE=%s", + rfkill_get_type_str(rfkill->type)); + if (error) + return error; + spin_lock_irqsave(&rfkill->lock, flags); + state = rfkill->state; + spin_unlock_irqrestore(&rfkill->lock, flags); + error = add_uevent_var(env, "RFKILL_STATE=%d", + user_state_from_blocked(state)); + return error; +} + +void rfkill_pause_polling(struct rfkill *rfkill) +{ + BUG_ON(!rfkill); + + if (!rfkill->ops->poll) + return; + + cancel_delayed_work_sync(&rfkill->poll_work); +} +EXPORT_SYMBOL(rfkill_pause_polling); + +void rfkill_resume_polling(struct rfkill *rfkill) +{ + BUG_ON(!rfkill); + + if (!rfkill->ops->poll) + return; + + schedule_work(&rfkill->poll_work.work); +} +EXPORT_SYMBOL(rfkill_resume_polling); + +static int rfkill_suspend(struct device *dev, pm_message_t state) +{ + struct rfkill *rfkill = to_rfkill(dev); + + rfkill_pause_polling(rfkill); + + return 0; +} + +static int rfkill_resume(struct device *dev) +{ + struct rfkill *rfkill = to_rfkill(dev); + bool cur; + + if (!rfkill->persistent) { + cur = !!(rfkill->state & RFKILL_BLOCK_SW); + rfkill_set_block(rfkill, cur); + } + + rfkill_resume_polling(rfkill); + + return 0; +} + +static struct class rfkill_class = { + .name = "rfkill", + .dev_release = rfkill_release, + .dev_attrs = rfkill_dev_attrs, + .dev_uevent = rfkill_dev_uevent, + .suspend = rfkill_suspend, + .resume = rfkill_resume, +}; + +bool rfkill_blocked(struct rfkill *rfkill) +{ + unsigned long flags; + u32 state; + + spin_lock_irqsave(&rfkill->lock, flags); + state = rfkill->state; + spin_unlock_irqrestore(&rfkill->lock, flags); + + return !!(state & RFKILL_BLOCK_ANY); +} +EXPORT_SYMBOL(rfkill_blocked); + + +struct rfkill * __must_check rfkill_alloc(const char *name, + struct device *parent, + const enum rfkill_type type, + const struct rfkill_ops *ops, + void *ops_data) +{ + struct rfkill *rfkill; + struct device *dev; + + if (WARN_ON(!ops)) + return NULL; + + if (WARN_ON(!ops->set_block)) + return NULL; + + if (WARN_ON(!name)) + return NULL; + + if (WARN_ON(type == RFKILL_TYPE_ALL || type >= NUM_RFKILL_TYPES)) + return NULL; + + rfkill = kzalloc(sizeof(*rfkill), GFP_KERNEL); + if (!rfkill) + return NULL; + + spin_lock_init(&rfkill->lock); + INIT_LIST_HEAD(&rfkill->node); + rfkill->type = type; + rfkill->name = name; + rfkill->ops = ops; + rfkill->data = ops_data; + + dev = &rfkill->dev; + dev->class = &rfkill_class; + dev->parent = parent; + device_initialize(dev); + + return rfkill; +} +EXPORT_SYMBOL(rfkill_alloc); + +static void rfkill_poll(struct work_struct *work) +{ + struct rfkill *rfkill; + + rfkill = container_of(work, struct rfkill, poll_work.work); + + /* + * Poll hardware state -- driver will use one of the + * rfkill_set{,_hw,_sw}_state functions and use its + * return value to update the current status. + */ + rfkill->ops->poll(rfkill, rfkill->data); + + schedule_delayed_work(&rfkill->poll_work, + round_jiffies_relative(POLL_INTERVAL)); +} + +static void rfkill_uevent_work(struct work_struct *work) +{ + struct rfkill *rfkill; + + rfkill = container_of(work, struct rfkill, uevent_work); + + mutex_lock(&rfkill_global_mutex); + rfkill_event(rfkill); + mutex_unlock(&rfkill_global_mutex); +} + +static void rfkill_sync_work(struct work_struct *work) +{ + struct rfkill *rfkill; + bool cur; + + rfkill = container_of(work, struct rfkill, sync_work); + + mutex_lock(&rfkill_global_mutex); + cur = rfkill_global_states[rfkill->type].cur; + rfkill_set_block(rfkill, cur); + mutex_unlock(&rfkill_global_mutex); +} + +int __must_check rfkill_register(struct rfkill *rfkill) +{ + static unsigned long rfkill_no; + struct device *dev = &rfkill->dev; + int error; + + BUG_ON(!rfkill); + + mutex_lock(&rfkill_global_mutex); + + if (rfkill->registered) { + error = -EALREADY; + goto unlock; + } + + rfkill->idx = rfkill_no; + dev_set_name(dev, "rfkill%lu", rfkill_no); + rfkill_no++; + + list_add_tail(&rfkill->node, &rfkill_list); + + error = device_add(dev); + if (error) + goto remove; + + error = rfkill_led_trigger_register(rfkill); + if (error) + goto devdel; + + rfkill->registered = true; + + INIT_DELAYED_WORK(&rfkill->poll_work, rfkill_poll); + INIT_WORK(&rfkill->uevent_work, rfkill_uevent_work); + INIT_WORK(&rfkill->sync_work, rfkill_sync_work); + + if (rfkill->ops->poll) + schedule_delayed_work(&rfkill->poll_work, + round_jiffies_relative(POLL_INTERVAL)); + + if (!rfkill->persistent || rfkill_epo_lock_active) { + schedule_work(&rfkill->sync_work); + } else { +#ifdef CONFIG_RFKILL_INPUT + bool soft_blocked = !!(rfkill->state & RFKILL_BLOCK_SW); + + if (!atomic_read(&rfkill_input_disabled)) + __rfkill_switch_all(rfkill->type, soft_blocked); +#endif + } + + rfkill_send_events(rfkill, RFKILL_OP_ADD); + + mutex_unlock(&rfkill_global_mutex); + return 0; + + devdel: + device_del(&rfkill->dev); + remove: + list_del_init(&rfkill->node); + unlock: + mutex_unlock(&rfkill_global_mutex); + return error; +} +EXPORT_SYMBOL(rfkill_register); + +void rfkill_unregister(struct rfkill *rfkill) +{ + BUG_ON(!rfkill); + + if (rfkill->ops->poll) + cancel_delayed_work_sync(&rfkill->poll_work); + + cancel_work_sync(&rfkill->uevent_work); + cancel_work_sync(&rfkill->sync_work); + + rfkill->registered = false; + + device_del(&rfkill->dev); + + mutex_lock(&rfkill_global_mutex); + rfkill_send_events(rfkill, RFKILL_OP_DEL); + list_del_init(&rfkill->node); + mutex_unlock(&rfkill_global_mutex); + + rfkill_led_trigger_unregister(rfkill); +} +EXPORT_SYMBOL(rfkill_unregister); + +void rfkill_destroy(struct rfkill *rfkill) +{ + if (rfkill) + put_device(&rfkill->dev); +} +EXPORT_SYMBOL(rfkill_destroy); + +static int rfkill_fop_open(struct inode *inode, struct file *file) +{ + struct rfkill_data *data; + struct rfkill *rfkill; + struct rfkill_int_event *ev, *tmp; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + INIT_LIST_HEAD(&data->events); + mutex_init(&data->mtx); + init_waitqueue_head(&data->read_wait); + + mutex_lock(&rfkill_global_mutex); + mutex_lock(&data->mtx); + /* + * start getting events from elsewhere but hold mtx to get + * startup events added first + */ + list_add(&data->list, &rfkill_fds); + + list_for_each_entry(rfkill, &rfkill_list, node) { + ev = kzalloc(sizeof(*ev), GFP_KERNEL); + if (!ev) + goto free; + rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD); + list_add_tail(&ev->list, &data->events); + } + mutex_unlock(&data->mtx); + mutex_unlock(&rfkill_global_mutex); + + file->private_data = data; + + return nonseekable_open(inode, file); + + free: + mutex_unlock(&data->mtx); + mutex_unlock(&rfkill_global_mutex); + mutex_destroy(&data->mtx); + list_for_each_entry_safe(ev, tmp, &data->events, list) + kfree(ev); + kfree(data); + return -ENOMEM; +} + +static unsigned int rfkill_fop_poll(struct file *file, poll_table *wait) +{ + struct rfkill_data *data = file->private_data; + unsigned int res = POLLOUT | POLLWRNORM; + + poll_wait(file, &data->read_wait, wait); + + mutex_lock(&data->mtx); + if (!list_empty(&data->events)) + res = POLLIN | POLLRDNORM; + mutex_unlock(&data->mtx); + + return res; +} + +static bool rfkill_readable(struct rfkill_data *data) +{ + bool r; + + mutex_lock(&data->mtx); + r = !list_empty(&data->events); + mutex_unlock(&data->mtx); + + return r; +} + +static ssize_t rfkill_fop_read(struct file *file, char __user *buf, + size_t count, loff_t *pos) +{ + struct rfkill_data *data = file->private_data; + struct rfkill_int_event *ev; + unsigned long sz; + int ret; + + mutex_lock(&data->mtx); + + while (list_empty(&data->events)) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + goto out; + } + mutex_unlock(&data->mtx); + ret = wait_event_interruptible(data->read_wait, + rfkill_readable(data)); + mutex_lock(&data->mtx); + + if (ret) + goto out; + } + + ev = list_first_entry(&data->events, struct rfkill_int_event, + list); + + sz = min_t(unsigned long, sizeof(ev->ev), count); + ret = sz; + if (copy_to_user(buf, &ev->ev, sz)) + ret = -EFAULT; + + list_del(&ev->list); + kfree(ev); + out: + mutex_unlock(&data->mtx); + return ret; +} + +static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, + size_t count, loff_t *pos) +{ + struct rfkill *rfkill; + struct rfkill_event ev; + + /* we don't need the 'hard' variable but accept it */ + if (count < sizeof(ev) - 1) + return -EINVAL; + + if (copy_from_user(&ev, buf, sizeof(ev) - 1)) + return -EFAULT; + + if (ev.op != RFKILL_OP_CHANGE && ev.op != RFKILL_OP_CHANGE_ALL) + return -EINVAL; + + if (ev.type >= NUM_RFKILL_TYPES) + return -EINVAL; + + mutex_lock(&rfkill_global_mutex); + + if (ev.op == RFKILL_OP_CHANGE_ALL) { + if (ev.type == RFKILL_TYPE_ALL) { + enum rfkill_type i; + for (i = 0; i < NUM_RFKILL_TYPES; i++) + rfkill_global_states[i].cur = ev.soft; + } else { + rfkill_global_states[ev.type].cur = ev.soft; + } + } + + list_for_each_entry(rfkill, &rfkill_list, node) { + if (rfkill->idx != ev.idx && ev.op != RFKILL_OP_CHANGE_ALL) + continue; + + if (rfkill->type != ev.type && ev.type != RFKILL_TYPE_ALL) + continue; + + rfkill_set_block(rfkill, ev.soft); + } + mutex_unlock(&rfkill_global_mutex); + + return count; +} + +static int rfkill_fop_release(struct inode *inode, struct file *file) +{ + struct rfkill_data *data = file->private_data; + struct rfkill_int_event *ev, *tmp; + + mutex_lock(&rfkill_global_mutex); + list_del(&data->list); + mutex_unlock(&rfkill_global_mutex); + + mutex_destroy(&data->mtx); + list_for_each_entry_safe(ev, tmp, &data->events, list) + kfree(ev); + +#ifdef CONFIG_RFKILL_INPUT + if (data->input_handler) + if (atomic_dec_return(&rfkill_input_disabled) == 0) + printk(KERN_DEBUG "rfkill: input handler enabled\n"); +#endif + + kfree(data); + + return 0; +} + +#ifdef CONFIG_RFKILL_INPUT +static long rfkill_fop_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct rfkill_data *data = file->private_data; + + if (_IOC_TYPE(cmd) != RFKILL_IOC_MAGIC) + return -ENOSYS; + + if (_IOC_NR(cmd) != RFKILL_IOC_NOINPUT) + return -ENOSYS; + + mutex_lock(&data->mtx); + + if (!data->input_handler) { + if (atomic_inc_return(&rfkill_input_disabled) == 1) + printk(KERN_DEBUG "rfkill: input handler disabled\n"); + data->input_handler = true; + } + + mutex_unlock(&data->mtx); + + return 0; +} +#endif + +static const struct file_operations rfkill_fops = { + .open = rfkill_fop_open, + .read = rfkill_fop_read, + .write = rfkill_fop_write, + .poll = rfkill_fop_poll, + .release = rfkill_fop_release, +#ifdef CONFIG_RFKILL_INPUT + .unlocked_ioctl = rfkill_fop_ioctl, + .compat_ioctl = rfkill_fop_ioctl, +#endif +}; + +static struct miscdevice rfkill_miscdev = { + .name = "rfkill", + .fops = &rfkill_fops, + .minor = MISC_DYNAMIC_MINOR, +}; + +static int __init rfkill_init(void) +{ + int error; + int i; + + for (i = 0; i < NUM_RFKILL_TYPES; i++) + rfkill_global_states[i].cur = !rfkill_default_state; + + error = class_register(&rfkill_class); + if (error) + goto out; + + error = misc_register(&rfkill_miscdev); + if (error) { + class_unregister(&rfkill_class); + goto out; + } + +#ifdef CONFIG_RFKILL_INPUT + error = rfkill_handler_init(); + if (error) { + misc_deregister(&rfkill_miscdev); + class_unregister(&rfkill_class); + goto out; + } +#endif + + out: + return error; +} +subsys_initcall(rfkill_init); + +static void __exit rfkill_exit(void) +{ +#ifdef CONFIG_RFKILL_INPUT + rfkill_handler_exit(); +#endif + misc_deregister(&rfkill_miscdev); + class_unregister(&rfkill_class); +} +module_exit(rfkill_exit); diff --git a/net/rfkill/input.c b/net/rfkill/input.c new file mode 100644 index 00000000000..a7295ad5f9c --- /dev/null +++ b/net/rfkill/input.c @@ -0,0 +1,342 @@ +/* + * Input layer to RF Kill interface connector + * + * Copyright (c) 2007 Dmitry Torokhov + * Copyright 2009 Johannes Berg <johannes@sipsolutions.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. + * + * If you ever run into a situation in which you have a SW_ type rfkill + * input device, then you can revive code that was removed in the patch + * "rfkill-input: remove unused code". + */ + +#include <linux/input.h> +#include <linux/slab.h> +#include <linux/workqueue.h> +#include <linux/init.h> +#include <linux/rfkill.h> +#include <linux/sched.h> + +#include "rfkill.h" + +enum rfkill_input_master_mode { + RFKILL_INPUT_MASTER_UNLOCK = 0, + RFKILL_INPUT_MASTER_RESTORE = 1, + RFKILL_INPUT_MASTER_UNBLOCKALL = 2, + NUM_RFKILL_INPUT_MASTER_MODES +}; + +/* Delay (in ms) between consecutive switch ops */ +#define RFKILL_OPS_DELAY 200 + +static enum rfkill_input_master_mode rfkill_master_switch_mode = + RFKILL_INPUT_MASTER_UNBLOCKALL; +module_param_named(master_switch_mode, rfkill_master_switch_mode, uint, 0); +MODULE_PARM_DESC(master_switch_mode, + "SW_RFKILL_ALL ON should: 0=do nothing (only unlock); 1=restore; 2=unblock all"); + +static spinlock_t rfkill_op_lock; +static bool rfkill_op_pending; +static unsigned long rfkill_sw_pending[BITS_TO_LONGS(NUM_RFKILL_TYPES)]; +static unsigned long rfkill_sw_state[BITS_TO_LONGS(NUM_RFKILL_TYPES)]; + +enum rfkill_sched_op { + RFKILL_GLOBAL_OP_EPO = 0, + RFKILL_GLOBAL_OP_RESTORE, + RFKILL_GLOBAL_OP_UNLOCK, + RFKILL_GLOBAL_OP_UNBLOCK, +}; + +static enum rfkill_sched_op rfkill_master_switch_op; +static enum rfkill_sched_op rfkill_op; + +static void __rfkill_handle_global_op(enum rfkill_sched_op op) +{ + unsigned int i; + + switch (op) { + case RFKILL_GLOBAL_OP_EPO: + rfkill_epo(); + break; + case RFKILL_GLOBAL_OP_RESTORE: + rfkill_restore_states(); + break; + case RFKILL_GLOBAL_OP_UNLOCK: + rfkill_remove_epo_lock(); + break; + case RFKILL_GLOBAL_OP_UNBLOCK: + rfkill_remove_epo_lock(); + for (i = 0; i < NUM_RFKILL_TYPES; i++) + rfkill_switch_all(i, false); + break; + default: + /* memory corruption or bug, fail safely */ + rfkill_epo(); + WARN(1, "Unknown requested operation %d! " + "rfkill Emergency Power Off activated\n", + op); + } +} + +static void __rfkill_handle_normal_op(const enum rfkill_type type, + const bool complement) +{ + bool blocked; + + blocked = rfkill_get_global_sw_state(type); + if (complement) + blocked = !blocked; + + rfkill_switch_all(type, blocked); +} + +static void rfkill_op_handler(struct work_struct *work) +{ + unsigned int i; + bool c; + + spin_lock_irq(&rfkill_op_lock); + do { + if (rfkill_op_pending) { + enum rfkill_sched_op op = rfkill_op; + rfkill_op_pending = false; + memset(rfkill_sw_pending, 0, + sizeof(rfkill_sw_pending)); + spin_unlock_irq(&rfkill_op_lock); + + __rfkill_handle_global_op(op); + + spin_lock_irq(&rfkill_op_lock); + + /* + * handle global ops first -- during unlocked period + * we might have gotten a new global op. + */ + if (rfkill_op_pending) + continue; + } + + if (rfkill_is_epo_lock_active()) + continue; + + for (i = 0; i < NUM_RFKILL_TYPES; i++) { + if (__test_and_clear_bit(i, rfkill_sw_pending)) { + c = __test_and_clear_bit(i, rfkill_sw_state); + spin_unlock_irq(&rfkill_op_lock); + + __rfkill_handle_normal_op(i, c); + + spin_lock_irq(&rfkill_op_lock); + } + } + } while (rfkill_op_pending); + spin_unlock_irq(&rfkill_op_lock); +} + +static DECLARE_DELAYED_WORK(rfkill_op_work, rfkill_op_handler); +static unsigned long rfkill_last_scheduled; + +static unsigned long rfkill_ratelimit(const unsigned long last) +{ + const unsigned long delay = msecs_to_jiffies(RFKILL_OPS_DELAY); + return (time_after(jiffies, last + delay)) ? 0 : delay; +} + +static void rfkill_schedule_ratelimited(void) +{ + if (delayed_work_pending(&rfkill_op_work)) + return; + schedule_delayed_work(&rfkill_op_work, + rfkill_ratelimit(rfkill_last_scheduled)); + rfkill_last_scheduled = jiffies; +} + +static void rfkill_schedule_global_op(enum rfkill_sched_op op) +{ + unsigned long flags; + + spin_lock_irqsave(&rfkill_op_lock, flags); + rfkill_op = op; + rfkill_op_pending = true; + if (op == RFKILL_GLOBAL_OP_EPO && !rfkill_is_epo_lock_active()) { + /* bypass the limiter for EPO */ + cancel_delayed_work(&rfkill_op_work); + schedule_delayed_work(&rfkill_op_work, 0); + rfkill_last_scheduled = jiffies; + } else + rfkill_schedule_ratelimited(); + spin_unlock_irqrestore(&rfkill_op_lock, flags); +} + +static void rfkill_schedule_toggle(enum rfkill_type type) +{ + unsigned long flags; + + if (rfkill_is_epo_lock_active()) + return; + + spin_lock_irqsave(&rfkill_op_lock, flags); + if (!rfkill_op_pending) { + __set_bit(type, rfkill_sw_pending); + __change_bit(type, rfkill_sw_state); + rfkill_schedule_ratelimited(); + } + spin_unlock_irqrestore(&rfkill_op_lock, flags); +} + +static void rfkill_schedule_evsw_rfkillall(int state) +{ + if (state) + rfkill_schedule_global_op(rfkill_master_switch_op); + else + rfkill_schedule_global_op(RFKILL_GLOBAL_OP_EPO); +} + +static void rfkill_event(struct input_handle *handle, unsigned int type, + unsigned int code, int data) +{ + if (type == EV_KEY && data == 1) { + switch (code) { + case KEY_WLAN: + rfkill_schedule_toggle(RFKILL_TYPE_WLAN); + break; + case KEY_BLUETOOTH: + rfkill_schedule_toggle(RFKILL_TYPE_BLUETOOTH); + break; + case KEY_UWB: + rfkill_schedule_toggle(RFKILL_TYPE_UWB); + break; + case KEY_WIMAX: + rfkill_schedule_toggle(RFKILL_TYPE_WIMAX); + break; + } + } else if (type == EV_SW && code == SW_RFKILL_ALL) + rfkill_schedule_evsw_rfkillall(data); +} + +static int rfkill_connect(struct input_handler *handler, struct input_dev *dev, + const struct input_device_id *id) +{ + struct input_handle *handle; + int error; + + handle = kzalloc(sizeof(struct input_handle), GFP_KERNEL); + if (!handle) + return -ENOMEM; + + handle->dev = dev; + handle->handler = handler; + handle->name = "rfkill"; + + /* causes rfkill_start() to be called */ + error = input_register_handle(handle); + if (error) + goto err_free_handle; + + error = input_open_device(handle); + if (error) + goto err_unregister_handle; + + return 0; + + err_unregister_handle: + input_unregister_handle(handle); + err_free_handle: + kfree(handle); + return error; +} + +static void rfkill_start(struct input_handle *handle) +{ + /* + * Take event_lock to guard against configuration changes, we + * should be able to deal with concurrency with rfkill_event() + * just fine (which event_lock will also avoid). + */ + spin_lock_irq(&handle->dev->event_lock); + + if (test_bit(EV_SW, handle->dev->evbit) && + test_bit(SW_RFKILL_ALL, handle->dev->swbit)) + rfkill_schedule_evsw_rfkillall(test_bit(SW_RFKILL_ALL, + handle->dev->sw)); + + spin_unlock_irq(&handle->dev->event_lock); +} + +static void rfkill_disconnect(struct input_handle *handle) +{ + input_close_device(handle); + input_unregister_handle(handle); + kfree(handle); +} + +static const struct input_device_id rfkill_ids[] = { + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, + .evbit = { BIT_MASK(EV_KEY) }, + .keybit = { [BIT_WORD(KEY_WLAN)] = BIT_MASK(KEY_WLAN) }, + }, + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, + .evbit = { BIT_MASK(EV_KEY) }, + .keybit = { [BIT_WORD(KEY_BLUETOOTH)] = BIT_MASK(KEY_BLUETOOTH) }, + }, + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, + .evbit = { BIT_MASK(EV_KEY) }, + .keybit = { [BIT_WORD(KEY_UWB)] = BIT_MASK(KEY_UWB) }, + }, + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, + .evbit = { BIT_MASK(EV_KEY) }, + .keybit = { [BIT_WORD(KEY_WIMAX)] = BIT_MASK(KEY_WIMAX) }, + }, + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_SWBIT, + .evbit = { BIT(EV_SW) }, + .swbit = { [BIT_WORD(SW_RFKILL_ALL)] = BIT_MASK(SW_RFKILL_ALL) }, + }, + { } +}; + +static struct input_handler rfkill_handler = { + .name = "rfkill", + .event = rfkill_event, + .connect = rfkill_connect, + .start = rfkill_start, + .disconnect = rfkill_disconnect, + .id_table = rfkill_ids, +}; + +int __init rfkill_handler_init(void) +{ + switch (rfkill_master_switch_mode) { + case RFKILL_INPUT_MASTER_UNBLOCKALL: + rfkill_master_switch_op = RFKILL_GLOBAL_OP_UNBLOCK; + break; + case RFKILL_INPUT_MASTER_RESTORE: + rfkill_master_switch_op = RFKILL_GLOBAL_OP_RESTORE; + break; + case RFKILL_INPUT_MASTER_UNLOCK: + rfkill_master_switch_op = RFKILL_GLOBAL_OP_UNLOCK; + break; + default: + return -EINVAL; + } + + spin_lock_init(&rfkill_op_lock); + + /* Avoid delay at first schedule */ + rfkill_last_scheduled = + jiffies - msecs_to_jiffies(RFKILL_OPS_DELAY) - 1; + return input_register_handler(&rfkill_handler); +} + +void __exit rfkill_handler_exit(void) +{ + input_unregister_handler(&rfkill_handler); + cancel_delayed_work_sync(&rfkill_op_work); +} diff --git a/net/rfkill/rfkill-input.c b/net/rfkill/rfkill-input.c deleted file mode 100644 index 84efde97c5a..00000000000 --- a/net/rfkill/rfkill-input.c +++ /dev/null @@ -1,459 +0,0 @@ -/* - * Input layer to RF Kill interface connector - * - * Copyright (c) 2007 Dmitry Torokhov - */ - -/* - * 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/input.h> -#include <linux/slab.h> -#include <linux/workqueue.h> -#include <linux/init.h> -#include <linux/rfkill.h> -#include <linux/sched.h> - -#include "rfkill-input.h" - -MODULE_AUTHOR("Dmitry Torokhov <dtor@mail.ru>"); -MODULE_DESCRIPTION("Input layer to RF switch connector"); -MODULE_LICENSE("GPL"); - -enum rfkill_input_master_mode { - RFKILL_INPUT_MASTER_DONOTHING = 0, - RFKILL_INPUT_MASTER_RESTORE = 1, - RFKILL_INPUT_MASTER_UNBLOCKALL = 2, - RFKILL_INPUT_MASTER_MAX, /* marker */ -}; - -/* Delay (in ms) between consecutive switch ops */ -#define RFKILL_OPS_DELAY 200 - -static enum rfkill_input_master_mode rfkill_master_switch_mode = - RFKILL_INPUT_MASTER_UNBLOCKALL; -module_param_named(master_switch_mode, rfkill_master_switch_mode, uint, 0); -MODULE_PARM_DESC(master_switch_mode, - "SW_RFKILL_ALL ON should: 0=do nothing; 1=restore; 2=unblock all"); - -enum rfkill_global_sched_op { - RFKILL_GLOBAL_OP_EPO = 0, - RFKILL_GLOBAL_OP_RESTORE, - RFKILL_GLOBAL_OP_UNLOCK, - RFKILL_GLOBAL_OP_UNBLOCK, -}; - -/* - * Currently, the code marked with RFKILL_NEED_SWSET is inactive. - * If handling of EV_SW SW_WLAN/WWAN/BLUETOOTH/etc is needed in the - * future, when such events are added, that code will be necessary. - */ - -struct rfkill_task { - struct delayed_work dwork; - - /* ensures that task is serialized */ - struct mutex mutex; - - /* protects everything below */ - spinlock_t lock; - - /* pending regular switch operations (1=pending) */ - unsigned long sw_pending[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; - -#ifdef RFKILL_NEED_SWSET - /* set operation pending (1=pending) */ - unsigned long sw_setpending[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; - - /* desired state for pending set operation (1=unblock) */ - unsigned long sw_newstate[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; -#endif - - /* should the state be complemented (1=yes) */ - unsigned long sw_togglestate[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; - - bool global_op_pending; - enum rfkill_global_sched_op op; - - /* last time it was scheduled */ - unsigned long last_scheduled; -}; - -static void __rfkill_handle_global_op(enum rfkill_global_sched_op op) -{ - unsigned int i; - - switch (op) { - case RFKILL_GLOBAL_OP_EPO: - rfkill_epo(); - break; - case RFKILL_GLOBAL_OP_RESTORE: - rfkill_restore_states(); - break; - case RFKILL_GLOBAL_OP_UNLOCK: - rfkill_remove_epo_lock(); - break; - case RFKILL_GLOBAL_OP_UNBLOCK: - rfkill_remove_epo_lock(); - for (i = 0; i < RFKILL_TYPE_MAX; i++) - rfkill_switch_all(i, RFKILL_STATE_UNBLOCKED); - break; - default: - /* memory corruption or bug, fail safely */ - rfkill_epo(); - WARN(1, "Unknown requested operation %d! " - "rfkill Emergency Power Off activated\n", - op); - } -} - -#ifdef RFKILL_NEED_SWSET -static void __rfkill_handle_normal_op(const enum rfkill_type type, - const bool sp, const bool s, const bool c) -{ - enum rfkill_state state; - - if (sp) - state = (s) ? RFKILL_STATE_UNBLOCKED : - RFKILL_STATE_SOFT_BLOCKED; - else - state = rfkill_get_global_state(type); - - if (c) - state = rfkill_state_complement(state); - - rfkill_switch_all(type, state); -} -#else -static void __rfkill_handle_normal_op(const enum rfkill_type type, - const bool c) -{ - enum rfkill_state state; - - state = rfkill_get_global_state(type); - if (c) - state = rfkill_state_complement(state); - - rfkill_switch_all(type, state); -} -#endif - -static void rfkill_task_handler(struct work_struct *work) -{ - struct rfkill_task *task = container_of(work, - struct rfkill_task, dwork.work); - bool doit = true; - - mutex_lock(&task->mutex); - - spin_lock_irq(&task->lock); - while (doit) { - if (task->global_op_pending) { - enum rfkill_global_sched_op op = task->op; - task->global_op_pending = false; - memset(task->sw_pending, 0, sizeof(task->sw_pending)); - spin_unlock_irq(&task->lock); - - __rfkill_handle_global_op(op); - - /* make sure we do at least one pass with - * !task->global_op_pending */ - spin_lock_irq(&task->lock); - continue; - } else if (!rfkill_is_epo_lock_active()) { - unsigned int i = 0; - - while (!task->global_op_pending && - i < RFKILL_TYPE_MAX) { - if (test_and_clear_bit(i, task->sw_pending)) { - bool c; -#ifdef RFKILL_NEED_SWSET - bool sp, s; - sp = test_and_clear_bit(i, - task->sw_setpending); - s = test_bit(i, task->sw_newstate); -#endif - c = test_and_clear_bit(i, - task->sw_togglestate); - spin_unlock_irq(&task->lock); - -#ifdef RFKILL_NEED_SWSET - __rfkill_handle_normal_op(i, sp, s, c); -#else - __rfkill_handle_normal_op(i, c); -#endif - - spin_lock_irq(&task->lock); - } - i++; - } - } - doit = task->global_op_pending; - } - spin_unlock_irq(&task->lock); - - mutex_unlock(&task->mutex); -} - -static struct rfkill_task rfkill_task = { - .dwork = __DELAYED_WORK_INITIALIZER(rfkill_task.dwork, - rfkill_task_handler), - .mutex = __MUTEX_INITIALIZER(rfkill_task.mutex), - .lock = __SPIN_LOCK_UNLOCKED(rfkill_task.lock), -}; - -static unsigned long rfkill_ratelimit(const unsigned long last) -{ - const unsigned long delay = msecs_to_jiffies(RFKILL_OPS_DELAY); - return (time_after(jiffies, last + delay)) ? 0 : delay; -} - -static void rfkill_schedule_ratelimited(void) -{ - if (!delayed_work_pending(&rfkill_task.dwork)) { - schedule_delayed_work(&rfkill_task.dwork, - rfkill_ratelimit(rfkill_task.last_scheduled)); - rfkill_task.last_scheduled = jiffies; - } -} - -static void rfkill_schedule_global_op(enum rfkill_global_sched_op op) -{ - unsigned long flags; - - spin_lock_irqsave(&rfkill_task.lock, flags); - rfkill_task.op = op; - rfkill_task.global_op_pending = true; - if (op == RFKILL_GLOBAL_OP_EPO && !rfkill_is_epo_lock_active()) { - /* bypass the limiter for EPO */ - cancel_delayed_work(&rfkill_task.dwork); - schedule_delayed_work(&rfkill_task.dwork, 0); - rfkill_task.last_scheduled = jiffies; - } else - rfkill_schedule_ratelimited(); - spin_unlock_irqrestore(&rfkill_task.lock, flags); -} - -#ifdef RFKILL_NEED_SWSET -/* Use this if you need to add EV_SW SW_WLAN/WWAN/BLUETOOTH/etc handling */ - -static void rfkill_schedule_set(enum rfkill_type type, - enum rfkill_state desired_state) -{ - unsigned long flags; - - if (rfkill_is_epo_lock_active()) - return; - - spin_lock_irqsave(&rfkill_task.lock, flags); - if (!rfkill_task.global_op_pending) { - set_bit(type, rfkill_task.sw_pending); - set_bit(type, rfkill_task.sw_setpending); - clear_bit(type, rfkill_task.sw_togglestate); - if (desired_state) - set_bit(type, rfkill_task.sw_newstate); - else - clear_bit(type, rfkill_task.sw_newstate); - rfkill_schedule_ratelimited(); - } - spin_unlock_irqrestore(&rfkill_task.lock, flags); -} -#endif - -static void rfkill_schedule_toggle(enum rfkill_type type) -{ - unsigned long flags; - - if (rfkill_is_epo_lock_active()) - return; - - spin_lock_irqsave(&rfkill_task.lock, flags); - if (!rfkill_task.global_op_pending) { - set_bit(type, rfkill_task.sw_pending); - change_bit(type, rfkill_task.sw_togglestate); - rfkill_schedule_ratelimited(); - } - spin_unlock_irqrestore(&rfkill_task.lock, flags); -} - -static void rfkill_schedule_evsw_rfkillall(int state) -{ - if (state) { - switch (rfkill_master_switch_mode) { - case RFKILL_INPUT_MASTER_UNBLOCKALL: - rfkill_schedule_global_op(RFKILL_GLOBAL_OP_UNBLOCK); - break; - case RFKILL_INPUT_MASTER_RESTORE: - rfkill_schedule_global_op(RFKILL_GLOBAL_OP_RESTORE); - break; - case RFKILL_INPUT_MASTER_DONOTHING: - rfkill_schedule_global_op(RFKILL_GLOBAL_OP_UNLOCK); - break; - default: - /* memory corruption or driver bug! fail safely */ - rfkill_schedule_global_op(RFKILL_GLOBAL_OP_EPO); - WARN(1, "Unknown rfkill_master_switch_mode (%d), " - "driver bug or memory corruption detected!\n", - rfkill_master_switch_mode); - break; - } - } else - rfkill_schedule_global_op(RFKILL_GLOBAL_OP_EPO); -} - -static void rfkill_event(struct input_handle *handle, unsigned int type, - unsigned int code, int data) -{ - if (type == EV_KEY && data == 1) { - enum rfkill_type t; - - switch (code) { - case KEY_WLAN: - t = RFKILL_TYPE_WLAN; - break; - case KEY_BLUETOOTH: - t = RFKILL_TYPE_BLUETOOTH; - break; - case KEY_UWB: - t = RFKILL_TYPE_UWB; - break; - case KEY_WIMAX: - t = RFKILL_TYPE_WIMAX; - break; - default: - return; - } - rfkill_schedule_toggle(t); - return; - } else if (type == EV_SW) { - switch (code) { - case SW_RFKILL_ALL: - rfkill_schedule_evsw_rfkillall(data); - return; - default: - return; - } - } -} - -static int rfkill_connect(struct input_handler *handler, struct input_dev *dev, - const struct input_device_id *id) -{ - struct input_handle *handle; - int error; - - handle = kzalloc(sizeof(struct input_handle), GFP_KERNEL); - if (!handle) - return -ENOMEM; - - handle->dev = dev; - handle->handler = handler; - handle->name = "rfkill"; - - /* causes rfkill_start() to be called */ - error = input_register_handle(handle); - if (error) - goto err_free_handle; - - error = input_open_device(handle); - if (error) - goto err_unregister_handle; - - return 0; - - err_unregister_handle: - input_unregister_handle(handle); - err_free_handle: - kfree(handle); - return error; -} - -static void rfkill_start(struct input_handle *handle) -{ - /* Take event_lock to guard against configuration changes, we - * should be able to deal with concurrency with rfkill_event() - * just fine (which event_lock will also avoid). */ - spin_lock_irq(&handle->dev->event_lock); - - if (test_bit(EV_SW, handle->dev->evbit)) { - if (test_bit(SW_RFKILL_ALL, handle->dev->swbit)) - rfkill_schedule_evsw_rfkillall(test_bit(SW_RFKILL_ALL, - handle->dev->sw)); - /* add resync for further EV_SW events here */ - } - - spin_unlock_irq(&handle->dev->event_lock); -} - -static void rfkill_disconnect(struct input_handle *handle) -{ - input_close_device(handle); - input_unregister_handle(handle); - kfree(handle); -} - -static const struct input_device_id rfkill_ids[] = { - { - .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, - .evbit = { BIT_MASK(EV_KEY) }, - .keybit = { [BIT_WORD(KEY_WLAN)] = BIT_MASK(KEY_WLAN) }, - }, - { - .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, - .evbit = { BIT_MASK(EV_KEY) }, - .keybit = { [BIT_WORD(KEY_BLUETOOTH)] = BIT_MASK(KEY_BLUETOOTH) }, - }, - { - .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, - .evbit = { BIT_MASK(EV_KEY) }, - .keybit = { [BIT_WORD(KEY_UWB)] = BIT_MASK(KEY_UWB) }, - }, - { - .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_KEYBIT, - .evbit = { BIT_MASK(EV_KEY) }, - .keybit = { [BIT_WORD(KEY_WIMAX)] = BIT_MASK(KEY_WIMAX) }, - }, - { - .flags = INPUT_DEVICE_ID_MATCH_EVBIT | INPUT_DEVICE_ID_MATCH_SWBIT, - .evbit = { BIT(EV_SW) }, - .swbit = { [BIT_WORD(SW_RFKILL_ALL)] = BIT_MASK(SW_RFKILL_ALL) }, - }, - { } -}; - -static struct input_handler rfkill_handler = { - .event = rfkill_event, - .connect = rfkill_connect, - .disconnect = rfkill_disconnect, - .start = rfkill_start, - .name = "rfkill", - .id_table = rfkill_ids, -}; - -static int __init rfkill_handler_init(void) -{ - if (rfkill_master_switch_mode >= RFKILL_INPUT_MASTER_MAX) - return -EINVAL; - - /* - * The penalty to not doing this is a possible RFKILL_OPS_DELAY delay - * at the first use. Acceptable, but if we can avoid it, why not? - */ - rfkill_task.last_scheduled = - jiffies - msecs_to_jiffies(RFKILL_OPS_DELAY) - 1; - return input_register_handler(&rfkill_handler); -} - -static void __exit rfkill_handler_exit(void) -{ - input_unregister_handler(&rfkill_handler); - cancel_delayed_work_sync(&rfkill_task.dwork); - rfkill_remove_epo_lock(); -} - -module_init(rfkill_handler_init); -module_exit(rfkill_handler_exit); diff --git a/net/rfkill/rfkill.c b/net/rfkill/rfkill.c deleted file mode 100644 index 3eaa39403c1..00000000000 --- a/net/rfkill/rfkill.c +++ /dev/null @@ -1,882 +0,0 @@ -/* - * Copyright (C) 2006 - 2007 Ivo van Doorn - * Copyright (C) 2007 Dmitry Torokhov - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * 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., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/workqueue.h> -#include <linux/capability.h> -#include <linux/list.h> -#include <linux/mutex.h> -#include <linux/rfkill.h> - -/* Get declaration of rfkill_switch_all() to shut up sparse. */ -#include "rfkill-input.h" - - -MODULE_AUTHOR("Ivo van Doorn <IvDoorn@gmail.com>"); -MODULE_VERSION("1.0"); -MODULE_DESCRIPTION("RF switch support"); -MODULE_LICENSE("GPL"); - -static LIST_HEAD(rfkill_list); /* list of registered rf switches */ -static DEFINE_MUTEX(rfkill_global_mutex); - -static unsigned int rfkill_default_state = RFKILL_STATE_UNBLOCKED; -module_param_named(default_state, rfkill_default_state, uint, 0444); -MODULE_PARM_DESC(default_state, - "Default initial state for all radio types, 0 = radio off"); - -struct rfkill_gsw_state { - enum rfkill_state current_state; - enum rfkill_state default_state; -}; - -static struct rfkill_gsw_state rfkill_global_states[RFKILL_TYPE_MAX]; -static unsigned long rfkill_states_lockdflt[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; -static bool rfkill_epo_lock_active; - - -#ifdef CONFIG_RFKILL_LEDS -static void rfkill_led_trigger(struct rfkill *rfkill, - enum rfkill_state state) -{ - struct led_trigger *led = &rfkill->led_trigger; - - if (!led->name) - return; - if (state != RFKILL_STATE_UNBLOCKED) - led_trigger_event(led, LED_OFF); - else - led_trigger_event(led, LED_FULL); -} - -static void rfkill_led_trigger_activate(struct led_classdev *led) -{ - struct rfkill *rfkill = container_of(led->trigger, - struct rfkill, led_trigger); - - rfkill_led_trigger(rfkill, rfkill->state); -} -#endif /* CONFIG_RFKILL_LEDS */ - -static void rfkill_uevent(struct rfkill *rfkill) -{ - kobject_uevent(&rfkill->dev.kobj, KOBJ_CHANGE); -} - -static void update_rfkill_state(struct rfkill *rfkill) -{ - enum rfkill_state newstate, oldstate; - - if (rfkill->get_state) { - mutex_lock(&rfkill->mutex); - if (!rfkill->get_state(rfkill->data, &newstate)) { - oldstate = rfkill->state; - rfkill->state = newstate; - if (oldstate != newstate) - rfkill_uevent(rfkill); - } - mutex_unlock(&rfkill->mutex); - } -} - -/** - * rfkill_toggle_radio - wrapper for toggle_radio hook - * @rfkill: the rfkill struct to use - * @force: calls toggle_radio even if cache says it is not needed, - * and also makes sure notifications of the state will be - * sent even if it didn't change - * @state: the new state to call toggle_radio() with - * - * Calls rfkill->toggle_radio, enforcing the API for toggle_radio - * calls and handling all the red tape such as issuing notifications - * if the call is successful. - * - * Suspended devices are not touched at all, and -EAGAIN is returned. - * - * Note that the @force parameter cannot override a (possibly cached) - * state of RFKILL_STATE_HARD_BLOCKED. Any device making use of - * RFKILL_STATE_HARD_BLOCKED implements either get_state() or - * rfkill_force_state(), so the cache either is bypassed or valid. - * - * Note that we do call toggle_radio for RFKILL_STATE_SOFT_BLOCKED - * even if the radio is in RFKILL_STATE_HARD_BLOCKED state, so as to - * give the driver a hint that it should double-BLOCK the transmitter. - * - * Caller must have acquired rfkill->mutex. - */ -static int rfkill_toggle_radio(struct rfkill *rfkill, - enum rfkill_state state, - int force) -{ - int retval = 0; - enum rfkill_state oldstate, newstate; - - if (unlikely(rfkill->dev.power.power_state.event & PM_EVENT_SLEEP)) - return -EBUSY; - - oldstate = rfkill->state; - - if (rfkill->get_state && !force && - !rfkill->get_state(rfkill->data, &newstate)) - rfkill->state = newstate; - - switch (state) { - case RFKILL_STATE_HARD_BLOCKED: - /* typically happens when refreshing hardware state, - * such as on resume */ - state = RFKILL_STATE_SOFT_BLOCKED; - break; - case RFKILL_STATE_UNBLOCKED: - /* force can't override this, only rfkill_force_state() can */ - if (rfkill->state == RFKILL_STATE_HARD_BLOCKED) - return -EPERM; - break; - case RFKILL_STATE_SOFT_BLOCKED: - /* nothing to do, we want to give drivers the hint to double - * BLOCK even a transmitter that is already in state - * RFKILL_STATE_HARD_BLOCKED */ - break; - default: - WARN(1, KERN_WARNING - "rfkill: illegal state %d passed as parameter " - "to rfkill_toggle_radio\n", state); - return -EINVAL; - } - - if (force || state != rfkill->state) { - retval = rfkill->toggle_radio(rfkill->data, state); - /* never allow a HARD->SOFT downgrade! */ - if (!retval && rfkill->state != RFKILL_STATE_HARD_BLOCKED) - rfkill->state = state; - } - - if (force || rfkill->state != oldstate) - rfkill_uevent(rfkill); - - return retval; -} - -/** - * __rfkill_switch_all - Toggle state of all switches of given type - * @type: type of interfaces to be affected - * @state: the new state - * - * This function toggles the state of all switches of given type, - * unless a specific switch is claimed by userspace (in which case, - * that switch is left alone) or suspended. - * - * Caller must have acquired rfkill_global_mutex. - */ -static void __rfkill_switch_all(const enum rfkill_type type, - const enum rfkill_state state) -{ - struct rfkill *rfkill; - - if (WARN((state >= RFKILL_STATE_MAX || type >= RFKILL_TYPE_MAX), - KERN_WARNING - "rfkill: illegal state %d or type %d " - "passed as parameter to __rfkill_switch_all\n", - state, type)) - return; - - rfkill_global_states[type].current_state = state; - list_for_each_entry(rfkill, &rfkill_list, node) { - if ((!rfkill->user_claim) && (rfkill->type == type)) { - mutex_lock(&rfkill->mutex); - rfkill_toggle_radio(rfkill, state, 0); - mutex_unlock(&rfkill->mutex); - } - } -} - -/** - * rfkill_switch_all - Toggle state of all switches of given type - * @type: type of interfaces to be affected - * @state: the new state - * - * Acquires rfkill_global_mutex and calls __rfkill_switch_all(@type, @state). - * Please refer to __rfkill_switch_all() for details. - * - * Does nothing if the EPO lock is active. - */ -void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state) -{ - mutex_lock(&rfkill_global_mutex); - if (!rfkill_epo_lock_active) - __rfkill_switch_all(type, state); - mutex_unlock(&rfkill_global_mutex); -} -EXPORT_SYMBOL(rfkill_switch_all); - -/** - * rfkill_epo - emergency power off all transmitters - * - * This kicks all non-suspended rfkill devices to RFKILL_STATE_SOFT_BLOCKED, - * ignoring everything in its path but rfkill_global_mutex and rfkill->mutex. - * - * The global state before the EPO is saved and can be restored later - * using rfkill_restore_states(). - */ -void rfkill_epo(void) -{ - struct rfkill *rfkill; - int i; - - mutex_lock(&rfkill_global_mutex); - - rfkill_epo_lock_active = true; - list_for_each_entry(rfkill, &rfkill_list, node) { - mutex_lock(&rfkill->mutex); - rfkill_toggle_radio(rfkill, RFKILL_STATE_SOFT_BLOCKED, 1); - mutex_unlock(&rfkill->mutex); - } - for (i = 0; i < RFKILL_TYPE_MAX; i++) { - rfkill_global_states[i].default_state = - rfkill_global_states[i].current_state; - rfkill_global_states[i].current_state = - RFKILL_STATE_SOFT_BLOCKED; - } - mutex_unlock(&rfkill_global_mutex); -} -EXPORT_SYMBOL_GPL(rfkill_epo); - -/** - * rfkill_restore_states - restore global states - * - * Restore (and sync switches to) the global state from the - * states in rfkill_default_states. This can undo the effects of - * a call to rfkill_epo(). - */ -void rfkill_restore_states(void) -{ - int i; - - mutex_lock(&rfkill_global_mutex); - - rfkill_epo_lock_active = false; - for (i = 0; i < RFKILL_TYPE_MAX; i++) - __rfkill_switch_all(i, rfkill_global_states[i].default_state); - mutex_unlock(&rfkill_global_mutex); -} -EXPORT_SYMBOL_GPL(rfkill_restore_states); - -/** - * rfkill_remove_epo_lock - unlock state changes - * - * Used by rfkill-input manually unlock state changes, when - * the EPO switch is deactivated. - */ -void rfkill_remove_epo_lock(void) -{ - mutex_lock(&rfkill_global_mutex); - rfkill_epo_lock_active = false; - mutex_unlock(&rfkill_global_mutex); -} -EXPORT_SYMBOL_GPL(rfkill_remove_epo_lock); - -/** - * rfkill_is_epo_lock_active - returns true EPO is active - * - * Returns 0 (false) if there is NOT an active EPO contidion, - * and 1 (true) if there is an active EPO contition, which - * locks all radios in one of the BLOCKED states. - * - * Can be called in atomic context. - */ -bool rfkill_is_epo_lock_active(void) -{ - return rfkill_epo_lock_active; -} -EXPORT_SYMBOL_GPL(rfkill_is_epo_lock_active); - -/** - * rfkill_get_global_state - returns global state for a type - * @type: the type to get the global state of - * - * Returns the current global state for a given wireless - * device type. - */ -enum rfkill_state rfkill_get_global_state(const enum rfkill_type type) -{ - return rfkill_global_states[type].current_state; -} -EXPORT_SYMBOL_GPL(rfkill_get_global_state); - -/** - * rfkill_force_state - Force the internal rfkill radio state - * @rfkill: pointer to the rfkill class to modify. - * @state: the current radio state the class should be forced to. - * - * This function updates the internal state of the radio cached - * by the rfkill class. It should be used when the driver gets - * a notification by the firmware/hardware of the current *real* - * state of the radio rfkill switch. - * - * Devices which are subject to external changes on their rfkill - * state (such as those caused by a hardware rfkill line) MUST - * have their driver arrange to call rfkill_force_state() as soon - * as possible after such a change. - * - * This function may not be called from an atomic context. - */ -int rfkill_force_state(struct rfkill *rfkill, enum rfkill_state state) -{ - enum rfkill_state oldstate; - - BUG_ON(!rfkill); - if (WARN((state >= RFKILL_STATE_MAX), - KERN_WARNING - "rfkill: illegal state %d passed as parameter " - "to rfkill_force_state\n", state)) - return -EINVAL; - - mutex_lock(&rfkill->mutex); - - oldstate = rfkill->state; - rfkill->state = state; - - if (state != oldstate) - rfkill_uevent(rfkill); - - mutex_unlock(&rfkill->mutex); - - return 0; -} -EXPORT_SYMBOL(rfkill_force_state); - -static ssize_t rfkill_name_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct rfkill *rfkill = to_rfkill(dev); - - return sprintf(buf, "%s\n", rfkill->name); -} - -static const char *rfkill_get_type_str(enum rfkill_type type) -{ - switch (type) { - case RFKILL_TYPE_WLAN: - return "wlan"; - case RFKILL_TYPE_BLUETOOTH: - return "bluetooth"; - case RFKILL_TYPE_UWB: - return "ultrawideband"; - case RFKILL_TYPE_WIMAX: - return "wimax"; - case RFKILL_TYPE_WWAN: - return "wwan"; - default: - BUG(); - } -} - -static ssize_t rfkill_type_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct rfkill *rfkill = to_rfkill(dev); - - return sprintf(buf, "%s\n", rfkill_get_type_str(rfkill->type)); -} - -static ssize_t rfkill_state_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct rfkill *rfkill = to_rfkill(dev); - - update_rfkill_state(rfkill); - return sprintf(buf, "%d\n", rfkill->state); -} - -static ssize_t rfkill_state_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct rfkill *rfkill = to_rfkill(dev); - unsigned long state; - int error; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - error = strict_strtoul(buf, 0, &state); - if (error) - return error; - - /* RFKILL_STATE_HARD_BLOCKED is illegal here... */ - if (state != RFKILL_STATE_UNBLOCKED && - state != RFKILL_STATE_SOFT_BLOCKED) - return -EINVAL; - - error = mutex_lock_killable(&rfkill->mutex); - if (error) - return error; - - if (!rfkill_epo_lock_active) - error = rfkill_toggle_radio(rfkill, state, 0); - else - error = -EPERM; - - mutex_unlock(&rfkill->mutex); - - return error ? error : count; -} - -static ssize_t rfkill_claim_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct rfkill *rfkill = to_rfkill(dev); - - return sprintf(buf, "%d\n", rfkill->user_claim); -} - -static ssize_t rfkill_claim_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct rfkill *rfkill = to_rfkill(dev); - unsigned long claim_tmp; - bool claim; - int error; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (rfkill->user_claim_unsupported) - return -EOPNOTSUPP; - - error = strict_strtoul(buf, 0, &claim_tmp); - if (error) - return error; - claim = !!claim_tmp; - - /* - * Take the global lock to make sure the kernel is not in - * the middle of rfkill_switch_all - */ - error = mutex_lock_killable(&rfkill_global_mutex); - if (error) - return error; - - if (rfkill->user_claim != claim) { - if (!claim && !rfkill_epo_lock_active) { - mutex_lock(&rfkill->mutex); - rfkill_toggle_radio(rfkill, - rfkill_global_states[rfkill->type].current_state, - 0); - mutex_unlock(&rfkill->mutex); - } - rfkill->user_claim = claim; - } - - mutex_unlock(&rfkill_global_mutex); - - return error ? error : count; -} - -static struct device_attribute rfkill_dev_attrs[] = { - __ATTR(name, S_IRUGO, rfkill_name_show, NULL), - __ATTR(type, S_IRUGO, rfkill_type_show, NULL), - __ATTR(state, S_IRUGO|S_IWUSR, rfkill_state_show, rfkill_state_store), - __ATTR(claim, S_IRUGO|S_IWUSR, rfkill_claim_show, rfkill_claim_store), - __ATTR_NULL -}; - -static void rfkill_release(struct device *dev) -{ - struct rfkill *rfkill = to_rfkill(dev); - - kfree(rfkill); - module_put(THIS_MODULE); -} - -#ifdef CONFIG_PM -static int rfkill_suspend(struct device *dev, pm_message_t state) -{ - struct rfkill *rfkill = to_rfkill(dev); - - /* mark class device as suspended */ - if (dev->power.power_state.event != state.event) - dev->power.power_state = state; - - /* store state for the resume handler */ - rfkill->state_for_resume = rfkill->state; - - return 0; -} - -static int rfkill_resume(struct device *dev) -{ - struct rfkill *rfkill = to_rfkill(dev); - enum rfkill_state newstate; - - if (dev->power.power_state.event != PM_EVENT_ON) { - mutex_lock(&rfkill->mutex); - - dev->power.power_state.event = PM_EVENT_ON; - - /* - * rfkill->state could have been modified before we got - * called, and won't be updated by rfkill_toggle_radio() - * in force mode. Sync it FIRST. - */ - if (rfkill->get_state && - !rfkill->get_state(rfkill->data, &newstate)) - rfkill->state = newstate; - - /* - * If we are under EPO, kick transmitter offline, - * otherwise restore to pre-suspend state. - * - * Issue a notification in any case - */ - rfkill_toggle_radio(rfkill, - rfkill_epo_lock_active ? - RFKILL_STATE_SOFT_BLOCKED : - rfkill->state_for_resume, - 1); - - mutex_unlock(&rfkill->mutex); - } - - return 0; -} -#else -#define rfkill_suspend NULL -#define rfkill_resume NULL -#endif - -static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - struct rfkill *rfkill = to_rfkill(dev); - int error; - - error = add_uevent_var(env, "RFKILL_NAME=%s", rfkill->name); - if (error) - return error; - error = add_uevent_var(env, "RFKILL_TYPE=%s", - rfkill_get_type_str(rfkill->type)); - if (error) - return error; - error = add_uevent_var(env, "RFKILL_STATE=%d", rfkill->state); - return error; -} - -static struct class rfkill_class = { - .name = "rfkill", - .dev_release = rfkill_release, - .dev_attrs = rfkill_dev_attrs, - .suspend = rfkill_suspend, - .resume = rfkill_resume, - .dev_uevent = rfkill_dev_uevent, -}; - -static int rfkill_check_duplicity(const struct rfkill *rfkill) -{ - struct rfkill *p; - unsigned long seen[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; - - memset(seen, 0, sizeof(seen)); - - list_for_each_entry(p, &rfkill_list, node) { - if (WARN((p == rfkill), KERN_WARNING - "rfkill: illegal attempt to register " - "an already registered rfkill struct\n")) - return -EEXIST; - set_bit(p->type, seen); - } - - /* 0: first switch of its kind */ - return (test_bit(rfkill->type, seen)) ? 1 : 0; -} - -static int rfkill_add_switch(struct rfkill *rfkill) -{ - int error; - - mutex_lock(&rfkill_global_mutex); - - error = rfkill_check_duplicity(rfkill); - if (error < 0) - goto unlock_out; - - if (!error) { - /* lock default after first use */ - set_bit(rfkill->type, rfkill_states_lockdflt); - rfkill_global_states[rfkill->type].current_state = - rfkill_global_states[rfkill->type].default_state; - } - - rfkill_toggle_radio(rfkill, - rfkill_global_states[rfkill->type].current_state, - 0); - - list_add_tail(&rfkill->node, &rfkill_list); - - error = 0; -unlock_out: - mutex_unlock(&rfkill_global_mutex); - - return error; -} - -static void rfkill_remove_switch(struct rfkill *rfkill) -{ - mutex_lock(&rfkill_global_mutex); - list_del_init(&rfkill->node); - mutex_unlock(&rfkill_global_mutex); - - mutex_lock(&rfkill->mutex); - rfkill_toggle_radio(rfkill, RFKILL_STATE_SOFT_BLOCKED, 1); - mutex_unlock(&rfkill->mutex); -} - -/** - * rfkill_allocate - allocate memory for rfkill structure. - * @parent: device that has rf switch on it - * @type: type of the switch (RFKILL_TYPE_*) - * - * This function should be called by the network driver when it needs - * rfkill structure. Once the structure is allocated the driver should - * finish its initialization by setting the name, private data, enable_radio - * and disable_radio methods and then register it with rfkill_register(). - * - * NOTE: If registration fails the structure shoudl be freed by calling - * rfkill_free() otherwise rfkill_unregister() should be used. - */ -struct rfkill * __must_check rfkill_allocate(struct device *parent, - enum rfkill_type type) -{ - struct rfkill *rfkill; - struct device *dev; - - if (WARN((type >= RFKILL_TYPE_MAX), - KERN_WARNING - "rfkill: illegal type %d passed as parameter " - "to rfkill_allocate\n", type)) - return NULL; - - rfkill = kzalloc(sizeof(struct rfkill), GFP_KERNEL); - if (!rfkill) - return NULL; - - mutex_init(&rfkill->mutex); - INIT_LIST_HEAD(&rfkill->node); - rfkill->type = type; - - dev = &rfkill->dev; - dev->class = &rfkill_class; - dev->parent = parent; - device_initialize(dev); - - __module_get(THIS_MODULE); - - return rfkill; -} -EXPORT_SYMBOL(rfkill_allocate); - -/** - * rfkill_free - Mark rfkill structure for deletion - * @rfkill: rfkill structure to be destroyed - * - * Decrements reference count of the rfkill structure so it is destroyed. - * Note that rfkill_free() should _not_ be called after rfkill_unregister(). - */ -void rfkill_free(struct rfkill *rfkill) -{ - if (rfkill) - put_device(&rfkill->dev); -} -EXPORT_SYMBOL(rfkill_free); - -static void rfkill_led_trigger_register(struct rfkill *rfkill) -{ -#ifdef CONFIG_RFKILL_LEDS - int error; - - if (!rfkill->led_trigger.name) - rfkill->led_trigger.name = dev_name(&rfkill->dev); - if (!rfkill->led_trigger.activate) - rfkill->led_trigger.activate = rfkill_led_trigger_activate; - error = led_trigger_register(&rfkill->led_trigger); - if (error) - rfkill->led_trigger.name = NULL; -#endif /* CONFIG_RFKILL_LEDS */ -} - -static void rfkill_led_trigger_unregister(struct rfkill *rfkill) -{ -#ifdef CONFIG_RFKILL_LEDS - if (rfkill->led_trigger.name) { - led_trigger_unregister(&rfkill->led_trigger); - rfkill->led_trigger.name = NULL; - } -#endif -} - -/** - * rfkill_register - Register a rfkill structure. - * @rfkill: rfkill structure to be registered - * - * This function should be called by the network driver when the rfkill - * structure needs to be registered. Immediately from registration the - * switch driver should be able to service calls to toggle_radio. - */ -int __must_check rfkill_register(struct rfkill *rfkill) -{ - static atomic_t rfkill_no = ATOMIC_INIT(0); - struct device *dev = &rfkill->dev; - int error; - - if (WARN((!rfkill || !rfkill->toggle_radio || - rfkill->type >= RFKILL_TYPE_MAX || - rfkill->state >= RFKILL_STATE_MAX), - KERN_WARNING - "rfkill: attempt to register a " - "badly initialized rfkill struct\n")) - return -EINVAL; - - dev_set_name(dev, "rfkill%ld", (long)atomic_inc_return(&rfkill_no) - 1); - - rfkill_led_trigger_register(rfkill); - - error = rfkill_add_switch(rfkill); - if (error) { - rfkill_led_trigger_unregister(rfkill); - return error; - } - - error = device_add(dev); - if (error) { - rfkill_remove_switch(rfkill); - rfkill_led_trigger_unregister(rfkill); - return error; - } - - return 0; -} -EXPORT_SYMBOL(rfkill_register); - -/** - * rfkill_unregister - Unregister a rfkill structure. - * @rfkill: rfkill structure to be unregistered - * - * This function should be called by the network driver during device - * teardown to destroy rfkill structure. Note that rfkill_free() should - * _not_ be called after rfkill_unregister(). - */ -void rfkill_unregister(struct rfkill *rfkill) -{ - BUG_ON(!rfkill); - device_del(&rfkill->dev); - rfkill_remove_switch(rfkill); - rfkill_led_trigger_unregister(rfkill); - put_device(&rfkill->dev); -} -EXPORT_SYMBOL(rfkill_unregister); - -/** - * rfkill_set_default - set initial value for a switch type - * @type - the type of switch to set the default state of - * @state - the new default state for that group of switches - * - * Sets the initial state rfkill should use for a given type. - * The following initial states are allowed: RFKILL_STATE_SOFT_BLOCKED - * and RFKILL_STATE_UNBLOCKED. - * - * This function is meant to be used by platform drivers for platforms - * that can save switch state across power down/reboot. - * - * The default state for each switch type can be changed exactly once. - * After a switch of that type is registered, the default state cannot - * be changed anymore. This guards against multiple drivers it the - * same platform trying to set the initial switch default state, which - * is not allowed. - * - * Returns -EPERM if the state has already been set once or is in use, - * so drivers likely want to either ignore or at most printk(KERN_NOTICE) - * if this function returns -EPERM. - * - * Returns 0 if the new default state was set, or an error if it - * could not be set. - */ -int rfkill_set_default(enum rfkill_type type, enum rfkill_state state) -{ - int error; - - if (WARN((type >= RFKILL_TYPE_MAX || - (state != RFKILL_STATE_SOFT_BLOCKED && - state != RFKILL_STATE_UNBLOCKED)), - KERN_WARNING - "rfkill: illegal state %d or type %d passed as " - "parameter to rfkill_set_default\n", state, type)) - return -EINVAL; - - mutex_lock(&rfkill_global_mutex); - - if (!test_and_set_bit(type, rfkill_states_lockdflt)) { - rfkill_global_states[type].default_state = state; - rfkill_global_states[type].current_state = state; - error = 0; - } else - error = -EPERM; - - mutex_unlock(&rfkill_global_mutex); - return error; -} -EXPORT_SYMBOL_GPL(rfkill_set_default); - -/* - * Rfkill module initialization/deinitialization. - */ -static int __init rfkill_init(void) -{ - int error; - int i; - - /* RFKILL_STATE_HARD_BLOCKED is illegal here... */ - if (rfkill_default_state != RFKILL_STATE_SOFT_BLOCKED && - rfkill_default_state != RFKILL_STATE_UNBLOCKED) - return -EINVAL; - - for (i = 0; i < RFKILL_TYPE_MAX; i++) - rfkill_global_states[i].default_state = rfkill_default_state; - - error = class_register(&rfkill_class); - if (error) { - printk(KERN_ERR "rfkill: unable to register rfkill class\n"); - return error; - } - - return 0; -} - -static void __exit rfkill_exit(void) -{ - class_unregister(&rfkill_class); -} - -subsys_initcall(rfkill_init); -module_exit(rfkill_exit); diff --git a/net/rfkill/rfkill-input.h b/net/rfkill/rfkill.h index fe8df6b5b93..d1117cb6e4d 100644 --- a/net/rfkill/rfkill-input.h +++ b/net/rfkill/rfkill.h @@ -1,5 +1,6 @@ /* * Copyright (C) 2007 Ivo van Doorn + * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> */ /* @@ -11,11 +12,16 @@ #ifndef __RFKILL_INPUT_H #define __RFKILL_INPUT_H -void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state); +/* core code */ +void rfkill_switch_all(const enum rfkill_type type, bool blocked); void rfkill_epo(void); void rfkill_restore_states(void); void rfkill_remove_epo_lock(void); bool rfkill_is_epo_lock_active(void); -enum rfkill_state rfkill_get_global_state(const enum rfkill_type type); +bool rfkill_get_global_sw_state(const enum rfkill_type type); + +/* input handler */ +int rfkill_handler_init(void); +void rfkill_handler_exit(void); #endif /* __RFKILL_INPUT_H */ diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 877a7f65f70..e5f478ca3d6 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -92,23 +92,21 @@ static void rose_set_lockdep_key(struct net_device *dev) /* * Convert a ROSE address into text. */ -const char *rose2asc(const rose_address *addr) +char *rose2asc(char *buf, const rose_address *addr) { - static char buffer[11]; - if (addr->rose_addr[0] == 0x00 && addr->rose_addr[1] == 0x00 && addr->rose_addr[2] == 0x00 && addr->rose_addr[3] == 0x00 && addr->rose_addr[4] == 0x00) { - strcpy(buffer, "*"); + strcpy(buf, "*"); } else { - sprintf(buffer, "%02X%02X%02X%02X%02X", addr->rose_addr[0] & 0xFF, + sprintf(buf, "%02X%02X%02X%02X%02X", addr->rose_addr[0] & 0xFF, addr->rose_addr[1] & 0xFF, addr->rose_addr[2] & 0xFF, addr->rose_addr[3] & 0xFF, addr->rose_addr[4] & 0xFF); } - return buffer; + return buf; } /* @@ -356,8 +354,7 @@ void rose_destroy_socket(struct sock *sk) kfree_skb(skb); } - if (atomic_read(&sk->sk_wmem_alloc) || - atomic_read(&sk->sk_rmem_alloc)) { + if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ setup_timer(&sk->sk_timer, rose_destroy_timer, (unsigned long)sk); @@ -957,6 +954,7 @@ static int rose_getname(struct socket *sock, struct sockaddr *uaddr, struct rose_sock *rose = rose_sk(sk); int n; + memset(srose, 0, sizeof(*srose)); if (peer != 0) { if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; @@ -1310,7 +1308,8 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) switch (cmd) { case TIOCOUTQ: { long amount; - amount = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + + amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; return put_user(amount, (unsigned int __user *) argp); @@ -1437,7 +1436,7 @@ static void rose_info_stop(struct seq_file *seq, void *v) static int rose_info_show(struct seq_file *seq, void *v) { - char buf[11]; + char buf[11], rsbuf[11]; if (v == SEQ_START_TOKEN) seq_puts(seq, @@ -1455,8 +1454,8 @@ static int rose_info_show(struct seq_file *seq, void *v) devname = dev->name; seq_printf(seq, "%-10s %-9s ", - rose2asc(&rose->dest_addr), - ax2asc(buf, &rose->dest_call)); + rose2asc(rsbuf, &rose->dest_addr), + ax2asc(buf, &rose->dest_call)); if (ax25cmp(&rose->source_call, &null_ax25_address) == 0) callsign = "??????-?"; @@ -1465,7 +1464,7 @@ static int rose_info_show(struct seq_file *seq, void *v) seq_printf(seq, "%-10s %-9s %-5s %3.3X %05d %d %d %d %d %3lu %3lu %3lu %3lu %3lu %3lu/%03lu %5d %5d %ld\n", - rose2asc(&rose->source_addr), + rose2asc(rsbuf, &rose->source_addr), callsign, devname, rose->lci & 0x0FFF, @@ -1481,8 +1480,8 @@ static int rose_info_show(struct seq_file *seq, void *v) rose->hb / HZ, ax25_display_timer(&rose->idletimer) / (60 * HZ), rose->idle / (60 * HZ), - atomic_read(&s->sk_wmem_alloc), - atomic_read(&s->sk_rmem_alloc), + sk_wmem_alloc_get(s), + sk_rmem_alloc_get(s), s->sk_socket ? SOCK_INODE(s->sk_socket)->i_ino : 0L); } diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c index 7dcf2569613..389d6e0d774 100644 --- a/net/rose/rose_dev.c +++ b/net/rose/rose_dev.c @@ -137,7 +137,7 @@ static int rose_xmit(struct sk_buff *skb, struct net_device *dev) if (!netif_running(dev)) { printk(KERN_ERR "ROSE: rose_xmit - called when iface is down\n"); - return 1; + return NETDEV_TX_BUSY; } dev_kfree_skb(skb); stats->tx_errors++; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index a81066a1010..9478d9b3d97 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -1104,6 +1104,7 @@ static void rose_node_stop(struct seq_file *seq, void *v) static int rose_node_show(struct seq_file *seq, void *v) { + char rsbuf[11]; int i; if (v == SEQ_START_TOKEN) @@ -1112,13 +1113,13 @@ static int rose_node_show(struct seq_file *seq, void *v) const struct rose_node *rose_node = v; /* if (rose_node->loopback) { seq_printf(seq, "%-10s %04d 1 loopback\n", - rose2asc(&rose_node->address), - rose_node->mask); + rose2asc(rsbuf, &rose_node->address), + rose_node->mask); } else { */ seq_printf(seq, "%-10s %04d %d", - rose2asc(&rose_node->address), - rose_node->mask, - rose_node->count); + rose2asc(rsbuf, &rose_node->address), + rose_node->mask, + rose_node->count); for (i = 0; i < rose_node->count; i++) seq_printf(seq, " %05d", @@ -1267,7 +1268,7 @@ static void rose_route_stop(struct seq_file *seq, void *v) static int rose_route_show(struct seq_file *seq, void *v) { - char buf[11]; + char buf[11], rsbuf[11]; if (v == SEQ_START_TOKEN) seq_puts(seq, @@ -1279,7 +1280,7 @@ static int rose_route_show(struct seq_file *seq, void *v) seq_printf(seq, "%3.3X %-10s %-9s %05d ", rose_route->lci1, - rose2asc(&rose_route->src_addr), + rose2asc(rsbuf, &rose_route->src_addr), ax2asc(buf, &rose_route->src_call), rose_route->neigh1->number); else @@ -1289,10 +1290,10 @@ static int rose_route_show(struct seq_file *seq, void *v) if (rose_route->neigh2) seq_printf(seq, "%3.3X %-10s %-9s %05d\n", - rose_route->lci2, - rose2asc(&rose_route->dest_addr), - ax2asc(buf, &rose_route->dest_call), - rose_route->neigh2->number); + rose_route->lci2, + rose2asc(rsbuf, &rose_route->dest_addr), + ax2asc(buf, &rose_route->dest_call), + rose_route->neigh2->number); else seq_puts(seq, "000 * * 00000\n"); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index eac5e7bb736..bfe493ebf27 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -63,7 +63,7 @@ static void rxrpc_write_space(struct sock *sk) _enter("%p", sk); read_lock(&sk->sk_callback_lock); if (rxrpc_writable(sk)) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible(sk->sk_sleep); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } @@ -588,7 +588,7 @@ static unsigned int rxrpc_poll(struct file *file, struct socket *sock, unsigned int mask; struct sock *sk = sock->sk; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; /* the socket is readable if there are any messages waiting on the Rx diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 67e38a05624..9f1ce841a0b 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -444,6 +444,11 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, conn = list_entry(bundle->avail_conns.next, struct rxrpc_connection, bundle_link); + if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { + list_del_init(&conn->bundle_link); + bundle->num_conns--; + continue; + } if (--conn->avail_calls == 0) list_move(&conn->bundle_link, &bundle->busy_conns); @@ -461,6 +466,11 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, conn = list_entry(bundle->unused_conns.next, struct rxrpc_connection, bundle_link); + if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { + list_del_init(&conn->bundle_link); + bundle->num_conns--; + continue; + } ASSERTCMP(conn->avail_calls, ==, RXRPC_MAXCALLS); conn->avail_calls = RXRPC_MAXCALLS - 1; ASSERT(conn->channels[0] == NULL && diff --git a/net/rxrpc/ar-connevent.c b/net/rxrpc/ar-connevent.c index dc5cb1e1950..0505cdc4d6d 100644 --- a/net/rxrpc/ar-connevent.c +++ b/net/rxrpc/ar-connevent.c @@ -150,11 +150,15 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, u32 serial; int loop, ret; - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) + if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { + kleave(" = -ECONNABORTED [%u]", conn->state); return -ECONNABORTED; + } serial = ntohl(sp->hdr.serial); + _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, serial); + switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_ABORT: if (skb_copy_bits(skb, 0, &tmp, sizeof(tmp)) < 0) @@ -199,6 +203,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return 0; default: + _leave(" = -EPROTO [%u]", sp->hdr.type); return -EPROTO; } } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index f8f047b6124..723964c3ee4 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -294,6 +294,8 @@ static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, if (police->tcfp_ewma_rate && police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { police->tcf_qstats.overlimits++; + if (police->tcf_action == TC_ACT_SHOT) + police->tcf_qstats.drops++; spin_unlock(&police->tcf_lock); return police->tcf_action; } @@ -327,6 +329,8 @@ static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, } police->tcf_qstats.overlimits++; + if (police->tcf_action == TC_ACT_SHOT) + police->tcf_qstats.drops++; spin_unlock(&police->tcf_lock); return police->tcf_action; } diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index e5becb92b3e..e4877ca6727 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -62,13 +62,7 @@ static u64 read_classid(struct cgroup *cgrp, struct cftype *cft) static int write_classid(struct cgroup *cgrp, struct cftype *cft, u64 value) { - if (!cgroup_lock_live_group(cgrp)) - return -ENODEV; - cgrp_cls_state(cgrp)->classid = (u32) value; - - cgroup_unlock(); - return 0; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 0ef4e3065bc..9402a7fd378 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -84,7 +84,7 @@ static u32 flow_get_dst(const struct sk_buff *skb) case htons(ETH_P_IPV6): return ntohl(ipv6_hdr(skb)->daddr.s6_addr32[3]); default: - return addr_fold(skb->dst) ^ (__force u16)skb->protocol; + return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol; } } @@ -163,7 +163,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb) break; } default: - res = addr_fold(skb->dst) ^ (__force u16)skb->protocol; + res = addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol; } return res; @@ -251,8 +251,8 @@ fallback: static u32 flow_get_rtclassid(const struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ROUTE - if (skb->dst) - return skb->dst->tclassid; + if (skb_dst(skb)) + return skb_dst(skb)->tclassid; #endif return 0; } diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index bdf1f4172ee..dd872d5383e 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -137,7 +137,7 @@ static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, u32 id, h; int iif, dont_cache = 0; - if ((dst = skb->dst) == NULL) + if ((dst = skb_dst(skb)) == NULL) goto failure; id = dst->tclassid; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index fad596bf32d..18d85d25910 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -246,11 +246,11 @@ META_COLLECTOR(int_tcindex) META_COLLECTOR(int_rtclassid) { - if (unlikely(skb->dst == NULL)) + if (unlikely(skb_dst(skb) == NULL)) *err = -1; else #ifdef CONFIG_NET_CLS_ROUTE - dst->value = skb->dst->tclassid; + dst->value = skb_dst(skb)->tclassid; #else dst->value = 0; #endif @@ -258,10 +258,10 @@ META_COLLECTOR(int_rtclassid) META_COLLECTOR(int_rtiif) { - if (unlikely(skb->rtable == NULL)) + if (unlikely(skb_rtable(skb) == NULL)) *err = -1; else - dst->value = skb->rtable->fl.iif; + dst->value = skb_rtable(skb)->fl.iif; } /************************************************************************** @@ -349,13 +349,13 @@ META_COLLECTOR(int_sk_type) META_COLLECTOR(int_sk_rmem_alloc) { SKIP_NONLOCAL(skb); - dst->value = atomic_read(&skb->sk->sk_rmem_alloc); + dst->value = sk_rmem_alloc_get(skb->sk); } META_COLLECTOR(int_sk_wmem_alloc) { SKIP_NONLOCAL(skb); - dst->value = atomic_read(&skb->sk->sk_wmem_alloc); + dst->value = sk_wmem_alloc_get(skb->sk); } META_COLLECTOR(int_sk_omem_alloc) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 32009793307..92e6f3a52c1 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -458,7 +458,7 @@ EXPORT_SYMBOL(qdisc_warn_nonwc); static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) { struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, - timer); + timer.timer); wd->qdisc->flags &= ~TCQ_F_THROTTLED; __netif_schedule(qdisc_root(wd->qdisc)); @@ -468,8 +468,8 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) { - hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - wd->timer.function = qdisc_watchdog; + tasklet_hrtimer_init(&wd->timer, qdisc_watchdog, + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); wd->qdisc = qdisc; } EXPORT_SYMBOL(qdisc_watchdog_init); @@ -484,14 +484,14 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) wd->qdisc->flags |= TCQ_F_THROTTLED; time = ktime_set(0, 0); - time = ktime_add_ns(time, PSCHED_US2NS(expires)); - hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); + time = ktime_add_ns(time, PSCHED_TICKS2NS(expires)); + tasklet_hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); } EXPORT_SYMBOL(qdisc_watchdog_schedule); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { - hrtimer_cancel(&wd->timer); + tasklet_hrtimer_cancel(&wd->timer); wd->qdisc->flags &= ~TCQ_F_THROTTLED; } EXPORT_SYMBOL(qdisc_watchdog_cancel); @@ -1680,7 +1680,7 @@ static int psched_show(struct seq_file *seq, void *v) hrtimer_get_res(CLOCK_MONOTONIC, &ts); seq_printf(seq, "%08x %08x %08x %08x\n", - (u32)NSEC_PER_USEC, (u32)PSCHED_US2NS(1), + (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1), 1000000, (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts))); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 2a8b83af7c4..ab82f145f68 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -49,7 +49,7 @@ struct atm_flow_data { struct socket *sock; /* for closing */ u32 classid; /* x:y type ID */ int ref; /* reference count */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct atm_flow_data *next; struct atm_flow_data *excess; /* flow for excess traffic; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index d728d811173..149b0405c5e 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -128,7 +128,7 @@ struct cbq_class long avgidle; long deficit; /* Saved deficit for WRR */ psched_time_t penalized; - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct tc_cbq_xstats xstats; @@ -163,7 +163,7 @@ struct cbq_sched_data psched_time_t now_rt; /* Cached real time */ unsigned pmask; - struct hrtimer delay_timer; + struct tasklet_hrtimer delay_timer; struct qdisc_watchdog watchdog; /* Watchdog timer, started when CBQ has backlog, but cannot @@ -503,19 +503,21 @@ static void cbq_ovl_delay(struct cbq_class *cl) cl->undertime = q->now + delay; if (delay > 0) { + struct hrtimer *ht; + sched += delay + cl->penalty; cl->penalized = sched; cl->cpriority = TC_CBQ_MAXPRIO; q->pmask |= (1<<TC_CBQ_MAXPRIO); expires = ktime_set(0, 0); - expires = ktime_add_ns(expires, PSCHED_US2NS(sched)); - if (hrtimer_try_to_cancel(&q->delay_timer) && - ktime_to_ns(ktime_sub( - hrtimer_get_expires(&q->delay_timer), - expires)) > 0) - hrtimer_set_expires(&q->delay_timer, expires); - hrtimer_restart(&q->delay_timer); + expires = ktime_add_ns(expires, PSCHED_TICKS2NS(sched)); + ht = &q->delay_timer.timer; + if (hrtimer_try_to_cancel(ht) && + ktime_to_ns(ktime_sub(hrtimer_get_expires(ht), + expires)) > 0) + hrtimer_set_expires(ht, expires); + hrtimer_restart(ht); cl->delayed = 1; cl->xstats.overactions++; return; @@ -591,7 +593,7 @@ static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio, static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) { struct cbq_sched_data *q = container_of(timer, struct cbq_sched_data, - delay_timer); + delay_timer.timer); struct Qdisc *sch = q->watchdog.qdisc; psched_time_t now; psched_tdiff_t delay = 0; @@ -620,8 +622,8 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) ktime_t time; time = ktime_set(0, 0); - time = ktime_add_ns(time, PSCHED_US2NS(now + delay)); - hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS); + time = ktime_add_ns(time, PSCHED_TICKS2NS(now + delay)); + tasklet_hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS); } sch->flags &= ~TCQ_F_THROTTLED; @@ -1214,7 +1216,7 @@ cbq_reset(struct Qdisc* sch) q->tx_class = NULL; q->tx_borrowed = NULL; qdisc_watchdog_cancel(&q->watchdog); - hrtimer_cancel(&q->delay_timer); + tasklet_hrtimer_cancel(&q->delay_timer); q->toplevel = TC_CBQ_MAXLEVEL; q->now = psched_get_time(); q->now_rt = q->now; @@ -1397,7 +1399,8 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) q->link.minidle = -0x7FFFFFFF; qdisc_watchdog_init(&q->watchdog, sch); - hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + tasklet_hrtimer_init(&q->delay_timer, cbq_undelay, + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); q->delay_timer.function = cbq_undelay; q->toplevel = TC_CBQ_MAXLEVEL; q->now = psched_get_time(); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 7597fe14686..12b2fb04b29 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -22,7 +22,7 @@ struct drr_class { unsigned int refcnt; unsigned int filter_cnt; - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct list_head alist; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 5f5efe4e607..27d03816ec3 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -196,6 +196,21 @@ void __qdisc_run(struct Qdisc *q) clear_bit(__QDISC_STATE_RUNNING, &q->state); } +unsigned long dev_trans_start(struct net_device *dev) +{ + unsigned long val, res = dev->trans_start; + unsigned int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + val = netdev_get_tx_queue(dev, i)->trans_start; + if (val && time_after(val, res)) + res = val; + } + dev->trans_start = res; + return res; +} +EXPORT_SYMBOL(dev_trans_start); + static void dev_watchdog(unsigned long arg) { struct net_device *dev = (struct net_device *)arg; @@ -205,25 +220,30 @@ static void dev_watchdog(unsigned long arg) if (netif_device_present(dev) && netif_running(dev) && netif_carrier_ok(dev)) { - int some_queue_stopped = 0; + int some_queue_timedout = 0; unsigned int i; + unsigned long trans_start; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); - if (netif_tx_queue_stopped(txq)) { - some_queue_stopped = 1; + /* + * old device drivers set dev->trans_start + */ + trans_start = txq->trans_start ? : dev->trans_start; + if (netif_tx_queue_stopped(txq) && + time_after(jiffies, (trans_start + + dev->watchdog_timeo))) { + some_queue_timedout = 1; break; } } - if (some_queue_stopped && - time_after(jiffies, (dev->trans_start + - dev->watchdog_timeo))) { + if (some_queue_timedout) { char drivername[64]; - WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit timed out\n", - dev->name, netdev_drivername(dev, drivername, 64)); + WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", + dev->name, netdev_drivername(dev, drivername, 64), i); dev->netdev_ops->ndo_tx_timeout(dev); } if (!mod_timer(&dev->watchdog_timer, @@ -602,8 +622,10 @@ static void transition_one_qdisc(struct net_device *dev, clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state); rcu_assign_pointer(dev_queue->qdisc, new_qdisc); - if (need_watchdog_p && new_qdisc != &noqueue_qdisc) + if (need_watchdog_p && new_qdisc != &noqueue_qdisc) { + dev_queue->trans_start = 0; *need_watchdog_p = 1; + } } void dev_activate(struct net_device *dev) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 5022f9c1f34..dad0144423d 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -116,7 +116,7 @@ struct hfsc_class struct Qdisc_class_common cl_common; unsigned int refcnt; /* usage count */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; unsigned int level; /* class level in hierarchy */ @@ -372,7 +372,7 @@ cftree_update(struct hfsc_class *cl) * ism: (psched_us/byte) << ISM_SHIFT * dx: psched_us * - * The clock source resolution with ktime is 1.024us. + * The clock source resolution with ktime and PSCHED_SHIFT 10 is 1.024us. * * sm and ism are scaled in order to keep effective digits. * SM_SHIFT and ISM_SHIFT are selected to keep at least 4 effective @@ -383,9 +383,11 @@ cftree_update(struct hfsc_class *cl) * bytes/1.024us 12.8e-3 128e-3 1280e-3 12800e-3 128000e-3 * * 1.024us/byte 78.125 7.8125 0.78125 0.078125 0.0078125 + * + * So, for PSCHED_SHIFT 10 we need: SM_SHIFT 20, ISM_SHIFT 18. */ -#define SM_SHIFT 20 -#define ISM_SHIFT 18 +#define SM_SHIFT (30 - PSCHED_SHIFT) +#define ISM_SHIFT (8 + PSCHED_SHIFT) #define SM_MASK ((1ULL << SM_SHIFT) - 1) #define ISM_MASK ((1ULL << ISM_SHIFT) - 1) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 88cd0262662..ec4d46399d5 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -74,7 +74,7 @@ enum htb_cmode { struct htb_class { struct Qdisc_class_common common; /* general class parameters */ - struct gnet_stats_basic bstats; + struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct tc_htb_xstats xstats; /* our special stats */ diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 33133d27b53..8706920a6d4 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -149,7 +149,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) break; } default: - h = (unsigned long)skb->dst ^ skb->protocol; + h = (unsigned long)skb_dst(skb) ^ skb->protocol; h2 = (unsigned long)skb->sk; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 3b641829723..9c002b6e053 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -58,7 +58,6 @@ struct teql_master struct net_device *dev; struct Qdisc *slaves; struct list_head master_list; - struct net_device_stats stats; }; struct teql_sched_data @@ -223,7 +222,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * { struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0); struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc); - struct neighbour *mn = skb->dst->neighbour; + struct neighbour *mn = skb_dst(skb)->neighbour; struct neighbour *n = q->ncache; if (mn->tbl == NULL) @@ -263,8 +262,8 @@ static inline int teql_resolve(struct sk_buff *skb, return -ENODEV; if (dev->header_ops == NULL || - skb->dst == NULL || - skb->dst->neighbour == NULL) + skb_dst(skb) == NULL || + skb_dst(skb)->neighbour == NULL) return 0; return __teql_resolve(skb, skb_res, dev); } @@ -272,6 +271,7 @@ static inline int teql_resolve(struct sk_buff *skb, static int 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); struct Qdisc *start, *q; int busy; int nores; @@ -308,11 +308,12 @@ restart: if (!netif_tx_queue_stopped(slave_txq) && !netif_tx_queue_frozen(slave_txq) && slave_ops->ndo_start_xmit(skb, slave) == 0) { + txq_trans_update(slave_txq); __netif_tx_unlock(slave_txq); master->slaves = NEXT_SLAVE(q); netif_wake_queue(dev); - master->stats.tx_packets++; - master->stats.tx_bytes += length; + txq->tx_packets++; + txq->tx_bytes += length; return 0; } __netif_tx_unlock(slave_txq); @@ -337,12 +338,12 @@ restart: if (busy) { netif_stop_queue(dev); - return 1; + return NETDEV_TX_BUSY; } - master->stats.tx_errors++; + dev->stats.tx_errors++; drop: - master->stats.tx_dropped++; + txq->tx_dropped++; dev_kfree_skb(skb); return 0; } @@ -395,12 +396,6 @@ static int teql_master_close(struct net_device *dev) return 0; } -static struct net_device_stats *teql_master_stats(struct net_device *dev) -{ - struct teql_master *m = netdev_priv(dev); - return &m->stats; -} - static int teql_master_mtu(struct net_device *dev, int new_mtu) { struct teql_master *m = netdev_priv(dev); @@ -425,7 +420,6 @@ static const struct net_device_ops teql_netdev_ops = { .ndo_open = teql_master_open, .ndo_stop = teql_master_close, .ndo_start_xmit = teql_master_xmit, - .ndo_get_stats = teql_master_stats, .ndo_change_mtu = teql_master_mtu, }; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index f4b23043b61..525864bf4f0 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -293,7 +293,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a * told otherwise. */ asoc->peer.ipv4_address = 1; - asoc->peer.ipv6_address = 1; + if (asoc->base.sk->sk_family == PF_INET6) + asoc->peer.ipv6_address = 1; INIT_LIST_HEAD(&asoc->asocs); asoc->autoclose = sp->autoclose; @@ -566,6 +567,21 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, if (asoc->init_last_sent_to == peer) asoc->init_last_sent_to = NULL; + /* If we remove the transport an SHUTDOWN was last sent to, set it + * to NULL. Combined with the update of the retran path above, this + * will cause the next SHUTDOWN to be sent to the next available + * transport, maintaining the cycle. + */ + if (asoc->shutdown_last_sent_to == peer) + asoc->shutdown_last_sent_to = NULL; + + /* If we remove the transport an ASCONF was last sent to, set it to + * NULL. + */ + if (asoc->addip_last_asconf && + asoc->addip_last_asconf->transport == peer) + asoc->addip_last_asconf->transport = NULL; + asoc->peer.transport_count--; sctp_transport_free(peer); @@ -1268,49 +1284,21 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) ntohs(t->ipaddr.v4.sin_port)); } -/* Choose the transport for sending a INIT packet. */ -struct sctp_transport *sctp_assoc_choose_init_transport( - struct sctp_association *asoc) -{ - struct sctp_transport *t; - - /* Use the retran path. If the last INIT was sent over the - * retran path, update the retran path and use it. - */ - if (!asoc->init_last_sent_to) { - t = asoc->peer.active_path; - } else { - if (asoc->init_last_sent_to == asoc->peer.retran_path) - sctp_assoc_update_retran_path(asoc); - t = asoc->peer.retran_path; - } - - SCTP_DEBUG_PRINTK_IPADDR("sctp_assoc_update_retran_path:association" - " %p addr: ", - " port: %d\n", - asoc, - (&t->ipaddr), - ntohs(t->ipaddr.v4.sin_port)); - - return t; -} - -/* Choose the transport for sending a SHUTDOWN packet. */ -struct sctp_transport *sctp_assoc_choose_shutdown_transport( - struct sctp_association *asoc) +/* Choose the transport for sending retransmit packet. */ +struct sctp_transport *sctp_assoc_choose_alter_transport( + struct sctp_association *asoc, struct sctp_transport *last_sent_to) { - /* If this is the first time SHUTDOWN is sent, use the active path, - * else use the retran path. If the last SHUTDOWN was sent over the + /* If this is the first time packet is sent, use the active path, + * else use the retran path. If the last packet was sent over the * retran path, update the retran path and use it. */ - if (!asoc->shutdown_last_sent_to) + if (!last_sent_to) return asoc->peer.active_path; else { - if (asoc->shutdown_last_sent_to == asoc->peer.retran_path) + if (last_sent_to == asoc->peer.retran_path) sctp_assoc_update_retran_path(asoc); return asoc->peer.retran_path; } - } /* Update the association's pmtu and frag_point by going through all the @@ -1482,6 +1470,10 @@ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) { int assoc_id; int error = 0; + + /* If the id is already assigned, keep it. */ + if (asoc->assoc_id) + return error; retry: if (unlikely(!idr_pre_get(&sctp_assocs_id, gfp))) return -ENOMEM; diff --git a/net/sctp/input.c b/net/sctp/input.c index d2e98803ffe..c0c973e67ad 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -81,13 +81,13 @@ static void sctp_add_backlog(struct sock *sk, struct sk_buff *skb); /* Calculate the SCTP checksum of an SCTP packet. */ static inline int sctp_rcv_checksum(struct sk_buff *skb) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; struct sctphdr *sh = sctp_hdr(skb); __le32 cmp = sh->checksum; + struct sk_buff *list; __le32 val; __u32 tmp = sctp_start_cksum((__u8 *)sh, skb_headlen(skb)); - for (; list; list = list->next) + skb_walk_frags(skb, list) tmp = sctp_update_cksum((__u8 *)list->data, skb_headlen(list), tmp); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index a63de3f7f18..6a4b1909414 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -133,7 +133,7 @@ static struct notifier_block sctp_inet6addr_notifier = { /* ICMP error handler. */ SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { struct inet6_dev *idev; struct sock *sk; diff --git a/net/sctp/output.c b/net/sctp/output.c index 7d08f522ec8..b94c2119056 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -405,13 +405,14 @@ int sctp_packet_transmit(struct sctp_packet *packet) sctp_assoc_sync_pmtu(asoc); } } - nskb->dst = dst_clone(tp->dst); - if (!nskb->dst) + dst = dst_clone(tp->dst); + skb_dst_set(nskb, dst); + if (!dst) goto no_route; - dst = nskb->dst; /* Build the SCTP header. */ sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr)); + skb_reset_transport_header(nskb); sh->source = htons(packet->source_port); sh->dest = htons(packet->destination_port); @@ -527,15 +528,25 @@ int sctp_packet_transmit(struct sctp_packet *packet) * Note: Adler-32 is no longer applicable, as has been replaced * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ - if (!sctp_checksum_disable && !(dst->dev->features & NETIF_F_NO_CSUM)) { + if (!sctp_checksum_disable && + !(dst->dev->features & (NETIF_F_NO_CSUM | NETIF_F_SCTP_CSUM))) { __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); /* 3) Put the resultant value into the checksum field in the * common header, and leave the rest of the bits unchanged. */ sh->checksum = sctp_end_cksum(crc32); - } else - nskb->ip_summed = CHECKSUM_UNNECESSARY; + } else { + if (dst->dev->features & NETIF_F_SCTP_CSUM) { + /* no need to seed psuedo checksum for SCTP */ + nskb->ip_summed = CHECKSUM_PARTIAL; + nskb->csum_start = (skb_transport_header(nskb) - + nskb->head); + nskb->csum_offset = offsetof(struct sctphdr, checksum); + } else { + nskb->ip_summed = CHECKSUM_UNNECESSARY; + } + } /* IP layer ECN support * From RFC 2481 diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 8eb3e61cb70..a76da657244 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -160,6 +160,7 @@ static void sctp_proc_exit(void) remove_proc_entry("sctp", init_net.proc_net); } #endif + percpu_counter_destroy(&sctp_sockets_allocated); } /* Private helper to extract ipv4 address and stash them in @@ -393,7 +394,7 @@ static int sctp_v4_addr_valid(union sctp_addr *addr, return 0; /* Is this a broadcast address? */ - if (skb && skb->rtable->rt_flags & RTCF_BROADCAST) + if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST) return 0; return 1; @@ -572,7 +573,7 @@ static void sctp_v4_get_saddr(struct sctp_sock *sk, /* What interface did this skb arrive on? */ static int sctp_v4_skb_iif(const struct sk_buff *skb) { - return skb->rtable->rt_iif; + return skb_rtable(skb)->rt_iif; } /* Was this packet marked by Explicit Congestion Notification? */ @@ -848,8 +849,8 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, skb->len, - &skb->rtable->rt_src, - &skb->rtable->rt_dst); + &skb_rtable(skb)->rt_src, + &skb_rtable(skb)->rt_dst); inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO : IP_PMTUDISC_DONT; @@ -1370,6 +1371,8 @@ SCTP_STATIC __exit void sctp_exit(void) sctp_proc_exit(); cleanup_sctp_mibs(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ + kmem_cache_destroy(sctp_chunk_cachep); kmem_cache_destroy(sctp_bucket_cachep); } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 6851ee94e97..61cc6075b0d 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2864,19 +2864,19 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, switch (addr_param->v4.param_hdr.type) { case SCTP_PARAM_IPV6_ADDRESS: if (!asoc->peer.ipv6_address) - return SCTP_ERROR_INV_PARAM; + return SCTP_ERROR_DNS_FAILED; break; case SCTP_PARAM_IPV4_ADDRESS: if (!asoc->peer.ipv4_address) - return SCTP_ERROR_INV_PARAM; + return SCTP_ERROR_DNS_FAILED; break; default: - return SCTP_ERROR_INV_PARAM; + return SCTP_ERROR_DNS_FAILED; } af = sctp_get_af_specific(param_type2af(addr_param->v4.param_hdr.type)); if (unlikely(!af)) - return SCTP_ERROR_INV_PARAM; + return SCTP_ERROR_DNS_FAILED; af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); @@ -2886,7 +2886,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, * make sure we check for that) */ if (!af->is_any(&addr) && !af->addr_valid(&addr, NULL, asconf->skb)) - return SCTP_ERROR_INV_PARAM; + return SCTP_ERROR_DNS_FAILED; switch (asconf_param->param_hdr.type) { case SCTP_PARAM_ADD_IP: @@ -2954,12 +2954,12 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, peer = sctp_assoc_lookup_paddr(asoc, &addr); if (!peer) - return SCTP_ERROR_INV_PARAM; + return SCTP_ERROR_DNS_FAILED; sctp_assoc_set_primary(asoc, peer); break; default: - return SCTP_ERROR_INV_PARAM; + return SCTP_ERROR_UNKNOWN_PARAM; break; } @@ -3273,7 +3273,7 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, retval = 1; break; - case SCTP_ERROR_INV_PARAM: + case SCTP_ERROR_UNKNOWN_PARAM: /* Disable sending this type of asconf parameter in * future. */ diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e2020eb2c8c..86426aac160 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -686,7 +686,8 @@ static void sctp_cmd_setup_t2(sctp_cmd_seq_t *cmds, { struct sctp_transport *t; - t = sctp_assoc_choose_shutdown_transport(asoc); + t = sctp_assoc_choose_alter_transport(asoc, + asoc->shutdown_last_sent_to); asoc->shutdown_last_sent_to = t; asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = t->rto; chunk->transport = t; @@ -777,7 +778,7 @@ static void sctp_cmd_setup_t4(sctp_cmd_seq_t *cmds, { struct sctp_transport *t; - t = asoc->peer.active_path; + t = sctp_assoc_choose_alter_transport(asoc, chunk->transport); asoc->timeouts[SCTP_EVENT_TIMEOUT_T4_RTO] = t->rto; chunk->transport = t; } @@ -1379,7 +1380,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_INIT_CHOOSE_TRANSPORT: chunk = cmd->obj.ptr; - t = sctp_assoc_choose_init_transport(asoc); + t = sctp_assoc_choose_alter_transport(asoc, + asoc->init_last_sent_to); asoc->init_last_sent_to = t; chunk->transport = t; t->init_sent_count++; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 55a61aa6966..7288192f7df 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -5432,9 +5432,13 @@ sctp_disposition_t sctp_sf_t2_timer_expire(const struct sctp_endpoint *ep, if (!reply) goto nomem; - /* Do some failure management (Section 8.2). */ - sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, - SCTP_TRANSPORT(asoc->shutdown_last_sent_to)); + /* Do some failure management (Section 8.2). + * If we remove the transport an SHUTDOWN was last sent to, don't + * do failure management. + */ + if (asoc->shutdown_last_sent_to) + sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, + SCTP_TRANSPORT(asoc->shutdown_last_sent_to)); /* Set the transport for the SHUTDOWN/ACK chunk and the timeout for * the T2-shutdown timer. @@ -5471,7 +5475,9 @@ sctp_disposition_t sctp_sf_t4_timer_expire( * detection on the appropriate destination address as defined in * RFC2960 [5] section 8.1 and 8.2. */ - sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, SCTP_TRANSPORT(transport)); + if (transport) + sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, + SCTP_TRANSPORT(transport)); /* Reconfig T4 timer and transport. */ sctp_add_cmd_sf(commands, SCTP_CMD_SETUP_T4, SCTP_CHUNK(chunk)); diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 5c8186d88c6..6d9b3aafcc5 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -698,7 +698,7 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ -} /* TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT */ +} /* TYPE_SCTP_PRIMITIVE_ASCONF */ /* The primary index for this table is the primitive type. * The secondary index for this table is the state. diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 5fb3a8c9792..971890dbfea 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -130,7 +130,7 @@ static inline int sctp_wspace(struct sctp_association *asoc) if (asoc->ep->sndbuf_policy) amt = asoc->sndbuf_used; else - amt = atomic_read(&asoc->base.sk->sk_wmem_alloc); + amt = sk_wmem_alloc_get(asoc->base.sk); if (amt >= asoc->base.sk->sk_sndbuf) { if (asoc->base.sk->sk_userlocks & SOCK_SNDBUF_LOCK) @@ -1100,6 +1100,15 @@ static int __sctp_connect(struct sock* sk, goto out_free; } + /* In case the user of sctp_connectx() wants an association + * id back, assign one now. + */ + if (assoc_id) { + err = sctp_assoc_set_id(asoc, GFP_KERNEL); + if (err < 0) + goto out_free; + } + err = sctp_primitive_ASSOCIATE(asoc, NULL); if (err < 0) { goto out_free; @@ -1120,7 +1129,7 @@ static int __sctp_connect(struct sock* sk, timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK); err = sctp_wait_for_connect(asoc, &timeo); - if (!err && assoc_id) + if ((err == 0 || err == -EINPROGRESS) && assoc_id) *assoc_id = asoc->assoc_id; /* Don't free association on exit. */ @@ -1264,6 +1273,34 @@ SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk, return assoc_id; } +/* + * New (hopefully final) interface for the API. The option buffer is used + * both for the returned association id and the addresses. + */ +SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len, + char __user *optval, + int __user *optlen) +{ + sctp_assoc_t assoc_id = 0; + int err = 0; + + if (len < sizeof(assoc_id)) + return -EINVAL; + + err = __sctp_setsockopt_connectx(sk, + (struct sockaddr __user *)(optval + sizeof(assoc_id)), + len - sizeof(assoc_id), &assoc_id); + + if (err == 0 || err == -EINPROGRESS) { + if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) + return -EFAULT; + if (put_user(sizeof(assoc_id), optlen)) + return -EFAULT; + } + + return err; +} + /* API 3.1.4 close() - UDP Style Syntax * Applications use close() to perform graceful shutdown (as described in * Section 10.1 of [SCTP]) on ALL the associations currently represented @@ -1844,7 +1881,7 @@ static int sctp_skb_pull(struct sk_buff *skb, int len) len -= skb_len; __skb_pull(skb, skb_len); - for (list = skb_shinfo(skb)->frag_list; list; list = list->next) { + skb_walk_frags(skb, list) { rlen = sctp_skb_pull(list, len); skb->len -= (len-rlen); skb->data_len -= (len-rlen); @@ -5578,6 +5615,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_local_addrs(sk, len, optval, optlen); break; + case SCTP_SOCKOPT_CONNECTX3: + retval = sctp_getsockopt_connectx3(sk, len, optval, optlen); + break; case SCTP_DEFAULT_SEND_PARAM: retval = sctp_getsockopt_default_send_param(sk, len, optval, optlen); @@ -6483,7 +6523,7 @@ static int sctp_writeable(struct sock *sk) { int amt = 0; - amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + amt = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amt < 0) amt = 0; return amt; @@ -6612,21 +6652,6 @@ static void sctp_wait_for_close(struct sock *sk, long timeout) finish_wait(sk->sk_sleep, &wait); } -static void sctp_sock_rfree_frag(struct sk_buff *skb) -{ - struct sk_buff *frag; - - if (!skb->data_len) - goto done; - - /* Don't forget the fragments. */ - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) - sctp_sock_rfree_frag(frag); - -done: - sctp_sock_rfree(skb); -} - static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) { struct sk_buff *frag; @@ -6635,7 +6660,7 @@ static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) goto done; /* Don't forget the fragments. */ - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) + skb_walk_frags(skb, frag) sctp_skb_set_owner_r_frag(frag, sk); done: @@ -6736,7 +6761,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { - sctp_sock_rfree_frag(skb); __skb_unlink(skb, &oldsk->sk_receive_queue); __skb_queue_tail(&newsk->sk_receive_queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); @@ -6767,7 +6791,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { - sctp_sock_rfree_frag(skb); __skb_unlink(skb, &oldsp->pd_lobby); __skb_queue_tail(queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); @@ -6782,15 +6805,11 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, } - sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) { - sctp_sock_rfree_frag(skb); + sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) sctp_skb_set_owner_r_frag(skb, newsk); - } - sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) { - sctp_sock_rfree_frag(skb); + sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) sctp_skb_set_owner_r_frag(skb, newsk); - } /* Set the type of socket to indicate that it is peeled off from the * original UDP-style socket or created with the accept() call on a diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index f58e994e685..63eabbc7129 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -49,8 +49,8 @@ static int zero = 0; static int one = 1; static int timer_max = 86400000; /* ms in one day */ static int int_max = INT_MAX; -static long sack_timer_min = 1; -static long sack_timer_max = 500; +static int sack_timer_min = 1; +static int sack_timer_max = 500; extern int sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; @@ -223,7 +223,7 @@ static ctl_table sctp_table[] = { .ctl_name = NET_SCTP_SACK_TIMEOUT, .procname = "sack_timeout", .data = &sctp_sack_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .strategy = sysctl_intvec, diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 5f186ca550d..8b3560fd876 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -976,9 +976,8 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, * In general, the skb passed from IP can have only 1 level of * fragments. But we allow multiple levels of fragments. */ - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) { + skb_walk_frags(skb, frag) sctp_ulpevent_receive_data(sctp_skb2event(frag), asoc); - } } /* Do accounting for bytes just read by user and release the references to @@ -1003,7 +1002,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) goto done; /* Don't forget the fragments. */ - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) { + skb_walk_frags(skb, frag) { /* NOTE: skb_shinfos are recursive. Although IP returns * skb's with only 1 level of fragments, SCTP reassembly can * increase the levels. @@ -1026,7 +1025,7 @@ static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) goto done; /* Don't forget the fragments. */ - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) { + skb_walk_frags(skb, frag) { /* NOTE: skb_shinfos are recursive. Although IP returns * skb's with only 1 level of fragments, SCTP reassembly can * increase the levels. diff --git a/net/socket.c b/net/socket.c index 791d71a36a9..6d471655904 100644 --- a/net/socket.c +++ b/net/socket.c @@ -736,7 +736,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, if (more) flags |= MSG_MORE; - return sock->ops->sendpage(sock, page, offset, size, flags); + return kernel_sendpage(sock, page, offset, size, flags); } static ssize_t sock_splice_read(struct file *file, loff_t *ppos, diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 5369aa369b3..db73fd2a3f0 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -13,5 +13,6 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.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 sunrpc-$(CONFIG_PROC_FS) += stats.o sunrpc-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index e630b38a604..66d458fc692 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1548,6 +1548,7 @@ static void __exit exit_rpcsec_gss(void) { gss_svc_shutdown(); rpcauth_unregister(&authgss_ops); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_LICENSE("GPL"); diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c new file mode 100644 index 00000000000..553621fb2c4 --- /dev/null +++ b/net/sunrpc/backchannel_rqst.c @@ -0,0 +1,281 @@ +/****************************************************************************** + +(c) 2007 Network Appliance, Inc. All Rights Reserved. +(c) 2009 NetApp. All Rights Reserved. + +NetApp provides this source code under the GPL v2 License. +The GPL v2 license is available at +http://opensource.org/licenses/gpl-license.php. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR +CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, +EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, +PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +******************************************************************************/ + +#include <linux/tcp.h> +#include <linux/sunrpc/xprt.h> + +#ifdef RPC_DEBUG +#define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +#if defined(CONFIG_NFS_V4_1) + +/* + * Helper routines that track the number of preallocation elements + * on the transport. + */ +static inline int xprt_need_to_requeue(struct rpc_xprt *xprt) +{ + return xprt->bc_alloc_count > 0; +} + +static inline void xprt_inc_alloc_count(struct rpc_xprt *xprt, unsigned int n) +{ + xprt->bc_alloc_count += n; +} + +static inline int xprt_dec_alloc_count(struct rpc_xprt *xprt, unsigned int n) +{ + return xprt->bc_alloc_count -= n; +} + +/* + * Free the preallocated rpc_rqst structure and the memory + * buffers hanging off of it. + */ +static void xprt_free_allocation(struct rpc_rqst *req) +{ + struct xdr_buf *xbufp; + + dprintk("RPC: free allocations for req= %p\n", req); + BUG_ON(test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state)); + xbufp = &req->rq_private_buf; + free_page((unsigned long)xbufp->head[0].iov_base); + xbufp = &req->rq_snd_buf; + free_page((unsigned long)xbufp->head[0].iov_base); + list_del(&req->rq_bc_pa_list); + kfree(req); +} + +/* + * Preallocate up to min_reqs structures and related buffers for use + * by the backchannel. This function can be called multiple times + * when creating new sessions that use the same rpc_xprt. The + * preallocated buffers are added to the pool of resources used by + * the rpc_xprt. Anyone of these resources may be used used by an + * incoming callback request. It's up to the higher levels in the + * stack to enforce that the maximum number of session slots is not + * being exceeded. + * + * Some callback arguments can be large. For example, a pNFS server + * using multiple deviceids. The list can be unbound, but the client + * has the ability to tell the server the maximum size of the callback + * requests. Each deviceID is 16 bytes, so allocate one page + * for the arguments to have enough room to receive a number of these + * deviceIDs. The NFS client indicates to the pNFS server that its + * callback requests can be up to 4096 bytes in size. + */ +int xprt_setup_backchannel(struct rpc_xprt *xprt, unsigned int min_reqs) +{ + struct page *page_rcv = NULL, *page_snd = NULL; + struct xdr_buf *xbufp = NULL; + struct rpc_rqst *req, *tmp; + struct list_head tmp_list; + int i; + + dprintk("RPC: setup backchannel transport\n"); + + /* + * We use a temporary list to keep track of the preallocated + * buffers. Once we're done building the list we splice it + * into the backchannel preallocation list off of the rpc_xprt + * struct. This helps minimize the amount of time the list + * lock is held on the rpc_xprt struct. It also makes cleanup + * easier in case of memory allocation errors. + */ + INIT_LIST_HEAD(&tmp_list); + for (i = 0; i < min_reqs; i++) { + /* Pre-allocate one backchannel rpc_rqst */ + req = kzalloc(sizeof(struct rpc_rqst), GFP_KERNEL); + if (req == NULL) { + printk(KERN_ERR "Failed to create bc rpc_rqst\n"); + goto out_free; + } + + /* Add the allocated buffer to the tmp list */ + dprintk("RPC: adding req= %p\n", req); + list_add(&req->rq_bc_pa_list, &tmp_list); + + req->rq_xprt = xprt; + INIT_LIST_HEAD(&req->rq_list); + INIT_LIST_HEAD(&req->rq_bc_list); + + /* Preallocate one XDR receive buffer */ + page_rcv = alloc_page(GFP_KERNEL); + if (page_rcv == NULL) { + printk(KERN_ERR "Failed to create bc receive xbuf\n"); + goto out_free; + } + xbufp = &req->rq_rcv_buf; + xbufp->head[0].iov_base = page_address(page_rcv); + xbufp->head[0].iov_len = PAGE_SIZE; + xbufp->tail[0].iov_base = NULL; + xbufp->tail[0].iov_len = 0; + xbufp->page_len = 0; + xbufp->len = PAGE_SIZE; + xbufp->buflen = PAGE_SIZE; + + /* Preallocate one XDR send buffer */ + page_snd = alloc_page(GFP_KERNEL); + if (page_snd == NULL) { + printk(KERN_ERR "Failed to create bc snd xbuf\n"); + goto out_free; + } + + xbufp = &req->rq_snd_buf; + xbufp->head[0].iov_base = page_address(page_snd); + xbufp->head[0].iov_len = 0; + xbufp->tail[0].iov_base = NULL; + xbufp->tail[0].iov_len = 0; + xbufp->page_len = 0; + xbufp->len = 0; + xbufp->buflen = PAGE_SIZE; + } + + /* + * Add the temporary list to the backchannel preallocation list + */ + spin_lock_bh(&xprt->bc_pa_lock); + list_splice(&tmp_list, &xprt->bc_pa_list); + xprt_inc_alloc_count(xprt, min_reqs); + spin_unlock_bh(&xprt->bc_pa_lock); + + dprintk("RPC: setup backchannel transport done\n"); + return 0; + +out_free: + /* + * Memory allocation failed, free the temporary list + */ + list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) + xprt_free_allocation(req); + + dprintk("RPC: setup backchannel transport failed\n"); + return -1; +} +EXPORT_SYMBOL(xprt_setup_backchannel); + +/* + * Destroys the backchannel preallocated structures. + * Since these structures may have been allocated by multiple calls + * to xprt_setup_backchannel, we only destroy up to the maximum number + * of reqs specified by the caller. + * @xprt: the transport holding the preallocated strucures + * @max_reqs the maximum number of preallocated structures to destroy + */ +void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs) +{ + struct rpc_rqst *req = NULL, *tmp = NULL; + + dprintk("RPC: destroy backchannel transport\n"); + + BUG_ON(max_reqs == 0); + spin_lock_bh(&xprt->bc_pa_lock); + xprt_dec_alloc_count(xprt, max_reqs); + list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) { + dprintk("RPC: req=%p\n", req); + xprt_free_allocation(req); + if (--max_reqs == 0) + break; + } + spin_unlock_bh(&xprt->bc_pa_lock); + + dprintk("RPC: backchannel list empty= %s\n", + list_empty(&xprt->bc_pa_list) ? "true" : "false"); +} +EXPORT_SYMBOL(xprt_destroy_backchannel); + +/* + * One or more rpc_rqst structure have been preallocated during the + * backchannel setup. Buffer space for the send and private XDR buffers + * has been preallocated as well. Use xprt_alloc_bc_request to allocate + * to this request. Use xprt_free_bc_request to return it. + * + * We know that we're called in soft interrupt context, grab the spin_lock + * since there is no need to grab the bottom half spin_lock. + * + * Return an available rpc_rqst, otherwise NULL if non are available. + */ +struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt) +{ + struct rpc_rqst *req; + + dprintk("RPC: allocate a backchannel request\n"); + spin_lock(&xprt->bc_pa_lock); + if (!list_empty(&xprt->bc_pa_list)) { + req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst, + rq_bc_pa_list); + list_del(&req->rq_bc_pa_list); + } else { + req = NULL; + } + spin_unlock(&xprt->bc_pa_lock); + + if (req != NULL) { + set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); + req->rq_reply_bytes_recvd = 0; + req->rq_bytes_sent = 0; + memcpy(&req->rq_private_buf, &req->rq_rcv_buf, + sizeof(req->rq_private_buf)); + } + dprintk("RPC: backchannel req=%p\n", req); + return req; +} + +/* + * Return the preallocated rpc_rqst structure and XDR buffers + * associated with this rpc_task. + */ +void xprt_free_bc_request(struct rpc_rqst *req) +{ + struct rpc_xprt *xprt = req->rq_xprt; + + dprintk("RPC: free backchannel req=%p\n", req); + + smp_mb__before_clear_bit(); + BUG_ON(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state)); + clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); + smp_mb__after_clear_bit(); + + if (!xprt_need_to_requeue(xprt)) { + /* + * The last remaining session was destroyed while this + * entry was in use. Free the entry and don't attempt + * to add back to the list because there is no need to + * have anymore preallocated entries. + */ + dprintk("RPC: Last session removed req=%p\n", req); + xprt_free_allocation(req); + return; + } + + /* + * Return it to the list of preallocations so that it + * may be reused by a new callback request. + */ + spin_lock_bh(&xprt->bc_pa_lock); + list_add(&req->rq_bc_pa_list, &xprt->bc_pa_list); + spin_unlock_bh(&xprt->bc_pa_lock); +} + +#endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/bc_svc.c b/net/sunrpc/bc_svc.c new file mode 100644 index 00000000000..13f214f5312 --- /dev/null +++ b/net/sunrpc/bc_svc.c @@ -0,0 +1,81 @@ +/****************************************************************************** + +(c) 2007 Network Appliance, Inc. All Rights Reserved. +(c) 2009 NetApp. All Rights Reserved. + +NetApp provides this source code under the GPL v2 License. +The GPL v2 license is available at +http://opensource.org/licenses/gpl-license.php. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR +CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, +EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, +PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +******************************************************************************/ + +/* + * The NFSv4.1 callback service helper routines. + * They implement the transport level processing required to send the + * reply over an existing open connection previously established by the client. + */ + +#if defined(CONFIG_NFS_V4_1) + +#include <linux/module.h> + +#include <linux/sunrpc/xprt.h> +#include <linux/sunrpc/sched.h> +#include <linux/sunrpc/bc_xprt.h> + +#define RPCDBG_FACILITY RPCDBG_SVCDSP + +void bc_release_request(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + + dprintk("RPC: bc_release_request: task= %p\n", task); + + /* + * Release this request only if it's a backchannel + * preallocated request + */ + if (!bc_prealloc(req)) + return; + xprt_free_bc_request(req); +} + +/* Empty callback ops */ +static const struct rpc_call_ops nfs41_callback_ops = { +}; + + +/* + * Send the callback reply + */ +int bc_send(struct rpc_rqst *req) +{ + struct rpc_task *task; + int ret; + + dprintk("RPC: bc_send req= %p\n", req); + task = rpc_run_bc_task(req, &nfs41_callback_ops); + if (IS_ERR(task)) + ret = PTR_ERR(task); + else { + BUG_ON(atomic_read(&task->tk_count) != 1); + ret = task->tk_status; + rpc_put_task(task); + } + return ret; + dprintk("RPC: bc_send ret= %d \n", ret); +} + +#endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 20029a79a5d..ff0c23053d2 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -488,7 +488,7 @@ static void do_cache_clean(struct work_struct *work) { int delay = 5; if (cache_clean() == -1) - delay = 30*HZ; + delay = round_jiffies_relative(30*HZ); if (list_empty(&cache_list)) delay = 0; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 5abab094441..ebfcf9b8990 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -28,7 +28,6 @@ #include <linux/kallsyms.h> #include <linux/mm.h> #include <linux/slab.h> -#include <linux/smp_lock.h> #include <linux/utsname.h> #include <linux/workqueue.h> #include <linux/in6.h> @@ -36,7 +35,9 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/metrics.h> +#include <linux/sunrpc/bc_xprt.h> +#include "sunrpc.h" #ifdef RPC_DEBUG # define RPCDBG_FACILITY RPCDBG_CALL @@ -63,6 +64,9 @@ static void call_decode(struct rpc_task *task); static void call_bind(struct rpc_task *task); static void call_bind_status(struct rpc_task *task); static void call_transmit(struct rpc_task *task); +#if defined(CONFIG_NFS_V4_1) +static void call_bc_transmit(struct rpc_task *task); +#endif /* CONFIG_NFS_V4_1 */ static void call_status(struct rpc_task *task); static void call_transmit_status(struct rpc_task *task); static void call_refresh(struct rpc_task *task); @@ -613,6 +617,50 @@ rpc_call_async(struct rpc_clnt *clnt, const struct rpc_message *msg, int flags, } EXPORT_SYMBOL_GPL(rpc_call_async); +#if defined(CONFIG_NFS_V4_1) +/** + * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run + * rpc_execute against it + * @ops: RPC call ops + */ +struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, + const struct rpc_call_ops *tk_ops) +{ + struct rpc_task *task; + struct xdr_buf *xbufp = &req->rq_snd_buf; + struct rpc_task_setup task_setup_data = { + .callback_ops = tk_ops, + }; + + dprintk("RPC: rpc_run_bc_task req= %p\n", req); + /* + * Create an rpc_task to send the data + */ + task = rpc_new_task(&task_setup_data); + if (!task) { + xprt_free_bc_request(req); + goto out; + } + task->tk_rqstp = req; + + /* + * Set up the xdr_buf length. + * This also indicates that the buffer is XDR encoded already. + */ + xbufp->len = xbufp->head[0].iov_len + xbufp->page_len + + xbufp->tail[0].iov_len; + + task->tk_action = call_bc_transmit; + atomic_inc(&task->tk_count); + BUG_ON(atomic_read(&task->tk_count) != 2); + rpc_execute(task); + +out: + dprintk("RPC: rpc_run_bc_task: task= %p\n", task); + return task; +} +#endif /* CONFIG_NFS_V4_1 */ + void rpc_call_start(struct rpc_task *task) { @@ -695,6 +743,19 @@ void rpc_force_rebind(struct rpc_clnt *clnt) EXPORT_SYMBOL_GPL(rpc_force_rebind); /* + * Restart an (async) RPC call from the call_prepare state. + * Usually called from within the exit handler. + */ +void +rpc_restart_call_prepare(struct rpc_task *task) +{ + if (RPC_ASSASSINATED(task)) + return; + task->tk_action = rpc_prepare_task; +} +EXPORT_SYMBOL_GPL(rpc_restart_call_prepare); + +/* * Restart an (async) RPC call. Usually called from within the * exit handler. */ @@ -1085,7 +1146,7 @@ call_transmit(struct rpc_task *task) * in order to allow access to the socket to other RPC requests. */ call_transmit_status(task); - if (task->tk_msg.rpc_proc->p_decode != NULL) + if (rpc_reply_expected(task)) return; task->tk_action = rpc_exit_task; rpc_wake_up_queued_task(&task->tk_xprt->pending, task); @@ -1120,6 +1181,72 @@ call_transmit_status(struct rpc_task *task) } } +#if defined(CONFIG_NFS_V4_1) +/* + * 5b. Send the backchannel RPC reply. On error, drop the reply. In + * addition, disconnect on connectivity errors. + */ +static void +call_bc_transmit(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + + BUG_ON(task->tk_status != 0); + task->tk_status = xprt_prepare_transmit(task); + if (task->tk_status == -EAGAIN) { + /* + * Could not reserve the transport. Try again after the + * transport is released. + */ + task->tk_status = 0; + task->tk_action = call_bc_transmit; + return; + } + + task->tk_action = rpc_exit_task; + if (task->tk_status < 0) { + printk(KERN_NOTICE "RPC: Could not send backchannel reply " + "error: %d\n", task->tk_status); + return; + } + + xprt_transmit(task); + xprt_end_transmit(task); + dprint_status(task); + switch (task->tk_status) { + case 0: + /* Success */ + break; + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -ETIMEDOUT: + /* + * Problem reaching the server. Disconnect and let the + * forechannel reestablish the connection. The server will + * have to retransmit the backchannel request and we'll + * reprocess it. Since these ops are idempotent, there's no + * need to cache our reply at this time. + */ + printk(KERN_NOTICE "RPC: Could not send backchannel reply " + "error: %d\n", task->tk_status); + xprt_conditional_disconnect(task->tk_xprt, + req->rq_connect_cookie); + break; + default: + /* + * We were unable to reply and will have to drop the + * request. The server should reconnect and retransmit. + */ + BUG_ON(task->tk_status == -EAGAIN); + printk(KERN_NOTICE "RPC: Could not send backchannel reply " + "error: %d\n", task->tk_status); + break; + } + rpc_wake_up_queued_task(&req->rq_xprt->pending, task); +} +#endif /* CONFIG_NFS_V4_1 */ + /* * 6. Sort out the RPC call status */ @@ -1130,8 +1257,8 @@ call_status(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; int status; - if (req->rq_received > 0 && !req->rq_bytes_sent) - task->tk_status = req->rq_received; + if (req->rq_reply_bytes_recvd > 0 && !req->rq_bytes_sent) + task->tk_status = req->rq_reply_bytes_recvd; dprint_status(task); @@ -1248,7 +1375,7 @@ call_decode(struct rpc_task *task) /* * Ensure that we see all writes made by xprt_complete_rqst() - * before it changed req->rq_received. + * before it changed req->rq_reply_bytes_recvd. */ smp_rmb(); req->rq_rcv_buf.len = req->rq_private_buf.len; @@ -1289,7 +1416,7 @@ out_retry: task->tk_status = 0; /* Note: rpc_verify_header() may have freed the RPC slot */ if (task->tk_rqstp == req) { - req->rq_received = req->rq_rcv_buf.len = 0; + req->rq_reply_bytes_recvd = req->rq_rcv_buf.len = 0; if (task->tk_client->cl_discrtry) xprt_conditional_disconnect(task->tk_xprt, req->rq_connect_cookie); @@ -1377,13 +1504,14 @@ rpc_verify_header(struct rpc_task *task) } if ((len -= 3) < 0) goto out_overflow; - p += 1; /* skip XID */ + p += 1; /* skip XID */ if ((n = ntohl(*p++)) != RPC_REPLY) { dprintk("RPC: %5u %s: not an RPC reply: %x\n", - task->tk_pid, __func__, n); + task->tk_pid, __func__, n); goto out_garbage; } + if ((n = ntohl(*p++)) != RPC_MSG_ACCEPTED) { if (--len < 0) goto out_overflow; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index ff50a054686..8f459abe97c 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -16,7 +16,6 @@ #include <linux/slab.h> #include <linux/mempool.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/spinlock.h> #include <linux/mutex.h> @@ -569,7 +568,7 @@ EXPORT_SYMBOL_GPL(rpc_delay); /* * Helper to call task->tk_ops->rpc_call_prepare */ -static void rpc_prepare_task(struct rpc_task *task) +void rpc_prepare_task(struct rpc_task *task) { task->tk_ops->rpc_call_prepare(task, task->tk_calldata); } diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 1ef6e46d9da..1b4e6791ecf 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -141,12 +141,14 @@ EXPORT_SYMBOL_GPL(rpc_free_iostats); void rpc_count_iostats(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; - struct rpc_iostats *stats = task->tk_client->cl_metrics; + struct rpc_iostats *stats; struct rpc_iostats *op_metrics; long rtt, execute, queue; - if (!stats || !req) + if (!task->tk_client || !task->tk_client->cl_metrics || !req) return; + + stats = task->tk_client->cl_metrics; op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx]; op_metrics->om_ops++; @@ -154,7 +156,7 @@ void rpc_count_iostats(struct rpc_task *task) op_metrics->om_timeouts += task->tk_timeouts; op_metrics->om_bytes_sent += task->tk_bytes_sent; - op_metrics->om_bytes_recv += req->rq_received; + op_metrics->om_bytes_recv += req->rq_reply_bytes_recvd; queue = (long)req->rq_xtime - task->tk_start; if (queue < 0) diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h new file mode 100644 index 00000000000..5d9dd742264 --- /dev/null +++ b/net/sunrpc/sunrpc.h @@ -0,0 +1,37 @@ +/****************************************************************************** + +(c) 2008 NetApp. All Rights Reserved. + +NetApp provides this source code under the GPL v2 License. +The GPL v2 license is available at +http://opensource.org/licenses/gpl-license.php. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR +CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, +EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, +PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +******************************************************************************/ + +/* + * Functions and macros used internally by RPC + */ + +#ifndef _NET_SUNRPC_SUNRPC_H +#define _NET_SUNRPC_SUNRPC_H + +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); +} + +#endif /* _NET_SUNRPC_SUNRPC_H */ + diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 843629f5576..adaa81982f7 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -66,6 +66,7 @@ cleanup_sunrpc(void) #ifdef CONFIG_PROC_FS rpc_proc_exit(); #endif + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_LICENSE("GPL"); module_init(init_sunrpc); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 8847add6ca1..952f206ff30 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -25,6 +25,7 @@ #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/bc_xprt.h> #define RPCDBG_FACILITY RPCDBG_SVCDSP @@ -124,7 +125,7 @@ svc_pool_map_choose_mode(void) { unsigned int node; - if (num_online_nodes() > 1) { + if (nr_online_nodes > 1) { /* * Actually have multiple NUMA nodes, * so split pools on NUMA node boundaries @@ -486,6 +487,10 @@ svc_destroy(struct svc_serv *serv) if (svc_serv_is_pooled(serv)) svc_pool_map_put(); +#if defined(CONFIG_NFS_V4_1) + svc_sock_destroy(serv->bc_xprt); +#endif /* CONFIG_NFS_V4_1 */ + svc_unregister(serv); kfree(serv->sv_pools); kfree(serv); @@ -970,20 +975,18 @@ svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) } /* - * Process the RPC request. + * Common routine for processing the RPC request. */ -int -svc_process(struct svc_rqst *rqstp) +static int +svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) { struct svc_program *progp; struct svc_version *versp = NULL; /* compiler food */ struct svc_procedure *procp = NULL; - struct kvec * argv = &rqstp->rq_arg.head[0]; - struct kvec * resv = &rqstp->rq_res.head[0]; struct svc_serv *serv = rqstp->rq_server; kxdrproc_t xdr; __be32 *statp; - u32 dir, prog, vers, proc; + u32 prog, vers, proc; __be32 auth_stat, rpc_stat; int auth_res; __be32 *reply_statp; @@ -993,19 +996,6 @@ svc_process(struct svc_rqst *rqstp) if (argv->iov_len < 6*4) goto err_short_len; - /* setup response xdr_buf. - * Initially it has just one page - */ - rqstp->rq_resused = 1; - resv->iov_base = page_address(rqstp->rq_respages[0]); - resv->iov_len = 0; - rqstp->rq_res.pages = rqstp->rq_respages + 1; - rqstp->rq_res.len = 0; - rqstp->rq_res.page_base = 0; - rqstp->rq_res.page_len = 0; - rqstp->rq_res.buflen = PAGE_SIZE; - rqstp->rq_res.tail[0].iov_base = NULL; - rqstp->rq_res.tail[0].iov_len = 0; /* Will be turned off only in gss privacy case: */ rqstp->rq_splice_ok = 1; /* Will be turned off only when NFSv4 Sessions are used */ @@ -1014,17 +1004,13 @@ svc_process(struct svc_rqst *rqstp) /* Setup reply header */ rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); - rqstp->rq_xid = svc_getu32(argv); svc_putu32(resv, rqstp->rq_xid); - dir = svc_getnl(argv); vers = svc_getnl(argv); /* First words of reply: */ svc_putnl(resv, 1); /* REPLY */ - if (dir != 0) /* direction != CALL */ - goto err_bad_dir; if (vers != 2) /* RPC version number */ goto err_bad_rpc; @@ -1147,7 +1133,7 @@ svc_process(struct svc_rqst *rqstp) sendit: if (svc_authorise(rqstp)) goto dropit; - return svc_send(rqstp); + return 1; /* Caller can now send it */ dropit: svc_authorise(rqstp); /* doesn't hurt to call this twice */ @@ -1161,12 +1147,6 @@ err_short_len: goto dropit; /* drop request */ -err_bad_dir: - svc_printk(rqstp, "bad direction %d, dropping request\n", dir); - - serv->sv_stats->rpcbadfmt++; - goto dropit; /* drop request */ - err_bad_rpc: serv->sv_stats->rpcbadfmt++; svc_putnl(resv, 1); /* REJECT */ @@ -1220,6 +1200,100 @@ err_bad: EXPORT_SYMBOL_GPL(svc_process); /* + * Process the RPC request. + */ +int +svc_process(struct svc_rqst *rqstp) +{ + struct kvec *argv = &rqstp->rq_arg.head[0]; + struct kvec *resv = &rqstp->rq_res.head[0]; + struct svc_serv *serv = rqstp->rq_server; + u32 dir; + int error; + + /* + * Setup response xdr_buf. + * Initially it has just one page + */ + rqstp->rq_resused = 1; + resv->iov_base = page_address(rqstp->rq_respages[0]); + resv->iov_len = 0; + rqstp->rq_res.pages = rqstp->rq_respages + 1; + rqstp->rq_res.len = 0; + rqstp->rq_res.page_base = 0; + rqstp->rq_res.page_len = 0; + rqstp->rq_res.buflen = PAGE_SIZE; + rqstp->rq_res.tail[0].iov_base = NULL; + rqstp->rq_res.tail[0].iov_len = 0; + + rqstp->rq_xid = svc_getu32(argv); + + dir = svc_getnl(argv); + if (dir != 0) { + /* direction != CALL */ + svc_printk(rqstp, "bad direction %d, dropping request\n", dir); + serv->sv_stats->rpcbadfmt++; + svc_drop(rqstp); + return 0; + } + + error = svc_process_common(rqstp, argv, resv); + if (error <= 0) + return error; + + return svc_send(rqstp); +} + +#if defined(CONFIG_NFS_V4_1) +/* + * Process a backchannel RPC request that arrived over an existing + * outbound connection + */ +int +bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, + struct svc_rqst *rqstp) +{ + struct kvec *argv = &rqstp->rq_arg.head[0]; + struct kvec *resv = &rqstp->rq_res.head[0]; + int error; + + /* Build the svc_rqst used by the common processing routine */ + rqstp->rq_xprt = serv->bc_xprt; + rqstp->rq_xid = req->rq_xid; + rqstp->rq_prot = req->rq_xprt->prot; + rqstp->rq_server = serv; + + rqstp->rq_addrlen = sizeof(req->rq_xprt->addr); + memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen); + memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg)); + memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res)); + + /* reset result send buffer "put" position */ + resv->iov_len = 0; + + if (rqstp->rq_prot != IPPROTO_TCP) { + printk(KERN_ERR "No support for Non-TCP transports!\n"); + BUG(); + } + + /* + * Skip the next two words because they've already been + * processed in the trasport + */ + svc_getu32(argv); /* XID */ + svc_getnl(argv); /* CALLDIR */ + + error = svc_process_common(rqstp, argv, resv); + if (error <= 0) + return error; + + memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); + return bc_send(req); +} +EXPORT_SYMBOL(bc_svc_process); +#endif /* CONFIG_NFS_V4_1 */ + +/* * Return (transport-specific) limit on the rpc payload. */ u32 svc_max_payload(const struct svc_rqst *rqstp) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index c200d92e57e..27d44332f01 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -5,12 +5,14 @@ */ #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/errno.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <net/sock.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svc_xprt.h> +#include <linux/sunrpc/svcsock.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -1097,36 +1099,58 @@ struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, } EXPORT_SYMBOL_GPL(svc_find_xprt); -/* - * Format a buffer with a list of the active transports. A zero for - * the buflen parameter disables target buffer overflow checking. +static int svc_one_xprt_name(const struct svc_xprt *xprt, + char *pos, int remaining) +{ + int len; + + len = snprintf(pos, remaining, "%s %u\n", + xprt->xpt_class->xcl_name, + svc_xprt_local_port(xprt)); + if (len >= remaining) + return -ENAMETOOLONG; + return len; +} + +/** + * svc_xprt_names - format a buffer with a list of transport names + * @serv: pointer to an RPC service + * @buf: pointer to a buffer to be filled in + * @buflen: length of buffer to be filled in + * + * Fills in @buf with a string containing a list of transport names, + * each name terminated with '\n'. + * + * Returns positive length of the filled-in string on success; otherwise + * a negative errno value is returned if an error occurs. */ -int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen) +int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen) { struct svc_xprt *xprt; - char xprt_str[64]; - int totlen = 0; - int len; + int len, totlen; + char *pos; /* Sanity check args */ if (!serv) return 0; spin_lock_bh(&serv->sv_lock); + + pos = buf; + totlen = 0; list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) { - len = snprintf(xprt_str, sizeof(xprt_str), - "%s %d\n", xprt->xpt_class->xcl_name, - svc_xprt_local_port(xprt)); - /* If the string was truncated, replace with error string */ - if (len >= sizeof(xprt_str)) - strcpy(xprt_str, "name-too-long\n"); - /* Don't overflow buffer */ - len = strlen(xprt_str); - if (buflen && (len + totlen >= buflen)) + len = svc_one_xprt_name(xprt, pos, buflen - totlen); + if (len < 0) { + *buf = '\0'; + totlen = len; + } + if (len <= 0) break; - strcpy(buf+totlen, xprt_str); + + pos += len; totlen += len; } + spin_unlock_bh(&serv->sv_lock); return totlen; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 9d504234af4..23128ee191a 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -240,42 +240,76 @@ out: /* * Report socket names for nfsdfs */ -static int one_sock_name(char *buf, struct svc_sock *svsk) +static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining) { + const struct sock *sk = svsk->sk_sk; + const char *proto_name = sk->sk_protocol == IPPROTO_UDP ? + "udp" : "tcp"; int len; - switch(svsk->sk_sk->sk_family) { - case AF_INET: - len = sprintf(buf, "ipv4 %s %pI4 %d\n", - svsk->sk_sk->sk_protocol == IPPROTO_UDP ? - "udp" : "tcp", - &inet_sk(svsk->sk_sk)->rcv_saddr, - inet_sk(svsk->sk_sk)->num); + switch (sk->sk_family) { + case PF_INET: + len = snprintf(buf, remaining, "ipv4 %s %pI4 %d\n", + proto_name, + &inet_sk(sk)->rcv_saddr, + inet_sk(sk)->num); + break; + case PF_INET6: + len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n", + proto_name, + &inet6_sk(sk)->rcv_saddr, + inet_sk(sk)->num); break; default: - len = sprintf(buf, "*unknown-%d*\n", - svsk->sk_sk->sk_family); + len = snprintf(buf, remaining, "*unknown-%d*\n", + sk->sk_family); + } + + if (len >= remaining) { + *buf = '\0'; + return -ENAMETOOLONG; } return len; } -int -svc_sock_names(char *buf, struct svc_serv *serv, char *toclose) +/** + * svc_sock_names - construct a list of listener names in a string + * @serv: pointer to RPC service + * @buf: pointer to a buffer to fill in with socket names + * @buflen: size of the buffer to be filled + * @toclose: pointer to '\0'-terminated C string containing the name + * of a listener to be closed + * + * Fills in @buf with a '\n'-separated list of names of listener + * sockets. If @toclose is not NULL, the socket named by @toclose + * is closed, and is not included in the output list. + * + * Returns positive length of the socket name string, or a negative + * errno value on error. + */ +int svc_sock_names(struct svc_serv *serv, char *buf, const size_t buflen, + const char *toclose) { struct svc_sock *svsk, *closesk = NULL; int len = 0; if (!serv) return 0; + spin_lock_bh(&serv->sv_lock); list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list) { - int onelen = one_sock_name(buf+len, svsk); - if (toclose && strcmp(toclose, buf+len) == 0) + int onelen = svc_one_sock_name(svsk, buf + len, buflen - len); + if (onelen < 0) { + len = onelen; + break; + } + if (toclose && strcmp(toclose, buf + len) == 0) closesk = svsk; else len += onelen; } spin_unlock_bh(&serv->sv_lock); + if (closesk) /* Should unregister with portmap, but you cannot * unregister just one protocol... @@ -346,6 +380,7 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd, sock->sk->sk_sndbuf = snd * 2; sock->sk->sk_rcvbuf = rcv * 2; sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK; + sock->sk->sk_write_space(sock->sk); release_sock(sock->sk); #endif } @@ -387,6 +422,15 @@ static void svc_write_space(struct sock *sk) } } +static void svc_tcp_write_space(struct sock *sk) +{ + struct socket *sock = sk->sk_socket; + + if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) + clear_bit(SOCK_NOSPACE, &sock->flags); + svc_write_space(sk); +} + /* * Copy the UDP datagram's destination address to the rqstp structure. * The 'destination' address in this case is the address to which the @@ -427,13 +471,14 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) long all[SVC_PKTINFO_SPACE / sizeof(long)]; } buffer; struct cmsghdr *cmh = &buffer.hdr; - int err, len; struct msghdr msg = { .msg_name = svc_addr(rqstp), .msg_control = cmh, .msg_controllen = sizeof(buffer), .msg_flags = MSG_DONTWAIT, }; + size_t len; + int err; if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags)) /* udp sockets need large rcvbuf as all pending @@ -465,8 +510,8 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) return -EAGAIN; } len = svc_addr_len(svc_addr(rqstp)); - if (len < 0) - return len; + if (len == 0) + return -EAFNOSUPPORT; rqstp->rq_addrlen = len; if (skb->tstamp.tv64 == 0) { skb->tstamp = ktime_get_real(); @@ -980,25 +1025,16 @@ static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp) static int svc_tcp_has_wspace(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - struct svc_serv *serv = svsk->sk_xprt.xpt_server; + struct svc_serv *serv = svsk->sk_xprt.xpt_server; int required; - int wspace; - /* - * Set the SOCK_NOSPACE flag before checking the available - * sock space. - */ + if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) + return 1; + required = atomic_read(&xprt->xpt_reserved) + serv->sv_max_mesg; + if (sk_stream_wspace(svsk->sk_sk) >= required) + return 1; set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); - required = atomic_read(&svsk->sk_xprt.xpt_reserved) + serv->sv_max_mesg; - wspace = sk_stream_wspace(svsk->sk_sk); - - if (wspace < sk_stream_min_wspace(svsk->sk_sk)) - return 0; - if (required * 2 > wspace) - return 0; - - clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); - return 1; + return 0; } static struct svc_xprt *svc_tcp_create(struct svc_serv *serv, @@ -1054,7 +1090,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) dprintk("setting up TCP socket for reading\n"); sk->sk_state_change = svc_tcp_state_change; sk->sk_data_ready = svc_tcp_data_ready; - sk->sk_write_space = svc_write_space; + sk->sk_write_space = svc_tcp_write_space; svsk->sk_reclen = 0; svsk->sk_tcplen = 0; @@ -1148,9 +1184,19 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } -int svc_addsock(struct svc_serv *serv, - int fd, - char *name_return) +/** + * svc_addsock - add a listener socket to an RPC service + * @serv: pointer to RPC service to which to add a new listener + * @fd: file descriptor of the new listener + * @name_return: pointer to buffer to fill in with name of listener + * @len: size of the buffer + * + * Fills in socket name and returns positive length of name if successful. + * Name is terminated with '\n'. On error, returns a negative errno + * value. + */ +int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, + const size_t len) { int err = 0; struct socket *so = sockfd_lookup(fd, &err); @@ -1190,7 +1236,7 @@ int svc_addsock(struct svc_serv *serv, sockfd_put(so); return err; } - return one_sock_name(name_return, svsk); + return svc_one_sock_name(svsk, name_return, len); } EXPORT_SYMBOL_GPL(svc_addsock); @@ -1327,3 +1373,42 @@ static void svc_sock_free(struct svc_xprt *xprt) sock_release(svsk->sk_sock); kfree(svsk); } + +/* + * Create a svc_xprt. + * + * For internal use only (e.g. nfsv4.1 backchannel). + * Callers should typically use the xpo_create() method. + */ +struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot) +{ + struct svc_sock *svsk; + struct svc_xprt *xprt = NULL; + + dprintk("svc: %s\n", __func__); + svsk = kzalloc(sizeof(*svsk), GFP_KERNEL); + if (!svsk) + goto out; + + xprt = &svsk->sk_xprt; + if (prot == IPPROTO_TCP) + svc_xprt_init(&svc_tcp_class, xprt, serv); + else if (prot == IPPROTO_UDP) + svc_xprt_init(&svc_udp_class, xprt, serv); + else + BUG(); +out: + dprintk("svc: %s return %p\n", __func__, xprt); + return xprt; +} +EXPORT_SYMBOL_GPL(svc_sock_create); + +/* + * Destroy a svc_sock. + */ +void svc_sock_destroy(struct svc_xprt *xprt) +{ + if (xprt) + kfree(container_of(xprt, struct svc_sock, sk_xprt)); +} +EXPORT_SYMBOL_GPL(svc_sock_destroy); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 06ca058572f..f412a852bc7 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -12,8 +12,9 @@ * - Next, the caller puts together the RPC message, stuffs it into * the request struct, and calls xprt_transmit(). * - xprt_transmit sends the message and installs the caller on the - * transport's wait list. At the same time, it installs a timer that - * is run after the packet's timeout has expired. + * transport's wait list. At the same time, if a reply is expected, + * it installs a timer that is run after the packet's timeout has + * expired. * - When a packet arrives, the data_ready handler walks the list of * pending requests for that transport. If a matching XID is found, the * caller is woken up, and the timer removed. @@ -46,6 +47,8 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/metrics.h> +#include "sunrpc.h" + /* * Local variables */ @@ -192,8 +195,8 @@ EXPORT_SYMBOL_GPL(xprt_load_transport); */ int xprt_reserve_xprt(struct rpc_task *task) { - struct rpc_xprt *xprt = task->tk_xprt; struct rpc_rqst *req = task->tk_rqstp; + struct rpc_xprt *xprt = req->rq_xprt; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) { if (task == xprt->snd_task) @@ -803,9 +806,10 @@ void xprt_complete_rqst(struct rpc_task *task, int copied) list_del_init(&req->rq_list); req->rq_private_buf.len = copied; - /* Ensure all writes are done before we update req->rq_received */ + /* Ensure all writes are done before we update */ + /* req->rq_reply_bytes_recvd */ smp_wmb(); - req->rq_received = copied; + req->rq_reply_bytes_recvd = copied; rpc_wake_up_queued_task(&xprt->pending, task); } EXPORT_SYMBOL_GPL(xprt_complete_rqst); @@ -820,7 +824,7 @@ static void xprt_timer(struct rpc_task *task) dprintk("RPC: %5u xprt_timer\n", task->tk_pid); spin_lock_bh(&xprt->transport_lock); - if (!req->rq_received) { + if (!req->rq_reply_bytes_recvd) { if (xprt->ops->timer) xprt->ops->timer(task); } else @@ -842,8 +846,8 @@ int xprt_prepare_transmit(struct rpc_task *task) dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid); spin_lock_bh(&xprt->transport_lock); - if (req->rq_received && !req->rq_bytes_sent) { - err = req->rq_received; + if (req->rq_reply_bytes_recvd && !req->rq_bytes_sent) { + err = req->rq_reply_bytes_recvd; goto out_unlock; } if (!xprt->ops->reserve_xprt(task)) @@ -855,7 +859,7 @@ out_unlock: void xprt_end_transmit(struct rpc_task *task) { - xprt_release_write(task->tk_xprt, task); + xprt_release_write(task->tk_rqstp->rq_xprt, task); } /** @@ -872,8 +876,11 @@ void xprt_transmit(struct rpc_task *task) dprintk("RPC: %5u xprt_transmit(%u)\n", task->tk_pid, req->rq_slen); - if (!req->rq_received) { - if (list_empty(&req->rq_list)) { + if (!req->rq_reply_bytes_recvd) { + if (list_empty(&req->rq_list) && rpc_reply_expected(task)) { + /* + * Add to the list only if we're expecting a reply + */ spin_lock_bh(&xprt->transport_lock); /* Update the softirq receive buffer */ memcpy(&req->rq_private_buf, &req->rq_rcv_buf, @@ -908,8 +915,13 @@ void xprt_transmit(struct rpc_task *task) /* Don't race with disconnect */ if (!xprt_connected(xprt)) task->tk_status = -ENOTCONN; - else if (!req->rq_received) + else if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) { + /* + * Sleep on the pending queue since + * we're expecting a reply. + */ rpc_sleep_on(&xprt->pending, task, xprt_timer); + } spin_unlock_bh(&xprt->transport_lock); } @@ -982,11 +994,17 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) */ void xprt_release(struct rpc_task *task) { - struct rpc_xprt *xprt = task->tk_xprt; + struct rpc_xprt *xprt; struct rpc_rqst *req; + int is_bc_request; if (!(req = task->tk_rqstp)) return; + + /* Preallocated backchannel request? */ + is_bc_request = bc_prealloc(req); + + xprt = req->rq_xprt; rpc_count_iostats(task); spin_lock_bh(&xprt->transport_lock); xprt->ops->release_xprt(xprt, task); @@ -999,10 +1017,19 @@ void xprt_release(struct rpc_task *task) mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); spin_unlock_bh(&xprt->transport_lock); - xprt->ops->buf_free(req->rq_buffer); + if (!bc_prealloc(req)) + xprt->ops->buf_free(req->rq_buffer); task->tk_rqstp = NULL; if (req->rq_release_snd_buf) req->rq_release_snd_buf(req); + + /* + * Early exit if this is a backchannel preallocated request. + * There is no need to have it added to the RPC slot list. + */ + if (is_bc_request) + return; + memset(req, 0, sizeof(*req)); /* mark unused */ dprintk("RPC: %5u release request %p\n", task->tk_pid, req); @@ -1049,6 +1076,11 @@ found: INIT_LIST_HEAD(&xprt->free); INIT_LIST_HEAD(&xprt->recv); +#if defined(CONFIG_NFS_V4_1) + spin_lock_init(&xprt->bc_pa_lock); + INIT_LIST_HEAD(&xprt->bc_pa_list); +#endif /* CONFIG_NFS_V4_1 */ + INIT_WORK(&xprt->task_cleanup, xprt_autoclose); setup_timer(&xprt->timer, xprt_init_autodisconnect, (unsigned long)xprt); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 42a6f9f2028..9e884383134 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -397,14 +397,14 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt, if (!ch) return 0; - /* Allocate temporary reply and chunk maps */ - rpl_map = svc_rdma_get_req_map(); - chl_map = svc_rdma_get_req_map(); - svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count); if (ch_count > RPCSVC_MAXPAGES) return -EINVAL; + /* Allocate temporary reply and chunk maps */ + rpl_map = svc_rdma_get_req_map(); + chl_map = svc_rdma_get_req_map(); + if (!xprt->sc_frmr_pg_list_len) sge_count = map_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp, rpl_map, chl_map, ch_count, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e1859614601..83c73c4d017 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -34,6 +34,9 @@ #include <linux/sunrpc/sched.h> #include <linux/sunrpc/xprtsock.h> #include <linux/file.h> +#ifdef CONFIG_NFS_V4_1 +#include <linux/sunrpc/bc_xprt.h> +#endif #include <net/sock.h> #include <net/checksum.h> @@ -270,6 +273,13 @@ struct sock_xprt { #define TCP_RCV_COPY_FRAGHDR (1UL << 1) #define TCP_RCV_COPY_XID (1UL << 2) #define TCP_RCV_COPY_DATA (1UL << 3) +#define TCP_RCV_READ_CALLDIR (1UL << 4) +#define TCP_RCV_COPY_CALLDIR (1UL << 5) + +/* + * TCP RPC flags + */ +#define TCP_RPC_REPLY (1UL << 6) static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt) { @@ -918,7 +928,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) UDPX_INC_STATS_BH(sk, UDP_MIB_INDATAGRAMS); /* Something worked... */ - dst_confirm(skb->dst); + dst_confirm(skb_dst(skb)); xprt_adjust_cwnd(task, copied); xprt_update_rtt(task); @@ -956,7 +966,7 @@ static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_rea transport->tcp_offset = 0; /* Sanity check of the record length */ - if (unlikely(transport->tcp_reclen < 4)) { + if (unlikely(transport->tcp_reclen < 8)) { dprintk("RPC: invalid TCP record fragment length\n"); xprt_force_disconnect(xprt); return; @@ -991,33 +1001,77 @@ static inline void xs_tcp_read_xid(struct sock_xprt *transport, struct xdr_skb_r if (used != len) return; transport->tcp_flags &= ~TCP_RCV_COPY_XID; - transport->tcp_flags |= TCP_RCV_COPY_DATA; + transport->tcp_flags |= TCP_RCV_READ_CALLDIR; transport->tcp_copied = 4; - dprintk("RPC: reading reply for XID %08x\n", + dprintk("RPC: reading %s XID %08x\n", + (transport->tcp_flags & TCP_RPC_REPLY) ? "reply for" + : "request with", ntohl(transport->tcp_xid)); xs_tcp_check_fraghdr(transport); } -static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) +static inline void xs_tcp_read_calldir(struct sock_xprt *transport, + struct xdr_skb_reader *desc) { - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - struct rpc_rqst *req; + size_t len, used; + u32 offset; + __be32 calldir; + + /* + * We want transport->tcp_offset to be 8 at the end of this routine + * (4 bytes for the xid and 4 bytes for the call/reply flag). + * When this function is called for the first time, + * transport->tcp_offset is 4 (after having already read the xid). + */ + offset = transport->tcp_offset - sizeof(transport->tcp_xid); + len = sizeof(calldir) - offset; + dprintk("RPC: reading CALL/REPLY flag (%Zu bytes)\n", len); + used = xdr_skb_read_bits(desc, &calldir, len); + transport->tcp_offset += used; + if (used != len) + return; + transport->tcp_flags &= ~TCP_RCV_READ_CALLDIR; + transport->tcp_flags |= TCP_RCV_COPY_CALLDIR; + transport->tcp_flags |= TCP_RCV_COPY_DATA; + /* + * We don't yet have the XDR buffer, so we will write the calldir + * out after we get the buffer from the 'struct rpc_rqst' + */ + if (ntohl(calldir) == RPC_REPLY) + transport->tcp_flags |= TCP_RPC_REPLY; + else + transport->tcp_flags &= ~TCP_RPC_REPLY; + dprintk("RPC: reading %s CALL/REPLY flag %08x\n", + (transport->tcp_flags & TCP_RPC_REPLY) ? + "reply for" : "request with", calldir); + xs_tcp_check_fraghdr(transport); +} + +static inline void xs_tcp_read_common(struct rpc_xprt *xprt, + struct xdr_skb_reader *desc, + struct rpc_rqst *req) +{ + struct sock_xprt *transport = + container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *rcvbuf; size_t len; ssize_t r; - /* Find and lock the request corresponding to this xid */ - spin_lock(&xprt->transport_lock); - req = xprt_lookup_rqst(xprt, transport->tcp_xid); - if (!req) { - transport->tcp_flags &= ~TCP_RCV_COPY_DATA; - dprintk("RPC: XID %08x request not found!\n", - ntohl(transport->tcp_xid)); - spin_unlock(&xprt->transport_lock); - return; + rcvbuf = &req->rq_private_buf; + + if (transport->tcp_flags & TCP_RCV_COPY_CALLDIR) { + /* + * Save the RPC direction in the XDR buffer + */ + __be32 calldir = transport->tcp_flags & TCP_RPC_REPLY ? + htonl(RPC_REPLY) : 0; + + memcpy(rcvbuf->head[0].iov_base + transport->tcp_copied, + &calldir, sizeof(calldir)); + transport->tcp_copied += sizeof(calldir); + transport->tcp_flags &= ~TCP_RCV_COPY_CALLDIR; } - rcvbuf = &req->rq_private_buf; len = desc->count; if (len > transport->tcp_reclen - transport->tcp_offset) { struct xdr_skb_reader my_desc; @@ -1054,7 +1108,7 @@ static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_rea "tcp_offset = %u, tcp_reclen = %u\n", xprt, transport->tcp_copied, transport->tcp_offset, transport->tcp_reclen); - goto out; + return; } dprintk("RPC: XID %08x read %Zd bytes\n", @@ -1070,11 +1124,125 @@ static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_rea transport->tcp_flags &= ~TCP_RCV_COPY_DATA; } -out: + return; +} + +/* + * Finds the request corresponding to the RPC xid and invokes the common + * tcp read code to read the data. + */ +static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, + struct xdr_skb_reader *desc) +{ + struct sock_xprt *transport = + container_of(xprt, struct sock_xprt, xprt); + struct rpc_rqst *req; + + dprintk("RPC: read reply XID %08x\n", ntohl(transport->tcp_xid)); + + /* Find and lock the request corresponding to this xid */ + spin_lock(&xprt->transport_lock); + req = xprt_lookup_rqst(xprt, transport->tcp_xid); + if (!req) { + dprintk("RPC: XID %08x request not found!\n", + ntohl(transport->tcp_xid)); + spin_unlock(&xprt->transport_lock); + return -1; + } + + xs_tcp_read_common(xprt, desc, req); + if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) xprt_complete_rqst(req->rq_task, transport->tcp_copied); + spin_unlock(&xprt->transport_lock); - xs_tcp_check_fraghdr(transport); + return 0; +} + +#if defined(CONFIG_NFS_V4_1) +/* + * Obtains an rpc_rqst previously allocated and invokes the common + * tcp read code to read the data. The result is placed in the callback + * queue. + * If we're unable to obtain the rpc_rqst we schedule the closing of the + * connection and return -1. + */ +static inline int xs_tcp_read_callback(struct rpc_xprt *xprt, + struct xdr_skb_reader *desc) +{ + struct sock_xprt *transport = + container_of(xprt, struct sock_xprt, xprt); + struct rpc_rqst *req; + + req = xprt_alloc_bc_request(xprt); + if (req == NULL) { + printk(KERN_WARNING "Callback slot table overflowed\n"); + xprt_force_disconnect(xprt); + return -1; + } + + req->rq_xid = transport->tcp_xid; + dprintk("RPC: read callback XID %08x\n", ntohl(req->rq_xid)); + xs_tcp_read_common(xprt, desc, req); + + if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) { + struct svc_serv *bc_serv = xprt->bc_serv; + + /* + * Add callback request to callback list. The callback + * service sleeps on the sv_cb_waitq waiting for new + * requests. Wake it up after adding enqueing the + * request. + */ + dprintk("RPC: add callback request to list\n"); + spin_lock(&bc_serv->sv_cb_lock); + list_add(&req->rq_bc_list, &bc_serv->sv_cb_list); + spin_unlock(&bc_serv->sv_cb_lock); + wake_up(&bc_serv->sv_cb_waitq); + } + + req->rq_private_buf.len = transport->tcp_copied; + + return 0; +} + +static inline int _xs_tcp_read_data(struct rpc_xprt *xprt, + struct xdr_skb_reader *desc) +{ + struct sock_xprt *transport = + container_of(xprt, struct sock_xprt, xprt); + + return (transport->tcp_flags & TCP_RPC_REPLY) ? + xs_tcp_read_reply(xprt, desc) : + xs_tcp_read_callback(xprt, desc); +} +#else +static inline int _xs_tcp_read_data(struct rpc_xprt *xprt, + struct xdr_skb_reader *desc) +{ + return xs_tcp_read_reply(xprt, desc); +} +#endif /* CONFIG_NFS_V4_1 */ + +/* + * Read data off the transport. This can be either an RPC_CALL or an + * RPC_REPLY. Relay the processing to helper functions. + */ +static void xs_tcp_read_data(struct rpc_xprt *xprt, + struct xdr_skb_reader *desc) +{ + struct sock_xprt *transport = + container_of(xprt, struct sock_xprt, xprt); + + if (_xs_tcp_read_data(xprt, desc) == 0) + xs_tcp_check_fraghdr(transport); + else { + /* + * The transport_lock protects the request handling. + * There's no need to hold it to update the tcp_flags. + */ + transport->tcp_flags &= ~TCP_RCV_COPY_DATA; + } } static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc) @@ -1114,9 +1282,14 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns xs_tcp_read_xid(transport, &desc); continue; } + /* Read in the call/reply flag */ + if (transport->tcp_flags & TCP_RCV_READ_CALLDIR) { + xs_tcp_read_calldir(transport, &desc); + continue; + } /* Read in the request data */ if (transport->tcp_flags & TCP_RCV_COPY_DATA) { - xs_tcp_read_request(xprt, &desc); + xs_tcp_read_data(xprt, &desc); continue; } /* Skip over any trailing bytes on short reads */ @@ -1792,6 +1965,7 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt, */ set_bit(XPRT_CONNECTION_CLOSE, &xprt->state); xprt_force_disconnect(xprt); + break; case -ECONNREFUSED: case -ECONNRESET: case -ENETUNREACH: @@ -2010,6 +2184,9 @@ static struct rpc_xprt_ops xs_tcp_ops = { .buf_free = rpc_free, .send_request = xs_tcp_send_request, .set_retrans_timeout = xprt_set_retrans_timeout_def, +#if defined(CONFIG_NFS_V4_1) + .release_request = bc_release_request, +#endif /* CONFIG_NFS_V4_1 */ .close = xs_tcp_close, .destroy = xs_destroy, .print_stats = xs_tcp_print_stats, diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index f72ba774c24..524ba5696d4 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -167,7 +167,7 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) tb_ptr->mtu = dev->mtu; tb_ptr->blocked = 0; tb_ptr->addr.type = htonl(TIPC_MEDIA_TYPE_ETH); - memcpy(&tb_ptr->addr.dev_addr, &dev->dev_addr, ETH_ALEN); + memcpy(&tb_ptr->addr.dev_addr, dev->dev_addr, ETH_ALEN); return 0; } diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index c387217bb23..3c57005e44d 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -68,7 +68,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) return 0; } -static struct genl_family family = { +static struct genl_family tipc_genl_family = { .id = GENL_ID_GENERATE, .name = TIPC_GENL_NAME, .version = TIPC_GENL_VERSION, @@ -76,39 +76,33 @@ static struct genl_family family = { .maxattr = 0, }; -static struct genl_ops ops = { +static struct genl_ops tipc_genl_ops = { .cmd = TIPC_GENL_CMD, .doit = handle_cmd, }; -static int family_registered = 0; +static int tipc_genl_family_registered; int tipc_netlink_start(void) { + int res; + res = genl_register_family_with_ops(&tipc_genl_family, + &tipc_genl_ops, 1); + if (res) { + err("Failed to register netlink interface\n"); + return res; + } - if (genl_register_family(&family)) - goto err; - - family_registered = 1; - - if (genl_register_ops(&family, &ops)) - goto err_unregister; - + tipc_genl_family_registered = 1; return 0; - - err_unregister: - genl_unregister_family(&family); - family_registered = 0; - err: - err("Failed to register netlink interface\n"); - return -EFAULT; } void tipc_netlink_stop(void) { - if (family_registered) { - genl_unregister_family(&family); - family_registered = 0; - } + if (!tipc_genl_family_registered) + return; + + genl_unregister_family(&tipc_genl_family); + tipc_genl_family_registered = 0; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 9dcc6e7f96e..fc3ebb90691 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -315,7 +315,7 @@ static void unix_write_space(struct sock *sk) { read_lock(&sk->sk_callback_lock); if (unix_writable(sk)) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_sync(sk->sk_sleep); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } @@ -1946,7 +1946,7 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) switch (cmd) { case SIOCOUTQ: - amount = atomic_read(&sk->sk_wmem_alloc); + amount = sk_wmem_alloc_get(sk); err = put_user(amount, (int __user *)arg); break; case SIOCINQ: @@ -1985,7 +1985,7 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table struct sock *sk = sock->sk; unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; /* exceptional events? */ @@ -2022,7 +2022,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk, *other; unsigned int mask, writable; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; /* exceptional events? */ @@ -2053,7 +2053,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, other = unix_peer_get(sk); if (other) { if (unix_peer(other) != sk) { - poll_wait(file, &unix_sk(other)->peer_wait, + sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); if (unix_recvq_full(other)) writable = 0; diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 466e2d22d25..258daa80ad9 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -48,6 +48,7 @@ #include <linux/kernel.h> #include <linux/module.h> /* support for loadable modules */ #include <linux/slab.h> /* kmalloc(), kfree() */ +#include <linux/smp_lock.h> #include <linux/mm.h> #include <linux/string.h> /* inline mem*, str* functions */ diff --git a/net/wimax/Kconfig b/net/wimax/Kconfig index 1b46747a5f5..e4d97ab476d 100644 --- a/net/wimax/Kconfig +++ b/net/wimax/Kconfig @@ -1,23 +1,10 @@ # # WiMAX LAN device configuration # -# Note the ugly 'depends on' on WIMAX: that disallows RFKILL to be a -# module if WIMAX is to be linked in. The WiMAX code is done in such a -# way that it doesn't require and explicit dependency on RFKILL in -# case an embedded system wants to rip it out. -# -# As well, enablement of the RFKILL code means we need the INPUT layer -# support to inject events coming from hw rfkill switches. That -# dependency could be killed if input.h provided appropriate means to -# work when input is disabled. - -comment "WiMAX Wireless Broadband support requires CONFIG_INPUT enabled" - depends on INPUT = n && RFKILL != n menuconfig WIMAX tristate "WiMAX Wireless Broadband support" - depends on (y && RFKILL != m) || m - depends on (INPUT && RFKILL != n) || RFKILL = n + depends on RFKILL || !RFKILL help Select to configure support for devices that provide diff --git a/net/wimax/Makefile b/net/wimax/Makefile index 5b80b941c2c..8f1510d0cc2 100644 --- a/net/wimax/Makefile +++ b/net/wimax/Makefile @@ -6,6 +6,7 @@ wimax-y := \ op-msg.o \ op-reset.o \ op-rfkill.o \ + op-state-get.o \ stack.o wimax-$(CONFIG_DEBUG_FS) += debugfs.o diff --git a/net/wimax/debug-levels.h b/net/wimax/debug-levels.h index 1c29123a3aa..0975adba6b7 100644 --- a/net/wimax/debug-levels.h +++ b/net/wimax/debug-levels.h @@ -36,6 +36,7 @@ enum d_module { D_SUBMODULE_DECLARE(op_msg), D_SUBMODULE_DECLARE(op_reset), D_SUBMODULE_DECLARE(op_rfkill), + D_SUBMODULE_DECLARE(op_state_get), D_SUBMODULE_DECLARE(stack), }; diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c index 94d216a4640..6c9bedb7431 100644 --- a/net/wimax/debugfs.c +++ b/net/wimax/debugfs.c @@ -61,6 +61,7 @@ int wimax_debugfs_add(struct wimax_dev *wimax_dev) __debugfs_register("wimax_dl_", op_msg, dentry); __debugfs_register("wimax_dl_", op_reset, dentry); __debugfs_register("wimax_dl_", op_rfkill, dentry); + __debugfs_register("wimax_dl_", op_state_get, dentry); __debugfs_register("wimax_dl_", stack, dentry); result = 0; out: diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c index 9ad4d893a56..d631a17186b 100644 --- a/net/wimax/op-msg.c +++ b/net/wimax/op-msg.c @@ -108,6 +108,12 @@ * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as * wimax_msg_send() depends on skb->data being placed at the * beginning of the user message. + * + * Unlike other WiMAX stack calls, this call can be used way early, + * even before wimax_dev_add() is called, as long as the + * wimax_dev->net_dev pointer is set to point to a proper + * net_dev. This is so that drivers can use it early in case they need + * to send stuff around or communicate with user space. */ struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev, const char *pipe_name, @@ -115,7 +121,7 @@ struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev, gfp_t gfp_flags) { int result; - struct device *dev = wimax_dev->net_dev->dev.parent; + struct device *dev = wimax_dev_to_dev(wimax_dev); size_t msg_size; void *genl_msg; struct sk_buff *skb; @@ -161,7 +167,6 @@ error_genlmsg_put: error_new: nlmsg_free(skb); return ERR_PTR(result); - } EXPORT_SYMBOL_GPL(wimax_msg_alloc); @@ -256,10 +261,16 @@ EXPORT_SYMBOL_GPL(wimax_msg_len); * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as * wimax_msg_send() depends on skb->data being placed at the * beginning of the user message. + * + * Unlike other WiMAX stack calls, this call can be used way early, + * even before wimax_dev_add() is called, as long as the + * wimax_dev->net_dev pointer is set to point to a proper + * net_dev. This is so that drivers can use it early in case they need + * to send stuff around or communicate with user space. */ int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb) { - struct device *dev = wimax_dev->net_dev->dev.parent; + struct device *dev = wimax_dev_to_dev(wimax_dev); void *msg = skb->data; size_t size = skb->len; might_sleep(); diff --git a/net/wimax/op-rfkill.c b/net/wimax/op-rfkill.c index 2b75aee0421..70ef4df863b 100644 --- a/net/wimax/op-rfkill.c +++ b/net/wimax/op-rfkill.c @@ -29,8 +29,8 @@ * A non-polled generic rfkill device is embedded into the WiMAX * subsystem's representation of a device. * - * FIXME: Need polled support? use a timer or add the implementation - * to the stack. + * FIXME: Need polled support? Let drivers provide a poll routine + * and hand it to rfkill ops then? * * All device drivers have to do is after wimax_dev_init(), call * wimax_report_rfkill_hw() and wimax_report_rfkill_sw() to update @@ -43,7 +43,7 @@ * wimax_rfkill() Kernel calling wimax_rfkill() * __wimax_rf_toggle_radio() * - * wimax_rfkill_toggle_radio() RF-Kill subsytem calling + * wimax_rfkill_set_radio_block() RF-Kill subsytem calling * __wimax_rf_toggle_radio() * * __wimax_rf_toggle_radio() @@ -65,15 +65,11 @@ #include <linux/wimax.h> #include <linux/security.h> #include <linux/rfkill.h> -#include <linux/input.h> #include "wimax-internal.h" #define D_SUBMODULE op_rfkill #include "debug-levels.h" -#if defined(CONFIG_RFKILL) || defined(CONFIG_RFKILL_MODULE) - - /** * wimax_report_rfkill_hw - Reports changes in the hardware RF switch * @@ -99,7 +95,6 @@ void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev, int result; struct device *dev = wimax_dev_to_dev(wimax_dev); enum wimax_st wimax_state; - enum rfkill_state rfkill_state; d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state); BUG_ON(state == WIMAX_RF_QUERY); @@ -112,16 +107,16 @@ void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev, if (state != wimax_dev->rf_hw) { wimax_dev->rf_hw = state; - rfkill_state = state == WIMAX_RF_ON ? - RFKILL_STATE_OFF : RFKILL_STATE_ON; if (wimax_dev->rf_hw == WIMAX_RF_ON && wimax_dev->rf_sw == WIMAX_RF_ON) wimax_state = WIMAX_ST_READY; else wimax_state = WIMAX_ST_RADIO_OFF; + + result = rfkill_set_hw_state(wimax_dev->rfkill, + state == WIMAX_RF_OFF); + __wimax_state_change(wimax_dev, wimax_state); - input_report_key(wimax_dev->rfkill_input, KEY_WIMAX, - rfkill_state); } error_not_ready: mutex_unlock(&wimax_dev->mutex); @@ -174,6 +169,7 @@ void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev, else wimax_state = WIMAX_ST_RADIO_OFF; __wimax_state_change(wimax_dev, wimax_state); + rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF); } error_not_ready: mutex_unlock(&wimax_dev->mutex); @@ -249,36 +245,31 @@ out_no_change: * * NOTE: This call will block until the operation is completed. */ -static -int wimax_rfkill_toggle_radio(void *data, enum rfkill_state state) +static int wimax_rfkill_set_radio_block(void *data, bool blocked) { int result; struct wimax_dev *wimax_dev = data; struct device *dev = wimax_dev_to_dev(wimax_dev); enum wimax_rf_state rf_state; - d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state); - switch (state) { - case RFKILL_STATE_ON: + d_fnstart(3, dev, "(wimax_dev %p blocked %u)\n", wimax_dev, blocked); + rf_state = WIMAX_RF_ON; + if (blocked) rf_state = WIMAX_RF_OFF; - break; - case RFKILL_STATE_OFF: - rf_state = WIMAX_RF_ON; - break; - default: - BUG(); - } mutex_lock(&wimax_dev->mutex); if (wimax_dev->state <= __WIMAX_ST_QUIESCING) - result = 0; /* just pretend it didn't happen */ + result = 0; else result = __wimax_rf_toggle_radio(wimax_dev, rf_state); mutex_unlock(&wimax_dev->mutex); - d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n", - wimax_dev, state, result); + d_fnend(3, dev, "(wimax_dev %p blocked %u) = %d\n", + wimax_dev, blocked, result); return result; } +static const struct rfkill_ops wimax_rfkill_ops = { + .set_block = wimax_rfkill_set_radio_block, +}; /** * wimax_rfkill - Set the software RF switch state for a WiMAX device @@ -322,6 +313,7 @@ int wimax_rfkill(struct wimax_dev *wimax_dev, enum wimax_rf_state state) result = __wimax_rf_toggle_radio(wimax_dev, state); if (result < 0) goto error; + rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF); break; case WIMAX_RF_QUERY: break; @@ -349,41 +341,20 @@ int wimax_rfkill_add(struct wimax_dev *wimax_dev) { int result; struct rfkill *rfkill; - struct input_dev *input_dev; struct device *dev = wimax_dev_to_dev(wimax_dev); d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev); /* Initialize RF Kill */ result = -ENOMEM; - rfkill = rfkill_allocate(dev, RFKILL_TYPE_WIMAX); + rfkill = rfkill_alloc(wimax_dev->name, dev, RFKILL_TYPE_WIMAX, + &wimax_rfkill_ops, wimax_dev); if (rfkill == NULL) goto error_rfkill_allocate; + + d_printf(1, dev, "rfkill %p\n", rfkill); + wimax_dev->rfkill = rfkill; - rfkill->name = wimax_dev->name; - rfkill->state = RFKILL_STATE_OFF; - rfkill->data = wimax_dev; - rfkill->toggle_radio = wimax_rfkill_toggle_radio; - rfkill->user_claim_unsupported = 1; - - /* Initialize the input device for the hw key */ - input_dev = input_allocate_device(); - if (input_dev == NULL) - goto error_input_allocate; - wimax_dev->rfkill_input = input_dev; - d_printf(1, dev, "rfkill %p input %p\n", rfkill, input_dev); - - input_dev->name = wimax_dev->name; - /* FIXME: get a real device bus ID and stuff? do we care? */ - input_dev->id.bustype = BUS_HOST; - input_dev->id.vendor = 0xffff; - input_dev->evbit[0] = BIT(EV_KEY); - set_bit(KEY_WIMAX, input_dev->keybit); - - /* Register both */ - result = input_register_device(wimax_dev->rfkill_input); - if (result < 0) - goto error_input_register; result = rfkill_register(wimax_dev->rfkill); if (result < 0) goto error_rfkill_register; @@ -395,17 +366,8 @@ int wimax_rfkill_add(struct wimax_dev *wimax_dev) d_fnend(3, dev, "(wimax_dev %p) = 0\n", wimax_dev); return 0; - /* if rfkill_register() suceeds, can't use rfkill_free() any - * more, only rfkill_unregister() [it owns the refcount]; with - * the input device we have the same issue--hence the if. */ error_rfkill_register: - input_unregister_device(wimax_dev->rfkill_input); - wimax_dev->rfkill_input = NULL; -error_input_register: - if (wimax_dev->rfkill_input) - input_free_device(wimax_dev->rfkill_input); -error_input_allocate: - rfkill_free(wimax_dev->rfkill); + rfkill_destroy(wimax_dev->rfkill); error_rfkill_allocate: d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result); return result; @@ -424,45 +386,12 @@ void wimax_rfkill_rm(struct wimax_dev *wimax_dev) { struct device *dev = wimax_dev_to_dev(wimax_dev); d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev); - rfkill_unregister(wimax_dev->rfkill); /* frees */ - input_unregister_device(wimax_dev->rfkill_input); + rfkill_unregister(wimax_dev->rfkill); + rfkill_destroy(wimax_dev->rfkill); d_fnend(3, dev, "(wimax_dev %p)\n", wimax_dev); } -#else /* #ifdef CONFIG_RFKILL */ - -void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev, - enum wimax_rf_state state) -{ -} -EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw); - -void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev, - enum wimax_rf_state state) -{ -} -EXPORT_SYMBOL_GPL(wimax_report_rfkill_sw); - -int wimax_rfkill(struct wimax_dev *wimax_dev, - enum wimax_rf_state state) -{ - return WIMAX_RF_ON << 1 | WIMAX_RF_ON; -} -EXPORT_SYMBOL_GPL(wimax_rfkill); - -int wimax_rfkill_add(struct wimax_dev *wimax_dev) -{ - return 0; -} - -void wimax_rfkill_rm(struct wimax_dev *wimax_dev) -{ -} - -#endif /* #ifdef CONFIG_RFKILL */ - - /* * Exporting to user space over generic netlink * diff --git a/net/wimax/op-state-get.c b/net/wimax/op-state-get.c new file mode 100644 index 00000000000..a76b8fcb056 --- /dev/null +++ b/net/wimax/op-state-get.c @@ -0,0 +1,86 @@ +/* + * Linux WiMAX + * Implement and export a method for getting a WiMAX device current state + * + * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt> + * + * Based on previous WiMAX core work by: + * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com> + * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com> + * + * 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 <net/wimax.h> +#include <net/genetlink.h> +#include <linux/wimax.h> +#include <linux/security.h> +#include "wimax-internal.h" + +#define D_SUBMODULE op_state_get +#include "debug-levels.h" + + +static const +struct nla_policy wimax_gnl_state_get_policy[WIMAX_GNL_ATTR_MAX + 1] = { + [WIMAX_GNL_STGET_IFIDX] = { + .type = NLA_U32, + }, +}; + + +/* + * Exporting to user space over generic netlink + * + * Parse the state get command from user space, return a combination + * value that describe the current state. + * + * No attributes. + */ +static +int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info) +{ + int result, ifindex; + struct wimax_dev *wimax_dev; + struct device *dev; + + d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info); + result = -ENODEV; + if (info->attrs[WIMAX_GNL_STGET_IFIDX] == NULL) { + printk(KERN_ERR "WIMAX_GNL_OP_STATE_GET: can't find IFIDX " + "attribute\n"); + goto error_no_wimax_dev; + } + ifindex = nla_get_u32(info->attrs[WIMAX_GNL_STGET_IFIDX]); + wimax_dev = wimax_dev_get_by_genl_info(info, ifindex); + if (wimax_dev == NULL) + goto error_no_wimax_dev; + dev = wimax_dev_to_dev(wimax_dev); + /* Execute the operation and send the result back to user space */ + result = wimax_state_get(wimax_dev); + dev_put(wimax_dev->net_dev); +error_no_wimax_dev: + d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result); + return result; +} + + +struct genl_ops wimax_gnl_state_get = { + .cmd = WIMAX_GNL_OP_STATE_GET, + .flags = GENL_ADMIN_PERM, + .policy = wimax_gnl_state_get_policy, + .doit = wimax_gnl_doit_state_get, + .dumpit = NULL, +}; diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 933e1422b09..79fb7d7c640 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -402,13 +402,15 @@ EXPORT_SYMBOL_GPL(wimax_dev_init); extern struct genl_ops wimax_gnl_msg_from_user, wimax_gnl_reset, - wimax_gnl_rfkill; + wimax_gnl_rfkill, + wimax_gnl_state_get; static struct genl_ops *wimax_gnl_ops[] = { &wimax_gnl_msg_from_user, &wimax_gnl_reset, &wimax_gnl_rfkill, + &wimax_gnl_state_get, }; @@ -533,6 +535,7 @@ struct d_level D_LEVEL[] = { D_SUBMODULE_DEFINE(op_msg), D_SUBMODULE_DEFINE(op_reset), D_SUBMODULE_DEFINE(op_rfkill), + D_SUBMODULE_DEFINE(op_state_get), D_SUBMODULE_DEFINE(stack), }; size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 3c3bc9e579e..4428dd5e911 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -1,5 +1,6 @@ config CFG80211 - tristate "Improved wireless configuration API" + tristate "Improved wireless configuration API" + depends on RFKILL || !RFKILL config CFG80211_REG_DEBUG bool "cfg80211 regulatory debugging" @@ -10,6 +11,14 @@ config CFG80211_REG_DEBUG If unsure, say N. +config CFG80211_DEBUGFS + bool "cfg80211 DebugFS entries" + depends on CFG80211 && DEBUG_FS + ---help--- + You can enable this if you want to debugfs entries for cfg80211. + + If unsure, say N. + config WIRELESS_OLD_REGULATORY bool "Old wireless static regulatory definitions" default n diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 6d1e7b27b75..f78c4832a9c 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -5,7 +5,8 @@ obj-$(CONFIG_LIB80211_CRYPT_WEP) += lib80211_crypt_wep.o obj-$(CONFIG_LIB80211_CRYPT_CCMP) += lib80211_crypt_ccmp.o obj-$(CONFIG_LIB80211_CRYPT_TKIP) += lib80211_crypt_tkip.o -cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o mlme.o +cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o mlme.o ibss.o +cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_WIRELESS_EXT) += wext-compat.o ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/wireless/core.c b/net/wireless/core.c index d1f556535f6..d5850292b3d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1,7 +1,7 @@ /* * This is the linux wireless configuration interface. * - * Copyright 2006-2008 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2006-2009 Johannes Berg <johannes@sipsolutions.net> */ #include <linux/if.h> @@ -12,12 +12,13 @@ #include <linux/debugfs.h> #include <linux/notifier.h> #include <linux/device.h> +#include <linux/rtnetlink.h> #include <net/genetlink.h> #include <net/cfg80211.h> -#include <net/wireless.h> #include "nl80211.h" #include "core.h" #include "sysfs.h" +#include "debugfs.h" /* name for sysfs, %d is appended */ #define PHY_NAME "phy" @@ -227,9 +228,44 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, return 0; } +static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data) +{ + struct cfg80211_registered_device *drv = data; + + drv->ops->rfkill_poll(&drv->wiphy); +} + +static int cfg80211_rfkill_set_block(void *data, bool blocked) +{ + struct cfg80211_registered_device *drv = data; + struct wireless_dev *wdev; + + if (!blocked) + return 0; + + rtnl_lock(); + mutex_lock(&drv->devlist_mtx); + + list_for_each_entry(wdev, &drv->netdev_list, list) + dev_close(wdev->netdev); + + mutex_unlock(&drv->devlist_mtx); + rtnl_unlock(); + + return 0; +} + +static void cfg80211_rfkill_sync_work(struct work_struct *work) +{ + struct cfg80211_registered_device *drv; + + drv = container_of(work, struct cfg80211_registered_device, rfkill_sync); + cfg80211_rfkill_set_block(drv, rfkill_blocked(drv->rfkill)); +} + /* exported functions */ -struct wiphy *wiphy_new(struct cfg80211_ops *ops, int sizeof_priv) +struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) { static int wiphy_counter; @@ -274,6 +310,28 @@ struct wiphy *wiphy_new(struct cfg80211_ops *ops, int sizeof_priv) drv->wiphy.dev.class = &ieee80211_class; drv->wiphy.dev.platform_data = drv; + 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); + + if (!drv->rfkill) { + kfree(drv); + return NULL; + } + + INIT_WORK(&drv->rfkill_sync, cfg80211_rfkill_sync_work); + + /* + * 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; + return &drv->wiphy; } EXPORT_SYMBOL(wiphy_new); @@ -337,17 +395,23 @@ int wiphy_register(struct wiphy *wiphy) /* check and set up bitrates */ ieee80211_set_bitrate_flags(wiphy); + res = device_add(&drv->wiphy.dev); + if (res) + return res; + + res = rfkill_register(drv->rfkill); + if (res) + goto out_rm_dev; + mutex_lock(&cfg80211_mutex); /* set up regulatory info */ wiphy_update_regulatory(wiphy, NL80211_REGDOM_SET_BY_CORE); - res = device_add(&drv->wiphy.dev); - if (res) - goto out_unlock; - list_add(&drv->list, &cfg80211_drv_list); + mutex_unlock(&cfg80211_mutex); + /* add to debugfs */ drv->wiphy.debugfsdir = debugfs_create_dir(wiphy_name(&drv->wiphy), @@ -366,17 +430,41 @@ int wiphy_register(struct wiphy *wiphy) nl80211_send_reg_change_event(&request); } - res = 0; -out_unlock: - mutex_unlock(&cfg80211_mutex); + cfg80211_debugfs_drv_add(drv); + + return 0; + + out_rm_dev: + device_del(&drv->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); + + if (!drv->ops->rfkill_poll) + return; + drv->rfkill_ops.poll = cfg80211_rfkill_poll; + rfkill_resume_polling(drv->rfkill); +} +EXPORT_SYMBOL(wiphy_rfkill_start_polling); + +void wiphy_rfkill_stop_polling(struct wiphy *wiphy) +{ + struct cfg80211_registered_device *drv = wiphy_to_dev(wiphy); + + rfkill_pause_polling(drv->rfkill); +} +EXPORT_SYMBOL(wiphy_rfkill_stop_polling); + void wiphy_unregister(struct wiphy *wiphy) { struct cfg80211_registered_device *drv = wiphy_to_dev(wiphy); + rfkill_unregister(drv->rfkill); + /* protect the device list */ mutex_lock(&cfg80211_mutex); @@ -396,6 +484,8 @@ void wiphy_unregister(struct wiphy *wiphy) /* unlock again before freeing */ mutex_unlock(&drv->mtx); + cfg80211_debugfs_drv_del(drv); + /* 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); @@ -411,6 +501,7 @@ EXPORT_SYMBOL(wiphy_unregister); void cfg80211_dev_free(struct cfg80211_registered_device *drv) { 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) @@ -424,6 +515,15 @@ void wiphy_free(struct wiphy *wiphy) } EXPORT_SYMBOL(wiphy_free); +void wiphy_rfkill_set_hw_state(struct wiphy *wiphy, bool blocked) +{ + struct cfg80211_registered_device *drv = wiphy_to_dev(wiphy); + + if (rfkill_set_hw_state(drv->rfkill, blocked)) + schedule_work(&drv->rfkill_sync); +} +EXPORT_SYMBOL(wiphy_rfkill_set_hw_state); + static int cfg80211_netdev_notifier_call(struct notifier_block * nb, unsigned long state, void *ndev) @@ -432,7 +532,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, struct cfg80211_registered_device *rdev; if (!dev->ieee80211_ptr) - return 0; + return NOTIFY_DONE; rdev = wiphy_to_dev(dev->ieee80211_ptr->wiphy); @@ -448,8 +548,28 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, "symlink to netdev!\n"); } dev->ieee80211_ptr->netdev = dev; +#ifdef CONFIG_WIRELESS_EXT + dev->ieee80211_ptr->wext.default_key = -1; + dev->ieee80211_ptr->wext.default_mgmt_key = -1; +#endif mutex_unlock(&rdev->devlist_mtx); break; + case NETDEV_GOING_DOWN: + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) + break; + if (!dev->ieee80211_ptr->ssid_len) + break; + cfg80211_leave_ibss(rdev, dev, true); + break; + case NETDEV_UP: +#ifdef CONFIG_WIRELESS_EXT + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) + break; + if (!dev->ieee80211_ptr->wext.ibss.ssid_len) + break; + cfg80211_join_ibss(rdev, dev, &dev->ieee80211_ptr->wext.ibss); + break; +#endif case NETDEV_UNREGISTER: mutex_lock(&rdev->devlist_mtx); if (!list_empty(&dev->ieee80211_ptr->list)) { @@ -458,9 +578,13 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, } mutex_unlock(&rdev->devlist_mtx); break; + case NETDEV_PRE_UP: + if (rfkill_blocked(rdev->rfkill)) + return notifier_from_errno(-ERFKILL); + break; } - return 0; + return NOTIFY_DONE; } static struct notifier_block cfg80211_netdev_notifier = { diff --git a/net/wireless/core.h b/net/wireless/core.h index 0a592e4295f..bfa340c7abb 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -1,7 +1,7 @@ /* * Wireless configuration interface internals. * - * Copyright 2006, 2007 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2006-2009 Johannes Berg <johannes@sipsolutions.net> */ #ifndef __NET_WIRELESS_CORE_H #define __NET_WIRELESS_CORE_H @@ -10,14 +10,15 @@ #include <linux/netdevice.h> #include <linux/kref.h> #include <linux/rbtree.h> -#include <linux/mutex.h> +#include <linux/debugfs.h> +#include <linux/rfkill.h> +#include <linux/workqueue.h> #include <net/genetlink.h> -#include <net/wireless.h> #include <net/cfg80211.h> #include "reg.h" struct cfg80211_registered_device { - struct cfg80211_ops *ops; + const struct cfg80211_ops *ops; struct list_head list; /* we hold this mutex during any call so that * we cannot do multiple calls at once, and also @@ -25,6 +26,11 @@ struct cfg80211_registered_device { * any call is in progress */ struct mutex mtx; + /* rfkill support */ + struct rfkill_ops rfkill_ops; + struct rfkill *rfkill; + struct work_struct rfkill_sync; + /* ISO / IEC 3166 alpha2 for which this device is receiving * country IEs on, this can help disregard country IEs from APs * on the same alpha2 quickly. The alpha2 may differ from @@ -52,6 +58,17 @@ struct cfg80211_registered_device { struct cfg80211_scan_request *scan_req; /* protected by RTNL */ unsigned long suspend_at; +#ifdef CONFIG_CFG80211_DEBUGFS + /* Debugfs entries */ + struct wiphy_debugfsdentries { + struct dentry *rts_threshold; + struct dentry *fragmentation_threshold; + struct dentry *short_retry_limit; + struct dentry *long_retry_limit; + struct dentry *ht40allow_map; + } debugfs; +#endif + /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wiphy wiphy __attribute__((__aligned__(NETDEV_ALIGN))); @@ -74,10 +91,7 @@ bool wiphy_idx_valid(int wiphy_idx) extern struct mutex cfg80211_mutex; extern struct list_head cfg80211_drv_list; -static inline void assert_cfg80211_lock(void) -{ - WARN_ON(!mutex_is_locked(&cfg80211_mutex)); -} +#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. @@ -148,4 +162,16 @@ void cfg80211_bss_expire(struct cfg80211_registered_device *dev); 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); +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); + +/* internal helpers */ +int cfg80211_validate_key_settings(struct key_params *params, int key_idx, + const u8 *mac_addr); + #endif /* __NET_WIRELESS_CORE_H */ diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c new file mode 100644 index 00000000000..679ddfcec1e --- /dev/null +++ b/net/wireless/debugfs.c @@ -0,0 +1,131 @@ +/* + * cfg80211 debugfs + * + * Copyright 2009 Luis R. Rodriguez <lrodriguez@atheros.com> + * Copyright 2007 Johannes Berg <johannes@sipsolutions.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 "core.h" +#include "debugfs.h" + +static int cfg80211_open_file_generic(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + return 0; +} + +#define DEBUGFS_READONLY_FILE(name, buflen, fmt, value...) \ +static ssize_t name## _read(struct file *file, char __user *userbuf, \ + size_t count, loff_t *ppos) \ +{ \ + struct wiphy *wiphy= file->private_data; \ + char buf[buflen]; \ + int res; \ + \ + res = scnprintf(buf, buflen, fmt "\n", ##value); \ + return simple_read_from_buffer(userbuf, count, ppos, buf, res); \ +} \ + \ +static const struct file_operations name## _ops = { \ + .read = name## _read, \ + .open = cfg80211_open_file_generic, \ +}; + +DEBUGFS_READONLY_FILE(rts_threshold, 20, "%d", + wiphy->rts_threshold) +DEBUGFS_READONLY_FILE(fragmentation_threshold, 20, "%d", + wiphy->frag_threshold); +DEBUGFS_READONLY_FILE(short_retry_limit, 20, "%d", + wiphy->retry_short) +DEBUGFS_READONLY_FILE(long_retry_limit, 20, "%d", + wiphy->retry_long); + +static int ht_print_chan(struct ieee80211_channel *chan, + char *buf, int buf_size, int offset) +{ + if (WARN_ON(offset > buf_size)) + return 0; + + if (chan->flags & IEEE80211_CHAN_DISABLED) + return snprintf(buf + offset, + buf_size - offset, + "%d Disabled\n", + chan->center_freq); + + return snprintf(buf + offset, + buf_size - offset, + "%d HT40 %c%c\n", + chan->center_freq, + (chan->flags & IEEE80211_CHAN_NO_HT40MINUS) ? ' ' : '-', + (chan->flags & IEEE80211_CHAN_NO_HT40PLUS) ? ' ' : '+'); +} + +static ssize_t ht40allow_map_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct wiphy *wiphy = file->private_data; + char *buf; + unsigned int offset = 0, buf_size = PAGE_SIZE, i, r; + enum ieee80211_band band; + struct ieee80211_supported_band *sband; + + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + mutex_lock(&cfg80211_mutex); + + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + sband = wiphy->bands[band]; + if (!sband) + continue; + for (i = 0; i < sband->n_channels; i++) + offset += ht_print_chan(&sband->channels[i], + buf, buf_size, offset); + } + + mutex_unlock(&cfg80211_mutex); + + r = simple_read_from_buffer(user_buf, count, ppos, buf, offset); + + kfree(buf); + + return r; +} + +static const struct file_operations ht40allow_map_ops = { + .read = ht40allow_map_read, + .open = cfg80211_open_file_generic, +}; + +#define DEBUGFS_ADD(name) \ + drv->debugfs.name = debugfs_create_file(#name, S_IRUGO, phyd, \ + &drv->wiphy, &name## _ops); +#define DEBUGFS_DEL(name) \ + debugfs_remove(drv->debugfs.name); \ + drv->debugfs.name = NULL; + +void cfg80211_debugfs_drv_add(struct cfg80211_registered_device *drv) +{ + struct dentry *phyd = drv->wiphy.debugfsdir; + + DEBUGFS_ADD(rts_threshold); + DEBUGFS_ADD(fragmentation_threshold); + DEBUGFS_ADD(short_retry_limit); + DEBUGFS_ADD(long_retry_limit); + DEBUGFS_ADD(ht40allow_map); +} + +void cfg80211_debugfs_drv_del(struct cfg80211_registered_device *drv) +{ + DEBUGFS_DEL(rts_threshold); + DEBUGFS_DEL(fragmentation_threshold); + DEBUGFS_DEL(short_retry_limit); + DEBUGFS_DEL(long_retry_limit); + DEBUGFS_DEL(ht40allow_map); +} diff --git a/net/wireless/debugfs.h b/net/wireless/debugfs.h new file mode 100644 index 00000000000..c226983ae66 --- /dev/null +++ b/net/wireless/debugfs.h @@ -0,0 +1,14 @@ +#ifndef __CFG80211_DEBUGFS_H +#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); +#else +static inline +void cfg80211_debugfs_drv_add(struct cfg80211_registered_device *drv) {} +static inline +void cfg80211_debugfs_drv_del(struct cfg80211_registered_device *drv) {} +#endif + +#endif /* __CFG80211_DEBUGFS_H */ diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c new file mode 100644 index 00000000000..a4a1c3498ff --- /dev/null +++ b/net/wireless/ibss.c @@ -0,0 +1,369 @@ +/* + * Some IBSS support code for cfg80211. + * + * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + */ + +#include <linux/etherdevice.h> +#include <linux/if_arp.h> +#include <net/cfg80211.h> +#include "nl80211.h" + + +void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_bss *bss; +#ifdef CONFIG_WIRELESS_EXT + union iwreq_data wrqu; +#endif + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) + return; + + if (WARN_ON(!wdev->ssid_len)) + return; + + if (memcmp(bssid, wdev->bssid, ETH_ALEN) == 0) + return; + + bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, + wdev->ssid, wdev->ssid_len, + WLAN_CAPABILITY_IBSS, WLAN_CAPABILITY_IBSS); + + if (WARN_ON(!bss)) + return; + + if (wdev->current_bss) { + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(wdev->current_bss); + } + + cfg80211_hold_bss(bss); + wdev->current_bss = bss; + memcpy(wdev->bssid, bssid, ETH_ALEN); + + nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid, gfp); +#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 +} +EXPORT_SYMBOL(cfg80211_ibss_joined); + +int cfg80211_join_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ibss_params *params) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + if (wdev->ssid_len) + return -EALREADY; + +#ifdef CONFIG_WIRELESS_EXT + wdev->wext.ibss.channel = params->channel; +#endif + err = rdev->ops->join_ibss(&rdev->wiphy, dev, params); + + if (err) + return err; + + memcpy(wdev->ssid, params->ssid, params->ssid_len); + wdev->ssid_len = params->ssid_len; + + return 0; +} + +void cfg80211_clear_ibss(struct net_device *dev, bool nowext) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + if (wdev->current_bss) { + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(wdev->current_bss); + } + + 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) +{ + int err; + + err = rdev->ops->leave_ibss(&rdev->wiphy, dev); + + if (err) + return err; + + cfg80211_clear_ibss(dev, nowext); + + return 0; +} + +#ifdef CONFIG_WIRELESS_EXT +static int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + enum ieee80211_band band; + int i; + + if (!wdev->wext.ibss.beacon_interval) + wdev->wext.ibss.beacon_interval = 100; + + /* try to find an IBSS channel if none requested ... */ + if (!wdev->wext.ibss.channel) { + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + struct ieee80211_supported_band *sband; + struct ieee80211_channel *chan; + + sband = rdev->wiphy.bands[band]; + if (!sband) + continue; + + for (i = 0; i < sband->n_channels; i++) { + chan = &sband->channels[i]; + if (chan->flags & IEEE80211_CHAN_NO_IBSS) + continue; + if (chan->flags & IEEE80211_CHAN_DISABLED) + continue; + wdev->wext.ibss.channel = chan; + break; + } + + if (wdev->wext.ibss.channel) + break; + } + + if (!wdev->wext.ibss.channel) + return -EINVAL; + } + + /* don't join -- SSID is not there */ + if (!wdev->wext.ibss.ssid_len) + return 0; + + if (!netif_running(wdev->netdev)) + return 0; + + return cfg80211_join_ibss(wiphy_to_dev(wdev->wiphy), + wdev->netdev, &wdev->wext.ibss); +} + +int cfg80211_ibss_wext_siwfreq(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; + int err; + + /* call only for ibss! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) + return -EINVAL; + + if (!wiphy_to_dev(wdev->wiphy)->ops->join_ibss) + return -EOPNOTSUPP; + + chan = cfg80211_wext_freq(wdev->wiphy, freq); + if (chan && IS_ERR(chan)) + return PTR_ERR(chan); + + if (chan && + (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; + } + + if (chan) { + wdev->wext.ibss.channel = chan; + wdev->wext.ibss.channel_fixed = true; + } else { + /* cfg80211_ibss_wext_join will pick one if needed */ + wdev->wext.ibss.channel_fixed = false; + } + + return cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); +} +/* 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, + struct iw_freq *freq, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct ieee80211_channel *chan = NULL; + + /* call only for ibss! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) + return -EINVAL; + + if (wdev->current_bss) + chan = wdev->current_bss->channel; + else if (wdev->wext.ibss.channel) + chan = wdev->wext.ibss.channel; + + if (chan) { + freq->m = chan->center_freq; + freq->e = 6; + return 0; + } + + /* 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; + size_t len = data->length; + int err; + + /* call only for ibss! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) + return -EINVAL; + + if (!wiphy_to_dev(wdev->wiphy)->ops->join_ibss) + return -EOPNOTSUPP; + + if (wdev->ssid_len) { + err = cfg80211_leave_ibss(wiphy_to_dev(wdev->wiphy), + dev, true); + if (err) + return err; + } + + /* iwconfig uses nul termination in SSID.. */ + if (len > 0 && ssid[len - 1] == '\0') + len--; + + wdev->wext.ibss.ssid = wdev->ssid; + memcpy(wdev->wext.ibss.ssid, ssid, len); + wdev->wext.ibss.ssid_len = len; + + return cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); +} +/* 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, + struct iw_point *data, char *ssid) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + /* call only for ibss! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) + return -EINVAL; + + data->flags = 0; + + if (wdev->ssid_len) { + data->flags = 1; + data->length = wdev->ssid_len; + memcpy(ssid, wdev->ssid, data->length); + } else if (wdev->wext.ibss.ssid && wdev->wext.ibss.ssid_len) { + data->flags = 1; + data->length = wdev->wext.ibss.ssid_len; + memcpy(ssid, wdev->wext.ibss.ssid, data->length); + } + + 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; + u8 *bssid = ap_addr->sa_data; + int err; + + /* call only for ibss! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) + return -EINVAL; + + if (!wiphy_to_dev(wdev->wiphy)->ops->join_ibss) + return -EOPNOTSUPP; + + if (ap_addr->sa_family != ARPHRD_ETHER) + return -EINVAL; + + /* automatic mode */ + if (is_zero_ether_addr(bssid) || is_broadcast_ether_addr(bssid)) + bssid = NULL; + + /* both automatic */ + if (!bssid && !wdev->wext.ibss.bssid) + return 0; + + /* fixed already - and no change */ + if (wdev->wext.ibss.bssid && bssid && + 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; + } + + if (bssid) { + memcpy(wdev->wext.bssid, bssid, ETH_ALEN); + wdev->wext.ibss.bssid = wdev->wext.bssid; + } else + wdev->wext.ibss.bssid = NULL; + + return cfg80211_ibss_wext_join(wiphy_to_dev(wdev->wiphy), wdev); +} +/* 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, + struct sockaddr *ap_addr, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + /* call only for ibss! */ + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_ADHOC)) + return -EINVAL; + + ap_addr->sa_family = ARPHRD_ETHER; + + if (wdev->wext.ibss.bssid) { + memcpy(ap_addr->sa_data, wdev->wext.ibss.bssid, ETH_ALEN); + return 0; + } + + 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 bec5721b6f9..42184361a10 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -28,19 +28,55 @@ void cfg80211_send_rx_assoc(struct net_device *dev, const u8 *buf, size_t len) } EXPORT_SYMBOL(cfg80211_send_rx_assoc); -void cfg80211_send_rx_deauth(struct net_device *dev, const u8 *buf, size_t len) +void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len) { struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_rx_deauth(rdev, dev, buf, len); + nl80211_send_deauth(rdev, dev, buf, len); } -EXPORT_SYMBOL(cfg80211_send_rx_deauth); +EXPORT_SYMBOL(cfg80211_send_deauth); -void cfg80211_send_rx_disassoc(struct net_device *dev, const u8 *buf, - size_t len) +void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len) { struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_rx_disassoc(rdev, dev, buf, len); + nl80211_send_disassoc(rdev, dev, buf, len); } -EXPORT_SYMBOL(cfg80211_send_rx_disassoc); +EXPORT_SYMBOL(cfg80211_send_disassoc); + +static void cfg80211_wext_disconnected(struct net_device *dev) +{ +#ifdef CONFIG_WIRELESS_EXT + union iwreq_data wrqu; + memset(&wrqu, 0, sizeof(wrqu)); + wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); +#endif +} + +void cfg80211_send_auth_timeout(struct net_device *dev, const u8 *addr) +{ + struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + nl80211_send_auth_timeout(rdev, dev, addr); + cfg80211_wext_disconnected(dev); +} +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 cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + nl80211_send_assoc_timeout(rdev, dev, addr); + cfg80211_wext_disconnected(dev); +} +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) +{ + 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); +} +EXPORT_SYMBOL(cfg80211_michael_mic_failure); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2456e4ee445..634496b3ed7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1,7 +1,7 @@ /* * This is the new netlink-based wireless configuration interface. * - * Copyright 2006, 2007 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2006-2009 Johannes Berg <johannes@sipsolutions.net> */ #include <linux/if.h> @@ -57,10 +57,14 @@ static int get_drv_dev_by_info_ifindex(struct nlattr **attrs, static struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] __read_mostly = { [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING, - .len = BUS_ID_SIZE-1 }, + .len = 20-1 }, [NL80211_ATTR_WIPHY_TXQ_PARAMS] = { .type = NLA_NESTED }, [NL80211_ATTR_WIPHY_FREQ] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_CHANNEL_TYPE] = { .type = NLA_U32 }, + [NL80211_ATTR_WIPHY_RETRY_SHORT] = { .type = NLA_U8 }, + [NL80211_ATTR_WIPHY_RETRY_LONG] = { .type = NLA_U8 }, + [NL80211_ATTR_WIPHY_FRAG_THRESHOLD] = { .type = NLA_U32 }, + [NL80211_ATTR_WIPHY_RTS_THRESHOLD] = { .type = NLA_U32 }, [NL80211_ATTR_IFTYPE] = { .type = NLA_U32 }, [NL80211_ATTR_IFINDEX] = { .type = NLA_U32 }, @@ -73,6 +77,7 @@ static struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] __read_mostly = { [NL80211_ATTR_KEY_IDX] = { .type = NLA_U8 }, [NL80211_ATTR_KEY_CIPHER] = { .type = NLA_U32 }, [NL80211_ATTR_KEY_DEFAULT] = { .type = NLA_FLAG }, + [NL80211_ATTR_KEY_SEQ] = { .type = NLA_BINARY, .len = 8 }, [NL80211_ATTR_BEACON_INTERVAL] = { .type = NLA_U32 }, [NL80211_ATTR_DTIM_PERIOD] = { .type = NLA_U32 }, @@ -116,8 +121,45 @@ static struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] __read_mostly = { .len = IEEE80211_MAX_SSID_LEN }, [NL80211_ATTR_AUTH_TYPE] = { .type = NLA_U32 }, [NL80211_ATTR_REASON_CODE] = { .type = NLA_U16 }, + [NL80211_ATTR_FREQ_FIXED] = { .type = NLA_FLAG }, + [NL80211_ATTR_TIMED_OUT] = { .type = NLA_FLAG }, + [NL80211_ATTR_USE_MFP] = { .type = NLA_U32 }, + [NL80211_ATTR_STA_FLAGS2] = { + .len = sizeof(struct nl80211_sta_flag_update), + }, + [NL80211_ATTR_CONTROL_PORT] = { .type = NLA_FLAG }, }; +/* IE validation */ +static bool is_valid_ie_attr(const struct nlattr *attr) +{ + const u8 *pos; + int len; + + if (!attr) + return true; + + pos = nla_data(attr); + len = nla_len(attr); + + while (len) { + u8 elemlen; + + if (len < 2) + return false; + len -= 2; + + elemlen = pos[1]; + if (elemlen > len) + return false; + + len -= elemlen; + pos += 2 + elemlen; + } + + return true; +} + /* message building helper */ static inline void *nl80211hdr_put(struct sk_buff *skb, u32 pid, u32 seq, int flags, u8 cmd) @@ -126,6 +168,30 @@ static inline void *nl80211hdr_put(struct sk_buff *skb, u32 pid, u32 seq, return genlmsg_put(skb, pid, seq, &nl80211_fam, flags, cmd); } +static int nl80211_msg_put_channel(struct sk_buff *msg, + struct ieee80211_channel *chan) +{ + NLA_PUT_U32(msg, NL80211_FREQUENCY_ATTR_FREQ, + chan->center_freq); + + if (chan->flags & IEEE80211_CHAN_DISABLED) + NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_DISABLED); + if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) + NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_PASSIVE_SCAN); + if (chan->flags & IEEE80211_CHAN_NO_IBSS) + NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_NO_IBSS); + if (chan->flags & IEEE80211_CHAN_RADAR) + NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_RADAR); + + NLA_PUT_U32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, + DBM_TO_MBM(chan->max_power)); + + return 0; + + nla_put_failure: + return -ENOBUFS; +} + /* netlink command implementations */ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, @@ -149,8 +215,24 @@ 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_U8(msg, NL80211_ATTR_WIPHY_RETRY_SHORT, + dev->wiphy.retry_short); + NLA_PUT_U8(msg, NL80211_ATTR_WIPHY_RETRY_LONG, + dev->wiphy.retry_long); + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_FRAG_THRESHOLD, + dev->wiphy.frag_threshold); + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY_RTS_THRESHOLD, + dev->wiphy.rts_threshold); + NLA_PUT_U8(msg, NL80211_ATTR_MAX_NUM_SCAN_SSIDS, dev->wiphy.max_scan_ssids); + NLA_PUT_U16(msg, NL80211_ATTR_MAX_SCAN_IE_LEN, + dev->wiphy.max_scan_ie_len); + + NLA_PUT(msg, NL80211_ATTR_CIPHER_SUITES, + sizeof(u32) * dev->wiphy.n_cipher_suites, + dev->wiphy.cipher_suites); nl_modes = nla_nest_start(msg, NL80211_ATTR_SUPPORTED_IFTYPES); if (!nl_modes) @@ -202,20 +284,9 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, goto nla_put_failure; chan = &dev->wiphy.bands[band]->channels[i]; - NLA_PUT_U32(msg, NL80211_FREQUENCY_ATTR_FREQ, - chan->center_freq); - - if (chan->flags & IEEE80211_CHAN_DISABLED) - NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_DISABLED); - if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) - NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_PASSIVE_SCAN); - if (chan->flags & IEEE80211_CHAN_NO_IBSS) - NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_NO_IBSS); - if (chan->flags & IEEE80211_CHAN_RADAR) - NLA_PUT_FLAG(msg, NL80211_FREQUENCY_ATTR_RADAR); - NLA_PUT_U32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, - DBM_TO_MBM(chan->max_power)); + if (nl80211_msg_put_channel(msg, chan)) + goto nla_put_failure; nla_nest_end(msg, nl_freq); } @@ -273,6 +344,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, CMD(assoc, ASSOCIATE); CMD(deauth, DEAUTHENTICATE); CMD(disassoc, DISASSOCIATE); + CMD(join_ibss, JOIN_IBSS); #undef CMD nla_nest_end(msg, nl_cmds); @@ -317,7 +389,7 @@ static int nl80211_get_wiphy(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(dev)) return PTR_ERR(dev); - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out_err; @@ -365,6 +437,9 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev; int result = 0, rem_txq_params = 0; struct nlattr *nl_txq_params; + u32 changed; + u8 retry_short = 0, retry_long = 0; + u32 frag_threshold = 0, rts_threshold = 0; rtnl_lock(); @@ -372,6 +447,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev = __cfg80211_drv_from_info(info); if (IS_ERR(rdev)) { + mutex_unlock(&cfg80211_mutex); result = PTR_ERR(rdev); goto unlock; } @@ -418,7 +494,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; struct ieee80211_channel *chan; struct ieee80211_sta_ht_cap *ht_cap; - u32 freq, sec_freq; + u32 freq; if (!rdev->ops->set_channel) { result = -EOPNOTSUPP; @@ -444,33 +520,28 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) goto bad_res; - if (channel_type == NL80211_CHAN_HT40MINUS) - sec_freq = freq - 20; - else if (channel_type == NL80211_CHAN_HT40PLUS) - sec_freq = freq + 20; - else - sec_freq = 0; - - ht_cap = &rdev->wiphy.bands[chan->band]->ht_cap; - - /* no HT capabilities */ - if (channel_type != NL80211_CHAN_NO_HT && - !ht_cap->ht_supported) + 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; - if (sec_freq) { - struct ieee80211_channel *schan; + /* + * 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 40 MHz capabilities */ + /* 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; - - schan = ieee80211_get_channel(&rdev->wiphy, sec_freq); - - /* Secondary channel not allowed */ - if (!schan || schan->flags & IEEE80211_CHAN_DISABLED) - goto bad_res; } result = rdev->ops->set_channel(&rdev->wiphy, chan, @@ -479,6 +550,84 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) goto bad_res; } + changed = 0; + + if (info->attrs[NL80211_ATTR_WIPHY_RETRY_SHORT]) { + retry_short = nla_get_u8( + info->attrs[NL80211_ATTR_WIPHY_RETRY_SHORT]); + if (retry_short == 0) { + result = -EINVAL; + goto bad_res; + } + changed |= WIPHY_PARAM_RETRY_SHORT; + } + + if (info->attrs[NL80211_ATTR_WIPHY_RETRY_LONG]) { + retry_long = nla_get_u8( + info->attrs[NL80211_ATTR_WIPHY_RETRY_LONG]); + if (retry_long == 0) { + result = -EINVAL; + goto bad_res; + } + changed |= WIPHY_PARAM_RETRY_LONG; + } + + if (info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]) { + frag_threshold = nla_get_u32( + info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]); + if (frag_threshold < 256) { + result = -EINVAL; + goto bad_res; + } + if (frag_threshold != (u32) -1) { + /* + * Fragments (apart from the last one) are required to + * have even length. Make the fragmentation code + * simpler by stripping LSB should someone try to use + * odd threshold value. + */ + frag_threshold &= ~0x1; + } + changed |= WIPHY_PARAM_FRAG_THRESHOLD; + } + + if (info->attrs[NL80211_ATTR_WIPHY_RTS_THRESHOLD]) { + rts_threshold = nla_get_u32( + info->attrs[NL80211_ATTR_WIPHY_RTS_THRESHOLD]); + changed |= WIPHY_PARAM_RTS_THRESHOLD; + } + + if (changed) { + u8 old_retry_short, old_retry_long; + u32 old_frag_threshold, old_rts_threshold; + + if (!rdev->ops->set_wiphy_params) { + result = -EOPNOTSUPP; + goto bad_res; + } + + old_retry_short = rdev->wiphy.retry_short; + old_retry_long = rdev->wiphy.retry_long; + old_frag_threshold = rdev->wiphy.frag_threshold; + old_rts_threshold = rdev->wiphy.rts_threshold; + + if (changed & WIPHY_PARAM_RETRY_SHORT) + rdev->wiphy.retry_short = retry_short; + if (changed & WIPHY_PARAM_RETRY_LONG) + rdev->wiphy.retry_long = retry_long; + if (changed & WIPHY_PARAM_FRAG_THRESHOLD) + rdev->wiphy.frag_threshold = frag_threshold; + if (changed & WIPHY_PARAM_RTS_THRESHOLD) + rdev->wiphy.rts_threshold = rts_threshold; + + result = rdev->ops->set_wiphy_params(&rdev->wiphy, changed); + if (result) { + rdev->wiphy.retry_short = old_retry_short; + rdev->wiphy.retry_long = old_retry_long; + rdev->wiphy.frag_threshold = old_frag_threshold; + rdev->wiphy.rts_threshold = old_rts_threshold; + } + } bad_res: mutex_unlock(&rdev->mtx); @@ -489,6 +638,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, + struct cfg80211_registered_device *rdev, struct net_device *dev) { void *hdr; @@ -498,6 +648,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, return -1; NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, dev->ifindex); + 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); return genlmsg_end(msg, hdr); @@ -532,7 +683,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * } if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - wdev->netdev) < 0) { + dev, wdev->netdev) < 0) { mutex_unlock(&dev->devlist_mtx); goto out; } @@ -562,11 +713,12 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info) if (err) return err; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out_err; - if (nl80211_send_iface(msg, info->snd_pid, info->snd_seq, 0, netdev) < 0) + if (nl80211_send_iface(msg, info->snd_pid, info->snd_seq, 0, + dev, netdev) < 0) goto out_free; dev_put(netdev); @@ -616,7 +768,7 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *drv; struct vif_params params; int err, ifindex; - enum nl80211_iftype type; + enum nl80211_iftype otype, ntype; struct net_device *dev; u32 _flags, *flags = NULL; bool change = false; @@ -630,30 +782,27 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) goto unlock_rtnl; ifindex = dev->ifindex; - type = dev->ieee80211_ptr->iftype; + otype = ntype = dev->ieee80211_ptr->iftype; dev_put(dev); if (info->attrs[NL80211_ATTR_IFTYPE]) { - enum nl80211_iftype ntype; - ntype = nla_get_u32(info->attrs[NL80211_ATTR_IFTYPE]); - if (type != ntype) + if (otype != ntype) change = true; - type = ntype; - if (type > NL80211_IFTYPE_MAX) { + if (ntype > NL80211_IFTYPE_MAX) { err = -EINVAL; goto unlock; } } if (!drv->ops->change_virtual_intf || - !(drv->wiphy.interface_modes & (1 << type))) { + !(drv->wiphy.interface_modes & (1 << ntype))) { err = -EOPNOTSUPP; goto unlock; } if (info->attrs[NL80211_ATTR_MESH_ID]) { - if (type != NL80211_IFTYPE_MESH_POINT) { + if (ntype != NL80211_IFTYPE_MESH_POINT) { err = -EINVAL; goto unlock; } @@ -663,7 +812,7 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_MNTR_FLAGS]) { - if (type != NL80211_IFTYPE_MONITOR) { + if (ntype != NL80211_IFTYPE_MONITOR) { err = -EINVAL; goto unlock; } @@ -678,12 +827,17 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) if (change) err = drv->ops->change_virtual_intf(&drv->wiphy, ifindex, - type, flags, ¶ms); + ntype, flags, ¶ms); else err = 0; dev = __dev_get_by_index(&init_net, ifindex); - WARN_ON(!dev || (!err && dev->ieee80211_ptr->iftype != type)); + 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); @@ -832,7 +986,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) goto out; } - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOMEM; goto out; @@ -843,7 +997,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(hdr)) { err = PTR_ERR(hdr); - goto out; + goto free_msg; } cookie.msg = msg; @@ -857,7 +1011,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) &cookie, get_key_callback); if (err) - goto out; + goto free_msg; if (cookie.error) goto nla_put_failure; @@ -868,6 +1022,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) nla_put_failure: err = -ENOBUFS; + free_msg: nlmsg_free(msg); out: cfg80211_put_dev(drv); @@ -920,6 +1075,14 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) } err = func(&drv->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; + else + dev->ieee80211_ptr->wext.default_mgmt_key = key_idx; + } +#endif out: cfg80211_put_dev(drv); @@ -934,7 +1097,7 @@ 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; + int err, i; struct net_device *dev; struct key_params params; u8 key_idx = 0; @@ -950,6 +1113,11 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) 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]); @@ -958,51 +1126,23 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - if (key_idx > 5) + if (cfg80211_validate_key_settings(¶ms, key_idx, mac_addr)) return -EINVAL; - /* - * Disallow pairwise keys with non-zero index unless it's WEP - * (because current deployments use pairwise WEP keys with - * non-zero indizes but 802.11i clearly specifies to use zero) - */ - if (mac_addr && key_idx && - params.cipher != WLAN_CIPHER_SUITE_WEP40 && - params.cipher != WLAN_CIPHER_SUITE_WEP104) - return -EINVAL; - - /* TODO: add definitions for the lengths to linux/ieee80211.h */ - switch (params.cipher) { - case WLAN_CIPHER_SUITE_WEP40: - if (params.key_len != 5) - return -EINVAL; - break; - case WLAN_CIPHER_SUITE_TKIP: - if (params.key_len != 32) - return -EINVAL; - break; - case WLAN_CIPHER_SUITE_CCMP: - if (params.key_len != 16) - return -EINVAL; - break; - case WLAN_CIPHER_SUITE_WEP104: - if (params.key_len != 13) - return -EINVAL; - break; - case WLAN_CIPHER_SUITE_AES_CMAC: - if (params.key_len != 16) - return -EINVAL; - break; - default: - return -EINVAL; - } - rtnl_lock(); err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &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; + goto out; + } + if (!drv->ops->add_key) { err = -EOPNOTSUPP; goto out; @@ -1049,6 +1189,15 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) err = drv->ops->del_key(&drv->wiphy, dev, key_idx, mac_addr); +#ifdef CONFIG_WIRELESS_EXT + if (!err) { + 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) + dev->ieee80211_ptr->wext.default_mgmt_key = -1; + } +#endif + out: cfg80211_put_dev(drv); dev_put(dev); @@ -1069,6 +1218,9 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) struct beacon_parameters params; int haveinfo = 0; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_BEACON_TAIL])) + return -EINVAL; + rtnl_lock(); err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); @@ -1186,15 +1338,36 @@ static const struct nla_policy sta_flags_policy[NL80211_STA_FLAG_MAX + 1] = { [NL80211_STA_FLAG_AUTHORIZED] = { .type = NLA_FLAG }, [NL80211_STA_FLAG_SHORT_PREAMBLE] = { .type = NLA_FLAG }, [NL80211_STA_FLAG_WME] = { .type = NLA_FLAG }, + [NL80211_STA_FLAG_MFP] = { .type = NLA_FLAG }, }; -static int parse_station_flags(struct nlattr *nla, u32 *staflags) +static int parse_station_flags(struct genl_info *info, + struct station_parameters *params) { struct nlattr *flags[NL80211_STA_FLAG_MAX + 1]; + struct nlattr *nla; int flag; - *staflags = 0; + /* + * Try parsing the new attribute first so userspace + * can specify both for older kernels. + */ + nla = info->attrs[NL80211_ATTR_STA_FLAGS2]; + if (nla) { + struct nl80211_sta_flag_update *sta_flags; + + sta_flags = nla_data(nla); + params->sta_flags_mask = sta_flags->mask; + params->sta_flags_set = sta_flags->set; + if ((params->sta_flags_mask | + params->sta_flags_set) & BIT(__NL80211_STA_FLAG_INVALID)) + return -EINVAL; + return 0; + } + + /* if present, parse the old attribute */ + nla = info->attrs[NL80211_ATTR_STA_FLAGS]; if (!nla) return 0; @@ -1202,11 +1375,12 @@ static int parse_station_flags(struct nlattr *nla, u32 *staflags) nla, sta_flags_policy)) return -EINVAL; - *staflags = STATION_FLAG_CHANGED; + params->sta_flags_mask = (1 << __NL80211_STA_FLAG_AFTER_LAST) - 1; + params->sta_flags_mask &= ~1; for (flag = 1; flag <= NL80211_STA_FLAG_MAX; flag++) if (flags[flag]) - *staflags |= (1<<flag); + params->sta_flags_set |= (1<<flag); return 0; } @@ -1424,7 +1598,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) if (err) goto out; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out; @@ -1502,8 +1676,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) params.ht_capa = nla_data(info->attrs[NL80211_ATTR_HT_CAPABILITY]); - if (parse_station_flags(info->attrs[NL80211_ATTR_STA_FLAGS], - ¶ms.station_flags)) + if (parse_station_flags(info, ¶ms)) return -EINVAL; if (info->attrs[NL80211_ATTR_STA_PLINK_ACTION]) @@ -1520,6 +1693,51 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) if (err) goto out; + /* validate settings */ + err = 0; + + switch (dev->ieee80211_ptr->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + /* disallow mesh-specific things */ + if (params.plink_action) + err = -EINVAL; + break; + case NL80211_IFTYPE_STATION: + /* disallow everything but AUTHORIZED flag */ + if (params.plink_action) + err = -EINVAL; + if (params.vlan) + err = -EINVAL; + if (params.supported_rates) + err = -EINVAL; + if (params.ht_capa) + err = -EINVAL; + if (params.listen_interval >= 0) + err = -EINVAL; + if (params.sta_flags_mask & ~BIT(NL80211_STA_FLAG_AUTHORIZED)) + err = -EINVAL; + break; + case NL80211_IFTYPE_MESH_POINT: + /* disallow things mesh doesn't support */ + if (params.vlan) + err = -EINVAL; + if (params.ht_capa) + err = -EINVAL; + if (params.listen_interval >= 0) + err = -EINVAL; + if (params.supported_rates) + err = -EINVAL; + if (params.sta_flags_mask) + err = -EINVAL; + break; + default: + err = -EINVAL; + } + + if (err) + goto out; + if (!drv->ops->change_station) { err = -EOPNOTSUPP; goto out; @@ -1551,9 +1769,6 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_MAC]) return -EINVAL; - if (!info->attrs[NL80211_ATTR_STA_AID]) - return -EINVAL; - if (!info->attrs[NL80211_ATTR_STA_LISTEN_INTERVAL]) return -EINVAL; @@ -1567,13 +1782,18 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_RATES]); params.listen_interval = nla_get_u16(info->attrs[NL80211_ATTR_STA_LISTEN_INTERVAL]); - params.aid = nla_get_u16(info->attrs[NL80211_ATTR_STA_AID]); + + if (info->attrs[NL80211_ATTR_STA_AID]) { + params.aid = nla_get_u16(info->attrs[NL80211_ATTR_STA_AID]); + if (!params.aid || params.aid > IEEE80211_MAX_AID) + return -EINVAL; + } + if (info->attrs[NL80211_ATTR_HT_CAPABILITY]) params.ht_capa = nla_data(info->attrs[NL80211_ATTR_HT_CAPABILITY]); - if (parse_station_flags(info->attrs[NL80211_ATTR_STA_FLAGS], - ¶ms.station_flags)) + if (parse_station_flags(info, ¶ms)) return -EINVAL; rtnl_lock(); @@ -1586,6 +1806,38 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (err) goto out; + /* validate settings */ + err = 0; + + switch (dev->ieee80211_ptr->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + /* all ok but must have AID */ + if (!params.aid) + err = -EINVAL; + break; + case NL80211_IFTYPE_MESH_POINT: + /* disallow things mesh doesn't support */ + if (params.vlan) + err = -EINVAL; + if (params.aid) + err = -EINVAL; + if (params.ht_capa) + err = -EINVAL; + if (params.listen_interval >= 0) + err = -EINVAL; + if (params.supported_rates) + err = -EINVAL; + if (params.sta_flags_mask) + err = -EINVAL; + break; + default: + err = -EINVAL; + } + + if (err) + goto out; + if (!drv->ops->add_station) { err = -EOPNOTSUPP; goto out; @@ -1625,6 +1877,13 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) if (err) goto out_rtnl; + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) { + err = -EINVAL; + goto out; + } + if (!drv->ops->del_station) { err = -EOPNOTSUPP; goto out; @@ -1808,7 +2067,7 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) if (err) goto out; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out; @@ -2124,7 +2383,7 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, goto out; /* Draw up a netlink message to send back */ - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOBUFS; goto out; @@ -2302,7 +2561,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) if (!cfg80211_regdomain) goto out; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOBUFS; goto out; @@ -2385,18 +2644,24 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) rem_reg_rules) { num_rules++; if (num_rules > NL80211_MAX_SUPP_REG_RULES) - goto bad_reg; + return -EINVAL; } - if (!reg_is_valid_request(alpha2)) - return -EINVAL; + mutex_lock(&cfg80211_mutex); + + if (!reg_is_valid_request(alpha2)) { + r = -EINVAL; + goto bad_reg; + } size_of_regd = sizeof(struct ieee80211_regdomain) + (num_rules * sizeof(struct ieee80211_reg_rule)); rd = kzalloc(size_of_regd, GFP_KERNEL); - if (!rd) - return -ENOMEM; + if (!rd) { + r = -ENOMEM; + goto bad_reg; + } rd->n_reg_rules = num_rules; rd->alpha2[0] = alpha2[0]; @@ -2413,20 +2678,24 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) rule_idx++; - if (rule_idx > NL80211_MAX_SUPP_REG_RULES) + if (rule_idx > NL80211_MAX_SUPP_REG_RULES) { + r = -EINVAL; goto bad_reg; + } } BUG_ON(rule_idx != num_rules); - mutex_lock(&cfg80211_mutex); r = set_regdom(rd); + mutex_unlock(&cfg80211_mutex); + return r; bad_reg: + mutex_unlock(&cfg80211_mutex); kfree(rd); - return -EINVAL; + return r; } static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) @@ -2442,6 +2711,9 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) enum ieee80211_band band; size_t ie_len; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) + return -EINVAL; + rtnl_lock(); err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); @@ -2492,6 +2764,11 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) else ie_len = 0; + if (ie_len > wiphy->max_scan_ie_len) { + err = -EINVAL; + goto out; + } + request = kzalloc(sizeof(*request) + sizeof(*ssid) * n_ssids + sizeof(channel) * n_channels @@ -2554,7 +2831,8 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_IE]) { request->ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); - memcpy(request->ie, nla_data(info->attrs[NL80211_ATTR_IE]), + memcpy((void *)request->ie, + nla_data(info->attrs[NL80211_ATTR_IE]), request->ie_len); } @@ -2710,6 +2988,15 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) struct wiphy *wiphy; int err; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_AUTH_TYPE]) + return -EINVAL; + rtnl_lock(); err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); @@ -2731,11 +3018,6 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!info->attrs[NL80211_ATTR_MAC]) { - err = -EINVAL; - goto out; - } - wiphy = &drv->wiphy; memset(&req, 0, sizeof(req)); @@ -2761,13 +3043,10 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) req.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } - if (info->attrs[NL80211_ATTR_AUTH_TYPE]) { - req.auth_type = - nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); - if (!nl80211_valid_auth_type(req.auth_type)) { - err = -EINVAL; - goto out; - } + req.auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); + if (!nl80211_valid_auth_type(req.auth_type)) { + err = -EINVAL; + goto out; } err = drv->ops->auth(&drv->wiphy, dev, &req); @@ -2788,6 +3067,13 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) struct wiphy *wiphy; int err; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_MAC] || + !info->attrs[NL80211_ATTR_SSID]) + return -EINVAL; + rtnl_lock(); err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); @@ -2809,12 +3095,6 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!info->attrs[NL80211_ATTR_MAC] || - !info->attrs[NL80211_ATTR_SSID]) { - err = -EINVAL; - goto out; - } - wiphy = &drv->wiphy; memset(&req, 0, sizeof(req)); @@ -2838,6 +3118,19 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) req.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } + if (info->attrs[NL80211_ATTR_USE_MFP]) { + enum nl80211_mfp use_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) { + err = -EINVAL; + goto out; + } + } + + req.control_port = info->attrs[NL80211_ATTR_CONTROL_PORT]; + err = drv->ops->assoc(&drv->wiphy, dev, &req); out: @@ -2856,6 +3149,15 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) struct wiphy *wiphy; int err; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_REASON_CODE]) + return -EINVAL; + rtnl_lock(); err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); @@ -2877,24 +3179,16 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!info->attrs[NL80211_ATTR_MAC]) { - err = -EINVAL; - 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_REASON_CODE]) { - req.reason_code = - nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); - if (req.reason_code == 0) { - /* Reason Code 0 is reserved */ - err = -EINVAL; - goto out; - } + req.reason_code = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); + if (req.reason_code == 0) { + /* Reason Code 0 is reserved */ + err = -EINVAL; + goto out; } if (info->attrs[NL80211_ATTR_IE]) { @@ -2920,6 +3214,15 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) struct wiphy *wiphy; int err; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_REASON_CODE]) + return -EINVAL; + rtnl_lock(); err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); @@ -2941,24 +3244,16 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!info->attrs[NL80211_ATTR_MAC]) { - err = -EINVAL; - 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_REASON_CODE]) { - req.reason_code = - nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); - if (req.reason_code == 0) { - /* Reason Code 0 is reserved */ - err = -EINVAL; - goto out; - } + req.reason_code = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); + if (req.reason_code == 0) { + /* Reason Code 0 is reserved */ + err = -EINVAL; + goto out; } if (info->attrs[NL80211_ATTR_IE]) { @@ -2976,6 +3271,124 @@ unlock_rtnl: return err; } +static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *drv; + struct net_device *dev; + struct cfg80211_ibss_params ibss; + struct wiphy *wiphy; + int err; + + memset(&ibss, 0, sizeof(ibss)); + + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_WIPHY_FREQ] || + !info->attrs[NL80211_ATTR_SSID] || + !nla_len(info->attrs[NL80211_ATTR_SSID])) + return -EINVAL; + + ibss.beacon_interval = 100; + + if (info->attrs[NL80211_ATTR_BEACON_INTERVAL]) { + ibss.beacon_interval = + nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]); + if (ibss.beacon_interval < 1 || ibss.beacon_interval > 10000) + return -EINVAL; + } + + rtnl_lock(); + + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + if (err) + goto unlock_rtnl; + + if (!drv->ops->join_ibss) { + err = -EOPNOTSUPP; + goto out; + } + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) { + err = -EOPNOTSUPP; + goto out; + } + + if (!netif_running(dev)) { + err = -ENETDOWN; + goto out; + } + + wiphy = &drv->wiphy; + + if (info->attrs[NL80211_ATTR_MAC]) + ibss.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); + ibss.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); + ibss.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + + if (info->attrs[NL80211_ATTR_IE]) { + ibss.ie = nla_data(info->attrs[NL80211_ATTR_IE]); + ibss.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + } + + ibss.channel = ieee80211_get_channel(wiphy, + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); + if (!ibss.channel || + ibss.channel->flags & IEEE80211_CHAN_NO_IBSS || + ibss.channel->flags & IEEE80211_CHAN_DISABLED) { + err = -EINVAL; + goto out; + } + + ibss.channel_fixed = !!info->attrs[NL80211_ATTR_FREQ_FIXED]; + + err = cfg80211_join_ibss(drv, dev, &ibss); + +out: + cfg80211_put_dev(drv); + dev_put(dev); +unlock_rtnl: + rtnl_unlock(); + return err; +} + +static int nl80211_leave_ibss(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *drv; + struct net_device *dev; + int err; + + rtnl_lock(); + + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); + if (err) + goto unlock_rtnl; + + if (!drv->ops->leave_ibss) { + err = -EOPNOTSUPP; + goto out; + } + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) { + err = -EOPNOTSUPP; + goto out; + } + + if (!netif_running(dev)) { + err = -ENETDOWN; + goto out; + } + + err = cfg80211_leave_ibss(drv, dev, false); + +out: + cfg80211_put_dev(drv); + dev_put(dev); +unlock_rtnl: + rtnl_unlock(); + return err; +} + static struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_WIPHY, @@ -3177,6 +3590,18 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, }, + { + .cmd = NL80211_CMD_JOIN_IBSS, + .doit = nl80211_join_ibss, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = NL80211_CMD_LEAVE_IBSS, + .doit = nl80211_leave_ibss, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { .name = "mlme", @@ -3199,7 +3624,7 @@ void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev) { struct sk_buff *msg; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -3211,11 +3636,43 @@ void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev) genlmsg_multicast(msg, 0, nl80211_config_mcgrp.id, GFP_KERNEL); } +static int nl80211_add_scan_req(struct sk_buff *msg, + struct cfg80211_registered_device *rdev) +{ + struct cfg80211_scan_request *req = rdev->scan_req; + struct nlattr *nest; + int i; + + if (WARN_ON(!req)) + return 0; + + nest = nla_nest_start(msg, NL80211_ATTR_SCAN_SSIDS); + if (!nest) + goto nla_put_failure; + for (i = 0; i < req->n_ssids; i++) + NLA_PUT(msg, i, req->ssids[i].ssid_len, req->ssids[i].ssid); + nla_nest_end(msg, nest); + + nest = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES); + if (!nest) + goto nla_put_failure; + for (i = 0; i < req->n_channels; i++) + NLA_PUT_U32(msg, i, req->channels[i]->center_freq); + nla_nest_end(msg, nest); + + if (req->ie) + NLA_PUT(msg, NL80211_ATTR_IE, req->ie_len, req->ie); + + return 0; + nla_put_failure: + 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) + struct cfg80211_registered_device *rdev, + struct net_device *netdev, + u32 pid, u32 seq, int flags, + u32 cmd) { void *hdr; @@ -3226,7 +3683,8 @@ static int nl80211_send_scan_donemsg(struct sk_buff *msg, NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); - /* XXX: we should probably bounce back the request? */ + /* ignore errors and send incomplete event anyway */ + nl80211_add_scan_req(msg, rdev); return genlmsg_end(msg, hdr); @@ -3240,7 +3698,7 @@ void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, { struct sk_buff *msg; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -3258,7 +3716,7 @@ void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, { struct sk_buff *msg; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -3280,7 +3738,7 @@ void nl80211_send_reg_change_event(struct regulatory_request *request) struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -3334,7 +3792,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return; @@ -3375,38 +3833,208 @@ void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, nl80211_send_mlme_event(rdev, netdev, buf, len, NL80211_CMD_ASSOCIATE); } -void nl80211_send_rx_deauth(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *buf, - size_t len) +void nl80211_send_deauth(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *buf, size_t len) { nl80211_send_mlme_event(rdev, netdev, buf, len, NL80211_CMD_DEAUTHENTICATE); } -void nl80211_send_rx_disassoc(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *buf, - size_t len) +void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *buf, + size_t len) { nl80211_send_mlme_event(rdev, netdev, buf, len, NL80211_CMD_DISASSOCIATE); } +static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev, + struct net_device *netdev, int cmd, + const u8 *addr) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, cmd); + 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_FLAG(msg, NL80211_ATTR_TIMED_OUT); + NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, addr); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, GFP_ATOMIC); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + +void nl80211_send_auth_timeout(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *addr) +{ + nl80211_send_mlme_timeout(rdev, netdev, NL80211_CMD_AUTHENTICATE, + addr); +} + +void nl80211_send_assoc_timeout(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *addr) +{ + nl80211_send_mlme_timeout(rdev, netdev, NL80211_CMD_ASSOCIATE, addr); +} + +void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid, + gfp_t gfp) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_JOIN_IBSS); + 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 (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + +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) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_MICHAEL_MIC_FAILURE); + 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 (addr) + NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, addr); + NLA_PUT_U32(msg, NL80211_ATTR_KEY_TYPE, key_type); + NLA_PUT_U8(msg, NL80211_ATTR_KEY_IDX, key_id); + if (tsc) + NLA_PUT(msg, NL80211_ATTR_KEY_SEQ, 6, tsc); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, GFP_ATOMIC); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + +void nl80211_send_beacon_hint_event(struct wiphy *wiphy, + struct ieee80211_channel *channel_before, + struct ieee80211_channel *channel_after) +{ + struct sk_buff *msg; + void *hdr; + struct nlattr *nl_freq; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_REG_BEACON_HINT); + if (!hdr) { + nlmsg_free(msg); + return; + } + + /* + * Since we are applying the beacon hint to a wiphy we know its + * wiphy_idx is valid + */ + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy)); + + /* Before */ + nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_BEFORE); + if (!nl_freq) + goto nla_put_failure; + if (nl80211_msg_put_channel(msg, channel_before)) + goto nla_put_failure; + nla_nest_end(msg, nl_freq); + + /* After */ + nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_AFTER); + if (!nl_freq) + goto nla_put_failure; + if (nl80211_msg_put_channel(msg, channel_after)) + goto nla_put_failure; + nla_nest_end(msg, nl_freq); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast(msg, 0, nl80211_regulatory_mcgrp.id, GFP_ATOMIC); + + return; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + /* initialisation/exit functions */ int nl80211_init(void) { - int err, i; + int err; - err = genl_register_family(&nl80211_fam); + err = genl_register_family_with_ops(&nl80211_fam, + nl80211_ops, ARRAY_SIZE(nl80211_ops)); if (err) return err; - for (i = 0; i < ARRAY_SIZE(nl80211_ops); i++) { - err = genl_register_ops(&nl80211_fam, &nl80211_ops[i]); - if (err) - goto err_out; - } - err = genl_register_mc_group(&nl80211_fam, &nl80211_config_mcgrp); if (err) goto err_out; diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index b77af4ab80b..5c12ad13499 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -17,11 +17,31 @@ extern void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, 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_rx_deauth(struct cfg80211_registered_device *rdev, - struct net_device *netdev, - const u8 *buf, size_t len); -extern void nl80211_send_rx_disassoc(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, + 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 +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); + +extern void +nl80211_send_beacon_hint_event(struct wiphy *wiphy, + struct ieee80211_channel *channel_before, + struct ieee80211_channel *channel_after); + +void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid, + gfp_t gfp); #endif /* __NET_WIRELESS_NL80211_H */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 487cb627ddb..75a406d3361 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -37,7 +37,6 @@ #include <linux/random.h> #include <linux/nl80211.h> #include <linux/platform_device.h> -#include <net/wireless.h> #include <net/cfg80211.h> #include "core.h" #include "reg.h" @@ -49,12 +48,6 @@ static struct regulatory_request *last_request; /* To trigger userspace events */ static struct platform_device *reg_pdev; -/* Keep the ordering from large to small */ -static u32 supported_bandwidths[] = { - MHZ_TO_KHZ(40), - MHZ_TO_KHZ(20), -}; - /* * Central wireless core regulatory domains, we only need two, * the current one and a world regulatory domain in case we have no @@ -389,6 +382,8 @@ static int call_crda(const char *alpha2) /* Used by nl80211 before kmalloc'ing our regulatory domain */ bool reg_is_valid_request(const char *alpha2) { + assert_cfg80211_lock(); + if (!last_request) return false; @@ -436,19 +431,20 @@ static bool is_valid_rd(const struct ieee80211_regdomain *rd) return true; } -/* Returns value in KHz */ -static u32 freq_max_bandwidth(const struct ieee80211_freq_range *freq_range, - u32 freq) +static bool reg_does_bw_fit(const struct ieee80211_freq_range *freq_range, + u32 center_freq_khz, + u32 bw_khz) { - unsigned int i; - for (i = 0; i < ARRAY_SIZE(supported_bandwidths); i++) { - u32 start_freq_khz = freq - supported_bandwidths[i]/2; - u32 end_freq_khz = freq + supported_bandwidths[i]/2; - if (start_freq_khz >= freq_range->start_freq_khz && - end_freq_khz <= freq_range->end_freq_khz) - return supported_bandwidths[i]; - } - return 0; + u32 start_freq_khz, end_freq_khz; + + start_freq_khz = center_freq_khz - (bw_khz/2); + end_freq_khz = center_freq_khz + (bw_khz/2); + + if (start_freq_khz >= freq_range->start_freq_khz && + end_freq_khz <= freq_range->end_freq_khz) + return true; + + return false; } /** @@ -848,14 +844,17 @@ static u32 map_regdom_flags(u32 rd_flags) static int freq_reg_info_regd(struct wiphy *wiphy, u32 center_freq, - u32 *bandwidth, + u32 desired_bw_khz, const struct ieee80211_reg_rule **reg_rule, const struct ieee80211_regdomain *custom_regd) { int i; bool band_rule_found = false; const struct ieee80211_regdomain *regd; - u32 max_bandwidth = 0; + bool bw_fits = false; + + if (!desired_bw_khz) + desired_bw_khz = MHZ_TO_KHZ(20); regd = custom_regd ? custom_regd : cfg80211_regdomain; @@ -888,38 +887,54 @@ static int freq_reg_info_regd(struct wiphy *wiphy, if (!band_rule_found) band_rule_found = freq_in_rule_band(fr, center_freq); - max_bandwidth = freq_max_bandwidth(fr, center_freq); + bw_fits = reg_does_bw_fit(fr, + center_freq, + desired_bw_khz); - if (max_bandwidth && *bandwidth <= max_bandwidth) { + if (band_rule_found && bw_fits) { *reg_rule = rr; - *bandwidth = max_bandwidth; - break; + return 0; } } if (!band_rule_found) return -ERANGE; - return !max_bandwidth; + return -EINVAL; } EXPORT_SYMBOL(freq_reg_info); -int freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 *bandwidth, - const struct ieee80211_reg_rule **reg_rule) +int freq_reg_info(struct wiphy *wiphy, + u32 center_freq, + u32 desired_bw_khz, + const struct ieee80211_reg_rule **reg_rule) { assert_cfg80211_lock(); - return freq_reg_info_regd(wiphy, center_freq, - bandwidth, reg_rule, NULL); + return freq_reg_info_regd(wiphy, + center_freq, + desired_bw_khz, + reg_rule, + NULL); } +/* + * Note that right now we assume the desired channel bandwidth + * is always 20 MHz for each individual channel (HT40 uses 20 MHz + * per channel, the primary and the extension channel). To support + * smaller custom bandwidths such as 5 MHz or 10 MHz we'll need a + * new ieee80211_channel.target_bw and re run the regulatory check + * on the wiphy with the target_bw specified. Then we can simply use + * that below for the desired_bw_khz below. + */ static void handle_channel(struct wiphy *wiphy, enum ieee80211_band band, unsigned int chan_idx) { int r; - u32 flags; - u32 max_bandwidth = 0; + u32 flags, bw_flags = 0; + u32 desired_bw_khz = MHZ_TO_KHZ(20); const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; + const struct ieee80211_freq_range *freq_range = NULL; struct ieee80211_supported_band *sband; struct ieee80211_channel *chan; struct wiphy *request_wiphy = NULL; @@ -934,8 +949,10 @@ static void handle_channel(struct wiphy *wiphy, enum ieee80211_band band, flags = chan->orig_flags; - r = freq_reg_info(wiphy, MHZ_TO_KHZ(chan->center_freq), - &max_bandwidth, ®_rule); + r = freq_reg_info(wiphy, + MHZ_TO_KHZ(chan->center_freq), + desired_bw_khz, + ®_rule); if (r) { /* @@ -978,6 +995,10 @@ static void handle_channel(struct wiphy *wiphy, enum ieee80211_band band, } power_rule = ®_rule->power_rule; + freq_range = ®_rule->freq_range; + + if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(40)) + bw_flags = IEEE80211_CHAN_NO_HT40; if (last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER && request_wiphy && request_wiphy == wiphy && @@ -988,19 +1009,19 @@ static void handle_channel(struct wiphy *wiphy, enum ieee80211_band band, * settings */ chan->flags = chan->orig_flags = - map_regdom_flags(reg_rule->flags); + 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(max_bandwidth); + chan->max_bandwidth = KHZ_TO_MHZ(desired_bw_khz); chan->max_power = chan->orig_mpwr = (int) MBM_TO_DBM(power_rule->max_eirp); return; } - chan->flags = flags | map_regdom_flags(reg_rule->flags); + 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(max_bandwidth); + 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)); @@ -1050,18 +1071,10 @@ static void handle_reg_beacon(struct wiphy *wiphy, unsigned int chan_idx, struct reg_beacon *reg_beacon) { -#ifdef CONFIG_CFG80211_REG_DEBUG -#define REG_DEBUG_BEACON_FLAG(desc) \ - printk(KERN_DEBUG "cfg80211: Enabling " desc " on " \ - "frequency: %d MHz (Ch %d) on %s\n", \ - reg_beacon->chan.center_freq, \ - ieee80211_frequency_to_channel(reg_beacon->chan.center_freq), \ - wiphy_name(wiphy)); -#else -#define REG_DEBUG_BEACON_FLAG(desc) do {} while (0) -#endif struct ieee80211_supported_band *sband; struct ieee80211_channel *chan; + bool channel_changed = false; + struct ieee80211_channel chan_before; assert_cfg80211_lock(); @@ -1071,18 +1084,29 @@ static void handle_reg_beacon(struct wiphy *wiphy, if (likely(chan->center_freq != reg_beacon->chan.center_freq)) return; + if (chan->beacon_found) + return; + + chan->beacon_found = true; + + if (wiphy->disable_beacon_hints) + return; + + chan_before.center_freq = chan->center_freq; + chan_before.flags = chan->flags; + if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) { chan->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN; - REG_DEBUG_BEACON_FLAG("active scanning"); + channel_changed = true; } if (chan->flags & IEEE80211_CHAN_NO_IBSS) { chan->flags &= ~IEEE80211_CHAN_NO_IBSS; - REG_DEBUG_BEACON_FLAG("beaconing"); + channel_changed = true; } - chan->beacon_found = true; -#undef REG_DEBUG_BEACON_FLAG + if (channel_changed) + nl80211_send_beacon_hint_event(wiphy, &chan_before, chan); } /* @@ -1155,6 +1179,93 @@ static void reg_process_beacons(struct wiphy *wiphy) wiphy_update_beacon_reg(wiphy); } +static bool is_ht40_not_allowed(struct ieee80211_channel *chan) +{ + if (!chan) + return true; + if (chan->flags & IEEE80211_CHAN_DISABLED) + return true; + /* This would happen when regulatory rules disallow HT40 completely */ + if (IEEE80211_CHAN_NO_HT40 == (chan->flags & (IEEE80211_CHAN_NO_HT40))) + return true; + return false; +} + +static void reg_process_ht_flags_channel(struct wiphy *wiphy, + enum ieee80211_band band, + unsigned int chan_idx) +{ + struct ieee80211_supported_band *sband; + struct ieee80211_channel *channel; + struct ieee80211_channel *channel_before = NULL, *channel_after = NULL; + unsigned int i; + + assert_cfg80211_lock(); + + sband = wiphy->bands[band]; + BUG_ON(chan_idx >= sband->n_channels); + channel = &sband->channels[chan_idx]; + + if (is_ht40_not_allowed(channel)) { + channel->flags |= IEEE80211_CHAN_NO_HT40; + return; + } + + /* + * We need to ensure the extension channels exist to + * be able to use HT40- or HT40+, this finds them (or not) + */ + for (i = 0; i < sband->n_channels; i++) { + struct ieee80211_channel *c = &sband->channels[i]; + if (c->center_freq == (channel->center_freq - 20)) + channel_before = c; + if (c->center_freq == (channel->center_freq + 20)) + channel_after = c; + } + + /* + * Please note that this assumes target bandwidth is 20 MHz, + * if that ever changes we also need to change the below logic + * to include that as well. + */ + if (is_ht40_not_allowed(channel_before)) + channel->flags |= IEEE80211_CHAN_NO_HT40MINUS; + else + channel->flags &= ~IEEE80211_CHAN_NO_HT40MINUS; + + if (is_ht40_not_allowed(channel_after)) + channel->flags |= IEEE80211_CHAN_NO_HT40PLUS; + else + channel->flags &= ~IEEE80211_CHAN_NO_HT40PLUS; +} + +static void reg_process_ht_flags_band(struct wiphy *wiphy, + enum ieee80211_band band) +{ + unsigned int i; + struct ieee80211_supported_band *sband; + + BUG_ON(!wiphy->bands[band]); + sband = wiphy->bands[band]; + + for (i = 0; i < sband->n_channels; i++) + reg_process_ht_flags_channel(wiphy, band, i); +} + +static void reg_process_ht_flags(struct wiphy *wiphy) +{ + enum ieee80211_band band; + + if (!wiphy) + return; + + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + if (wiphy->bands[band]) + reg_process_ht_flags_band(wiphy, band); + } + +} + void wiphy_update_regulatory(struct wiphy *wiphy, enum nl80211_reg_initiator initiator) { @@ -1168,6 +1279,7 @@ void wiphy_update_regulatory(struct wiphy *wiphy, } out: reg_process_beacons(wiphy); + reg_process_ht_flags(wiphy); if (wiphy->reg_notifier) wiphy->reg_notifier(wiphy, last_request); } @@ -1178,9 +1290,11 @@ static void handle_channel_custom(struct wiphy *wiphy, const struct ieee80211_regdomain *regd) { int r; - u32 max_bandwidth = 0; + u32 desired_bw_khz = MHZ_TO_KHZ(20); + u32 bw_flags = 0; const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; + const struct ieee80211_freq_range *freq_range = NULL; struct ieee80211_supported_band *sband; struct ieee80211_channel *chan; @@ -1190,8 +1304,11 @@ static void handle_channel_custom(struct wiphy *wiphy, BUG_ON(chan_idx >= sband->n_channels); chan = &sband->channels[chan_idx]; - r = freq_reg_info_regd(wiphy, MHZ_TO_KHZ(chan->center_freq), - &max_bandwidth, ®_rule, regd); + r = freq_reg_info_regd(wiphy, + MHZ_TO_KHZ(chan->center_freq), + desired_bw_khz, + ®_rule, + regd); if (r) { chan->flags = IEEE80211_CHAN_DISABLED; @@ -1199,10 +1316,14 @@ static void handle_channel_custom(struct wiphy *wiphy, } power_rule = ®_rule->power_rule; + freq_range = ®_rule->freq_range; + + if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(40)) + bw_flags = IEEE80211_CHAN_NO_HT40; - chan->flags |= map_regdom_flags(reg_rule->flags); + 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(max_bandwidth); + chan->max_bandwidth = KHZ_TO_MHZ(desired_bw_khz); chan->max_power = (int) MBM_TO_DBM(power_rule->max_eirp); } @@ -1224,13 +1345,22 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, const struct ieee80211_regdomain *regd) { enum ieee80211_band band; + unsigned int bands_set = 0; mutex_lock(&cfg80211_mutex); for (band = 0; band < IEEE80211_NUM_BANDS; band++) { - if (wiphy->bands[band]) - handle_band_custom(wiphy, band, regd); + if (!wiphy->bands[band]) + continue; + handle_band_custom(wiphy, band, regd); + bands_set++; } mutex_unlock(&cfg80211_mutex); + + /* + * no point in calling this if it won't have any effect + * on your device's supportd bands. + */ + WARN_ON(!bands_set); } EXPORT_SYMBOL(wiphy_apply_custom_regulatory); @@ -2000,7 +2130,12 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) * driver wanted to the wiphy to deal with conflicts */ - BUG_ON(request_wiphy->regd); + /* + * Userspace could have sent two replies with only + * one kernel request. + */ + if (request_wiphy->regd) + return -EALREADY; r = reg_copy_regd(&request_wiphy->regd, rd); if (r) @@ -2042,7 +2177,13 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) * the country IE rd with what CRDA believes that country should have */ - BUG_ON(!country_ie_regdomain); + /* + * Userspace could have sent two replies with only + * one kernel request. By the second reply we would have + * already processed and consumed the country_ie_regdomain. + */ + if (!country_ie_regdomain) + return -EALREADY; BUG_ON(rd == country_ie_regdomain); /* @@ -2119,14 +2260,14 @@ void reg_device_remove(struct wiphy *wiphy) assert_cfg80211_lock(); + kfree(wiphy->regd); + if (last_request) request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); - kfree(wiphy->regd); - if (!last_request || !request_wiphy) - return; - if (request_wiphy != wiphy) + if (!request_wiphy || request_wiphy != wiphy) return; + last_request->wiphy_idx = WIPHY_IDX_STALE; last_request->country_ie_env = ENVIRON_ANY; } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index e37829a49dc..4e167a8e11b 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -30,7 +30,8 @@ int set_regdom(const struct ieee80211_regdomain *rd); * non-radar 5 GHz channels. * * Drivers do not need to call this, cfg80211 will do it for after a scan - * on a newly found BSS. + * on a newly found BSS. If you cannot make use of this feature you can + * set the wiphy->disable_beacon_hints to true. */ int regulatory_hint_found_beacon(struct wiphy *wiphy, struct ieee80211_channel *beacon_chan, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 1f260c40b6c..7e595ce24ee 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -29,7 +29,6 @@ void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) goto out; WARN_ON(request != wiphy_to_dev(request->wiphy)->scan_req); - wiphy_to_dev(request->wiphy)->scan_req = NULL; if (aborted) nl80211_send_scan_aborted(wiphy_to_dev(request->wiphy), dev); @@ -47,6 +46,7 @@ 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); } EXPORT_SYMBOL(cfg80211_scan_done); @@ -118,7 +118,7 @@ static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2) if (!ie1 && !ie2) return 0; - if (!ie1) + if (!ie1 || !ie2) return -1; r = memcmp(ie1 + 2, ie2 + 2, min(ie1[1], ie2[1])); @@ -171,6 +171,8 @@ static bool is_mesh(struct cfg80211_bss *a, ie = find_ie(WLAN_EID_MESH_CONFIG, a->information_elements, a->len_information_elements); + if (!ie) + return false; if (ie[1] != IEEE80211_MESH_CONFIG_LEN) return false; @@ -365,7 +367,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, found = rb_find_bss(dev, res); if (found) { - kref_get(&found->ref); found->pub.beacon_interval = res->pub.beacon_interval; found->pub.tsf = res->pub.tsf; found->pub.signal = res->pub.signal; @@ -377,18 +378,16 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, size_t used = dev->wiphy.bss_priv_size + sizeof(*res); size_t ielen = res->pub.len_information_elements; - if (ksize(found) >= used + ielen) { + if (!found->ies_allocated && ksize(found) >= used + ielen) { memcpy(found->pub.information_elements, res->pub.information_elements, ielen); found->pub.len_information_elements = ielen; } else { u8 *ies = found->pub.information_elements; - if (found->ies_allocated) { - if (ksize(ies) < ielen) - ies = krealloc(ies, ielen, - GFP_ATOMIC); - } else + if (found->ies_allocated) + ies = krealloc(ies, ielen, GFP_ATOMIC); + else ies = kmalloc(ielen, GFP_ATOMIC); if (ies) { @@ -415,6 +414,55 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, return found; } +struct cfg80211_bss* +cfg80211_inform_bss(struct wiphy *wiphy, + struct ieee80211_channel *channel, + const u8 *bssid, + u64 timestamp, u16 capability, u16 beacon_interval, + const u8 *ie, size_t ielen, + s32 signal, gfp_t gfp) +{ + struct cfg80211_internal_bss *res; + size_t privsz; + + if (WARN_ON(!wiphy)) + return NULL; + + privsz = wiphy->bss_priv_size; + + if (WARN_ON(wiphy->signal_type == NL80211_BSS_SIGNAL_UNSPEC && + (signal < 0 || signal > 100))) + return NULL; + + res = kzalloc(sizeof(*res) + privsz + ielen, gfp); + if (!res) + return NULL; + + memcpy(res->pub.bssid, bssid, ETH_ALEN); + res->pub.channel = channel; + res->pub.signal = signal; + res->pub.tsf = timestamp; + res->pub.beacon_interval = beacon_interval; + res->pub.capability = capability; + /* point to after the private area */ + res->pub.information_elements = (u8 *)res + sizeof(*res) + privsz; + memcpy(res->pub.information_elements, ie, ielen); + res->pub.len_information_elements = ielen; + + kref_init(&res->ref); + + res = cfg80211_bss_update(wiphy_to_dev(wiphy), res, 0); + if (!res) + return NULL; + + if (res->pub.capability & WLAN_CAPABILITY_ESS) + regulatory_hint_found_beacon(wiphy, channel, gfp); + + /* cfg80211_bss_update gives us a referenced result */ + return &res->pub; +} +EXPORT_SYMBOL(cfg80211_inform_bss); + struct cfg80211_bss * cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_channel *channel, @@ -605,7 +653,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, cfg80211_put_dev(rdev); return err; } -EXPORT_SYMBOL(cfg80211_wext_siwscan); +EXPORT_SYMBOL_GPL(cfg80211_wext_siwscan); static void ieee80211_scan_add_ies(struct iw_request_info *info, struct cfg80211_bss *bss, @@ -914,5 +962,5 @@ int cfg80211_wext_giwscan(struct net_device *dev, cfg80211_put_dev(rdev); return res; } -EXPORT_SYMBOL(cfg80211_wext_giwscan); +EXPORT_SYMBOL_GPL(cfg80211_wext_giwscan); #endif diff --git a/net/wireless/util.c b/net/wireless/util.c index 487cdd9bcff..25550692dda 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1,10 +1,12 @@ /* * Wireless utility functions * - * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> */ -#include <net/wireless.h> -#include <asm/bitops.h> +#include <linux/bitops.h> +#include <linux/etherdevice.h> +#include <net/cfg80211.h> +#include <net/ip.h> #include "core.h" struct ieee80211_rate * @@ -138,3 +140,365 @@ void ieee80211_set_bitrate_flags(struct wiphy *wiphy) if (wiphy->bands[band]) set_mandatory_flags_band(wiphy->bands[band], band); } + +int cfg80211_validate_key_settings(struct key_params *params, int key_idx, + const u8 *mac_addr) +{ + if (key_idx > 5) + return -EINVAL; + + /* + * Disallow pairwise keys with non-zero index unless it's WEP + * (because current deployments use pairwise WEP keys with + * non-zero indizes but 802.11i clearly specifies to use zero) + */ + if (mac_addr && key_idx && + params->cipher != WLAN_CIPHER_SUITE_WEP40 && + params->cipher != WLAN_CIPHER_SUITE_WEP104) + return -EINVAL; + + switch (params->cipher) { + case WLAN_CIPHER_SUITE_WEP40: + if (params->key_len != WLAN_KEY_LEN_WEP40) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_TKIP: + if (params->key_len != WLAN_KEY_LEN_TKIP) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_CCMP: + if (params->key_len != WLAN_KEY_LEN_CCMP) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_WEP104: + if (params->key_len != WLAN_KEY_LEN_WEP104) + return -EINVAL; + break; + case WLAN_CIPHER_SUITE_AES_CMAC: + if (params->key_len != WLAN_KEY_LEN_AES_CMAC) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (params->seq) { + switch (params->cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + /* These ciphers do not use key sequence */ + return -EINVAL; + case WLAN_CIPHER_SUITE_TKIP: + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_AES_CMAC: + if (params->seq_len != 6) + return -EINVAL; + break; + } + } + + return 0; +} + +/* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ +/* Ethernet-II snap header (RFC1042 for most EtherTypes) */ +const unsigned char rfc1042_header[] __aligned(2) = + { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; +EXPORT_SYMBOL(rfc1042_header); + +/* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */ +const unsigned char bridge_tunnel_header[] __aligned(2) = + { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; +EXPORT_SYMBOL(bridge_tunnel_header); + +unsigned int ieee80211_hdrlen(__le16 fc) +{ + unsigned int hdrlen = 24; + + if (ieee80211_is_data(fc)) { + if (ieee80211_has_a4(fc)) + hdrlen = 30; + if (ieee80211_is_data_qos(fc)) + hdrlen += IEEE80211_QOS_CTL_LEN; + goto out; + } + + if (ieee80211_is_ctl(fc)) { + /* + * ACK and CTS are 10 bytes, all others 16. To see how + * to get this condition consider + * subtype mask: 0b0000000011110000 (0x00F0) + * ACK subtype: 0b0000000011010000 (0x00D0) + * CTS subtype: 0b0000000011000000 (0x00C0) + * bits that matter: ^^^ (0x00E0) + * value of those: 0b0000000011000000 (0x00C0) + */ + if ((fc & cpu_to_le16(0x00E0)) == cpu_to_le16(0x00C0)) + hdrlen = 10; + else + hdrlen = 16; + } +out: + return hdrlen; +} +EXPORT_SYMBOL(ieee80211_hdrlen); + +unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb) +{ + const struct ieee80211_hdr *hdr = + (const struct ieee80211_hdr *)skb->data; + unsigned int hdrlen; + + if (unlikely(skb->len < 10)) + return 0; + hdrlen = ieee80211_hdrlen(hdr->frame_control); + if (unlikely(hdrlen > skb->len)) + return 0; + return hdrlen; +} +EXPORT_SYMBOL(ieee80211_get_hdrlen_from_skb); + +static int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) +{ + int ae = meshhdr->flags & MESH_FLAGS_AE; + /* 7.1.3.5a.2 */ + switch (ae) { + case 0: + return 6; + case 1: + return 12; + case 2: + return 18; + case 3: + return 24; + default: + return 6; + } +} + +int ieee80211_data_to_8023(struct sk_buff *skb, u8 *addr, + enum nl80211_iftype iftype) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + u16 hdrlen, ethertype; + u8 *payload; + u8 dst[ETH_ALEN]; + u8 src[ETH_ALEN] __aligned(2); + + if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) + return -1; + + hdrlen = ieee80211_hdrlen(hdr->frame_control); + + /* convert IEEE 802.11 header + possible LLC headers into Ethernet + * header + * IEEE 802.11 address fields: + * ToDS FromDS Addr1 Addr2 Addr3 Addr4 + * 0 0 DA SA BSSID n/a + * 0 1 DA BSSID SA n/a + * 1 0 BSSID SA DA n/a + * 1 1 RA TA DA SA + */ + memcpy(dst, ieee80211_get_DA(hdr), ETH_ALEN); + memcpy(src, ieee80211_get_SA(hdr), ETH_ALEN); + + switch (hdr->frame_control & + cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) { + case cpu_to_le16(IEEE80211_FCTL_TODS): + if (unlikely(iftype != NL80211_IFTYPE_AP && + iftype != NL80211_IFTYPE_AP_VLAN)) + return -1; + break; + case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS): + if (unlikely(iftype != NL80211_IFTYPE_WDS && + iftype != NL80211_IFTYPE_MESH_POINT)) + 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_A5_A6) { + memcpy(dst, meshdr->eaddr1, ETH_ALEN); + memcpy(src, meshdr->eaddr2, ETH_ALEN); + } + } + break; + case cpu_to_le16(IEEE80211_FCTL_FROMDS): + if (iftype != NL80211_IFTYPE_STATION || + (is_multicast_ether_addr(dst) && + !compare_ether_addr(src, addr))) + return -1; + break; + case cpu_to_le16(0): + if (iftype != NL80211_IFTYPE_ADHOC) + return -1; + break; + } + + if (unlikely(skb->len - hdrlen < 8)) + return -1; + + payload = skb->data + hdrlen; + ethertype = (payload[6] << 8) | payload[7]; + + if (likely((compare_ether_addr(payload, rfc1042_header) == 0 && + ethertype != ETH_P_AARP && ethertype != ETH_P_IPX) || + compare_ether_addr(payload, bridge_tunnel_header) == 0)) { + /* remove RFC1042 or Bridge-Tunnel encapsulation and + * replace EtherType */ + skb_pull(skb, hdrlen + 6); + memcpy(skb_push(skb, ETH_ALEN), src, ETH_ALEN); + memcpy(skb_push(skb, ETH_ALEN), dst, ETH_ALEN); + } else { + struct ethhdr *ehdr; + __be16 len; + + skb_pull(skb, hdrlen); + len = htons(skb->len); + ehdr = (struct ethhdr *) skb_push(skb, sizeof(struct ethhdr)); + memcpy(ehdr->h_dest, dst, ETH_ALEN); + memcpy(ehdr->h_source, src, ETH_ALEN); + ehdr->h_proto = len; + } + return 0; +} +EXPORT_SYMBOL(ieee80211_data_to_8023); + +int ieee80211_data_from_8023(struct sk_buff *skb, u8 *addr, + enum nl80211_iftype iftype, u8 *bssid, bool qos) +{ + struct ieee80211_hdr hdr; + u16 hdrlen, ethertype; + __le16 fc; + const u8 *encaps_data; + int encaps_len, skip_header_bytes; + int nh_pos, h_pos; + int head_need; + + if (unlikely(skb->len < ETH_HLEN)) + return -EINVAL; + + nh_pos = skb_network_header(skb) - skb->data; + h_pos = skb_transport_header(skb) - skb->data; + + /* convert Ethernet header to proper 802.11 header (based on + * operation mode) */ + ethertype = (skb->data[12] << 8) | skb->data[13]; + fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); + + switch (iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); + /* DA BSSID SA */ + memcpy(hdr.addr1, skb->data, ETH_ALEN); + memcpy(hdr.addr2, addr, ETH_ALEN); + memcpy(hdr.addr3, skb->data + ETH_ALEN, ETH_ALEN); + hdrlen = 24; + break; + case NL80211_IFTYPE_STATION: + fc |= cpu_to_le16(IEEE80211_FCTL_TODS); + /* BSSID SA DA */ + memcpy(hdr.addr1, bssid, ETH_ALEN); + memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); + memcpy(hdr.addr3, skb->data, ETH_ALEN); + hdrlen = 24; + break; + case NL80211_IFTYPE_ADHOC: + /* DA SA BSSID */ + memcpy(hdr.addr1, skb->data, ETH_ALEN); + memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); + memcpy(hdr.addr3, bssid, ETH_ALEN); + hdrlen = 24; + break; + default: + return -EOPNOTSUPP; + } + + if (qos) { + fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA); + hdrlen += 2; + } + + hdr.frame_control = fc; + hdr.duration_id = 0; + hdr.seq_ctrl = 0; + + skip_header_bytes = ETH_HLEN; + if (ethertype == ETH_P_AARP || ethertype == ETH_P_IPX) { + encaps_data = bridge_tunnel_header; + encaps_len = sizeof(bridge_tunnel_header); + skip_header_bytes -= 2; + } else if (ethertype > 0x600) { + encaps_data = rfc1042_header; + encaps_len = sizeof(rfc1042_header); + skip_header_bytes -= 2; + } else { + encaps_data = NULL; + encaps_len = 0; + } + + skb_pull(skb, skip_header_bytes); + nh_pos -= skip_header_bytes; + h_pos -= skip_header_bytes; + + head_need = hdrlen + encaps_len - skb_headroom(skb); + + if (head_need > 0 || skb_cloned(skb)) { + head_need = max(head_need, 0); + if (head_need) + skb_orphan(skb); + + if (pskb_expand_head(skb, head_need, 0, GFP_ATOMIC)) { + printk(KERN_ERR "failed to reallocate Tx buffer\n"); + return -ENOMEM; + } + skb->truesize += head_need; + } + + if (encaps_data) { + memcpy(skb_push(skb, encaps_len), encaps_data, encaps_len); + nh_pos += encaps_len; + h_pos += encaps_len; + } + + memcpy(skb_push(skb, hdrlen), &hdr, hdrlen); + + nh_pos += hdrlen; + h_pos += hdrlen; + + /* Update skb pointers to various headers since this modified frame + * is going to go through Linux networking code that may potentially + * need things like pointer to IP header. */ + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, nh_pos); + skb_set_transport_header(skb, h_pos); + + return 0; +} +EXPORT_SYMBOL(ieee80211_data_from_8023); + +/* Given a data frame determine the 802.1p/1d tag to use. */ +unsigned int cfg80211_classify8021d(struct sk_buff *skb) +{ + unsigned int dscp; + + /* skb->priority values from 256->263 are magic values to + * directly indicate a specific 802.1d priority. This is used + * to allow 802.1d priority to be passed directly in from VLAN + * tags, etc. + */ + if (skb->priority >= 256 && skb->priority <= 263) + return skb->priority - 256; + + switch (skb->protocol) { + case htons(ETH_P_IP): + dscp = ip_hdr(skb)->tos & 0xfc; + break; + default: + return 0; + } + + return dscp >> 5; +} +EXPORT_SYMBOL(cfg80211_classify8021d); diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 0fd1db6e95b..d030c531567 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -5,13 +5,14 @@ * into cfg80211, when that happens all the exports here go away and * we directly assign the wireless handlers of wireless interfaces. * - * Copyright 2008 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2008-2009 Johannes Berg <johannes@sipsolutions.net> */ #include <linux/wireless.h> #include <linux/nl80211.h> +#include <linux/if_arp.h> +#include <linux/etherdevice.h> #include <net/iw_handler.h> -#include <net/wireless.h> #include <net/cfg80211.h> #include "core.h" @@ -57,7 +58,7 @@ int cfg80211_wext_giwname(struct net_device *dev, return 0; } -EXPORT_SYMBOL(cfg80211_wext_giwname); +EXPORT_SYMBOL_GPL(cfg80211_wext_giwname); int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, u32 *mode, char *extra) @@ -108,7 +109,7 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, return ret; } -EXPORT_SYMBOL(cfg80211_wext_siwmode); +EXPORT_SYMBOL_GPL(cfg80211_wext_siwmode); int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, u32 *mode, char *extra) @@ -143,7 +144,7 @@ int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, } return 0; } -EXPORT_SYMBOL(cfg80211_wext_giwmode); +EXPORT_SYMBOL_GPL(cfg80211_wext_giwmode); int cfg80211_wext_giwrange(struct net_device *dev, @@ -206,7 +207,6 @@ int cfg80211_wext_giwrange(struct net_device *dev, range->enc_capa = IW_ENC_CAPA_WPA | IW_ENC_CAPA_WPA2 | IW_ENC_CAPA_CIPHER_TKIP | IW_ENC_CAPA_CIPHER_CCMP; - for (band = 0; band < IEEE80211_NUM_BANDS; band ++) { int i; struct ieee80211_supported_band *sband; @@ -240,4 +240,590 @@ int cfg80211_wext_giwrange(struct net_device *dev, return 0; } -EXPORT_SYMBOL(cfg80211_wext_giwrange); +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! + */ +struct ieee80211_channel *cfg80211_wext_freq(struct wiphy *wiphy, + struct iw_freq *freq) +{ + struct ieee80211_channel *chan; + int f; + + /* + * Parse frequency - return NULL for auto and + * -EINVAL for impossible things. + */ + if (freq->e == 0) { + if (freq->m < 0) + return NULL; + f = 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; + } + + /* + * 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, + struct iw_param *rts, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + u32 orts = wdev->wiphy->rts_threshold; + int err; + + if (rts->disabled || !rts->fixed) + wdev->wiphy->rts_threshold = (u32) -1; + else if (rts->value < 0) + return -EINVAL; + else + wdev->wiphy->rts_threshold = rts->value; + + err = rdev->ops->set_wiphy_params(wdev->wiphy, + WIPHY_PARAM_RTS_THRESHOLD); + if (err) + wdev->wiphy->rts_threshold = orts; + + return err; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwrts); + +int cfg80211_wext_giwrts(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *rts, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + rts->value = wdev->wiphy->rts_threshold; + rts->disabled = rts->value == (u32) -1; + rts->fixed = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwrts); + +int cfg80211_wext_siwfrag(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *frag, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + u32 ofrag = wdev->wiphy->frag_threshold; + int err; + + if (frag->disabled || !frag->fixed) + wdev->wiphy->frag_threshold = (u32) -1; + else if (frag->value < 256) + return -EINVAL; + else { + /* Fragment length must be even, so strip LSB. */ + wdev->wiphy->frag_threshold = frag->value & ~0x1; + } + + err = rdev->ops->set_wiphy_params(wdev->wiphy, + WIPHY_PARAM_FRAG_THRESHOLD); + if (err) + wdev->wiphy->frag_threshold = ofrag; + + return err; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwfrag); + +int cfg80211_wext_giwfrag(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *frag, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + frag->value = wdev->wiphy->frag_threshold; + frag->disabled = frag->value == (u32) -1; + frag->fixed = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwfrag); + +int cfg80211_wext_siwretry(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *retry, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + u32 changed = 0; + u8 olong = wdev->wiphy->retry_long; + u8 oshort = wdev->wiphy->retry_short; + int err; + + if (retry->disabled || + (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT) + return -EINVAL; + + if (retry->flags & IW_RETRY_LONG) { + wdev->wiphy->retry_long = retry->value; + changed |= WIPHY_PARAM_RETRY_LONG; + } else if (retry->flags & IW_RETRY_SHORT) { + wdev->wiphy->retry_short = retry->value; + changed |= WIPHY_PARAM_RETRY_SHORT; + } else { + wdev->wiphy->retry_short = retry->value; + wdev->wiphy->retry_long = retry->value; + changed |= WIPHY_PARAM_RETRY_LONG; + changed |= WIPHY_PARAM_RETRY_SHORT; + } + + if (!changed) + return 0; + + err = rdev->ops->set_wiphy_params(wdev->wiphy, changed); + if (err) { + wdev->wiphy->retry_short = oshort; + wdev->wiphy->retry_long = olong; + } + + return err; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwretry); + +int cfg80211_wext_giwretry(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *retry, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + retry->disabled = 0; + + if (retry->flags == 0 || (retry->flags & IW_RETRY_SHORT)) { + /* + * First return short value, iwconfig will ask long value + * later if needed + */ + retry->flags |= IW_RETRY_LIMIT; + retry->value = wdev->wiphy->retry_short; + if (wdev->wiphy->retry_long != wdev->wiphy->retry_short) + retry->flags |= IW_RETRY_LONG; + + return 0; + } + + if (retry->flags & IW_RETRY_LONG) { + retry->flags = IW_RETRY_LIMIT | IW_RETRY_LONG; + retry->value = wdev->wiphy->retry_long; + } + + return 0; +} +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) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC) { + if (!rdev->ops->set_default_mgmt_key) + return -EOPNOTSUPP; + + if (idx < 4 || idx > 5) + return -EINVAL; + } else if (idx < 0 || idx > 3) + return -EINVAL; + + if (remove) { + err = rdev->ops->del_key(&rdev->wiphy, dev, idx, addr); + if (!err) { + if (idx == wdev->wext.default_key) + wdev->wext.default_key = -1; + else if (idx == wdev->wext.default_mgmt_key) + wdev->wext.default_mgmt_key = -1; + } + /* + * Applications using wireless extensions expect to be + * able to delete keys that don't exist, so allow that. + */ + if (err == -ENOENT) + return 0; + + return err; + } else { + if (addr) + tx_key = false; + + if (cfg80211_validate_key_settings(params, idx, addr)) + return -EINVAL; + + err = rdev->ops->add_key(&rdev->wiphy, dev, idx, addr, params); + if (err) + return err; + + if (tx_key || (!addr && wdev->wext.default_key == -1)) { + err = rdev->ops->set_default_key(&rdev->wiphy, + dev, idx); + 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))) { + err = rdev->ops->set_default_mgmt_key(&rdev->wiphy, + dev, idx); + if (!err) + wdev->wext.default_mgmt_key = idx; + return err; + } + + return 0; + } +} + +int cfg80211_wext_siwencode(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; + bool remove = false; + struct key_params params; + + /* no use -- only MFP (set_default_mgmt_key) is optional */ + if (!rdev->ops->del_key || + !rdev->ops->add_key || + !rdev->ops->set_default_key) + return -EOPNOTSUPP; + + idx = erq->flags & IW_ENCODE_INDEX; + if (idx == 0) { + idx = wdev->wext.default_key; + if (idx < 0) + idx = 0; + } else if (idx < 1 || idx > 4) + return -EINVAL; + else + idx--; + + if (erq->flags & IW_ENCODE_DISABLED) + 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); + if (!err) + wdev->wext.default_key = idx; + return err; + } + + memset(¶ms, 0, sizeof(params)); + params.key = keybuf; + params.key_len = erq->length; + if (erq->length == 5) + params.cipher = WLAN_CIPHER_SUITE_WEP40; + else if (erq->length == 13) + params.cipher = WLAN_CIPHER_SUITE_WEP104; + else if (!remove) + return -EINVAL; + + return cfg80211_set_encryption(rdev, dev, NULL, remove, + wdev->wext.default_key == -1, + idx, ¶ms); +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwencode); + +int cfg80211_wext_siwencodeext(struct net_device *dev, + struct iw_request_info *info, + struct iw_point *erq, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct iw_encode_ext *ext = (struct iw_encode_ext *) extra; + const u8 *addr; + int idx; + bool remove = false; + struct key_params params; + u32 cipher; + + /* no use -- only MFP (set_default_mgmt_key) is optional */ + if (!rdev->ops->del_key || + !rdev->ops->add_key || + !rdev->ops->set_default_key) + return -EOPNOTSUPP; + + switch (ext->alg) { + case IW_ENCODE_ALG_NONE: + remove = true; + cipher = 0; + break; + case IW_ENCODE_ALG_WEP: + if (ext->key_len == 5) + cipher = WLAN_CIPHER_SUITE_WEP40; + else if (ext->key_len == 13) + cipher = WLAN_CIPHER_SUITE_WEP104; + else + return -EINVAL; + break; + case IW_ENCODE_ALG_TKIP: + cipher = WLAN_CIPHER_SUITE_TKIP; + break; + case IW_ENCODE_ALG_CCMP: + cipher = WLAN_CIPHER_SUITE_CCMP; + break; + case IW_ENCODE_ALG_AES_CMAC: + cipher = WLAN_CIPHER_SUITE_AES_CMAC; + break; + default: + return -EOPNOTSUPP; + } + + if (erq->flags & IW_ENCODE_DISABLED) + remove = true; + + idx = erq->flags & IW_ENCODE_INDEX; + if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) { + if (idx < 4 || idx > 5) { + idx = wdev->wext.default_mgmt_key; + if (idx < 0) + return -EINVAL; + } else + idx--; + } else { + if (idx < 1 || idx > 4) { + idx = wdev->wext.default_key; + if (idx < 0) + return -EINVAL; + } else + idx--; + } + + addr = ext->addr.sa_data; + if (is_broadcast_ether_addr(addr)) + addr = NULL; + + memset(¶ms, 0, sizeof(params)); + params.key = ext->key; + params.key_len = ext->key_len; + params.cipher = cipher; + + if (ext->ext_flags & IW_ENCODE_EXT_RX_SEQ_VALID) { + params.seq = ext->rx_seq; + params.seq_len = 6; + } + + return cfg80211_set_encryption( + rdev, dev, addr, remove, + ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, + idx, ¶ms); +} +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, + }; + + if (!rdev->ops->get_key) + return -EOPNOTSUPP; + + idx = erq->flags & IW_ENCODE_INDEX; + if (idx == 0) { + idx = wdev->wext.default_key; + if (idx < 0) + idx = 0; + } else if (idx < 1 || idx > 4) + return -EINVAL; + else + idx--; + + 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) { + erq->flags |= IW_ENCODE_DISABLED; + erq->length = 0; + return 0; + } + + return err; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwencode); + +int cfg80211_wext_siwtxpower(struct net_device *dev, + struct iw_request_info *info, + union iwreq_data *data, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + enum tx_power_setting type; + int dbm = 0; + + if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) + return -EINVAL; + if (data->txpower.flags & IW_TXPOW_RANGE) + return -EINVAL; + + if (!rdev->ops->set_tx_power) + return -EOPNOTSUPP; + + /* only change when not disabling */ + if (!data->txpower.disabled) { + rfkill_set_sw_state(rdev->rfkill, false); + + if (data->txpower.fixed) { + /* + * wext doesn't support negative values, see + * below where it's for automatic + */ + if (data->txpower.value < 0) + return -EINVAL; + dbm = data->txpower.value; + type = TX_POWER_FIXED; + /* TODO: do regulatory check! */ + } else { + /* + * Automatic power level setting, max being the value + * passed in from userland. + */ + if (data->txpower.value < 0) { + type = TX_POWER_AUTOMATIC; + } else { + dbm = data->txpower.value; + type = TX_POWER_LIMITED; + } + } + } else { + rfkill_set_sw_state(rdev->rfkill, true); + schedule_work(&rdev->rfkill_sync); + return 0; + } + + return rdev->ops->set_tx_power(wdev->wiphy, type, dbm);; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_siwtxpower); + +int cfg80211_wext_giwtxpower(struct net_device *dev, + struct iw_request_info *info, + union iwreq_data *data, char *extra) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + int err, val; + + if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) + return -EINVAL; + if (data->txpower.flags & IW_TXPOW_RANGE) + return -EINVAL; + + if (!rdev->ops->get_tx_power) + return -EOPNOTSUPP; + + err = rdev->ops->get_tx_power(wdev->wiphy, &val); + if (err) + return err; + + /* well... oh well */ + data->txpower.fixed = 1; + data->txpower.disabled = rfkill_blocked(rdev->rfkill); + data->txpower.value = val; + data->txpower.flags = IW_TXPOW_DBM; + + return 0; +} +EXPORT_SYMBOL_GPL(cfg80211_wext_giwtxpower); diff --git a/net/wireless/wext.c b/net/wireless/wext.c index 0e59f9ae9b8..252c2010c2e 100644 --- a/net/wireless/wext.c +++ b/net/wireless/wext.c @@ -636,8 +636,10 @@ static void wireless_seq_printf_stats(struct seq_file *seq, /* * Print info for /proc/net/wireless (print all entries) */ -static int wireless_seq_show(struct seq_file *seq, void *v) +static int wireless_dev_seq_show(struct seq_file *seq, void *v) { + might_sleep(); + if (v == SEQ_START_TOKEN) seq_printf(seq, "Inter-| sta-| Quality | Discarded " "packets | Missed | WE\n" @@ -649,14 +651,46 @@ static int wireless_seq_show(struct seq_file *seq, void *v) return 0; } +static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct net *net = seq_file_net(seq); + loff_t off; + struct net_device *dev; + + rtnl_lock(); + if (!*pos) + return SEQ_START_TOKEN; + + off = 1; + for_each_netdev(net, dev) + if (off++ == *pos) + return dev; + return NULL; +} + +static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct net *net = seq_file_net(seq); + + ++*pos; + + return v == SEQ_START_TOKEN ? + first_net_device(net) : next_net_device(v); +} + +static void wireless_dev_seq_stop(struct seq_file *seq, void *v) +{ + rtnl_unlock(); +} + static const struct seq_operations wireless_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = wireless_seq_show, + .start = wireless_dev_seq_start, + .next = wireless_dev_seq_next, + .stop = wireless_dev_seq_stop, + .show = wireless_dev_seq_show, }; -static int wireless_seq_open(struct inode *inode, struct file *file) +static int seq_open_wireless(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &wireless_seq_ops, sizeof(struct seq_net_private)); @@ -664,7 +698,7 @@ static int wireless_seq_open(struct inode *inode, struct file *file) static const struct file_operations wireless_seq_fops = { .owner = THIS_MODULE, - .open = wireless_seq_open, + .open = seq_open_wireless, .read = seq_read, .llseek = seq_lseek, .release = seq_release_net, diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index ed80af8ca5f..5e6c072c64d 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -40,6 +40,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/net.h> @@ -332,14 +333,14 @@ static unsigned int x25_new_lci(struct x25_neigh *nb) /* * Deferred destroy. */ -void x25_destroy_socket(struct sock *); +static void __x25_destroy_socket(struct sock *); /* * handler for deferred kills. */ static void x25_destroy_timer(unsigned long data) { - x25_destroy_socket((struct sock *)data); + x25_destroy_socket_from_timer((struct sock *)data); } /* @@ -349,12 +350,10 @@ static void x25_destroy_timer(unsigned long data) * will touch it and we are (fairly 8-) ) safe. * Not static as it's used by the timer */ -void x25_destroy_socket(struct sock *sk) +static void __x25_destroy_socket(struct sock *sk) { struct sk_buff *skb; - sock_hold(sk); - lock_sock(sk); x25_stop_heartbeat(sk); x25_stop_timer(sk); @@ -374,8 +373,7 @@ void x25_destroy_socket(struct sock *sk) kfree_skb(skb); } - if (atomic_read(&sk->sk_wmem_alloc) || - atomic_read(&sk->sk_rmem_alloc)) { + if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ sk->sk_timer.expires = jiffies + 10 * HZ; sk->sk_timer.function = x25_destroy_timer; @@ -385,7 +383,22 @@ void x25_destroy_socket(struct sock *sk) /* drop last reference so sock_put will free */ __sock_put(sk); } +} + +void x25_destroy_socket_from_timer(struct sock *sk) +{ + sock_hold(sk); + bh_lock_sock(sk); + __x25_destroy_socket(sk); + bh_unlock_sock(sk); + sock_put(sk); +} +static void x25_destroy_socket(struct sock *sk) +{ + sock_hold(sk); + lock_sock(sk); + __x25_destroy_socket(sk); release_sock(sk); sock_put(sk); } @@ -1259,8 +1272,8 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) switch (cmd) { case TIOCOUTQ: { - int amount = sk->sk_sndbuf - - atomic_read(&sk->sk_wmem_alloc); + int amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); + if (amount < 0) amount = 0; rc = put_user(amount, (unsigned int __user *)argp); diff --git a/net/x25/x25_proc.c b/net/x25/x25_proc.c index 1afa44d25be..0a04e62e0e1 100644 --- a/net/x25/x25_proc.c +++ b/net/x25/x25_proc.c @@ -163,8 +163,8 @@ static int x25_seq_socket_show(struct seq_file *seq, void *v) devname, x25->lci & 0x0FFF, x25->state, x25->vs, x25->vr, x25->va, x25_display_timer(s) / HZ, x25->t2 / HZ, x25->t21 / HZ, x25->t22 / HZ, x25->t23 / HZ, - atomic_read(&s->sk_wmem_alloc), - atomic_read(&s->sk_rmem_alloc), + sk_wmem_alloc_get(s), + sk_rmem_alloc_get(s), s->sk_socket ? SOCK_INODE(s->sk_socket)->i_ino : 0L); out: return 0; diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c index d3e3e54db93..5c5db1a3639 100644 --- a/net/x25/x25_timer.c +++ b/net/x25/x25_timer.c @@ -113,7 +113,7 @@ static void x25_heartbeat_expiry(unsigned long param) (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { bh_unlock_sock(sk); - x25_destroy_socket(sk); + x25_destroy_socket_from_timer(sk); return; } break; diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 96036cf2216..faf54c6bf96 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -292,8 +292,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, { - .name = "cbc(cast128)", - .compat = "cast128", + .name = "cbc(cast5)", + .compat = "cast5", .uinfo = { .encr = { @@ -696,8 +696,9 @@ int skb_icv_walk(const struct sk_buff *skb, struct hash_desc *desc, { int start = skb_headlen(skb); int i, copy = start - offset; - int err; + struct sk_buff *frag_iter; struct scatterlist sg; + int err; /* Checksum header. */ if (copy > 0) { @@ -742,28 +743,24 @@ int skb_icv_walk(const struct sk_buff *skb, struct hash_desc *desc, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - err = skb_icv_walk(list, desc, offset-start, - copy, icv_update); - if (unlikely(err)) - return err; - if ((len -= copy) == 0) - return 0; - offset += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + err = skb_icv_walk(frag_iter, desc, offset-start, + copy, icv_update); + if (unlikely(err)) + return err; + if ((len -= copy) == 0) + return 0; + offset += copy; } + start = end; } BUG_ON(len); return 0; diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h index d401dc8f05e..e5195c99f71 100644 --- a/net/xfrm/xfrm_hash.h +++ b/net/xfrm/xfrm_hash.h @@ -16,7 +16,7 @@ static inline unsigned int __xfrm6_addr_hash(xfrm_address_t *addr) static inline unsigned int __xfrm4_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) { - return ntohl(daddr->a4 ^ saddr->a4); + return ntohl(daddr->a4 + saddr->a4); } static inline unsigned int __xfrm6_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index b4a13178fb4..e0009c17d80 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -251,8 +251,7 @@ resume: nf_reset(skb); if (decaps) { - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); netif_rx(skb); return 0; } else { diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index c235597ba8d..b9fe13138c0 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -22,7 +22,7 @@ static int xfrm_output2(struct sk_buff *skb); static int xfrm_state_check_space(struct xfrm_state *x, struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); int nhead = dst->header_len + LL_RESERVED_SPACE(dst->dev) - skb_headroom(skb); int ntail = dst->dev->needed_tailroom - skb_tailroom(skb); @@ -39,7 +39,7 @@ static int xfrm_state_check_space(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_output_one(struct sk_buff *skb, int err) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; struct net *net = xs_net(x); @@ -94,12 +94,13 @@ resume: goto error_nolock; } - if (!(skb->dst = dst_pop(dst))) { + dst = dst_pop(dst); + if (!dst) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); err = -EHOSTUNREACH; goto error_nolock; } - dst = skb->dst; + skb_dst_set(skb, dst); x = dst->xfrm; } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); @@ -119,16 +120,16 @@ int xfrm_output_resume(struct sk_buff *skb, int err) while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset(skb); - err = skb->dst->ops->local_out(skb); + err = skb_dst(skb)->ops->local_out(skb); if (unlikely(err != 1)) goto out; - if (!skb->dst->xfrm) + if (!skb_dst(skb)->xfrm) return dst_output(skb); - err = nf_hook(skb->dst->ops->family, + err = nf_hook(skb_dst(skb)->ops->family, NF_INET_POST_ROUTING, skb, - NULL, skb->dst->dev, xfrm_output2); + NULL, skb_dst(skb)->dev, xfrm_output2); if (unlikely(err != 1)) goto out; } @@ -179,7 +180,7 @@ static int xfrm_output_gso(struct sk_buff *skb) int xfrm_output(struct sk_buff *skb) { - struct net *net = dev_net(skb->dst->dev); + struct net *net = dev_net(skb_dst(skb)->dev); int err; if (skb_is_gso(skb)) @@ -202,7 +203,7 @@ int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_mode *inner_mode; if (x->sel.family == AF_UNSPEC) inner_mode = xfrm_ip2inner_mode(x, - xfrm_af2proto(skb->dst->ops->family)); + xfrm_af2proto(skb_dst(skb)->ops->family)); else inner_mode = x->inner_mode; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9c068ab3a83..cb81ca35b0d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2027,6 +2027,8 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct flowi fl; + struct dst_entry *dst; + int res; if (xfrm_decode_session(skb, &fl, family) < 0) { /* XXX: we should have something like FWDHDRERROR here. */ @@ -2034,7 +2036,11 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) return 0; } - return xfrm_lookup(net, &skb->dst, &fl, NULL, 0) == 0; + dst = skb_dst(skb); + + res = xfrm_lookup(net, &dst, &fl, NULL, 0) == 0; + skb_dst_set(skb, dst); + return res; } EXPORT_SYMBOL(__xfrm_route_forward); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5f1f86565f1..f2f7c638083 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -668,22 +668,10 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, xfrm_address_t *d hlist_for_each_entry(x, entry, net->xfrm.state_byspi+h, byspi) { if (x->props.family != family || x->id.spi != spi || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)daddr, - (struct in6_addr *) - x->id.daddr.a6)) - continue; - break; - } - xfrm_state_hold(x); return x; } @@ -699,26 +687,11 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, xfrm_addre hlist_for_each_entry(x, entry, net->xfrm.state_bysrc+h, bysrc) { if (x->props.family != family || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family) || + xfrm_addr_cmp(&x->props.saddr, saddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4 || - x->props.saddr.a4 != saddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)daddr, - (struct in6_addr *) - x->id.daddr.a6) || - !ipv6_addr_equal((struct in6_addr *)saddr, - (struct in6_addr *) - x->props.saddr.a6)) - continue; - break; - } - xfrm_state_hold(x); return x; } @@ -1001,25 +974,11 @@ static struct xfrm_state *__find_acq_core(struct net *net, unsigned short family x->props.family != family || x->km.state != XFRM_STATE_ACQ || x->id.spi != 0 || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family) || + xfrm_addr_cmp(&x->props.saddr, saddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4 || - x->props.saddr.a4 != saddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)x->id.daddr.a6, - (struct in6_addr *)daddr) || - !ipv6_addr_equal((struct in6_addr *) - x->props.saddr.a6, - (struct in6_addr *)saddr)) - continue; - break; - } - xfrm_state_hold(x); return x; } |