diff options
Diffstat (limited to 'net')
290 files changed, 6325 insertions, 5805 deletions
diff --git a/net/802/fc.c b/net/802/fc.c index 34cf1ee..1e49f2d 100644 --- a/net/802/fc.c +++ b/net/802/fc.c @@ -70,7 +70,7 @@ static int fc_header(struct sk_buff *skb, struct net_device *dev, if(daddr) { memcpy(fch->daddr,daddr,dev->addr_len); - return(hdr_len); + return hdr_len; } return -hdr_len; } diff --git a/net/802/fddi.c b/net/802/fddi.c index 3ef0ab0..94b3ad0 100644 --- a/net/802/fddi.c +++ b/net/802/fddi.c @@ -82,10 +82,10 @@ static int fddi_header(struct sk_buff *skb, struct net_device *dev, if (daddr != NULL) { memcpy(fddi->daddr, daddr, dev->addr_len); - return(hl); + return hl; } - return(-hl); + return -hl; } @@ -108,7 +108,7 @@ static int fddi_rebuild_header(struct sk_buff *skb) { printk("%s: Don't know how to resolve type %04X addresses.\n", skb->dev->name, ntohs(fddi->hdr.llc_snap.ethertype)); - return(0); + return 0; } } @@ -162,7 +162,7 @@ __be16 fddi_type_trans(struct sk_buff *skb, struct net_device *dev) /* Assume 802.2 SNAP frames, for now */ - return(type); + return type; } EXPORT_SYMBOL(fddi_type_trans); @@ -170,9 +170,9 @@ EXPORT_SYMBOL(fddi_type_trans); int fddi_change_mtu(struct net_device *dev, int new_mtu) { if ((new_mtu < FDDI_K_SNAP_HLEN) || (new_mtu > FDDI_K_SNAP_DLEN)) - return(-EINVAL); + return -EINVAL; dev->mtu = new_mtu; - return(0); + return 0; } EXPORT_SYMBOL(fddi_change_mtu); diff --git a/net/802/hippi.c b/net/802/hippi.c index cd3e8e9..91aca87 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -152,7 +152,7 @@ int hippi_change_mtu(struct net_device *dev, int new_mtu) if ((new_mtu < 68) || (new_mtu > 65280)) return -EINVAL; dev->mtu = new_mtu; - return(0); + return 0; } EXPORT_SYMBOL(hippi_change_mtu); diff --git a/net/802/tr.c b/net/802/tr.c index 1c6e596..5e20cf8 100644 --- a/net/802/tr.c +++ b/net/802/tr.c @@ -145,7 +145,7 @@ static int tr_header(struct sk_buff *skb, struct net_device *dev, { memcpy(trh->daddr,daddr,dev->addr_len); tr_source_route(skb, trh, dev); - return(hdr_len); + return hdr_len; } return -hdr_len; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a2ad152..05b867e 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -44,9 +44,6 @@ int vlan_net_id __read_mostly; -/* Our listing of VLAN group(s) */ -static struct hlist_head vlan_group_hash[VLAN_GRP_HASH_SIZE]; - const char vlan_fullname[] = "802.1Q VLAN Support"; const char vlan_version[] = DRV_VERSION; static const char vlan_copyright[] = "Ben Greear <greearb@candelatech.com>"; @@ -59,40 +56,6 @@ static struct packet_type vlan_packet_type __read_mostly = { /* End of global variables definitions. */ -static inline unsigned int vlan_grp_hashfn(unsigned int idx) -{ - return ((idx >> VLAN_GRP_HASH_SHIFT) ^ idx) & VLAN_GRP_HASH_MASK; -} - -/* Must be invoked with RCU read lock (no preempt) */ -static struct vlan_group *__vlan_find_group(struct net_device *real_dev) -{ - struct vlan_group *grp; - struct hlist_node *n; - int hash = vlan_grp_hashfn(real_dev->ifindex); - - hlist_for_each_entry_rcu(grp, n, &vlan_group_hash[hash], hlist) { - if (grp->real_dev == real_dev) - return grp; - } - - return NULL; -} - -/* Find the protocol handler. Assumes VID < VLAN_VID_MASK. - * - * Must be invoked with RCU read lock (no preempt) - */ -struct net_device *__find_vlan_dev(struct net_device *real_dev, u16 vlan_id) -{ - struct vlan_group *grp = __vlan_find_group(real_dev); - - if (grp) - return vlan_group_get_device(grp, vlan_id); - - return NULL; -} - static void vlan_group_free(struct vlan_group *grp) { int i; @@ -111,8 +74,6 @@ static struct vlan_group *vlan_group_alloc(struct net_device *real_dev) return NULL; grp->real_dev = real_dev; - hlist_add_head_rcu(&grp->hlist, - &vlan_group_hash[vlan_grp_hashfn(real_dev->ifindex)]); return grp; } @@ -151,7 +112,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) ASSERT_RTNL(); - grp = __vlan_find_group(real_dev); + grp = real_dev->vlgrp; BUG_ON(!grp); /* Take it out of our own structures, but be sure to interlock with @@ -173,11 +134,10 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) if (grp->nr_vlans == 0) { vlan_gvrp_uninit_applicant(real_dev); - if (real_dev->features & NETIF_F_HW_VLAN_RX) + rcu_assign_pointer(real_dev->vlgrp, NULL); + if (ops->ndo_vlan_rx_register) ops->ndo_vlan_rx_register(real_dev, NULL); - hlist_del_rcu(&grp->hlist); - /* Free the group, after all cpu's are done. */ call_rcu(&grp->rcu, vlan_rcu_free); } @@ -196,18 +156,13 @@ int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id) return -EOPNOTSUPP; } - if ((real_dev->features & NETIF_F_HW_VLAN_RX) && !ops->ndo_vlan_rx_register) { - pr_info("8021q: device %s has buggy VLAN hw accel\n", name); - return -EOPNOTSUPP; - } - if ((real_dev->features & NETIF_F_HW_VLAN_FILTER) && (!ops->ndo_vlan_rx_add_vid || !ops->ndo_vlan_rx_kill_vid)) { pr_info("8021q: Device %s has buggy VLAN hw accel\n", name); return -EOPNOTSUPP; } - if (__find_vlan_dev(real_dev, vlan_id) != NULL) + if (vlan_find_dev(real_dev, vlan_id) != NULL) return -EEXIST; return 0; @@ -222,7 +177,7 @@ int register_vlan_dev(struct net_device *dev) struct vlan_group *grp, *ngrp = NULL; int err; - grp = __vlan_find_group(real_dev); + grp = real_dev->vlgrp; if (!grp) { ngrp = grp = vlan_group_alloc(real_dev); if (!grp) @@ -252,8 +207,11 @@ int register_vlan_dev(struct net_device *dev) vlan_group_set_device(grp, vlan_id, dev); grp->nr_vlans++; - if (ngrp && real_dev->features & NETIF_F_HW_VLAN_RX) - ops->ndo_vlan_rx_register(real_dev, ngrp); + if (ngrp) { + if (ops->ndo_vlan_rx_register) + ops->ndo_vlan_rx_register(real_dev, ngrp); + rcu_assign_pointer(real_dev->vlgrp, ngrp); + } if (real_dev->features & NETIF_F_HW_VLAN_FILTER) ops->ndo_vlan_rx_add_vid(real_dev, vlan_id); @@ -264,7 +222,6 @@ out_uninit_applicant: vlan_gvrp_uninit_applicant(real_dev); out_free_group: if (ngrp) { - hlist_del_rcu(&ngrp->hlist); /* Free the group, after all cpu's are done. */ call_rcu(&ngrp->rcu, vlan_rcu_free); } @@ -321,7 +278,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) if (new_dev == NULL) return -ENOBUFS; - new_dev->real_num_tx_queues = real_dev->real_num_tx_queues; + netif_copy_real_num_queues(new_dev, real_dev); dev_net_set(new_dev, net); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. @@ -428,7 +385,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, dev->netdev_ops->ndo_vlan_rx_add_vid(dev, 0); } - grp = __vlan_find_group(dev); + grp = dev->vlgrp; if (!grp) goto out; @@ -439,7 +396,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, switch (event) { case NETDEV_CHANGE: /* Propagate real device state to vlan devices */ - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) continue; @@ -450,7 +407,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_CHANGEADDR: /* Adjust unicast filters on underlying device */ - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) continue; @@ -464,7 +421,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, break; case NETDEV_CHANGEMTU: - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) continue; @@ -478,7 +435,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_FEAT_CHANGE: /* Propagate device features to underlying device */ - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) continue; @@ -490,7 +447,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_DOWN: /* Put all VLANs for this dev in the down state too. */ - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) continue; @@ -508,7 +465,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) continue; @@ -525,10 +482,14 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, break; case NETDEV_UNREGISTER: + /* twiddle thumbs on netns device moves */ + if (dev->reg_state != NETREG_UNREGISTERING) + break; + /* Delete all VLANs for this dev. */ grp->killall = 1; - for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) continue; @@ -536,7 +497,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, /* unregistration of last vlan destroys group, abort * afterwards */ if (grp->nr_vlans == 1) - i = VLAN_GROUP_ARRAY_LEN; + i = VLAN_N_VID; unregister_vlan_dev(vlandev, &list); } @@ -742,8 +703,6 @@ err0: static void __exit vlan_cleanup_module(void) { - unsigned int i; - vlan_ioctl_set(NULL); vlan_netlink_fini(); @@ -751,10 +710,6 @@ static void __exit vlan_cleanup_module(void) dev_remove_pack(&vlan_packet_type); - /* This table must be empty if there are no module references left. */ - for (i = 0; i < VLAN_GRP_HASH_SIZE; i++) - BUG_ON(!hlist_empty(&vlan_group_hash[i])); - unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 8d9503a..db01b31 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -72,23 +72,6 @@ static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev) return netdev_priv(dev); } -#define VLAN_GRP_HASH_SHIFT 5 -#define VLAN_GRP_HASH_SIZE (1 << VLAN_GRP_HASH_SHIFT) -#define VLAN_GRP_HASH_MASK (VLAN_GRP_HASH_SIZE - 1) - -/* Find a VLAN device by the MAC address of its Ethernet device, and - * it's VLAN ID. The default configuration is to have VLAN's scope - * to be box-wide, so the MAC will be ignored. The mac will only be - * looked at if we are configured to have a separate set of VLANs per - * each MAC addressable interface. Note that this latter option does - * NOT follow the spec for VLANs, but may be useful for doing very - * large quantities of VLAN MUX/DEMUX onto FrameRelay or ATM PVCs. - * - * Must be invoked with rcu_read_lock (ie preempt disabled) - * or with RTNL. - */ -struct net_device *__find_vlan_dev(struct net_device *real_dev, u16 vlan_id); - /* found in vlan_dev.c */ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 889f4ac..69b2f79 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -4,50 +4,29 @@ #include <linux/netpoll.h> #include "vlan.h" -/* VLAN rx hw acceleration helper. This acts like netif_{rx,receive_skb}(). */ -int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, - u16 vlan_tci, int polling) +bool vlan_hwaccel_do_receive(struct sk_buff **skbp) { + struct sk_buff *skb = *skbp; + u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK; struct net_device *vlan_dev; - u16 vlan_id; - - if (netpoll_rx(skb)) - return NET_RX_DROP; - - if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master))) - skb->deliver_no_wcard = 1; - - skb->skb_iif = skb->dev->ifindex; - __vlan_hwaccel_put_tag(skb, vlan_tci); - vlan_id = vlan_tci & VLAN_VID_MASK; - vlan_dev = vlan_group_get_device(grp, vlan_id); - - if (vlan_dev) - skb->dev = vlan_dev; - else if (vlan_id) - goto drop; - - return (polling ? netif_receive_skb(skb) : netif_rx(skb)); + struct vlan_rx_stats *rx_stats; -drop: - dev_kfree_skb_any(skb); - return NET_RX_DROP; -} -EXPORT_SYMBOL(__vlan_hwaccel_rx); - -void vlan_hwaccel_do_receive(struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - struct vlan_rx_stats *rx_stats; + vlan_dev = vlan_find_dev(skb->dev, vlan_id); + if (!vlan_dev) { + if (vlan_id) + skb->pkt_type = PACKET_OTHERHOST; + return false; + } - skb->dev = vlan_dev_real_dev(dev); - netif_nit_deliver(skb); + skb = *skbp = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + return false; - skb->dev = dev; - skb->priority = vlan_get_ingress_priority(dev, skb->vlan_tci); + skb->dev = vlan_dev; + skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci); skb->vlan_tci = 0; - rx_stats = this_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats); + rx_stats = this_cpu_ptr(vlan_dev_info(vlan_dev)->vlan_rx_stats); u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; @@ -64,11 +43,13 @@ void vlan_hwaccel_do_receive(struct sk_buff *skb) * This allows the VLAN to have a different MAC than the * underlying device, and still route correctly. */ if (!compare_ether_addr(eth_hdr(skb)->h_dest, - dev->dev_addr)) + vlan_dev->dev_addr)) skb->pkt_type = PACKET_HOST; break; } u64_stats_update_end(&rx_stats->syncp); + + return true; } struct net_device *vlan_dev_real_dev(const struct net_device *dev) @@ -83,71 +64,27 @@ u16 vlan_dev_vlan_id(const struct net_device *dev) } EXPORT_SYMBOL(vlan_dev_vlan_id); -static gro_result_t -vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct sk_buff *skb) +/* VLAN rx hw acceleration helper. This acts like netif_{rx,receive_skb}(). */ +int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, + u16 vlan_tci, int polling) { - struct sk_buff *p; - struct net_device *vlan_dev; - u16 vlan_id; - - if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master))) - skb->deliver_no_wcard = 1; - - skb->skb_iif = skb->dev->ifindex; __vlan_hwaccel_put_tag(skb, vlan_tci); - vlan_id = vlan_tci & VLAN_VID_MASK; - vlan_dev = vlan_group_get_device(grp, vlan_id); - - if (vlan_dev) - skb->dev = vlan_dev; - else if (vlan_id) - goto drop; - - for (p = napi->gro_list; p; p = p->next) { - unsigned long diffs; - - diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); - NAPI_GRO_CB(p)->same_flow = !diffs; - NAPI_GRO_CB(p)->flush = 0; - } - - return dev_gro_receive(napi, skb); - -drop: - return GRO_DROP; + return polling ? netif_receive_skb(skb) : netif_rx(skb); } +EXPORT_SYMBOL(__vlan_hwaccel_rx); gro_result_t vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, unsigned int vlan_tci, struct sk_buff *skb) { - if (netpoll_rx_on(skb)) - return vlan_hwaccel_receive_skb(skb, grp, vlan_tci) - ? GRO_DROP : GRO_NORMAL; - - skb_gro_reset_offset(skb); - - return napi_skb_finish(vlan_gro_common(napi, grp, vlan_tci, skb), skb); + __vlan_hwaccel_put_tag(skb, vlan_tci); + return napi_gro_receive(napi, skb); } EXPORT_SYMBOL(vlan_gro_receive); gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, unsigned int vlan_tci) { - struct sk_buff *skb = napi_frags_skb(napi); - - if (!skb) - return GRO_DROP; - - if (netpoll_rx_on(skb)) { - skb->protocol = eth_type_trans(skb, skb->dev); - return vlan_hwaccel_receive_skb(skb, grp, vlan_tci) - ? GRO_DROP : GRO_NORMAL; - } - - return napi_frags_finish(napi, skb, - vlan_gro_common(napi, grp, vlan_tci, skb)); + __vlan_hwaccel_put_tag(napi->skb, vlan_tci); + return napi_gro_frags(napi); } EXPORT_SYMBOL(vlan_gro_frags); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 3bccdd1..14e3d1f 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -158,7 +158,7 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, vlan_id = vlan_tci & VLAN_VID_MASK; rcu_read_lock(); - vlan_dev = __find_vlan_dev(dev, vlan_id); + vlan_dev = vlan_find_dev(dev, vlan_id); /* If the VLAN device is defined, we use it. * If not, and the VID is 0, it is a 802.1p packet (not @@ -177,8 +177,8 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, } else { skb->dev = vlan_dev; - rx_stats = per_cpu_ptr(vlan_dev_info(skb->dev)->vlan_rx_stats, - smp_processor_id()); + rx_stats = this_cpu_ptr(vlan_dev_info(skb->dev)->vlan_rx_stats); + u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; rx_stats->rx_bytes += skb->len; @@ -226,12 +226,14 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, } netif_rx(skb); + rcu_read_unlock(); return NET_RX_SUCCESS; err_unlock: rcu_read_unlock(); err_free: + atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } @@ -843,7 +845,7 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st accum.rx_packets += rxpackets; accum.rx_bytes += rxbytes; accum.rx_multicast += rxmulticast; - /* rx_errors is an ulong, not protected by syncp */ + /* rx_errors is ulong, not protected by syncp */ accum.rx_errors += p->rx_errors; } stats->rx_packets = accum.rx_packets; diff --git a/net/9p/client.c b/net/9p/client.c index dc6f2f2..83bf054 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -61,13 +61,13 @@ static const match_table_t tokens = { inline int p9_is_proto_dotl(struct p9_client *clnt) { - return (clnt->proto_version == p9_proto_2000L); + return clnt->proto_version == p9_proto_2000L; } EXPORT_SYMBOL(p9_is_proto_dotl); inline int p9_is_proto_dotu(struct p9_client *clnt) { - return (clnt->proto_version == p9_proto_2000u); + return clnt->proto_version == p9_proto_2000u; } EXPORT_SYMBOL(p9_is_proto_dotu); @@ -331,8 +331,10 @@ static void p9_tag_cleanup(struct p9_client *c) } } - if (c->tagpool) + if (c->tagpool) { + p9_idpool_put(0, c->tagpool); /* free reserved tag 0 */ p9_idpool_destroy(c->tagpool); + } /* free requests associated with tags */ for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) { @@ -669,7 +671,7 @@ static void p9_fid_destroy(struct p9_fid *fid) kfree(fid); } -int p9_client_version(struct p9_client *c) +static int p9_client_version(struct p9_client *c) { int err = 0; struct p9_req_t *req; @@ -728,7 +730,6 @@ error: return err; } -EXPORT_SYMBOL(p9_client_version); struct p9_client *p9_client_create(const char *dev_name, char *options) { @@ -885,54 +886,6 @@ error: } EXPORT_SYMBOL(p9_client_attach); -struct p9_fid * -p9_client_auth(struct p9_client *clnt, char *uname, u32 n_uname, char *aname) -{ - int err; - struct p9_req_t *req; - struct p9_qid qid; - struct p9_fid *afid; - - P9_DPRINTK(P9_DEBUG_9P, ">>> TAUTH uname %s aname %s\n", uname, aname); - err = 0; - - afid = p9_fid_create(clnt); - if (IS_ERR(afid)) { - err = PTR_ERR(afid); - afid = NULL; - goto error; - } - - req = p9_client_rpc(clnt, P9_TAUTH, "dss?d", - afid ? afid->fid : P9_NOFID, uname, aname, n_uname); - if (IS_ERR(req)) { - err = PTR_ERR(req); - goto error; - } - - err = p9pdu_readf(req->rc, clnt->proto_version, "Q", &qid); - if (err) { - p9pdu_dump(1, req->rc); - p9_free_req(clnt, req); - goto error; - } - - P9_DPRINTK(P9_DEBUG_9P, "<<< RAUTH qid %x.%llx.%x\n", - qid.type, - (unsigned long long)qid.path, - qid.version); - - memmove(&afid->qid, &qid, sizeof(struct p9_qid)); - p9_free_req(clnt, req); - return afid; - -error: - if (afid) - p9_fid_destroy(afid); - return ERR_PTR(err); -} -EXPORT_SYMBOL(p9_client_auth); - struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, int clone) { @@ -944,6 +897,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, int16_t nwqids, count; err = 0; + wqids = NULL; clnt = oldfid->clnt; if (clone) { fid = p9_fid_create(clnt); @@ -994,9 +948,11 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, else fid->qid = oldfid->qid; + kfree(wqids); return fid; clunk_fid: + kfree(wqids); p9_client_clunk(fid); fid = NULL; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 0ea20c3..17c5ba7 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -426,8 +426,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) /* Allocate an fcall for the reply */ rpl_context = kmalloc(sizeof *rpl_context, GFP_KERNEL); - if (!rpl_context) + if (!rpl_context) { + err = -ENOMEM; goto err_close; + } /* * If the request has a buffer, steal it, otherwise @@ -445,8 +447,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) } rpl_context->rc = req->rc; if (!rpl_context->rc) { - kfree(rpl_context); - goto err_close; + err = -ENOMEM; + goto err_free2; } /* @@ -458,11 +460,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) */ if (atomic_inc_return(&rdma->rq_count) <= rdma->rq_depth) { err = post_recv(client, rpl_context); - if (err) { - kfree(rpl_context->rc); - kfree(rpl_context); - goto err_close; - } + if (err) + goto err_free1; } else atomic_dec(&rdma->rq_count); @@ -471,8 +470,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) /* Post the request */ c = kmalloc(sizeof *c, GFP_KERNEL); - if (!c) - goto err_close; + if (!c) { + err = -ENOMEM; + goto err_free1; + } c->req = req; c->busa = ib_dma_map_single(rdma->cm_id->device, @@ -499,9 +500,15 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) return ib_post_send(rdma->qp, &wr, &bad_wr); error: + kfree(c); + kfree(rpl_context->rc); + kfree(rpl_context); P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n"); return -EIO; - + err_free1: + kfree(rpl_context->rc); + err_free2: + kfree(rpl_context); err_close: spin_lock_irqsave(&rdma->req_lock, flags); if (rdma->state < P9_RDMA_CLOSING) { diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index dcfbe99..b885159 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -329,7 +329,8 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args) mutex_lock(&virtio_9p_lock); list_for_each_entry(chan, &virtio_chan_list, chan_list) { - if (!strncmp(devname, chan->tag, chan->tag_len)) { + if (!strncmp(devname, chan->tag, chan->tag_len) && + strlen(devname) == chan->tag_len) { if (!chan->inuse) { chan->inuse = true; found = 1; diff --git a/net/Kconfig b/net/Kconfig index e330594..e926884 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -217,7 +217,7 @@ source "net/dns_resolver/Kconfig" config RPS boolean - depends on SMP && SYSFS + depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y menu "Network testing" diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 651babd..ad2b232 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -399,12 +399,6 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) unregister_netdev(net_dev); free_netdev(net_dev); } - read_lock_irq(&devs_lock); - if (list_empty(&br2684_devs)) { - /* last br2684 device */ - unregister_atmdevice_notifier(&atm_dev_notifier); - } - read_unlock_irq(&devs_lock); return; } @@ -675,7 +669,6 @@ static int br2684_create(void __user *arg) if (list_empty(&br2684_devs)) { /* 1st br2684 device */ - register_atmdevice_notifier(&atm_dev_notifier); brdev->number = 1; } else brdev->number = BRPRIV(list_entry_brdev(br2684_devs.prev))->number + 1; @@ -815,6 +808,7 @@ static int __init br2684_init(void) return -ENOMEM; #endif register_atm_ioctl(&br2684_ioctl_ops); + register_atmdevice_notifier(&atm_dev_notifier); return 0; } @@ -830,9 +824,7 @@ static void __exit br2684_exit(void) #endif - /* if not already empty */ - if (!list_empty(&br2684_devs)) - unregister_atmdevice_notifier(&atm_dev_notifier); + unregister_atmdevice_notifier(&atm_dev_notifier); while (!list_empty(&br2684_devs)) { net_dev = list_entry_brdev(br2684_devs.next); diff --git a/net/atm/clip.c b/net/atm/clip.c index 95fdd11..ff956d1 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -310,9 +310,9 @@ static int clip_constructor(struct neighbour *neigh) return 0; } -static u32 clip_hash(const void *pkey, const struct net_device *dev) +static u32 clip_hash(const void *pkey, const struct net_device *dev, __u32 rnd) { - return jhash_2words(*(u32 *) pkey, dev->ifindex, clip_tbl.hash_rnd); + return jhash_2words(*(u32 *) pkey, dev->ifindex, rnd); } static struct neigh_table clip_tbl = { diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 622b471..74bcc66 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -778,7 +778,7 @@ static void mpc_push(struct atm_vcc *vcc, struct sk_buff *skb) eg->packets_rcvd++; mpc->eg_ops->put(eg); - memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); + memset(ATM_SKB(new_skb), 0, sizeof(struct atm_skb_data)); netif_rx(new_skb); } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ed0f22f..c4cf3f5 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -265,6 +265,115 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, } EXPORT_SYMBOL(bt_sock_recvmsg); +static long bt_sock_data_wait(struct sock *sk, long timeo) +{ + DECLARE_WAITQUEUE(wait, current); + + add_wait_queue(sk_sleep(sk), &wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + if (!skb_queue_empty(&sk->sk_receive_queue)) + break; + + if (sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN)) + break; + + if (signal_pending(current) || !timeo) + break; + + set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + release_sock(sk); + timeo = schedule_timeout(timeo); + lock_sock(sk); + clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); + } + + __set_current_state(TASK_RUNNING); + remove_wait_queue(sk_sleep(sk), &wait); + return timeo; +} + +int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size, int flags) +{ + struct sock *sk = sock->sk; + int err = 0; + size_t target, copied = 0; + long timeo; + + if (flags & MSG_OOB) + return -EOPNOTSUPP; + + msg->msg_namelen = 0; + + BT_DBG("sk %p size %zu", sk, size); + + lock_sock(sk); + + target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + + do { + struct sk_buff *skb; + int chunk; + + skb = skb_dequeue(&sk->sk_receive_queue); + if (!skb) { + if (copied >= target) + break; + + if ((err = sock_error(sk)) != 0) + break; + if (sk->sk_shutdown & RCV_SHUTDOWN) + break; + + err = -EAGAIN; + if (!timeo) + break; + + timeo = bt_sock_data_wait(sk, timeo); + + if (signal_pending(current)) { + err = sock_intr_errno(timeo); + goto out; + } + continue; + } + + chunk = min_t(unsigned int, skb->len, size); + if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { + skb_queue_head(&sk->sk_receive_queue, skb); + if (!copied) + copied = -EFAULT; + break; + } + copied += chunk; + size -= chunk; + + sock_recv_ts_and_drops(msg, sk, skb); + + if (!(flags & MSG_PEEK)) { + skb_pull(skb, chunk); + if (skb->len) { + skb_queue_head(&sk->sk_receive_queue, skb); + break; + } + kfree_skb(skb); + + } else { + /* put message back and return */ + skb_queue_head(&sk->sk_receive_queue, skb); + break; + } + } while (size); + +out: + release_sock(sk); + return copied ? : err; +} +EXPORT_SYMBOL(bt_sock_stream_recvmsg); + static inline unsigned int bt_accept_poll(struct sock *parent) { struct list_head *p, *n; diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index d4c6af0..ec0a134 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -321,14 +321,10 @@ static int cmtp_session(void *arg) int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) { struct cmtp_session *session, *s; - bdaddr_t src, dst; int i, err; BT_DBG(""); - baswap(&src, &bt_sk(sock->sk)->src); - baswap(&dst, &bt_sk(sock->sk)->dst); - session = kzalloc(sizeof(struct cmtp_session), GFP_KERNEL); if (!session) return -ENOMEM; @@ -347,7 +343,7 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) BT_DBG("mtu %d", session->mtu); - sprintf(session->name, "%s", batostr(&dst)); + sprintf(session->name, "%s", batostr(&bt_sk(sock->sk)->dst)); session->sock = sock; session->state = BT_CONFIG; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index c52f091..bc2a052 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -562,7 +562,6 @@ static int hci_dev_do_close(struct hci_dev *hdev) hci_dev_lock_bh(hdev); inquiry_cache_flush(hdev); hci_conn_hash_flush(hdev); - hci_blacklist_clear(hdev); hci_dev_unlock_bh(hdev); hci_notify(hdev, HCI_DEV_DOWN); diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 8fb967b..5fce3d6 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -37,9 +37,7 @@ static ssize_t show_link_type(struct device *dev, struct device_attribute *attr, static ssize_t show_link_address(struct device *dev, struct device_attribute *attr, char *buf) { struct hci_conn *conn = dev_get_drvdata(dev); - bdaddr_t bdaddr; - baswap(&bdaddr, &conn->dst); - return sprintf(buf, "%s\n", batostr(&bdaddr)); + return sprintf(buf, "%s\n", batostr(&conn->dst)); } static ssize_t show_link_features(struct device *dev, struct device_attribute *attr, char *buf) @@ -196,8 +194,8 @@ static inline char *host_typetostr(int type) switch (type) { case HCI_BREDR: return "BR/EDR"; - case HCI_80211: - return "802.11"; + case HCI_AMP: + return "AMP"; default: return "UNKNOWN"; } @@ -238,9 +236,7 @@ static ssize_t show_class(struct device *dev, struct device_attribute *attr, cha static ssize_t show_address(struct device *dev, struct device_attribute *attr, char *buf) { struct hci_dev *hdev = dev_get_drvdata(dev); - bdaddr_t bdaddr; - baswap(&bdaddr, &hdev->bdaddr); - return sprintf(buf, "%s\n", batostr(&bdaddr)); + return sprintf(buf, "%s\n", batostr(&hdev->bdaddr)); } static ssize_t show_features(struct device *dev, struct device_attribute *attr, char *buf) @@ -408,10 +404,8 @@ static int inquiry_cache_show(struct seq_file *f, void *p) for (e = cache->list; e; e = e->next) { struct inquiry_data *data = &e->data; - bdaddr_t bdaddr; - baswap(&bdaddr, &data->bdaddr); seq_printf(f, "%s %d %d %d 0x%.2x%.2x%.2x 0x%.4x %d %d %u\n", - batostr(&bdaddr), + batostr(&data->bdaddr), data->pscan_rep_mode, data->pscan_period_mode, data->pscan_mode, data->dev_class[2], data->dev_class[1], data->dev_class[0], @@ -445,13 +439,10 @@ static int blacklist_show(struct seq_file *f, void *p) list_for_each(l, &hdev->blacklist) { struct bdaddr_list *b; - bdaddr_t bdaddr; b = list_entry(l, struct bdaddr_list, list); - baswap(&bdaddr, &b->bdaddr); - - seq_printf(f, "%s\n", batostr(&bdaddr)); + seq_printf(f, "%s\n", batostr(&b->bdaddr)); } hci_dev_unlock_bh(hdev); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index bfe641b..c0ee8b3 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -758,7 +758,6 @@ static int hidp_setup_hid(struct hidp_session *session, struct hidp_connadd_req *req) { struct hid_device *hid; - bdaddr_t src, dst; int err; session->rd_data = kzalloc(req->rd_size, GFP_KERNEL); @@ -781,9 +780,6 @@ static int hidp_setup_hid(struct hidp_session *session, hid->driver_data = session; - baswap(&src, &bt_sk(session->ctrl_sock->sk)->src); - baswap(&dst, &bt_sk(session->ctrl_sock->sk)->dst); - hid->bus = BUS_BLUETOOTH; hid->vendor = req->vendor; hid->product = req->product; @@ -791,8 +787,8 @@ static int hidp_setup_hid(struct hidp_session *session, hid->country = req->country; strncpy(hid->name, req->name, 128); - strncpy(hid->phys, batostr(&src), 64); - strncpy(hid->uniq, batostr(&dst), 64); + strncpy(hid->phys, batostr(&bt_sk(session->ctrl_sock->sk)->src), 64); + strncpy(hid->uniq, batostr(&bt_sk(session->ctrl_sock->sk)->dst), 64); hid->dev.parent = hidp_get_device(session); hid->ll_driver = &hidp_hid_driver; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index fadf26b..16049de 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1008,10 +1008,20 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) goto done; } - if (la.l2_psm && __le16_to_cpu(la.l2_psm) < 0x1001 && - !capable(CAP_NET_BIND_SERVICE)) { - err = -EACCES; - goto done; + if (la.l2_psm) { + __u16 psm = __le16_to_cpu(la.l2_psm); + + /* PSM must be odd and lsb of upper byte must be 0 */ + if ((psm & 0x0101) != 0x0001) { + err = -EINVAL; + goto done; + } + + /* Restrict usage of well-known PSMs */ + if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) { + err = -EACCES; + goto done; + } } write_lock_bh(&l2cap_sk_list.lock); @@ -1190,6 +1200,13 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al goto done; } + /* PSM must be odd and lsb of upper byte must be 0 */ + if ((__le16_to_cpu(la.l2_psm) & 0x0101) != 0x0001 && + sk->sk_type != SOCK_RAW) { + err = -EINVAL; + goto done; + } + /* Set destination address and psm */ bacpy(&bt_sk(sk)->dst, &la.l2_bdaddr); l2cap_pi(sk)->psm = la.l2_psm; @@ -1441,33 +1458,23 @@ static inline void l2cap_do_send(struct sock *sk, struct sk_buff *skb) static void l2cap_streaming_send(struct sock *sk) { - struct sk_buff *skb, *tx_skb; + struct sk_buff *skb; struct l2cap_pinfo *pi = l2cap_pi(sk); u16 control, fcs; - while ((skb = sk->sk_send_head)) { - tx_skb = skb_clone(skb, GFP_ATOMIC); - - control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); + while ((skb = skb_dequeue(TX_QUEUE(sk)))) { + control = get_unaligned_le16(skb->data + L2CAP_HDR_SIZE); control |= pi->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT; - put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); + put_unaligned_le16(control, skb->data + L2CAP_HDR_SIZE); if (pi->fcs == L2CAP_FCS_CRC16) { - fcs = crc16(0, (u8 *)tx_skb->data, tx_skb->len - 2); - put_unaligned_le16(fcs, tx_skb->data + tx_skb->len - 2); + fcs = crc16(0, (u8 *)skb->data, skb->len - 2); + put_unaligned_le16(fcs, skb->data + skb->len - 2); } - l2cap_do_send(sk, tx_skb); + l2cap_do_send(sk, skb); pi->next_tx_seq = (pi->next_tx_seq + 1) % 64; - - if (skb_queue_is_last(TX_QUEUE(sk), skb)) - sk->sk_send_head = NULL; - else - sk->sk_send_head = skb_queue_next(TX_QUEUE(sk), skb); - - skb = skb_dequeue(TX_QUEUE(sk)); - kfree_skb(skb); } } @@ -1645,7 +1652,7 @@ static inline int l2cap_skbuff_fromiovec(struct sock *sk, struct msghdr *msg, in *frag = bt_skb_send_alloc(sk, count, msg->msg_flags & MSG_DONTWAIT, &err); if (!*frag) - return -EFAULT; + return err; if (memcpy_fromiovec(skb_put(*frag, count), msg->msg_iov, count)) return -EFAULT; @@ -1671,7 +1678,7 @@ static struct sk_buff *l2cap_create_connless_pdu(struct sock *sk, struct msghdr skb = bt_skb_send_alloc(sk, count + hlen, msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) - return ERR_PTR(-ENOMEM); + return ERR_PTR(err); /* Create L2CAP header */ lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); @@ -1700,7 +1707,7 @@ static struct sk_buff *l2cap_create_basic_pdu(struct sock *sk, struct msghdr *ms skb = bt_skb_send_alloc(sk, count + hlen, msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) - return ERR_PTR(-ENOMEM); + return ERR_PTR(err); /* Create L2CAP header */ lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); @@ -1737,7 +1744,7 @@ static struct sk_buff *l2cap_create_iframe_pdu(struct sock *sk, struct msghdr *m skb = bt_skb_send_alloc(sk, count + hlen, msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) - return ERR_PTR(-ENOMEM); + return ERR_PTR(err); /* Create L2CAP header */ lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); @@ -1944,6 +1951,9 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct ms release_sock(sk); + if (sock->type == SOCK_STREAM) + return bt_sock_stream_recvmsg(iocb, sock, msg, len, flags); + return bt_sock_recvmsg(iocb, sock, msg, len, flags); } @@ -1960,6 +1970,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us switch (optname) { case L2CAP_OPTIONS: + if (sk->sk_state == BT_CONNECTED) { + err = -EINVAL; + break; + } + opts.imtu = l2cap_pi(sk)->imtu; opts.omtu = l2cap_pi(sk)->omtu; opts.flush_to = l2cap_pi(sk)->flush_to; @@ -2771,10 +2786,10 @@ static int l2cap_parse_conf_rsp(struct sock *sk, void *rsp, int len, void *data, case L2CAP_CONF_MTU: if (val < L2CAP_DEFAULT_MIN_MTU) { *result = L2CAP_CONF_UNACCEPT; - pi->omtu = L2CAP_DEFAULT_MIN_MTU; + pi->imtu = L2CAP_DEFAULT_MIN_MTU; } else - pi->omtu = val; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->omtu); + pi->imtu = val; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, pi->imtu); break; case L2CAP_CONF_FLUSH_TO: @@ -3071,6 +3086,17 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd return 0; } +static inline void set_default_fcs(struct l2cap_pinfo *pi) +{ + /* FCS is enabled only in ERTM or streaming mode, if one or both + * sides request it. + */ + if (pi->mode != L2CAP_MODE_ERTM && pi->mode != L2CAP_MODE_STREAMING) + pi->fcs = L2CAP_FCS_NONE; + else if (!(pi->conf_state & L2CAP_CONF_NO_FCS_RECV)) + pi->fcs = L2CAP_FCS_CRC16; +} + static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) { struct l2cap_conf_req *req = (struct l2cap_conf_req *) data; @@ -3088,14 +3114,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr if (!sk) return -ENOENT; - if (sk->sk_state != BT_CONFIG) { - struct l2cap_cmd_rej rej; - - rej.reason = cpu_to_le16(0x0002); - l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ, - sizeof(rej), &rej); + if (sk->sk_state == BT_DISCONN) goto unlock; - } /* Reject if config buffer is too small. */ len = cmd_len - sizeof(*req); @@ -3135,9 +3155,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr goto unlock; if (l2cap_pi(sk)->conf_state & L2CAP_CONF_INPUT_DONE) { - if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) || - l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) - l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16; + set_default_fcs(l2cap_pi(sk)); sk->sk_state = BT_CONNECTED; @@ -3153,6 +3171,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_REQ_SENT)) { u8 buf[64]; + l2cap_pi(sk)->conf_state |= L2CAP_CONF_REQ_SENT; l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, l2cap_build_conf_req(sk, buf), buf); l2cap_pi(sk)->num_conf_req++; @@ -3225,9 +3244,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr l2cap_pi(sk)->conf_state |= L2CAP_CONF_INPUT_DONE; if (l2cap_pi(sk)->conf_state & L2CAP_CONF_OUTPUT_DONE) { - if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) || - l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) - l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16; + set_default_fcs(l2cap_pi(sk)); sk->sk_state = BT_CONNECTED; l2cap_pi(sk)->next_tx_seq = 0; @@ -4647,6 +4664,8 @@ static int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 fl if (flags & ACL_START) { struct l2cap_hdr *hdr; + struct sock *sk; + u16 cid; int len; if (conn->rx_len) { @@ -4657,7 +4676,8 @@ static int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 fl l2cap_conn_unreliable(conn, ECOMM); } - if (skb->len < 2) { + /* Start fragment always begin with Basic L2CAP header */ + if (skb->len < L2CAP_HDR_SIZE) { BT_ERR("Frame is too short (len %d)", skb->len); l2cap_conn_unreliable(conn, ECOMM); goto drop; @@ -4665,6 +4685,7 @@ static int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 fl hdr = (struct l2cap_hdr *) skb->data; len = __le16_to_cpu(hdr->len) + L2CAP_HDR_SIZE; + cid = __le16_to_cpu(hdr->cid); if (len == skb->len) { /* Complete frame received */ @@ -4681,6 +4702,19 @@ static int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 fl goto drop; } + sk = l2cap_get_chan_by_scid(&conn->chan_list, cid); + + if (sk && l2cap_pi(sk)->imtu < len - L2CAP_HDR_SIZE) { + BT_ERR("Frame exceeding recv MTU (len %d, MTU %d)", + len, l2cap_pi(sk)->imtu); + bh_unlock_sock(sk); + l2cap_conn_unreliable(conn, ECOMM); + goto drop; + } + + if (sk) + bh_unlock_sock(sk); + /* Allocate skb for the complete frame (with header) */ conn->rx_skb = bt_skb_alloc(len, GFP_ATOMIC); if (!conn->rx_skb) diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c index ad2af58..b826d1b 100644 --- a/net/bluetooth/lib.c +++ b/net/bluetooth/lib.c @@ -51,8 +51,8 @@ char *batostr(bdaddr_t *ba) i ^= 1; sprintf(str[i], "%2.2X:%2.2X:%2.2X:%2.2X:%2.2X:%2.2X", - ba->b[0], ba->b[1], ba->b[2], - ba->b[3], ba->b[4], ba->b[5]); + ba->b[5], ba->b[4], ba->b[3], + ba->b[2], ba->b[1], ba->b[0]); return str[i]; } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 7dca91b..39a5d87 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -113,11 +113,10 @@ static void rfcomm_session_del(struct rfcomm_session *s); #define __get_rpn_stop_bits(line) (((line) >> 2) & 0x1) #define __get_rpn_parity(line) (((line) >> 3) & 0x7) -static inline void rfcomm_schedule(uint event) +static inline void rfcomm_schedule(void) { if (!rfcomm_thread) return; - //set_bit(event, &rfcomm_event); set_bit(RFCOMM_SCHED_WAKEUP, &rfcomm_event); wake_up_process(rfcomm_thread); } @@ -179,13 +178,13 @@ static unsigned char rfcomm_crc_table[256] = { /* FCS on 2 bytes */ static inline u8 __fcs(u8 *data) { - return (0xff - __crc(data)); + return 0xff - __crc(data); } /* FCS on 3 bytes */ static inline u8 __fcs2(u8 *data) { - return (0xff - rfcomm_crc_table[__crc(data) ^ data[2]]); + return 0xff - rfcomm_crc_table[__crc(data) ^ data[2]]; } /* Check FCS */ @@ -203,13 +202,13 @@ static inline int __check_fcs(u8 *data, int type, u8 fcs) static void rfcomm_l2state_change(struct sock *sk) { BT_DBG("%p state %d", sk, sk->sk_state); - rfcomm_schedule(RFCOMM_SCHED_STATE); + rfcomm_schedule(); } static void rfcomm_l2data_ready(struct sock *sk, int bytes) { BT_DBG("%p bytes %d", sk, bytes); - rfcomm_schedule(RFCOMM_SCHED_RX); + rfcomm_schedule(); } static int rfcomm_l2sock_create(struct socket **sock) @@ -255,7 +254,7 @@ static void rfcomm_session_timeout(unsigned long arg) BT_DBG("session %p state %ld", s, s->state); set_bit(RFCOMM_TIMED_OUT, &s->flags); - rfcomm_schedule(RFCOMM_SCHED_TIMEO); + rfcomm_schedule(); } static void rfcomm_session_set_timer(struct rfcomm_session *s, long timeout) @@ -283,7 +282,7 @@ static void rfcomm_dlc_timeout(unsigned long arg) set_bit(RFCOMM_TIMED_OUT, &d->flags); rfcomm_dlc_put(d); - rfcomm_schedule(RFCOMM_SCHED_TIMEO); + rfcomm_schedule(); } static void rfcomm_dlc_set_timer(struct rfcomm_dlc *d, long timeout) @@ -465,7 +464,7 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) case BT_CONFIG: if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { set_bit(RFCOMM_AUTH_REJECT, &d->flags); - rfcomm_schedule(RFCOMM_SCHED_AUTH); + rfcomm_schedule(); break; } /* Fall through */ @@ -485,7 +484,7 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) case BT_CONNECT2: if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { set_bit(RFCOMM_AUTH_REJECT, &d->flags); - rfcomm_schedule(RFCOMM_SCHED_AUTH); + rfcomm_schedule(); break; } /* Fall through */ @@ -533,7 +532,7 @@ int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) skb_queue_tail(&d->tx_queue, skb); if (!test_bit(RFCOMM_TX_THROTTLED, &d->flags)) - rfcomm_schedule(RFCOMM_SCHED_TX); + rfcomm_schedule(); return len; } @@ -545,7 +544,7 @@ void __rfcomm_dlc_throttle(struct rfcomm_dlc *d) d->v24_sig |= RFCOMM_V24_FC; set_bit(RFCOMM_MSC_PENDING, &d->flags); } - rfcomm_schedule(RFCOMM_SCHED_TX); + rfcomm_schedule(); } void __rfcomm_dlc_unthrottle(struct rfcomm_dlc *d) @@ -556,7 +555,7 @@ void __rfcomm_dlc_unthrottle(struct rfcomm_dlc *d) d->v24_sig &= ~RFCOMM_V24_FC; set_bit(RFCOMM_MSC_PENDING, &d->flags); } - rfcomm_schedule(RFCOMM_SCHED_TX); + rfcomm_schedule(); } /* @@ -577,7 +576,7 @@ int rfcomm_dlc_set_modem_status(struct rfcomm_dlc *d, u8 v24_sig) d->v24_sig = v24_sig; if (!test_and_set_bit(RFCOMM_MSC_PENDING, &d->flags)) - rfcomm_schedule(RFCOMM_SCHED_TX); + rfcomm_schedule(); return 0; } @@ -816,7 +815,7 @@ static int rfcomm_queue_disc(struct rfcomm_dlc *d) cmd->fcs = __fcs2((u8 *) cmd); skb_queue_tail(&d->tx_queue, skb); - rfcomm_schedule(RFCOMM_SCHED_TX); + rfcomm_schedule(); return 0; } @@ -1415,8 +1414,8 @@ static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_ return 0; if (len == 1) { - /* This is a request, return default settings */ - bit_rate = RFCOMM_RPN_BR_115200; + /* This is a request, return default (according to ETSI TS 07.10) settings */ + bit_rate = RFCOMM_RPN_BR_9600; data_bits = RFCOMM_RPN_DATA_8; stop_bits = RFCOMM_RPN_STOP_1; parity = RFCOMM_RPN_PARITY_NONE; @@ -1431,9 +1430,9 @@ static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_ if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_BITRATE)) { bit_rate = rpn->bit_rate; - if (bit_rate != RFCOMM_RPN_BR_115200) { + if (bit_rate > RFCOMM_RPN_BR_230400) { BT_DBG("RPN bit rate mismatch 0x%x", bit_rate); - bit_rate = RFCOMM_RPN_BR_115200; + bit_rate = RFCOMM_RPN_BR_9600; rpn_mask ^= RFCOMM_RPN_PM_BITRATE; } } @@ -1698,7 +1697,7 @@ static int rfcomm_recv_frame(struct rfcomm_session *s, struct sk_buff *skb) break; default: - BT_ERR("Unknown packet type 0x%02x\n", type); + BT_ERR("Unknown packet type 0x%02x", type); break; } kfree_skb(skb); @@ -1884,7 +1883,7 @@ static inline void rfcomm_accept_connection(struct rfcomm_session *s) * L2CAP MTU minus UIH header and FCS. */ s->mtu = min(l2cap_pi(nsock->sk)->omtu, l2cap_pi(nsock->sk)->imtu) - 5; - rfcomm_schedule(RFCOMM_SCHED_RX); + rfcomm_schedule(); } else sock_release(nsock); } @@ -2093,7 +2092,7 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) rfcomm_session_put(s); - rfcomm_schedule(RFCOMM_SCHED_AUTH); + rfcomm_schedule(); } static struct hci_cb rfcomm_cb = { diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 44a6232..aec505f 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -82,11 +82,14 @@ static void rfcomm_sk_data_ready(struct rfcomm_dlc *d, struct sk_buff *skb) static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) { struct sock *sk = d->owner, *parent; + unsigned long flags; + if (!sk) return; BT_DBG("dlc %p state %ld err %d", d, d->state, err); + local_irq_save(flags); bh_lock_sock(sk); if (err) @@ -108,6 +111,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) } bh_unlock_sock(sk); + local_irq_restore(flags); if (parent && sock_flag(sk, SOCK_ZAPPED)) { /* We have to drop DLC lock here, otherwise @@ -617,121 +621,29 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock, return sent; } -static long rfcomm_sock_data_wait(struct sock *sk, long timeo) -{ - DECLARE_WAITQUEUE(wait, current); - - add_wait_queue(sk_sleep(sk), &wait); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - - if (!skb_queue_empty(&sk->sk_receive_queue) || - sk->sk_err || - (sk->sk_shutdown & RCV_SHUTDOWN) || - signal_pending(current) || - !timeo) - break; - - set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - release_sock(sk); - timeo = schedule_timeout(timeo); - lock_sock(sk); - clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - } - - __set_current_state(TASK_RUNNING); - remove_wait_queue(sk_sleep(sk), &wait); - return timeo; -} - static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc; - int err = 0; - size_t target, copied = 0; - long timeo; + int len; if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { rfcomm_dlc_accept(d); return 0; } - if (flags & MSG_OOB) - return -EOPNOTSUPP; - - msg->msg_namelen = 0; - - BT_DBG("sk %p size %zu", sk, size); + len = bt_sock_stream_recvmsg(iocb, sock, msg, size, flags); lock_sock(sk); + if (!(flags & MSG_PEEK) && len > 0) + atomic_sub(len, &sk->sk_rmem_alloc); - target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - do { - struct sk_buff *skb; - int chunk; - - skb = skb_dequeue(&sk->sk_receive_queue); - if (!skb) { - if (copied >= target) - break; - - if ((err = sock_error(sk)) != 0) - break; - if (sk->sk_shutdown & RCV_SHUTDOWN) - break; - - err = -EAGAIN; - if (!timeo) - break; - - timeo = rfcomm_sock_data_wait(sk, timeo); - - if (signal_pending(current)) { - err = sock_intr_errno(timeo); - goto out; - } - continue; - } - - chunk = min_t(unsigned int, skb->len, size); - if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { - skb_queue_head(&sk->sk_receive_queue, skb); - if (!copied) - copied = -EFAULT; - break; - } - copied += chunk; - size -= chunk; - - sock_recv_ts_and_drops(msg, sk, skb); - - if (!(flags & MSG_PEEK)) { - atomic_sub(chunk, &sk->sk_rmem_alloc); - - skb_pull(skb, chunk); - if (skb->len) { - skb_queue_head(&sk->sk_receive_queue, skb); - break; - } - kfree_skb(skb); - - } else { - /* put message back and return */ - skb_queue_head(&sk->sk_receive_queue, skb); - break; - } - } while (size); - -out: if (atomic_read(&sk->sk_rmem_alloc) <= (sk->sk_rcvbuf >> 2)) rfcomm_dlc_unthrottle(rfcomm_pi(sk)->dlc); - release_sock(sk); - return copied ? : err; + + return len; } static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index befc3a5..2646163 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -183,9 +183,7 @@ static struct device *rfcomm_get_device(struct rfcomm_dev *dev) static ssize_t show_address(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); - bdaddr_t bdaddr; - baswap(&bdaddr, &dev->dst); - return sprintf(buf, "%s\n", batostr(&bdaddr)); + return sprintf(buf, "%s\n", batostr(&dev->dst)); } static ssize_t show_channel(struct device *tty_dev, struct device_attribute *attr, char *buf) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index cf09fe59..17cb0b6 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -212,6 +212,11 @@ static int br_set_tx_csum(struct net_device *dev, u32 data) return 0; } +static int br_set_flags(struct net_device *netdev, u32 data) +{ + return ethtool_op_set_flags(netdev, data, ETH_FLAG_TXVLAN); +} + #ifdef CONFIG_NET_POLL_CONTROLLER static void br_poll_controller(struct net_device *br_dev) { @@ -304,6 +309,7 @@ static const struct ethtool_ops br_ethtool_ops = { .get_ufo = ethtool_op_get_ufo, .set_ufo = ethtool_op_set_ufo, .get_flags = ethtool_op_get_flags, + .set_flags = br_set_flags, }; static const struct net_device_ops br_netdev_ops = { @@ -343,5 +349,5 @@ void br_dev_setup(struct net_device *dev) dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_NO_CSUM | NETIF_F_LLTX | - NETIF_F_NETNS_LOCAL | NETIF_F_GSO; + NETIF_F_NETNS_LOCAL | NETIF_F_GSO | NETIF_F_HW_VLAN_TX; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 6d04cfd..25207a1 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -159,7 +159,7 @@ struct sk_buff *br_handle_frame(struct sk_buff *skb) goto drop; /* If STP is turned off, then forward */ - if (p->br->stp_enabled == BR_NO_STP && dest[5] == 0) + if (p->br->stp_enabled == BR_NO_STP) goto forward; if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 137f232..865fd76 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -64,22 +64,24 @@ static int brnf_filter_pppoe_tagged __read_mostly = 0; static inline __be16 vlan_proto(const struct sk_buff *skb) { - return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; + if (vlan_tx_tag_present(skb)) + return skb->protocol; + else if (skb->protocol == htons(ETH_P_8021Q)) + return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; + else + return 0; } #define IS_VLAN_IP(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_IP) && \ + (vlan_proto(skb) == htons(ETH_P_IP) && \ brnf_filter_vlan_tagged) #define IS_VLAN_IPV6(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_IPV6) &&\ + (vlan_proto(skb) == htons(ETH_P_IPV6) && \ brnf_filter_vlan_tagged) #define IS_VLAN_ARP(skb) \ - (skb->protocol == htons(ETH_P_8021Q) && \ - vlan_proto(skb) == htons(ETH_P_ARP) && \ + (vlan_proto(skb) == htons(ETH_P_ARP) && \ brnf_filter_vlan_tagged) static inline __be16 pppoe_proto(const struct sk_buff *skb) @@ -106,7 +108,6 @@ static struct dst_ops fake_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, - .entries = ATOMIC_INIT(0), }; /* @@ -209,6 +210,72 @@ static inline void nf_bridge_update_protocol(struct sk_buff *skb) skb->protocol = htons(ETH_P_PPP_SES); } +/* When handing a packet over to the IP layer + * check whether we have a skb that is in the + * expected format + */ + +static int br_parse_ip_options(struct sk_buff *skb) +{ + struct ip_options *opt; + struct iphdr *iph; + struct net_device *dev = skb->dev; + u32 len; + + iph = ip_hdr(skb); + opt = &(IPCB(skb)->opt); + + /* Basic sanity checks */ + if (iph->ihl < 5 || iph->version != 4) + goto inhdr_error; + + if (!pskb_may_pull(skb, iph->ihl*4)) + goto inhdr_error; + + iph = ip_hdr(skb); + if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + goto inhdr_error; + + len = ntohs(iph->tot_len); + if (skb->len < len) { + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS); + goto drop; + } else if (len < (iph->ihl*4)) + goto inhdr_error; + + if (pskb_trim_rcsum(skb, len)) { + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); + goto drop; + } + + /* Zero out the CB buffer if no options present */ + if (iph->ihl == 5) { + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + return 0; + } + + opt->optlen = iph->ihl*4 - sizeof(struct iphdr); + if (ip_options_compile(dev_net(dev), opt, skb)) + goto inhdr_error; + + /* Check correct handling of SRR option */ + if (unlikely(opt->srr)) { + struct in_device *in_dev = __in_dev_get_rcu(dev); + if (in_dev && !IN_DEV_SOURCE_ROUTE(in_dev)) + goto drop; + + if (ip_options_rcv_srr(skb)) + goto drop; + } + + return 0; + +inhdr_error: + IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS); +drop: + return -1; +} + /* Fill in the header for fragmented IP packets handled by * the IPv4 connection tracking code. */ @@ -549,7 +616,6 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, { struct net_bridge_port *p; struct net_bridge *br; - struct iphdr *iph; __u32 len = nf_bridge_encap_header_len(skb); if (unlikely(!pskb_may_pull(skb, len))) @@ -578,28 +644,9 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, nf_bridge_pull_encap_header_rcsum(skb); - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto inhdr_error; - - iph = ip_hdr(skb); - if (iph->ihl < 5 || iph->version != 4) - goto inhdr_error; - - if (!pskb_may_pull(skb, 4 * iph->ihl)) - goto inhdr_error; - - iph = ip_hdr(skb); - if (ip_fast_csum((__u8 *) iph, iph->ihl) != 0) - goto inhdr_error; - - len = ntohs(iph->tot_len); - if (skb->len < len || len < 4 * iph->ihl) - goto inhdr_error; - - pskb_trim_rcsum(skb, len); - - /* BUG: Should really parse the IP options here. */ - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + if (br_parse_ip_options(skb)) + /* Drop invalid packet */ + goto out; nf_bridge_put(skb->nf_bridge); if (!nf_bridge_alloc(skb)) @@ -614,8 +661,6 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, return NF_STOLEN; -inhdr_error: -// IP_INC_STATS_BH(IpInHdrErrors); out: return NF_DROP; } @@ -759,14 +804,19 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb, #if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE) static int br_nf_dev_queue_xmit(struct sk_buff *skb) { + int ret; + if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) && skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && !skb_is_gso(skb)) { - /* BUG: Should really parse the IP options here. */ - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - return ip_fragment(skb, br_dev_queue_push_xmit); + if (br_parse_ip_options(skb)) + /* Drop invalid packet */ + return NF_DROP; + ret = ip_fragment(skb, br_dev_queue_push_xmit); } else - return br_dev_queue_push_xmit(skb); + ret = br_dev_queue_push_xmit(skb); + + return ret; } #else static int br_nf_dev_queue_xmit(struct sk_buff *skb) @@ -954,15 +1004,22 @@ int __init br_netfilter_init(void) { int ret; - ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + ret = dst_entries_init(&fake_dst_ops); if (ret < 0) return ret; + + ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + if (ret < 0) { + dst_entries_destroy(&fake_dst_ops); + return ret; + } #ifdef CONFIG_SYSCTL brnf_sysctl_header = register_sysctl_paths(brnf_path, brnf_table); if (brnf_sysctl_header == NULL) { printk(KERN_WARNING "br_netfilter: can't register to sysctl.\n"); nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + dst_entries_destroy(&fake_dst_ops); return -ENOMEM; } #endif @@ -976,4 +1033,5 @@ void br_netfilter_fini(void) #ifdef CONFIG_SYSCTL unregister_sysctl_table(brnf_sysctl_header); #endif + dst_entries_destroy(&fake_dst_ops); } diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c index 87b53b3..eae67bf 100644 --- a/net/bridge/netfilter/ebt_vlan.c +++ b/net/bridge/netfilter/ebt_vlan.c @@ -39,8 +39,6 @@ static bool ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_vlan_info *info = par->matchinfo; - const struct vlan_hdr *fp; - struct vlan_hdr _frame; unsigned short TCI; /* Whole TCI, given from parsed frame */ unsigned short id; /* VLAN ID, given from frame TCI */ @@ -48,9 +46,20 @@ ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par) /* VLAN encapsulated Type/Length field, given from orig frame */ __be16 encap; - fp = skb_header_pointer(skb, 0, sizeof(_frame), &_frame); - if (fp == NULL) - return false; + if (vlan_tx_tag_present(skb)) { + TCI = vlan_tx_tag_get(skb); + encap = skb->protocol; + } else { + const struct vlan_hdr *fp; + struct vlan_hdr _frame; + + fp = skb_header_pointer(skb, 0, sizeof(_frame), &_frame); + if (fp == NULL) + return false; + + TCI = ntohs(fp->h_vlan_TCI); + encap = fp->h_vlan_encapsulated_proto; + } /* Tag Control Information (TCI) consists of the following elements: * - User_priority. The user_priority field is three bits in length, @@ -59,10 +68,8 @@ ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par) * (CFI) is a single bit flag value. Currently ignored. * - VLAN Identifier (VID). The VID is encoded as * an unsigned binary number. */ - TCI = ntohs(fp->h_vlan_TCI); id = TCI & VLAN_VID_MASK; prio = (TCI >> 13) & 0x7; - encap = fp->h_vlan_encapsulated_proto; /* Checking VLAN Identifier (VID) */ if (GET_BITMASK(EBT_VLAN_ID)) @@ -111,10 +118,10 @@ static int ebt_vlan_mt_check(const struct xt_mtchk_param *par) * 0 - The null VLAN ID. * 1 - The default Port VID (PVID) * 0x0FFF - Reserved for implementation use. - * if_vlan.h: VLAN_GROUP_ARRAY_LEN 4096. */ + * if_vlan.h: VLAN_N_VID 4096. */ if (GET_BITMASK(EBT_VLAN_ID)) { if (!!info->id) { /* if id!=0 => check vid range */ - if (info->id > VLAN_GROUP_ARRAY_LEN) { + if (info->id > VLAN_N_VID) { pr_debug("id %d is out of range (1-4096)\n", info->id); return -EINVAL; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bcc102e..a1dcf83 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -124,16 +124,23 @@ ebt_dev_check(const char *entry, const struct net_device *device) #define FWINV2(bool,invflg) ((bool) ^ !!(e->invflags & invflg)) /* process standard matches */ static inline int -ebt_basic_match(const struct ebt_entry *e, const struct ethhdr *h, +ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out) { + const struct ethhdr *h = eth_hdr(skb); + __be16 ethproto; int verdict, i; + if (vlan_tx_tag_present(skb)) + ethproto = htons(ETH_P_8021Q); + else + ethproto = h->h_proto; + if (e->bitmask & EBT_802_3) { - if (FWINV2(ntohs(h->h_proto) >= 1536, EBT_IPROTO)) + if (FWINV2(ntohs(ethproto) >= 1536, EBT_IPROTO)) return 1; } else if (!(e->bitmask & EBT_NOPROTO) && - FWINV2(e->ethproto != h->h_proto, EBT_IPROTO)) + FWINV2(e->ethproto != ethproto, EBT_IPROTO)) return 1; if (FWINV2(ebt_dev_check(e->in, in), EBT_IIN)) @@ -213,7 +220,7 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, base = private->entries; i = 0; while (i < nentries) { - if (ebt_basic_match(point, eth_hdr(skb), in, out)) + if (ebt_basic_match(point, skb, in, out)) goto letscontinue; if (EBT_MATCH_ITERATE(point, ebt_do_match, skb, &acpar) != 0) diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 0fd01dd..b99369a 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -173,7 +173,7 @@ static int receive(struct sk_buff *skb, struct net_device *dev, net = dev_net(dev); pkt = cfpkt_fromnative(CAIF_DIR_IN, skb); caifd = caif_get(dev); - if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) + if (!caifd || !caifd->layer.up || !caifd->layer.up->receive) return NET_RX_DROP; if (caifd->layer.up->receive(caifd->layer.up, pkt)) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index fd1f5df..2eca2dd 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -17,7 +17,6 @@ #include <linux/poll.h> #include <linux/tcp.h> #include <linux/uaccess.h> -#include <linux/mutex.h> #include <linux/debugfs.h> #include <linux/caif/caif_socket.h> #include <asm/atomic.h> @@ -30,9 +29,6 @@ MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(AF_CAIF); -#define CAIF_DEF_SNDBUF (4096*10) -#define CAIF_DEF_RCVBUF (4096*100) - /* * CAIF state is re-using the TCP socket states. * caif_states stored in sk_state reflect the state as reported by @@ -159,9 +155,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned)sk->sk_rcvbuf && rx_flow_is_on(cf_sk)) { - trace_printk("CAIF: %s(): " - "sending flow OFF (queue len = %d %d)\n", - __func__, + pr_debug("sending flow OFF (queue len = %d %d)\n", atomic_read(&cf_sk->sk.sk_rmem_alloc), sk_rcvbuf_lowwater(cf_sk)); set_rx_flow_off(cf_sk); @@ -174,9 +168,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return err; if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) { set_rx_flow_off(cf_sk); - trace_printk("CAIF: %s(): " - "sending flow OFF due to rmem_schedule\n", - __func__); + pr_debug("sending flow OFF due to rmem_schedule\n"); dbfs_atomic_inc(&cnt.num_rx_flow_off); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); } @@ -827,6 +819,7 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr, long timeo; int err; int ifindex, headroom, tailroom; + unsigned int mtu; struct net_device *dev; lock_sock(sk); @@ -896,14 +889,22 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr, cf_sk->sk.sk_state = CAIF_DISCONNECTED; goto out; } - dev = dev_get_by_index(sock_net(sk), ifindex); + + err = -ENODEV; + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); + if (!dev) { + rcu_read_unlock(); + goto out; + } cf_sk->headroom = LL_RESERVED_SPACE_EXTRA(dev, headroom); + mtu = dev->mtu; + rcu_read_unlock(); + cf_sk->tailroom = tailroom; - cf_sk->maxframe = dev->mtu - (headroom + tailroom); - dev_put(dev); + cf_sk->maxframe = mtu - (headroom + tailroom); if (cf_sk->maxframe < 1) { pr_warn("CAIF Interface MTU too small (%d)\n", dev->mtu); - err = -ENODEV; goto out; } @@ -1122,10 +1123,6 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, /* Store the protocol */ sk->sk_protocol = (unsigned char) protocol; - /* Sendbuf dictates the amount of outbound packets not yet sent */ - sk->sk_sndbuf = CAIF_DEF_SNDBUF; - sk->sk_rcvbuf = CAIF_DEF_RCVBUF; - /* * Lock in order to try to stop someone from opening the socket * too early. diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index ef93a13..41adafd1 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -197,7 +197,7 @@ int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) caif_assert(adap_layer != NULL); channel_id = adap_layer->id; if (adap_layer->dn == NULL || channel_id == 0) { - pr_err("adap_layer->id is 0\n"); + pr_err("adap_layer->dn == NULL or adap_layer->id is 0\n"); ret = -ENOTCONN; goto end; } diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 86aac24..84a422c 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -30,9 +30,6 @@ #define CONNECT_TIMEOUT (5 * HZ) #define CAIF_NET_DEFAULT_QUEUE_LEN 500 -#undef pr_debug -#define pr_debug pr_warn - /*This list is protected by the rtnl lock. */ static LIST_HEAD(chnl_net_list); diff --git a/net/can/raw.c b/net/can/raw.c index 7d77e67..e88f610 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -90,23 +90,39 @@ struct raw_sock { can_err_mask_t err_mask; }; +/* + * Return pointer to store the extra msg flags for raw_recvmsg(). + * We use the space of one unsigned int beyond the 'struct sockaddr_can' + * in skb->cb. + */ +static inline unsigned int *raw_flags(struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(skb->cb) <= (sizeof(struct sockaddr_can) + + sizeof(unsigned int))); + + /* return pointer after struct sockaddr_can */ + return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); +} + static inline struct raw_sock *raw_sk(const struct sock *sk) { return (struct raw_sock *)sk; } -static void raw_rcv(struct sk_buff *skb, void *data) +static void raw_rcv(struct sk_buff *oskb, void *data) { struct sock *sk = (struct sock *)data; struct raw_sock *ro = raw_sk(sk); struct sockaddr_can *addr; + struct sk_buff *skb; + unsigned int *pflags; /* check the received tx sock reference */ - if (!ro->recv_own_msgs && skb->sk == sk) + if (!ro->recv_own_msgs && oskb->sk == sk) return; /* clone the given skb to be able to enqueue it into the rcv queue */ - skb = skb_clone(skb, GFP_ATOMIC); + skb = skb_clone(oskb, GFP_ATOMIC); if (!skb) return; @@ -123,6 +139,14 @@ static void raw_rcv(struct sk_buff *skb, void *data) addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; + /* add CAN specific message flags for raw_recvmsg() */ + pflags = raw_flags(skb); + *pflags = 0; + if (oskb->sk) + *pflags |= MSG_DONTROUTE; + if (oskb->sk == sk) + *pflags |= MSG_CONFIRM; + if (sock_queue_rcv_skb(sk, skb) < 0) kfree_skb(skb); } @@ -707,6 +731,9 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } + /* assign the flags that have been recorded in raw_rcv() */ + msg->msg_flags |= *(raw_flags(skb)); + skb_free_datagram(sk, skb); return size; diff --git a/net/core/dev.c b/net/core/dev.c index fc2dc93..b2269ac 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -129,6 +129,7 @@ #include <linux/random.h> #include <trace/events/napi.h> #include <linux/pci.h> +#include <linux/inetdevice.h> #include "net-sysfs.h" @@ -1482,8 +1483,9 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_orphan(skb); nf_reset(skb); - if (!(dev->flags & IFF_UP) || - (skb->len > (dev->mtu + dev->hard_header_len))) { + if (unlikely(!(dev->flags & IFF_UP) || + (skb->len > (dev->mtu + dev->hard_header_len)))) { + atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } @@ -1551,21 +1553,56 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. */ -void netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) +int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { - unsigned int real_num = dev->real_num_tx_queues; + if (txq < 1 || txq > dev->num_tx_queues) + return -EINVAL; + + if (dev->reg_state == NETREG_REGISTERED) { + ASSERT_RTNL(); - if (unlikely(txq > dev->num_tx_queues)) - ; - else if (txq > real_num) - dev->real_num_tx_queues = txq; - else if (txq < real_num) { - dev->real_num_tx_queues = txq; - qdisc_reset_all_tx_gt(dev, txq); + if (txq < dev->real_num_tx_queues) + qdisc_reset_all_tx_gt(dev, txq); } + + dev->real_num_tx_queues = txq; + return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues); +#ifdef CONFIG_RPS +/** + * netif_set_real_num_rx_queues - set actual number of RX queues used + * @dev: Network device + * @rxq: Actual number of RX queues + * + * This must be called either with the rtnl_lock held or before + * registration of the net device. Returns 0 on success, or a + * negative error code. If called before registration, it always + * succeeds. + */ +int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) +{ + int rc; + + if (rxq < 1 || rxq > dev->num_rx_queues) + return -EINVAL; + + if (dev->reg_state == NETREG_REGISTERED) { + ASSERT_RTNL(); + + rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, + rxq); + if (rc) + return rc; + } + + dev->real_num_rx_queues = rxq; + return 0; +} +EXPORT_SYMBOL(netif_set_real_num_rx_queues); +#endif + static inline void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; @@ -1657,7 +1694,12 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol) static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) { - if (can_checksum_protocol(dev->features, skb->protocol)) + int features = dev->features; + + if (vlan_tx_tag_present(skb)) + features &= dev->vlan_features; + + if (can_checksum_protocol(features, skb->protocol)) return true; if (skb->protocol == htons(ETH_P_8021Q)) { @@ -1756,6 +1798,16 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) __be16 type = skb->protocol; int err; + if (type == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veh; + + if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) + return ERR_PTR(-EINVAL); + + veh = (struct vlan_ethhdr *)skb->data; + type = veh->h_vlan_encapsulated_proto; + } + skb_reset_mac_header(skb); skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); @@ -1927,9 +1979,14 @@ static inline void skb_orphan_try(struct sk_buff *skb) static inline int skb_needs_linearize(struct sk_buff *skb, struct net_device *dev) { + int features = dev->features; + + if (skb->protocol == htons(ETH_P_8021Q) || vlan_tx_tag_present(skb)) + features &= dev->vlan_features; + return skb_is_nonlinear(skb) && - ((skb_has_frag_list(skb) && !(dev->features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) || + ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || + (skb_shinfo(skb)->nr_frags && (!(features & NETIF_F_SG) || illegal_highdma(dev, skb)))); } @@ -1952,6 +2009,15 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb_orphan_try(skb); + if (vlan_tx_tag_present(skb) && + !(dev->features & NETIF_F_HW_VLAN_TX)) { + skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); + if (unlikely(!skb)) + goto out; + + skb->vlan_tci = 0; + } + if (netif_needs_gso(dev, skb)) { if (unlikely(dev_gso_segment(skb))) goto out_kfree_skb; @@ -2013,6 +2079,7 @@ out_kfree_gso_skb: skb->destructor = DEV_GSO_CB(skb)->destructor; out_kfree_skb: kfree_skb(skb); +out: return rc; } @@ -2141,6 +2208,9 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } +static DEFINE_PER_CPU(int, xmit_recursion); +#define RECURSION_LIMIT 3 + /** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit @@ -2206,10 +2276,15 @@ int dev_queue_xmit(struct sk_buff *skb) if (txq->xmit_lock_owner != cpu) { + if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT) + goto recursion_alert; + HARD_TX_LOCK(dev, txq, cpu); if (!netif_tx_queue_stopped(txq)) { + __this_cpu_inc(xmit_recursion); rc = dev_hard_start_xmit(skb, dev, txq); + __this_cpu_dec(xmit_recursion); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; @@ -2221,7 +2296,9 @@ int dev_queue_xmit(struct sk_buff *skb) "queue packet!\n", dev->name); } else { /* Recursion is detected! It is possible, - * unfortunately */ + * unfortunately + */ +recursion_alert: if (net_ratelimit()) printk(KERN_CRIT "Dead loop on virtual device " "%s, fix it urgently!\n", dev->name); @@ -2351,10 +2428,11 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); - if (unlikely(index >= dev->num_rx_queues)) { - WARN_ONCE(dev->num_rx_queues > 1, "%s received packet " - "on queue %u, but number of RX queues is %u\n", - dev->name, index, dev->num_rx_queues); + if (unlikely(index >= dev->real_num_rx_queues)) { + WARN_ONCE(dev->real_num_rx_queues > 1, + "%s received packet on queue %u, but number " + "of RX queues is %u\n", + dev->name, index, dev->real_num_rx_queues); goto done; } rxqueue = dev->_rx + index; @@ -2501,6 +2579,7 @@ enqueue: local_irq_restore(flags); + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } @@ -2655,11 +2734,10 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); * the ingress scheduler, you just cant add policies on ingress. * */ -static int ing_filter(struct sk_buff *skb) +static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) { struct net_device *dev = skb->dev; u32 ttl = G_TC_RTTL(skb->tc_verd); - struct netdev_queue *rxq; int result = TC_ACT_OK; struct Qdisc *q; @@ -2673,8 +2751,6 @@ static int ing_filter(struct sk_buff *skb) skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl); skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); - rxq = &dev->rx_queue; - q = rxq->qdisc; if (q != &noop_qdisc) { spin_lock(qdisc_lock(q)); @@ -2690,7 +2766,9 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { - if (skb->dev->rx_queue.qdisc == &noop_qdisc) + struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue); + + if (!rxq || rxq->qdisc == &noop_qdisc) goto out; if (*pt_prev) { @@ -2698,7 +2776,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, *pt_prev = NULL; } - switch (ing_filter(skb)) { + switch (ing_filter(skb, rxq)) { case TC_ACT_SHOT: case TC_ACT_STOLEN: kfree_skb(skb); @@ -2711,33 +2789,6 @@ out: } #endif -/* - * netif_nit_deliver - deliver received packets to network taps - * @skb: buffer - * - * This function is used to deliver incoming packets to network - * taps. It should be used when the normal netif_receive_skb path - * is bypassed, for example because of VLAN acceleration. - */ -void netif_nit_deliver(struct sk_buff *skb) -{ - struct packet_type *ptype; - - if (list_empty(&ptype_all)) - return; - - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (!ptype->dev || ptype->dev == skb->dev) - deliver_skb(skb, ptype, skb->dev); - } - rcu_read_unlock(); -} - /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for @@ -2847,9 +2898,6 @@ static int __netif_receive_skb(struct sk_buff *skb) if (!netdev_tstamp_prequeue) net_timestamp_check(skb); - if (vlan_tx_tag_present(skb)) - vlan_hwaccel_do_receive(skb); - /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) return NET_RX_DROP; @@ -2862,8 +2910,7 @@ static int __netif_receive_skb(struct sk_buff *skb) * be delivered to pkt handlers that are exact matches. Also * the deliver_no_wcard flag will be set. If packet handlers * are sensitive to duplicate packets these skbs will need to - * be dropped at the handler. The vlan accel path may have - * already set the deliver_no_wcard flag. + * be dropped at the handler. */ null_or_orig = NULL; orig_dev = skb->dev; @@ -2922,6 +2969,18 @@ ncls: goto out; } + if (vlan_tx_tag_present(skb)) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + if (vlan_hwaccel_do_receive(&skb)) { + ret = __netif_receive_skb(skb); + goto out; + } else if (unlikely(!skb)) + goto out; + } + /* * Make sure frames received on VLAN interfaces stacked on * bonding interfaces still make their way to any base bonding @@ -2949,6 +3008,7 @@ ncls: if (pt_prev) { ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) @@ -3185,6 +3245,7 @@ __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) unsigned long diffs; diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; + diffs |= p->vlan_tci ^ skb->vlan_tci; diffs |= compare_ether_header(skb_mac_header(p), skb_gro_mac_header(skb)); NAPI_GRO_CB(p)->same_flow = !diffs; @@ -3240,14 +3301,14 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) } EXPORT_SYMBOL(napi_gro_receive); -void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) +static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) { __skb_pull(skb, skb_headlen(skb)); skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb)); + skb->vlan_tci = 0; napi->skb = skb; } -EXPORT_SYMBOL(napi_reuse_skb); struct sk_buff *napi_get_frags(struct napi_struct *napi) { @@ -4867,7 +4928,7 @@ static void rollback_registered_many(struct list_head *head) dev = list_first_entry(head, struct net_device, unreg_list); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - synchronize_net(); + rcu_barrier(); list_for_each_entry(dev, head, unreg_list) dev_put(dev); @@ -4881,21 +4942,6 @@ static void rollback_registered(struct net_device *dev) rollback_registered_many(&single); } -static void __netdev_init_queue_locks_one(struct net_device *dev, - struct netdev_queue *dev_queue, - void *_unused) -{ - spin_lock_init(&dev_queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type); - dev_queue->xmit_lock_owner = -1; -} - -static void netdev_init_queue_locks(struct net_device *dev) -{ - netdev_for_each_tx_queue(dev, __netdev_init_queue_locks_one, NULL); - __netdev_init_queue_locks_one(dev, &dev->rx_queue, NULL); -} - unsigned long netdev_fix_features(unsigned long features, const char *name) { /* Fix illegal SG+CSUM combinations. */ @@ -4963,6 +5009,66 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); +static int netif_alloc_rx_queues(struct net_device *dev) +{ +#ifdef CONFIG_RPS + unsigned int i, count = dev->num_rx_queues; + struct netdev_rx_queue *rx; + + BUG_ON(count < 1); + + rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); + if (!rx) { + pr_err("netdev: Unable to allocate %u rx queues.\n", count); + return -ENOMEM; + } + dev->_rx = rx; + + /* + * Set a pointer to first element in the array which holds the + * reference count. + */ + for (i = 0; i < count; i++) + rx[i].first = rx; +#endif + return 0; +} + +static int netif_alloc_netdev_queues(struct net_device *dev) +{ + unsigned int count = dev->num_tx_queues; + struct netdev_queue *tx; + + BUG_ON(count < 1); + + tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL); + if (!tx) { + pr_err("netdev: Unable to allocate %u tx queues.\n", + count); + return -ENOMEM; + } + dev->_tx = tx; + return 0; +} + +static void netdev_init_one_queue(struct net_device *dev, + struct netdev_queue *queue, + void *_unused) +{ + queue->dev = dev; + + /* Initialize queue lock */ + spin_lock_init(&queue->_xmit_lock); + netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + queue->xmit_lock_owner = -1; +} + +static void netdev_init_queues(struct net_device *dev) +{ + netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); + spin_lock_init(&dev->tx_global_lock); +} + /** * register_netdevice - register a network device * @dev: device to register @@ -4996,28 +5102,19 @@ int register_netdevice(struct net_device *dev) spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); - netdev_init_queue_locks(dev); dev->iflink = -1; -#ifdef CONFIG_RPS - if (!dev->num_rx_queues) { - /* - * Allocate a single RX queue if driver never called - * alloc_netdev_mq - */ + ret = netif_alloc_rx_queues(dev); + if (ret) + goto out; - dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!dev->_rx) { - ret = -ENOMEM; - goto out; - } + ret = netif_alloc_netdev_queues(dev); + if (ret) + goto out; + + netdev_init_queues(dev); - dev->_rx->first = dev->_rx; - atomic_set(&dev->_rx->count, 1); - dev->num_rx_queues = 1; - } -#endif /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -5057,6 +5154,12 @@ int register_netdevice(struct net_device *dev) if (dev->features & NETIF_F_SG) dev->features |= NETIF_F_GSO; + /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, + * vlan_dev_init() will do the dev->features check, so these features + * are enabled only if supported by underlying device. + */ + dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA); + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) @@ -5127,9 +5230,6 @@ int init_dummy_netdev(struct net_device *dev) */ dev->reg_state = NETREG_DUMMY; - /* initialize the ref count */ - atomic_set(&dev->refcnt, 1); - /* NAPI wants this */ INIT_LIST_HEAD(&dev->napi_list); @@ -5137,6 +5237,11 @@ int init_dummy_netdev(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); + /* Note : We dont allocate pcpu_refcnt for dummy devices, + * because users of this 'device' dont need to change + * its refcount. + */ + return 0; } EXPORT_SYMBOL_GPL(init_dummy_netdev); @@ -5178,6 +5283,16 @@ out: } EXPORT_SYMBOL(register_netdev); +int netdev_refcnt_read(const struct net_device *dev) +{ + int i, refcnt = 0; + + for_each_possible_cpu(i) + refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); + return refcnt; +} +EXPORT_SYMBOL(netdev_refcnt_read); + /* * netdev_wait_allrefs - wait until all references are gone. * @@ -5192,11 +5307,14 @@ EXPORT_SYMBOL(register_netdev); static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; + int refcnt; linkwatch_forget_dev(dev); rebroadcast_time = warning_time = jiffies; - while (atomic_read(&dev->refcnt) != 0) { + refcnt = netdev_refcnt_read(dev); + + while (refcnt != 0) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); @@ -5223,11 +5341,13 @@ static void netdev_wait_allrefs(struct net_device *dev) msleep(250); + refcnt = netdev_refcnt_read(dev); + if (time_after(jiffies, warning_time + 10 * HZ)) { printk(KERN_EMERG "unregister_netdevice: " "waiting for %s to become free. Usage " "count = %d\n", - dev->name, atomic_read(&dev->refcnt)); + dev->name, refcnt); warning_time = jiffies; } } @@ -5285,8 +5405,8 @@ void netdev_run_todo(void) netdev_wait_allrefs(dev); /* paranoia */ - BUG_ON(atomic_read(&dev->refcnt)); - WARN_ON(dev->ip_ptr); + BUG_ON(netdev_refcnt_read(dev)); + WARN_ON(rcu_dereference_raw(dev->ip_ptr)); WARN_ON(dev->ip6_ptr); WARN_ON(dev->dn_ptr); @@ -5364,30 +5484,34 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); - return ops->ndo_get_stats64(dev, storage); - } - if (ops->ndo_get_stats) { + ops->ndo_get_stats64(dev, storage); + } else if (ops->ndo_get_stats) { netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); - return storage; + } else { + netdev_stats_to_stats64(storage, &dev->stats); + dev_txq_stats_fold(dev, storage); } - netdev_stats_to_stats64(storage, &dev->stats); - dev_txq_stats_fold(dev, storage); + storage->rx_dropped += atomic_long_read(&dev->rx_dropped); return storage; } EXPORT_SYMBOL(dev_get_stats); -static void netdev_init_one_queue(struct net_device *dev, - struct netdev_queue *queue, - void *_unused) +struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { - queue->dev = dev; -} + struct netdev_queue *queue = dev_ingress_queue(dev); -static void netdev_init_queues(struct net_device *dev) -{ - netdev_init_one_queue(dev, &dev->rx_queue, NULL); - netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); - spin_lock_init(&dev->tx_global_lock); +#ifdef CONFIG_NET_CLS_ACT + if (queue) + return queue; + queue = kzalloc(sizeof(*queue), GFP_KERNEL); + if (!queue) + return NULL; + netdev_init_one_queue(dev, queue, NULL); + queue->qdisc = &noop_qdisc; + queue->qdisc_sleeping = &noop_qdisc; + rcu_assign_pointer(dev->ingress_queue, queue); +#endif + return queue; } /** @@ -5404,17 +5528,18 @@ static void netdev_init_queues(struct net_device *dev) struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, void (*setup)(struct net_device *), unsigned int queue_count) { - struct netdev_queue *tx; struct net_device *dev; size_t alloc_size; struct net_device *p; -#ifdef CONFIG_RPS - struct netdev_rx_queue *rx; - int i; -#endif BUG_ON(strlen(name) >= sizeof(dev->name)); + if (queue_count < 1) { + pr_err("alloc_netdev: Unable to allocate device " + "with zero queues.\n"); + return NULL; + } + alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ @@ -5430,55 +5555,31 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, return NULL; } - tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL); - if (!tx) { - printk(KERN_ERR "alloc_netdev: Unable to allocate " - "tx qdiscs.\n"); - goto free_p; - } - -#ifdef CONFIG_RPS - rx = kcalloc(queue_count, sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!rx) { - printk(KERN_ERR "alloc_netdev: Unable to allocate " - "rx queues.\n"); - goto free_tx; - } - - atomic_set(&rx->count, queue_count); - - /* - * Set a pointer to first element in the array which holds the - * reference count. - */ - for (i = 0; i < queue_count; i++) - rx[i].first = rx; -#endif - dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; + dev->pcpu_refcnt = alloc_percpu(int); + if (!dev->pcpu_refcnt) + goto free_p; + if (dev_addr_init(dev)) - goto free_rx; + goto free_pcpu; dev_mc_init(dev); dev_uc_init(dev); dev_net_set(dev, &init_net); - dev->_tx = tx; dev->num_tx_queues = queue_count; dev->real_num_tx_queues = queue_count; #ifdef CONFIG_RPS - dev->_rx = rx; dev->num_rx_queues = queue_count; + dev->real_num_rx_queues = queue_count; #endif dev->gso_max_size = GSO_MAX_SIZE; - netdev_init_queues(dev); - INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); dev->ethtool_ntuple_list.count = 0; INIT_LIST_HEAD(&dev->napi_list); @@ -5489,12 +5590,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, strcpy(dev->name, name); return dev; -free_rx: -#ifdef CONFIG_RPS - kfree(rx); -free_tx: -#endif - kfree(tx); +free_pcpu: + free_percpu(dev->pcpu_refcnt); free_p: kfree(p); return NULL; @@ -5517,6 +5614,8 @@ void free_netdev(struct net_device *dev) kfree(dev->_tx); + kfree(rcu_dereference_raw(dev->ingress_queue)); + /* Flush device addresses */ dev_addr_flush(dev); @@ -5526,6 +5625,9 @@ void free_netdev(struct net_device *dev) list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); + free_percpu(dev->pcpu_refcnt); + dev->pcpu_refcnt = NULL; + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { kfree((char *)dev - dev->padded); @@ -5680,6 +5782,10 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Notify protocols, that we are about to destroy this device. They should clean all the things. + + Note that dev->reg_state stays at NETREG_REGISTERED. + This is wanted because this way 8021q and macvlan know + the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); diff --git a/net/core/dst.c b/net/core/dst.c index 6c41b1f..8abe628 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -168,7 +168,7 @@ void *dst_alloc(struct dst_ops *ops) { struct dst_entry *dst; - if (ops->gc && atomic_read(&ops->entries) > ops->gc_thresh) { + if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { if (ops->gc(ops)) return NULL; } @@ -183,7 +183,7 @@ void *dst_alloc(struct dst_ops *ops) #if RT_CACHE_DEBUG >= 2 atomic_inc(&dst_total); #endif - atomic_inc(&ops->entries); + dst_entries_add(ops, 1); return dst; } EXPORT_SYMBOL(dst_alloc); @@ -228,15 +228,15 @@ again: child = dst->child; dst->hh = NULL; - if (hh && atomic_dec_and_test(&hh->hh_refcnt)) - kfree(hh); + if (hh) + hh_cache_put(hh); if (neigh) { dst->neighbour = NULL; neigh_release(neigh); } - atomic_dec(&dst->ops->entries); + dst_entries_add(dst->ops, -1); if (dst->ops->destroy) dst->ops->destroy(dst); @@ -271,13 +271,40 @@ void dst_release(struct dst_entry *dst) if (dst) { int newrefcnt; - smp_mb__before_atomic_dec(); newrefcnt = atomic_dec_return(&dst->__refcnt); WARN_ON(newrefcnt < 0); + if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) { + dst = dst_destroy(dst); + if (dst) + __dst_free(dst); + } } } EXPORT_SYMBOL(dst_release); +/** + * skb_dst_set_noref - sets skb dst, without a reference + * @skb: buffer + * @dst: dst entry + * + * Sets skb dst, assuming a reference was not taken on dst + * skb_dst_drop() should not dst_release() this dst + */ +void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) +{ + WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + /* If dst not in cache, we must take a reference, because + * dst_release() will destroy dst as soon as its refcount becomes zero + */ + if (unlikely(dst->flags & DST_NOCACHE)) { + dst_hold(dst); + skb_dst_set(skb, dst); + } else { + skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; + } +} +EXPORT_SYMBOL(skb_dst_set_noref); + /* Dirty hack. We did it in 2.2 (in __dst_free), * we have _very_ good reasons not to repeat * this mistake in 2.3, but we have no choice diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 970eb98..956a9f4 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -19,6 +19,7 @@ #include <linux/netdevice.h> #include <linux/bitops.h> #include <linux/uaccess.h> +#include <linux/vmalloc.h> #include <linux/slab.h> /* @@ -131,7 +132,8 @@ EXPORT_SYMBOL(ethtool_op_set_ufo); * NETIF_F_xxx values in include/linux/netdevice.h */ static const u32 flags_dup_features = - (ETH_FLAG_LRO | ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH); + (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | ETH_FLAG_NTUPLE | + ETH_FLAG_RXHASH); u32 ethtool_op_get_flags(struct net_device *dev) { @@ -354,7 +356,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, if (info.cmd == ETHTOOL_GRXCLSRLALL) { if (info.rule_cnt > 0) { if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32)) - rule_buf = kmalloc(info.rule_cnt * sizeof(u32), + rule_buf = kzalloc(info.rule_cnt * sizeof(u32), GFP_USER); if (!rule_buf) return -ENOMEM; @@ -403,7 +405,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index)) return -ENOMEM; full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size; - indir = kmalloc(full_size, GFP_USER); + indir = kzalloc(full_size, GFP_USER); if (!indir) return -ENOMEM; @@ -485,6 +487,38 @@ static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, list->count++; } +/* + * ethtool does not (or did not) set masks for flow parameters that are + * not specified, so if both value and mask are 0 then this must be + * treated as equivalent to a mask with all bits set. Implement that + * here rather than in drivers. + */ +static void rx_ntuple_fix_masks(struct ethtool_rx_ntuple_flow_spec *fs) +{ + struct ethtool_tcpip4_spec *entry = &fs->h_u.tcp_ip4_spec; + struct ethtool_tcpip4_spec *mask = &fs->m_u.tcp_ip4_spec; + + if (fs->flow_type != TCP_V4_FLOW && + fs->flow_type != UDP_V4_FLOW && + fs->flow_type != SCTP_V4_FLOW) + return; + + if (!(entry->ip4src | mask->ip4src)) + mask->ip4src = htonl(0xffffffff); + if (!(entry->ip4dst | mask->ip4dst)) + mask->ip4dst = htonl(0xffffffff); + if (!(entry->psrc | mask->psrc)) + mask->psrc = htons(0xffff); + if (!(entry->pdst | mask->pdst)) + mask->pdst = htons(0xffff); + if (!(entry->tos | mask->tos)) + mask->tos = 0xff; + if (!(fs->vlan_tag | fs->vlan_tag_mask)) + fs->vlan_tag_mask = 0xffff; + if (!(fs->data | fs->data_mask)) + fs->data_mask = 0xffffffffffffffffULL; +} + static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, void __user *useraddr) { @@ -499,6 +533,8 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; + rx_ntuple_fix_masks(&cmd.fs); + /* * Cache filter in dev struct for GET operation only if * the underlying driver doesn't have its own GET operation, and @@ -544,7 +580,7 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) gstrings.len = ret; - data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + data = kzalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); if (!data) return -ENOMEM; @@ -673,19 +709,19 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) break; case IP_USER_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.raw_ip4_spec.ip4src); + fsc->fs.h_u.usr_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.raw_ip4_spec.ip4src); + fsc->fs.m_u.usr_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.raw_ip4_spec.ip4dst); + fsc->fs.h_u.usr_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.raw_ip4_spec.ip4dst); + fsc->fs.m_u.usr_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; break; @@ -781,7 +817,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = kmalloc(reglen, GFP_USER); + regbuf = vmalloc(reglen); if (!regbuf) return -ENOMEM; @@ -796,7 +832,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) ret = 0; out: - kfree(regbuf); + vfree(regbuf); return ret; } @@ -1181,8 +1217,11 @@ static int ethtool_set_gro(struct net_device *dev, char __user *useraddr) return -EFAULT; if (edata.data) { - if (!dev->ethtool_ops->get_rx_csum || - !dev->ethtool_ops->get_rx_csum(dev)) + u32 rxcsum = dev->ethtool_ops->get_rx_csum ? + dev->ethtool_ops->get_rx_csum(dev) : + ethtool_op_get_rx_csum(dev); + + if (!rxcsum) return -EINVAL; dev->features |= NETIF_F_GRO; } else diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 42e84e0..1bc3f25 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -144,7 +144,7 @@ fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) } EXPORT_SYMBOL_GPL(fib_rules_register); -void fib_rules_cleanup_ops(struct fib_rules_ops *ops) +static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) { struct fib_rule *rule, *tmp; @@ -153,7 +153,6 @@ void fib_rules_cleanup_ops(struct fib_rules_ops *ops) fib_rule_put(rule); } } -EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops); static void fib_rules_put_rcu(struct rcu_head *head) { @@ -182,7 +181,8 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->iifindex && (rule->iifindex != fl->iif)) + if (rule->iifindex && (rule->iifindex != fl->iif) && + !(fl->flags & FLOWI_FLAG_MATCH_ANY_IIF)) goto out; if (rule->oifindex && (rule->oifindex != fl->oif)) @@ -225,9 +225,12 @@ jumped: err = ops->action(rule, fl, flags, arg); if (err != -EAGAIN) { - fib_rule_get(rule); - arg->rule = rule; - goto out; + if ((arg->flags & FIB_LOOKUP_NOREF) || + likely(atomic_inc_not_zero(&rule->refcnt))) { + arg->rule = rule; + goto out; + } + break; } } @@ -491,7 +494,6 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) } } - synchronize_rcu(); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).pid); fib_rule_put(rule); diff --git a/net/core/filter.c b/net/core/filter.c index 52b051f..7adf503 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -638,10 +638,9 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return err; } - rcu_read_lock_bh(); - old_fp = rcu_dereference_bh(sk->sk_filter); + old_fp = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); rcu_assign_pointer(sk->sk_filter, fp); - rcu_read_unlock_bh(); if (old_fp) sk_filter_delayed_uncharge(sk, old_fp); @@ -654,14 +653,13 @@ int sk_detach_filter(struct sock *sk) int ret = -ENOENT; struct sk_filter *filter; - rcu_read_lock_bh(); - filter = rcu_dereference_bh(sk->sk_filter); + filter = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); if (filter) { rcu_assign_pointer(sk->sk_filter, NULL); sk_filter_delayed_uncharge(sk, filter); ret = 0; } - rcu_read_unlock_bh(); return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); diff --git a/net/core/flow.c b/net/core/flow.c index b143b86..127c8a7 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -176,8 +176,8 @@ static u32 flow_hash_code(struct flow_cache *fc, { u32 *k = (u32 *) key; - return (jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd) - & (flow_cache_hash_size(fc) - 1)); + return jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd) + & (flow_cache_hash_size(fc) - 1); } typedef unsigned long flow_compare_t; diff --git a/net/core/iovec.c b/net/core/iovec.c index f4657c2..72aceb1 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -35,9 +35,10 @@ * in any case. */ -int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) +long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) { - int size, err, ct; + int size, ct; + long err; if (m->msg_namelen) { if (mode == VERIFY_READ) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a4e0a74..8cc8f9a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -122,7 +122,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return (base ? (net_random() % base) + (base >> 1) : 0); + return base ? (net_random() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -131,15 +131,20 @@ static int neigh_forced_gc(struct neigh_table *tbl) { int shrunk = 0; int i; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); write_lock_bh(&tbl->lock); - for (i = 0; i <= tbl->hash_mask; i++) { - struct neighbour *n, **np; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + for (i = 0; i <= nht->hash_mask; i++) { + struct neighbour *n; + struct neighbour __rcu **np; - np = &tbl->hash_buckets[i]; - while ((n = *np) != NULL) { + np = &nht->hash_buckets[i]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { /* Neighbour record may be discarded if: * - nobody refers to it. * - it is not permanent @@ -147,7 +152,9 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if (atomic_read(&n->refcnt) == 1 && !(n->nud_state & NUD_PERMANENT)) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); n->dead = 1; shrunk = 1; write_unlock(&n->lock); @@ -199,16 +206,24 @@ static void pneigh_queue_purge(struct sk_buff_head *list) static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) { int i; + struct neigh_hash_table *nht; - for (i = 0; i <= tbl->hash_mask; i++) { - struct neighbour *n, **np = &tbl->hash_buckets[i]; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); - while ((n = *np) != NULL) { + for (i = 0; i <= nht->hash_mask; i++) { + struct neighbour *n; + struct neighbour __rcu **np = &nht->hash_buckets[i]; + + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { if (dev && n->dev != dev) { np = &n->next; continue; } - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); write_lock(&n->lock); neigh_del_timer(n); n->dead = 1; @@ -279,6 +294,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl) skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); + seqlock_init(&n->ha_lock); n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; @@ -297,64 +313,86 @@ out_entries: goto out; } -static struct neighbour **neigh_hash_alloc(unsigned int entries) +static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) { - unsigned long size = entries * sizeof(struct neighbour *); - struct neighbour **ret; + size_t size = entries * sizeof(struct neighbour *); + struct neigh_hash_table *ret; + struct neighbour **buckets; - if (size <= PAGE_SIZE) { - ret = kzalloc(size, GFP_ATOMIC); - } else { - ret = (struct neighbour **) - __get_free_pages(GFP_ATOMIC|__GFP_ZERO, get_order(size)); + ret = kmalloc(sizeof(*ret), GFP_ATOMIC); + if (!ret) + return NULL; + if (size <= PAGE_SIZE) + buckets = kzalloc(size, GFP_ATOMIC); + else + buckets = (struct neighbour **) + __get_free_pages(GFP_ATOMIC | __GFP_ZERO, + get_order(size)); + if (!buckets) { + kfree(ret); + return NULL; } + rcu_assign_pointer(ret->hash_buckets, buckets); + ret->hash_mask = entries - 1; + get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd)); return ret; } -static void neigh_hash_free(struct neighbour **hash, unsigned int entries) +static void neigh_hash_free_rcu(struct rcu_head *head) { - unsigned long size = entries * sizeof(struct neighbour *); + struct neigh_hash_table *nht = container_of(head, + struct neigh_hash_table, + rcu); + size_t size = (nht->hash_mask + 1) * sizeof(struct neighbour *); + struct neighbour **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) - kfree(hash); + kfree(buckets); else - free_pages((unsigned long)hash, get_order(size)); + free_pages((unsigned long)buckets, get_order(size)); + kfree(nht); } -static void neigh_hash_grow(struct neigh_table *tbl, unsigned long new_entries) +static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, + unsigned long new_entries) { - struct neighbour **new_hash, **old_hash; - unsigned int i, new_hash_mask, old_entries; + unsigned int i, hash; + struct neigh_hash_table *new_nht, *old_nht; NEIGH_CACHE_STAT_INC(tbl, hash_grows); BUG_ON(!is_power_of_2(new_entries)); - new_hash = neigh_hash_alloc(new_entries); - if (!new_hash) - return; - - old_entries = tbl->hash_mask + 1; - new_hash_mask = new_entries - 1; - old_hash = tbl->hash_buckets; + old_nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + new_nht = neigh_hash_alloc(new_entries); + if (!new_nht) + return old_nht; - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); - for (i = 0; i < old_entries; i++) { + for (i = 0; i <= old_nht->hash_mask; i++) { struct neighbour *n, *next; - for (n = old_hash[i]; n; n = next) { - unsigned int hash_val = tbl->hash(n->primary_key, n->dev); - - hash_val &= new_hash_mask; - next = n->next; - - n->next = new_hash[hash_val]; - new_hash[hash_val] = n; + for (n = rcu_dereference_protected(old_nht->hash_buckets[i], + lockdep_is_held(&tbl->lock)); + n != NULL; + n = next) { + hash = tbl->hash(n->primary_key, n->dev, + new_nht->hash_rnd); + + hash &= new_nht->hash_mask; + next = rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock)); + + rcu_assign_pointer(n->next, + rcu_dereference_protected( + new_nht->hash_buckets[hash], + lockdep_is_held(&tbl->lock))); + rcu_assign_pointer(new_nht->hash_buckets[hash], n); } } - tbl->hash_buckets = new_hash; - tbl->hash_mask = new_hash_mask; - neigh_hash_free(old_hash, old_entries); + rcu_assign_pointer(tbl->nht, new_nht); + call_rcu(&old_nht->rcu, neigh_hash_free_rcu); + return new_nht; } struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, @@ -363,19 +401,26 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct neighbour *n; int key_len = tbl->key_len; u32 hash_val; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, lookups); - read_lock_bh(&tbl->lock); - hash_val = tbl->hash(pkey, dev); - for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask; + + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) { - neigh_hold(n); + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); break; } } - read_unlock_bh(&tbl->lock); + + rcu_read_unlock_bh(); return n; } EXPORT_SYMBOL(neigh_lookup); @@ -386,20 +431,27 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, struct neighbour *n; int key_len = tbl->key_len; u32 hash_val; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, lookups); - read_lock_bh(&tbl->lock); - hash_val = tbl->hash(pkey, NULL); - for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) & nht->hash_mask; + + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { if (!memcmp(n->primary_key, pkey, key_len) && net_eq(dev_net(n->dev), net)) { - neigh_hold(n); + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); break; } } - read_unlock_bh(&tbl->lock); + + rcu_read_unlock_bh(); return n; } EXPORT_SYMBOL(neigh_lookup_nodev); @@ -411,6 +463,7 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, int key_len = tbl->key_len; int error; struct neighbour *n1, *rc, *n = neigh_alloc(tbl); + struct neigh_hash_table *nht; if (!n) { rc = ERR_PTR(-ENOBUFS); @@ -437,18 +490,24 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, n->confirmed = jiffies - (n->parms->base_reachable_time << 1); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) > (tbl->hash_mask + 1)) - neigh_hash_grow(tbl, (tbl->hash_mask + 1) << 1); + if (atomic_read(&tbl->entries) > (nht->hash_mask + 1)) + nht = neigh_hash_grow(tbl, (nht->hash_mask + 1) << 1); - hash_val = tbl->hash(pkey, dev) & tbl->hash_mask; + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask; if (n->parms->dead) { rc = ERR_PTR(-EINVAL); goto out_tbl_unlock; } - for (n1 = tbl->hash_buckets[hash_val]; n1; n1 = n1->next) { + for (n1 = rcu_dereference_protected(nht->hash_buckets[hash_val], + lockdep_is_held(&tbl->lock)); + n1 != NULL; + n1 = rcu_dereference_protected(n1->next, + lockdep_is_held(&tbl->lock))) { if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) { neigh_hold(n1); rc = n1; @@ -456,10 +515,12 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, } } - n->next = tbl->hash_buckets[hash_val]; - tbl->hash_buckets[hash_val] = n; n->dead = 0; neigh_hold(n); + rcu_assign_pointer(n->next, + rcu_dereference_protected(nht->hash_buckets[hash_val], + lockdep_is_held(&tbl->lock))); + rcu_assign_pointer(nht->hash_buckets[hash_val], n); write_unlock_bh(&tbl->lock); NEIGH_PRINTK2("neigh %p is created.\n", n); rc = n; @@ -616,6 +677,12 @@ static inline void neigh_parms_put(struct neigh_parms *parms) neigh_parms_destroy(parms); } +static void neigh_destroy_rcu(struct rcu_head *head) +{ + struct neighbour *neigh = container_of(head, struct neighbour, rcu); + + kmem_cache_free(neigh->tbl->kmem_cachep, neigh); +} /* * neighbour must already be out of the table; * @@ -643,8 +710,7 @@ void neigh_destroy(struct neighbour *neigh) write_seqlock_bh(&hh->hh_lock); hh->hh_output = neigh_blackhole; write_sequnlock_bh(&hh->hh_lock); - if (atomic_dec_and_test(&hh->hh_refcnt)) - kfree(hh); + hh_cache_put(hh); } skb_queue_purge(&neigh->arp_queue); @@ -655,7 +721,7 @@ void neigh_destroy(struct neighbour *neigh) NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh); atomic_dec(&neigh->tbl->entries); - kmem_cache_free(neigh->tbl->kmem_cachep, neigh); + call_rcu(&neigh->rcu, neigh_destroy_rcu); } EXPORT_SYMBOL(neigh_destroy); @@ -696,12 +762,16 @@ static void neigh_connect(struct neighbour *neigh) static void neigh_periodic_work(struct work_struct *work) { struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work); - struct neighbour *n, **np; + struct neighbour *n; + struct neighbour __rcu **np; unsigned int i; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); /* * periodically recompute ReachableTime from random function @@ -715,10 +785,11 @@ static void neigh_periodic_work(struct work_struct *work) neigh_rand_reach_time(p->base_reachable_time); } - for (i = 0 ; i <= tbl->hash_mask; i++) { - np = &tbl->hash_buckets[i]; + for (i = 0 ; i <= nht->hash_mask; i++) { + np = &nht->hash_buckets[i]; - while ((n = *np) != NULL) { + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { unsigned int state; write_lock(&n->lock); @@ -766,9 +837,9 @@ next_elt: static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - return (n->nud_state & NUD_PROBE ? + return (n->nud_state & NUD_PROBE) ? p->ucast_probes : - p->ucast_probes + p->app_probes + p->mcast_probes); + p->ucast_probes + p->app_probes + p->mcast_probes; } static void neigh_invalidate(struct neighbour *neigh) @@ -945,7 +1016,7 @@ out_unlock_bh: } EXPORT_SYMBOL(__neigh_event_send); -static void neigh_update_hhs(struct neighbour *neigh) +static void neigh_update_hhs(const struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) @@ -1081,7 +1152,9 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } if (lladdr != neigh->ha) { + write_seqlock(&neigh->ha_lock); memcpy(&neigh->ha, lladdr, dev->addr_len); + write_sequnlock(&neigh->ha_lock); neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - @@ -1139,44 +1212,73 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, } EXPORT_SYMBOL(neigh_event_ns); +static inline bool neigh_hh_lookup(struct neighbour *n, struct dst_entry *dst, + __be16 protocol) +{ + struct hh_cache *hh; + + smp_rmb(); /* paired with smp_wmb() in neigh_hh_init() */ + for (hh = n->hh; hh; hh = hh->hh_next) { + if (hh->hh_type == protocol) { + atomic_inc(&hh->hh_refcnt); + if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL)) + hh_cache_put(hh); + return true; + } + } + return false; +} + +/* called with read_lock_bh(&n->lock); */ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, __be16 protocol) { struct hh_cache *hh; struct net_device *dev = dst->dev; - for (hh = n->hh; hh; hh = hh->hh_next) - if (hh->hh_type == protocol) - break; + if (likely(neigh_hh_lookup(n, dst, protocol))) + return; - if (!hh && (hh = kzalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) { - seqlock_init(&hh->hh_lock); - hh->hh_type = protocol; - atomic_set(&hh->hh_refcnt, 0); - hh->hh_next = NULL; + /* slow path */ + hh = kzalloc(sizeof(*hh), GFP_ATOMIC); + if (!hh) + return; - if (dev->header_ops->cache(n, hh)) { - kfree(hh); - hh = NULL; - } else { - atomic_inc(&hh->hh_refcnt); - hh->hh_next = n->hh; - n->hh = hh; - if (n->nud_state & NUD_CONNECTED) - hh->hh_output = n->ops->hh_output; - else - hh->hh_output = n->ops->output; - } + seqlock_init(&hh->hh_lock); + hh->hh_type = protocol; + atomic_set(&hh->hh_refcnt, 2); + + if (dev->header_ops->cache(n, hh)) { + kfree(hh); + return; } - if (hh) { - atomic_inc(&hh->hh_refcnt); - dst->hh = hh; + + write_lock_bh(&n->lock); + + /* must check if another thread already did the insert */ + if (neigh_hh_lookup(n, dst, protocol)) { + kfree(hh); + goto end; } + + if (n->nud_state & NUD_CONNECTED) + hh->hh_output = n->ops->hh_output; + else + hh->hh_output = n->ops->output; + + hh->hh_next = n->hh; + smp_wmb(); /* paired with smp_rmb() in neigh_hh_lookup() */ + n->hh = hh; + + if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL)) + hh_cache_put(hh); +end: + write_unlock_bh(&n->lock); } /* This function can be used in contexts, where only old dev_queue_xmit - worked, f.e. if you want to override normal output path (eql, shaper), - but resolution is not made yet. + * worked, f.e. if you want to override normal output path (eql, shaper), + * but resolution is not made yet. */ int neigh_compat_output(struct sk_buff *skb) @@ -1210,19 +1312,19 @@ int neigh_resolve_output(struct sk_buff *skb) if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; - if (dev->header_ops->cache && !dst->hh) { - write_lock_bh(&neigh->lock); - if (!dst->hh) - neigh_hh_init(neigh, dst, dst->ops->protocol); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); - write_unlock_bh(&neigh->lock); - } else { - read_lock_bh(&neigh->lock); + unsigned int seq; + + if (dev->header_ops->cache && + !dst->hh && + !(dst->flags & DST_NOCACHE)) + neigh_hh_init(neigh, dst, dst->ops->protocol); + + do { + seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); - read_unlock_bh(&neigh->lock); - } + } while (read_seqretry(&neigh->ha_lock, seq)); + if (err >= 0) rc = neigh->ops->queue_xmit(skb); else @@ -1248,13 +1350,16 @@ int neigh_connected_output(struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; + unsigned int seq; __skb_pull(skb, skb_network_offset(skb)); - read_lock_bh(&neigh->lock); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); - read_unlock_bh(&neigh->lock); + do { + seq = read_seqbegin(&neigh->ha_lock); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + neigh->ha, NULL, skb->len); + } while (read_seqretry(&neigh->ha_lock, seq)); + if (err >= 0) err = neigh->ops->queue_xmit(skb); else { @@ -1436,17 +1541,14 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) panic("cannot create neighbour proc dir entry"); #endif - tbl->hash_mask = 1; - tbl->hash_buckets = neigh_hash_alloc(tbl->hash_mask + 1); + tbl->nht = neigh_hash_alloc(8); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); - if (!tbl->hash_buckets || !tbl->phash_buckets) + if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); - rwlock_init(&tbl->lock); INIT_DELAYED_WORK_DEFERRABLE(&tbl->gc_work, neigh_periodic_work); schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); @@ -1486,8 +1588,7 @@ int neigh_table_clear(struct neigh_table *tbl) struct neigh_table **tp; /* It is not clean... Fix it to unload IPv6 module safely */ - cancel_delayed_work(&tbl->gc_work); - flush_scheduled_work(); + cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); neigh_ifdown(tbl, NULL); @@ -1502,8 +1603,8 @@ int neigh_table_clear(struct neigh_table *tbl) } write_unlock(&neigh_tbl_lock); - neigh_hash_free(tbl->hash_buckets, tbl->hash_mask + 1); - tbl->hash_buckets = NULL; + call_rcu(&tbl->nht->rcu, neigh_hash_free_rcu); + tbl->nht = NULL; kfree(tbl->phash_buckets); tbl->phash_buckets = NULL; @@ -1529,6 +1630,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct net_device *dev = NULL; int err = -EINVAL; + ASSERT_RTNL(); if (nlmsg_len(nlh) < sizeof(*ndm)) goto out; @@ -1538,7 +1640,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { - dev = dev_get_by_index(net, ndm->ndm_ifindex); + dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; @@ -1554,34 +1656,31 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) read_unlock(&neigh_tbl_lock); if (nla_len(dst_attr) < tbl->key_len) - goto out_dev_put; + goto out; if (ndm->ndm_flags & NTF_PROXY) { err = pneigh_delete(tbl, net, nla_data(dst_attr), dev); - goto out_dev_put; + goto out; } if (dev == NULL) - goto out_dev_put; + goto out; neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); if (neigh == NULL) { err = -ENOENT; - goto out_dev_put; + goto out; } err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN); neigh_release(neigh); - goto out_dev_put; + goto out; } read_unlock(&neigh_tbl_lock); err = -EAFNOSUPPORT; -out_dev_put: - if (dev) - dev_put(dev); out: return err; } @@ -1595,6 +1694,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct net_device *dev = NULL; int err; + ASSERT_RTNL(); err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); if (err < 0) goto out; @@ -1605,14 +1705,14 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { - dev = dev_get_by_index(net, ndm->ndm_ifindex); + dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; } if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) - goto out_dev_put; + goto out; } read_lock(&neigh_tbl_lock); @@ -1626,7 +1726,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) read_unlock(&neigh_tbl_lock); if (nla_len(tb[NDA_DST]) < tbl->key_len) - goto out_dev_put; + goto out; dst = nla_data(tb[NDA_DST]); lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; @@ -1639,29 +1739,29 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) pn->flags = ndm->ndm_flags; err = 0; } - goto out_dev_put; + goto out; } if (dev == NULL) - goto out_dev_put; + goto out; neigh = neigh_lookup(tbl, dst, dev); if (neigh == NULL) { if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { err = -ENOENT; - goto out_dev_put; + goto out; } neigh = __neigh_lookup_errno(tbl, dst, dev); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); - goto out_dev_put; + goto out; } } else { if (nlh->nlmsg_flags & NLM_F_EXCL) { err = -EEXIST; neigh_release(neigh); - goto out_dev_put; + goto out; } if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) @@ -1674,15 +1774,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) } else err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); neigh_release(neigh); - goto out_dev_put; + goto out; } read_unlock(&neigh_tbl_lock); err = -EAFNOSUPPORT; - -out_dev_put: - if (dev) - dev_put(dev); out: return err; } @@ -1748,18 +1844,22 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, unsigned long now = jiffies; unsigned int flush_delta = now - tbl->last_flush; unsigned int rand_delta = now - tbl->last_rand; - + struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, .ndtc_entry_size = tbl->entry_size, .ndtc_entries = atomic_read(&tbl->entries), .ndtc_last_flush = jiffies_to_msecs(flush_delta), .ndtc_last_rand = jiffies_to_msecs(rand_delta), - .ndtc_hash_rnd = tbl->hash_rnd, - .ndtc_hash_mask = tbl->hash_mask, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + ndc.ndtc_hash_rnd = nht->hash_rnd; + ndc.ndtc_hash_mask = nht->hash_mask; + rcu_read_unlock_bh(); + NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); } @@ -2056,10 +2156,14 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, read_lock_bh(&neigh->lock); ndm->ndm_state = neigh->nud_state; - if ((neigh->nud_state & NUD_VALID) && - nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, neigh->ha) < 0) { - read_unlock_bh(&neigh->lock); - goto nla_put_failure; + if (neigh->nud_state & NUD_VALID) { + char haddr[MAX_ADDR_LEN]; + + neigh_ha_snapshot(haddr, neigh, neigh->dev); + if (nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, haddr) < 0) { + read_unlock_bh(&neigh->lock); + goto nla_put_failure; + } } ci.ndm_used = jiffies_to_clock_t(now - neigh->used); @@ -2087,18 +2191,23 @@ static void neigh_update_notify(struct neighbour *neigh) static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { - struct net * net = sock_net(skb->sk); + struct net *net = sock_net(skb->sk); struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; + struct neigh_hash_table *nht; - read_lock_bh(&tbl->lock); - for (h = 0; h <= tbl->hash_mask; h++) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + + for (h = 0; h <= nht->hash_mask; h++) { if (h < s_h) continue; if (h > s_h) s_idx = 0; - for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { + for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; + n != NULL; + n = rcu_dereference_bh(n->next)) { if (!net_eq(dev_net(n->dev), net)) continue; if (idx < s_idx) @@ -2107,17 +2216,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI) <= 0) { - read_unlock_bh(&tbl->lock); rc = -1; goto out; } - next: +next: idx++; } } - read_unlock_bh(&tbl->lock); rc = skb->len; out: + rcu_read_unlock_bh(); cb->args[1] = h; cb->args[2] = idx; return rc; @@ -2150,15 +2258,22 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie) { int chain; + struct neigh_hash_table *nht; - read_lock_bh(&tbl->lock); - for (chain = 0; chain <= tbl->hash_mask; chain++) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + + read_lock(&tbl->lock); /* avoid resizes */ + for (chain = 0; chain <= nht->hash_mask; chain++) { struct neighbour *n; - for (n = tbl->hash_buckets[chain]; n; n = n->next) + for (n = rcu_dereference_bh(nht->hash_buckets[chain]); + n != NULL; + n = rcu_dereference_bh(n->next)) cb(n, cookie); } - read_unlock_bh(&tbl->lock); + read_unlock(&tbl->lock); + rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_for_each); @@ -2167,18 +2282,25 @@ void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)) { int chain; + struct neigh_hash_table *nht; - for (chain = 0; chain <= tbl->hash_mask; chain++) { - struct neighbour *n, **np; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + for (chain = 0; chain <= nht->hash_mask; chain++) { + struct neighbour *n; + struct neighbour __rcu **np; - np = &tbl->hash_buckets[chain]; - while ((n = *np) != NULL) { + np = &nht->hash_buckets[chain]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { int release; write_lock(&n->lock); release = cb(n); if (release) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); n->dead = 1; } else np = &n->next; @@ -2196,13 +2318,13 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); - struct neigh_table *tbl = state->tbl; + struct neigh_hash_table *nht = state->nht; struct neighbour *n = NULL; int bucket = state->bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; - for (bucket = 0; bucket <= tbl->hash_mask; bucket++) { - n = tbl->hash_buckets[bucket]; + for (bucket = 0; bucket <= nht->hash_mask; bucket++) { + n = rcu_dereference_bh(nht->hash_buckets[bucket]); while (n) { if (!net_eq(dev_net(n->dev), net)) @@ -2219,8 +2341,8 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) break; if (n->nud_state & ~NUD_NOARP) break; - next: - n = n->next; +next: + n = rcu_dereference_bh(n->next); } if (n) @@ -2237,14 +2359,14 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); - struct neigh_table *tbl = state->tbl; + struct neigh_hash_table *nht = state->nht; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) return n; } - n = n->next; + n = rcu_dereference_bh(n->next); while (1) { while (n) { @@ -2261,17 +2383,17 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, if (n->nud_state & ~NUD_NOARP) break; - next: - n = n->next; +next: + n = rcu_dereference_bh(n->next); } if (n) break; - if (++state->bucket > tbl->hash_mask) + if (++state->bucket > nht->hash_mask) break; - n = tbl->hash_buckets[state->bucket]; + n = rcu_dereference_bh(nht->hash_buckets[state->bucket]); } if (n && pos) @@ -2369,7 +2491,7 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos) } void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags) - __acquires(tbl->lock) + __acquires(rcu_bh) { struct neigh_seq_state *state = seq->private; @@ -2377,7 +2499,8 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl state->bucket = 0; state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH); - read_lock_bh(&tbl->lock); + rcu_read_lock_bh(); + state->nht = rcu_dereference_bh(tbl->nht); return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } @@ -2411,12 +2534,9 @@ out: EXPORT_SYMBOL(neigh_seq_next); void neigh_seq_stop(struct seq_file *seq, void *v) - __releases(tbl->lock) + __releases(rcu_bh) { - struct neigh_seq_state *state = seq->private; - struct neigh_table *tbl = state->tbl; - - read_unlock_bh(&tbl->lock); + rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_seq_stop); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 76485a3..b143173 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -726,6 +726,7 @@ static struct kobj_type rx_queue_ktype = { static int rx_queue_add_kobject(struct net_device *net, int index) { struct netdev_rx_queue *queue = net->_rx + index; + struct netdev_rx_queue *first = queue->first; struct kobject *kobj = &queue->kobj; int error = 0; @@ -738,38 +739,43 @@ static int rx_queue_add_kobject(struct net_device *net, int index) } kobject_uevent(kobj, KOBJ_ADD); + atomic_inc(&first->count); return error; } -static int rx_queue_register_kobjects(struct net_device *net) +int +net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { int i; int error = 0; - net->queues_kset = kset_create_and_add("queues", - NULL, &net->dev.kobj); - if (!net->queues_kset) - return -ENOMEM; - for (i = 0; i < net->num_rx_queues; i++) { + for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(net, i); - if (error) + if (error) { + new_num = old_num; break; + } } - if (error) - while (--i >= 0) - kobject_put(&net->_rx[i].kobj); + while (--i >= new_num) + kobject_put(&net->_rx[i].kobj); return error; } -static void rx_queue_remove_kobjects(struct net_device *net) +static int rx_queue_register_kobjects(struct net_device *net) { - int i; + net->queues_kset = kset_create_and_add("queues", + NULL, &net->dev.kobj); + if (!net->queues_kset) + return -ENOMEM; + return net_rx_queue_update_kobjects(net, 0, net->real_num_rx_queues); +} - for (i = 0; i < net->num_rx_queues; i++) - kobject_put(&net->_rx[i].kobj); +static void rx_queue_remove_kobjects(struct net_device *net) +{ + net_rx_queue_update_kobjects(net, net->real_num_rx_queues, 0); kset_unregister(net->queues_kset); } #endif /* CONFIG_RPS */ diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 805555e..778e157 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -4,4 +4,8 @@ int netdev_kobject_init(void); int netdev_register_kobject(struct net_device *); void netdev_unregister_kobject(struct net_device *); +#ifdef CONFIG_RPS +int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); +#endif + #endif diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 537e01a..4e98ffa 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -288,11 +288,11 @@ static int netpoll_owner_active(struct net_device *dev) return 0; } -void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) +void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, + struct net_device *dev) { int status = NETDEV_TX_BUSY; unsigned long tries; - struct net_device *dev = np->dev; const struct net_device_ops *ops = dev->netdev_ops; /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo = np->dev->npinfo; @@ -346,7 +346,7 @@ void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) schedule_delayed_work(&npinfo->tx_work,0); } } -EXPORT_SYMBOL(netpoll_send_skb); +EXPORT_SYMBOL(netpoll_send_skb_on_dev); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 386c228..2c0df0f 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -729,16 +729,14 @@ static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, *num = 0; for (; i < maxlen; i++) { + int value; char c; *num <<= 4; if (get_user(c, &user_buffer[i])) return -EFAULT; - if ((c >= '0') && (c <= '9')) - *num |= c - '0'; - else if ((c >= 'a') && (c <= 'f')) - *num |= c - 'a' + 10; - else if ((c >= 'A') && (c <= 'F')) - *num |= c - 'A' + 10; + value = hex_to_bin(c); + if (value >= 0) + *num |= value; else break; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b2a718d..8121268 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -299,14 +299,6 @@ static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) unregister_netdevice_many(&list_kill); } -void rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) -{ - rtnl_lock(); - __rtnl_kill_links(net, ops); - rtnl_unlock(); -} -EXPORT_SYMBOL_GPL(rtnl_kill_links); - /** * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 752c197..4e8b82e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -247,10 +247,9 @@ EXPORT_SYMBOL(__alloc_skb); struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask) { - int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1; struct sk_buff *skb; - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node); + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; @@ -259,16 +258,6 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, } EXPORT_SYMBOL(__netdev_alloc_skb); -struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask) -{ - int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1; - struct page *page; - - page = alloc_pages_node(node, gfp_mask, 0); - return page; -} -EXPORT_SYMBOL(__netdev_alloc_page); - void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size) { diff --git a/net/core/sock.c b/net/core/sock.c index f3a06c4..42365de 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1351,9 +1351,9 @@ int sock_i_uid(struct sock *sk) { int uid; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); @@ -1362,9 +1362,9 @@ unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(sock_i_ino); diff --git a/net/core/stream.c b/net/core/stream.c index d959e0f..f5df85d 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -141,10 +141,10 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, !sk->sk_err && - !(sk->sk_shutdown & SEND_SHUTDOWN) && - sk_stream_memory_free(sk) && - vm_wait); + sk_wait_event(sk, ¤t_timeo, sk->sk_err || + (sk->sk_shutdown & SEND_SHUTDOWN) || + (sk_stream_memory_free(sk) && + !vm_wait)); sk->sk_write_pending--; if (vm_wait) { diff --git a/net/core/utils.c b/net/core/utils.c index f418544..5fea0ab 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -75,7 +75,7 @@ __be32 in_aton(const char *str) str++; } } - return(htonl(l)); + return htonl(l); } EXPORT_SYMBOL(in_aton); @@ -92,18 +92,19 @@ EXPORT_SYMBOL(in_aton); static inline int xdigit2bin(char c, int delim) { + int val; + if (c == delim || c == '\0') return IN6PTON_DELIM; if (c == ':') return IN6PTON_COLON_MASK; if (c == '.') return IN6PTON_DOT; - if (c >= '0' && c <= '9') - return (IN6PTON_XDIGIT | IN6PTON_DIGIT| (c - '0')); - if (c >= 'a' && c <= 'f') - return (IN6PTON_XDIGIT | (c - 'a' + 10)); - if (c >= 'A' && c <= 'F') - return (IN6PTON_XDIGIT | (c - 'A' + 10)); + + val = hex_to_bin(c); + if (val >= 0) + return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); + if (delim == -1) return IN6PTON_DELIM; return IN6PTON_UNKNOWN; diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6df6f8a..117fb09 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -62,22 +62,18 @@ struct ccid_operations { void (*ccid_hc_tx_exit)(struct sock *sk); void (*ccid_hc_rx_packet_recv)(struct sock *sk, struct sk_buff *skb); - int (*ccid_hc_rx_parse_options)(struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value); + int (*ccid_hc_rx_parse_options)(struct sock *sk, u8 pkt, + u8 opt, u8 *val, u8 len); int (*ccid_hc_rx_insert_options)(struct sock *sk, struct sk_buff *skb); void (*ccid_hc_tx_packet_recv)(struct sock *sk, struct sk_buff *skb); - int (*ccid_hc_tx_parse_options)(struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value); + int (*ccid_hc_tx_parse_options)(struct sock *sk, u8 pkt, + u8 opt, u8 *val, u8 len); int (*ccid_hc_tx_send_packet)(struct sock *sk, struct sk_buff *skb); void (*ccid_hc_tx_packet_sent)(struct sock *sk, - int more, unsigned int len); + unsigned int len); void (*ccid_hc_rx_get_info)(struct sock *sk, struct tcp_info *info); void (*ccid_hc_tx_get_info)(struct sock *sk, @@ -148,10 +144,10 @@ static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk, } static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk, - int more, unsigned int len) + unsigned int len) { if (ccid->ccid_ops->ccid_hc_tx_packet_sent != NULL) - ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, more, len); + ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, len); } static inline void ccid_hc_rx_packet_recv(struct ccid *ccid, struct sock *sk, @@ -168,27 +164,31 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, ccid->ccid_ops->ccid_hc_tx_packet_recv(sk, skb); } +/** + * ccid_hc_tx_parse_options - Parse CCID-specific options sent by the receiver + * @pkt: type of packet that @opt appears on (RFC 4340, 5.1) + * @opt: the CCID-specific option type (RFC 4340, 5.8 and 10.3) + * @val: value of @opt + * @len: length of @val in bytes + */ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value) + u8 pkt, u8 opt, u8 *val, u8 len) { - int rc = 0; - if (ccid->ccid_ops->ccid_hc_tx_parse_options != NULL) - rc = ccid->ccid_ops->ccid_hc_tx_parse_options(sk, option, len, idx, - value); - return rc; + if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + return 0; + return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } +/** + * ccid_hc_rx_parse_options - Parse CCID-specific options sent by the sender + * Arguments are analogous to ccid_hc_tx_parse_options() + */ static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value) + u8 pkt, u8 opt, u8 *val, u8 len) { - int rc = 0; - if (ccid->ccid_ops->ccid_hc_rx_parse_options != NULL) - rc = ccid->ccid_ops->ccid_hc_rx_parse_options(sk, option, len, idx, value); - return rc; + if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + return 0; + return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } static inline int ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk, diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index dc18172..d850e29 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -151,7 +151,7 @@ out: sock_put(sk); } -static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) +static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 278e170..3060a60 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -54,7 +54,6 @@ static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) [TFRC_SSTATE_NO_SENT] = "NO_SENT", [TFRC_SSTATE_NO_FBACK] = "NO_FBACK", [TFRC_SSTATE_FBACK] = "FBACK", - [TFRC_SSTATE_TERM] = "TERM", }; return ccid3_state_names[state]; @@ -91,19 +90,16 @@ static inline u64 rfc3390_initial_rate(struct sock *sk) return scaled_div(w_init << 6, hc->tx_rtt); } -/* - * Recalculate t_ipi and delta (should be called whenever X changes) +/** + * ccid3_update_send_interval - Calculate new t_ipi = s / X_inst + * This respects the granularity of X_inst (64 * bytes/second). */ static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc) { - /* Calculate new t_ipi = s / X_inst (X_inst is in 64 * bytes/second) */ hc->tx_t_ipi = scaled_div32(((u64)hc->tx_s) << 6, hc->tx_x); - /* Calculate new delta by delta = min(t_ipi / 2, t_gran / 2) */ - hc->tx_delta = min_t(u32, hc->tx_t_ipi / 2, TFRC_OPSYS_HALF_TIME_GRAN); - - ccid3_pr_debug("t_ipi=%u, delta=%u, s=%u, X=%u\n", hc->tx_t_ipi, - hc->tx_delta, hc->tx_s, (unsigned)(hc->tx_x >> 6)); + ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hc->tx_t_ipi, + hc->tx_s, (unsigned)(hc->tx_x >> 6)); } static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) @@ -211,10 +207,13 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data) ccid3_pr_debug("%s(%p, state=%s) - entry\n", dccp_role(sk), sk, ccid3_tx_state_name(hc->tx_state)); + /* Ignore and do not restart after leaving the established state */ + if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN)) + goto out; + + /* Reset feedback state to "no feedback received" */ if (hc->tx_state == TFRC_SSTATE_FBACK) ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); - else if (hc->tx_state != TFRC_SSTATE_NO_FBACK) - goto out; /* * Determine new allowed sending rate X as per draft rfc3448bis-00, 4.4 @@ -290,8 +289,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) if (unlikely(skb->len == 0)) return -EBADMSG; - switch (hc->tx_state) { - case TFRC_SSTATE_NO_SENT: + if (hc->tx_state == TFRC_SSTATE_NO_SENT) { sk_reset_timer(sk, &hc->tx_no_feedback_timer, (jiffies + usecs_to_jiffies(TFRC_INITIAL_TIMEOUT))); hc->tx_last_win_count = 0; @@ -326,27 +324,22 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) ccid3_update_send_interval(hc); ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); - break; - case TFRC_SSTATE_NO_FBACK: - case TFRC_SSTATE_FBACK: + + } else { delay = ktime_us_delta(hc->tx_t_nom, now); ccid3_pr_debug("delay=%ld\n", (long)delay); /* - * Scheduling of packet transmissions [RFC 3448, 4.6] + * Scheduling of packet transmissions (RFC 5348, 8.3) * * if (t_now > t_nom - delta) * // send the packet now * else * // send the packet in (t_nom - t_now) milliseconds. */ - if (delay - (s64)hc->tx_delta >= 1000) - return (u32)delay / 1000L; + if (delay >= TFRC_T_DELTA) + return (u32)delay / USEC_PER_MSEC; ccid3_hc_tx_update_win_count(hc, now); - break; - case TFRC_SSTATE_TERM: - DCCP_BUG("%s(%p) - Illegal state TERM", dccp_role(sk), sk); - return -EINVAL; } /* prepare to send now (add options etc.) */ @@ -358,8 +351,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) return 0; } -static void ccid3_hc_tx_packet_sent(struct sock *sk, int more, - unsigned int len) +static void ccid3_hc_tx_packet_sent(struct sock *sk, unsigned int len) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); @@ -372,47 +364,34 @@ static void ccid3_hc_tx_packet_sent(struct sock *sk, int more, static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - struct ccid3_options_received *opt_recv = &hc->tx_options_received; + struct tfrc_tx_hist_entry *acked; ktime_t now; unsigned long t_nfb; - u32 pinv, r_sample; + u32 r_sample; /* we are only interested in ACKs */ if (!(DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_ACK || DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK)) return; - /* ... and only in the established state */ - if (hc->tx_state != TFRC_SSTATE_FBACK && - hc->tx_state != TFRC_SSTATE_NO_FBACK) - return; - - now = ktime_get_real(); - - /* Estimate RTT from history if ACK number is valid */ - r_sample = tfrc_tx_hist_rtt(hc->tx_hist, - DCCP_SKB_CB(skb)->dccpd_ack_seq, now); - if (r_sample == 0) { - DCCP_WARN("%s(%p): %s with bogus ACK-%llu\n", dccp_role(sk), sk, - dccp_packet_name(DCCP_SKB_CB(skb)->dccpd_type), - (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq); - return; - } - - /* Update receive rate in units of 64 * bytes/second */ - hc->tx_x_recv = opt_recv->ccid3or_receive_rate; - hc->tx_x_recv <<= 6; - - /* Update loss event rate (which is scaled by 1e6) */ - pinv = opt_recv->ccid3or_loss_event_rate; - if (pinv == ~0U || pinv == 0) /* see RFC 4342, 8.5 */ - hc->tx_p = 0; - else /* can not exceed 100% */ - hc->tx_p = scaled_div(1, pinv); /* - * Validate new RTT sample and update moving average + * Locate the acknowledged packet in the TX history. + * + * Returning "entry not found" here can for instance happen when + * - the host has not sent out anything (e.g. a passive server), + * - the Ack is outdated (packet with higher Ack number was received), + * - it is a bogus Ack (for a packet not sent on this connection). */ - r_sample = dccp_sample_rtt(sk, r_sample); + acked = tfrc_tx_hist_find_entry(hc->tx_hist, dccp_hdr_ack_seq(skb)); + if (acked == NULL) + return; + /* For the sake of RTT sampling, ignore/remove all older entries */ + tfrc_tx_hist_purge(&acked->next); + + /* Update the moving average for the RTT estimate (RFC 3448, 4.3) */ + now = ktime_get_real(); + r_sample = dccp_sample_rtt(sk, ktime_us_delta(now, acked->stamp)); hc->tx_rtt = tfrc_ewma(hc->tx_rtt, r_sample, 9); + /* * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3 */ @@ -480,64 +459,41 @@ done_computing_x: jiffies + usecs_to_jiffies(t_nfb)); } -static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, - unsigned char len, u16 idx, - unsigned char *value) +static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type, + u8 option, u8 *optval, u8 optlen) { - int rc = 0; - const struct dccp_sock *dp = dccp_sk(sk); struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - struct ccid3_options_received *opt_recv = &hc->tx_options_received; __be32 opt_val; - if (opt_recv->ccid3or_seqno != dp->dccps_gsr) { - opt_recv->ccid3or_seqno = dp->dccps_gsr; - opt_recv->ccid3or_loss_event_rate = ~0; - opt_recv->ccid3or_loss_intervals_idx = 0; - opt_recv->ccid3or_loss_intervals_len = 0; - opt_recv->ccid3or_receive_rate = 0; - } - switch (option) { + case TFRC_OPT_RECEIVE_RATE: case TFRC_OPT_LOSS_EVENT_RATE: - if (unlikely(len != 4)) { - DCCP_WARN("%s(%p), invalid len %d " - "for TFRC_OPT_LOSS_EVENT_RATE\n", - dccp_role(sk), sk, len); - rc = -EINVAL; - } else { - opt_val = get_unaligned((__be32 *)value); - opt_recv->ccid3or_loss_event_rate = ntohl(opt_val); - ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n", - dccp_role(sk), sk, - opt_recv->ccid3or_loss_event_rate); + /* Must be ignored on Data packets, cf. RFC 4342 8.3 and 8.5 */ + if (packet_type == DCCP_PKT_DATA) + break; + if (unlikely(optlen != 4)) { + DCCP_WARN("%s(%p), invalid len %d for %u\n", + dccp_role(sk), sk, optlen, option); + return -EINVAL; } - break; - case TFRC_OPT_LOSS_INTERVALS: - opt_recv->ccid3or_loss_intervals_idx = idx; - opt_recv->ccid3or_loss_intervals_len = len; - ccid3_pr_debug("%s(%p), LOSS_INTERVALS=(%u, %u)\n", - dccp_role(sk), sk, - opt_recv->ccid3or_loss_intervals_idx, - opt_recv->ccid3or_loss_intervals_len); - break; - case TFRC_OPT_RECEIVE_RATE: - if (unlikely(len != 4)) { - DCCP_WARN("%s(%p), invalid len %d " - "for TFRC_OPT_RECEIVE_RATE\n", - dccp_role(sk), sk, len); - rc = -EINVAL; - } else { - opt_val = get_unaligned((__be32 *)value); - opt_recv->ccid3or_receive_rate = ntohl(opt_val); + opt_val = ntohl(get_unaligned((__be32 *)optval)); + + if (option == TFRC_OPT_RECEIVE_RATE) { + /* Receive Rate is kept in units of 64 bytes/second */ + hc->tx_x_recv = opt_val; + hc->tx_x_recv <<= 6; + ccid3_pr_debug("%s(%p), RECEIVE_RATE=%u\n", - dccp_role(sk), sk, - opt_recv->ccid3or_receive_rate); + dccp_role(sk), sk, opt_val); + } else { + /* Update the fixpoint Loss Event Rate fraction */ + hc->tx_p = tfrc_invert_loss_event_rate(opt_val); + + ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n", + dccp_role(sk), sk, opt_val); } - break; } - - return rc; + return 0; } static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) @@ -555,9 +511,7 @@ static void ccid3_hc_tx_exit(struct sock *sk) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - ccid3_hc_tx_set_state(sk, TFRC_SSTATE_TERM); sk_stop_timer(sk, &hc->tx_no_feedback_timer); - tfrc_tx_hist_purge(&hc->tx_hist); } @@ -616,7 +570,6 @@ static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) static const char *const ccid3_rx_state_names[] = { [TFRC_RSTATE_NO_DATA] = "NO_DATA", [TFRC_RSTATE_DATA] = "DATA", - [TFRC_RSTATE_TERM] = "TERM", }; return ccid3_rx_state_names[state]; @@ -642,14 +595,9 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - ktime_t now; + ktime_t now = ktime_get_real(); s64 delta = 0; - if (unlikely(hc->rx_state == TFRC_RSTATE_TERM)) - return; - - now = ktime_get_real(); - switch (fbtype) { case CCID3_FBACK_INITIAL: hc->rx_x_recv = 0; @@ -853,8 +801,6 @@ static void ccid3_hc_rx_exit(struct sock *sk) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); - ccid3_hc_rx_set_state(sk, TFRC_RSTATE_TERM); - tfrc_rx_hist_purge(&hc->rx_hist); tfrc_lh_cleanup(&hc->rx_li_hist); } @@ -879,8 +825,7 @@ static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len, return -EINVAL; rx_info.tfrcrx_x_recv = hc->rx_x_recv; rx_info.tfrcrx_rtt = hc->rx_rtt; - rx_info.tfrcrx_p = hc->rx_pinv == 0 ? ~0U : - scaled_div(1, hc->rx_pinv); + rx_info.tfrcrx_p = tfrc_invert_loss_event_rate(hc->rx_pinv); len = sizeof(rx_info); val = &rx_info; break; diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index b7e569c..1a9933c 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -45,32 +45,33 @@ /* Two seconds as per RFC 5348, 4.2 */ #define TFRC_INITIAL_TIMEOUT (2 * USEC_PER_SEC) -/* In usecs - half the scheduling granularity as per RFC3448 4.6 */ -#define TFRC_OPSYS_HALF_TIME_GRAN (USEC_PER_SEC / (2 * HZ)) - /* Parameter t_mbi from [RFC 3448, 4.3]: backoff interval in seconds */ #define TFRC_T_MBI 64 +/* + * The t_delta parameter (RFC 5348, 8.3): delays of less than %USEC_PER_MSEC are + * rounded down to 0, since sk_reset_timer() here uses millisecond granularity. + * Hence we can use a constant t_delta = %USEC_PER_MSEC when HZ >= 500. A coarse + * resolution of HZ < 500 means that the error is below one timer tick (t_gran) + * when using the constant t_delta = t_gran / 2 = %USEC_PER_SEC / (2 * HZ). + */ +#if (HZ >= 500) +# define TFRC_T_DELTA USEC_PER_MSEC +#else +# define TFRC_T_DELTA (USEC_PER_SEC / (2 * HZ)) +#endif + enum ccid3_options { TFRC_OPT_LOSS_EVENT_RATE = 192, TFRC_OPT_LOSS_INTERVALS = 193, TFRC_OPT_RECEIVE_RATE = 194, }; -struct ccid3_options_received { - u64 ccid3or_seqno:48, - ccid3or_loss_intervals_idx:16; - u16 ccid3or_loss_intervals_len; - u32 ccid3or_loss_event_rate; - u32 ccid3or_receive_rate; -}; - /* TFRC sender states */ enum ccid3_hc_tx_states { TFRC_SSTATE_NO_SENT = 1, TFRC_SSTATE_NO_FBACK, TFRC_SSTATE_FBACK, - TFRC_SSTATE_TERM, }; /** @@ -90,9 +91,7 @@ enum ccid3_hc_tx_states { * @tx_no_feedback_timer: Handle to no feedback timer * @tx_t_ld: Time last doubled during slow start * @tx_t_nom: Nominal send time of next packet - * @tx_delta: Send timer delta (RFC 3448, 4.6) in usecs * @tx_hist: Packet history - * @tx_options_received: Parsed set of retrieved options */ struct ccid3_hc_tx_sock { u64 tx_x; @@ -109,9 +108,7 @@ struct ccid3_hc_tx_sock { struct timer_list tx_no_feedback_timer; ktime_t tx_t_ld; ktime_t tx_t_nom; - u32 tx_delta; struct tfrc_tx_hist_entry *tx_hist; - struct ccid3_options_received tx_options_received; }; static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) @@ -125,7 +122,6 @@ static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) enum ccid3_hc_rx_states { TFRC_RSTATE_NO_DATA = 1, TFRC_RSTATE_DATA, - TFRC_RSTATE_TERM = 127, }; /** diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c index 8fc3cbf..497723c 100644 --- a/net/dccp/ccids/lib/loss_interval.c +++ b/net/dccp/ccids/lib/loss_interval.c @@ -116,7 +116,7 @@ u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb) cur->li_length = len; tfrc_lh_calc_i_mean(lh); - return (lh->i_mean < old_i_mean); + return lh->i_mean < old_i_mean; } /* Determine if `new_loss' does begin a new loss interval [RFC 4342, 10.2] */ diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c index 3a4f414..de8fe29 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -38,18 +38,6 @@ #include "packet_history.h" #include "../../dccp.h" -/** - * tfrc_tx_hist_entry - Simple singly-linked TX history list - * @next: next oldest entry (LIFO order) - * @seqno: sequence number of this entry - * @stamp: send time of packet with sequence number @seqno - */ -struct tfrc_tx_hist_entry { - struct tfrc_tx_hist_entry *next; - u64 seqno; - ktime_t stamp; -}; - /* * Transmitter History Routines */ @@ -71,15 +59,6 @@ void tfrc_tx_packet_history_exit(void) } } -static struct tfrc_tx_hist_entry * - tfrc_tx_hist_find_entry(struct tfrc_tx_hist_entry *head, u64 seqno) -{ - while (head != NULL && head->seqno != seqno) - head = head->next; - - return head; -} - int tfrc_tx_hist_add(struct tfrc_tx_hist_entry **headp, u64 seqno) { struct tfrc_tx_hist_entry *entry = kmem_cache_alloc(tfrc_tx_hist_slab, gfp_any()); @@ -107,24 +86,6 @@ void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp) *headp = NULL; } -u32 tfrc_tx_hist_rtt(struct tfrc_tx_hist_entry *head, const u64 seqno, - const ktime_t now) -{ - u32 rtt = 0; - struct tfrc_tx_hist_entry *packet = tfrc_tx_hist_find_entry(head, seqno); - - if (packet != NULL) { - rtt = ktime_us_delta(now, packet->stamp); - /* - * Garbage-collect older (irrelevant) entries: - */ - tfrc_tx_hist_purge(&packet->next); - } - - return rtt; -} - - /* * Receiver History Routines */ diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h index 7df6c52..7ee4a9d 100644 --- a/net/dccp/ccids/lib/packet_history.h +++ b/net/dccp/ccids/lib/packet_history.h @@ -40,12 +40,28 @@ #include <linux/slab.h> #include "tfrc.h" -struct tfrc_tx_hist_entry; +/** + * tfrc_tx_hist_entry - Simple singly-linked TX history list + * @next: next oldest entry (LIFO order) + * @seqno: sequence number of this entry + * @stamp: send time of packet with sequence number @seqno + */ +struct tfrc_tx_hist_entry { + struct tfrc_tx_hist_entry *next; + u64 seqno; + ktime_t stamp; +}; + +static inline struct tfrc_tx_hist_entry * + tfrc_tx_hist_find_entry(struct tfrc_tx_hist_entry *head, u64 seqno) +{ + while (head != NULL && head->seqno != seqno) + head = head->next; + return head; +} extern int tfrc_tx_hist_add(struct tfrc_tx_hist_entry **headp, u64 seqno); extern void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp); -extern u32 tfrc_tx_hist_rtt(struct tfrc_tx_hist_entry *head, - const u64 seqno, const ktime_t now); /* Subtraction a-b modulo-16, respects circular wrap-around */ #define SUB16(a, b) (((a) + 16 - (b)) & 0xF) diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index 01bb48e..f8ee3f5 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -57,6 +57,7 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight) extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +extern u32 tfrc_invert_loss_event_rate(u32 loss_event_rate); extern int tfrc_tx_packet_history_init(void); extern void tfrc_tx_packet_history_exit(void); diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index 22ca1cf..a052a43 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -687,3 +687,17 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) index = tfrc_binsearch(fvalue, 0); return (index + 1) * 1000000 / TFRC_CALC_X_ARRSIZE; } + +/** + * tfrc_invert_loss_event_rate - Compute p so that 10^6 corresponds to 100% + * When @loss_event_rate is large, there is a chance that p is truncated to 0. + * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0. + */ +u32 tfrc_invert_loss_event_rate(u32 loss_event_rate) +{ + if (loss_event_rate == UINT_MAX) /* see RFC 4342, 8.5 */ + return 0; + if (unlikely(loss_event_rate == 0)) /* map 1/0 into 100% */ + return 1000000; + return max_t(u32, scaled_div(1, loss_event_rate), TFRC_SMALLEST_P); +} diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 3ccef1b..3eb264b 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -153,18 +153,27 @@ static inline u64 max48(const u64 seq1, const u64 seq2) } /** - * dccp_loss_free - Evaluates condition for data loss from RFC 4340, 7.7.1 - * @s1: start sequence number - * @s2: end sequence number + * dccp_loss_count - Approximate the number of lost data packets in a burst loss + * @s1: last known sequence number before the loss ('hole') + * @s2: first sequence number seen after the 'hole' * @ndp: NDP count on packet with sequence number @s2 - * Returns true if the sequence range s1...s2 has no data loss. */ -static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp) +static inline u64 dccp_loss_count(const u64 s1, const u64 s2, const u64 ndp) { s64 delta = dccp_delta_seqno(s1, s2); WARN_ON(delta < 0); - return (u64)delta <= ndp + 1; + delta -= ndp + 1; + + return delta > 0 ? delta : 0; +} + +/** + * dccp_loss_free - Evaluate condition for data loss from RFC 4340, 7.7.1 + */ +static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp) +{ + return dccp_loss_count(s1, s2, ndp) == 0; } enum { @@ -246,7 +255,6 @@ static inline void dccp_clear_xmit_timers(struct sock *sk) extern unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu); extern const char *dccp_packet_name(const int type); -extern const char *dccp_state_name(const int state); extern void dccp_set_state(struct sock *sk, const int state); extern void dccp_done(struct sock *sk); @@ -415,6 +423,23 @@ static inline void dccp_update_gsr(struct sock *sk, u64 seq) dp->dccps_gsr = seq; /* Sequence validity window depends on remote Sequence Window (7.5.1) */ dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4); + /* + * Adjust SWL so that it is not below ISR. In contrast to RFC 4340, + * 7.5.1 we perform this check beyond the initial handshake: W/W' are + * always > 32, so for the first W/W' packets in the lifetime of a + * connection we always have to adjust SWL. + * A second reason why we are doing this is that the window depends on + * the feature-remote value of Sequence Window: nothing stops the peer + * from updating this value while we are busy adjusting SWL for the + * first W packets (we would have to count from scratch again then). + * Therefore it is safer to always make sure that the Sequence Window + * is not artificially extended by a peer who grows SWL downwards by + * continually updating the feature-remote Sequence-Window. + * If sequence numbers wrap it is bad luck. But that will take a while + * (48 bit), and this measure prevents Sequence-number attacks. + */ + if (before48(dp->dccps_swl, dp->dccps_isr)) + dp->dccps_swl = dp->dccps_isr; dp->dccps_swh = ADD48(dp->dccps_gsr, (3 * dp->dccps_r_seq_win) / 4); } @@ -425,14 +450,16 @@ static inline void dccp_update_gss(struct sock *sk, u64 seq) dp->dccps_gss = seq; /* Ack validity window depends on local Sequence Window value (7.5.1) */ dp->dccps_awl = SUB48(ADD48(dp->dccps_gss, 1), dp->dccps_l_seq_win); + /* Adjust AWL so that it is not below ISS - see comment above for SWL */ + if (before48(dp->dccps_awl, dp->dccps_iss)) + dp->dccps_awl = dp->dccps_iss; dp->dccps_awh = dp->dccps_gss; } static inline int dccp_ack_pending(const struct sock *sk) { const struct dccp_sock *dp = dccp_sk(sk); - return dp->dccps_timestamp_echo != 0 || - (dp->dccps_hc_rx_ackvec != NULL && + return (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || inet_csk_ack_scheduled(sk); } @@ -449,7 +476,6 @@ extern int dccp_insert_options_rsk(struct dccp_request_sock*, struct sk_buff*); extern int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed); extern u32 dccp_timestamp(void); extern void dccp_timestamping_init(void); -extern int dccp_insert_option_timestamp(struct sk_buff *skb); extern int dccp_insert_option(struct sk_buff *skb, unsigned char option, const void *value, unsigned char len); diff --git a/net/dccp/feat.c b/net/dccp/feat.c index df7dd26..568def9 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -730,16 +730,6 @@ int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local, 0, list, len); } -/* Analogous to dccp_feat_register_sp(), but for non-negotiable values */ -int dccp_feat_register_nn(struct sock *sk, u8 feat, u64 val) -{ - /* any changes must be registered before establishing the connection */ - if (sk->sk_state != DCCP_CLOSED) - return -EISCONN; - if (dccp_feat_type(feat) != FEAT_NN) - return -EINVAL; - return __feat_register_nn(&dccp_sk(sk)->dccps_featneg, feat, 0, val); -} /* * Tracking features whose value depend on the choice of CCID diff --git a/net/dccp/feat.h b/net/dccp/feat.h index f967216..e56a4e5 100644 --- a/net/dccp/feat.h +++ b/net/dccp/feat.h @@ -111,7 +111,6 @@ extern int dccp_feat_init(struct sock *sk); extern void dccp_feat_initialise_sysctls(void); extern int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local, u8 const *list, u8 len); -extern int dccp_feat_register_nn(struct sock *sk, u8 feat, u64 val); extern int dccp_feat_parse_options(struct sock *, struct dccp_request_sock *, u8 mand, u8 opt, u8 feat, u8 *val, u8 len); extern int dccp_feat_clone_list(struct list_head const *, struct list_head *); diff --git a/net/dccp/input.c b/net/dccp/input.c index 10c957a..2659853 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -259,7 +259,7 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) sysctl_dccp_sync_ratelimit))) return 0; - DCCP_WARN("DCCP: Step 6 failed for %s packet, " + DCCP_WARN("Step 6 failed for %s packet, " "(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and " "(P.ackno %s or LAWL(%llu) <= P.ackno(%llu) <= S.AWH(%llu), " "sending SYNC...\n", dccp_packet_name(dh->dccph_type), @@ -441,20 +441,14 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; - dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; - dccp_update_gsr(sk, dp->dccps_isr); /* - * SWL and AWL are initially adjusted so that they are not less than - * the initial Sequence Numbers received and sent, respectively: - * SWL := max(GSR + 1 - floor(W/4), ISR), - * AWL := max(GSS - W' + 1, ISS). - * These adjustments MUST be applied only at the beginning of the - * connection. - * - * AWL was adjusted in dccp_v4_connect -acme + * Set ISR, GSR from packet. ISS was set in dccp_v{4,6}_connect + * and GSS in dccp_transmit_skb(). Setting AWL/AWH and SWL/SWH + * is done as part of activating the feature values below, since + * these settings depend on the local/remote Sequence Window + * features, which were undefined or not confirmed until now. */ - dccp_set_seqno(&dp->dccps_swl, - max48(dp->dccps_swl, dp->dccps_isr)); + dp->dccps_gsr = dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; dccp_sync_mss(sk, icsk->icsk_pmtu_cookie); diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 128b089..d7041a0 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -121,30 +121,18 @@ struct sock *dccp_create_openreq_child(struct sock *sk, * * Choose S.ISS (initial seqno) or set from Init Cookies * Initialize S.GAR := S.ISS - * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies - */ - newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss; - dccp_update_gss(newsk, dreq->dreq_iss); - - newdp->dccps_isr = dreq->dreq_isr; - dccp_update_gsr(newsk, dreq->dreq_isr); - - /* - * SWL and AWL are initially adjusted so that they are not less than - * the initial Sequence Numbers received and sent, respectively: - * SWL := max(GSR + 1 - floor(W/4), ISR), - * AWL := max(GSS - W' + 1, ISS). - * These adjustments MUST be applied only at the beginning of the - * connection. + * Set S.ISR, S.GSR from packet (or Init Cookies) + * + * Setting AWL/AWH and SWL/SWH happens as part of the feature + * activation below, as these windows all depend on the local + * and remote Sequence Window feature values (7.5.2). */ - dccp_set_seqno(&newdp->dccps_swl, - max48(newdp->dccps_swl, newdp->dccps_isr)); - dccp_set_seqno(&newdp->dccps_awl, - max48(newdp->dccps_awl, newdp->dccps_iss)); + newdp->dccps_gss = newdp->dccps_iss = dreq->dreq_iss; + newdp->dccps_gar = newdp->dccps_iss; + newdp->dccps_gsr = newdp->dccps_isr = dreq->dreq_isr; /* - * Activate features after initialising the sequence numbers, - * since CCID initialisation may depend on GSS, ISR, ISS etc. + * Activate features: initialise CCIDs, sequence windows etc. */ if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) { /* It is still raw copy of parent, so invalidate diff --git a/net/dccp/options.c b/net/dccp/options.c index bfda087..cd30618 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -96,18 +96,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, } /* - * CCID-Specific Options (from RFC 4340, sec. 10.3): - * - * Option numbers 128 through 191 are for options sent from the - * HC-Sender to the HC-Receiver; option numbers 192 through 255 - * are for options sent from the HC-Receiver to the HC-Sender. - * * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). * The same applies to Ack Vectors, as these depend on the CCID. - * */ - if (dreq != NULL && (opt >= 128 || + if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC || opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; @@ -170,6 +163,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, dccp_role(sk), ntohl(opt_val), (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); + /* schedule an Ack in case this sender is quiescent */ + inet_csk_schedule_ack(sk); break; case DCCPO_TIMESTAMP_ECHO: if (len != 4 && len != 6 && len != 8) @@ -226,23 +221,15 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n", dccp_role(sk), elapsed_time); break; - case 128 ... 191: { - const u16 idx = value - options; - + case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC: if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk, - opt, len, idx, - value) != 0) + pkt_type, opt, value, len)) goto out_invalid_option; - } break; - case 192 ... 255: { - const u16 idx = value - options; - + case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, - opt, len, idx, - value) != 0) + pkt_type, opt, value, len)) goto out_invalid_option; - } break; default: DCCP_CRIT("DCCP(%p): option %d(len=%d) not " @@ -384,7 +371,7 @@ int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed_time) EXPORT_SYMBOL_GPL(dccp_insert_option_elapsed_time); -int dccp_insert_option_timestamp(struct sk_buff *skb) +static int dccp_insert_option_timestamp(struct sk_buff *skb) { __be32 now = htonl(dccp_timestamp()); /* yes this will overflow but that is the point as we want a @@ -393,8 +380,6 @@ int dccp_insert_option_timestamp(struct sk_buff *skb) return dccp_insert_option(skb, DCCPO_TIMESTAMP, &now, sizeof(now)); } -EXPORT_SYMBOL_GPL(dccp_insert_option_timestamp); - static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, struct dccp_request_sock *dreq, struct sk_buff *skb) diff --git a/net/dccp/output.c b/net/dccp/output.c index aadbdb5..a988fe9 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -304,7 +304,7 @@ void dccp_write_xmit(struct sock *sk, int block) dcb->dccpd_type = DCCP_PKT_DATA; err = dccp_transmit_skb(sk, skb); - ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len); + ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len); if (err) DCCP_BUG("err=%d after ccid_hc_tx_packet_sent", err); @@ -474,8 +474,9 @@ int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code) /* * Do all connect socket setups that can be done AF independent. */ -static inline void dccp_connect_init(struct sock *sk) +int dccp_connect(struct sock *sk) { + struct sk_buff *skb; struct dccp_sock *dp = dccp_sk(sk); struct dst_entry *dst = __sk_dst_get(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -485,22 +486,12 @@ static inline void dccp_connect_init(struct sock *sk) dccp_sync_mss(sk, dst_mtu(dst)); - /* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */ - dp->dccps_gar = dp->dccps_iss; - - icsk->icsk_retransmits = 0; -} - -int dccp_connect(struct sock *sk) -{ - struct sk_buff *skb; - struct inet_connection_sock *icsk = inet_csk(sk); - /* do not connect if feature negotiation setup fails */ if (dccp_feat_finalise_settings(dccp_sk(sk))) return -EPROTO; - dccp_connect_init(sk); + /* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */ + dp->dccps_gar = dp->dccps_iss; skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation); if (unlikely(skb == NULL)) @@ -516,6 +507,7 @@ int dccp_connect(struct sock *sk) DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS); /* Timer for repeating the REQUEST until an answer. */ + icsk->icsk_retransmits = 0; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, DCCP_RTO_MAX); return 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 096250d..7e5fc04 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -50,6 +50,30 @@ EXPORT_SYMBOL_GPL(dccp_hashinfo); /* the maximum queue length for tx in packets. 0 is no limit */ int sysctl_dccp_tx_qlen __read_mostly = 5; +#ifdef CONFIG_IP_DCCP_DEBUG +static const char *dccp_state_name(const int state) +{ + static const char *const dccp_state_names[] = { + [DCCP_OPEN] = "OPEN", + [DCCP_REQUESTING] = "REQUESTING", + [DCCP_PARTOPEN] = "PARTOPEN", + [DCCP_LISTEN] = "LISTEN", + [DCCP_RESPOND] = "RESPOND", + [DCCP_CLOSING] = "CLOSING", + [DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ", + [DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE", + [DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ", + [DCCP_TIME_WAIT] = "TIME_WAIT", + [DCCP_CLOSED] = "CLOSED", + }; + + if (state >= DCCP_MAX_STATES) + return "INVALID STATE!"; + else + return dccp_state_names[state]; +} +#endif + void dccp_set_state(struct sock *sk, const int state) { const int oldstate = sk->sk_state; @@ -146,30 +170,6 @@ const char *dccp_packet_name(const int type) EXPORT_SYMBOL_GPL(dccp_packet_name); -const char *dccp_state_name(const int state) -{ - static const char *const dccp_state_names[] = { - [DCCP_OPEN] = "OPEN", - [DCCP_REQUESTING] = "REQUESTING", - [DCCP_PARTOPEN] = "PARTOPEN", - [DCCP_LISTEN] = "LISTEN", - [DCCP_RESPOND] = "RESPOND", - [DCCP_CLOSING] = "CLOSING", - [DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ", - [DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE", - [DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ", - [DCCP_TIME_WAIT] = "TIME_WAIT", - [DCCP_CLOSED] = "CLOSED", - }; - - if (state >= DCCP_MAX_STATES) - return "INVALID STATE!"; - else - return dccp_state_names[state]; -} - -EXPORT_SYMBOL_GPL(dccp_state_name); - int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) { struct dccp_sock *dp = dccp_sk(sk); @@ -944,7 +944,7 @@ void dccp_close(struct sock *sk, long timeout) if (data_was_unread) { /* Unread data was tossed, send an appropriate Reset Code */ - DCCP_WARN("DCCP: ABORT -- %u bytes unread\n", data_was_unread); + DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_set_state(sk, DCCP_CLOSED); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 0363bb95..a085dbc 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -48,7 +48,6 @@ #include <net/dn_neigh.h> #include <net/dn_route.h> -static u32 dn_neigh_hash(const void *pkey, const struct net_device *dev); static int dn_neigh_construct(struct neighbour *); static void dn_long_error_report(struct neighbour *, struct sk_buff *); static void dn_short_error_report(struct neighbour *, struct sk_buff *); @@ -93,6 +92,13 @@ static const struct neigh_ops dn_phase3_ops = { .queue_xmit = dev_queue_xmit }; +static u32 dn_neigh_hash(const void *pkey, + const struct net_device *dev, + __u32 hash_rnd) +{ + return jhash_2words(*(__u16 *)pkey, 0, hash_rnd); +} + struct neigh_table dn_neigh_table = { .family = PF_DECnet, .entry_size = sizeof(struct dn_neigh), @@ -122,11 +128,6 @@ struct neigh_table dn_neigh_table = { .gc_thresh3 = 1024, }; -static u32 dn_neigh_hash(const void *pkey, const struct net_device *dev) -{ - return jhash_2words(*(__u16 *)pkey, 0, dn_neigh_table.hash_rnd); -} - static int dn_neigh_construct(struct neighbour *neigh) { struct net_device *dev = neigh->dev; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 6585ea6..df0f3e5 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -132,7 +132,6 @@ static struct dst_ops dn_dst_ops = { .negative_advice = dn_dst_negative_advice, .link_failure = dn_dst_link_failure, .update_pmtu = dn_dst_update_pmtu, - .entries = ATOMIC_INIT(0), }; static __inline__ unsigned dn_hash(__le16 src, __le16 dst) @@ -1758,6 +1757,7 @@ void __init dn_route_init(void) dn_dst_ops.kmem_cachep = kmem_cache_create("dn_dst_cache", sizeof(struct dn_route), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + dst_entries_init(&dn_dst_ops); setup_timer(&dn_route_timer, dn_dst_check_expire, 0); dn_route_timer.expires = jiffies + decnet_dst_gc_interval * HZ; add_timer(&dn_route_timer); @@ -1816,5 +1816,6 @@ void __exit dn_route_cleanup(void) dn_run_flush(0); proc_net_remove(&init_net, "decnet_cache"); + dst_entries_destroy(&dn_dst_ops); } diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index baa98fb..f8c1ae4 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -392,7 +392,7 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, dev_queue_xmit(skb); dev_put(dev); mutex_unlock(&econet_mutex); - return(len); + return len; out_free: kfree_skb(skb); @@ -637,7 +637,7 @@ static int econet_create(struct net *net, struct socket *sock, int protocol, eo->num = protocol; econet_insert_socket(&econet_sklist, sk); - return(0); + return 0; out: return err; } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 85e7b45..f00ef2f 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -387,6 +387,6 @@ ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len) l = _format_mac_addr(buf, PAGE_SIZE, addr, len); l += scnprintf(buf + l, PAGE_SIZE - l, "\n"); - return ((ssize_t) l); + return (ssize_t)l; } EXPORT_SYMBOL(sysfs_format_mac); diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 5462e2d..e848e6c 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -223,7 +223,7 @@ config NET_IPGRE_DEMUX config NET_IPGRE tristate "IP: GRE tunnels over IP" - depends on NET_IPGRE_DEMUX + depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX help Tunneling means encapsulating data of one protocol type within another protocol and sending it over a channel that understands the @@ -419,7 +419,7 @@ config INET_XFRM_MODE_BEET If unsure, say Y. config INET_LRO - bool "Large Receive Offload (ipv4/tcp)" + tristate "Large Receive Offload (ipv4/tcp)" default y ---help--- Support for Large Receive Offload (ipv4/tcp). diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index dcfe7e9..d8e540c 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -127,7 +127,7 @@ EXPORT_SYMBOL(clip_tbl_hook); /* * Interface to generic neighbour cache. */ -static u32 arp_hash(const void *pkey, const struct net_device *dev); +static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 rnd); static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -161,7 +161,7 @@ static const struct neigh_ops arp_direct_ops = { .queue_xmit = dev_queue_xmit, }; -const struct neigh_ops arp_broken_ops = { +static const struct neigh_ops arp_broken_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, @@ -170,7 +170,6 @@ const struct neigh_ops arp_broken_ops = { .hh_output = dev_queue_xmit, .queue_xmit = dev_queue_xmit, }; -EXPORT_SYMBOL(arp_broken_ops); struct neigh_table arp_tbl = { .family = AF_INET, @@ -226,9 +225,11 @@ int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) } -static u32 arp_hash(const void *pkey, const struct net_device *dev) +static u32 arp_hash(const void *pkey, + const struct net_device *dev, + __u32 hash_rnd) { - return jhash_2words(*(u32 *)pkey, dev->ifindex, arp_tbl.hash_rnd); + return jhash_2words(*(u32 *)pkey, dev->ifindex, hash_rnd); } static int arp_constructor(struct neighbour *neigh) @@ -501,10 +502,8 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) if (n) { n->used = jiffies; - if (n->nud_state&NUD_VALID || neigh_event_send(n, skb) == 0) { - read_lock_bh(&n->lock); - memcpy(haddr, n->ha, dev->addr_len); - read_unlock_bh(&n->lock); + if (n->nud_state & NUD_VALID || neigh_event_send(n, skb) == 0) { + neigh_ha_snapshot(haddr, n, dev); neigh_release(n); return 0; } @@ -567,7 +566,7 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, if (out_dev) omi = IN_DEV_MEDIUM_ID(out_dev); - return (omi != imi && omi != -1); + return omi != imi && omi != -1; } /* diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 721a8a3..174be6c 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,6 +73,6 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_id = jiffies; sk_dst_set(sk, &rt->dst); - return(0); + return 0; } EXPORT_SYMBOL(ip4_datagram_connect); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index da14c49..dc94b03 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -209,7 +209,7 @@ static void inetdev_destroy(struct in_device *in_dev) inet_free_ifa(ifa); } - dev->ip_ptr = NULL; + rcu_assign_pointer(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); @@ -403,6 +403,9 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) return inet_insert_ifa(ifa); } +/* Caller must hold RCU or RTNL : + * We dont take a reference on found in_device + */ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; @@ -411,7 +414,7 @@ struct in_device *inetdev_by_index(struct net *net, int ifindex) rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) - in_dev = in_dev_get(dev); + in_dev = rcu_dereference_rtnl(dev->ip_ptr); rcu_read_unlock(); return in_dev; } @@ -453,8 +456,6 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg goto errout; } - __in_dev_put(in_dev); - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && @@ -1059,7 +1060,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_REGISTER: printk(KERN_DEBUG "inetdev_event: bug\n"); - dev->ip_ptr = NULL; + rcu_assign_pointer(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 7d02a9f..36e27c2 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -147,35 +147,43 @@ static void fib_flush(struct net *net) rt_cache_flush(net, -1); } -/* - * Find the first device with a given source address. +/** + * __ip_dev_find - find the first device with a given source address. + * @net: the net namespace + * @addr: the source address + * @devref: if true, take a reference on the found device + * + * If a caller uses devref=false, it should be protected by RCU, or RTNL */ - -struct net_device * ip_dev_find(struct net *net, __be32 addr) +struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } }; - struct fib_result res; + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = addr + } + }, + .flags = FLOWI_FLAG_MATCH_ANY_IIF + }; + struct fib_result res = { 0 }; struct net_device *dev = NULL; - struct fib_table *local_table; -#ifdef CONFIG_IP_MULTIPLE_TABLES - res.r = NULL; -#endif - - local_table = fib_get_table(net, RT_TABLE_LOCAL); - if (!local_table || fib_table_lookup(local_table, &fl, &res)) + rcu_read_lock(); + if (fib_lookup(net, &fl, &res)) { + rcu_read_unlock(); return NULL; + } if (res.type != RTN_LOCAL) goto out; dev = FIB_RES_DEV(res); - if (dev) + if (dev && devref) dev_hold(dev); out: - fib_res_put(&res); + rcu_read_unlock(); return dev; } -EXPORT_SYMBOL(ip_dev_find); +EXPORT_SYMBOL(__ip_dev_find); /* * Find address type as if only "dev" was present in the system. If @@ -202,11 +210,12 @@ static inline unsigned __inet_dev_addr_type(struct net *net, local_table = fib_get_table(net, RT_TABLE_LOCAL); if (local_table) { ret = RTN_UNICAST; - if (!fib_table_lookup(local_table, &fl, &res)) { + rcu_read_lock(); + if (!fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) { if (!dev || dev == res.fi->fib_dev) ret = res.type; - fib_res_put(&res); } + rcu_read_unlock(); } return ret; } @@ -220,30 +229,34 @@ EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { - return __inet_dev_addr_type(net, dev, addr); + return __inet_dev_addr_type(net, dev, addr); } EXPORT_SYMBOL(inet_dev_addr_type); /* Given (packet source, input interface) and optional (dst, oif, tos): - - (main) check, that source is valid i.e. not broadcast or our local - address. - - figure out what "logical" interface this packet arrived - and calculate "specific destination" address. - - check, that packet arrived from expected physical interface. + * - (main) check, that source is valid i.e. not broadcast or our local + * address. + * - figure out what "logical" interface this packet arrived + * and calculate "specific destination" address. + * - check, that packet arrived from expected physical interface. + * called with rcu_read_lock() */ - int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, __be32 *spec_dst, u32 *itag, u32 mark) { struct in_device *in_dev; - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = src, - .saddr = dst, - .tos = tos } }, - .mark = mark, - .iif = oif }; - + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = src, + .saddr = dst, + .tos = tos + } + }, + .mark = mark, + .iif = oif + }; struct fib_result res; int no_addr, rpf, accept_local; bool dev_match; @@ -251,7 +264,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct net *net; no_addr = rpf = accept_local = 0; - rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) { no_addr = in_dev->ifa_list == NULL; @@ -260,7 +272,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, if (mark && !IN_DEV_SRC_VMARK(in_dev)) fl.mark = 0; } - rcu_read_unlock(); if (in_dev == NULL) goto e_inval; @@ -270,7 +281,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, goto last_resort; if (res.type != RTN_UNICAST) { if (res.type != RTN_LOCAL || !accept_local) - goto e_inval_res; + goto e_inval; } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); @@ -291,10 +302,8 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, #endif if (dev_match) { ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; - fib_res_put(&res); return ret; } - fib_res_put(&res); if (no_addr) goto last_resort; if (rpf == 1) @@ -307,7 +316,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, *spec_dst = FIB_RES_PREFSRC(res); ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; } - fib_res_put(&res); } return ret; @@ -318,8 +326,6 @@ last_resort: *itag = 0; return 0; -e_inval_res: - fib_res_put(&res); e_inval: return -EINVAL; e_rpf: @@ -472,9 +478,9 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, } /* - * Handle IP routing ioctl calls. These are used to manipulate the routing tables + * Handle IP routing ioctl calls. + * These are used to manipulate the routing tables */ - int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct fib_config cfg; @@ -518,7 +524,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) return -EINVAL; } -const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { +const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, @@ -532,7 +538,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_config *cfg) + struct nlmsghdr *nlh, struct fib_config *cfg) { struct nlattr *attr; int err, remaining; @@ -687,12 +693,11 @@ out: } /* Prepare and feed intra-kernel routing request. - Really, it should be netlink message, but :-( netlink - can be not configured, so that we feed it directly - to fib engine. It is legal, because all events occur - only when netlink is already locked. + * Really, it should be netlink message, but :-( netlink + * can be not configured, so that we feed it directly + * to fib engine. It is legal, because all events occur + * only when netlink is already locked. */ - static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { struct net *net = dev_net(ifa->ifa_dev->dev); @@ -738,9 +743,9 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) struct in_ifaddr *prim = ifa; __be32 mask = ifa->ifa_mask; __be32 addr = ifa->ifa_local; - __be32 prefix = ifa->ifa_address&mask; + __be32 prefix = ifa->ifa_address & mask; - if (ifa->ifa_flags&IFA_F_SECONDARY) { + if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (prim == NULL) { printk(KERN_WARNING "fib_add_ifaddr: bug: prim == NULL\n"); @@ -750,22 +755,24 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim); - if (!(dev->flags&IFF_UP)) + if (!(dev->flags & IFF_UP)) return; /* Add broadcast address, if it is explicitly assigned. */ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); - if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags&IFA_F_SECONDARY) && + if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { - fib_magic(RTM_NEWROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL : - RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim); + fib_magic(RTM_NEWROUTE, + dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, + prefix, ifa->ifa_prefixlen, prim); /* Add network specific broadcasts, when it takes a sense */ if (ifa->ifa_prefixlen < 31) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, prim); - fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix|~mask, 32, prim); + fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, + 32, prim); } } } @@ -776,17 +783,18 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; struct in_ifaddr *prim = ifa; - __be32 brd = ifa->ifa_address|~ifa->ifa_mask; - __be32 any = ifa->ifa_address&ifa->ifa_mask; + __be32 brd = ifa->ifa_address | ~ifa->ifa_mask; + __be32 any = ifa->ifa_address & ifa->ifa_mask; #define LOCAL_OK 1 #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 unsigned ok = 0; - if (!(ifa->ifa_flags&IFA_F_SECONDARY)) - fib_magic(RTM_DELROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL : - RTN_UNICAST, any, ifa->ifa_prefixlen, prim); + if (!(ifa->ifa_flags & IFA_F_SECONDARY)) + fib_magic(RTM_DELROUTE, + dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, + any, ifa->ifa_prefixlen, prim); else { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (prim == NULL) { @@ -796,9 +804,9 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) } /* Deletion is more complicated than add. - We should take care of not to delete too much :-) - - Scan address list to be sure that addresses are really gone. + * We should take care of not to delete too much :-) + * + * Scan address list to be sure that addresses are really gone. */ for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) { @@ -812,23 +820,23 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) ok |= BRD0_OK; } - if (!(ok&BRD_OK)) + if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); - if (!(ok&BRD1_OK)) + if (!(ok & BRD1_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim); - if (!(ok&BRD0_OK)) + if (!(ok & BRD0_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim); - if (!(ok&LOCAL_OK)) { + if (!(ok & LOCAL_OK)) { fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); /* Check, that this local address finally disappeared. */ if (inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { /* And the last, but not the least thing. - We must flush stray FIB entries. - - First of all, we scan fib_info list searching - for stray nexthop entries, then ignite fib_flush. - */ + * We must flush stray FIB entries. + * + * First of all, we scan fib_info list searching + * for stray nexthop entries, then ignite fib_flush. + */ if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local)) fib_flush(dev_net(dev)); } @@ -839,14 +847,20 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) #undef BRD1_OK } -static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) +static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb) { struct fib_result res; - struct flowi fl = { .mark = frn->fl_mark, - .nl_u = { .ip4_u = { .daddr = frn->fl_addr, - .tos = frn->fl_tos, - .scope = frn->fl_scope } } }; + struct flowi fl = { + .mark = frn->fl_mark, + .nl_u = { + .ip4_u = { + .daddr = frn->fl_addr, + .tos = frn->fl_tos, + .scope = frn->fl_scope + } + } + }; #ifdef CONFIG_IP_MULTIPLE_TABLES res.r = NULL; @@ -857,15 +871,16 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) local_bh_disable(); frn->tb_id = tb->tb_id; - frn->err = fib_table_lookup(tb, &fl, &res); + rcu_read_lock(); + frn->err = fib_table_lookup(tb, &fl, &res, FIB_LOOKUP_NOREF); if (!frn->err) { frn->prefixlen = res.prefixlen; frn->nh_sel = res.nh_sel; frn->type = res.type; frn->scope = res.scope; - fib_res_put(&res); } + rcu_read_unlock(); local_bh_enable(); } } @@ -894,8 +909,8 @@ static void nl_fib_input(struct sk_buff *skb) nl_fib_lookup(frn, tb); - pid = NETLINK_CB(skb).pid; /* pid of sending process */ - NETLINK_CB(skb).pid = 0; /* from kernel */ + pid = NETLINK_CB(skb).pid; /* pid of sending process */ + NETLINK_CB(skb).pid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ netlink_unicast(net->ipv4.fibnl, skb, pid, MSG_DONTWAIT); } @@ -942,7 +957,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, fib_del_ifaddr(ifa); if (ifa->ifa_dev->ifa_list == NULL) { /* Last address was deleted from this interface. - Disable IP. + * Disable IP. */ fib_disable_ip(dev, 1, 0); } else { @@ -1001,16 +1016,15 @@ static struct notifier_block fib_netdev_notifier = { static int __net_init ip_fib_net_init(struct net *net) { int err; - unsigned int i; + size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ; - net->ipv4.fib_table_hash = kzalloc( - sizeof(struct hlist_head)*FIB_TABLE_HASHSZ, GFP_KERNEL); + /* Avoid false sharing : Use at least a full cache line */ + size = max_t(size_t, size, L1_CACHE_BYTES); + + net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); if (net->ipv4.fib_table_hash == NULL) return -ENOMEM; - for (i = 0; i < FIB_TABLE_HASHSZ; i++) - INIT_HLIST_HEAD(&net->ipv4.fib_table_hash[i]); - err = fib4_rules_init(net); if (err < 0) goto fail; diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 4ed7e0d..43e1c59 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -54,36 +54,37 @@ struct fib_node { struct fib_alias fn_embedded_alias; }; -struct fn_zone { - struct fn_zone *fz_next; /* Next not empty zone */ - struct hlist_head *fz_hash; /* Hash table pointer */ - int fz_nent; /* Number of entries */ +#define EMBEDDED_HASH_SIZE (L1_CACHE_BYTES / sizeof(struct hlist_head)) - int fz_divisor; /* Hash divisor */ +struct fn_zone { + struct fn_zone __rcu *fz_next; /* Next not empty zone */ + struct hlist_head __rcu *fz_hash; /* Hash table pointer */ + seqlock_t fz_lock; u32 fz_hashmask; /* (fz_divisor - 1) */ -#define FZ_HASHMASK(fz) ((fz)->fz_hashmask) - int fz_order; /* Zone order */ - __be32 fz_mask; + u8 fz_order; /* Zone order (0..32) */ + u8 fz_revorder; /* 32 - fz_order */ + __be32 fz_mask; /* inet_make_mask(order) */ #define FZ_MASK(fz) ((fz)->fz_mask) -}; -/* NOTE. On fast computers evaluation of fz_hashmask and fz_mask - * can be cheaper than memory lookup, so that FZ_* macros are used. - */ + struct hlist_head fz_embedded_hash[EMBEDDED_HASH_SIZE]; + + int fz_nent; /* Number of entries */ + int fz_divisor; /* Hash size (mask+1) */ +}; struct fn_hash { - struct fn_zone *fn_zones[33]; - struct fn_zone *fn_zone_list; + struct fn_zone *fn_zones[33]; + struct fn_zone __rcu *fn_zone_list; }; static inline u32 fn_hash(__be32 key, struct fn_zone *fz) { - u32 h = ntohl(key)>>(32 - fz->fz_order); + u32 h = ntohl(key) >> fz->fz_revorder; h ^= (h>>20); h ^= (h>>10); h ^= (h>>5); - h &= FZ_HASHMASK(fz); + h &= fz->fz_hashmask; return h; } @@ -92,7 +93,6 @@ static inline __be32 fz_key(__be32 dst, struct fn_zone *fz) return dst & FZ_MASK(fz); } -static DEFINE_RWLOCK(fib_hash_lock); static unsigned int fib_hash_genid; #define FZ_MAX_DIVISOR ((PAGE_SIZE<<MAX_ORDER) / sizeof(struct hlist_head)) @@ -101,12 +101,11 @@ static struct hlist_head *fz_hash_alloc(int divisor) { unsigned long size = divisor * sizeof(struct hlist_head); - if (size <= PAGE_SIZE) { + if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); - } else { - return (struct hlist_head *) - __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(size)); - } + + return (struct hlist_head *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(size)); } /* The fib hash lock must be held when this is called. */ @@ -121,12 +120,12 @@ static inline void fn_rebuild_zone(struct fn_zone *fz, struct fib_node *f; hlist_for_each_entry_safe(f, node, n, &old_ht[i], fn_hash) { - struct hlist_head *new_head; + struct hlist_head __rcu *new_head; - hlist_del(&f->fn_hash); + hlist_del_rcu(&f->fn_hash); new_head = &fz->fz_hash[fn_hash(f->fn_key, fz)]; - hlist_add_head(&f->fn_hash, new_head); + hlist_add_head_rcu(&f->fn_hash, new_head); } } } @@ -147,14 +146,14 @@ static void fn_rehash_zone(struct fn_zone *fz) int old_divisor, new_divisor; u32 new_hashmask; - old_divisor = fz->fz_divisor; + new_divisor = old_divisor = fz->fz_divisor; switch (old_divisor) { - case 16: - new_divisor = 256; + case EMBEDDED_HASH_SIZE: + new_divisor *= EMBEDDED_HASH_SIZE; break; - case 256: - new_divisor = 1024; + case EMBEDDED_HASH_SIZE*EMBEDDED_HASH_SIZE: + new_divisor *= (EMBEDDED_HASH_SIZE/2); break; default: if ((old_divisor << 1) > FZ_MAX_DIVISOR) { @@ -175,31 +174,55 @@ static void fn_rehash_zone(struct fn_zone *fz) ht = fz_hash_alloc(new_divisor); if (ht) { - write_lock_bh(&fib_hash_lock); + struct fn_zone nfz; + + memcpy(&nfz, fz, sizeof(nfz)); + + write_seqlock_bh(&fz->fz_lock); old_ht = fz->fz_hash; - fz->fz_hash = ht; + nfz.fz_hash = ht; + nfz.fz_hashmask = new_hashmask; + nfz.fz_divisor = new_divisor; + fn_rebuild_zone(&nfz, old_ht, old_divisor); + fib_hash_genid++; + rcu_assign_pointer(fz->fz_hash, ht); fz->fz_hashmask = new_hashmask; fz->fz_divisor = new_divisor; - fn_rebuild_zone(fz, old_ht, old_divisor); - fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); + write_sequnlock_bh(&fz->fz_lock); - fz_hash_free(old_ht, old_divisor); + if (old_ht != fz->fz_embedded_hash) { + synchronize_rcu(); + fz_hash_free(old_ht, old_divisor); + } } } -static inline void fn_free_node(struct fib_node * f) +static void fn_free_node_rcu(struct rcu_head *head) { + struct fib_node *f = container_of(head, struct fib_node, fn_embedded_alias.rcu); + kmem_cache_free(fn_hash_kmem, f); } +static inline void fn_free_node(struct fib_node *f) +{ + call_rcu(&f->fn_embedded_alias.rcu, fn_free_node_rcu); +} + +static void fn_free_alias_rcu(struct rcu_head *head) +{ + struct fib_alias *fa = container_of(head, struct fib_alias, rcu); + + kmem_cache_free(fn_alias_kmem, fa); +} + static inline void fn_free_alias(struct fib_alias *fa, struct fib_node *f) { fib_release_info(fa->fa_info); if (fa == &f->fn_embedded_alias) fa->fa_info = NULL; else - kmem_cache_free(fn_alias_kmem, fa); + call_rcu(&fa->rcu, fn_free_alias_rcu); } static struct fn_zone * @@ -210,68 +233,71 @@ fn_new_zone(struct fn_hash *table, int z) if (!fz) return NULL; - if (z) { - fz->fz_divisor = 16; - } else { - fz->fz_divisor = 1; - } - fz->fz_hashmask = (fz->fz_divisor - 1); - fz->fz_hash = fz_hash_alloc(fz->fz_divisor); - if (!fz->fz_hash) { - kfree(fz); - return NULL; - } + seqlock_init(&fz->fz_lock); + fz->fz_divisor = z ? EMBEDDED_HASH_SIZE : 1; + fz->fz_hashmask = fz->fz_divisor - 1; + fz->fz_hash = fz->fz_embedded_hash; fz->fz_order = z; + fz->fz_revorder = 32 - z; fz->fz_mask = inet_make_mask(z); /* Find the first not empty zone with more specific mask */ - for (i=z+1; i<=32; i++) + for (i = z + 1; i <= 32; i++) if (table->fn_zones[i]) break; - write_lock_bh(&fib_hash_lock); - if (i>32) { + if (i > 32) { /* No more specific masks, we are the first. */ - fz->fz_next = table->fn_zone_list; - table->fn_zone_list = fz; + rcu_assign_pointer(fz->fz_next, + rtnl_dereference(table->fn_zone_list)); + rcu_assign_pointer(table->fn_zone_list, fz); } else { - fz->fz_next = table->fn_zones[i]->fz_next; - table->fn_zones[i]->fz_next = fz; + rcu_assign_pointer(fz->fz_next, + rtnl_dereference(table->fn_zones[i]->fz_next)); + rcu_assign_pointer(table->fn_zones[i]->fz_next, fz); } table->fn_zones[z] = fz; fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); return fz; } int fib_table_lookup(struct fib_table *tb, - const struct flowi *flp, struct fib_result *res) + const struct flowi *flp, struct fib_result *res, + int fib_flags) { int err; struct fn_zone *fz; struct fn_hash *t = (struct fn_hash *)tb->tb_data; - read_lock(&fib_hash_lock); - for (fz = t->fn_zone_list; fz; fz = fz->fz_next) { - struct hlist_head *head; + rcu_read_lock(); + for (fz = rcu_dereference(t->fn_zone_list); + fz != NULL; + fz = rcu_dereference(fz->fz_next)) { + struct hlist_head __rcu *head; struct hlist_node *node; struct fib_node *f; - __be32 k = fz_key(flp->fl4_dst, fz); + __be32 k; + unsigned int seq; - head = &fz->fz_hash[fn_hash(k, fz)]; - hlist_for_each_entry(f, node, head, fn_hash) { - if (f->fn_key != k) - continue; + do { + seq = read_seqbegin(&fz->fz_lock); + k = fz_key(flp->fl4_dst, fz); + + head = &fz->fz_hash[fn_hash(k, fz)]; + hlist_for_each_entry_rcu(f, node, head, fn_hash) { + if (f->fn_key != k) + continue; - err = fib_semantic_match(&f->fn_alias, + err = fib_semantic_match(&f->fn_alias, flp, res, - fz->fz_order); - if (err <= 0) - goto out; - } + fz->fz_order, fib_flags); + if (err <= 0) + goto out; + } + } while (read_seqretry(&fz->fz_lock, seq)); } err = 1; out: - read_unlock(&fib_hash_lock); + rcu_read_unlock(); return err; } @@ -293,11 +319,11 @@ void fib_table_select_default(struct fib_table *tb, last_resort = NULL; order = -1; - read_lock(&fib_hash_lock); - hlist_for_each_entry(f, node, &fz->fz_hash[0], fn_hash) { + rcu_read_lock(); + hlist_for_each_entry_rcu(f, node, &fz->fz_hash[0], fn_hash) { struct fib_alias *fa; - list_for_each_entry(fa, &f->fn_alias, fa_list) { + list_for_each_entry_rcu(fa, &f->fn_alias, fa_list) { struct fib_info *next_fi = fa->fa_info; if (fa->fa_scope != res->scope || @@ -309,7 +335,8 @@ void fib_table_select_default(struct fib_table *tb, if (!next_fi->fib_nh[0].nh_gw || next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) continue; - fa->fa_state |= FA_S_ACCESSED; + + fib_alias_accessed(fa); if (fi == NULL) { if (next_fi != res->fi) @@ -341,7 +368,7 @@ void fib_table_select_default(struct fib_table *tb, fib_result_assign(res, last_resort); tb->tb_default = last_idx; out: - read_unlock(&fib_hash_lock); + rcu_read_unlock(); } /* Insert node F to FZ. */ @@ -349,7 +376,7 @@ static inline void fib_insert_node(struct fn_zone *fz, struct fib_node *f) { struct hlist_head *head = &fz->fz_hash[fn_hash(f->fn_key, fz)]; - hlist_add_head(&f->fn_hash, head); + hlist_add_head_rcu(&f->fn_hash, head); } /* Return the node in FZ matching KEY. */ @@ -359,7 +386,7 @@ static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key) struct hlist_node *node; struct fib_node *f; - hlist_for_each_entry(f, node, head, fn_hash) { + hlist_for_each_entry_rcu(f, node, head, fn_hash) { if (f->fn_key == key) return f; } @@ -367,6 +394,17 @@ static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key) return NULL; } + +static struct fib_alias *fib_fast_alloc(struct fib_node *f) +{ + struct fib_alias *fa = &f->fn_embedded_alias; + + if (fa->fa_info != NULL) + fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); + return fa; +} + +/* Caller must hold RTNL. */ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; @@ -451,7 +489,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) } if (cfg->fc_nlflags & NLM_F_REPLACE) { - struct fib_info *fi_drop; u8 state; fa = fa_first; @@ -460,21 +497,25 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) err = 0; goto out; } - write_lock_bh(&fib_hash_lock); - fi_drop = fa->fa_info; - fa->fa_info = fi; - fa->fa_type = cfg->fc_type; - fa->fa_scope = cfg->fc_scope; + err = -ENOBUFS; + new_fa = fib_fast_alloc(f); + if (new_fa == NULL) + goto out; + + new_fa->fa_tos = fa->fa_tos; + new_fa->fa_info = fi; + new_fa->fa_type = cfg->fc_type; + new_fa->fa_scope = cfg->fc_scope; state = fa->fa_state; - fa->fa_state &= ~FA_S_ACCESSED; + new_fa->fa_state = state & ~FA_S_ACCESSED; fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); + list_replace_rcu(&fa->fa_list, &new_fa->fa_list); - fib_release_info(fi_drop); + fn_free_alias(fa, f); if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); - rtmsg_fib(RTM_NEWROUTE, key, fa, cfg->fc_dst_len, tb->tb_id, - &cfg->fc_nlinfo, NLM_F_REPLACE); + rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, + tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); return 0; } @@ -506,12 +547,10 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) f = new_f; } - new_fa = &f->fn_embedded_alias; - if (new_fa->fa_info != NULL) { - new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); - if (new_fa == NULL) - goto out; - } + new_fa = fib_fast_alloc(f); + if (new_fa == NULL) + goto out; + new_fa->fa_info = fi; new_fa->fa_tos = tos; new_fa->fa_type = cfg->fc_type; @@ -522,13 +561,11 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) * Insert new entry to the list. */ - write_lock_bh(&fib_hash_lock); if (new_f) fib_insert_node(fz, new_f); - list_add_tail(&new_fa->fa_list, + list_add_tail_rcu(&new_fa->fa_list, (fa ? &fa->fa_list : &f->fn_alias)); fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); if (new_f) fz->fz_nent++; @@ -603,14 +640,12 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) tb->tb_id, &cfg->fc_nlinfo, 0); kill_fn = 0; - write_lock_bh(&fib_hash_lock); - list_del(&fa->fa_list); + list_del_rcu(&fa->fa_list); if (list_empty(&f->fn_alias)) { - hlist_del(&f->fn_hash); + hlist_del_rcu(&f->fn_hash); kill_fn = 1; } fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); if (fa->fa_state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); @@ -641,14 +676,12 @@ static int fn_flush_list(struct fn_zone *fz, int idx) struct fib_info *fi = fa->fa_info; if (fi && (fi->fib_flags&RTNH_F_DEAD)) { - write_lock_bh(&fib_hash_lock); - list_del(&fa->fa_list); + list_del_rcu(&fa->fa_list); if (list_empty(&f->fn_alias)) { - hlist_del(&f->fn_hash); + hlist_del_rcu(&f->fn_hash); kill_f = 1; } fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); fn_free_alias(fa, f); found++; @@ -662,13 +695,16 @@ static int fn_flush_list(struct fn_zone *fz, int idx) return found; } +/* caller must hold RTNL. */ int fib_table_flush(struct fib_table *tb) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; struct fn_zone *fz; int found = 0; - for (fz = table->fn_zone_list; fz; fz = fz->fz_next) { + for (fz = rtnl_dereference(table->fn_zone_list); + fz != NULL; + fz = rtnl_dereference(fz->fz_next)) { int i; for (i = fz->fz_divisor - 1; i >= 0; i--) @@ -690,10 +726,10 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, s_i = cb->args[4]; i = 0; - hlist_for_each_entry(f, node, head, fn_hash) { + hlist_for_each_entry_rcu(f, node, head, fn_hash) { struct fib_alias *fa; - list_for_each_entry(fa, &f->fn_alias, fa_list) { + list_for_each_entry_rcu(fa, &f->fn_alias, fa_list) { if (i < s_i) goto next; @@ -711,7 +747,7 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, cb->args[4] = i; return -1; } - next: +next: i++; } } @@ -746,23 +782,26 @@ fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb, int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) { - int m, s_m; + int m = 0, s_m; struct fn_zone *fz; struct fn_hash *table = (struct fn_hash *)tb->tb_data; s_m = cb->args[2]; - read_lock(&fib_hash_lock); - for (fz = table->fn_zone_list, m=0; fz; fz = fz->fz_next, m++) { - if (m < s_m) continue; + rcu_read_lock(); + for (fz = rcu_dereference(table->fn_zone_list); + fz != NULL; + fz = rcu_dereference(fz->fz_next), m++) { + if (m < s_m) + continue; if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) { cb->args[2] = m; - read_unlock(&fib_hash_lock); + rcu_read_unlock(); return -1; } memset(&cb->args[3], 0, sizeof(cb->args) - 3*sizeof(cb->args[0])); } - read_unlock(&fib_hash_lock); + rcu_read_unlock(); cb->args[2] = m; return skb->len; } @@ -825,8 +864,9 @@ static struct fib_alias *fib_get_first(struct seq_file *seq) iter->genid = fib_hash_genid; iter->valid = 1; - for (iter->zone = table->fn_zone_list; iter->zone; - iter->zone = iter->zone->fz_next) { + for (iter->zone = rcu_dereference(table->fn_zone_list); + iter->zone != NULL; + iter->zone = rcu_dereference(iter->zone->fz_next)) { int maxslot; if (!iter->zone->fz_nent) @@ -911,7 +951,7 @@ static struct fib_alias *fib_get_next(struct seq_file *seq) } } - iter->zone = iter->zone->fz_next; + iter->zone = rcu_dereference(iter->zone->fz_next); if (!iter->zone) goto out; @@ -950,11 +990,11 @@ static struct fib_alias *fib_get_idx(struct seq_file *seq, loff_t pos) } static void *fib_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(fib_hash_lock) + __acquires(RCU) { void *v = NULL; - read_lock(&fib_hash_lock); + rcu_read_lock(); if (fib_get_table(seq_file_net(seq), RT_TABLE_MAIN)) v = *pos ? fib_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; return v; @@ -967,15 +1007,16 @@ static void *fib_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void fib_seq_stop(struct seq_file *seq, void *v) - __releases(fib_hash_lock) + __releases(RCU) { - read_unlock(&fib_hash_lock); + rcu_read_unlock(); } static unsigned fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { static const unsigned type2flags[RTN_MAX + 1] = { - [7] = RTF_REJECT, [8] = RTF_REJECT, + [7] = RTF_REJECT, + [8] = RTF_REJECT, }; unsigned flags = type2flags[type]; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 637b133..a29edf2 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -12,17 +12,22 @@ struct fib_alias { u8 fa_type; u8 fa_scope; u8 fa_state; -#ifdef CONFIG_IP_FIB_TRIE struct rcu_head rcu; -#endif }; #define FA_S_ACCESSED 0x01 +/* Dont write on fa_state unless needed, to keep it shared on all cpus */ +static inline void fib_alias_accessed(struct fib_alias *fa) +{ + if (!(fa->fa_state & FA_S_ACCESSED)) + fa->fa_state |= FA_S_ACCESSED; +} + /* Exported by fib_semantics.c */ extern int fib_semantic_match(struct list_head *head, const struct flowi *flp, - struct fib_result *res, int prefixlen); + struct fib_result *res, int prefixlen, int fib_flags); 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 76daeb5..7981a24 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -6,7 +6,7 @@ * IPv4 Forwarding Information Base: policy rules. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - * Thomas Graf <tgraf@suug.ch> + * Thomas Graf <tgraf@suug.ch> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -14,7 +14,7 @@ * 2 of the License, or (at your option) any later version. * * Fixes: - * Rani Assaf : local_rule cannot be deleted + * Rani Assaf : local_rule cannot be deleted * Marc Boucher : routing by fwmark */ @@ -32,8 +32,7 @@ #include <net/ip_fib.h> #include <net/fib_rules.h> -struct fib4_rule -{ +struct fib4_rule { struct fib_rule common; u8 dst_len; u8 src_len; @@ -58,6 +57,7 @@ int fib_lookup(struct net *net, struct flowi *flp, struct fib_result *res) { struct fib_lookup_arg arg = { .result = res, + .flags = FIB_LOOKUP_NOREF, }; int err; @@ -91,10 +91,11 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, goto errout; } - if ((tbl = fib_get_table(rule->fr_net, rule->table)) == NULL) + tbl = fib_get_table(rule->fr_net, rule->table); + if (!tbl) goto errout; - err = fib_table_lookup(tbl, flp, (struct fib_result *) arg->result); + err = fib_table_lookup(tbl, flp, (struct fib_result *) arg->result, arg->flags); if (err > 0) err = -EAGAIN; errout: diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 20f09c5..3e0da3e 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -60,21 +60,30 @@ static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE]; static DEFINE_SPINLOCK(fib_multipath_lock); -#define for_nexthops(fi) { int nhsel; const struct fib_nh * nh; \ -for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) - -#define change_nexthops(fi) { int nhsel; struct fib_nh *nexthop_nh; \ -for (nhsel=0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nexthop_nh++, nhsel++) +#define for_nexthops(fi) { \ + int nhsel; const struct fib_nh *nh; \ + for (nhsel = 0, nh = (fi)->fib_nh; \ + nhsel < (fi)->fib_nhs; \ + nh++, nhsel++) + +#define change_nexthops(fi) { \ + int nhsel; struct fib_nh *nexthop_nh; \ + for (nhsel = 0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ + nhsel < (fi)->fib_nhs; \ + nexthop_nh++, nhsel++) #else /* CONFIG_IP_ROUTE_MULTIPATH */ /* Hope, that gcc will optimize it to get rid of dummy loop */ -#define for_nexthops(fi) { int nhsel = 0; const struct fib_nh * nh = (fi)->fib_nh; \ -for (nhsel=0; nhsel < 1; nhsel++) +#define for_nexthops(fi) { \ + int nhsel; const struct fib_nh *nh = (fi)->fib_nh; \ + for (nhsel = 0; nhsel < 1; nhsel++) -#define change_nexthops(fi) { int nhsel = 0; struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ -for (nhsel=0; nhsel < 1; nhsel++) +#define change_nexthops(fi) { \ + int nhsel; \ + struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ + for (nhsel = 0; nhsel < 1; nhsel++) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -86,63 +95,70 @@ static const struct int error; u8 scope; } fib_props[RTN_MAX + 1] = { - { + [RTN_UNSPEC] = { .error = 0, .scope = RT_SCOPE_NOWHERE, - }, /* RTN_UNSPEC */ - { + }, + [RTN_UNICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_UNICAST */ - { + }, + [RTN_LOCAL] = { .error = 0, .scope = RT_SCOPE_HOST, - }, /* RTN_LOCAL */ - { + }, + [RTN_BROADCAST] = { .error = 0, .scope = RT_SCOPE_LINK, - }, /* RTN_BROADCAST */ - { + }, + [RTN_ANYCAST] = { .error = 0, .scope = RT_SCOPE_LINK, - }, /* RTN_ANYCAST */ - { + }, + [RTN_MULTICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_MULTICAST */ - { + }, + [RTN_BLACKHOLE] = { .error = -EINVAL, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_BLACKHOLE */ - { + }, + [RTN_UNREACHABLE] = { .error = -EHOSTUNREACH, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_UNREACHABLE */ - { + }, + [RTN_PROHIBIT] = { .error = -EACCES, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_PROHIBIT */ - { + }, + [RTN_THROW] = { .error = -EAGAIN, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_THROW */ - { + }, + [RTN_NAT] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE, - }, /* RTN_NAT */ - { + }, + [RTN_XRESOLVE] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE, - }, /* RTN_XRESOLVE */ + }, }; /* Release a nexthop info record */ +static void free_fib_info_rcu(struct rcu_head *head) +{ + struct fib_info *fi = container_of(head, struct fib_info, rcu); + + kfree(fi); +} + void free_fib_info(struct fib_info *fi) { if (fi->fib_dead == 0) { - printk(KERN_WARNING "Freeing alive fib_info %p\n", fi); + pr_warning("Freeing alive fib_info %p\n", fi); return; } change_nexthops(fi) { @@ -152,7 +168,7 @@ void free_fib_info(struct fib_info *fi) } endfor_nexthops(fi); fib_info_cnt--; release_net(fi->fib_net); - kfree(fi); + call_rcu(&fi->rcu, free_fib_info_rcu); } void fib_release_info(struct fib_info *fi) @@ -173,7 +189,7 @@ void fib_release_info(struct fib_info *fi) spin_unlock_bh(&fib_info_lock); } -static __inline__ int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) +static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) { const struct fib_nh *onh = ofi->fib_nh; @@ -187,7 +203,7 @@ static __inline__ int nh_comp(const struct fib_info *fi, const struct fib_info * #ifdef CONFIG_NET_CLS_ROUTE nh->nh_tclassid != onh->nh_tclassid || #endif - ((nh->nh_flags^onh->nh_flags)&~RTNH_F_DEAD)) + ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD)) return -1; onh++; } endfor_nexthops(fi); @@ -238,7 +254,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) nfi->fib_priority == fi->fib_priority && memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(fi->fib_metrics)) == 0 && - ((nfi->fib_flags^fi->fib_flags)&~RTNH_F_DEAD) == 0 && + ((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 && (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0)) return fi; } @@ -247,9 +263,8 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) } /* Check, that the gateway is already configured. - Used only by redirect accept routine. + * Used only by redirect accept routine. */ - int ip_fib_check_default(__be32 gw, struct net_device *dev) { struct hlist_head *head; @@ -264,7 +279,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) hlist_for_each_entry(nh, node, head, nh_hash) { if (nh->nh_dev == dev && nh->nh_gw == gw && - !(nh->nh_flags&RTNH_F_DEAD)) { + !(nh->nh_flags & RTNH_F_DEAD)) { spin_unlock(&fib_info_lock); return 0; } @@ -362,10 +377,10 @@ int fib_detect_death(struct fib_info *fi, int order, } if (state == NUD_REACHABLE) return 0; - if ((state&NUD_VALID) && order != dflt) + if ((state & NUD_VALID) && order != dflt) return 0; - if ((state&NUD_VALID) || - (*last_idx<0 && order > dflt)) { + if ((state & NUD_VALID) || + (*last_idx < 0 && order > dflt)) { *last_resort = fi; *last_idx = order; } @@ -476,75 +491,76 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) /* - Picture - ------- - - Semantics of nexthop is very messy by historical reasons. - We have to take into account, that: - a) gateway can be actually local interface address, - so that gatewayed route is direct. - b) gateway must be on-link address, possibly - described not by an ifaddr, but also by a direct route. - c) If both gateway and interface are specified, they should not - contradict. - d) If we use tunnel routes, gateway could be not on-link. - - Attempt to reconcile all of these (alas, self-contradictory) conditions - results in pretty ugly and hairy code with obscure logic. - - I chose to generalized it instead, so that the size - of code does not increase practically, but it becomes - much more general. - Every prefix is assigned a "scope" value: "host" is local address, - "link" is direct route, - [ ... "site" ... "interior" ... ] - and "universe" is true gateway route with global meaning. - - Every prefix refers to a set of "nexthop"s (gw, oif), - where gw must have narrower scope. This recursion stops - when gw has LOCAL scope or if "nexthop" is declared ONLINK, - which means that gw is forced to be on link. - - Code is still hairy, but now it is apparently logically - consistent and very flexible. F.e. as by-product it allows - to co-exists in peace independent exterior and interior - routing processes. - - Normally it looks as following. - - {universe prefix} -> (gw, oif) [scope link] - | - |-> {link prefix} -> (gw, oif) [scope local] - | - |-> {local prefix} (terminal node) + * Picture + * ------- + * + * Semantics of nexthop is very messy by historical reasons. + * We have to take into account, that: + * a) gateway can be actually local interface address, + * so that gatewayed route is direct. + * b) gateway must be on-link address, possibly + * described not by an ifaddr, but also by a direct route. + * c) If both gateway and interface are specified, they should not + * contradict. + * d) If we use tunnel routes, gateway could be not on-link. + * + * Attempt to reconcile all of these (alas, self-contradictory) conditions + * results in pretty ugly and hairy code with obscure logic. + * + * I chose to generalized it instead, so that the size + * of code does not increase practically, but it becomes + * much more general. + * Every prefix is assigned a "scope" value: "host" is local address, + * "link" is direct route, + * [ ... "site" ... "interior" ... ] + * and "universe" is true gateway route with global meaning. + * + * Every prefix refers to a set of "nexthop"s (gw, oif), + * where gw must have narrower scope. This recursion stops + * when gw has LOCAL scope or if "nexthop" is declared ONLINK, + * which means that gw is forced to be on link. + * + * Code is still hairy, but now it is apparently logically + * consistent and very flexible. F.e. as by-product it allows + * to co-exists in peace independent exterior and interior + * routing processes. + * + * Normally it looks as following. + * + * {universe prefix} -> (gw, oif) [scope link] + * | + * |-> {link prefix} -> (gw, oif) [scope local] + * | + * |-> {local prefix} (terminal node) */ - static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, struct fib_nh *nh) { int err; struct net *net; + struct net_device *dev; net = cfg->fc_nlinfo.nl_net; if (nh->nh_gw) { struct fib_result res; - if (nh->nh_flags&RTNH_F_ONLINK) { - struct net_device *dev; + if (nh->nh_flags & RTNH_F_ONLINK) { if (cfg->fc_scope >= RT_SCOPE_LINK) return -EINVAL; if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST) return -EINVAL; - if ((dev = __dev_get_by_index(net, nh->nh_oif)) == NULL) + dev = __dev_get_by_index(net, nh->nh_oif); + if (!dev) return -ENODEV; - if (!(dev->flags&IFF_UP)) + if (!(dev->flags & IFF_UP)) return -ENETDOWN; nh->nh_dev = dev; dev_hold(dev); nh->nh_scope = RT_SCOPE_LINK; return 0; } + rcu_read_lock(); { struct flowi fl = { .nl_u = { @@ -559,50 +575,53 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, /* It is not necessary, but requires a bit of thinking */ if (fl.fl4_scope < RT_SCOPE_LINK) fl.fl4_scope = RT_SCOPE_LINK; - if ((err = fib_lookup(net, &fl, &res)) != 0) + err = fib_lookup(net, &fl, &res); + if (err) { + rcu_read_unlock(); return err; + } } err = -EINVAL; if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) goto out; nh->nh_scope = res.scope; nh->nh_oif = FIB_RES_OIF(res); - if ((nh->nh_dev = FIB_RES_DEV(res)) == NULL) + nh->nh_dev = dev = FIB_RES_DEV(res); + if (!dev) goto out; - dev_hold(nh->nh_dev); - err = -ENETDOWN; - if (!(nh->nh_dev->flags & IFF_UP)) - goto out; - err = 0; -out: - fib_res_put(&res); - return err; + dev_hold(dev); + err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN; } else { struct in_device *in_dev; - if (nh->nh_flags&(RTNH_F_PERVASIVE|RTNH_F_ONLINK)) + if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) return -EINVAL; + rcu_read_lock(); + err = -ENODEV; in_dev = inetdev_by_index(net, nh->nh_oif); if (in_dev == NULL) - return -ENODEV; - if (!(in_dev->dev->flags&IFF_UP)) { - in_dev_put(in_dev); - return -ENETDOWN; - } + goto out; + err = -ENETDOWN; + if (!(in_dev->dev->flags & IFF_UP)) + goto out; nh->nh_dev = in_dev->dev; dev_hold(nh->nh_dev); nh->nh_scope = RT_SCOPE_HOST; - in_dev_put(in_dev); + err = 0; } - return 0; +out: + rcu_read_unlock(); + return err; } static inline unsigned int fib_laddr_hashfn(__be32 val) { unsigned int mask = (fib_hash_size - 1); - return ((__force u32)val ^ ((__force u32)val >> 7) ^ ((__force u32)val >> 14)) & mask; + return ((__force u32)val ^ + ((__force u32)val >> 7) ^ + ((__force u32)val >> 14)) & mask; } static struct hlist_head *fib_hash_alloc(int bytes) @@ -611,7 +630,8 @@ static struct hlist_head *fib_hash_alloc(int bytes) return kzalloc(bytes, GFP_KERNEL); else return (struct hlist_head *) - __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(bytes)); + __get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(bytes)); } static void fib_hash_free(struct hlist_head *hash, int bytes) @@ -806,7 +826,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto failure; } else { change_nexthops(fi) { - if ((err = fib_check_nh(cfg, fi, nexthop_nh)) != 0) + err = fib_check_nh(cfg, fi, nexthop_nh); + if (err != 0) goto failure; } endfor_nexthops(fi) } @@ -819,7 +840,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } link_it: - if ((ofi = fib_find_info(fi)) != NULL) { + ofi = fib_find_info(fi); + if (ofi) { fi->fib_dead = 1; free_fib_info(fi); ofi->fib_treeref++; @@ -864,7 +886,7 @@ 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, int prefixlen) + struct fib_result *res, int prefixlen, int fib_flags) { struct fib_alias *fa; int nh_sel = 0; @@ -879,7 +901,7 @@ int fib_semantic_match(struct list_head *head, const struct flowi *flp, if (fa->fa_scope < flp->fl4_scope) continue; - fa->fa_state |= FA_S_ACCESSED; + fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (err == 0) { @@ -895,7 +917,7 @@ int fib_semantic_match(struct list_head *head, const struct flowi *flp, case RTN_ANYCAST: case RTN_MULTICAST: for_nexthops(fi) { - if (nh->nh_flags&RTNH_F_DEAD) + if (nh->nh_flags & RTNH_F_DEAD) continue; if (!flp->oif || flp->oif == nh->nh_oif) break; @@ -906,16 +928,15 @@ int fib_semantic_match(struct list_head *head, const struct flowi *flp, goto out_fill_res; } #else - if (nhsel < 1) { + if (nhsel < 1) goto out_fill_res; - } #endif endfor_nexthops(fi); continue; default: - printk(KERN_WARNING "fib_semantic_match bad type %#x\n", - fa->fa_type); + pr_warning("fib_semantic_match bad type %#x\n", + fa->fa_type); return -EINVAL; } } @@ -929,7 +950,8 @@ out_fill_res: res->type = fa->fa_type; res->scope = fa->fa_scope; res->fi = fa->fa_info; - atomic_inc(&res->fi->fib_clntref); + if (!(fib_flags & FIB_LOOKUP_NOREF)) + atomic_inc(&res->fi->fib_clntref); return 0; } @@ -1028,10 +1050,10 @@ nla_put_failure: } /* - Update FIB if: - - local address disappeared -> we must delete all the entries - referring to it. - - device went down -> we must shutdown all nexthops going via it. + * Update FIB if: + * - local address disappeared -> we must delete all the entries + * referring to it. + * - device went down -> we must shutdown all nexthops going via it. */ int fib_sync_down_addr(struct net *net, __be32 local) { @@ -1078,7 +1100,7 @@ int fib_sync_down_dev(struct net_device *dev, int force) prev_fi = fi; dead = 0; change_nexthops(fi) { - if (nexthop_nh->nh_flags&RTNH_F_DEAD) + if (nexthop_nh->nh_flags & RTNH_F_DEAD) dead++; else if (nexthop_nh->nh_dev == dev && nexthop_nh->nh_scope != scope) { @@ -1110,10 +1132,9 @@ int fib_sync_down_dev(struct net_device *dev, int force) #ifdef CONFIG_IP_ROUTE_MULTIPATH /* - Dead device goes up. We wake up dead nexthops. - It takes sense only on multipath routes. + * Dead device goes up. We wake up dead nexthops. + * It takes sense only on multipath routes. */ - int fib_sync_up(struct net_device *dev) { struct fib_info *prev_fi; @@ -1123,7 +1144,7 @@ int fib_sync_up(struct net_device *dev) struct fib_nh *nh; int ret; - if (!(dev->flags&IFF_UP)) + if (!(dev->flags & IFF_UP)) return 0; prev_fi = NULL; @@ -1142,12 +1163,12 @@ int fib_sync_up(struct net_device *dev) prev_fi = fi; alive = 0; change_nexthops(fi) { - if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) { + if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) { alive++; continue; } if (nexthop_nh->nh_dev == NULL || - !(nexthop_nh->nh_dev->flags&IFF_UP)) + !(nexthop_nh->nh_dev->flags & IFF_UP)) continue; if (nexthop_nh->nh_dev != dev || !__in_dev_get_rtnl(dev)) @@ -1169,10 +1190,9 @@ int fib_sync_up(struct net_device *dev) } /* - The algorithm is suboptimal, but it provides really - fair weighted route distribution. + * The algorithm is suboptimal, but it provides really + * fair weighted route distribution. */ - void fib_select_multipath(const struct flowi *flp, struct fib_result *res) { struct fib_info *fi = res->fi; @@ -1182,7 +1202,7 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res) if (fi->fib_power <= 0) { int power = 0; change_nexthops(fi) { - if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) { + if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) { power += nexthop_nh->nh_weight; nexthop_nh->nh_power = nexthop_nh->nh_weight; } @@ -1198,15 +1218,16 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res) /* w should be random number [0..fi->fib_power-1], - it is pretty bad approximation. + * it is pretty bad approximation. */ w = jiffies % fi->fib_power; change_nexthops(fi) { - if (!(nexthop_nh->nh_flags&RTNH_F_DEAD) && + if (!(nexthop_nh->nh_flags & RTNH_F_DEAD) && nexthop_nh->nh_power) { - if ((w -= nexthop_nh->nh_power) <= 0) { + w -= nexthop_nh->nh_power; + if (w <= 0) { nexthop_nh->nh_power--; fi->fib_power--; res->nh_sel = nhsel; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index a96e5ec..cd5e13a 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1342,7 +1342,7 @@ err: /* should be called with rcu_read_lock */ static int check_leaf(struct trie *t, struct leaf *l, t_key key, const struct flowi *flp, - struct fib_result *res) + struct fib_result *res, int fib_flags) { struct leaf_info *li; struct hlist_head *hhead = &l->list; @@ -1356,7 +1356,7 @@ 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, plen); + err = fib_semantic_match(&li->falh, flp, res, plen, fib_flags); #ifdef CONFIG_IP_FIB_TRIE_STATS if (err <= 0) @@ -1372,7 +1372,7 @@ static int check_leaf(struct trie *t, struct leaf *l, } int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, - struct fib_result *res) + struct fib_result *res, int fib_flags) { struct trie *t = (struct trie *) tb->tb_data; int ret; @@ -1384,8 +1384,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, t_key cindex = 0; int current_prefix_length = KEYLENGTH; struct tnode *cn; - t_key node_prefix, key_prefix, pref_mismatch; - int mp; + t_key pref_mismatch; rcu_read_lock(); @@ -1399,7 +1398,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, /* Just a leaf? */ if (IS_LEAF(n)) { - ret = check_leaf(t, (struct leaf *)n, key, flp, res); + ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags); goto found; } @@ -1424,7 +1423,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, } if (IS_LEAF(n)) { - ret = check_leaf(t, (struct leaf *)n, key, flp, res); + ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags); if (ret > 0) goto backtrace; goto found; @@ -1500,10 +1499,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, * matching prefix. */ - node_prefix = mask_pfx(cn->key, cn->pos); - key_prefix = mask_pfx(key, cn->pos); - pref_mismatch = key_prefix^node_prefix; - mp = 0; + pref_mismatch = mask_pfx(cn->key ^ key, cn->pos); /* * In short: If skipped bits in this node do not match @@ -1511,13 +1507,9 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, * state.directly. */ if (pref_mismatch) { - while (!(pref_mismatch & (1<<(KEYLENGTH-1)))) { - mp++; - pref_mismatch = pref_mismatch << 1; - } - key_prefix = tkey_extract_bits(cn->key, mp, cn->pos-mp); + int mp = KEYLENGTH - fls(pref_mismatch); - if (key_prefix != 0) + if (tkey_extract_bits(cn->key, mp, cn->pos - mp) != 0) goto backtrace; if (current_prefix_length >= cn->pos) @@ -1846,7 +1838,8 @@ void fib_table_select_default(struct fib_table *tb, if (!next_fi->fib_nh[0].nh_gw || next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) continue; - fa->fa_state |= FA_S_ACCESSED; + + fib_alias_accessed(fa); if (fi == NULL) { if (next_fi != res->fi) diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index b546736..caea688 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -22,7 +22,7 @@ #include <net/gre.h> -const struct gre_protocol *gre_proto[GREPROTO_MAX] __read_mostly; +static const struct gre_protocol *gre_proto[GREPROTO_MAX] __read_mostly; static DEFINE_SPINLOCK(gre_proto_lock); int gre_add_protocol(const struct gre_protocol *proto, u8 version) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a1ad0e7..c8877c6 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -856,6 +856,18 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, igmpv3_clear_delrec(in_dev); } else if (len < 12) { return; /* ignore bogus packet; freed by caller */ + } else if (IGMP_V1_SEEN(in_dev)) { + /* This is a v3 query with v1 queriers present */ + max_delay = IGMP_Query_Response_Interval; + group = 0; + } else if (IGMP_V2_SEEN(in_dev)) { + /* this is a v3 query with v2 queriers present; + * Interpretation of the max_delay code is problematic here. + * A real v2 host would use ih_code directly, while v3 has a + * different encoding. We use the v3 encoding as more likely + * to be intended in a v3 query. + */ + max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return; @@ -1257,14 +1269,14 @@ void ip_mc_rejoin_group(struct ip_mc_list *im) if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { - igmp_mod_timer(im, IGMP_Initial_Report_Delay); - return; - } - /* else, v3 */ - im->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; - igmp_ifc_event(in_dev); + /* a failover is happening and switches + * must be notified immediately */ + if (IGMP_V1_SEEN(in_dev)) + igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); + else if (IGMP_V2_SEEN(in_dev)) + igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); + else + igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); #endif } EXPORT_SYMBOL(ip_mc_rejoin_group); @@ -1406,6 +1418,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) write_unlock_bh(&in_dev->mc_list_lock); } +/* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct flowi fl = { .nl_u = { .ip4_u = @@ -1416,15 +1429,12 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); - if (idev) - __in_dev_put(idev); return idev; } if (imr->imr_address.s_addr) { - dev = ip_dev_find(net, imr->imr_address.s_addr); + dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; - dev_put(dev); } if (!dev && !ip_route_output_key(net, &rt, &fl)) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e5fa2dd..ba80426 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -425,7 +425,7 @@ static int inet_diag_bc_run(const void *bc, int len, bc += op->no; } } - return (len == 0); + return len == 0; } static int valid_cc(const void *bc, int len, int cc) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index f4dc879..1684408 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -116,11 +116,11 @@ static int ip4_frag_match(struct inet_frag_queue *q, void *a) struct ip4_create_arg *arg = a; qp = container_of(q, struct ipq, q); - return (qp->id == arg->iph->id && + return qp->id == arg->iph->id && qp->saddr == arg->iph->saddr && qp->daddr == arg->iph->daddr && qp->protocol == arg->iph->protocol && - qp->user == arg->user); + qp->user == arg->user; } /* Memory Tracking Functions. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8517689..d0ffcbe 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -46,7 +46,7 @@ #include <net/rtnetlink.h> #include <net/gre.h> -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> @@ -64,13 +64,13 @@ We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), - and silently drop packet when it expires. It is the best + and silently drop packet when it expires. It is a good solution, but it supposes maintaing new variable in ALL skb, even if no tunneling is used. - Current solution: HARD_TX_LOCK lock breaks dead loops. - - + Current solution: xmit_recursion breaks dead loops. This is a percpu + counter, since when we enter the first ndo_xmit(), cpu migration is + forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, @@ -129,7 +129,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev); static int ipgre_net_id __read_mostly; struct ipgre_net { - struct ip_tunnel *tunnels[4][HASH_SIZE]; + struct ip_tunnel __rcu *tunnels[4][HASH_SIZE]; struct net_device *fb_tunnel_dev; }; @@ -159,13 +159,40 @@ struct ipgre_net { #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] /* - * Locking : hash tables are protected by RCU and a spinlock + * Locking : hash tables are protected by RCU and RTNL */ -static DEFINE_SPINLOCK(ipgre_lock); #define for_each_ip_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + +static struct net_device_stats *ipgre_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} + /* Given src, dst and key, find appropriate for input tunnel. */ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, @@ -174,8 +201,8 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, { struct net *net = dev_net(dev); int link = dev->ifindex; - unsigned h0 = HASH(remote); - unsigned h1 = HASH(key); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(key); struct ip_tunnel *t, *cand = NULL; struct ipgre_net *ign = net_generic(net, ipgre_net_id); int dev_type = (gre_proto == htons(ETH_P_TEB)) ? @@ -290,13 +317,13 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, return NULL; } -static struct ip_tunnel **__ipgre_bucket(struct ipgre_net *ign, +static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign, struct ip_tunnel_parm *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; __be32 key = parms->i_key; - unsigned h = HASH(key); + unsigned int h = HASH(key); int prio = 0; if (local) @@ -309,7 +336,7 @@ static struct ip_tunnel **__ipgre_bucket(struct ipgre_net *ign, return &ign->tunnels[prio][h]; } -static inline struct ip_tunnel **ipgre_bucket(struct ipgre_net *ign, +static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign, struct ip_tunnel *t) { return __ipgre_bucket(ign, &t->parms); @@ -317,23 +344,22 @@ static inline struct ip_tunnel **ipgre_bucket(struct ipgre_net *ign, static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t) { - struct ip_tunnel **tp = ipgre_bucket(ign, t); + struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t); - spin_lock_bh(&ipgre_lock); - t->next = *tp; + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); - spin_unlock_bh(&ipgre_lock); } static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t) { - struct ip_tunnel **tp; - - for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) { - if (t == *tp) { - spin_lock_bh(&ipgre_lock); - *tp = t->next; - spin_unlock_bh(&ipgre_lock); + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = ipgre_bucket(ign, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } @@ -347,10 +373,13 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net, __be32 local = parms->iph.saddr; __be32 key = parms->i_key; int link = parms->link; - struct ip_tunnel *t, **tp; + struct ip_tunnel *t; + struct ip_tunnel __rcu **tp; struct ipgre_net *ign = net_generic(net, ipgre_net_id); - for (tp = __ipgre_bucket(ign, parms); (t = *tp) != NULL; tp = &t->next) + for (tp = __ipgre_bucket(ign, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && key == t->parms.i_key && @@ -361,7 +390,7 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net, return t; } -static struct ip_tunnel * ipgre_tunnel_locate(struct net *net, +static struct ip_tunnel *ipgre_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { struct ip_tunnel *t, *nt; @@ -583,7 +612,7 @@ static int ipgre_rcv(struct sk_buff *skb) if ((tunnel = ipgre_tunnel_lookup(skb->dev, iph->saddr, iph->daddr, key, gre_proto))) { - struct net_device_stats *stats = &tunnel->dev->stats; + struct pcpu_tstats *tstats; secpath_reset(skb); @@ -607,22 +636,22 @@ static int ipgre_rcv(struct sk_buff *skb) /* Looped back packet, drop it! */ if (skb_rtable(skb)->fl.iif == 0) goto drop; - stats->multicast++; + tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; } #endif if (((flags&GRE_CSUM) && csum) || (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) { - stats->rx_crc_errors++; - stats->rx_errors++; + tunnel->dev->stats.rx_crc_errors++; + tunnel->dev->stats.rx_errors++; goto drop; } if (tunnel->parms.i_flags&GRE_SEQ) { if (!(flags&GRE_SEQ) || (tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) { - stats->rx_fifo_errors++; - stats->rx_errors++; + tunnel->dev->stats.rx_fifo_errors++; + tunnel->dev->stats.rx_errors++; goto drop; } tunnel->i_seqno = seqno + 1; @@ -631,8 +660,8 @@ static int ipgre_rcv(struct sk_buff *skb) /* Warning: All skb pointers will be invalidated! */ if (tunnel->dev->type == ARPHRD_ETHER) { if (!pskb_may_pull(skb, ETH_HLEN)) { - stats->rx_length_errors++; - stats->rx_errors++; + tunnel->dev->stats.rx_length_errors++; + tunnel->dev->stats.rx_errors++; goto drop; } @@ -641,14 +670,19 @@ static int ipgre_rcv(struct sk_buff *skb) skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } - skb_tunnel_rx(skb, tunnel->dev); + tstats = this_cpu_ptr(tunnel->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + __skb_tunnel_rx(skb, tunnel->dev); skb_reset_network_header(skb); ipgre_ecn_decapsulate(iph, skb); netif_rx(skb); + rcu_read_unlock(); - return(0); + return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); @@ -656,20 +690,19 @@ drop: rcu_read_unlock(); drop_nolock: kfree_skb(skb); - return(0); + return 0; } static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct pcpu_tstats *tstats; struct iphdr *old_iph = ip_hdr(skb); struct iphdr *tiph; u8 tos; __be16 df; struct rtable *rt; /* Route to the other host */ - struct net_device *tdev; /* Device to other host */ + struct net_device *tdev; /* Device to other host */ struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int gre_hlen; @@ -691,7 +724,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev /* NBMA tunnel */ if (skb_dst(skb) == NULL) { - stats->tx_fifo_errors++; + dev->stats.tx_fifo_errors++; goto tx_error; } @@ -700,7 +733,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if ((dst = rt->rt_gateway) == 0) goto tx_error_icmp; } -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; int addr_type; @@ -737,14 +770,20 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } { - struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { .ip4_u = - { .daddr = dst, - .saddr = tiph->saddr, - .tos = RT_TOS(tos) } }, - .proto = IPPROTO_GRE }; + struct flowi fl = { + .oif = tunnel->parms.link, + .nl_u = { + .ip4_u = { + .daddr = dst, + .saddr = tiph->saddr, + .tos = RT_TOS(tos) + } + }, + .proto = IPPROTO_GRE + } +; if (ip_route_output_key(dev_net(dev), &rt, &fl)) { - stats->tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error; } } @@ -752,7 +791,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (tdev == dev) { ip_rt_put(rt); - stats->collisions++; + dev->stats.collisions++; goto tx_error; } @@ -775,7 +814,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev goto tx_error; } } -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); @@ -815,7 +854,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev dev->needed_headroom = max_headroom; if (!new_skb) { ip_rt_put(rt); - txq->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -851,7 +890,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if ((iph->ttl = tiph->ttl) == 0) { if (skb->protocol == htons(ETH_P_IP)) iph->ttl = old_iph->ttl; -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit; #endif @@ -882,15 +921,15 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } nf_reset(skb); - - IPTUNNEL_XMIT(); + tstats = this_cpu_ptr(dev->tstats); + __IPTUNNEL_XMIT(tstats, &dev->stats); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: - stats->tx_errors++; + dev->stats.tx_errors++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -910,13 +949,19 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) /* Guess output device to choose reasonable mtu and needed_headroom */ if (iph->daddr) { - struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { .ip4_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, - .tos = RT_TOS(iph->tos) } }, - .proto = IPPROTO_GRE }; + struct flowi fl = { + .oif = tunnel->parms.link, + .nl_u = { + .ip4_u = { + .daddr = iph->daddr, + .saddr = iph->saddr, + .tos = RT_TOS(iph->tos) + } + }, + .proto = IPPROTO_GRE + }; struct rtable *rt; + if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { tdev = rt->dst.dev; ip_rt_put(rt); @@ -1013,7 +1058,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } } else { - unsigned nflags = 0; + unsigned int nflags = 0; t = netdev_priv(dev); @@ -1126,7 +1171,7 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu) static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *daddr, const void *saddr, unsigned len) + const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen); @@ -1168,13 +1213,19 @@ static int ipgre_open(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { - struct flowi fl = { .oif = t->parms.link, - .nl_u = { .ip4_u = - { .daddr = t->parms.iph.daddr, - .saddr = t->parms.iph.saddr, - .tos = RT_TOS(t->parms.iph.tos) } }, - .proto = IPPROTO_GRE }; + struct flowi fl = { + .oif = t->parms.link, + .nl_u = { + .ip4_u = { + .daddr = t->parms.iph.daddr, + .saddr = t->parms.iph.saddr, + .tos = RT_TOS(t->parms.iph.tos) + } + }, + .proto = IPPROTO_GRE + }; struct rtable *rt; + if (ip_route_output_key(dev_net(dev), &rt, &fl)) return -EADDRNOTAVAIL; dev = rt->dst.dev; @@ -1194,10 +1245,8 @@ static int ipgre_close(struct net_device *dev) if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; in_dev = inetdev_by_index(dev_net(dev), t->mlink); - if (in_dev) { + if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); - in_dev_put(in_dev); - } } return 0; } @@ -1214,12 +1263,19 @@ static const struct net_device_ops ipgre_netdev_ops = { .ndo_start_xmit = ipgre_tunnel_xmit, .ndo_do_ioctl = ipgre_tunnel_ioctl, .ndo_change_mtu = ipgre_tunnel_change_mtu, + .ndo_get_stats = ipgre_get_stats, }; +static void ipgre_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ipgre_dev_free; dev->type = ARPHRD_IPGRE; dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4; @@ -1257,6 +1313,10 @@ static int ipgre_tunnel_init(struct net_device *dev) } else dev->header_ops = &ipgre_header_ops; + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + return 0; } @@ -1275,7 +1335,7 @@ static void ipgre_fb_tunnel_init(struct net_device *dev) tunnel->hlen = sizeof(struct iphdr) + 4; dev_hold(dev); - ign->tunnels_wc[0] = tunnel; + rcu_assign_pointer(ign->tunnels_wc[0], tunnel); } @@ -1291,11 +1351,13 @@ static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head) for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t = ign->tunnels[prio][h]; + struct ip_tunnel *t; + + t = rtnl_dereference(ign->tunnels[prio][h]); while (t != NULL) { unregister_netdevice_queue(t->dev, head); - t = t->next; + t = rtnl_dereference(t->next); } } } @@ -1441,6 +1503,10 @@ static int ipgre_tap_init(struct net_device *dev) ipgre_tunnel_bind_dev(dev); + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + return 0; } @@ -1451,6 +1517,7 @@ static const struct net_device_ops ipgre_tap_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ipgre_tunnel_change_mtu, + .ndo_get_stats = ipgre_get_stats, }; static void ipgre_tap_setup(struct net_device *dev) @@ -1459,7 +1526,7 @@ static void ipgre_tap_setup(struct net_device *dev) ether_setup(dev); dev->netdev_ops = &ipgre_tap_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ipgre_dev_free; dev->iflink = 0; dev->features |= NETIF_F_NETNS_LOCAL; @@ -1487,6 +1554,10 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nla if (!tb[IFLA_MTU]) dev->mtu = mtu; + /* Can use a lockless transmit, unless we generate output sequences */ + if (!(nt->parms.o_flags & GRE_SEQ)) + dev->features |= NETIF_F_LLTX; + err = register_netdevice(dev); if (err) goto out; @@ -1522,7 +1593,7 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], t = nt; if (dev->type != ARPHRD_ETHER) { - unsigned nflags = 0; + unsigned int nflags = 0; if (ipv4_is_multicast(p.iph.daddr)) nflags = IFF_BROADCAST; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ba9836c..1906fa3 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -466,7 +466,7 @@ error: } return -EINVAL; } - +EXPORT_SYMBOL(ip_options_compile); /* * Undo all the changes done by ip_options_compile(). @@ -646,3 +646,4 @@ int ip_options_rcv_srr(struct sk_buff *skb) } return 0; } +EXPORT_SYMBOL(ip_options_rcv_srr); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e427620..439d2a3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -488,9 +488,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) * we can switch to copy when see the first bad fragment. */ if (skb_has_frag_list(skb)) { - struct sk_buff *frag; + struct sk_buff *frag, *frag2; int first_len = skb_pagelen(skb); - int truesizes = 0; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || @@ -503,18 +502,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } - truesizes += frag->truesize; + skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ @@ -524,7 +523,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); skb->data_len = first_len - skb_headlen(skb); - skb->truesize -= truesizes; skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); @@ -576,6 +574,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) } IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: @@ -926,16 +933,19 @@ alloc_new_skb: !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else - alloclen = datalen + fragheaderlen; + alloclen = fraglen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ - if (datalen == length + fraggap) + if (datalen == length + fraggap) { alloclen += rt->dst.trailer_len; - + /* make sure mtu is not reached */ + if (datalen > mtu - fragheaderlen - rt->dst.trailer_len) + datalen -= ALIGN(rt->dst.trailer_len, 8); + } if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len + 15, diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6c40a8c..64b70ad 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1129,6 +1129,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_HDRINCL: val = inet->hdrincl; break; + case IP_NODEFRAG: + val = inet->nodefrag; + break; case IP_MTU_DISCOVER: val = inet->pmtudisc; break; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 3c6f8f3..e9b816e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -122,31 +122,59 @@ static int ipip_net_id __read_mostly; struct ipip_net { - struct ip_tunnel *tunnels_r_l[HASH_SIZE]; - struct ip_tunnel *tunnels_r[HASH_SIZE]; - struct ip_tunnel *tunnels_l[HASH_SIZE]; - struct ip_tunnel *tunnels_wc[1]; - struct ip_tunnel **tunnels[4]; + struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_wc[1]; + struct ip_tunnel __rcu **tunnels[4]; struct net_device *fb_tunnel_dev; }; -static void ipip_tunnel_init(struct net_device *dev); +static int ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); +static void ipip_dev_free(struct net_device *dev); /* - * Locking : hash tables are protected by RCU and a spinlock + * Locking : hash tables are protected by RCU and RTNL */ -static DEFINE_SPINLOCK(ipip_lock); #define for_each_ip_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + +static struct net_device_stats *ipip_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} + static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, __be32 remote, __be32 local) { - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(local); struct ip_tunnel *t; struct ipip_net *ipn = net_generic(net, ipip_net_id); @@ -169,12 +197,12 @@ static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, return NULL; } -static struct ip_tunnel **__ipip_bucket(struct ipip_net *ipn, +static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn, struct ip_tunnel_parm *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; - unsigned h = 0; + unsigned int h = 0; int prio = 0; if (remote) { @@ -188,7 +216,7 @@ static struct ip_tunnel **__ipip_bucket(struct ipip_net *ipn, return &ipn->tunnels[prio][h]; } -static inline struct ip_tunnel **ipip_bucket(struct ipip_net *ipn, +static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn, struct ip_tunnel *t) { return __ipip_bucket(ipn, &t->parms); @@ -196,13 +224,14 @@ static inline struct ip_tunnel **ipip_bucket(struct ipip_net *ipn, static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t) { - struct ip_tunnel **tp; - - for (tp = ipip_bucket(ipn, t); *tp; tp = &(*tp)->next) { - if (t == *tp) { - spin_lock_bh(&ipip_lock); - *tp = t->next; - spin_unlock_bh(&ipip_lock); + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = ipip_bucket(ipn, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } @@ -210,12 +239,10 @@ static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t) static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) { - struct ip_tunnel **tp = ipip_bucket(ipn, t); + struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t); - spin_lock_bh(&ipip_lock); - t->next = *tp; + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); - spin_unlock_bh(&ipip_lock); } static struct ip_tunnel * ipip_tunnel_locate(struct net *net, @@ -223,12 +250,15 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; - struct ip_tunnel *t, **tp, *nt; + struct ip_tunnel *t, *nt; + struct ip_tunnel __rcu **tp; struct net_device *dev; char name[IFNAMSIZ]; struct ipip_net *ipn = net_generic(net, ipip_net_id); - for (tp = __ipip_bucket(ipn, parms); (t = *tp) != NULL; tp = &t->next) { + for (tp = __ipip_bucket(ipn, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) return t; } @@ -238,7 +268,7 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, if (parms->name[0]) strlcpy(name, parms->name, IFNAMSIZ); else - sprintf(name, "tunl%%d"); + strcpy(name, "tunl%d"); dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup); if (dev == NULL) @@ -254,7 +284,8 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - ipip_tunnel_init(dev); + if (ipip_tunnel_init(dev) < 0) + goto failed_free; if (register_netdevice(dev) < 0) goto failed_free; @@ -264,20 +295,19 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, return nt; failed_free: - free_netdev(dev); + ipip_dev_free(dev); return NULL; } +/* called with RTNL */ static void ipip_tunnel_uninit(struct net_device *dev) { struct net *net = dev_net(dev); struct ipip_net *ipn = net_generic(net, ipip_net_id); - if (dev == ipn->fb_tunnel_dev) { - spin_lock_bh(&ipip_lock); - ipn->tunnels_wc[0] = NULL; - spin_unlock_bh(&ipip_lock); - } else + if (dev == ipn->fb_tunnel_dev) + rcu_assign_pointer(ipn->tunnels_wc[0], NULL); + else ipip_tunnel_unlink(ipn, netdev_priv(dev)); dev_put(dev); } @@ -359,8 +389,10 @@ static int ipip_rcv(struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); rcu_read_lock(); - if ((tunnel = ipip_tunnel_lookup(dev_net(skb->dev), - iph->saddr, iph->daddr)) != NULL) { + tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); + if (tunnel != NULL) { + struct pcpu_tstats *tstats; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { rcu_read_unlock(); kfree_skb(skb); @@ -374,10 +406,16 @@ static int ipip_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); skb->pkt_type = PACKET_HOST; - skb_tunnel_rx(skb, tunnel->dev); + tstats = this_cpu_ptr(tunnel->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + __skb_tunnel_rx(skb, tunnel->dev); ipip_ecn_decapsulate(iph, skb); + netif_rx(skb); + rcu_read_unlock(); return 0; } @@ -394,13 +432,12 @@ static int ipip_rcv(struct sk_buff *skb) static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct pcpu_tstats *tstats; struct iphdr *tiph = &tunnel->parms.iph; u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ - struct net_device *tdev; /* Device to other host */ + struct net_device *tdev; /* Device to other host */ struct iphdr *old_iph = ip_hdr(skb); struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ @@ -410,13 +447,13 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->protocol != htons(ETH_P_IP)) goto tx_error; - if (tos&1) + if (tos & 1) tos = old_iph->tos; if (!dst) { /* NBMA tunnel */ if ((rt = skb_rtable(skb)) == NULL) { - stats->tx_fifo_errors++; + dev->stats.tx_fifo_errors++; goto tx_error; } if ((dst = rt->rt_gateway) == 0) @@ -424,14 +461,20 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } { - struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { .ip4_u = - { .daddr = dst, - .saddr = tiph->saddr, - .tos = RT_TOS(tos) } }, - .proto = IPPROTO_IPIP }; + struct flowi fl = { + .oif = tunnel->parms.link, + .nl_u = { + .ip4_u = { + .daddr = dst, + .saddr = tiph->saddr, + .tos = RT_TOS(tos) + } + }, + .proto = IPPROTO_IPIP + }; + if (ip_route_output_key(dev_net(dev), &rt, &fl)) { - stats->tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error_icmp; } } @@ -439,7 +482,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (tdev == dev) { ip_rt_put(rt); - stats->collisions++; + dev->stats.collisions++; goto tx_error; } @@ -449,7 +492,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { - stats->collisions++; + dev->stats.collisions++; ip_rt_put(rt); goto tx_error; } @@ -485,7 +528,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - txq->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -522,14 +565,14 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) iph->ttl = old_iph->ttl; nf_reset(skb); - - IPTUNNEL_XMIT(); + tstats = this_cpu_ptr(dev->tstats); + __IPTUNNEL_XMIT(tstats, &dev->stats); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: - stats->tx_errors++; + dev->stats.tx_errors++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -544,13 +587,19 @@ static void ipip_tunnel_bind_dev(struct net_device *dev) iph = &tunnel->parms.iph; if (iph->daddr) { - struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { .ip4_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, - .tos = RT_TOS(iph->tos) } }, - .proto = IPPROTO_IPIP }; + struct flowi fl = { + .oif = tunnel->parms.link, + .nl_u = { + .ip4_u = { + .daddr = iph->daddr, + .saddr = iph->saddr, + .tos = RT_TOS(iph->tos) + } + }, + .proto = IPPROTO_IPIP + }; struct rtable *rt; + if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { tdev = rt->dst.dev; ip_rt_put(rt); @@ -696,13 +745,19 @@ static const struct net_device_ops ipip_netdev_ops = { .ndo_start_xmit = ipip_tunnel_xmit, .ndo_do_ioctl = ipip_tunnel_ioctl, .ndo_change_mtu = ipip_tunnel_change_mtu, - + .ndo_get_stats = ipip_get_stats, }; +static void ipip_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ipip_dev_free; dev->type = ARPHRD_TUNNEL; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); @@ -711,10 +766,11 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } -static void ipip_tunnel_init(struct net_device *dev) +static int ipip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); @@ -725,9 +781,15 @@ static void ipip_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip_tunnel_bind_dev(dev); + + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; } -static void __net_init ipip_fb_tunnel_init(struct net_device *dev) +static int __net_init ipip_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -740,8 +802,13 @@ static void __net_init ipip_fb_tunnel_init(struct net_device *dev) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + dev_hold(dev); - ipn->tunnels_wc[0] = tunnel; + rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); + return 0; } static struct xfrm_tunnel ipip_handler __read_mostly = { @@ -760,11 +827,12 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t = ipn->tunnels[prio][h]; + struct ip_tunnel *t; + t = rtnl_dereference(ipn->tunnels[prio][h]); while (t != NULL) { unregister_netdevice_queue(t->dev, head); - t = t->next; + t = rtnl_dereference(t->next); } } } @@ -789,7 +857,9 @@ static int __net_init ipip_init_net(struct net *net) } dev_net_set(ipn->fb_tunnel_dev, net); - ipip_fb_tunnel_init(ipn->fb_tunnel_dev); + err = ipip_fb_tunnel_init(ipn->fb_tunnel_dev); + if (err) + goto err_reg_dev; if ((err = register_netdev(ipn->fb_tunnel_dev))) goto err_reg_dev; @@ -797,7 +867,7 @@ static int __net_init ipip_init_net(struct net *net) return 0; err_reg_dev: - free_netdev(ipn->fb_tunnel_dev); + ipip_dev_free(ipn->fb_tunnel_dev); err_alloc_dev: /* nothing */ return err; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 179fcab..86dd569 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -75,7 +75,7 @@ struct mr_table { struct net *net; #endif u32 id; - struct sock *mroute_sk; + struct sock __rcu *mroute_sk; struct timer_list ipmr_expire_timer; struct list_head mfc_unres_queue; struct list_head mfc_cache_array[MFC_LINES]; @@ -98,7 +98,7 @@ struct ipmr_result { }; /* Big lock, protecting vif table, mrt cache and mroute socket state. - Note that the changes are semaphored via rtnl_lock. + * Note that the changes are semaphored via rtnl_lock. */ static DEFINE_RWLOCK(mrt_lock); @@ -113,11 +113,11 @@ static DEFINE_RWLOCK(mrt_lock); static DEFINE_SPINLOCK(mfc_unres_lock); /* We return to original Alan's scheme. Hash table of resolved - entries is changed only in process context and protected - with weak lock mrt_lock. Queue of unresolved entries is protected - with strong spinlock mfc_unres_lock. - - In this case data path is free of exclusive locks at all. + * entries is changed only in process context and protected + * with weak lock mrt_lock. Queue of unresolved entries is protected + * with strong spinlock mfc_unres_lock. + * + * In this case data path is free of exclusive locks at all. */ static struct kmem_cache *mrt_cachep __read_mostly; @@ -396,9 +396,9 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) set_fs(KERNEL_DS); err = ops->ndo_do_ioctl(dev, &ifr, SIOCADDTUNNEL); set_fs(oldfs); - } else + } else { err = -EOPNOTSUPP; - + } dev = NULL; if (err == 0 && @@ -495,7 +495,8 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) dev->iflink = 0; rcu_read_lock(); - if ((in_dev = __in_dev_get_rcu(dev)) == NULL) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) { rcu_read_unlock(); goto failure; } @@ -552,9 +553,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, mrt->mroute_reg_vif_num = -1; #endif - if (vifi+1 == mrt->maxvif) { + if (vifi + 1 == mrt->maxvif) { int tmp; - for (tmp=vifi-1; tmp>=0; tmp--) { + + for (tmp = vifi - 1; tmp >= 0; tmp--) { if (VIF_EXISTS(mrt, tmp)) break; } @@ -565,25 +567,33 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, dev_set_allmulti(dev, -1); - if ((in_dev = __in_dev_get_rtnl(dev)) != NULL) { + in_dev = __in_dev_get_rtnl(dev); + if (in_dev) { IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--; ip_rt_multicast_event(in_dev); } - if (v->flags&(VIFF_TUNNEL|VIFF_REGISTER) && !notify) + if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); dev_put(dev); return 0; } -static inline void ipmr_cache_free(struct mfc_cache *c) +static void ipmr_cache_free_rcu(struct rcu_head *head) { + struct mfc_cache *c = container_of(head, struct mfc_cache, rcu); + kmem_cache_free(mrt_cachep, c); } +static inline void ipmr_cache_free(struct mfc_cache *c) +{ + call_rcu(&c->rcu, ipmr_cache_free_rcu); +} + /* Destroy an unresolved cache entry, killing queued skbs - and reporting error to netlink readers. + * and reporting error to netlink readers. */ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) @@ -605,8 +615,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) memset(&e->msg, 0, sizeof(e->msg)); rtnl_unicast(skb, net, NETLINK_CB(skb).pid); - } else + } else { kfree_skb(skb); + } } ipmr_cache_free(c); @@ -724,13 +735,13 @@ static int vif_add(struct net *net, struct mr_table *mrt, case 0: if (vifc->vifc_flags == VIFF_USE_IFINDEX) { dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); - if (dev && dev->ip_ptr == NULL) { + if (dev && __in_dev_get_rtnl(dev) == NULL) { dev_put(dev); return -EADDRNOTAVAIL; } - } else + } else { dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); - + } if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); @@ -743,16 +754,16 @@ static int vif_add(struct net *net, struct mr_table *mrt, return -EINVAL; } - if ((in_dev = __in_dev_get_rtnl(dev)) == NULL) { + in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) { dev_put(dev); return -EADDRNOTAVAIL; } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; ip_rt_multicast_event(in_dev); - /* - * Fill in the VIF structures - */ + /* Fill in the VIF structures */ + v->rate_limit = vifc->vifc_rate_limit; v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; @@ -765,14 +776,14 @@ static int vif_add(struct net *net, struct mr_table *mrt, v->pkt_in = 0; v->pkt_out = 0; v->link = dev->ifindex; - if (v->flags&(VIFF_TUNNEL|VIFF_REGISTER)) + if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER)) v->link = dev->iflink; /* And finish update writing critical data */ write_lock_bh(&mrt_lock); v->dev = dev; #ifdef CONFIG_IP_PIMSM - if (v->flags&VIFF_REGISTER) + if (v->flags & VIFF_REGISTER) mrt->mroute_reg_vif_num = vifi; #endif if (vifi+1 > mrt->maxvif) @@ -781,6 +792,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, return 0; } +/* called with rcu_read_lock() */ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, __be32 origin, __be32 mcastgrp) @@ -788,7 +800,7 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, int line = MFC_HASH(mcastgrp, origin); struct mfc_cache *c; - list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp) return c; } @@ -801,19 +813,20 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); - if (c == NULL) - return NULL; - c->mfc_un.res.minvif = MAXVIFS; + + if (c) + c->mfc_un.res.minvif = MAXVIFS; return c; } static struct mfc_cache *ipmr_cache_alloc_unres(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); - if (c == NULL) - return NULL; - skb_queue_head_init(&c->mfc_un.unres.unresolved); - c->mfc_un.unres.expires = jiffies + 10*HZ; + + if (c) { + skb_queue_head_init(&c->mfc_un.unres.unresolved); + c->mfc_un.unres.expires = jiffies + 10*HZ; + } return c; } @@ -827,17 +840,15 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct sk_buff *skb; struct nlmsgerr *e; - /* - * Play the pending entries through our router - */ + /* Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); if (__ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) { - nlh->nlmsg_len = (skb_tail_pointer(skb) - - (u8 *)nlh); + nlh->nlmsg_len = skb_tail_pointer(skb) - + (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr)); @@ -848,8 +859,9 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, } rtnl_unicast(skb, net, NETLINK_CB(skb).pid); - } else + } else { ip_mr_forward(net, mrt, skb, c, 0); + } } } @@ -867,6 +879,7 @@ static int ipmr_cache_report(struct mr_table *mrt, const int ihl = ip_hdrlen(pkt); struct igmphdr *igmp; struct igmpmsg *msg; + struct sock *mroute_sk; int ret; #ifdef CONFIG_IP_PIMSM @@ -882,9 +895,9 @@ static int ipmr_cache_report(struct mr_table *mrt, #ifdef CONFIG_IP_PIMSM if (assert == IGMPMSG_WHOLEPKT) { /* Ugly, but we have no choice with this interface. - Duplicate old header, fix ihl, length etc. - And all this only to mangle msg->im_msgtype and - to set msg->im_mbz to "mbz" :-) + * Duplicate old header, fix ihl, length etc. + * And all this only to mangle msg->im_msgtype and + * to set msg->im_mbz to "mbz" :-) */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); @@ -901,39 +914,38 @@ static int ipmr_cache_report(struct mr_table *mrt, #endif { - /* - * Copy the IP header - */ + /* Copy the IP header */ skb->network_header = skb->tail; skb_put(skb, ihl); skb_copy_to_linear_data(skb, pkt->data, ihl); - ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */ + 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_set(skb, dst_clone(skb_dst(pkt))); - /* - * Add our header - */ + /* Add our header */ - igmp=(struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); + igmp = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); igmp->type = msg->im_msgtype = assert; - igmp->code = 0; - ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ + igmp->code = 0; + ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ skb->transport_header = skb->network_header; } - if (mrt->mroute_sk == NULL) { + rcu_read_lock(); + mroute_sk = rcu_dereference(mrt->mroute_sk); + if (mroute_sk == NULL) { + rcu_read_unlock(); kfree_skb(skb); return -EINVAL; } - /* - * Deliver to mrouted - */ - ret = sock_queue_rcv_skb(mrt->mroute_sk, skb); + /* Deliver to mrouted */ + + ret = sock_queue_rcv_skb(mroute_sk, skb); + rcu_read_unlock(); if (ret < 0) { if (net_ratelimit()) printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n"); @@ -965,9 +977,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) } if (!found) { - /* - * Create a new entry if allowable - */ + /* Create a new entry if allowable */ if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || (c = ipmr_cache_alloc_unres()) == NULL) { @@ -977,16 +987,14 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) return -ENOBUFS; } - /* - * Fill in the new cache entry - */ + /* Fill in the new cache entry */ + c->mfc_parent = -1; c->mfc_origin = iph->saddr; c->mfc_mcastgrp = iph->daddr; - /* - * Reflect first query at mrouted. - */ + /* Reflect first query at mrouted. */ + err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry @@ -1006,10 +1014,9 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); } - /* - * See if we can append the packet - */ - if (c->mfc_un.unres.unresolved.qlen>3) { + /* See if we can append the packet */ + + if (c->mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { @@ -1035,9 +1042,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { - write_lock_bh(&mrt_lock); - list_del(&c->list); - write_unlock_bh(&mrt_lock); + list_del_rcu(&c->list); ipmr_cache_free(c); return 0; @@ -1090,9 +1095,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; - write_lock_bh(&mrt_lock); - list_add(&c->list, &mrt->mfc_cache_array[line]); - write_unlock_bh(&mrt_lock); + list_add_rcu(&c->list, &mrt->mfc_cache_array[line]); /* * Check to see if we resolved a queued list. If so we @@ -1130,26 +1133,21 @@ static void mroute_clean_tables(struct mr_table *mrt) LIST_HEAD(list); struct mfc_cache *c, *next; - /* - * Shut down all active vif entries - */ + /* Shut down all active vif entries */ + for (i = 0; i < mrt->maxvif; i++) { - if (!(mrt->vif_table[i].flags&VIFF_STATIC)) + if (!(mrt->vif_table[i].flags & VIFF_STATIC)) vif_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); - /* - * Wipe the cache - */ + /* Wipe the cache */ + for (i = 0; i < MFC_LINES; i++) { list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) { - if (c->mfc_flags&MFC_STATIC) + if (c->mfc_flags & MFC_STATIC) continue; - write_lock_bh(&mrt_lock); - list_del(&c->list); - write_unlock_bh(&mrt_lock); - + list_del_rcu(&c->list); ipmr_cache_free(c); } } @@ -1164,6 +1162,9 @@ static void mroute_clean_tables(struct mr_table *mrt) } } +/* called from ip_ra_control(), before an RCU grace period, + * we dont need to call synchronize_rcu() here + */ static void mrtsock_destruct(struct sock *sk) { struct net *net = sock_net(sk); @@ -1171,13 +1172,9 @@ static void mrtsock_destruct(struct sock *sk) rtnl_lock(); ipmr_for_each_table(mrt, net) { - if (sk == mrt->mroute_sk) { + if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; - - write_lock_bh(&mrt_lock); - mrt->mroute_sk = NULL; - write_unlock_bh(&mrt_lock); - + rcu_assign_pointer(mrt->mroute_sk, NULL); mroute_clean_tables(mrt); } } @@ -1204,7 +1201,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENOENT; if (optname != MRT_INIT) { - if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN)) + if (sk != rcu_dereference_raw(mrt->mroute_sk) && + !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -1217,23 +1215,20 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENOPROTOOPT; rtnl_lock(); - if (mrt->mroute_sk) { + if (rtnl_dereference(mrt->mroute_sk)) { rtnl_unlock(); return -EADDRINUSE; } ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { - write_lock_bh(&mrt_lock); - mrt->mroute_sk = sk; - write_unlock_bh(&mrt_lock); - + rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; } rtnl_unlock(); return ret; case MRT_DONE: - if (sk != mrt->mroute_sk) + if (sk != rcu_dereference_raw(mrt->mroute_sk)) return -EACCES; return ip_ra_control(sk, 0, NULL); case MRT_ADD_VIF: @@ -1246,7 +1241,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENFILE; rtnl_lock(); if (optname == MRT_ADD_VIF) { - ret = vif_add(net, mrt, &vif, sk == mrt->mroute_sk); + ret = vif_add(net, mrt, &vif, + sk == rtnl_dereference(mrt->mroute_sk)); } else { ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL); } @@ -1267,7 +1263,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi if (optname == MRT_DEL_MFC) ret = ipmr_mfc_delete(mrt, &mfc); else - ret = ipmr_mfc_add(net, mrt, &mfc, sk == mrt->mroute_sk); + ret = ipmr_mfc_add(net, mrt, &mfc, + sk == rtnl_dereference(mrt->mroute_sk)); rtnl_unlock(); return ret; /* @@ -1276,7 +1273,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi case MRT_ASSERT: { int v; - if (get_user(v,(int __user *)optval)) + if (get_user(v, (int __user *)optval)) return -EFAULT; mrt->mroute_do_assert = (v) ? 1 : 0; return 0; @@ -1286,7 +1283,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi { int v; - if (get_user(v,(int __user *)optval)) + if (get_user(v, (int __user *)optval)) return -EFAULT; v = (v) ? 1 : 0; @@ -1309,14 +1306,16 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -EINVAL; if (get_user(v, (u32 __user *)optval)) return -EFAULT; - if (sk == mrt->mroute_sk) - return -EBUSY; rtnl_lock(); ret = 0; - if (!ipmr_new_table(net, v)) - ret = -ENOMEM; - raw_sk(sk)->ipmr_table = v; + if (sk == rtnl_dereference(mrt->mroute_sk)) { + ret = -EBUSY; + } else { + if (!ipmr_new_table(net, v)) + ret = -ENOMEM; + raw_sk(sk)->ipmr_table = v; + } rtnl_unlock(); return ret; } @@ -1347,9 +1346,9 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int if (optname != MRT_VERSION && #ifdef CONFIG_IP_PIMSM - optname!=MRT_PIM && + optname != MRT_PIM && #endif - optname!=MRT_ASSERT) + optname != MRT_ASSERT) return -ENOPROTOOPT; if (get_user(olr, optlen)) @@ -1416,19 +1415,19 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; - read_lock(&mrt_lock); + rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { sr.pktcnt = c->mfc_un.res.pkt; sr.bytecnt = c->mfc_un.res.bytes; sr.wrong_if = c->mfc_un.res.wrong_if; - read_unlock(&mrt_lock); + rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; @@ -1465,7 +1464,7 @@ static struct notifier_block ip_mr_notifier = { }; /* - * Encapsulate a packet by attaching a valid IPIP header to it. + * Encapsulate a packet by attaching a valid IPIP header to it. * This avoids tunnel drivers and other mess and gives us the speed so * important for multicast video. */ @@ -1480,7 +1479,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) skb_reset_network_header(skb); iph = ip_hdr(skb); - iph->version = 4; + iph->version = 4; iph->tos = old_iph->tos; iph->ttl = old_iph->ttl; iph->frag_off = 0; @@ -1498,7 +1497,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) static inline int ipmr_forward_finish(struct sk_buff *skb) { - struct ip_options * opt = &(IPCB(skb)->opt); + struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); @@ -1535,22 +1534,34 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, } #endif - if (vif->flags&VIFF_TUNNEL) { - struct flowi fl = { .oif = vif->link, - .nl_u = { .ip4_u = - { .daddr = vif->remote, - .saddr = vif->local, - .tos = RT_TOS(iph->tos) } }, - .proto = IPPROTO_IPIP }; + if (vif->flags & VIFF_TUNNEL) { + struct flowi fl = { + .oif = vif->link, + .nl_u = { + .ip4_u = { + .daddr = vif->remote, + .saddr = vif->local, + .tos = RT_TOS(iph->tos) + } + }, + .proto = IPPROTO_IPIP + }; + if (ip_route_output_key(net, &rt, &fl)) goto out_free; encap = sizeof(struct iphdr); } else { - struct flowi fl = { .oif = vif->link, - .nl_u = { .ip4_u = - { .daddr = iph->daddr, - .tos = RT_TOS(iph->tos) } }, - .proto = IPPROTO_IPIP }; + struct flowi fl = { + .oif = vif->link, + .nl_u = { + .ip4_u = { + .daddr = iph->daddr, + .tos = RT_TOS(iph->tos) + } + }, + .proto = IPPROTO_IPIP + }; + if (ip_route_output_key(net, &rt, &fl)) goto out_free; } @@ -1559,8 +1570,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) { /* Do not fragment multicasts. Alas, IPv4 does not - allow to send ICMP, so that packets will disappear - to blackhole. + * allow to send ICMP, so that packets will disappear + * to blackhole. */ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS); @@ -1583,7 +1594,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, ip_decrease_ttl(ip_hdr(skb)); /* FIXME: forward and output firewalls used to be called here. - * What do we do with netfilter? -- RR */ + * What do we do with netfilter? -- RR + */ if (vif->flags & VIFF_TUNNEL) { ip_encap(skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ @@ -1644,15 +1656,15 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, if (skb_rtable(skb)->fl.iif == 0) { /* It is our own packet, looped back. - Very complicated situation... - - The best workaround until routing daemons will be - fixed is not to redistribute packet, if it was - send through wrong interface. It means, that - multicast applications WILL NOT work for - (S,G), which have default multicast route pointing - to wrong oif. In any case, it is not a good - idea to use multicasting applications on router. + * Very complicated situation... + * + * The best workaround until routing daemons will be + * fixed is not to redistribute packet, if it was + * send through wrong interface. It means, that + * multicast applications WILL NOT work for + * (S,G), which have default multicast route pointing + * to wrong oif. In any case, it is not a good + * idea to use multicasting applications on router. */ goto dont_forward; } @@ -1662,9 +1674,9 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, - so that we cannot check that packet arrived on an oif. - It is bad, but otherwise we would need to move pretty - large chunk of pimd to kernel. Ough... --ANK + * so that we cannot check that packet arrived on an oif. + * It is bad, but otherwise we would need to move pretty + * large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) && @@ -1682,10 +1694,12 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, /* * Forward the frame */ - for (ct = cache->mfc_un.res.maxvif-1; ct >= cache->mfc_un.res.minvif; ct--) { + for (ct = cache->mfc_un.res.maxvif - 1; + ct >= cache->mfc_un.res.minvif; ct--) { if (ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) ipmr_queue_xmit(net, mrt, skb2, cache, psend); @@ -1696,6 +1710,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) ipmr_queue_xmit(net, mrt, skb2, cache, psend); } else { @@ -1713,6 +1728,7 @@ dont_forward: /* * Multicast packets for forwarding arrive here + * Called with rcu_read_lock(); */ int ip_mr_input(struct sk_buff *skb) @@ -1724,9 +1740,9 @@ int ip_mr_input(struct sk_buff *skb) int err; /* Packet is looped back after forward, it should not be - forwarded second time, but still can be delivered locally. + * forwarded second time, but still can be delivered locally. */ - if (IPCB(skb)->flags&IPSKB_FORWARDED) + if (IPCB(skb)->flags & IPSKB_FORWARDED) goto dont_forward; err = ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt); @@ -1736,28 +1752,28 @@ int ip_mr_input(struct sk_buff *skb) } if (!local) { - if (IPCB(skb)->opt.router_alert) { - if (ip_call_ra_chain(skb)) - return 0; - } else if (ip_hdr(skb)->protocol == IPPROTO_IGMP){ - /* IGMPv1 (and broken IGMPv2 implementations sort of - Cisco IOS <= 11.2(8)) do not put router alert - option to IGMP packets destined to routable - groups. It is very bad, because it means - that we can forward NO IGMP messages. - */ - read_lock(&mrt_lock); - if (mrt->mroute_sk) { - nf_reset(skb); - raw_rcv(mrt->mroute_sk, skb); - read_unlock(&mrt_lock); - return 0; - } - read_unlock(&mrt_lock); + if (IPCB(skb)->opt.router_alert) { + if (ip_call_ra_chain(skb)) + return 0; + } else if (ip_hdr(skb)->protocol == IPPROTO_IGMP) { + /* IGMPv1 (and broken IGMPv2 implementations sort of + * Cisco IOS <= 11.2(8)) do not put router alert + * option to IGMP packets destined to routable + * groups. It is very bad, because it means + * that we can forward NO IGMP messages. + */ + struct sock *mroute_sk; + + mroute_sk = rcu_dereference(mrt->mroute_sk); + if (mroute_sk) { + nf_reset(skb); + raw_rcv(mroute_sk, skb); + return 0; + } } } - read_lock(&mrt_lock); + /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); /* @@ -1769,13 +1785,12 @@ int ip_mr_input(struct sk_buff *skb) if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); ip_local_deliver(skb); - if (skb2 == NULL) { - read_unlock(&mrt_lock); + if (skb2 == NULL) return -ENOBUFS; - } skb = skb2; } + read_lock(&mrt_lock); vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) { int err2 = ipmr_cache_unresolved(mrt, vif, skb); @@ -1788,8 +1803,8 @@ int ip_mr_input(struct sk_buff *skb) return -ENODEV; } + read_lock(&mrt_lock); ip_mr_forward(net, mrt, skb, cache, local); - read_unlock(&mrt_lock); if (local) @@ -1805,6 +1820,7 @@ dont_forward: } #ifdef CONFIG_IP_PIMSM +/* called with rcu_read_lock() */ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, unsigned int pimlen) { @@ -1813,10 +1829,10 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* - Check that: - a. packet is really destinted to a multicast group - b. packet is not a NULL-REGISTER - c. packet is not truncated + * Check that: + * a. packet is really sent to a multicast group + * b. packet is not a NULL-REGISTER + * c. packet is not truncated */ if (!ipv4_is_multicast(encap->daddr) || encap->tot_len == 0 || @@ -1826,26 +1842,23 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, read_lock(&mrt_lock); if (mrt->mroute_reg_vif_num >= 0) reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev; - if (reg_dev) - dev_hold(reg_dev); read_unlock(&mrt_lock); if (reg_dev == NULL) return 1; skb->mac_header = skb->network_header; - skb_pull(skb, (u8*)encap - skb->data); + skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); - skb->ip_summed = 0; + skb->ip_summed = CHECKSUM_NONE; skb->pkt_type = PACKET_HOST; skb_tunnel_rx(skb, reg_dev); netif_rx(skb); - dev_put(reg_dev); - return 0; + return NET_RX_SUCCESS; } #endif @@ -1854,7 +1867,7 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, * Handle IGMP messages of PIMv1 */ -int pim_rcv_v1(struct sk_buff * skb) +int pim_rcv_v1(struct sk_buff *skb) { struct igmphdr *pim; struct net *net = dev_net(skb->dev); @@ -1881,7 +1894,7 @@ drop: #endif #ifdef CONFIG_IP_PIMSM_V2 -static int pim_rcv(struct sk_buff * skb) +static int pim_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct net *net = dev_net(skb->dev); @@ -1891,8 +1904,8 @@ static int pim_rcv(struct sk_buff * skb) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); - if (pim->type != ((PIM_VERSION<<4)|(PIM_REGISTER)) || - (pim->flags&PIM_NULL_REGISTER) || + if (pim->type != ((PIM_VERSION << 4) | (PIM_REGISTER)) || + (pim->flags & PIM_NULL_REGISTER) || (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; @@ -1958,28 +1971,33 @@ int ipmr_get_route(struct net *net, if (mrt == NULL) return -ENOENT; - read_lock(&mrt_lock); + rcu_read_lock(); cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst); if (cache == NULL) { struct sk_buff *skb2; struct iphdr *iph; struct net_device *dev; - int vif; + int vif = -1; if (nowait) { - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EAGAIN; } dev = skb->dev; - if (dev == NULL || (vif = ipmr_find_vif(mrt, dev)) < 0) { + read_lock(&mrt_lock); + if (dev) + vif = ipmr_find_vif(mrt, dev); + if (vif < 0) { read_unlock(&mrt_lock); + rcu_read_unlock(); return -ENODEV; } skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) { read_unlock(&mrt_lock); + rcu_read_unlock(); return -ENOMEM; } @@ -1992,13 +2010,16 @@ int ipmr_get_route(struct net *net, iph->version = 0; err = ipmr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); + rcu_read_unlock(); return err; } - if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) + read_lock(&mrt_lock); + if (!nowait && (rtm->rtm_flags & RTM_F_NOTIFY)) cache->mfc_flags |= MFC_NOTIFY; err = __ipmr_fill_mroute(mrt, skb, cache, rtm); read_unlock(&mrt_lock); + rcu_read_unlock(); return err; } @@ -2050,14 +2071,14 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) s_h = cb->args[1]; s_e = cb->args[2]; - read_lock(&mrt_lock); + rcu_read_lock(); ipmr_for_each_table(mrt, net) { if (t < s_t) goto next_table; if (t > s_t) s_h = 0; for (h = s_h; h < MFC_LINES; h++) { - list_for_each_entry(mfc, &mrt->mfc_cache_array[h], list) { + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_array[h], list) { if (e < s_e) goto next_entry; if (ipmr_fill_mroute(mrt, skb, @@ -2075,7 +2096,7 @@ next_table: t++; } done: - read_unlock(&mrt_lock); + rcu_read_unlock(); cb->args[2] = e; cb->args[1] = h; @@ -2086,7 +2107,8 @@ done: #ifdef CONFIG_PROC_FS /* - * The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif + * The /proc interfaces to multicast routing : + * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif */ struct ipmr_vif_iter { struct seq_net_private p; @@ -2208,14 +2230,14 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, struct mr_table *mrt = it->mrt; struct mfc_cache *mfc; - read_lock(&mrt_lock); + rcu_read_lock(); for (it->ct = 0; it->ct < MFC_LINES; it->ct++) { it->cache = &mrt->mfc_cache_array[it->ct]; - list_for_each_entry(mfc, it->cache, list) + list_for_each_entry_rcu(mfc, it->cache, list) if (pos-- == 0) return mfc; } - read_unlock(&mrt_lock); + rcu_read_unlock(); spin_lock_bh(&mfc_unres_lock); it->cache = &mrt->mfc_unres_queue; @@ -2274,7 +2296,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) } /* exhausted cache_array, show unresolved */ - read_unlock(&mrt_lock); + rcu_read_unlock(); it->cache = &mrt->mfc_unres_queue; it->ct = 0; @@ -2282,7 +2304,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!list_empty(it->cache)) return list_first_entry(it->cache, struct mfc_cache, list); - end_of_list: +end_of_list: spin_unlock_bh(&mfc_unres_lock); it->cache = NULL; @@ -2297,7 +2319,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) if (it->cache == &mrt->mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); else if (it->cache == &mrt->mfc_cache_array[it->ct]) - read_unlock(&mrt_lock); + rcu_read_unlock(); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) @@ -2323,7 +2345,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) mfc->mfc_un.res.bytes, mfc->mfc_un.res.wrong_if); for (n = mfc->mfc_un.res.minvif; - n < mfc->mfc_un.res.maxvif; n++ ) { + n < mfc->mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && mfc->mfc_un.res.ttls[n] < 255) seq_printf(seq, @@ -2421,7 +2443,7 @@ int __init ip_mr_init(void) mrt_cachep = kmem_cache_create("ip_mrt_cache", sizeof(struct mfc_cache), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, + 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); if (!mrt_cachep) return -ENOMEM; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d756eda..3cad259 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -72,7 +72,7 @@ static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, for (i = 0; i < len; i++) ret |= (hdr_addr[i] ^ ap->addr[i]) & ap->mask[i]; - return (ret != 0); + return ret != 0; } /* diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index b254daf..43eec80 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); + nskb->protocol = htons(ETH_P_IP); if (ip_route_me_harder(nskb, addr_type)) goto free_nskb; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index eab8de3..f3a9b42 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -66,9 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { + struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(skb->sk); - if (inet && inet->nodefrag) + if (sk && (sk->sk_family == PF_INET) && + inet->nodefrag) return NF_ACCEPT; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 1679e2c..ee5f419 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -893,13 +893,15 @@ static void fast_csum(__sum16 *csum, unsigned char s[4]; if (offset & 1) { - s[0] = s[2] = 0; + s[0] = ~0; s[1] = ~*optr; + s[2] = 0; s[3] = *nptr; } else { - s[1] = s[3] = 0; s[0] = ~*optr; + s[1] = ~0; s[2] = *nptr; + s[3] = 0; } *csum = csum_fold(csum_partial(s, 4, ~csum_unfold(*csum))); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e24d48d..d6cb2bf 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -159,7 +159,6 @@ static struct dst_ops ipv4_dst_ops = { .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .local_out = __ip_local_out, - .entries = ATOMIC_INIT(0), }; #define ECN_OR_COST(class) TC_PRIO_##class @@ -466,7 +465,7 @@ static int rt_cpu_seq_show(struct seq_file *seq, void *v) seq_printf(seq,"%08x %08x %08x %08x %08x %08x %08x %08x " " %08x %08x %08x %08x %08x %08x %08x %08x %08x \n", - atomic_read(&ipv4_dst_ops.entries), + dst_entries_get_slow(&ipv4_dst_ops), st->in_hit, st->in_slow_tot, st->in_slow_mc, @@ -945,6 +944,7 @@ static int rt_garbage_collect(struct dst_ops *ops) struct rtable *rth, **rthp; unsigned long now = jiffies; int goal; + int entries = dst_entries_get_fast(&ipv4_dst_ops); /* * Garbage collection is pretty expensive, @@ -954,28 +954,28 @@ static int rt_garbage_collect(struct dst_ops *ops) RT_CACHE_STAT_INC(gc_total); if (now - last_gc < ip_rt_gc_min_interval && - atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) { + entries < ip_rt_max_size) { RT_CACHE_STAT_INC(gc_ignored); goto out; } + entries = dst_entries_get_slow(&ipv4_dst_ops); /* Calculate number of entries, which we want to expire now. */ - goal = atomic_read(&ipv4_dst_ops.entries) - - (ip_rt_gc_elasticity << rt_hash_log); + goal = entries - (ip_rt_gc_elasticity << rt_hash_log); if (goal <= 0) { if (equilibrium < ipv4_dst_ops.gc_thresh) equilibrium = ipv4_dst_ops.gc_thresh; - goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium; + goal = entries - equilibrium; if (goal > 0) { equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1); - goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium; + goal = entries - equilibrium; } } else { /* We are in dangerous area. Try to reduce cache really * aggressively. */ goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1); - equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal; + equilibrium = entries - goal; } if (now - last_gc >= ip_rt_gc_min_interval) @@ -1032,14 +1032,16 @@ static int rt_garbage_collect(struct dst_ops *ops) expire >>= 1; #if RT_CACHE_DEBUG >= 2 printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire, - atomic_read(&ipv4_dst_ops.entries), goal, i); + dst_entries_get_fast(&ipv4_dst_ops), goal, i); #endif - if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) + if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size) goto out; } while (!in_softirq() && time_before_eq(jiffies, now)); - if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) + if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size) + goto out; + if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size) goto out; if (net_ratelimit()) printk(KERN_WARNING "dst cache overflow\n"); @@ -1049,11 +1051,12 @@ static int rt_garbage_collect(struct dst_ops *ops) work_done: expire += ip_rt_gc_min_interval; if (expire > ip_rt_gc_timeout || - atomic_read(&ipv4_dst_ops.entries) < ipv4_dst_ops.gc_thresh) + dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh || + dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh) expire = ip_rt_gc_timeout; #if RT_CACHE_DEBUG >= 2 printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire, - atomic_read(&ipv4_dst_ops.entries), goal, rover); + dst_entries_get_fast(&ipv4_dst_ops), goal, rover); #endif out: return 0; } @@ -1102,23 +1105,23 @@ restart: * 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. + * Note: To avoid expensive rcu stuff for this uncached dst, + * we set DST_NOCACHE so that dst_release() can free dst without + * waiting a grace period. */ + rt->dst.flags |= DST_NOCACHE; if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { int err = arp_bind_neighbour(&rt->dst); if (err) { if (net_ratelimit()) printk(KERN_WARNING "Neighbour table failure & not caching routes.\n"); - rt_drop(rt); + ip_rt_put(rt); return err; } } - rt_free(rt); goto skip_hashing; } @@ -1231,7 +1234,7 @@ restart: } if (net_ratelimit()) - printk(KERN_WARNING "Neighbour table overflow.\n"); + printk(KERN_WARNING "ipv4: Neighbour table overflow.\n"); rt_drop(rt); return -ENOBUFS; } @@ -1772,12 +1775,15 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) if (rt->fl.iif == 0) src = rt->rt_src; - else if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0) { - src = FIB_RES_PREFSRC(res); - fib_res_put(&res); - } else - src = inet_select_addr(rt->dst.dev, rt->rt_gateway, + else { + rcu_read_lock(); + if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0) + src = FIB_RES_PREFSRC(res); + else + src = inet_select_addr(rt->dst.dev, rt->rt_gateway, RT_SCOPE_UNIVERSE); + rcu_read_unlock(); + } memcpy(addr, &src, 4); } @@ -2080,6 +2086,7 @@ static int ip_mkroute_input(struct sk_buff *skb, * Such approach solves two big problems: * 1. Not simplex devices are handled properly. * 2. IP spoofing attempts are filtered with 100% of guarantee. + * called with rcu_read_lock() */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, @@ -2101,7 +2108,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, unsigned hash; __be32 spec_dst; int err = -EINVAL; - int free_res = 0; struct net * net = dev_net(dev); /* IP on this device is disabled. */ @@ -2117,7 +2123,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, ipv4_is_loopback(saddr)) goto martian_source; - if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0)) + if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; /* Accept zero addresses only to limited broadcast; @@ -2126,19 +2132,18 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_zeronet(saddr)) goto martian_source; - if (ipv4_is_lbcast(daddr) || ipv4_is_zeronet(daddr) || - ipv4_is_loopback(daddr)) + if (ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr)) goto martian_destination; /* * Now we are ready to route packet. */ - if ((err = fib_lookup(net, &fl, &res)) != 0) { + err = fib_lookup(net, &fl, &res); + if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) goto e_hostunreach; goto no_route; } - free_res = 1; RT_CACHE_STAT_INC(in_slow_tot); @@ -2147,8 +2152,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res.type == RTN_LOCAL) { err = fib_validate_source(saddr, daddr, tos, - net->loopback_dev->ifindex, - dev, &spec_dst, &itag, skb->mark); + net->loopback_dev->ifindex, + dev, &spec_dst, &itag, skb->mark); if (err < 0) goto martian_source_keep_err; if (err) @@ -2163,9 +2168,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto martian_destination; err = ip_mkroute_input(skb, &res, &fl, in_dev, daddr, saddr, tos); -done: - if (free_res) - fib_res_put(&res); out: return err; brd_input: @@ -2225,7 +2227,7 @@ local_input: rth->rt_type = res.type; hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net)); err = rt_intern_hash(hash, rth, NULL, skb, fl.iif); - goto done; + goto out; no_route: RT_CACHE_STAT_INC(in_no_route); @@ -2248,21 +2250,21 @@ martian_destination: e_hostunreach: err = -EHOSTUNREACH; - goto done; + goto out; e_inval: err = -EINVAL; - goto done; + goto out; e_nobufs: err = -ENOBUFS; - goto done; + goto out; martian_source: err = -EINVAL; martian_source_keep_err: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); - goto done; + goto out; } int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, @@ -2348,6 +2350,7 @@ skip_cache: } EXPORT_SYMBOL(ip_route_input_common); +/* called with rcu_read_lock() */ static int __mkroute_output(struct rtable **result, struct fib_result *res, const struct flowi *fl, @@ -2358,53 +2361,47 @@ static int __mkroute_output(struct rtable **result, struct rtable *rth; struct in_device *in_dev; u32 tos = RT_FL_TOS(oldflp); - int err = 0; - if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK)) + if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags & IFF_LOOPBACK)) return -EINVAL; - if (fl->fl4_dst == htonl(0xFFFFFFFF)) + if (ipv4_is_lbcast(fl->fl4_dst)) res->type = RTN_BROADCAST; else if (ipv4_is_multicast(fl->fl4_dst)) res->type = RTN_MULTICAST; - else if (ipv4_is_lbcast(fl->fl4_dst) || ipv4_is_zeronet(fl->fl4_dst)) + else if (ipv4_is_zeronet(fl->fl4_dst)) return -EINVAL; if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - /* get work reference to inet device */ - in_dev = in_dev_get(dev_out); + in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) return -EINVAL; if (res->type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; - if (res->fi) { - fib_info_put(res->fi); - res->fi = NULL; - } + res->fi = NULL; } else if (res->type == RTN_MULTICAST) { - flags |= RTCF_MULTICAST|RTCF_LOCAL; + flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src, oldflp->proto)) flags &= ~RTCF_LOCAL; /* If multicast route do not exist use - default one, but do not gateway in this case. - Yes, it is hack. + * default one, but do not gateway in this case. + * Yes, it is hack. */ - if (res->fi && res->prefixlen < 4) { - fib_info_put(res->fi); + if (res->fi && res->prefixlen < 4) res->fi = NULL; - } } rth = dst_alloc(&ipv4_dst_ops); - if (!rth) { - err = -ENOBUFS; - goto cleanup; - } + if (!rth) + return -ENOBUFS; + + in_dev_hold(in_dev); + rth->idev = in_dev; atomic_set(&rth->dst.__refcnt, 1); rth->dst.flags= DST_HOST; @@ -2425,7 +2422,6 @@ static int __mkroute_output(struct rtable **result, cache entry */ rth->dst.dev = dev_out; dev_hold(dev_out); - rth->idev = in_dev_get(dev_out); rth->rt_gateway = fl->fl4_dst; rth->rt_spec_dst= fl->fl4_src; @@ -2460,15 +2456,11 @@ static int __mkroute_output(struct rtable **result, rt_set_nexthop(rth, res, 0); rth->rt_flags = flags; - *result = rth; - cleanup: - /* release work reference to inet device */ - in_dev_put(in_dev); - - return err; + return 0; } +/* called with rcu_read_lock() */ static int ip_mkroute_output(struct rtable **rp, struct fib_result *res, const struct flowi *fl, @@ -2490,6 +2482,7 @@ static int ip_mkroute_output(struct rtable **rp, /* * Major route resolver routine. + * called with rcu_read_lock(); */ static int ip_route_output_slow(struct net *net, struct rtable **rp, @@ -2508,9 +2501,8 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, .iif = net->loopback_dev->ifindex, .oif = oldflp->oif }; struct fib_result res; - unsigned flags = 0; + unsigned int flags = 0; struct net_device *dev_out = NULL; - int free_res = 0; int err; @@ -2536,9 +2528,9 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, if (oldflp->oif == 0 && (ipv4_is_multicast(oldflp->fl4_dst) || - oldflp->fl4_dst == htonl(0xFFFFFFFF))) { + ipv4_is_lbcast(oldflp->fl4_dst))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ - dev_out = ip_dev_find(net, oldflp->fl4_src); + dev_out = __ip_dev_find(net, oldflp->fl4_src, false); if (dev_out == NULL) goto out; @@ -2563,29 +2555,24 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, if (!(oldflp->flags & FLOWI_FLAG_ANYSRC)) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ - dev_out = ip_dev_find(net, oldflp->fl4_src); - if (dev_out == NULL) + if (!__ip_dev_find(net, oldflp->fl4_src, false)) goto out; - dev_put(dev_out); - dev_out = NULL; } } if (oldflp->oif) { - dev_out = dev_get_by_index(net, oldflp->oif); + dev_out = dev_get_by_index_rcu(net, oldflp->oif); err = -ENODEV; if (dev_out == NULL) goto out; /* RACE: Check return value of inet_select_addr instead. */ - if (__in_dev_get_rtnl(dev_out) == NULL) { - dev_put(dev_out); + if (rcu_dereference(dev_out->ip_ptr) == NULL) goto out; /* Wrong error code */ - } if (ipv4_is_local_multicast(oldflp->fl4_dst) || - oldflp->fl4_dst == htonl(0xFFFFFFFF)) { + ipv4_is_lbcast(oldflp->fl4_dst)) { if (!fl.fl4_src) fl.fl4_src = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); @@ -2605,10 +2592,7 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, fl.fl4_dst = fl.fl4_src; if (!fl.fl4_dst) fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK); - if (dev_out) - dev_put(dev_out); dev_out = net->loopback_dev; - dev_hold(dev_out); fl.oif = net->loopback_dev->ifindex; res.type = RTN_LOCAL; flags |= RTCF_LOCAL; @@ -2642,23 +2626,15 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, res.type = RTN_UNICAST; goto make_route; } - if (dev_out) - dev_put(dev_out); err = -ENETUNREACH; goto out; } - free_res = 1; if (res.type == RTN_LOCAL) { if (!fl.fl4_src) fl.fl4_src = fl.fl4_dst; - if (dev_out) - dev_put(dev_out); dev_out = net->loopback_dev; - dev_hold(dev_out); fl.oif = dev_out->ifindex; - if (res.fi) - fib_info_put(res.fi); res.fi = NULL; flags |= RTCF_LOCAL; goto make_route; @@ -2675,28 +2651,21 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, if (!fl.fl4_src) fl.fl4_src = FIB_RES_PREFSRC(res); - if (dev_out) - dev_put(dev_out); dev_out = FIB_RES_DEV(res); - dev_hold(dev_out); fl.oif = dev_out->ifindex; make_route: err = ip_mkroute_output(rp, &res, &fl, oldflp, dev_out, flags); - - if (free_res) - fib_res_put(&res); - if (dev_out) - dev_put(dev_out); out: return err; } int __ip_route_output_key(struct net *net, struct rtable **rp, const struct flowi *flp) { - unsigned hash; + unsigned int hash; + int res; struct rtable *rth; if (!rt_caching(net)) @@ -2727,7 +2696,10 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, rcu_read_unlock_bh(); slow_output: - return ip_route_output_slow(net, rp, flp); + rcu_read_lock(); + res = ip_route_output_slow(net, rp, flp); + rcu_read_unlock(); + return res; } EXPORT_SYMBOL_GPL(__ip_route_output_key); @@ -2746,7 +2718,6 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, .update_pmtu = ipv4_rt_blackhole_update_pmtu, - .entries = ATOMIC_INIT(0), }; @@ -2791,7 +2762,7 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi dst_release(&(*rp)->dst); *rp = rt; - return (rt ? 0 : -ENOMEM); + return rt ? 0 : -ENOMEM; } int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp, @@ -3316,6 +3287,12 @@ int __init ip_rt_init(void) ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; + if (dst_entries_init(&ipv4_dst_ops) < 0) + panic("IP: failed to allocate ipv4_dst_ops counter\n"); + + if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0) + panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n"); + rt_hash_table = (struct rt_hash_bucket *) alloc_large_system_hash("IP route cache", sizeof(struct rt_hash_bucket), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3e8a4db..1664a05 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ mask = 0; - if (sk->sk_err) - mask = POLLERR; /* * POLLHUP is certainly not done right. But poll() doesn't @@ -457,6 +455,11 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; } + /* This barrier is coupled with smp_wmb() in tcp_reset() */ + smp_rmb(); + if (sk->sk_err) + mask |= POLLERR; + return mask; } EXPORT_SYMBOL(tcp_poll); @@ -940,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sg = sk->sk_route_caps & NETIF_F_SG; while (--iovlen >= 0) { - int seglen = iov->iov_len; + size_t seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; iov++; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1bc87a0..ee0df48 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -182,7 +182,7 @@ static void tcp_incr_quickack(struct sock *sk) icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS); } -void tcp_enter_quickack_mode(struct sock *sk) +static void tcp_enter_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_incr_quickack(sk); @@ -2301,7 +2301,7 @@ static inline int tcp_dupack_heuristics(struct tcp_sock *tp) static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb) { - return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto); + return tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto; } static inline int tcp_head_timedout(struct sock *sk) @@ -2495,7 +2495,7 @@ static void tcp_timeout_skbs(struct sock *sk) /* Mark head of queue up as lost. With RFC3517 SACK, the packets is * is against sacked "cnt", otherwise it's against facked "cnt" */ -static void tcp_mark_head_lost(struct sock *sk, int packets) +static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -2503,13 +2503,13 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) int err; unsigned int mss; - if (packets == 0) - return; - WARN_ON(packets > tp->packets_out); if (tp->lost_skb_hint) { skb = tp->lost_skb_hint; cnt = tp->lost_cnt_hint; + /* Head already handled? */ + if (mark_head && skb != tcp_write_queue_head(sk)) + return; } else { skb = tcp_write_queue_head(sk); cnt = 0; @@ -2532,7 +2532,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) cnt += tcp_skb_pcount(skb); if (cnt > packets) { - if (tcp_is_sack(tp) || (oldcnt >= packets)) + if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + (oldcnt >= packets)) break; mss = skb_shinfo(skb)->gso_size; @@ -2543,6 +2544,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) } tcp_skb_mark_lost(tp, skb); + + if (mark_head) + break; } tcp_verify_left_out(tp); } @@ -2554,17 +2558,18 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) struct tcp_sock *tp = tcp_sk(sk); if (tcp_is_reno(tp)) { - tcp_mark_head_lost(sk, 1); + tcp_mark_head_lost(sk, 1, 1); } else if (tcp_is_fack(tp)) { int lost = tp->fackets_out - tp->reordering; if (lost <= 0) lost = 1; - tcp_mark_head_lost(sk, lost); + tcp_mark_head_lost(sk, lost, 0); } else { int sacked_upto = tp->sacked_out - tp->reordering; - if (sacked_upto < fast_rexmit) - sacked_upto = fast_rexmit; - tcp_mark_head_lost(sk, sacked_upto); + if (sacked_upto >= 0) + tcp_mark_head_lost(sk, sacked_upto, 0); + else if (fast_rexmit) + tcp_mark_head_lost(sk, 1, 1); } tcp_timeout_skbs(sk); @@ -2873,7 +2878,7 @@ static void tcp_mtup_probe_success(struct sock *sk) icsk->icsk_mtup.probe_size; tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; - tp->rcv_ssthresh = tcp_current_ssthresh(sk); + tp->snd_ssthresh = tcp_current_ssthresh(sk); icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; icsk->icsk_mtup.probe_size = 0; @@ -2970,7 +2975,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) before(tp->snd_una, tp->high_seq) && icsk->icsk_ca_state != TCP_CA_Open && tp->fackets_out > tp->reordering) { - tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering); + tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering, 0); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSS); } @@ -3398,8 +3403,8 @@ static void tcp_ack_probe(struct sock *sk) static inline int tcp_ack_is_dubious(const struct sock *sk, const int flag) { - return (!(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) || - inet_csk(sk)->icsk_ca_state != TCP_CA_Open); + return !(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) || + inet_csk(sk)->icsk_ca_state != TCP_CA_Open; } static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag) @@ -3416,9 +3421,9 @@ static inline int tcp_may_update_window(const struct tcp_sock *tp, const u32 ack, const u32 ack_seq, const u32 nwin) { - return (after(ack, tp->snd_una) || + return after(ack, tp->snd_una) || after(ack_seq, tp->snd_wl1) || - (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd)); + (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd); } /* Update our send window. @@ -4035,6 +4040,8 @@ static void tcp_reset(struct sock *sk) default: sk->sk_err = ECONNRESET; } + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f25b56c..43cf901 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -55,7 +55,7 @@ static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) return 1; if (after(end_seq, s_win) && before(seq, e_win)) return 1; - return (seq == e_win && seq == end_seq); + return seq == e_win && seq == end_seq; } /* diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ea09d2f..05b1ecf 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1370,9 +1370,9 @@ static inline int tcp_nagle_check(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned mss_now, int nonagle) { - return (skb->len < mss_now && + return skb->len < mss_now && ((nonagle & TCP_NAGLE_CORK) || - (!nonagle && tp->packets_out && tcp_minshall_check(tp)))); + (!nonagle && tp->packets_out && tcp_minshall_check(tp))); } /* Return non-zero if the Nagle test allows this packet to be @@ -1443,10 +1443,10 @@ int tcp_may_send_now(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = tcp_send_head(sk); - return (skb && + return skb && tcp_snd_test(sk, skb, tcp_current_mss(sk), (tcp_skb_is_last(sk, skb) ? - tp->nonagle : TCP_NAGLE_PUSH))); + tp->nonagle : TCP_NAGLE_PUSH)); } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index baea4a1..74a6aa0 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -135,13 +135,16 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) /* This function calculates a "timeout" which is equivalent to the timeout of a * TCP connection after "boundary" unsuccessful, exponentially backed-off - * retransmissions with an initial RTO of TCP_RTO_MIN. + * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if + * syn_set flag is set. */ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, - unsigned int timeout) + unsigned int timeout, + bool syn_set) { unsigned int linear_backoff_thresh, start_ts; + unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; if (!inet_csk(sk)->icsk_retransmits) return false; @@ -152,12 +155,12 @@ static bool retransmits_timed_out(struct sock *sk, start_ts = tcp_sk(sk)->retrans_stamp; if (likely(timeout == 0)) { - linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN); + linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); if (boundary <= linear_backoff_thresh) - timeout = ((2 << boundary) - 1) * TCP_RTO_MIN; + timeout = ((2 << boundary) - 1) * rto_base; else - timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN + + timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; } return (tcp_time_stamp - start_ts) >= timeout; @@ -168,14 +171,15 @@ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int retry_until; - bool do_reset; + bool do_reset, syn_set = 0; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; + syn_set = 1; } else { - if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0)) { + if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); @@ -188,7 +192,7 @@ static int tcp_write_timeout(struct sock *sk) retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || - !retransmits_timed_out(sk, retry_until, 0); + !retransmits_timed_out(sk, retry_until, 0, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; @@ -196,8 +200,7 @@ static int tcp_write_timeout(struct sock *sk) } if (retransmits_timed_out(sk, retry_until, - (1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV) ? 0 : - icsk->icsk_user_timeout)) { + syn_set ? 0 : icsk->icsk_user_timeout, syn_set)) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; @@ -364,18 +367,19 @@ void tcp_retransmit_timer(struct sock *sk) if (icsk->icsk_retransmits == 0) { int mib_idx; - if (icsk->icsk_ca_state == TCP_CA_Disorder) { - if (tcp_is_sack(tp)) - mib_idx = LINUX_MIB_TCPSACKFAILURES; - else - mib_idx = LINUX_MIB_TCPRENOFAILURES; - } else if (icsk->icsk_ca_state == TCP_CA_Recovery) { + if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL; else mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL; } else if (icsk->icsk_ca_state == TCP_CA_Loss) { mib_idx = LINUX_MIB_TCPLOSSFAILURES; + } else if ((icsk->icsk_ca_state == TCP_CA_Disorder) || + tp->sacked_out) { + if (tcp_is_sack(tp)) + mib_idx = LINUX_MIB_TCPSACKFAILURES; + else + mib_idx = LINUX_MIB_TCPRENOFAILURES; } else { mib_idx = LINUX_MIB_TCPTIMEOUTS; } @@ -439,7 +443,7 @@ out_reset_timer: icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0)) + if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0)) __sk_dst_reset(sk); out:; diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index 20151d6..a534dda 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -80,7 +80,7 @@ static void tcp_westwood_init(struct sock *sk) */ static inline u32 westwood_do_filter(u32 a, u32 b) { - return (((7 * a) + b) >> 3); + return ((7 * a) + b) >> 3; } static void westwood_filter(struct westwood *w, u32 delta) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 869078d..4464f3b 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -61,7 +61,7 @@ static int xfrm4_get_saddr(struct net *net, static int xfrm4_get_tos(struct flowi *fl) { - return fl->fl4_tos; + return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */ } static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst, @@ -174,7 +174,7 @@ static inline int xfrm4_garbage_collect(struct dst_ops *ops) struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops); xfrm4_policy_afinfo.garbage_collect(net); - return (atomic_read(&ops->entries) > ops->gc_thresh * 2); + return (dst_entries_get_slow(ops) > ops->gc_thresh * 2); } static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -232,7 +232,6 @@ static struct dst_ops xfrm4_dst_ops = { .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, .gc_thresh = 1024, - .entries = ATOMIC_INIT(0), }; static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { @@ -288,6 +287,7 @@ void __init xfrm4_init(int rt_max_size) * and start cleaning when were 1/2 full */ xfrm4_dst_ops.gc_thresh = rt_max_size/2; + dst_entries_init(&xfrm4_dst_ops); xfrm4_state_init(); xfrm4_policy_init(); diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 1ef1366..4794762 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -21,21 +21,25 @@ static int xfrm4_init_flags(struct xfrm_state *x) } static void -__xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) +{ + sel->daddr.a4 = fl->fl4_dst; + sel->saddr.a4 = fl->fl4_src; + sel->dport = xfrm_flowi_dport(fl); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET; + sel->prefixlen_d = 32; + sel->prefixlen_s = 32; + sel->proto = fl->proto; + sel->ifindex = fl->oif; +} + +static void +xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr) { - x->sel.daddr.a4 = fl->fl4_dst; - x->sel.saddr.a4 = fl->fl4_src; - x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = htons(0xffff); - x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = htons(0xffff); - x->sel.family = AF_INET; - x->sel.prefixlen_d = 32; - x->sel.prefixlen_s = 32; - x->sel.proto = fl->proto; - x->sel.ifindex = fl->oif; x->id = tmpl->id; if (x->id.daddr.a4 == 0) x->id.daddr.a4 = daddr->a4; @@ -70,6 +74,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .owner = THIS_MODULE, .init_flags = xfrm4_init_flags, .init_tempsel = __xfrm4_init_tempsel, + .init_temprop = xfrm4_init_temprop, .output = xfrm4_output, .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5bc893e..ec7a91d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -243,7 +243,7 @@ static inline bool addrconf_qdisc_ok(const struct net_device *dev) /* Check if a route is valid prefix route */ static inline int addrconf_is_prefix_route(const struct rt6_info *rt) { - return ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0); + return (rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0; } static void addrconf_del_timer(struct inet6_ifaddr *ifp) @@ -1544,7 +1544,7 @@ static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev) return 0; } -int __ipv6_isatap_ifid(u8 *eui, __be32 addr) +static int __ipv6_isatap_ifid(u8 *eui, __be32 addr) { if (addr == 0) return -1; @@ -1560,7 +1560,6 @@ int __ipv6_isatap_ifid(u8 *eui, __be32 addr) memcpy(eui + 4, &addr, 4); return 0; } -EXPORT_SYMBOL(__ipv6_isatap_ifid); static int addrconf_ifid_sit(u8 *eui, struct net_device *dev) { @@ -4638,10 +4637,12 @@ int __init addrconf_init(void) if (err < 0) { printk(KERN_CRIT "IPv6 Addrconf:" " cannot initialize default policy table: %d.\n", err); - return err; + goto out; } - register_pernet_subsys(&addrconf_ops); + err = register_pernet_subsys(&addrconf_ops); + if (err < 0) + goto out_addrlabel; /* The addrconf netdev notifier requires that loopback_dev * has it's ipv6 private information allocated and setup @@ -4693,7 +4694,9 @@ errout: unregister_netdevice_notifier(&ipv6_dev_notf); errlo: unregister_pernet_subsys(&addrconf_ops); - +out_addrlabel: + ipv6_addr_label_cleanup(); +out: return err; } @@ -4704,6 +4707,7 @@ void addrconf_cleanup(void) unregister_netdevice_notifier(&ipv6_dev_notf); unregister_pernet_subsys(&addrconf_ops); + ipv6_addr_label_cleanup(); rtnl_lock(); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f0e774c..c8993e5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -393,6 +393,11 @@ int __init ipv6_addr_label_init(void) return register_pernet_subsys(&ipv6_addr_label_ops); } +void ipv6_addr_label_cleanup(void) +{ + unregister_pernet_subsys(&ipv6_addr_label_ops); +} + static const struct nla_policy ifal_policy[IFAL_MAX+1] = { [IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), }, [IFAL_LABEL] = { .len = sizeof(u32), }, @@ -513,10 +518,9 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) static inline int ip6addrlbl_msgsize(void) { - return (NLMSG_ALIGN(sizeof(struct ifaddrlblmsg)) + return NLMSG_ALIGN(sizeof(struct ifaddrlblmsg)) + nla_total_size(16) /* IFAL_ADDRESS */ - + nla_total_size(4) /* IFAL_LABEL */ - ); + + nla_total_size(4); /* IFAL_LABEL */ } static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 4869797..54e8e42 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -468,7 +468,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = sk->sk_bound_dev_if; *uaddr_len = sizeof(*sin); - return(0); + return 0; } EXPORT_SYMBOL(inet6_getname); @@ -489,7 +489,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCADDRT: case SIOCDELRT: - return(ipv6_route_ioctl(net, cmd, (void __user *)arg)); + return ipv6_route_ioctl(net, cmd, (void __user *)arg); case SIOCSIFADDR: return addrconf_add_ifaddr(net, (void __user *) arg); @@ -503,7 +503,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return sk->sk_prot->ioctl(sk, cmd, arg); } /*NOTREACHED*/ - return(0); + return 0; } EXPORT_SYMBOL(inet6_ioctl); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index e1caa5d..14ed0a9 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -13,12 +13,12 @@ int ipv6_ext_hdr(u8 nexthdr) /* * find out if nexthdr is an extension header or a protocol */ - return ( (nexthdr == NEXTHDR_HOP) || + return (nexthdr == NEXTHDR_HOP) || (nexthdr == NEXTHDR_ROUTING) || (nexthdr == NEXTHDR_FRAGMENT) || (nexthdr == NEXTHDR_AUTH) || (nexthdr == NEXTHDR_NONE) || - (nexthdr == NEXTHDR_DEST) ); + (nexthdr == NEXTHDR_DEST); } /* diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b1108ed..d829874 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -34,11 +34,10 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, { struct fib_lookup_arg arg = { .lookup_ptr = lookup, + .flags = FIB_LOOKUP_NOREF, }; fib_rules_lookup(net->ipv6.fib6_rules_ops, fl, flags, &arg); - if (arg.rule) - fib_rule_put(arg.rule); if (arg.result) return arg.result; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b6a5859..de38211 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1500,15 +1500,18 @@ static void fib6_gc_timer_cb(unsigned long arg) static int __net_init fib6_net_init(struct net *net) { + size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; + setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) goto out_timer; - net->ipv6.fib_table_hash = kcalloc(FIB6_TABLE_HASHSZ, - sizeof(*net->ipv6.fib_table_hash), - GFP_KERNEL); + /* Avoid false sharing : Use at least a full cache line */ + size = max_t(size_t, size, L1_CACHE_BYTES); + + net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1838927..99157b4 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -639,7 +639,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); - int truesizes = 0; + struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || @@ -651,18 +651,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; - truesizes += frag->truesize; } + skb->truesize -= frag->truesize; } err = 0; @@ -693,7 +693,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); - skb->truesize -= truesizes; skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); @@ -756,6 +755,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) IPSTATS_MIB_FRAGFAILS); dst_release(&rt->dst); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: @@ -870,8 +878,8 @@ static inline int ip6_rt_check(struct rt6key *rt_key, struct in6_addr *fl_addr, struct in6_addr *addr_cache) { - return ((rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && - (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache))); + return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && + (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache)); } static struct dst_entry *ip6_sk_dst_check(struct sock *sk, diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 29f99dd..c2c0f89 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -75,7 +75,7 @@ MODULE_LICENSE("GPL"); (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ (HASH_SIZE - 1)) -static void ip6_tnl_dev_init(struct net_device *dev); +static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); static int ip6_tnl_net_id __read_mostly; @@ -83,15 +83,42 @@ struct ip6_tnl_net { /* the IPv6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ - struct ip6_tnl *tnls_r_l[HASH_SIZE]; - struct ip6_tnl *tnls_wc[1]; - struct ip6_tnl **tnls[2]; + struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE]; + struct ip6_tnl __rcu *tnls_wc[1]; + struct ip6_tnl __rcu **tnls[2]; }; +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + +static struct net_device_stats *ip6_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} + /* - * Locking : hash tables are protected by RCU and a spinlock + * Locking : hash tables are protected by RCU and RTNL */ -static DEFINE_SPINLOCK(ip6_tnl_lock); static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) { @@ -138,8 +165,8 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) static struct ip6_tnl * ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) { - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(local); struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); @@ -167,7 +194,7 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) * Return: head of IPv6 tunnel list **/ -static struct ip6_tnl ** +static struct ip6_tnl __rcu ** ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p) { struct in6_addr *remote = &p->raddr; @@ -190,12 +217,10 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p) static void ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { - struct ip6_tnl **tp = ip6_tnl_bucket(ip6n, &t->parms); + struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); - spin_lock_bh(&ip6_tnl_lock); - t->next = *tp; + rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); - spin_unlock_bh(&ip6_tnl_lock); } /** @@ -206,18 +231,25 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) static void ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { - struct ip6_tnl **tp; - - for (tp = ip6_tnl_bucket(ip6n, &t->parms); *tp; tp = &(*tp)->next) { - if (t == *tp) { - spin_lock_bh(&ip6_tnl_lock); - *tp = t->next; - spin_unlock_bh(&ip6_tnl_lock); + struct ip6_tnl __rcu **tp; + struct ip6_tnl *iter; + + for (tp = ip6_tnl_bucket(ip6n, &t->parms); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } } +static void ip6_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + /** * ip6_tnl_create() - create a new tunnel * @p: tunnel parameters @@ -256,7 +288,9 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) t = netdev_priv(dev); t->parms = *p; - ip6_tnl_dev_init(dev); + err = ip6_tnl_dev_init(dev); + if (err < 0) + goto failed_free; if ((err = register_netdevice(dev)) < 0) goto failed_free; @@ -266,7 +300,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) return t; failed_free: - free_netdev(dev); + ip6_dev_free(dev); failed: return NULL; } @@ -290,10 +324,13 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net, { struct in6_addr *remote = &p->raddr; struct in6_addr *local = &p->laddr; + struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for (t = *ip6_tnl_bucket(ip6n, p); t; t = t->next) { + for (tp = ip6_tnl_bucket(ip6n, p); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr)) return t; @@ -318,13 +355,10 @@ ip6_tnl_dev_uninit(struct net_device *dev) struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - if (dev == ip6n->fb_tnl_dev) { - spin_lock_bh(&ip6_tnl_lock); - ip6n->tnls_wc[0] = NULL; - spin_unlock_bh(&ip6_tnl_lock); - } else { + if (dev == ip6n->fb_tnl_dev) + rcu_assign_pointer(ip6n->tnls_wc[0], NULL); + else ip6_tnl_unlink(ip6n, t); - } ip6_tnl_dst_reset(t); dev_put(dev); } @@ -702,6 +736,8 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { + struct pcpu_tstats *tstats; + if (t->parms.proto != ipproto && t->parms.proto != 0) { rcu_read_unlock(); goto discard; @@ -724,10 +760,16 @@ 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_tunnel_rx(skb, t->dev); + tstats = this_cpu_ptr(t->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + __skb_tunnel_rx(skb, t->dev); dscp_ecn_decapsulate(t, ipv6h, skb); + netif_rx(skb); + rcu_read_unlock(); return 0; } @@ -934,8 +976,10 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, err = ip6_local_out(skb); if (net_xmit_eval(err) == 0) { - stats->tx_bytes += pkt_len; - stats->tx_packets++; + struct pcpu_tstats *tstats = this_cpu_ptr(t->dev->tstats); + + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; } else { stats->tx_errors++; stats->tx_aborted_errors++; @@ -1300,12 +1344,14 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ip6_tnl_netdev_ops = { - .ndo_uninit = ip6_tnl_dev_uninit, + .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_xmit, - .ndo_do_ioctl = ip6_tnl_ioctl, + .ndo_do_ioctl = ip6_tnl_ioctl, .ndo_change_mtu = ip6_tnl_change_mtu, + .ndo_get_stats = ip6_get_stats, }; + /** * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel @@ -1317,7 +1363,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { static void ip6_tnl_dev_setup(struct net_device *dev) { dev->netdev_ops = &ip6_tnl_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr); @@ -1333,12 +1379,17 @@ static void ip6_tnl_dev_setup(struct net_device *dev) * @dev: virtual device associated with tunnel **/ -static inline void +static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + t->dev = dev; strcpy(t->parms.name, dev->name); + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + return 0; } /** @@ -1346,11 +1397,15 @@ ip6_tnl_dev_init_gen(struct net_device *dev) * @dev: virtual device associated with tunnel **/ -static void ip6_tnl_dev_init(struct net_device *dev) +static int ip6_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - ip6_tnl_dev_init_gen(dev); + int err = ip6_tnl_dev_init_gen(dev); + + if (err) + return err; ip6_tnl_link_config(t); + return 0; } /** @@ -1360,16 +1415,20 @@ static void ip6_tnl_dev_init(struct net_device *dev) * Return: 0 **/ -static void __net_init ip6_fb_tnl_dev_init(struct net_device *dev) +static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err = ip6_tnl_dev_init_gen(dev); + + if (err) + return err; - ip6_tnl_dev_init_gen(dev); t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - ip6n->tnls_wc[0] = t; + rcu_assign_pointer(ip6n->tnls_wc[0], t); + return 0; } static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { @@ -1391,14 +1450,14 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) LIST_HEAD(list); for (h = 0; h < HASH_SIZE; h++) { - t = ip6n->tnls_r_l[h]; + t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t != NULL) { unregister_netdevice_queue(t->dev, &list); - t = t->next; + t = rtnl_dereference(t->next); } } - t = ip6n->tnls_wc[0]; + t = rtnl_dereference(ip6n->tnls_wc[0]); unregister_netdevice_queue(t->dev, &list); unregister_netdevice_many(&list); } @@ -1419,7 +1478,9 @@ static int __net_init ip6_tnl_init_net(struct net *net) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); - ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + if (err < 0) + goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) @@ -1427,7 +1488,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) return 0; err_register: - free_netdev(ip6n->fb_tnl_dev); + ip6_dev_free(ip6n->fb_tnl_dev); err_alloc_dev: return err; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 66078da..6f32ffc 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -667,6 +667,7 @@ static int pim6_rcv(struct sk_buff *skb) skb_tunnel_rx(skb, reg_dev); netif_rx(skb); + dev_put(reg_dev); return 0; drop: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 69a0051..998d6d2 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -91,7 +91,9 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> -static u32 ndisc_hash(const void *pkey, const struct net_device *dev); +static u32 ndisc_hash(const void *pkey, + const struct net_device *dev, + __u32 rnd); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -228,12 +230,12 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while(cur < end && cur->nd_opt_type != type); - return (cur <= end && cur->nd_opt_type == type ? cur : NULL); + return cur <= end && cur->nd_opt_type == type ? cur : NULL; } static inline int ndisc_is_useropt(struct nd_opt_hdr *opt) { - return (opt->nd_opt_type == ND_OPT_RDNSS); + return opt->nd_opt_type == ND_OPT_RDNSS; } static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, @@ -244,7 +246,7 @@ static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while(cur < end && !ndisc_is_useropt(cur)); - return (cur <= end && ndisc_is_useropt(cur) ? cur : NULL); + return cur <= end && ndisc_is_useropt(cur) ? cur : NULL; } static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, @@ -319,7 +321,7 @@ static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, int prepad = ndisc_addr_option_pad(dev->type); if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad)) return NULL; - return (lladdr + prepad); + return lladdr + prepad; } int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir) @@ -350,7 +352,9 @@ int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int d EXPORT_SYMBOL(ndisc_mc_map); -static u32 ndisc_hash(const void *pkey, const struct net_device *dev) +static u32 ndisc_hash(const void *pkey, + const struct net_device *dev, + __u32 hash_rnd) { const u32 *p32 = pkey; u32 addr_hash, i; @@ -359,7 +363,7 @@ static u32 ndisc_hash(const void *pkey, const struct net_device *dev) for (i = 0; i < (sizeof(struct in6_addr) / sizeof(u32)); i++) addr_hash ^= *p32++; - return jhash_2words(addr_hash, dev->ifindex, nd_tbl.hash_rnd); + return jhash_2words(addr_hash, dev->ifindex, hash_rnd); } static int ndisc_constructor(struct neighbour *neigh) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index c683e9e..51df035 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -82,13 +82,13 @@ EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); int ip6t_ext_hdr(u8 nexthdr) { - return ( (nexthdr == IPPROTO_HOPOPTS) || - (nexthdr == IPPROTO_ROUTING) || - (nexthdr == IPPROTO_FRAGMENT) || - (nexthdr == IPPROTO_ESP) || - (nexthdr == IPPROTO_AH) || - (nexthdr == IPPROTO_NONE) || - (nexthdr == IPPROTO_DSTOPTS) ); + return (nexthdr == IPPROTO_HOPOPTS) || + (nexthdr == IPPROTO_ROUTING) || + (nexthdr == IPPROTO_FRAGMENT) || + (nexthdr == IPPROTO_ESP) || + (nexthdr == IPPROTO_AH) || + (nexthdr == IPPROTO_NONE) || + (nexthdr == IPPROTO_DSTOPTS); } /* Returns whether matches rule or not. */ diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e677937..45e6efb7 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -764,7 +764,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) - return(-EAFNOSUPPORT); + return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); @@ -772,10 +772,10 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num) - return(-EINVAL); + return -EINVAL; if (proto > 255) - return(-EINVAL); + return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { @@ -985,7 +985,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) - return(-EINVAL); + return -EINVAL; if (val < 0) { rp->checksum = 0; } else { @@ -997,7 +997,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, break; default: - return(-ENOPROTOOPT); + return -ENOPROTOOPT; } } @@ -1190,7 +1190,7 @@ static int rawv6_init_sk(struct sock *sk) default: break; } - return(0); + return 0; } struct proto rawv6_prot = { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d126365..25661f9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -109,7 +109,6 @@ static struct dst_ops ip6_dst_ops_template = { .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .local_out = __ip6_local_out, - .entries = ATOMIC_INIT(0), }; static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -122,7 +121,6 @@ static struct dst_ops ip6_dst_blackhole_ops = { .destroy = ip6_dst_destroy, .check = ip6_dst_check, .update_pmtu = ip6_rt_blackhole_update_pmtu, - .entries = ATOMIC_INIT(0), }; static struct rt6_info ip6_null_entry_template = { @@ -217,14 +215,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static __inline__ int rt6_check_expired(const struct rt6_info *rt) { - return (rt->rt6i_flags & RTF_EXPIRES && - time_after(jiffies, rt->rt6i_expires)); + return (rt->rt6i_flags & RTF_EXPIRES) && + time_after(jiffies, rt->rt6i_expires); } static inline int rt6_need_strict(struct in6_addr *daddr) { - return (ipv6_addr_type(daddr) & - (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK)); + return ipv6_addr_type(daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } /* @@ -440,7 +438,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) __func__, match); net = dev_net(rt0->rt6i_dev); - return (match ? match : net->ipv6.ip6_null_entry); + return match ? match : net->ipv6.ip6_null_entry; } #ifdef CONFIG_IPV6_ROUTE_INFO @@ -670,7 +668,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad if (net_ratelimit()) printk(KERN_WARNING - "Neighbour table overflow.\n"); + "ipv6: Neighbour table overflow.\n"); dst_free(&rt->dst); return NULL; } @@ -859,7 +857,7 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl dst_release(*dstp); *dstp = new; - return (new ? 0 : -ENOMEM); + return new ? 0 : -ENOMEM; } EXPORT_SYMBOL_GPL(ip6_dst_blackhole); @@ -1058,19 +1056,22 @@ static int ip6_dst_gc(struct dst_ops *ops) int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + int entries; + entries = dst_entries_get_fast(ops); if (time_after(rt_last_gc + rt_min_interval, now) && - atomic_read(&ops->entries) <= rt_max_size) + entries <= rt_max_size) goto out; net->ipv6.ip6_rt_gc_expire++; fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net); net->ipv6.ip6_rt_last_gc = now; - if (atomic_read(&ops->entries) < ops->gc_thresh) + entries = dst_entries_get_slow(ops); + if (entries < ops->gc_thresh) net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; out: net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; - return (atomic_read(&ops->entries) > rt_max_size); + return entries > rt_max_size; } /* Clean host part of a prefix. Not necessary in radix tree, @@ -1169,6 +1170,8 @@ int ip6_route_add(struct fib6_config *cfg) if (addr_type & IPV6_ADDR_MULTICAST) rt->dst.input = ip6_mc_input; + else if (cfg->fc_flags & RTF_LOCAL) + rt->dst.input = ip6_input; else rt->dst.input = ip6_forward; @@ -1190,7 +1193,8 @@ int ip6_route_add(struct fib6_config *cfg) they would result in kernel looping; promote them to reject routes */ if ((cfg->fc_flags & RTF_REJECT) || - (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) { + (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK) + && !(cfg->fc_flags&RTF_LOCAL))) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { @@ -1556,14 +1560,13 @@ out: * i.e. Path MTU discovery */ -void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, - struct net_device *dev, u32 pmtu) +static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr, + struct net *net, u32 pmtu, int ifindex) { struct rt6_info *rt, *nrt; - struct net *net = dev_net(dev); int allfrag = 0; - rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0); + rt = rt6_lookup(net, daddr, saddr, ifindex, 0); if (rt == NULL) return; @@ -1631,6 +1634,27 @@ out: dst_release(&rt->dst); } +void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, + struct net_device *dev, u32 pmtu) +{ + struct net *net = dev_net(dev); + + /* + * RFC 1981 states that a node "MUST reduce the size of the packets it + * is sending along the path" that caused the Packet Too Big message. + * Since it's not possible in the general case to determine which + * interface was used to send the original packet, we update the MTU + * on the interface that will be used to send future packets. We also + * update the MTU on the interface that received the Packet Too Big in + * case the original packet was forced out that interface with + * SO_BINDTODEVICE or similar. This is the next best thing to the + * correct behaviour, which would be to update the MTU on all + * interfaces. + */ + rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0); + rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex); +} + /* * Misc support functions */ @@ -2082,6 +2106,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (rtm->rtm_type == RTN_UNREACHABLE) cfg->fc_flags |= RTF_REJECT; + if (rtm->rtm_type == RTN_LOCAL) + cfg->fc_flags |= RTF_LOCAL; + cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = sock_net(skb->sk); @@ -2202,6 +2229,8 @@ static int rt6_fill_node(struct net *net, NLA_PUT_U32(skb, RTA_TABLE, table); if (rt->rt6i_flags&RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; + else if (rt->rt6i_flags&RTF_LOCAL) + rtm->rtm_type = RTN_LOCAL; else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) rtm->rtm_type = RTN_LOCAL; else @@ -2496,7 +2525,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) net->ipv6.rt6_stats->fib_rt_alloc, net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, - atomic_read(&net->ipv6.ip6_dst_ops.entries), + dst_entries_get_slow(&net->ipv6.ip6_dst_ops), net->ipv6.rt6_stats->fib_discarded_routes); return 0; @@ -2638,11 +2667,14 @@ static int __net_init ip6_route_net_init(struct net *net) memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, sizeof(net->ipv6.ip6_dst_ops)); + if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) + goto out_ip6_dst_ops; + net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) - goto out_ip6_dst_ops; + goto out_ip6_dst_entries; net->ipv6.ip6_null_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; @@ -2692,6 +2724,8 @@ out_ip6_prohibit_entry: out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif +out_ip6_dst_entries: + dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: goto out; } @@ -2730,10 +2764,14 @@ int __init ip6_route_init(void) if (!ip6_dst_ops_template.kmem_cachep) goto out; - ret = register_pernet_subsys(&ip6_route_net_ops); + ret = dst_entries_init(&ip6_dst_blackhole_ops); if (ret) goto out_kmem_cache; + ret = register_pernet_subsys(&ip6_route_net_ops); + if (ret) + goto out_dst_entries; + ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; /* Registering of the loopback is done before this portion of code, @@ -2780,6 +2818,8 @@ out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); +out_dst_entries: + dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); goto out; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 86618eb..367a6cc 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -63,36 +63,63 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) -static void ipip6_tunnel_init(struct net_device *dev); +static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); +static void ipip6_dev_free(struct net_device *dev); static int sit_net_id __read_mostly; struct sit_net { - struct ip_tunnel *tunnels_r_l[HASH_SIZE]; - struct ip_tunnel *tunnels_r[HASH_SIZE]; - struct ip_tunnel *tunnels_l[HASH_SIZE]; - struct ip_tunnel *tunnels_wc[1]; - struct ip_tunnel **tunnels[4]; + struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_wc[1]; + struct ip_tunnel __rcu **tunnels[4]; struct net_device *fb_tunnel_dev; }; /* - * Locking : hash tables are protected by RCU and a spinlock + * Locking : hash tables are protected by RCU and RTNL */ -static DEFINE_SPINLOCK(ipip6_lock); #define for_each_ip_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + +static struct net_device_stats *ipip6_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} /* * Must be invoked with rcu_read_lock */ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local) { - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(local); struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); @@ -121,12 +148,12 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, return NULL; } -static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn, +static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; - unsigned h = 0; + unsigned int h = 0; int prio = 0; if (remote) { @@ -140,7 +167,7 @@ static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn, return &sitn->tunnels[prio][h]; } -static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn, +static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn, struct ip_tunnel *t) { return __ipip6_bucket(sitn, &t->parms); @@ -148,13 +175,14 @@ static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn, static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) { - struct ip_tunnel **tp; - - for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) { - if (t == *tp) { - spin_lock_bh(&ipip6_lock); - *tp = t->next; - spin_unlock_bh(&ipip6_lock); + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = ipip6_bucket(sitn, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } @@ -162,12 +190,10 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { - struct ip_tunnel **tp = ipip6_bucket(sitn, t); + struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t); - spin_lock_bh(&ipip6_lock); - t->next = *tp; + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); - spin_unlock_bh(&ipip6_lock); } static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) @@ -187,17 +213,20 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) #endif } -static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, +static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; - struct ip_tunnel *t, **tp, *nt; + struct ip_tunnel *t, *nt; + struct ip_tunnel __rcu **tp; struct net_device *dev; char name[IFNAMSIZ]; struct sit_net *sitn = net_generic(net, sit_net_id); - for (tp = __ipip6_bucket(sitn, parms); (t = *tp) != NULL; tp = &t->next) { + for (tp = __ipip6_bucket(sitn, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && parms->link == t->parms.link) { @@ -213,7 +242,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, if (parms->name[0]) strlcpy(name, parms->name, IFNAMSIZ); else - sprintf(name, "sit%%d"); + strcpy(name, "sit%d"); dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup); if (dev == NULL) @@ -229,7 +258,8 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - ipip6_tunnel_init(dev); + if (ipip6_tunnel_init(dev) < 0) + goto failed_free; ipip6_tunnel_clone_6rd(dev, sitn); if (parms->i_flags & SIT_ISATAP) @@ -244,7 +274,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, return nt; failed_free: - free_netdev(dev); + ipip6_dev_free(dev); failed: return NULL; } @@ -340,7 +370,7 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) ASSERT_RTNL(); - for (p = t->prl; p; p = p->next) { + for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) { if (p->addr == a->addr) { if (chg) { p->flags = a->flags; @@ -451,15 +481,12 @@ static void ipip6_tunnel_uninit(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { - spin_lock_bh(&ipip6_lock); - sitn->tunnels_wc[0] = NULL; - spin_unlock_bh(&ipip6_lock); - dev_put(dev); + rcu_assign_pointer(sitn->tunnels_wc[0], NULL); } else { ipip6_tunnel_unlink(sitn, netdev_priv(dev)); ipip6_tunnel_del_prl(netdev_priv(dev), NULL); - dev_put(dev); } + dev_put(dev); } @@ -548,6 +575,8 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { + struct pcpu_tstats *tstats; + secpath_reset(skb); skb->mac_header = skb->network_header; skb_reset_network_header(skb); @@ -563,10 +592,16 @@ static int ipip6_rcv(struct sk_buff *skb) return 0; } - skb_tunnel_rx(skb, tunnel->dev); + tstats = this_cpu_ptr(tunnel->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + __skb_tunnel_rx(skb, tunnel->dev); ipip6_ecn_decapsulate(iph, skb); + netif_rx(skb); + rcu_read_unlock(); return 0; } @@ -590,7 +625,7 @@ __be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel) #ifdef CONFIG_IPV6_SIT_6RD if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, tunnel->ip6rd.prefixlen)) { - unsigned pbw0, pbi0; + unsigned int pbw0, pbi0; int pbi1; u32 d; @@ -625,14 +660,13 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct pcpu_tstats *tstats; struct iphdr *tiph = &tunnel->parms.iph; struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ - struct net_device *tdev; /* Device to other host */ + struct net_device *tdev; /* Device to other host */ struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; @@ -703,20 +737,20 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, .oif = tunnel->parms.link, .proto = IPPROTO_IPV6 }; if (ip_route_output_key(dev_net(dev), &rt, &fl)) { - stats->tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error_icmp; } } if (rt->rt_type != RTN_UNICAST) { ip_rt_put(rt); - stats->tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error_icmp; } tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); - stats->collisions++; + dev->stats.collisions++; goto tx_error; } @@ -724,7 +758,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { - stats->collisions++; + dev->stats.collisions++; ip_rt_put(rt); goto tx_error; } @@ -763,7 +797,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - txq->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -799,14 +833,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, iph->ttl = iph6->hop_limit; nf_reset(skb); - - IPTUNNEL_XMIT(); + tstats = this_cpu_ptr(dev->tstats); + __IPTUNNEL_XMIT(tstats, &dev->stats); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: - stats->tx_errors++; + dev->stats.tx_errors++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -1083,12 +1117,19 @@ static const struct net_device_ops ipip6_netdev_ops = { .ndo_start_xmit = ipip6_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, .ndo_change_mtu = ipip6_tunnel_change_mtu, + .ndo_get_stats = ipip6_get_stats, }; +static void ipip6_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + static void ipip6_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip6_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); @@ -1098,9 +1139,10 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_LLTX; } -static void ipip6_tunnel_init(struct net_device *dev) +static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); @@ -1111,9 +1153,14 @@ static void ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; } -static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) +static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -1128,8 +1175,12 @@ static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; dev_hold(dev); sitn->tunnels_wc[0] = tunnel; + return 0; } static struct xfrm_tunnel sit_handler __read_mostly = { @@ -1173,7 +1224,10 @@ static int __net_init sit_init_net(struct net *net) } dev_net_set(sitn->fb_tunnel_dev, net); - ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + if (err) + goto err_dev_free; + ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); if ((err = register_netdev(sitn->fb_tunnel_dev))) @@ -1183,7 +1237,8 @@ static int __net_init sit_init_net(struct net *net) err_reg_dev: dev_put(sitn->fb_tunnel_dev); - free_netdev(sitn->fb_tunnel_dev); +err_dev_free: + ipip6_dev_free(sitn->fb_tunnel_dev); err_alloc_dev: return err; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ba5258ef..7e41e2c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -139,7 +139,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; if (usin->sin6_family != AF_INET6) - return(-EAFNOSUPPORT); + return -EAFNOSUPPORT; memset(&fl, 0, sizeof(fl)); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 6baeabb..7e74023 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -199,7 +199,7 @@ static inline int xfrm6_garbage_collect(struct dst_ops *ops) struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops); xfrm6_policy_afinfo.garbage_collect(net); - return (atomic_read(&ops->entries) > ops->gc_thresh * 2); + return dst_entries_get_fast(ops) > ops->gc_thresh * 2; } static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -255,7 +255,6 @@ static struct dst_ops xfrm6_dst_ops = { .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, .gc_thresh = 1024, - .entries = ATOMIC_INIT(0), }; static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { @@ -312,11 +311,13 @@ int __init xfrm6_init(void) */ gc_thresh = FIB6_TABLE_HASHSZ * 8; xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; + dst_entries_init(&xfrm6_dst_ops); ret = xfrm6_policy_init(); - if (ret) + if (ret) { + dst_entries_destroy(&xfrm6_dst_ops); goto out; - + } ret = xfrm6_state_init(); if (ret) goto out_policy; @@ -341,4 +342,5 @@ void xfrm6_fini(void) //xfrm6_input_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); + dst_entries_destroy(&xfrm6_dst_ops); } diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index f417b77..a67575d 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -20,23 +20,27 @@ #include <net/addrconf.h> static void -__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) { /* Initialize temporary selector matching only * to current session. */ - ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst); - ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src); - x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = htons(0xffff); - x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = htons(0xffff); - x->sel.family = AF_INET6; - x->sel.prefixlen_d = 128; - x->sel.prefixlen_s = 128; - x->sel.proto = fl->proto; - x->sel.ifindex = fl->oif; + ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst); + ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src); + sel->dport = xfrm_flowi_dport(fl); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET6; + sel->prefixlen_d = 128; + sel->prefixlen_s = 128; + sel->proto = fl->proto; + sel->ifindex = fl->oif; +} + +static void +xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr) +{ x->id = tmpl->id; if (ipv6_addr_any((struct in6_addr*)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); @@ -168,6 +172,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .eth_proto = htons(ETH_P_IPV6), .owner = THIS_MODULE, .init_tempsel = __xfrm6_init_tempsel, + .init_temprop = xfrm6_init_temprop, .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index ac7584b..2969cad 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -199,7 +199,7 @@ static void x6spi_destroy_rcu(struct rcu_head *head) container_of(head, struct xfrm6_tunnel_spi, rcu_head)); } -void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) +static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; @@ -223,8 +223,6 @@ void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) spin_unlock_bh(&xfrm6_tunnel_spi_lock); } -EXPORT_SYMBOL(xfrm6_tunnel_free_spi); - static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { skb_push(skb, -skb_network_offset(skb)); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index fd55b51..7f097989 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -573,9 +573,9 @@ static int irda_find_lsap_sel(struct irda_sock *self, char *name) /* Requested object/attribute doesn't exist */ if((self->errno == IAS_CLASS_UNKNOWN) || (self->errno == IAS_ATTRIB_UNKNOWN)) - return (-EADDRNOTAVAIL); + return -EADDRNOTAVAIL; else - return (-EHOSTUNREACH); + return -EHOSTUNREACH; } /* Get the remote TSAP selector */ @@ -663,7 +663,7 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name) __func__, name); self->daddr = DEV_ADDR_ANY; kfree(discoveries); - return(-ENOTUNIQ); + return -ENOTUNIQ; } /* First time we found that one, save it ! */ daddr = self->daddr; @@ -677,7 +677,7 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name) IRDA_DEBUG(0, "%s(), unexpected IAS query failure\n", __func__); self->daddr = DEV_ADDR_ANY; kfree(discoveries); - return(-EHOSTUNREACH); + return -EHOSTUNREACH; break; } } @@ -689,7 +689,7 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name) IRDA_DEBUG(1, "%s(), cannot discover service ''%s'' in any device !!!\n", __func__, name); self->daddr = DEV_ADDR_ANY; - return(-EADDRNOTAVAIL); + return -EADDRNOTAVAIL; } /* Revert back to discovered device & service */ @@ -715,14 +715,11 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr, struct sockaddr_irda saddr; struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); - int err; - lock_kernel(); memset(&saddr, 0, sizeof(saddr)); if (peer) { - err = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) - goto out; + return -ENOTCONN; saddr.sir_family = AF_IRDA; saddr.sir_lsap_sel = self->dtsap_sel; @@ -739,10 +736,8 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr, /* uaddr_len come to us uninitialised */ *uaddr_len = sizeof (struct sockaddr_irda); memcpy(uaddr, &saddr, *uaddr_len); - err = 0; -out: - unlock_kernel(); - return err; + + return 0; } /* @@ -758,7 +753,8 @@ static int irda_listen(struct socket *sock, int backlog) IRDA_DEBUG(2, "%s()\n", __func__); - lock_kernel(); + lock_sock(sk); + if ((sk->sk_type != SOCK_STREAM) && (sk->sk_type != SOCK_SEQPACKET) && (sk->sk_type != SOCK_DGRAM)) goto out; @@ -770,7 +766,7 @@ static int irda_listen(struct socket *sock, int backlog) err = 0; } out: - unlock_kernel(); + release_sock(sk); return err; } @@ -793,7 +789,7 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len != sizeof(struct sockaddr_irda)) return -EINVAL; - lock_kernel(); + lock_sock(sk); #ifdef CONFIG_IRDA_ULTRA /* Special care for Ultra sockets */ if ((sk->sk_type == SOCK_DGRAM) && @@ -836,7 +832,7 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = 0; out: - unlock_kernel(); + release_sock(sk); return err; } @@ -856,12 +852,13 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) IRDA_DEBUG(2, "%s()\n", __func__); - lock_kernel(); err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0); if (err) - goto out; + return err; err = -EINVAL; + + lock_sock(sk); if (sock->state != SS_UNCONNECTED) goto out; @@ -947,7 +944,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) irda_connect_response(new); err = 0; out: - unlock_kernel(); + release_sock(sk); return err; } @@ -981,7 +978,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr, IRDA_DEBUG(2, "%s(%p)\n", __func__, self); - lock_kernel(); + lock_sock(sk); /* Don't allow connect for Ultra sockets */ err = -ESOCKTNOSUPPORT; if ((sk->sk_type == SOCK_DGRAM) && (sk->sk_protocol == IRDAPROTO_ULTRA)) @@ -1072,6 +1069,8 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr, if (sk->sk_state != TCP_ESTABLISHED) { sock->state = SS_UNCONNECTED; + if (sk->sk_prot->disconnect(sk, flags)) + sock->state = SS_DISCONNECTING; err = sock_error(sk); if (!err) err = -ECONNRESET; @@ -1084,7 +1083,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr, self->saddr = irttp_get_saddr(self->tsap); err = 0; out: - unlock_kernel(); + release_sock(sk); return err; } @@ -1231,7 +1230,6 @@ static int irda_release(struct socket *sock) if (sk == NULL) return 0; - lock_kernel(); lock_sock(sk); sk->sk_state = TCP_CLOSE; sk->sk_shutdown |= SEND_SHUTDOWN; @@ -1250,7 +1248,6 @@ static int irda_release(struct socket *sock) /* Destroy networking socket if we are the last reference on it, * i.e. if(sk->sk_refcnt == 0) -> sk_free(sk) */ sock_put(sk); - unlock_kernel(); /* Notes on socket locking and deallocation... - Jean II * In theory we should put pairs of sock_hold() / sock_put() to @@ -1298,7 +1295,6 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len); - lock_kernel(); /* Note : socket.c set MSG_EOR on SEQPACKET sockets */ if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_EOR | MSG_CMSG_COMPAT | MSG_NOSIGNAL)) { @@ -1306,6 +1302,8 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock, goto out; } + lock_sock(sk); + if (sk->sk_shutdown & SEND_SHUTDOWN) goto out_err; @@ -1361,14 +1359,14 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock, goto out_err; } - unlock_kernel(); + release_sock(sk); /* Tell client how much data we actually sent */ return len; out_err: err = sk_stream_error(sk, msg->msg_flags, err); out: - unlock_kernel(); + release_sock(sk); return err; } @@ -1390,14 +1388,10 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(4, "%s()\n", __func__); - lock_kernel(); - if ((err = sock_error(sk)) < 0) - goto out; - skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); if (!skb) - goto out; + return err; skb_reset_transport_header(skb); copied = skb->len; @@ -1425,12 +1419,8 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, irttp_flow_request(self->tsap, FLOW_START); } } - unlock_kernel(); - return copied; -out: - unlock_kernel(); - return err; + return copied; } /* @@ -1448,17 +1438,15 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(3, "%s()\n", __func__); - lock_kernel(); if ((err = sock_error(sk)) < 0) - goto out; + return err; - err = -EINVAL; if (sock->flags & __SO_ACCEPTCON) - goto out; + return -EINVAL; err =-EOPNOTSUPP; if (flags & MSG_OOB) - goto out; + return -EOPNOTSUPP; err = 0; target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); @@ -1500,7 +1488,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, finish_wait(sk_sleep(sk), &wait); if (err) - goto out; + return err; if (sk->sk_shutdown & RCV_SHUTDOWN) break; @@ -1553,9 +1541,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, } } -out: - unlock_kernel(); - return err ? : copied; + return copied; } /* @@ -1573,13 +1559,12 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock, struct sk_buff *skb; int err; - lock_kernel(); - IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len); - err = -EINVAL; if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT)) - goto out; + return -EINVAL; + + lock_sock(sk); if (sk->sk_shutdown & SEND_SHUTDOWN) { send_sig(SIGPIPE, current, 0); @@ -1630,10 +1615,12 @@ static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(0, "%s(), err=%d\n", __func__, err); goto out; } - unlock_kernel(); + + release_sock(sk); return len; + out: - unlock_kernel(); + release_sock(sk); return err; } @@ -1656,10 +1643,11 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(4, "%s(), len=%zd\n", __func__, len); - lock_kernel(); err = -EINVAL; if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT)) - goto out; + return -EINVAL; + + lock_sock(sk); err = -EPIPE; if (sk->sk_shutdown & SEND_SHUTDOWN) { @@ -1732,7 +1720,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock, if (err) IRDA_DEBUG(0, "%s(), err=%d\n", __func__, err); out: - unlock_kernel(); + release_sock(sk); return err ? : len; } #endif /* CONFIG_IRDA_ULTRA */ @@ -1747,7 +1735,7 @@ static int irda_shutdown(struct socket *sock, int how) IRDA_DEBUG(1, "%s(%p)\n", __func__, self); - lock_kernel(); + lock_sock(sk); sk->sk_state = TCP_CLOSE; sk->sk_shutdown |= SEND_SHUTDOWN; @@ -1769,7 +1757,7 @@ static int irda_shutdown(struct socket *sock, int how) self->daddr = DEV_ADDR_ANY; /* Until we get re-connected */ self->saddr = 0x0; /* so IrLMP assign us any link */ - unlock_kernel(); + release_sock(sk); return 0; } @@ -1786,7 +1774,6 @@ static unsigned int irda_poll(struct file * file, struct socket *sock, IRDA_DEBUG(4, "%s()\n", __func__); - lock_kernel(); poll_wait(file, sk_sleep(sk), wait); mask = 0; @@ -1834,20 +1821,8 @@ static unsigned int irda_poll(struct file * file, struct socket *sock, default: break; } - unlock_kernel(); - return mask; -} -static unsigned int irda_datagram_poll(struct file *file, struct socket *sock, - poll_table *wait) -{ - int err; - - lock_kernel(); - err = datagram_poll(file, sock, wait); - unlock_kernel(); - - return err; + return mask; } /* @@ -1860,7 +1835,6 @@ static int irda_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) IRDA_DEBUG(4, "%s(), cmd=%#x\n", __func__, cmd); - lock_kernel(); err = -EINVAL; switch (cmd) { case TIOCOUTQ: { @@ -1903,7 +1877,6 @@ static int irda_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) IRDA_DEBUG(1, "%s(), doing device ioctl!\n", __func__); err = -ENOIOCTLCMD; } - unlock_kernel(); return err; } @@ -1927,7 +1900,7 @@ static int irda_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon * Set some options for the socket * */ -static int __irda_setsockopt(struct socket *sock, int level, int optname, +static int irda_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; @@ -1935,13 +1908,15 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, struct irda_ias_set *ias_opt; struct ias_object *ias_obj; struct ias_attrib * ias_attr; /* Attribute in IAS object */ - int opt, free_ias = 0; + int opt, free_ias = 0, err = 0; IRDA_DEBUG(2, "%s(%p)\n", __func__, self); if (level != SOL_IRLMP) return -ENOPROTOOPT; + lock_sock(sk); + switch (optname) { case IRLMP_IAS_SET: /* The user want to add an attribute to an existing IAS object @@ -1951,17 +1926,22 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, * create the right attribute... */ - if (optlen != sizeof(struct irda_ias_set)) - return -EINVAL; + if (optlen != sizeof(struct irda_ias_set)) { + err = -EINVAL; + goto out; + } ias_opt = kmalloc(sizeof(struct irda_ias_set), GFP_ATOMIC); - if (ias_opt == NULL) - return -ENOMEM; + if (ias_opt == NULL) { + err = -ENOMEM; + goto out; + } /* Copy query to the driver. */ if (copy_from_user(ias_opt, optval, optlen)) { kfree(ias_opt); - return -EFAULT; + err = -EFAULT; + goto out; } /* Find the object we target. @@ -1971,7 +1951,8 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, if(ias_opt->irda_class_name[0] == '\0') { if(self->ias_obj == NULL) { kfree(ias_opt); - return -EINVAL; + err = -EINVAL; + goto out; } ias_obj = self->ias_obj; } else @@ -1983,7 +1964,8 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, if((!capable(CAP_NET_ADMIN)) && ((ias_obj == NULL) || (ias_obj != self->ias_obj))) { kfree(ias_opt); - return -EPERM; + err = -EPERM; + goto out; } /* If the object doesn't exist, create it */ @@ -1993,7 +1975,8 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, jiffies); if (ias_obj == NULL) { kfree(ias_opt); - return -ENOMEM; + err = -ENOMEM; + goto out; } free_ias = 1; } @@ -2005,7 +1988,8 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, kfree(ias_obj->name); kfree(ias_obj); } - return -EINVAL; + err = -EINVAL; + goto out; } /* Look at the type */ @@ -2028,7 +2012,8 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, kfree(ias_obj); } - return -EINVAL; + err = -EINVAL; + goto out; } /* Add an octet sequence attribute */ irias_add_octseq_attrib( @@ -2060,7 +2045,8 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, kfree(ias_obj->name); kfree(ias_obj); } - return -EINVAL; + err = -EINVAL; + goto out; } irias_insert_object(ias_obj); kfree(ias_opt); @@ -2071,17 +2057,22 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, * object is not owned by the kernel and delete it. */ - if (optlen != sizeof(struct irda_ias_set)) - return -EINVAL; + if (optlen != sizeof(struct irda_ias_set)) { + err = -EINVAL; + goto out; + } ias_opt = kmalloc(sizeof(struct irda_ias_set), GFP_ATOMIC); - if (ias_opt == NULL) - return -ENOMEM; + if (ias_opt == NULL) { + err = -ENOMEM; + goto out; + } /* Copy query to the driver. */ if (copy_from_user(ias_opt, optval, optlen)) { kfree(ias_opt); - return -EFAULT; + err = -EFAULT; + goto out; } /* Find the object we target. @@ -2094,7 +2085,8 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, ias_obj = irias_find_object(ias_opt->irda_class_name); if(ias_obj == (struct ias_object *) NULL) { kfree(ias_opt); - return -EINVAL; + err = -EINVAL; + goto out; } /* Only ROOT can mess with the global IAS database. @@ -2103,7 +2095,8 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, if((!capable(CAP_NET_ADMIN)) && ((ias_obj == NULL) || (ias_obj != self->ias_obj))) { kfree(ias_opt); - return -EPERM; + err = -EPERM; + goto out; } /* Find the attribute (in the object) we target */ @@ -2111,14 +2104,16 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, ias_opt->irda_attrib_name); if(ias_attr == (struct ias_attrib *) NULL) { kfree(ias_opt); - return -EINVAL; + err = -EINVAL; + goto out; } /* Check is the user space own the object */ if(ias_attr->value->owner != IAS_USER_ATTR) { IRDA_DEBUG(1, "%s(), attempting to delete a kernel attribute\n", __func__); kfree(ias_opt); - return -EPERM; + err = -EPERM; + goto out; } /* Remove the attribute (and maybe the object) */ @@ -2126,11 +2121,15 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, kfree(ias_opt); break; case IRLMP_MAX_SDU_SIZE: - if (optlen < sizeof(int)) - return -EINVAL; + if (optlen < sizeof(int)) { + err = -EINVAL; + goto out; + } - if (get_user(opt, (int __user *)optval)) - return -EFAULT; + if (get_user(opt, (int __user *)optval)) { + err = -EFAULT; + goto out; + } /* Only possible for a seqpacket service (TTP with SAR) */ if (sk->sk_type != SOCK_SEQPACKET) { @@ -2140,16 +2139,21 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, } else { IRDA_WARNING("%s: not allowed to set MAXSDUSIZE for this socket type!\n", __func__); - return -ENOPROTOOPT; + err = -ENOPROTOOPT; + goto out; } break; case IRLMP_HINTS_SET: - if (optlen < sizeof(int)) - return -EINVAL; + if (optlen < sizeof(int)) { + err = -EINVAL; + goto out; + } /* The input is really a (__u8 hints[2]), easier as an int */ - if (get_user(opt, (int __user *)optval)) - return -EFAULT; + if (get_user(opt, (int __user *)optval)) { + err = -EFAULT; + goto out; + } /* Unregister any old registration */ if (self->skey) @@ -2163,12 +2167,16 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, * making a discovery (nodes which don't match any hint * bit in the mask are not reported). */ - if (optlen < sizeof(int)) - return -EINVAL; + if (optlen < sizeof(int)) { + err = -EINVAL; + goto out; + } /* The input is really a (__u8 hints[2]), easier as an int */ - if (get_user(opt, (int __user *)optval)) - return -EFAULT; + if (get_user(opt, (int __user *)optval)) { + err = -EFAULT; + goto out; + } /* Set the new hint mask */ self->mask.word = (__u16) opt; @@ -2180,19 +2188,12 @@ static int __irda_setsockopt(struct socket *sock, int level, int optname, break; default: - return -ENOPROTOOPT; + err = -ENOPROTOOPT; + break; } - return 0; -} -static int irda_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, unsigned int optlen) -{ - int err; - - lock_kernel(); - err = __irda_setsockopt(sock, level, optname, optval, optlen); - unlock_kernel(); +out: + release_sock(sk); return err; } @@ -2249,7 +2250,7 @@ static int irda_extract_ias_value(struct irda_ias_set *ias_opt, /* * Function irda_getsockopt (sock, level, optname, optval, optlen) */ -static int __irda_getsockopt(struct socket *sock, int level, int optname, +static int irda_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; @@ -2262,7 +2263,7 @@ static int __irda_getsockopt(struct socket *sock, int level, int optname, int daddr = DEV_ADDR_ANY; /* Dest address for IAS queries */ int val = 0; int len = 0; - int err; + int err = 0; int offset, total; IRDA_DEBUG(2, "%s(%p)\n", __func__, self); @@ -2276,15 +2277,18 @@ static int __irda_getsockopt(struct socket *sock, int level, int optname, if(len < 0) return -EINVAL; + lock_sock(sk); + switch (optname) { case IRLMP_ENUMDEVICES: /* Ask lmp for the current discovery log */ discoveries = irlmp_get_discoveries(&list.len, self->mask.word, self->nslots); /* Check if the we got some results */ - if (discoveries == NULL) - return -EAGAIN; /* Didn't find any devices */ - err = 0; + if (discoveries == NULL) { + err = -EAGAIN; + goto out; /* Didn't find any devices */ + } /* Write total list length back to client */ if (copy_to_user(optval, &list, @@ -2297,8 +2301,7 @@ static int __irda_getsockopt(struct socket *sock, int level, int optname, sizeof(struct irda_device_info); /* Copy the list itself - watch for overflow */ - if(list.len > 2048) - { + if (list.len > 2048) { err = -EINVAL; goto bed; } @@ -2314,17 +2317,20 @@ static int __irda_getsockopt(struct socket *sock, int level, int optname, bed: /* Free up our buffer */ kfree(discoveries); - if (err) - return err; break; case IRLMP_MAX_SDU_SIZE: val = self->max_data_size; len = sizeof(int); - if (put_user(len, optlen)) - return -EFAULT; + if (put_user(len, optlen)) { + err = -EFAULT; + goto out; + } + + if (copy_to_user(optval, &val, len)) { + err = -EFAULT; + goto out; + } - if (copy_to_user(optval, &val, len)) - return -EFAULT; break; case IRLMP_IAS_GET: /* The user want an object from our local IAS database. @@ -2332,17 +2338,22 @@ bed: * that we found */ /* Check that the user has allocated the right space for us */ - if (len != sizeof(struct irda_ias_set)) - return -EINVAL; + if (len != sizeof(struct irda_ias_set)) { + err = -EINVAL; + goto out; + } ias_opt = kmalloc(sizeof(struct irda_ias_set), GFP_ATOMIC); - if (ias_opt == NULL) - return -ENOMEM; + if (ias_opt == NULL) { + err = -ENOMEM; + goto out; + } /* Copy query to the driver. */ if (copy_from_user(ias_opt, optval, len)) { kfree(ias_opt); - return -EFAULT; + err = -EFAULT; + goto out; } /* Find the object we target. @@ -2355,7 +2366,8 @@ bed: ias_obj = irias_find_object(ias_opt->irda_class_name); if(ias_obj == (struct ias_object *) NULL) { kfree(ias_opt); - return -EINVAL; + err = -EINVAL; + goto out; } /* Find the attribute (in the object) we target */ @@ -2363,21 +2375,23 @@ bed: ias_opt->irda_attrib_name); if(ias_attr == (struct ias_attrib *) NULL) { kfree(ias_opt); - return -EINVAL; + err = -EINVAL; + goto out; } /* Translate from internal to user structure */ err = irda_extract_ias_value(ias_opt, ias_attr->value); if(err) { kfree(ias_opt); - return err; + goto out; } /* Copy reply to the user */ if (copy_to_user(optval, ias_opt, sizeof(struct irda_ias_set))) { kfree(ias_opt); - return -EFAULT; + err = -EFAULT; + goto out; } /* Note : don't need to put optlen, we checked it */ kfree(ias_opt); @@ -2388,17 +2402,22 @@ bed: * then wait for the answer to come back. */ /* Check that the user has allocated the right space for us */ - if (len != sizeof(struct irda_ias_set)) - return -EINVAL; + if (len != sizeof(struct irda_ias_set)) { + err = -EINVAL; + goto out; + } ias_opt = kmalloc(sizeof(struct irda_ias_set), GFP_ATOMIC); - if (ias_opt == NULL) - return -ENOMEM; + if (ias_opt == NULL) { + err = -ENOMEM; + goto out; + } /* Copy query to the driver. */ if (copy_from_user(ias_opt, optval, len)) { kfree(ias_opt); - return -EFAULT; + err = -EFAULT; + goto out; } /* At this point, there are two cases... @@ -2419,7 +2438,8 @@ bed: daddr = ias_opt->daddr; if((!daddr) || (daddr == DEV_ADDR_ANY)) { kfree(ias_opt); - return -EINVAL; + err = -EINVAL; + goto out; } } @@ -2428,7 +2448,8 @@ bed: IRDA_WARNING("%s: busy with a previous query\n", __func__); kfree(ias_opt); - return -EBUSY; + err = -EBUSY; + goto out; } self->iriap = iriap_open(LSAP_ANY, IAS_CLIENT, self, @@ -2436,7 +2457,8 @@ bed: if (self->iriap == NULL) { kfree(ias_opt); - return -ENOMEM; + err = -ENOMEM; + goto out; } /* Treat unexpected wakeup as disconnect */ @@ -2455,7 +2477,8 @@ bed: * we can free it regardless! */ kfree(ias_opt); /* Treat signals as disconnect */ - return -EHOSTUNREACH; + err = -EHOSTUNREACH; + goto out; } /* Check what happened */ @@ -2465,9 +2488,11 @@ bed: /* Requested object/attribute doesn't exist */ if((self->errno == IAS_CLASS_UNKNOWN) || (self->errno == IAS_ATTRIB_UNKNOWN)) - return (-EADDRNOTAVAIL); + err = -EADDRNOTAVAIL; else - return (-EHOSTUNREACH); + err = -EHOSTUNREACH; + + goto out; } /* Translate from internal to user structure */ @@ -2476,14 +2501,15 @@ bed: irias_delete_value(self->ias_result); if (err) { kfree(ias_opt); - return err; + goto out; } /* Copy reply to the user */ if (copy_to_user(optval, ias_opt, sizeof(struct irda_ias_set))) { kfree(ias_opt); - return -EFAULT; + err = -EFAULT; + goto out; } /* Note : don't need to put optlen, we checked it */ kfree(ias_opt); @@ -2504,11 +2530,15 @@ bed: */ /* Check that the user is passing us an int */ - if (len != sizeof(int)) - return -EINVAL; + if (len != sizeof(int)) { + err = -EINVAL; + goto out; + } /* Get timeout in ms (max time we block the caller) */ - if (get_user(val, (int __user *)optval)) - return -EFAULT; + if (get_user(val, (int __user *)optval)) { + err = -EFAULT; + goto out; + } /* Tell IrLMP we want to be notified */ irlmp_update_client(self->ckey, self->mask.word, @@ -2520,8 +2550,6 @@ bed: /* Wait until a node is discovered */ if (!self->cachedaddr) { - int ret = 0; - IRDA_DEBUG(1, "%s(), nothing discovered yet, going to sleep...\n", __func__); /* Set watchdog timer to expire in <val> ms. */ @@ -2534,7 +2562,7 @@ bed: /* Wait for IR-LMP to call us back */ __wait_event_interruptible(self->query_wait, (self->cachedaddr != 0 || self->errno == -ETIME), - ret); + err); /* If watchdog is still activated, kill it! */ if(timer_pending(&(self->watchdog))) @@ -2542,8 +2570,8 @@ bed: IRDA_DEBUG(1, "%s(), ...waking up !\n", __func__); - if (ret != 0) - return ret; + if (err != 0) + goto out; } else IRDA_DEBUG(1, "%s(), found immediately !\n", @@ -2566,25 +2594,19 @@ bed: * If the user want more details, he should query * the whole discovery log and pick one device... */ - if (put_user(daddr, (int __user *)optval)) - return -EFAULT; + if (put_user(daddr, (int __user *)optval)) { + err = -EFAULT; + goto out; + } break; default: - return -ENOPROTOOPT; + err = -ENOPROTOOPT; } - return 0; -} - -static int irda_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) -{ - int err; +out: - lock_kernel(); - err = __irda_getsockopt(sock, level, optname, optval, optlen); - unlock_kernel(); + release_sock(sk); return err; } @@ -2628,7 +2650,7 @@ static const struct proto_ops irda_seqpacket_ops = { .socketpair = sock_no_socketpair, .accept = irda_accept, .getname = irda_getname, - .poll = irda_datagram_poll, + .poll = datagram_poll, .ioctl = irda_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = irda_compat_ioctl, @@ -2652,7 +2674,7 @@ static const struct proto_ops irda_dgram_ops = { .socketpair = sock_no_socketpair, .accept = irda_accept, .getname = irda_getname, - .poll = irda_datagram_poll, + .poll = datagram_poll, .ioctl = irda_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = irda_compat_ioctl, @@ -2677,7 +2699,7 @@ static const struct proto_ops irda_ultra_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = irda_getname, - .poll = irda_datagram_poll, + .poll = datagram_poll, .ioctl = irda_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = irda_compat_ioctl, diff --git a/net/irda/discovery.c b/net/irda/discovery.c index c1c8ae9..36c3f03 100644 --- a/net/irda/discovery.c +++ b/net/irda/discovery.c @@ -315,7 +315,7 @@ struct irda_device_info *irlmp_copy_discoveries(hashbin_t *log, int *pn, /* Get the actual number of device in the buffer and return */ *pn = i; - return(buffer); + return buffer; } #ifdef CONFIG_PROC_FS diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index faa82ca..a39cca8 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -449,8 +449,8 @@ static int ircomm_tty_open(struct tty_struct *tty, struct file *filp) } #ifdef SERIAL_DO_RESTART - return ((self->flags & ASYNC_HUP_NOTIFY) ? - -EAGAIN : -ERESTARTSYS); + return (self->flags & ASYNC_HUP_NOTIFY) ? + -EAGAIN : -ERESTARTSYS; #else return -EAGAIN; #endif diff --git a/net/irda/iriap.c b/net/irda/iriap.c index fce364c..5b743bd 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -502,7 +502,8 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self, IRDA_DEBUG(4, "%s(), strlen=%d\n", __func__, value_len); /* Make sure the string is null-terminated */ - fp[n+value_len] = 0x00; + if (n + value_len < skb->len) + fp[n + value_len] = 0x00; IRDA_DEBUG(4, "Got string %s\n", fp+n); /* Will truncate to IAS_MAX_STRING bytes */ diff --git a/net/irda/irlan/irlan_event.c b/net/irda/irlan/irlan_event.c index cbcb4eb..43f1604 100644 --- a/net/irda/irlan/irlan_event.c +++ b/net/irda/irlan/irlan_event.c @@ -24,7 +24,7 @@ #include <net/irda/irlan_event.h> -char *irlan_state[] = { +const char * const irlan_state[] = { "IRLAN_IDLE", "IRLAN_QUERY", "IRLAN_CONN", diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index 0e7d8bd..6115a44 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -939,7 +939,7 @@ struct irda_device_info *irlmp_get_discoveries(int *pn, __u16 mask, int nslots) } /* Return current cached discovery log */ - return(irlmp_copy_discoveries(irlmp->cachelog, pn, mask, TRUE)); + return irlmp_copy_discoveries(irlmp->cachelog, pn, mask, TRUE); } EXPORT_SYMBOL(irlmp_get_discoveries); diff --git a/net/irda/irlmp_frame.c b/net/irda/irlmp_frame.c index 3750884..062e63b 100644 --- a/net/irda/irlmp_frame.c +++ b/net/irda/irlmp_frame.c @@ -448,7 +448,7 @@ static struct lsap_cb *irlmp_find_lsap(struct lap_cb *self, __u8 dlsap_sel, (self->cache.slsap_sel == slsap_sel) && (self->cache.dlsap_sel == dlsap_sel)) { - return (self->cache.lsap); + return self->cache.lsap; } #endif diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index 4300df3..0d82ff5 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -458,6 +458,8 @@ typedef struct irnet_socket int disco_index; /* Last read in the discovery log */ int disco_number; /* Size of the discovery log */ + struct mutex lock; + } irnet_socket; /* diff --git a/net/irda/irnet/irnet_irda.c b/net/irda/irnet/irnet_irda.c index e98e40d..7f17a80 100644 --- a/net/irda/irnet/irnet_irda.c +++ b/net/irda/irnet/irnet_irda.c @@ -238,7 +238,7 @@ irnet_ias_to_tsap(irnet_socket * self, DEXIT(IRDA_SR_TRACE, "\n"); /* Return the TSAP */ - return(dtsap_sel); + return dtsap_sel; } /*------------------------------------------------------------------*/ @@ -301,7 +301,7 @@ irnet_connect_tsap(irnet_socket * self) { clear_bit(0, &self->ttp_connect); DERROR(IRDA_SR_ERROR, "connect aborted!\n"); - return(err); + return err; } /* Connect to remote device */ @@ -312,7 +312,7 @@ irnet_connect_tsap(irnet_socket * self) { clear_bit(0, &self->ttp_connect); DERROR(IRDA_SR_ERROR, "connect aborted!\n"); - return(err); + return err; } /* The above call is non-blocking. @@ -321,7 +321,7 @@ irnet_connect_tsap(irnet_socket * self) * See you there ;-) */ DEXIT(IRDA_SR_TRACE, "\n"); - return(err); + return err; } /*------------------------------------------------------------------*/ @@ -362,10 +362,10 @@ irnet_discover_next_daddr(irnet_socket * self) /* The above request is non-blocking. * After a while, IrDA will call us back in irnet_discovervalue_confirm() * We will then call irnet_ias_to_tsap() and come back here again... */ - return(0); + return 0; } else - return(1); + return 1; } /*------------------------------------------------------------------*/ @@ -436,7 +436,7 @@ irnet_discover_daddr_and_lsap_sel(irnet_socket * self) /* Follow me in irnet_discovervalue_confirm() */ DEXIT(IRDA_SR_TRACE, "\n"); - return(0); + return 0; } /*------------------------------------------------------------------*/ @@ -485,7 +485,7 @@ irnet_dname_to_daddr(irnet_socket * self) /* No luck ! */ DEBUG(IRDA_SR_INFO, "cannot discover device ``%s'' !!!\n", self->rname); kfree(discoveries); - return(-EADDRNOTAVAIL); + return -EADDRNOTAVAIL; } @@ -527,7 +527,7 @@ irda_irnet_create(irnet_socket * self) INIT_WORK(&self->disconnect_work, irnet_ppp_disconnect); DEXIT(IRDA_SOCK_TRACE, "\n"); - return(0); + return 0; } /*------------------------------------------------------------------*/ @@ -601,7 +601,7 @@ irda_irnet_connect(irnet_socket * self) * We will finish the connection procedure in irnet_connect_tsap(). */ DEXIT(IRDA_SOCK_TRACE, "\n"); - return(0); + return 0; } /*------------------------------------------------------------------*/ @@ -733,7 +733,7 @@ irnet_daddr_to_dname(irnet_socket * self) /* No luck ! */ DEXIT(IRDA_SERV_INFO, ": cannot discover device 0x%08x !!!\n", self->daddr); kfree(discoveries); - return(-EADDRNOTAVAIL); + return -EADDRNOTAVAIL; } /*------------------------------------------------------------------*/ diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index dfe7b38..0993bd4 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -166,7 +166,7 @@ irnet_ctrl_write(irnet_socket * ap, } /* Success : we have parsed all commands successfully */ - return(count); + return count; } #ifdef INITIAL_DISCOVERY @@ -300,7 +300,7 @@ irnet_ctrl_read(irnet_socket * ap, } DEXIT(CTRL_TRACE, "\n"); - return(strlen(event)); + return strlen(event); } #endif /* INITIAL_DISCOVERY */ @@ -409,7 +409,7 @@ irnet_ctrl_read(irnet_socket * ap, } DEXIT(CTRL_TRACE, "\n"); - return(strlen(event)); + return strlen(event); } /*------------------------------------------------------------------*/ @@ -480,7 +480,6 @@ dev_irnet_open(struct inode * inode, ap = kzalloc(sizeof(*ap), GFP_KERNEL); DABORT(ap == NULL, -ENOMEM, FS_ERROR, "Can't allocate struct irnet...\n"); - lock_kernel(); /* initialize the irnet structure */ ap->file = file; @@ -502,18 +501,20 @@ dev_irnet_open(struct inode * inode, { DERROR(FS_ERROR, "Can't setup IrDA link...\n"); kfree(ap); - unlock_kernel(); + return err; } /* For the control channel */ ap->event_index = irnet_events.index; /* Cancel all past events */ + mutex_init(&ap->lock); + /* Put our stuff where we will be able to find it later */ file->private_data = ap; DEXIT(FS_TRACE, " - ap=0x%p\n", ap); - unlock_kernel(); + return 0; } @@ -623,7 +624,7 @@ dev_irnet_poll(struct file * file, mask |= irnet_ctrl_poll(ap, file, wait); DEXIT(FS_TRACE, " - mask=0x%X\n", mask); - return(mask); + return mask; } /*------------------------------------------------------------------*/ @@ -664,7 +665,9 @@ dev_irnet_ioctl( { DEBUG(FS_INFO, "Entering PPP discipline.\n"); /* PPP channel setup (ap->chan in configued in dev_irnet_open())*/ - lock_kernel(); + if (mutex_lock_interruptible(&ap->lock)) + return -EINTR; + err = ppp_register_channel(&ap->chan); if(err == 0) { @@ -677,14 +680,17 @@ dev_irnet_ioctl( } else DERROR(FS_ERROR, "Can't setup PPP channel...\n"); - unlock_kernel(); + + mutex_unlock(&ap->lock); } else { /* In theory, should be N_TTY */ DEBUG(FS_INFO, "Exiting PPP discipline.\n"); /* Disconnect from the generic PPP layer */ - lock_kernel(); + if (mutex_lock_interruptible(&ap->lock)) + return -EINTR; + if(ap->ppp_open) { ap->ppp_open = 0; @@ -693,24 +699,31 @@ dev_irnet_ioctl( else DERROR(FS_ERROR, "Channel not registered !\n"); err = 0; - unlock_kernel(); + + mutex_unlock(&ap->lock); } break; /* Query PPP channel and unit number */ case PPPIOCGCHAN: - lock_kernel(); + if (mutex_lock_interruptible(&ap->lock)) + return -EINTR; + if(ap->ppp_open && !put_user(ppp_channel_index(&ap->chan), (int __user *)argp)) err = 0; - unlock_kernel(); + + mutex_unlock(&ap->lock); break; case PPPIOCGUNIT: - lock_kernel(); + if (mutex_lock_interruptible(&ap->lock)) + return -EINTR; + if(ap->ppp_open && !put_user(ppp_unit_number(&ap->chan), (int __user *)argp)) err = 0; - unlock_kernel(); + + mutex_unlock(&ap->lock); break; /* All these ioctls can be passed both directly and from ppp_generic, @@ -730,9 +743,12 @@ dev_irnet_ioctl( if(!capable(CAP_NET_ADMIN)) err = -EPERM; else { - lock_kernel(); + if (mutex_lock_interruptible(&ap->lock)) + return -EINTR; + err = ppp_irnet_ioctl(&ap->chan, cmd, arg); - unlock_kernel(); + + mutex_unlock(&ap->lock); } break; @@ -740,7 +756,9 @@ dev_irnet_ioctl( /* Get termios */ case TCGETS: DEBUG(FS_INFO, "Get termios.\n"); - lock_kernel(); + if (mutex_lock_interruptible(&ap->lock)) + return -EINTR; + #ifndef TCGETS2 if(!kernel_termios_to_user_termios((struct termios __user *)argp, &ap->termios)) err = 0; @@ -748,12 +766,15 @@ dev_irnet_ioctl( if(kernel_termios_to_user_termios_1((struct termios __user *)argp, &ap->termios)) err = 0; #endif - unlock_kernel(); + + mutex_unlock(&ap->lock); break; /* Set termios */ case TCSETSF: DEBUG(FS_INFO, "Set termios.\n"); - lock_kernel(); + if (mutex_lock_interruptible(&ap->lock)) + return -EINTR; + #ifndef TCGETS2 if(!user_termios_to_kernel_termios(&ap->termios, (struct termios __user *)argp)) err = 0; @@ -761,7 +782,8 @@ dev_irnet_ioctl( if(!user_termios_to_kernel_termios_1(&ap->termios, (struct termios __user *)argp)) err = 0; #endif - unlock_kernel(); + + mutex_unlock(&ap->lock); break; /* Set DTR/RTS */ @@ -784,9 +806,10 @@ dev_irnet_ioctl( * We should also worry that we don't accept junk here and that * we get rid of our own buffers */ #ifdef FLUSH_TO_PPP - lock_kernel(); + if (mutex_lock_interruptible(&ap->lock)) + return -EINTR; ppp_output_wakeup(&ap->chan); - unlock_kernel(); + mutex_unlock(&ap->lock); #endif /* FLUSH_TO_PPP */ err = 0; break; diff --git a/net/irda/irnet/irnet_ppp.h b/net/irda/irnet/irnet_ppp.h index b5df241..9402258 100644 --- a/net/irda/irnet/irnet_ppp.h +++ b/net/irda/irnet/irnet_ppp.h @@ -103,7 +103,8 @@ static const struct file_operations irnet_device_fops = .poll = dev_irnet_poll, .unlocked_ioctl = dev_irnet_ioctl, .open = dev_irnet_open, - .release = dev_irnet_close + .release = dev_irnet_close, + .llseek = noop_llseek, /* Also : llseek, readdir, mmap, flush, fsync, fasync, lock, readv, writev */ }; diff --git a/net/irda/parameters.c b/net/irda/parameters.c index fc1a205..71cd38c 100644 --- a/net/irda/parameters.c +++ b/net/irda/parameters.c @@ -298,6 +298,8 @@ static int irda_extract_string(void *self, __u8 *buf, int len, __u8 pi, p.pi = pi; /* In case handler needs to know */ p.pl = buf[1]; /* Extract length of value */ + if (p.pl > 32) + p.pl = 32; IRDA_DEBUG(2, "%s(), pi=%#x, pl=%d\n", __func__, p.pi, p.pl); @@ -318,7 +320,7 @@ static int irda_extract_string(void *self, __u8 *buf, int len, __u8 pi, (__u8) str[0], (__u8) str[1]); /* Null terminate string */ - str[p.pl+1] = '\0'; + str[p.pl] = '\0'; p.pv.c = str; /* Handler will need to take a copy */ diff --git a/net/key/af_key.c b/net/key/af_key.c index 43040e9..d87c22d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -565,12 +565,12 @@ pfkey_proto2satype(uint16_t proto) static uint8_t pfkey_proto_to_xfrm(uint8_t proto) { - return (proto == IPSEC_PROTO_ANY ? 0 : proto); + return proto == IPSEC_PROTO_ANY ? 0 : proto; } static uint8_t pfkey_proto_from_xfrm(uint8_t proto) { - return (proto ? proto : IPSEC_PROTO_ANY); + return proto ? proto : IPSEC_PROTO_ANY; } static inline int pfkey_sockaddr_len(sa_family_t family) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 226a0ae..1c770c0 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -65,9 +65,7 @@ static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif continue; if ((l2tp->conn_id == tunnel_id) && -#ifdef CONFIG_NET_NS - (sk->sk_net == net) && -#endif + net_eq(sock_net(sk), net) && !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) goto found; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index ff954b3..39a21d0 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1768,7 +1768,7 @@ static const struct proto_ops pppol2tp_ops = { .ioctl = pppox_ioctl, }; -static struct pppox_proto pppol2tp_proto = { +static const struct pppox_proto pppol2tp_proto = { .create = pppol2tp_create, .ioctl = pppol2tp_ioctl }; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 023ba82..5826129 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -1024,7 +1024,8 @@ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - int rc = -EINVAL, opt; + unsigned int opt; + int rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC || optlen != sizeof(int))) diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index e4dae02..cf4aea3 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -689,7 +689,7 @@ static void llc_station_rcv(struct sk_buff *skb) int __init llc_station_init(void) { - u16 rc = -ENOBUFS; + int rc = -ENOBUFS; struct sk_buff *skb; struct llc_station_state_ev *ev; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 58eab9e..720b7a8 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -56,7 +56,7 @@ static void ieee80211_free_tid_rx(struct rcu_head *h) } void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, - u16 initiator, u16 reason) + u16 initiator, u16 reason, bool tx) { struct ieee80211_local *local = sta->local; struct tid_ampdu_rx *tid_rx; @@ -81,7 +81,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, "aggregation for tid %d\n", tid); /* check if this is a self generated aggregation halt */ - if (initiator == WLAN_BACK_RECIPIENT) + if (initiator == WLAN_BACK_RECIPIENT && tx) ieee80211_send_delba(sta->sdata, sta->sta.addr, tid, 0, reason); @@ -92,10 +92,10 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, } void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, - u16 initiator, u16 reason) + u16 initiator, u16 reason, bool tx) { mutex_lock(&sta->ampdu_mlme.mtx); - ___ieee80211_stop_rx_ba_session(sta, tid, initiator, reason); + ___ieee80211_stop_rx_ba_session(sta, tid, initiator, reason, tx); mutex_unlock(&sta->ampdu_mlme.mtx); } diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index c893f23..d4679b2 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -145,7 +145,8 @@ static void kfree_tid_tx(struct rcu_head *rcu_head) } int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator) + enum ieee80211_back_parties initiator, + bool tx) { struct ieee80211_local *local = sta->local; struct tid_ampdu_tx *tid_tx = sta->ampdu_mlme.tid_tx[tid]; @@ -175,6 +176,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + del_timer_sync(&tid_tx->addba_resp_timer); + /* * After this packets are no longer handed right through * to the driver but are put onto tid_tx->pending instead, @@ -183,6 +186,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, clear_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); tid_tx->stop_initiator = initiator; + tid_tx->tx_stop = tx; ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_TX_STOP, @@ -575,13 +579,14 @@ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, EXPORT_SYMBOL(ieee80211_start_tx_ba_cb_irqsafe); int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator) + enum ieee80211_back_parties initiator, + bool tx) { int ret; mutex_lock(&sta->ampdu_mlme.mtx); - ret = ___ieee80211_stop_tx_ba_session(sta, tid, initiator); + ret = ___ieee80211_stop_tx_ba_session(sta, tid, initiator, tx); mutex_unlock(&sta->ampdu_mlme.mtx); @@ -670,7 +675,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) goto unlock_sta; } - if (tid_tx->stop_initiator == WLAN_BACK_INITIATOR) + if (tid_tx->stop_initiator == WLAN_BACK_INITIATOR && tid_tx->tx_stop) ieee80211_send_delba(sta->sdata, ra, tid, WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); @@ -770,7 +775,8 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, sta->ampdu_mlme.addba_req_num[tid] = 0; } else { - ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR); + ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR, + true); } out: diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 5de1ca3..18bd0e5 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -68,14 +68,42 @@ static int ieee80211_change_iface(struct wiphy *wiphy, params && params->use_4addr >= 0) sdata->u.mgd.use_4addr = params->use_4addr; - if (sdata->vif.type == NL80211_IFTYPE_MONITOR && flags) - sdata->u.mntr_flags = *flags; + if (sdata->vif.type == NL80211_IFTYPE_MONITOR && flags) { + struct ieee80211_local *local = sdata->local; + + if (ieee80211_sdata_running(sdata)) { + /* + * Prohibit MONITOR_FLAG_COOK_FRAMES to be + * changed while the interface is up. + * Else we would need to add a lot of cruft + * to update everything: + * cooked_mntrs, monitor and all fif_* counters + * reconfigure hardware + */ + if ((*flags & MONITOR_FLAG_COOK_FRAMES) != + (sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES)) + return -EBUSY; + + ieee80211_adjust_monitor_flags(sdata, -1); + sdata->u.mntr_flags = *flags; + ieee80211_adjust_monitor_flags(sdata, 1); + + ieee80211_configure_filter(local); + } else { + /* + * Because the interface is down, ieee80211_do_stop + * and ieee80211_do_open take care of "everything" + * mentioned in the comment above. + */ + sdata->u.mntr_flags = *flags; + } + } return 0; } static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, - u8 key_idx, const u8 *mac_addr, + u8 key_idx, bool pairwise, const u8 *mac_addr, struct key_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -103,6 +131,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, if (IS_ERR(key)) return PTR_ERR(key); + if (pairwise) + key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE; + mutex_lock(&sdata->local->sta_mtx); if (mac_addr) { @@ -125,7 +156,7 @@ 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, const u8 *mac_addr) + u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_sub_if_data *sdata; struct sta_info *sta; @@ -142,10 +173,17 @@ static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, if (!sta) goto out_unlock; - if (sta->key) { - ieee80211_key_free(sdata->local, sta->key); - WARN_ON(sta->key); - ret = 0; + if (pairwise) { + if (sta->ptk) { + ieee80211_key_free(sdata->local, sta->ptk); + ret = 0; + } + } else { + if (sta->gtk[key_idx]) { + ieee80211_key_free(sdata->local, + sta->gtk[key_idx]); + ret = 0; + } } goto out_unlock; @@ -167,7 +205,8 @@ 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, const u8 *mac_addr, void *cookie, + u8 key_idx, bool pairwise, const u8 *mac_addr, + void *cookie, void (*callback)(void *cookie, struct key_params *params)) { @@ -175,7 +214,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, struct sta_info *sta = NULL; u8 seq[6] = {0}; struct key_params params; - struct ieee80211_key *key; + struct ieee80211_key *key = NULL; u32 iv32; u16 iv16; int err = -ENOENT; @@ -189,7 +228,10 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, if (!sta) goto out; - key = sta->key; + if (pairwise) + key = sta->ptk; + else if (key_idx < NUM_DEFAULT_KEYS) + key = sta->gtk[key_idx]; } else key = sdata->keys[key_idx]; @@ -285,13 +327,19 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) STATION_INFO_TX_BYTES | STATION_INFO_RX_PACKETS | STATION_INFO_TX_PACKETS | - STATION_INFO_TX_BITRATE; + STATION_INFO_TX_RETRIES | + STATION_INFO_TX_FAILED | + STATION_INFO_TX_BITRATE | + STATION_INFO_RX_DROP_MISC; sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx); sinfo->rx_bytes = sta->rx_bytes; sinfo->tx_bytes = sta->tx_bytes; sinfo->rx_packets = sta->rx_packets; sinfo->tx_packets = sta->tx_packets; + sinfo->tx_retries = sta->tx_retry_count; + sinfo->tx_failed = sta->tx_retry_failed; + sinfo->rx_dropped_misc = sta->rx_dropped; if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { @@ -577,6 +625,7 @@ static void sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) { + unsigned long flags; u32 rates; int i, j; struct ieee80211_supported_band *sband; @@ -585,7 +634,7 @@ static void sta_apply_parameters(struct ieee80211_local *local, sband = local->hw.wiphy->bands[local->oper_channel->band]; - spin_lock_bh(&sta->lock); + spin_lock_irqsave(&sta->flaglock, flags); mask = params->sta_flags_mask; set = params->sta_flags_set; @@ -612,7 +661,7 @@ static void sta_apply_parameters(struct ieee80211_local *local, if (set & BIT(NL80211_STA_FLAG_MFP)) sta->flags |= WLAN_STA_MFP; } - spin_unlock_bh(&sta->lock); + spin_unlock_irqrestore(&sta->flaglock, flags); /* * cfg80211 validates this (1-2007) and allows setting the AID @@ -1150,15 +1199,26 @@ static int ieee80211_scan(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_scan_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); - 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_AP || sdata->u.ap.beacon)) + switch (ieee80211_vif_type_p2p(&sdata->vif)) { + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_P2P_CLIENT: + break; + case NL80211_IFTYPE_P2P_GO: + if (sdata->local->ops->hw_scan) + break; + /* FIXME: implement NoA while scanning in software */ + return -EOPNOTSUPP; + case NL80211_IFTYPE_AP: + if (sdata->u.ap.beacon) + return -EOPNOTSUPP; + break; + default: return -EOPNOTSUPP; + } return ieee80211_request_scan(sdata, req); } @@ -1305,7 +1365,7 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy, int *dbm) } static int ieee80211_set_wds_peer(struct wiphy *wiphy, struct net_device *dev, - u8 *addr) + const u8 *addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -1354,7 +1414,7 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, if (!sdata->u.mgd.associated || sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT) { mutex_lock(&sdata->local->iflist_mtx); - ieee80211_recalc_smps(sdata->local, sdata); + ieee80211_recalc_smps(sdata->local); mutex_unlock(&sdata->local->iflist_mtx); return 0; } @@ -1509,7 +1569,11 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, switch (sdata->vif.type) { case NL80211_IFTYPE_ADHOC: - if (mgmt->u.action.category == WLAN_CATEGORY_PUBLIC) + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_P2P_GO: + if (!ieee80211_is_action(mgmt->frame_control) || + mgmt->u.action.category == WLAN_CATEGORY_PUBLIC) break; rcu_read_lock(); sta = sta_info_get(sdata, mgmt->da); @@ -1518,6 +1582,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, return -ENOLINK; break; case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: break; default: return -EOPNOTSUPP; @@ -1539,6 +1604,23 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, return 0; } +static void ieee80211_mgmt_frame_register(struct wiphy *wiphy, + struct net_device *dev, + u16 frame_type, bool reg) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + + if (frame_type != (IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ)) + return; + + if (reg) + local->probe_req_reg++; + else + local->probe_req_reg--; + + ieee80211_queue_work(&local->hw, &local->reconfig_filter); +} + struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -1590,4 +1672,5 @@ struct cfg80211_ops mac80211_config_ops = { .cancel_remain_on_channel = ieee80211_cancel_remain_on_channel, .mgmt_tx = ieee80211_mgmt_tx, .set_cqm_rssi_config = ieee80211_set_cqm_rssi_config, + .mgmt_frame_register = ieee80211_mgmt_frame_register, }; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 32be11e..5b24740 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -11,7 +11,7 @@ __ieee80211_get_channel_mode(struct ieee80211_local *local, { struct ieee80211_sub_if_data *sdata; - WARN_ON(!mutex_is_locked(&local->iflist_mtx)); + lockdep_assert_held(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { if (sdata == ignore) diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index e81ef4e..ebd5b69 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -368,7 +368,6 @@ void debugfs_hw_add(struct ieee80211_local *local) if (!phyd) return; - local->debugfs.stations = debugfs_create_dir("stations", phyd); local->debugfs.keys = debugfs_create_dir("keys", phyd); DEBUGFS_ADD(frequency); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 20b2998..3e12430 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -409,6 +409,9 @@ void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata) sprintf(buf, "netdev:%s", sdata->name); sdata->debugfs.dir = debugfs_create_dir(buf, sdata->local->hw.wiphy->debugfsdir); + if (sdata->debugfs.dir) + sdata->debugfs.subdir_stations = debugfs_create_dir("stations", + sdata->debugfs.dir); add_files(sdata); } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 76839d4..50c40ea 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -196,7 +196,8 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu else ret = ieee80211_stop_tx_ba_session(&sta->sta, tid); } else { - __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, 3); + __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, + 3, true); ret = 0; } @@ -300,7 +301,7 @@ STA_OPS(ht_capa); void ieee80211_sta_debugfs_add(struct sta_info *sta) { - struct dentry *stations_dir = sta->local->debugfs.stations; + struct dentry *stations_dir = sta->sdata->debugfs.subdir_stations; u8 mac[3*ETH_ALEN]; sta->debugfs.add_has_run = true; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 6064b7b..1698382 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -56,14 +56,14 @@ static inline int drv_add_interface(struct ieee80211_local *local, static inline int drv_change_interface(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum nl80211_iftype type) + enum nl80211_iftype type, bool p2p) { int ret; might_sleep(); - trace_drv_change_interface(local, sdata, type); - ret = local->ops->change_interface(&local->hw, &sdata->vif, type); + trace_drv_change_interface(local, sdata, type, p2p); + ret = local->ops->change_interface(&local->hw, &sdata->vif, type, p2p); trace_drv_return_int(local, ret); return ret; } diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index f6f3d89..6831fb1 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -25,12 +25,14 @@ static inline void trace_ ## name(proto) {} #define STA_PR_FMT " sta:%pM" #define STA_PR_ARG __entry->sta_addr -#define VIF_ENTRY __field(enum nl80211_iftype, vif_type) __field(void *, sdata) \ +#define VIF_ENTRY __field(enum nl80211_iftype, vif_type) __field(void *, sdata) \ + __field(bool, p2p) \ __string(vif_name, sdata->dev ? sdata->dev->name : "<nodev>") -#define VIF_ASSIGN __entry->vif_type = sdata->vif.type; __entry->sdata = sdata; \ +#define VIF_ASSIGN __entry->vif_type = sdata->vif.type; __entry->sdata = sdata; \ + __entry->p2p = sdata->vif.p2p; \ __assign_str(vif_name, sdata->dev ? sdata->dev->name : "<nodev>") -#define VIF_PR_FMT " vif:%s(%d)" -#define VIF_PR_ARG __get_str(vif_name), __entry->vif_type +#define VIF_PR_FMT " vif:%s(%d%s)" +#define VIF_PR_ARG __get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : "" /* * Tracing for driver callbacks. @@ -139,25 +141,28 @@ TRACE_EVENT(drv_add_interface, TRACE_EVENT(drv_change_interface, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum nl80211_iftype type), + enum nl80211_iftype type, bool p2p), - TP_ARGS(local, sdata, type), + TP_ARGS(local, sdata, type, p2p), TP_STRUCT__entry( LOCAL_ENTRY VIF_ENTRY __field(u32, new_type) + __field(bool, new_p2p) ), TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; __entry->new_type = type; + __entry->new_p2p = p2p; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " new type:%d", - LOCAL_PR_ARG, VIF_PR_ARG, __entry->new_type + LOCAL_PR_FMT VIF_PR_FMT " new type:%d%s", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->new_type, + __entry->new_p2p ? "/p2p" : "" ) ); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 11f74f5..75d679d 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -101,16 +101,16 @@ void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_supported_band *sband, ht_cap->mcs.rx_mask[32/8] |= 1; } -void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta) +void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, bool tx) { int i; cancel_work_sync(&sta->ampdu_mlme.work); for (i = 0; i < STA_TID_NUM; i++) { - __ieee80211_stop_tx_ba_session(sta, i, WLAN_BACK_INITIATOR); + __ieee80211_stop_tx_ba_session(sta, i, WLAN_BACK_INITIATOR, tx); __ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_LEAVE_QBSS); + WLAN_REASON_QSTA_LEAVE_QBSS, tx); } } @@ -135,7 +135,7 @@ void ieee80211_ba_session_work(struct work_struct *work) if (test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_timer_expired)) ___ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_TIMEOUT); + WLAN_REASON_QSTA_TIMEOUT, true); tid_tx = sta->ampdu_mlme.tid_tx[tid]; if (!tid_tx) @@ -146,7 +146,8 @@ void ieee80211_ba_session_work(struct work_struct *work) else if (test_and_clear_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state)) ___ieee80211_stop_tx_ba_session(sta, tid, - WLAN_BACK_INITIATOR); + WLAN_BACK_INITIATOR, + true); } mutex_unlock(&sta->ampdu_mlme.mtx); } @@ -214,9 +215,11 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, #endif /* CONFIG_MAC80211_HT_DEBUG */ if (initiator == WLAN_BACK_INITIATOR) - __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_INITIATOR, 0); + __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_INITIATOR, 0, + true); else - __ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_RECIPIENT); + __ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, + true); } int ieee80211_send_smps_action(struct ieee80211_sub_if_data *sdata, @@ -288,6 +291,8 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, if (WARN_ON(smps_mode == IEEE80211_SMPS_OFF)) smps_mode = IEEE80211_SMPS_AUTOMATIC; + sdata->u.mgd.driver_smps_mode = smps_mode; + ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.request_smps_work); } diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 1a3aae5..ff60c02 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -173,6 +173,19 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, memcpy(skb_put(skb, ifibss->ie_len), ifibss->ie, ifibss->ie_len); + if (local->hw.queues >= 4) { + pos = skb_put(skb, 9); + *pos++ = WLAN_EID_VENDOR_SPECIFIC; + *pos++ = 7; /* len */ + *pos++ = 0x00; /* Microsoft OUI 00:50:F2 */ + *pos++ = 0x50; + *pos++ = 0xf2; + *pos++ = 2; /* WME */ + *pos++ = 0; /* WME info */ + *pos++ = 1; /* WME ver */ + *pos++ = 0; /* U-APSD no in use */ + } + rcu_assign_pointer(ifibss->presp, skb); sdata->vif.bss_conf.beacon_int = beacon_int; @@ -266,37 +279,45 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) return; - if (sdata->vif.type == NL80211_IFTYPE_ADHOC && elems->supp_rates && + if (sdata->vif.type == NL80211_IFTYPE_ADHOC && memcmp(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN) == 0) { - supp_rates = ieee80211_sta_get_rates(local, elems, band); rcu_read_lock(); - sta = sta_info_get(sdata, mgmt->sa); - if (sta) { - u32 prev_rates; - prev_rates = sta->sta.supp_rates[band]; - /* make sure mandatory rates are always added */ - sta->sta.supp_rates[band] = supp_rates | - ieee80211_mandatory_rates(local, band); + if (elems->supp_rates) { + supp_rates = ieee80211_sta_get_rates(local, elems, + band); + if (sta) { + u32 prev_rates; - if (sta->sta.supp_rates[band] != prev_rates) { + prev_rates = sta->sta.supp_rates[band]; + /* make sure mandatory rates are always added */ + sta->sta.supp_rates[band] = supp_rates | + ieee80211_mandatory_rates(local, band); + + if (sta->sta.supp_rates[band] != prev_rates) { #ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG "%s: updated supp_rates set " - "for %pM based on beacon/probe_response " - "(0x%x -> 0x%x)\n", - sdata->name, sta->sta.addr, - prev_rates, sta->sta.supp_rates[band]); + printk(KERN_DEBUG + "%s: updated supp_rates set " + "for %pM based on beacon" + "/probe_resp (0x%x -> 0x%x)\n", + sdata->name, sta->sta.addr, + prev_rates, + sta->sta.supp_rates[band]); #endif - rate_control_rate_init(sta); - } - rcu_read_unlock(); - } else { - rcu_read_unlock(); - ieee80211_ibss_add_sta(sdata, mgmt->bssid, mgmt->sa, - supp_rates, GFP_KERNEL); + rate_control_rate_init(sta); + } + } else + sta = ieee80211_ibss_add_sta(sdata, mgmt->bssid, + mgmt->sa, supp_rates, + GFP_ATOMIC); } + + if (sta && elems->wmm_info) + set_sta_flags(sta, WLAN_STA_WME); + + rcu_read_unlock(); } bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 4e635e2..b80c386 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -159,13 +159,37 @@ typedef unsigned __bitwise__ ieee80211_rx_result; #define RX_DROP_MONITOR ((__force ieee80211_rx_result) 2u) #define RX_QUEUED ((__force ieee80211_rx_result) 3u) -#define IEEE80211_RX_IN_SCAN BIT(0) -/* frame is destined to interface currently processed (incl. multicast frames) */ -#define IEEE80211_RX_RA_MATCH BIT(1) -#define IEEE80211_RX_AMSDU BIT(2) -#define IEEE80211_RX_FRAGMENTED BIT(3) -#define IEEE80211_MALFORMED_ACTION_FRM BIT(4) -/* only add flags here that do not change with subframes of an aMPDU */ +/** + * enum ieee80211_packet_rx_flags - packet RX flags + * @IEEE80211_RX_RA_MATCH: frame is destined to interface currently processed + * (incl. multicast frames) + * @IEEE80211_RX_IN_SCAN: received while scanning + * @IEEE80211_RX_FRAGMENTED: fragmented frame + * @IEEE80211_RX_AMSDU: a-MSDU packet + * @IEEE80211_RX_MALFORMED_ACTION_FRM: action frame is malformed + * + * These are per-frame flags that are attached to a frame in the + * @rx_flags field of &struct ieee80211_rx_status. + */ +enum ieee80211_packet_rx_flags { + IEEE80211_RX_IN_SCAN = BIT(0), + IEEE80211_RX_RA_MATCH = BIT(1), + IEEE80211_RX_FRAGMENTED = BIT(2), + IEEE80211_RX_AMSDU = BIT(3), + IEEE80211_RX_MALFORMED_ACTION_FRM = BIT(4), +}; + +/** + * enum ieee80211_rx_flags - RX data flags + * + * @IEEE80211_RX_CMNTR: received on cooked monitor already + * + * These flags are used across handling multiple interfaces + * for a single frame. + */ +enum ieee80211_rx_flags { + IEEE80211_RX_CMNTR = BIT(0), +}; struct ieee80211_rx_data { struct sk_buff *skb; @@ -345,6 +369,7 @@ struct ieee80211_if_managed { unsigned int flags; + bool beacon_crc_valid; u32 beacon_crc; enum { @@ -524,8 +549,6 @@ struct ieee80211_sub_if_data { struct ieee80211_fragment_entry fragments[IEEE80211_FRAGMENT_MAX]; unsigned int fragment_next; -#define NUM_DEFAULT_KEYS 4 -#define NUM_DEFAULT_MGMT_KEYS 2 struct ieee80211_key *keys[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; struct ieee80211_key *default_key; struct ieee80211_key *default_mgmt_key; @@ -564,6 +587,7 @@ struct ieee80211_sub_if_data { #ifdef CONFIG_MAC80211_DEBUGFS struct { struct dentry *dir; + struct dentry *subdir_stations; struct dentry *default_key; struct dentry *default_mgmt_key; } debugfs; @@ -683,7 +707,9 @@ struct ieee80211_local { int open_count; int monitors, cooked_mntrs; /* number of interfaces with corresponding FIF_ flags */ - int fif_fcsfail, fif_plcpfail, fif_control, fif_other_bss, fif_pspoll; + int fif_fcsfail, fif_plcpfail, fif_control, fif_other_bss, fif_pspoll, + fif_probe_req; + int probe_req_reg; unsigned int filter_flags; /* FIF_* */ bool wiphy_ciphers_allocated; @@ -899,7 +925,6 @@ struct ieee80211_local { #ifdef CONFIG_MAC80211_DEBUGFS struct local_debugfsdentries { struct dentry *rcdir; - struct dentry *stations; struct dentry *keys; } debugfs; #endif @@ -1041,6 +1066,8 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); +void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata); +void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata); /* IBSS code */ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local); @@ -1106,6 +1133,8 @@ 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); +void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, + const int offset); static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata) { @@ -1146,10 +1175,10 @@ int ieee80211_send_smps_action(struct ieee80211_sub_if_data *sdata, void ieee80211_request_smps_work(struct work_struct *work); void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, - u16 initiator, u16 reason); + u16 initiator, u16 reason, bool stop); void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, - u16 initiator, u16 reason); -void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta); + u16 initiator, u16 reason, bool stop); +void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, bool tx); void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_mgmt *mgmt, size_t len); @@ -1163,9 +1192,11 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, size_t len); int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator); + enum ieee80211_back_parties initiator, + bool tx); int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator); + enum ieee80211_back_parties initiator, + bool tx); void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid); void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid); void ieee80211_ba_session_work(struct work_struct *work); @@ -1254,7 +1285,8 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, const u8 *key, u8 key_len, u8 key_idx); int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, const u8 *ie, size_t ie_len, - enum ieee80211_band band); + enum ieee80211_band band, u32 rate_mask, + u8 channel); void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len); @@ -1267,8 +1299,7 @@ u32 ieee80211_sta_get_rates(struct ieee80211_local *local, enum ieee80211_band band); int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode); -void ieee80211_recalc_smps(struct ieee80211_local *local, - struct ieee80211_sub_if_data *forsdata); +void ieee80211_recalc_smps(struct ieee80211_local *local); size_t ieee80211_ie_split(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, size_t offset); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index c1cc200..f9163b1 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -24,6 +24,7 @@ #include "led.h" #include "driver-ops.h" #include "wme.h" +#include "rate.h" /** * DOC: Interface list locking @@ -148,6 +149,26 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, return 0; } +void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, + const int offset) +{ + struct ieee80211_local *local = sdata->local; + u32 flags = sdata->u.mntr_flags; + +#define ADJUST(_f, _s) do { \ + if (flags & MONITOR_FLAG_##_f) \ + local->fif_##_s += offset; \ + } while (0) + + ADJUST(FCSFAIL, fcsfail); + ADJUST(PLCPFAIL, plcpfail); + ADJUST(CONTROL, control); + ADJUST(CONTROL, pspoll); + ADJUST(OTHER_BSS, other_bss); + +#undef ADJUST +} + /* * NOTE: Be very careful when changing this function, it must NOT return * an error on interface type changes that have been pre-checked, so most @@ -188,6 +209,8 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_P2P_GO: /* cannot happen */ WARN_ON(1); break; @@ -238,17 +261,7 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR; } - if (sdata->u.mntr_flags & MONITOR_FLAG_FCSFAIL) - local->fif_fcsfail++; - if (sdata->u.mntr_flags & MONITOR_FLAG_PLCPFAIL) - local->fif_plcpfail++; - if (sdata->u.mntr_flags & MONITOR_FLAG_CONTROL) { - local->fif_control++; - local->fif_pspoll++; - } - if (sdata->u.mntr_flags & MONITOR_FLAG_OTHER_BSS) - local->fif_other_bss++; - + ieee80211_adjust_monitor_flags(sdata, 1); ieee80211_configure_filter(local); netif_carrier_on(dev); @@ -267,8 +280,11 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) ieee80211_start_mesh(sdata); } else if (sdata->vif.type == NL80211_IFTYPE_AP) { local->fif_pspoll++; + local->fif_probe_req++; ieee80211_configure_filter(local); + } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { + local->fif_probe_req++; } changed |= ieee80211_reset_erp_info(sdata); @@ -280,6 +296,8 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) netif_carrier_on(dev); } + set_bit(SDATA_STATE_RUNNING, &sdata->state); + if (sdata->vif.type == NL80211_IFTYPE_WDS) { /* Create STA entry for the WDS peer */ sta = sta_info_alloc(sdata, sdata->u.wds.remote_addr, @@ -297,6 +315,8 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) /* STA has been freed */ goto err_del_interface; } + + rate_control_rate_init(sta); } /* @@ -331,8 +351,6 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) netif_tx_start_all_queues(dev); - set_bit(SDATA_STATE_RUNNING, &sdata->state); - return 0; err_del_interface: drv_remove_interface(local, &sdata->vif); @@ -343,6 +361,7 @@ static int ieee80211_do_open(struct net_device *dev, bool coming_up) sdata->bss = NULL; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) list_del(&sdata->u.vlan.list); + clear_bit(SDATA_STATE_RUNNING, &sdata->state); return res; } @@ -412,8 +431,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, if (sdata->flags & IEEE80211_SDATA_PROMISC) atomic_dec(&local->iff_promiscs); - if (sdata->vif.type == NL80211_IFTYPE_AP) + if (sdata->vif.type == NL80211_IFTYPE_AP) { local->fif_pspoll--; + local->fif_probe_req--; + } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { + local->fif_probe_req--; + } netif_addr_lock_bh(sdata->dev); spin_lock_bh(&local->filter_lock); @@ -474,17 +497,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR; } - if (sdata->u.mntr_flags & MONITOR_FLAG_FCSFAIL) - local->fif_fcsfail--; - if (sdata->u.mntr_flags & MONITOR_FLAG_PLCPFAIL) - local->fif_plcpfail--; - if (sdata->u.mntr_flags & MONITOR_FLAG_CONTROL) { - local->fif_pspoll--; - local->fif_control--; - } - if (sdata->u.mntr_flags & MONITOR_FLAG_OTHER_BSS) - local->fif_other_bss--; - + ieee80211_adjust_monitor_flags(sdata, -1); ieee80211_configure_filter(local); break; case NL80211_IFTYPE_MESH_POINT: @@ -790,7 +803,8 @@ static void ieee80211_iface_work(struct work_struct *work) __ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_REQUIRE_SETUP); + WLAN_REASON_QSTA_REQUIRE_SETUP, + true); } mutex_unlock(&local->sta_mtx); } else switch (sdata->vif.type) { @@ -843,6 +857,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, /* and set some type-dependent values */ sdata->vif.type = type; + sdata->vif.p2p = false; sdata->dev->netdev_ops = &ieee80211_dataif_ops; sdata->wdev.iftype = type; @@ -856,10 +871,20 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, INIT_WORK(&sdata->work, ieee80211_iface_work); switch (type) { + case NL80211_IFTYPE_P2P_GO: + type = NL80211_IFTYPE_AP; + sdata->vif.type = type; + sdata->vif.p2p = true; + /* fall through */ case NL80211_IFTYPE_AP: skb_queue_head_init(&sdata->u.ap.ps_bc_buf); INIT_LIST_HEAD(&sdata->u.ap.vlans); break; + case NL80211_IFTYPE_P2P_CLIENT: + type = NL80211_IFTYPE_STATION; + sdata->vif.type = type; + sdata->vif.p2p = true; + /* fall through */ case NL80211_IFTYPE_STATION: ieee80211_sta_setup_sdata(sdata); break; @@ -893,6 +918,8 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; int ret, err; + enum nl80211_iftype internal_type = type; + bool p2p = false; ASSERT_RTNL(); @@ -925,11 +952,19 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, * code isn't prepared to handle). */ break; + case NL80211_IFTYPE_P2P_CLIENT: + p2p = true; + internal_type = NL80211_IFTYPE_STATION; + break; + case NL80211_IFTYPE_P2P_GO: + p2p = true; + internal_type = NL80211_IFTYPE_AP; + break; default: return -EBUSY; } - ret = ieee80211_check_concurrent_iface(sdata, type); + ret = ieee80211_check_concurrent_iface(sdata, internal_type); if (ret) return ret; @@ -937,7 +972,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, ieee80211_teardown_sdata(sdata->dev); - ret = drv_change_interface(local, sdata, type); + ret = drv_change_interface(local, sdata, internal_type, p2p); if (ret) type = sdata->vif.type; @@ -956,7 +991,7 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, ASSERT_RTNL(); - if (type == sdata->vif.type) + if (type == ieee80211_vif_type_p2p(&sdata->vif)) return 0; /* Setting ad-hoc mode on non-IBSS channel is not supported. */ diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 3570f8c..ccd676b 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -49,7 +49,7 @@ static const u8 bcast_addr[ETH_ALEN] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; static void assert_key_lock(struct ieee80211_local *local) { - WARN_ON(!mutex_is_locked(&local->key_mtx)); + lockdep_assert_held(&local->key_mtx); } static struct ieee80211_sta *get_sta_for_key(struct ieee80211_key *key) @@ -68,15 +68,21 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) might_sleep(); - if (!key->local->ops->set_key) { - ret = -EOPNOTSUPP; + if (!key->local->ops->set_key) goto out_unsupported; - } assert_key_lock(key->local); sta = get_sta_for_key(key); + /* + * If this is a per-STA GTK, check if it + * is supported; if not, return. + */ + if (sta && !(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE) && + !(key->local->hw.flags & IEEE80211_HW_SUPPORTS_PER_STA_GTK)) + goto out_unsupported; + sdata = key->sdata; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, @@ -85,31 +91,28 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) ret = drv_set_key(key->local, SET_KEY, sdata, sta, &key->conf); - if (!ret) + if (!ret) { key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; + return 0; + } - if (ret && ret != -ENOSPC && ret != -EOPNOTSUPP) + if (ret != -ENOSPC && ret != -EOPNOTSUPP) wiphy_err(key->local->hw.wiphy, "failed to set key (%d, %pM) to hardware (%d)\n", key->conf.keyidx, sta ? sta->addr : bcast_addr, ret); -out_unsupported: - if (ret) { - switch (key->conf.cipher) { - case WLAN_CIPHER_SUITE_WEP40: - case WLAN_CIPHER_SUITE_WEP104: - case WLAN_CIPHER_SUITE_TKIP: - case WLAN_CIPHER_SUITE_CCMP: - case WLAN_CIPHER_SUITE_AES_CMAC: - /* all of these we can do in software */ - ret = 0; - break; - default: - ret = -EINVAL; - } + out_unsupported: + switch (key->conf.cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + case WLAN_CIPHER_SUITE_TKIP: + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_AES_CMAC: + /* all of these we can do in software */ + return 0; + default: + return -EINVAL; } - - return ret; } static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) @@ -147,6 +150,26 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; } +void ieee80211_key_removed(struct ieee80211_key_conf *key_conf) +{ + struct ieee80211_key *key; + + key = container_of(key_conf, struct ieee80211_key, conf); + + might_sleep(); + assert_key_lock(key->local); + + key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; + + /* + * Flush TX path to avoid attempts to use this key + * after this function returns. Until then, drivers + * must be prepared to handle the key. + */ + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(ieee80211_key_removed); + static void __ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx) { @@ -202,6 +225,7 @@ void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, static void __ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, + bool pairwise, struct ieee80211_key *old, struct ieee80211_key *new) { @@ -210,8 +234,14 @@ static void __ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, if (new) list_add(&new->list, &sdata->key_list); - if (sta) { - rcu_assign_pointer(sta->key, new); + if (sta && pairwise) { + rcu_assign_pointer(sta->ptk, new); + } else if (sta) { + if (old) + idx = old->conf.keyidx; + else + idx = new->conf.keyidx; + rcu_assign_pointer(sta->gtk[idx], new); } else { WARN_ON(new && old && new->conf.keyidx != old->conf.keyidx); @@ -355,6 +385,7 @@ int ieee80211_key_link(struct ieee80211_key *key, { struct ieee80211_key *old_key; int idx, ret; + bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; BUG_ON(!sdata); BUG_ON(!key); @@ -371,13 +402,6 @@ int ieee80211_key_link(struct ieee80211_key *key, */ if (test_sta_flags(sta, WLAN_STA_WME)) key->conf.flags |= IEEE80211_KEY_FLAG_WMM_STA; - - /* - * This key is for a specific sta interface, - * inform the driver that it should try to store - * this key as pairwise key. - */ - key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE; } else { if (sdata->vif.type == NL80211_IFTYPE_STATION) { struct sta_info *ap; @@ -399,12 +423,14 @@ int ieee80211_key_link(struct ieee80211_key *key, mutex_lock(&sdata->local->key_mtx); - if (sta) - old_key = sta->key; + if (sta && pairwise) + old_key = sta->ptk; + else if (sta) + old_key = sta->gtk[idx]; else old_key = sdata->keys[idx]; - __ieee80211_key_replace(sdata, sta, old_key, key); + __ieee80211_key_replace(sdata, sta, pairwise, old_key, key); __ieee80211_key_destroy(old_key); ieee80211_debugfs_key_add(key); @@ -423,7 +449,8 @@ static void __ieee80211_key_free(struct ieee80211_key *key) */ if (key->sdata) __ieee80211_key_replace(key->sdata, key->sta, - key, NULL); + key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, + key, NULL); __ieee80211_key_destroy(key); } diff --git a/net/mac80211/key.h b/net/mac80211/key.h index cb9a4a6..0db1c0f 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -16,6 +16,9 @@ #include <linux/rcupdate.h> #include <net/mac80211.h> +#define NUM_DEFAULT_KEYS 4 +#define NUM_DEFAULT_MGMT_KEYS 2 + #define WEP_IV_LEN 4 #define WEP_ICV_LEN 4 #define ALG_TKIP_KEY_LEN 32 diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4935b84..22bc42b 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -54,6 +54,9 @@ void ieee80211_configure_filter(struct ieee80211_local *local) if (local->monitors || local->scanning) new_flags |= FIF_BCN_PRBRESP_PROMISC; + if (local->fif_probe_req || local->probe_req_reg) + new_flags |= FIF_PROBE_REQ; + if (local->fif_fcsfail) new_flags |= FIF_FCSFAIL; @@ -110,7 +113,8 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) chan = scan_chan; channel_type = NL80211_CHAN_NO_HT; local->hw.conf.flags |= IEEE80211_CONF_OFFCHANNEL; - } else if (local->tmp_channel) { + } else if (local->tmp_channel && + local->oper_channel != local->tmp_channel) { chan = scan_chan = local->tmp_channel; channel_type = local->tmp_channel_type; local->hw.conf.flags |= IEEE80211_CONF_OFFCHANNEL; @@ -200,6 +204,8 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.bssid = sdata->u.ibss.bssid; else if (sdata->vif.type == NL80211_IFTYPE_AP) sdata->vif.bss_conf.bssid = sdata->vif.addr; + else if (sdata->vif.type == NL80211_IFTYPE_WDS) + sdata->vif.bss_conf.bssid = NULL; else if (ieee80211_vif_is_mesh(&sdata->vif)) { sdata->vif.bss_conf.bssid = zero; } else { @@ -210,6 +216,7 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MESH_POINT: break; default: @@ -294,7 +301,16 @@ static void ieee80211_restart_work(struct work_struct *work) struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); + /* wait for scan work complete */ + flush_workqueue(local->workqueue); + + mutex_lock(&local->mtx); + WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), + "%s called with hardware scan in progress\n", __func__); + mutex_unlock(&local->mtx); + rtnl_lock(); + ieee80211_scan_cancel(local); ieee80211_reconfig(local); rtnl_unlock(); } @@ -305,12 +321,6 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw) trace_api_restart_hw(local); - WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), - "%s called with hardware scan in progress\n", __func__); - - if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning))) - ieee80211_scan_cancel(local); - /* use this reason, ieee80211_reconfig will unblock it */ ieee80211_stop_queues_by_reason(hw, IEEE80211_QUEUE_STOP_REASON_SUSPEND); @@ -325,7 +335,7 @@ static void ieee80211_recalc_smps_work(struct work_struct *work) container_of(work, struct ieee80211_local, recalc_smps); mutex_lock(&local->iflist_mtx); - ieee80211_recalc_smps(local, NULL); + ieee80211_recalc_smps(local); mutex_unlock(&local->iflist_mtx); } @@ -362,7 +372,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb, if (sdata->vif.type != NL80211_IFTYPE_STATION) return NOTIFY_DONE; - idev = sdata->dev->ip_ptr; + idev = __in_dev_get_rtnl(sdata->dev); if (!idev) return NOTIFY_DONE; @@ -456,6 +466,21 @@ ieee80211_default_mgmt_stypes[NUM_NL80211_IFTYPES] = { BIT(IEEE80211_STYPE_DEAUTH >> 4) | BIT(IEEE80211_STYPE_ACTION >> 4), }, + [NL80211_IFTYPE_P2P_CLIENT] = { + .tx = 0xffff, + .rx = BIT(IEEE80211_STYPE_ACTION >> 4) | + BIT(IEEE80211_STYPE_PROBE_REQ >> 4), + }, + [NL80211_IFTYPE_P2P_GO] = { + .tx = 0xffff, + .rx = BIT(IEEE80211_STYPE_ASSOC_REQ >> 4) | + BIT(IEEE80211_STYPE_REASSOC_REQ >> 4) | + BIT(IEEE80211_STYPE_PROBE_REQ >> 4) | + BIT(IEEE80211_STYPE_DISASSOC >> 4) | + BIT(IEEE80211_STYPE_AUTH >> 4) | + BIT(IEEE80211_STYPE_DEAUTH >> 4) | + BIT(IEEE80211_STYPE_ACTION >> 4), + }, }; struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, @@ -514,6 +539,7 @@ 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->hw.max_report_rates = 0; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; local->user_power_level = -1; @@ -589,6 +615,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) WLAN_CIPHER_SUITE_AES_CMAC }; + if (hw->max_report_rates == 0) + hw->max_report_rates = hw->max_rates; + /* * generic code guarantees at least one band, * set this very early because much code assumes diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index ea13a80..1c91f0f 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -412,7 +412,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m enum plink_event event; enum plink_frame_type ftype; size_t baselen; - bool deactivated; + bool deactivated, matches_local = true; u8 ie_len; u8 *baseaddr; __le16 plid, llid, reason; @@ -487,6 +487,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m /* Now we will figure out the appropriate event... */ event = PLINK_UNDEFINED; if (ftype != PLINK_CLOSE && (!mesh_matches_local(&elems, sdata))) { + matches_local = false; switch (ftype) { case PLINK_OPEN: event = OPN_RJCT; @@ -498,7 +499,15 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m /* avoid warning */ break; } - spin_lock_bh(&sta->lock); + } + + if (!sta && !matches_local) { + rcu_read_unlock(); + reason = cpu_to_le16(MESH_CAPABILITY_POLICY_VIOLATION); + llid = 0; + mesh_plink_frame_tx(sdata, PLINK_CLOSE, mgmt->sa, llid, + plid, reason); + return; } else if (!sta) { /* ftype == PLINK_OPEN */ u32 rates; @@ -522,7 +531,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m } event = OPN_ACPT; spin_lock_bh(&sta->lock); - } else { + } else if (matches_local) { spin_lock_bh(&sta->lock); switch (ftype) { case PLINK_OPEN: @@ -564,6 +573,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m rcu_read_unlock(); return; } + } else { + spin_lock_bh(&sta->lock); } mpl_dbg("Mesh plink (peer, state, llid, plid, event): %pM %s %d %d %d\n", diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0cb822c..a3a9421 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -92,7 +92,7 @@ enum rx_mgmt_action { /* utils */ static inline void ASSERT_MGD_MTX(struct ieee80211_if_managed *ifmgd) { - WARN_ON(!mutex_is_locked(&ifmgd->mtx)); + lockdep_assert_held(&ifmgd->mtx); } /* @@ -115,7 +115,7 @@ static void run_again(struct ieee80211_if_managed *ifmgd, mod_timer(&ifmgd->timer, timeout); } -static void mod_beacon_timer(struct ieee80211_sub_if_data *sdata) +void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata) { if (sdata->local->hw.flags & IEEE80211_HW_BEACON_FILTER) return; @@ -124,6 +124,19 @@ static void mod_beacon_timer(struct ieee80211_sub_if_data *sdata) round_jiffies_up(jiffies + IEEE80211_BEACON_LOSS_TIME)); } +void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR) + return; + + mod_timer(&sdata->u.mgd.conn_mon_timer, + round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); + + ifmgd->probe_send_count = 0; +} + static int ecw2cw(int ecw) { return (1 << ecw) - 1; @@ -867,14 +880,6 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, sdata->u.mgd.flags &= ~(IEEE80211_STA_CONNECTION_POLL | IEEE80211_STA_BEACON_POLL); - /* - * Always handle WMM once after association regardless - * of the first value the AP uses. Setting -1 here has - * that effect because the AP values is an unsigned - * 4-bit value. - */ - sdata->u.mgd.wmm_last_param_set = -1; - ieee80211_led_assoc(local, 1); if (local->hw.flags & IEEE80211_HW_NEED_DTIM_PERIOD) @@ -908,7 +913,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, mutex_lock(&local->iflist_mtx); ieee80211_recalc_ps(local, -1); - ieee80211_recalc_smps(local, sdata); + ieee80211_recalc_smps(local); mutex_unlock(&local->iflist_mtx); netif_tx_start_all_queues(sdata->dev); @@ -916,7 +921,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, } static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, - bool remove_sta) + bool remove_sta, bool tx) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; @@ -955,7 +960,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sta = sta_info_get(sdata, bssid); if (sta) { set_sta_flags(sta, WLAN_STA_BLOCK_BA); - ieee80211_sta_tear_down_BA_sessions(sta); + ieee80211_sta_tear_down_BA_sessions(sta, tx); } mutex_unlock(&local->sta_mtx); @@ -1018,21 +1023,26 @@ void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, if (is_multicast_ether_addr(hdr->addr1)) return; - if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR) - return; - - mod_timer(&sdata->u.mgd.conn_mon_timer, - round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); + ieee80211_sta_reset_conn_monitor(sdata); } static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; const u8 *ssid; + u8 *dst = ifmgd->associated->bssid; + u8 unicast_limit = max(1, IEEE80211_MAX_PROBE_TRIES - 3); + + /* + * Try sending broadcast probe requests for the last three + * probe requests after the first ones failed since some + * buggy APs only support broadcast probe requests. + */ + if (ifmgd->probe_send_count >= unicast_limit) + dst = NULL; ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); - ieee80211_send_probe_req(sdata, ifmgd->associated->bssid, - ssid + 2, ssid[1], NULL, 0); + ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid[1], NULL, 0); ifmgd->probe_send_count++; ifmgd->probe_timeout = jiffies + IEEE80211_PROBE_WAIT; @@ -1114,7 +1124,7 @@ static void __ieee80211_connection_loss(struct ieee80211_sub_if_data *sdata) printk(KERN_DEBUG "Connection to AP %pM lost.\n", bssid); - ieee80211_set_disassoc(sdata, true); + ieee80211_set_disassoc(sdata, true, true); mutex_unlock(&ifmgd->mtx); mutex_lock(&local->mtx); @@ -1187,7 +1197,7 @@ ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, printk(KERN_DEBUG "%s: deauthenticated from %pM (Reason: %u)\n", sdata->name, bssid, reason_code); - ieee80211_set_disassoc(sdata, true); + ieee80211_set_disassoc(sdata, true, false); mutex_lock(&sdata->local->mtx); ieee80211_recalc_idle(sdata->local); mutex_unlock(&sdata->local->mtx); @@ -1219,7 +1229,7 @@ ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, printk(KERN_DEBUG "%s: disassociated from %pM (Reason: %u)\n", sdata->name, mgmt->sa, reason_code); - ieee80211_set_disassoc(sdata, true); + ieee80211_set_disassoc(sdata, true, false); mutex_lock(&sdata->local->mtx); ieee80211_recalc_idle(sdata->local); mutex_unlock(&sdata->local->mtx); @@ -1281,7 +1291,7 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, rates = 0; basic_rates = 0; - sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + sband = local->hw.wiphy->bands[wk->chan->band]; for (i = 0; i < elems.supp_rates_len; i++) { int rate = (elems.supp_rates[i] & 0x7f) * 5; @@ -1317,11 +1327,11 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, } } - sta->sta.supp_rates[local->hw.conf.channel->band] = rates; + sta->sta.supp_rates[wk->chan->band] = rates; sdata->vif.bss_conf.basic_rates = basic_rates; /* cf. IEEE 802.11 9.2.12 */ - if (local->hw.conf.channel->band == IEEE80211_BAND_2GHZ && + if (wk->chan->band == IEEE80211_BAND_2GHZ && have_higher_than_11mbit) sdata->flags |= IEEE80211_SDATA_OPERATING_GMODE; else @@ -1349,6 +1359,14 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, return false; } + /* + * Always handle WMM once after association regardless + * of the first value the AP uses. Setting -1 here has + * that effect because the AP values is an unsigned + * 4-bit value. + */ + ifmgd->wmm_last_param_set = -1; + if (elems.wmm_param) ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, elems.wmm_param_len); @@ -1381,7 +1399,7 @@ static bool ieee80211_assoc_success(struct ieee80211_work *wk, * Also start the timer that will detect beacon loss. */ ieee80211_sta_rx_notify(sdata, (struct ieee80211_hdr *)mgmt); - mod_beacon_timer(sdata); + ieee80211_sta_reset_beacon_monitor(sdata); return true; } @@ -1484,7 +1502,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, * we have or will be receiving any beacons or data, so let's * schedule the timers again, just in case. */ - mod_beacon_timer(sdata); + ieee80211_sta_reset_beacon_monitor(sdata); mod_timer(&ifmgd->conn_mon_timer, round_jiffies_up(jiffies + @@ -1610,7 +1628,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, * Push the beacon loss detection into the future since * we are processing a beacon from the AP just now. */ - mod_beacon_timer(sdata); + ieee80211_sta_reset_beacon_monitor(sdata); ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4); ncrc = ieee802_11_parse_elems_crc(mgmt->u.beacon.variable, @@ -1621,7 +1639,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, directed_tim = ieee80211_check_tim(elems.tim, elems.tim_len, ifmgd->aid); - if (ncrc != ifmgd->beacon_crc) { + if (ncrc != ifmgd->beacon_crc || !ifmgd->beacon_crc_valid) { ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, true); @@ -1652,9 +1670,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } } - if (ncrc == ifmgd->beacon_crc) + if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) return; ifmgd->beacon_crc = ncrc; + ifmgd->beacon_crc_valid = true; if (elems.erp_info && elems.erp_info_len >= 1) { erp_valid = true; @@ -1845,10 +1864,12 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) else if (ifmgd->probe_send_count < IEEE80211_MAX_PROBE_TRIES) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG - printk(KERN_DEBUG "No probe response from AP %pM" - " after %dms, try %d\n", bssid, - (1000 * IEEE80211_PROBE_WAIT)/HZ, - ifmgd->probe_send_count); + wiphy_debug(local->hw.wiphy, + "%s: No probe response from AP %pM" + " after %dms, try %d\n", + sdata->name, + bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ, + ifmgd->probe_send_count); #endif ieee80211_mgd_probe_ap_send(sdata); } else { @@ -1858,10 +1879,12 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) */ ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | IEEE80211_STA_BEACON_POLL); - printk(KERN_DEBUG "No probe response from AP %pM" - " after %dms, disconnecting.\n", - bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ); - ieee80211_set_disassoc(sdata, true); + wiphy_debug(local->hw.wiphy, + "%s: No probe response from AP %pM" + " after %dms, disconnecting.\n", + sdata->name, + bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ); + ieee80211_set_disassoc(sdata, true, true); mutex_unlock(&ifmgd->mtx); mutex_lock(&local->mtx); ieee80211_recalc_idle(local); @@ -2185,7 +2208,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, } /* Trying to reassociate - clear previous association state */ - ieee80211_set_disassoc(sdata, true); + ieee80211_set_disassoc(sdata, true, false); } mutex_unlock(&ifmgd->mtx); @@ -2196,6 +2219,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, ifmgd->flags &= ~IEEE80211_STA_DISABLE_11N; ifmgd->flags &= ~IEEE80211_STA_NULLFUNC_ACKED; + ifmgd->beacon_crc_valid = false; + for (i = 0; i < req->crypto.n_ciphers_pairwise; i++) if (req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP40 || req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_TKIP || @@ -2297,7 +2322,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, memcpy(bssid, req->bss->bssid, ETH_ALEN); if (ifmgd->associated == req->bss) { - ieee80211_set_disassoc(sdata, false); + ieee80211_set_disassoc(sdata, false, true); mutex_unlock(&ifmgd->mtx); assoc_bss = true; } else { @@ -2380,7 +2405,7 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, sdata->name, req->bss->bssid, req->reason_code); memcpy(bssid, req->bss->bssid, ETH_ALEN); - ieee80211_set_disassoc(sdata, false); + ieee80211_set_disassoc(sdata, false, true); mutex_unlock(&ifmgd->mtx); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index eeacaa5..4b56409 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -22,12 +22,16 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; local->offchannel_ps_enabled = false; /* FIXME: what to do when local->pspolling is true? */ del_timer_sync(&local->dynamic_ps_timer); + del_timer_sync(&ifmgd->bcn_mon_timer); + del_timer_sync(&ifmgd->conn_mon_timer); + cancel_work_sync(&local->dynamic_ps_enable_work); if (local->hw.conf.flags & IEEE80211_CONF_PS) { @@ -85,6 +89,9 @@ static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata) mod_timer(&local->dynamic_ps_timer, jiffies + msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout)); } + + ieee80211_sta_reset_beacon_monitor(sdata); + ieee80211_sta_reset_conn_monitor(sdata); } void ieee80211_offchannel_stop_beaconing(struct ieee80211_local *local) diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index ce671df..e373551 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -12,8 +12,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) struct ieee80211_sub_if_data *sdata; struct sta_info *sta; - if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning))) - ieee80211_scan_cancel(local); + ieee80211_scan_cancel(local); ieee80211_stop_queues_by_reason(hw, IEEE80211_QUEUE_STOP_REASON_SUSPEND); @@ -46,7 +45,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) list_for_each_entry(sta, &local->sta_list, list) { if (hw->flags & IEEE80211_HW_AMPDU_AGGREGATION) { set_sta_flags(sta, WLAN_STA_BLOCK_BA); - ieee80211_sta_tear_down_BA_sessions(sta); + ieee80211_sta_tear_down_BA_sessions(sta, true); } if (sta->uploaded) { diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 4f772de..b0cc385 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -207,7 +207,7 @@ static bool rc_no_data_or_no_ack(struct ieee80211_tx_rate_control *txrc) fc = hdr->frame_control; - return ((info->flags & IEEE80211_TX_CTL_NO_ACK) || !ieee80211_is_data(fc)); + return (info->flags & IEEE80211_TX_CTL_NO_ACK) || !ieee80211_is_data(fc); } static void rc_send_low_broadcast(s8 *idx, u32 basic_rates, u8 max_rate_idx) diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index c5b4659..2a18d66 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -397,8 +397,9 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, !(info->flags & IEEE80211_TX_STAT_AMPDU)) return; - if (!info->status.ampdu_len) { - info->status.ampdu_ack_len = 1; + if (!(info->flags & IEEE80211_TX_STAT_AMPDU)) { + info->status.ampdu_ack_len = + (info->flags & IEEE80211_TX_STAT_ACK ? 1 : 0); info->status.ampdu_len = 1; } @@ -426,7 +427,7 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, group = minstrel_ht_get_group_idx(&ar[i]); rate = &mi->groups[group].rates[ar[i].idx % 8]; - if (last && (info->flags & IEEE80211_TX_STAT_ACK)) + if (last) rate->success += info->status.ampdu_ack_len; rate->attempts += ar[i].count * info->status.ampdu_len; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index ac205a3..902b03ee 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -315,6 +315,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); int tid; /* does the frame have a qos control field? */ @@ -323,9 +324,7 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) /* frame has qos control */ tid = *qc & IEEE80211_QOS_CTL_TID_MASK; if (*qc & IEEE80211_QOS_CONTROL_A_MSDU_PRESENT) - rx->flags |= IEEE80211_RX_AMSDU; - else - rx->flags &= ~IEEE80211_RX_AMSDU; + status->rx_flags |= IEEE80211_RX_AMSDU; } else { /* * IEEE 802.11-2007, 7.1.3.4.1 ("Sequence Number field"): @@ -387,26 +386,25 @@ static ieee80211_rx_result debug_noinline ieee80211_rx_h_passive_scan(struct ieee80211_rx_data *rx) { struct ieee80211_local *local = rx->local; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); struct sk_buff *skb = rx->skb; - if (unlikely(test_bit(SCAN_HW_SCANNING, &local->scanning))) + if (likely(!(status->rx_flags & IEEE80211_RX_IN_SCAN))) + return RX_CONTINUE; + + if (test_bit(SCAN_HW_SCANNING, &local->scanning)) return ieee80211_scan_rx(rx->sdata, skb); - if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning) && - (rx->flags & IEEE80211_RX_IN_SCAN))) { + if (test_bit(SCAN_SW_SCANNING, &local->scanning)) { /* drop all the other packets during a software scan anyway */ if (ieee80211_scan_rx(rx->sdata, skb) != RX_QUEUED) dev_kfree_skb(skb); return RX_QUEUED; } - if (unlikely(rx->flags & IEEE80211_RX_IN_SCAN)) { - /* scanning finished during invoking of handlers */ - I802_DEBUG_INC(local->rx_handlers_drop_passive_scan); - return RX_DROP_UNUSABLE; - } - - return RX_CONTINUE; + /* scanning finished during invoking of handlers */ + I802_DEBUG_INC(local->rx_handlers_drop_passive_scan); + return RX_DROP_UNUSABLE; } @@ -624,6 +622,26 @@ static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw, tid_agg_rx->buf_size; } + /* + * Disable the reorder release timer for now. + * + * The current implementation lacks a proper locking scheme + * which would protect vital statistic and debug counters + * from being updated by two different but concurrent BHs. + * + * More information about the topic is available from: + * - thread: http://marc.info/?t=128635927000001 + * + * What was wrong: + * => http://marc.info/?l=linux-wireless&m=128636170811964 + * "Basically the thing is that until your patch, the data + * in the struct didn't actually need locking because it + * was accessed by the RX path only which is not concurrent." + * + * List of what needs to be fixed: + * => http://marc.info/?l=linux-wireless&m=128656352920957 + * + if (tid_agg_rx->stored_mpdu_num) { j = index = seq_sub(tid_agg_rx->head_seq_num, tid_agg_rx->ssn) % tid_agg_rx->buf_size; @@ -642,6 +660,10 @@ static void ieee80211_sta_reorder_release(struct ieee80211_hw *hw, } else { del_timer(&tid_agg_rx->reorder_timer); } + */ + +set_release_timer: + return; } /* @@ -785,13 +807,14 @@ static ieee80211_rx_result debug_noinline ieee80211_rx_h_check(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); /* Drop duplicate 802.11 retransmissions (IEEE 802.11 Chap. 9.2.9) */ if (rx->sta && !is_multicast_ether_addr(hdr->addr1)) { if (unlikely(ieee80211_has_retry(hdr->frame_control) && rx->sta->last_seq_ctrl[rx->queue] == hdr->seq_ctrl)) { - if (rx->flags & IEEE80211_RX_RA_MATCH) { + if (status->rx_flags & IEEE80211_RX_RA_MATCH) { rx->local->dot11FrameDuplicateCount++; rx->sta->num_duplicates++; } @@ -820,11 +843,12 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) if (unlikely((ieee80211_is_data(hdr->frame_control) || ieee80211_is_pspoll(hdr->frame_control)) && rx->sdata->vif.type != NL80211_IFTYPE_ADHOC && + rx->sdata->vif.type != NL80211_IFTYPE_WDS && (!rx->sta || !test_sta_flags(rx->sta, WLAN_STA_ASSOC)))) { if ((!ieee80211_has_fromds(hdr->frame_control) && !ieee80211_has_tods(hdr->frame_control) && ieee80211_is_data(hdr->frame_control)) || - !(rx->flags & IEEE80211_RX_RA_MATCH)) { + !(status->rx_flags & IEEE80211_RX_RA_MATCH)) { /* Drop IBSS frames and frames for other hosts * silently. */ return RX_DROP_MONITOR; @@ -846,7 +870,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) int keyidx; int hdrlen; ieee80211_rx_result result = RX_DROP_UNUSABLE; - struct ieee80211_key *stakey = NULL; + struct ieee80211_key *sta_ptk = NULL; int mmie_keyidx = -1; __le16 fc; @@ -881,22 +905,22 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) * No point in finding a key and decrypting if the frame is neither * addressed to us nor a multicast frame. */ - if (!(rx->flags & IEEE80211_RX_RA_MATCH)) + if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) return RX_CONTINUE; /* start without a key */ rx->key = NULL; if (rx->sta) - stakey = rcu_dereference(rx->sta->key); + sta_ptk = rcu_dereference(rx->sta->ptk); fc = hdr->frame_control; if (!ieee80211_has_protected(fc)) mmie_keyidx = ieee80211_get_mmie_keyidx(rx->skb); - if (!is_multicast_ether_addr(hdr->addr1) && stakey) { - rx->key = stakey; + if (!is_multicast_ether_addr(hdr->addr1) && sta_ptk) { + rx->key = sta_ptk; if ((status->flag & RX_FLAG_DECRYPTED) && (status->flag & RX_FLAG_IV_STRIPPED)) return RX_CONTINUE; @@ -912,7 +936,10 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) if (mmie_keyidx < NUM_DEFAULT_KEYS || 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]); + if (rx->sta) + rx->key = rcu_dereference(rx->sta->gtk[mmie_keyidx]); + if (!rx->key) + rx->key = rcu_dereference(rx->sdata->keys[mmie_keyidx]); } else if (!ieee80211_has_protected(fc)) { /* * The frame was not protected, so skip decryption. However, we @@ -955,17 +982,25 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) skb_copy_bits(rx->skb, hdrlen + 3, &keyid, 1); keyidx = keyid >> 6; - rx->key = rcu_dereference(rx->sdata->keys[keyidx]); + /* check per-station GTK first, if multicast packet */ + if (is_multicast_ether_addr(hdr->addr1) && rx->sta) + rx->key = rcu_dereference(rx->sta->gtk[keyidx]); - /* - * RSNA-protected unicast frames should always be sent with - * pairwise or station-to-station keys, but for WEP we allow - * using a key index as well. - */ - if (rx->key && rx->key->conf.cipher != WLAN_CIPHER_SUITE_WEP40 && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_WEP104 && - !is_multicast_ether_addr(hdr->addr1)) - rx->key = NULL; + /* if not found, try default key */ + if (!rx->key) { + rx->key = rcu_dereference(rx->sdata->keys[keyidx]); + + /* + * RSNA-protected unicast frames should always be + * sent with pairwise or station-to-station keys, + * but for WEP we allow using a key index as well. + */ + if (rx->key && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_WEP40 && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_WEP104 && + !is_multicast_ether_addr(hdr->addr1)) + rx->key = NULL; + } } if (rx->key) { @@ -1114,7 +1149,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) sta->last_rx = jiffies; } - if (!(rx->flags & IEEE80211_RX_RA_MATCH)) + if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) return RX_CONTINUE; if (rx->sdata->vif.type == NL80211_IFTYPE_STATION) @@ -1271,6 +1306,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) unsigned int frag, seq; struct ieee80211_fragment_entry *entry; struct sk_buff *skb; + struct ieee80211_rx_status *status; hdr = (struct ieee80211_hdr *)rx->skb->data; fc = hdr->frame_control; @@ -1370,7 +1406,8 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) } /* Complete frame has been reassembled - process it now */ - rx->flags |= IEEE80211_RX_FRAGMENTED; + status = IEEE80211_SKB_RXCB(rx->skb); + status->rx_flags |= IEEE80211_RX_FRAGMENTED; out: if (rx->sta) @@ -1387,9 +1424,10 @@ ieee80211_rx_h_ps_poll(struct ieee80211_rx_data *rx) { struct ieee80211_sub_if_data *sdata = rx->sdata; __le16 fc = ((struct ieee80211_hdr *)rx->skb->data)->frame_control; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); if (likely(!rx->sta || !ieee80211_is_pspoll(fc) || - !(rx->flags & IEEE80211_RX_RA_MATCH))) + !(status->rx_flags & IEEE80211_RX_RA_MATCH))) return RX_CONTINUE; if ((sdata->vif.type != NL80211_IFTYPE_AP) && @@ -1550,6 +1588,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) struct sk_buff *skb, *xmit_skb; struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data; struct sta_info *dsta; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); skb = rx->skb; xmit_skb = NULL; @@ -1557,7 +1596,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) if ((sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && - (rx->flags & IEEE80211_RX_RA_MATCH) && + (status->rx_flags & IEEE80211_RX_RA_MATCH) && (sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta)) { if (is_multicast_ether_addr(ehdr->h_dest)) { /* @@ -1634,6 +1673,7 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; __le16 fc = hdr->frame_control; struct sk_buff_head frame_list; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); if (unlikely(!ieee80211_is_data(fc))) return RX_CONTINUE; @@ -1641,7 +1681,7 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) if (unlikely(!ieee80211_is_data_present(fc))) return RX_DROP_MONITOR; - if (!(rx->flags & IEEE80211_RX_AMSDU)) + if (!(status->rx_flags & IEEE80211_RX_AMSDU)) return RX_CONTINUE; if (ieee80211_has_a4(hdr->frame_control) && @@ -1692,6 +1732,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct sk_buff *skb = rx->skb, *fwd_skb; struct ieee80211_local *local = rx->local; struct ieee80211_sub_if_data *sdata = rx->sdata; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -1737,7 +1778,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) mesh_hdr->ttl--; - if (rx->flags & IEEE80211_RX_RA_MATCH) { + if (status->rx_flags & IEEE80211_RX_RA_MATCH) { if (!mesh_hdr->ttl) IEEE80211_IFSTA_MESH_CTR_INC(&rx->sdata->u.mesh, dropped_frames_ttl); @@ -1947,6 +1988,7 @@ static ieee80211_rx_result debug_noinline ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx) { struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *) rx->skb->data; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); /* * From here on, look only at management frames. @@ -1959,7 +2001,7 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx) if (!ieee80211_is_mgmt(mgmt->frame_control)) return RX_DROP_MONITOR; - if (!(rx->flags & IEEE80211_RX_RA_MATCH)) + if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) return RX_DROP_MONITOR; if (ieee80211_drop_unencrypted_mgmt(rx)) @@ -1974,6 +2016,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) struct ieee80211_local *local = rx->local; struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *) rx->skb->data; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); int len = rx->skb->len; if (!ieee80211_is_action(mgmt->frame_control)) @@ -1986,7 +2029,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) if (!rx->sta && mgmt->u.action.category != WLAN_CATEGORY_PUBLIC) return RX_DROP_UNUSABLE; - if (!(rx->flags & IEEE80211_RX_RA_MATCH)) + if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) return RX_DROP_UNUSABLE; switch (mgmt->u.action.category) { @@ -2082,7 +2125,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) return RX_CONTINUE; invalid: - rx->flags |= IEEE80211_MALFORMED_ACTION_FRM; + status->rx_flags |= IEEE80211_RX_MALFORMED_ACTION_FRM; /* will return in the next handlers */ return RX_CONTINUE; @@ -2104,10 +2147,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) static ieee80211_rx_result debug_noinline ieee80211_rx_h_userspace_mgmt(struct ieee80211_rx_data *rx) { - struct ieee80211_rx_status *status; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); /* skip known-bad action frames and return them in the next handler */ - if (rx->flags & IEEE80211_MALFORMED_ACTION_FRM) + if (status->rx_flags & IEEE80211_RX_MALFORMED_ACTION_FRM) return RX_CONTINUE; /* @@ -2116,7 +2159,6 @@ ieee80211_rx_h_userspace_mgmt(struct ieee80211_rx_data *rx) * so userspace can register for those to know whether ones * it transmitted were processed or returned. */ - status = IEEE80211_SKB_RXCB(rx->skb); if (cfg80211_rx_mgmt(rx->sdata->dev, status->freq, rx->skb->data, rx->skb->len, @@ -2138,6 +2180,7 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *) rx->skb->data; struct sk_buff *nskb; struct ieee80211_sub_if_data *sdata = rx->sdata; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); if (!ieee80211_is_action(mgmt->frame_control)) return RX_CONTINUE; @@ -2152,7 +2195,7 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) * registration mechanisms, but older ones still use cooked * monitor interfaces so push all frames there. */ - if (!(rx->flags & IEEE80211_MALFORMED_ACTION_FRM) && + if (!(status->rx_flags & IEEE80211_RX_MALFORMED_ACTION_FRM) && (sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) return RX_DROP_MONITOR; @@ -2286,8 +2329,13 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, struct net_device *prev_dev = NULL; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - if (status->flag & RX_FLAG_INTERNAL_CMTR) + /* + * If cooked monitor has been processed already, then + * don't do it again. If not, set the flag. + */ + if (rx->flags & IEEE80211_RX_CMNTR) goto out_free_skb; + rx->flags |= IEEE80211_RX_CMNTR; if (skb_headroom(skb) < sizeof(*rthdr) && pskb_expand_head(skb, sizeof(*rthdr), 0, GFP_ATOMIC)) @@ -2343,12 +2391,8 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, if (prev_dev) { skb->dev = prev_dev; netif_receive_skb(skb); - skb = NULL; - } else - goto out_free_skb; - - status->flag |= RX_FLAG_INTERNAL_CMTR; - return; + return; + } out_free_skb: dev_kfree_skb(skb); @@ -2409,6 +2453,7 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx, * same TID from the same station */ rx->skb = skb; + rx->flags = 0; CALL_RXH(ieee80211_rx_h_decrypt) CALL_RXH(ieee80211_rx_h_check_more_data) @@ -2443,18 +2488,13 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx, } } -static void ieee80211_invoke_rx_handlers(struct ieee80211_sub_if_data *sdata, - struct ieee80211_rx_data *rx, - struct sk_buff *skb) +static void ieee80211_invoke_rx_handlers(struct ieee80211_rx_data *rx) { struct sk_buff_head reorder_release; ieee80211_rx_result res = RX_DROP_MONITOR; __skb_queue_head_init(&reorder_release); - rx->skb = skb; - rx->sdata = sdata; - #define CALL_RXH(rxh) \ do { \ res = rxh(rx); \ @@ -2484,7 +2524,12 @@ static void ieee80211_invoke_rx_handlers(struct ieee80211_sub_if_data *sdata, void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) { struct sk_buff_head frames; - struct ieee80211_rx_data rx = { }; + struct ieee80211_rx_data rx = { + .sta = sta, + .sdata = sta->sdata, + .local = sta->local, + .queue = tid, + }; struct tid_ampdu_rx *tid_agg_rx; tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]); @@ -2493,17 +2538,6 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) __skb_queue_head_init(&frames); - /* construct rx struct */ - rx.sta = sta; - rx.sdata = sta->sdata; - rx.local = sta->local; - rx.queue = tid; - rx.flags |= IEEE80211_RX_RA_MATCH; - - if (unlikely(test_bit(SCAN_HW_SCANNING, &sta->local->scanning) || - test_bit(SCAN_OFF_CHANNEL, &sta->local->scanning))) - rx.flags |= IEEE80211_RX_IN_SCAN; - spin_lock(&tid_agg_rx->reorder_lock); ieee80211_sta_reorder_release(&sta->local->hw, tid_agg_rx, &frames); spin_unlock(&tid_agg_rx->reorder_lock); @@ -2513,10 +2547,10 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) /* main receive path */ -static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, - struct ieee80211_rx_data *rx, +static int prepare_for_handlers(struct ieee80211_rx_data *rx, struct ieee80211_hdr *hdr) { + struct ieee80211_sub_if_data *sdata = rx->sdata; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); u8 *bssid = ieee80211_get_bssid(hdr, skb->len, sdata->vif.type); @@ -2530,7 +2564,7 @@ static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, compare_ether_addr(sdata->vif.addr, hdr->addr1) != 0) { if (!(sdata->dev->flags & IFF_PROMISC)) return 0; - rx->flags &= ~IEEE80211_RX_RA_MATCH; + status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } break; case NL80211_IFTYPE_ADHOC: @@ -2540,15 +2574,15 @@ static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, return 1; } else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) { - if (!(rx->flags & IEEE80211_RX_IN_SCAN)) + if (!(status->rx_flags & IEEE80211_RX_IN_SCAN)) return 0; - rx->flags &= ~IEEE80211_RX_RA_MATCH; + status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } else if (!multicast && compare_ether_addr(sdata->vif.addr, hdr->addr1) != 0) { if (!(sdata->dev->flags & IFF_PROMISC)) return 0; - rx->flags &= ~IEEE80211_RX_RA_MATCH; + status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } else if (!rx->sta) { int rate_idx; if (status->flag & RX_FLAG_HT) @@ -2566,7 +2600,7 @@ static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, if (!(sdata->dev->flags & IFF_PROMISC)) return 0; - rx->flags &= ~IEEE80211_RX_RA_MATCH; + status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } break; case NL80211_IFTYPE_AP_VLAN: @@ -2577,9 +2611,9 @@ static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, return 0; } else if (!ieee80211_bssid_match(bssid, sdata->vif.addr)) { - if (!(rx->flags & IEEE80211_RX_IN_SCAN)) + if (!(status->rx_flags & IEEE80211_RX_IN_SCAN)) return 0; - rx->flags &= ~IEEE80211_RX_RA_MATCH; + status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } break; case NL80211_IFTYPE_WDS: @@ -2588,9 +2622,7 @@ static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, if (compare_ether_addr(sdata->u.wds.remote_addr, hdr->addr2)) return 0; break; - case NL80211_IFTYPE_MONITOR: - case NL80211_IFTYPE_UNSPECIFIED: - case NUM_NL80211_IFTYPES: + default: /* should never get here */ WARN_ON(1); break; @@ -2600,6 +2632,51 @@ static int prepare_for_handlers(struct ieee80211_sub_if_data *sdata, } /* + * This function returns whether or not the SKB + * was destined for RX processing or not, which, + * if consume is true, is equivalent to whether + * or not the skb was consumed. + */ +static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, + struct sk_buff *skb, bool consume) +{ + struct ieee80211_local *local = rx->local; + struct ieee80211_sub_if_data *sdata = rx->sdata; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + struct ieee80211_hdr *hdr = (void *)skb->data; + int prepares; + + rx->skb = skb; + status->rx_flags |= IEEE80211_RX_RA_MATCH; + prepares = prepare_for_handlers(rx, hdr); + + if (!prepares) + return false; + + if (status->flag & RX_FLAG_MMIC_ERROR) { + if (status->rx_flags & IEEE80211_RX_RA_MATCH) + ieee80211_rx_michael_mic_report(hdr, rx); + return false; + } + + if (!consume) { + skb = skb_copy(skb, GFP_ATOMIC); + if (!skb) { + if (net_ratelimit()) + wiphy_debug(local->hw.wiphy, + "failed to copy multicast frame for %s\n", + sdata->name); + return true; + } + + rx->skb = skb; + } + + ieee80211_invoke_rx_handlers(rx); + return true; +} + +/* * This is the actual Rx frames handler. as it blongs to Rx path it must * be called with rcu_read_lock protection. */ @@ -2612,11 +2689,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr; __le16 fc; struct ieee80211_rx_data rx; - int prepares; - struct ieee80211_sub_if_data *prev = NULL; - struct sk_buff *skb_new; - struct sta_info *sta, *tmp; - bool found_sta = false; + struct ieee80211_sub_if_data *prev; + struct sta_info *sta, *tmp, *prev_sta; int err = 0; fc = ((struct ieee80211_hdr *)skb->data)->frame_control; @@ -2629,7 +2703,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (unlikely(test_bit(SCAN_HW_SCANNING, &local->scanning) || test_bit(SCAN_OFF_CHANNEL, &local->scanning))) - rx.flags |= IEEE80211_RX_IN_SCAN; + status->rx_flags |= IEEE80211_RX_IN_SCAN; if (ieee80211_is_mgmt(fc)) err = skb_linearize(skb); @@ -2646,90 +2720,67 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, ieee80211_verify_alignment(&rx); if (ieee80211_is_data(fc)) { + prev_sta = NULL; + for_each_sta_info(local, hdr->addr2, sta, tmp) { - rx.sta = sta; - found_sta = true; - rx.sdata = sta->sdata; - - rx.flags |= IEEE80211_RX_RA_MATCH; - prepares = prepare_for_handlers(rx.sdata, &rx, hdr); - if (prepares) { - if (status->flag & RX_FLAG_MMIC_ERROR) { - if (rx.flags & IEEE80211_RX_RA_MATCH) - ieee80211_rx_michael_mic_report(hdr, &rx); - } else - prev = rx.sdata; - } - } - } - if (!found_sta) { - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata)) + if (!prev_sta) { + prev_sta = sta; continue; + } - if (sdata->vif.type == NL80211_IFTYPE_MONITOR || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - continue; + rx.sta = prev_sta; + rx.sdata = prev_sta->sdata; + ieee80211_prepare_and_rx_handle(&rx, skb, false); - /* - * frame is destined for this interface, but if it's - * not also for the previous one we handle that after - * the loop to avoid copying the SKB once too much - */ + prev_sta = sta; + } - if (!prev) { - prev = sdata; - continue; - } + if (prev_sta) { + rx.sta = prev_sta; + rx.sdata = prev_sta->sdata; - rx.sta = sta_info_get_bss(prev, hdr->addr2); + if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) + return; + } + } - rx.flags |= IEEE80211_RX_RA_MATCH; - prepares = prepare_for_handlers(prev, &rx, hdr); + prev = NULL; - if (!prepares) - goto next; + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(sdata)) + continue; - if (status->flag & RX_FLAG_MMIC_ERROR) { - rx.sdata = prev; - if (rx.flags & IEEE80211_RX_RA_MATCH) - ieee80211_rx_michael_mic_report(hdr, - &rx); - goto next; - } + if (sdata->vif.type == NL80211_IFTYPE_MONITOR || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; - /* - * frame was destined for the previous interface - * so invoke RX handlers for it - */ + /* + * frame is destined for this interface, but if it's + * not also for the previous one we handle that after + * the loop to avoid copying the SKB once too much + */ - skb_new = skb_copy(skb, GFP_ATOMIC); - if (!skb_new) { - if (net_ratelimit()) - wiphy_debug(local->hw.wiphy, - "failed to copy multicast frame for %s\n", - prev->name); - goto next; - } - ieee80211_invoke_rx_handlers(prev, &rx, skb_new); -next: + if (!prev) { prev = sdata; + continue; } - if (prev) { - rx.sta = sta_info_get_bss(prev, hdr->addr2); + rx.sta = sta_info_get_bss(prev, hdr->addr2); + rx.sdata = prev; + ieee80211_prepare_and_rx_handle(&rx, skb, false); - rx.flags |= IEEE80211_RX_RA_MATCH; - prepares = prepare_for_handlers(prev, &rx, hdr); + prev = sdata; + } - if (!prepares) - prev = NULL; - } + if (prev) { + rx.sta = sta_info_get_bss(prev, hdr->addr2); + rx.sdata = prev; + + if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) + return; } - if (prev) - ieee80211_invoke_rx_handlers(prev, &rx, skb); - else - dev_kfree_skb(skb); + + dev_kfree_skb(skb); } /* @@ -2803,6 +2854,8 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) } } + status->rx_flags = 0; + /* * key references and virtual interfaces are protected using RCU * and this requires that we are in a read-side RCU section during diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index d60389b..fb274db 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -242,18 +242,19 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) local->hw_scan_req->n_channels = n_chans; ielen = ieee80211_build_preq_ies(local, (u8 *)local->hw_scan_req->ie, - req->ie, req->ie_len, band); + req->ie, req->ie_len, band, (u32) -1, + 0); local->hw_scan_req->ie_len = ielen; return true; } -static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) +static bool __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, + bool was_hw_scan) { struct ieee80211_local *local = hw_to_local(hw); - bool was_hw_scan; - mutex_lock(&local->mtx); + lockdep_assert_held(&local->mtx); /* * It's ok to abort a not-yet-running scan (that @@ -264,17 +265,13 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) if (WARN_ON(!local->scanning && !aborted)) aborted = true; - if (WARN_ON(!local->scan_req)) { - mutex_unlock(&local->mtx); - return; - } + if (WARN_ON(!local->scan_req)) + return false; - was_hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning); if (was_hw_scan && !aborted && ieee80211_prep_hw_scan(local)) { - ieee80211_queue_delayed_work(&local->hw, - &local->scan_work, 0); - mutex_unlock(&local->mtx); - return; + int rc = drv_hw_scan(local, local->scan_sdata, local->hw_scan_req); + if (rc == 0) + return false; } kfree(local->hw_scan_req); @@ -288,23 +285,25 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) local->scanning = 0; local->scan_channel = NULL; - /* we only have to protect scan_req and hw/sw scan */ - mutex_unlock(&local->mtx); - - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - if (was_hw_scan) - goto done; - - ieee80211_configure_filter(local); + return true; +} - drv_sw_scan_complete(local); +static void __ieee80211_scan_completed_finish(struct ieee80211_hw *hw, + bool was_hw_scan) +{ + struct ieee80211_local *local = hw_to_local(hw); - ieee80211_offchannel_return(local, true); + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + if (!was_hw_scan) { + ieee80211_configure_filter(local); + drv_sw_scan_complete(local); + ieee80211_offchannel_return(local, true); + } - done: mutex_lock(&local->mtx); ieee80211_recalc_idle(local); mutex_unlock(&local->mtx); + ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); ieee80211_mesh_notify_scan_completed(local); @@ -365,6 +364,8 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; int rc; + lockdep_assert_held(&local->mtx); + if (local->scan_req) return -EBUSY; @@ -446,8 +447,8 @@ ieee80211_scan_get_channel_time(struct ieee80211_channel *chan) return IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME; } -static int ieee80211_scan_state_decision(struct ieee80211_local *local, - unsigned long *next_delay) +static void ieee80211_scan_state_decision(struct ieee80211_local *local, + unsigned long *next_delay) { bool associated = false; bool tx_empty = true; @@ -457,12 +458,6 @@ static int ieee80211_scan_state_decision(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata; struct ieee80211_channel *next_chan; - /* if no more bands/channels left, complete scan and advance to the idle state */ - if (local->scan_channel_idx >= local->scan_req->n_channels) { - __ieee80211_scan_completed(&local->hw, false); - return 1; - } - /* * check if at least one STA interface is associated, * check if at least one STA interface has pending tx frames @@ -534,7 +529,6 @@ static int ieee80211_scan_state_decision(struct ieee80211_local *local, } *next_delay = 0; - return 0; } static void ieee80211_scan_state_leave_oper_channel(struct ieee80211_local *local, @@ -650,28 +644,17 @@ void ieee80211_scan_work(struct work_struct *work) container_of(work, struct ieee80211_local, scan_work.work); struct ieee80211_sub_if_data *sdata = local->scan_sdata; unsigned long next_delay = 0; + bool aborted, hw_scan, finish; - if (test_and_clear_bit(SCAN_COMPLETED, &local->scanning)) { - bool aborted; + mutex_lock(&local->mtx); + if (test_and_clear_bit(SCAN_COMPLETED, &local->scanning)) { aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); - __ieee80211_scan_completed(&local->hw, aborted); - return; - } - - mutex_lock(&local->mtx); - if (!sdata || !local->scan_req) { - mutex_unlock(&local->mtx); - return; + goto out_complete; } - if (local->hw_scan_req) { - int rc = drv_hw_scan(local, sdata, local->hw_scan_req); - mutex_unlock(&local->mtx); - if (rc) - __ieee80211_scan_completed(&local->hw, true); - return; - } + if (!sdata || !local->scan_req) + goto out; if (local->scan_req && !local->scanning) { struct cfg80211_scan_request *req = local->scan_req; @@ -681,21 +664,21 @@ void ieee80211_scan_work(struct work_struct *work) local->scan_sdata = NULL; rc = __ieee80211_start_scan(sdata, req); - mutex_unlock(&local->mtx); - - if (rc) - __ieee80211_scan_completed(&local->hw, true); - return; + if (rc) { + /* need to complete scan in cfg80211 */ + local->scan_req = req; + aborted = true; + goto out_complete; + } else + goto out; } - mutex_unlock(&local->mtx); - /* * Avoid re-scheduling when the sdata is going away. */ if (!ieee80211_sdata_running(sdata)) { - __ieee80211_scan_completed(&local->hw, true); - return; + aborted = true; + goto out_complete; } /* @@ -705,8 +688,12 @@ void ieee80211_scan_work(struct work_struct *work) do { switch (local->next_scan_state) { case SCAN_DECISION: - if (ieee80211_scan_state_decision(local, &next_delay)) - return; + /* if no more bands/channels left, complete scan */ + if (local->scan_channel_idx >= local->scan_req->n_channels) { + aborted = false; + goto out_complete; + } + ieee80211_scan_state_decision(local, &next_delay); break; case SCAN_SET_CHANNEL: ieee80211_scan_state_set_channel(local, &next_delay); @@ -724,6 +711,19 @@ void ieee80211_scan_work(struct work_struct *work) } while (next_delay == 0); ieee80211_queue_delayed_work(&local->hw, &local->scan_work, next_delay); + mutex_unlock(&local->mtx); + return; + +out_complete: + hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning); + finish = __ieee80211_scan_completed(&local->hw, aborted, hw_scan); + mutex_unlock(&local->mtx); + if (finish) + __ieee80211_scan_completed_finish(&local->hw, hw_scan); + return; + +out: + mutex_unlock(&local->mtx); } int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, @@ -785,21 +785,40 @@ int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, return ret; } +/* + * Only call this function when a scan can't be queued -- under RTNL. + */ void ieee80211_scan_cancel(struct ieee80211_local *local) { bool abortscan; - - cancel_delayed_work_sync(&local->scan_work); + bool finish = false; /* - * Only call this function when a scan can't be - * queued -- mostly at suspend under RTNL. + * We are only canceling software scan, or deferred scan that was not + * yet really started (see __ieee80211_start_scan ). + * + * Regarding hardware scan: + * - we can not call __ieee80211_scan_completed() as when + * SCAN_HW_SCANNING bit is set this function change + * local->hw_scan_req to operate on 5G band, what race with + * driver which can use local->hw_scan_req + * + * - we can not cancel scan_work since driver can schedule it + * by ieee80211_scan_completed(..., true) to finish scan + * + * Hence low lever driver is responsible for canceling HW scan. */ + mutex_lock(&local->mtx); - abortscan = test_bit(SCAN_SW_SCANNING, &local->scanning) || - (!local->scanning && local->scan_req); + abortscan = local->scan_req && !test_bit(SCAN_HW_SCANNING, &local->scanning); + if (abortscan) + finish = __ieee80211_scan_completed(&local->hw, true, false); mutex_unlock(&local->mtx); - if (abortscan) - __ieee80211_scan_completed(&local->hw, true); + if (abortscan) { + /* The scan is canceled, but stop work from being pending */ + cancel_delayed_work_sync(&local->scan_work); + } + if (finish) + __ieee80211_scan_completed_finish(&local->hw, false); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 687077e..6d8f897 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -125,7 +125,7 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, lockdep_is_held(&local->sta_mtx)); while (sta) { if ((sta->sdata == sdata || - sta->sdata->bss == sdata->bss) && + (sta->sdata->bss && sta->sdata->bss == sdata->bss)) && memcmp(sta->sta.addr, addr, ETH_ALEN) == 0) break; sta = rcu_dereference_check(sta->hnext, @@ -280,7 +280,7 @@ static int sta_info_finish_insert(struct sta_info *sta, bool async) unsigned long flags; int err = 0; - WARN_ON(!mutex_is_locked(&local->sta_mtx)); + lockdep_assert_held(&local->sta_mtx); /* notify driver */ if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) @@ -616,7 +616,7 @@ static int __must_check __sta_info_destroy(struct sta_info *sta) struct ieee80211_sub_if_data *sdata; struct sk_buff *skb; unsigned long flags; - int ret; + int ret, i; might_sleep(); @@ -633,7 +633,7 @@ static int __must_check __sta_info_destroy(struct sta_info *sta) * will be sufficient. */ set_sta_flags(sta, WLAN_STA_BLOCK_BA); - ieee80211_sta_tear_down_BA_sessions(sta); + ieee80211_sta_tear_down_BA_sessions(sta, true); spin_lock_irqsave(&local->sta_lock, flags); ret = sta_info_hash_del(local, sta); @@ -644,10 +644,10 @@ static int __must_check __sta_info_destroy(struct sta_info *sta) if (ret) return ret; - if (sta->key) { - ieee80211_key_free(local, sta->key); - WARN_ON(sta->key); - } + for (i = 0; i < NUM_DEFAULT_KEYS; i++) + ieee80211_key_free(local, sta->gtk[i]); + if (sta->ptk) + ieee80211_key_free(local, sta->ptk); sta->dead = true; @@ -838,13 +838,20 @@ void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, mutex_unlock(&local->sta_mtx); } -struct ieee80211_sta *ieee80211_find_sta_by_hw(struct ieee80211_hw *hw, - const u8 *addr) +struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, + const u8 *addr, + const u8 *localaddr) { struct sta_info *sta, *nxt; - /* Just return a random station ... first in list ... */ + /* + * Just return a random station if localaddr is NULL + * ... first in list. + */ for_each_sta_info(hw_to_local(hw), addr, sta, nxt) { + if (localaddr && + compare_ether_addr(sta->sdata->vif.addr, localaddr) != 0) + continue; if (!sta->uploaded) return NULL; return &sta->sta; @@ -852,7 +859,7 @@ struct ieee80211_sta *ieee80211_find_sta_by_hw(struct ieee80211_hw *hw, return NULL; } -EXPORT_SYMBOL_GPL(ieee80211_find_sta_by_hw); +EXPORT_SYMBOL_GPL(ieee80211_find_sta_by_ifaddr); struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif, const u8 *addr) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 810c5ce..9265aca 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -79,6 +79,7 @@ enum ieee80211_sta_info_flags { * @dialog_token: dialog token for aggregation session * @state: session state (see above) * @stop_initiator: initiator of a session stop + * @tx_stop: TX DelBA frame when stopping * * This structure is protected by RCU and the per-station * spinlock. Assignments to the array holding it must hold @@ -95,6 +96,7 @@ struct tid_ampdu_tx { unsigned long state; u8 dialog_token; u8 stop_initiator; + bool tx_stop; }; /** @@ -197,7 +199,8 @@ enum plink_state { * @hnext: hash table linked list pointer * @local: pointer to the global information * @sdata: virtual interface this station belongs to - * @key: peer key negotiated with this station, if any + * @ptk: peer key negotiated with this station, if any + * @gtk: group keys negotiated with this station, if any * @rate_ctrl: rate control algorithm reference * @rate_ctrl_priv: rate control private per-STA pointer * @last_tx_rate: rate used for last transmit, to report to userspace as @@ -252,7 +255,8 @@ struct sta_info { struct sta_info *hnext; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; - struct ieee80211_key *key; + struct ieee80211_key *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; + struct ieee80211_key *ptk; struct rate_control_ref *rate_ctrl; void *rate_ctrl_priv; spinlock_t lock; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 571b32b..3153c19 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -58,6 +58,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, info->control.vif = &sta->sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING | IEEE80211_TX_INTFL_RETRANSMISSION; + info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; sta->tx_filtered_count++; @@ -175,7 +176,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { /* the HW cannot have attempted that rate */ - if (i >= hw->max_rates) { + if (i >= hw->max_report_rates) { info->status.rates[i].idx = -1; info->status.rates[i].count = 0; } else if (info->status.rates[i].idx >= 0) { @@ -376,7 +377,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) { skb2->dev = prev_dev; - netif_receive_skb(skb2); + netif_rx(skb2); } } @@ -385,7 +386,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) } if (prev_dev) { skb->dev = prev_dev; - netif_receive_skb(skb); + netif_rx(skb); skb = NULL; } rcu_read_unlock(); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index ccf3737..96c5943 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -273,6 +273,9 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) */ return TX_DROP; + if (tx->sdata->vif.type == NL80211_IFTYPE_WDS) + return TX_CONTINUE; + if (tx->sdata->vif.type == NL80211_IFTYPE_MESH_POINT) return TX_CONTINUE; @@ -529,7 +532,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) if (unlikely(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)) tx->key = NULL; - else if (tx->sta && (key = rcu_dereference(tx->sta->key))) + else if (tx->sta && (key = rcu_dereference(tx->sta->ptk))) tx->key = key; else if (ieee80211_is_mgmt(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && @@ -1609,6 +1612,7 @@ static void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, return; } + hdr = (struct ieee80211_hdr *) skb->data; info->control.vif = &sdata->vif; if (ieee80211_vif_is_mesh(&sdata->vif) && diff --git a/net/mac80211/util.c b/net/mac80211/util.c index bd40b11..0b6fc92 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -474,16 +474,10 @@ void ieee80211_iterate_active_interfaces( list_for_each_entry(sdata, &local->interfaces, list) { switch (sdata->vif.type) { - case NUM_NL80211_IFTYPES: - case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_AP_VLAN: continue; - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_WDS: - case NL80211_IFTYPE_MESH_POINT: + default: break; } if (ieee80211_sdata_running(sdata)) @@ -508,16 +502,10 @@ void ieee80211_iterate_active_interfaces_atomic( list_for_each_entry_rcu(sdata, &local->interfaces, list) { switch (sdata->vif.type) { - case NUM_NL80211_IFTYPES: - case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_AP_VLAN: continue; - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_WDS: - case NL80211_IFTYPE_MESH_POINT: + default: break; } if (ieee80211_sdata_running(sdata)) @@ -907,26 +895,34 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, const u8 *ie, size_t ie_len, - enum ieee80211_band band) + enum ieee80211_band band, u32 rate_mask, + u8 channel) { struct ieee80211_supported_band *sband; u8 *pos; size_t offset = 0, noffset; int supp_rates_len, i; + u8 rates[32]; + int num_rates; + int ext_rates_len; sband = local->hw.wiphy->bands[band]; pos = buffer; - supp_rates_len = min_t(int, sband->n_bitrates, 8); + num_rates = 0; + for (i = 0; i < sband->n_bitrates; i++) { + if ((BIT(i) & rate_mask) == 0) + continue; /* skip rate */ + rates[num_rates++] = (u8) (sband->bitrates[i].bitrate / 5); + } + + supp_rates_len = min_t(int, num_rates, 8); *pos++ = WLAN_EID_SUPP_RATES; *pos++ = supp_rates_len; - - for (i = 0; i < supp_rates_len; i++) { - int rate = sband->bitrates[i].bitrate; - *pos++ = (u8) (rate / 5); - } + memcpy(pos, rates, supp_rates_len); + pos += supp_rates_len; /* insert "request information" if in custom IEs */ if (ie && ie_len) { @@ -944,14 +940,18 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, offset = noffset; } - if (sband->n_bitrates > i) { + ext_rates_len = num_rates - supp_rates_len; + if (ext_rates_len > 0) { *pos++ = WLAN_EID_EXT_SUPP_RATES; - *pos++ = sband->n_bitrates - i; + *pos++ = ext_rates_len; + memcpy(pos, rates + supp_rates_len, ext_rates_len); + pos += ext_rates_len; + } - for (; i < sband->n_bitrates; i++) { - int rate = sband->bitrates[i].bitrate; - *pos++ = (u8) (rate / 5); - } + if (channel && sband->band == IEEE80211_BAND_2GHZ) { + *pos++ = WLAN_EID_DS_PARAMS; + *pos++ = 1; + *pos++ = channel; } /* insert custom IEs that go before HT */ @@ -1020,6 +1020,7 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, struct ieee80211_mgmt *mgmt; size_t buf_len; u8 *buf; + u8 chan; /* FIXME: come up with a proper value */ buf = kmalloc(200 + ie_len, GFP_KERNEL); @@ -1029,8 +1030,14 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, return; } + chan = ieee80211_frequency_to_channel( + local->hw.conf.channel->center_freq); + buf_len = ieee80211_build_preq_ies(local, buf, ie, ie_len, - local->hw.conf.channel->band); + local->hw.conf.channel->band, + sdata->rc_rateidx_mask + [local->hw.conf.channel->band], + chan); skb = ieee80211_probereq_get(&local->hw, &sdata->vif, ssid, ssid_len, @@ -1193,6 +1200,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_P2P_GO: WARN_ON(1); break; } @@ -1212,7 +1221,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { - ieee80211_sta_tear_down_BA_sessions(sta); + ieee80211_sta_tear_down_BA_sessions(sta, true); clear_sta_flags(sta, WLAN_STA_BLOCK_BA); } @@ -1288,17 +1297,13 @@ static int check_mgd_smps(struct ieee80211_if_managed *ifmgd, } /* must hold iflist_mtx */ -void ieee80211_recalc_smps(struct ieee80211_local *local, - struct ieee80211_sub_if_data *forsdata) +void ieee80211_recalc_smps(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; enum ieee80211_smps_mode smps_mode = IEEE80211_SMPS_OFF; int count = 0; - if (forsdata) - WARN_ON(!mutex_is_locked(&forsdata->u.mgd.mtx)); - - WARN_ON(!mutex_is_locked(&local->iflist_mtx)); + lockdep_assert_held(&local->iflist_mtx); /* * This function could be improved to handle multiple @@ -1315,18 +1320,8 @@ void ieee80211_recalc_smps(struct ieee80211_local *local, continue; if (sdata->vif.type != NL80211_IFTYPE_STATION) goto set; - if (sdata != forsdata) { - /* - * This nested is ok -- we are holding the iflist_mtx - * so can't get here twice or so. But it's required - * since normally we acquire it first and then the - * iflist_mtx. - */ - mutex_lock_nested(&sdata->u.mgd.mtx, SINGLE_DEPTH_NESTING); - count += check_mgd_smps(&sdata->u.mgd, &smps_mode); - mutex_unlock(&sdata->u.mgd.mtx); - } else - count += check_mgd_smps(&sdata->u.mgd, &smps_mode); + + count += check_mgd_smps(&sdata->u.mgd, &smps_mode); if (count > 1) { smps_mode = IEEE80211_SMPS_OFF; diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index f27484c..2ff6d1e 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -222,7 +222,7 @@ static int ieee80211_wep_decrypt(struct ieee80211_local *local, struct ieee80211_key *key) { u32 klen; - u8 *rc4key; + u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; u8 keyidx; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; unsigned int hdrlen; @@ -245,10 +245,6 @@ static int ieee80211_wep_decrypt(struct ieee80211_local *local, klen = 3 + key->conf.keylen; - rc4key = kmalloc(klen, GFP_ATOMIC); - if (!rc4key) - return -1; - /* Prepend 24-bit IV to RC4 key */ memcpy(rc4key, skb->data + hdrlen, 3); @@ -260,8 +256,6 @@ static int ieee80211_wep_decrypt(struct ieee80211_local *local, len)) ret = -1; - kfree(rc4key); - /* Trim ICV */ skb_trim(skb, skb->len - WEP_ICV_LEN); diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 43882b3..bee230d 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -117,7 +117,7 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) key = &rx->key->conf.key[key_offset]; michael_mic(key, hdr, data, data_len, mic); if (memcmp(mic, data + data_len, MICHAEL_MIC_LEN) != 0 || wpa_test) { - if (!(rx->flags & IEEE80211_RX_RA_MATCH)) + if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) return RX_DROP_UNUSABLE; mac80211_ev_michael_mic_failure(rx->sdata, rx->key->conf.keyidx, diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index d254345..1ea96bcd 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -63,6 +63,7 @@ sctp_snat_handler(struct sk_buff *skb, { sctp_sctphdr_t *sctph; unsigned int sctphoff; + struct sk_buff *iter; __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 @@ -91,8 +92,8 @@ sctp_snat_handler(struct sk_buff *skb, /* Calculate the checksum */ crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff); - 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, iter) + crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter), crc32); crc32 = sctp_end_cksum(crc32); sctph->checksum = crc32; @@ -104,9 +105,9 @@ static int sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp) { - sctp_sctphdr_t *sctph; unsigned int sctphoff; + struct sk_buff *iter; __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 @@ -135,8 +136,8 @@ sctp_dnat_handler(struct sk_buff *skb, /* Calculate the checksum */ crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff); - 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, iter) + crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter), crc32); crc32 = sctp_end_cksum(crc32); sctph->checksum = crc32; @@ -147,9 +148,9 @@ sctp_dnat_handler(struct sk_buff *skb, static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; unsigned int sctphoff; struct sctphdr *sh, _sctph; + struct sk_buff *iter; __le32 cmp; __le32 val; __u32 tmp; @@ -168,9 +169,9 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) cmp = sh->checksum; tmp = sctp_start_cksum((__u8 *) sh, skb_headlen(skb)); - for (; list; list = list->next) - tmp = sctp_update_cksum((__u8 *) list->data, - skb_headlen(list), tmp); + skb_walk_frags(skb, iter) + tmp = sctp_update_cksum((__u8 *) iter->data, + skb_headlen(iter), tmp); val = sctp_end_cksum(tmp); diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 7dcf7a4..8d9e4c9 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -48,15 +48,17 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) { unsigned int off, len; struct nf_ct_ext_type *t; + size_t alloc_size; rcu_read_lock(); t = rcu_dereference(nf_ct_ext_types[id]); BUG_ON(t == NULL); off = ALIGN(sizeof(struct nf_ct_ext), t->align); len = off + t->len; + alloc_size = t->alloc_size; rcu_read_unlock(); - *ext = kzalloc(t->alloc_size, gfp); + *ext = kzalloc(alloc_size, gfp); if (!*ext) return NULL; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 715ce54..bcf47eb 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1418,7 +1418,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, unsigned int msglen, origlen; const char *dptr, *end; s16 diff, tdiff = 0; - int ret; + int ret = NF_ACCEPT; typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust; if (ctinfo != IP_CT_ESTABLISHED && diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c index db65563..4d87bef 100644 --- a/net/netfilter/nf_tproxy_core.c +++ b/net/netfilter/nf_tproxy_core.c @@ -35,7 +35,11 @@ nf_tproxy_destructor(struct sk_buff *skb) int nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) { - if (inet_sk(sk)->transparent) { + bool transparent = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_transparent : + inet_sk(sk)->transparent; + + if (transparent) { skb_orphan(skb); skb->sk = sk; skb->destructor = nf_tproxy_destructor; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 26ed3e8..1781d99 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -547,8 +547,20 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; info.attrs = family->attrbuf; genl_info_net_set(&info, net); + memset(&info.user_ptr, 0, sizeof(info.user_ptr)); - return ops->doit(skb, &info); + if (family->pre_doit) { + err = family->pre_doit(ops, skb, &info); + if (err) + return err; + } + + err = ops->doit(skb, &info); + + if (family->post_doit) + family->post_doit(ops, skb, &info); + + return err; } static void genl_rcv(struct sk_buff *skb) diff --git a/net/phonet/Kconfig b/net/phonet/Kconfig index 6ec7d55..0d9b8a2 100644 --- a/net/phonet/Kconfig +++ b/net/phonet/Kconfig @@ -14,3 +14,15 @@ config PHONET To compile this driver as a module, choose M here: the module will be called phonet. If unsure, say N. + +config PHONET_PIPECTRLR + bool "Phonet Pipe Controller (EXPERIMENTAL)" + depends on PHONET && EXPERIMENTAL + default N + help + The Pipe Controller implementation in Phonet stack to support Pipe + data with Nokia Slim modems like WG2.5 used on ST-Ericsson U8500 + platform. + + This option is incompatible with older Nokia modems. + Say N here unless you really know what you are doing. diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 73aee7f..fd95beb 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -251,6 +251,16 @@ int pn_skb_send(struct sock *sk, struct sk_buff *skb, else if (phonet_address_lookup(net, daddr) == 0) { dev = phonet_device_get(net); skb->pkt_type = PACKET_LOOPBACK; + } else if (pn_sockaddr_get_object(target) == 0) { + /* Resource routing (small race until phonet_rcv()) */ + struct sock *sk = pn_find_sock_by_res(net, + target->spn_resource); + if (sk) { + sock_put(sk); + dev = phonet_device_get(net); + skb->pkt_type = PACKET_LOOPBACK; + } else + dev = phonet_route_output(net, daddr); } else dev = phonet_route_output(net, daddr); @@ -383,6 +393,13 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, goto out; } + /* resource routing */ + if (pn_sockaddr_get_object(&sa) == 0) { + struct sock *sk = pn_find_sock_by_res(net, sa.spn_resource); + if (sk) + return sk_receive_skb(sk, skb, 0); + } + /* check if we are the destination */ if (phonet_address_lookup(net, pn_sockaddr_get_addr(&sa)) == 0) { /* Phonet packet input */ diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 1bd38db..2f03238 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -52,6 +52,19 @@ static int pn_ioctl(struct sock *sk, int cmd, unsigned long arg) answ = skb ? skb->len : 0; release_sock(sk); return put_user(answ, (int __user *)arg); + + case SIOCPNADDRESOURCE: + case SIOCPNDELRESOURCE: { + u32 res; + if (get_user(res, (u32 __user *)arg)) + return -EFAULT; + if (res >= 256) + return -EINVAL; + if (cmd == SIOCPNADDRESOURCE) + return pn_sock_bind_res(sk, res); + else + return pn_sock_unbind_res(sk, res); + } } return -ENOIOCTLCMD; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 04e3419..3e60f2e 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -109,6 +109,210 @@ static int pep_reply(struct sock *sk, struct sk_buff *oskb, } #define PAD 0x00 + +#ifdef CONFIG_PHONET_PIPECTRLR +static u8 pipe_negotiate_fc(u8 *host_fc, u8 *remote_fc, int len) +{ + int i, j; + u8 base_fc, final_fc; + + for (i = 0; i < len; i++) { + base_fc = host_fc[i]; + for (j = 0; j < len; j++) { + if (remote_fc[j] == base_fc) { + final_fc = base_fc; + goto done; + } + } + } + return -EINVAL; + +done: + return final_fc; + +} + +static int pipe_get_flow_info(struct sock *sk, struct sk_buff *skb, + u8 *pref_rx_fc, u8 *req_tx_fc) +{ + struct pnpipehdr *hdr; + u8 n_sb; + + if (!pskb_may_pull(skb, sizeof(*hdr) + 4)) + return -EINVAL; + + hdr = pnp_hdr(skb); + n_sb = hdr->data[4]; + + __skb_pull(skb, sizeof(*hdr) + 4); + while (n_sb > 0) { + u8 type, buf[3], len = sizeof(buf); + u8 *data = pep_get_sb(skb, &type, &len, buf); + + if (data == NULL) + return -EINVAL; + + switch (type) { + case PN_PIPE_SB_REQUIRED_FC_TX: + if (len < 3 || (data[2] | data[3] | data[4]) > 3) + break; + req_tx_fc[0] = data[2]; + req_tx_fc[1] = data[3]; + req_tx_fc[2] = data[4]; + break; + + case PN_PIPE_SB_PREFERRED_FC_RX: + if (len < 3 || (data[2] | data[3] | data[4]) > 3) + break; + pref_rx_fc[0] = data[2]; + pref_rx_fc[1] = data[3]; + pref_rx_fc[2] = data[4]; + break; + + } + n_sb--; + } + return 0; +} + +static int pipe_handler_send_req(struct sock *sk, u8 utid, + u8 msg_id, gfp_t priority) +{ + int len; + struct pnpipehdr *ph; + struct sk_buff *skb; + struct pep_sock *pn = pep_sk(sk); + + static const u8 data[4] = { + PAD, PAD, PAD, PAD, + }; + + switch (msg_id) { + case PNS_PEP_CONNECT_REQ: + len = sizeof(data); + break; + + case PNS_PEP_DISCONNECT_REQ: + case PNS_PEP_ENABLE_REQ: + case PNS_PEP_DISABLE_REQ: + len = 0; + break; + + default: + return -EINVAL; + } + + skb = alloc_skb(MAX_PNPIPE_HEADER + len, priority); + if (!skb) + return -ENOMEM; + skb_set_owner_w(skb, sk); + + skb_reserve(skb, MAX_PNPIPE_HEADER); + if (len) { + __skb_put(skb, len); + skb_copy_to_linear_data(skb, data, len); + } + __skb_push(skb, sizeof(*ph)); + skb_reset_transport_header(skb); + ph = pnp_hdr(skb); + ph->utid = utid; + ph->message_id = msg_id; + ph->pipe_handle = pn->pipe_handle; + ph->error_code = PN_PIPE_NO_ERROR; + + return pn_skb_send(sk, skb, &pn->remote_pep); +} + +static int pipe_handler_send_created_ind(struct sock *sk, + u8 utid, u8 msg_id) +{ + int err_code; + struct pnpipehdr *ph; + struct sk_buff *skb; + + struct pep_sock *pn = pep_sk(sk); + static u8 data[4] = { + 0x03, 0x04, + }; + data[2] = pn->tx_fc; + data[3] = pn->rx_fc; + + /* + * actually, below is number of sub-blocks and not error code. + * Pipe_created_ind message format does not have any + * error code field. However, the Phonet stack will always send + * an error code as part of pnpipehdr. So, use that err_code to + * specify the number of sub-blocks. + */ + err_code = 0x01; + + skb = alloc_skb(MAX_PNPIPE_HEADER + sizeof(data), GFP_ATOMIC); + if (!skb) + return -ENOMEM; + skb_set_owner_w(skb, sk); + + skb_reserve(skb, MAX_PNPIPE_HEADER); + __skb_put(skb, sizeof(data)); + skb_copy_to_linear_data(skb, data, sizeof(data)); + __skb_push(skb, sizeof(*ph)); + skb_reset_transport_header(skb); + ph = pnp_hdr(skb); + ph->utid = utid; + ph->message_id = msg_id; + ph->pipe_handle = pn->pipe_handle; + ph->error_code = err_code; + + return pn_skb_send(sk, skb, &pn->remote_pep); +} + +static int pipe_handler_send_ind(struct sock *sk, u8 utid, u8 msg_id) +{ + int err_code; + struct pnpipehdr *ph; + struct sk_buff *skb; + struct pep_sock *pn = pep_sk(sk); + + /* + * actually, below is a filler. + * Pipe_enabled/disabled_ind message format does not have any + * error code field. However, the Phonet stack will always send + * an error code as part of pnpipehdr. So, use that err_code to + * specify the filler value. + */ + err_code = 0x0; + + skb = alloc_skb(MAX_PNPIPE_HEADER, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + skb_set_owner_w(skb, sk); + + skb_reserve(skb, MAX_PNPIPE_HEADER); + __skb_push(skb, sizeof(*ph)); + skb_reset_transport_header(skb); + ph = pnp_hdr(skb); + ph->utid = utid; + ph->message_id = msg_id; + ph->pipe_handle = pn->pipe_handle; + ph->error_code = err_code; + + return pn_skb_send(sk, skb, &pn->remote_pep); +} + +static int pipe_handler_enable_pipe(struct sock *sk, int enable) +{ + int utid, req; + + if (enable) { + utid = PNS_PIPE_ENABLE_UTID; + req = PNS_PEP_ENABLE_REQ; + } else { + utid = PNS_PIPE_DISABLE_UTID; + req = PNS_PEP_DISABLE_REQ; + } + return pipe_handler_send_req(sk, utid, req, GFP_ATOMIC); +} +#endif + static int pep_accept_conn(struct sock *sk, struct sk_buff *skb) { static const u8 data[20] = { @@ -192,7 +396,11 @@ static int pipe_snd_status(struct sock *sk, u8 type, u8 status, gfp_t priority) ph->data[3] = PAD; ph->data[4] = status; +#ifdef CONFIG_PHONET_PIPECTRLR + return pn_skb_send(sk, skb, &pn->remote_pep); +#else return pn_skb_send(sk, skb, &pipe_srv); +#endif } /* Send our RX flow control information to the sender. @@ -225,12 +433,13 @@ static void pipe_grant_credits(struct sock *sk) static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); - struct pnpipehdr *hdr = pnp_hdr(skb); + struct pnpipehdr *hdr; int wake = 0; if (!pskb_may_pull(skb, sizeof(*hdr) + 4)) return -EINVAL; + hdr = pnp_hdr(skb); if (hdr->data[0] != PN_PEP_TYPE_COMMON) { LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n", (unsigned)hdr->data[0]); @@ -323,11 +532,35 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) sk->sk_state_change(sk); break; +#ifdef CONFIG_PHONET_PIPECTRLR + case PNS_PEP_DISCONNECT_RESP: + pn->pipe_state = PIPE_IDLE; + sk->sk_state = TCP_CLOSE; + break; +#endif + case PNS_PEP_ENABLE_REQ: /* Wait for PNS_PIPE_(ENABLED|REDIRECTED)_IND */ pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC); break; +#ifdef CONFIG_PHONET_PIPECTRLR + case PNS_PEP_ENABLE_RESP: + pn->pipe_state = PIPE_ENABLED; + pipe_handler_send_ind(sk, PNS_PIPE_ENABLED_IND_UTID, + PNS_PIPE_ENABLED_IND); + + if (!pn_flow_safe(pn->tx_fc)) { + atomic_set(&pn->tx_credits, 1); + sk->sk_write_space(sk); + } + if (sk->sk_state == TCP_ESTABLISHED) + break; /* Nothing to do */ + sk->sk_state = TCP_ESTABLISHED; + pipe_grant_credits(sk); + break; +#endif + case PNS_PEP_RESET_REQ: switch (hdr->state_after_reset) { case PN_PIPE_DISABLE: @@ -346,6 +579,17 @@ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC); break; +#ifdef CONFIG_PHONET_PIPECTRLR + case PNS_PEP_DISABLE_RESP: + pn->pipe_state = PIPE_DISABLED; + atomic_set(&pn->tx_credits, 0); + pipe_handler_send_ind(sk, PNS_PIPE_DISABLED_IND_UTID, + PNS_PIPE_DISABLED_IND); + sk->sk_state = TCP_SYN_RECV; + pn->rx_credits = 0; + break; +#endif + case PNS_PEP_CTRL_REQ: if (skb_queue_len(&pn->ctrlreq_queue) >= PNPIPE_CTRLREQ_MAX) { atomic_inc(&sk->sk_drops); @@ -437,6 +681,42 @@ static void pipe_destruct(struct sock *sk) skb_queue_purge(&pn->ctrlreq_queue); } +#ifdef CONFIG_PHONET_PIPECTRLR +static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb) +{ + struct pep_sock *pn = pep_sk(sk); + u8 host_pref_rx_fc[3] = {3, 2, 1}, host_req_tx_fc[3] = {3, 2, 1}; + u8 remote_pref_rx_fc[3], remote_req_tx_fc[3]; + u8 negotiated_rx_fc, negotiated_tx_fc; + int ret; + + pipe_get_flow_info(sk, skb, remote_pref_rx_fc, + remote_req_tx_fc); + negotiated_tx_fc = pipe_negotiate_fc(remote_req_tx_fc, + host_pref_rx_fc, + sizeof(host_pref_rx_fc)); + negotiated_rx_fc = pipe_negotiate_fc(host_req_tx_fc, + remote_pref_rx_fc, + sizeof(host_pref_rx_fc)); + + pn->pipe_state = PIPE_DISABLED; + sk->sk_state = TCP_SYN_RECV; + sk->sk_backlog_rcv = pipe_do_rcv; + sk->sk_destruct = pipe_destruct; + pn->rx_credits = 0; + pn->rx_fc = negotiated_rx_fc; + pn->tx_fc = negotiated_tx_fc; + sk->sk_state_change(sk); + + ret = pipe_handler_send_created_ind(sk, + PNS_PIPE_CREATED_IND_UTID, + PNS_PIPE_CREATED_IND + ); + + return ret; +} +#endif + static int pep_connreq_rcv(struct sock *sk, struct sk_buff *skb) { struct sock *newsk; @@ -600,6 +880,12 @@ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb) err = pep_connreq_rcv(sk, skb); break; +#ifdef CONFIG_PHONET_PIPECTRLR + case PNS_PEP_CONNECT_RESP: + err = pep_connresp_rcv(sk, skb); + break; +#endif + case PNS_PEP_DISCONNECT_REQ: pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC); break; @@ -620,6 +906,28 @@ drop: return err; } +static int pipe_do_remove(struct sock *sk) +{ + struct pep_sock *pn = pep_sk(sk); + struct pnpipehdr *ph; + struct sk_buff *skb; + + skb = alloc_skb(MAX_PNPIPE_HEADER, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + skb_reserve(skb, MAX_PNPIPE_HEADER); + __skb_push(skb, sizeof(*ph)); + skb_reset_transport_header(skb); + ph = pnp_hdr(skb); + ph->utid = 0; + ph->message_id = PNS_PIPE_REMOVE_REQ; + ph->pipe_handle = pn->pipe_handle; + ph->data[0] = PAD; + + return pn_skb_send(sk, skb, &pipe_srv); +} + /* associated socket ceases to exist */ static void pep_sock_close(struct sock *sk, long timeout) { @@ -638,7 +946,22 @@ static void pep_sock_close(struct sock *sk, long timeout) sk_for_each_safe(sknode, p, n, &pn->ackq) sk_del_node_init(sknode); sk->sk_state = TCP_CLOSE; + } else if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED)) + /* Forcefully remove dangling Phonet pipe */ + pipe_do_remove(sk); + +#ifdef CONFIG_PHONET_PIPECTRLR + if (pn->pipe_state != PIPE_IDLE) { + /* send pep disconnect request */ + pipe_handler_send_req(sk, + PNS_PEP_DISCONNECT_UTID, PNS_PEP_DISCONNECT_REQ, + GFP_KERNEL); + + pn->pipe_state = PIPE_IDLE; + sk->sk_state = TCP_CLOSE; } +#endif + ifindex = pn->ifindex; pn->ifindex = 0; release_sock(sk); @@ -715,6 +1038,20 @@ out: return newsk; } +#ifdef CONFIG_PHONET_PIPECTRLR +static int pep_sock_connect(struct sock *sk, struct sockaddr *addr, int len) +{ + struct pep_sock *pn = pep_sk(sk); + struct sockaddr_pn *spn = (struct sockaddr_pn *)addr; + + memcpy(&pn->remote_pep, spn, sizeof(struct sockaddr_pn)); + + return pipe_handler_send_req(sk, + PNS_PEP_CONNECT_UTID, PNS_PEP_CONNECT_REQ, + GFP_ATOMIC); +} +#endif + static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct pep_sock *pn = pep_sk(sk); @@ -766,6 +1103,18 @@ static int pep_setsockopt(struct sock *sk, int level, int optname, lock_sock(sk); switch (optname) { +#ifdef CONFIG_PHONET_PIPECTRLR + case PNPIPE_PIPE_HANDLE: + if (val) { + if (pn->pipe_state > PIPE_IDLE) { + err = -EFAULT; + break; + } + pn->pipe_handle = val; + break; + } +#endif + case PNPIPE_ENCAP: if (val && val != PNPIPE_ENCAP_IP) { err = -EINVAL; @@ -791,6 +1140,17 @@ static int pep_setsockopt(struct sock *sk, int level, int optname, err = 0; } goto out_norel; + +#ifdef CONFIG_PHONET_PIPECTRLR + case PNPIPE_ENABLE: + if (pn->pipe_state <= PIPE_IDLE) { + err = -ENOTCONN; + break; + } + err = pipe_handler_enable_pipe(sk, val); + break; +#endif + default: err = -ENOPROTOOPT; } @@ -815,9 +1175,19 @@ static int pep_getsockopt(struct sock *sk, int level, int optname, case PNPIPE_ENCAP: val = pn->ifindex ? PNPIPE_ENCAP_IP : PNPIPE_ENCAP_NONE; break; + case PNPIPE_IFINDEX: val = pn->ifindex; break; + +#ifdef CONFIG_PHONET_PIPECTRLR + case PNPIPE_ENABLE: + if (pn->pipe_state <= PIPE_IDLE) + return -ENOTCONN; + val = pn->pipe_state != PIPE_DISABLED; + break; +#endif + default: return -ENOPROTOOPT; } @@ -852,11 +1222,16 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) } else ph->message_id = PNS_PIPE_DATA; ph->pipe_handle = pn->pipe_handle; - +#ifdef CONFIG_PHONET_PIPECTRLR + err = pn_skb_send(sk, skb, &pn->remote_pep); +#else err = pn_skb_send(sk, skb, &pipe_srv); +#endif + if (err && pn_flow_safe(pn->tx_fc)) atomic_inc(&pn->tx_credits); return err; + } static int pep_sendmsg(struct kiocb *iocb, struct sock *sk, @@ -1048,6 +1423,8 @@ static void pep_sock_unhash(struct sock *sk) struct sock *skparent = NULL; lock_sock(sk); + +#ifndef CONFIG_PHONET_PIPECTRLR if ((1 << sk->sk_state) & ~(TCPF_CLOSE|TCPF_LISTEN)) { skparent = pn->listener; release_sock(sk); @@ -1057,6 +1434,7 @@ static void pep_sock_unhash(struct sock *sk) sk_del_node_init(sk); sk = skparent; } +#endif /* Unhash a listening sock only when it is closed * and all of its active connected pipes are closed. */ if (hlist_empty(&pn->hlist)) @@ -1070,6 +1448,9 @@ static void pep_sock_unhash(struct sock *sk) static struct proto pep_proto = { .close = pep_sock_close, .accept = pep_sock_accept, +#ifdef CONFIG_PHONET_PIPECTRLR + .connect = pep_sock_connect, +#endif .ioctl = pep_ioctl, .init = pep_init, .setsockopt = pep_setsockopt, diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index d0a4294..947038d 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -373,6 +373,7 @@ int __init phonet_device_init(void) if (err) return err; + proc_net_fops_create(&init_net, "pnresource", 0, &pn_res_seq_fops); register_netdevice_notifier(&phonet_device_notifier); err = phonet_netlink_register(); if (err) @@ -385,6 +386,7 @@ void phonet_device_exit(void) rtnl_unregister_all(PF_PHONET); unregister_netdevice_notifier(&phonet_device_notifier); unregister_pernet_device(&phonet_net_ops); + proc_net_remove(&init_net, "pnresource"); } int phonet_route_add(struct net_device *dev, u8 daddr) diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 7c91f73..25f746d 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -158,6 +158,7 @@ void pn_sock_unhash(struct sock *sk) spin_lock_bh(&pnsocks.lock); sk_del_node_init(sk); spin_unlock_bh(&pnsocks.lock); + pn_sock_unbind_all_res(sk); } EXPORT_SYMBOL(pn_sock_unhash); @@ -224,6 +225,101 @@ static int pn_socket_autobind(struct socket *sock) return 0; /* socket was already bound */ } +#ifdef CONFIG_PHONET_PIPECTRLR +static int pn_socket_connect(struct socket *sock, struct sockaddr *addr, + int len, int flags) +{ + struct sock *sk = sock->sk; + struct sockaddr_pn *spn = (struct sockaddr_pn *)addr; + long timeo; + int err; + + if (len < sizeof(struct sockaddr_pn)) + return -EINVAL; + if (spn->spn_family != AF_PHONET) + return -EAFNOSUPPORT; + + lock_sock(sk); + + switch (sock->state) { + case SS_UNCONNECTED: + sk->sk_state = TCP_CLOSE; + break; + case SS_CONNECTING: + switch (sk->sk_state) { + case TCP_SYN_RECV: + sock->state = SS_CONNECTED; + err = -EISCONN; + goto out; + case TCP_CLOSE: + err = -EALREADY; + if (flags & O_NONBLOCK) + goto out; + goto wait_connect; + } + break; + case SS_CONNECTED: + switch (sk->sk_state) { + case TCP_SYN_RECV: + err = -EISCONN; + goto out; + case TCP_CLOSE: + sock->state = SS_UNCONNECTED; + break; + } + break; + case SS_DISCONNECTING: + case SS_FREE: + break; + } + sk->sk_state = TCP_CLOSE; + sk_stream_kill_queues(sk); + + sock->state = SS_CONNECTING; + err = sk->sk_prot->connect(sk, addr, len); + if (err < 0) { + sock->state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; + goto out; + } + + err = -EINPROGRESS; +wait_connect: + if (sk->sk_state != TCP_SYN_RECV && (flags & O_NONBLOCK)) + goto out; + + timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); + release_sock(sk); + + err = -ERESTARTSYS; + timeo = wait_event_interruptible_timeout(*sk_sleep(sk), + sk->sk_state != TCP_CLOSE, + timeo); + + lock_sock(sk); + if (timeo < 0) + goto out; /* -ERESTARTSYS */ + + err = -ETIMEDOUT; + if (timeo == 0 && sk->sk_state != TCP_SYN_RECV) + goto out; + + if (sk->sk_state != TCP_SYN_RECV) { + sock->state = SS_UNCONNECTED; + err = sock_error(sk); + if (!err) + err = -ECONNREFUSED; + goto out; + } + sock->state = SS_CONNECTED; + err = 0; + +out: + release_sock(sk); + return err; +} +#endif + static int pn_socket_accept(struct socket *sock, struct socket *newsock, int flags) { @@ -392,7 +488,11 @@ const struct proto_ops phonet_stream_ops = { .owner = THIS_MODULE, .release = pn_socket_release, .bind = pn_socket_bind, +#ifdef CONFIG_PHONET_PIPECTRLR + .connect = pn_socket_connect, +#else .connect = sock_no_connect, +#endif .socketpair = sock_no_socketpair, .accept = pn_socket_accept, .getname = pn_socket_getname, @@ -565,3 +665,188 @@ const struct file_operations pn_sock_seq_fops = { .release = seq_release_net, }; #endif + +static struct { + struct sock *sk[256]; +} pnres; + +/* + * Find and hold socket based on resource. + */ +struct sock *pn_find_sock_by_res(struct net *net, u8 res) +{ + struct sock *sk; + + if (!net_eq(net, &init_net)) + return NULL; + + rcu_read_lock(); + sk = rcu_dereference(pnres.sk[res]); + if (sk) + sock_hold(sk); + rcu_read_unlock(); + return sk; +} + +static DEFINE_MUTEX(resource_mutex); + +int pn_sock_bind_res(struct sock *sk, u8 res) +{ + int ret = -EADDRINUSE; + + if (!net_eq(sock_net(sk), &init_net)) + return -ENOIOCTLCMD; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (pn_socket_autobind(sk->sk_socket)) + return -EAGAIN; + + mutex_lock(&resource_mutex); + if (pnres.sk[res] == NULL) { + sock_hold(sk); + rcu_assign_pointer(pnres.sk[res], sk); + ret = 0; + } + mutex_unlock(&resource_mutex); + return ret; +} + +int pn_sock_unbind_res(struct sock *sk, u8 res) +{ + int ret = -ENOENT; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&resource_mutex); + if (pnres.sk[res] == sk) { + rcu_assign_pointer(pnres.sk[res], NULL); + ret = 0; + } + mutex_unlock(&resource_mutex); + + if (ret == 0) { + synchronize_rcu(); + sock_put(sk); + } + return ret; +} + +void pn_sock_unbind_all_res(struct sock *sk) +{ + unsigned res, match = 0; + + mutex_lock(&resource_mutex); + for (res = 0; res < 256; res++) { + if (pnres.sk[res] == sk) { + rcu_assign_pointer(pnres.sk[res], NULL); + match++; + } + } + mutex_unlock(&resource_mutex); + + if (match == 0) + return; + synchronize_rcu(); + while (match > 0) { + sock_put(sk); + match--; + } +} + +#ifdef CONFIG_PROC_FS +static struct sock **pn_res_get_idx(struct seq_file *seq, loff_t pos) +{ + struct net *net = seq_file_net(seq); + unsigned i; + + if (!net_eq(net, &init_net)) + return NULL; + + for (i = 0; i < 256; i++) { + if (pnres.sk[i] == NULL) + continue; + if (!pos) + return pnres.sk + i; + pos--; + } + return NULL; +} + +static struct sock **pn_res_get_next(struct seq_file *seq, struct sock **sk) +{ + struct net *net = seq_file_net(seq); + unsigned i; + + BUG_ON(!net_eq(net, &init_net)); + + for (i = (sk - pnres.sk) + 1; i < 256; i++) + if (pnres.sk[i]) + return pnres.sk + i; + return NULL; +} + +static void *pn_res_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(resource_mutex) +{ + mutex_lock(&resource_mutex); + return *pos ? pn_res_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; +} + +static void *pn_res_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct sock **sk; + + if (v == SEQ_START_TOKEN) + sk = pn_res_get_idx(seq, 0); + else + sk = pn_res_get_next(seq, v); + (*pos)++; + return sk; +} + +static void pn_res_seq_stop(struct seq_file *seq, void *v) + __releases(resource_mutex) +{ + mutex_unlock(&resource_mutex); +} + +static int pn_res_seq_show(struct seq_file *seq, void *v) +{ + int len; + + if (v == SEQ_START_TOKEN) + seq_printf(seq, "%s%n", "rs uid inode", &len); + else { + struct sock **psk = v; + struct sock *sk = *psk; + + seq_printf(seq, "%02X %5d %lu%n", + (int) (psk - pnres.sk), sock_i_uid(sk), + sock_i_ino(sk), &len); + } + seq_printf(seq, "%*s\n", 63 - len, ""); + return 0; +} + +static const struct seq_operations pn_res_seq_ops = { + .start = pn_res_seq_start, + .next = pn_res_seq_next, + .stop = pn_res_seq_stop, + .show = pn_res_seq_show, +}; + +static int pn_res_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &pn_res_seq_ops, + sizeof(struct seq_net_private)); +} + +const struct file_operations pn_res_seq_fops = { + .owner = THIS_MODULE, + .open = pn_res_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; +#endif diff --git a/net/rds/connection.c b/net/rds/connection.c index 870992e..9334d89 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -88,7 +88,7 @@ static struct rds_connection *rds_conn_lookup(struct hlist_head *head, * and receiving over this connection again in the future. It is up to * the transport to have serialized this call with its send and recv. */ -void rds_conn_reset(struct rds_connection *conn) +static void rds_conn_reset(struct rds_connection *conn) { rdsdebug("connection %pI4 to %pI4 reset\n", &conn->c_laddr, &conn->c_faddr); diff --git a/net/rds/ib.c b/net/rds/ib.c index b12a395..4123967 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -42,7 +42,7 @@ #include "rds.h" #include "ib.h" -unsigned int fmr_pool_size = RDS_FMR_POOL_SIZE; +static unsigned int fmr_pool_size = RDS_FMR_POOL_SIZE; unsigned int fmr_message_size = RDS_FMR_SIZE + 1; /* +1 allows for unaligned MRs */ unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT; @@ -65,7 +65,7 @@ struct list_head rds_ib_devices; DEFINE_SPINLOCK(ib_nodev_conns_lock); LIST_HEAD(ib_nodev_conns); -void rds_ib_nodev_connect(void) +static void rds_ib_nodev_connect(void) { struct rds_ib_connection *ic; @@ -75,7 +75,7 @@ void rds_ib_nodev_connect(void) spin_unlock(&ib_nodev_conns_lock); } -void rds_ib_dev_shutdown(struct rds_ib_device *rds_ibdev) +static void rds_ib_dev_shutdown(struct rds_ib_device *rds_ibdev) { struct rds_ib_connection *ic; unsigned long flags; @@ -118,7 +118,7 @@ void rds_ib_dev_put(struct rds_ib_device *rds_ibdev) queue_work(rds_wq, &rds_ibdev->free_work); } -void rds_ib_add_one(struct ib_device *device) +static void rds_ib_add_one(struct ib_device *device) { struct rds_ib_device *rds_ibdev; struct ib_device_attr *dev_attr; @@ -229,7 +229,7 @@ struct rds_ib_device *rds_ib_get_client_data(struct ib_device *device) * * This can be called at any time and can be racing with any other RDS path. */ -void rds_ib_remove_one(struct ib_device *device) +static void rds_ib_remove_one(struct ib_device *device) { struct rds_ib_device *rds_ibdev; diff --git a/net/rds/ib.h b/net/rds/ib.h index 7ad3d57..e34ad03 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -265,13 +265,10 @@ static inline void rds_ib_dma_sync_sg_for_device(struct ib_device *dev, /* ib.c */ extern struct rds_transport rds_ib_transport; -extern void rds_ib_add_one(struct ib_device *device); -extern void rds_ib_remove_one(struct ib_device *device); struct rds_ib_device *rds_ib_get_client_data(struct ib_device *device); void rds_ib_dev_put(struct rds_ib_device *rds_ibdev); extern struct ib_client rds_ib_client; -extern unsigned int fmr_pool_size; extern unsigned int fmr_message_size; extern unsigned int rds_ib_retry_count; @@ -374,6 +371,5 @@ extern unsigned long rds_ib_sysctl_max_unsig_wrs; extern unsigned long rds_ib_sysctl_max_unsig_bytes; extern unsigned long rds_ib_sysctl_max_recv_allocation; extern unsigned int rds_ib_sysctl_flow_control; -extern ctl_table rds_ib_sysctl_table[]; #endif diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index bc3dbc1..ee369d2 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -521,7 +521,6 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, err = rds_ib_setup_qp(conn); if (err) { rds_ib_conn_error(conn, "rds_ib_setup_qp failed (%d)\n", err); - mutex_unlock(&conn->c_cm_lock); goto out; } diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 8f6e221..18a833c 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -38,7 +38,7 @@ #include "ib.h" #include "xlist.h" -struct workqueue_struct *rds_ib_fmr_wq; +static struct workqueue_struct *rds_ib_fmr_wq; static DEFINE_PER_CPU(unsigned long, clean_list_grace); #define CLEAN_LIST_BUSY_BIT 0 @@ -171,9 +171,9 @@ void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *con BUG_ON(list_empty(&ic->ib_node)); list_del(&ic->ib_node); - spin_lock_irq(&rds_ibdev->spinlock); + spin_lock(&rds_ibdev->spinlock); list_add_tail(&ic->ib_node, &rds_ibdev->conn_list); - spin_unlock_irq(&rds_ibdev->spinlock); + spin_unlock(&rds_ibdev->spinlock); spin_unlock_irq(&ib_nodev_conns_lock); ic->rds_ibdev = rds_ibdev; diff --git a/net/rds/ib_sysctl.c b/net/rds/ib_sysctl.c index fc3da37..1253b00 100644 --- a/net/rds/ib_sysctl.c +++ b/net/rds/ib_sysctl.c @@ -61,7 +61,7 @@ static unsigned long rds_ib_sysctl_max_unsig_wr_max = 64; */ unsigned int rds_ib_sysctl_flow_control = 0; -ctl_table rds_ib_sysctl_table[] = { +static ctl_table rds_ib_sysctl_table[] = { { .procname = "max_send_wr", .data = &rds_ib_sysctl_max_send_wr, diff --git a/net/rds/iw.c b/net/rds/iw.c index 56808ca..5a9676f 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -56,7 +56,7 @@ struct list_head rds_iw_devices; DEFINE_SPINLOCK(iw_nodev_conns_lock); LIST_HEAD(iw_nodev_conns); -void rds_iw_add_one(struct ib_device *device) +static void rds_iw_add_one(struct ib_device *device) { struct rds_iw_device *rds_iwdev; struct ib_device_attr *dev_attr; @@ -124,7 +124,7 @@ free_attr: kfree(dev_attr); } -void rds_iw_remove_one(struct ib_device *device) +static void rds_iw_remove_one(struct ib_device *device) { struct rds_iw_device *rds_iwdev; struct rds_iw_cm_id *i_cm_id, *next; diff --git a/net/rds/iw.h b/net/rds/iw.h index 543e665..9015192 100644 --- a/net/rds/iw.h +++ b/net/rds/iw.h @@ -268,8 +268,6 @@ static inline u32 rds_iw_local_dma_lkey(struct rds_iw_connection *ic) /* ib.c */ extern struct rds_transport rds_iw_transport; -extern void rds_iw_add_one(struct ib_device *device); -extern void rds_iw_remove_one(struct ib_device *device); extern struct ib_client rds_iw_client; extern unsigned int fastreg_pool_size; @@ -318,7 +316,6 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents, void rds_iw_sync_mr(void *trans_private, int dir); void rds_iw_free_mr(void *trans_private, int invalidate); void rds_iw_flush_mrs(void); -void rds_iw_remove_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_id); /* ib_recv.c */ int rds_iw_recv_init(void); @@ -378,7 +375,6 @@ extern unsigned long rds_iw_sysctl_max_unsig_wrs; extern unsigned long rds_iw_sysctl_max_unsig_bytes; extern unsigned long rds_iw_sysctl_max_recv_allocation; extern unsigned int rds_iw_sysctl_flow_control; -extern ctl_table rds_iw_sysctl_table[]; /* * Helper functions for getting/setting the header and data SGEs in diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index 4e152e2..59509e9 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -157,7 +157,8 @@ static int rds_iw_add_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id * return 0; } -void rds_iw_remove_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_id) +static void rds_iw_remove_cm_id(struct rds_iw_device *rds_iwdev, + struct rdma_cm_id *cm_id) { struct rds_iw_cm_id *i_cm_id; @@ -206,9 +207,9 @@ void rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *con BUG_ON(list_empty(&ic->iw_node)); list_del(&ic->iw_node); - spin_lock_irq(&rds_iwdev->spinlock); + spin_lock(&rds_iwdev->spinlock); list_add_tail(&ic->iw_node, &rds_iwdev->conn_list); - spin_unlock_irq(&rds_iwdev->spinlock); + spin_unlock(&rds_iwdev->spinlock); spin_unlock_irq(&iw_nodev_conns_lock); ic->rds_iwdev = rds_iwdev; diff --git a/net/rds/iw_sysctl.c b/net/rds/iw_sysctl.c index 23e3a9a..e2e4717 100644 --- a/net/rds/iw_sysctl.c +++ b/net/rds/iw_sysctl.c @@ -55,7 +55,7 @@ static unsigned long rds_iw_sysctl_max_unsig_bytes_max = ~0UL; unsigned int rds_iw_sysctl_flow_control = 1; -ctl_table rds_iw_sysctl_table[] = { +static ctl_table rds_iw_sysctl_table[] = { { .procname = "max_send_wr", .data = &rds_iw_sysctl_max_send_wr, diff --git a/net/rds/message.c b/net/rds/message.c index 84f937f..a84545d 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -106,8 +106,8 @@ void rds_message_populate_header(struct rds_header *hdr, __be16 sport, } EXPORT_SYMBOL_GPL(rds_message_populate_header); -int rds_message_add_extension(struct rds_header *hdr, - unsigned int type, const void *data, unsigned int len) +int rds_message_add_extension(struct rds_header *hdr, unsigned int type, + const void *data, unsigned int len) { unsigned int ext_len = sizeof(u8) + len; unsigned char *dst; @@ -177,26 +177,6 @@ none: return RDS_EXTHDR_NONE; } -int rds_message_add_version_extension(struct rds_header *hdr, unsigned int version) -{ - struct rds_ext_header_version ext_hdr; - - ext_hdr.h_version = cpu_to_be32(version); - return rds_message_add_extension(hdr, RDS_EXTHDR_VERSION, &ext_hdr, sizeof(ext_hdr)); -} - -int rds_message_get_version_extension(struct rds_header *hdr, unsigned int *version) -{ - struct rds_ext_header_version ext_hdr; - unsigned int pos = 0, len = sizeof(ext_hdr); - - /* We assume the version extension is the only one present */ - if (rds_message_next_extension(hdr, &pos, &ext_hdr, &len) != RDS_EXTHDR_VERSION) - return 0; - *version = be32_to_cpu(ext_hdr.h_version); - return 1; -} - int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 offset) { struct rds_ext_header_rdma_dest ext_hdr; diff --git a/net/rds/page.c b/net/rds/page.c index 5e44f5a..a3e2e0a 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -40,7 +40,8 @@ struct rds_page_remainder { unsigned long r_offset; }; -DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, + rds_page_remainders); /* * returns 0 on success or -errno on failure. diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 4806467..1a41deb 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -522,7 +522,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct rds_rdma_args *args; struct rds_iovec vec; struct rm_rdma_op *op = &rm->rdma; - unsigned int nr_pages; + int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; struct rds_iovec __user *local_vec; diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index e6ed10a..4195a05 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -207,7 +207,7 @@ static void rds_rdma_listen_stop(void) } } -int rds_rdma_init(void) +static int rds_rdma_init(void) { int ret; @@ -234,7 +234,7 @@ out: } module_init(rds_rdma_init); -void rds_rdma_exit(void) +static void rds_rdma_exit(void) { /* stop listening first to ensure no new connections are attempted */ rds_rdma_listen_stop(); diff --git a/net/rds/rdma_transport.h b/net/rds/rdma_transport.h index 2f2c7d9..faba4e3 100644 --- a/net/rds/rdma_transport.h +++ b/net/rds/rdma_transport.h @@ -11,10 +11,6 @@ int rds_rdma_conn_connect(struct rds_connection *conn); int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); -/* from rdma_transport.c */ -int rds_rdma_init(void); -void rds_rdma_exit(void); - /* from ib.c */ extern struct rds_transport rds_ib_transport; int rds_ib_init(void); diff --git a/net/rds/rds.h b/net/rds/rds.h index 8103dcf..9542449 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -619,7 +619,6 @@ struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp); void rds_conn_shutdown(struct rds_connection *conn); void rds_conn_destroy(struct rds_connection *conn); -void rds_conn_reset(struct rds_connection *conn); void rds_conn_drop(struct rds_connection *conn); void rds_conn_connect_if_down(struct rds_connection *conn); void rds_for_each_conn_info(struct socket *sock, unsigned int len, @@ -668,8 +667,6 @@ int rds_message_add_extension(struct rds_header *hdr, unsigned int type, const void *data, unsigned int len); int rds_message_next_extension(struct rds_header *hdr, unsigned int *pos, void *buf, unsigned int *buflen); -int rds_message_add_version_extension(struct rds_header *hdr, unsigned int version); -int rds_message_get_version_extension(struct rds_header *hdr, unsigned int *version); int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 offset); int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iovec *first_iov, size_t size); @@ -706,7 +703,6 @@ void rds_page_exit(void); /* recv.c */ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, __be32 saddr); -void rds_inc_addref(struct rds_incoming *inc); void rds_inc_put(struct rds_incoming *inc); void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, struct rds_incoming *inc, gfp_t gfp, enum km_type km); @@ -728,7 +724,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest); typedef int (*is_acked_func)(struct rds_message *rm, uint64_t ack); void rds_send_drop_acked(struct rds_connection *conn, u64 ack, is_acked_func is_acked); -void rds_send_remove_from_sock(struct list_head *messages, int status); int rds_send_pong(struct rds_connection *conn, __be16 dport); struct rds_message *rds_send_get_message(struct rds_connection *, struct rm_rdma_op *); diff --git a/net/rds/recv.c b/net/rds/recv.c index 68800f0..596689e 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -48,12 +48,11 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, } EXPORT_SYMBOL_GPL(rds_inc_init); -void rds_inc_addref(struct rds_incoming *inc) +static void rds_inc_addref(struct rds_incoming *inc) { rdsdebug("addref inc %p ref %d\n", inc, atomic_read(&inc->i_refcount)); atomic_inc(&inc->i_refcount); } -EXPORT_SYMBOL_GPL(rds_inc_addref); void rds_inc_put(struct rds_incoming *inc) { diff --git a/net/rds/send.c b/net/rds/send.c index 9b951a0..0bc9db1 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -52,6 +52,8 @@ static int send_batch_count = 64; module_param(send_batch_count, int, 0444); MODULE_PARM_DESC(send_batch_count, " batch factor when working the send queue"); +static void rds_send_remove_from_sock(struct list_head *messages, int status); + /* * Reset the send state. Callers must ensure that this doesn't race with * rds_send_xmit(). @@ -555,7 +557,7 @@ EXPORT_SYMBOL_GPL(rds_send_get_message); * removing the messages from the 'messages' list regardless of if it found * the messages on the socket list or not. */ -void rds_send_remove_from_sock(struct list_head *messages, int status) +static void rds_send_remove_from_sock(struct list_head *messages, int status) { unsigned long flags; struct rds_sock *rs = NULL; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index eeb08e6..08a8c6c 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -41,7 +41,7 @@ /* only for info exporting */ static DEFINE_SPINLOCK(rds_tcp_tc_list_lock); static LIST_HEAD(rds_tcp_tc_list); -unsigned int rds_tcp_tc_count; +static unsigned int rds_tcp_tc_count; /* Track rds_tcp_connection structs so they can be cleaned up */ static DEFINE_SPINLOCK(rds_tcp_conn_lock); @@ -243,7 +243,7 @@ static void rds_tcp_destroy_conns(void) } } -void rds_tcp_exit(void) +static void rds_tcp_exit(void) { rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); rds_tcp_listen_stop(); @@ -274,7 +274,7 @@ struct rds_transport rds_tcp_transport = { .t_prefer_loopback = 1, }; -int rds_tcp_init(void) +static int rds_tcp_init(void) { int ret; diff --git a/net/rds/tcp.h b/net/rds/tcp.h index f5e6f7b..9cf2927 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -43,8 +43,6 @@ struct rds_tcp_statistics { }; /* tcp.c */ -int rds_tcp_init(void); -void rds_tcp_exit(void); void rds_tcp_tune(struct socket *sock); void rds_tcp_nonagle(struct socket *sock); void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index a65ee78..af95c8e 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -43,7 +43,7 @@ void rds_tcp_state_change(struct sock *sk) struct rds_connection *conn; struct rds_tcp_connection *tc; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (!conn) { state_change = sk->sk_state_change; @@ -68,7 +68,7 @@ void rds_tcp_state_change(struct sock *sk) break; } out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); state_change(sk); } diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index ae27869..8b5cc4a 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -114,7 +114,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) rdsdebug("listen data ready sk %p\n", sk); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ready = sk->sk_user_data; if (!ready) { /* check for teardown race */ ready = sk->sk_data_ready; @@ -131,7 +131,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) queue_work(rds_wq, &rds_tcp_listen_work); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); ready(sk, bytes); } diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index 7017f3a..78205e2 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -272,7 +272,8 @@ out: } /* the caller has to hold the sock lock */ -int rds_tcp_read_sock(struct rds_connection *conn, gfp_t gfp, enum km_type km) +static int rds_tcp_read_sock(struct rds_connection *conn, gfp_t gfp, + enum km_type km) { struct rds_tcp_connection *tc = conn->c_transport_data; struct socket *sock = tc->t_sock; @@ -324,7 +325,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) rdsdebug("data ready sk %p bytes %d\n", sk, bytes); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (!conn) { /* check for teardown race */ ready = sk->sk_data_ready; @@ -338,7 +339,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) if (rds_tcp_read_sock(conn, GFP_ATOMIC, KM_SOFTIRQ0) == -ENOMEM) queue_delayed_work(rds_wq, &conn->c_recv_w, 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); ready(sk, bytes); } diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index 2979fb4..1b4fd68 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -63,7 +63,7 @@ void rds_tcp_xmit_complete(struct rds_connection *conn) } /* the core send_sem serializes this with other xmit and shutdown */ -int rds_tcp_sendmsg(struct socket *sock, void *data, unsigned int len) +static int rds_tcp_sendmsg(struct socket *sock, void *data, unsigned int len) { struct kvec vec = { .iov_base = data, @@ -174,7 +174,7 @@ void rds_tcp_write_space(struct sock *sk) struct rds_connection *conn; struct rds_tcp_connection *tc; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (!conn) { write_space = sk->sk_write_space; @@ -194,7 +194,7 @@ void rds_tcp_write_space(struct sock *sk) queue_delayed_work(rds_wq, &conn->c_send_w, 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); /* * write_space is only called when data leaves tcp's send queue if diff --git a/net/rfkill/input.c b/net/rfkill/input.c index 3713d7e..1bca6d4 100644 --- a/net/rfkill/input.c +++ b/net/rfkill/input.c @@ -142,7 +142,7 @@ 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; + return time_after(jiffies, last + delay) ? 0 : delay; } static void rfkill_schedule_ratelimited(void) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 8e45e76..d952e7e 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -679,7 +679,7 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1) return -EINVAL; - if (addr->srose_ndigis > ROSE_MAX_DIGIS) + if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS) return -EINVAL; if ((dev = rose_dev_get(&addr->srose_addr)) == NULL) { @@ -739,7 +739,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1) return -EINVAL; - if (addr->srose_ndigis > ROSE_MAX_DIGIS) + if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS) return -EINVAL; /* Source + Destination digis should not exceed ROSE_MAX_DIGIS */ diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index a750a28..fa5f564 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -114,7 +114,7 @@ static int rose_send_frame(struct sk_buff *skb, struct rose_neigh *neigh) if (ax25s) ax25_cb_put(ax25s); - return (neigh->ax25 != NULL); + return neigh->ax25 != NULL; } /* @@ -137,7 +137,7 @@ static int rose_link_up(struct rose_neigh *neigh) if (ax25s) ax25_cb_put(ax25s); - return (neigh->ax25 != NULL); + return neigh->ax25 != NULL; } /* diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 7416a5c..b0c2a82 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -137,7 +137,7 @@ next_knode: int toff = off + key->off + (off2 & key->offmask); __be32 *data, _data; - if (skb_headroom(skb) + toff < 0) + if (skb_headroom(skb) + toff > INT_MAX) goto out; data = skb_header_pointer(skb, toff, 4, &_data); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 6fb3d41..b22ca2d 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -240,7 +240,10 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) if (q) goto out; - q = qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle); + if (dev_ingress_queue(dev)) + q = qdisc_match_from_root( + dev_ingress_queue(dev)->qdisc_sleeping, + handle); out: return q; } @@ -690,6 +693,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, (new && new->flags & TCQ_F_INGRESS)) { num_q = 1; ingress = 1; + if (!dev_ingress_queue(dev)) + return -ENOENT; } if (dev->flags & IFF_UP) @@ -701,7 +706,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, } for (i = 0; i < num_q; i++) { - struct netdev_queue *dev_queue = &dev->rx_queue; + struct netdev_queue *dev_queue = dev_ingress_queue(dev); if (!ingress) dev_queue = netdev_get_tx_queue(dev, i); @@ -979,7 +984,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -ENOENT; q = qdisc_leaf(p, clid); } else { /* ingress */ - q = dev->rx_queue.qdisc_sleeping; + if (dev_ingress_queue(dev)) + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -1043,8 +1049,9 @@ replay: if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL) return -ENOENT; q = qdisc_leaf(p, clid); - } else { /*ingress */ - q = dev->rx_queue.qdisc_sleeping; + } else { /* ingress */ + if (dev_ingress_queue_create(dev)) + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -1123,11 +1130,14 @@ replay: create_n_graft: if (!(n->nlmsg_flags&NLM_F_CREATE)) return -ENOENT; - if (clid == TC_H_INGRESS) - q = qdisc_create(dev, &dev->rx_queue, p, - tcm->tcm_parent, tcm->tcm_parent, - tca, &err); - else { + if (clid == TC_H_INGRESS) { + if (dev_ingress_queue(dev)) + q = qdisc_create(dev, dev_ingress_queue(dev), p, + tcm->tcm_parent, tcm->tcm_parent, + tca, &err); + else + err = -ENOENT; + } else { struct netdev_queue *dev_queue; if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue) @@ -1304,8 +1314,10 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx) < 0) goto done; - dev_queue = &dev->rx_queue; - if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0) + dev_queue = dev_ingress_queue(dev); + if (dev_queue && + tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, + &q_idx, s_q_idx) < 0) goto done; cont: @@ -1595,8 +1607,10 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0) goto done; - dev_queue = &dev->rx_queue; - if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0) + dev_queue = dev_ingress_queue(dev); + if (dev_queue && + tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, + &t, s_t) < 0) goto done; done: diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 34066278..2825407 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -255,10 +255,6 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, error = -EINVAL; goto err_out; } - if (!list_empty(&flow->list)) { - error = -EEXIST; - goto err_out; - } } else { int i; unsigned long cl; @@ -279,8 +275,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, goto err_out; } flow->filter_list = NULL; - flow->q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, classid); + flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!flow->q) flow->q = &noop_qdisc; pr_debug("atm_tc_change: qdisc %p\n", flow->q); @@ -547,7 +542,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) INIT_LIST_HEAD(&p->flows); INIT_LIST_HEAD(&p->link.list); list_add(&p->link.list, &p->flows); - p->link.q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + p->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (!p->link.q) p->link.q = &noop_qdisc; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 28c01ef..eb76315 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1379,9 +1379,9 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) q->link.sibling = &q->link; q->link.common.classid = sch->handle; q->link.qdisc = sch; - if (!(q->link.q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, - sch->handle))) + q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + sch->handle); + if (!q->link.q) q->link.q = &noop_qdisc; q->link.priority = TC_CBQ_MAXPRIO-1; @@ -1623,7 +1623,7 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct cbq_class *cl = (struct cbq_class*)arg; if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->common.classid); if (new == NULL) return -ENOBUFS; @@ -1874,8 +1874,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->R_tab = rtab; rtab = NULL; cl->refcnt = 1; - if (!(cl->q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, classid))) + cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); + if (!cl->q) cl->q = &noop_qdisc; cl->common.classid = classid; cl->tparent = parent; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index b74046a..aa8b531 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -110,7 +110,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->refcnt = 1; cl->common.classid = classid; cl->quantum = quantum; - cl->qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; @@ -218,7 +218,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg, struct drr_class *cl = (struct drr_class *)arg; if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->common.classid); if (new == NULL) new = &noop_qdisc; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 63d41f8..1d295d6 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -61,8 +61,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg, sch, p, new, old); if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (new == NULL) new = &noop_qdisc; @@ -384,8 +383,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) p->default_index = default_index; p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - p->q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, sch->handle); + p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (p->q == NULL) p->q = &noop_qdisc; diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 5948baf..4dfecb0 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -172,8 +172,7 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, struct Qdisc *q; int err = -ENOMEM; - q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - ops, TC_H_MAKE(sch->handle, 1)); + q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1)); if (q) { err = fifo_set_limit(q, limit); if (err < 0) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 2aeb3a4..5dbb3cd 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -383,6 +383,7 @@ struct Qdisc noop_qdisc = { .list = LIST_HEAD_INIT(noop_qdisc.list), .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, + .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), }; EXPORT_SYMBOL(noop_qdisc); @@ -409,6 +410,7 @@ static struct Qdisc noqueue_qdisc = { .list = LIST_HEAD_INIT(noqueue_qdisc.list), .q.lock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock), .dev_queue = &noqueue_netdev_queue, + .busylock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.busylock), }; @@ -574,10 +576,8 @@ errout: return ERR_PTR(err); } -struct Qdisc * qdisc_create_dflt(struct net_device *dev, - struct netdev_queue *dev_queue, - struct Qdisc_ops *ops, - unsigned int parentid) +struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, + struct Qdisc_ops *ops, unsigned int parentid) { struct Qdisc *sch; @@ -682,7 +682,7 @@ static void attach_one_default_qdisc(struct net_device *dev, struct Qdisc *qdisc; if (dev->tx_queue_len) { - qdisc = qdisc_create_dflt(dev, dev_queue, + qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, TC_H_ROOT); if (!qdisc) { printk(KERN_INFO "%s: activation failed\n", dev->name); @@ -709,7 +709,7 @@ static void attach_default_qdiscs(struct net_device *dev) dev->qdisc = txq->qdisc_sleeping; atomic_inc(&dev->qdisc->refcnt); } else { - qdisc = qdisc_create_dflt(dev, txq, &mq_qdisc_ops, TC_H_ROOT); + qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT); if (qdisc) { qdisc->ops->attach(qdisc); dev->qdisc = qdisc; @@ -753,7 +753,8 @@ void dev_activate(struct net_device *dev) need_watchdog = 0; netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog); - transition_one_qdisc(dev, &dev->rx_queue, NULL); + if (dev_ingress_queue(dev)) + transition_one_qdisc(dev, dev_ingress_queue(dev), NULL); if (need_watchdog) { dev->trans_start = jiffies; @@ -812,7 +813,8 @@ static bool some_qdisc_is_busy(struct net_device *dev) void dev_deactivate(struct net_device *dev) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); - dev_deactivate_queue(dev, &dev->rx_queue, &noop_qdisc); + if (dev_ingress_queue(dev)) + dev_deactivate_queue(dev, dev_ingress_queue(dev), &noop_qdisc); dev_watchdog_down(dev); @@ -838,7 +840,8 @@ void dev_init_scheduler(struct net_device *dev) { dev->qdisc = &noop_qdisc; netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); - dev_init_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc); + if (dev_ingress_queue(dev)) + dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); } @@ -861,7 +864,8 @@ static void shutdown_scheduler_queue(struct net_device *dev, void dev_shutdown(struct net_device *dev) { netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); - shutdown_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc); + if (dev_ingress_queue(dev)) + shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); qdisc_destroy(dev->qdisc); dev->qdisc = &noop_qdisc; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 4749609..069c62b 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1088,7 +1088,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->refcnt = 1; cl->sched = q; cl->cl_parent = parent; - cl->qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; @@ -1209,8 +1209,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (cl->level > 0) return -EINVAL; if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->cl_common.classid); if (new == NULL) new = &noop_qdisc; @@ -1452,8 +1451,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) q->root.cl_common.classid = sch->handle; q->root.refcnt = 1; q->root.sched = q; - q->root.qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + q->root.qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 4be8d04..01b519d 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1121,8 +1121,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (cl->level) return -EINVAL; if (new == NULL && - (new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + (new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->common.classid)) == NULL) return -ENOBUFS; @@ -1247,8 +1246,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) return -EBUSY; if (!cl->level && htb_parent_last_child(cl)) { - new_q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->parent->common.classid); last_child = 1; } @@ -1302,14 +1300,14 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; struct qdisc_rate_table *rtab = NULL, *ctab = NULL; - struct nlattr *tb[TCA_HTB_RTAB + 1]; + struct nlattr *tb[__TCA_HTB_MAX]; struct tc_htb_opt *hopt; /* extract all subattrs from opt attr */ if (!opt) goto failure; - err = nla_parse_nested(tb, TCA_HTB_RTAB, opt, htb_policy); + err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy); if (err < 0) goto failure; @@ -1377,7 +1375,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) so that can't be used inside of sch_tree_lock -- thanks to Karlis Peisenieks */ - new_q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); sch_tree_lock(sch); if (parent && !parent->level) { diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index fe91e50..ecc302f 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -56,7 +56,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { dev_queue = netdev_get_tx_queue(dev, ntx); - qdisc = qdisc_create_dflt(dev, dev_queue, &pfifo_fast_ops, + qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(ntx + 1))); if (qdisc == NULL) diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 6ae2512..32690de 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -227,8 +227,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; - child = qdisc_create_dflt(qdisc_dev(sch), - sch->dev_queue, + child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, i + 1)); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 4714ff1..e5593c0 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -538,8 +538,7 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); - q->qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &tfifo_qdisc_ops, + q->qdisc = qdisc_create_dflt(sch->dev_queue, &tfifo_qdisc_ops, TC_H_MAKE(sch->handle, 1)); if (!q->qdisc) { pr_debug("netem: qdisc create failed\n"); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 0748fb1..b1c95bc 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -200,7 +200,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) for (i=0; i<q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; - child = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, i + 1)); if (child) { diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index feaabc1..401af95 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -241,11 +241,11 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * } if (neigh_event_send(n, skb_res) == 0) { int err; + char haddr[MAX_ADDR_LEN]; - read_lock(&n->lock); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), - n->ha, NULL, skb->len); - read_unlock(&n->lock); + neigh_ha_snapshot(haddr, n, dev); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), haddr, + NULL, skb->len); if (err < 0) { neigh_release(n); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 8636639..ddbbf7c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -543,16 +543,20 @@ struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc) id = ntohs(hmacs->hmac_ids[i]); /* Check the id is in the supported range */ - if (id > SCTP_AUTH_HMAC_ID_MAX) + if (id > SCTP_AUTH_HMAC_ID_MAX) { + id = 0; continue; + } /* See is we support the id. Supported IDs have name and * length fields set, so that we can allocated and use * them. We can safely just check for name, for without the * name, we can't allocate the TFM. */ - if (!sctp_hmac_list[id].hmac_name) + if (!sctp_hmac_list[id].hmac_name) { + id = 0; continue; + } break; } diff --git a/net/sctp/output.c b/net/sctp/output.c index 901764b..60600d3 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -94,7 +94,6 @@ struct sctp_packet *sctp_packet_config(struct sctp_packet *packet, SCTP_DEBUG_PRINTK("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); - sctp_packet_reset(packet); packet->vtag = vtag; if (ecn_capable && sctp_packet_empty(packet)) { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index f774e65..1ef29c7 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -799,7 +799,7 @@ static void sctp_inet_skb_msgname(struct sk_buff *skb, char *msgname, int *len) static int sctp_inet_af_supported(sa_family_t family, struct sctp_sock *sp) { /* PF_INET only supports AF_INET addresses. */ - return (AF_INET == family); + return AF_INET == family; } /* Address matching with wildcards allowed. */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6a691d8..e34ca9c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -918,6 +918,11 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk, /* Walk through the addrs buffer and count the number of addresses. */ addr_buf = kaddrs; while (walk_size < addrs_size) { + if (walk_size + sizeof(sa_family_t) > addrs_size) { + kfree(kaddrs); + return -EINVAL; + } + sa_addr = (struct sockaddr *)addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); @@ -1004,9 +1009,13 @@ static int __sctp_connect(struct sock* sk, /* Walk through the addrs buffer and count the number of addresses. */ addr_buf = kaddrs; while (walk_size < addrs_size) { + if (walk_size + sizeof(sa_family_t) > addrs_size) { + err = -EINVAL; + goto out_free; + } + sa_addr = (union sctp_addr *)addr_buf; af = sctp_get_af_specific(sa_addr->sa.sa_family); - port = ntohs(sa_addr->v4.sin_port); /* If the address family is not supported or if this address * causes the address buffer to overflow return EINVAL. @@ -1016,6 +1025,8 @@ static int __sctp_connect(struct sock* sk, goto out_free; } + port = ntohs(sa_addr->v4.sin_port); + /* Save current address so we can work with it */ memcpy(&to, sa_addr, af->sockaddr_len); @@ -3617,8 +3628,8 @@ SCTP_STATIC int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) amount = skb->len; } rc = put_user(amount, (int __user *)arg); - } break; + } default: rc = -ENOIOCTLCMD; break; @@ -3884,7 +3895,7 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, } out: - return (retval); + return retval; } @@ -3940,7 +3951,7 @@ static int sctp_getsockopt_peer_addr_info(struct sock *sk, int len, } out: - return (retval); + return retval; } /* 7.1.12 Enable/Disable message fragmentation (SCTP_DISABLE_FRAGMENTS) @@ -5594,7 +5605,7 @@ static int sctp_get_port(struct sock *sk, unsigned short snum) /* Note: sk->sk_num gets filled in if ephemeral port request. */ ret = sctp_get_port_local(sk, &addr); - return (ret ? 1 : 0); + return ret ? 1 : 0; } /* diff --git a/net/socket.c b/net/socket.c index 717a5f1..72da57d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -209,8 +209,8 @@ int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr *kaddr) * specified. Zero is returned for a success. */ -int move_addr_to_user(struct sockaddr *kaddr, int klen, void __user *uaddr, - int __user *ulen) +static int move_addr_to_user(struct sockaddr *kaddr, int klen, + void __user *uaddr, int __user *ulen) { int err; int len; @@ -661,7 +661,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); -inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) +static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) { if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount) put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 36cb660..e9eaaf7 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -38,7 +38,7 @@ static const struct rpc_authops *auth_flavors[RPC_AUTH_MAXFLAVOR] = { static LIST_HEAD(cred_unused); static unsigned long number_cred_unused; -#define MAX_HASHTABLE_BITS (10) +#define MAX_HASHTABLE_BITS (14) static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp) { unsigned long num; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index dcfc66b..3835ce3 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -745,17 +745,18 @@ gss_pipe_release(struct inode *inode) struct rpc_inode *rpci = RPC_I(inode); struct gss_upcall_msg *gss_msg; +restart: spin_lock(&inode->i_lock); - while (!list_empty(&rpci->in_downcall)) { + list_for_each_entry(gss_msg, &rpci->in_downcall, list) { - gss_msg = list_entry(rpci->in_downcall.next, - struct gss_upcall_msg, list); + if (!list_empty(&gss_msg->msg.list)) + continue; gss_msg->msg.errno = -EPIPE; atomic_inc(&gss_msg->count); __gss_unhash_msg(gss_msg); spin_unlock(&inode->i_lock); gss_release_msg(gss_msg); - spin_lock(&inode->i_lock); + goto restart; } spin_unlock(&inode->i_lock); @@ -1049,7 +1050,7 @@ gss_match(struct auth_cred *acred, struct rpc_cred *rc, int flags) out: if (acred->machine_cred != gss_cred->gc_machine_cred) return 0; - return (rc->cr_uid == acred->uid); + return rc->cr_uid == acred->uid; } /* diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c index 310b78e..c586e92 100644 --- a/net/sunrpc/auth_gss/gss_generic_token.c +++ b/net/sunrpc/auth_gss/gss_generic_token.c @@ -76,19 +76,19 @@ static int der_length_size( int length) { if (length < (1<<7)) - return(1); + return 1; else if (length < (1<<8)) - return(2); + return 2; #if (SIZEOF_INT == 2) else - return(3); + return 3; #else else if (length < (1<<16)) - return(3); + return 3; else if (length < (1<<24)) - return(4); + return 4; else - return(5); + return 5; #endif } @@ -121,14 +121,14 @@ der_read_length(unsigned char **buf, int *bufsize) int ret; if (*bufsize < 1) - return(-1); + return -1; sf = *(*buf)++; (*bufsize)--; if (sf & 0x80) { if ((sf &= 0x7f) > ((*bufsize)-1)) - return(-1); + return -1; if (sf > SIZEOF_INT) - return (-1); + return -1; ret = 0; for (; sf; sf--) { ret = (ret<<8) + (*(*buf)++); @@ -138,7 +138,7 @@ der_read_length(unsigned char **buf, int *bufsize) ret = sf; } - return(ret); + return ret; } /* returns the length of a token, given the mech oid and the body size */ @@ -148,7 +148,7 @@ g_token_size(struct xdr_netobj *mech, unsigned int body_size) { /* set body_size to sequence contents size */ body_size += 2 + (int) mech->len; /* NEED overflow check */ - return(1 + der_length_size(body_size) + body_size); + return 1 + der_length_size(body_size) + body_size; } EXPORT_SYMBOL_GPL(g_token_size); @@ -186,27 +186,27 @@ g_verify_token_header(struct xdr_netobj *mech, int *body_size, int ret = 0; if ((toksize-=1) < 0) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; if (*buf++ != 0x60) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; if ((seqsize = der_read_length(&buf, &toksize)) < 0) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; if (seqsize != toksize) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; if ((toksize-=1) < 0) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; if (*buf++ != 0x06) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; if ((toksize-=1) < 0) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; toid.len = *buf++; if ((toksize-=toid.len) < 0) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; toid.data = buf; buf+=toid.len; @@ -217,17 +217,17 @@ g_verify_token_header(struct xdr_netobj *mech, int *body_size, to return G_BAD_TOK_HEADER if the token header is in fact bad */ if ((toksize-=2) < 0) - return(G_BAD_TOK_HEADER); + return G_BAD_TOK_HEADER; if (ret) - return(ret); + return ret; if (!ret) { *buf_in = buf; *body_size = toksize; } - return(ret); + return ret; } EXPORT_SYMBOL_GPL(g_verify_token_header); diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 0326446..778e5df 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -237,6 +237,7 @@ get_key(const void *p, const void *end, if (!supported_gss_krb5_enctype(alg)) { printk(KERN_WARNING "gss_kerberos_mech: unsupported " "encryption key algorithm %d\n", alg); + p = ERR_PTR(-EINVAL); goto out_err; } p = simple_get_netobj(p, end, &key); @@ -282,15 +283,19 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) ctx->enctype = ENCTYPE_DES_CBC_RAW; ctx->gk5e = get_gss_krb5_enctype(ctx->enctype); - if (ctx->gk5e == NULL) + if (ctx->gk5e == NULL) { + p = ERR_PTR(-EINVAL); goto out_err; + } /* The downcall format was designed before we completely understood * the uses of the context fields; so it includes some stuff we * just give some minimal sanity-checking, and some we ignore * completely (like the next twenty bytes): */ - if (unlikely(p + 20 > end || p + 20 < p)) + if (unlikely(p + 20 > end || p + 20 < p)) { + p = ERR_PTR(-EFAULT); goto out_err; + } p += 20; p = simple_get_bytes(p, end, &tmp, sizeof(tmp)); if (IS_ERR(p)) @@ -619,6 +624,7 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, if (ctx->seq_send64 != ctx->seq_send) { dprintk("%s: seq_send64 %lx, seq_send %x overflow?\n", __func__, (long unsigned)ctx->seq_send64, ctx->seq_send); + p = ERR_PTR(-EINVAL); goto out_err; } p = simple_get_bytes(p, end, &ctx->enctype, sizeof(ctx->enctype)); diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index 415c013..62ac90c 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -162,5 +162,5 @@ krb5_get_seq_num(struct krb5_ctx *kctx, *seqnum = ((plain[0]) | (plain[1] << 8) | (plain[2] << 16) | (plain[3] << 24)); - return (0); + return 0; } diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 2689de3..8b40610 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -331,7 +331,7 @@ gss_delete_sec_context(struct gss_ctx **context_handle) *context_handle); if (!*context_handle) - return(GSS_S_NO_CONTEXT); + return GSS_S_NO_CONTEXT; if ((*context_handle)->internal_ctx_id) (*context_handle)->mech_type->gm_ops ->gss_delete_sec_context((*context_handle) diff --git a/net/sunrpc/auth_gss/gss_spkm3_mech.c b/net/sunrpc/auth_gss/gss_spkm3_mech.c index dc3f1f5..adade3d 100644 --- a/net/sunrpc/auth_gss/gss_spkm3_mech.c +++ b/net/sunrpc/auth_gss/gss_spkm3_mech.c @@ -100,6 +100,7 @@ gss_import_sec_context_spkm3(const void *p, size_t len, if (version != 1) { dprintk("RPC: unknown spkm3 token format: " "obsolete nfs-utils?\n"); + p = ERR_PTR(-EINVAL); goto out_err_free_ctx; } @@ -135,8 +136,10 @@ gss_import_sec_context_spkm3(const void *p, size_t len, if (IS_ERR(p)) goto out_err_free_intg_alg; - if (p != end) + if (p != end) { + p = ERR_PTR(-EFAULT); goto out_err_free_intg_key; + } ctx_id->internal_ctx_id = ctx; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 2388d83..fa55490 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -226,7 +226,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru goto out_no_principal; } - kref_init(&clnt->cl_kref); + atomic_set(&clnt->cl_count, 1); err = rpc_setup_pipedir(clnt, program->pipe_dir_name); if (err < 0) @@ -390,14 +390,14 @@ rpc_clone_client(struct rpc_clnt *clnt) if (new->cl_principal == NULL) goto out_no_principal; } - kref_init(&new->cl_kref); + atomic_set(&new->cl_count, 1); err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name); if (err != 0) goto out_no_path; if (new->cl_auth) atomic_inc(&new->cl_auth->au_count); xprt_get(clnt->cl_xprt); - kref_get(&clnt->cl_kref); + atomic_inc(&clnt->cl_count); rpc_register_client(new); rpciod_up(); return new; @@ -465,10 +465,8 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client); * Free an RPC client */ static void -rpc_free_client(struct kref *kref) +rpc_free_client(struct rpc_clnt *clnt) { - struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref); - dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); if (!IS_ERR(clnt->cl_path.dentry)) { @@ -495,12 +493,10 @@ out_free: * Free an RPC client */ static void -rpc_free_auth(struct kref *kref) +rpc_free_auth(struct rpc_clnt *clnt) { - struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref); - if (clnt->cl_auth == NULL) { - rpc_free_client(kref); + rpc_free_client(clnt); return; } @@ -509,10 +505,11 @@ rpc_free_auth(struct kref *kref) * release remaining GSS contexts. This mechanism ensures * that it can do so safely. */ - kref_init(kref); + atomic_inc(&clnt->cl_count); rpcauth_release(clnt->cl_auth); clnt->cl_auth = NULL; - kref_put(kref, rpc_free_client); + if (atomic_dec_and_test(&clnt->cl_count)) + rpc_free_client(clnt); } /* @@ -525,7 +522,8 @@ rpc_release_client(struct rpc_clnt *clnt) if (list_empty(&clnt->cl_tasks)) wake_up(&destroy_wait); - kref_put(&clnt->cl_kref, rpc_free_auth); + if (atomic_dec_and_test(&clnt->cl_count)) + rpc_free_auth(clnt); } /** @@ -588,7 +586,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) if (clnt != NULL) { rpc_task_release_client(task); task->tk_client = clnt; - kref_get(&clnt->cl_kref); + atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; /* Add to the client's list of all tasks */ @@ -931,7 +929,7 @@ call_reserveresult(struct rpc_task *task) task->tk_status = 0; if (status >= 0) { if (task->tk_rqstp) { - task->tk_action = call_allocate; + task->tk_action = call_refresh; return; } @@ -966,13 +964,54 @@ call_reserveresult(struct rpc_task *task) } /* - * 2. Allocate the buffer. For details, see sched.c:rpc_malloc. + * 2. Bind and/or refresh the credentials + */ +static void +call_refresh(struct rpc_task *task) +{ + dprint_status(task); + + task->tk_action = call_refreshresult; + task->tk_status = 0; + task->tk_client->cl_stats->rpcauthrefresh++; + rpcauth_refreshcred(task); +} + +/* + * 2a. Process the results of a credential refresh + */ +static void +call_refreshresult(struct rpc_task *task) +{ + int status = task->tk_status; + + dprint_status(task); + + task->tk_status = 0; + task->tk_action = call_allocate; + if (status >= 0 && rpcauth_uptodatecred(task)) + return; + switch (status) { + case -EACCES: + rpc_exit(task, -EACCES); + return; + case -ENOMEM: + rpc_exit(task, -ENOMEM); + return; + case -ETIMEDOUT: + rpc_delay(task, 3*HZ); + } + task->tk_action = call_refresh; +} + +/* + * 2b. Allocate the buffer. For details, see sched.c:rpc_malloc. * (Note: buffer memory is freed in xprt_release). */ static void call_allocate(struct rpc_task *task) { - unsigned int slack = task->tk_client->cl_auth->au_cslack; + unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack; struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = task->tk_xprt; struct rpc_procinfo *proc = task->tk_msg.rpc_proc; @@ -980,7 +1019,7 @@ call_allocate(struct rpc_task *task) dprint_status(task); task->tk_status = 0; - task->tk_action = call_refresh; + task->tk_action = call_bind; if (req->rq_buffer) return; @@ -1017,47 +1056,6 @@ call_allocate(struct rpc_task *task) rpc_exit(task, -ERESTARTSYS); } -/* - * 2a. Bind and/or refresh the credentials - */ -static void -call_refresh(struct rpc_task *task) -{ - dprint_status(task); - - task->tk_action = call_refreshresult; - task->tk_status = 0; - task->tk_client->cl_stats->rpcauthrefresh++; - rpcauth_refreshcred(task); -} - -/* - * 2b. Process the results of a credential refresh - */ -static void -call_refreshresult(struct rpc_task *task) -{ - int status = task->tk_status; - - dprint_status(task); - - task->tk_status = 0; - task->tk_action = call_bind; - if (status >= 0 && rpcauth_uptodatecred(task)) - return; - switch (status) { - case -EACCES: - rpc_exit(task, -EACCES); - return; - case -ENOMEM: - rpc_exit(task, -ENOMEM); - return; - case -ETIMEDOUT: - rpc_delay(task, 3*HZ); - } - task->tk_action = call_refresh; -} - static inline int rpc_task_need_encode(struct rpc_task *task) { diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 95ccbcf..8c8eef2 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -48,7 +48,7 @@ static void rpc_purge_list(struct rpc_inode *rpci, struct list_head *head, return; do { msg = list_entry(head->next, struct rpc_pipe_msg, list); - list_del(&msg->list); + list_del_init(&msg->list); msg->errno = err; destroy_msg(msg); } while (!list_empty(head)); @@ -208,7 +208,7 @@ rpc_pipe_release(struct inode *inode, struct file *filp) if (msg != NULL) { spin_lock(&inode->i_lock); msg->errno = -EAGAIN; - list_del(&msg->list); + list_del_init(&msg->list); spin_unlock(&inode->i_lock); rpci->ops->destroy_msg(msg); } @@ -268,7 +268,7 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) if (res < 0 || msg->len == msg->copied) { filp->private_data = NULL; spin_lock(&inode->i_lock); - list_del(&msg->list); + list_del_init(&msg->list); spin_unlock(&inode->i_lock); rpci->ops->destroy_msg(msg); } @@ -371,21 +371,23 @@ rpc_show_info(struct seq_file *m, void *v) static int rpc_info_open(struct inode *inode, struct file *file) { - struct rpc_clnt *clnt; + struct rpc_clnt *clnt = NULL; int ret = single_open(file, rpc_show_info, NULL); if (!ret) { struct seq_file *m = file->private_data; - mutex_lock(&inode->i_mutex); - clnt = RPC_I(inode)->private; - if (clnt) { - kref_get(&clnt->cl_kref); + + spin_lock(&file->f_path.dentry->d_lock); + if (!d_unhashed(file->f_path.dentry)) + clnt = RPC_I(inode)->private; + if (clnt != NULL && atomic_inc_not_zero(&clnt->cl_count)) { + spin_unlock(&file->f_path.dentry->d_lock); m->private = clnt; } else { + spin_unlock(&file->f_path.dentry->d_lock); single_release(inode, file); ret = -EINVAL; } - mutex_unlock(&inode->i_mutex); } return ret; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index cace604..aa5dbda 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -376,7 +376,7 @@ int rpc_queue_empty(struct rpc_wait_queue *queue) spin_lock_bh(&queue->lock); res = queue->qlen; spin_unlock_bh(&queue->lock); - return (res == 0); + return res == 0; } EXPORT_SYMBOL_GPL(rpc_queue_empty); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index b6309db..fe9306b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -800,7 +800,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) u32 _xid; __be32 *xp; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); dprintk("RPC: xs_udp_data_ready...\n"); if (!(xprt = xprt_from_sock(sk))) goto out; @@ -852,7 +852,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) dropit: skb_free_datagram(sk, skb); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) @@ -1229,7 +1229,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) dprintk("RPC: xs_tcp_data_ready...\n"); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; if (xprt->shutdown) @@ -1248,7 +1248,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv); } while (read > 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /* @@ -1301,7 +1301,7 @@ static void xs_tcp_state_change(struct sock *sk) { struct rpc_xprt *xprt; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: xs_tcp_state_change client %p...\n", xprt); @@ -1313,7 +1313,7 @@ static void xs_tcp_state_change(struct sock *sk) switch (sk->sk_state) { case TCP_ESTABLISHED: - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->transport_lock); if (!xprt_test_and_set_connected(xprt)) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1327,7 +1327,7 @@ static void xs_tcp_state_change(struct sock *sk) xprt_wake_pending_tasks(xprt, -EAGAIN); } - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->transport_lock); break; case TCP_FIN_WAIT1: /* The client initiated a shutdown of the socket */ @@ -1365,7 +1365,7 @@ static void xs_tcp_state_change(struct sock *sk) xs_sock_mark_closed(xprt); } out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1376,7 +1376,7 @@ static void xs_error_report(struct sock *sk) { struct rpc_xprt *xprt; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: %s client %p...\n" @@ -1384,7 +1384,7 @@ static void xs_error_report(struct sock *sk) __func__, xprt, sk->sk_err); xprt_wake_pending_tasks(xprt, -EAGAIN); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static void xs_write_space(struct sock *sk) @@ -1416,13 +1416,13 @@ static void xs_write_space(struct sock *sk) */ static void xs_udp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); /* from net/core/sock.c:sock_def_write_space */ if (sock_writeable(sk)) xs_write_space(sk); - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1437,13 +1437,13 @@ static void xs_udp_write_space(struct sock *sk) */ static void xs_tcp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); /* from net/core/stream.c:sk_stream_write_space */ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) xs_write_space(sk); - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt) diff --git a/net/tipc/addr.c b/net/tipc/addr.c index c048543..8a2e89b 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -41,11 +41,6 @@ #include "cluster.h" #include "net.h" -u32 tipc_get_addr(void) -{ - return tipc_own_addr; -} - /** * tipc_addr_domain_valid - validates a network domain address * @@ -89,7 +84,7 @@ int tipc_addr_domain_valid(u32 addr) int tipc_addr_node_valid(u32 addr) { - return (tipc_addr_domain_valid(addr) && tipc_node(addr)); + return tipc_addr_domain_valid(addr) && tipc_node(addr); } int tipc_in_scope(u32 domain, u32 addr) diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index b11248c..22a60fc 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -121,6 +121,9 @@ static DEFINE_SPINLOCK(bc_lock); const char tipc_bclink_name[] = "broadcast-link"; +static void tipc_nmap_diff(struct tipc_node_map *nm_a, + struct tipc_node_map *nm_b, + struct tipc_node_map *nm_diff); static u32 buf_seqno(struct sk_buff *buf) { @@ -184,7 +187,7 @@ static void bclink_set_gap(struct tipc_node *n_ptr) static int bclink_ack_allowed(u32 n) { - return((n % TIPC_MIN_LINK_WIN) == tipc_own_tag); + return (n % TIPC_MIN_LINK_WIN) == tipc_own_tag; } @@ -287,7 +290,7 @@ static void bclink_send_nack(struct tipc_node *n_ptr) if (!less(n_ptr->bclink.gap_after, n_ptr->bclink.gap_to)) return; - buf = buf_acquire(INT_H_SIZE); + buf = tipc_buf_acquire(INT_H_SIZE); if (buf) { msg = buf_msg(buf); tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, @@ -871,8 +874,9 @@ void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node) * @nm_diff: output node map A-B (i.e. nodes of A that are not in B) */ -void tipc_nmap_diff(struct tipc_node_map *nm_a, struct tipc_node_map *nm_b, - struct tipc_node_map *nm_diff) +static void tipc_nmap_diff(struct tipc_node_map *nm_a, + struct tipc_node_map *nm_b, + struct tipc_node_map *nm_diff) { int stop = ARRAY_SIZE(nm_a->map); int w; diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index e8c2b81..011c03f 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -84,9 +84,6 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a, struct tipc_node_m return !memcmp(nm_a, nm_b, sizeof(*nm_a)); } -void tipc_nmap_diff(struct tipc_node_map *nm_a, struct tipc_node_map *nm_b, - struct tipc_node_map *nm_diff); - void tipc_port_list_add(struct port_list *pl_ptr, u32 port); void tipc_port_list_free(struct port_list *pl_ptr); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 52ae17b..9927d1d 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -63,7 +63,7 @@ static int media_name_valid(const char *name) len = strlen(name); if ((len + 1) > TIPC_MAX_MEDIA_NAME) return 0; - return (strspn(name, tipc_alphabet) == len); + return strspn(name, tipc_alphabet) == len; } /** @@ -288,9 +288,6 @@ static struct bearer *bearer_find(const char *name) struct bearer *b_ptr; u32 i; - if (tipc_mode != TIPC_NET_MODE) - return NULL; - for (i = 0, b_ptr = tipc_bearers; i < MAX_BEARERS; i++, b_ptr++) { if (b_ptr->active && (!strcmp(b_ptr->publ.name, name))) return b_ptr; @@ -559,8 +556,6 @@ restart: } b_ptr = &tipc_bearers[bearer_id]; - memset(b_ptr, 0, sizeof(struct bearer)); - strcpy(b_ptr->publ.name, name); res = m_ptr->enable_bearer(&b_ptr->publ); if (res) { @@ -630,30 +625,17 @@ int tipc_block_bearer(const char *name) * Note: This routine assumes caller holds tipc_net_lock. */ -static int bearer_disable(const char *name) +static int bearer_disable(struct bearer *b_ptr) { - struct bearer *b_ptr; struct link *l_ptr; struct link *temp_l_ptr; - b_ptr = bearer_find(name); - if (!b_ptr) { - warn("Attempt to disable unknown bearer <%s>\n", name); - return -EINVAL; - } - - info("Disabling bearer <%s>\n", name); + info("Disabling bearer <%s>\n", b_ptr->publ.name); tipc_disc_stop_link_req(b_ptr->link_req); spin_lock_bh(&b_ptr->publ.lock); b_ptr->link_req = NULL; b_ptr->publ.blocked = 1; - if (b_ptr->media->disable_bearer) { - spin_unlock_bh(&b_ptr->publ.lock); - write_unlock_bh(&tipc_net_lock); - b_ptr->media->disable_bearer(&b_ptr->publ); - write_lock_bh(&tipc_net_lock); - spin_lock_bh(&b_ptr->publ.lock); - } + b_ptr->media->disable_bearer(&b_ptr->publ); list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { tipc_link_delete(l_ptr); } @@ -664,10 +646,16 @@ static int bearer_disable(const char *name) int tipc_disable_bearer(const char *name) { + struct bearer *b_ptr; int res; write_lock_bh(&tipc_net_lock); - res = bearer_disable(name); + b_ptr = bearer_find(name); + if (b_ptr == NULL) { + warn("Attempt to disable unknown bearer <%s>\n", name); + res = -EINVAL; + } else + res = bearer_disable(b_ptr); write_unlock_bh(&tipc_net_lock); return res; } @@ -680,13 +668,7 @@ void tipc_bearer_stop(void) for (i = 0; i < MAX_BEARERS; i++) { if (tipc_bearers[i].active) - tipc_bearers[i].publ.blocked = 1; - } - for (i = 0; i < MAX_BEARERS; i++) { - if (tipc_bearers[i].active) - bearer_disable(tipc_bearers[i].publ.name); + bearer_disable(&tipc_bearers[i]); } media_count = 0; } - - diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c index e68f705..7fea14b 100644 --- a/net/tipc/cluster.c +++ b/net/tipc/cluster.c @@ -113,25 +113,6 @@ void tipc_cltr_delete(struct cluster *c_ptr) kfree(c_ptr); } -u32 tipc_cltr_next_node(struct cluster *c_ptr, u32 addr) -{ - struct tipc_node *n_ptr; - u32 n_num = tipc_node(addr) + 1; - - if (!c_ptr) - return addr; - for (; n_num <= c_ptr->highest_node; n_num++) { - n_ptr = c_ptr->nodes[n_num]; - if (n_ptr && tipc_node_has_active_links(n_ptr)) - return n_ptr->addr; - } - for (n_num = 1; n_num < tipc_node(addr); n_num++) { - n_ptr = c_ptr->nodes[n_num]; - if (n_ptr && tipc_node_has_active_links(n_ptr)) - return n_ptr->addr; - } - return 0; -} void tipc_cltr_attach_node(struct cluster *c_ptr, struct tipc_node *n_ptr) { @@ -232,7 +213,7 @@ struct tipc_node *tipc_cltr_select_node(struct cluster *c_ptr, u32 selector) static struct sk_buff *tipc_cltr_prepare_routing_msg(u32 data_size, u32 dest) { u32 size = INT_H_SIZE + data_size; - struct sk_buff *buf = buf_acquire(size); + struct sk_buff *buf = tipc_buf_acquire(size); struct tipc_msg *msg; if (buf) { diff --git a/net/tipc/cluster.h b/net/tipc/cluster.h index 333efb0..32636d9 100644 --- a/net/tipc/cluster.h +++ b/net/tipc/cluster.h @@ -75,7 +75,7 @@ void tipc_cltr_attach_node(struct cluster *c_ptr, struct tipc_node *n_ptr); void tipc_cltr_send_slave_routes(struct cluster *c_ptr, u32 dest); void tipc_cltr_broadcast(struct sk_buff *buf); int tipc_cltr_init(void); -u32 tipc_cltr_next_node(struct cluster *c_ptr, u32 addr); + void tipc_cltr_bcast_new_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi); void tipc_cltr_send_local_routes(struct cluster *c_ptr, u32 dest); void tipc_cltr_bcast_lost_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi); diff --git a/net/tipc/config.c b/net/tipc/config.c index 961d1b0..50a6133 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -95,7 +95,7 @@ int tipc_cfg_append_tlv(struct sk_buff *buf, int tlv_type, return 1; } -struct sk_buff *tipc_cfg_reply_unsigned_type(u16 tlv_type, u32 value) +static struct sk_buff *tipc_cfg_reply_unsigned_type(u16 tlv_type, u32 value) { struct sk_buff *buf; __be32 value_net; @@ -109,6 +109,11 @@ struct sk_buff *tipc_cfg_reply_unsigned_type(u16 tlv_type, u32 value) return buf; } +static struct sk_buff *tipc_cfg_reply_unsigned(u32 value) +{ + return tipc_cfg_reply_unsigned_type(TIPC_TLV_UNSIGNED, value); +} + struct sk_buff *tipc_cfg_reply_string_type(u16 tlv_type, char *string) { struct sk_buff *buf; @@ -120,139 +125,6 @@ struct sk_buff *tipc_cfg_reply_string_type(u16 tlv_type, char *string) return buf; } - -#if 0 - -/* Now obsolete code for handling commands not yet implemented the new way */ - -/* - * Some of this code assumed that the manager structure contains two added - * fields: - * u32 link_subscriptions; - * struct list_head link_subscribers; - * which are currently not present. These fields may need to be re-introduced - * if and when support for link subscriptions is added. - */ - -void tipc_cfg_link_event(u32 addr, char *name, int up) -{ - /* TIPC DOESN'T HANDLE LINK EVENT SUBSCRIPTIONS AT THE MOMENT */ -} - -int tipc_cfg_cmd(const struct tipc_cmd_msg * msg, - char *data, - u32 sz, - u32 *ret_size, - struct tipc_portid *orig) -{ - int rv = -EINVAL; - u32 cmd = msg->cmd; - - *ret_size = 0; - switch (cmd) { - case TIPC_REMOVE_LINK: - case TIPC_CMD_BLOCK_LINK: - case TIPC_CMD_UNBLOCK_LINK: - if (!cfg_check_connection(orig)) - rv = link_control(msg->argv.link_name, msg->cmd, 0); - break; - case TIPC_ESTABLISH: - { - int connected; - - tipc_isconnected(mng.conn_port_ref, &connected); - if (connected || !orig) { - rv = TIPC_FAILURE; - break; - } - rv = tipc_connect2port(mng.conn_port_ref, orig); - if (rv == TIPC_OK) - orig = 0; - break; - } - case TIPC_GET_PEER_ADDRESS: - *ret_size = link_peer_addr(msg->argv.link_name, data, sz); - break; - case TIPC_GET_ROUTES: - rv = TIPC_OK; - break; - default: {} - } - if (*ret_size) - rv = TIPC_OK; - return rv; -} - -static void cfg_cmd_event(struct tipc_cmd_msg *msg, - char *data, - u32 sz, - struct tipc_portid const *orig) -{ - int rv = -EINVAL; - struct tipc_cmd_result_msg rmsg; - struct iovec msg_sect[2]; - int *arg; - - msg->cmd = ntohl(msg->cmd); - - cfg_prepare_res_msg(msg->cmd, msg->usr_handle, rv, &rmsg, msg_sect, - data, 0); - if (ntohl(msg->magic) != TIPC_MAGIC) - goto exit; - - switch (msg->cmd) { - case TIPC_CREATE_LINK: - if (!cfg_check_connection(orig)) - rv = disc_create_link(&msg->argv.create_link); - break; - case TIPC_LINK_SUBSCRIBE: - { - struct subscr_data *sub; - - if (mng.link_subscriptions > 64) - break; - sub = kmalloc(sizeof(*sub), - GFP_ATOMIC); - if (sub == NULL) { - warn("Memory squeeze; dropped remote link subscription\n"); - break; - } - INIT_LIST_HEAD(&sub->subd_list); - tipc_createport(mng.user_ref, - (void *)sub, - TIPC_HIGH_IMPORTANCE, - 0, - 0, - (tipc_conn_shutdown_event)cfg_linksubscr_cancel, - 0, - 0, - (tipc_conn_msg_event)cfg_linksubscr_cancel, - 0, - &sub->port_ref); - if (!sub->port_ref) { - kfree(sub); - break; - } - memcpy(sub->usr_handle,msg->usr_handle, - sizeof(sub->usr_handle)); - sub->domain = msg->argv.domain; - list_add_tail(&sub->subd_list, &mng.link_subscribers); - tipc_connect2port(sub->port_ref, orig); - rmsg.retval = TIPC_OK; - tipc_send(sub->port_ref, 2u, msg_sect); - mng.link_subscriptions++; - return; - } - default: - rv = tipc_cfg_cmd(msg, data, sz, (u32 *)&msg_sect[1].iov_len, orig); - } -exit: - rmsg.result_len = htonl(msg_sect[1].iov_len); - rmsg.retval = htonl(rv); - tipc_cfg_respond(msg_sect, 2u, orig); -} -#endif - #define MAX_STATS_INFO 2000 static struct sk_buff *tipc_show_stats(void) @@ -557,14 +429,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SHOW_PORTS: rep_tlv_buf = tipc_port_get_ports(); break; -#if 0 - case TIPC_CMD_SHOW_PORT_STATS: - rep_tlv_buf = port_show_stats(req_tlv_area, req_tlv_space); - break; - case TIPC_CMD_RESET_PORT_STATS: - rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED); - break; -#endif case TIPC_CMD_SET_LOG_SIZE: rep_tlv_buf = tipc_log_resize_cmd(req_tlv_area, req_tlv_space); break; diff --git a/net/tipc/config.h b/net/tipc/config.h index 5cd7cc5..481e12e 100644 --- a/net/tipc/config.h +++ b/net/tipc/config.h @@ -45,7 +45,6 @@ struct sk_buff *tipc_cfg_reply_alloc(int payload_size); int tipc_cfg_append_tlv(struct sk_buff *buf, int tlv_type, void *tlv_data, int tlv_data_size); -struct sk_buff *tipc_cfg_reply_unsigned_type(u16 tlv_type, u32 value); struct sk_buff *tipc_cfg_reply_string_type(u16 tlv_type, char *string); static inline struct sk_buff *tipc_cfg_reply_none(void) @@ -53,11 +52,6 @@ static inline struct sk_buff *tipc_cfg_reply_none(void) return tipc_cfg_reply_alloc(0); } -static inline struct sk_buff *tipc_cfg_reply_unsigned(u32 value) -{ - return tipc_cfg_reply_unsigned_type(TIPC_TLV_UNSIGNED, value); -} - static inline struct sk_buff *tipc_cfg_reply_error_string(char *string) { return tipc_cfg_reply_string_type(TIPC_TLV_ERROR_STRING, string); diff --git a/net/tipc/core.c b/net/tipc/core.c index 466b861..e2a09eb 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -96,13 +96,8 @@ int tipc_net_id; int tipc_remote_management; -int tipc_get_mode(void) -{ - return tipc_mode; -} - /** - * buf_acquire - creates a TIPC message buffer + * tipc_buf_acquire - creates a TIPC message buffer * @size: message size (including TIPC header) * * Returns a new buffer with data pointers set to the specified size. @@ -111,7 +106,7 @@ int tipc_get_mode(void) * There may also be unrequested tailroom present at the buffer's end. */ -struct sk_buff *buf_acquire(u32 size) +struct sk_buff *tipc_buf_acquire(u32 size) { struct sk_buff *skb; unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; @@ -129,7 +124,7 @@ struct sk_buff *buf_acquire(u32 size) * tipc_core_stop_net - shut down TIPC networking sub-systems */ -void tipc_core_stop_net(void) +static void tipc_core_stop_net(void) { tipc_eth_media_stop(); tipc_net_stop(); @@ -154,7 +149,7 @@ int tipc_core_start_net(unsigned long addr) * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode */ -void tipc_core_stop(void) +static void tipc_core_stop(void) { if (tipc_mode != TIPC_NODE_MODE) return; @@ -176,7 +171,7 @@ void tipc_core_stop(void) * tipc_core_start - switch TIPC from NOT RUNNING to SINGLE NODE mode */ -int tipc_core_start(void) +static int tipc_core_start(void) { int res; @@ -246,8 +241,6 @@ MODULE_VERSION(TIPC_MOD_VER); EXPORT_SYMBOL(tipc_attach); EXPORT_SYMBOL(tipc_detach); -EXPORT_SYMBOL(tipc_get_addr); -EXPORT_SYMBOL(tipc_get_mode); EXPORT_SYMBOL(tipc_createport); EXPORT_SYMBOL(tipc_deleteport); EXPORT_SYMBOL(tipc_ownidentity); @@ -262,23 +255,10 @@ EXPORT_SYMBOL(tipc_withdraw); EXPORT_SYMBOL(tipc_connect2port); EXPORT_SYMBOL(tipc_disconnect); EXPORT_SYMBOL(tipc_shutdown); -EXPORT_SYMBOL(tipc_isconnected); -EXPORT_SYMBOL(tipc_peer); -EXPORT_SYMBOL(tipc_ref_valid); EXPORT_SYMBOL(tipc_send); -EXPORT_SYMBOL(tipc_send_buf); EXPORT_SYMBOL(tipc_send2name); -EXPORT_SYMBOL(tipc_forward2name); -EXPORT_SYMBOL(tipc_send_buf2name); -EXPORT_SYMBOL(tipc_forward_buf2name); EXPORT_SYMBOL(tipc_send2port); -EXPORT_SYMBOL(tipc_forward2port); -EXPORT_SYMBOL(tipc_send_buf2port); -EXPORT_SYMBOL(tipc_forward_buf2port); EXPORT_SYMBOL(tipc_multicast); -/* EXPORT_SYMBOL(tipc_multicast_buf); not available yet */ -EXPORT_SYMBOL(tipc_ispublished); -EXPORT_SYMBOL(tipc_available_nodes); /* TIPC API for external bearers (see tipc_bearer.h) */ @@ -295,6 +275,4 @@ EXPORT_SYMBOL(tipc_createport_raw); EXPORT_SYMBOL(tipc_reject_msg); EXPORT_SYMBOL(tipc_send_buf_fast); EXPORT_SYMBOL(tipc_acknowledge); -EXPORT_SYMBOL(tipc_get_port); -EXPORT_SYMBOL(tipc_get_handle); diff --git a/net/tipc/core.h b/net/tipc/core.h index 1887990..e19389e 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -83,9 +83,7 @@ * Note: TIPC_LOG is configured to echo its output to the system console; * user-defined buffers can be configured to do the same thing. */ - extern struct print_buf *const TIPC_NULL; -extern struct print_buf *const TIPC_CONS; extern struct print_buf *const TIPC_LOG; void tipc_printf(struct print_buf *, const char *fmt, ...); @@ -204,10 +202,7 @@ extern atomic_t tipc_user_count; * Routines available to privileged subsystems */ -extern int tipc_core_start(void); -extern void tipc_core_stop(void); -extern int tipc_core_start_net(unsigned long addr); -extern void tipc_core_stop_net(void); +extern int tipc_core_start_net(unsigned long); extern int tipc_handler_start(void); extern void tipc_handler_stop(void); extern int tipc_netlink_start(void); @@ -328,7 +323,7 @@ static inline struct tipc_msg *buf_msg(struct sk_buff *skb) return (struct tipc_msg *)skb->data; } -extern struct sk_buff *buf_acquire(u32 size); +extern struct sk_buff *tipc_buf_acquire(u32 size); /** * buf_discard - frees a TIPC message buffer diff --git a/net/tipc/dbg.c b/net/tipc/dbg.c index 1885a7e..46f51d2 100644 --- a/net/tipc/dbg.c +++ b/net/tipc/dbg.c @@ -52,7 +52,7 @@ static struct print_buf null_buf = { NULL, 0, NULL, 0 }; struct print_buf *const TIPC_NULL = &null_buf; static struct print_buf cons_buf = { NULL, 0, NULL, 1 }; -struct print_buf *const TIPC_CONS = &cons_buf; +static struct print_buf *const TIPC_CONS = &cons_buf; static struct print_buf log_buf = { NULL, 0, NULL, 1 }; struct print_buf *const TIPC_LOG = &log_buf; @@ -76,6 +76,10 @@ struct print_buf *const TIPC_LOG = &log_buf; static char print_string[TIPC_PB_MAX_STR]; static DEFINE_SPINLOCK(print_lock); +static void tipc_printbuf_reset(struct print_buf *pb); +static int tipc_printbuf_empty(struct print_buf *pb); +static void tipc_printbuf_move(struct print_buf *pb_to, + struct print_buf *pb_from); #define FORMAT(PTR,LEN,FMT) \ {\ @@ -116,7 +120,7 @@ void tipc_printbuf_init(struct print_buf *pb, char *raw, u32 size) * @pb: pointer to print buffer structure */ -void tipc_printbuf_reset(struct print_buf *pb) +static void tipc_printbuf_reset(struct print_buf *pb) { if (pb->buf) { pb->crs = pb->buf; @@ -132,9 +136,9 @@ void tipc_printbuf_reset(struct print_buf *pb) * Returns non-zero if print buffer is empty. */ -int tipc_printbuf_empty(struct print_buf *pb) +static int tipc_printbuf_empty(struct print_buf *pb) { - return (!pb->buf || (pb->crs == pb->buf)); + return !pb->buf || (pb->crs == pb->buf); } /** @@ -169,7 +173,7 @@ int tipc_printbuf_validate(struct print_buf *pb) tipc_printf(pb, err); } } - return (pb->crs - pb->buf + 1); + return pb->crs - pb->buf + 1; } /** @@ -181,7 +185,8 @@ int tipc_printbuf_validate(struct print_buf *pb) * Source print buffer becomes empty if a successful move occurs. */ -void tipc_printbuf_move(struct print_buf *pb_to, struct print_buf *pb_from) +static void tipc_printbuf_move(struct print_buf *pb_to, + struct print_buf *pb_from) { int len; diff --git a/net/tipc/dbg.h b/net/tipc/dbg.h index 5ef1bc8..3ba6ba8 100644 --- a/net/tipc/dbg.h +++ b/net/tipc/dbg.h @@ -56,10 +56,7 @@ struct print_buf { #define TIPC_PB_MAX_STR 512 /* max printable string (with trailing NUL) */ void tipc_printbuf_init(struct print_buf *pb, char *buf, u32 size); -void tipc_printbuf_reset(struct print_buf *pb); -int tipc_printbuf_empty(struct print_buf *pb); int tipc_printbuf_validate(struct print_buf *pb); -void tipc_printbuf_move(struct print_buf *pb_to, struct print_buf *pb_from); int tipc_log_resize(int log_size); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index f28d1ae..4a7cd37 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -46,16 +46,6 @@ #define TIPC_LINK_REQ_FAST 2000 /* normal delay if bearer has no links */ #define TIPC_LINK_REQ_SLOW 600000 /* normal delay if bearer has links */ -#if 0 -#define GET_NODE_INFO 300 -#define GET_NODE_INFO_RESULT 301 -#define FORWARD_LINK_PROBE 302 -#define LINK_REQUEST_REJECTED 303 -#define LINK_REQUEST_ACCEPTED 304 -#define DROP_LINK_REQUEST 305 -#define CHECK_LINK_COUNT 306 -#endif - /* * TODO: Most of the inter-cluster setup stuff should be * rewritten, and be made conformant with specification. @@ -78,30 +68,6 @@ struct link_req { unsigned int timer_intv; }; - -#if 0 -int disc_create_link(const struct tipc_link_create *argv) -{ - /* - * Code for inter cluster link setup here - */ - return TIPC_OK; -} -#endif - -/* - * disc_lost_link(): A link has lost contact - */ - -void tipc_disc_link_event(u32 addr, char *name, int up) -{ - if (in_own_cluster(addr)) - return; - /* - * Code for inter cluster link setup here - */ -} - /** * tipc_disc_init_msg - initialize a link setup message * @type: message type (request or response) @@ -115,7 +81,7 @@ static struct sk_buff *tipc_disc_init_msg(u32 type, u32 dest_domain, struct bearer *b_ptr) { - struct sk_buff *buf = buf_acquire(DSC_H_SIZE); + struct sk_buff *buf = tipc_buf_acquire(DSC_H_SIZE); struct tipc_msg *msg; if (buf) { diff --git a/net/tipc/discover.h b/net/tipc/discover.h index c36eaeb..f8e7506 100644 --- a/net/tipc/discover.h +++ b/net/tipc/discover.h @@ -50,9 +50,4 @@ void tipc_disc_stop_link_req(struct link_req *req); void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr); -void tipc_disc_link_event(u32 addr, char *name, int up); -#if 0 -int disc_create_link(const struct tipc_link_create *argv); -#endif - #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index a6a3102..b31992c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -99,23 +99,6 @@ struct link_name { char if_peer[TIPC_MAX_IF_NAME]; }; -#if 0 - -/* LINK EVENT CODE IS NOT SUPPORTED AT PRESENT */ - -/** - * struct link_event - link up/down event notification - */ - -struct link_event { - u32 addr; - int up; - void (*fcn)(u32, char *, int); - char name[TIPC_MAX_LINK_NAME]; -}; - -#endif - static void link_handle_out_of_seq_msg(struct link *l_ptr, struct sk_buff *buf); static void link_recv_proto_msg(struct link *l_ptr, struct sk_buff *buf); @@ -129,6 +112,9 @@ static void link_state_event(struct link *l_ptr, u32 event); static void link_reset_statistics(struct link *l_ptr); static void link_print(struct link *l_ptr, struct print_buf *buf, const char *str); +static void link_start(struct link *l_ptr); +static int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf); + /* * Debugging code used by link routines only @@ -239,13 +225,13 @@ int tipc_link_is_up(struct link *l_ptr) { if (!l_ptr) return 0; - return (link_working_working(l_ptr) || link_working_unknown(l_ptr)); + return link_working_working(l_ptr) || link_working_unknown(l_ptr); } int tipc_link_is_active(struct link *l_ptr) { - return ((l_ptr->owner->active_links[0] == l_ptr) || - (l_ptr->owner->active_links[1] == l_ptr)); + return (l_ptr->owner->active_links[0] == l_ptr) || + (l_ptr->owner->active_links[1] == l_ptr); } /** @@ -459,7 +445,7 @@ struct link *tipc_link_create(struct bearer *b_ptr, const u32 peer, k_init_timer(&l_ptr->timer, (Handler)link_timeout, (unsigned long)l_ptr); list_add_tail(&l_ptr->link_list, &b_ptr->links); - tipc_k_signal((Handler)tipc_link_start, (unsigned long)l_ptr); + tipc_k_signal((Handler)link_start, (unsigned long)l_ptr); dbg("tipc_link_create(): tolerance = %u,cont intv = %u, abort_limit = %u\n", l_ptr->tolerance, l_ptr->continuity_interval, l_ptr->abort_limit); @@ -499,9 +485,9 @@ void tipc_link_delete(struct link *l_ptr) kfree(l_ptr); } -void tipc_link_start(struct link *l_ptr) +static void link_start(struct link *l_ptr) { - dbg("tipc_link_start %x\n", l_ptr); + dbg("link_start %x\n", l_ptr); link_state_event(l_ptr, STARTING_EVT); } @@ -634,39 +620,9 @@ void tipc_link_stop(struct link *l_ptr) l_ptr->proto_msg_queue = NULL; } -#if 0 - /* LINK EVENT CODE IS NOT SUPPORTED AT PRESENT */ - -static void link_recv_event(struct link_event *ev) -{ - ev->fcn(ev->addr, ev->name, ev->up); - kfree(ev); -} - -static void link_send_event(void (*fcn)(u32 a, char *n, int up), - struct link *l_ptr, int up) -{ - struct link_event *ev; - - ev = kmalloc(sizeof(*ev), GFP_ATOMIC); - if (!ev) { - warn("Link event allocation failure\n"); - return; - } - ev->addr = l_ptr->addr; - ev->up = up; - ev->fcn = fcn; - memcpy(ev->name, l_ptr->name, TIPC_MAX_LINK_NAME); - tipc_k_signal((Handler)link_recv_event, (unsigned long)ev); -} - -#else - #define link_send_event(fcn, l_ptr, up) do { } while (0) -#endif - void tipc_link_reset(struct link *l_ptr) { struct sk_buff *buf; @@ -690,10 +646,7 @@ void tipc_link_reset(struct link *l_ptr) tipc_node_link_down(l_ptr->owner, l_ptr); tipc_bearer_remove_dest(l_ptr->b_ptr, l_ptr->addr); -#if 0 - tipc_printf(TIPC_CONS, "\nReset link <%s>\n", l_ptr->name); - dbg_link_dump(); -#endif + if (was_active_link && tipc_node_has_active_links(l_ptr->owner) && l_ptr->owner->permit_changeover) { l_ptr->reset_checkpoint = checkpoint; @@ -1050,7 +1003,7 @@ int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf) /* Fragmentation needed ? */ if (size > max_packet) - return tipc_link_send_long_buf(l_ptr, buf); + return link_send_long_buf(l_ptr, buf); /* Packet can be queued or sent: */ @@ -1086,7 +1039,7 @@ int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf) /* Try creating a new bundle */ if (size <= max_packet * 2 / 3) { - struct sk_buff *bundler = buf_acquire(max_packet); + struct sk_buff *bundler = tipc_buf_acquire(max_packet); struct tipc_msg bundler_hdr; if (bundler) { @@ -1362,7 +1315,7 @@ again: /* Prepare header of first fragment: */ - buf_chain = buf = buf_acquire(max_pkt); + buf_chain = buf = tipc_buf_acquire(max_pkt); if (!buf) return -ENOMEM; buf->next = NULL; @@ -1419,7 +1372,7 @@ error: msg_set_size(&fragm_hdr, fragm_sz + INT_H_SIZE); msg_set_fragm_no(&fragm_hdr, ++fragm_no); prev = buf; - buf = buf_acquire(fragm_sz + INT_H_SIZE); + buf = tipc_buf_acquire(fragm_sz + INT_H_SIZE); if (!buf) goto error; @@ -2195,7 +2148,7 @@ void tipc_link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int probe_msg, if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) { if (!l_ptr->proto_msg_queue) { l_ptr->proto_msg_queue = - buf_acquire(sizeof(l_ptr->proto_msg)); + tipc_buf_acquire(sizeof(l_ptr->proto_msg)); } buf = l_ptr->proto_msg_queue; if (!buf) @@ -2209,7 +2162,7 @@ void tipc_link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int probe_msg, msg_dbg(msg, ">>"); - buf = buf_acquire(msg_size); + buf = tipc_buf_acquire(msg_size); if (!buf) return; @@ -2368,10 +2321,10 @@ exit: * tipc_link_tunnel(): Send one message via a link belonging to * another bearer. Owner node is locked. */ -void tipc_link_tunnel(struct link *l_ptr, - struct tipc_msg *tunnel_hdr, - struct tipc_msg *msg, - u32 selector) +static void tipc_link_tunnel(struct link *l_ptr, + struct tipc_msg *tunnel_hdr, + struct tipc_msg *msg, + u32 selector) { struct link *tunnel; struct sk_buff *buf; @@ -2384,7 +2337,7 @@ void tipc_link_tunnel(struct link *l_ptr, return; } msg_set_size(tunnel_hdr, length + INT_H_SIZE); - buf = buf_acquire(length + INT_H_SIZE); + buf = tipc_buf_acquire(length + INT_H_SIZE); if (!buf) { warn("Link changeover error, " "unable to send tunnel msg\n"); @@ -2430,7 +2383,7 @@ void tipc_link_changeover(struct link *l_ptr) if (!l_ptr->first_out) { struct sk_buff *buf; - buf = buf_acquire(INT_H_SIZE); + buf = tipc_buf_acquire(INT_H_SIZE); if (buf) { skb_copy_to_linear_data(buf, &tunnel_hdr, INT_H_SIZE); msg_set_size(&tunnel_hdr, INT_H_SIZE); @@ -2491,7 +2444,7 @@ void tipc_link_send_duplicate(struct link *l_ptr, struct link *tunnel) msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); /* Update */ msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); msg_set_size(&tunnel_hdr, length + INT_H_SIZE); - outbuf = buf_acquire(length + INT_H_SIZE); + outbuf = tipc_buf_acquire(length + INT_H_SIZE); if (outbuf == NULL) { warn("Link changeover error, " "unable to send duplicate msg\n"); @@ -2527,7 +2480,7 @@ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) u32 size = msg_size(msg); struct sk_buff *eb; - eb = buf_acquire(size); + eb = tipc_buf_acquire(size); if (eb) skb_copy_to_linear_data(eb, msg, size); return eb; @@ -2655,11 +2608,11 @@ void tipc_link_recv_bundle(struct sk_buff *buf) /* - * tipc_link_send_long_buf: Entry for buffers needing fragmentation. + * link_send_long_buf: Entry for buffers needing fragmentation. * The buffer is complete, inclusive total message length. * Returns user data length. */ -int tipc_link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) +static int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) { struct tipc_msg *inmsg = buf_msg(buf); struct tipc_msg fragm_hdr; @@ -2698,7 +2651,7 @@ int tipc_link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) fragm_sz = rest; msg_set_type(&fragm_hdr, LAST_FRAGMENT); } - fragm = buf_acquire(fragm_sz + INT_H_SIZE); + fragm = tipc_buf_acquire(fragm_sz + INT_H_SIZE); if (fragm == NULL) { warn("Link unable to fragment message\n"); dsz = -ENOMEM; @@ -2803,7 +2756,7 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, buf_discard(fbuf); return 0; } - pbuf = buf_acquire(msg_size(imsg)); + pbuf = tipc_buf_acquire(msg_size(imsg)); if (pbuf != NULL) { pbuf->next = *pending; *pending = pbuf; @@ -3197,44 +3150,6 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_s return buf; } -#if 0 -int link_control(const char *name, u32 op, u32 val) -{ - int res = -EINVAL; - struct link *l_ptr; - u32 bearer_id; - struct tipc_node * node; - u32 a; - - a = link_name2addr(name, &bearer_id); - read_lock_bh(&tipc_net_lock); - node = tipc_node_find(a); - if (node) { - tipc_node_lock(node); - l_ptr = node->links[bearer_id]; - if (l_ptr) { - if (op == TIPC_REMOVE_LINK) { - struct bearer *b_ptr = l_ptr->b_ptr; - spin_lock_bh(&b_ptr->publ.lock); - tipc_link_delete(l_ptr); - spin_unlock_bh(&b_ptr->publ.lock); - } - if (op == TIPC_CMD_BLOCK_LINK) { - tipc_link_reset(l_ptr); - l_ptr->blocked = 1; - } - if (op == TIPC_CMD_UNBLOCK_LINK) { - l_ptr->blocked = 0; - } - res = 0; - } - tipc_node_unlock(node); - } - read_unlock_bh(&tipc_net_lock); - return res; -} -#endif - /** * tipc_link_get_max_pkt - get maximum packet size to use when sending to destination * @dest: network address of destination node @@ -3265,28 +3180,6 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector) return res; } -#if 0 -static void link_dump_rec_queue(struct link *l_ptr) -{ - struct sk_buff *crs; - - if (!l_ptr->oldest_deferred_in) { - info("Reception queue empty\n"); - return; - } - info("Contents of Reception queue:\n"); - crs = l_ptr->oldest_deferred_in; - while (crs) { - if (crs->data == (void *)0x0000a3a3) { - info("buffer %x invalid\n", crs); - return; - } - msg_dbg(buf_msg(crs), "In rec queue:\n"); - crs = crs->next; - } -} -#endif - static void link_dump_send_queue(struct link *l_ptr) { if (l_ptr->next_out) { diff --git a/net/tipc/link.h b/net/tipc/link.h index 2e5385c..f98bc61 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -210,10 +210,6 @@ struct link { u32 msg_length_counts; u32 msg_lengths_total; u32 msg_length_profile[7]; -#if 0 - u32 sent_tunneled; - u32 recv_tunneled; -#endif } stats; struct print_buf print_buf; @@ -229,7 +225,6 @@ void tipc_link_send_duplicate(struct link *l_ptr, struct link *dest); void tipc_link_reset_fragments(struct link *l_ptr); int tipc_link_is_up(struct link *l_ptr); int tipc_link_is_active(struct link *l_ptr); -void tipc_link_start(struct link *l_ptr); u32 tipc_link_push_packet(struct link *l_ptr); void tipc_link_stop(struct link *l_ptr); struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space, u16 cmd); @@ -243,9 +238,6 @@ int tipc_link_send_sections_fast(struct port* sender, struct iovec const *msg_sect, const u32 num_sect, u32 destnode); -int tipc_link_send_long_buf(struct link *l_ptr, struct sk_buff *buf); -void tipc_link_tunnel(struct link *l_ptr, struct tipc_msg *tnl_hdr, - struct tipc_msg *msg, u32 selector); void tipc_link_recv_bundle(struct sk_buff *buf); int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, @@ -279,12 +271,12 @@ static inline int between(u32 lower, u32 upper, u32 n) static inline int less_eq(u32 left, u32 right) { - return (mod(right - left) < 32768u); + return mod(right - left) < 32768u; } static inline int less(u32 left, u32 right) { - return (less_eq(left, right) && (mod(right) != mod(left))); + return less_eq(left, right) && (mod(right) != mod(left)); } static inline u32 lesser(u32 left, u32 right) @@ -299,32 +291,32 @@ static inline u32 lesser(u32 left, u32 right) static inline int link_working_working(struct link *l_ptr) { - return (l_ptr->state == WORKING_WORKING); + return l_ptr->state == WORKING_WORKING; } static inline int link_working_unknown(struct link *l_ptr) { - return (l_ptr->state == WORKING_UNKNOWN); + return l_ptr->state == WORKING_UNKNOWN; } static inline int link_reset_unknown(struct link *l_ptr) { - return (l_ptr->state == RESET_UNKNOWN); + return l_ptr->state == RESET_UNKNOWN; } static inline int link_reset_reset(struct link *l_ptr) { - return (l_ptr->state == RESET_RESET); + return l_ptr->state == RESET_RESET; } static inline int link_blocked(struct link *l_ptr) { - return (l_ptr->exp_msg_count || l_ptr->blocked); + return l_ptr->exp_msg_count || l_ptr->blocked; } static inline int link_congested(struct link *l_ptr) { - return (l_ptr->out_queue_size >= l_ptr->queue_limit[0]); + return l_ptr->out_queue_size >= l_ptr->queue_limit[0]; } #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 3810638..ecb532f 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -112,7 +112,7 @@ int tipc_msg_build(struct tipc_msg *hdr, return dsz; } - *buf = buf_acquire(sz); + *buf = tipc_buf_acquire(sz); if (!(*buf)) return -ENOMEM; skb_copy_to_linear_data(*buf, hdr, hsz); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 995d2da..031aad1 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -104,7 +104,7 @@ static inline u32 msg_user(struct tipc_msg *m) static inline u32 msg_isdata(struct tipc_msg *m) { - return (msg_user(m) <= TIPC_CRITICAL_IMPORTANCE); + return msg_user(m) <= TIPC_CRITICAL_IMPORTANCE; } static inline void msg_set_user(struct tipc_msg *m, u32 n) @@ -289,7 +289,7 @@ static inline void msg_set_destnode(struct tipc_msg *m, u32 a) static inline int msg_is_dest(struct tipc_msg *m, u32 d) { - return(msg_short(m) || (msg_destnode(m) == d)); + return msg_short(m) || (msg_destnode(m) == d); } static inline u32 msg_routed(struct tipc_msg *m) @@ -632,7 +632,7 @@ static inline void msg_set_bcast_tag(struct tipc_msg *m, u32 n) static inline u32 msg_max_pkt(struct tipc_msg *m) { - return (msg_bits(m, 9, 16, 0xffff) * 4); + return msg_bits(m, 9, 16, 0xffff) * 4; } static inline void msg_set_max_pkt(struct tipc_msg *m, u32 n) diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 6ac3c54..7b90717 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -98,7 +98,7 @@ static void publ_to_item(struct distr_item *i, struct publication *p) static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest) { - struct sk_buff *buf = buf_acquire(LONG_H_SIZE + size); + struct sk_buff *buf = tipc_buf_acquire(LONG_H_SIZE + size); struct tipc_msg *msg; if (buf != NULL) { diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index c13c2c7..3a8de43 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -116,7 +116,7 @@ DEFINE_RWLOCK(tipc_nametbl_lock); static int hash(int x) { - return(x & (tipc_nametbl_size - 1)); + return x & (tipc_nametbl_size - 1); } /** @@ -1009,16 +1009,6 @@ static void nametbl_list(struct print_buf *buf, u32 depth_info, } } -#if 0 -void tipc_nametbl_print(struct print_buf *buf, const char *str) -{ - tipc_printf(buf, str); - read_lock_bh(&tipc_nametbl_lock); - nametbl_list(buf, 0, 0, 0, 0); - read_unlock_bh(&tipc_nametbl_lock); -} -#endif - #define MAX_NAME_TBL_QUERY 32768 struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space) @@ -1051,13 +1041,6 @@ struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space) return buf; } -#if 0 -void tipc_nametbl_dump(void) -{ - nametbl_list(TIPC_CONS, 0, 0, 0, 0); -} -#endif - int tipc_nametbl_init(void) { table.types = kcalloc(tipc_nametbl_size, sizeof(struct hlist_head), diff --git a/net/tipc/net.c b/net/tipc/net.c index 7e05af4..1a621cf 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -129,15 +129,6 @@ u32 tipc_net_select_router(u32 addr, u32 ref) return tipc_zone_select_router(tipc_net.zones[tipc_zone(addr)], addr, ref); } -#if 0 -u32 tipc_net_next_node(u32 a) -{ - if (tipc_net.zones[tipc_zone(a)]) - return tipc_zone_next_node(a); - return 0; -} -#endif - void tipc_net_remove_as_router(u32 router) { u32 z_num; diff --git a/net/tipc/node.c b/net/tipc/node.c index b702c7b..b4d87eb 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -50,7 +50,8 @@ void node_print(struct print_buf *buf, struct tipc_node *n_ptr, char *str); static void node_lost_contact(struct tipc_node *n_ptr); static void node_established_contact(struct tipc_node *n_ptr); -struct tipc_node *tipc_nodes = NULL; /* sorted list of nodes within cluster */ +/* sorted list of nodes within cluster */ +static struct tipc_node *tipc_nodes = NULL; static DEFINE_SPINLOCK(node_create_lock); @@ -125,16 +126,6 @@ void tipc_node_delete(struct tipc_node *n_ptr) if (!n_ptr) return; -#if 0 - /* Not needed because links are already deleted via tipc_bearer_stop() */ - - u32 l_num; - - for (l_num = 0; l_num < MAX_BEARERS; l_num++) { - link_delete(n_ptr->links[l_num]); - } -#endif - dbg("node %x deleted\n", n_ptr->addr); kfree(n_ptr); } @@ -242,17 +233,17 @@ int tipc_node_has_active_links(struct tipc_node *n_ptr) int tipc_node_has_redundant_links(struct tipc_node *n_ptr) { - return (n_ptr->working_links > 1); + return n_ptr->working_links > 1; } static int tipc_node_has_active_routes(struct tipc_node *n_ptr) { - return (n_ptr && (n_ptr->last_router >= 0)); + return n_ptr && (n_ptr->last_router >= 0); } int tipc_node_is_up(struct tipc_node *n_ptr) { - return (tipc_node_has_active_links(n_ptr) || tipc_node_has_active_routes(n_ptr)); + return tipc_node_has_active_links(n_ptr) || tipc_node_has_active_routes(n_ptr); } struct tipc_node *tipc_node_attach_link(struct link *l_ptr) @@ -597,38 +588,6 @@ void tipc_node_remove_router(struct tipc_node *n_ptr, u32 router) node_lost_contact(n_ptr); } -#if 0 -void node_print(struct print_buf *buf, struct tipc_node *n_ptr, char *str) -{ - u32 i; - - tipc_printf(buf, "\n\n%s", str); - for (i = 0; i < MAX_BEARERS; i++) { - if (!n_ptr->links[i]) - continue; - tipc_printf(buf, "Links[%u]: %x, ", i, n_ptr->links[i]); - } - tipc_printf(buf, "Active links: [%x,%x]\n", - n_ptr->active_links[0], n_ptr->active_links[1]); -} -#endif - -u32 tipc_available_nodes(const u32 domain) -{ - struct tipc_node *n_ptr; - u32 cnt = 0; - - read_lock_bh(&tipc_net_lock); - for (n_ptr = tipc_nodes; n_ptr; n_ptr = n_ptr->next) { - if (!tipc_in_scope(domain, n_ptr->addr)) - continue; - if (tipc_node_is_up(n_ptr)) - cnt++; - } - read_unlock_bh(&tipc_net_lock); - return cnt; -} - struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) { u32 domain; diff --git a/net/tipc/node.h b/net/tipc/node.h index 45f3db3..fff331b 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -96,7 +96,6 @@ struct tipc_node { } bclink; }; -extern struct tipc_node *tipc_nodes; extern u32 tipc_own_tag; struct tipc_node *tipc_node_create(u32 addr); diff --git a/net/tipc/port.c b/net/tipc/port.c index d760336..82092ea 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -293,34 +293,6 @@ int tipc_deleteport(u32 ref) return 0; } -/** - * tipc_get_port() - return port associated with 'ref' - * - * Note: Port is not locked. - */ - -struct tipc_port *tipc_get_port(const u32 ref) -{ - return (struct tipc_port *)tipc_ref_deref(ref); -} - -/** - * tipc_get_handle - return user handle associated to port 'ref' - */ - -void *tipc_get_handle(const u32 ref) -{ - struct port *p_ptr; - void * handle; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return NULL; - handle = p_ptr->publ.usr_handle; - tipc_port_unlock(p_ptr); - return handle; -} - static int port_unreliable(struct port *p_ptr) { return msg_src_droppable(&p_ptr->publ.phdr); @@ -392,7 +364,7 @@ static struct sk_buff *port_build_proto_msg(u32 destport, u32 destnode, struct sk_buff *buf; struct tipc_msg *msg; - buf = buf_acquire(LONG_H_SIZE); + buf = tipc_buf_acquire(LONG_H_SIZE); if (buf) { msg = buf_msg(buf); tipc_msg_init(msg, usr, type, LONG_H_SIZE, destnode); @@ -433,7 +405,7 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) hdr_sz = MCAST_H_SIZE; else hdr_sz = LONG_H_SIZE; - rbuf = buf_acquire(data_sz + hdr_sz); + rbuf = tipc_buf_acquire(data_sz + hdr_sz); if (rbuf == NULL) { buf_discard(buf); return data_sz; @@ -710,50 +682,6 @@ struct sk_buff *tipc_port_get_ports(void) return buf; } -#if 0 - -#define MAX_PORT_STATS 2000 - -struct sk_buff *port_show_stats(const void *req_tlv_area, int req_tlv_space) -{ - u32 ref; - struct port *p_ptr; - struct sk_buff *buf; - struct tlv_desc *rep_tlv; - struct print_buf pb; - int str_len; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_PORT_REF)) - return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - - ref = *(u32 *)TLV_DATA(req_tlv_area); - ref = ntohl(ref); - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return cfg_reply_error_string("port not found"); - - buf = tipc_cfg_reply_alloc(TLV_SPACE(MAX_PORT_STATS)); - if (!buf) { - tipc_port_unlock(p_ptr); - return NULL; - } - rep_tlv = (struct tlv_desc *)buf->data; - - tipc_printbuf_init(&pb, TLV_DATA(rep_tlv), MAX_PORT_STATS); - port_print(p_ptr, &pb, 1); - /* NEED TO FILL IN ADDITIONAL PORT STATISTICS HERE */ - tipc_port_unlock(p_ptr); - str_len = tipc_printbuf_validate(&pb); - - skb_put(buf, TLV_SPACE(str_len)); - TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); - - return buf; -} - -#endif - void tipc_port_reinit(void) { struct port *p_ptr; @@ -1286,50 +1214,13 @@ int tipc_shutdown(u32 ref) return tipc_disconnect(ref); } -int tipc_isconnected(u32 ref, int *isconnected) -{ - struct port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *isconnected = p_ptr->publ.connected; - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_peer(u32 ref, struct tipc_portid *peer) -{ - struct port *p_ptr; - int res; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - if (p_ptr->publ.connected) { - peer->ref = port_peerport(p_ptr); - peer->node = port_peernode(p_ptr); - res = 0; - } else - res = -ENOTCONN; - tipc_port_unlock(p_ptr); - return res; -} - -int tipc_ref_valid(u32 ref) -{ - /* Works irrespective of type */ - return !!tipc_ref_deref(ref); -} - - /* * tipc_port_recv_sections(): Concatenate and deliver sectioned * message for this node. */ -int tipc_port_recv_sections(struct port *sender, unsigned int num_sect, - struct iovec const *msg_sect) +static int tipc_port_recv_sections(struct port *sender, unsigned int num_sect, + struct iovec const *msg_sect) { struct sk_buff *buf; int res; @@ -1380,65 +1271,16 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) } /** - * tipc_send_buf - send message buffer on connection - */ - -int tipc_send_buf(u32 ref, struct sk_buff *buf, unsigned int dsz) -{ - struct port *p_ptr; - struct tipc_msg *msg; - u32 destnode; - u32 hsz; - u32 sz; - u32 res; - - p_ptr = tipc_port_deref(ref); - if (!p_ptr || !p_ptr->publ.connected) - return -EINVAL; - - msg = &p_ptr->publ.phdr; - hsz = msg_hdr_sz(msg); - sz = hsz + dsz; - msg_set_size(msg, sz); - if (skb_cow(buf, hsz)) - return -ENOMEM; - - skb_push(buf, hsz); - skb_copy_to_linear_data(buf, msg, hsz); - destnode = msg_destnode(msg); - p_ptr->publ.congested = 1; - if (!tipc_port_congested(p_ptr)) { - if (likely(destnode != tipc_own_addr)) - res = tipc_send_buf_fast(buf, destnode); - else { - tipc_port_recv_msg(buf); - res = sz; - } - if (likely(res != -ELINKCONG)) { - port_incr_out_seqno(p_ptr); - p_ptr->sent++; - p_ptr->publ.congested = 0; - return res; - } - } - if (port_unreliable(p_ptr)) { - p_ptr->publ.congested = 0; - return dsz; - } - return -ELINKCONG; -} - -/** * tipc_forward2name - forward message sections to port name */ -int tipc_forward2name(u32 ref, - struct tipc_name const *name, - u32 domain, - u32 num_sect, - struct iovec const *msg_sect, - struct tipc_portid const *orig, - unsigned int importance) +static int tipc_forward2name(u32 ref, + struct tipc_name const *name, + u32 domain, + u32 num_sect, + struct iovec const *msg_sect, + struct tipc_portid const *orig, + unsigned int importance) { struct port *p_ptr; struct tipc_msg *msg; @@ -1501,89 +1343,15 @@ int tipc_send2name(u32 ref, } /** - * tipc_forward_buf2name - forward message buffer to port name - */ - -int tipc_forward_buf2name(u32 ref, - struct tipc_name const *name, - u32 domain, - struct sk_buff *buf, - unsigned int dsz, - struct tipc_portid const *orig, - unsigned int importance) -{ - struct port *p_ptr; - struct tipc_msg *msg; - u32 destnode = domain; - u32 destport; - int res; - - p_ptr = (struct port *)tipc_ref_deref(ref); - if (!p_ptr || p_ptr->publ.connected) - return -EINVAL; - - msg = &p_ptr->publ.phdr; - if (importance <= TIPC_CRITICAL_IMPORTANCE) - msg_set_importance(msg, importance); - msg_set_type(msg, TIPC_NAMED_MSG); - msg_set_orignode(msg, orig->node); - msg_set_origport(msg, orig->ref); - msg_set_nametype(msg, name->type); - msg_set_nameinst(msg, name->instance); - msg_set_lookup_scope(msg, tipc_addr_scope(domain)); - msg_set_hdr_sz(msg, LONG_H_SIZE); - msg_set_size(msg, LONG_H_SIZE + dsz); - destport = tipc_nametbl_translate(name->type, name->instance, &destnode); - msg_set_destnode(msg, destnode); - msg_set_destport(msg, destport); - msg_dbg(msg, "forw2name ==> "); - if (skb_cow(buf, LONG_H_SIZE)) - return -ENOMEM; - skb_push(buf, LONG_H_SIZE); - skb_copy_to_linear_data(buf, msg, LONG_H_SIZE); - msg_dbg(buf_msg(buf),"PREP:"); - if (likely(destport)) { - p_ptr->sent++; - if (destnode == tipc_own_addr) - return tipc_port_recv_msg(buf); - res = tipc_send_buf_fast(buf, destnode); - if (likely(res != -ELINKCONG)) - return res; - if (port_unreliable(p_ptr)) - return dsz; - return -ELINKCONG; - } - return tipc_reject_msg(buf, TIPC_ERR_NO_NAME); -} - -/** - * tipc_send_buf2name - send message buffer to port name - */ - -int tipc_send_buf2name(u32 ref, - struct tipc_name const *dest, - u32 domain, - struct sk_buff *buf, - unsigned int dsz) -{ - struct tipc_portid orig; - - orig.ref = ref; - orig.node = tipc_own_addr; - return tipc_forward_buf2name(ref, dest, domain, buf, dsz, &orig, - TIPC_PORT_IMPORTANCE); -} - -/** * tipc_forward2port - forward message sections to port identity */ -int tipc_forward2port(u32 ref, - struct tipc_portid const *dest, - unsigned int num_sect, - struct iovec const *msg_sect, - struct tipc_portid const *orig, - unsigned int importance) +static int tipc_forward2port(u32 ref, + struct tipc_portid const *dest, + unsigned int num_sect, + struct iovec const *msg_sect, + struct tipc_portid const *orig, + unsigned int importance) { struct port *p_ptr; struct tipc_msg *msg; @@ -1635,12 +1403,12 @@ int tipc_send2port(u32 ref, /** * tipc_forward_buf2port - forward message buffer to port identity */ -int tipc_forward_buf2port(u32 ref, - struct tipc_portid const *dest, - struct sk_buff *buf, - unsigned int dsz, - struct tipc_portid const *orig, - unsigned int importance) +static int tipc_forward_buf2port(u32 ref, + struct tipc_portid const *dest, + struct sk_buff *buf, + unsigned int dsz, + struct tipc_portid const *orig, + unsigned int importance) { struct port *p_ptr; struct tipc_msg *msg; diff --git a/net/tipc/port.h b/net/tipc/port.h index 8d1652a..73bbf44 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -109,8 +109,6 @@ struct port { extern spinlock_t tipc_port_list_lock; struct port_list; -int tipc_port_recv_sections(struct port *p_ptr, u32 num_sect, - struct iovec const *msg_sect); int tipc_port_reject_sections(struct port *p_ptr, struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, int err); @@ -157,7 +155,7 @@ static inline u32 tipc_peer_node(struct port *p_ptr) static inline int tipc_port_congested(struct port *p_ptr) { - return((p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2)); + return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); } /** diff --git a/net/tipc/ref.c b/net/tipc/ref.c index 8dea665..ab8ad32 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -282,23 +282,6 @@ void *tipc_ref_lock(u32 ref) return NULL; } -/** - * tipc_ref_unlock - unlock referenced object - */ - -void tipc_ref_unlock(u32 ref) -{ - if (likely(tipc_ref_table.entries)) { - struct reference *entry; - - entry = &tipc_ref_table.entries[ref & - tipc_ref_table.index_mask]; - if (likely((entry->ref == ref) && (entry->object))) - spin_unlock_bh(&entry->lock); - else - err("Attempt to unlock non-existent reference\n"); - } -} /** * tipc_ref_deref - return pointer referenced object (without locking it) diff --git a/net/tipc/ref.h b/net/tipc/ref.h index 7e3798e..5bc8e7a 100644 --- a/net/tipc/ref.h +++ b/net/tipc/ref.h @@ -44,7 +44,6 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock); void tipc_ref_discard(u32 ref); void *tipc_ref_lock(u32 ref); -void tipc_ref_unlock(u32 ref); void *tipc_ref_deref(u32 ref); #endif diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f7ac94d..33217fc 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1195,7 +1195,7 @@ static int rx_queue_full(struct tipc_msg *msg, u32 queue_size, u32 base) if (msg_connected(msg)) threshold *= 4; - return (queue_size >= threshold); + return queue_size >= threshold; } /** diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index ab6eab4..18813ac 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -598,12 +598,3 @@ void tipc_subscr_stop(void) topsrv.user_ref = 0; } } - - -int tipc_ispublished(struct tipc_name const *name) -{ - u32 domain = 0; - - return(tipc_nametbl_translate(name->type, name->instance,&domain) != 0); -} - diff --git a/net/tipc/zone.c b/net/tipc/zone.c index 2c01ba2..83f8b5e 100644 --- a/net/tipc/zone.c +++ b/net/tipc/zone.c @@ -160,14 +160,3 @@ u32 tipc_zone_select_router(struct _zone *z_ptr, u32 addr, u32 ref) } return 0; } - - -u32 tipc_zone_next_node(u32 addr) -{ - struct cluster *c_ptr = tipc_cltr_find(addr); - - if (c_ptr) - return tipc_cltr_next_node(c_ptr, addr); - return 0; -} - diff --git a/net/tipc/zone.h b/net/tipc/zone.h index 7bdc340..bd1c20c 100644 --- a/net/tipc/zone.h +++ b/net/tipc/zone.h @@ -61,7 +61,6 @@ void tipc_zone_send_external_routes(struct _zone *z_ptr, u32 dest); struct _zone *tipc_zone_create(u32 addr); void tipc_zone_delete(struct _zone *z_ptr); void tipc_zone_attach_cluster(struct _zone *z_ptr, struct cluster *c_ptr); -u32 tipc_zone_next_node(u32 addr); static inline struct _zone *tipc_zone_find(u32 addr) { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c586da3..0ebc777 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1511,6 +1511,8 @@ restart: goto restart; } + if (sock_flag(other, SOCK_RCVTSTAMP)) + __net_timestamp(skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); other->sk_data_ready(other, len); @@ -1722,6 +1724,9 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (err) goto out_free; + if (sock_flag(sk, SOCK_RCVTSTAMP)) + __sock_recv_timestamp(msg, sk, skb); + if (!siocb->scm) { siocb->scm = &tmp_scm; memset(&tmp_scm, 0, sizeof(tmp_scm)); diff --git a/net/wireless/core.c b/net/wireless/core.c index d587ad2..9c21ebf 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -729,6 +729,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, dev->ethtool_ops = &cfg80211_ethtool_ops; if ((wdev->iftype == NL80211_IFTYPE_STATION || + wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) dev->priv_flags |= IFF_DONT_BRIDGE; break; @@ -737,6 +738,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, dev, true); break; + case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: wdev_lock(wdev); #ifdef CONFIG_CFG80211_WEXT @@ -915,52 +917,3 @@ static void __exit cfg80211_exit(void) destroy_workqueue(cfg80211_wq); } module_exit(cfg80211_exit); - -static int ___wiphy_printk(const char *level, const struct wiphy *wiphy, - struct va_format *vaf) -{ - if (!wiphy) - return printk("%s(NULL wiphy *): %pV", level, vaf); - - return printk("%s%s: %pV", level, wiphy_name(wiphy), vaf); -} - -int __wiphy_printk(const char *level, const struct wiphy *wiphy, - const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - int r; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - r = ___wiphy_printk(level, wiphy, &vaf); - va_end(args); - - return r; -} -EXPORT_SYMBOL(__wiphy_printk); - -#define define_wiphy_printk_level(func, kern_level) \ -int func(const struct wiphy *wiphy, const char *fmt, ...) \ -{ \ - struct va_format vaf; \ - va_list args; \ - int r; \ - \ - va_start(args, fmt); \ - \ - vaf.fmt = fmt; \ - vaf.va = &args; \ - \ - r = ___wiphy_printk(kern_level, wiphy, &vaf); \ - va_end(args); \ - \ - return r; \ -} \ -EXPORT_SYMBOL(func); - -define_wiphy_printk_level(wiphy_debug, KERN_DEBUG); diff --git a/net/wireless/core.h b/net/wireless/core.h index 58ab2c7..6583cca 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -86,7 +86,7 @@ struct cfg80211_registered_device *wiphy_to_dev(struct wiphy *wiphy) static inline bool wiphy_idx_valid(int wiphy_idx) { - return (wiphy_idx >= 0); + return wiphy_idx >= 0; } @@ -95,7 +95,10 @@ extern struct mutex cfg80211_mutex; extern struct list_head cfg80211_rdev_list; extern int cfg80211_rdev_list_generation; -#define assert_cfg80211_lock() WARN_ON(!mutex_is_locked(&cfg80211_mutex)) +static inline void assert_cfg80211_lock(void) +{ + lockdep_assert_held(&cfg80211_mutex); +} /* * You can use this to mark a wiphy_idx as not having an associated wiphy. @@ -202,8 +205,8 @@ static inline void wdev_unlock(struct wireless_dev *wdev) mutex_unlock(&wdev->mtx); } -#define ASSERT_RDEV_LOCK(rdev) WARN_ON(!mutex_is_locked(&(rdev)->mtx)); -#define ASSERT_WDEV_LOCK(wdev) WARN_ON(!mutex_is_locked(&(wdev)->mtx)); +#define ASSERT_RDEV_LOCK(rdev) lockdep_assert_held(&(rdev)->mtx) +#define ASSERT_WDEV_LOCK(wdev) lockdep_assert_held(&(wdev)->mtx) enum cfg80211_event_type { EVENT_CONNECT_RESULT, @@ -372,7 +375,7 @@ bool cfg80211_sme_failed_reassoc(struct wireless_dev *wdev); /* internal helpers */ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, - const u8 *mac_addr); + bool pairwise, const u8 *mac_addr); void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap); void cfg80211_sme_scan_done(struct net_device *dev); diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 27a8ce9..f33fbb7 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -88,6 +88,25 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, if (wdev->ssid_len) return -EALREADY; + if (!params->basic_rates) { + /* + * If no rates were explicitly configured, + * use the mandatory rate set for 11b or + * 11a for maximum compatibility. + */ + struct ieee80211_supported_band *sband = + rdev->wiphy.bands[params->channel->band]; + int j; + u32 flag = params->channel->band == IEEE80211_BAND_5GHZ ? + IEEE80211_RATE_MANDATORY_A : + IEEE80211_RATE_MANDATORY_B; + + for (j = 0; j < sband->n_bitrates; j++) { + if (sband->bitrates[j].flags & flag) + params->basic_rates |= BIT(j); + } + } + if (WARN_ON(wdev->connect_keys)) kfree(wdev->connect_keys); wdev->connect_keys = connkeys; @@ -141,7 +160,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) */ if (rdev->ops->del_key) for (i = 0; i < 6; i++) - rdev->ops->del_key(wdev->wiphy, dev, i, NULL); + rdev->ops->del_key(wdev->wiphy, dev, i, false, NULL); if (wdev->current_bss) { cfg80211_unhold_bss(wdev->current_bss); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 8515b1e..26838d9 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -764,6 +764,8 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, u16 frame_type, const u8 *match_data, int match_len) { + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); struct cfg80211_mgmt_registration *reg, *nreg; int err = 0; u16 mgmt_type; @@ -810,22 +812,37 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, nreg->frame_type = cpu_to_le16(frame_type); list_add(&nreg->list, &wdev->mgmt_registrations); + if (rdev->ops->mgmt_frame_register) + rdev->ops->mgmt_frame_register(wiphy, wdev->netdev, + frame_type, true); + out: spin_unlock_bh(&wdev->mgmt_registrations_lock); + return err; } void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid) { + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); struct cfg80211_mgmt_registration *reg, *tmp; spin_lock_bh(&wdev->mgmt_registrations_lock); list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) { - if (reg->nlpid == nlpid) { - list_del(®->list); - kfree(reg); + if (reg->nlpid != nlpid) + continue; + + if (rdev->ops->mgmt_frame_register) { + u16 frame_type = le16_to_cpu(reg->frame_type); + + rdev->ops->mgmt_frame_register(wiphy, wdev->netdev, + frame_type, false); } + + list_del(®->list); + kfree(reg); } spin_unlock_bh(&wdev->mgmt_registrations_lock); @@ -876,20 +893,53 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category != WLAN_CATEGORY_PUBLIC) { - /* Verify that we are associated with the destination AP */ + int err = 0; + wdev_lock(wdev); - if (!wdev->current_bss || - memcmp(wdev->current_bss->pub.bssid, mgmt->bssid, - ETH_ALEN) != 0 || - (wdev->iftype == NL80211_IFTYPE_STATION && - memcmp(wdev->current_bss->pub.bssid, mgmt->da, - ETH_ALEN) != 0)) { - wdev_unlock(wdev); - return -ENOTCONN; - } + switch (wdev->iftype) { + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: + if (!wdev->current_bss) { + err = -ENOTCONN; + break; + } + + if (memcmp(wdev->current_bss->pub.bssid, + mgmt->bssid, ETH_ALEN)) { + err = -ENOTCONN; + break; + } + + /* + * check for IBSS DA must be done by driver as + * cfg80211 doesn't track the stations + */ + if (wdev->iftype == NL80211_IFTYPE_ADHOC) + break; + /* for station, check that DA is the AP */ + if (memcmp(wdev->current_bss->pub.bssid, + mgmt->da, ETH_ALEN)) { + err = -ENOTCONN; + break; + } + break; + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_AP_VLAN: + if (memcmp(mgmt->bssid, dev->dev_addr, ETH_ALEN)) + err = -EINVAL; + break; + default: + err = -EOPNOTSUPP; + break; + } wdev_unlock(wdev); + + if (err) + return err; } if (memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) != 0) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 85a23de..c506241 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -23,6 +23,11 @@ #include "nl80211.h" #include "reg.h" +static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info); +static void nl80211_post_doit(struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info); + /* the netlink family */ static struct genl_family nl80211_fam = { .id = GENL_ID_GENERATE, /* don't bother with a hardcoded ID */ @@ -31,6 +36,8 @@ static struct genl_family nl80211_fam = { .version = 1, /* no particular meaning now */ .maxattr = NL80211_ATTR_MAX, .netnsok = true, + .pre_doit = nl80211_pre_doit, + .post_doit = nl80211_post_doit, }; /* internal helper: get rdev and dev */ @@ -86,6 +93,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [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_KEY_TYPE] = { .type = NLA_U32 }, [NL80211_ATTR_BEACON_INTERVAL] = { .type = NLA_U32 }, [NL80211_ATTR_DTIM_PERIOD] = { .type = NLA_U32 }, @@ -161,7 +169,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_FRAME_TYPE] = { .type = NLA_U16 }, }; -/* policy for the attributes */ +/* policy for the key attributes */ static const struct nla_policy nl80211_key_policy[NL80211_KEY_MAX + 1] = { [NL80211_KEY_DATA] = { .type = NLA_BINARY, .len = WLAN_MAX_KEY_LEN }, [NL80211_KEY_IDX] = { .type = NLA_U8 }, @@ -169,6 +177,7 @@ static const struct nla_policy nl80211_key_policy[NL80211_KEY_MAX + 1] = { [NL80211_KEY_SEQ] = { .type = NLA_BINARY, .len = 8 }, [NL80211_KEY_DEFAULT] = { .type = NLA_FLAG }, [NL80211_KEY_DEFAULT_MGMT] = { .type = NLA_FLAG }, + [NL80211_KEY_TYPE] = { .type = NLA_U32 }, }; /* ifidx get helper */ @@ -191,6 +200,47 @@ static int nl80211_get_ifidx(struct netlink_callback *cb) return res; } +static int nl80211_prepare_netdev_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct cfg80211_registered_device **rdev, + struct net_device **dev) +{ + int ifidx = cb->args[0]; + int err; + + if (!ifidx) + ifidx = nl80211_get_ifidx(cb); + if (ifidx < 0) + return ifidx; + + cb->args[0] = ifidx; + + rtnl_lock(); + + *dev = __dev_get_by_index(sock_net(skb->sk), ifidx); + if (!*dev) { + err = -ENODEV; + goto out_rtnl; + } + + *rdev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + goto out_rtnl; + } + + return 0; + out_rtnl: + rtnl_unlock(); + return err; +} + +static void nl80211_finish_netdev_dump(struct cfg80211_registered_device *rdev) +{ + cfg80211_unlock_rdev(rdev); + rtnl_unlock(); +} + /* IE validation */ static bool is_valid_ie_attr(const struct nlattr *attr) { @@ -258,6 +308,7 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct key_parse { struct key_params p; int idx; + int type; bool def, defmgmt; }; @@ -288,6 +339,12 @@ static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k) if (tb[NL80211_KEY_CIPHER]) k->p.cipher = nla_get_u32(tb[NL80211_KEY_CIPHER]); + if (tb[NL80211_KEY_TYPE]) { + k->type = nla_get_u32(tb[NL80211_KEY_TYPE]); + if (k->type < 0 || k->type >= NUM_NL80211_KEYTYPES) + return -EINVAL; + } + return 0; } @@ -312,6 +369,12 @@ static int nl80211_parse_key_old(struct genl_info *info, struct key_parse *k) k->def = !!info->attrs[NL80211_ATTR_KEY_DEFAULT]; k->defmgmt = !!info->attrs[NL80211_ATTR_KEY_DEFAULT_MGMT]; + if (info->attrs[NL80211_ATTR_KEY_TYPE]) { + k->type = nla_get_u32(info->attrs[NL80211_ATTR_KEY_TYPE]); + if (k->type < 0 || k->type >= NUM_NL80211_KEYTYPES) + return -EINVAL; + } + return 0; } @@ -321,6 +384,7 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) memset(k, 0, sizeof(*k)); k->idx = -1; + k->type = -1; if (info->attrs[NL80211_ATTR_KEY]) err = nl80211_parse_key_new(info->attrs[NL80211_ATTR_KEY], k); @@ -385,7 +449,7 @@ nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, } else if (parse.defmgmt) goto error; err = cfg80211_validate_key_settings(rdev, &parse.p, - parse.idx, NULL); + parse.idx, false, NULL); if (err) goto error; result->params[parse.idx].cipher = parse.p.cipher; @@ -404,18 +468,17 @@ static int nl80211_key_allowed(struct wireless_dev *wdev) { ASSERT_WDEV_LOCK(wdev); - if (!netif_running(wdev->netdev)) - return -ENETDOWN; - switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_P2P_GO: break; case NL80211_IFTYPE_ADHOC: if (!wdev->current_bss) return -ENOLINK; break; case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: if (wdev->sme_state != CFG80211_SME_CONNECTED) return -ENOLINK; break; @@ -469,6 +532,9 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, NLA_PUT_U16(msg, NL80211_ATTR_MAX_SCAN_IE_LEN, dev->wiphy.max_scan_ie_len); + if (dev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) + NLA_PUT_FLAG(msg, NL80211_ATTR_SUPPORT_IBSS_RSN); + NLA_PUT(msg, NL80211_ATTR_CIPHER_SUITES, sizeof(u32) * dev->wiphy.n_cipher_suites, dev->wiphy.cipher_suites); @@ -601,6 +667,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, NLA_PUT_U32(msg, i, NL80211_CMD_SET_WIPHY_NETNS); } CMD(set_channel, SET_CHANNEL); + CMD(set_wds_peer, SET_WDS_PEER); #undef CMD @@ -701,28 +768,18 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) static int nl80211_get_wiphy(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; - struct cfg80211_registered_device *dev; - - dev = cfg80211_get_dev_from_info(info); - if (IS_ERR(dev)) - return PTR_ERR(dev); + struct cfg80211_registered_device *dev = info->user_ptr[0]; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) - goto out_err; - - if (nl80211_send_wiphy(msg, info->snd_pid, info->snd_seq, 0, dev) < 0) - goto out_free; + return -ENOMEM; - cfg80211_unlock_rdev(dev); + if (nl80211_send_wiphy(msg, info->snd_pid, info->snd_seq, 0, dev) < 0) { + nlmsg_free(msg); + return -ENOBUFS; + } return genlmsg_reply(msg, info); - - out_free: - nlmsg_free(msg); - out_err: - cfg80211_unlock_rdev(dev); - return -ENOBUFS; } static const struct nla_policy txq_params_policy[NL80211_TXQ_ATTR_MAX + 1] = { @@ -766,7 +823,8 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) wdev->iftype == NL80211_IFTYPE_AP || wdev->iftype == NL80211_IFTYPE_WDS || wdev->iftype == NL80211_IFTYPE_MESH_POINT || - wdev->iftype == NL80211_IFTYPE_MONITOR; + wdev->iftype == NL80211_IFTYPE_MONITOR || + wdev->iftype == NL80211_IFTYPE_P2P_GO; } static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, @@ -810,38 +868,48 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *netdev; - int result; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *netdev = info->user_ptr[1]; - rtnl_lock(); + return __nl80211_set_channel(rdev, netdev->ieee80211_ptr, info); +} - result = get_rdev_dev_by_info_ifindex(info, &rdev, &netdev); - if (result) - goto unlock; +static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + const u8 *bssid; + + if (!info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; - result = __nl80211_set_channel(rdev, netdev->ieee80211_ptr, info); + if (netif_running(dev)) + return -EBUSY; - unlock: - rtnl_unlock(); + if (!rdev->ops->set_wds_peer) + return -EOPNOTSUPP; - return result; + if (wdev->iftype != NL80211_IFTYPE_WDS) + return -EOPNOTSUPP; + + bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); + return rdev->ops->set_wds_peer(wdev->wiphy, dev, bssid); } + static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev; struct net_device *netdev = NULL; struct wireless_dev *wdev; - int result, rem_txq_params = 0; + 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; u8 coverage_class = 0; - rtnl_lock(); - /* * Try to find the wiphy and netdev. Normally this * function shouldn't need the netdev, but this is @@ -868,8 +936,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev = __cfg80211_rdev_from_info(info); if (IS_ERR(rdev)) { mutex_unlock(&cfg80211_mutex); - result = PTR_ERR(rdev); - goto unlock; + return PTR_ERR(rdev); } wdev = NULL; netdev = NULL; @@ -1051,8 +1118,6 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) mutex_unlock(&rdev->mtx); if (netdev) dev_put(netdev); - unlock: - rtnl_unlock(); return result; } @@ -1132,33 +1197,20 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; - struct cfg80211_registered_device *dev; - struct net_device *netdev; - int err; - - err = get_rdev_dev_by_info_ifindex(info, &dev, &netdev); - if (err) - return err; + struct cfg80211_registered_device *dev = info->user_ptr[0]; + struct net_device *netdev = info->user_ptr[1]; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) - goto out_err; + return -ENOMEM; if (nl80211_send_iface(msg, info->snd_pid, info->snd_seq, 0, - dev, netdev) < 0) - goto out_free; - - dev_put(netdev); - cfg80211_unlock_rdev(dev); + dev, netdev) < 0) { + nlmsg_free(msg); + return -ENOBUFS; + } return genlmsg_reply(msg, info); - - out_free: - nlmsg_free(msg); - out_err: - dev_put(netdev); - cfg80211_unlock_rdev(dev); - return -ENOBUFS; } static const struct nla_policy mntr_flags_policy[NL80211_MNTR_FLAG_MAX + 1] = { @@ -1218,39 +1270,29 @@ static int nl80211_valid_4addr(struct cfg80211_registered_device *rdev, static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct vif_params params; int err; enum nl80211_iftype otype, ntype; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; u32 _flags, *flags = NULL; bool change = false; memset(¶ms, 0, sizeof(params)); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - otype = ntype = dev->ieee80211_ptr->iftype; if (info->attrs[NL80211_ATTR_IFTYPE]) { ntype = nla_get_u32(info->attrs[NL80211_ATTR_IFTYPE]); if (otype != ntype) change = true; - if (ntype > NL80211_IFTYPE_MAX) { - err = -EINVAL; - goto unlock; - } + if (ntype > NL80211_IFTYPE_MAX) + return -EINVAL; } if (info->attrs[NL80211_ATTR_MESH_ID]) { - if (ntype != NL80211_IFTYPE_MESH_POINT) { - err = -EINVAL; - goto unlock; - } + if (ntype != NL80211_IFTYPE_MESH_POINT) + return -EINVAL; params.mesh_id = nla_data(info->attrs[NL80211_ATTR_MESH_ID]); params.mesh_id_len = nla_len(info->attrs[NL80211_ATTR_MESH_ID]); change = true; @@ -1261,20 +1303,18 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) change = true; err = nl80211_valid_4addr(rdev, dev, params.use_4addr, ntype); if (err) - goto unlock; + return err; } else { params.use_4addr = -1; } if (info->attrs[NL80211_ATTR_MNTR_FLAGS]) { - if (ntype != NL80211_IFTYPE_MONITOR) { - err = -EINVAL; - goto unlock; - } + if (ntype != NL80211_IFTYPE_MONITOR) + return -EINVAL; err = parse_monitor_flags(info->attrs[NL80211_ATTR_MNTR_FLAGS], &_flags); if (err) - goto unlock; + return err; flags = &_flags; change = true; @@ -1288,17 +1328,12 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) if (!err && params.use_4addr != -1) dev->ieee80211_ptr->use_4addr = params.use_4addr; - unlock: - dev_put(dev); - cfg80211_unlock_rdev(rdev); - unlock_rtnl: - rtnl_unlock(); return err; } static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct vif_params params; int err; enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED; @@ -1315,19 +1350,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - rtnl_lock(); - - rdev = cfg80211_get_dev_from_info(info); - if (IS_ERR(rdev)) { - err = PTR_ERR(rdev); - goto unlock_rtnl; - } - if (!rdev->ops->add_virtual_intf || - !(rdev->wiphy.interface_modes & (1 << type))) { - err = -EOPNOTSUPP; - goto unlock; - } + !(rdev->wiphy.interface_modes & (1 << type))) + return -EOPNOTSUPP; if (type == NL80211_IFTYPE_MESH_POINT && info->attrs[NL80211_ATTR_MESH_ID]) { @@ -1339,7 +1364,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) params.use_4addr = !!nla_get_u8(info->attrs[NL80211_ATTR_4ADDR]); err = nl80211_valid_4addr(rdev, NULL, params.use_4addr, type); if (err) - goto unlock; + return err; } err = parse_monitor_flags(type == NL80211_IFTYPE_MONITOR ? @@ -1349,38 +1374,18 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) nla_data(info->attrs[NL80211_ATTR_IFNAME]), type, err ? NULL : &flags, ¶ms); - unlock: - cfg80211_unlock_rdev(rdev); - unlock_rtnl: - rtnl_unlock(); return err; } static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; - - rtnl_lock(); + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->del_virtual_intf) { - err = -EOPNOTSUPP; - goto out; - } - - err = rdev->ops->del_virtual_intf(&rdev->wiphy, dev); + if (!rdev->ops->del_virtual_intf) + return -EOPNOTSUPP; - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - unlock_rtnl: - rtnl_unlock(); - return err; + return rdev->ops->del_virtual_intf(&rdev->wiphy, dev); } struct get_key_cookie { @@ -1433,11 +1438,12 @@ static void get_key_callback(void *c, struct key_params *params) static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; u8 key_idx = 0; - u8 *mac_addr = NULL; + const u8 *mac_addr = NULL; + bool pairwise; struct get_key_cookie cookie = { .error = 0, }; @@ -1453,30 +1459,28 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->get_key) { - err = -EOPNOTSUPP; - goto out; + pairwise = !!mac_addr; + if (info->attrs[NL80211_ATTR_KEY_TYPE]) { + u32 kt = nla_get_u32(info->attrs[NL80211_ATTR_KEY_TYPE]); + if (kt >= NUM_NL80211_KEYTYPES) + return -EINVAL; + if (kt != NL80211_KEYTYPE_GROUP && + kt != NL80211_KEYTYPE_PAIRWISE) + return -EINVAL; + pairwise = kt == NL80211_KEYTYPE_PAIRWISE; } + if (!rdev->ops->get_key) + return -EOPNOTSUPP; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - err = -ENOMEM; - goto out; - } + if (!msg) + return -ENOMEM; hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, NL80211_CMD_NEW_KEY); - - if (IS_ERR(hdr)) { - err = PTR_ERR(hdr); - goto free_msg; - } + if (IS_ERR(hdr)) + return PTR_ERR(hdr); cookie.msg = msg; cookie.idx = key_idx; @@ -1486,8 +1490,12 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (mac_addr) NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr); - err = rdev->ops->get_key(&rdev->wiphy, dev, key_idx, mac_addr, - &cookie, get_key_callback); + if (pairwise && mac_addr && + !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) + return -ENOENT; + + err = rdev->ops->get_key(&rdev->wiphy, dev, key_idx, pairwise, + mac_addr, &cookie, get_key_callback); if (err) goto free_msg; @@ -1496,28 +1504,21 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) goto nla_put_failure; genlmsg_end(msg, hdr); - err = genlmsg_reply(msg, info); - goto out; + return genlmsg_reply(msg, info); nla_put_failure: err = -ENOBUFS; free_msg: nlmsg_free(msg); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - unlock_rtnl: - rtnl_unlock(); - return err; } static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct key_parse key; int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; int (*func)(struct wiphy *wiphy, struct net_device *netdev, u8 key_index); @@ -1532,21 +1533,13 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) if (!key.def && !key.defmgmt) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - if (key.def) func = rdev->ops->set_default_key; else func = rdev->ops->set_default_mgmt_key; - if (!func) { - err = -EOPNOTSUPP; - goto out; - } + if (!func) + return -EOPNOTSUPP; wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); @@ -1563,23 +1556,16 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) #endif wdev_unlock(dev->ieee80211_ptr); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - - unlock_rtnl: - rtnl_unlock(); - return err; } static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; struct key_parse key; - u8 *mac_addr = NULL; + const u8 *mac_addr = NULL; err = nl80211_parse_key(info, &key); if (err) @@ -1591,43 +1577,42 @@ 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]); - rtnl_lock(); + if (key.type == -1) { + if (mac_addr) + key.type = NL80211_KEYTYPE_PAIRWISE; + else + key.type = NL80211_KEYTYPE_GROUP; + } - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; + /* for now */ + if (key.type != NL80211_KEYTYPE_PAIRWISE && + key.type != NL80211_KEYTYPE_GROUP) + return -EINVAL; - if (!rdev->ops->add_key) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->add_key) + return -EOPNOTSUPP; - if (cfg80211_validate_key_settings(rdev, &key.p, key.idx, mac_addr)) { - err = -EINVAL; - goto out; - } + if (cfg80211_validate_key_settings(rdev, &key.p, key.idx, + key.type == NL80211_KEYTYPE_PAIRWISE, + mac_addr)) + return -EINVAL; wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); if (!err) err = rdev->ops->add_key(&rdev->wiphy, dev, key.idx, + key.type == NL80211_KEYTYPE_PAIRWISE, mac_addr, &key.p); wdev_unlock(dev->ieee80211_ptr); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - unlock_rtnl: - rtnl_unlock(); - return err; } static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; u8 *mac_addr = NULL; struct key_parse key; @@ -1638,21 +1623,32 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - rtnl_lock(); + if (key.type == -1) { + if (mac_addr) + key.type = NL80211_KEYTYPE_PAIRWISE; + else + key.type = NL80211_KEYTYPE_GROUP; + } - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; + /* for now */ + if (key.type != NL80211_KEYTYPE_PAIRWISE && + key.type != NL80211_KEYTYPE_GROUP) + return -EINVAL; - if (!rdev->ops->del_key) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->del_key) + return -EOPNOTSUPP; wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); + + if (key.type == NL80211_KEYTYPE_PAIRWISE && mac_addr && + !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) + err = -ENOENT; + if (!err) - err = rdev->ops->del_key(&rdev->wiphy, dev, key.idx, mac_addr); + err = rdev->ops->del_key(&rdev->wiphy, dev, key.idx, + key.type == NL80211_KEYTYPE_PAIRWISE, + mac_addr); #ifdef CONFIG_CFG80211_WEXT if (!err) { @@ -1664,13 +1660,6 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) #endif wdev_unlock(dev->ieee80211_ptr); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - - unlock_rtnl: - rtnl_unlock(); - return err; } @@ -1678,35 +1667,25 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) { int (*call)(struct wiphy *wiphy, struct net_device *dev, struct beacon_parameters *info); - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct beacon_parameters params; int haveinfo = 0; if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_BEACON_TAIL])) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP) { - err = -EOPNOTSUPP; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EOPNOTSUPP; switch (info->genlhdr->cmd) { case NL80211_CMD_NEW_BEACON: /* these are required for NEW_BEACON */ if (!info->attrs[NL80211_ATTR_BEACON_INTERVAL] || !info->attrs[NL80211_ATTR_DTIM_PERIOD] || - !info->attrs[NL80211_ATTR_BEACON_HEAD]) { - err = -EINVAL; - goto out; - } + !info->attrs[NL80211_ATTR_BEACON_HEAD]) + return -EINVAL; call = rdev->ops->add_beacon; break; @@ -1715,14 +1694,11 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) break; default: WARN_ON(1); - err = -EOPNOTSUPP; - goto out; + return -EOPNOTSUPP; } - if (!call) { - err = -EOPNOTSUPP; - goto out; - } + if (!call) + return -EOPNOTSUPP; memset(¶ms, 0, sizeof(params)); @@ -1752,52 +1728,25 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) haveinfo = 1; } - if (!haveinfo) { - err = -EINVAL; - goto out; - } - - err = call(&rdev->wiphy, dev, ¶ms); - - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - unlock_rtnl: - rtnl_unlock(); + if (!haveinfo) + return -EINVAL; - return err; + return call(&rdev->wiphy, dev, ¶ms); } static int nl80211_del_beacon(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; - - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->del_beacon) { - err = -EOPNOTSUPP; - goto out; - } + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP) { - err = -EOPNOTSUPP; - goto out; - } - err = rdev->ops->del_beacon(&rdev->wiphy, dev); + if (!rdev->ops->del_beacon) + return -EOPNOTSUPP; - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - unlock_rtnl: - rtnl_unlock(); + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EOPNOTSUPP; - return err; + return rdev->ops->del_beacon(&rdev->wiphy, dev); } static const struct nla_policy sta_flags_policy[NL80211_STA_FLAG_MAX + 1] = { @@ -1918,6 +1867,12 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, if (sinfo->filled & STATION_INFO_TX_PACKETS) NLA_PUT_U32(msg, NL80211_STA_INFO_TX_PACKETS, sinfo->tx_packets); + if (sinfo->filled & STATION_INFO_TX_RETRIES) + NLA_PUT_U32(msg, NL80211_STA_INFO_TX_RETRIES, + sinfo->tx_retries); + if (sinfo->filled & STATION_INFO_TX_FAILED) + NLA_PUT_U32(msg, NL80211_STA_INFO_TX_FAILED, + sinfo->tx_failed); nla_nest_end(msg, sinfoattr); return genlmsg_end(msg, hdr); @@ -1934,28 +1889,12 @@ static int nl80211_dump_station(struct sk_buff *skb, struct cfg80211_registered_device *dev; struct net_device *netdev; u8 mac_addr[ETH_ALEN]; - int ifidx = cb->args[0]; int sta_idx = cb->args[1]; int err; - if (!ifidx) - ifidx = nl80211_get_ifidx(cb); - if (ifidx < 0) - return ifidx; - - rtnl_lock(); - - netdev = __dev_get_by_index(sock_net(skb->sk), ifidx); - if (!netdev) { - err = -ENODEV; - goto out_rtnl; - } - - dev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); - if (IS_ERR(dev)) { - err = PTR_ERR(dev); - goto out_rtnl; - } + err = nl80211_prepare_netdev_dump(skb, cb, &dev, &netdev); + if (err) + return err; if (!dev->ops->dump_station) { err = -EOPNOTSUPP; @@ -1985,21 +1924,19 @@ static int nl80211_dump_station(struct sk_buff *skb, cb->args[1] = sta_idx; err = skb->len; out_err: - cfg80211_unlock_rdev(dev); - out_rtnl: - rtnl_unlock(); + nl80211_finish_netdev_dump(dev); return err; } static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct station_info sinfo; struct sk_buff *msg; u8 *mac_addr = NULL; + int err; memset(&sinfo, 0, sizeof(sinfo)); @@ -2008,41 +1945,24 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (!rdev->ops->get_station) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->get_station) + return -EOPNOTSUPP; err = rdev->ops->get_station(&rdev->wiphy, dev, mac_addr, &sinfo); if (err) - goto out; + return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) - goto out; + return -ENOMEM; if (nl80211_send_station(msg, info->snd_pid, info->snd_seq, 0, - dev, mac_addr, &sinfo) < 0) - goto out_free; - - err = genlmsg_reply(msg, info); - goto out; - - out_free: - nlmsg_free(msg); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + dev, mac_addr, &sinfo) < 0) { + nlmsg_free(msg); + return -ENOBUFS; + } - return err; + return genlmsg_reply(msg, info); } /* @@ -2072,9 +1992,9 @@ static int get_vlan(struct genl_info *info, static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; struct station_parameters params; u8 *mac_addr = NULL; @@ -2112,12 +2032,6 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) params.plink_action = nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - err = get_vlan(info, rdev, ¶ms.vlan); if (err) goto out; @@ -2128,10 +2042,12 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) switch (dev->ieee80211_ptr->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_P2P_GO: /* disallow mesh-specific things */ if (params.plink_action) err = -EINVAL; break; + case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: /* disallow everything but AUTHORIZED flag */ if (params.plink_action) @@ -2177,19 +2093,15 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) out: if (params.vlan) dev_put(params.vlan); - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); return err; } static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; struct station_parameters params; u8 *mac_addr = NULL; @@ -2226,17 +2138,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (parse_station_flags(info, ¶ms)) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN) { - err = -EINVAL; - goto out; - } + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EINVAL; err = get_vlan(info, rdev, ¶ms.vlan); if (err) @@ -2250,61 +2155,33 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } - err = rdev->ops->add_station(&rdev->wiphy, dev, mac_addr, ¶ms); out: if (params.vlan) dev_put(params.vlan); - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); - return err; } static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; u8 *mac_addr = NULL; if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - 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 (!rdev->ops->del_station) { - err = -EOPNOTSUPP; - goto out; - } - - err = rdev->ops->del_station(&rdev->wiphy, dev, mac_addr); + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EINVAL; - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + if (!rdev->ops->del_station) + return -EOPNOTSUPP; - return err; + return rdev->ops->del_station(&rdev->wiphy, dev, mac_addr); } static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, @@ -2367,28 +2244,12 @@ static int nl80211_dump_mpath(struct sk_buff *skb, struct net_device *netdev; u8 dst[ETH_ALEN]; u8 next_hop[ETH_ALEN]; - int ifidx = cb->args[0]; int path_idx = cb->args[1]; int err; - if (!ifidx) - ifidx = nl80211_get_ifidx(cb); - if (ifidx < 0) - return ifidx; - - rtnl_lock(); - - netdev = __dev_get_by_index(sock_net(skb->sk), ifidx); - if (!netdev) { - err = -ENODEV; - goto out_rtnl; - } - - dev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); - if (IS_ERR(dev)) { - err = PTR_ERR(dev); - goto out_rtnl; - } + err = nl80211_prepare_netdev_dump(skb, cb, &dev, &netdev); + if (err) + return err; if (!dev->ops->dump_mpath) { err = -EOPNOTSUPP; @@ -2422,18 +2283,15 @@ static int nl80211_dump_mpath(struct sk_buff *skb, cb->args[1] = path_idx; err = skb->len; out_err: - cfg80211_unlock_rdev(dev); - out_rtnl: - rtnl_unlock(); - + nl80211_finish_netdev_dump(dev); return err; } static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; struct mpath_info pinfo; struct sk_buff *msg; u8 *dst = NULL; @@ -2446,53 +2304,33 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) dst = nla_data(info->attrs[NL80211_ATTR_MAC]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (!rdev->ops->get_mpath) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->get_mpath) + return -EOPNOTSUPP; - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) { - err = -EOPNOTSUPP; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; err = rdev->ops->get_mpath(&rdev->wiphy, dev, dst, next_hop, &pinfo); if (err) - goto out; + return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) - goto out; + return -ENOMEM; if (nl80211_send_mpath(msg, info->snd_pid, info->snd_seq, 0, - dev, dst, next_hop, &pinfo) < 0) - goto out_free; - - err = genlmsg_reply(msg, info); - goto out; - - out_free: - nlmsg_free(msg); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + dev, dst, next_hop, &pinfo) < 0) { + nlmsg_free(msg); + return -ENOBUFS; + } - return err; + return genlmsg_reply(msg, info); } static int nl80211_set_mpath(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; u8 *dst = NULL; u8 *next_hop = NULL; @@ -2505,42 +2343,19 @@ static int nl80211_set_mpath(struct sk_buff *skb, struct genl_info *info) dst = nla_data(info->attrs[NL80211_ATTR_MAC]); next_hop = nla_data(info->attrs[NL80211_ATTR_MPATH_NEXT_HOP]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (!rdev->ops->change_mpath) { - err = -EOPNOTSUPP; - goto out; - } - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) { - err = -EOPNOTSUPP; - goto out; - } - - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } - - err = rdev->ops->change_mpath(&rdev->wiphy, dev, dst, next_hop); + if (!rdev->ops->change_mpath) + return -EOPNOTSUPP; - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; - return err; + return rdev->ops->change_mpath(&rdev->wiphy, dev, dst, next_hop); } + static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; u8 *dst = NULL; u8 *next_hop = NULL; @@ -2553,75 +2368,34 @@ static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) dst = nla_data(info->attrs[NL80211_ATTR_MAC]); next_hop = nla_data(info->attrs[NL80211_ATTR_MPATH_NEXT_HOP]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (!rdev->ops->add_mpath) { - err = -EOPNOTSUPP; - goto out; - } - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) { - err = -EOPNOTSUPP; - goto out; - } - - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } - - err = rdev->ops->add_mpath(&rdev->wiphy, dev, dst, next_hop); + if (!rdev->ops->add_mpath) + return -EOPNOTSUPP; - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; - return err; + return rdev->ops->add_mpath(&rdev->wiphy, dev, dst, next_hop); } static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; u8 *dst = NULL; if (info->attrs[NL80211_ATTR_MAC]) dst = nla_data(info->attrs[NL80211_ATTR_MAC]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (!rdev->ops->del_mpath) { - err = -EOPNOTSUPP; - goto out; - } - - err = rdev->ops->del_mpath(&rdev->wiphy, dev, dst); - - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + if (!rdev->ops->del_mpath) + return -EOPNOTSUPP; - return err; + return rdev->ops->del_mpath(&rdev->wiphy, dev, dst); } static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct bss_parameters params; memset(¶ms, 0, sizeof(params)); @@ -2649,31 +2423,14 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_AP_ISOLATE]) params.ap_isolate = !!nla_get_u8(info->attrs[NL80211_ATTR_AP_ISOLATE]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (!rdev->ops->change_bss) { - err = -EOPNOTSUPP; - goto out; - } - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP) { - err = -EOPNOTSUPP; - goto out; - } - - err = rdev->ops->change_bss(&rdev->wiphy, dev, ¶ms); + if (!rdev->ops->change_bss) + return -EOPNOTSUPP; - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EOPNOTSUPP; - return err; + return rdev->ops->change_bss(&rdev->wiphy, dev, ¶ms); } static const struct nla_policy reg_rule_policy[NL80211_REG_RULE_ATTR_MAX + 1] = { @@ -2752,37 +2509,26 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) static int nl80211_get_mesh_params(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct mesh_config cur_params; int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; void *hdr; struct nlattr *pinfoattr; struct sk_buff *msg; - rtnl_lock(); - - /* Look up our device */ - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (!rdev->ops->get_mesh_params) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->get_mesh_params) + return -EOPNOTSUPP; /* Get the mesh params */ err = rdev->ops->get_mesh_params(&rdev->wiphy, dev, &cur_params); if (err) - goto out; + return err; /* Draw up a netlink message to send back */ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - err = -ENOBUFS; - goto out; - } + if (!msg) + return -ENOMEM; hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, NL80211_CMD_GET_MESH_PARAMS); if (!hdr) @@ -2821,21 +2567,12 @@ static int nl80211_get_mesh_params(struct sk_buff *skb, cur_params.dot11MeshHWMPRootMode); nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); - err = genlmsg_reply(msg, info); - goto out; + return genlmsg_reply(msg, info); nla_put_failure: genlmsg_cancel(msg, hdr); nlmsg_free(msg); - err = -EMSGSIZE; - out: - /* Cleanup */ - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); - - return err; + return -ENOBUFS; } #define FILL_IN_MESH_PARAM_IF_SET(table, cfg, param, mask, attr_num, nla_fn) \ @@ -2865,10 +2602,9 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info) { - int err; u32 mask; - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct mesh_config cfg; struct nlattr *tb[NL80211_MESHCONF_ATTR_MAX + 1]; struct nlattr *parent_attr; @@ -2880,16 +2616,8 @@ static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info) parent_attr, nl80211_meshconf_params_policy)) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (!rdev->ops->set_mesh_params) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->set_mesh_params) + return -EOPNOTSUPP; /* This makes sure that there aren't more than 32 mesh config * parameters (otherwise our bitfield scheme would not work.) */ @@ -2935,16 +2663,7 @@ static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info) nla_get_u8); /* Apply changes */ - err = rdev->ops->set_mesh_params(&rdev->wiphy, dev, &cfg, mask); - - out: - /* cleanup */ - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); - - return err; + return rdev->ops->set_mesh_params(&rdev->wiphy, dev, &cfg, mask); } #undef FILL_IN_MESH_PARAM_IF_SET @@ -3127,8 +2846,8 @@ static int validate_scan_freqs(struct nlattr *freqs) static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct cfg80211_scan_request *request; struct cfg80211_ssid *ssid; struct ieee80211_channel *channel; @@ -3141,36 +2860,19 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - wiphy = &rdev->wiphy; - if (!rdev->ops->scan) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->scan) + return -EOPNOTSUPP; - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } - - if (rdev->scan_req) { - err = -EBUSY; - goto out; - } + if (rdev->scan_req) + return -EBUSY; if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { n_channels = validate_scan_freqs( info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]); - if (!n_channels) { - err = -EINVAL; - goto out; - } + if (!n_channels) + return -EINVAL; } else { n_channels = 0; @@ -3183,29 +2885,23 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) n_ssids++; - if (n_ssids > wiphy->max_scan_ssids) { - err = -EINVAL; - goto out; - } + if (n_ssids > wiphy->max_scan_ssids) + return -EINVAL; if (info->attrs[NL80211_ATTR_IE]) ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); else ie_len = 0; - if (ie_len > wiphy->max_scan_ie_len) { - err = -EINVAL; - goto out; - } + if (ie_len > wiphy->max_scan_ie_len) + return -EINVAL; request = kzalloc(sizeof(*request) + sizeof(*ssid) * n_ssids + sizeof(channel) * n_channels + ie_len, GFP_KERNEL); - if (!request) { - err = -ENOMEM; - goto out; - } + if (!request) + return -ENOMEM; if (n_ssids) request->ssids = (void *)&request->channels[n_channels]; @@ -3293,18 +2989,11 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) if (!err) { nl80211_send_scan_start(rdev, dev); dev_hold(dev); - } - + } else { out_free: - if (err) { rdev->scan_req = NULL; kfree(request); } - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); return err; } @@ -3363,6 +3052,7 @@ static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, } switch (wdev->iftype) { + case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: if (intbss == wdev->current_bss) NLA_PUT_U32(msg, NL80211_BSS_STATUS, @@ -3400,25 +3090,12 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct net_device *dev; struct cfg80211_internal_bss *scan; struct wireless_dev *wdev; - int ifidx = cb->args[0]; int start = cb->args[1], idx = 0; int err; - if (!ifidx) - ifidx = nl80211_get_ifidx(cb); - if (ifidx < 0) - return ifidx; - cb->args[0] = ifidx; - - dev = dev_get_by_index(sock_net(skb->sk), ifidx); - if (!dev) - return -ENODEV; - - rdev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); - if (IS_ERR(rdev)) { - err = PTR_ERR(rdev); - goto out_put_netdev; - } + err = nl80211_prepare_netdev_dump(skb, cb, &rdev, &dev); + if (err) + return err; wdev = dev->ieee80211_ptr; @@ -3434,21 +3111,17 @@ static int nl80211_dump_scan(struct sk_buff *skb, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev, scan) < 0) { idx--; - goto out; + break; } } - out: spin_unlock_bh(&rdev->bss_lock); wdev_unlock(wdev); cb->args[1] = idx; - err = skb->len; - cfg80211_unlock_rdev(rdev); - out_put_netdev: - dev_put(dev); + nl80211_finish_netdev_dump(rdev); - return err; + return skb->len; } static int nl80211_send_survey(struct sk_buff *msg, u32 pid, u32 seq, @@ -3478,6 +3151,23 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 pid, u32 seq, if (survey->filled & SURVEY_INFO_NOISE_DBM) NLA_PUT_U8(msg, NL80211_SURVEY_INFO_NOISE, survey->noise); + if (survey->filled & SURVEY_INFO_IN_USE) + NLA_PUT_FLAG(msg, NL80211_SURVEY_INFO_IN_USE); + if (survey->filled & SURVEY_INFO_CHANNEL_TIME) + NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME, + survey->channel_time); + if (survey->filled & SURVEY_INFO_CHANNEL_TIME_BUSY) + NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY, + survey->channel_time_busy); + if (survey->filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) + NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY, + survey->channel_time_ext_busy); + if (survey->filled & SURVEY_INFO_CHANNEL_TIME_RX) + NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_RX, + survey->channel_time_rx); + if (survey->filled & SURVEY_INFO_CHANNEL_TIME_TX) + NLA_PUT_U64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_TX, + survey->channel_time_tx); nla_nest_end(msg, infoattr); @@ -3494,29 +3184,12 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct survey_info survey; struct cfg80211_registered_device *dev; struct net_device *netdev; - int ifidx = cb->args[0]; int survey_idx = cb->args[1]; int res; - if (!ifidx) - ifidx = nl80211_get_ifidx(cb); - if (ifidx < 0) - return ifidx; - cb->args[0] = ifidx; - - rtnl_lock(); - - netdev = __dev_get_by_index(sock_net(skb->sk), ifidx); - if (!netdev) { - res = -ENODEV; - goto out_rtnl; - } - - dev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); - if (IS_ERR(dev)) { - res = PTR_ERR(dev); - goto out_rtnl; - } + res = nl80211_prepare_netdev_dump(skb, cb, &dev, &netdev); + if (res) + return res; if (!dev->ops->dump_survey) { res = -EOPNOTSUPP; @@ -3544,10 +3217,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, cb->args[1] = survey_idx; res = skb->len; out_err: - cfg80211_unlock_rdev(dev); - out_rtnl: - rtnl_unlock(); - + nl80211_finish_netdev_dump(dev); return res; } @@ -3580,8 +3250,8 @@ static bool nl80211_valid_cipher_suite(u32 cipher) static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct ieee80211_channel *chan; const u8 *bssid, *ssid, *ie = NULL; int err, ssid_len, ie_len = 0; @@ -3609,6 +3279,8 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) return err; if (key.idx >= 0) { + if (key.type != -1 && key.type != NL80211_KEYTYPE_GROUP) + return -EINVAL; if (!key.p.key || !key.p.key_len) return -EINVAL; if ((key.p.cipher != WLAN_CIPHER_SUITE_WEP40 || @@ -3623,12 +3295,6 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) key.p.key = NULL; } - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - if (key.idx >= 0) { int i; bool ok = false; @@ -3638,34 +3304,22 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) break; } } - if (!ok) { - err = -EINVAL; - goto out; - } - } - - if (!rdev->ops->auth) { - err = -EOPNOTSUPP; - goto out; + if (!ok) + return -EINVAL; } - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->auth) + return -EOPNOTSUPP; - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); chan = ieee80211_get_channel(&rdev->wiphy, nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); - if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED)) { - err = -EINVAL; - goto out; - } + if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED)) + return -EINVAL; ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); @@ -3676,24 +3330,15 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) } auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); - if (!nl80211_valid_auth_type(auth_type)) { - err = -EINVAL; - goto out; - } + if (!nl80211_valid_auth_type(auth_type)) + return -EINVAL; local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; - err = cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, - ssid, ssid_len, ie, ie_len, - key.p.key, key.p.key_len, key.idx, - local_state_change); - -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: - rtnl_unlock(); - return err; + return cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, + ssid, ssid_len, ie, ie_len, + key.p.key, key.p.key_len, key.idx, + local_state_change); } static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, @@ -3777,8 +3422,8 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct cfg80211_crypto_settings crypto; struct ieee80211_channel *chan; const u8 *bssid, *ssid, *ie = NULL, *prev_bssid = NULL; @@ -3793,35 +3438,19 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) !info->attrs[NL80211_ATTR_WIPHY_FREQ]) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->assoc) { - err = -EOPNOTSUPP; - goto out; - } - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->assoc) + return -EOPNOTSUPP; - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); chan = ieee80211_get_channel(&rdev->wiphy, nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); - if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED)) { - err = -EINVAL; - goto out; - } + if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED)) + return -EINVAL; ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); @@ -3836,10 +3465,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) nla_get_u32(info->attrs[NL80211_ATTR_USE_MFP]); if (mfp == NL80211_MFP_REQUIRED) use_mfp = true; - else if (mfp != NL80211_MFP_NO) { - err = -EINVAL; - goto out; - } + else if (mfp != NL80211_MFP_NO) + return -EINVAL; } if (info->attrs[NL80211_ATTR_PREV_BSSID]) @@ -3851,20 +3478,15 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) ssid, ssid_len, ie, ie_len, use_mfp, &crypto); -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: - rtnl_unlock(); return err; } static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; const u8 *ie = NULL, *bssid; - int err, ie_len = 0; + int ie_len = 0; u16 reason_code; bool local_state_change; @@ -3877,34 +3499,19 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_REASON_CODE]) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->deauth) { - err = -EOPNOTSUPP; - goto out; - } - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->deauth) + return -EOPNOTSUPP; - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); reason_code = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); if (reason_code == 0) { /* Reason Code 0 is reserved */ - err = -EINVAL; - goto out; + return -EINVAL; } if (info->attrs[NL80211_ATTR_IE]) { @@ -3914,23 +3521,16 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; - err = cfg80211_mlme_deauth(rdev, dev, bssid, ie, ie_len, reason_code, - local_state_change); - -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: - rtnl_unlock(); - return err; + return cfg80211_mlme_deauth(rdev, dev, bssid, ie, ie_len, reason_code, + local_state_change); } static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; const u8 *ie = NULL, *bssid; - int err, ie_len = 0; + int ie_len = 0; u16 reason_code; bool local_state_change; @@ -3943,34 +3543,19 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_REASON_CODE]) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->disassoc) { - err = -EOPNOTSUPP; - goto out; - } - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->disassoc) + return -EOPNOTSUPP; - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); reason_code = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); if (reason_code == 0) { /* Reason Code 0 is reserved */ - err = -EINVAL; - goto out; + return -EINVAL; } if (info->attrs[NL80211_ATTR_IE]) { @@ -3980,21 +3565,14 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; - err = cfg80211_mlme_disassoc(rdev, dev, bssid, ie, ie_len, reason_code, - local_state_change); - -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: - rtnl_unlock(); - return err; + return cfg80211_mlme_disassoc(rdev, dev, bssid, ie, ie_len, reason_code, + local_state_change); } static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct cfg80211_ibss_params ibss; struct wiphy *wiphy; struct cfg80211_cached_keys *connkeys = NULL; @@ -4019,26 +3597,11 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->join_ibss) { - err = -EOPNOTSUPP; - goto out; - } - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->join_ibss) + return -EOPNOTSUPP; - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) + return -EOPNOTSUPP; wiphy = &rdev->wiphy; @@ -4056,24 +3619,12 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) 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->flags & IEEE80211_CHAN_DISABLED) + return -EINVAL; ibss.channel_fixed = !!info->attrs[NL80211_ATTR_FREQ_FIXED]; ibss.privacy = !!info->attrs[NL80211_ATTR_PRIVACY]; - if (ibss.privacy && info->attrs[NL80211_ATTR_KEYS]) { - connkeys = nl80211_parse_connkeys(rdev, - info->attrs[NL80211_ATTR_KEYS]); - if (IS_ERR(connkeys)) { - err = PTR_ERR(connkeys); - connkeys = NULL; - goto out; - } - } - if (info->attrs[NL80211_ATTR_BSS_BASIC_RATES]) { u8 *rates = nla_data(info->attrs[NL80211_ATTR_BSS_BASIC_RATES]); @@ -4083,10 +3634,8 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) wiphy->bands[ibss.channel->band]; int i, j; - if (n_rates == 0) { - err = -EINVAL; - goto out; - } + if (n_rates == 0) + return -EINVAL; for (i = 0; i < n_rates; i++) { int rate = (rates[i] & 0x7f) * 5; @@ -4099,77 +3648,36 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) break; } } - if (!found) { - err = -EINVAL; - goto out; - } - } - } else { - /* - * If no rates were explicitly configured, - * use the mandatory rate set for 11b or - * 11a for maximum compatibility. - */ - struct ieee80211_supported_band *sband = - wiphy->bands[ibss.channel->band]; - int j; - u32 flag = ibss.channel->band == IEEE80211_BAND_5GHZ ? - IEEE80211_RATE_MANDATORY_A : - IEEE80211_RATE_MANDATORY_B; - - for (j = 0; j < sband->n_bitrates; j++) { - if (sband->bitrates[j].flags & flag) - ibss.basic_rates |= BIT(j); + if (!found) + return -EINVAL; } } - err = cfg80211_join_ibss(rdev, dev, &ibss, connkeys); + if (ibss.privacy && info->attrs[NL80211_ATTR_KEYS]) { + connkeys = nl80211_parse_connkeys(rdev, + info->attrs[NL80211_ATTR_KEYS]); + if (IS_ERR(connkeys)) + return PTR_ERR(connkeys); + } -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: + err = cfg80211_join_ibss(rdev, dev, &ibss, connkeys); if (err) kfree(connkeys); - rtnl_unlock(); return err; } static int nl80211_leave_ibss(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; - int err; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->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; - } + if (!rdev->ops->leave_ibss) + return -EOPNOTSUPP; - err = cfg80211_leave_ibss(rdev, dev, false); + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) + return -EOPNOTSUPP; -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: - rtnl_unlock(); - return err; + return cfg80211_leave_ibss(rdev, dev, false); } #ifdef CONFIG_NL80211_TESTMODE @@ -4179,20 +3687,12 @@ static struct genl_multicast_group nl80211_testmode_mcgrp = { static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; int err; if (!info->attrs[NL80211_ATTR_TESTDATA]) return -EINVAL; - rtnl_lock(); - - rdev = cfg80211_get_dev_from_info(info); - if (IS_ERR(rdev)) { - err = PTR_ERR(rdev); - goto unlock_rtnl; - } - err = -EOPNOTSUPP; if (rdev->ops->testmode_cmd) { rdev->testmode_info = info; @@ -4202,10 +3702,6 @@ static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info) rdev->testmode_info = NULL; } - cfg80211_unlock_rdev(rdev); - - unlock_rtnl: - rtnl_unlock(); return err; } @@ -4296,8 +3792,8 @@ EXPORT_SYMBOL(cfg80211_testmode_event); static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct cfg80211_connect_params connect; struct wiphy *wiphy; struct cfg80211_cached_keys *connkeys = NULL; @@ -4326,21 +3822,10 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) NL80211_MAX_NR_CIPHER_SUITES); if (err) return err; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto out; - } - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; wiphy = &rdev->wiphy; @@ -4359,39 +3844,27 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) ieee80211_get_channel(wiphy, nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); if (!connect.channel || - connect.channel->flags & IEEE80211_CHAN_DISABLED) { - err = -EINVAL; - goto out; - } + connect.channel->flags & IEEE80211_CHAN_DISABLED) + return -EINVAL; } if (connect.privacy && info->attrs[NL80211_ATTR_KEYS]) { connkeys = nl80211_parse_connkeys(rdev, info->attrs[NL80211_ATTR_KEYS]); - if (IS_ERR(connkeys)) { - err = PTR_ERR(connkeys); - connkeys = NULL; - goto out; - } + if (IS_ERR(connkeys)) + return PTR_ERR(connkeys); } err = cfg80211_connect(rdev, dev, &connect, connkeys); - -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: if (err) kfree(connkeys); - rtnl_unlock(); return err; } static int nl80211_disconnect(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; - int err; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; u16 reason; if (!info->attrs[NL80211_ATTR_REASON_CODE]) @@ -4402,35 +3875,16 @@ static int nl80211_disconnect(struct sk_buff *skb, struct genl_info *info) if (reason == 0) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto out; - } - - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } - - err = cfg80211_disconnect(rdev, dev, reason, true); + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: - rtnl_unlock(); - return err; + return cfg80211_disconnect(rdev, dev, reason, true); } static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net *net; int err; u32 pid; @@ -4440,43 +3894,26 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info) pid = nla_get_u32(info->attrs[NL80211_ATTR_PID]); - rtnl_lock(); - - rdev = cfg80211_get_dev_from_info(info); - if (IS_ERR(rdev)) { - err = PTR_ERR(rdev); - goto out_rtnl; - } - net = get_net_ns_by_pid(pid); - if (IS_ERR(net)) { - err = PTR_ERR(net); - goto out; - } + if (IS_ERR(net)) + return PTR_ERR(net); err = 0; /* check if anything to do */ - if (net_eq(wiphy_net(&rdev->wiphy), net)) - goto out_put_net; + if (!net_eq(wiphy_net(&rdev->wiphy), net)) + err = cfg80211_switch_netns(rdev, net); - err = cfg80211_switch_netns(rdev, net); - out_put_net: put_net(net); - out: - cfg80211_unlock_rdev(rdev); - out_rtnl: - rtnl_unlock(); return err; } static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; int (*rdev_ops)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_pmksa *pmksa) = NULL; - int err; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; struct cfg80211_pmksa pmksa; memset(&pmksa, 0, sizeof(struct cfg80211_pmksa)); @@ -4487,19 +3924,12 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_PMKID]) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - pmksa.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]); pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto out; - } + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; switch (info->genlhdr->cmd) { case NL80211_CMD_SET_PMKSA: @@ -4513,61 +3943,32 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) break; } - if (!rdev_ops) { - err = -EOPNOTSUPP; - goto out; - } - - err = rdev_ops(&rdev->wiphy, dev, &pmksa); - - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + if (!rdev_ops) + return -EOPNOTSUPP; - return err; + return rdev_ops(&rdev->wiphy, dev, &pmksa); } static int nl80211_flush_pmksa(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - int err; - struct net_device *dev; - - rtnl_lock(); + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto out_rtnl; - - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto out; - } - - if (!rdev->ops->flush_pmksa) { - err = -EOPNOTSUPP; - goto out; - } - - err = rdev->ops->flush_pmksa(&rdev->wiphy, dev); - - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - out_rtnl: - rtnl_unlock(); + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; - return err; + if (!rdev->ops->flush_pmksa) + return -EOPNOTSUPP; + return rdev->ops->flush_pmksa(&rdev->wiphy, dev); } static int nl80211_remain_on_channel(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct ieee80211_channel *chan; struct sk_buff *msg; void *hdr; @@ -4589,21 +3990,8 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, if (!duration || !msecs_to_jiffies(duration) || duration > 5000) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->remain_on_channel) { - err = -EOPNOTSUPP; - goto out; - } - - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + if (!rdev->ops->remain_on_channel) + return -EOPNOTSUPP; if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { channel_type = nla_get_u32( @@ -4611,24 +3999,18 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, if (channel_type != NL80211_CHAN_NO_HT && channel_type != NL80211_CHAN_HT20 && channel_type != NL80211_CHAN_HT40PLUS && - channel_type != NL80211_CHAN_HT40MINUS) { - err = -EINVAL; - goto out; - } + channel_type != NL80211_CHAN_HT40MINUS) + return -EINVAL; } freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); chan = rdev_freq_to_chan(rdev, freq, channel_type); - if (chan == NULL) { - err = -EINVAL; - goto out; - } + if (chan == NULL) + return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - err = -ENOMEM; - goto out; - } + if (!msg) + return -ENOMEM; hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, NL80211_CMD_REMAIN_ON_CHANNEL); @@ -4647,58 +4029,32 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, NLA_PUT_U64(msg, NL80211_ATTR_COOKIE, cookie); genlmsg_end(msg, hdr); - err = genlmsg_reply(msg, info); - goto out; + + return genlmsg_reply(msg, info); nla_put_failure: err = -ENOBUFS; free_msg: nlmsg_free(msg); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - unlock_rtnl: - rtnl_unlock(); return err; } static int nl80211_cancel_remain_on_channel(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; u64 cookie; - int err; if (!info->attrs[NL80211_ATTR_COOKIE]) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->cancel_remain_on_channel) { - err = -EOPNOTSUPP; - goto out; - } - - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + if (!rdev->ops->cancel_remain_on_channel) + return -EOPNOTSUPP; cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]); - err = rdev->ops->cancel_remain_on_channel(&rdev->wiphy, dev, cookie); - - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - unlock_rtnl: - rtnl_unlock(); - return err; + return rdev->ops->cancel_remain_on_channel(&rdev->wiphy, dev, cookie); } static u32 rateset_to_mask(struct ieee80211_supported_band *sband, @@ -4734,26 +4090,18 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[NL80211_TXRATE_MAX + 1]; - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct cfg80211_bitrate_mask mask; - int err, rem, i; - struct net_device *dev; + int rem, i; + struct net_device *dev = info->user_ptr[1]; struct nlattr *tx_rates; struct ieee80211_supported_band *sband; if (info->attrs[NL80211_ATTR_TX_RATES] == NULL) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->set_bitrate_mask) { - err = -EOPNOTSUPP; - goto unlock; - } + if (!rdev->ops->set_bitrate_mask) + return -EOPNOTSUPP; memset(&mask, 0, sizeof(mask)); /* Default to all rates enabled */ @@ -4770,15 +4118,11 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, nla_for_each_nested(tx_rates, info->attrs[NL80211_ATTR_TX_RATES], rem) { enum ieee80211_band band = nla_type(tx_rates); - if (band < 0 || band >= IEEE80211_NUM_BANDS) { - err = -EINVAL; - goto unlock; - } + if (band < 0 || band >= IEEE80211_NUM_BANDS) + return -EINVAL; sband = rdev->wiphy.bands[band]; - if (sband == NULL) { - err = -EINVAL; - goto unlock; - } + if (sband == NULL) + return -EINVAL; nla_parse(tb, NL80211_TXRATE_MAX, nla_data(tx_rates), nla_len(tx_rates), nl80211_txattr_policy); if (tb[NL80211_TXRATE_LEGACY]) { @@ -4786,29 +4130,19 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, sband, nla_data(tb[NL80211_TXRATE_LEGACY]), nla_len(tb[NL80211_TXRATE_LEGACY])); - if (mask.control[band].legacy == 0) { - err = -EINVAL; - goto unlock; - } + if (mask.control[band].legacy == 0) + return -EINVAL; } } - err = rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, NULL, &mask); - - unlock: - dev_put(dev); - cfg80211_unlock_rdev(rdev); - unlock_rtnl: - rtnl_unlock(); - return err; + return rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, NULL, &mask); } static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; u16 frame_type = IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION; - int err; if (!info->attrs[NL80211_ATTR_FRAME_MATCH]) return -EINVAL; @@ -4816,40 +4150,28 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_FRAME_TYPE]) frame_type = nla_get_u16(info->attrs[NL80211_ATTR_FRAME_TYPE]); - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) { - err = -EOPNOTSUPP; - goto out; - } + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EOPNOTSUPP; /* not much point in registering if we can't reply */ - if (!rdev->ops->mgmt_tx) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->mgmt_tx) + return -EOPNOTSUPP; - err = cfg80211_mlme_register_mgmt(dev->ieee80211_ptr, info->snd_pid, + return cfg80211_mlme_register_mgmt(dev->ieee80211_ptr, info->snd_pid, frame_type, nla_data(info->attrs[NL80211_ATTR_FRAME_MATCH]), nla_len(info->attrs[NL80211_ATTR_FRAME_MATCH])); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - unlock_rtnl: - rtnl_unlock(); - return err; } static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; - struct net_device *dev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; struct ieee80211_channel *chan; enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; bool channel_type_valid = false; @@ -4863,27 +4185,16 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) !info->attrs[NL80211_ATTR_WIPHY_FREQ]) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - - if (!rdev->ops->mgmt_tx) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->mgmt_tx) + return -EOPNOTSUPP; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC) { - err = -EOPNOTSUPP; - goto out; - } - - if (!netif_running(dev)) { - err = -ENETDOWN; - goto out; - } + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP_VLAN && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EOPNOTSUPP; if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { channel_type = nla_get_u32( @@ -4891,25 +4202,19 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) if (channel_type != NL80211_CHAN_NO_HT && channel_type != NL80211_CHAN_HT20 && channel_type != NL80211_CHAN_HT40PLUS && - channel_type != NL80211_CHAN_HT40MINUS) { - err = -EINVAL; - goto out; - } + channel_type != NL80211_CHAN_HT40MINUS) + return -EINVAL; channel_type_valid = true; } freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); chan = rdev_freq_to_chan(rdev, freq, channel_type); - if (chan == NULL) { - err = -EINVAL; - goto out; - } + if (chan == NULL) + return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - err = -ENOMEM; - goto out; - } + if (!msg) + return -ENOMEM; hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, NL80211_CMD_FRAME); @@ -4929,109 +4234,72 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) NLA_PUT_U64(msg, NL80211_ATTR_COOKIE, cookie); genlmsg_end(msg, hdr); - err = genlmsg_reply(msg, info); - goto out; + return genlmsg_reply(msg, info); nla_put_failure: err = -ENOBUFS; free_msg: nlmsg_free(msg); - out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); -unlock_rtnl: - rtnl_unlock(); return err; } static int nl80211_set_power_save(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; u8 ps_state; bool state; int err; - if (!info->attrs[NL80211_ATTR_PS_STATE]) { - err = -EINVAL; - goto out; - } + if (!info->attrs[NL80211_ATTR_PS_STATE]) + return -EINVAL; ps_state = nla_get_u32(info->attrs[NL80211_ATTR_PS_STATE]); - if (ps_state != NL80211_PS_DISABLED && ps_state != NL80211_PS_ENABLED) { - err = -EINVAL; - goto out; - } - - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rdev; + if (ps_state != NL80211_PS_DISABLED && ps_state != NL80211_PS_ENABLED) + return -EINVAL; wdev = dev->ieee80211_ptr; - if (!rdev->ops->set_power_mgmt) { - err = -EOPNOTSUPP; - goto unlock_rdev; - } + if (!rdev->ops->set_power_mgmt) + return -EOPNOTSUPP; state = (ps_state == NL80211_PS_ENABLED) ? true : false; if (state == wdev->ps) - goto unlock_rdev; - - wdev->ps = state; - - if (rdev->ops->set_power_mgmt(wdev->wiphy, dev, wdev->ps, - wdev->ps_timeout)) - /* assume this means it's off */ - wdev->ps = false; - -unlock_rdev: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - rtnl_unlock(); + return 0; -out: + err = rdev->ops->set_power_mgmt(wdev->wiphy, dev, state, + wdev->ps_timeout); + if (!err) + wdev->ps = state; return err; } static int nl80211_get_power_save(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; enum nl80211_ps_state ps_state; struct wireless_dev *wdev; - struct net_device *dev; + struct net_device *dev = info->user_ptr[1]; struct sk_buff *msg; void *hdr; int err; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rtnl; - wdev = dev->ieee80211_ptr; - if (!rdev->ops->set_power_mgmt) { - err = -EOPNOTSUPP; - goto out; - } + if (!rdev->ops->set_power_mgmt) + return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - err = -ENOMEM; - goto out; - } + if (!msg) + return -ENOMEM; hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, NL80211_CMD_GET_POWER_SAVE); if (!hdr) { - err = -ENOMEM; + err = -ENOBUFS; goto free_msg; } @@ -5043,22 +4311,12 @@ static int nl80211_get_power_save(struct sk_buff *skb, struct genl_info *info) NLA_PUT_U32(msg, NL80211_ATTR_PS_STATE, ps_state); genlmsg_end(msg, hdr); - err = genlmsg_reply(msg, info); - goto out; + return genlmsg_reply(msg, info); -nla_put_failure: + nla_put_failure: err = -ENOBUFS; - -free_msg: + free_msg: nlmsg_free(msg); - -out: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - -unlock_rtnl: - rtnl_unlock(); - return err; } @@ -5072,41 +4330,24 @@ nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] __read_mostly = { static int nl80211_set_cqm_rssi(struct genl_info *info, s32 threshold, u32 hysteresis) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev; - struct net_device *dev; - int err; + struct net_device *dev = info->user_ptr[1]; if (threshold > 0) return -EINVAL; - rtnl_lock(); - - err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); - if (err) - goto unlock_rdev; - wdev = dev->ieee80211_ptr; - if (!rdev->ops->set_cqm_rssi_config) { - err = -EOPNOTSUPP; - goto unlock_rdev; - } - - if (wdev->iftype != NL80211_IFTYPE_STATION) { - err = -EOPNOTSUPP; - goto unlock_rdev; - } - - err = rdev->ops->set_cqm_rssi_config(wdev->wiphy, dev, - threshold, hysteresis); + if (!rdev->ops->set_cqm_rssi_config) + return -EOPNOTSUPP; -unlock_rdev: - cfg80211_unlock_rdev(rdev); - dev_put(dev); - rtnl_unlock(); + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; - return err; + return rdev->ops->set_cqm_rssi_config(wdev->wiphy, dev, + threshold, hysteresis); } static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info) @@ -5140,6 +4381,65 @@ out: return err; } +#define NL80211_FLAG_NEED_WIPHY 0x01 +#define NL80211_FLAG_NEED_NETDEV 0x02 +#define NL80211_FLAG_NEED_RTNL 0x04 +#define NL80211_FLAG_CHECK_NETDEV_UP 0x08 +#define NL80211_FLAG_NEED_NETDEV_UP (NL80211_FLAG_NEED_NETDEV |\ + NL80211_FLAG_CHECK_NETDEV_UP) + +static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev; + struct net_device *dev; + int err; + bool rtnl = ops->internal_flags & NL80211_FLAG_NEED_RTNL; + + if (rtnl) + rtnl_lock(); + + if (ops->internal_flags & NL80211_FLAG_NEED_WIPHY) { + rdev = cfg80211_get_dev_from_info(info); + if (IS_ERR(rdev)) { + if (rtnl) + rtnl_unlock(); + return PTR_ERR(rdev); + } + info->user_ptr[0] = rdev; + } else if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV) { + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); + if (err) { + if (rtnl) + rtnl_unlock(); + return err; + } + if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP && + !netif_running(dev)) { + cfg80211_unlock_rdev(rdev); + dev_put(dev); + if (rtnl) + rtnl_unlock(); + return -ENETDOWN; + } + info->user_ptr[0] = rdev; + info->user_ptr[1] = dev; + } + + return 0; +} + +static void nl80211_post_doit(struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + if (info->user_ptr[0]) + cfg80211_unlock_rdev(info->user_ptr[0]); + if (info->user_ptr[1]) + dev_put(info->user_ptr[1]); + if (ops->internal_flags & NL80211_FLAG_NEED_RTNL) + rtnl_unlock(); +} + static struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_WIPHY, @@ -5147,12 +4447,14 @@ static struct genl_ops nl80211_ops[] = { .dumpit = nl80211_dump_wiphy, .policy = nl80211_policy, /* can be retrieved by unprivileged users */ + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, { .cmd = NL80211_CMD_SET_WIPHY, .doit = nl80211_set_wiphy, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_INTERFACE, @@ -5160,90 +4462,119 @@ static struct genl_ops nl80211_ops[] = { .dumpit = nl80211_dump_interface, .policy = nl80211_policy, /* can be retrieved by unprivileged users */ + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_SET_INTERFACE, .doit = nl80211_set_interface, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_NEW_INTERFACE, .doit = nl80211_new_interface, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WIPHY | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DEL_INTERFACE, .doit = nl80211_del_interface, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_KEY, .doit = nl80211_get_key, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_KEY, .doit = nl80211_set_key, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_NEW_KEY, .doit = nl80211_new_key, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DEL_KEY, .doit = nl80211_del_key, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_BEACON, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_addset_beacon, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_NEW_BEACON, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_addset_beacon, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DEL_BEACON, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .doit = nl80211_del_beacon, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_STATION, .doit = nl80211_get_station, .dumpit = nl80211_dump_station, .policy = nl80211_policy, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_STATION, .doit = nl80211_set_station, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_NEW_STATION, .doit = nl80211_new_station, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DEL_STATION, .doit = nl80211_del_station, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_MPATH, @@ -5251,30 +4582,40 @@ static struct genl_ops nl80211_ops[] = { .dumpit = nl80211_dump_mpath, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_MPATH, .doit = nl80211_set_mpath, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_NEW_MPATH, .doit = nl80211_new_mpath, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DEL_MPATH, .doit = nl80211_del_mpath, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_BSS, .doit = nl80211_set_bss, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_REG, @@ -5299,18 +4640,24 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_get_mesh_params, .policy = nl80211_policy, /* can be retrieved by unprivileged users */ + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_MESH_PARAMS, .doit = nl80211_set_mesh_params, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_TRIGGER_SCAN, .doit = nl80211_trigger_scan, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_SCAN, @@ -5322,36 +4669,48 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_authenticate, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_ASSOCIATE, .doit = nl80211_associate, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DEAUTHENTICATE, .doit = nl80211_deauthenticate, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DISASSOCIATE, .doit = nl80211_disassociate, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_JOIN_IBSS, .doit = nl80211_join_ibss, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_LEAVE_IBSS, .doit = nl80211_leave_ibss, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, #ifdef CONFIG_NL80211_TESTMODE { @@ -5359,6 +4718,8 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_testmode_do, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WIPHY | + NL80211_FLAG_NEED_RTNL, }, #endif { @@ -5366,18 +4727,24 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_connect, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DISCONNECT, .doit = nl80211_disconnect, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_WIPHY_NETNS, .doit = nl80211_wiphy_netns, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WIPHY | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_SURVEY, @@ -5389,72 +4756,104 @@ static struct genl_ops nl80211_ops[] = { .doit = nl80211_setdel_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_DEL_PMKSA, .doit = nl80211_setdel_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_FLUSH_PMKSA, .doit = nl80211_flush_pmksa, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_REMAIN_ON_CHANNEL, .doit = nl80211_remain_on_channel, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL, .doit = nl80211_cancel_remain_on_channel, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_TX_BITRATE_MASK, .doit = nl80211_set_tx_bitrate_mask, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_REGISTER_FRAME, .doit = nl80211_register_mgmt, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_FRAME, .doit = nl80211_tx_mgmt, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_POWER_SAVE, .doit = nl80211_set_power_save, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_POWER_SAVE, .doit = nl80211_get_power_save, .policy = nl80211_policy, /* can be retrieved by unprivileged users */ + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_CQM, .doit = nl80211_set_cqm, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_SET_CHANNEL, .doit = nl80211_set_channel, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, + }, + { + .cmd = NL80211_CMD_SET_WDS_PEER, + .doit = nl80211_set_wds_peer, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, }, }; diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index 1332c44..dbe35e1 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -14,6 +14,7 @@ * See COPYING for more details. */ +#include <linux/kernel.h> #include <net/cfg80211.h> #include <net/ieee80211_radiotap.h> #include <asm/unaligned.h> @@ -45,7 +46,7 @@ static const struct radiotap_align_size rtap_namespace_sizes[] = { }; static const struct ieee80211_radiotap_namespace radiotap_ns = { - .n_bits = sizeof(rtap_namespace_sizes) / sizeof(rtap_namespace_sizes[0]), + .n_bits = ARRAY_SIZE(rtap_namespace_sizes), .align_size = rtap_namespace_sizes, }; @@ -200,7 +201,7 @@ int ieee80211_radiotap_iterator_next( { while (1) { int hit = 0; - int pad, align, size, subns, vnslen; + int pad, align, size, subns; uint32_t oui; /* if no more EXT bits, that's it */ @@ -260,6 +261,27 @@ int ieee80211_radiotap_iterator_next( if (pad) iterator->_arg += align - pad; + if (iterator->_arg_index % 32 == IEEE80211_RADIOTAP_VENDOR_NAMESPACE) { + int vnslen; + + if ((unsigned long)iterator->_arg + size - + (unsigned long)iterator->_rtheader > + (unsigned long)iterator->_max_length) + return -EINVAL; + + oui = (*iterator->_arg << 16) | + (*(iterator->_arg + 1) << 8) | + *(iterator->_arg + 2); + subns = *(iterator->_arg + 3); + + find_ns(iterator, oui, subns); + + vnslen = get_unaligned_le16(iterator->_arg + 4); + iterator->_next_ns_data = iterator->_arg + size + vnslen; + if (!iterator->current_namespace) + size += vnslen; + } + /* * this is what we will return to user, but we need to * move on first so next call has something fresh to test @@ -286,40 +308,25 @@ int ieee80211_radiotap_iterator_next( /* these special ones are valid in each bitmap word */ switch (iterator->_arg_index % 32) { case IEEE80211_RADIOTAP_VENDOR_NAMESPACE: - iterator->_bitmap_shifter >>= 1; - iterator->_arg_index++; - iterator->_reset_on_ext = 1; - vnslen = get_unaligned_le16(iterator->this_arg + 4); - iterator->_next_ns_data = iterator->_arg + vnslen; - oui = (*iterator->this_arg << 16) | - (*(iterator->this_arg + 1) << 8) | - *(iterator->this_arg + 2); - subns = *(iterator->this_arg + 3); - - find_ns(iterator, oui, subns); - iterator->is_radiotap_ns = 0; - /* allow parsers to show this information */ + /* + * If parser didn't register this vendor + * namespace with us, allow it to show it + * as 'raw. Do do that, set argument index + * to vendor namespace. + */ iterator->this_arg_index = IEEE80211_RADIOTAP_VENDOR_NAMESPACE; - iterator->this_arg_size += vnslen; - if ((unsigned long)iterator->this_arg + - iterator->this_arg_size - - (unsigned long)iterator->_rtheader > - (unsigned long)(unsigned long)iterator->_max_length) - return -EINVAL; - hit = 1; - break; + if (!iterator->current_namespace) + hit = 1; + goto next_entry; case IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE: - iterator->_bitmap_shifter >>= 1; - iterator->_arg_index++; - iterator->_reset_on_ext = 1; iterator->current_namespace = &radiotap_ns; iterator->is_radiotap_ns = 1; - break; + goto next_entry; case IEEE80211_RADIOTAP_EXT: /* * bit 31 was set, there is more diff --git a/net/wireless/reg.c b/net/wireless/reg.c index b0d9a08..d14bbf9 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -74,7 +74,11 @@ const struct ieee80211_regdomain *cfg80211_regdomain; * - last_request */ static DEFINE_MUTEX(reg_mutex); -#define assert_reg_lock() WARN_ON(!mutex_is_locked(®_mutex)) + +static inline void assert_reg_lock(void) +{ + lockdep_assert_held(®_mutex); +} /* Used to queue up regulatory hints */ static LIST_HEAD(reg_requests_list); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 5ca8c71..503ebb8 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -650,14 +650,14 @@ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub) bss = container_of(pub, struct cfg80211_internal_bss, pub); spin_lock_bh(&dev->bss_lock); + if (!list_empty(&bss->list)) { + list_del_init(&bss->list); + dev->bss_generation++; + rb_erase(&bss->rbn, &dev->bss_tree); - list_del(&bss->list); - dev->bss_generation++; - rb_erase(&bss->rbn, &dev->bss_tree); - + kref_put(&bss->ref, bss_release); + } spin_unlock_bh(&dev->bss_lock); - - kref_put(&bss->ref, bss_release); } EXPORT_SYMBOL(cfg80211_unlink_bss); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index a8c2d6b..e17b0be 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -411,7 +411,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, ASSERT_WDEV_LOCK(wdev); - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; if (wdev->sme_state != CFG80211_SME_CONNECTING) @@ -548,7 +549,8 @@ void __cfg80211_roamed(struct wireless_dev *wdev, const u8 *bssid, ASSERT_WDEV_LOCK(wdev); - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; if (wdev->sme_state != CFG80211_SME_CONNECTED) @@ -644,7 +646,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, ASSERT_WDEV_LOCK(wdev); - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; if (wdev->sme_state != CFG80211_SME_CONNECTED) @@ -695,7 +698,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, */ if (rdev->ops->del_key) for (i = 0; i < 6; i++) - rdev->ops->del_key(wdev->wiphy, dev, i, NULL); + rdev->ops->del_key(wdev->wiphy, dev, i, false, NULL); #ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 74a9e3c..4294fa2 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -35,6 +35,14 @@ SHOW_FMT(index, "%d", wiphy_idx); SHOW_FMT(macaddress, "%pM", wiphy.perm_addr); SHOW_FMT(address_mask, "%pM", wiphy.addr_mask); +static ssize_t name_show(struct device *dev, + struct device_attribute *attr, + char *buf) { + struct wiphy *wiphy = &dev_to_rdev(dev)->wiphy; + return sprintf(buf, "%s\n", dev_name(&wiphy->dev)); +} + + static ssize_t addresses_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -57,6 +65,7 @@ static struct device_attribute ieee80211_dev_attrs[] = { __ATTR_RO(macaddress), __ATTR_RO(address_mask), __ATTR_RO(addresses), + __ATTR_RO(name), {} }; diff --git a/net/wireless/util.c b/net/wireless/util.c index bca32eb..76120ae 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -144,19 +144,25 @@ void ieee80211_set_bitrate_flags(struct wiphy *wiphy) int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, - const u8 *mac_addr) + bool pairwise, const u8 *mac_addr) { int i; if (key_idx > 5) return -EINVAL; + if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) + return -EINVAL; + + if (pairwise && !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 && + if (pairwise && key_idx && params->cipher != WLAN_CIPHER_SUITE_WEP40 && params->cipher != WLAN_CIPHER_SUITE_WEP104) return -EINVAL; @@ -326,7 +332,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, 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)) + iftype != NL80211_IFTYPE_AP_VLAN && + iftype != NL80211_IFTYPE_P2P_GO)) return -1; break; case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS): @@ -354,7 +361,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, break; case cpu_to_le16(IEEE80211_FCTL_FROMDS): if ((iftype != NL80211_IFTYPE_STATION && - iftype != NL80211_IFTYPE_MESH_POINT) || + iftype != NL80211_IFTYPE_P2P_CLIENT && + iftype != NL80211_IFTYPE_MESH_POINT) || (is_multicast_ether_addr(dst) && !compare_ether_addr(src, addr))) return -1; @@ -431,6 +439,7 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, switch (iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_P2P_GO: fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); /* DA BSSID SA */ memcpy(hdr.addr1, skb->data, ETH_ALEN); @@ -439,6 +448,7 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, hdrlen = 24; break; case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: fc |= cpu_to_le16(IEEE80211_FCTL_TODS); /* BSSID SA DA */ memcpy(hdr.addr1, bssid, ETH_ALEN); @@ -673,7 +683,7 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev) for (i = 0; i < 6; i++) { if (!wdev->connect_keys->params[i].cipher) continue; - if (rdev->ops->add_key(wdev->wiphy, dev, i, NULL, + if (rdev->ops->add_key(wdev->wiphy, dev, i, false, NULL, &wdev->connect_keys->params[i])) { printk(KERN_ERR "%s: failed to set key %d\n", dev->name, i); @@ -778,7 +788,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, /* if it's part of a bridge, reject changing type to station/ibss */ if ((dev->priv_flags & IFF_BRIDGE_PORT) && - (ntype == NL80211_IFTYPE_ADHOC || ntype == NL80211_IFTYPE_STATION)) + (ntype == NL80211_IFTYPE_ADHOC || + ntype == NL80211_IFTYPE_STATION || + ntype == NL80211_IFTYPE_P2P_CLIENT)) return -EBUSY; if (ntype != otype) { @@ -789,6 +801,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, cfg80211_leave_ibss(rdev, dev, false); break; case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_P2P_CLIENT: cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, true); break; @@ -817,9 +830,11 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, if (dev->ieee80211_ptr->use_4addr) break; /* fall through */ + case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_ADHOC: dev->priv_flags |= IFF_DONT_BRIDGE; break; + case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_WDS: diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 7e5c3a4..12222ee 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -432,14 +432,17 @@ int cfg80211_wext_giwretry(struct net_device *dev, EXPORT_SYMBOL_GPL(cfg80211_wext_giwretry); static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, - struct net_device *dev, const u8 *addr, - bool remove, bool tx_key, int idx, - struct key_params *params) + struct net_device *dev, bool pairwise, + const u8 *addr, bool remove, bool tx_key, + int idx, struct key_params *params) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err, i; bool rejoin = false; + if (pairwise && !addr) + return -EINVAL; + if (!wdev->wext.keys) { wdev->wext.keys = kzalloc(sizeof(*wdev->wext.keys), GFP_KERNEL); @@ -478,7 +481,13 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, __cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } - err = rdev->ops->del_key(&rdev->wiphy, dev, idx, addr); + + if (!pairwise && addr && + !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) + err = -ENOENT; + else + err = rdev->ops->del_key(&rdev->wiphy, dev, idx, + pairwise, addr); } wdev->wext.connect.privacy = false; /* @@ -507,12 +516,13 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, if (addr) tx_key = false; - if (cfg80211_validate_key_settings(rdev, params, idx, addr)) + if (cfg80211_validate_key_settings(rdev, params, idx, pairwise, addr)) return -EINVAL; err = 0; if (wdev->current_bss) - err = rdev->ops->add_key(&rdev->wiphy, dev, idx, addr, params); + err = rdev->ops->add_key(&rdev->wiphy, dev, idx, + pairwise, addr, params); if (err) return err; @@ -563,17 +573,17 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, } 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 net_device *dev, bool pairwise, + const u8 *addr, bool remove, bool tx_key, + int idx, struct key_params *params) { int err; /* devlist mutex needed for possible IBSS re-join */ mutex_lock(&rdev->devlist_mtx); wdev_lock(dev->ieee80211_ptr); - err = __cfg80211_set_encryption(rdev, dev, addr, remove, - tx_key, idx, params); + err = __cfg80211_set_encryption(rdev, dev, pairwise, addr, + remove, tx_key, idx, params); wdev_unlock(dev->ieee80211_ptr); mutex_unlock(&rdev->devlist_mtx); @@ -635,7 +645,7 @@ int cfg80211_wext_siwencode(struct net_device *dev, else if (!remove) return -EINVAL; - return cfg80211_set_encryption(rdev, dev, NULL, remove, + return cfg80211_set_encryption(rdev, dev, false, NULL, remove, wdev->wext.default_key == -1, idx, ¶ms); } @@ -725,7 +735,9 @@ int cfg80211_wext_siwencodeext(struct net_device *dev, } return cfg80211_set_encryption( - rdev, dev, addr, remove, + rdev, dev, + !(ext->ext_flags & IW_ENCODE_EXT_GROUP_KEY), + addr, remove, ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, idx, ¶ms); } @@ -1354,6 +1366,10 @@ struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) } wstats.qual.updated |= IW_QUAL_NOISE_INVALID; + if (sinfo.filled & STATION_INFO_RX_DROP_MISC) + wstats.discard.misc = sinfo.rx_dropped_misc; + if (sinfo.filled & STATION_INFO_TX_FAILED) + wstats.discard.retries = sinfo.tx_failed; return &wstats; } diff --git a/net/wireless/wext-priv.c b/net/wireless/wext-priv.c index 3feb28e..674d426 100644 --- a/net/wireless/wext-priv.c +++ b/net/wireless/wext-priv.c @@ -152,7 +152,7 @@ static int ioctl_private_iw_point(struct iw_point *iwp, unsigned int cmd, } else if (!iwp->pointer) return -EFAULT; - extra = kmalloc(extra_size, GFP_KERNEL); + extra = kzalloc(extra_size, GFP_KERNEL); if (!extra) return -ENOMEM; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5e86d4e..f7af98d 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -507,14 +507,14 @@ static int x25_listen(struct socket *sock, int backlog) struct sock *sk = sock->sk; int rc = -EOPNOTSUPP; - lock_kernel(); + lock_sock(sk); if (sk->sk_state != TCP_LISTEN) { memset(&x25_sk(sk)->dest_addr, 0, X25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; rc = 0; } - unlock_kernel(); + release_sock(sk); return rc; } @@ -688,7 +688,6 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr; int len, i, rc = 0; - lock_kernel(); if (!sock_flag(sk, SOCK_ZAPPED) || addr_len != sizeof(struct sockaddr_x25) || addr->sx25_family != AF_X25) { @@ -704,12 +703,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } } + lock_sock(sk); x25_sk(sk)->source_addr = addr->sx25_addr; x25_insert_socket(sk); sock_reset_flag(sk, SOCK_ZAPPED); + release_sock(sk); SOCK_DEBUG(sk, "x25_bind: socket is bound\n"); out: - unlock_kernel(); return rc; } @@ -751,7 +751,6 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, struct x25_route *rt; int rc = 0; - lock_kernel(); lock_sock(sk); if (sk->sk_state == TCP_ESTABLISHED && sock->state == SS_CONNECTING) { sock->state = SS_CONNECTED; @@ -829,7 +828,6 @@ out_put_route: x25_route_put(rt); out: release_sock(sk); - unlock_kernel(); return rc; } @@ -869,8 +867,7 @@ static int x25_accept(struct socket *sock, struct socket *newsock, int flags) struct sk_buff *skb; int rc = -EINVAL; - lock_kernel(); - if (!sk || sk->sk_state != TCP_LISTEN) + if (!sk) goto out; rc = -EOPNOTSUPP; @@ -878,6 +875,10 @@ static int x25_accept(struct socket *sock, struct socket *newsock, int flags) goto out; lock_sock(sk); + rc = -EINVAL; + if (sk->sk_state != TCP_LISTEN) + goto out2; + rc = x25_wait_for_data(sk, sk->sk_rcvtimeo); if (rc) goto out2; @@ -897,7 +898,6 @@ static int x25_accept(struct socket *sock, struct socket *newsock, int flags) out2: release_sock(sk); out: - unlock_kernel(); return rc; } @@ -909,7 +909,6 @@ static int x25_getname(struct socket *sock, struct sockaddr *uaddr, struct x25_sock *x25 = x25_sk(sk); int rc = 0; - lock_kernel(); if (peer) { if (sk->sk_state != TCP_ESTABLISHED) { rc = -ENOTCONN; @@ -923,19 +922,6 @@ static int x25_getname(struct socket *sock, struct sockaddr *uaddr, *uaddr_len = sizeof(*sx25); out: - unlock_kernel(); - return rc; -} - -static unsigned int x25_datagram_poll(struct file *file, struct socket *sock, - poll_table *wait) -{ - int rc; - - lock_kernel(); - rc = datagram_poll(file, sock, wait); - unlock_kernel(); - return rc; } @@ -1746,7 +1732,7 @@ static const struct proto_ops x25_proto_ops = { .socketpair = sock_no_socketpair, .accept = x25_accept, .getname = x25_getname, - .poll = x25_datagram_poll, + .poll = datagram_poll, .ioctl = x25_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_x25_ioctl, diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index a3cca0a..64f2ae1 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -101,7 +101,7 @@ resume: err = -EHOSTUNREACH; goto error_nolock; } - skb_dst_set_noref(skb, dst); + skb_dst_set(skb, dst_clone(dst)); x = dst->xfrm; } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 2b3ed7a..044e778 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -50,6 +50,9 @@ static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family); static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo); static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); +static int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *xdst, + struct flowi *fl, int family, int strict); + static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); @@ -1175,9 +1178,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; - family = tmpl->encap_family; - if (xfrm_addr_any(local, family)) { - error = xfrm_get_saddr(net, &tmp, remote, family); + if (xfrm_addr_any(local, tmpl->encap_family)) { + error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family); if (error) goto fail; local = &tmp; @@ -2277,7 +2279,7 @@ static void xfrm_init_pmtu(struct dst_entry *dst) * still valid. */ -int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, +static int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, struct flowi *fl, int family, int strict) { struct dst_entry *dst = &first->u.dst; @@ -2359,8 +2361,6 @@ int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, return 1; } -EXPORT_SYMBOL(xfrm_bundle_ok); - int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) { struct net *net; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5208b12f..eb96ce5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -656,15 +656,23 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) EXPORT_SYMBOL(xfrm_sad_getinfo); static int -xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr, - unsigned short family) +xfrm_init_tempstate(struct xfrm_state *x, struct flowi *fl, + struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr, + unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (!afinfo) return -1; - afinfo->init_tempsel(x, fl, tmpl, daddr, saddr); + afinfo->init_tempsel(&x->sel, fl); + + if (family != tmpl->encap_family) { + xfrm_state_put_afinfo(afinfo); + afinfo = xfrm_state_get_afinfo(tmpl->encap_family); + if (!afinfo) + return -1; + } + afinfo->init_temprop(x, tmpl, daddr, saddr); xfrm_state_put_afinfo(afinfo); return 0; } @@ -790,37 +798,38 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; + unsigned short encap_family = tmpl->encap_family; to_put = NULL; spin_lock_bh(&xfrm_state_lock); - h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, family); + h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { - if (x->props.family == family && + if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && !(x->props.flags & XFRM_STATE_WILDRECV) && - xfrm_state_addr_check(x, daddr, saddr, family) && + xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, family, daddr, saddr, + xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr, &best, &acquire_in_progress, &error); } if (best) goto found; - h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); + h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) { - if (x->props.family == family && + if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && !(x->props.flags & XFRM_STATE_WILDRECV) && - xfrm_state_addr_check(x, daddr, saddr, family) && + xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, family, daddr, saddr, + xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr, &best, &acquire_in_progress, &error); } @@ -829,7 +838,7 @@ found: if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && (x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi, - tmpl->id.proto, family)) != NULL) { + tmpl->id.proto, encap_family)) != NULL) { to_put = x0; error = -EEXIST; goto out; @@ -839,9 +848,9 @@ found: error = -ENOMEM; goto out; } - /* Initialize temporary selector matching only + /* Initialize temporary state matching only * to current session. */ - xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family); + xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid); @@ -856,10 +865,10 @@ found: x->km.state = XFRM_STATE_ACQ; list_add(&x->km.all, &net->xfrm.state_all); hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); - h = xfrm_src_hash(net, daddr, saddr, family); + h = xfrm_src_hash(net, daddr, saddr, encap_family); hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); if (x->id.spi) { - h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, family); + h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; |