diff options
Diffstat (limited to 'net')
373 files changed, 9674 insertions, 6172 deletions
diff --git a/net/802/garp.c b/net/802/garp.c index c1df2dad8c6b..16102951d36a 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -554,8 +554,7 @@ static void garp_release_port(struct net_device *dev) return; } rcu_assign_pointer(dev->garp_port, NULL); - synchronize_rcu(); - kfree(port); + kfree_rcu(port, rcu); } int garp_init_applicant(struct net_device *dev, struct garp_application *appl) @@ -607,7 +606,6 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl ASSERT_RTNL(); rcu_assign_pointer(port->applicants[appl->type], NULL); - synchronize_rcu(); /* Delete timer and generate a final TRANSMIT_PDU event to flush out * all pending messages before the applicant is gone. */ @@ -617,7 +615,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl garp_queue_xmit(app); dev_mc_del(dev, appl->proto.group_address); - kfree(app); + kfree_rcu(app, rcu); garp_release_port(dev); } EXPORT_SYMBOL_GPL(garp_uninit_applicant); diff --git a/net/802/psnap.c b/net/802/psnap.c index 21cde8fd5795..db6baf7cf6e9 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -147,7 +147,6 @@ struct datalink_proto *register_snap_client(const unsigned char *desc, out: spin_unlock_bh(&snap_lock); - synchronize_net(); return proto; } diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 7850412f52b7..c7a581a96894 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -46,13 +46,6 @@ int vlan_net_id __read_mostly; const char vlan_fullname[] = "802.1Q VLAN Support"; const char vlan_version[] = DRV_VERSION; -static const char vlan_copyright[] = "Ben Greear <greearb@candelatech.com>"; -static const char vlan_buggyright[] = "David S. Miller <davem@redhat.com>"; - -static struct packet_type vlan_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_8021Q), - .func = vlan_skb_recv, /* VLAN receive method */ -}; /* End of global variables definitions. */ @@ -124,10 +117,14 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) grp->nr_vlans--; - vlan_group_set_device(grp, vlan_id, NULL); - if (!grp->killall) - synchronize_net(); + if (vlan->flags & VLAN_FLAG_GVRP) + vlan_gvrp_request_leave(dev); + vlan_group_set_device(grp, vlan_id, NULL); + /* Because unregister_netdevice_queue() makes sure at least one rcu + * grace period is respected before device freeing, + * we dont need to call synchronize_net() here. + */ unregister_netdevice_queue(dev, head); /* If the group is now empty, kill off the group. */ @@ -327,10 +324,6 @@ static void vlan_sync_address(struct net_device *dev, static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { - u32 old_features = vlandev->features; - - vlandev->features &= ~dev->vlan_features; - vlandev->features |= dev->features & dev->vlan_features; vlandev->gso_max_size = dev->gso_max_size; if (dev->features & NETIF_F_HW_VLAN_TX) @@ -341,8 +334,8 @@ static void vlan_transfer_features(struct net_device *dev, #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif - if (old_features != vlandev->features) - netdev_features_change(vlandev); + + netdev_update_features(vlandev); } static void __vlan_device_event(struct net_device *dev, unsigned long event) @@ -487,9 +480,6 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (dev->reg_state != NETREG_UNREGISTERING) break; - /* Delete all VLANs for this dev. */ - grp->killall = 1; - for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); if (!vlandev) @@ -508,6 +498,18 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ return NOTIFY_BAD; + + case NETDEV_NOTIFY_PEERS: + case NETDEV_BONDING_FAILOVER: + /* Propagate to vlan devices */ + for (i = 0; i < VLAN_N_VID; i++) { + vlandev = vlan_group_get_device(grp, i); + if (!vlandev) + continue; + + call_netdevice_notifiers(event, vlandev); + } + break; } out: @@ -669,8 +671,7 @@ static int __init vlan_proto_init(void) { int err; - pr_info("%s v%s %s\n", vlan_fullname, vlan_version, vlan_copyright); - pr_info("All bugs added by %s\n", vlan_buggyright); + pr_info("%s v%s\n", vlan_fullname, vlan_version); err = register_pernet_subsys(&vlan_net_ops); if (err < 0) @@ -688,7 +689,6 @@ static int __init vlan_proto_init(void) if (err < 0) goto err4; - dev_add_pack(&vlan_packet_type); vlan_ioctl_set(vlan_ioctl_handler); return 0; @@ -709,8 +709,6 @@ static void __exit vlan_cleanup_module(void) unregister_netdevice_notifier(&vlan_notifier_block); - dev_remove_pack(&vlan_packet_type); - 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 5687c9b95f33..9da07e30d1a2 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -75,8 +75,6 @@ static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev) } /* 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); void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); int vlan_dev_set_egress_priority(const struct net_device *dev, @@ -120,11 +118,6 @@ extern void vlan_netlink_fini(void); extern struct rtnl_link_ops vlan_link_ops; -static inline int is_vlan_dev(struct net_device *dev) -{ - return dev->priv_flags & IFF_802_1Q_VLAN; -} - extern int vlan_net_id; struct proc_dir_entry; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index ce8e3ab3e7a5..41495dc2a4c9 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -4,7 +4,7 @@ #include <linux/netpoll.h> #include "vlan.h" -bool vlan_hwaccel_do_receive(struct sk_buff **skbp) +bool vlan_do_receive(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK; @@ -88,3 +88,86 @@ gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, return napi_gro_frags(napi); } EXPORT_SYMBOL(vlan_gro_frags); + +static struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb) +{ + if (vlan_dev_info(skb->dev)->flags & VLAN_FLAG_REORDER_HDR) { + if (skb_cow(skb, skb_headroom(skb)) < 0) + skb = NULL; + if (skb) { + /* Lifted from Gleb's VLAN code... */ + memmove(skb->data - ETH_HLEN, + skb->data - VLAN_ETH_HLEN, 12); + skb->mac_header += VLAN_HLEN; + } + } + return skb; +} + +static void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) +{ + __be16 proto; + unsigned char *rawp; + + /* + * Was a VLAN packet, grab the encapsulated protocol, which the layer + * three protocols care about. + */ + + proto = vhdr->h_vlan_encapsulated_proto; + if (ntohs(proto) >= 1536) { + skb->protocol = proto; + return; + } + + rawp = skb->data; + if (*(unsigned short *) rawp == 0xFFFF) + /* + * This is a magic hack to spot IPX packets. Older Novell + * breaks the protocol design and runs IPX over 802.3 without + * an 802.2 LLC layer. We look for FFFF which isn't a used + * 802.2 SSAP/DSAP. This won't work for fault tolerant netware + * but does for the rest. + */ + skb->protocol = htons(ETH_P_802_3); + else + /* + * Real 802.2 LLC + */ + skb->protocol = htons(ETH_P_802_2); +} + +struct sk_buff *vlan_untag(struct sk_buff *skb) +{ + struct vlan_hdr *vhdr; + u16 vlan_tci; + + if (unlikely(vlan_tx_tag_present(skb))) { + /* vlan_tci is already set-up so leave this for another time */ + return skb; + } + + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + goto err_free; + + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + goto err_free; + + vhdr = (struct vlan_hdr *) skb->data; + vlan_tci = ntohs(vhdr->h_vlan_TCI); + __vlan_hwaccel_put_tag(skb, vlan_tci); + + skb_pull_rcsum(skb, VLAN_HLEN); + vlan_set_encap_proto(skb, vhdr); + + skb = vlan_check_reorder_header(skb); + if (unlikely(!skb)) + goto err_free; + + return skb; + +err_free: + kfree_skb(skb); + return NULL; +} diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e34ea9e5e28b..f247f5bff88d 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -65,179 +65,6 @@ static int vlan_dev_rebuild_header(struct sk_buff *skb) return 0; } -static inline struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb) -{ - if (vlan_dev_info(skb->dev)->flags & VLAN_FLAG_REORDER_HDR) { - if (skb_cow(skb, skb_headroom(skb)) < 0) - skb = NULL; - if (skb) { - /* Lifted from Gleb's VLAN code... */ - memmove(skb->data - ETH_HLEN, - skb->data - VLAN_ETH_HLEN, 12); - skb->mac_header += VLAN_HLEN; - } - } - - return skb; -} - -static inline void vlan_set_encap_proto(struct sk_buff *skb, - struct vlan_hdr *vhdr) -{ - __be16 proto; - unsigned char *rawp; - - /* - * Was a VLAN packet, grab the encapsulated protocol, which the layer - * three protocols care about. - */ - - proto = vhdr->h_vlan_encapsulated_proto; - if (ntohs(proto) >= 1536) { - skb->protocol = proto; - return; - } - - rawp = skb->data; - if (*(unsigned short *)rawp == 0xFFFF) - /* - * This is a magic hack to spot IPX packets. Older Novell - * breaks the protocol design and runs IPX over 802.3 without - * an 802.2 LLC layer. We look for FFFF which isn't a used - * 802.2 SSAP/DSAP. This won't work for fault tolerant netware - * but does for the rest. - */ - skb->protocol = htons(ETH_P_802_3); - else - /* - * Real 802.2 LLC - */ - skb->protocol = htons(ETH_P_802_2); -} - -/* - * Determine the packet's protocol ID. The rule here is that we - * assume 802.3 if the type field is short enough to be a length. - * This is normal practice and works for any 'now in use' protocol. - * - * Also, at this point we assume that we ARE dealing exclusively with - * VLAN packets, or packets that should be made into VLAN packets based - * on a default VLAN ID. - * - * NOTE: Should be similar to ethernet/eth.c. - * - * SANITY NOTE: This method is called when a packet is moving up the stack - * towards userland. To get here, it would have already passed - * through the ethernet/eth.c eth_type_trans() method. - * SANITY NOTE 2: We are referencing to the VLAN_HDR frields, which MAY be - * stored UNALIGNED in the memory. RISC systems don't like - * such cases very much... - * SANITY NOTE 2a: According to Dave Miller & Alexey, it will always be - * aligned, so there doesn't need to be any of the unaligned - * stuff. It has been commented out now... --Ben - * - */ -int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *ptype, struct net_device *orig_dev) -{ - struct vlan_hdr *vhdr; - struct vlan_pcpu_stats *rx_stats; - struct net_device *vlan_dev; - u16 vlan_id; - u16 vlan_tci; - - skb = skb_share_check(skb, GFP_ATOMIC); - if (skb == NULL) - goto err_free; - - if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) - goto err_free; - - vhdr = (struct vlan_hdr *)skb->data; - vlan_tci = ntohs(vhdr->h_vlan_TCI); - vlan_id = vlan_tci & VLAN_VID_MASK; - - rcu_read_lock(); - 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 - * really a VLAN), so we will just netif_rx it later to the - * original interface, but with the skb->proto set to the - * wrapped proto: we do nothing here. - */ - - if (!vlan_dev) { - if (vlan_id) { - pr_debug("%s: ERROR: No net_device for VID: %u on dev: %s\n", - __func__, vlan_id, dev->name); - goto err_unlock; - } - rx_stats = NULL; - } else { - skb->dev = vlan_dev; - - rx_stats = this_cpu_ptr(vlan_dev_info(skb->dev)->vlan_pcpu_stats); - - u64_stats_update_begin(&rx_stats->syncp); - rx_stats->rx_packets++; - rx_stats->rx_bytes += skb->len; - - skb->priority = vlan_get_ingress_priority(skb->dev, vlan_tci); - - pr_debug("%s: priority: %u for TCI: %hu\n", - __func__, skb->priority, vlan_tci); - - switch (skb->pkt_type) { - case PACKET_BROADCAST: - /* Yeah, stats collect these together.. */ - /* stats->broadcast ++; // no such counter :-( */ - break; - - case PACKET_MULTICAST: - rx_stats->rx_multicast++; - break; - - case PACKET_OTHERHOST: - /* Our lower layer thinks this is not local, let's make - * sure. - * 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, - skb->dev->dev_addr)) - skb->pkt_type = PACKET_HOST; - break; - default: - break; - } - u64_stats_update_end(&rx_stats->syncp); - } - - skb_pull_rcsum(skb, VLAN_HLEN); - vlan_set_encap_proto(skb, vhdr); - - if (vlan_dev) { - skb = vlan_check_reorder_header(skb); - if (!skb) { - rx_stats->rx_errors++; - goto err_unlock; - } - } - - 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; -} - static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb) { @@ -487,9 +314,6 @@ static int vlan_dev_stop(struct net_device *dev) struct vlan_dev_info *vlan = vlan_dev_info(dev); struct net_device *real_dev = vlan->real_dev; - if (vlan->flags & VLAN_FLAG_GVRP) - vlan_gvrp_request_leave(dev); - dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); if (dev->flags & IFF_ALLMULTI) @@ -704,8 +528,8 @@ static int vlan_dev_init(struct net_device *dev) (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); - dev->features |= real_dev->features & real_dev->vlan_features; - dev->features |= NETIF_F_LLTX; + dev->hw_features = NETIF_F_ALL_TX_OFFLOADS; + dev->features |= real_dev->vlan_features | NETIF_F_LLTX; dev->gso_max_size = real_dev->gso_max_size; /* ipv6 shared card related stuff */ @@ -759,6 +583,19 @@ static void vlan_dev_uninit(struct net_device *dev) } } +static u32 vlan_dev_fix_features(struct net_device *dev, u32 features) +{ + struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + + features &= real_dev->features; + features &= real_dev->vlan_features; + if (dev_ethtool_get_rx_csum(real_dev)) + features |= NETIF_F_RXCSUM; + features |= NETIF_F_LLTX; + + return features; +} + static int vlan_ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { @@ -774,18 +611,6 @@ static void vlan_ethtool_get_drvinfo(struct net_device *dev, strcpy(info->fw_version, "N/A"); } -static u32 vlan_ethtool_get_rx_csum(struct net_device *dev) -{ - const struct vlan_dev_info *vlan = vlan_dev_info(dev); - return dev_ethtool_get_rx_csum(vlan->real_dev); -} - -static u32 vlan_ethtool_get_flags(struct net_device *dev) -{ - const struct vlan_dev_info *vlan = vlan_dev_info(dev); - return dev_ethtool_get_flags(vlan->real_dev); -} - static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { @@ -823,32 +648,10 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st return stats; } -static int vlan_ethtool_set_tso(struct net_device *dev, u32 data) -{ - if (data) { - struct net_device *real_dev = vlan_dev_info(dev)->real_dev; - - /* Underlying device must support TSO for VLAN-tagged packets - * and must have TSO enabled now. - */ - if (!(real_dev->vlan_features & NETIF_F_TSO)) - return -EOPNOTSUPP; - if (!(real_dev->features & NETIF_F_TSO)) - return -EINVAL; - dev->features |= NETIF_F_TSO; - } else { - dev->features &= ~NETIF_F_TSO; - } - return 0; -} - static const struct ethtool_ops vlan_ethtool_ops = { .get_settings = vlan_ethtool_get_settings, .get_drvinfo = vlan_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, - .get_rx_csum = vlan_ethtool_get_rx_csum, - .get_flags = vlan_ethtool_get_flags, - .set_tso = vlan_ethtool_set_tso, }; static const struct net_device_ops vlan_netdev_ops = { @@ -874,6 +677,7 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, .ndo_fcoe_ddp_target = vlan_dev_fcoe_ddp_target, #endif + .ndo_fix_features = vlan_dev_fix_features, }; void vlan_setup(struct net_device *dev) diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index d1314cf18adf..d940c49d168a 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -54,7 +54,7 @@ static const char name_conf[] = "config"; /* * Structures for interfacing with the /proc filesystem. - * VLAN creates its own directory /proc/net/vlan with the folowing + * VLAN creates its own directory /proc/net/vlan with the following * entries: * config device status/configuration * <device> entry for each device diff --git a/net/9p/client.c b/net/9p/client.c index 2ccbf04d37df..ceab943dfc49 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -178,7 +178,7 @@ free_and_return: * @tag: numeric id for transaction * * this is a simple array lookup, but will grow the - * request_slots as necessary to accomodate transaction + * request_slots as necessary to accommodate transaction * ids which did not previously have a slot. * * this code relies on the client spinlock to manage locks, its @@ -614,7 +614,7 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) err = c->trans_mod->request(c, req); if (err < 0) { - if (err != -ERESTARTSYS) + if (err != -ERESTARTSYS && err != -EFAULT) c->status = Disconnected; goto reterr; } @@ -929,15 +929,15 @@ error: } EXPORT_SYMBOL(p9_client_attach); -struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, - int clone) +struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, + char **wnames, int clone) { int err; struct p9_client *clnt; struct p9_fid *fid; struct p9_qid *wqids; struct p9_req_t *req; - int16_t nwqids, count; + uint16_t nwqids, count; err = 0; wqids = NULL; @@ -955,7 +955,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, fid = oldfid; - P9_DPRINTK(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %d wname[0] %s\n", + P9_DPRINTK(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n", oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL); req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid, @@ -1220,27 +1220,6 @@ error: } EXPORT_SYMBOL(p9_client_fsync); -int p9_client_sync_fs(struct p9_fid *fid) -{ - int err = 0; - struct p9_req_t *req; - struct p9_client *clnt; - - P9_DPRINTK(P9_DEBUG_9P, ">>> TSYNC_FS fid %d\n", fid->fid); - - clnt = fid->clnt; - req = p9_client_rpc(clnt, P9_TSYNCFS, "d", fid->fid); - if (IS_ERR(req)) { - err = PTR_ERR(req); - goto error; - } - P9_DPRINTK(P9_DEBUG_9P, "<<< RSYNCFS fid %d\n", fid->fid); - p9_free_req(clnt, req); -error: - return err; -} -EXPORT_SYMBOL(p9_client_sync_fs); - int p9_client_clunk(struct p9_fid *fid) { int err; @@ -1302,7 +1281,7 @@ int p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, u32 count) { - int err, rsize, total; + int err, rsize; struct p9_client *clnt; struct p9_req_t *req; char *dataptr; @@ -1311,7 +1290,6 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, (long long unsigned) offset, count); err = 0; clnt = fid->clnt; - total = 0; rsize = fid->iounit; if (!rsize || rsize > clnt->msize-P9_IOHDRSZ) @@ -1367,7 +1345,7 @@ int p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, u64 offset, u32 count) { - int err, rsize, total; + int err, rsize; struct p9_client *clnt; struct p9_req_t *req; @@ -1375,7 +1353,6 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, fid->fid, (long long unsigned) offset, count); err = 0; clnt = fid->clnt; - total = 0; rsize = fid->iounit; if (!rsize || rsize > clnt->msize-P9_IOHDRSZ) @@ -1766,7 +1743,7 @@ EXPORT_SYMBOL_GPL(p9_client_xattrcreate); int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) { - int err, rsize, total; + int err, rsize; struct p9_client *clnt; struct p9_req_t *req; char *dataptr; @@ -1776,7 +1753,6 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) err = 0; clnt = fid->clnt; - total = 0; rsize = fid->iounit; if (!rsize || rsize > clnt->msize-P9_READDIRHDRSZ) diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 8a4084fa8b5a..a873277cb996 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -265,7 +265,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'T':{ - int16_t *nwname = va_arg(ap, int16_t *); + uint16_t *nwname = va_arg(ap, uint16_t *); char ***wnames = va_arg(ap, char ***); errcode = p9pdu_readf(pdu, proto_version, @@ -468,7 +468,8 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, case 'E':{ int32_t cnt = va_arg(ap, int32_t); const char *k = va_arg(ap, const void *); - const char *u = va_arg(ap, const void *); + const char __user *u = va_arg(ap, + const void __user *); errcode = p9pdu_writef(pdu, proto_version, "d", cnt); if (!errcode && pdu_write_urw(pdu, k, u, cnt)) @@ -495,7 +496,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'T':{ - int16_t nwname = va_arg(ap, int); + uint16_t nwname = va_arg(ap, int); const char **wnames = va_arg(ap, const char **); errcode = p9pdu_writef(pdu, proto_version, "w", @@ -673,6 +674,7 @@ int p9dirent_read(char *buf, int len, struct p9_dirent *dirent, } strcpy(dirent->d_name, nameptr); + kfree(nameptr); out: return fake_pdu.offset; diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index 9172ab78fcb0..9a70ebdec56e 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -36,7 +36,7 @@ p9_release_req_pages(struct trans_rpage_info *rpinfo) EXPORT_SYMBOL(p9_release_req_pages); /** - * p9_nr_pages - Return number of pages needed to accomodate the payload. + * p9_nr_pages - Return number of pages needed to accommodate the payload. */ int p9_nr_pages(struct p9_req_t *req) @@ -55,7 +55,7 @@ EXPORT_SYMBOL(p9_nr_pages); * @req: Request to be sent to server. * @pdata_off: data offset into the first page after translation (gup). * @pdata_len: Total length of the IO. gup may not return requested # of pages. - * @nr_pages: number of pages to accomodate the payload + * @nr_pages: number of pages to accommodate the payload * @rw: Indicates if the pages are for read or write. */ int @@ -63,10 +63,10 @@ p9_payload_gup(struct p9_req_t *req, size_t *pdata_off, int *pdata_len, int nr_pages, u8 rw) { uint32_t first_page_bytes = 0; - uint32_t pdata_mapped_pages; + int32_t pdata_mapped_pages; struct trans_rpage_info *rpinfo; - *pdata_off = (size_t)req->tc->pubuf & (PAGE_SIZE-1); + *pdata_off = (__force size_t)req->tc->pubuf & (PAGE_SIZE-1); if (*pdata_off) first_page_bytes = min(((size_t)PAGE_SIZE - *pdata_off), @@ -75,14 +75,9 @@ p9_payload_gup(struct p9_req_t *req, size_t *pdata_off, int *pdata_len, rpinfo = req->tc->private; pdata_mapped_pages = get_user_pages_fast((unsigned long)req->tc->pubuf, nr_pages, rw, &rpinfo->rp_data[0]); + if (pdata_mapped_pages <= 0) + return pdata_mapped_pages; - if (pdata_mapped_pages < 0) { - printk(KERN_ERR "get_user_pages_fast failed:%d udata:%p" - "nr_pages:%d\n", pdata_mapped_pages, - req->tc->pubuf, nr_pages); - pdata_mapped_pages = 0; - return -EIO; - } rpinfo->rp_nr_pages = pdata_mapped_pages; if (*pdata_off) { *pdata_len = first_page_bytes; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index aa5672b15eae..4a9084395d35 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -716,7 +716,6 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) substring_t args[MAX_OPT_ARGS]; int option; char *options, *tmp_options; - int ret; opts->port = P9_PORT; opts->rfd = ~0; @@ -744,7 +743,6 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) if (r < 0) { P9_DPRINTK(P9_DEBUG_ERROR, "integer field, but no integer?\n"); - ret = r; continue; } } diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 150e0c4bbf40..844a7a5607e3 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -167,7 +167,6 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) substring_t args[MAX_OPT_ARGS]; int option; char *options, *tmp_options; - int ret; opts->port = P9_PORT; opts->sq_depth = P9_RDMA_SQ_DEPTH; @@ -195,7 +194,6 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) if (r < 0) { P9_DPRINTK(P9_DEBUG_ERROR, "integer field, but no integer?\n"); - ret = r; continue; } switch (token) { diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index e8f046b07182..244e70742183 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -326,8 +326,11 @@ req_retry_pinned: outp = pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM, pdata_off, rpinfo->rp_data, pdata_len); } else { - char *pbuf = req->tc->pubuf ? req->tc->pubuf : - req->tc->pkbuf; + char *pbuf; + if (req->tc->pubuf) + pbuf = (__force char *) req->tc->pubuf; + else + pbuf = req->tc->pkbuf; outp = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, pbuf, req->tc->pbuf_size); } @@ -352,8 +355,12 @@ req_retry_pinned: in = pack_sg_list_p(chan->sg, out+inp, VIRTQUEUE_NUM, pdata_off, rpinfo->rp_data, pdata_len); } else { - char *pbuf = req->tc->pubuf ? req->tc->pubuf : - req->tc->pkbuf; + char *pbuf; + if (req->tc->pubuf) + pbuf = (__force char *) req->tc->pubuf; + else + pbuf = req->tc->pkbuf; + in = pack_sg_list(chan->sg, out+inp, VIRTQUEUE_NUM, pbuf, req->tc->pbuf_size); } diff --git a/net/9p/util.c b/net/9p/util.c index b84619b5ba22..da6af81e59d9 100644 --- a/net/9p/util.c +++ b/net/9p/util.c @@ -67,7 +67,7 @@ EXPORT_SYMBOL(p9_idpool_create); /** * p9_idpool_destroy - create a new per-connection id pool - * @p: idpool to destory + * @p: idpool to destroy */ void p9_idpool_destroy(struct p9_idpool *p) diff --git a/net/Kconfig b/net/Kconfig index 79cabf1ee68b..878151c772c9 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -232,6 +232,20 @@ config XPS depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y +config HAVE_BPF_JIT + bool + +config BPF_JIT + bool "enable BPF Just In Time compiler" + depends on HAVE_BPF_JIT + depends on MODULES + ---help--- + Berkeley Packet Filter filtering capabilities are normally handled + by an interpreter. This option allows kernel to generate a native + code when filter is loaded in memory. This should speedup + packet sniffing (libpcap/tcpdump). Note : Admin should enable + this feature changing /proc/sys/net/core/bpf_jit_enable + menu "Network testing" config NET_PKTGEN diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index f7fa67c78766..f49da5814bc3 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -59,6 +59,14 @@ static ssize_t show_atmaddress(struct device *cdev, return pos - buf; } +static ssize_t show_atmindex(struct device *cdev, + struct device_attribute *attr, char *buf) +{ + struct atm_dev *adev = to_atm_dev(cdev); + + return sprintf(buf, "%d\n", adev->number); +} + static ssize_t show_carrier(struct device *cdev, struct device_attribute *attr, char *buf) { @@ -99,6 +107,7 @@ static ssize_t show_link_rate(struct device *cdev, static DEVICE_ATTR(address, S_IRUGO, show_address, NULL); static DEVICE_ATTR(atmaddress, S_IRUGO, show_atmaddress, NULL); +static DEVICE_ATTR(atmindex, S_IRUGO, show_atmindex, NULL); static DEVICE_ATTR(carrier, S_IRUGO, show_carrier, NULL); static DEVICE_ATTR(type, S_IRUGO, show_type, NULL); static DEVICE_ATTR(link_rate, S_IRUGO, show_link_rate, NULL); @@ -106,6 +115,7 @@ static DEVICE_ATTR(link_rate, S_IRUGO, show_link_rate, NULL); static struct device_attribute *atm_attrs[] = { &dev_attr_atmaddress, &dev_attr_address, + &dev_attr_atmindex, &dev_attr_carrier, &dev_attr_type, &dev_attr_link_rate, diff --git a/net/atm/br2684.c b/net/atm/br2684.c index fce2eae8d476..2252c2085dac 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -509,7 +509,7 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) write_lock_irq(&devs_lock); net_dev = br2684_find_dev(&be.ifspec); if (net_dev == NULL) { - pr_err("tried to attach to non-existant device\n"); + pr_err("tried to attach to non-existent device\n"); err = -ENXIO; goto error; } diff --git a/net/atm/lec.c b/net/atm/lec.c index 38754fdb88ba..25073b6ef474 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -129,7 +129,6 @@ static struct net_device *dev_lec[MAX_LEC_ITF]; #if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) { - struct ethhdr *eth; char *buff; struct lec_priv *priv; @@ -138,7 +137,6 @@ static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) * LE_TOPOLOGY_REQUEST with the same value of Topology Change bit * as the Config BPDU has */ - eth = (struct ethhdr *)skb->data; buff = skb->data + skb->dev->hard_header_len; if (*buff++ == 0x42 && *buff++ == 0x42 && *buff++ == 0x03) { struct sock *sk; @@ -1180,7 +1178,6 @@ static int __init lane_module_init(void) static void __exit lane_module_cleanup(void) { int i; - struct lec_priv *priv; remove_proc_entry("lec", atm_proc_root); @@ -1188,7 +1185,6 @@ static void __exit lane_module_cleanup(void) for (i = 0; i < MAX_LEC_ITF; i++) { if (dev_lec[i] != NULL) { - priv = netdev_priv(dev_lec[i]); unregister_netdev(dev_lec[i]); free_netdev(dev_lec[i]); dev_lec[i] = NULL; diff --git a/net/atm/lec.h b/net/atm/lec.h index 9d14d196cc1d..dfc071966463 100644 --- a/net/atm/lec.h +++ b/net/atm/lec.h @@ -35,7 +35,7 @@ struct lecdatahdr_8025 { * Operations that LANE2 capable device can do. Two first functions * are used to make the device do things. See spec 3.1.3 and 3.1.4. * - * The third function is intented for the MPOA component sitting on + * The third function is intended for the MPOA component sitting on * top of the LANE device. The MPOA component assigns it's own function * to (*associate_indicator)() and the LANE device will use that * function to tell about TLVs it sees floating through. diff --git a/net/atm/proc.c b/net/atm/proc.c index f85da0779e5e..be3afdefec58 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -191,7 +191,7 @@ static void vcc_info(struct seq_file *seq, struct atm_vcc *vcc) { struct sock *sk = sk_atm(vcc); - seq_printf(seq, "%p ", vcc); + seq_printf(seq, "%pK ", vcc); if (!vcc->dev) seq_printf(seq, "Unassigned "); else @@ -218,7 +218,7 @@ static void svc_info(struct seq_file *seq, struct atm_vcc *vcc) { if (!vcc->dev) seq_printf(seq, sizeof(void *) == 4 ? - "N/A@%p%10s" : "N/A@%p%2s", vcc, ""); + "N/A@%pK%10s" : "N/A@%pK%2s", vcc, ""); else seq_printf(seq, "%3d %3d %5d ", vcc->dev->number, vcc->vpi, vcc->vci); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 6da5daeebab7..e7c69f4619ec 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1538,8 +1538,6 @@ static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock, } /* Build a packet */ - SOCK_DEBUG(sk, "AX.25: sendto: Addresses built. Building packet.\n"); - /* Assume the worst case */ size = len + ax25->ax25_dev->dev->hard_header_len; @@ -1549,8 +1547,6 @@ static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock, skb_reserve(skb, size - len); - SOCK_DEBUG(sk, "AX.25: Appending user data\n"); - /* User data follows immediately after the AX.25 data */ if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { err = -EFAULT; @@ -1564,8 +1560,6 @@ static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock, if (!ax25->pidincl) *skb_push(skb, 1) = sk->sk_protocol; - SOCK_DEBUG(sk, "AX.25: Transmitting buffer\n"); - if (sk->sk_type == SOCK_SEQPACKET) { /* Connected mode sockets go via the LAPB machine */ if (sk->sk_state != TCP_ESTABLISHED) { @@ -1583,22 +1577,14 @@ static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock, skb_push(skb, 1 + ax25_addr_size(dp)); - SOCK_DEBUG(sk, "Building AX.25 Header (dp=%p).\n", dp); - - if (dp != NULL) - SOCK_DEBUG(sk, "Num digipeaters=%d\n", dp->ndigi); + /* Building AX.25 Header */ /* Build an AX.25 header */ lv = ax25_addr_build(skb->data, &ax25->source_addr, &sax.sax25_call, dp, AX25_COMMAND, AX25_MODULUS); - SOCK_DEBUG(sk, "Built header (%d bytes)\n",lv); - skb_set_transport_header(skb, lv); - SOCK_DEBUG(sk, "base=%p pos=%p\n", - skb->data, skb_transport_header(skb)); - *skb_transport_header(skb) = AX25_UI; /* Datagram frames go straight out of the door as UI */ diff --git a/net/ax25/ax25_iface.c b/net/ax25/ax25_iface.c index 5a0dda8df492..60b545e2822a 100644 --- a/net/ax25/ax25_iface.c +++ b/net/ax25/ax25_iface.c @@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ax25_register_pid); void ax25_protocol_release(unsigned int pid) { - struct ax25_protocol *s, *protocol; + struct ax25_protocol *protocol; write_lock_bh(&protocol_list_lock); protocol = protocol_list; @@ -72,7 +72,6 @@ void ax25_protocol_release(unsigned int pid) while (protocol != NULL && protocol->next != NULL) { if (protocol->next->pid == pid) { - s = protocol->next; protocol->next = protocol->next->next; goto out; } diff --git a/net/batman-adv/aggregation.c b/net/batman-adv/aggregation.c index af45d6b2031f..a8c32030527c 100644 --- a/net/batman-adv/aggregation.c +++ b/net/batman-adv/aggregation.c @@ -23,11 +23,12 @@ #include "aggregation.h" #include "send.h" #include "routing.h" +#include "hard-interface.h" -/* calculate the size of the hna information for a given packet */ -static int hna_len(struct batman_packet *batman_packet) +/* calculate the size of the tt information for a given packet */ +static int tt_len(struct batman_packet *batman_packet) { - return batman_packet->num_hna * ETH_ALEN; + return batman_packet->num_tt * ETH_ALEN; } /* return true if new_packet can be aggregated with forw_packet */ @@ -95,7 +96,6 @@ static bool can_aggregate_with(struct batman_packet *new_batman_packet, return false; } -#define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) /* create a new aggregated packet and add this packet to it */ static void new_aggregated_packet(unsigned char *packet_buff, int packet_len, unsigned long send_time, bool direct_link, @@ -106,12 +106,15 @@ static void new_aggregated_packet(unsigned char *packet_buff, int packet_len, struct forw_packet *forw_packet_aggr; unsigned char *skb_buff; + if (!atomic_inc_not_zero(&if_incoming->refcount)) + return; + /* own packet should always be scheduled */ if (!own_packet) { if (!atomic_dec_not_zero(&bat_priv->batman_queue_left)) { bat_dbg(DBG_BATMAN, bat_priv, "batman packet queue full\n"); - return; + goto out; } } @@ -119,7 +122,7 @@ static void new_aggregated_packet(unsigned char *packet_buff, int packet_len, if (!forw_packet_aggr) { if (!own_packet) atomic_inc(&bat_priv->batman_queue_left); - return; + goto out; } if ((atomic_read(&bat_priv->aggregated_ogms)) && @@ -134,7 +137,7 @@ static void new_aggregated_packet(unsigned char *packet_buff, int packet_len, if (!own_packet) atomic_inc(&bat_priv->batman_queue_left); kfree(forw_packet_aggr); - return; + goto out; } skb_reserve(forw_packet_aggr->skb, sizeof(struct ethhdr)); @@ -165,6 +168,10 @@ static void new_aggregated_packet(unsigned char *packet_buff, int packet_len, queue_delayed_work(bat_event_workqueue, &forw_packet_aggr->delayed_work, send_time - jiffies); + + return; +out: + hardif_free_ref(if_incoming); } /* aggregate a new packet into the existing aggregation */ @@ -251,7 +258,7 @@ void receive_aggr_bat_packet(struct ethhdr *ethhdr, unsigned char *packet_buff, { struct batman_packet *batman_packet; int buff_pos = 0; - unsigned char *hna_buff; + unsigned char *tt_buff; batman_packet = (struct batman_packet *)packet_buff; @@ -260,14 +267,14 @@ void receive_aggr_bat_packet(struct ethhdr *ethhdr, unsigned char *packet_buff, orig_interval. */ batman_packet->seqno = ntohl(batman_packet->seqno); - hna_buff = packet_buff + buff_pos + BAT_PACKET_LEN; + tt_buff = packet_buff + buff_pos + BAT_PACKET_LEN; receive_bat_packet(ethhdr, batman_packet, - hna_buff, hna_len(batman_packet), + tt_buff, tt_len(batman_packet), if_incoming); - buff_pos += BAT_PACKET_LEN + hna_len(batman_packet); + buff_pos += BAT_PACKET_LEN + tt_len(batman_packet); batman_packet = (struct batman_packet *) (packet_buff + buff_pos); } while (aggregated_packet(buff_pos, packet_len, - batman_packet->num_hna)); + batman_packet->num_tt)); } diff --git a/net/batman-adv/aggregation.h b/net/batman-adv/aggregation.h index 062204289d1f..7e6d72fbf540 100644 --- a/net/batman-adv/aggregation.h +++ b/net/batman-adv/aggregation.h @@ -25,9 +25,9 @@ #include "main.h" /* is there another aggregated packet here? */ -static inline int aggregated_packet(int buff_pos, int packet_len, int num_hna) +static inline int aggregated_packet(int buff_pos, int packet_len, int num_tt) { - int next_buff_pos = buff_pos + BAT_PACKET_LEN + (num_hna * ETH_ALEN); + int next_buff_pos = buff_pos + BAT_PACKET_LEN + (num_tt * ETH_ALEN); return (next_buff_pos <= packet_len) && (next_buff_pos <= MAX_AGGREGATION_BYTES); diff --git a/net/batman-adv/bat_debugfs.c b/net/batman-adv/bat_debugfs.c index 0e9d43509935..abaeec5f6247 100644 --- a/net/batman-adv/bat_debugfs.c +++ b/net/batman-adv/bat_debugfs.c @@ -241,13 +241,13 @@ static int softif_neigh_open(struct inode *inode, struct file *file) static int transtable_global_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, hna_global_seq_print_text, net_dev); + return single_open(file, tt_global_seq_print_text, net_dev); } static int transtable_local_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; - return single_open(file, hna_local_seq_print_text, net_dev); + return single_open(file, tt_local_seq_print_text, net_dev); } static int vis_data_open(struct inode *inode, struct file *file) diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c index e449bf6353e0..497a0700cc3c 100644 --- a/net/batman-adv/bat_sysfs.c +++ b/net/batman-adv/bat_sysfs.c @@ -488,22 +488,24 @@ static ssize_t store_mesh_iface(struct kobject *kobj, struct attribute *attr, (strncmp(hard_iface->soft_iface->name, buff, IFNAMSIZ) == 0)) goto out; + if (!rtnl_trylock()) { + ret = -ERESTARTSYS; + goto out; + } + if (status_tmp == IF_NOT_IN_USE) { - rtnl_lock(); hardif_disable_interface(hard_iface); - rtnl_unlock(); - goto out; + goto unlock; } /* if the interface already is in use */ - if (hard_iface->if_status != IF_NOT_IN_USE) { - rtnl_lock(); + if (hard_iface->if_status != IF_NOT_IN_USE) hardif_disable_interface(hard_iface); - rtnl_unlock(); - } ret = hardif_enable_interface(hard_iface, buff); +unlock: + rtnl_unlock(); out: hardif_free_ref(hard_iface); return ret; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 3cc43558cf9c..61605a0f3f39 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -23,80 +23,88 @@ #include "gateway_client.h" #include "gateway_common.h" #include "hard-interface.h" +#include "originator.h" #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/udp.h> #include <linux/if_vlan.h> -static void gw_node_free_rcu(struct rcu_head *rcu) -{ - struct gw_node *gw_node; - - gw_node = container_of(rcu, struct gw_node, rcu); - kfree(gw_node); -} - static void gw_node_free_ref(struct gw_node *gw_node) { if (atomic_dec_and_test(&gw_node->refcount)) - call_rcu(&gw_node->rcu, gw_node_free_rcu); + kfree_rcu(gw_node, rcu); } -void *gw_get_selected(struct bat_priv *bat_priv) +static struct gw_node *gw_get_selected_gw_node(struct bat_priv *bat_priv) { - struct gw_node *curr_gateway_tmp; - struct orig_node *orig_node = NULL; + struct gw_node *gw_node; rcu_read_lock(); - curr_gateway_tmp = rcu_dereference(bat_priv->curr_gw); - if (!curr_gateway_tmp) + gw_node = rcu_dereference(bat_priv->curr_gw); + if (!gw_node) goto out; - orig_node = curr_gateway_tmp->orig_node; - if (!orig_node) - goto out; - - if (!atomic_inc_not_zero(&orig_node->refcount)) - orig_node = NULL; + if (!atomic_inc_not_zero(&gw_node->refcount)) + gw_node = NULL; out: rcu_read_unlock(); - return orig_node; + return gw_node; } -void gw_deselect(struct bat_priv *bat_priv) +struct orig_node *gw_get_selected_orig(struct bat_priv *bat_priv) { struct gw_node *gw_node; + struct orig_node *orig_node = NULL; - spin_lock_bh(&bat_priv->gw_list_lock); - gw_node = rcu_dereference(bat_priv->curr_gw); - rcu_assign_pointer(bat_priv->curr_gw, NULL); - spin_unlock_bh(&bat_priv->gw_list_lock); + gw_node = gw_get_selected_gw_node(bat_priv); + if (!gw_node) + goto out; + + rcu_read_lock(); + orig_node = gw_node->orig_node; + if (!orig_node) + goto unlock; + if (!atomic_inc_not_zero(&orig_node->refcount)) + orig_node = NULL; + +unlock: + rcu_read_unlock(); +out: if (gw_node) gw_node_free_ref(gw_node); + return orig_node; } static void gw_select(struct bat_priv *bat_priv, struct gw_node *new_gw_node) { struct gw_node *curr_gw_node; + spin_lock_bh(&bat_priv->gw_list_lock); + if (new_gw_node && !atomic_inc_not_zero(&new_gw_node->refcount)) new_gw_node = NULL; - spin_lock_bh(&bat_priv->gw_list_lock); - curr_gw_node = rcu_dereference(bat_priv->curr_gw); + curr_gw_node = bat_priv->curr_gw; rcu_assign_pointer(bat_priv->curr_gw, new_gw_node); - spin_unlock_bh(&bat_priv->gw_list_lock); if (curr_gw_node) gw_node_free_ref(curr_gw_node); + + spin_unlock_bh(&bat_priv->gw_list_lock); +} + +void gw_deselect(struct bat_priv *bat_priv) +{ + gw_select(bat_priv, NULL); } void gw_election(struct bat_priv *bat_priv) { struct hlist_node *node; - struct gw_node *gw_node, *curr_gw, *curr_gw_tmp = NULL; + struct gw_node *gw_node, *curr_gw = NULL, *curr_gw_tmp = NULL; + struct neigh_node *router; uint8_t max_tq = 0; uint32_t max_gw_factor = 0, tmp_gw_factor = 0; int down, up; @@ -110,32 +118,25 @@ void gw_election(struct bat_priv *bat_priv) if (atomic_read(&bat_priv->gw_mode) != GW_MODE_CLIENT) return; - rcu_read_lock(); - curr_gw = rcu_dereference(bat_priv->curr_gw); - if (curr_gw) { - rcu_read_unlock(); - return; - } + curr_gw = gw_get_selected_gw_node(bat_priv); + if (curr_gw) + goto out; + rcu_read_lock(); if (hlist_empty(&bat_priv->gw_list)) { - - if (curr_gw) { - rcu_read_unlock(); - bat_dbg(DBG_BATMAN, bat_priv, - "Removing selected gateway - " - "no gateway in range\n"); - gw_deselect(bat_priv); - } else - rcu_read_unlock(); - - return; + bat_dbg(DBG_BATMAN, bat_priv, + "Removing selected gateway - " + "no gateway in range\n"); + gw_deselect(bat_priv); + goto unlock; } hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw_list, list) { - if (!gw_node->orig_node->router) + if (gw_node->deleted) continue; - if (gw_node->deleted) + router = orig_node_get_router(gw_node->orig_node); + if (!router) continue; switch (atomic_read(&bat_priv->gw_sel_class)) { @@ -143,15 +144,14 @@ void gw_election(struct bat_priv *bat_priv) gw_bandwidth_to_kbit(gw_node->orig_node->gw_flags, &down, &up); - tmp_gw_factor = (gw_node->orig_node->router->tq_avg * - gw_node->orig_node->router->tq_avg * + tmp_gw_factor = (router->tq_avg * router->tq_avg * down * 100 * 100) / (TQ_LOCAL_WINDOW_SIZE * TQ_LOCAL_WINDOW_SIZE * 64); if ((tmp_gw_factor > max_gw_factor) || ((tmp_gw_factor == max_gw_factor) && - (gw_node->orig_node->router->tq_avg > max_tq))) + (router->tq_avg > max_tq))) curr_gw_tmp = gw_node; break; @@ -163,19 +163,25 @@ void gw_election(struct bat_priv *bat_priv) * soon as a better gateway appears which has * $routing_class more tq points) **/ - if (gw_node->orig_node->router->tq_avg > max_tq) + if (router->tq_avg > max_tq) curr_gw_tmp = gw_node; break; } - if (gw_node->orig_node->router->tq_avg > max_tq) - max_tq = gw_node->orig_node->router->tq_avg; + if (router->tq_avg > max_tq) + max_tq = router->tq_avg; if (tmp_gw_factor > max_gw_factor) max_gw_factor = tmp_gw_factor; + + neigh_node_free_ref(router); } if (curr_gw != curr_gw_tmp) { + router = orig_node_get_router(curr_gw_tmp->orig_node); + if (!router) + goto unlock; + if ((curr_gw) && (!curr_gw_tmp)) bat_dbg(DBG_BATMAN, bat_priv, "Removing selected gateway - " @@ -186,48 +192,50 @@ void gw_election(struct bat_priv *bat_priv) "(gw_flags: %i, tq: %i)\n", curr_gw_tmp->orig_node->orig, curr_gw_tmp->orig_node->gw_flags, - curr_gw_tmp->orig_node->router->tq_avg); + router->tq_avg); else bat_dbg(DBG_BATMAN, bat_priv, "Changing route to gateway %pM " "(gw_flags: %i, tq: %i)\n", curr_gw_tmp->orig_node->orig, curr_gw_tmp->orig_node->gw_flags, - curr_gw_tmp->orig_node->router->tq_avg); + router->tq_avg); + neigh_node_free_ref(router); gw_select(bat_priv, curr_gw_tmp); } +unlock: rcu_read_unlock(); +out: + if (curr_gw) + gw_node_free_ref(curr_gw); } void gw_check_election(struct bat_priv *bat_priv, struct orig_node *orig_node) { - struct gw_node *curr_gateway_tmp; + struct orig_node *curr_gw_orig; + struct neigh_node *router_gw = NULL, *router_orig = NULL; uint8_t gw_tq_avg, orig_tq_avg; - rcu_read_lock(); - curr_gateway_tmp = rcu_dereference(bat_priv->curr_gw); - if (!curr_gateway_tmp) - goto out_rcu; - - if (!curr_gateway_tmp->orig_node) - goto deselect_rcu; + curr_gw_orig = gw_get_selected_orig(bat_priv); + if (!curr_gw_orig) + goto deselect; - if (!curr_gateway_tmp->orig_node->router) - goto deselect_rcu; + router_gw = orig_node_get_router(curr_gw_orig); + if (!router_gw) + goto deselect; /* this node already is the gateway */ - if (curr_gateway_tmp->orig_node == orig_node) - goto out_rcu; - - if (!orig_node->router) - goto out_rcu; + if (curr_gw_orig == orig_node) + goto out; - gw_tq_avg = curr_gateway_tmp->orig_node->router->tq_avg; - rcu_read_unlock(); + router_orig = orig_node_get_router(orig_node); + if (!router_orig) + goto out; - orig_tq_avg = orig_node->router->tq_avg; + gw_tq_avg = router_gw->tq_avg; + orig_tq_avg = router_orig->tq_avg; /* the TQ value has to be better */ if (orig_tq_avg < gw_tq_avg) @@ -245,16 +253,17 @@ void gw_check_election(struct bat_priv *bat_priv, struct orig_node *orig_node) "Restarting gateway selection: better gateway found (tq curr: " "%i, tq new: %i)\n", gw_tq_avg, orig_tq_avg); - goto deselect; -out_rcu: - rcu_read_unlock(); - goto out; -deselect_rcu: - rcu_read_unlock(); deselect: gw_deselect(bat_priv); out: + if (curr_gw_orig) + orig_node_free_ref(curr_gw_orig); + if (router_gw) + neigh_node_free_ref(router_gw); + if (router_orig) + neigh_node_free_ref(router_orig); + return; } @@ -291,7 +300,15 @@ void gw_node_update(struct bat_priv *bat_priv, struct orig_node *orig_node, uint8_t new_gwflags) { struct hlist_node *node; - struct gw_node *gw_node; + struct gw_node *gw_node, *curr_gw; + + /** + * Note: We don't need a NULL check here, since curr_gw never gets + * dereferenced. If curr_gw is NULL we also should not exit as we may + * have this gateway in our list (duplication check!) even though we + * have no currently selected gateway. + */ + curr_gw = gw_get_selected_gw_node(bat_priv); rcu_read_lock(); hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw_list, list) { @@ -312,22 +329,26 @@ void gw_node_update(struct bat_priv *bat_priv, "Gateway %pM removed from gateway list\n", orig_node->orig); - if (gw_node == rcu_dereference(bat_priv->curr_gw)) { - rcu_read_unlock(); - gw_deselect(bat_priv); - return; - } + if (gw_node == curr_gw) + goto deselect; } - rcu_read_unlock(); - return; + goto unlock; } - rcu_read_unlock(); if (new_gwflags == 0) - return; + goto unlock; gw_node_add(bat_priv, orig_node, new_gwflags); + goto unlock; + +deselect: + gw_deselect(bat_priv); +unlock: + rcu_read_unlock(); + + if (curr_gw) + gw_node_free_ref(curr_gw); } void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node) @@ -337,9 +358,12 @@ void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node) void gw_node_purge(struct bat_priv *bat_priv) { - struct gw_node *gw_node; + struct gw_node *gw_node, *curr_gw; struct hlist_node *node, *node_tmp; unsigned long timeout = 2 * PURGE_TIMEOUT * HZ; + char do_deselect = 0; + + curr_gw = gw_get_selected_gw_node(bat_priv); spin_lock_bh(&bat_priv->gw_list_lock); @@ -350,41 +374,56 @@ void gw_node_purge(struct bat_priv *bat_priv) atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE) continue; - if (rcu_dereference(bat_priv->curr_gw) == gw_node) - gw_deselect(bat_priv); + if (curr_gw == gw_node) + do_deselect = 1; hlist_del_rcu(&gw_node->list); gw_node_free_ref(gw_node); } - spin_unlock_bh(&bat_priv->gw_list_lock); + + /* gw_deselect() needs to acquire the gw_list_lock */ + if (do_deselect) + gw_deselect(bat_priv); + + if (curr_gw) + gw_node_free_ref(curr_gw); } +/** + * fails if orig_node has no router + */ static int _write_buffer_text(struct bat_priv *bat_priv, struct seq_file *seq, struct gw_node *gw_node) { struct gw_node *curr_gw; - int down, up, ret; + struct neigh_node *router; + int down, up, ret = -1; gw_bandwidth_to_kbit(gw_node->orig_node->gw_flags, &down, &up); - rcu_read_lock(); - curr_gw = rcu_dereference(bat_priv->curr_gw); + router = orig_node_get_router(gw_node->orig_node); + if (!router) + goto out; - ret = seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %3i - %i%s/%i%s\n", - (curr_gw == gw_node ? "=>" : " "), - gw_node->orig_node->orig, - gw_node->orig_node->router->tq_avg, - gw_node->orig_node->router->addr, - gw_node->orig_node->router->if_incoming->net_dev->name, - gw_node->orig_node->gw_flags, - (down > 2048 ? down / 1024 : down), - (down > 2048 ? "MBit" : "KBit"), - (up > 2048 ? up / 1024 : up), - (up > 2048 ? "MBit" : "KBit")); + curr_gw = gw_get_selected_gw_node(bat_priv); - rcu_read_unlock(); + ret = seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %3i - %i%s/%i%s\n", + (curr_gw == gw_node ? "=>" : " "), + gw_node->orig_node->orig, + router->tq_avg, router->addr, + router->if_incoming->net_dev->name, + gw_node->orig_node->gw_flags, + (down > 2048 ? down / 1024 : down), + (down > 2048 ? "MBit" : "KBit"), + (up > 2048 ? up / 1024 : up), + (up > 2048 ? "MBit" : "KBit")); + + neigh_node_free_ref(router); + if (curr_gw) + gw_node_free_ref(curr_gw); +out: return ret; } @@ -392,40 +431,42 @@ int gw_client_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; struct bat_priv *bat_priv = netdev_priv(net_dev); + struct hard_iface *primary_if; struct gw_node *gw_node; struct hlist_node *node; - int gw_count = 0; - - if (!bat_priv->primary_if) { + int gw_count = 0, ret = 0; - return seq_printf(seq, "BATMAN mesh %s disabled - please " - "specify interfaces to enable it\n", - net_dev->name); + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) { + ret = seq_printf(seq, "BATMAN mesh %s disabled - please " + "specify interfaces to enable it\n", + net_dev->name); + goto out; } - if (bat_priv->primary_if->if_status != IF_ACTIVE) { - - return seq_printf(seq, "BATMAN mesh %s disabled - " - "primary interface not active\n", - net_dev->name); + if (primary_if->if_status != IF_ACTIVE) { + ret = seq_printf(seq, "BATMAN mesh %s disabled - " + "primary interface not active\n", + net_dev->name); + goto out; } seq_printf(seq, " %-12s (%s/%i) %17s [%10s]: gw_class ... " "[B.A.T.M.A.N. adv %s%s, MainIF/MAC: %s/%pM (%s)]\n", "Gateway", "#", TQ_MAX_VALUE, "Nexthop", "outgoingIF", SOURCE_VERSION, REVISION_VERSION_STR, - bat_priv->primary_if->net_dev->name, - bat_priv->primary_if->net_dev->dev_addr, net_dev->name); + primary_if->net_dev->name, + primary_if->net_dev->dev_addr, net_dev->name); rcu_read_lock(); hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw_list, list) { if (gw_node->deleted) continue; - if (!gw_node->orig_node->router) + /* fails if orig_node has no router */ + if (_write_buffer_text(bat_priv, seq, gw_node) < 0) continue; - _write_buffer_text(bat_priv, seq, gw_node); gw_count++; } rcu_read_unlock(); @@ -433,7 +474,10 @@ int gw_client_seq_print_text(struct seq_file *seq, void *offset) if (gw_count == 0) seq_printf(seq, "No gateways in range ...\n"); - return 0; +out: + if (primary_if) + hardif_free_ref(primary_if); + return ret; } int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb) @@ -442,6 +486,7 @@ int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb) struct iphdr *iphdr; struct ipv6hdr *ipv6hdr; struct udphdr *udphdr; + struct gw_node *curr_gw; unsigned int header_len = 0; if (atomic_read(&bat_priv->gw_mode) == GW_MODE_OFF) @@ -506,12 +551,11 @@ int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb) if (atomic_read(&bat_priv->gw_mode) == GW_MODE_SERVER) return -1; - rcu_read_lock(); - if (!rcu_dereference(bat_priv->curr_gw)) { - rcu_read_unlock(); + curr_gw = gw_get_selected_gw_node(bat_priv); + if (!curr_gw) return 0; - } - rcu_read_unlock(); + if (curr_gw) + gw_node_free_ref(curr_gw); return 1; } diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 2aa439124ee3..1ce8c6066da1 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -24,7 +24,7 @@ void gw_deselect(struct bat_priv *bat_priv); void gw_election(struct bat_priv *bat_priv); -void *gw_get_selected(struct bat_priv *bat_priv); +struct orig_node *gw_get_selected_orig(struct bat_priv *bat_priv); void gw_check_election(struct bat_priv *bat_priv, struct orig_node *orig_node); void gw_node_update(struct bat_priv *bat_priv, struct orig_node *orig_node, uint8_t new_gwflags); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index b3058e46ee6b..dfbfccc9fe40 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -31,9 +31,6 @@ #include <linux/if_arp.h> -/* protect update critical side of hardif_list - but not the content */ -static DEFINE_SPINLOCK(hardif_list_lock); - static int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, @@ -110,47 +107,57 @@ out: return hard_iface; } -static void update_primary_addr(struct bat_priv *bat_priv) +static void primary_if_update_addr(struct bat_priv *bat_priv) { struct vis_packet *vis_packet; + struct hard_iface *primary_if; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; vis_packet = (struct vis_packet *) bat_priv->my_vis_info->skb_packet->data; - memcpy(vis_packet->vis_orig, - bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN); + memcpy(vis_packet->vis_orig, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(vis_packet->sender_orig, - bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN); + primary_if->net_dev->dev_addr, ETH_ALEN); + +out: + if (primary_if) + hardif_free_ref(primary_if); } -static void set_primary_if(struct bat_priv *bat_priv, - struct hard_iface *hard_iface) +static void primary_if_select(struct bat_priv *bat_priv, + struct hard_iface *new_hard_iface) { + struct hard_iface *curr_hard_iface; struct batman_packet *batman_packet; - struct hard_iface *old_if; - if (hard_iface && !atomic_inc_not_zero(&hard_iface->refcount)) - hard_iface = NULL; + ASSERT_RTNL(); + + if (new_hard_iface && !atomic_inc_not_zero(&new_hard_iface->refcount)) + new_hard_iface = NULL; - old_if = bat_priv->primary_if; - bat_priv->primary_if = hard_iface; + curr_hard_iface = bat_priv->primary_if; + rcu_assign_pointer(bat_priv->primary_if, new_hard_iface); - if (old_if) - hardif_free_ref(old_if); + if (curr_hard_iface) + hardif_free_ref(curr_hard_iface); - if (!bat_priv->primary_if) + if (!new_hard_iface) return; - batman_packet = (struct batman_packet *)(hard_iface->packet_buff); + batman_packet = (struct batman_packet *)(new_hard_iface->packet_buff); batman_packet->flags = PRIMARIES_FIRST_HOP; batman_packet->ttl = TTL; - update_primary_addr(bat_priv); + primary_if_update_addr(bat_priv); /*** - * hacky trick to make sure that we send the HNA information via + * hacky trick to make sure that we send the TT information via * our new primary interface */ - atomic_set(&bat_priv->hna_local_changed, 1); + atomic_set(&bat_priv->tt_local_changed, 1); } static bool hardif_is_iface_up(struct hard_iface *hard_iface) @@ -236,9 +243,10 @@ void update_min_mtu(struct net_device *soft_iface) static void hardif_activate_interface(struct hard_iface *hard_iface) { struct bat_priv *bat_priv; + struct hard_iface *primary_if = NULL; if (hard_iface->if_status != IF_INACTIVE) - return; + goto out; bat_priv = netdev_priv(hard_iface->soft_iface); @@ -249,14 +257,18 @@ static void hardif_activate_interface(struct hard_iface *hard_iface) * the first active interface becomes our primary interface or * the next active interface after the old primay interface was removed */ - if (!bat_priv->primary_if) - set_primary_if(bat_priv, hard_iface); + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + primary_if_select(bat_priv, hard_iface); bat_info(hard_iface->soft_iface, "Interface activated: %s\n", hard_iface->net_dev->name); update_min_mtu(hard_iface->soft_iface); - return; + +out: + if (primary_if) + hardif_free_ref(primary_if); } static void hardif_deactivate_interface(struct hard_iface *hard_iface) @@ -327,7 +339,7 @@ int hardif_enable_interface(struct hard_iface *hard_iface, char *iface_name) batman_packet->flags = 0; batman_packet->ttl = 2; batman_packet->tq = TQ_MAX_VALUE; - batman_packet->num_hna = 0; + batman_packet->num_tt = 0; hard_iface->if_num = bat_priv->num_ifaces; bat_priv->num_ifaces++; @@ -386,12 +398,13 @@ err: void hardif_disable_interface(struct hard_iface *hard_iface) { struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct hard_iface *primary_if = NULL; if (hard_iface->if_status == IF_ACTIVE) hardif_deactivate_interface(hard_iface); if (hard_iface->if_status != IF_INACTIVE) - return; + goto out; bat_info(hard_iface->soft_iface, "Removing interface: %s\n", hard_iface->net_dev->name); @@ -400,11 +413,12 @@ void hardif_disable_interface(struct hard_iface *hard_iface) bat_priv->num_ifaces--; orig_hash_del_if(hard_iface, bat_priv->num_ifaces); - if (hard_iface == bat_priv->primary_if) { + primary_if = primary_if_get_selected(bat_priv); + if (hard_iface == primary_if) { struct hard_iface *new_if; new_if = hardif_get_active(hard_iface->soft_iface); - set_primary_if(bat_priv, new_if); + primary_if_select(bat_priv, new_if); if (new_if) hardif_free_ref(new_if); @@ -425,6 +439,10 @@ void hardif_disable_interface(struct hard_iface *hard_iface) hard_iface->soft_iface = NULL; hardif_free_ref(hard_iface); + +out: + if (primary_if) + hardif_free_ref(primary_if); } static struct hard_iface *hardif_add_interface(struct net_device *net_dev) @@ -432,6 +450,8 @@ static struct hard_iface *hardif_add_interface(struct net_device *net_dev) struct hard_iface *hard_iface; int ret; + ASSERT_RTNL(); + ret = is_valid_iface(net_dev); if (ret != 1) goto out; @@ -458,10 +478,7 @@ static struct hard_iface *hardif_add_interface(struct net_device *net_dev) atomic_set(&hard_iface->refcount, 2); check_known_mac_addr(hard_iface->net_dev); - - spin_lock(&hardif_list_lock); list_add_tail_rcu(&hard_iface->list, &hardif_list); - spin_unlock(&hardif_list_lock); return hard_iface; @@ -475,6 +492,8 @@ out: static void hardif_remove_interface(struct hard_iface *hard_iface) { + ASSERT_RTNL(); + /* first deactivate interface */ if (hard_iface->if_status != IF_NOT_IN_USE) hardif_disable_interface(hard_iface); @@ -490,20 +509,11 @@ static void hardif_remove_interface(struct hard_iface *hard_iface) void hardif_remove_interfaces(void) { struct hard_iface *hard_iface, *hard_iface_tmp; - struct list_head if_queue; - - INIT_LIST_HEAD(&if_queue); - spin_lock(&hardif_list_lock); + rtnl_lock(); list_for_each_entry_safe(hard_iface, hard_iface_tmp, &hardif_list, list) { list_del_rcu(&hard_iface->list); - list_add_tail(&hard_iface->list, &if_queue); - } - spin_unlock(&hardif_list_lock); - - rtnl_lock(); - list_for_each_entry_safe(hard_iface, hard_iface_tmp, &if_queue, list) { hardif_remove_interface(hard_iface); } rtnl_unlock(); @@ -514,6 +524,7 @@ static int hard_if_event(struct notifier_block *this, { struct net_device *net_dev = (struct net_device *)ptr; struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); + struct hard_iface *primary_if = NULL; struct bat_priv *bat_priv; if (!hard_iface && event == NETDEV_REGISTER) @@ -531,9 +542,7 @@ static int hard_if_event(struct notifier_block *this, hardif_deactivate_interface(hard_iface); break; case NETDEV_UNREGISTER: - spin_lock(&hardif_list_lock); list_del_rcu(&hard_iface->list); - spin_unlock(&hardif_list_lock); hardif_remove_interface(hard_iface); break; @@ -549,8 +558,12 @@ static int hard_if_event(struct notifier_block *this, update_mac_addresses(hard_iface); bat_priv = netdev_priv(hard_iface->soft_iface); - if (hard_iface == bat_priv->primary_if) - update_primary_addr(bat_priv); + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto hardif_put; + + if (hard_iface == primary_if) + primary_if_update_addr(bat_priv); break; default: break; @@ -559,6 +572,8 @@ static int hard_if_event(struct notifier_block *this, hardif_put: hardif_free_ref(hard_iface); out: + if (primary_if) + hardif_free_ref(primary_if); return NOTIFY_DONE; } diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index a9ddf36e51c8..64265991460b 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -45,4 +45,22 @@ static inline void hardif_free_ref(struct hard_iface *hard_iface) call_rcu(&hard_iface->rcu, hardif_free_rcu); } +static inline struct hard_iface *primary_if_get_selected( + struct bat_priv *bat_priv) +{ + struct hard_iface *hard_iface; + + rcu_read_lock(); + hard_iface = rcu_dereference(bat_priv->primary_if); + if (!hard_iface) + goto out; + + if (!atomic_inc_not_zero(&hard_iface->refcount)) + hard_iface = NULL; + +out: + rcu_read_unlock(); + return hard_iface; +} + #endif /* _NET_BATMAN_ADV_HARD_INTERFACE_H_ */ diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 34ce56c358e5..fa22ba2bb832 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -153,6 +153,7 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, { struct socket_client *socket_client = file->private_data; struct bat_priv *bat_priv = socket_client->bat_priv; + struct hard_iface *primary_if = NULL; struct sk_buff *skb; struct icmp_packet_rr *icmp_packet; @@ -167,15 +168,21 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, return -EINVAL; } - if (!bat_priv->primary_if) - return -EFAULT; + primary_if = primary_if_get_selected(bat_priv); + + if (!primary_if) { + len = -EFAULT; + goto out; + } if (len >= sizeof(struct icmp_packet_rr)) packet_len = sizeof(struct icmp_packet_rr); skb = dev_alloc_skb(packet_len + sizeof(struct ethhdr)); - if (!skb) - return -ENOMEM; + if (!skb) { + len = -ENOMEM; + goto out; + } skb_reserve(skb, sizeof(struct ethhdr)); icmp_packet = (struct icmp_packet_rr *)skb_put(skb, packet_len); @@ -218,23 +225,13 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE) goto dst_unreach; - rcu_read_lock(); orig_node = orig_hash_find(bat_priv, icmp_packet->dst); - if (!orig_node) - goto unlock; - - neigh_node = orig_node->router; + goto dst_unreach; + neigh_node = orig_node_get_router(orig_node); if (!neigh_node) - goto unlock; - - if (!atomic_inc_not_zero(&neigh_node->refcount)) { - neigh_node = NULL; - goto unlock; - } - - rcu_read_unlock(); + goto dst_unreach; if (!neigh_node->if_incoming) goto dst_unreach; @@ -243,7 +240,7 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, goto dst_unreach; memcpy(icmp_packet->orig, - bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN); + primary_if->net_dev->dev_addr, ETH_ALEN); if (packet_len == sizeof(struct icmp_packet_rr)) memcpy(icmp_packet->rr, @@ -252,14 +249,14 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); goto out; -unlock: - rcu_read_unlock(); dst_unreach: icmp_packet->msg_type = DESTINATION_UNREACHABLE; bat_socket_add_packet(socket_client, icmp_packet, packet_len); free_skb: kfree_skb(skb); out: + if (primary_if) + hardif_free_ref(primary_if); if (neigh_node) neigh_node_free_ref(neigh_node); if (orig_node) diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 709b33bbdf43..0a7cee0076f4 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -33,6 +33,9 @@ #include "vis.h" #include "hash.h" + +/* List manipulations on hardif_list have to be rtnl_lock()'ed, + * list traversals just rcu-locked */ struct list_head hardif_list; unsigned char broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; @@ -81,28 +84,29 @@ int mesh_init(struct net_device *soft_iface) spin_lock_init(&bat_priv->forw_bat_list_lock); spin_lock_init(&bat_priv->forw_bcast_list_lock); - spin_lock_init(&bat_priv->hna_lhash_lock); - spin_lock_init(&bat_priv->hna_ghash_lock); + spin_lock_init(&bat_priv->tt_lhash_lock); + spin_lock_init(&bat_priv->tt_ghash_lock); spin_lock_init(&bat_priv->gw_list_lock); spin_lock_init(&bat_priv->vis_hash_lock); spin_lock_init(&bat_priv->vis_list_lock); spin_lock_init(&bat_priv->softif_neigh_lock); + spin_lock_init(&bat_priv->softif_neigh_vid_lock); INIT_HLIST_HEAD(&bat_priv->forw_bat_list); INIT_HLIST_HEAD(&bat_priv->forw_bcast_list); INIT_HLIST_HEAD(&bat_priv->gw_list); - INIT_HLIST_HEAD(&bat_priv->softif_neigh_list); + INIT_HLIST_HEAD(&bat_priv->softif_neigh_vids); if (originator_init(bat_priv) < 1) goto err; - if (hna_local_init(bat_priv) < 1) + if (tt_local_init(bat_priv) < 1) goto err; - if (hna_global_init(bat_priv) < 1) + if (tt_global_init(bat_priv) < 1) goto err; - hna_local_add(soft_iface, soft_iface->dev_addr); + tt_local_add(soft_iface, soft_iface->dev_addr); if (vis_init(bat_priv) < 1) goto err; @@ -133,8 +137,8 @@ void mesh_free(struct net_device *soft_iface) gw_node_purge(bat_priv); originator_free(bat_priv); - hna_local_free(bat_priv); - hna_global_free(bat_priv); + tt_local_free(bat_priv); + tt_global_free(bat_priv); softif_neigh_purge(bat_priv); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index dc248697de71..148b49e02642 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -34,16 +34,18 @@ #define TQ_MAX_VALUE 255 #define JITTER 20 -#define TTL 50 /* Time To Live of broadcast messages */ -#define PURGE_TIMEOUT 200 /* purge originators after time in seconds if no - * valid packet comes in -> TODO: check - * influence on TQ_LOCAL_WINDOW_SIZE */ -#define LOCAL_HNA_TIMEOUT 3600 /* in seconds */ + /* Time To Live of broadcast messages */ +#define TTL 50 -#define TQ_LOCAL_WINDOW_SIZE 64 /* sliding packet range of received originator - * messages in squence numbers (should be a - * multiple of our word size) */ +/* purge originators after time in seconds if no valid packet comes in + * -> TODO: check influence on TQ_LOCAL_WINDOW_SIZE */ +#define PURGE_TIMEOUT 200 +#define TT_LOCAL_TIMEOUT 3600 /* in seconds */ + +/* sliding packet range of received originator messages in squence numbers + * (should be a multiple of our word size) */ +#define TQ_LOCAL_WINDOW_SIZE 64 #define TQ_GLOBAL_WINDOW_SIZE 5 #define TQ_LOCAL_BIDRECT_SEND_MINIMUM 1 #define TQ_LOCAL_BIDRECT_RECV_MINIMUM 1 @@ -55,21 +57,20 @@ #define VIS_INTERVAL 5000 /* 5 seconds */ -/* how much worse secondary interfaces may be to - * to be considered as bonding candidates */ - +/* how much worse secondary interfaces may be to be considered as bonding + * candidates */ #define BONDING_TQ_THRESHOLD 50 -#define MAX_AGGREGATION_BYTES 512 /* should not be bigger than 512 bytes or - * change the size of - * forw_packet->direct_link_flags */ +/* should not be bigger than 512 bytes or change the size of + * forw_packet->direct_link_flags */ +#define MAX_AGGREGATION_BYTES 512 #define MAX_AGGREGATION_MS 100 #define SOFTIF_NEIGH_TIMEOUT 180000 /* 3 minutes */ +/* don't reset again within 30 seconds */ #define RESET_PROTECTION_MS 30000 #define EXPECTED_SEQNO_RANGE 65536 -/* don't reset again within 30 seconds */ #define MESH_INACTIVE 0 #define MESH_ACTIVE 1 @@ -84,12 +85,13 @@ #ifdef pr_fmt #undef pr_fmt #endif -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* Append 'batman-adv: ' before - * kernel messages */ +/* Append 'batman-adv: ' before kernel messages */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#define DBG_BATMAN 1 /* all messages related to routing / flooding / - * broadcasting / etc */ -#define DBG_ROUTES 2 /* route or hna added / changed / deleted */ +/* all messages related to routing / flooding / broadcasting / etc */ +#define DBG_BATMAN 1 +/* route or tt entry added / changed / deleted */ +#define DBG_ROUTES 2 #define DBG_ALL 3 @@ -175,4 +177,6 @@ static inline int compare_eth(void *data1, void *data2) return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } +#define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) + #endif /* _NET_BATMAN_ADV_MAIN_H_ */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 0b9133022d2d..40a30bbcd147 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -19,8 +19,6 @@ * */ -/* increase the reference counter for this originator */ - #include "main.h" #include "originator.h" #include "hash.h" @@ -56,18 +54,25 @@ err: return 0; } -static void neigh_node_free_rcu(struct rcu_head *rcu) +void neigh_node_free_ref(struct neigh_node *neigh_node) { - struct neigh_node *neigh_node; - - neigh_node = container_of(rcu, struct neigh_node, rcu); - kfree(neigh_node); + if (atomic_dec_and_test(&neigh_node->refcount)) + kfree_rcu(neigh_node, rcu); } -void neigh_node_free_ref(struct neigh_node *neigh_node) +/* increases the refcounter of a found router */ +struct neigh_node *orig_node_get_router(struct orig_node *orig_node) { - if (atomic_dec_and_test(&neigh_node->refcount)) - call_rcu(&neigh_node->rcu, neigh_node_free_rcu); + struct neigh_node *router; + + rcu_read_lock(); + router = rcu_dereference(orig_node->router); + + if (router && !atomic_inc_not_zero(&router->refcount)) + router = NULL; + + rcu_read_unlock(); + return router; } struct neigh_node *create_neighbor(struct orig_node *orig_node, @@ -87,6 +92,7 @@ struct neigh_node *create_neighbor(struct orig_node *orig_node, INIT_HLIST_NODE(&neigh_node->list); INIT_LIST_HEAD(&neigh_node->bonding_list); + spin_lock_init(&neigh_node->tq_lock); memcpy(neigh_node->addr, neigh, ETH_ALEN); neigh_node->orig_node = orig_neigh_node; @@ -128,7 +134,7 @@ static void orig_node_free_rcu(struct rcu_head *rcu) spin_unlock_bh(&orig_node->neigh_list_lock); frag_list_free(&orig_node->frag_list); - hna_global_del_orig(orig_node->bat_priv, orig_node, + tt_global_del_orig(orig_node->bat_priv, orig_node, "originator timed out"); kfree(orig_node->bcast_own); @@ -206,7 +212,7 @@ struct orig_node *get_orig_node(struct bat_priv *bat_priv, uint8_t *addr) orig_node->bat_priv = bat_priv; memcpy(orig_node->orig, addr, ETH_ALEN); orig_node->router = NULL; - orig_node->hna_buff = NULL; + orig_node->tt_buff = NULL; orig_node->bcast_seqno_reset = jiffies - 1 - msecs_to_jiffies(RESET_PROTECTION_MS); orig_node->batman_seqno_reset = jiffies - 1 @@ -317,8 +323,8 @@ static bool purge_orig_node(struct bat_priv *bat_priv, &best_neigh_node)) { update_routes(bat_priv, orig_node, best_neigh_node, - orig_node->hna_buff, - orig_node->hna_buff_len); + orig_node->tt_buff, + orig_node->tt_buff_len); } } @@ -389,29 +395,34 @@ int orig_seq_print_text(struct seq_file *seq, void *offset) struct hashtable_t *hash = bat_priv->orig_hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; + struct hard_iface *primary_if; struct orig_node *orig_node; - struct neigh_node *neigh_node; + struct neigh_node *neigh_node, *neigh_node_tmp; int batman_count = 0; int last_seen_secs; int last_seen_msecs; - int i; + int i, ret = 0; + + primary_if = primary_if_get_selected(bat_priv); - if ((!bat_priv->primary_if) || - (bat_priv->primary_if->if_status != IF_ACTIVE)) { - if (!bat_priv->primary_if) - return seq_printf(seq, "BATMAN mesh %s disabled - " - "please specify interfaces to enable it\n", - net_dev->name); + if (!primary_if) { + ret = seq_printf(seq, "BATMAN mesh %s disabled - " + "please specify interfaces to enable it\n", + net_dev->name); + goto out; + } - return seq_printf(seq, "BATMAN mesh %s " - "disabled - primary interface not active\n", - net_dev->name); + if (primary_if->if_status != IF_ACTIVE) { + ret = seq_printf(seq, "BATMAN mesh %s " + "disabled - primary interface not active\n", + net_dev->name); + goto out; } seq_printf(seq, "[B.A.T.M.A.N. adv %s%s, MainIF/MAC: %s/%pM (%s)]\n", SOURCE_VERSION, REVISION_VERSION_STR, - bat_priv->primary_if->net_dev->name, - bat_priv->primary_if->net_dev->dev_addr, net_dev->name); + primary_if->net_dev->name, + primary_if->net_dev->dev_addr, net_dev->name); seq_printf(seq, " %-15s %s (%s/%i) %17s [%10s]: %20s ...\n", "Originator", "last-seen", "#", TQ_MAX_VALUE, "Nexthop", "outgoingIF", "Potential nexthops"); @@ -421,40 +432,47 @@ int orig_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { - if (!orig_node->router) + neigh_node = orig_node_get_router(orig_node); + if (!neigh_node) continue; - if (orig_node->router->tq_avg == 0) - continue; + if (neigh_node->tq_avg == 0) + goto next; last_seen_secs = jiffies_to_msecs(jiffies - orig_node->last_valid) / 1000; last_seen_msecs = jiffies_to_msecs(jiffies - orig_node->last_valid) % 1000; - neigh_node = orig_node->router; seq_printf(seq, "%pM %4i.%03is (%3i) %pM [%10s]:", orig_node->orig, last_seen_secs, last_seen_msecs, neigh_node->tq_avg, neigh_node->addr, neigh_node->if_incoming->net_dev->name); - hlist_for_each_entry_rcu(neigh_node, node_tmp, + hlist_for_each_entry_rcu(neigh_node_tmp, node_tmp, &orig_node->neigh_list, list) { - seq_printf(seq, " %pM (%3i)", neigh_node->addr, - neigh_node->tq_avg); + seq_printf(seq, " %pM (%3i)", + neigh_node_tmp->addr, + neigh_node_tmp->tq_avg); } seq_printf(seq, "\n"); batman_count++; + +next: + neigh_node_free_ref(neigh_node); } rcu_read_unlock(); } - if ((batman_count == 0)) + if (batman_count == 0) seq_printf(seq, "No batman nodes in range ...\n"); - return 0; +out: + if (primary_if) + hardif_free_ref(primary_if); + return ret; } static int orig_node_add_if(struct orig_node *orig_node, int max_if_num) diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 5cc011057da1..e1d641f27aa9 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -34,6 +34,7 @@ struct neigh_node *create_neighbor(struct orig_node *orig_node, uint8_t *neigh, struct hard_iface *if_incoming); void neigh_node_free_ref(struct neigh_node *neigh_node); +struct neigh_node *orig_node_get_router(struct orig_node *orig_node); int orig_seq_print_text(struct seq_file *seq, void *offset); int orig_hash_add_if(struct hard_iface *hard_iface, int max_if_num); int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num); diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index e7571879af3f..eda99650e9f8 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -61,7 +61,7 @@ struct batman_packet { uint8_t orig[6]; uint8_t prev_sender[6]; uint8_t ttl; - uint8_t num_hna; + uint8_t num_tt; uint8_t gw_flags; /* flags related to gateway class */ uint8_t align; } __packed; @@ -128,8 +128,7 @@ struct vis_packet { uint8_t entries; /* number of entries behind this struct */ uint32_t seqno; /* sequence number */ uint8_t ttl; /* TTL */ - uint8_t vis_orig[6]; /* originator that informs about its - * neighbors */ + uint8_t vis_orig[6]; /* originator that announces its neighbors */ uint8_t target_orig[6]; /* who should receive this packet */ uint8_t sender_orig[6]; /* who sent or rebroadcasted this packet */ } __packed; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index c172f5d0e05a..bb1c3ec7e3ff 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -64,80 +64,97 @@ void slide_own_bcast_window(struct hard_iface *hard_iface) } } -static void update_HNA(struct bat_priv *bat_priv, struct orig_node *orig_node, - unsigned char *hna_buff, int hna_buff_len) +static void update_TT(struct bat_priv *bat_priv, struct orig_node *orig_node, + unsigned char *tt_buff, int tt_buff_len) { - if ((hna_buff_len != orig_node->hna_buff_len) || - ((hna_buff_len > 0) && - (orig_node->hna_buff_len > 0) && - (memcmp(orig_node->hna_buff, hna_buff, hna_buff_len) != 0))) { - - if (orig_node->hna_buff_len > 0) - hna_global_del_orig(bat_priv, orig_node, - "originator changed hna"); - - if ((hna_buff_len > 0) && (hna_buff)) - hna_global_add_orig(bat_priv, orig_node, - hna_buff, hna_buff_len); + if ((tt_buff_len != orig_node->tt_buff_len) || + ((tt_buff_len > 0) && + (orig_node->tt_buff_len > 0) && + (memcmp(orig_node->tt_buff, tt_buff, tt_buff_len) != 0))) { + + if (orig_node->tt_buff_len > 0) + tt_global_del_orig(bat_priv, orig_node, + "originator changed tt"); + + if ((tt_buff_len > 0) && (tt_buff)) + tt_global_add_orig(bat_priv, orig_node, + tt_buff, tt_buff_len); } } static void update_route(struct bat_priv *bat_priv, struct orig_node *orig_node, struct neigh_node *neigh_node, - unsigned char *hna_buff, int hna_buff_len) + unsigned char *tt_buff, int tt_buff_len) { - struct neigh_node *neigh_node_tmp; + struct neigh_node *curr_router; + + curr_router = orig_node_get_router(orig_node); /* route deleted */ - if ((orig_node->router) && (!neigh_node)) { + if ((curr_router) && (!neigh_node)) { bat_dbg(DBG_ROUTES, bat_priv, "Deleting route towards: %pM\n", orig_node->orig); - hna_global_del_orig(bat_priv, orig_node, + tt_global_del_orig(bat_priv, orig_node, "originator timed out"); - /* route added */ - } else if ((!orig_node->router) && (neigh_node)) { + /* route added */ + } else if ((!curr_router) && (neigh_node)) { bat_dbg(DBG_ROUTES, bat_priv, "Adding route towards: %pM (via %pM)\n", orig_node->orig, neigh_node->addr); - hna_global_add_orig(bat_priv, orig_node, - hna_buff, hna_buff_len); + tt_global_add_orig(bat_priv, orig_node, + tt_buff, tt_buff_len); - /* route changed */ + /* route changed */ } else { bat_dbg(DBG_ROUTES, bat_priv, "Changing route towards: %pM " "(now via %pM - was via %pM)\n", orig_node->orig, neigh_node->addr, - orig_node->router->addr); + curr_router->addr); } + if (curr_router) + neigh_node_free_ref(curr_router); + + /* increase refcount of new best neighbor */ if (neigh_node && !atomic_inc_not_zero(&neigh_node->refcount)) neigh_node = NULL; - neigh_node_tmp = orig_node->router; - orig_node->router = neigh_node; - if (neigh_node_tmp) - neigh_node_free_ref(neigh_node_tmp); + + spin_lock_bh(&orig_node->neigh_list_lock); + rcu_assign_pointer(orig_node->router, neigh_node); + spin_unlock_bh(&orig_node->neigh_list_lock); + + /* decrease refcount of previous best neighbor */ + if (curr_router) + neigh_node_free_ref(curr_router); } void update_routes(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node, unsigned char *hna_buff, - int hna_buff_len) + struct neigh_node *neigh_node, unsigned char *tt_buff, + int tt_buff_len) { + struct neigh_node *router = NULL; if (!orig_node) - return; + goto out; + + router = orig_node_get_router(orig_node); - if (orig_node->router != neigh_node) + if (router != neigh_node) update_route(bat_priv, orig_node, neigh_node, - hna_buff, hna_buff_len); - /* may be just HNA changed */ + tt_buff, tt_buff_len); + /* may be just TT changed */ else - update_HNA(bat_priv, orig_node, hna_buff, hna_buff_len); + update_TT(bat_priv, orig_node, tt_buff, tt_buff_len); + +out: + if (router) + neigh_node_free_ref(router); } static int is_bidirectional_neigh(struct orig_node *orig_node, @@ -152,65 +169,41 @@ static int is_bidirectional_neigh(struct orig_node *orig_node, uint8_t orig_eq_count, neigh_rq_count, tq_own; int tq_asym_penalty, ret = 0; - if (orig_node == orig_neigh_node) { - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, - &orig_node->neigh_list, list) { - - if (!compare_eth(tmp_neigh_node->addr, - orig_neigh_node->orig)) - continue; - - if (tmp_neigh_node->if_incoming != if_incoming) - continue; - - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) - continue; - - neigh_node = tmp_neigh_node; - } - rcu_read_unlock(); + /* find corresponding one hop neighbor */ + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_node, node, + &orig_neigh_node->neigh_list, list) { - if (!neigh_node) - neigh_node = create_neighbor(orig_node, - orig_neigh_node, - orig_neigh_node->orig, - if_incoming); - if (!neigh_node) - goto out; + if (!compare_eth(tmp_neigh_node->addr, orig_neigh_node->orig)) + continue; - neigh_node->last_valid = jiffies; - } else { - /* find packet count of corresponding one hop neighbor */ - rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, - &orig_neigh_node->neigh_list, list) { + if (tmp_neigh_node->if_incoming != if_incoming) + continue; - if (!compare_eth(tmp_neigh_node->addr, - orig_neigh_node->orig)) - continue; + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; - if (tmp_neigh_node->if_incoming != if_incoming) - continue; + neigh_node = tmp_neigh_node; + break; + } + rcu_read_unlock(); - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) - continue; + if (!neigh_node) + neigh_node = create_neighbor(orig_neigh_node, + orig_neigh_node, + orig_neigh_node->orig, + if_incoming); - neigh_node = tmp_neigh_node; - } - rcu_read_unlock(); + if (!neigh_node) + goto out; - if (!neigh_node) - neigh_node = create_neighbor(orig_neigh_node, - orig_neigh_node, - orig_neigh_node->orig, - if_incoming); - if (!neigh_node) - goto out; - } + /* if orig_node is direct neighbour update neigh_node last_valid */ + if (orig_node == orig_neigh_node) + neigh_node->last_valid = jiffies; orig_node->last_valid = jiffies; + /* find packet count of corresponding one hop neighbor */ spin_lock_bh(&orig_node->ogm_cnt_lock); orig_eq_count = orig_neigh_node->bcast_own_sum[if_incoming->if_num]; neigh_rq_count = neigh_node->real_packet_count; @@ -288,8 +281,8 @@ static void bonding_candidate_add(struct orig_node *orig_node, struct neigh_node *neigh_node) { struct hlist_node *node; - struct neigh_node *tmp_neigh_node; - uint8_t best_tq, interference_candidate = 0; + struct neigh_node *tmp_neigh_node, *router = NULL; + uint8_t interference_candidate = 0; spin_lock_bh(&orig_node->neigh_list_lock); @@ -298,13 +291,12 @@ static void bonding_candidate_add(struct orig_node *orig_node, neigh_node->orig_node->primary_addr)) goto candidate_del; - if (!orig_node->router) + router = orig_node_get_router(orig_node); + if (!router) goto candidate_del; - best_tq = orig_node->router->tq_avg; - /* ... and is good enough to be considered */ - if (neigh_node->tq_avg < best_tq - BONDING_TQ_THRESHOLD) + if (neigh_node->tq_avg < router->tq_avg - BONDING_TQ_THRESHOLD) goto candidate_del; /** @@ -350,7 +342,9 @@ candidate_del: out: spin_unlock_bh(&orig_node->neigh_list_lock); - return; + + if (router) + neigh_node_free_ref(router); } /* copy primary address for bonding */ @@ -369,13 +363,14 @@ static void update_orig(struct bat_priv *bat_priv, struct ethhdr *ethhdr, struct batman_packet *batman_packet, struct hard_iface *if_incoming, - unsigned char *hna_buff, int hna_buff_len, + unsigned char *tt_buff, int tt_buff_len, char is_duplicate) { struct neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; + struct neigh_node *router = NULL; struct orig_node *orig_node_tmp; struct hlist_node *node; - int tmp_hna_buff_len; + int tmp_tt_buff_len; uint8_t bcast_own_sum_orig, bcast_own_sum_neigh; bat_dbg(DBG_BATMAN, bat_priv, "update_originator(): " @@ -396,10 +391,12 @@ static void update_orig(struct bat_priv *bat_priv, if (is_duplicate) continue; + spin_lock_bh(&tmp_neigh_node->tq_lock); ring_buffer_set(tmp_neigh_node->tq_recv, &tmp_neigh_node->tq_index, 0); tmp_neigh_node->tq_avg = ring_buffer_avg(tmp_neigh_node->tq_recv); + spin_unlock_bh(&tmp_neigh_node->tq_lock); } if (!neigh_node) { @@ -424,10 +421,12 @@ static void update_orig(struct bat_priv *bat_priv, orig_node->flags = batman_packet->flags; neigh_node->last_valid = jiffies; + spin_lock_bh(&neigh_node->tq_lock); ring_buffer_set(neigh_node->tq_recv, &neigh_node->tq_index, batman_packet->tq); neigh_node->tq_avg = ring_buffer_avg(neigh_node->tq_recv); + spin_unlock_bh(&neigh_node->tq_lock); if (!is_duplicate) { orig_node->last_ttl = batman_packet->ttl; @@ -436,24 +435,23 @@ static void update_orig(struct bat_priv *bat_priv, bonding_candidate_add(orig_node, neigh_node); - tmp_hna_buff_len = (hna_buff_len > batman_packet->num_hna * ETH_ALEN ? - batman_packet->num_hna * ETH_ALEN : hna_buff_len); + tmp_tt_buff_len = (tt_buff_len > batman_packet->num_tt * ETH_ALEN ? + batman_packet->num_tt * ETH_ALEN : tt_buff_len); /* if this neighbor already is our next hop there is nothing * to change */ - if (orig_node->router == neigh_node) - goto update_hna; + router = orig_node_get_router(orig_node); + if (router == neigh_node) + goto update_tt; /* if this neighbor does not offer a better TQ we won't consider it */ - if ((orig_node->router) && - (orig_node->router->tq_avg > neigh_node->tq_avg)) - goto update_hna; + if (router && (router->tq_avg > neigh_node->tq_avg)) + goto update_tt; /* if the TQ is the same and the link not more symetric we * won't consider it either */ - if ((orig_node->router) && - (neigh_node->tq_avg == orig_node->router->tq_avg)) { - orig_node_tmp = orig_node->router->orig_node; + if (router && (neigh_node->tq_avg == router->tq_avg)) { + orig_node_tmp = router->orig_node; spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); bcast_own_sum_orig = orig_node_tmp->bcast_own_sum[if_incoming->if_num]; @@ -466,16 +464,16 @@ static void update_orig(struct bat_priv *bat_priv, spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); if (bcast_own_sum_orig >= bcast_own_sum_neigh) - goto update_hna; + goto update_tt; } update_routes(bat_priv, orig_node, neigh_node, - hna_buff, tmp_hna_buff_len); + tt_buff, tmp_tt_buff_len); goto update_gw; -update_hna: - update_routes(bat_priv, orig_node, orig_node->router, - hna_buff, tmp_hna_buff_len); +update_tt: + update_routes(bat_priv, orig_node, router, + tt_buff, tmp_tt_buff_len); update_gw: if (orig_node->gw_flags != batman_packet->gw_flags) @@ -496,6 +494,8 @@ unlock: out: if (neigh_node) neigh_node_free_ref(neigh_node); + if (router) + neigh_node_free_ref(router); } /* checks whether the host restarted and is in the protection time. @@ -597,12 +597,14 @@ out: void receive_bat_packet(struct ethhdr *ethhdr, struct batman_packet *batman_packet, - unsigned char *hna_buff, int hna_buff_len, + unsigned char *tt_buff, int tt_buff_len, struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct hard_iface *hard_iface; struct orig_node *orig_neigh_node, *orig_node; + struct neigh_node *router = NULL, *router_router = NULL; + struct neigh_node *orig_neigh_router = NULL; char has_directlink_flag; char is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; char is_broadcast = 0, is_bidirectional, is_single_hop_neigh; @@ -747,14 +749,15 @@ void receive_bat_packet(struct ethhdr *ethhdr, goto out; } + router = orig_node_get_router(orig_node); + if (router) + router_router = orig_node_get_router(router->orig_node); + /* avoid temporary routing loops */ - if ((orig_node->router) && - (orig_node->router->orig_node->router) && - (compare_eth(orig_node->router->addr, - batman_packet->prev_sender)) && + if (router && router_router && + (compare_eth(router->addr, batman_packet->prev_sender)) && !(compare_eth(batman_packet->orig, batman_packet->prev_sender)) && - (compare_eth(orig_node->router->addr, - orig_node->router->orig_node->router->addr))) { + (compare_eth(router->addr, router_router->addr))) { bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: ignoring all rebroadcast packets that " "may make me loop (sender: %pM)\n", ethhdr->h_source); @@ -769,9 +772,11 @@ void receive_bat_packet(struct ethhdr *ethhdr, if (!orig_neigh_node) goto out; + orig_neigh_router = orig_node_get_router(orig_neigh_node); + /* drop packet if sender is not a direct neighbor and if we * don't route towards it */ - if (!is_single_hop_neigh && (!orig_neigh_node->router)) { + if (!is_single_hop_neigh && (!orig_neigh_router)) { bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: OGM via unknown neighbor!\n"); goto out_neigh; @@ -789,14 +794,14 @@ void receive_bat_packet(struct ethhdr *ethhdr, ((orig_node->last_real_seqno == batman_packet->seqno) && (orig_node->last_ttl - 3 <= batman_packet->ttl)))) update_orig(bat_priv, orig_node, ethhdr, batman_packet, - if_incoming, hna_buff, hna_buff_len, is_duplicate); + if_incoming, tt_buff, tt_buff_len, is_duplicate); /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { /* mark direct link on incoming interface */ schedule_forward_packet(orig_node, ethhdr, batman_packet, - 1, hna_buff_len, if_incoming); + 1, tt_buff_len, if_incoming); bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: " "rebroadcast neighbor packet with direct link flag\n"); @@ -819,12 +824,19 @@ void receive_bat_packet(struct ethhdr *ethhdr, bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast originator packet\n"); schedule_forward_packet(orig_node, ethhdr, batman_packet, - 0, hna_buff_len, if_incoming); + 0, tt_buff_len, if_incoming); out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) orig_node_free_ref(orig_neigh_node); out: + if (router) + neigh_node_free_ref(router); + if (router_router) + neigh_node_free_ref(router_router); + if (orig_neigh_router) + neigh_node_free_ref(orig_neigh_router); + orig_node_free_ref(orig_node); } @@ -868,8 +880,9 @@ int recv_bat_packet(struct sk_buff *skb, struct hard_iface *hard_iface) static int recv_my_icmp_packet(struct bat_priv *bat_priv, struct sk_buff *skb, size_t icmp_len) { + struct hard_iface *primary_if = NULL; struct orig_node *orig_node = NULL; - struct neigh_node *neigh_node = NULL; + struct neigh_node *router = NULL; struct icmp_packet_rr *icmp_packet; int ret = NET_RX_DROP; @@ -881,28 +894,19 @@ static int recv_my_icmp_packet(struct bat_priv *bat_priv, goto out; } - if (!bat_priv->primary_if) + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) goto out; /* answer echo request (ping) */ /* get routing information */ - rcu_read_lock(); orig_node = orig_hash_find(bat_priv, icmp_packet->orig); - if (!orig_node) - goto unlock; - - neigh_node = orig_node->router; - - if (!neigh_node) - goto unlock; - - if (!atomic_inc_not_zero(&neigh_node->refcount)) { - neigh_node = NULL; - goto unlock; - } + goto out; - rcu_read_unlock(); + router = orig_node_get_router(orig_node); + if (!router) + goto out; /* create a copy of the skb, if needed, to modify it. */ if (skb_cow(skb, sizeof(struct ethhdr)) < 0) @@ -911,20 +915,18 @@ static int recv_my_icmp_packet(struct bat_priv *bat_priv, icmp_packet = (struct icmp_packet_rr *)skb->data; memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); - memcpy(icmp_packet->orig, - bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN); + memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr, ETH_ALEN); icmp_packet->msg_type = ECHO_REPLY; icmp_packet->ttl = TTL; - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + send_skb_packet(skb, router->if_incoming, router->addr); ret = NET_RX_SUCCESS; - goto out; -unlock: - rcu_read_unlock(); out: - if (neigh_node) - neigh_node_free_ref(neigh_node); + if (primary_if) + hardif_free_ref(primary_if); + if (router) + neigh_node_free_ref(router); if (orig_node) orig_node_free_ref(orig_node); return ret; @@ -933,8 +935,9 @@ out: static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, struct sk_buff *skb) { + struct hard_iface *primary_if = NULL; struct orig_node *orig_node = NULL; - struct neigh_node *neigh_node = NULL; + struct neigh_node *router = NULL; struct icmp_packet *icmp_packet; int ret = NET_RX_DROP; @@ -948,27 +951,18 @@ static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, goto out; } - if (!bat_priv->primary_if) + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) goto out; /* get routing information */ - rcu_read_lock(); orig_node = orig_hash_find(bat_priv, icmp_packet->orig); - if (!orig_node) - goto unlock; - - neigh_node = orig_node->router; - - if (!neigh_node) - goto unlock; - - if (!atomic_inc_not_zero(&neigh_node->refcount)) { - neigh_node = NULL; - goto unlock; - } + goto out; - rcu_read_unlock(); + router = orig_node_get_router(orig_node); + if (!router) + goto out; /* create a copy of the skb, if needed, to modify it. */ if (skb_cow(skb, sizeof(struct ethhdr)) < 0) @@ -977,20 +971,18 @@ static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, icmp_packet = (struct icmp_packet *)skb->data; memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); - memcpy(icmp_packet->orig, - bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN); + memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr, ETH_ALEN); icmp_packet->msg_type = TTL_EXCEEDED; icmp_packet->ttl = TTL; - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + send_skb_packet(skb, router->if_incoming, router->addr); ret = NET_RX_SUCCESS; - goto out; -unlock: - rcu_read_unlock(); out: - if (neigh_node) - neigh_node_free_ref(neigh_node); + if (primary_if) + hardif_free_ref(primary_if); + if (router) + neigh_node_free_ref(router); if (orig_node) orig_node_free_ref(orig_node); return ret; @@ -1003,7 +995,7 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) struct icmp_packet_rr *icmp_packet; struct ethhdr *ethhdr; struct orig_node *orig_node = NULL; - struct neigh_node *neigh_node = NULL; + struct neigh_node *router = NULL; int hdr_size = sizeof(struct icmp_packet); int ret = NET_RX_DROP; @@ -1050,23 +1042,13 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) return recv_icmp_ttl_exceeded(bat_priv, skb); /* get routing information */ - rcu_read_lock(); orig_node = orig_hash_find(bat_priv, icmp_packet->dst); - if (!orig_node) - goto unlock; - - neigh_node = orig_node->router; - - if (!neigh_node) - goto unlock; - - if (!atomic_inc_not_zero(&neigh_node->refcount)) { - neigh_node = NULL; - goto unlock; - } + goto out; - rcu_read_unlock(); + router = orig_node_get_router(orig_node); + if (!router) + goto out; /* create a copy of the skb, if needed, to modify it. */ if (skb_cow(skb, sizeof(struct ethhdr)) < 0) @@ -1078,20 +1060,117 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) icmp_packet->ttl--; /* route it */ - send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + send_skb_packet(skb, router->if_incoming, router->addr); ret = NET_RX_SUCCESS; - goto out; -unlock: - rcu_read_unlock(); out: - if (neigh_node) - neigh_node_free_ref(neigh_node); + if (router) + neigh_node_free_ref(router); if (orig_node) orig_node_free_ref(orig_node); return ret; } +/* In the bonding case, send the packets in a round + * robin fashion over the remaining interfaces. + * + * This method rotates the bonding list and increases the + * returned router's refcount. */ +static struct neigh_node *find_bond_router(struct orig_node *primary_orig, + struct hard_iface *recv_if) +{ + struct neigh_node *tmp_neigh_node; + struct neigh_node *router = NULL, *first_candidate = NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, + bonding_list) { + if (!first_candidate) + first_candidate = tmp_neigh_node; + + /* recv_if == NULL on the first node. */ + if (tmp_neigh_node->if_incoming == recv_if) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; + + router = tmp_neigh_node; + break; + } + + /* use the first candidate if nothing was found. */ + if (!router && first_candidate && + atomic_inc_not_zero(&first_candidate->refcount)) + router = first_candidate; + + if (!router) + goto out; + + /* selected should point to the next element + * after the current router */ + spin_lock_bh(&primary_orig->neigh_list_lock); + /* this is a list_move(), which unfortunately + * does not exist as rcu version */ + list_del_rcu(&primary_orig->bond_list); + list_add_rcu(&primary_orig->bond_list, + &router->bonding_list); + spin_unlock_bh(&primary_orig->neigh_list_lock); + +out: + rcu_read_unlock(); + return router; +} + +/* Interface Alternating: Use the best of the + * remaining candidates which are not using + * this interface. + * + * Increases the returned router's refcount */ +static struct neigh_node *find_ifalter_router(struct orig_node *primary_orig, + struct hard_iface *recv_if) +{ + struct neigh_node *tmp_neigh_node; + struct neigh_node *router = NULL, *first_candidate = NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, + bonding_list) { + if (!first_candidate) + first_candidate = tmp_neigh_node; + + /* recv_if == NULL on the first node. */ + if (tmp_neigh_node->if_incoming == recv_if) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; + + /* if we don't have a router yet + * or this one is better, choose it. */ + if ((!router) || + (tmp_neigh_node->tq_avg > router->tq_avg)) { + /* decrement refcount of + * previously selected router */ + if (router) + neigh_node_free_ref(router); + + router = tmp_neigh_node; + atomic_inc_not_zero(&router->refcount); + } + + neigh_node_free_ref(tmp_neigh_node); + } + + /* use the first candidate if nothing was found. */ + if (!router && first_candidate && + atomic_inc_not_zero(&first_candidate->refcount)) + router = first_candidate; + + rcu_read_unlock(); + return router; +} + /* find a suitable router for this originator, and use * bonding if possible. increases the found neighbors * refcount.*/ @@ -1101,15 +1180,16 @@ struct neigh_node *find_router(struct bat_priv *bat_priv, { struct orig_node *primary_orig_node; struct orig_node *router_orig; - struct neigh_node *router, *first_candidate, *tmp_neigh_node; + struct neigh_node *router; static uint8_t zero_mac[ETH_ALEN] = {0, 0, 0, 0, 0, 0}; int bonding_enabled; if (!orig_node) return NULL; - if (!orig_node->router) - return NULL; + router = orig_node_get_router(orig_node); + if (!router) + goto err; /* without bonding, the first node should * always choose the default router. */ @@ -1117,12 +1197,9 @@ struct neigh_node *find_router(struct bat_priv *bat_priv, rcu_read_lock(); /* select default router to output */ - router = orig_node->router; - router_orig = orig_node->router->orig_node; - if (!router_orig || !atomic_inc_not_zero(&router->refcount)) { - rcu_read_unlock(); - return NULL; - } + router_orig = router->orig_node; + if (!router_orig) + goto err_unlock; if ((!recv_if) && (!bonding_enabled)) goto return_router; @@ -1151,91 +1228,26 @@ struct neigh_node *find_router(struct bat_priv *bat_priv, if (atomic_read(&primary_orig_node->bond_candidates) < 2) goto return_router; - /* all nodes between should choose a candidate which * is is not on the interface where the packet came * in. */ neigh_node_free_ref(router); - first_candidate = NULL; - router = NULL; - - if (bonding_enabled) { - /* in the bonding case, send the packets in a round - * robin fashion over the remaining interfaces. */ - - list_for_each_entry_rcu(tmp_neigh_node, - &primary_orig_node->bond_list, bonding_list) { - if (!first_candidate) - first_candidate = tmp_neigh_node; - /* recv_if == NULL on the first node. */ - if (tmp_neigh_node->if_incoming != recv_if && - atomic_inc_not_zero(&tmp_neigh_node->refcount)) { - router = tmp_neigh_node; - break; - } - } - - /* use the first candidate if nothing was found. */ - if (!router && first_candidate && - atomic_inc_not_zero(&first_candidate->refcount)) - router = first_candidate; - if (!router) { - rcu_read_unlock(); - return NULL; - } - - /* selected should point to the next element - * after the current router */ - spin_lock_bh(&primary_orig_node->neigh_list_lock); - /* this is a list_move(), which unfortunately - * does not exist as rcu version */ - list_del_rcu(&primary_orig_node->bond_list); - list_add_rcu(&primary_orig_node->bond_list, - &router->bonding_list); - spin_unlock_bh(&primary_orig_node->neigh_list_lock); - - } else { - /* if bonding is disabled, use the best of the - * remaining candidates which are not using - * this interface. */ - list_for_each_entry_rcu(tmp_neigh_node, - &primary_orig_node->bond_list, bonding_list) { - if (!first_candidate) - first_candidate = tmp_neigh_node; - - /* recv_if == NULL on the first node. */ - if (tmp_neigh_node->if_incoming == recv_if) - continue; - - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) - continue; - - /* if we don't have a router yet - * or this one is better, choose it. */ - if ((!router) || - (tmp_neigh_node->tq_avg > router->tq_avg)) { - /* decrement refcount of - * previously selected router */ - if (router) - neigh_node_free_ref(router); - - router = tmp_neigh_node; - atomic_inc_not_zero(&router->refcount); - } - - neigh_node_free_ref(tmp_neigh_node); - } + if (bonding_enabled) + router = find_bond_router(primary_orig_node, recv_if); + else + router = find_ifalter_router(primary_orig_node, recv_if); - /* use the first candidate if nothing was found. */ - if (!router && first_candidate && - atomic_inc_not_zero(&first_candidate->refcount)) - router = first_candidate; - } return_router: rcu_read_unlock(); return router; +err_unlock: + rcu_read_unlock(); +err: + if (router) + neigh_node_free_ref(router); + return NULL; } static int check_unicast_packet(struct sk_buff *skb, int hdr_size) @@ -1284,13 +1296,10 @@ int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) } /* get routing information */ - rcu_read_lock(); orig_node = orig_hash_find(bat_priv, unicast_packet->dest); if (!orig_node) - goto unlock; - - rcu_read_unlock(); + goto out; /* find_router() increases neigh_nodes refcount if found. */ neigh_node = find_router(bat_priv, orig_node, recv_if); @@ -1336,10 +1345,7 @@ int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) /* route it */ send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); ret = NET_RX_SUCCESS; - goto out; -unlock: - rcu_read_unlock(); out: if (neigh_node) neigh_node_free_ref(neigh_node); @@ -1438,13 +1444,10 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) if (bcast_packet->ttl < 2) goto out; - rcu_read_lock(); orig_node = orig_hash_find(bat_priv, bcast_packet->orig); if (!orig_node) - goto rcu_unlock; - - rcu_read_unlock(); + goto out; spin_lock_bh(&orig_node->bcast_seqno_lock); @@ -1475,9 +1478,6 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) ret = NET_RX_SUCCESS; goto out; -rcu_unlock: - rcu_read_unlock(); - goto out; spin_unlock: spin_unlock_bh(&orig_node->bcast_seqno_lock); out: diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index b5a064c88a4f..870f29842b28 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -25,11 +25,11 @@ void slide_own_bcast_window(struct hard_iface *hard_iface); void receive_bat_packet(struct ethhdr *ethhdr, struct batman_packet *batman_packet, - unsigned char *hna_buff, int hna_buff_len, + unsigned char *tt_buff, int tt_buff_len, struct hard_iface *if_incoming); void update_routes(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node, unsigned char *hna_buff, - int hna_buff_len); + struct neigh_node *neigh_node, unsigned char *tt_buff, + int tt_buff_len); int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index d49e54d932af..33779278f1b2 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -121,7 +121,7 @@ static void send_packet_to_if(struct forw_packet *forw_packet, /* adjust all flags and log packets */ while (aggregated_packet(buff_pos, forw_packet->packet_len, - batman_packet->num_hna)) { + batman_packet->num_tt)) { /* we might have aggregated direct link packets with an * ordinary base packet */ @@ -146,7 +146,7 @@ static void send_packet_to_if(struct forw_packet *forw_packet, hard_iface->net_dev->dev_addr); buff_pos += sizeof(struct batman_packet) + - (batman_packet->num_hna * ETH_ALEN); + (batman_packet->num_tt * ETH_ALEN); packet_num++; batman_packet = (struct batman_packet *) (forw_packet->skb->data + buff_pos); @@ -222,7 +222,7 @@ static void rebuild_batman_packet(struct bat_priv *bat_priv, struct batman_packet *batman_packet; new_len = sizeof(struct batman_packet) + - (bat_priv->num_local_hna * ETH_ALEN); + (bat_priv->num_local_tt * ETH_ALEN); new_buff = kmalloc(new_len, GFP_ATOMIC); /* keep old buffer if kmalloc should fail */ @@ -231,7 +231,7 @@ static void rebuild_batman_packet(struct bat_priv *bat_priv, sizeof(struct batman_packet)); batman_packet = (struct batman_packet *)new_buff; - batman_packet->num_hna = hna_local_fill_buffer(bat_priv, + batman_packet->num_tt = tt_local_fill_buffer(bat_priv, new_buff + sizeof(struct batman_packet), new_len - sizeof(struct batman_packet)); @@ -244,6 +244,7 @@ static void rebuild_batman_packet(struct bat_priv *bat_priv, void schedule_own_packet(struct hard_iface *hard_iface) { struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct hard_iface *primary_if; unsigned long send_time; struct batman_packet *batman_packet; int vis_server; @@ -253,6 +254,7 @@ void schedule_own_packet(struct hard_iface *hard_iface) return; vis_server = atomic_read(&bat_priv->vis_mode); + primary_if = primary_if_get_selected(bat_priv); /** * the interface gets activated here to avoid race conditions between @@ -264,9 +266,9 @@ void schedule_own_packet(struct hard_iface *hard_iface) if (hard_iface->if_status == IF_TO_BE_ACTIVATED) hard_iface->if_status = IF_ACTIVE; - /* if local hna has changed and interface is a primary interface */ - if ((atomic_read(&bat_priv->hna_local_changed)) && - (hard_iface == bat_priv->primary_if)) + /* if local tt has changed and interface is a primary interface */ + if ((atomic_read(&bat_priv->tt_local_changed)) && + (hard_iface == primary_if)) rebuild_batman_packet(bat_priv, hard_iface); /** @@ -284,7 +286,7 @@ void schedule_own_packet(struct hard_iface *hard_iface) else batman_packet->flags &= ~VIS_SERVER; - if ((hard_iface == bat_priv->primary_if) && + if ((hard_iface == primary_if) && (atomic_read(&bat_priv->gw_mode) == GW_MODE_SERVER)) batman_packet->gw_flags = (uint8_t)atomic_read(&bat_priv->gw_bandwidth); @@ -299,15 +301,19 @@ void schedule_own_packet(struct hard_iface *hard_iface) hard_iface->packet_buff, hard_iface->packet_len, hard_iface, 1, send_time); + + if (primary_if) + hardif_free_ref(primary_if); } void schedule_forward_packet(struct orig_node *orig_node, struct ethhdr *ethhdr, struct batman_packet *batman_packet, - uint8_t directlink, int hna_buff_len, + uint8_t directlink, int tt_buff_len, struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct neigh_node *router; unsigned char in_tq, in_ttl, tq_avg = 0; unsigned long send_time; @@ -316,6 +322,8 @@ void schedule_forward_packet(struct orig_node *orig_node, return; } + router = orig_node_get_router(orig_node); + in_tq = batman_packet->tq; in_ttl = batman_packet->ttl; @@ -324,20 +332,22 @@ void schedule_forward_packet(struct orig_node *orig_node, /* rebroadcast tq of our best ranking neighbor to ensure the rebroadcast * of our best tq value */ - if ((orig_node->router) && (orig_node->router->tq_avg != 0)) { + if (router && router->tq_avg != 0) { /* rebroadcast ogm of best ranking neighbor as is */ - if (!compare_eth(orig_node->router->addr, ethhdr->h_source)) { - batman_packet->tq = orig_node->router->tq_avg; + if (!compare_eth(router->addr, ethhdr->h_source)) { + batman_packet->tq = router->tq_avg; - if (orig_node->router->last_ttl) - batman_packet->ttl = orig_node->router->last_ttl - - 1; + if (router->last_ttl) + batman_packet->ttl = router->last_ttl - 1; } - tq_avg = orig_node->router->tq_avg; + tq_avg = router->tq_avg; } + if (router) + neigh_node_free_ref(router); + /* apply hop penalty */ batman_packet->tq = hop_penalty(batman_packet->tq, bat_priv); @@ -359,7 +369,7 @@ void schedule_forward_packet(struct orig_node *orig_node, send_time = forward_send_time(); add_bat_packet_to_list(bat_priv, (unsigned char *)batman_packet, - sizeof(struct batman_packet) + hna_buff_len, + sizeof(struct batman_packet) + tt_buff_len, if_incoming, 0, send_time); } @@ -367,6 +377,8 @@ static void forw_packet_free(struct forw_packet *forw_packet) { if (forw_packet->skb) kfree_skb(forw_packet->skb); + if (forw_packet->if_incoming) + hardif_free_ref(forw_packet->if_incoming); kfree(forw_packet); } @@ -388,7 +400,6 @@ static void _add_bcast_packet_to_list(struct bat_priv *bat_priv, send_time); } -#define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) /* add a broadcast packet to the queue and setup timers. broadcast packets * are sent multiple times to increase probability for beeing received. * @@ -399,6 +410,7 @@ static void _add_bcast_packet_to_list(struct bat_priv *bat_priv, * skb is freed. */ int add_bcast_packet_to_list(struct bat_priv *bat_priv, struct sk_buff *skb) { + struct hard_iface *primary_if = NULL; struct forw_packet *forw_packet; struct bcast_packet *bcast_packet; @@ -407,8 +419,9 @@ int add_bcast_packet_to_list(struct bat_priv *bat_priv, struct sk_buff *skb) goto out; } - if (!bat_priv->primary_if) - goto out; + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out_and_inc; forw_packet = kmalloc(sizeof(struct forw_packet), GFP_ATOMIC); @@ -426,7 +439,7 @@ int add_bcast_packet_to_list(struct bat_priv *bat_priv, struct sk_buff *skb) skb_reset_mac_header(skb); forw_packet->skb = skb; - forw_packet->if_incoming = bat_priv->primary_if; + forw_packet->if_incoming = primary_if; /* how often did we send the bcast packet ? */ forw_packet->num_packets = 0; @@ -439,6 +452,8 @@ packet_free: out_and_inc: atomic_inc(&bat_priv->bcast_queue_left); out: + if (primary_if) + hardif_free_ref(primary_if); return NETDEV_TX_BUSY; } @@ -526,6 +541,7 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, { struct forw_packet *forw_packet; struct hlist_node *tmp_node, *safe_tmp_node; + bool pending; if (hard_iface) bat_dbg(DBG_BATMAN, bat_priv, @@ -554,8 +570,13 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, * send_outstanding_bcast_packet() will lock the list to * delete the item from the list */ - cancel_delayed_work_sync(&forw_packet->delayed_work); + pending = cancel_delayed_work_sync(&forw_packet->delayed_work); spin_lock_bh(&bat_priv->forw_bcast_list_lock); + + if (pending) { + hlist_del(&forw_packet->list); + forw_packet_free(forw_packet); + } } spin_unlock_bh(&bat_priv->forw_bcast_list_lock); @@ -578,8 +599,13 @@ void purge_outstanding_packets(struct bat_priv *bat_priv, * send_outstanding_bat_packet() will lock the list to * delete the item from the list */ - cancel_delayed_work_sync(&forw_packet->delayed_work); + pending = cancel_delayed_work_sync(&forw_packet->delayed_work); spin_lock_bh(&bat_priv->forw_bat_list_lock); + + if (pending) { + hlist_del(&forw_packet->list); + forw_packet_free(forw_packet); + } } spin_unlock_bh(&bat_priv->forw_bat_list_lock); } diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 7b2ff19c05e7..247172d71e4b 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -29,7 +29,7 @@ void schedule_own_packet(struct hard_iface *hard_iface); void schedule_forward_packet(struct orig_node *orig_node, struct ethhdr *ethhdr, struct batman_packet *batman_packet, - uint8_t directlink, int hna_buff_len, + uint8_t directlink, int tt_buff_len, struct hard_iface *if_outgoing); int add_bcast_packet_to_list(struct bat_priv *bat_priv, struct sk_buff *skb); void send_outstanding_bat_packet(struct work_struct *work); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 9ed26140a269..d5aa60999e83 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -43,8 +43,6 @@ static void bat_get_drvinfo(struct net_device *dev, static u32 bat_get_msglevel(struct net_device *dev); static void bat_set_msglevel(struct net_device *dev, u32 value); static u32 bat_get_link(struct net_device *dev); -static u32 bat_get_rx_csum(struct net_device *dev); -static int bat_set_rx_csum(struct net_device *dev, u32 data); static const struct ethtool_ops bat_ethtool_ops = { .get_settings = bat_get_settings, @@ -52,8 +50,6 @@ static const struct ethtool_ops bat_ethtool_ops = { .get_msglevel = bat_get_msglevel, .set_msglevel = bat_set_msglevel, .get_link = bat_get_link, - .get_rx_csum = bat_get_rx_csum, - .set_rx_csum = bat_set_rx_csum }; int my_skb_head_push(struct sk_buff *skb, unsigned int len) @@ -76,120 +72,371 @@ int my_skb_head_push(struct sk_buff *skb, unsigned int len) return 0; } -static void softif_neigh_free_rcu(struct rcu_head *rcu) -{ - struct softif_neigh *softif_neigh; - - softif_neigh = container_of(rcu, struct softif_neigh, rcu); - kfree(softif_neigh); -} - static void softif_neigh_free_ref(struct softif_neigh *softif_neigh) { if (atomic_dec_and_test(&softif_neigh->refcount)) - call_rcu(&softif_neigh->rcu, softif_neigh_free_rcu); + kfree_rcu(softif_neigh, rcu); } -void softif_neigh_purge(struct bat_priv *bat_priv) +static void softif_neigh_vid_free_rcu(struct rcu_head *rcu) { - struct softif_neigh *softif_neigh, *softif_neigh_tmp; + struct softif_neigh_vid *softif_neigh_vid; + struct softif_neigh *softif_neigh; struct hlist_node *node, *node_tmp; + struct bat_priv *bat_priv; - spin_lock_bh(&bat_priv->softif_neigh_lock); + softif_neigh_vid = container_of(rcu, struct softif_neigh_vid, rcu); + bat_priv = softif_neigh_vid->bat_priv; + spin_lock_bh(&bat_priv->softif_neigh_lock); hlist_for_each_entry_safe(softif_neigh, node, node_tmp, - &bat_priv->softif_neigh_list, list) { + &softif_neigh_vid->softif_neigh_list, list) { + hlist_del_rcu(&softif_neigh->list); + softif_neigh_free_ref(softif_neigh); + } + spin_unlock_bh(&bat_priv->softif_neigh_lock); - if ((!time_after(jiffies, softif_neigh->last_seen + - msecs_to_jiffies(SOFTIF_NEIGH_TIMEOUT))) && - (atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE)) - continue; + kfree(softif_neigh_vid); +} - hlist_del_rcu(&softif_neigh->list); +static void softif_neigh_vid_free_ref(struct softif_neigh_vid *softif_neigh_vid) +{ + if (atomic_dec_and_test(&softif_neigh_vid->refcount)) + call_rcu(&softif_neigh_vid->rcu, softif_neigh_vid_free_rcu); +} - if (bat_priv->softif_neigh == softif_neigh) { - bat_dbg(DBG_ROUTES, bat_priv, - "Current mesh exit point '%pM' vanished " - "(vid: %d).\n", - softif_neigh->addr, softif_neigh->vid); - softif_neigh_tmp = bat_priv->softif_neigh; - bat_priv->softif_neigh = NULL; - softif_neigh_free_ref(softif_neigh_tmp); - } +static struct softif_neigh_vid *softif_neigh_vid_get(struct bat_priv *bat_priv, + short vid) +{ + struct softif_neigh_vid *softif_neigh_vid; + struct hlist_node *node; - softif_neigh_free_ref(softif_neigh); + rcu_read_lock(); + hlist_for_each_entry_rcu(softif_neigh_vid, node, + &bat_priv->softif_neigh_vids, list) { + if (softif_neigh_vid->vid != vid) + continue; + + if (!atomic_inc_not_zero(&softif_neigh_vid->refcount)) + continue; + + goto out; } - spin_unlock_bh(&bat_priv->softif_neigh_lock); + softif_neigh_vid = kzalloc(sizeof(struct softif_neigh_vid), + GFP_ATOMIC); + if (!softif_neigh_vid) + goto out; + + softif_neigh_vid->vid = vid; + softif_neigh_vid->bat_priv = bat_priv; + + /* initialize with 2 - caller decrements counter by one */ + atomic_set(&softif_neigh_vid->refcount, 2); + INIT_HLIST_HEAD(&softif_neigh_vid->softif_neigh_list); + INIT_HLIST_NODE(&softif_neigh_vid->list); + spin_lock_bh(&bat_priv->softif_neigh_vid_lock); + hlist_add_head_rcu(&softif_neigh_vid->list, + &bat_priv->softif_neigh_vids); + spin_unlock_bh(&bat_priv->softif_neigh_vid_lock); + +out: + rcu_read_unlock(); + return softif_neigh_vid; } static struct softif_neigh *softif_neigh_get(struct bat_priv *bat_priv, uint8_t *addr, short vid) { - struct softif_neigh *softif_neigh; + struct softif_neigh_vid *softif_neigh_vid; + struct softif_neigh *softif_neigh = NULL; struct hlist_node *node; + softif_neigh_vid = softif_neigh_vid_get(bat_priv, vid); + if (!softif_neigh_vid) + goto out; + rcu_read_lock(); hlist_for_each_entry_rcu(softif_neigh, node, - &bat_priv->softif_neigh_list, list) { + &softif_neigh_vid->softif_neigh_list, + list) { if (!compare_eth(softif_neigh->addr, addr)) continue; - if (softif_neigh->vid != vid) - continue; - if (!atomic_inc_not_zero(&softif_neigh->refcount)) continue; softif_neigh->last_seen = jiffies; - goto out; + goto unlock; } softif_neigh = kzalloc(sizeof(struct softif_neigh), GFP_ATOMIC); if (!softif_neigh) - goto out; + goto unlock; memcpy(softif_neigh->addr, addr, ETH_ALEN); - softif_neigh->vid = vid; softif_neigh->last_seen = jiffies; /* initialize with 2 - caller decrements counter by one */ atomic_set(&softif_neigh->refcount, 2); INIT_HLIST_NODE(&softif_neigh->list); spin_lock_bh(&bat_priv->softif_neigh_lock); - hlist_add_head_rcu(&softif_neigh->list, &bat_priv->softif_neigh_list); + hlist_add_head_rcu(&softif_neigh->list, + &softif_neigh_vid->softif_neigh_list); spin_unlock_bh(&bat_priv->softif_neigh_lock); +unlock: + rcu_read_unlock(); out: + if (softif_neigh_vid) + softif_neigh_vid_free_ref(softif_neigh_vid); + return softif_neigh; +} + +static struct softif_neigh *softif_neigh_get_selected( + struct softif_neigh_vid *softif_neigh_vid) +{ + struct softif_neigh *softif_neigh; + + rcu_read_lock(); + softif_neigh = rcu_dereference(softif_neigh_vid->softif_neigh); + + if (softif_neigh && !atomic_inc_not_zero(&softif_neigh->refcount)) + softif_neigh = NULL; + rcu_read_unlock(); return softif_neigh; } +static struct softif_neigh *softif_neigh_vid_get_selected( + struct bat_priv *bat_priv, + short vid) +{ + struct softif_neigh_vid *softif_neigh_vid; + struct softif_neigh *softif_neigh = NULL; + + softif_neigh_vid = softif_neigh_vid_get(bat_priv, vid); + if (!softif_neigh_vid) + goto out; + + softif_neigh = softif_neigh_get_selected(softif_neigh_vid); +out: + if (softif_neigh_vid) + softif_neigh_vid_free_ref(softif_neigh_vid); + return softif_neigh; +} + +static void softif_neigh_vid_select(struct bat_priv *bat_priv, + struct softif_neigh *new_neigh, + short vid) +{ + struct softif_neigh_vid *softif_neigh_vid; + struct softif_neigh *curr_neigh; + + softif_neigh_vid = softif_neigh_vid_get(bat_priv, vid); + if (!softif_neigh_vid) + goto out; + + spin_lock_bh(&bat_priv->softif_neigh_lock); + + if (new_neigh && !atomic_inc_not_zero(&new_neigh->refcount)) + new_neigh = NULL; + + curr_neigh = softif_neigh_vid->softif_neigh; + rcu_assign_pointer(softif_neigh_vid->softif_neigh, new_neigh); + + if ((curr_neigh) && (!new_neigh)) + bat_dbg(DBG_ROUTES, bat_priv, + "Removing mesh exit point on vid: %d (prev: %pM).\n", + vid, curr_neigh->addr); + else if ((curr_neigh) && (new_neigh)) + bat_dbg(DBG_ROUTES, bat_priv, + "Changing mesh exit point on vid: %d from %pM " + "to %pM.\n", vid, curr_neigh->addr, new_neigh->addr); + else if ((!curr_neigh) && (new_neigh)) + bat_dbg(DBG_ROUTES, bat_priv, + "Setting mesh exit point on vid: %d to %pM.\n", + vid, new_neigh->addr); + + if (curr_neigh) + softif_neigh_free_ref(curr_neigh); + + spin_unlock_bh(&bat_priv->softif_neigh_lock); + +out: + if (softif_neigh_vid) + softif_neigh_vid_free_ref(softif_neigh_vid); +} + +static void softif_neigh_vid_deselect(struct bat_priv *bat_priv, + struct softif_neigh_vid *softif_neigh_vid) +{ + struct softif_neigh *curr_neigh; + struct softif_neigh *softif_neigh = NULL, *softif_neigh_tmp; + struct hard_iface *primary_if = NULL; + struct hlist_node *node; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + /* find new softif_neigh immediately to avoid temporary loops */ + rcu_read_lock(); + curr_neigh = rcu_dereference(softif_neigh_vid->softif_neigh); + + hlist_for_each_entry_rcu(softif_neigh_tmp, node, + &softif_neigh_vid->softif_neigh_list, + list) { + if (softif_neigh_tmp == curr_neigh) + continue; + + /* we got a neighbor but its mac is 'bigger' than ours */ + if (memcmp(primary_if->net_dev->dev_addr, + softif_neigh_tmp->addr, ETH_ALEN) < 0) + continue; + + if (!atomic_inc_not_zero(&softif_neigh_tmp->refcount)) + continue; + + softif_neigh = softif_neigh_tmp; + goto unlock; + } + +unlock: + rcu_read_unlock(); +out: + softif_neigh_vid_select(bat_priv, softif_neigh, softif_neigh_vid->vid); + + if (primary_if) + hardif_free_ref(primary_if); + if (softif_neigh) + softif_neigh_free_ref(softif_neigh); +} + int softif_neigh_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; struct bat_priv *bat_priv = netdev_priv(net_dev); + struct softif_neigh_vid *softif_neigh_vid; struct softif_neigh *softif_neigh; - struct hlist_node *node; + struct hard_iface *primary_if; + struct hlist_node *node, *node_tmp; + struct softif_neigh *curr_softif_neigh; + int ret = 0, last_seen_secs, last_seen_msecs; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) { + ret = seq_printf(seq, "BATMAN mesh %s disabled - " + "please specify interfaces to enable it\n", + net_dev->name); + goto out; + } - if (!bat_priv->primary_if) { - return seq_printf(seq, "BATMAN mesh %s disabled - " - "please specify interfaces to enable it\n", - net_dev->name); + if (primary_if->if_status != IF_ACTIVE) { + ret = seq_printf(seq, "BATMAN mesh %s " + "disabled - primary interface not active\n", + net_dev->name); + goto out; } seq_printf(seq, "Softif neighbor list (%s)\n", net_dev->name); rcu_read_lock(); - hlist_for_each_entry_rcu(softif_neigh, node, - &bat_priv->softif_neigh_list, list) - seq_printf(seq, "%s %pM (vid: %d)\n", - bat_priv->softif_neigh == softif_neigh - ? "=>" : " ", softif_neigh->addr, - softif_neigh->vid); + hlist_for_each_entry_rcu(softif_neigh_vid, node, + &bat_priv->softif_neigh_vids, list) { + seq_printf(seq, " %-15s %s on vid: %d\n", + "Originator", "last-seen", softif_neigh_vid->vid); + + curr_softif_neigh = softif_neigh_get_selected(softif_neigh_vid); + + hlist_for_each_entry_rcu(softif_neigh, node_tmp, + &softif_neigh_vid->softif_neigh_list, + list) { + last_seen_secs = jiffies_to_msecs(jiffies - + softif_neigh->last_seen) / 1000; + last_seen_msecs = jiffies_to_msecs(jiffies - + softif_neigh->last_seen) % 1000; + seq_printf(seq, "%s %pM %3i.%03is\n", + curr_softif_neigh == softif_neigh + ? "=>" : " ", softif_neigh->addr, + last_seen_secs, last_seen_msecs); + } + + if (curr_softif_neigh) + softif_neigh_free_ref(curr_softif_neigh); + + seq_printf(seq, "\n"); + } rcu_read_unlock(); - return 0; +out: + if (primary_if) + hardif_free_ref(primary_if); + return ret; +} + +void softif_neigh_purge(struct bat_priv *bat_priv) +{ + struct softif_neigh *softif_neigh, *curr_softif_neigh; + struct softif_neigh_vid *softif_neigh_vid; + struct hlist_node *node, *node_tmp, *node_tmp2; + char do_deselect; + + rcu_read_lock(); + hlist_for_each_entry_rcu(softif_neigh_vid, node, + &bat_priv->softif_neigh_vids, list) { + if (!atomic_inc_not_zero(&softif_neigh_vid->refcount)) + continue; + + curr_softif_neigh = softif_neigh_get_selected(softif_neigh_vid); + do_deselect = 0; + + spin_lock_bh(&bat_priv->softif_neigh_lock); + hlist_for_each_entry_safe(softif_neigh, node_tmp, node_tmp2, + &softif_neigh_vid->softif_neigh_list, + list) { + if ((!time_after(jiffies, softif_neigh->last_seen + + msecs_to_jiffies(SOFTIF_NEIGH_TIMEOUT))) && + (atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE)) + continue; + + if (curr_softif_neigh == softif_neigh) { + bat_dbg(DBG_ROUTES, bat_priv, + "Current mesh exit point on vid: %d " + "'%pM' vanished.\n", + softif_neigh_vid->vid, + softif_neigh->addr); + do_deselect = 1; + } + + hlist_del_rcu(&softif_neigh->list); + softif_neigh_free_ref(softif_neigh); + } + spin_unlock_bh(&bat_priv->softif_neigh_lock); + + /* soft_neigh_vid_deselect() needs to acquire the + * softif_neigh_lock */ + if (do_deselect) + softif_neigh_vid_deselect(bat_priv, softif_neigh_vid); + + if (curr_softif_neigh) + softif_neigh_free_ref(curr_softif_neigh); + + softif_neigh_vid_free_ref(softif_neigh_vid); + } + rcu_read_unlock(); + + spin_lock_bh(&bat_priv->softif_neigh_vid_lock); + hlist_for_each_entry_safe(softif_neigh_vid, node, node_tmp, + &bat_priv->softif_neigh_vids, list) { + if (!hlist_empty(&softif_neigh_vid->softif_neigh_list)) + continue; + + hlist_del_rcu(&softif_neigh_vid->list); + softif_neigh_vid_free_ref(softif_neigh_vid); + } + spin_unlock_bh(&bat_priv->softif_neigh_vid_lock); + } static void softif_batman_recv(struct sk_buff *skb, struct net_device *dev, @@ -198,7 +445,9 @@ static void softif_batman_recv(struct sk_buff *skb, struct net_device *dev, struct bat_priv *bat_priv = netdev_priv(dev); struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batman_packet *batman_packet; - struct softif_neigh *softif_neigh, *softif_neigh_tmp; + struct softif_neigh *softif_neigh = NULL; + struct hard_iface *primary_if = NULL; + struct softif_neigh *curr_softif_neigh = NULL; if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) batman_packet = (struct batman_packet *) @@ -207,63 +456,52 @@ static void softif_batman_recv(struct sk_buff *skb, struct net_device *dev, batman_packet = (struct batman_packet *)(skb->data + ETH_HLEN); if (batman_packet->version != COMPAT_VERSION) - goto err; + goto out; if (batman_packet->packet_type != BAT_PACKET) - goto err; + goto out; if (!(batman_packet->flags & PRIMARIES_FIRST_HOP)) - goto err; + goto out; if (is_my_mac(batman_packet->orig)) - goto err; + goto out; softif_neigh = softif_neigh_get(bat_priv, batman_packet->orig, vid); - if (!softif_neigh) - goto err; + goto out; + + curr_softif_neigh = softif_neigh_vid_get_selected(bat_priv, vid); + if (curr_softif_neigh == softif_neigh) + goto out; - if (bat_priv->softif_neigh == softif_neigh) + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) goto out; /* we got a neighbor but its mac is 'bigger' than ours */ - if (memcmp(bat_priv->primary_if->net_dev->dev_addr, + if (memcmp(primary_if->net_dev->dev_addr, softif_neigh->addr, ETH_ALEN) < 0) goto out; - /* switch to new 'smallest neighbor' */ - if ((bat_priv->softif_neigh) && - (memcmp(softif_neigh->addr, bat_priv->softif_neigh->addr, - ETH_ALEN) < 0)) { - bat_dbg(DBG_ROUTES, bat_priv, - "Changing mesh exit point from %pM (vid: %d) " - "to %pM (vid: %d).\n", - bat_priv->softif_neigh->addr, - bat_priv->softif_neigh->vid, - softif_neigh->addr, softif_neigh->vid); - softif_neigh_tmp = bat_priv->softif_neigh; - bat_priv->softif_neigh = softif_neigh; - softif_neigh_free_ref(softif_neigh_tmp); - /* we need to hold the additional reference */ - goto err; - } - /* close own batX device and use softif_neigh as exit node */ - if ((!bat_priv->softif_neigh) && - (memcmp(softif_neigh->addr, - bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN) < 0)) { - bat_dbg(DBG_ROUTES, bat_priv, - "Setting mesh exit point to %pM (vid: %d).\n", - softif_neigh->addr, softif_neigh->vid); - bat_priv->softif_neigh = softif_neigh; - /* we need to hold the additional reference */ - goto err; + if (!curr_softif_neigh) { + softif_neigh_vid_select(bat_priv, softif_neigh, vid); + goto out; } + /* switch to new 'smallest neighbor' */ + if (memcmp(softif_neigh->addr, curr_softif_neigh->addr, ETH_ALEN) < 0) + softif_neigh_vid_select(bat_priv, softif_neigh, vid); + out: - softif_neigh_free_ref(softif_neigh); -err: kfree_skb(skb); + if (softif_neigh) + softif_neigh_free_ref(softif_neigh); + if (curr_softif_neigh) + softif_neigh_free_ref(curr_softif_neigh); + if (primary_if) + hardif_free_ref(primary_if); return; } @@ -293,11 +531,11 @@ static int interface_set_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - /* only modify hna-table if it has been initialised before */ + /* only modify transtable if it has been initialised before */ if (atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE) { - hna_local_remove(bat_priv, dev->dev_addr, + tt_local_remove(bat_priv, dev->dev_addr, "mac address changed"); - hna_local_add(dev, addr->sa_data); + tt_local_add(dev, addr->sa_data); } memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); @@ -319,8 +557,10 @@ int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct bat_priv *bat_priv = netdev_priv(soft_iface); + struct hard_iface *primary_if = NULL; struct bcast_packet *bcast_packet; struct vlan_ethhdr *vhdr; + struct softif_neigh *curr_softif_neigh = NULL; int data_len = skb->len, ret; short vid = -1; bool do_bcast = false; @@ -348,11 +588,12 @@ int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) * if we have a another chosen mesh exit node in range * it will transport the packets to the mesh */ - if ((bat_priv->softif_neigh) && (bat_priv->softif_neigh->vid == vid)) + curr_softif_neigh = softif_neigh_vid_get_selected(bat_priv, vid); + if (curr_softif_neigh) goto dropped; /* TODO: check this for locks */ - hna_local_add(soft_iface, ethhdr->h_source); + tt_local_add(soft_iface, ethhdr->h_source); if (is_multicast_ether_addr(ethhdr->h_dest)) { ret = gw_is_target(bat_priv, skb); @@ -366,7 +607,8 @@ int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) /* ethernet packet should be broadcasted */ if (do_bcast) { - if (!bat_priv->primary_if) + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) goto dropped; if (my_skb_head_push(skb, sizeof(struct bcast_packet)) < 0) @@ -382,7 +624,7 @@ int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) /* hw address of first interface is the orig mac because only * this mac is known throughout the mesh */ memcpy(bcast_packet->orig, - bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN); + primary_if->net_dev->dev_addr, ETH_ALEN); /* set broadcast sequence number */ bcast_packet->seqno = @@ -410,6 +652,10 @@ dropped: dropped_freed: bat_priv->stats.tx_dropped++; end: + if (curr_softif_neigh) + softif_neigh_free_ref(curr_softif_neigh); + if (primary_if) + hardif_free_ref(primary_if); return NETDEV_TX_OK; } @@ -421,6 +667,7 @@ void interface_rx(struct net_device *soft_iface, struct unicast_packet *unicast_packet; struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; + struct softif_neigh *curr_softif_neigh = NULL; short vid = -1; int ret; @@ -450,7 +697,8 @@ void interface_rx(struct net_device *soft_iface, * if we have a another chosen mesh exit node in range * it will transport the packets to the non-mesh network */ - if ((bat_priv->softif_neigh) && (bat_priv->softif_neigh->vid == vid)) { + curr_softif_neigh = softif_neigh_vid_get_selected(bat_priv, vid); + if (curr_softif_neigh) { skb_push(skb, hdr_size); unicast_packet = (struct unicast_packet *)skb->data; @@ -461,7 +709,7 @@ void interface_rx(struct net_device *soft_iface, skb_reset_mac_header(skb); memcpy(unicast_packet->dest, - bat_priv->softif_neigh->addr, ETH_ALEN); + curr_softif_neigh->addr, ETH_ALEN); ret = route_unicast_packet(skb, recv_if); if (ret == NET_RX_DROP) goto dropped; @@ -474,7 +722,7 @@ void interface_rx(struct net_device *soft_iface, goto dropped; skb->protocol = eth_type_trans(skb, soft_iface); - /* should not be neccesary anymore as we use skb_pull_rcsum() + /* should not be necessary anymore as we use skb_pull_rcsum() * TODO: please verify this and remove this TODO * -- Dec 21st 2009, Simon Wunderlich */ @@ -486,11 +734,13 @@ void interface_rx(struct net_device *soft_iface, soft_iface->last_rx = jiffies; netif_rx(skb); - return; + goto out; dropped: kfree_skb(skb); out: + if (curr_softif_neigh) + softif_neigh_free_ref(curr_softif_neigh); return; } @@ -524,14 +774,15 @@ static void interface_setup(struct net_device *dev) dev->hard_start_xmit = interface_tx; #endif dev->destructor = free_netdev; + dev->tx_queue_len = 0; /** * can't call min_mtu, because the needed variables * have not been initialized yet */ dev->mtu = ETH_DATA_LEN; - dev->hard_header_len = BAT_HEADER_LEN; /* reserve more space in the - * skbuff for our header */ + /* reserve more space in the skbuff for our header */ + dev->hard_header_len = BAT_HEADER_LEN; /* generate random address */ random_ether_addr(dev_addr); @@ -556,7 +807,7 @@ struct net_device *softif_create(char *name) goto out; } - ret = register_netdev(soft_iface); + ret = register_netdevice(soft_iface); if (ret < 0) { pr_err("Unable to register the batman interface '%s': %i\n", name, ret); @@ -580,11 +831,10 @@ struct net_device *softif_create(char *name) atomic_set(&bat_priv->mesh_state, MESH_INACTIVE); atomic_set(&bat_priv->bcast_seqno, 1); - atomic_set(&bat_priv->hna_local_changed, 0); + atomic_set(&bat_priv->tt_local_changed, 0); bat_priv->primary_if = NULL; bat_priv->num_ifaces = 0; - bat_priv->softif_neigh = NULL; ret = sysfs_add_meshif(soft_iface); if (ret < 0) @@ -640,7 +890,7 @@ static int bat_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { cmd->supported = 0; cmd->advertising = 0; - cmd->speed = SPEED_10; + ethtool_cmd_speed_set(cmd, SPEED_10); cmd->duplex = DUPLEX_FULL; cmd->port = PORT_TP; cmd->phy_address = 0; @@ -675,12 +925,3 @@ static u32 bat_get_link(struct net_device *dev) return 1; } -static u32 bat_get_rx_csum(struct net_device *dev) -{ - return 0; -} - -static int bat_set_rx_csum(struct net_device *dev, u32 data) -{ - return -EOPNOTSUPP; -} diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 8d15b48d1692..7b729660cbfd 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -22,43 +22,44 @@ #include "main.h" #include "translation-table.h" #include "soft-interface.h" +#include "hard-interface.h" #include "hash.h" #include "originator.h" -static void hna_local_purge(struct work_struct *work); -static void _hna_global_del_orig(struct bat_priv *bat_priv, - struct hna_global_entry *hna_global_entry, +static void tt_local_purge(struct work_struct *work); +static void _tt_global_del_orig(struct bat_priv *bat_priv, + struct tt_global_entry *tt_global_entry, char *message); /* returns 1 if they are the same mac addr */ -static int compare_lhna(struct hlist_node *node, void *data2) +static int compare_ltt(struct hlist_node *node, void *data2) { - void *data1 = container_of(node, struct hna_local_entry, hash_entry); + void *data1 = container_of(node, struct tt_local_entry, hash_entry); return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } /* returns 1 if they are the same mac addr */ -static int compare_ghna(struct hlist_node *node, void *data2) +static int compare_gtt(struct hlist_node *node, void *data2) { - void *data1 = container_of(node, struct hna_global_entry, hash_entry); + void *data1 = container_of(node, struct tt_global_entry, hash_entry); return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } -static void hna_local_start_timer(struct bat_priv *bat_priv) +static void tt_local_start_timer(struct bat_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->hna_work, hna_local_purge); - queue_delayed_work(bat_event_workqueue, &bat_priv->hna_work, 10 * HZ); + INIT_DELAYED_WORK(&bat_priv->tt_work, tt_local_purge); + queue_delayed_work(bat_event_workqueue, &bat_priv->tt_work, 10 * HZ); } -static struct hna_local_entry *hna_local_hash_find(struct bat_priv *bat_priv, +static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv, void *data) { - struct hashtable_t *hash = bat_priv->hna_local_hash; + struct hashtable_t *hash = bat_priv->tt_local_hash; struct hlist_head *head; struct hlist_node *node; - struct hna_local_entry *hna_local_entry, *hna_local_entry_tmp = NULL; + struct tt_local_entry *tt_local_entry, *tt_local_entry_tmp = NULL; int index; if (!hash) @@ -68,26 +69,26 @@ static struct hna_local_entry *hna_local_hash_find(struct bat_priv *bat_priv, head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(hna_local_entry, node, head, hash_entry) { - if (!compare_eth(hna_local_entry, data)) + hlist_for_each_entry_rcu(tt_local_entry, node, head, hash_entry) { + if (!compare_eth(tt_local_entry, data)) continue; - hna_local_entry_tmp = hna_local_entry; + tt_local_entry_tmp = tt_local_entry; break; } rcu_read_unlock(); - return hna_local_entry_tmp; + return tt_local_entry_tmp; } -static struct hna_global_entry *hna_global_hash_find(struct bat_priv *bat_priv, +static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv, void *data) { - struct hashtable_t *hash = bat_priv->hna_global_hash; + struct hashtable_t *hash = bat_priv->tt_global_hash; struct hlist_head *head; struct hlist_node *node; - struct hna_global_entry *hna_global_entry; - struct hna_global_entry *hna_global_entry_tmp = NULL; + struct tt_global_entry *tt_global_entry; + struct tt_global_entry *tt_global_entry_tmp = NULL; int index; if (!hash) @@ -97,125 +98,125 @@ static struct hna_global_entry *hna_global_hash_find(struct bat_priv *bat_priv, head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(hna_global_entry, node, head, hash_entry) { - if (!compare_eth(hna_global_entry, data)) + hlist_for_each_entry_rcu(tt_global_entry, node, head, hash_entry) { + if (!compare_eth(tt_global_entry, data)) continue; - hna_global_entry_tmp = hna_global_entry; + tt_global_entry_tmp = tt_global_entry; break; } rcu_read_unlock(); - return hna_global_entry_tmp; + return tt_global_entry_tmp; } -int hna_local_init(struct bat_priv *bat_priv) +int tt_local_init(struct bat_priv *bat_priv) { - if (bat_priv->hna_local_hash) + if (bat_priv->tt_local_hash) return 1; - bat_priv->hna_local_hash = hash_new(1024); + bat_priv->tt_local_hash = hash_new(1024); - if (!bat_priv->hna_local_hash) + if (!bat_priv->tt_local_hash) return 0; - atomic_set(&bat_priv->hna_local_changed, 0); - hna_local_start_timer(bat_priv); + atomic_set(&bat_priv->tt_local_changed, 0); + tt_local_start_timer(bat_priv); return 1; } -void hna_local_add(struct net_device *soft_iface, uint8_t *addr) +void tt_local_add(struct net_device *soft_iface, uint8_t *addr) { struct bat_priv *bat_priv = netdev_priv(soft_iface); - struct hna_local_entry *hna_local_entry; - struct hna_global_entry *hna_global_entry; + struct tt_local_entry *tt_local_entry; + struct tt_global_entry *tt_global_entry; int required_bytes; - spin_lock_bh(&bat_priv->hna_lhash_lock); - hna_local_entry = hna_local_hash_find(bat_priv, addr); - spin_unlock_bh(&bat_priv->hna_lhash_lock); + spin_lock_bh(&bat_priv->tt_lhash_lock); + tt_local_entry = tt_local_hash_find(bat_priv, addr); + spin_unlock_bh(&bat_priv->tt_lhash_lock); - if (hna_local_entry) { - hna_local_entry->last_seen = jiffies; + if (tt_local_entry) { + tt_local_entry->last_seen = jiffies; return; } /* only announce as many hosts as possible in the batman-packet and - space in batman_packet->num_hna That also should give a limit to + space in batman_packet->num_tt That also should give a limit to MAC-flooding. */ - required_bytes = (bat_priv->num_local_hna + 1) * ETH_ALEN; + required_bytes = (bat_priv->num_local_tt + 1) * ETH_ALEN; required_bytes += BAT_PACKET_LEN; if ((required_bytes > ETH_DATA_LEN) || (atomic_read(&bat_priv->aggregated_ogms) && required_bytes > MAX_AGGREGATION_BYTES) || - (bat_priv->num_local_hna + 1 > 255)) { + (bat_priv->num_local_tt + 1 > 255)) { bat_dbg(DBG_ROUTES, bat_priv, - "Can't add new local hna entry (%pM): " - "number of local hna entries exceeds packet size\n", + "Can't add new local tt entry (%pM): " + "number of local tt entries exceeds packet size\n", addr); return; } bat_dbg(DBG_ROUTES, bat_priv, - "Creating new local hna entry: %pM\n", addr); + "Creating new local tt entry: %pM\n", addr); - hna_local_entry = kmalloc(sizeof(struct hna_local_entry), GFP_ATOMIC); - if (!hna_local_entry) + tt_local_entry = kmalloc(sizeof(struct tt_local_entry), GFP_ATOMIC); + if (!tt_local_entry) return; - memcpy(hna_local_entry->addr, addr, ETH_ALEN); - hna_local_entry->last_seen = jiffies; + memcpy(tt_local_entry->addr, addr, ETH_ALEN); + tt_local_entry->last_seen = jiffies; /* the batman interface mac address should never be purged */ if (compare_eth(addr, soft_iface->dev_addr)) - hna_local_entry->never_purge = 1; + tt_local_entry->never_purge = 1; else - hna_local_entry->never_purge = 0; + tt_local_entry->never_purge = 0; - spin_lock_bh(&bat_priv->hna_lhash_lock); + spin_lock_bh(&bat_priv->tt_lhash_lock); - hash_add(bat_priv->hna_local_hash, compare_lhna, choose_orig, - hna_local_entry, &hna_local_entry->hash_entry); - bat_priv->num_local_hna++; - atomic_set(&bat_priv->hna_local_changed, 1); + hash_add(bat_priv->tt_local_hash, compare_ltt, choose_orig, + tt_local_entry, &tt_local_entry->hash_entry); + bat_priv->num_local_tt++; + atomic_set(&bat_priv->tt_local_changed, 1); - spin_unlock_bh(&bat_priv->hna_lhash_lock); + spin_unlock_bh(&bat_priv->tt_lhash_lock); /* remove address from global hash if present */ - spin_lock_bh(&bat_priv->hna_ghash_lock); + spin_lock_bh(&bat_priv->tt_ghash_lock); - hna_global_entry = hna_global_hash_find(bat_priv, addr); + tt_global_entry = tt_global_hash_find(bat_priv, addr); - if (hna_global_entry) - _hna_global_del_orig(bat_priv, hna_global_entry, - "local hna received"); + if (tt_global_entry) + _tt_global_del_orig(bat_priv, tt_global_entry, + "local tt received"); - spin_unlock_bh(&bat_priv->hna_ghash_lock); + spin_unlock_bh(&bat_priv->tt_ghash_lock); } -int hna_local_fill_buffer(struct bat_priv *bat_priv, +int tt_local_fill_buffer(struct bat_priv *bat_priv, unsigned char *buff, int buff_len) { - struct hashtable_t *hash = bat_priv->hna_local_hash; - struct hna_local_entry *hna_local_entry; + struct hashtable_t *hash = bat_priv->tt_local_hash; + struct tt_local_entry *tt_local_entry; struct hlist_node *node; struct hlist_head *head; int i, count = 0; - spin_lock_bh(&bat_priv->hna_lhash_lock); + spin_lock_bh(&bat_priv->tt_lhash_lock); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(hna_local_entry, node, + hlist_for_each_entry_rcu(tt_local_entry, node, head, hash_entry) { if (buff_len < (count + 1) * ETH_ALEN) break; - memcpy(buff + (count * ETH_ALEN), hna_local_entry->addr, + memcpy(buff + (count * ETH_ALEN), tt_local_entry->addr, ETH_ALEN); count++; @@ -223,37 +224,47 @@ int hna_local_fill_buffer(struct bat_priv *bat_priv, rcu_read_unlock(); } - /* if we did not get all new local hnas see you next time ;-) */ - if (count == bat_priv->num_local_hna) - atomic_set(&bat_priv->hna_local_changed, 0); + /* if we did not get all new local tts see you next time ;-) */ + if (count == bat_priv->num_local_tt) + atomic_set(&bat_priv->tt_local_changed, 0); - spin_unlock_bh(&bat_priv->hna_lhash_lock); + spin_unlock_bh(&bat_priv->tt_lhash_lock); return count; } -int hna_local_seq_print_text(struct seq_file *seq, void *offset) +int tt_local_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; struct bat_priv *bat_priv = netdev_priv(net_dev); - struct hashtable_t *hash = bat_priv->hna_local_hash; - struct hna_local_entry *hna_local_entry; + struct hashtable_t *hash = bat_priv->tt_local_hash; + struct tt_local_entry *tt_local_entry; + struct hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; size_t buf_size, pos; char *buff; - int i; + int i, ret = 0; - if (!bat_priv->primary_if) { - return seq_printf(seq, "BATMAN mesh %s disabled - " - "please specify interfaces to enable it\n", - net_dev->name); + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) { + ret = seq_printf(seq, "BATMAN mesh %s disabled - " + "please specify interfaces to enable it\n", + net_dev->name); + goto out; + } + + if (primary_if->if_status != IF_ACTIVE) { + ret = seq_printf(seq, "BATMAN mesh %s disabled - " + "primary interface not active\n", + net_dev->name); + goto out; } seq_printf(seq, "Locally retrieved addresses (from %s) " - "announced via HNA:\n", + "announced via TT:\n", net_dev->name); - spin_lock_bh(&bat_priv->hna_lhash_lock); + spin_lock_bh(&bat_priv->tt_lhash_lock); buf_size = 1; /* Estimate length for: " * xx:xx:xx:xx:xx:xx\n" */ @@ -268,8 +279,9 @@ int hna_local_seq_print_text(struct seq_file *seq, void *offset) buff = kmalloc(buf_size, GFP_ATOMIC); if (!buff) { - spin_unlock_bh(&bat_priv->hna_lhash_lock); - return -ENOMEM; + spin_unlock_bh(&bat_priv->tt_lhash_lock); + ret = -ENOMEM; + goto out; } buff[0] = '\0'; @@ -279,211 +291,225 @@ int hna_local_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(hna_local_entry, node, + hlist_for_each_entry_rcu(tt_local_entry, node, head, hash_entry) { pos += snprintf(buff + pos, 22, " * %pM\n", - hna_local_entry->addr); + tt_local_entry->addr); } rcu_read_unlock(); } - spin_unlock_bh(&bat_priv->hna_lhash_lock); + spin_unlock_bh(&bat_priv->tt_lhash_lock); seq_printf(seq, "%s", buff); kfree(buff); - return 0; +out: + if (primary_if) + hardif_free_ref(primary_if); + return ret; } -static void _hna_local_del(struct hlist_node *node, void *arg) +static void _tt_local_del(struct hlist_node *node, void *arg) { struct bat_priv *bat_priv = (struct bat_priv *)arg; - void *data = container_of(node, struct hna_local_entry, hash_entry); + void *data = container_of(node, struct tt_local_entry, hash_entry); kfree(data); - bat_priv->num_local_hna--; - atomic_set(&bat_priv->hna_local_changed, 1); + bat_priv->num_local_tt--; + atomic_set(&bat_priv->tt_local_changed, 1); } -static void hna_local_del(struct bat_priv *bat_priv, - struct hna_local_entry *hna_local_entry, +static void tt_local_del(struct bat_priv *bat_priv, + struct tt_local_entry *tt_local_entry, char *message) { - bat_dbg(DBG_ROUTES, bat_priv, "Deleting local hna entry (%pM): %s\n", - hna_local_entry->addr, message); + bat_dbg(DBG_ROUTES, bat_priv, "Deleting local tt entry (%pM): %s\n", + tt_local_entry->addr, message); - hash_remove(bat_priv->hna_local_hash, compare_lhna, choose_orig, - hna_local_entry->addr); - _hna_local_del(&hna_local_entry->hash_entry, bat_priv); + hash_remove(bat_priv->tt_local_hash, compare_ltt, choose_orig, + tt_local_entry->addr); + _tt_local_del(&tt_local_entry->hash_entry, bat_priv); } -void hna_local_remove(struct bat_priv *bat_priv, +void tt_local_remove(struct bat_priv *bat_priv, uint8_t *addr, char *message) { - struct hna_local_entry *hna_local_entry; + struct tt_local_entry *tt_local_entry; - spin_lock_bh(&bat_priv->hna_lhash_lock); + spin_lock_bh(&bat_priv->tt_lhash_lock); - hna_local_entry = hna_local_hash_find(bat_priv, addr); + tt_local_entry = tt_local_hash_find(bat_priv, addr); - if (hna_local_entry) - hna_local_del(bat_priv, hna_local_entry, message); + if (tt_local_entry) + tt_local_del(bat_priv, tt_local_entry, message); - spin_unlock_bh(&bat_priv->hna_lhash_lock); + spin_unlock_bh(&bat_priv->tt_lhash_lock); } -static void hna_local_purge(struct work_struct *work) +static void tt_local_purge(struct work_struct *work) { struct delayed_work *delayed_work = container_of(work, struct delayed_work, work); struct bat_priv *bat_priv = - container_of(delayed_work, struct bat_priv, hna_work); - struct hashtable_t *hash = bat_priv->hna_local_hash; - struct hna_local_entry *hna_local_entry; + container_of(delayed_work, struct bat_priv, tt_work); + struct hashtable_t *hash = bat_priv->tt_local_hash; + struct tt_local_entry *tt_local_entry; struct hlist_node *node, *node_tmp; struct hlist_head *head; unsigned long timeout; int i; - spin_lock_bh(&bat_priv->hna_lhash_lock); + spin_lock_bh(&bat_priv->tt_lhash_lock); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; - hlist_for_each_entry_safe(hna_local_entry, node, node_tmp, + hlist_for_each_entry_safe(tt_local_entry, node, node_tmp, head, hash_entry) { - if (hna_local_entry->never_purge) + if (tt_local_entry->never_purge) continue; - timeout = hna_local_entry->last_seen; - timeout += LOCAL_HNA_TIMEOUT * HZ; + timeout = tt_local_entry->last_seen; + timeout += TT_LOCAL_TIMEOUT * HZ; if (time_before(jiffies, timeout)) continue; - hna_local_del(bat_priv, hna_local_entry, + tt_local_del(bat_priv, tt_local_entry, "address timed out"); } } - spin_unlock_bh(&bat_priv->hna_lhash_lock); - hna_local_start_timer(bat_priv); + spin_unlock_bh(&bat_priv->tt_lhash_lock); + tt_local_start_timer(bat_priv); } -void hna_local_free(struct bat_priv *bat_priv) +void tt_local_free(struct bat_priv *bat_priv) { - if (!bat_priv->hna_local_hash) + if (!bat_priv->tt_local_hash) return; - cancel_delayed_work_sync(&bat_priv->hna_work); - hash_delete(bat_priv->hna_local_hash, _hna_local_del, bat_priv); - bat_priv->hna_local_hash = NULL; + cancel_delayed_work_sync(&bat_priv->tt_work); + hash_delete(bat_priv->tt_local_hash, _tt_local_del, bat_priv); + bat_priv->tt_local_hash = NULL; } -int hna_global_init(struct bat_priv *bat_priv) +int tt_global_init(struct bat_priv *bat_priv) { - if (bat_priv->hna_global_hash) + if (bat_priv->tt_global_hash) return 1; - bat_priv->hna_global_hash = hash_new(1024); + bat_priv->tt_global_hash = hash_new(1024); - if (!bat_priv->hna_global_hash) + if (!bat_priv->tt_global_hash) return 0; return 1; } -void hna_global_add_orig(struct bat_priv *bat_priv, +void tt_global_add_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, - unsigned char *hna_buff, int hna_buff_len) + unsigned char *tt_buff, int tt_buff_len) { - struct hna_global_entry *hna_global_entry; - struct hna_local_entry *hna_local_entry; - int hna_buff_count = 0; - unsigned char *hna_ptr; + struct tt_global_entry *tt_global_entry; + struct tt_local_entry *tt_local_entry; + int tt_buff_count = 0; + unsigned char *tt_ptr; - while ((hna_buff_count + 1) * ETH_ALEN <= hna_buff_len) { - spin_lock_bh(&bat_priv->hna_ghash_lock); + while ((tt_buff_count + 1) * ETH_ALEN <= tt_buff_len) { + spin_lock_bh(&bat_priv->tt_ghash_lock); - hna_ptr = hna_buff + (hna_buff_count * ETH_ALEN); - hna_global_entry = hna_global_hash_find(bat_priv, hna_ptr); + tt_ptr = tt_buff + (tt_buff_count * ETH_ALEN); + tt_global_entry = tt_global_hash_find(bat_priv, tt_ptr); - if (!hna_global_entry) { - spin_unlock_bh(&bat_priv->hna_ghash_lock); + if (!tt_global_entry) { + spin_unlock_bh(&bat_priv->tt_ghash_lock); - hna_global_entry = - kmalloc(sizeof(struct hna_global_entry), + tt_global_entry = + kmalloc(sizeof(struct tt_global_entry), GFP_ATOMIC); - if (!hna_global_entry) + if (!tt_global_entry) break; - memcpy(hna_global_entry->addr, hna_ptr, ETH_ALEN); + memcpy(tt_global_entry->addr, tt_ptr, ETH_ALEN); bat_dbg(DBG_ROUTES, bat_priv, - "Creating new global hna entry: " + "Creating new global tt entry: " "%pM (via %pM)\n", - hna_global_entry->addr, orig_node->orig); + tt_global_entry->addr, orig_node->orig); - spin_lock_bh(&bat_priv->hna_ghash_lock); - hash_add(bat_priv->hna_global_hash, compare_ghna, - choose_orig, hna_global_entry, - &hna_global_entry->hash_entry); + spin_lock_bh(&bat_priv->tt_ghash_lock); + hash_add(bat_priv->tt_global_hash, compare_gtt, + choose_orig, tt_global_entry, + &tt_global_entry->hash_entry); } - hna_global_entry->orig_node = orig_node; - spin_unlock_bh(&bat_priv->hna_ghash_lock); + tt_global_entry->orig_node = orig_node; + spin_unlock_bh(&bat_priv->tt_ghash_lock); /* remove address from local hash if present */ - spin_lock_bh(&bat_priv->hna_lhash_lock); + spin_lock_bh(&bat_priv->tt_lhash_lock); - hna_ptr = hna_buff + (hna_buff_count * ETH_ALEN); - hna_local_entry = hna_local_hash_find(bat_priv, hna_ptr); + tt_ptr = tt_buff + (tt_buff_count * ETH_ALEN); + tt_local_entry = tt_local_hash_find(bat_priv, tt_ptr); - if (hna_local_entry) - hna_local_del(bat_priv, hna_local_entry, - "global hna received"); + if (tt_local_entry) + tt_local_del(bat_priv, tt_local_entry, + "global tt received"); - spin_unlock_bh(&bat_priv->hna_lhash_lock); + spin_unlock_bh(&bat_priv->tt_lhash_lock); - hna_buff_count++; + tt_buff_count++; } /* initialize, and overwrite if malloc succeeds */ - orig_node->hna_buff = NULL; - orig_node->hna_buff_len = 0; - - if (hna_buff_len > 0) { - orig_node->hna_buff = kmalloc(hna_buff_len, GFP_ATOMIC); - if (orig_node->hna_buff) { - memcpy(orig_node->hna_buff, hna_buff, hna_buff_len); - orig_node->hna_buff_len = hna_buff_len; + orig_node->tt_buff = NULL; + orig_node->tt_buff_len = 0; + + if (tt_buff_len > 0) { + orig_node->tt_buff = kmalloc(tt_buff_len, GFP_ATOMIC); + if (orig_node->tt_buff) { + memcpy(orig_node->tt_buff, tt_buff, tt_buff_len); + orig_node->tt_buff_len = tt_buff_len; } } } -int hna_global_seq_print_text(struct seq_file *seq, void *offset) +int tt_global_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; struct bat_priv *bat_priv = netdev_priv(net_dev); - struct hashtable_t *hash = bat_priv->hna_global_hash; - struct hna_global_entry *hna_global_entry; + struct hashtable_t *hash = bat_priv->tt_global_hash; + struct tt_global_entry *tt_global_entry; + struct hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; size_t buf_size, pos; char *buff; - int i; + int i, ret = 0; - if (!bat_priv->primary_if) { - return seq_printf(seq, "BATMAN mesh %s disabled - " - "please specify interfaces to enable it\n", - net_dev->name); + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) { + ret = seq_printf(seq, "BATMAN mesh %s disabled - please " + "specify interfaces to enable it\n", + net_dev->name); + goto out; } - seq_printf(seq, "Globally announced HNAs received via the mesh %s\n", + if (primary_if->if_status != IF_ACTIVE) { + ret = seq_printf(seq, "BATMAN mesh %s disabled - " + "primary interface not active\n", + net_dev->name); + goto out; + } + + seq_printf(seq, + "Globally announced TT entries received via the mesh %s\n", net_dev->name); - spin_lock_bh(&bat_priv->hna_ghash_lock); + spin_lock_bh(&bat_priv->tt_ghash_lock); buf_size = 1; /* Estimate length for: " * xx:xx:xx:xx:xx:xx via xx:xx:xx:xx:xx:xx\n"*/ @@ -498,8 +524,9 @@ int hna_global_seq_print_text(struct seq_file *seq, void *offset) buff = kmalloc(buf_size, GFP_ATOMIC); if (!buff) { - spin_unlock_bh(&bat_priv->hna_ghash_lock); - return -ENOMEM; + spin_unlock_bh(&bat_priv->tt_ghash_lock); + ret = -ENOMEM; + goto out; } buff[0] = '\0'; pos = 0; @@ -508,101 +535,104 @@ int hna_global_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(hna_global_entry, node, + hlist_for_each_entry_rcu(tt_global_entry, node, head, hash_entry) { pos += snprintf(buff + pos, 44, " * %pM via %pM\n", - hna_global_entry->addr, - hna_global_entry->orig_node->orig); + tt_global_entry->addr, + tt_global_entry->orig_node->orig); } rcu_read_unlock(); } - spin_unlock_bh(&bat_priv->hna_ghash_lock); + spin_unlock_bh(&bat_priv->tt_ghash_lock); seq_printf(seq, "%s", buff); kfree(buff); - return 0; +out: + if (primary_if) + hardif_free_ref(primary_if); + return ret; } -static void _hna_global_del_orig(struct bat_priv *bat_priv, - struct hna_global_entry *hna_global_entry, +static void _tt_global_del_orig(struct bat_priv *bat_priv, + struct tt_global_entry *tt_global_entry, char *message) { bat_dbg(DBG_ROUTES, bat_priv, - "Deleting global hna entry %pM (via %pM): %s\n", - hna_global_entry->addr, hna_global_entry->orig_node->orig, + "Deleting global tt entry %pM (via %pM): %s\n", + tt_global_entry->addr, tt_global_entry->orig_node->orig, message); - hash_remove(bat_priv->hna_global_hash, compare_ghna, choose_orig, - hna_global_entry->addr); - kfree(hna_global_entry); + hash_remove(bat_priv->tt_global_hash, compare_gtt, choose_orig, + tt_global_entry->addr); + kfree(tt_global_entry); } -void hna_global_del_orig(struct bat_priv *bat_priv, +void tt_global_del_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, char *message) { - struct hna_global_entry *hna_global_entry; - int hna_buff_count = 0; - unsigned char *hna_ptr; + struct tt_global_entry *tt_global_entry; + int tt_buff_count = 0; + unsigned char *tt_ptr; - if (orig_node->hna_buff_len == 0) + if (orig_node->tt_buff_len == 0) return; - spin_lock_bh(&bat_priv->hna_ghash_lock); + spin_lock_bh(&bat_priv->tt_ghash_lock); - while ((hna_buff_count + 1) * ETH_ALEN <= orig_node->hna_buff_len) { - hna_ptr = orig_node->hna_buff + (hna_buff_count * ETH_ALEN); - hna_global_entry = hna_global_hash_find(bat_priv, hna_ptr); + while ((tt_buff_count + 1) * ETH_ALEN <= orig_node->tt_buff_len) { + tt_ptr = orig_node->tt_buff + (tt_buff_count * ETH_ALEN); + tt_global_entry = tt_global_hash_find(bat_priv, tt_ptr); - if ((hna_global_entry) && - (hna_global_entry->orig_node == orig_node)) - _hna_global_del_orig(bat_priv, hna_global_entry, + if ((tt_global_entry) && + (tt_global_entry->orig_node == orig_node)) + _tt_global_del_orig(bat_priv, tt_global_entry, message); - hna_buff_count++; + tt_buff_count++; } - spin_unlock_bh(&bat_priv->hna_ghash_lock); + spin_unlock_bh(&bat_priv->tt_ghash_lock); - orig_node->hna_buff_len = 0; - kfree(orig_node->hna_buff); - orig_node->hna_buff = NULL; + orig_node->tt_buff_len = 0; + kfree(orig_node->tt_buff); + orig_node->tt_buff = NULL; } -static void hna_global_del(struct hlist_node *node, void *arg) +static void tt_global_del(struct hlist_node *node, void *arg) { - void *data = container_of(node, struct hna_global_entry, hash_entry); + void *data = container_of(node, struct tt_global_entry, hash_entry); kfree(data); } -void hna_global_free(struct bat_priv *bat_priv) +void tt_global_free(struct bat_priv *bat_priv) { - if (!bat_priv->hna_global_hash) + if (!bat_priv->tt_global_hash) return; - hash_delete(bat_priv->hna_global_hash, hna_global_del, NULL); - bat_priv->hna_global_hash = NULL; + hash_delete(bat_priv->tt_global_hash, tt_global_del, NULL); + bat_priv->tt_global_hash = NULL; } struct orig_node *transtable_search(struct bat_priv *bat_priv, uint8_t *addr) { - struct hna_global_entry *hna_global_entry; + struct tt_global_entry *tt_global_entry; struct orig_node *orig_node = NULL; - spin_lock_bh(&bat_priv->hna_ghash_lock); - hna_global_entry = hna_global_hash_find(bat_priv, addr); + spin_lock_bh(&bat_priv->tt_ghash_lock); + tt_global_entry = tt_global_hash_find(bat_priv, addr); - if (!hna_global_entry) + if (!tt_global_entry) goto out; - if (!atomic_inc_not_zero(&hna_global_entry->orig_node->refcount)) + if (!atomic_inc_not_zero(&tt_global_entry->orig_node->refcount)) goto out; - orig_node = hna_global_entry->orig_node; + orig_node = tt_global_entry->orig_node; out: - spin_unlock_bh(&bat_priv->hna_ghash_lock); + spin_unlock_bh(&bat_priv->tt_ghash_lock); return orig_node; } diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index f19931ca1457..46152c38cc95 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -22,22 +22,22 @@ #ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ #define _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ -int hna_local_init(struct bat_priv *bat_priv); -void hna_local_add(struct net_device *soft_iface, uint8_t *addr); -void hna_local_remove(struct bat_priv *bat_priv, +int tt_local_init(struct bat_priv *bat_priv); +void tt_local_add(struct net_device *soft_iface, uint8_t *addr); +void tt_local_remove(struct bat_priv *bat_priv, uint8_t *addr, char *message); -int hna_local_fill_buffer(struct bat_priv *bat_priv, +int tt_local_fill_buffer(struct bat_priv *bat_priv, unsigned char *buff, int buff_len); -int hna_local_seq_print_text(struct seq_file *seq, void *offset); -void hna_local_free(struct bat_priv *bat_priv); -int hna_global_init(struct bat_priv *bat_priv); -void hna_global_add_orig(struct bat_priv *bat_priv, +int tt_local_seq_print_text(struct seq_file *seq, void *offset); +void tt_local_free(struct bat_priv *bat_priv); +int tt_global_init(struct bat_priv *bat_priv); +void tt_global_add_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, - unsigned char *hna_buff, int hna_buff_len); -int hna_global_seq_print_text(struct seq_file *seq, void *offset); -void hna_global_del_orig(struct bat_priv *bat_priv, + unsigned char *tt_buff, int tt_buff_len); +int tt_global_seq_print_text(struct seq_file *seq, void *offset); +void tt_global_del_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, char *message); -void hna_global_free(struct bat_priv *bat_priv); +void tt_global_free(struct bat_priv *bat_priv); struct orig_node *transtable_search(struct bat_priv *bat_priv, uint8_t *addr); #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 83445cf0cc9f..fab70e8b16ee 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -67,7 +67,7 @@ struct hard_iface { struct orig_node { uint8_t orig[ETH_ALEN]; uint8_t primary_addr[ETH_ALEN]; - struct neigh_node *router; + struct neigh_node __rcu *router; /* rcu protected pointer */ unsigned long *bcast_own; uint8_t *bcast_own_sum; unsigned long last_valid; @@ -75,25 +75,25 @@ struct orig_node { unsigned long batman_seqno_reset; uint8_t gw_flags; uint8_t flags; - unsigned char *hna_buff; - int16_t hna_buff_len; + unsigned char *tt_buff; + int16_t tt_buff_len; uint32_t last_real_seqno; uint8_t last_ttl; unsigned long bcast_bits[NUM_WORDS]; uint32_t last_bcast_seqno; struct hlist_head neigh_list; struct list_head frag_list; - spinlock_t neigh_list_lock; /* protects neighbor list */ + spinlock_t neigh_list_lock; /* protects neigh_list and router */ atomic_t refcount; struct rcu_head rcu; struct hlist_node hash_entry; struct bat_priv *bat_priv; unsigned long last_frag_packet; - spinlock_t ogm_cnt_lock; /* protects: bcast_own, bcast_own_sum, - * neigh_node->real_bits, - * neigh_node->real_packet_count */ - spinlock_t bcast_seqno_lock; /* protects bcast_bits, - * last_bcast_seqno */ + /* ogm_cnt_lock protects: bcast_own, bcast_own_sum, + * neigh_node->real_bits, neigh_node->real_packet_count */ + spinlock_t ogm_cnt_lock; + /* bcast_seqno_lock protects bcast_bits, last_bcast_seqno */ + spinlock_t bcast_seqno_lock; atomic_t bond_candidates; struct list_head bond_list; }; @@ -125,6 +125,7 @@ struct neigh_node { struct rcu_head rcu; struct orig_node *orig_node; struct hard_iface *if_incoming; + spinlock_t tq_lock; /* protects: tq_recv, tq_index */ }; @@ -145,34 +146,34 @@ struct bat_priv { atomic_t bcast_queue_left; atomic_t batman_queue_left; char num_ifaces; - struct hlist_head softif_neigh_list; - struct softif_neigh *softif_neigh; struct debug_log *debug_log; - struct hard_iface *primary_if; struct kobject *mesh_obj; struct dentry *debug_dir; struct hlist_head forw_bat_list; struct hlist_head forw_bcast_list; struct hlist_head gw_list; + struct hlist_head softif_neigh_vids; struct list_head vis_send_list; struct hashtable_t *orig_hash; - struct hashtable_t *hna_local_hash; - struct hashtable_t *hna_global_hash; + struct hashtable_t *tt_local_hash; + struct hashtable_t *tt_global_hash; struct hashtable_t *vis_hash; spinlock_t forw_bat_list_lock; /* protects forw_bat_list */ spinlock_t forw_bcast_list_lock; /* protects */ - spinlock_t hna_lhash_lock; /* protects hna_local_hash */ - spinlock_t hna_ghash_lock; /* protects hna_global_hash */ + spinlock_t tt_lhash_lock; /* protects tt_local_hash */ + spinlock_t tt_ghash_lock; /* protects tt_global_hash */ spinlock_t gw_list_lock; /* protects gw_list and curr_gw */ spinlock_t vis_hash_lock; /* protects vis_hash */ spinlock_t vis_list_lock; /* protects vis_info::recv_list */ spinlock_t softif_neigh_lock; /* protects soft-interface neigh list */ - int16_t num_local_hna; - atomic_t hna_local_changed; - struct delayed_work hna_work; + spinlock_t softif_neigh_vid_lock; /* protects soft-interface vid list */ + int16_t num_local_tt; + atomic_t tt_local_changed; + struct delayed_work tt_work; struct delayed_work orig_work; struct delayed_work vis_work; struct gw_node __rcu *curr_gw; /* rcu protected pointer */ + struct hard_iface __rcu *primary_if; /* rcu protected pointer */ struct vis_info *my_vis_info; }; @@ -191,14 +192,14 @@ struct socket_packet { struct icmp_packet_rr icmp_packet; }; -struct hna_local_entry { +struct tt_local_entry { uint8_t addr[ETH_ALEN]; unsigned long last_seen; char never_purge; struct hlist_node hash_entry; }; -struct hna_global_entry { +struct tt_global_entry { uint8_t addr[ETH_ALEN]; struct orig_node *orig_node; struct hlist_node hash_entry; @@ -261,7 +262,7 @@ struct vis_info { struct vis_info_entry { uint8_t src[ETH_ALEN]; uint8_t dest[ETH_ALEN]; - uint8_t quality; /* quality = 0 means HNA */ + uint8_t quality; /* quality = 0 client */ } __packed; struct recvlist_node { @@ -269,11 +270,20 @@ struct recvlist_node { uint8_t mac[ETH_ALEN]; }; +struct softif_neigh_vid { + struct hlist_node list; + struct bat_priv *bat_priv; + short vid; + atomic_t refcount; + struct softif_neigh __rcu *softif_neigh; + struct rcu_head rcu; + struct hlist_head softif_neigh_list; +}; + struct softif_neigh { struct hlist_node list; uint8_t addr[ETH_ALEN]; unsigned long last_seen; - short vid; atomic_t refcount; struct rcu_head rcu; }; diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 19f84bd443af..19c3daf34ac6 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -221,15 +221,17 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, struct hard_iface *hard_iface, uint8_t dstaddr[]) { struct unicast_packet tmp_uc, *unicast_packet; + struct hard_iface *primary_if; struct sk_buff *frag_skb; struct unicast_frag_packet *frag1, *frag2; int uc_hdr_len = sizeof(struct unicast_packet); int ucf_hdr_len = sizeof(struct unicast_frag_packet); int data_len = skb->len - uc_hdr_len; - int large_tail = 0; + int large_tail = 0, ret = NET_RX_DROP; uint16_t seqno; - if (!bat_priv->primary_if) + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) goto dropped; frag_skb = dev_alloc_skb(data_len - (data_len / 2) + ucf_hdr_len); @@ -254,7 +256,7 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, frag1->version = COMPAT_VERSION; frag1->packet_type = BAT_UNICAST_FRAG; - memcpy(frag1->orig, bat_priv->primary_if->net_dev->dev_addr, ETH_ALEN); + memcpy(frag1->orig, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(frag2, frag1, sizeof(struct unicast_frag_packet)); if (data_len & 1) @@ -269,13 +271,17 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, send_skb_packet(skb, hard_iface, dstaddr); send_skb_packet(frag_skb, hard_iface, dstaddr); - return NET_RX_SUCCESS; + ret = NET_RX_SUCCESS; + goto out; drop_frag: kfree_skb(frag_skb); dropped: kfree_skb(skb); - return NET_RX_DROP; +out: + if (primary_if) + hardif_free_ref(primary_if); + return ret; } int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) @@ -289,12 +295,12 @@ int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) /* get routing information */ if (is_multicast_ether_addr(ethhdr->h_dest)) { - orig_node = (struct orig_node *)gw_get_selected(bat_priv); + orig_node = (struct orig_node *)gw_get_selected_orig(bat_priv); if (orig_node) goto find_router; } - /* check for hna host - increases orig_node refcount */ + /* check for tt host - increases orig_node refcount */ orig_node = transtable_search(bat_priv, ethhdr->h_dest); find_router: diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index f90212f42082..c39f20cc1ba6 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -194,7 +194,7 @@ static ssize_t vis_data_read_entry(char *buff, struct vis_info_entry *entry, { /* maximal length: max(4+17+2, 3+17+1+3+2) == 26 */ if (primary && entry->quality == 0) - return sprintf(buff, "HNA %pM, ", entry->dest); + return sprintf(buff, "TT %pM, ", entry->dest); else if (compare_eth(entry->src, src)) return sprintf(buff, "TQ %pM %d, ", entry->dest, entry->quality); @@ -204,6 +204,7 @@ static ssize_t vis_data_read_entry(char *buff, struct vis_info_entry *entry, int vis_seq_print_text(struct seq_file *seq, void *offset) { + struct hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; struct vis_info *info; @@ -215,15 +216,18 @@ int vis_seq_print_text(struct seq_file *seq, void *offset) HLIST_HEAD(vis_if_list); struct if_list_entry *entry; struct hlist_node *pos, *n; - int i, j; + int i, j, ret = 0; int vis_server = atomic_read(&bat_priv->vis_mode); size_t buff_pos, buf_size; char *buff; int compare; - if ((!bat_priv->primary_if) || - (vis_server == VIS_TYPE_CLIENT_UPDATE)) - return 0; + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + if (vis_server == VIS_TYPE_CLIENT_UPDATE) + goto out; buf_size = 1; /* Estimate length */ @@ -270,7 +274,8 @@ int vis_seq_print_text(struct seq_file *seq, void *offset) buff = kmalloc(buf_size, GFP_ATOMIC); if (!buff) { spin_unlock_bh(&bat_priv->vis_hash_lock); - return -ENOMEM; + ret = -ENOMEM; + goto out; } buff[0] = '\0'; buff_pos = 0; @@ -328,7 +333,10 @@ int vis_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, "%s", buff); kfree(buff); - return 0; +out: + if (primary_if) + hardif_free_ref(primary_if); + return ret; } /* add the info packet to the send list, if it was not @@ -558,6 +566,7 @@ static int find_best_vis_server(struct bat_priv *bat_priv, struct vis_info *info) { struct hashtable_t *hash = bat_priv->orig_hash; + struct neigh_node *router; struct hlist_node *node; struct hlist_head *head; struct orig_node *orig_node; @@ -571,13 +580,17 @@ static int find_best_vis_server(struct bat_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { - if ((orig_node) && (orig_node->router) && - (orig_node->flags & VIS_SERVER) && - (orig_node->router->tq_avg > best_tq)) { - best_tq = orig_node->router->tq_avg; + router = orig_node_get_router(orig_node); + if (!router) + continue; + + if ((orig_node->flags & VIS_SERVER) && + (router->tq_avg > best_tq)) { + best_tq = router->tq_avg; memcpy(packet->target_orig, orig_node->orig, ETH_ALEN); } + neigh_node_free_ref(router); } rcu_read_unlock(); } @@ -605,11 +618,11 @@ static int generate_vis_packet(struct bat_priv *bat_priv) struct hlist_node *node; struct hlist_head *head; struct orig_node *orig_node; - struct neigh_node *neigh_node; + struct neigh_node *router; struct vis_info *info = (struct vis_info *)bat_priv->my_vis_info; struct vis_packet *packet = (struct vis_packet *)info->skb_packet->data; struct vis_info_entry *entry; - struct hna_local_entry *hna_local_entry; + struct tt_local_entry *tt_local_entry; int best_tq = -1, i; info->first_seen = jiffies; @@ -633,59 +646,61 @@ static int generate_vis_packet(struct bat_priv *bat_priv) rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { - neigh_node = orig_node->router; - - if (!neigh_node) + router = orig_node_get_router(orig_node); + if (!router) continue; - if (!compare_eth(neigh_node->addr, orig_node->orig)) - continue; + if (!compare_eth(router->addr, orig_node->orig)) + goto next; - if (neigh_node->if_incoming->if_status != IF_ACTIVE) - continue; + if (router->if_incoming->if_status != IF_ACTIVE) + goto next; - if (neigh_node->tq_avg < 1) - continue; + if (router->tq_avg < 1) + goto next; /* fill one entry into buffer. */ entry = (struct vis_info_entry *) skb_put(info->skb_packet, sizeof(*entry)); memcpy(entry->src, - neigh_node->if_incoming->net_dev->dev_addr, + router->if_incoming->net_dev->dev_addr, ETH_ALEN); memcpy(entry->dest, orig_node->orig, ETH_ALEN); - entry->quality = neigh_node->tq_avg; + entry->quality = router->tq_avg; packet->entries++; +next: + neigh_node_free_ref(router); + if (vis_packet_full(info)) goto unlock; } rcu_read_unlock(); } - hash = bat_priv->hna_local_hash; + hash = bat_priv->tt_local_hash; - spin_lock_bh(&bat_priv->hna_lhash_lock); + spin_lock_bh(&bat_priv->tt_lhash_lock); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; - hlist_for_each_entry(hna_local_entry, node, head, hash_entry) { + hlist_for_each_entry(tt_local_entry, node, head, hash_entry) { entry = (struct vis_info_entry *) skb_put(info->skb_packet, sizeof(*entry)); memset(entry->src, 0, ETH_ALEN); - memcpy(entry->dest, hna_local_entry->addr, ETH_ALEN); - entry->quality = 0; /* 0 means HNA */ + memcpy(entry->dest, tt_local_entry->addr, ETH_ALEN); + entry->quality = 0; /* 0 means TT */ packet->entries++; if (vis_packet_full(info)) { - spin_unlock_bh(&bat_priv->hna_lhash_lock); + spin_unlock_bh(&bat_priv->tt_lhash_lock); return 0; } } } - spin_unlock_bh(&bat_priv->hna_lhash_lock); + spin_unlock_bh(&bat_priv->tt_lhash_lock); return 0; unlock: @@ -725,6 +740,7 @@ static void purge_vis_packets(struct bat_priv *bat_priv) static void broadcast_vis_packet(struct bat_priv *bat_priv, struct vis_info *info) { + struct neigh_node *router; struct hashtable_t *hash = bat_priv->orig_hash; struct hlist_node *node; struct hlist_head *head; @@ -745,19 +761,26 @@ static void broadcast_vis_packet(struct bat_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { /* if it's a vis server and reachable, send it. */ - if ((!orig_node) || (!orig_node->router)) - continue; if (!(orig_node->flags & VIS_SERVER)) continue; + + router = orig_node_get_router(orig_node); + if (!router) + continue; + /* don't send it if we already received the packet from - * this node. */ + * this node. */ if (recv_list_is_in(bat_priv, &info->recv_list, - orig_node->orig)) + orig_node->orig)) { + neigh_node_free_ref(router); continue; + } memcpy(packet->target_orig, orig_node->orig, ETH_ALEN); - hard_iface = orig_node->router->if_incoming; - memcpy(dstaddr, orig_node->router->addr, ETH_ALEN); + hard_iface = router->if_incoming; + memcpy(dstaddr, router->addr, ETH_ALEN); + + neigh_node_free_ref(router); skb = skb_clone(info->skb_packet, GFP_ATOMIC); if (skb) @@ -772,60 +795,48 @@ static void unicast_vis_packet(struct bat_priv *bat_priv, struct vis_info *info) { struct orig_node *orig_node; - struct neigh_node *neigh_node = NULL; + struct neigh_node *router = NULL; struct sk_buff *skb; struct vis_packet *packet; packet = (struct vis_packet *)info->skb_packet->data; - rcu_read_lock(); orig_node = orig_hash_find(bat_priv, packet->target_orig); - if (!orig_node) - goto unlock; - - neigh_node = orig_node->router; + goto out; - if (!neigh_node) - goto unlock; - - if (!atomic_inc_not_zero(&neigh_node->refcount)) { - neigh_node = NULL; - goto unlock; - } - - rcu_read_unlock(); + router = orig_node_get_router(orig_node); + if (!router) + goto out; skb = skb_clone(info->skb_packet, GFP_ATOMIC); if (skb) - send_skb_packet(skb, neigh_node->if_incoming, - neigh_node->addr); + send_skb_packet(skb, router->if_incoming, router->addr); - goto out; - -unlock: - rcu_read_unlock(); out: - if (neigh_node) - neigh_node_free_ref(neigh_node); + if (router) + neigh_node_free_ref(router); if (orig_node) orig_node_free_ref(orig_node); - return; } /* only send one vis packet. called from send_vis_packets() */ static void send_vis_packet(struct bat_priv *bat_priv, struct vis_info *info) { + struct hard_iface *primary_if; struct vis_packet *packet; + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + packet = (struct vis_packet *)info->skb_packet->data; if (packet->ttl < 2) { pr_debug("Error - can't send vis packet: ttl exceeded\n"); - return; + goto out; } - memcpy(packet->sender_orig, bat_priv->primary_if->net_dev->dev_addr, - ETH_ALEN); + memcpy(packet->sender_orig, primary_if->net_dev->dev_addr, ETH_ALEN); packet->ttl--; if (is_broadcast_ether_addr(packet->target_orig)) @@ -833,6 +844,10 @@ static void send_vis_packet(struct bat_priv *bat_priv, struct vis_info *info) else unicast_vis_packet(bat_priv, info); packet->ttl++; /* restore TTL */ + +out: + if (primary_if) + hardif_free_ref(primary_if); } /* called from timer; send (and maybe generate) vis packet. */ @@ -859,8 +874,7 @@ static void send_vis_packets(struct work_struct *work) kref_get(&info->refcount); spin_unlock_bh(&bat_priv->vis_hash_lock); - if (bat_priv->primary_if) - send_vis_packet(bat_priv, info); + send_vis_packet(bat_priv, info); spin_lock_bh(&bat_priv->vis_hash_lock); send_list_del(info); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 4487bbd0d72e..815269b07f20 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2004,7 +2004,7 @@ static void hci_tx_task(unsigned long arg) read_unlock(&hci_task_lock); } -/* ----- HCI RX task (incoming data proccessing) ----- */ +/* ----- HCI RX task (incoming data processing) ----- */ /* ACL data packet */ static inline void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index 12822cde4b49..19e95004b286 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -80,7 +80,7 @@ #define HIDP_VIRTUAL_CABLE_UNPLUG 0 #define HIDP_BOOT_PROTOCOL_MODE 1 #define HIDP_BLUETOOTH_VENDOR_ID 9 -#define HIDP_WAITING_FOR_RETURN 10 +#define HIDP_WAITING_FOR_RETURN 10 #define HIDP_WAITING_FOR_SEND_ACK 11 struct hidp_connadd_req { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a5ab4a29ae31..a86f9ba4f05c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3666,7 +3666,7 @@ drop: static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk_buff *skb) { struct l2cap_chan *chan; - struct sock *sk; + struct sock *sk = NULL; struct l2cap_pinfo *pi; u16 control; u8 tx_seq; @@ -3755,7 +3755,7 @@ done: static inline int l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, struct sk_buff *skb) { - struct sock *sk; + struct sock *sk = NULL; struct l2cap_chan *chan; chan = l2cap_global_chan_by_psm(0, psm, conn->src); @@ -3788,7 +3788,7 @@ done: static inline int l2cap_att_channel(struct l2cap_conn *conn, __le16 cid, struct sk_buff *skb) { - struct sock *sk; + struct sock *sk = NULL; struct l2cap_chan *chan; chan = l2cap_global_chan_by_scid(0, cid, conn->src); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index c98360d40b84..18dc9888d8c2 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -649,7 +649,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch if (opt == BT_FLUSHABLE_OFF) { struct l2cap_conn *conn = chan->conn; - /* proceed futher only when we have l2cap_conn and + /* proceed further only when we have l2cap_conn and No Flush support in the LM */ if (!conn || !lmp_no_flush_capable(conn->hcon->hdev)) { err = -EINVAL; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 94954c74f6ae..42fdffd1d76c 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -369,15 +369,6 @@ static void __sco_sock_close(struct sock *sk) case BT_CONNECTED: case BT_CONFIG: - if (sco_pi(sk)->conn) { - sk->sk_state = BT_DISCONN; - sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT); - hci_conn_put(sco_pi(sk)->conn->hcon); - sco_pi(sk)->conn = NULL; - } else - sco_chan_del(sk, ECONNRESET); - break; - case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); diff --git a/net/bridge/br.c b/net/bridge/br.c index 84bbb82599b2..f20c4fd915a8 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -104,3 +104,4 @@ module_init(br_init) module_exit(br_deinit) MODULE_LICENSE("GPL"); MODULE_VERSION(BR_VERSION); +MODULE_ALIAS_RTNL_LINK("bridge"); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 21e5901186ea..a6b2f86378c7 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -74,13 +74,23 @@ out: return NETDEV_TX_OK; } +static int br_dev_init(struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + + br->stats = alloc_percpu(struct br_cpu_netstats); + if (!br->stats) + return -ENOMEM; + + return 0; +} + static int br_dev_open(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); netif_carrier_off(dev); - - br_features_recompute(br); + netdev_update_features(dev); netif_start_queue(dev); br_stp_enable_bridge(br); br_multicast_open(br); @@ -177,48 +187,11 @@ static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info) strcpy(info->bus_info, "N/A"); } -static int br_set_sg(struct net_device *dev, u32 data) -{ - struct net_bridge *br = netdev_priv(dev); - - if (data) - br->feature_mask |= NETIF_F_SG; - else - br->feature_mask &= ~NETIF_F_SG; - - br_features_recompute(br); - return 0; -} - -static int br_set_tso(struct net_device *dev, u32 data) -{ - struct net_bridge *br = netdev_priv(dev); - - if (data) - br->feature_mask |= NETIF_F_TSO; - else - br->feature_mask &= ~NETIF_F_TSO; - - br_features_recompute(br); - return 0; -} - -static int br_set_tx_csum(struct net_device *dev, u32 data) +static u32 br_fix_features(struct net_device *dev, u32 features) { struct net_bridge *br = netdev_priv(dev); - if (data) - br->feature_mask |= NETIF_F_NO_CSUM; - else - br->feature_mask &= ~NETIF_F_ALL_CSUM; - - br_features_recompute(br); - return 0; -} - -static int br_set_flags(struct net_device *netdev, u32 data) -{ - return ethtool_op_set_flags(netdev, data, ETH_FLAG_TXVLAN); + return br_features_recompute(br, features); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -319,21 +292,12 @@ static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) static const struct ethtool_ops br_ethtool_ops = { .get_drvinfo = br_getinfo, .get_link = ethtool_op_get_link, - .get_tx_csum = ethtool_op_get_tx_csum, - .set_tx_csum = br_set_tx_csum, - .get_sg = ethtool_op_get_sg, - .set_sg = br_set_sg, - .get_tso = ethtool_op_get_tso, - .set_tso = br_set_tso, - .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 = { .ndo_open = br_dev_open, .ndo_stop = br_dev_stop, + .ndo_init = br_dev_init, .ndo_start_xmit = br_dev_xmit, .ndo_get_stats64 = br_get_stats64, .ndo_set_mac_address = br_set_mac_address, @@ -347,6 +311,7 @@ static const struct net_device_ops br_netdev_ops = { #endif .ndo_add_slave = br_add_slave, .ndo_del_slave = br_del_slave, + .ndo_fix_features = br_fix_features, }; static void br_dev_free(struct net_device *dev) @@ -357,18 +322,49 @@ static void br_dev_free(struct net_device *dev) free_netdev(dev); } +static struct device_type br_type = { + .name = "bridge", +}; + void br_dev_setup(struct net_device *dev) { + struct net_bridge *br = netdev_priv(dev); + random_ether_addr(dev->dev_addr); ether_setup(dev); dev->netdev_ops = &br_netdev_ops; dev->destructor = br_dev_free; SET_ETHTOOL_OPS(dev, &br_ethtool_ops); + SET_NETDEV_DEVTYPE(dev, &br_type); dev->tx_queue_len = 0; dev->priv_flags = IFF_EBRIDGE; 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_HW_VLAN_TX; + NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_TX; + dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | + NETIF_F_GSO_MASK | NETIF_F_NO_CSUM | + NETIF_F_HW_VLAN_TX; + + br->dev = dev; + spin_lock_init(&br->lock); + INIT_LIST_HEAD(&br->port_list); + spin_lock_init(&br->hash_lock); + + br->bridge_id.prio[0] = 0x80; + br->bridge_id.prio[1] = 0x00; + + memcpy(br->group_addr, br_group_address, ETH_ALEN); + + br->stp_enabled = BR_NO_STP; + br->designated_root = br->bridge_id; + br->bridge_max_age = br->max_age = 20 * HZ; + br->bridge_hello_time = br->hello_time = 2 * HZ; + br->bridge_forward_delay = br->forward_delay = 15 * HZ; + br->ageing_time = 300 * HZ; + + br_netfilter_rtable_init(br); + br_stp_timer_init(br); + br_multicast_init(br); } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 88485cc74dc3..e0dfbc151dd7 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -28,6 +28,7 @@ static struct kmem_cache *br_fdb_cache __read_mostly; static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr); +static void fdb_notify(const struct net_bridge_fdb_entry *, int); static u32 fdb_salt __read_mostly; @@ -62,7 +63,7 @@ static inline int has_expired(const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb) { return !fdb->is_static && - time_before_eq(fdb->ageing_timer + hold_time(br), jiffies); + time_before_eq(fdb->updated + hold_time(br), jiffies); } static inline int br_mac_hash(const unsigned char *mac) @@ -81,6 +82,7 @@ static void fdb_rcu_free(struct rcu_head *head) static inline void fdb_delete(struct net_bridge_fdb_entry *f) { + fdb_notify(f, RTM_DELNEIGH); hlist_del_rcu(&f->hlist); call_rcu(&f->rcu, fdb_rcu_free); } @@ -140,7 +142,7 @@ void br_fdb_cleanup(unsigned long _data) unsigned long this_timer; if (f->is_static) continue; - this_timer = f->ageing_timer + delay; + this_timer = f->updated + delay; if (time_before_eq(this_timer, jiffies)) fdb_delete(f); else if (time_before(this_timer, next_timer)) @@ -169,7 +171,7 @@ void br_fdb_flush(struct net_bridge *br) spin_unlock_bh(&br->hash_lock); } -/* Flush all entries refering to a specific port. +/* Flush all entries referring to a specific port. * if do_all is set also flush static entries */ void br_fdb_delete_by_port(struct net_bridge *br, @@ -293,7 +295,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, fe->is_local = f->is_local; if (!f->is_static) - fe->ageing_timer_value = jiffies_to_clock_t(jiffies - f->ageing_timer); + fe->ageing_timer_value = jiffies_to_clock_t(jiffies - f->updated); ++fe; ++num; } @@ -305,8 +307,21 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, return num; } -static inline struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, - const unsigned char *addr) +static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, + const unsigned char *addr) +{ + struct hlist_node *h; + struct net_bridge_fdb_entry *fdb; + + hlist_for_each_entry(fdb, h, head, hlist) { + if (!compare_ether_addr(fdb->addr.addr, addr)) + return fdb; + } + return NULL; +} + +static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head, + const unsigned char *addr) { struct hlist_node *h; struct net_bridge_fdb_entry *fdb; @@ -320,8 +335,7 @@ static inline struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, struct net_bridge_port *source, - const unsigned char *addr, - int is_local) + const unsigned char *addr) { struct net_bridge_fdb_entry *fdb; @@ -329,11 +343,11 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, if (fdb) { memcpy(fdb->addr.addr, addr, ETH_ALEN); fdb->dst = source; - fdb->is_local = is_local; - fdb->is_static = is_local; - fdb->ageing_timer = jiffies; - + fdb->is_local = 0; + fdb->is_static = 0; + fdb->updated = fdb->used = jiffies; hlist_add_head_rcu(&fdb->hlist, head); + fdb_notify(fdb, RTM_NEWNEIGH); } return fdb; } @@ -360,12 +374,15 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, fdb_delete(fdb); } - if (!fdb_create(head, source, addr, 1)) + fdb = fdb_create(head, source, addr); + if (!fdb) return -ENOMEM; + fdb->is_local = fdb->is_static = 1; return 0; } +/* Add entry for local address of interface */ int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr) { @@ -392,7 +409,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, source->state == BR_STATE_FORWARDING)) return; - fdb = fdb_find(head, addr); + fdb = fdb_find_rcu(head, addr); if (likely(fdb)) { /* attempt to update an entry for a local interface */ if (unlikely(fdb->is_local)) { @@ -403,15 +420,277 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, } else { /* fastpath: update of existing entry */ fdb->dst = source; - fdb->ageing_timer = jiffies; + fdb->updated = jiffies; } } else { spin_lock(&br->hash_lock); - if (!fdb_find(head, addr)) - fdb_create(head, source, addr, 0); + if (likely(!fdb_find(head, addr))) + fdb_create(head, source, addr); + /* else we lose race and someone else inserts * it first, don't bother updating */ spin_unlock(&br->hash_lock); } } + +static int fdb_to_nud(const struct net_bridge_fdb_entry *fdb) +{ + if (fdb->is_local) + return NUD_PERMANENT; + else if (fdb->is_static) + return NUD_NOARP; + else if (has_expired(fdb->dst->br, fdb)) + return NUD_STALE; + else + return NUD_REACHABLE; +} + +static int fdb_fill_info(struct sk_buff *skb, + const struct net_bridge_fdb_entry *fdb, + u32 pid, u32 seq, int type, unsigned int flags) +{ + unsigned long now = jiffies; + struct nda_cacheinfo ci; + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = 0; + ndm->ndm_type = 0; + ndm->ndm_ifindex = fdb->dst->dev->ifindex; + ndm->ndm_state = fdb_to_nud(fdb); + + NLA_PUT(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr); + + ci.ndm_used = jiffies_to_clock_t(now - fdb->used); + ci.ndm_confirmed = 0; + ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); + ci.ndm_refcnt = 0; + NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t fdb_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ndmsg)) + + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + + nla_total_size(sizeof(struct nda_cacheinfo)); +} + +static void fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +{ + struct net *net = dev_net(fdb->dst->dev); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = fdb_fill_info(skb, fdb, 0, 0, type, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in fdb_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); +} + +/* Dump information about entries, in response to GETNEIGH */ +int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int idx = 0; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + struct net_bridge *br = netdev_priv(dev); + int i; + + if (!(dev->priv_flags & IFF_EBRIDGE)) + continue; + + for (i = 0; i < BR_HASH_SIZE; i++) { + struct hlist_node *h; + struct net_bridge_fdb_entry *f; + + hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) { + if (idx < cb->args[0]) + goto skip; + + if (fdb_fill_info(skb, f, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI) < 0) + break; +skip: + ++idx; + } + } + } + rcu_read_unlock(); + + cb->args[0] = idx; + + return skb->len; +} + +/* Create new static fdb entry */ +static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, + __u16 state) +{ + struct net_bridge *br = source->br; + struct hlist_head *head = &br->hash[br_mac_hash(addr)]; + struct net_bridge_fdb_entry *fdb; + + fdb = fdb_find(head, addr); + if (fdb) + return -EEXIST; + + fdb = fdb_create(head, source, addr); + if (!fdb) + return -ENOMEM; + + if (state & NUD_PERMANENT) + fdb->is_local = fdb->is_static = 1; + else if (state & NUD_NOARP) + fdb->is_static = 1; + return 0; +} + +/* Add new permanent fdb entry with RTM_NEWNEIGH */ +int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; + struct net_device *dev; + struct net_bridge_port *p; + const __u8 *addr; + int err; + + ASSERT_RTNL(); + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + return err; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex == 0) { + pr_info("bridge: RTM_NEWNEIGH with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + pr_info("bridge: RTM_NEWNEIGH with unknown ifindex\n"); + return -ENODEV; + } + + if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { + pr_info("bridge: RTM_NEWNEIGH with invalid address\n"); + return -EINVAL; + } + + addr = nla_data(tb[NDA_LLADDR]); + if (!is_valid_ether_addr(addr)) { + pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n"); + return -EINVAL; + } + + p = br_port_get_rtnl(dev); + if (p == NULL) { + pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n", + dev->name); + return -EINVAL; + } + + spin_lock_bh(&p->br->hash_lock); + err = fdb_add_entry(p, addr, ndm->ndm_state); + spin_unlock_bh(&p->br->hash_lock); + + return err; +} + +static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr) +{ + struct net_bridge *br = p->br; + struct hlist_head *head = &br->hash[br_mac_hash(addr)]; + struct net_bridge_fdb_entry *fdb; + + fdb = fdb_find(head, addr); + if (!fdb) + return -ENOENT; + + fdb_delete(fdb); + return 0; +} + +/* Remove neighbor entry with RTM_DELNEIGH */ +int br_fdb_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct net_bridge_port *p; + struct nlattr *llattr; + const __u8 *addr; + struct net_device *dev; + int err; + + ASSERT_RTNL(); + if (nlmsg_len(nlh) < sizeof(*ndm)) + return -EINVAL; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex == 0) { + pr_info("bridge: RTM_DELNEIGH with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + pr_info("bridge: RTM_DELNEIGH with unknown ifindex\n"); + return -ENODEV; + } + + llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR); + if (llattr == NULL || nla_len(llattr) != ETH_ALEN) { + pr_info("bridge: RTM_DELNEIGH with invalid address\n"); + return -EINVAL; + } + + addr = nla_data(llattr); + + p = br_port_get_rtnl(dev); + if (p == NULL) { + pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n", + dev->name); + return -EINVAL; + } + + spin_lock_bh(&p->br->hash_lock); + err = fdb_delete_by_addr(p, addr); + spin_unlock_bh(&p->br->hash_lock); + + return err; +} diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 718b60366dfe..1bacca4cb676 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -36,8 +36,8 @@ static int port_cost(struct net_device *dev) if (dev->ethtool_ops && dev->ethtool_ops->get_settings) { struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET, }; - if (!dev->ethtool_ops->get_settings(dev, &ecmd)) { - switch(ecmd.speed) { + if (!dev_ethtool_get_settings(dev, &ecmd)) { + switch (ethtool_cmd_speed(&ecmd)) { case SPEED_10000: return 2; case SPEED_1000: @@ -147,6 +147,7 @@ static void del_nbp(struct net_bridge_port *p) dev->priv_flags &= ~IFF_BRIDGE_PORT; netdev_rx_handler_unregister(dev); + synchronize_net(); netdev_set_master(dev, NULL); @@ -175,56 +176,6 @@ static void del_br(struct net_bridge *br, struct list_head *head) unregister_netdevice_queue(br->dev, head); } -static struct net_device *new_bridge_dev(struct net *net, const char *name) -{ - struct net_bridge *br; - struct net_device *dev; - - dev = alloc_netdev(sizeof(struct net_bridge), name, - br_dev_setup); - - if (!dev) - return NULL; - dev_net_set(dev, net); - - br = netdev_priv(dev); - br->dev = dev; - - br->stats = alloc_percpu(struct br_cpu_netstats); - if (!br->stats) { - free_netdev(dev); - return NULL; - } - - spin_lock_init(&br->lock); - INIT_LIST_HEAD(&br->port_list); - spin_lock_init(&br->hash_lock); - - br->bridge_id.prio[0] = 0x80; - br->bridge_id.prio[1] = 0x00; - - memcpy(br->group_addr, br_group_address, ETH_ALEN); - - br->feature_mask = dev->features; - br->stp_enabled = BR_NO_STP; - br->designated_root = br->bridge_id; - br->root_path_cost = 0; - br->root_port = 0; - br->bridge_max_age = br->max_age = 20 * HZ; - br->bridge_hello_time = br->hello_time = 2 * HZ; - br->bridge_forward_delay = br->forward_delay = 15 * HZ; - br->topology_change = 0; - br->topology_change_detected = 0; - br->ageing_time = 300 * HZ; - - br_netfilter_rtable_init(br); - - br_stp_timer_init(br); - br_multicast_init(br); - - return dev; -} - /* find an available port number */ static int find_portno(struct net_bridge *br) { @@ -277,42 +228,19 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, return p; } -static struct device_type br_type = { - .name = "bridge", -}; - int br_add_bridge(struct net *net, const char *name) { struct net_device *dev; - int ret; - dev = new_bridge_dev(net, name); + dev = alloc_netdev(sizeof(struct net_bridge), name, + br_dev_setup); + if (!dev) return -ENOMEM; - rtnl_lock(); - if (strchr(dev->name, '%')) { - ret = dev_alloc_name(dev, dev->name); - if (ret < 0) - goto out_free; - } - - SET_NETDEV_DEVTYPE(dev, &br_type); - - ret = register_netdevice(dev); - if (ret) - goto out_free; - - ret = br_sysfs_addbr(dev); - if (ret) - unregister_netdevice(dev); - out: - rtnl_unlock(); - return ret; + dev_net_set(dev, net); -out_free: - free_netdev(dev); - goto out; + return register_netdev(dev); } int br_del_bridge(struct net *net, const char *name) @@ -364,15 +292,15 @@ int br_min_mtu(const struct net_bridge *br) /* * Recomputes features using slave's features */ -void br_features_recompute(struct net_bridge *br) +u32 br_features_recompute(struct net_bridge *br, u32 features) { struct net_bridge_port *p; - u32 features, mask; + u32 mask; - features = mask = br->feature_mask; if (list_empty(&br->port_list)) - goto done; + return features; + mask = features; features &= ~NETIF_F_ONE_FOR_ALL; list_for_each_entry(p, &br->port_list, list) { @@ -380,8 +308,7 @@ void br_features_recompute(struct net_bridge *br) p->dev->features, mask); } -done: - br->dev->features = netdev_fix_features(br->dev, features); + return features; } /* called with RTNL */ @@ -412,6 +339,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (IS_ERR(p)) return PTR_ERR(p); + call_netdevice_notifiers(NETDEV_JOIN, dev); + err = dev_set_promiscuity(dev, 1); if (err) goto put_back; @@ -446,9 +375,10 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) list_add_rcu(&p->list, &br->port_list); + netdev_update_features(br->dev); + spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); - br_features_recompute(br); if ((dev->flags & IFF_UP) && netif_carrier_ok(dev) && (br->dev->flags & IFF_UP)) @@ -496,9 +426,10 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) spin_lock_bh(&br->lock); br_stp_recalculate_bridge_id(br); - br_features_recompute(br); spin_unlock_bh(&br->lock); + netdev_update_features(br->dev); + return 0; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index e2160792e1bc..f3ac1e858ee1 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -98,9 +98,10 @@ int br_handle_frame_finish(struct sk_buff *skb) } if (skb) { - if (dst) + if (dst) { + dst->used = jiffies; br_forward(dst->dst, skb, skb2); - else + } else br_flood_forward(br, skb, skb2); } @@ -164,7 +165,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto drop; /* If STP is turned off, then forward */ - if (p->br->stp_enabled == BR_NO_STP) + if (p->br->stp_enabled == BR_NO_STP && dest[5] == 0) goto forward; if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index cb43312b846e..7222fe1d5460 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -106,7 +106,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) /* * Legacy ioctl's through SIOCDEVPRIVATE * This interface is deprecated because it was too difficult to - * to do the translation for 32/64bit ioctl compatability. + * to do the translation for 32/64bit ioctl compatibility. */ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { @@ -181,40 +181,19 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) if (!capable(CAP_NET_ADMIN)) return -EPERM; - spin_lock_bh(&br->lock); - br->bridge_forward_delay = clock_t_to_jiffies(args[1]); - if (br_is_root_bridge(br)) - br->forward_delay = br->bridge_forward_delay; - spin_unlock_bh(&br->lock); - return 0; + return br_set_forward_delay(br, args[1]); case BRCTL_SET_BRIDGE_HELLO_TIME: - { - unsigned long t = clock_t_to_jiffies(args[1]); if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (t < HZ) - return -EINVAL; - - spin_lock_bh(&br->lock); - br->bridge_hello_time = t; - if (br_is_root_bridge(br)) - br->hello_time = br->bridge_hello_time; - spin_unlock_bh(&br->lock); - return 0; - } + return br_set_hello_time(br, args[1]); case BRCTL_SET_BRIDGE_MAX_AGE: if (!capable(CAP_NET_ADMIN)) return -EPERM; - spin_lock_bh(&br->lock); - br->bridge_max_age = clock_t_to_jiffies(args[1]); - if (br_is_root_bridge(br)) - br->max_age = br->bridge_max_age; - spin_unlock_bh(&br->lock); - return 0; + return br_set_max_age(br, args[1]); case BRCTL_SET_AGEING_TIME: if (!capable(CAP_NET_ADMIN)) @@ -275,19 +254,16 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) case BRCTL_SET_PORT_PRIORITY: { struct net_bridge_port *p; - int ret = 0; + int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (args[2] >= (1<<(16-BR_PORT_BITS))) - return -ERANGE; - spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else - br_stp_set_port_priority(p, args[2]); + ret = br_stp_set_port_priority(p, args[2]); spin_unlock_bh(&br->lock); return ret; } @@ -295,15 +271,17 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) case BRCTL_SET_PATH_COST: { struct net_bridge_port *p; - int ret = 0; + int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; + spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else - br_stp_set_path_cost(p, args[2]); + ret = br_stp_set_path_cost(p, args[2]); + spin_unlock_bh(&br->lock); return ret; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 59660c909a7c..2f14eafdeeab 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -413,7 +413,7 @@ out: #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, - struct in6_addr *group) + const struct in6_addr *group) { struct sk_buff *skb; struct ipv6hdr *ip6h; @@ -1115,7 +1115,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb) { - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); struct igmphdr *ih = igmp_hdr(skb); struct net_bridge_mdb_entry *mp; struct igmpv3_query *ih3; @@ -1190,7 +1190,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb) { - struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct mld_msg *mld = (struct mld_msg *) icmp6_hdr(skb); struct net_bridge_mdb_entry *mp; struct mld2_query *mld2q; @@ -1198,7 +1198,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, struct net_bridge_port_group __rcu **pp; unsigned long max_delay; unsigned long now = jiffies; - struct in6_addr *group = NULL; + const struct in6_addr *group = NULL; int err = 0; spin_lock(&br->multicast_lock); @@ -1356,7 +1356,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, struct sk_buff *skb) { struct sk_buff *skb2 = skb; - struct iphdr *iph; + const struct iphdr *iph; struct igmphdr *ih; unsigned len; unsigned offset; @@ -1452,7 +1452,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, struct sk_buff *skb) { struct sk_buff *skb2; - struct ipv6hdr *ip6h; + const struct ipv6hdr *ip6h; struct icmp6hdr *icmp6h; u8 nexthdr; unsigned len; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 008ff6c4eecf..3fa123185e89 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -117,6 +117,10 @@ static struct dst_ops fake_dst_ops = { * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ +static const u32 br_dst_default_metrics[RTAX_MAX] = { + [RTAX_MTU - 1] = 1500, +}; + void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; @@ -124,7 +128,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) atomic_set(&rt->dst.__refcnt, 1); rt->dst.dev = br->dev; rt->dst.path = &rt->dst; - dst_metric_set(&rt->dst, RTAX_MTU, 1500); + dst_init_metrics(&rt->dst, br_dst_default_metrics, true); rt->dst.flags = DST_NOXFRM; rt->dst.ops = &fake_dst_ops; } @@ -219,7 +223,7 @@ static inline void nf_bridge_update_protocol(struct sk_buff *skb) static int br_parse_ip_options(struct sk_buff *skb) { struct ip_options *opt; - struct iphdr *iph; + const struct iphdr *iph; struct net_device *dev = skb->dev; u32 len; @@ -249,11 +253,9 @@ static int br_parse_ip_options(struct sk_buff *skb) goto drop; } - /* Zero out the CB buffer if no options present */ - if (iph->ihl == 5) { - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + if (iph->ihl == 5) return 0; - } opt->optlen = iph->ihl*4 - sizeof(struct iphdr); if (ip_options_compile(dev_net(dev), opt, skb)) @@ -556,7 +558,7 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; u32 pkt_len; if (skb->len < sizeof(struct ipv6hdr)) @@ -739,7 +741,7 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, nf_bridge->mask |= BRNF_PKT_TYPE; } - if (br_parse_ip_options(skb)) + if (pf == PF_INET && br_parse_ip_options(skb)) return NF_DROP; /* The physdev module checks on this */ diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index f8bf4c7f842c..ffb0dc4cc0e8 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -12,9 +12,11 @@ #include <linux/kernel.h> #include <linux/slab.h> +#include <linux/etherdevice.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> + #include "br_private.h" static inline size_t br_nlmsg_size(void) @@ -118,8 +120,9 @@ static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) int idx; idx = 0; - for_each_netdev(net, dev) { - struct net_bridge_port *port = br_port_get_rtnl(dev); + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + struct net_bridge_port *port = br_port_get_rcu(dev); /* not a bridge port */ if (!port || idx < cb->args[0]) @@ -133,7 +136,7 @@ static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) skip: ++idx; } - + rcu_read_unlock(); cb->args[0] = idx; return skb->len; @@ -188,20 +191,61 @@ static int br_rtm_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) return 0; } +static int br_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) + return -EADDRNOTAVAIL; + } + + return 0; +} + +static struct rtnl_link_ops br_link_ops __read_mostly = { + .kind = "bridge", + .priv_size = sizeof(struct net_bridge), + .setup = br_dev_setup, + .validate = br_validate, +}; int __init br_netlink_init(void) { - if (__rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, br_dump_ifinfo)) - return -ENOBUFS; + int err; - /* Only the first call to __rtnl_register can fail */ - __rtnl_register(PF_BRIDGE, RTM_SETLINK, br_rtm_setlink, NULL); + err = rtnl_link_register(&br_link_ops); + if (err < 0) + goto err1; + + err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, br_dump_ifinfo); + if (err) + goto err2; + err = __rtnl_register(PF_BRIDGE, RTM_SETLINK, br_rtm_setlink, NULL); + if (err) + goto err3; + err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, br_fdb_add, NULL); + if (err) + goto err3; + err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH, br_fdb_delete, NULL); + if (err) + goto err3; + err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, br_fdb_dump); + if (err) + goto err3; return 0; + +err3: + rtnl_unregister_all(PF_BRIDGE); +err2: + rtnl_link_unregister(&br_link_ops); +err1: + return err; } void __exit br_netlink_fini(void) { + rtnl_link_unregister(&br_link_ops); rtnl_unregister_all(PF_BRIDGE); } - diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 7d337c9b6082..6545ee9591d1 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -36,6 +36,12 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v struct net_bridge *br; int err; + /* register of bridge completed, add sysfs entries */ + if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) { + br_sysfs_addbr(dev); + return NOTIFY_DONE; + } + /* not a port of a bridge */ p = br_port_get_rtnl(dev); if (!p) @@ -60,10 +66,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v break; case NETDEV_FEAT_CHANGE: - spin_lock_bh(&br->lock); - if (netif_running(br->dev)) - br_features_recompute(br); - spin_unlock_bh(&br->lock); + netdev_update_features(br->dev); break; case NETDEV_DOWN: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 387013d33745..54578f274d85 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -64,7 +64,8 @@ struct net_bridge_fdb_entry struct net_bridge_port *dst; struct rcu_head rcu; - unsigned long ageing_timer; + unsigned long updated; + unsigned long used; mac_addr addr; unsigned char is_local; unsigned char is_static; @@ -182,7 +183,6 @@ struct net_bridge struct br_cpu_netstats __percpu *stats; spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; - u32 feature_mask; #ifdef CONFIG_BRIDGE_NETFILTER struct rtable fake_rtable; bool nf_call_iptables; @@ -353,6 +353,9 @@ extern int br_fdb_insert(struct net_bridge *br, extern void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr); +extern int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb); +extern int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); +extern int br_fdb_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); /* br_forward.c */ extern void br_deliver(const struct net_bridge_port *to, @@ -375,7 +378,7 @@ extern int br_add_if(struct net_bridge *br, extern int br_del_if(struct net_bridge *br, struct net_device *dev); extern int br_min_mtu(const struct net_bridge *br); -extern void br_features_recompute(struct net_bridge *br); +extern u32 br_features_recompute(struct net_bridge *br, u32 features); /* br_input.c */ extern int br_handle_frame_finish(struct sk_buff *skb); @@ -491,6 +494,11 @@ extern struct net_bridge_port *br_get_port(struct net_bridge *br, extern void br_init_port(struct net_bridge_port *p); extern void br_become_designated_port(struct net_bridge_port *p); +extern int br_set_forward_delay(struct net_bridge *br, unsigned long x); +extern int br_set_hello_time(struct net_bridge *br, unsigned long x); +extern int br_set_max_age(struct net_bridge *br, unsigned long x); + + /* br_stp_if.c */ extern void br_stp_enable_bridge(struct net_bridge *br); extern void br_stp_disable_bridge(struct net_bridge *br); @@ -501,10 +509,10 @@ extern bool br_stp_recalculate_bridge_id(struct net_bridge *br); extern void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *a); extern void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio); -extern void br_stp_set_port_priority(struct net_bridge_port *p, - u8 newprio); -extern void br_stp_set_path_cost(struct net_bridge_port *p, - u32 path_cost); +extern int br_stp_set_port_priority(struct net_bridge_port *p, + unsigned long newprio); +extern int br_stp_set_path_cost(struct net_bridge_port *p, + unsigned long path_cost); extern ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id); /* br_stp_bpdu.c */ diff --git a/net/bridge/br_private_stp.h b/net/bridge/br_private_stp.h index 8b650f7fbfa0..642ef47a867e 100644 --- a/net/bridge/br_private_stp.h +++ b/net/bridge/br_private_stp.h @@ -16,6 +16,19 @@ #define BPDU_TYPE_CONFIG 0 #define BPDU_TYPE_TCN 0x80 +/* IEEE 802.1D-1998 timer values */ +#define BR_MIN_HELLO_TIME (1*HZ) +#define BR_MAX_HELLO_TIME (10*HZ) + +#define BR_MIN_FORWARD_DELAY (2*HZ) +#define BR_MAX_FORWARD_DELAY (30*HZ) + +#define BR_MIN_MAX_AGE (6*HZ) +#define BR_MAX_MAX_AGE (40*HZ) + +#define BR_MIN_PATH_COST 1 +#define BR_MAX_PATH_COST 65535 + struct br_config_bpdu { unsigned topology_change:1; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 7370d14f634d..bb4383e84de9 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -484,3 +484,51 @@ void br_received_tcn_bpdu(struct net_bridge_port *p) br_topology_change_acknowledge(p); } } + +/* Change bridge STP parameter */ +int br_set_hello_time(struct net_bridge *br, unsigned long val) +{ + unsigned long t = clock_t_to_jiffies(val); + + if (t < BR_MIN_HELLO_TIME || t > BR_MAX_HELLO_TIME) + return -ERANGE; + + spin_lock_bh(&br->lock); + br->bridge_hello_time = t; + if (br_is_root_bridge(br)) + br->hello_time = br->bridge_hello_time; + spin_unlock_bh(&br->lock); + return 0; +} + +int br_set_max_age(struct net_bridge *br, unsigned long val) +{ + unsigned long t = clock_t_to_jiffies(val); + + if (t < BR_MIN_MAX_AGE || t > BR_MAX_MAX_AGE) + return -ERANGE; + + spin_lock_bh(&br->lock); + br->bridge_max_age = t; + if (br_is_root_bridge(br)) + br->max_age = br->bridge_max_age; + spin_unlock_bh(&br->lock); + return 0; + +} + +int br_set_forward_delay(struct net_bridge *br, unsigned long val) +{ + unsigned long t = clock_t_to_jiffies(val); + + if (br->stp_enabled != BR_NO_STP && + (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY)) + return -ERANGE; + + spin_lock_bh(&br->lock); + br->bridge_forward_delay = t; + if (br_is_root_bridge(br)) + br->forward_delay = br->bridge_forward_delay; + spin_unlock_bh(&br->lock); + return 0; +} diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 9b61d09de9b9..6f615b8192f4 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -20,7 +20,7 @@ /* Port id is composed of priority and port number. - * NB: least significant bits of priority are dropped to + * NB: some bits of priority are dropped to * make room for more ports. */ static inline port_id br_make_port_id(__u8 priority, __u16 port_no) @@ -29,6 +29,8 @@ static inline port_id br_make_port_id(__u8 priority, __u16 port_no) | (port_no & ((1<<BR_PORT_BITS)-1)); } +#define BR_MAX_PORT_PRIORITY ((u16)~0 >> BR_PORT_BITS) + /* called under bridge lock */ void br_init_port(struct net_bridge_port *p) { @@ -255,10 +257,14 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio) } /* called under bridge lock */ -void br_stp_set_port_priority(struct net_bridge_port *p, u8 newprio) +int br_stp_set_port_priority(struct net_bridge_port *p, unsigned long newprio) { - port_id new_port_id = br_make_port_id(newprio, p->port_no); + port_id new_port_id; + + if (newprio > BR_MAX_PORT_PRIORITY) + return -ERANGE; + new_port_id = br_make_port_id(newprio, p->port_no); if (br_is_designated_port(p)) p->designated_port = new_port_id; @@ -269,14 +275,21 @@ void br_stp_set_port_priority(struct net_bridge_port *p, u8 newprio) br_become_designated_port(p); br_port_state_selection(p->br); } + + return 0; } /* called under bridge lock */ -void br_stp_set_path_cost(struct net_bridge_port *p, u32 path_cost) +int br_stp_set_path_cost(struct net_bridge_port *p, unsigned long path_cost) { + if (path_cost < BR_MIN_PATH_COST || + path_cost > BR_MAX_PATH_COST) + return -ERANGE; + p->path_cost = path_cost; br_configuration_update(p->br); br_port_state_selection(p->br); + return 0; } ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id) diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 5c1e5559ebba..68b893ea8c3a 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -43,9 +43,7 @@ static ssize_t store_bridge_parm(struct device *d, if (endp == buf) return -EINVAL; - spin_lock_bh(&br->lock); err = (*set)(br, val); - spin_unlock_bh(&br->lock); return err ? err : len; } @@ -57,20 +55,11 @@ static ssize_t show_forward_delay(struct device *d, return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->forward_delay)); } -static int set_forward_delay(struct net_bridge *br, unsigned long val) -{ - unsigned long delay = clock_t_to_jiffies(val); - br->forward_delay = delay; - if (br_is_root_bridge(br)) - br->bridge_forward_delay = delay; - return 0; -} - static ssize_t store_forward_delay(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, set_forward_delay); + return store_bridge_parm(d, buf, len, br_set_forward_delay); } static DEVICE_ATTR(forward_delay, S_IRUGO | S_IWUSR, show_forward_delay, store_forward_delay); @@ -82,24 +71,11 @@ static ssize_t show_hello_time(struct device *d, struct device_attribute *attr, jiffies_to_clock_t(to_bridge(d)->hello_time)); } -static int set_hello_time(struct net_bridge *br, unsigned long val) -{ - unsigned long t = clock_t_to_jiffies(val); - - if (t < HZ) - return -EINVAL; - - br->hello_time = t; - if (br_is_root_bridge(br)) - br->bridge_hello_time = t; - return 0; -} - static ssize_t store_hello_time(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, set_hello_time); + return store_bridge_parm(d, buf, len, br_set_hello_time); } static DEVICE_ATTR(hello_time, S_IRUGO | S_IWUSR, show_hello_time, store_hello_time); @@ -111,19 +87,10 @@ static ssize_t show_max_age(struct device *d, struct device_attribute *attr, jiffies_to_clock_t(to_bridge(d)->max_age)); } -static int set_max_age(struct net_bridge *br, unsigned long val) -{ - unsigned long t = clock_t_to_jiffies(val); - br->max_age = t; - if (br_is_root_bridge(br)) - br->bridge_max_age = t; - return 0; -} - static ssize_t store_max_age(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, set_max_age); + return store_bridge_parm(d, buf, len, br_set_max_age); } static DEVICE_ATTR(max_age, S_IRUGO | S_IWUSR, show_max_age, store_max_age); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index fd5799c9bc8d..6229b62749e8 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -23,7 +23,7 @@ struct brport_attribute { struct attribute attr; ssize_t (*show)(struct net_bridge_port *, char *); - ssize_t (*store)(struct net_bridge_port *, unsigned long); + int (*store)(struct net_bridge_port *, unsigned long); }; #define BRPORT_ATTR(_name,_mode,_show,_store) \ @@ -38,27 +38,17 @@ static ssize_t show_path_cost(struct net_bridge_port *p, char *buf) { return sprintf(buf, "%d\n", p->path_cost); } -static ssize_t store_path_cost(struct net_bridge_port *p, unsigned long v) -{ - br_stp_set_path_cost(p, v); - return 0; -} + static BRPORT_ATTR(path_cost, S_IRUGO | S_IWUSR, - show_path_cost, store_path_cost); + show_path_cost, br_stp_set_path_cost); static ssize_t show_priority(struct net_bridge_port *p, char *buf) { return sprintf(buf, "%d\n", p->priority); } -static ssize_t store_priority(struct net_bridge_port *p, unsigned long v) -{ - if (v >= (1<<(16-BR_PORT_BITS))) - return -ERANGE; - br_stp_set_port_priority(p, v); - return 0; -} + static BRPORT_ATTR(priority, S_IRUGO | S_IWUSR, - show_priority, store_priority); + show_priority, br_stp_set_port_priority); static ssize_t show_designated_root(struct net_bridge_port *p, char *buf) { @@ -136,7 +126,7 @@ static ssize_t show_hold_timer(struct net_bridge_port *p, } static BRPORT_ATTR(hold_timer, S_IRUGO, show_hold_timer, NULL); -static ssize_t store_flush(struct net_bridge_port *p, unsigned long v) +static int store_flush(struct net_bridge_port *p, unsigned long v) { br_fdb_delete_by_port(p->br, p, 0); // Don't delete local entry return 0; @@ -148,7 +138,7 @@ static ssize_t show_hairpin_mode(struct net_bridge_port *p, char *buf) int hairpin_mode = (p->flags & BR_HAIRPIN_MODE) ? 1 : 0; return sprintf(buf, "%d\n", hairpin_mode); } -static ssize_t store_hairpin_mode(struct net_bridge_port *p, unsigned long v) +static int store_hairpin_mode(struct net_bridge_port *p, unsigned long v) { if (v) p->flags |= BR_HAIRPIN_MODE; @@ -165,7 +155,7 @@ static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) return sprintf(buf, "%d\n", p->multicast_router); } -static ssize_t store_multicast_router(struct net_bridge_port *p, +static int store_multicast_router(struct net_bridge_port *p, unsigned long v) { return br_multicast_set_port_router(p, v); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 893669caa8de..2b5ca1a0054d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1766,7 +1766,7 @@ static int compat_table_info(const struct ebt_table_info *info, newinfo->entries_size = size; - xt_compat_init_offsets(AF_INET, info->nentries); + xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); } @@ -1882,15 +1882,14 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, struct xt_match *match; struct xt_target *wt; void *dst = NULL; - int off, pad = 0, ret = 0; - unsigned int size_kern, entry_offset, match_size = mwt->match_size; + int off, pad = 0; + unsigned int size_kern, match_size = mwt->match_size; strlcpy(name, mwt->u.name, sizeof(name)); if (state->buf_kern_start) dst = state->buf_kern_start + state->buf_kern_offset; - entry_offset = (unsigned char *) mwt - base; switch (compat_mwt) { case EBT_COMPAT_MATCH: match = try_then_request_module(xt_find_match(NFPROTO_BRIDGE, @@ -1933,13 +1932,9 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, size_kern = wt->targetsize; module_put(wt->me); break; - } - if (!dst) { - ret = xt_compat_add_offset(NFPROTO_BRIDGE, entry_offset, - off + ebt_compat_entry_padsize()); - if (ret < 0) - return ret; + default: + return -EINVAL; } state->buf_kern_offset += match_size + off; @@ -2016,50 +2011,6 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, return growth; } -#define EBT_COMPAT_WATCHER_ITERATE(e, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct compat_ebt_entry_mwt *__watcher; \ - \ - for (__i = e->watchers_offset; \ - __i < (e)->target_offset; \ - __i += __watcher->watcher_size + \ - sizeof(struct compat_ebt_entry_mwt)) { \ - __watcher = (void *)(e) + __i; \ - __ret = fn(__watcher , ## args); \ - if (__ret != 0) \ - break; \ - } \ - if (__ret == 0) { \ - if (__i != (e)->target_offset) \ - __ret = -EINVAL; \ - } \ - __ret; \ -}) - -#define EBT_COMPAT_MATCH_ITERATE(e, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct compat_ebt_entry_mwt *__match; \ - \ - for (__i = sizeof(struct ebt_entry); \ - __i < (e)->watchers_offset; \ - __i += __match->match_size + \ - sizeof(struct compat_ebt_entry_mwt)) { \ - __match = (void *)(e) + __i; \ - __ret = fn(__match , ## args); \ - if (__ret != 0) \ - break; \ - } \ - if (__ret == 0) { \ - if (__i != (e)->watchers_offset) \ - __ret = -EINVAL; \ - } \ - __ret; \ -}) - /* called for all ebt_entry structures. */ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, unsigned int *total, @@ -2132,6 +2083,14 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, } } + if (state->buf_kern_start == NULL) { + unsigned int offset = buf_start - (char *) base; + + ret = xt_compat_add_offset(NFPROTO_BRIDGE, offset, new_offset); + if (ret < 0) + return ret; + } + startoff = state->buf_user_offset - startoff; BUG_ON(*total < startoff); @@ -2240,6 +2199,7 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); + xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; diff --git a/net/caif/Makefile b/net/caif/Makefile index 9d38e406e4a4..ebcd4e7e6f47 100644 --- a/net/caif/Makefile +++ b/net/caif/Makefile @@ -5,7 +5,7 @@ caif-y := caif_dev.o \ cffrml.o cfveil.o cfdbgl.o\ cfserl.o cfdgml.o \ cfrfml.o cfvidl.o cfutill.o \ - cfsrvl.o cfpkt_skbuff.o caif_config_util.o + cfsrvl.o cfpkt_skbuff.o obj-$(CONFIG_CAIF) += caif.o obj-$(CONFIG_CAIF_NETDEV) += chnl_net.o diff --git a/net/caif/caif_config_util.c b/net/caif/caif_config_util.c deleted file mode 100644 index d522d8c1703e..000000000000 --- a/net/caif/caif_config_util.c +++ /dev/null @@ -1,99 +0,0 @@ -/* - * Copyright (C) ST-Ericsson AB 2010 - * Author: Sjur Brendeland sjur.brandeland@stericsson.com - * License terms: GNU General Public License (GPL) version 2 - */ - -#include <linux/module.h> -#include <linux/spinlock.h> -#include <net/caif/cfctrl.h> -#include <net/caif/cfcnfg.h> -#include <net/caif/caif_dev.h> - -int connect_req_to_link_param(struct cfcnfg *cnfg, - struct caif_connect_request *s, - struct cfctrl_link_param *l) -{ - struct dev_info *dev_info; - enum cfcnfg_phy_preference pref; - int res; - - memset(l, 0, sizeof(*l)); - /* In caif protocol low value is high priority */ - l->priority = CAIF_PRIO_MAX - s->priority + 1; - - if (s->ifindex != 0){ - res = cfcnfg_get_id_from_ifi(cnfg, s->ifindex); - if (res < 0) - return res; - l->phyid = res; - } - else { - switch (s->link_selector) { - case CAIF_LINK_HIGH_BANDW: - pref = CFPHYPREF_HIGH_BW; - break; - case CAIF_LINK_LOW_LATENCY: - pref = CFPHYPREF_LOW_LAT; - break; - default: - return -EINVAL; - } - dev_info = cfcnfg_get_phyid(cnfg, pref); - if (dev_info == NULL) - return -ENODEV; - l->phyid = dev_info->id; - } - switch (s->protocol) { - case CAIFPROTO_AT: - l->linktype = CFCTRL_SRV_VEI; - if (s->sockaddr.u.at.type == CAIF_ATTYPE_PLAIN) - l->chtype = 0x02; - else - l->chtype = s->sockaddr.u.at.type; - l->endpoint = 0x00; - break; - case CAIFPROTO_DATAGRAM: - l->linktype = CFCTRL_SRV_DATAGRAM; - l->chtype = 0x00; - l->u.datagram.connid = s->sockaddr.u.dgm.connection_id; - break; - case CAIFPROTO_DATAGRAM_LOOP: - l->linktype = CFCTRL_SRV_DATAGRAM; - l->chtype = 0x03; - l->endpoint = 0x00; - l->u.datagram.connid = s->sockaddr.u.dgm.connection_id; - break; - case CAIFPROTO_RFM: - l->linktype = CFCTRL_SRV_RFM; - l->u.datagram.connid = s->sockaddr.u.rfm.connection_id; - strncpy(l->u.rfm.volume, s->sockaddr.u.rfm.volume, - sizeof(l->u.rfm.volume)-1); - l->u.rfm.volume[sizeof(l->u.rfm.volume)-1] = 0; - break; - case CAIFPROTO_UTIL: - l->linktype = CFCTRL_SRV_UTIL; - l->endpoint = 0x00; - l->chtype = 0x00; - strncpy(l->u.utility.name, s->sockaddr.u.util.service, - sizeof(l->u.utility.name)-1); - l->u.utility.name[sizeof(l->u.utility.name)-1] = 0; - caif_assert(sizeof(l->u.utility.name) > 10); - l->u.utility.paramlen = s->param.size; - if (l->u.utility.paramlen > sizeof(l->u.utility.params)) - l->u.utility.paramlen = sizeof(l->u.utility.params); - - memcpy(l->u.utility.params, s->param.data, - l->u.utility.paramlen); - - break; - case CAIFPROTO_DEBUG: - l->linktype = CFCTRL_SRV_DBG; - l->endpoint = s->sockaddr.u.dbg.service; - l->chtype = s->sockaddr.u.dbg.type; - break; - default: - return -EINVAL; - } - return 0; -} diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index a42a408306e4..682c0fedf360 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -12,49 +12,51 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/version.h> -#include <linux/module.h> #include <linux/kernel.h> #include <linux/if_arp.h> #include <linux/net.h> #include <linux/netdevice.h> -#include <linux/skbuff.h> -#include <linux/sched.h> -#include <linux/wait.h> +#include <linux/mutex.h> #include <net/netns/generic.h> #include <net/net_namespace.h> #include <net/pkt_sched.h> #include <net/caif/caif_device.h> -#include <net/caif/caif_dev.h> #include <net/caif/caif_layer.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> MODULE_LICENSE("GPL"); -#define TIMEOUT (HZ*5) /* Used for local tracking of the CAIF net devices */ struct caif_device_entry { struct cflayer layer; struct list_head list; - atomic_t in_use; - atomic_t state; - u16 phyid; struct net_device *netdev; - wait_queue_head_t event; + int __percpu *pcpu_refcnt; }; struct caif_device_entry_list { struct list_head list; /* Protects simulanous deletes in list */ - spinlock_t lock; + struct mutex lock; }; struct caif_net { + struct cfcnfg *cfg; struct caif_device_entry_list caifdevs; }; static int caif_net_id; -static struct cfcnfg *cfg; + +struct cfcnfg *get_cfcnfg(struct net *net) +{ + struct caif_net *caifn; + BUG_ON(!net); + caifn = net_generic(net, caif_net_id); + BUG_ON(!caifn); + return caifn->cfg; +} +EXPORT_SYMBOL(get_cfcnfg); static struct caif_device_entry_list *caif_device_list(struct net *net) { @@ -65,19 +67,39 @@ static struct caif_device_entry_list *caif_device_list(struct net *net) return &caifn->caifdevs; } +static void caifd_put(struct caif_device_entry *e) +{ + irqsafe_cpu_dec(*e->pcpu_refcnt); +} + +static void caifd_hold(struct caif_device_entry *e) +{ + irqsafe_cpu_inc(*e->pcpu_refcnt); +} + +static int caifd_refcnt_read(struct caif_device_entry *e) +{ + int i, refcnt = 0; + for_each_possible_cpu(i) + refcnt += *per_cpu_ptr(e->pcpu_refcnt, i); + return refcnt; +} + /* Allocate new CAIF device. */ static struct caif_device_entry *caif_device_alloc(struct net_device *dev) { struct caif_device_entry_list *caifdevs; struct caif_device_entry *caifd; + caifdevs = caif_device_list(dev_net(dev)); BUG_ON(!caifdevs); + caifd = kzalloc(sizeof(*caifd), GFP_ATOMIC); if (!caifd) return NULL; + caifd->pcpu_refcnt = alloc_percpu(int); caifd->netdev = dev; - list_add(&caifd->list, &caifdevs->list); - init_waitqueue_head(&caifd->event); + dev_hold(dev); return caifd; } @@ -87,98 +109,65 @@ static struct caif_device_entry *caif_get(struct net_device *dev) caif_device_list(dev_net(dev)); struct caif_device_entry *caifd; BUG_ON(!caifdevs); - list_for_each_entry(caifd, &caifdevs->list, list) { + list_for_each_entry_rcu(caifd, &caifdevs->list, list) { if (caifd->netdev == dev) return caifd; } return NULL; } -static void caif_device_destroy(struct net_device *dev) -{ - struct caif_device_entry_list *caifdevs = - caif_device_list(dev_net(dev)); - struct caif_device_entry *caifd; - ASSERT_RTNL(); - if (dev->type != ARPHRD_CAIF) - return; - - spin_lock_bh(&caifdevs->lock); - caifd = caif_get(dev); - if (caifd == NULL) { - spin_unlock_bh(&caifdevs->lock); - return; - } - - list_del(&caifd->list); - spin_unlock_bh(&caifdevs->lock); - - kfree(caifd); -} - static int transmit(struct cflayer *layer, struct cfpkt *pkt) { + int err; struct caif_device_entry *caifd = container_of(layer, struct caif_device_entry, layer); - struct sk_buff *skb, *skb2; - int ret = -EINVAL; + struct sk_buff *skb; + skb = cfpkt_tonative(pkt); skb->dev = caifd->netdev; - /* - * Don't allow SKB to be destroyed upon error, but signal resend - * notification to clients. We can't rely on the return value as - * congestion (NET_XMIT_CN) sometimes drops the packet, sometimes don't. - */ - if (netif_queue_stopped(caifd->netdev)) - return -EAGAIN; - skb2 = skb_get(skb); - - ret = dev_queue_xmit(skb2); - - if (!ret) - kfree_skb(skb); - else - return -EAGAIN; - return 0; -} + err = dev_queue_xmit(skb); + if (err > 0) + err = -EIO; -static int modemcmd(struct cflayer *layr, enum caif_modemcmd ctrl) -{ - struct caif_device_entry *caifd; - struct caif_dev_common *caifdev; - caifd = container_of(layr, struct caif_device_entry, layer); - caifdev = netdev_priv(caifd->netdev); - if (ctrl == _CAIF_MODEMCMD_PHYIF_USEFULL) { - atomic_set(&caifd->in_use, 1); - wake_up_interruptible(&caifd->event); - - } else if (ctrl == _CAIF_MODEMCMD_PHYIF_USELESS) { - atomic_set(&caifd->in_use, 0); - wake_up_interruptible(&caifd->event); - } - return 0; + return err; } /* - * Stuff received packets to associated sockets. + * Stuff received packets into the CAIF stack. * On error, returns non-zero and releases the skb. */ static int receive(struct sk_buff *skb, struct net_device *dev, struct packet_type *pkttype, struct net_device *orig_dev) { - struct net *net; struct cfpkt *pkt; struct caif_device_entry *caifd; - net = dev_net(dev); + int err; + pkt = cfpkt_fromnative(CAIF_DIR_IN, skb); + + rcu_read_lock(); caifd = caif_get(dev); - if (!caifd || !caifd->layer.up || !caifd->layer.up->receive) - return NET_RX_DROP; - if (caifd->layer.up->receive(caifd->layer.up, pkt)) + if (!caifd || !caifd->layer.up || !caifd->layer.up->receive || + !netif_oper_up(caifd->netdev)) { + rcu_read_unlock(); + kfree_skb(skb); return NET_RX_DROP; + } + + /* Hold reference to netdevice while using CAIF stack */ + caifd_hold(caifd); + rcu_read_unlock(); + + err = caifd->layer.up->receive(caifd->layer.up, pkt); + /* For -EILSEQ the packet is not freed so so it now */ + if (err == -EILSEQ) + cfpkt_destroy(pkt); + + /* Release reference to stack upwards */ + caifd_put(caifd); return 0; } @@ -189,15 +178,25 @@ static struct packet_type caif_packet_type __read_mostly = { static void dev_flowctrl(struct net_device *dev, int on) { - struct caif_device_entry *caifd = caif_get(dev); - if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) + struct caif_device_entry *caifd; + + rcu_read_lock(); + + caifd = caif_get(dev); + if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) { + rcu_read_unlock(); return; + } + + caifd_hold(caifd); + rcu_read_unlock(); caifd->layer.up->ctrlcmd(caifd->layer.up, on ? _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND : _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, caifd->layer.id); + caifd_put(caifd); } /* notify Caif of device events */ @@ -208,37 +207,28 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, struct caif_device_entry *caifd = NULL; struct caif_dev_common *caifdev; enum cfcnfg_phy_preference pref; - int res = -EINVAL; enum cfcnfg_phy_type phy_type; + struct cfcnfg *cfg; + struct caif_device_entry_list *caifdevs = + caif_device_list(dev_net(dev)); if (dev->type != ARPHRD_CAIF) return 0; + cfg = get_cfcnfg(dev_net(dev)); + if (cfg == NULL) + return 0; + switch (what) { case NETDEV_REGISTER: - netdev_info(dev, "register\n"); caifd = caif_device_alloc(dev); - if (caifd == NULL) - break; + if (!caifd) + return 0; + caifdev = netdev_priv(dev); caifdev->flowctrl = dev_flowctrl; - atomic_set(&caifd->state, what); - res = 0; - break; - case NETDEV_UP: - netdev_info(dev, "up\n"); - caifd = caif_get(dev); - if (caifd == NULL) - break; - caifdev = netdev_priv(dev); - if (atomic_read(&caifd->state) == NETDEV_UP) { - netdev_info(dev, "already up\n"); - break; - } - atomic_set(&caifd->state, what); caifd->layer.transmit = transmit; - caifd->layer.modemcmd = modemcmd; if (caifdev->use_frag) phy_type = CFPHYTYPE_FRAG; @@ -256,62 +246,94 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, pref = CFPHYPREF_HIGH_BW; break; } - dev_hold(dev); - cfcnfg_add_phy_layer(get_caif_conf(), + strncpy(caifd->layer.name, dev->name, + sizeof(caifd->layer.name) - 1); + caifd->layer.name[sizeof(caifd->layer.name) - 1] = 0; + + mutex_lock(&caifdevs->lock); + list_add_rcu(&caifd->list, &caifdevs->list); + + cfcnfg_add_phy_layer(cfg, phy_type, dev, &caifd->layer, - &caifd->phyid, pref, caifdev->use_fcs, caifdev->use_stx); - strncpy(caifd->layer.name, dev->name, - sizeof(caifd->layer.name) - 1); - caifd->layer.name[sizeof(caifd->layer.name) - 1] = 0; + mutex_unlock(&caifdevs->lock); break; - case NETDEV_GOING_DOWN: + case NETDEV_UP: + rcu_read_lock(); + caifd = caif_get(dev); - if (caifd == NULL) + if (caifd == NULL) { + rcu_read_unlock(); break; - netdev_info(dev, "going down\n"); + } - if (atomic_read(&caifd->state) == NETDEV_GOING_DOWN || - atomic_read(&caifd->state) == NETDEV_DOWN) - break; + cfcnfg_set_phy_state(cfg, &caifd->layer, true); + rcu_read_unlock(); - atomic_set(&caifd->state, what); - if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) - return -EINVAL; - caifd->layer.up->ctrlcmd(caifd->layer.up, - _CAIF_CTRLCMD_PHYIF_DOWN_IND, - caifd->layer.id); - might_sleep(); - res = wait_event_interruptible_timeout(caifd->event, - atomic_read(&caifd->in_use) == 0, - TIMEOUT); break; case NETDEV_DOWN: + rcu_read_lock(); + caifd = caif_get(dev); - if (caifd == NULL) - break; - netdev_info(dev, "down\n"); - if (atomic_read(&caifd->in_use)) - netdev_warn(dev, - "Unregistering an active CAIF device\n"); - cfcnfg_del_phy_layer(get_caif_conf(), &caifd->layer); - dev_put(dev); - atomic_set(&caifd->state, what); + if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) { + rcu_read_unlock(); + return -EINVAL; + } + + cfcnfg_set_phy_state(cfg, &caifd->layer, false); + caifd_hold(caifd); + rcu_read_unlock(); + + caifd->layer.up->ctrlcmd(caifd->layer.up, + _CAIF_CTRLCMD_PHYIF_DOWN_IND, + caifd->layer.id); + caifd_put(caifd); break; case NETDEV_UNREGISTER: + mutex_lock(&caifdevs->lock); + caifd = caif_get(dev); - if (caifd == NULL) + if (caifd == NULL) { + mutex_unlock(&caifdevs->lock); + break; + } + list_del_rcu(&caifd->list); + + /* + * NETDEV_UNREGISTER is called repeatedly until all reference + * counts for the net-device are released. If references to + * caifd is taken, simply ignore NETDEV_UNREGISTER and wait for + * the next call to NETDEV_UNREGISTER. + * + * If any packets are in flight down the CAIF Stack, + * cfcnfg_del_phy_layer will return nonzero. + * If no packets are in flight, the CAIF Stack associated + * with the net-device un-registering is freed. + */ + + if (caifd_refcnt_read(caifd) != 0 || + cfcnfg_del_phy_layer(cfg, &caifd->layer) != 0) { + + pr_info("Wait for device inuse\n"); + /* Enrole device if CAIF Stack is still in use */ + list_add_rcu(&caifd->list, &caifdevs->list); + mutex_unlock(&caifdevs->lock); break; - netdev_info(dev, "unregister\n"); - atomic_set(&caifd->state, what); - caif_device_destroy(dev); + } + + synchronize_rcu(); + dev_put(caifd->netdev); + free_percpu(caifd->pcpu_refcnt); + kfree(caifd); + + mutex_unlock(&caifdevs->lock); break; } return 0; @@ -322,61 +344,60 @@ static struct notifier_block caif_device_notifier = { .priority = 0, }; - -struct cfcnfg *get_caif_conf(void) -{ - return cfg; -} -EXPORT_SYMBOL(get_caif_conf); - -int caif_connect_client(struct caif_connect_request *conn_req, - struct cflayer *client_layer, int *ifindex, - int *headroom, int *tailroom) -{ - struct cfctrl_link_param param; - int ret; - ret = connect_req_to_link_param(get_caif_conf(), conn_req, ¶m); - if (ret) - return ret; - /* Hook up the adaptation layer. */ - return cfcnfg_add_adaptation_layer(get_caif_conf(), ¶m, - client_layer, ifindex, - headroom, tailroom); -} -EXPORT_SYMBOL(caif_connect_client); - -int caif_disconnect_client(struct cflayer *adap_layer) -{ - return cfcnfg_disconn_adapt_layer(get_caif_conf(), adap_layer); -} -EXPORT_SYMBOL(caif_disconnect_client); - -void caif_release_client(struct cflayer *adap_layer) -{ - cfcnfg_release_adap_layer(adap_layer); -} -EXPORT_SYMBOL(caif_release_client); - /* Per-namespace Caif devices handling */ static int caif_init_net(struct net *net) { struct caif_net *caifn = net_generic(net, caif_net_id); + BUG_ON(!caifn); INIT_LIST_HEAD(&caifn->caifdevs.list); - spin_lock_init(&caifn->caifdevs.lock); + mutex_init(&caifn->caifdevs.lock); + + caifn->cfg = cfcnfg_create(); + if (!caifn->cfg) { + pr_warn("can't create cfcnfg\n"); + return -ENOMEM; + } + return 0; } static void caif_exit_net(struct net *net) { - struct net_device *dev; - int res; + struct caif_device_entry *caifd, *tmp; + struct caif_device_entry_list *caifdevs = + caif_device_list(net); + struct cfcnfg *cfg; + rtnl_lock(); - for_each_netdev(net, dev) { - if (dev->type != ARPHRD_CAIF) - continue; - res = dev_close(dev); - caif_device_destroy(dev); + mutex_lock(&caifdevs->lock); + + cfg = get_cfcnfg(net); + if (cfg == NULL) { + mutex_unlock(&caifdevs->lock); + return; } + + list_for_each_entry_safe(caifd, tmp, &caifdevs->list, list) { + int i = 0; + list_del_rcu(&caifd->list); + cfcnfg_set_phy_state(cfg, &caifd->layer, false); + + while (i < 10 && + (caifd_refcnt_read(caifd) != 0 || + cfcnfg_del_phy_layer(cfg, &caifd->layer) != 0)) { + + pr_info("Wait for device inuse\n"); + msleep(250); + i++; + } + synchronize_rcu(); + dev_put(caifd->netdev); + free_percpu(caifd->pcpu_refcnt); + kfree(caifd); + } + cfcnfg_remove(cfg); + + mutex_unlock(&caifdevs->lock); rtnl_unlock(); } @@ -391,32 +412,23 @@ static struct pernet_operations caif_net_ops = { static int __init caif_device_init(void) { int result; - cfg = cfcnfg_create(); - if (!cfg) { - pr_warn("can't create cfcnfg\n"); - goto err_cfcnfg_create_failed; - } + result = register_pernet_device(&caif_net_ops); - if (result) { - kfree(cfg); - cfg = NULL; + if (result) return result; - } - dev_add_pack(&caif_packet_type); + register_netdevice_notifier(&caif_device_notifier); + dev_add_pack(&caif_packet_type); return result; -err_cfcnfg_create_failed: - return -ENODEV; } static void __exit caif_device_exit(void) { - dev_remove_pack(&caif_packet_type); unregister_pernet_device(&caif_net_ops); unregister_netdevice_notifier(&caif_device_notifier); - cfcnfg_remove(cfg); + dev_remove_pack(&caif_packet_type); } module_init(caif_device_init); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 8184c031d028..a98628086452 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -19,7 +19,7 @@ #include <linux/uaccess.h> #include <linux/debugfs.h> #include <linux/caif/caif_socket.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <net/sock.h> #include <net/tcp_states.h> #include <net/caif/caif_layer.h> @@ -48,6 +48,7 @@ static struct dentry *debugfsdir; #ifdef CONFIG_DEBUG_FS struct debug_fs_counter { atomic_t caif_nr_socks; + atomic_t caif_sock_create; atomic_t num_connect_req; atomic_t num_connect_resp; atomic_t num_connect_fail_resp; @@ -59,11 +60,11 @@ struct debug_fs_counter { atomic_t num_rx_flow_on; }; static struct debug_fs_counter cnt; -#define dbfs_atomic_inc(v) atomic_inc(v) -#define dbfs_atomic_dec(v) atomic_dec(v) +#define dbfs_atomic_inc(v) atomic_inc_return(v) +#define dbfs_atomic_dec(v) atomic_dec_return(v) #else -#define dbfs_atomic_inc(v) -#define dbfs_atomic_dec(v) +#define dbfs_atomic_inc(v) 0 +#define dbfs_atomic_dec(v) 0 #endif struct caifsock { @@ -155,9 +156,10 @@ 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)) { - pr_debug("sending flow OFF (queue len = %d %d)\n", - atomic_read(&cf_sk->sk.sk_rmem_alloc), - sk_rcvbuf_lowwater(cf_sk)); + if (net_ratelimit()) + 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); dbfs_atomic_inc(&cnt.num_rx_flow_off); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); @@ -168,7 +170,8 @@ 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); - pr_debug("sending flow OFF due to rmem_schedule\n"); + if (net_ratelimit()) + 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); } @@ -202,13 +205,25 @@ static int caif_sktrecv_cb(struct cflayer *layr, struct cfpkt *pkt) skb = cfpkt_tonative(pkt); if (unlikely(cf_sk->sk.sk_state != CAIF_CONNECTED)) { - cfpkt_destroy(pkt); + kfree_skb(skb); return 0; } caif_queue_rcv_skb(&cf_sk->sk, skb); return 0; } +static void cfsk_hold(struct cflayer *layr) +{ + struct caifsock *cf_sk = container_of(layr, struct caifsock, layer); + sock_hold(&cf_sk->sk); +} + +static void cfsk_put(struct cflayer *layr) +{ + struct caifsock *cf_sk = container_of(layr, struct caifsock, layer); + sock_put(&cf_sk->sk); +} + /* Packet Control Callback function called from CAIF */ static void caif_ctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow, @@ -232,6 +247,8 @@ static void caif_ctrl_cb(struct cflayer *layr, case CAIF_CTRLCMD_INIT_RSP: /* We're now connected */ + caif_client_register_refcnt(&cf_sk->layer, + cfsk_hold, cfsk_put); dbfs_atomic_inc(&cnt.num_connect_resp); cf_sk->sk.sk_state = CAIF_CONNECTED; set_tx_flow_on(cf_sk); @@ -242,7 +259,6 @@ static void caif_ctrl_cb(struct cflayer *layr, /* We're now disconnected */ cf_sk->sk.sk_state = CAIF_DISCONNECTED; cf_sk->sk.sk_state_change(&cf_sk->sk); - cfcnfg_release_adap_layer(&cf_sk->layer); break; case CAIF_CTRLCMD_INIT_FAIL_RSP: @@ -519,43 +535,14 @@ static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk, int noblock, long timeo) { struct cfpkt *pkt; - int ret, loopcnt = 0; pkt = cfpkt_fromnative(CAIF_DIR_OUT, skb); - memset(cfpkt_info(pkt), 0, sizeof(struct caif_payload_info)); - do { + memset(skb->cb, 0, sizeof(struct caif_payload_info)); - ret = -ETIMEDOUT; + if (cf_sk->layer.dn == NULL) + return -EINVAL; - /* Slight paranoia, probably not needed. */ - if (unlikely(loopcnt++ > 1000)) { - pr_warn("transmit retries failed, error = %d\n", ret); - break; - } - - if (cf_sk->layer.dn != NULL) - ret = cf_sk->layer.dn->transmit(cf_sk->layer.dn, pkt); - if (likely(ret >= 0)) - break; - /* if transmit return -EAGAIN, then retry */ - if (noblock && ret == -EAGAIN) - break; - timeo = caif_wait_for_flow_on(cf_sk, 0, timeo, &ret); - if (signal_pending(current)) { - ret = sock_intr_errno(timeo); - break; - } - if (ret) - break; - if (cf_sk->sk.sk_state != CAIF_CONNECTED || - sock_flag(&cf_sk->sk, SOCK_DEAD) || - (cf_sk->sk.sk_shutdown & RCV_SHUTDOWN)) { - ret = -EPIPE; - cf_sk->sk.sk_err = EPIPE; - break; - } - } while (ret == -EAGAIN); - return ret; + return cf_sk->layer.dn->transmit(cf_sk->layer.dn, pkt); } /* Copied from af_unix:unix_dgram_sendmsg, and adapted to CAIF */ @@ -620,7 +607,9 @@ static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock, goto err; ret = transmit_skb(skb, cf_sk, noblock, timeo); if (ret < 0) - goto err; + /* skb is already freed */ + return ret; + return len; err: kfree_skb(skb); @@ -826,7 +815,8 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr, sk->sk_state == CAIF_DISCONNECTED); if (sk->sk_shutdown & SHUTDOWN_MASK) { /* Allow re-connect after SHUTDOWN_IND */ - caif_disconnect_client(&cf_sk->layer); + caif_disconnect_client(sock_net(sk), &cf_sk->layer); + caif_free_client(&cf_sk->layer); break; } /* No reconnect on a seqpacket socket */ @@ -866,8 +856,10 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr, dbfs_atomic_inc(&cnt.num_connect_req); cf_sk->layer.receive = caif_sktrecv_cb; - err = caif_connect_client(&cf_sk->conn_req, + + err = caif_connect_client(sock_net(sk), &cf_sk->conn_req, &cf_sk->layer, &ifindex, &headroom, &tailroom); + if (err < 0) { cf_sk->sk.sk_socket->state = SS_UNCONNECTED; cf_sk->sk.sk_state = CAIF_DISCONNECTED; @@ -935,7 +927,6 @@ static int caif_release(struct socket *sock) { struct sock *sk = sock->sk; struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); - int res = 0; if (!sk) return 0; @@ -947,13 +938,14 @@ static int caif_release(struct socket *sock) * caif_queue_rcv_skb checks SOCK_DEAD holding the queue lock, * this ensures no packets when sock is dead. */ - spin_lock(&sk->sk_receive_queue.lock); + spin_lock_bh(&sk->sk_receive_queue.lock); sock_set_flag(sk, SOCK_DEAD); - spin_unlock(&sk->sk_receive_queue.lock); + spin_unlock_bh(&sk->sk_receive_queue.lock); sock->sk = NULL; dbfs_atomic_inc(&cnt.num_disconnect); + WARN_ON(IS_ERR(cf_sk->debugfs_socket_dir)); if (cf_sk->debugfs_socket_dir != NULL) debugfs_remove_recursive(cf_sk->debugfs_socket_dir); @@ -961,19 +953,15 @@ static int caif_release(struct socket *sock) sk->sk_state = CAIF_DISCONNECTED; sk->sk_shutdown = SHUTDOWN_MASK; - if (cf_sk->sk.sk_socket->state == SS_CONNECTED || - cf_sk->sk.sk_socket->state == SS_CONNECTING) - res = caif_disconnect_client(&cf_sk->layer); - + caif_disconnect_client(sock_net(sk), &cf_sk->layer); cf_sk->sk.sk_socket->state = SS_DISCONNECTING; wake_up_interruptible_poll(sk_sleep(sk), POLLERR|POLLHUP); sock_orphan(sk); - cf_sk->layer.dn = NULL; sk_stream_kill_queues(&cf_sk->sk); release_sock(sk); sock_put(sk); - return res; + return 0; } /* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */ @@ -1060,16 +1048,18 @@ static void caif_sock_destructor(struct sock *sk) caif_assert(sk_unhashed(sk)); caif_assert(!sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { - pr_info("Attempt to release alive CAIF socket: %p\n", sk); + pr_debug("Attempt to release alive CAIF socket: %p\n", sk); return; } sk_stream_kill_queues(&cf_sk->sk); dbfs_atomic_dec(&cnt.caif_nr_socks); + caif_free_client(&cf_sk->layer); } static int caif_create(struct net *net, struct socket *sock, int protocol, int kern) { + int num; struct sock *sk = NULL; struct caifsock *cf_sk = NULL; static struct proto prot = {.name = "PF_CAIF", @@ -1127,19 +1117,21 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, set_rx_flow_on(cf_sk); /* Set default options on configuration */ - cf_sk->sk.sk_priority= CAIF_PRIO_NORMAL; + cf_sk->sk.sk_priority = CAIF_PRIO_NORMAL; cf_sk->conn_req.link_selector = CAIF_LINK_LOW_LATENCY; cf_sk->conn_req.protocol = protocol; /* Increase the number of sockets created. */ dbfs_atomic_inc(&cnt.caif_nr_socks); + num = dbfs_atomic_inc(&cnt.caif_sock_create); #ifdef CONFIG_DEBUG_FS if (!IS_ERR(debugfsdir)) { + /* Fill in some information concerning the misc socket. */ - snprintf(cf_sk->name, sizeof(cf_sk->name), "cfsk%d", - atomic_read(&cnt.caif_nr_socks)); + snprintf(cf_sk->name, sizeof(cf_sk->name), "cfsk%d", num); cf_sk->debugfs_socket_dir = debugfs_create_dir(cf_sk->name, debugfsdir); + debugfs_create_u32("sk_state", S_IRUSR | S_IWUSR, cf_sk->debugfs_socket_dir, (u32 *) &cf_sk->sk.sk_state); @@ -1183,6 +1175,9 @@ static int __init caif_sktinit_module(void) debugfs_create_u32("num_sockets", S_IRUSR | S_IWUSR, debugfsdir, (u32 *) &cnt.caif_nr_socks); + debugfs_create_u32("num_create", S_IRUSR | S_IWUSR, + debugfsdir, + (u32 *) &cnt.caif_sock_create); debugfs_create_u32("num_connect_req", S_IRUSR | S_IWUSR, debugfsdir, (u32 *) &cnt.num_connect_req); diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index f1f98d967d8a..52fe33bee029 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -10,6 +10,7 @@ #include <linux/stddef.h> #include <linux/slab.h> #include <linux/netdevice.h> +#include <linux/module.h> #include <net/caif/caif_layer.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> @@ -18,11 +19,7 @@ #include <net/caif/cffrml.h> #include <net/caif/cfserl.h> #include <net/caif/cfsrvl.h> - -#include <linux/module.h> -#include <asm/atomic.h> - -#define MAX_PHY_LAYERS 7 +#include <net/caif/caif_dev.h> #define container_obj(layr) container_of(layr, struct cfcnfg, layer) @@ -30,6 +27,9 @@ * to manage physical interfaces */ struct cfcnfg_phyinfo { + struct list_head node; + bool up; + /* Pointer to the layer below the MUX (framing layer) */ struct cflayer *frm_layer; /* Pointer to the lowest actual physical layer */ @@ -39,9 +39,6 @@ struct cfcnfg_phyinfo { /* Preference of the physical in interface */ enum cfcnfg_phy_preference pref; - /* Reference count, number of channels using the device */ - int phy_ref_count; - /* Information about the physical device */ struct dev_info dev_info; @@ -59,8 +56,8 @@ struct cfcnfg { struct cflayer layer; struct cflayer *ctrl; struct cflayer *mux; - u8 last_phyid; - struct cfcnfg_phyinfo phy_layers[MAX_PHY_LAYERS]; + struct list_head phys; + struct mutex lock; }; static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, @@ -76,6 +73,9 @@ struct cfcnfg *cfcnfg_create(void) { struct cfcnfg *this; struct cfctrl_rsp *resp; + + might_sleep(); + /* Initiate this layer */ this = kzalloc(sizeof(struct cfcnfg), GFP_ATOMIC); if (!this) { @@ -99,27 +99,33 @@ struct cfcnfg *cfcnfg_create(void) resp->radioset_rsp = cfctrl_resp_func; resp->linksetup_rsp = cfcnfg_linkup_rsp; resp->reject_rsp = cfcnfg_reject_rsp; - - this->last_phyid = 1; + INIT_LIST_HEAD(&this->phys); cfmuxl_set_uplayer(this->mux, this->ctrl, 0); layer_set_dn(this->ctrl, this->mux); layer_set_up(this->ctrl, this); + mutex_init(&this->lock); + return this; out_of_mem: pr_warn("Out of memory\n"); + + synchronize_rcu(); + kfree(this->mux); kfree(this->ctrl); kfree(this); return NULL; } -EXPORT_SYMBOL(cfcnfg_create); void cfcnfg_remove(struct cfcnfg *cfg) { + might_sleep(); if (cfg) { + synchronize_rcu(); + kfree(cfg->mux); - kfree(cfg->ctrl); + cfctrl_remove(cfg->ctrl); kfree(cfg); } } @@ -128,132 +134,83 @@ static void cfctrl_resp_func(void) { } +static struct cfcnfg_phyinfo *cfcnfg_get_phyinfo_rcu(struct cfcnfg *cnfg, + u8 phyid) +{ + struct cfcnfg_phyinfo *phy; + + list_for_each_entry_rcu(phy, &cnfg->phys, node) + if (phy->id == phyid) + return phy; + return NULL; +} + static void cfctrl_enum_resp(void) { } -struct dev_info *cfcnfg_get_phyid(struct cfcnfg *cnfg, +static struct dev_info *cfcnfg_get_phyid(struct cfcnfg *cnfg, enum cfcnfg_phy_preference phy_pref) { - u16 i; - /* Try to match with specified preference */ - for (i = 1; i < MAX_PHY_LAYERS; i++) { - if (cnfg->phy_layers[i].id == i && - cnfg->phy_layers[i].pref == phy_pref && - cnfg->phy_layers[i].frm_layer != NULL) { - caif_assert(cnfg->phy_layers != NULL); - caif_assert(cnfg->phy_layers[i].id == i); - return &cnfg->phy_layers[i].dev_info; - } + struct cfcnfg_phyinfo *phy; + + list_for_each_entry_rcu(phy, &cnfg->phys, node) { + if (phy->up && phy->pref == phy_pref && + phy->frm_layer != NULL) + + return &phy->dev_info; } + /* Otherwise just return something */ - for (i = 1; i < MAX_PHY_LAYERS; i++) { - if (cnfg->phy_layers[i].id == i) { - caif_assert(cnfg->phy_layers != NULL); - caif_assert(cnfg->phy_layers[i].id == i); - return &cnfg->phy_layers[i].dev_info; - } - } + list_for_each_entry_rcu(phy, &cnfg->phys, node) + if (phy->up) + return &phy->dev_info; return NULL; } -static struct cfcnfg_phyinfo *cfcnfg_get_phyinfo(struct cfcnfg *cnfg, - u8 phyid) +static int cfcnfg_get_id_from_ifi(struct cfcnfg *cnfg, int ifi) { - int i; - /* Try to match with specified preference */ - for (i = 0; i < MAX_PHY_LAYERS; i++) - if (cnfg->phy_layers[i].frm_layer != NULL && - cnfg->phy_layers[i].id == phyid) - return &cnfg->phy_layers[i]; - return NULL; -} + struct cfcnfg_phyinfo *phy; - -int cfcnfg_get_id_from_ifi(struct cfcnfg *cnfg, int ifi) -{ - int i; - for (i = 0; i < MAX_PHY_LAYERS; i++) - if (cnfg->phy_layers[i].frm_layer != NULL && - cnfg->phy_layers[i].ifindex == ifi) - return i; + list_for_each_entry_rcu(phy, &cnfg->phys, node) + if (phy->ifindex == ifi && phy->up) + return phy->id; return -ENODEV; } -int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) +int caif_disconnect_client(struct net *net, struct cflayer *adap_layer) { - u8 channel_id = 0; - int ret = 0; - struct cflayer *servl = NULL; - struct cfcnfg_phyinfo *phyinfo = NULL; - u8 phyid = 0; + u8 channel_id; + struct cfcnfg *cfg = get_cfcnfg(net); caif_assert(adap_layer != NULL); + cfctrl_cancel_req(cfg->ctrl, adap_layer); channel_id = adap_layer->id; - if (adap_layer->dn == NULL || channel_id == 0) { - pr_err("adap_layer->dn == NULL or adap_layer->id is 0\n"); - ret = -ENOTCONN; - goto end; - } - servl = cfmuxl_remove_uplayer(cnfg->mux, channel_id); - if (servl == NULL) { - pr_err("PROTOCOL ERROR - Error removing service_layer Channel_Id(%d)", - channel_id); - ret = -EINVAL; - goto end; - } - layer_set_up(servl, NULL); - ret = cfctrl_linkdown_req(cnfg->ctrl, channel_id, adap_layer); - if (ret) - goto end; - caif_assert(channel_id == servl->id); - if (adap_layer->dn != NULL) { - phyid = cfsrvl_getphyid(adap_layer->dn); - - phyinfo = cfcnfg_get_phyinfo(cnfg, phyid); - if (phyinfo == NULL) { - pr_warn("No interface to send disconnect to\n"); - ret = -ENODEV; - goto end; - } - if (phyinfo->id != phyid || - phyinfo->phy_layer->id != phyid || - phyinfo->frm_layer->id != phyid) { - pr_err("Inconsistency in phy registration\n"); - ret = -EINVAL; - goto end; - } - } - if (phyinfo != NULL && --phyinfo->phy_ref_count == 0 && - phyinfo->phy_layer != NULL && - phyinfo->phy_layer->modemcmd != NULL) { - phyinfo->phy_layer->modemcmd(phyinfo->phy_layer, - _CAIF_MODEMCMD_PHYIF_USELESS); - } -end: - cfsrvl_put(servl); - cfctrl_cancel_req(cnfg->ctrl, adap_layer); + if (channel_id != 0) { + struct cflayer *servl; + servl = cfmuxl_remove_uplayer(cfg->mux, channel_id); + if (servl != NULL) + layer_set_up(servl, NULL); + } else + pr_debug("nothing to disconnect\n"); + cfctrl_linkdown_req(cfg->ctrl, channel_id, adap_layer); + + /* Do RCU sync before initiating cleanup */ + synchronize_rcu(); if (adap_layer->ctrlcmd != NULL) adap_layer->ctrlcmd(adap_layer, CAIF_CTRLCMD_DEINIT_RSP, 0); - return ret; - -} -EXPORT_SYMBOL(cfcnfg_disconn_adapt_layer); + return 0; -void cfcnfg_release_adap_layer(struct cflayer *adap_layer) -{ - if (adap_layer->dn) - cfsrvl_put(adap_layer->dn); } -EXPORT_SYMBOL(cfcnfg_release_adap_layer); +EXPORT_SYMBOL(caif_disconnect_client); static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id) { } -int protohead[CFCTRL_SRV_MASK] = { +static const int protohead[CFCTRL_SRV_MASK] = { [CFCTRL_SRV_VEI] = 4, [CFCTRL_SRV_DATAGRAM] = 7, [CFCTRL_SRV_UTIL] = 4, @@ -261,49 +218,157 @@ int protohead[CFCTRL_SRV_MASK] = { [CFCTRL_SRV_DBG] = 3, }; -int cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, - struct cfctrl_link_param *param, - struct cflayer *adap_layer, - int *ifindex, + +static int caif_connect_req_to_link_param(struct cfcnfg *cnfg, + struct caif_connect_request *s, + struct cfctrl_link_param *l) +{ + struct dev_info *dev_info; + enum cfcnfg_phy_preference pref; + int res; + + memset(l, 0, sizeof(*l)); + /* In caif protocol low value is high priority */ + l->priority = CAIF_PRIO_MAX - s->priority + 1; + + if (s->ifindex != 0) { + res = cfcnfg_get_id_from_ifi(cnfg, s->ifindex); + if (res < 0) + return res; + l->phyid = res; + } else { + switch (s->link_selector) { + case CAIF_LINK_HIGH_BANDW: + pref = CFPHYPREF_HIGH_BW; + break; + case CAIF_LINK_LOW_LATENCY: + pref = CFPHYPREF_LOW_LAT; + break; + default: + return -EINVAL; + } + dev_info = cfcnfg_get_phyid(cnfg, pref); + if (dev_info == NULL) + return -ENODEV; + l->phyid = dev_info->id; + } + switch (s->protocol) { + case CAIFPROTO_AT: + l->linktype = CFCTRL_SRV_VEI; + l->endpoint = (s->sockaddr.u.at.type >> 2) & 0x3; + l->chtype = s->sockaddr.u.at.type & 0x3; + break; + case CAIFPROTO_DATAGRAM: + l->linktype = CFCTRL_SRV_DATAGRAM; + l->chtype = 0x00; + l->u.datagram.connid = s->sockaddr.u.dgm.connection_id; + break; + case CAIFPROTO_DATAGRAM_LOOP: + l->linktype = CFCTRL_SRV_DATAGRAM; + l->chtype = 0x03; + l->endpoint = 0x00; + l->u.datagram.connid = s->sockaddr.u.dgm.connection_id; + break; + case CAIFPROTO_RFM: + l->linktype = CFCTRL_SRV_RFM; + l->u.datagram.connid = s->sockaddr.u.rfm.connection_id; + strncpy(l->u.rfm.volume, s->sockaddr.u.rfm.volume, + sizeof(l->u.rfm.volume)-1); + l->u.rfm.volume[sizeof(l->u.rfm.volume)-1] = 0; + break; + case CAIFPROTO_UTIL: + l->linktype = CFCTRL_SRV_UTIL; + l->endpoint = 0x00; + l->chtype = 0x00; + strncpy(l->u.utility.name, s->sockaddr.u.util.service, + sizeof(l->u.utility.name)-1); + l->u.utility.name[sizeof(l->u.utility.name)-1] = 0; + caif_assert(sizeof(l->u.utility.name) > 10); + l->u.utility.paramlen = s->param.size; + if (l->u.utility.paramlen > sizeof(l->u.utility.params)) + l->u.utility.paramlen = sizeof(l->u.utility.params); + + memcpy(l->u.utility.params, s->param.data, + l->u.utility.paramlen); + + break; + case CAIFPROTO_DEBUG: + l->linktype = CFCTRL_SRV_DBG; + l->endpoint = s->sockaddr.u.dbg.service; + l->chtype = s->sockaddr.u.dbg.type; + break; + default: + return -EINVAL; + } + return 0; +} + +int caif_connect_client(struct net *net, struct caif_connect_request *conn_req, + struct cflayer *adap_layer, int *ifindex, int *proto_head, int *proto_tail) { struct cflayer *frml; + struct cfcnfg_phyinfo *phy; + int err; + struct cfctrl_link_param param; + struct cfcnfg *cfg = get_cfcnfg(net); + caif_assert(cfg != NULL); + + rcu_read_lock(); + err = caif_connect_req_to_link_param(cfg, conn_req, ¶m); + if (err) + goto unlock; + + phy = cfcnfg_get_phyinfo_rcu(cfg, param.phyid); + if (!phy) { + err = -ENODEV; + goto unlock; + } + err = -EINVAL; + if (adap_layer == NULL) { pr_err("adap_layer is zero\n"); - return -EINVAL; + goto unlock; } if (adap_layer->receive == NULL) { pr_err("adap_layer->receive is NULL\n"); - return -EINVAL; + goto unlock; } if (adap_layer->ctrlcmd == NULL) { pr_err("adap_layer->ctrlcmd == NULL\n"); - return -EINVAL; + goto unlock; } - frml = cnfg->phy_layers[param->phyid].frm_layer; + + err = -ENODEV; + frml = phy->frm_layer; if (frml == NULL) { pr_err("Specified PHY type does not exist!\n"); - return -ENODEV; + goto unlock; } - caif_assert(param->phyid == cnfg->phy_layers[param->phyid].id); - caif_assert(cnfg->phy_layers[param->phyid].frm_layer->id == - param->phyid); - caif_assert(cnfg->phy_layers[param->phyid].phy_layer->id == - param->phyid); + caif_assert(param.phyid == phy->id); + caif_assert(phy->frm_layer->id == + param.phyid); + caif_assert(phy->phy_layer->id == + param.phyid); - *ifindex = cnfg->phy_layers[param->phyid].ifindex; + *ifindex = phy->ifindex; + *proto_tail = 2; *proto_head = - protohead[param->linktype]+ - (cnfg->phy_layers[param->phyid].use_stx ? 1 : 0); - *proto_tail = 2; + protohead[param.linktype] + (phy->use_stx ? 1 : 0); + + rcu_read_unlock(); /* FIXME: ENUMERATE INITIALLY WHEN ACTIVATING PHYSICAL INTERFACE */ - cfctrl_enum_req(cnfg->ctrl, param->phyid); - return cfctrl_linkup_request(cnfg->ctrl, param, adap_layer); + cfctrl_enum_req(cfg->ctrl, param.phyid); + return cfctrl_linkup_request(cfg->ctrl, ¶m, adap_layer); + +unlock: + rcu_read_unlock(); + return err; } -EXPORT_SYMBOL(cfcnfg_add_adaptation_layer); +EXPORT_SYMBOL(caif_connect_client); static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *adapt_layer) @@ -315,32 +380,45 @@ static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, - u8 phyid, struct cflayer *adapt_layer) + u8 phyid, struct cflayer *adapt_layer) { struct cfcnfg *cnfg = container_obj(layer); struct cflayer *servicel = NULL; struct cfcnfg_phyinfo *phyinfo; struct net_device *netdev; + if (channel_id == 0) { + pr_warn("received channel_id zero\n"); + if (adapt_layer != NULL && adapt_layer->ctrlcmd != NULL) + adapt_layer->ctrlcmd(adapt_layer, + CAIF_CTRLCMD_INIT_FAIL_RSP, 0); + return; + } + + rcu_read_lock(); + if (adapt_layer == NULL) { - pr_debug("link setup response but no client exist, send linkdown back\n"); + pr_debug("link setup response but no client exist," + "send linkdown back\n"); cfctrl_linkdown_req(cnfg->ctrl, channel_id, NULL); - return; + goto unlock; } caif_assert(cnfg != NULL); caif_assert(phyid != 0); - phyinfo = &cnfg->phy_layers[phyid]; + + phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phyid); + if (phyinfo == NULL) { + pr_err("ERROR: Link Layer Device dissapeared" + "while connecting\n"); + goto unlock; + } + + caif_assert(phyinfo != NULL); caif_assert(phyinfo->id == phyid); caif_assert(phyinfo->phy_layer != NULL); caif_assert(phyinfo->phy_layer->id == phyid); - phyinfo->phy_ref_count++; - if (phyinfo->phy_ref_count == 1 && - phyinfo->phy_layer->modemcmd != NULL) { - phyinfo->phy_layer->modemcmd(phyinfo->phy_layer, - _CAIF_MODEMCMD_PHYIF_USEFULL); - } adapt_layer->id = channel_id; switch (serv) { @@ -348,7 +426,8 @@ cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, servicel = cfvei_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_DATAGRAM: - servicel = cfdgml_create(channel_id, &phyinfo->dev_info); + servicel = cfdgml_create(channel_id, + &phyinfo->dev_info); break; case CFCTRL_SRV_RFM: netdev = phyinfo->dev_info.dev; @@ -365,94 +444,92 @@ cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, servicel = cfdbgl_create(channel_id, &phyinfo->dev_info); break; default: - pr_err("Protocol error. Link setup response - unknown channel type\n"); - return; + pr_err("Protocol error. Link setup response " + "- unknown channel type\n"); + goto unlock; } if (!servicel) { pr_warn("Out of memory\n"); - return; + goto unlock; } layer_set_dn(servicel, cnfg->mux); cfmuxl_set_uplayer(cnfg->mux, servicel, channel_id); layer_set_up(servicel, adapt_layer); layer_set_dn(adapt_layer, servicel); - cfsrvl_get(servicel); + + rcu_read_unlock(); + servicel->ctrlcmd(servicel, CAIF_CTRLCMD_INIT_RSP, 0); + return; +unlock: + rcu_read_unlock(); } void cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type, struct net_device *dev, struct cflayer *phy_layer, - u16 *phyid, enum cfcnfg_phy_preference pref, + enum cfcnfg_phy_preference pref, bool fcs, bool stx) { struct cflayer *frml; struct cflayer *phy_driver = NULL; + struct cfcnfg_phyinfo *phyinfo; int i; + u8 phyid; + mutex_lock(&cnfg->lock); - if (cnfg->phy_layers[cnfg->last_phyid].frm_layer == NULL) { - *phyid = cnfg->last_phyid; - - /* range: * 1..(MAX_PHY_LAYERS-1) */ - cnfg->last_phyid = - (cnfg->last_phyid % (MAX_PHY_LAYERS - 1)) + 1; - } else { - *phyid = 0; - for (i = 1; i < MAX_PHY_LAYERS; i++) { - if (cnfg->phy_layers[i].frm_layer == NULL) { - *phyid = i; - break; - } - } - } - if (*phyid == 0) { - pr_err("No Available PHY ID\n"); - return; + /* CAIF protocol allow maximum 6 link-layers */ + for (i = 0; i < 7; i++) { + phyid = (dev->ifindex + i) & 0x7; + if (phyid == 0) + continue; + if (cfcnfg_get_phyinfo_rcu(cnfg, phyid) == NULL) + goto got_phyid; } + pr_warn("Too many CAIF Link Layers (max 6)\n"); + goto out; + +got_phyid: + phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); switch (phy_type) { case CFPHYTYPE_FRAG: phy_driver = - cfserl_create(CFPHYTYPE_FRAG, *phyid, stx); + cfserl_create(CFPHYTYPE_FRAG, phyid, stx); if (!phy_driver) { pr_warn("Out of memory\n"); - return; + goto out; } - break; case CFPHYTYPE_CAIF: phy_driver = NULL; break; default: - pr_err("%d\n", phy_type); - return; - break; + goto out; } + phy_layer->id = phyid; + phyinfo->pref = pref; + phyinfo->id = phyid; + phyinfo->dev_info.id = phyid; + phyinfo->dev_info.dev = dev; + phyinfo->phy_layer = phy_layer; + phyinfo->ifindex = dev->ifindex; + phyinfo->use_stx = stx; + phyinfo->use_fcs = fcs; + + frml = cffrml_create(phyid, fcs); - phy_layer->id = *phyid; - cnfg->phy_layers[*phyid].pref = pref; - cnfg->phy_layers[*phyid].id = *phyid; - cnfg->phy_layers[*phyid].dev_info.id = *phyid; - cnfg->phy_layers[*phyid].dev_info.dev = dev; - cnfg->phy_layers[*phyid].phy_layer = phy_layer; - cnfg->phy_layers[*phyid].phy_ref_count = 0; - cnfg->phy_layers[*phyid].ifindex = dev->ifindex; - cnfg->phy_layers[*phyid].use_stx = stx; - cnfg->phy_layers[*phyid].use_fcs = fcs; - - phy_layer->type = phy_type; - frml = cffrml_create(*phyid, fcs); if (!frml) { pr_warn("Out of memory\n"); - return; + kfree(phyinfo); + goto out; } - cnfg->phy_layers[*phyid].frm_layer = frml; - cfmuxl_set_dnlayer(cnfg->mux, frml, *phyid); + phyinfo->frm_layer = frml; layer_set_up(frml, cnfg->mux); if (phy_driver != NULL) { - phy_driver->id = *phyid; + phy_driver->id = phyid; layer_set_dn(frml, phy_driver); layer_set_up(phy_driver, frml); layer_set_dn(phy_driver, phy_layer); @@ -461,33 +538,95 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type, layer_set_dn(frml, phy_layer); layer_set_up(phy_layer, frml); } + + list_add_rcu(&phyinfo->node, &cnfg->phys); +out: + mutex_unlock(&cnfg->lock); } EXPORT_SYMBOL(cfcnfg_add_phy_layer); +int cfcnfg_set_phy_state(struct cfcnfg *cnfg, struct cflayer *phy_layer, + bool up) +{ + struct cfcnfg_phyinfo *phyinfo; + + rcu_read_lock(); + phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phy_layer->id); + if (phyinfo == NULL) { + rcu_read_unlock(); + return -ENODEV; + } + + if (phyinfo->up == up) { + rcu_read_unlock(); + return 0; + } + phyinfo->up = up; + + if (up) { + cffrml_hold(phyinfo->frm_layer); + cfmuxl_set_dnlayer(cnfg->mux, phyinfo->frm_layer, + phy_layer->id); + } else { + cfmuxl_remove_dnlayer(cnfg->mux, phy_layer->id); + cffrml_put(phyinfo->frm_layer); + } + + rcu_read_unlock(); + return 0; +} +EXPORT_SYMBOL(cfcnfg_set_phy_state); + int cfcnfg_del_phy_layer(struct cfcnfg *cnfg, struct cflayer *phy_layer) { struct cflayer *frml, *frml_dn; u16 phyid; + struct cfcnfg_phyinfo *phyinfo; + + might_sleep(); + + mutex_lock(&cnfg->lock); + phyid = phy_layer->id; - caif_assert(phyid == cnfg->phy_layers[phyid].id); - caif_assert(phy_layer == cnfg->phy_layers[phyid].phy_layer); + phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phyid); + + if (phyinfo == NULL) { + mutex_unlock(&cnfg->lock); + return 0; + } + caif_assert(phyid == phyinfo->id); + caif_assert(phy_layer == phyinfo->phy_layer); caif_assert(phy_layer->id == phyid); - caif_assert(cnfg->phy_layers[phyid].frm_layer->id == phyid); + caif_assert(phyinfo->frm_layer->id == phyid); + + list_del_rcu(&phyinfo->node); + synchronize_rcu(); - memset(&cnfg->phy_layers[phy_layer->id], 0, - sizeof(struct cfcnfg_phyinfo)); - frml = cfmuxl_remove_dnlayer(cnfg->mux, phy_layer->id); + /* Fail if reference count is not zero */ + if (cffrml_refcnt_read(phyinfo->frm_layer) != 0) { + pr_info("Wait for device inuse\n"); + list_add_rcu(&phyinfo->node, &cnfg->phys); + mutex_unlock(&cnfg->lock); + return -EAGAIN; + } + + frml = phyinfo->frm_layer; frml_dn = frml->dn; cffrml_set_uplayer(frml, NULL); cffrml_set_dnlayer(frml, NULL); - kfree(frml); - if (phy_layer != frml_dn) { layer_set_up(frml_dn, NULL); layer_set_dn(frml_dn, NULL); - kfree(frml_dn); } layer_set_up(phy_layer, NULL); + + if (phyinfo->phy_layer != frml_dn) + kfree(frml_dn); + + cffrml_free(frml); + kfree(phyinfo); + mutex_unlock(&cnfg->lock); + return 0; } EXPORT_SYMBOL(cfcnfg_del_phy_layer); diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 3cd8f978e309..e22671bed669 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -17,7 +17,6 @@ #define UTILITY_NAME_LENGTH 16 #define CFPKT_CTRL_PKT_LEN 20 - #ifdef CAIF_NO_LOOP static int handle_loop(struct cfctrl *ctrl, int cmd, struct cfpkt *pkt){ @@ -51,14 +50,31 @@ struct cflayer *cfctrl_create(void) this->serv.layer.receive = cfctrl_recv; sprintf(this->serv.layer.name, "ctrl"); this->serv.layer.ctrlcmd = cfctrl_ctrlcmd; +#ifndef CAIF_NO_LOOP spin_lock_init(&this->loop_linkid_lock); + this->loop_linkid = 1; +#endif spin_lock_init(&this->info_list_lock); INIT_LIST_HEAD(&this->list); - this->loop_linkid = 1; return &this->serv.layer; } -static bool param_eq(struct cfctrl_link_param *p1, struct cfctrl_link_param *p2) +void cfctrl_remove(struct cflayer *layer) +{ + struct cfctrl_request_info *p, *tmp; + struct cfctrl *ctrl = container_obj(layer); + + spin_lock_bh(&ctrl->info_list_lock); + list_for_each_entry_safe(p, tmp, &ctrl->list, list) { + list_del(&p->list); + kfree(p); + } + spin_unlock_bh(&ctrl->info_list_lock); + kfree(layer); +} + +static bool param_eq(const struct cfctrl_link_param *p1, + const struct cfctrl_link_param *p2) { bool eq = p1->linktype == p2->linktype && @@ -100,8 +116,8 @@ static bool param_eq(struct cfctrl_link_param *p1, struct cfctrl_link_param *p2) return false; } -bool cfctrl_req_eq(struct cfctrl_request_info *r1, - struct cfctrl_request_info *r2) +static bool cfctrl_req_eq(const struct cfctrl_request_info *r1, + const struct cfctrl_request_info *r2) { if (r1->cmd != r2->cmd) return false; @@ -112,23 +128,22 @@ bool cfctrl_req_eq(struct cfctrl_request_info *r1, } /* Insert request at the end */ -void cfctrl_insert_req(struct cfctrl *ctrl, +static void cfctrl_insert_req(struct cfctrl *ctrl, struct cfctrl_request_info *req) { - spin_lock(&ctrl->info_list_lock); + spin_lock_bh(&ctrl->info_list_lock); atomic_inc(&ctrl->req_seq_no); req->sequence_no = atomic_read(&ctrl->req_seq_no); list_add_tail(&req->list, &ctrl->list); - spin_unlock(&ctrl->info_list_lock); + spin_unlock_bh(&ctrl->info_list_lock); } /* Compare and remove request */ -struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, - struct cfctrl_request_info *req) +static struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, + struct cfctrl_request_info *req) { struct cfctrl_request_info *p, *tmp, *first; - spin_lock(&ctrl->info_list_lock); first = list_first_entry(&ctrl->list, struct cfctrl_request_info, list); list_for_each_entry_safe(p, tmp, &ctrl->list, list) { @@ -144,7 +159,6 @@ struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, } p = NULL; out: - spin_unlock(&ctrl->info_list_lock); return p; } @@ -154,16 +168,6 @@ struct cfctrl_rsp *cfctrl_get_respfuncs(struct cflayer *layer) return &this->res; } -void cfctrl_set_dnlayer(struct cflayer *this, struct cflayer *dn) -{ - this->dn = dn; -} - -void cfctrl_set_uplayer(struct cflayer *this, struct cflayer *up) -{ - this->up = up; -} - static void init_info(struct caif_payload_info *info, struct cfctrl *cfctrl) { info->hdr_len = 0; @@ -174,24 +178,23 @@ static void init_info(struct caif_payload_info *info, struct cfctrl *cfctrl) void cfctrl_enum_req(struct cflayer *layer, u8 physlinkid) { struct cfctrl *cfctrl = container_obj(layer); - int ret; struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); + struct cflayer *dn = cfctrl->serv.layer.dn; if (!pkt) { pr_warn("Out of memory\n"); return; } + if (!dn) { + pr_debug("not able to send enum request\n"); + return; + } caif_assert(offsetof(struct cfctrl, serv.layer) == 0); init_info(cfpkt_info(pkt), cfctrl); cfpkt_info(pkt)->dev_info->id = physlinkid; cfctrl->serv.dev_info.id = physlinkid; cfpkt_addbdy(pkt, CFCTRL_CMD_ENUM); cfpkt_addbdy(pkt, physlinkid); - ret = - cfctrl->serv.layer.dn->transmit(cfctrl->serv.layer.dn, pkt); - if (ret < 0) { - pr_err("Could not transmit enum message\n"); - cfpkt_destroy(pkt); - } + dn->transmit(dn, pkt); } int cfctrl_linkup_request(struct cflayer *layer, @@ -205,14 +208,29 @@ int cfctrl_linkup_request(struct cflayer *layer, struct cfctrl_request_info *req; int ret; char utility_name[16]; - struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); + struct cfpkt *pkt; + struct cflayer *dn = cfctrl->serv.layer.dn; + + if (!dn) { + pr_debug("not able to send linkup request\n"); + return -ENODEV; + } + + if (cfctrl_cancel_req(layer, user_layer) > 0) { + /* Slight Paranoia, check if already connecting */ + pr_err("Duplicate connect request for same client\n"); + WARN_ON(1); + return -EALREADY; + } + + pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); if (!pkt) { pr_warn("Out of memory\n"); return -ENOMEM; } cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_SETUP); - cfpkt_addbdy(pkt, (param->chtype << 4) + param->linktype); - cfpkt_addbdy(pkt, (param->priority << 3) + param->phyid); + cfpkt_addbdy(pkt, (param->chtype << 4) | param->linktype); + cfpkt_addbdy(pkt, (param->priority << 3) | param->phyid); cfpkt_addbdy(pkt, param->endpoint & 0x03); switch (param->linktype) { @@ -273,11 +291,15 @@ int cfctrl_linkup_request(struct cflayer *layer, */ cfpkt_info(pkt)->dev_info->id = param->phyid; ret = - cfctrl->serv.layer.dn->transmit(cfctrl->serv.layer.dn, pkt); + dn->transmit(dn, pkt); if (ret < 0) { - pr_err("Could not transmit linksetup request\n"); - cfpkt_destroy(pkt); - return -ENODEV; + int count; + + count = cfctrl_cancel_req(&cfctrl->serv.layer, + user_layer); + if (count != 1) + pr_err("Could not remove request (%d)", count); + return -ENODEV; } return 0; } @@ -288,89 +310,46 @@ int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid, int ret; struct cfctrl *cfctrl = container_obj(layer); struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); - if (!pkt) { - pr_warn("Out of memory\n"); - return -ENOMEM; - } - cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_DESTROY); - cfpkt_addbdy(pkt, channelid); - init_info(cfpkt_info(pkt), cfctrl); - ret = - cfctrl->serv.layer.dn->transmit(cfctrl->serv.layer.dn, pkt); - if (ret < 0) { - pr_err("Could not transmit link-down request\n"); - cfpkt_destroy(pkt); - } - return ret; -} + struct cflayer *dn = cfctrl->serv.layer.dn; -void cfctrl_sleep_req(struct cflayer *layer) -{ - int ret; - struct cfctrl *cfctrl = container_obj(layer); - struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); if (!pkt) { pr_warn("Out of memory\n"); - return; + return -ENOMEM; } - cfpkt_addbdy(pkt, CFCTRL_CMD_SLEEP); - init_info(cfpkt_info(pkt), cfctrl); - ret = - cfctrl->serv.layer.dn->transmit(cfctrl->serv.layer.dn, pkt); - if (ret < 0) - cfpkt_destroy(pkt); -} -void cfctrl_wake_req(struct cflayer *layer) -{ - int ret; - struct cfctrl *cfctrl = container_obj(layer); - struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); - if (!pkt) { - pr_warn("Out of memory\n"); - return; + if (!dn) { + pr_debug("not able to send link-down request\n"); + return -ENODEV; } - cfpkt_addbdy(pkt, CFCTRL_CMD_WAKE); - init_info(cfpkt_info(pkt), cfctrl); - ret = - cfctrl->serv.layer.dn->transmit(cfctrl->serv.layer.dn, pkt); - if (ret < 0) - cfpkt_destroy(pkt); -} -void cfctrl_getstartreason_req(struct cflayer *layer) -{ - int ret; - struct cfctrl *cfctrl = container_obj(layer); - struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); - if (!pkt) { - pr_warn("Out of memory\n"); - return; - } - cfpkt_addbdy(pkt, CFCTRL_CMD_START_REASON); + cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_DESTROY); + cfpkt_addbdy(pkt, channelid); init_info(cfpkt_info(pkt), cfctrl); ret = - cfctrl->serv.layer.dn->transmit(cfctrl->serv.layer.dn, pkt); - if (ret < 0) - cfpkt_destroy(pkt); + dn->transmit(dn, pkt); +#ifndef CAIF_NO_LOOP + cfctrl->loop_linkused[channelid] = 0; +#endif + return ret; } - -void cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer) +int cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer) { struct cfctrl_request_info *p, *tmp; struct cfctrl *ctrl = container_obj(layr); - spin_lock(&ctrl->info_list_lock); + int found = 0; + spin_lock_bh(&ctrl->info_list_lock); list_for_each_entry_safe(p, tmp, &ctrl->list, list) { if (p->client_layer == adap_layer) { - pr_debug("cancel req :%d\n", p->sequence_no); list_del(&p->list); kfree(p); + found++; } } - spin_unlock(&ctrl->info_list_lock); + spin_unlock_bh(&ctrl->info_list_lock); + return found; } static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) @@ -389,7 +368,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) cfpkt_extr_head(pkt, &cmdrsp, 1); cmd = cmdrsp & CFCTRL_CMD_MASK; if (cmd != CFCTRL_CMD_LINK_ERR - && CFCTRL_RSP_BIT != (CFCTRL_RSP_BIT & cmdrsp)) { + && CFCTRL_RSP_BIT != (CFCTRL_RSP_BIT & cmdrsp) + && CFCTRL_ERR_BIT != (CFCTRL_ERR_BIT & cmdrsp)) { if (handle_loop(cfctrl, cmd, pkt) != 0) cmdrsp |= CFCTRL_ERR_BIT; } @@ -515,18 +495,20 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) cfpkt_extr_head(pkt, ¶m, len); break; default: - pr_warn("Request setup - invalid link type (%d)\n", + pr_warn("Request setup, invalid type (%d)\n", serv); goto error; } rsp.cmd = cmd; rsp.param = linkparam; + spin_lock_bh(&cfctrl->info_list_lock); req = cfctrl_remove_req(cfctrl, &rsp); if (CFCTRL_ERR_BIT == (CFCTRL_ERR_BIT & cmdrsp) || cfpkt_erroneous(pkt)) { - pr_err("Invalid O/E bit or parse error on CAIF control channel\n"); + pr_err("Invalid O/E bit or parse error " + "on CAIF control channel\n"); cfctrl->res.reject_rsp(cfctrl->serv.layer.up, 0, req ? req->client_layer @@ -541,6 +523,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) if (req != NULL) kfree(req); + + spin_unlock_bh(&cfctrl->info_list_lock); } break; case CFCTRL_CMD_LINK_DESTROY: @@ -584,12 +568,28 @@ static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, switch (ctrl) { case _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND: case CAIF_CTRLCMD_FLOW_OFF_IND: - spin_lock(&this->info_list_lock); - if (!list_empty(&this->list)) { + spin_lock_bh(&this->info_list_lock); + if (!list_empty(&this->list)) pr_debug("Received flow off in control layer\n"); + spin_unlock_bh(&this->info_list_lock); + break; + case _CAIF_CTRLCMD_PHYIF_DOWN_IND: { + struct cfctrl_request_info *p, *tmp; + + /* Find all connect request and report failure */ + spin_lock_bh(&this->info_list_lock); + list_for_each_entry_safe(p, tmp, &this->list, list) { + if (p->param.phyid == phyid) { + list_del(&p->list); + p->client_layer->ctrlcmd(p->client_layer, + CAIF_CTRLCMD_INIT_FAIL_RSP, + phyid); + kfree(p); + } } - spin_unlock(&this->info_list_lock); + spin_unlock_bh(&this->info_list_lock); break; + } default: break; } @@ -599,27 +599,33 @@ static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, static int handle_loop(struct cfctrl *ctrl, int cmd, struct cfpkt *pkt) { static int last_linkid; + static int dec; u8 linkid, linktype, tmp; switch (cmd) { case CFCTRL_CMD_LINK_SETUP: - spin_lock(&ctrl->loop_linkid_lock); - for (linkid = last_linkid + 1; linkid < 255; linkid++) - if (!ctrl->loop_linkused[linkid]) - goto found; - for (linkid = last_linkid - 1; linkid > 0; linkid--) + spin_lock_bh(&ctrl->loop_linkid_lock); + if (!dec) { + for (linkid = last_linkid + 1; linkid < 254; linkid++) + if (!ctrl->loop_linkused[linkid]) + goto found; + } + dec = 1; + for (linkid = last_linkid - 1; linkid > 1; linkid--) if (!ctrl->loop_linkused[linkid]) goto found; - spin_unlock(&ctrl->loop_linkid_lock); - pr_err("Out of link-ids\n"); - return -EINVAL; + spin_unlock_bh(&ctrl->loop_linkid_lock); + return -1; found: + if (linkid < 10) + dec = 0; + if (!ctrl->loop_linkused[linkid]) ctrl->loop_linkused[linkid] = 1; last_linkid = linkid; cfpkt_add_trail(pkt, &linkid, 1); - spin_unlock(&ctrl->loop_linkid_lock); + spin_unlock_bh(&ctrl->loop_linkid_lock); cfpkt_peek_head(pkt, &linktype, 1); if (linktype == CFCTRL_SRV_UTIL) { tmp = 0x01; @@ -629,10 +635,10 @@ found: break; case CFCTRL_CMD_LINK_DESTROY: - spin_lock(&ctrl->loop_linkid_lock); + spin_lock_bh(&ctrl->loop_linkid_lock); cfpkt_peek_head(pkt, &linkid, 1); ctrl->loop_linkused[linkid] = 0; - spin_unlock(&ctrl->loop_linkid_lock); + spin_unlock_bh(&ctrl->loop_linkid_lock); break; default: break; diff --git a/net/caif/cfdgml.c b/net/caif/cfdgml.c index 27dab26ad3b8..0382dec84fdc 100644 --- a/net/caif/cfdgml.c +++ b/net/caif/cfdgml.c @@ -13,6 +13,7 @@ #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> + #define container_obj(layr) ((struct cfsrvl *) layr) #define DGM_CMD_BIT 0x80 @@ -83,6 +84,7 @@ static int cfdgml_receive(struct cflayer *layr, struct cfpkt *pkt) static int cfdgml_transmit(struct cflayer *layr, struct cfpkt *pkt) { + u8 packet_type; u32 zero = 0; struct caif_payload_info *info; struct cfsrvl *service = container_obj(layr); @@ -94,7 +96,9 @@ static int cfdgml_transmit(struct cflayer *layr, struct cfpkt *pkt) if (cfpkt_getlen(pkt) > DGM_MTU) return -EMSGSIZE; - cfpkt_add_head(pkt, &zero, 4); + cfpkt_add_head(pkt, &zero, 3); + packet_type = 0x08; /* B9 set - UNCLASSIFIED */ + cfpkt_add_head(pkt, &packet_type, 1); /* Add info for MUX-layer to route the packet out. */ info = cfpkt_info(pkt); @@ -104,10 +108,5 @@ static int cfdgml_transmit(struct cflayer *layr, struct cfpkt *pkt) */ info->hdr_len = 4; info->dev_info = &service->dev_info; - ret = layr->dn->transmit(layr->dn, pkt); - if (ret < 0) { - u32 tmp32; - cfpkt_extr_head(pkt, &tmp32, 4); - } - return ret; + return layr->dn->transmit(layr->dn, pkt); } diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index a445043931ae..04204b202718 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -12,6 +12,7 @@ #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/crc-ccitt.h> +#include <linux/netdevice.h> #include <net/caif/caif_layer.h> #include <net/caif/cfpkt.h> #include <net/caif/cffrml.h> @@ -21,6 +22,7 @@ struct cffrml { struct cflayer layer; bool dofcs; /* !< FCS active */ + int __percpu *pcpu_refcnt; }; static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt); @@ -37,6 +39,12 @@ struct cflayer *cffrml_create(u16 phyid, bool use_fcs) pr_warn("Out of memory\n"); return NULL; } + this->pcpu_refcnt = alloc_percpu(int); + if (this->pcpu_refcnt == NULL) { + kfree(this); + return NULL; + } + caif_assert(offsetof(struct cffrml, layer) == 0); memset(this, 0, sizeof(struct cflayer)); @@ -49,6 +57,13 @@ struct cflayer *cffrml_create(u16 phyid, bool use_fcs) return (struct cflayer *) this; } +void cffrml_free(struct cflayer *layer) +{ + struct cffrml *this = container_obj(layer); + free_percpu(this->pcpu_refcnt); + kfree(layer); +} + void cffrml_set_uplayer(struct cflayer *this, struct cflayer *up) { this->up = up; @@ -112,6 +127,13 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt) cfpkt_destroy(pkt); return -EPROTO; } + + if (layr->up == NULL) { + pr_err("Layr up is missing!\n"); + cfpkt_destroy(pkt); + return -EINVAL; + } + return layr->up->receive(layr->up, pkt); } @@ -120,7 +142,6 @@ static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt) int tmp; u16 chks; u16 len; - int ret; struct cffrml *this = container_obj(layr); if (this->dofcs) { chks = cfpkt_iterate(pkt, cffrml_checksum, 0xffff); @@ -135,19 +156,44 @@ static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt) cfpkt_info(pkt)->hdr_len += 2; if (cfpkt_erroneous(pkt)) { pr_err("Packet is erroneous!\n"); + cfpkt_destroy(pkt); return -EPROTO; } - ret = layr->dn->transmit(layr->dn, pkt); - if (ret < 0) { - /* Remove header on faulty packet. */ - cfpkt_extr_head(pkt, &tmp, 2); + + if (layr->dn == NULL) { + cfpkt_destroy(pkt); + return -ENODEV; + } - return ret; + return layr->dn->transmit(layr->dn, pkt); } static void cffrml_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid) { - if (layr->up->ctrlcmd) + if (layr->up && layr->up->ctrlcmd) layr->up->ctrlcmd(layr->up, ctrl, layr->id); } + +void cffrml_put(struct cflayer *layr) +{ + struct cffrml *this = container_obj(layr); + if (layr != NULL && this->pcpu_refcnt != NULL) + irqsafe_cpu_dec(*this->pcpu_refcnt); +} + +void cffrml_hold(struct cflayer *layr) +{ + struct cffrml *this = container_obj(layr); + if (layr != NULL && this->pcpu_refcnt != NULL) + irqsafe_cpu_inc(*this->pcpu_refcnt); +} + +int cffrml_refcnt_read(struct cflayer *layr) +{ + int i, refcnt = 0; + struct cffrml *this = container_obj(layr); + for_each_possible_cpu(i) + refcnt += *per_cpu_ptr(this->pcpu_refcnt, i); + return refcnt; +} diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index 46f34b2e0478..3a66b8c10e09 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -9,6 +9,7 @@ #include <linux/stddef.h> #include <linux/spinlock.h> #include <linux/slab.h> +#include <linux/rculist.h> #include <net/caif/cfpkt.h> #include <net/caif/cfmuxl.h> #include <net/caif/cfsrvl.h> @@ -61,111 +62,88 @@ struct cflayer *cfmuxl_create(void) return &this->layer; } -int cfmuxl_set_uplayer(struct cflayer *layr, struct cflayer *up, u8 linkid) +int cfmuxl_set_dnlayer(struct cflayer *layr, struct cflayer *dn, u8 phyid) { - struct cfmuxl *muxl = container_obj(layr); - spin_lock(&muxl->receive_lock); - cfsrvl_get(up); - list_add(&up->node, &muxl->srvl_list); - spin_unlock(&muxl->receive_lock); + struct cfmuxl *muxl = (struct cfmuxl *) layr; + + spin_lock_bh(&muxl->transmit_lock); + list_add_rcu(&dn->node, &muxl->frml_list); + spin_unlock_bh(&muxl->transmit_lock); return 0; } -bool cfmuxl_is_phy_inuse(struct cflayer *layr, u8 phyid) +static struct cflayer *get_from_id(struct list_head *list, u16 id) { - struct list_head *node; - struct cflayer *layer; - struct cfmuxl *muxl = container_obj(layr); - bool match = false; - spin_lock(&muxl->receive_lock); - - list_for_each(node, &muxl->srvl_list) { - layer = list_entry(node, struct cflayer, node); - if (cfsrvl_phyid_match(layer, phyid)) { - match = true; - break; - } - + struct cflayer *lyr; + list_for_each_entry_rcu(lyr, list, node) { + if (lyr->id == id) + return lyr; } - spin_unlock(&muxl->receive_lock); - return match; + + return NULL; } -u8 cfmuxl_get_phyid(struct cflayer *layr, u8 channel_id) +int cfmuxl_set_uplayer(struct cflayer *layr, struct cflayer *up, u8 linkid) { - struct cflayer *up; - int phyid; struct cfmuxl *muxl = container_obj(layr); - spin_lock(&muxl->receive_lock); - up = get_up(muxl, channel_id); - if (up != NULL) - phyid = cfsrvl_getphyid(up); - else - phyid = 0; - spin_unlock(&muxl->receive_lock); - return phyid; -} + struct cflayer *old; -int cfmuxl_set_dnlayer(struct cflayer *layr, struct cflayer *dn, u8 phyid) -{ - struct cfmuxl *muxl = (struct cfmuxl *) layr; - spin_lock(&muxl->transmit_lock); - list_add(&dn->node, &muxl->frml_list); - spin_unlock(&muxl->transmit_lock); - return 0; -} + spin_lock_bh(&muxl->receive_lock); -static struct cflayer *get_from_id(struct list_head *list, u16 id) -{ - struct list_head *node; - struct cflayer *layer; - list_for_each(node, list) { - layer = list_entry(node, struct cflayer, node); - if (layer->id == id) - return layer; - } - return NULL; + /* Two entries with same id is wrong, so remove old layer from mux */ + old = get_from_id(&muxl->srvl_list, linkid); + if (old != NULL) + list_del_rcu(&old->node); + + list_add_rcu(&up->node, &muxl->srvl_list); + spin_unlock_bh(&muxl->receive_lock); + + return 0; } struct cflayer *cfmuxl_remove_dnlayer(struct cflayer *layr, u8 phyid) { struct cfmuxl *muxl = container_obj(layr); struct cflayer *dn; - spin_lock(&muxl->transmit_lock); - memset(muxl->dn_cache, 0, sizeof(muxl->dn_cache)); + int idx = phyid % DN_CACHE_SIZE; + + spin_lock_bh(&muxl->transmit_lock); + rcu_assign_pointer(muxl->dn_cache[idx], NULL); dn = get_from_id(&muxl->frml_list, phyid); - if (dn == NULL) { - spin_unlock(&muxl->transmit_lock); - return NULL; - } - list_del(&dn->node); + if (dn == NULL) + goto out; + + list_del_rcu(&dn->node); caif_assert(dn != NULL); - spin_unlock(&muxl->transmit_lock); +out: + spin_unlock_bh(&muxl->transmit_lock); return dn; } -/* Invariant: lock is taken */ static struct cflayer *get_up(struct cfmuxl *muxl, u16 id) { struct cflayer *up; int idx = id % UP_CACHE_SIZE; - up = muxl->up_cache[idx]; + up = rcu_dereference(muxl->up_cache[idx]); if (up == NULL || up->id != id) { + spin_lock_bh(&muxl->receive_lock); up = get_from_id(&muxl->srvl_list, id); - muxl->up_cache[idx] = up; + rcu_assign_pointer(muxl->up_cache[idx], up); + spin_unlock_bh(&muxl->receive_lock); } return up; } -/* Invariant: lock is taken */ static struct cflayer *get_dn(struct cfmuxl *muxl, struct dev_info *dev_info) { struct cflayer *dn; int idx = dev_info->id % DN_CACHE_SIZE; - dn = muxl->dn_cache[idx]; + dn = rcu_dereference(muxl->dn_cache[idx]); if (dn == NULL || dn->id != dev_info->id) { + spin_lock_bh(&muxl->transmit_lock); dn = get_from_id(&muxl->frml_list, dev_info->id); - muxl->dn_cache[idx] = dn; + rcu_assign_pointer(muxl->dn_cache[idx], dn); + spin_unlock_bh(&muxl->transmit_lock); } return dn; } @@ -174,15 +152,22 @@ struct cflayer *cfmuxl_remove_uplayer(struct cflayer *layr, u8 id) { struct cflayer *up; struct cfmuxl *muxl = container_obj(layr); - spin_lock(&muxl->receive_lock); - up = get_up(muxl, id); + int idx = id % UP_CACHE_SIZE; + + if (id == 0) { + pr_warn("Trying to remove control layer\n"); + return NULL; + } + + spin_lock_bh(&muxl->receive_lock); + up = get_from_id(&muxl->srvl_list, id); if (up == NULL) goto out; - memset(muxl->up_cache, 0, sizeof(muxl->up_cache)); - list_del(&up->node); - cfsrvl_put(up); + + rcu_assign_pointer(muxl->up_cache[idx], NULL); + list_del_rcu(&up->node); out: - spin_unlock(&muxl->receive_lock); + spin_unlock_bh(&muxl->receive_lock); return up; } @@ -197,58 +182,92 @@ static int cfmuxl_receive(struct cflayer *layr, struct cfpkt *pkt) cfpkt_destroy(pkt); return -EPROTO; } - - spin_lock(&muxl->receive_lock); + rcu_read_lock(); up = get_up(muxl, id); - spin_unlock(&muxl->receive_lock); + if (up == NULL) { - pr_info("Received data on unknown link ID = %d (0x%x) up == NULL", - id, id); + pr_debug("Received data on unknown link ID = %d (0x%x)" + " up == NULL", id, id); cfpkt_destroy(pkt); /* * Don't return ERROR, since modem misbehaves and sends out * flow on before linksetup response. */ + + rcu_read_unlock(); return /* CFGLU_EPROT; */ 0; } + + /* We can't hold rcu_lock during receive, so take a ref count instead */ cfsrvl_get(up); + rcu_read_unlock(); + ret = up->receive(up, pkt); + cfsrvl_put(up); return ret; } static int cfmuxl_transmit(struct cflayer *layr, struct cfpkt *pkt) { - int ret; struct cfmuxl *muxl = container_obj(layr); + int err; u8 linkid; struct cflayer *dn; struct caif_payload_info *info = cfpkt_info(pkt); - dn = get_dn(muxl, cfpkt_info(pkt)->dev_info); + BUG_ON(!info); + + rcu_read_lock(); + + dn = get_dn(muxl, info->dev_info); if (dn == NULL) { - pr_warn("Send data on unknown phy ID = %d (0x%x)\n", + pr_debug("Send data on unknown phy ID = %d (0x%x)\n", info->dev_info->id, info->dev_info->id); + rcu_read_unlock(); + cfpkt_destroy(pkt); return -ENOTCONN; } + info->hdr_len += 1; linkid = info->channel_id; cfpkt_add_head(pkt, &linkid, 1); - ret = dn->transmit(dn, pkt); - /* Remove MUX protocol header upon error. */ - if (ret < 0) - cfpkt_extr_head(pkt, &linkid, 1); - return ret; + + /* We can't hold rcu_lock during receive, so take a ref count instead */ + cffrml_hold(dn); + + rcu_read_unlock(); + + err = dn->transmit(dn, pkt); + + cffrml_put(dn); + return err; } static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid) { struct cfmuxl *muxl = container_obj(layr); - struct list_head *node; struct cflayer *layer; - list_for_each(node, &muxl->srvl_list) { - layer = list_entry(node, struct cflayer, node); - if (cfsrvl_phyid_match(layer, phyid)) + int idx; + + rcu_read_lock(); + list_for_each_entry_rcu(layer, &muxl->srvl_list, node) { + + if (cfsrvl_phyid_match(layer, phyid) && layer->ctrlcmd) { + + if ((ctrl == _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND || + ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && + layer->id != 0) { + + idx = layer->id % UP_CACHE_SIZE; + spin_lock_bh(&muxl->receive_lock); + rcu_assign_pointer(muxl->up_cache[idx], NULL); + list_del_rcu(&layer->node); + spin_unlock_bh(&muxl->receive_lock); + } + /* NOTE: ctrlcmd is not allowed to block */ layer->ctrlcmd(layer, ctrl, phyid); + } } + rcu_read_unlock(); } diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c index d7e865e2ff65..75d4bfae1a78 100644 --- a/net/caif/cfpkt_skbuff.c +++ b/net/caif/cfpkt_skbuff.c @@ -42,22 +42,22 @@ struct cfpkt_priv_data { bool erronous; }; -inline struct cfpkt_priv_data *cfpkt_priv(struct cfpkt *pkt) +static inline struct cfpkt_priv_data *cfpkt_priv(struct cfpkt *pkt) { return (struct cfpkt_priv_data *) pkt->skb.cb; } -inline bool is_erronous(struct cfpkt *pkt) +static inline bool is_erronous(struct cfpkt *pkt) { return cfpkt_priv(pkt)->erronous; } -inline struct sk_buff *pkt_to_skb(struct cfpkt *pkt) +static inline struct sk_buff *pkt_to_skb(struct cfpkt *pkt) { return &pkt->skb; } -inline struct cfpkt *skb_to_pkt(struct sk_buff *skb) +static inline struct cfpkt *skb_to_pkt(struct sk_buff *skb) { return (struct cfpkt *) skb; } @@ -97,21 +97,20 @@ inline struct cfpkt *cfpkt_create(u16 len) { return cfpkt_create_pfx(len + PKT_POSTFIX, PKT_PREFIX); } -EXPORT_SYMBOL(cfpkt_create); void cfpkt_destroy(struct cfpkt *pkt) { struct sk_buff *skb = pkt_to_skb(pkt); kfree_skb(skb); } -EXPORT_SYMBOL(cfpkt_destroy); + inline bool cfpkt_more(struct cfpkt *pkt) { struct sk_buff *skb = pkt_to_skb(pkt); return skb->len > 0; } -EXPORT_SYMBOL(cfpkt_more); + int cfpkt_peek_head(struct cfpkt *pkt, void *data, u16 len) { @@ -123,7 +122,6 @@ int cfpkt_peek_head(struct cfpkt *pkt, void *data, u16 len) return !cfpkt_extr_head(pkt, data, len) && !cfpkt_add_head(pkt, data, len); } -EXPORT_SYMBOL(cfpkt_peek_head); int cfpkt_extr_head(struct cfpkt *pkt, void *data, u16 len) { @@ -148,7 +146,6 @@ int cfpkt_extr_head(struct cfpkt *pkt, void *data, u16 len) memcpy(data, from, len); return 0; } -EXPORT_SYMBOL(cfpkt_extr_head); int cfpkt_extr_trail(struct cfpkt *pkt, void *dta, u16 len) { @@ -171,13 +168,13 @@ int cfpkt_extr_trail(struct cfpkt *pkt, void *dta, u16 len) memcpy(data, from, len); return 0; } -EXPORT_SYMBOL(cfpkt_extr_trail); + int cfpkt_pad_trail(struct cfpkt *pkt, u16 len) { return cfpkt_add_body(pkt, NULL, len); } -EXPORT_SYMBOL(cfpkt_pad_trail); + int cfpkt_add_body(struct cfpkt *pkt, const void *data, u16 len) { @@ -226,13 +223,11 @@ int cfpkt_add_body(struct cfpkt *pkt, const void *data, u16 len) memcpy(to, data, len); return 0; } -EXPORT_SYMBOL(cfpkt_add_body); inline int cfpkt_addbdy(struct cfpkt *pkt, u8 data) { return cfpkt_add_body(pkt, &data, 1); } -EXPORT_SYMBOL(cfpkt_addbdy); int cfpkt_add_head(struct cfpkt *pkt, const void *data2, u16 len) { @@ -259,20 +254,20 @@ int cfpkt_add_head(struct cfpkt *pkt, const void *data2, u16 len) memcpy(to, data, len); return 0; } -EXPORT_SYMBOL(cfpkt_add_head); + inline int cfpkt_add_trail(struct cfpkt *pkt, const void *data, u16 len) { return cfpkt_add_body(pkt, data, len); } -EXPORT_SYMBOL(cfpkt_add_trail); + inline u16 cfpkt_getlen(struct cfpkt *pkt) { struct sk_buff *skb = pkt_to_skb(pkt); return skb->len; } -EXPORT_SYMBOL(cfpkt_getlen); + inline u16 cfpkt_iterate(struct cfpkt *pkt, u16 (*iter_func)(u16, void *, u16), @@ -290,7 +285,7 @@ inline u16 cfpkt_iterate(struct cfpkt *pkt, } return iter_func(data, pkt->skb.data, cfpkt_getlen(pkt)); } -EXPORT_SYMBOL(cfpkt_iterate); + int cfpkt_setlen(struct cfpkt *pkt, u16 len) { @@ -315,18 +310,6 @@ int cfpkt_setlen(struct cfpkt *pkt, u16 len) return cfpkt_getlen(pkt); } -EXPORT_SYMBOL(cfpkt_setlen); - -struct cfpkt *cfpkt_create_uplink(const unsigned char *data, unsigned int len) -{ - struct cfpkt *pkt = cfpkt_create_pfx(len + PKT_POSTFIX, PKT_PREFIX); - if (!pkt) - return NULL; - if (unlikely(data != NULL)) - cfpkt_add_body(pkt, data, len); - return pkt; -} -EXPORT_SYMBOL(cfpkt_create_uplink); struct cfpkt *cfpkt_append(struct cfpkt *dstpkt, struct cfpkt *addpkt, @@ -368,7 +351,6 @@ struct cfpkt *cfpkt_append(struct cfpkt *dstpkt, dst->len += addlen; return skb_to_pkt(dst); } -EXPORT_SYMBOL(cfpkt_append); struct cfpkt *cfpkt_split(struct cfpkt *pkt, u16 pos) { @@ -406,174 +388,13 @@ struct cfpkt *cfpkt_split(struct cfpkt *pkt, u16 pos) skb2->len += len2nd; return skb_to_pkt(skb2); } -EXPORT_SYMBOL(cfpkt_split); - -char *cfpkt_log_pkt(struct cfpkt *pkt, char *buf, int buflen) -{ - struct sk_buff *skb = pkt_to_skb(pkt); - char *p = buf; - int i; - - /* - * Sanity check buffer length, it needs to be at least as large as - * the header info: ~=50+ bytes - */ - if (buflen < 50) - return NULL; - - snprintf(buf, buflen, "%s: pkt:%p len:%ld(%ld+%ld) {%ld,%ld} data: [", - is_erronous(pkt) ? "ERRONOUS-SKB" : - (skb->data_len != 0 ? "COMPLEX-SKB" : "SKB"), - skb, - (long) skb->len, - (long) (skb_tail_pointer(skb) - skb->data), - (long) skb->data_len, - (long) (skb->data - skb->head), - (long) (skb_tail_pointer(skb) - skb->head)); - p = buf + strlen(buf); - - for (i = 0; i < skb_tail_pointer(skb) - skb->data && i < 300; i++) { - if (p > buf + buflen - 10) { - sprintf(p, "..."); - p = buf + strlen(buf); - break; - } - sprintf(p, "%02x,", skb->data[i]); - p = buf + strlen(buf); - } - sprintf(p, "]\n"); - return buf; -} -EXPORT_SYMBOL(cfpkt_log_pkt); - -int cfpkt_raw_append(struct cfpkt *pkt, void **buf, unsigned int buflen) -{ - struct sk_buff *skb = pkt_to_skb(pkt); - struct sk_buff *lastskb; - - caif_assert(buf != NULL); - if (unlikely(is_erronous(pkt))) - return -EPROTO; - /* Make sure SKB is writable */ - if (unlikely(skb_cow_data(skb, 0, &lastskb) < 0)) { - PKT_ERROR(pkt, "skb_cow_data failed\n"); - return -EPROTO; - } - - if (unlikely(skb_linearize(skb) != 0)) { - PKT_ERROR(pkt, "linearize failed\n"); - return -EPROTO; - } - - if (unlikely(skb_tailroom(skb) < buflen)) { - PKT_ERROR(pkt, "buffer too short - failed\n"); - return -EPROTO; - } - - *buf = skb_put(skb, buflen); - return 1; -} -EXPORT_SYMBOL(cfpkt_raw_append); -int cfpkt_raw_extract(struct cfpkt *pkt, void **buf, unsigned int buflen) -{ - struct sk_buff *skb = pkt_to_skb(pkt); - - caif_assert(buf != NULL); - if (unlikely(is_erronous(pkt))) - return -EPROTO; - - if (unlikely(buflen > skb->len)) { - PKT_ERROR(pkt, "buflen too large - failed\n"); - return -EPROTO; - } - - if (unlikely(buflen > skb_headlen(skb))) { - if (unlikely(skb_linearize(skb) != 0)) { - PKT_ERROR(pkt, "linearize failed\n"); - return -EPROTO; - } - } - - *buf = skb->data; - skb_pull(skb, buflen); - - return 1; -} -EXPORT_SYMBOL(cfpkt_raw_extract); - -inline bool cfpkt_erroneous(struct cfpkt *pkt) +bool cfpkt_erroneous(struct cfpkt *pkt) { return cfpkt_priv(pkt)->erronous; } -EXPORT_SYMBOL(cfpkt_erroneous); - -struct cfpktq *cfpktq_create(void) -{ - struct cfpktq *q = kmalloc(sizeof(struct cfpktq), GFP_ATOMIC); - if (!q) - return NULL; - skb_queue_head_init(&q->head); - atomic_set(&q->count, 0); - spin_lock_init(&q->lock); - return q; -} -EXPORT_SYMBOL(cfpktq_create); - -void cfpkt_queue(struct cfpktq *pktq, struct cfpkt *pkt, unsigned short prio) -{ - atomic_inc(&pktq->count); - spin_lock(&pktq->lock); - skb_queue_tail(&pktq->head, pkt_to_skb(pkt)); - spin_unlock(&pktq->lock); - -} -EXPORT_SYMBOL(cfpkt_queue); - -struct cfpkt *cfpkt_qpeek(struct cfpktq *pktq) -{ - struct cfpkt *tmp; - spin_lock(&pktq->lock); - tmp = skb_to_pkt(skb_peek(&pktq->head)); - spin_unlock(&pktq->lock); - return tmp; -} -EXPORT_SYMBOL(cfpkt_qpeek); - -struct cfpkt *cfpkt_dequeue(struct cfpktq *pktq) -{ - struct cfpkt *pkt; - spin_lock(&pktq->lock); - pkt = skb_to_pkt(skb_dequeue(&pktq->head)); - if (pkt) { - atomic_dec(&pktq->count); - caif_assert(atomic_read(&pktq->count) >= 0); - } - spin_unlock(&pktq->lock); - return pkt; -} -EXPORT_SYMBOL(cfpkt_dequeue); - -int cfpkt_qcount(struct cfpktq *pktq) -{ - return atomic_read(&pktq->count); -} -EXPORT_SYMBOL(cfpkt_qcount); - -struct cfpkt *cfpkt_clone_release(struct cfpkt *pkt) -{ - struct cfpkt *clone; - clone = skb_to_pkt(skb_clone(pkt_to_skb(pkt), GFP_ATOMIC)); - /* Free original packet. */ - cfpkt_destroy(pkt); - if (!clone) - return NULL; - return clone; -} -EXPORT_SYMBOL(cfpkt_clone_release); struct caif_payload_info *cfpkt_info(struct cfpkt *pkt) { return (struct caif_payload_info *)&pkt_to_skb(pkt)->cb; } -EXPORT_SYMBOL(cfpkt_info); diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index e2fb5fa75795..0deabb440051 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -31,9 +31,9 @@ struct cfrfml { spinlock_t sync; }; -static void cfrfml_release(struct kref *kref) +static void cfrfml_release(struct cflayer *layer) { - struct cfsrvl *srvl = container_of(kref, struct cfsrvl, ref); + struct cfsrvl *srvl = container_of(layer, struct cfsrvl, layer); struct cfrfml *rfml = container_obj(&srvl->layer); if (rfml->incomplete_frm) diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c index 8303fe3ebf89..2715c84cfa87 100644 --- a/net/caif/cfserl.c +++ b/net/caif/cfserl.c @@ -179,15 +179,10 @@ static int cfserl_receive(struct cflayer *l, struct cfpkt *newpkt) static int cfserl_transmit(struct cflayer *layer, struct cfpkt *newpkt) { struct cfserl *layr = container_obj(layer); - int ret; u8 tmp8 = CFSERL_STX; if (layr->usestx) cfpkt_add_head(newpkt, &tmp8, 1); - ret = layer->dn->transmit(layer->dn, newpkt); - if (ret < 0) - cfpkt_extr_head(newpkt, &tmp8, 1); - - return ret; + return layer->dn->transmit(layer->dn, newpkt); } static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c index ab5e542526bf..535a1e72b366 100644 --- a/net/caif/cfsrvl.c +++ b/net/caif/cfsrvl.c @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/slab.h> +#include <linux/module.h> #include <net/caif/caif_layer.h> #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> @@ -27,8 +28,8 @@ static void cfservl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, { struct cfsrvl *service = container_obj(layr); - caif_assert(layr->up != NULL); - caif_assert(layr->up->ctrlcmd != NULL); + if (layr->up == NULL || layr->up->ctrlcmd == NULL) + return; switch (ctrl) { case CAIF_CTRLCMD_INIT_RSP: @@ -151,14 +152,9 @@ static int cfservl_modemcmd(struct cflayer *layr, enum caif_modemcmd ctrl) return -EINVAL; } -void cfservl_destroy(struct cflayer *layer) +static void cfsrvl_release(struct cflayer *layer) { - kfree(layer); -} - -void cfsrvl_release(struct kref *kref) -{ - struct cfsrvl *service = container_of(kref, struct cfsrvl, ref); + struct cfsrvl *service = container_of(layer, struct cfsrvl, layer); kfree(service); } @@ -178,10 +174,8 @@ void cfsrvl_init(struct cfsrvl *service, service->dev_info = *dev_info; service->supports_flowctrl = supports_flowctrl; service->release = cfsrvl_release; - kref_init(&service->ref); } - bool cfsrvl_ready(struct cfsrvl *service, int *err) { if (service->open && service->modem_flow_on && service->phy_flow_on) @@ -194,6 +188,7 @@ bool cfsrvl_ready(struct cfsrvl *service, int *err) *err = -EAGAIN; return false; } + u8 cfsrvl_getphyid(struct cflayer *layer) { struct cfsrvl *servl = container_obj(layer); @@ -205,3 +200,26 @@ bool cfsrvl_phyid_match(struct cflayer *layer, int phyid) struct cfsrvl *servl = container_obj(layer); return servl->dev_info.id == phyid; } + +void caif_free_client(struct cflayer *adap_layer) +{ + struct cfsrvl *servl; + if (adap_layer == NULL || adap_layer->dn == NULL) + return; + servl = container_obj(adap_layer->dn); + servl->release(&servl->layer); +} +EXPORT_SYMBOL(caif_free_client); + +void caif_client_register_refcnt(struct cflayer *adapt_layer, + void (*hold)(struct cflayer *lyr), + void (*put)(struct cflayer *lyr)) +{ + struct cfsrvl *service; + service = container_of(adapt_layer->dn, struct cfsrvl, layer); + + WARN_ON(adapt_layer == NULL || adapt_layer->dn == NULL); + service->hold = hold; + service->put = put; +} +EXPORT_SYMBOL(caif_client_register_refcnt); diff --git a/net/caif/cfutill.c b/net/caif/cfutill.c index 315c0d601368..98e027db18ed 100644 --- a/net/caif/cfutill.c +++ b/net/caif/cfutill.c @@ -100,10 +100,5 @@ static int cfutill_transmit(struct cflayer *layr, struct cfpkt *pkt) */ info->hdr_len = 1; info->dev_info = &service->dev_info; - ret = layr->dn->transmit(layr->dn, pkt); - if (ret < 0) { - u32 tmp32; - cfpkt_extr_head(pkt, &tmp32, 4); - } - return ret; + return layr->dn->transmit(layr->dn, pkt); } diff --git a/net/caif/cfveil.c b/net/caif/cfveil.c index c3b1dec4acf6..3ec83fbc2887 100644 --- a/net/caif/cfveil.c +++ b/net/caif/cfveil.c @@ -82,13 +82,14 @@ static int cfvei_transmit(struct cflayer *layr, struct cfpkt *pkt) int ret; struct cfsrvl *service = container_obj(layr); if (!cfsrvl_ready(service, &ret)) - return ret; + goto err; caif_assert(layr->dn != NULL); caif_assert(layr->dn->transmit != NULL); if (cfpkt_add_head(pkt, &tmp, 1) < 0) { pr_err("Packet is erroneous!\n"); - return -EPROTO; + ret = -EPROTO; + goto err; } /* Add info-> for MUX-layer to route the packet out. */ @@ -96,8 +97,8 @@ static int cfvei_transmit(struct cflayer *layr, struct cfpkt *pkt) info->channel_id = service->layer.id; info->hdr_len = 1; info->dev_info = &service->dev_info; - ret = layr->dn->transmit(layr->dn, pkt); - if (ret < 0) - cfpkt_extr_head(pkt, &tmp, 1); + return layr->dn->transmit(layr->dn, pkt); +err: + cfpkt_destroy(pkt); return ret; } diff --git a/net/caif/cfvidl.c b/net/caif/cfvidl.c index bf6fef2a0eff..b2f5989ad455 100644 --- a/net/caif/cfvidl.c +++ b/net/caif/cfvidl.c @@ -60,8 +60,5 @@ static int cfvidl_transmit(struct cflayer *layr, struct cfpkt *pkt) info = cfpkt_info(pkt); info->channel_id = service->layer.id; info->dev_info = &service->dev_info; - ret = layr->dn->transmit(layr->dn, pkt); - if (ret < 0) - cfpkt_extr_head(pkt, &videoheader, 4); - return ret; + return layr->dn->transmit(layr->dn, pkt); } diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 6008d6dc18a0..649ebacaf6bc 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -20,7 +20,6 @@ #include <linux/caif/if_caif.h> #include <net/rtnetlink.h> #include <net/caif/caif_layer.h> -#include <net/caif/cfcnfg.h> #include <net/caif/cfpkt.h> #include <net/caif/caif_dev.h> @@ -84,10 +83,11 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) if (!priv) return -EINVAL; + skb = (struct sk_buff *) cfpkt_tonative(pkt); + /* Get length of CAIF packet. */ - pktlen = cfpkt_getlen(pkt); + pktlen = skb->len; - skb = (struct sk_buff *) cfpkt_tonative(pkt); /* Pass some minimum information and * send the packet to the net stack. */ @@ -153,6 +153,18 @@ static void close_work(struct work_struct *work) } static DECLARE_WORK(close_worker, close_work); +static void chnl_hold(struct cflayer *lyr) +{ + struct chnl_net *priv = container_of(lyr, struct chnl_net, chnl); + dev_hold(priv->netdev); +} + +static void chnl_put(struct cflayer *lyr) +{ + struct chnl_net *priv = container_of(lyr, struct chnl_net, chnl); + dev_put(priv->netdev); +} + static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow, int phyid) { @@ -190,6 +202,7 @@ static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow, netif_wake_queue(priv->netdev); break; case CAIF_CTRLCMD_INIT_RSP: + caif_client_register_refcnt(&priv->chnl, chnl_hold, chnl_put); priv->state = CAIF_CONNECTED; priv->flowenabled = true; netif_wake_queue(priv->netdev); @@ -257,8 +270,9 @@ static int chnl_net_open(struct net_device *dev) if (priv->state != CAIF_CONNECTING) { priv->state = CAIF_CONNECTING; - result = caif_connect_client(&priv->conn_req, &priv->chnl, - &llifindex, &headroom, &tailroom); + result = caif_connect_client(dev_net(dev), &priv->conn_req, + &priv->chnl, &llifindex, + &headroom, &tailroom); if (result != 0) { pr_debug("err: " "Unable to register and open device," @@ -314,7 +328,7 @@ static int chnl_net_open(struct net_device *dev) if (result == 0) { pr_debug("connect timeout\n"); - caif_disconnect_client(&priv->chnl); + caif_disconnect_client(dev_net(dev), &priv->chnl); priv->state = CAIF_DISCONNECTED; pr_debug("state disconnected\n"); result = -ETIMEDOUT; @@ -330,7 +344,7 @@ static int chnl_net_open(struct net_device *dev) return 0; error: - caif_disconnect_client(&priv->chnl); + caif_disconnect_client(dev_net(dev), &priv->chnl); priv->state = CAIF_DISCONNECTED; pr_debug("state disconnected\n"); return result; @@ -344,7 +358,7 @@ static int chnl_net_stop(struct net_device *dev) ASSERT_RTNL(); priv = netdev_priv(dev); priv->state = CAIF_DISCONNECTED; - caif_disconnect_client(&priv->chnl); + caif_disconnect_client(dev_net(dev), &priv->chnl); return 0; } @@ -373,11 +387,18 @@ static const struct net_device_ops netdev_ops = { .ndo_start_xmit = chnl_net_start_xmit, }; +static void chnl_net_destructor(struct net_device *dev) +{ + struct chnl_net *priv = netdev_priv(dev); + caif_free_client(&priv->chnl); + free_netdev(dev); +} + static void ipcaif_net_setup(struct net_device *dev) { struct chnl_net *priv; dev->netdev_ops = &netdev_ops; - dev->destructor = free_netdev; + dev->destructor = chnl_net_destructor; dev->flags |= IFF_NOARP; dev->flags |= IFF_POINTOPOINT; dev->mtu = GPRS_PDP_MTU; @@ -391,7 +412,7 @@ static void ipcaif_net_setup(struct net_device *dev) priv->conn_req.link_selector = CAIF_LINK_HIGH_BANDW; priv->conn_req.priority = CAIF_PRIO_LOW; /* Insert illegal value */ - priv->conn_req.sockaddr.u.dgm.connection_id = -1; + priv->conn_req.sockaddr.u.dgm.connection_id = 0; priv->flowenabled = false; init_waitqueue_head(&priv->netmgmt_wq); @@ -453,6 +474,10 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev, pr_warn("device rtml registration failed\n"); else list_add(&caifdev->list_field, &chnl_net_list); + + /* Take ifindex as connection-id if null */ + if (caifdev->conn_req.sockaddr.u.dgm.connection_id == 0) + caifdev->conn_req.sockaddr.u.dgm.connection_id = dev->ifindex; return ret; } diff --git a/net/can/af_can.c b/net/can/af_can.c index 733d66f1b05a..094fc5332d42 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -84,8 +84,8 @@ static DEFINE_SPINLOCK(can_rcvlists_lock); static struct kmem_cache *rcv_cache __read_mostly; /* table of registered CAN protocols */ -static struct can_proto *proto_tab[CAN_NPROTO] __read_mostly; -static DEFINE_SPINLOCK(proto_tab_lock); +static const struct can_proto *proto_tab[CAN_NPROTO] __read_mostly; +static DEFINE_MUTEX(proto_tab_lock); struct timer_list can_stattimer; /* timer for statistics update */ struct s_stats can_stats; /* packet statistics */ @@ -115,11 +115,29 @@ static void can_sock_destruct(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); } +static const struct can_proto *can_get_proto(int protocol) +{ + const struct can_proto *cp; + + rcu_read_lock(); + cp = rcu_dereference(proto_tab[protocol]); + if (cp && !try_module_get(cp->prot->owner)) + cp = NULL; + rcu_read_unlock(); + + return cp; +} + +static inline void can_put_proto(const struct can_proto *cp) +{ + module_put(cp->prot->owner); +} + static int can_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; - struct can_proto *cp; + const struct can_proto *cp; int err = 0; sock->state = SS_UNCONNECTED; @@ -130,9 +148,12 @@ static int can_create(struct net *net, struct socket *sock, int protocol, if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; + cp = can_get_proto(protocol); + #ifdef CONFIG_MODULES - /* try to load protocol module kernel is modular */ - if (!proto_tab[protocol]) { + if (!cp) { + /* try to load protocol module if kernel is modular */ + err = request_module("can-proto-%d", protocol); /* @@ -143,22 +164,18 @@ static int can_create(struct net *net, struct socket *sock, int protocol, if (err && printk_ratelimit()) printk(KERN_ERR "can: request_module " "(can-proto-%d) failed.\n", protocol); + + cp = can_get_proto(protocol); } #endif - spin_lock(&proto_tab_lock); - cp = proto_tab[protocol]; - if (cp && !try_module_get(cp->prot->owner)) - cp = NULL; - spin_unlock(&proto_tab_lock); - /* check for available protocol and correct usage */ if (!cp) return -EPROTONOSUPPORT; if (cp->type != sock->type) { - err = -EPROTONOSUPPORT; + err = -EPROTOTYPE; goto errout; } @@ -183,7 +200,7 @@ static int can_create(struct net *net, struct socket *sock, int protocol, } errout: - module_put(cp->prot->owner); + can_put_proto(cp); return err; } @@ -679,7 +696,7 @@ drop: * -EBUSY protocol already in use * -ENOBUF if proto_register() fails */ -int can_proto_register(struct can_proto *cp) +int can_proto_register(const struct can_proto *cp) { int proto = cp->protocol; int err = 0; @@ -694,15 +711,16 @@ int can_proto_register(struct can_proto *cp) if (err < 0) return err; - spin_lock(&proto_tab_lock); + mutex_lock(&proto_tab_lock); + if (proto_tab[proto]) { printk(KERN_ERR "can: protocol %d already registered\n", proto); err = -EBUSY; } else - proto_tab[proto] = cp; + rcu_assign_pointer(proto_tab[proto], cp); - spin_unlock(&proto_tab_lock); + mutex_unlock(&proto_tab_lock); if (err < 0) proto_unregister(cp->prot); @@ -715,17 +733,16 @@ EXPORT_SYMBOL(can_proto_register); * can_proto_unregister - unregister CAN transport protocol * @cp: pointer to CAN protocol structure */ -void can_proto_unregister(struct can_proto *cp) +void can_proto_unregister(const struct can_proto *cp) { int proto = cp->protocol; - spin_lock(&proto_tab_lock); - if (!proto_tab[proto]) { - printk(KERN_ERR "BUG: can: protocol %d is not registered\n", - proto); - } - proto_tab[proto] = NULL; - spin_unlock(&proto_tab_lock); + mutex_lock(&proto_tab_lock); + BUG_ON(proto_tab[proto] != cp); + rcu_assign_pointer(proto_tab[proto], NULL); + mutex_unlock(&proto_tab_lock); + + synchronize_rcu(); proto_unregister(cp->prot); } diff --git a/net/can/bcm.c b/net/can/bcm.c index 871a0ad51025..184a6572b67e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -165,9 +165,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; - seq_printf(m, ">>> socket %p", sk->sk_socket); - seq_printf(m, " / sk %p", sk); - seq_printf(m, " / bo %p", bo); + seq_printf(m, ">>> socket %pK", sk->sk_socket); + seq_printf(m, " / sk %pK", sk); + seq_printf(m, " / bo %pK", bo); seq_printf(m, " / dropped %lu", bo->dropped_usr_msgs); seq_printf(m, " / bound %s", bcm_proc_getifname(ifname, bo->ifindex)); seq_printf(m, " <<<\n"); @@ -387,7 +387,7 @@ static void bcm_tx_timeout_tsklet(unsigned long data) } /* - * bcm_tx_timeout_handler - performes cyclic CAN frame transmissions + * bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) { @@ -1427,9 +1427,14 @@ static int bcm_init(struct sock *sk) static int bcm_release(struct socket *sock) { struct sock *sk = sock->sk; - struct bcm_sock *bo = bcm_sk(sk); + struct bcm_sock *bo; struct bcm_op *op, *next; + if (sk == NULL) + return 0; + + bo = bcm_sk(sk); + /* remove bcm_ops, timer, rx_unregister(), etc. */ unregister_netdevice_notifier(&bo->notifier); @@ -1596,7 +1601,7 @@ static struct proto bcm_proto __read_mostly = { .init = bcm_init, }; -static struct can_proto bcm_can_proto __read_mostly = { +static const struct can_proto bcm_can_proto = { .type = SOCK_DGRAM, .protocol = CAN_BCM, .ops = &bcm_ops, diff --git a/net/can/proc.c b/net/can/proc.c index f4265cc9c3fb..0016f7339699 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -204,12 +204,11 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, hlist_for_each_entry_rcu(r, n, rx_list, list) { char *fmt = (r->can_id & CAN_EFF_FLAG)? - " %-5s %08X %08x %08x %08x %8ld %s\n" : - " %-5s %03X %08x %08lx %08lx %8ld %s\n"; + " %-5s %08x %08x %pK %pK %8ld %s\n" : + " %-5s %03x %08x %pK %pK %8ld %s\n"; seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask, - (unsigned long)r->func, (unsigned long)r->data, - r->matches, r->ident); + r->func, r->data, r->matches, r->ident); } } diff --git a/net/can/raw.c b/net/can/raw.c index 649acfa7c70a..dea99a6e596c 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -305,7 +305,12 @@ static int raw_init(struct sock *sk) static int raw_release(struct socket *sock) { struct sock *sk = sock->sk; - struct raw_sock *ro = raw_sk(sk); + struct raw_sock *ro; + + if (!sk) + return 0; + + ro = raw_sk(sk); unregister_netdevice_notifier(&ro->notifier); @@ -769,7 +774,7 @@ static struct proto raw_proto __read_mostly = { .init = raw_init, }; -static struct can_proto raw_can_proto __read_mostly = { +static const struct can_proto raw_can_proto = { .type = SOCK_RAW, .protocol = CAN_RAW, .ops = &raw_ops, diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig index ad424049b0cf..be683f2d401f 100644 --- a/net/ceph/Kconfig +++ b/net/ceph/Kconfig @@ -4,6 +4,7 @@ config CEPH_LIB select LIBCRC32C select CRYPTO_AES select CRYPTO + select KEYS default n help Choose Y or M here to include cephlib, which provides the diff --git a/net/ceph/auth.c b/net/ceph/auth.c index 549c1f43e1d5..b4bf4ac090f1 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -35,12 +35,12 @@ static int ceph_auth_init_protocol(struct ceph_auth_client *ac, int protocol) /* * setup, teardown. */ -struct ceph_auth_client *ceph_auth_init(const char *name, const char *secret) +struct ceph_auth_client *ceph_auth_init(const char *name, const struct ceph_crypto_key *key) { struct ceph_auth_client *ac; int ret; - dout("auth_init name '%s' secret '%s'\n", name, secret); + dout("auth_init name '%s'\n", name); ret = -ENOMEM; ac = kzalloc(sizeof(*ac), GFP_NOFS); @@ -52,8 +52,8 @@ struct ceph_auth_client *ceph_auth_init(const char *name, const char *secret) ac->name = name; else ac->name = CEPH_AUTH_NAME_DEFAULT; - dout("auth_init name %s secret %s\n", ac->name, secret); - ac->secret = secret; + dout("auth_init name %s\n", ac->name); + ac->key = key; return ac; out: diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 7fd5dfcf6e18..1587dc6010c6 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -662,14 +662,16 @@ int ceph_x_init(struct ceph_auth_client *ac) goto out; ret = -EINVAL; - if (!ac->secret) { + if (!ac->key) { pr_err("no secret set (for auth_x protocol)\n"); goto out_nomem; } - ret = ceph_crypto_key_unarmor(&xi->secret, ac->secret); - if (ret) + ret = ceph_crypto_key_clone(&xi->secret, ac->key); + if (ret < 0) { + pr_err("cannot clone key: %d\n", ret); goto out_nomem; + } xi->starting = true; xi->ticket_handlers = RB_ROOT; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 95f96ab94bba..132963abc266 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -5,6 +5,8 @@ #include <linux/fs.h> #include <linux/inet.h> #include <linux/in6.h> +#include <linux/key.h> +#include <keys/ceph-type.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/parser.h> @@ -20,6 +22,7 @@ #include <linux/ceph/decode.h> #include <linux/ceph/mon_client.h> #include <linux/ceph/auth.h> +#include "crypto.h" @@ -117,9 +120,29 @@ int ceph_compare_options(struct ceph_options *new_opt, if (ret) return ret; - ret = strcmp_null(opt1->secret, opt2->secret); - if (ret) - return ret; + if (opt1->key && !opt2->key) + return -1; + if (!opt1->key && opt2->key) + return 1; + if (opt1->key && opt2->key) { + if (opt1->key->type != opt2->key->type) + return -1; + if (opt1->key->created.tv_sec != opt2->key->created.tv_sec) + return -1; + if (opt1->key->created.tv_nsec != opt2->key->created.tv_nsec) + return -1; + if (opt1->key->len != opt2->key->len) + return -1; + if (opt1->key->key && !opt2->key->key) + return -1; + if (!opt1->key->key && opt2->key->key) + return 1; + if (opt1->key->key && opt2->key->key) { + ret = memcmp(opt1->key->key, opt2->key->key, opt1->key->len); + if (ret) + return ret; + } + } /* any matching mon ip implies a match */ for (i = 0; i < opt1->num_mon; i++) { @@ -176,6 +199,7 @@ enum { Opt_fsid, Opt_name, Opt_secret, + Opt_key, Opt_ip, Opt_last_string, /* string args above */ @@ -192,6 +216,7 @@ static match_table_t opt_tokens = { {Opt_fsid, "fsid=%s"}, {Opt_name, "name=%s"}, {Opt_secret, "secret=%s"}, + {Opt_key, "key=%s"}, {Opt_ip, "ip=%s"}, /* string args above */ {Opt_noshare, "noshare"}, @@ -203,11 +228,56 @@ void ceph_destroy_options(struct ceph_options *opt) { dout("destroy_options %p\n", opt); kfree(opt->name); - kfree(opt->secret); + if (opt->key) { + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); + } kfree(opt); } EXPORT_SYMBOL(ceph_destroy_options); +/* get secret from key store */ +static int get_secret(struct ceph_crypto_key *dst, const char *name) { + struct key *ukey; + int key_err; + int err = 0; + struct ceph_crypto_key *ckey; + + ukey = request_key(&key_type_ceph, name, NULL); + if (!ukey || IS_ERR(ukey)) { + /* request_key errors don't map nicely to mount(2) + errors; don't even try, but still printk */ + key_err = PTR_ERR(ukey); + switch (key_err) { + case -ENOKEY: + pr_warning("ceph: Mount failed due to key not found: %s\n", name); + break; + case -EKEYEXPIRED: + pr_warning("ceph: Mount failed due to expired key: %s\n", name); + break; + case -EKEYREVOKED: + pr_warning("ceph: Mount failed due to revoked key: %s\n", name); + break; + default: + pr_warning("ceph: Mount failed due to unknown key error" + " %d: %s\n", key_err, name); + } + err = -EPERM; + goto out; + } + + ckey = ukey->payload.data; + err = ceph_crypto_key_clone(dst, ckey); + if (err) + goto out_key; + /* pass through, err is 0 */ + +out_key: + key_put(ukey); +out: + return err; +} + int ceph_parse_options(struct ceph_options **popt, char *options, const char *dev_name, const char *dev_name_end, int (*parse_extra_token)(char *c, void *private), @@ -295,9 +365,24 @@ int ceph_parse_options(struct ceph_options **popt, char *options, GFP_KERNEL); break; case Opt_secret: - opt->secret = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) { + err = -ENOMEM; + goto out; + } + err = ceph_crypto_key_unarmor(opt->key, argstr[0].from); + if (err < 0) + goto out; + break; + case Opt_key: + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) { + err = -ENOMEM; + goto out; + } + err = get_secret(opt->key, argstr[0].from); + if (err < 0) + goto out; break; /* misc */ @@ -394,8 +479,8 @@ void ceph_destroy_client(struct ceph_client *client) ceph_osdc_stop(&client->osdc); /* - * make sure mds and osd connections close out before destroying - * the auth module, which is needed to free those connections' + * make sure osd connections close out before destroying the + * auth module, which is needed to free those connections' * ceph_authorizers. */ ceph_msgr_flush(); @@ -496,10 +581,14 @@ static int __init init_ceph_lib(void) if (ret < 0) goto out; - ret = ceph_msgr_init(); + ret = ceph_crypto_init(); if (ret < 0) goto out_debugfs; + ret = ceph_msgr_init(); + if (ret < 0) + goto out_crypto; + pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n", CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL, CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT, @@ -507,6 +596,8 @@ static int __init init_ceph_lib(void) return 0; +out_crypto: + ceph_crypto_shutdown(); out_debugfs: ceph_debugfs_cleanup(); out: @@ -517,6 +608,7 @@ static void __exit exit_ceph_lib(void) { dout("exit_ceph_lib\n"); ceph_msgr_exit(); + ceph_crypto_shutdown(); ceph_debugfs_cleanup(); } diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 7b505b0c983f..5a8009c9e0cd 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -5,10 +5,23 @@ #include <linux/scatterlist.h> #include <linux/slab.h> #include <crypto/hash.h> +#include <linux/key-type.h> +#include <keys/ceph-type.h> #include <linux/ceph/decode.h> #include "crypto.h" +int ceph_crypto_key_clone(struct ceph_crypto_key *dst, + const struct ceph_crypto_key *src) +{ + memcpy(dst, src, sizeof(struct ceph_crypto_key)); + dst->key = kmalloc(src->len, GFP_NOFS); + if (!dst->key) + return -ENOMEM; + memcpy(dst->key, src->key, src->len); + return 0; +} + int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end) { if (*p + sizeof(u16) + sizeof(key->created) + @@ -410,3 +423,63 @@ int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, return -EINVAL; } } + +int ceph_key_instantiate(struct key *key, const void *data, size_t datalen) +{ + struct ceph_crypto_key *ckey; + int ret; + void *p; + + ret = -EINVAL; + if (datalen <= 0 || datalen > 32767 || !data) + goto err; + + ret = key_payload_reserve(key, datalen); + if (ret < 0) + goto err; + + ret = -ENOMEM; + ckey = kmalloc(sizeof(*ckey), GFP_KERNEL); + if (!ckey) + goto err; + + /* TODO ceph_crypto_key_decode should really take const input */ + p = (void*)data; + ret = ceph_crypto_key_decode(ckey, &p, (char*)data+datalen); + if (ret < 0) + goto err_ckey; + + key->payload.data = ckey; + return 0; + +err_ckey: + kfree(ckey); +err: + return ret; +} + +int ceph_key_match(const struct key *key, const void *description) +{ + return strcmp(key->description, description) == 0; +} + +void ceph_key_destroy(struct key *key) { + struct ceph_crypto_key *ckey = key->payload.data; + + ceph_crypto_key_destroy(ckey); +} + +struct key_type key_type_ceph = { + .name = "ceph", + .instantiate = ceph_key_instantiate, + .match = ceph_key_match, + .destroy = ceph_key_destroy, +}; + +int ceph_crypto_init(void) { + return register_key_type(&key_type_ceph); +} + +void ceph_crypto_shutdown(void) { + unregister_key_type(&key_type_ceph); +} diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h index f9eccace592b..1919d1550d75 100644 --- a/net/ceph/crypto.h +++ b/net/ceph/crypto.h @@ -19,6 +19,8 @@ static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key) kfree(key->key); } +extern int ceph_crypto_key_clone(struct ceph_crypto_key *dst, + const struct ceph_crypto_key *src); extern int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end); extern int ceph_crypto_key_decode(struct ceph_crypto_key *key, @@ -40,6 +42,8 @@ extern int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, const void *src1, size_t src1_len, const void *src2, size_t src2_len); +extern int ceph_crypto_init(void); +extern void ceph_crypto_shutdown(void); /* armor.c */ extern int ceph_armor(char *dst, const char *src, const char *end); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 05f357828a2f..e15a82ccc05f 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2267,6 +2267,19 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) m->more_to_follow = false; m->pool = NULL; + /* middle */ + m->middle = NULL; + + /* data */ + m->nr_pages = 0; + m->page_alignment = 0; + m->pages = NULL; + m->pagelist = NULL; + m->bio = NULL; + m->bio_iter = NULL; + m->bio_seg = 0; + m->trail = NULL; + /* front */ if (front_len) { if (front_len > PAGE_CACHE_SIZE) { @@ -2286,19 +2299,6 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags) } m->front.iov_len = front_len; - /* middle */ - m->middle = NULL; - - /* data */ - m->nr_pages = 0; - m->page_alignment = 0; - m->pages = NULL; - m->pagelist = NULL; - m->bio = NULL; - m->bio_iter = NULL; - m->bio_seg = 0; - m->trail = NULL; - dout("ceph_msg_new %p front %d\n", m, front_len); return m; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 8a079399174a..cbe31fa45508 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -759,7 +759,7 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl) /* authentication */ monc->auth = ceph_auth_init(cl->options->name, - cl->options->secret); + cl->options->key); if (IS_ERR(monc->auth)) return PTR_ERR(monc->auth); monc->auth->want_keys = diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 02212ed50852..6b5dda1cb5df 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -470,8 +470,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, snapc, ops, use_mempool, GFP_NOFS, NULL, NULL); - if (IS_ERR(req)) - return req; + if (!req) + return NULL; /* calculate max write size */ calc_layout(osdc, vino, layout, off, plen, req, ops); @@ -579,9 +579,15 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc, list_for_each_entry_safe(req, nreq, &osd->o_linger_requests, r_linger_osd) { - __unregister_linger_request(osdc, req); + /* + * reregister request prior to unregistering linger so + * that r_osd is preserved. + */ + BUG_ON(!list_empty(&req->r_req_lru_item)); __register_request(osdc, req); - list_move(&req->r_req_lru_item, &osdc->req_unsent); + list_add(&req->r_req_lru_item, &osdc->req_unsent); + list_add(&req->r_osd_item, &req->r_osd->o_requests); + __unregister_linger_request(osdc, req); dout("requeued lingering %p tid %llu osd%d\n", req, req->r_tid, osd->o_osd); } @@ -798,7 +804,7 @@ static void __register_request(struct ceph_osd_client *osdc, req->r_request->hdr.tid = cpu_to_le64(req->r_tid); INIT_LIST_HEAD(&req->r_req_lru_item); - dout("register_request %p tid %lld\n", req, req->r_tid); + dout("__register_request %p tid %lld\n", req, req->r_tid); __insert_request(osdc, req); ceph_osdc_get_request(req); osdc->num_requests++; @@ -837,8 +843,7 @@ static void __unregister_request(struct ceph_osd_client *osdc, dout("moving osd to %p lru\n", req->r_osd); __move_osd_to_lru(osdc, req->r_osd); } - if (list_empty(&req->r_osd_item) && - list_empty(&req->r_linger_item)) + if (list_empty(&req->r_linger_item)) req->r_osd = NULL; } @@ -883,7 +888,8 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, dout("moving osd to %p lru\n", req->r_osd); __move_osd_to_lru(osdc, req->r_osd); } - req->r_osd = NULL; + if (list_empty(&req->r_osd_item)) + req->r_osd = NULL; } } @@ -917,7 +923,7 @@ EXPORT_SYMBOL(ceph_osdc_set_request_linger); /* * Pick an osd (the first 'up' osd in the pg), allocate the osd struct * (as needed), and set the request r_osd appropriately. If there is - * no up osd, set r_osd to NULL. Move the request to the appropiate list + * no up osd, set r_osd to NULL. Move the request to the appropriate list * (unsent, homeless) or leave on in-flight lru. * * Return 0 if unchanged, 1 if changed, or negative on error. @@ -1602,11 +1608,11 @@ void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg) cookie, ver, event); if (event) { event_work = kmalloc(sizeof(*event_work), GFP_NOIO); - INIT_WORK(&event_work->work, do_event_work); if (!event_work) { dout("ERROR: could not allocate event_work\n"); goto done_err; } + INIT_WORK(&event_work->work, do_event_work); event_work->event = event; event_work->ver = ver; event_work->notify_id = notify_id; @@ -1672,7 +1678,7 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, if (req->r_sent == 0) { rc = __map_request(osdc, req); if (rc < 0) - return rc; + goto out_unlock; if (req->r_osd == NULL) { dout("send_request %p no up osds in pg\n", req); ceph_monc_request_next_osdmap(&osdc->client->monc); @@ -1689,6 +1695,8 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, } } } + +out_unlock: mutex_unlock(&osdc->request_mutex); up_read(&osdc->map_sem); return rc; diff --git a/net/compat.c b/net/compat.c index 3649d5895361..c578d9382e19 100644 --- a/net/compat.c +++ b/net/compat.c @@ -722,11 +722,11 @@ EXPORT_SYMBOL(compat_mc_getsockopt); /* Argument list sizes for compat_sys_socketcall */ #define AL(x) ((x) * sizeof(u32)) -static unsigned char nas[20] = { +static unsigned char nas[21] = { AL(0), AL(3), AL(3), AL(3), AL(2), AL(3), AL(3), AL(3), AL(4), AL(4), AL(4), AL(6), AL(6), AL(2), AL(5), AL(5), AL(3), AL(3), - AL(4), AL(5) + AL(4), AL(5), AL(4) }; #undef AL @@ -735,6 +735,13 @@ asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, uns return sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } +asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, + unsigned vlen, unsigned int flags) +{ + return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, + flags | MSG_CMSG_COMPAT); +} + asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); @@ -780,7 +787,7 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) u32 a[6]; u32 a0, a1; - if (call < SYS_SOCKET || call > SYS_RECVMMSG) + if (call < SYS_SOCKET || call > SYS_SENDMMSG) return -EINVAL; if (copy_from_user(a, args, nas[call])) return -EFAULT; @@ -839,6 +846,9 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) case SYS_SENDMSG: ret = compat_sys_sendmsg(a0, compat_ptr(a1), a[2]); break; + case SYS_SENDMMSG: + ret = compat_sys_sendmmsg(a0, compat_ptr(a1), a[2], a[3]); + break; case SYS_RECVMSG: ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]); break; diff --git a/net/core/dev.c b/net/core/dev.c index 3da9fb06d47a..c7e305d13b71 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -948,7 +948,7 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); -static int dev_get_valid_name(struct net_device *dev, const char *name, bool fmt) +static int dev_get_valid_name(struct net_device *dev, const char *name) { struct net *net; @@ -958,7 +958,7 @@ static int dev_get_valid_name(struct net_device *dev, const char *name, bool fmt if (!dev_valid_name(name)) return -EINVAL; - if (fmt && strchr(name, '%')) + if (strchr(name, '%')) return dev_alloc_name(dev, name); else if (__dev_get_by_name(net, name)) return -EEXIST; @@ -995,7 +995,7 @@ int dev_change_name(struct net_device *dev, const char *newname) memcpy(oldname, dev->name, IFNAMSIZ); - err = dev_get_valid_name(dev, newname, 1); + err = dev_get_valid_name(dev, newname); if (err < 0) return err; @@ -1007,7 +1007,7 @@ rollback: } write_lock_bh(&dev_base_lock); - hlist_del(&dev->name_hlist); + hlist_del_rcu(&dev->name_hlist); write_unlock_bh(&dev_base_lock); synchronize_rcu(); @@ -1284,11 +1284,13 @@ static int dev_close_many(struct list_head *head) */ int dev_close(struct net_device *dev) { - LIST_HEAD(single); + if (dev->flags & IFF_UP) { + LIST_HEAD(single); - list_add(&dev->unreg_list, &single); - dev_close_many(&single); - list_del(&single); + list_add(&dev->unreg_list, &single); + dev_close_many(&single); + list_del(&single); + } return 0; } EXPORT_SYMBOL(dev_close); @@ -1306,6 +1308,13 @@ void dev_disable_lro(struct net_device *dev) { u32 flags; + /* + * If we're trying to disable lro on a vlan device + * use the underlying physical device instead + */ + if (is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); + if (dev->ethtool_ops && dev->ethtool_ops->get_flags) flags = dev->ethtool_ops->get_flags(dev); else @@ -1315,7 +1324,8 @@ void dev_disable_lro(struct net_device *dev) return; __ethtool_set_flags(dev, flags & ~ETH_FLAG_LRO); - WARN_ON(dev->features & NETIF_F_LRO); + if (unlikely(dev->features & NETIF_F_LRO)) + netdev_WARN(dev, "failed to disable LRO!\n"); } EXPORT_SYMBOL(dev_disable_lro); @@ -2091,7 +2101,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 features; /* - * If device doesnt need skb->dst, release it right now while + * If device doesn't need skb->dst, release it right now while * its hot in this cpu cache */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) @@ -2151,7 +2161,7 @@ gso: nskb->next = NULL; /* - * If device doesnt need nskb->dst, release it right now while + * If device doesn't need nskb->dst, release it right now while * its hot in this cpu cache */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) @@ -2502,8 +2512,8 @@ static inline void ____napi_schedule(struct softnet_data *sd, __u32 __skb_get_rxhash(struct sk_buff *skb) { int nhoff, hash = 0, poff; - struct ipv6hdr *ip6; - struct iphdr *ip; + const struct ipv6hdr *ip6; + const struct iphdr *ip; u8 ip_proto; u32 addr1, addr2, ihl; union { @@ -2518,7 +2528,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(*ip) + nhoff)) goto done; - ip = (struct iphdr *) (skb->data + nhoff); + ip = (const struct iphdr *) (skb->data + nhoff); if (ip->frag_off & htons(IP_MF | IP_OFFSET)) ip_proto = 0; else @@ -2531,7 +2541,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff)) goto done; - ip6 = (struct ipv6hdr *) (skb->data + nhoff); + ip6 = (const struct ipv6hdr *) (skb->data + nhoff); ip_proto = ip6->nexthdr; addr1 = (__force u32) ip6->saddr.s6_addr32[3]; addr2 = (__force u32) ip6->daddr.s6_addr32[3]; @@ -2970,8 +2980,8 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions * a compare and 2 stores extra right now if we dont have it on * but have CONFIG_NET_CLS_ACT - * NOTE: This doesnt stop any functionality; if you dont have - * the ingress scheduler, you just cant add policies on ingress. + * NOTE: This doesn't stop any functionality; if you dont have + * the ingress scheduler, you just can't add policies on ingress. * */ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) @@ -3076,25 +3086,6 @@ void netdev_rx_handler_unregister(struct net_device *dev) } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); -static void vlan_on_bond_hook(struct sk_buff *skb) -{ - /* - * Make sure ARP frames received on VLAN interfaces stacked on - * bonding interfaces still make their way to any base bonding - * device that may have registered for a specific ptype. - */ - if (skb->dev->priv_flags & IFF_802_1Q_VLAN && - vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING && - skb->protocol == htons(ETH_P_ARP)) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - - if (!skb2) - return; - skb2->dev = vlan_dev_real_dev(skb->dev); - netif_rx(skb2); - } -} - static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; @@ -3130,6 +3121,12 @@ another_round: __this_cpu_inc(softnet_data.processed); + if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + goto out; + } + #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); @@ -3177,15 +3174,13 @@ ncls: ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } - if (vlan_hwaccel_do_receive(&skb)) { + if (vlan_do_receive(&skb)) { ret = __netif_receive_skb(skb); goto out; } else if (unlikely(!skb)) goto out; } - vlan_on_bond_hook(skb); - /* deliver only exact match when indicated */ null_or_dev = deliver_exact ? skb->dev : NULL; @@ -3800,7 +3795,7 @@ static void net_rx_action(struct softirq_action *h) * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid - * accidently calling ->poll() when NAPI is not scheduled. + * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (test_bit(NAPI_STATE_SCHED, &n->state)) { @@ -4306,10 +4301,8 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) slave->master = master; - if (old) { - synchronize_net(); + if (old) dev_put(old); - } return 0; } EXPORT_SYMBOL(netdev_set_master); @@ -4510,6 +4503,30 @@ void dev_set_rx_mode(struct net_device *dev) } /** + * dev_ethtool_get_settings - call device's ethtool_ops::get_settings() + * @dev: device + * @cmd: memory area for ethtool_ops::get_settings() result + * + * The cmd arg is initialized properly (cleared and + * ethtool_cmd::cmd field set to ETHTOOL_GSET). + * + * Return device's ethtool_ops::get_settings() result value or + * -EOPNOTSUPP when device doesn't expose + * ethtool_ops::get_settings() operation. + */ +int dev_ethtool_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd) +{ + if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; + + memset(cmd, 0, sizeof(struct ethtool_cmd)); + cmd->cmd = ETHTOOL_GSET; + return dev->ethtool_ops->get_settings(dev, cmd); +} +EXPORT_SYMBOL(dev_ethtool_get_settings); + +/** * dev_get_flags - get flags reported to userspace * @dev: device * @@ -4773,7 +4790,7 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm * is never reached */ WARN_ON(1); - err = -EINVAL; + err = -ENOTTY; break; } @@ -5041,7 +5058,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) /* Set the per device memory buffer space. * Not applicable in our case */ case SIOCSIFLINK: - return -EINVAL; + return -ENOTTY; /* * Unknown or private ioctl. @@ -5062,7 +5079,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) /* Take care of Wireless Extensions */ if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) return wext_handle_ioctl(net, &ifr, cmd, arg); - return -EINVAL; + return -ENOTTY; } } @@ -5114,7 +5131,7 @@ static void rollback_registered_many(struct list_head *head) list_del(&dev->unreg_list); continue; } - + dev->dismantle = true; BUG_ON(dev->reg_state != NETREG_REGISTERED); } @@ -5184,33 +5201,37 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - netdev_info(dev, "mixed HW and IP checksum settings.\n"); + netdev_warn(dev, "mixed HW and IP checksum settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } if ((features & NETIF_F_NO_CSUM) && (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - netdev_info(dev, "mixed no checksumming and other settings.\n"); + netdev_warn(dev, "mixed no checksumming and other settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); } /* Fix illegal SG+CSUM combinations. */ if ((features & NETIF_F_SG) && !(features & NETIF_F_ALL_CSUM)) { - netdev_info(dev, - "Dropping NETIF_F_SG since no checksum feature.\n"); + netdev_dbg(dev, + "Dropping NETIF_F_SG since no checksum feature.\n"); features &= ~NETIF_F_SG; } /* TSO requires that SG is present as well. */ - if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) { - netdev_info(dev, "Dropping NETIF_F_TSO since no SG feature.\n"); - features &= ~NETIF_F_TSO; + if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { + netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); + features &= ~NETIF_F_ALL_TSO; } + /* TSO ECN requires that TSO is present as well. */ + if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) + features &= ~NETIF_F_TSO_ECN; + /* Software GSO depends on SG. */ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { - netdev_info(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); + netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); features &= ~NETIF_F_GSO; } @@ -5220,13 +5241,13 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) if (!((features & NETIF_F_GEN_CSUM) || (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - netdev_info(dev, + netdev_dbg(dev, "Dropping NETIF_F_UFO since no checksum offload features.\n"); features &= ~NETIF_F_UFO; } if (!(features & NETIF_F_SG)) { - netdev_info(dev, + netdev_dbg(dev, "Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n"); features &= ~NETIF_F_UFO; } @@ -5236,11 +5257,13 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) } EXPORT_SYMBOL(netdev_fix_features); -void netdev_update_features(struct net_device *dev) +int __netdev_update_features(struct net_device *dev) { u32 features; int err = 0; + ASSERT_RTNL(); + features = netdev_get_wanted_features(dev); if (dev->netdev_ops->ndo_fix_features) @@ -5250,24 +5273,60 @@ void netdev_update_features(struct net_device *dev) features = netdev_fix_features(dev, features); if (dev->features == features) - return; + return 0; - netdev_info(dev, "Features changed: 0x%08x -> 0x%08x\n", + netdev_dbg(dev, "Features changed: 0x%08x -> 0x%08x\n", dev->features, features); if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); - if (!err) - dev->features = features; - else if (err < 0) + if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted 0x%08x, left 0x%08x\n", err, features, dev->features); + return -1; + } + + if (!err) + dev->features = features; + + return 1; +} + +/** + * netdev_update_features - recalculate device features + * @dev: the device to check + * + * Recalculate dev->features set and send notifications if it + * has changed. Should be called after driver or hardware dependent + * conditions might have changed that influence the features. + */ +void netdev_update_features(struct net_device *dev) +{ + if (__netdev_update_features(dev)) + netdev_features_change(dev); } EXPORT_SYMBOL(netdev_update_features); /** + * netdev_change_features - recalculate device features + * @dev: the device to check + * + * Recalculate dev->features set and send notifications even + * if they have not changed. Should be called instead of + * netdev_update_features() if also dev->vlan_features might + * have changed to allow the changes to be propagated to stacked + * VLAN devices. + */ +void netdev_change_features(struct net_device *dev) +{ + __netdev_update_features(dev); + netdev_features_change(dev); +} +EXPORT_SYMBOL(netdev_change_features); + +/** * netif_stacked_transfer_operstate - transfer operstate * @rootdev: the root or lower level device to transfer state from * @dev: the device to transfer operstate to @@ -5383,6 +5442,10 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; + ret = dev_get_valid_name(dev, dev->name); + if (ret < 0) + goto out; + /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -5393,10 +5456,6 @@ int register_netdevice(struct net_device *dev) } } - ret = dev_get_valid_name(dev, dev->name, 0); - if (ret) - goto err_uninit; - dev->ifindex = dev_new_index(net); if (dev->iflink == -1) dev->iflink = dev->ifindex; @@ -5408,10 +5467,12 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_SOFT_FEATURES; dev->wanted_features = dev->features & dev->hw_features; - /* Avoid warning from netdev_fix_features() for GSO without SG */ - if (!(dev->wanted_features & NETIF_F_SG)) { - dev->wanted_features &= ~NETIF_F_GSO; - dev->features &= ~NETIF_F_GSO; + /* Turn on no cache copy if HW is doing checksum */ + dev->hw_features |= NETIF_F_NOCACHE_COPY; + if ((dev->features & NETIF_F_ALL_CSUM) && + !(dev->features & NETIF_F_NO_CSUM)) { + dev->wanted_features |= NETIF_F_NOCACHE_COPY; + dev->features |= NETIF_F_NOCACHE_COPY; } /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, @@ -5430,7 +5491,7 @@ int register_netdevice(struct net_device *dev) goto err_uninit; dev->reg_state = NETREG_REGISTERED; - netdev_update_features(dev); + __netdev_update_features(dev); /* * Default initial state at registry is that the @@ -5527,19 +5588,7 @@ int register_netdev(struct net_device *dev) int err; rtnl_lock(); - - /* - * If the name is a format string the caller wants us to do a - * name allocation. - */ - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto out; - } - err = register_netdevice(dev); -out: rtnl_unlock(); return err; } @@ -5912,7 +5961,10 @@ EXPORT_SYMBOL(free_netdev); void synchronize_net(void) { might_sleep(); - synchronize_rcu(); + if (rtnl_is_locked()) + synchronize_rcu_expedited(); + else + synchronize_rcu(); } EXPORT_SYMBOL(synchronize_net); @@ -6021,7 +6073,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* We get here if we can't use the current device name */ if (!pat) goto out; - if (dev_get_valid_name(dev, pat, 1)) + if (dev_get_valid_name(dev, pat) < 0) goto out; } @@ -6153,29 +6205,20 @@ static int dev_cpu_callback(struct notifier_block *nfb, */ u32 netdev_increment_features(u32 all, u32 one, u32 mask) { - /* If device needs checksumming, downgrade to it. */ - if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) - all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM); - else if (mask & NETIF_F_ALL_CSUM) { - /* If one device supports v4/v6 checksumming, set for all. */ - if (one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM) && - !(all & NETIF_F_GEN_CSUM)) { - all &= ~NETIF_F_ALL_CSUM; - all |= one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - } + if (mask & NETIF_F_GEN_CSUM) + mask |= NETIF_F_ALL_CSUM; + mask |= NETIF_F_VLAN_CHALLENGED; - /* If one device supports hw checksumming, set for all. */ - if (one & NETIF_F_GEN_CSUM && !(all & NETIF_F_GEN_CSUM)) { - all &= ~NETIF_F_ALL_CSUM; - all |= NETIF_F_HW_CSUM; - } - } + all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; + all &= one | ~NETIF_F_ALL_FOR_ALL; - one |= NETIF_F_ALL_CSUM; + /* If device needs checksumming, downgrade to it. */ + if (all & (NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM)) + all &= ~NETIF_F_NO_CSUM; - one |= all & NETIF_F_ONE_FOR_ALL; - all &= one | NETIF_F_LLTX | NETIF_F_GSO | NETIF_F_UFO; - all |= one & mask & NETIF_F_ONE_FOR_ALL; + /* If one device supports hw checksumming, set for all. */ + if (all & NETIF_F_GEN_CSUM) + all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); return all; } @@ -6336,7 +6379,7 @@ static void __net_exit default_device_exit(struct net *net) if (dev->rtnl_link_ops) continue; - /* Push remaing network devices to init_net */ + /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 7b39f3ed2fda..e2e66939ed00 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -68,14 +68,6 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, return __hw_addr_add_ex(list, addr, addr_len, addr_type, false); } -static void ha_rcu_free(struct rcu_head *head) -{ - struct netdev_hw_addr *ha; - - ha = container_of(head, struct netdev_hw_addr, rcu_head); - kfree(ha); -} - static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, unsigned char *addr, int addr_len, unsigned char addr_type, bool global) @@ -94,7 +86,7 @@ static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, if (--ha->refcount) return 0; list_del_rcu(&ha->list); - call_rcu(&ha->rcu_head, ha_rcu_free); + kfree_rcu(ha, rcu_head); list->count--; return 0; } @@ -197,7 +189,7 @@ void __hw_addr_flush(struct netdev_hw_addr_list *list) list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); - call_rcu(&ha->rcu_head, ha_rcu_free); + kfree_rcu(ha, rcu_head); } list->count = 0; } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 706502ff64aa..7f36b38e060f 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -207,14 +207,6 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi) rcu_read_unlock(); } - -static void free_dm_hw_stat(struct rcu_head *head) -{ - struct dm_hw_stat_delta *n; - n = container_of(head, struct dm_hw_stat_delta, rcu); - kfree(n); -} - static int set_all_monitor_traces(int state) { int rc = 0; @@ -245,7 +237,7 @@ static int set_all_monitor_traces(int state) list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { if (new_stat->dev == NULL) { list_del_rcu(&new_stat->list); - call_rcu(&new_stat->rcu, free_dm_hw_stat); + kfree_rcu(new_stat, rcu); } } break; @@ -314,7 +306,7 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = NULL; if (trace_state == TRACE_OFF) { list_del_rcu(&new_stat->list); - call_rcu(&new_stat->rcu, free_dm_hw_stat); + kfree_rcu(new_stat, rcu); break; } } diff --git a/net/core/dst.c b/net/core/dst.c index 91104d35de7d..9ccca038444f 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <net/net_namespace.h> #include <linux/sched.h> +#include <linux/prefetch.h> #include <net/dst.h> @@ -33,9 +34,6 @@ * 3) This list is guarded by a mutex, * so that the gc_task and dst_dev_event() can be synchronized. */ -#if RT_CACHE_DEBUG >= 2 -static atomic_t dst_total = ATOMIC_INIT(0); -#endif /* * We want to keep lock & list close together @@ -69,10 +67,6 @@ static void dst_gc_task(struct work_struct *work) unsigned long expires = ~0L; struct dst_entry *dst, *next, head; struct dst_entry *last = &head; -#if RT_CACHE_DEBUG >= 2 - ktime_t time_start = ktime_get(); - struct timespec elapsed; -#endif mutex_lock(&dst_gc_mutex); next = dst_busy_list; @@ -146,15 +140,6 @@ loop: spin_unlock_bh(&dst_garbage.lock); mutex_unlock(&dst_gc_mutex); -#if RT_CACHE_DEBUG >= 2 - elapsed = ktime_to_timespec(ktime_sub(ktime_get(), time_start)); - printk(KERN_DEBUG "dst_total: %d delayed: %d work_perf: %d" - " expires: %lu elapsed: %lu us\n", - atomic_read(&dst_total), delayed, work_performed, - expires, - elapsed.tv_sec * USEC_PER_SEC + - elapsed.tv_nsec / NSEC_PER_USEC); -#endif } int dst_discard(struct sk_buff *skb) @@ -166,7 +151,8 @@ EXPORT_SYMBOL(dst_discard); const u32 dst_default_metrics[RTAX_MAX]; -void *dst_alloc(struct dst_ops *ops, int initial_ref) +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, + int initial_ref, int initial_obsolete, int flags) { struct dst_entry *dst; @@ -174,18 +160,36 @@ void *dst_alloc(struct dst_ops *ops, int initial_ref) if (ops->gc(ops)) return NULL; } - dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC); + dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) return NULL; - atomic_set(&dst->__refcnt, initial_ref); + dst->child = NULL; + dst->dev = dev; + if (dev) + dev_hold(dev); dst->ops = ops; - dst->lastuse = jiffies; - dst->path = dst; - dst->input = dst->output = dst_discard; dst_init_metrics(dst, dst_default_metrics, true); -#if RT_CACHE_DEBUG >= 2 - atomic_inc(&dst_total); + dst->expires = 0UL; + dst->path = dst; + dst->neighbour = NULL; + dst->hh = NULL; +#ifdef CONFIG_XFRM + dst->xfrm = NULL; +#endif + dst->input = dst_discard; + dst->output = dst_discard; + dst->error = 0; + dst->obsolete = initial_obsolete; + dst->header_len = 0; + dst->trailer_len = 0; +#ifdef CONFIG_IP_ROUTE_CLASSID + dst->tclassid = 0; #endif + atomic_set(&dst->__refcnt, initial_ref); + dst->__use = 0; + dst->lastuse = jiffies; + dst->flags = flags; + dst->next = NULL; dst_entries_add(ops, 1); return dst; } @@ -245,9 +249,6 @@ again: dst->ops->destroy(dst); if (dst->dev) dev_put(dst->dev); -#if RT_CACHE_DEBUG >= 2 - atomic_dec(&dst_total); -#endif kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; @@ -314,7 +315,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) { unsigned long prev, new; - new = (unsigned long) dst_default_metrics; + new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY; prev = cmpxchg(&dst->_metrics, old, new); if (prev == old) kfree(__DST_METRICS_PTR(old)); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 74ead9eca126..fd14116ad7f0 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -21,6 +21,8 @@ #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/slab.h> +#include <linux/rtnetlink.h> +#include <linux/sched.h> /* * Some useful ethtool_ops methods that're device independent. @@ -231,6 +233,29 @@ static int ethtool_set_feature_compat(struct net_device *dev, return 1; } +static int ethtool_set_flags_compat(struct net_device *dev, + int (*legacy_set)(struct net_device *, u32), + struct ethtool_set_features_block *features, u32 mask) +{ + u32 value; + + if (!legacy_set) + return 0; + + if (!(features[0].valid & mask)) + return 0; + + value = dev->features & ~features[0].valid; + value |= features[0].requested; + + features[0].valid &= ~mask; + + if (legacy_set(dev, value & mask) < 0) + netdev_info(dev, "Legacy flags change failed\n"); + + return 1; +} + static int ethtool_set_features_compat(struct net_device *dev, struct ethtool_set_features_block *features) { @@ -247,7 +272,7 @@ static int ethtool_set_features_compat(struct net_device *dev, features, NETIF_F_ALL_TSO); compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_rx_csum, features, NETIF_F_RXCSUM); - compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_flags, + compat |= ethtool_set_flags_compat(dev, dev->ethtool_ops->set_flags, features, flags_dup_features); return compat; @@ -317,7 +342,7 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) dev->wanted_features &= ~features[0].valid; dev->wanted_features |= features[0].valid & features[0].requested; - netdev_update_features(dev); + __netdev_update_features(dev); if ((dev->wanted_features ^ dev->features) & features[0].valid) ret |= ETHTOOL_F_WISH; @@ -330,7 +355,7 @@ static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GS /* NETIF_F_IP_CSUM */ "tx-checksum-ipv4", /* NETIF_F_NO_CSUM */ "tx-checksum-unneeded", /* NETIF_F_HW_CSUM */ "tx-checksum-ip-generic", - /* NETIF_F_IPV6_CSUM */ "tx_checksum-ipv6", + /* NETIF_F_IPV6_CSUM */ "tx-checksum-ipv6", /* NETIF_F_HIGHDMA */ "highdma", /* NETIF_F_FRAGLIST */ "tx-scatter-gather-fraglist", /* NETIF_F_HW_VLAN_TX */ "tx-vlan-hw-insert", @@ -359,8 +384,8 @@ static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GS /* NETIF_F_NTUPLE */ "rx-ntuple-filter", /* NETIF_F_RXHASH */ "rx-hashing", /* NETIF_F_RXCSUM */ "rx-checksum", - "", - "", + /* NETIF_F_NOCACHE_COPY */ "tx-nocache-copy", + /* NETIF_F_LOOPBACK */ "loopback", }; static int __ethtool_get_sset_count(struct net_device *dev, int sset) @@ -499,7 +524,7 @@ static int ethtool_set_one_feature(struct net_device *dev, else dev->wanted_features &= ~mask; - netdev_update_features(dev); + __netdev_update_features(dev); return 0; } @@ -544,14 +569,14 @@ int __ethtool_set_flags(struct net_device *dev, u32 data) } /* allow changing only bits set in hw_features */ - changed = (data ^ dev->wanted_features) & flags_dup_features; + changed = (data ^ dev->features) & flags_dup_features; if (changed & ~dev->hw_features) return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP; dev->wanted_features = - (dev->wanted_features & ~changed) | data; + (dev->wanted_features & ~changed) | (data & dev->hw_features); - netdev_update_features(dev); + __netdev_update_features(dev); return 0; } @@ -908,6 +933,9 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, struct ethtool_rx_ntuple_flow_spec_container *fsc = NULL; int ret; + if (!ops->set_rx_ntuple) + return -EOPNOTSUPP; + if (!(dev->features & NETIF_F_NTUPLE)) return -EINVAL; @@ -1441,6 +1469,35 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_ringparam(dev, &ringparam); } +static noinline_for_stack int ethtool_get_channels(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + + if (!dev->ethtool_ops->get_channels) + return -EOPNOTSUPP; + + dev->ethtool_ops->get_channels(dev, &channels); + + if (copy_to_user(useraddr, &channels, sizeof(channels))) + return -EFAULT; + return 0; +} + +static noinline_for_stack int ethtool_set_channels(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_channels channels; + + if (!dev->ethtool_ops->set_channels) + return -EOPNOTSUPP; + + if (copy_from_user(&channels, useraddr, sizeof(channels))) + return -EFAULT; + + return dev->ethtool_ops->set_channels(dev, &channels); +} + static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) { struct ethtool_pauseparam pauseparam = { ETHTOOL_GPAUSEPARAM }; @@ -1618,14 +1675,60 @@ out: static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; + static bool busy; + int rc; - if (!dev->ethtool_ops->phys_id) + if (!dev->ethtool_ops->set_phys_id) return -EOPNOTSUPP; + if (busy) + return -EBUSY; + if (copy_from_user(&id, useraddr, sizeof(id))) return -EFAULT; - return dev->ethtool_ops->phys_id(dev, id.data); + rc = dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); + if (rc < 0) + return rc; + + /* Drop the RTNL lock while waiting, but prevent reentry or + * removal of the device. + */ + busy = true; + dev_hold(dev); + rtnl_unlock(); + + if (rc == 0) { + /* Driver will handle this itself */ + schedule_timeout_interruptible( + id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT); + } else { + /* Driver expects to be called at twice the frequency in rc */ + int n = rc * 2, i, interval = HZ / n; + + /* Count down seconds */ + do { + /* Count down iterations per second */ + i = n; + do { + rtnl_lock(); + rc = dev->ethtool_ops->set_phys_id(dev, + (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); + rtnl_unlock(); + if (rc) + break; + schedule_timeout_interruptible(interval); + } while (!signal_pending(current) && --i != 0); + } while (!signal_pending(current) && + (id.data == 0 || --id.data != 0)); + } + + rtnl_lock(); + dev_put(dev); + busy = false; + + (void)dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); + return rc; } static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) @@ -1743,6 +1846,87 @@ static noinline_for_stack int ethtool_flash_device(struct net_device *dev, return dev->ethtool_ops->flash_device(dev, &efl); } +static int ethtool_set_dump(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_dump dump; + + if (!dev->ethtool_ops->set_dump) + return -EOPNOTSUPP; + + if (copy_from_user(&dump, useraddr, sizeof(dump))) + return -EFAULT; + + return dev->ethtool_ops->set_dump(dev, &dump); +} + +static int ethtool_get_dump_flag(struct net_device *dev, + void __user *useraddr) +{ + int ret; + struct ethtool_dump dump; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!dev->ethtool_ops->get_dump_flag) + return -EOPNOTSUPP; + + if (copy_from_user(&dump, useraddr, sizeof(dump))) + return -EFAULT; + + ret = ops->get_dump_flag(dev, &dump); + if (ret) + return ret; + + if (copy_to_user(useraddr, &dump, sizeof(dump))) + return -EFAULT; + return 0; +} + +static int ethtool_get_dump_data(struct net_device *dev, + void __user *useraddr) +{ + int ret; + __u32 len; + struct ethtool_dump dump, tmp; + const struct ethtool_ops *ops = dev->ethtool_ops; + void *data = NULL; + + if (!dev->ethtool_ops->get_dump_data || + !dev->ethtool_ops->get_dump_flag) + return -EOPNOTSUPP; + + if (copy_from_user(&dump, useraddr, sizeof(dump))) + return -EFAULT; + + memset(&tmp, 0, sizeof(tmp)); + tmp.cmd = ETHTOOL_GET_DUMP_FLAG; + ret = ops->get_dump_flag(dev, &tmp); + if (ret) + return ret; + + len = (tmp.len > dump.len) ? dump.len : tmp.len; + if (!len) + return -EFAULT; + + data = vzalloc(tmp.len); + if (!data) + return -ENOMEM; + ret = ops->get_dump_data(dev, &dump, data); + if (ret) + goto out; + + if (copy_to_user(useraddr, &dump, sizeof(dump))) { + ret = -EFAULT; + goto out; + } + useraddr += offsetof(struct ethtool_dump, data); + if (copy_to_user(useraddr, data, len)) + ret = -EFAULT; +out: + vfree(data); + return ret; +} + /* The main entry point in this file. Called from net/core/dev.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) @@ -1953,6 +2137,21 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SGRO: rc = ethtool_set_one_feature(dev, useraddr, ethcmd); break; + case ETHTOOL_GCHANNELS: + rc = ethtool_get_channels(dev, useraddr); + break; + case ETHTOOL_SCHANNELS: + rc = ethtool_set_channels(dev, useraddr); + break; + case ETHTOOL_SET_DUMP: + rc = ethtool_set_dump(dev, useraddr); + break; + case ETHTOOL_GET_DUMP_FLAG: + rc = ethtool_get_dump_flag(dev, useraddr); + break; + case ETHTOOL_GET_DUMP_DATA: + rc = ethtool_get_dump_data(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 8248ebb5891d..008dc70b064b 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -590,7 +590,8 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, int idx = 0; struct fib_rule *rule; - list_for_each_entry(rule, &ops->rules_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; @@ -601,6 +602,7 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, skip: idx++; } + rcu_read_unlock(); cb->args[1] = idx; rules_ops_put(ops); diff --git a/net/core/filter.c b/net/core/filter.c index 232b1873bb28..36f975fa87cb 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -38,65 +38,7 @@ #include <asm/unaligned.h> #include <linux/filter.h> #include <linux/reciprocal_div.h> - -enum { - BPF_S_RET_K = 1, - BPF_S_RET_A, - BPF_S_ALU_ADD_K, - BPF_S_ALU_ADD_X, - BPF_S_ALU_SUB_K, - BPF_S_ALU_SUB_X, - BPF_S_ALU_MUL_K, - BPF_S_ALU_MUL_X, - BPF_S_ALU_DIV_X, - BPF_S_ALU_AND_K, - BPF_S_ALU_AND_X, - BPF_S_ALU_OR_K, - BPF_S_ALU_OR_X, - BPF_S_ALU_LSH_K, - BPF_S_ALU_LSH_X, - BPF_S_ALU_RSH_K, - BPF_S_ALU_RSH_X, - BPF_S_ALU_NEG, - BPF_S_LD_W_ABS, - BPF_S_LD_H_ABS, - BPF_S_LD_B_ABS, - BPF_S_LD_W_LEN, - BPF_S_LD_W_IND, - BPF_S_LD_H_IND, - BPF_S_LD_B_IND, - BPF_S_LD_IMM, - BPF_S_LDX_W_LEN, - BPF_S_LDX_B_MSH, - BPF_S_LDX_IMM, - BPF_S_MISC_TAX, - BPF_S_MISC_TXA, - BPF_S_ALU_DIV_K, - BPF_S_LD_MEM, - BPF_S_LDX_MEM, - BPF_S_ST, - BPF_S_STX, - BPF_S_JMP_JA, - BPF_S_JMP_JEQ_K, - BPF_S_JMP_JEQ_X, - BPF_S_JMP_JGE_K, - BPF_S_JMP_JGE_X, - BPF_S_JMP_JGT_K, - BPF_S_JMP_JGT_X, - BPF_S_JMP_JSET_K, - BPF_S_JMP_JSET_X, - /* Ancillary data */ - BPF_S_ANC_PROTOCOL, - BPF_S_ANC_PKTTYPE, - BPF_S_ANC_IFINDEX, - BPF_S_ANC_NLATTR, - BPF_S_ANC_NLATTR_NEST, - BPF_S_ANC_MARK, - BPF_S_ANC_QUEUE, - BPF_S_ANC_HATYPE, - BPF_S_ANC_RXHASH, - BPF_S_ANC_CPU, -}; +#include <linux/ratelimit.h> /* No hurry in this branch */ static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size) @@ -145,7 +87,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { - unsigned int pkt_len = sk_run_filter(skb, filter->insns); + unsigned int pkt_len = SK_RUN_FILTER(filter, skb); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } @@ -409,7 +351,9 @@ load_b: continue; } default: - WARN_ON(1); + WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n", + fentry->code, fentry->jt, + fentry->jf, fentry->k); return 0; } } @@ -425,7 +369,7 @@ EXPORT_SYMBOL(sk_run_filter); * As we dont want to clear mem[] array for each packet going through * sk_run_filter(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure - * a malicious user doesnt try to abuse us. + * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(struct sock_filter *filter, int flen) { @@ -638,6 +582,7 @@ void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); + bpf_jit_free(fp); kfree(fp); } EXPORT_SYMBOL(sk_filter_release_rcu); @@ -672,6 +617,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) atomic_set(&fp->refcnt, 1); fp->len = fprog->len; + fp->bpf_func = sk_run_filter; err = sk_chk_filter(fp->insns, fp->len); if (err) { @@ -679,6 +625,8 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return err; } + bpf_jit_compile(fp); + old_fp = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); rcu_assign_pointer(sk->sk_filter, fp); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 7c2373321b74..43b03dd71e85 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -249,13 +249,6 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, } EXPORT_SYMBOL(gen_new_estimator); -static void __gen_kill_estimator(struct rcu_head *head) -{ - struct gen_estimator *e = container_of(head, - struct gen_estimator, e_rcu); - kfree(e); -} - /** * gen_kill_estimator - remove a rate estimator * @bstats: basic statistics @@ -279,7 +272,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, write_unlock(&est_lock); list_del_rcu(&e->list); - call_rcu(&e->e_rcu, __gen_kill_estimator); + kfree_rcu(e, e_rcu); } spin_unlock_bh(&est_tree_lock); } diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 01a1101b5936..a7b342131869 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -129,7 +129,7 @@ static void linkwatch_schedule_work(int urgent) if (!cancel_delayed_work(&linkwatch_work)) return; - /* Otherwise we reschedule it again for immediate exection. */ + /* Otherwise we reschedule it again for immediate execution. */ schedule_delayed_work(&linkwatch_work, 0); } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5ceb257e860c..11b98bc2aa8f 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -28,6 +28,7 @@ static const char fmt_hex[] = "%#x\n"; static const char fmt_long_hex[] = "%#lx\n"; static const char fmt_dec[] = "%d\n"; +static const char fmt_udec[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; @@ -145,13 +146,10 @@ static ssize_t show_speed(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && - netdev->ethtool_ops && - netdev->ethtool_ops->get_settings) { - struct ethtool_cmd cmd = { ETHTOOL_GSET }; - - if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) - ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd)); + if (netif_running(netdev)) { + struct ethtool_cmd cmd; + if (!dev_ethtool_get_settings(netdev, &cmd)) + ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd)); } rtnl_unlock(); return ret; @@ -166,13 +164,11 @@ static ssize_t show_duplex(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && - netdev->ethtool_ops && - netdev->ethtool_ops->get_settings) { - struct ethtool_cmd cmd = { ETHTOOL_GSET }; - - if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) - ret = sprintf(buf, "%s\n", cmd.duplex ? "full" : "half"); + if (netif_running(netdev)) { + struct ethtool_cmd cmd; + if (!dev_ethtool_get_settings(netdev, &cmd)) + ret = sprintf(buf, "%s\n", + cmd.duplex ? "full" : "half"); } rtnl_unlock(); return ret; @@ -565,13 +561,6 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, return len; } -static void rps_map_release(struct rcu_head *rcu) -{ - struct rps_map *map = container_of(rcu, struct rps_map, rcu); - - kfree(map); -} - static ssize_t store_rps_map(struct netdev_rx_queue *queue, struct rx_queue_attribute *attribute, const char *buf, size_t len) @@ -619,7 +608,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, spin_unlock(&rps_map_lock); if (old_map) - call_rcu(&old_map->rcu, rps_map_release); + kfree_rcu(old_map, rcu); free_cpumask_var(mask); return len; @@ -728,7 +717,7 @@ static void rx_queue_release(struct kobject *kobj) map = rcu_dereference_raw(queue->rps_map); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); - call_rcu(&map->rcu, rps_map_release); + kfree_rcu(map, rcu); } flow_table = rcu_dereference_raw(queue->rps_flow_table); @@ -898,21 +887,6 @@ static ssize_t show_xps_map(struct netdev_queue *queue, return len; } -static void xps_map_release(struct rcu_head *rcu) -{ - struct xps_map *map = container_of(rcu, struct xps_map, rcu); - - kfree(map); -} - -static void xps_dev_maps_release(struct rcu_head *rcu) -{ - struct xps_dev_maps *dev_maps = - container_of(rcu, struct xps_dev_maps, rcu); - - kfree(dev_maps); -} - static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) @@ -968,7 +942,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, } else pos = map_len = alloc_len = 0; - need_set = cpu_isset(cpu, *mask) && cpu_online(cpu); + need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu); #ifdef CONFIG_NUMA if (need_set) { if (numa_node == -2) @@ -1009,7 +983,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) - call_rcu(&map->rcu, xps_map_release); + kfree_rcu(map, rcu); if (new_dev_maps->cpu_map[cpu]) nonempty = 1; } @@ -1022,7 +996,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, } if (dev_maps) - call_rcu(&dev_maps->rcu, xps_dev_maps_release); + kfree_rcu(dev_maps, rcu); netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node : NUMA_NO_NODE); @@ -1084,7 +1058,7 @@ static void netdev_queue_release(struct kobject *kobj) else { RCU_INIT_POINTER(dev_maps->cpu_map[i], NULL); - call_rcu(&map->rcu, xps_map_release); + kfree_rcu(map, rcu); map = NULL; } } @@ -1094,7 +1068,7 @@ static void netdev_queue_release(struct kobject *kobj) if (!nonempty) { RCU_INIT_POINTER(dev->xps_maps, NULL); - call_rcu(&dev_maps->rcu, xps_dev_maps_release); + kfree_rcu(dev_maps, rcu); } } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 3f860261c5ee..2e2dce6583e1 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,14 +27,6 @@ EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ -static void net_generic_release(struct rcu_head *rcu) -{ - struct net_generic *ng; - - ng = container_of(rcu, struct net_generic, rcu); - kfree(ng); -} - static int net_assign_generic(struct net *net, int id, void *data) { struct net_generic *ng, *old_ng; @@ -68,7 +60,7 @@ static int net_assign_generic(struct net *net, int id, void *data) memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); rcu_assign_pointer(net->gen, ng); - call_rcu(&old_ng->rcu, net_generic_release); + kfree_rcu(old_ng, rcu); assign: ng->ptr[id - 1] = data; return 0; @@ -216,11 +208,14 @@ static void net_free(struct net *net) kmem_cache_free(net_cachep, net); } -static struct net *net_create(void) +struct net *copy_net_ns(unsigned long flags, struct net *old_net) { struct net *net; int rv; + if (!(flags & CLONE_NEWNET)) + return get_net(old_net); + net = net_alloc(); if (!net) return ERR_PTR(-ENOMEM); @@ -239,13 +234,6 @@ static struct net *net_create(void) return net; } -struct net *copy_net_ns(unsigned long flags, struct net *old_net) -{ - if (!(flags & CLONE_NEWNET)) - return get_net(old_net); - return net_create(); -} - static DEFINE_SPINLOCK(cleanup_list_lock); static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 06be2431753e..2d7d6d473781 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -539,7 +539,7 @@ int __netpoll_rx(struct sk_buff *skb) { int proto, len, ulen; int hits = 0; - struct iphdr *iph; + const struct iphdr *iph; struct udphdr *uh; struct netpoll_info *npinfo = skb->dev->npinfo; struct netpoll *np, *tmp; @@ -698,32 +698,8 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if (*cur != 0) { /* MAC address */ - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim = 0; - np->remote_mac[0] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim = 0; - np->remote_mac[1] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - if ((delim = strchr(cur, ':')) == NULL) + if (!mac_pton(cur, np->remote_mac)) goto parse_failed; - *delim = 0; - np->remote_mac[2] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim = 0; - np->remote_mac[3] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim = 0; - np->remote_mac[4] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - np->remote_mac[5] = simple_strtol(cur, NULL, 16); } netpoll_print_options(np); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index aeeece72b72f..f76079cd750c 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -156,6 +156,7 @@ #include <linux/wait.h> #include <linux/etherdevice.h> #include <linux/kthread.h> +#include <linux/prefetch.h> #include <net/net_namespace.h> #include <net/checksum.h> #include <net/ipv6.h> @@ -449,7 +450,6 @@ static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); static unsigned int scan_ip6(const char *s, char ip[16]); -static unsigned int fmt_ip6(char *s, const char ip[16]); /* Module parameters, defaults. */ static int pg_count_d __read_mostly = 1000; @@ -556,21 +556,13 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->skb_priority); if (pkt_dev->flags & F_IPV6) { - char b1[128], b2[128], b3[128]; - fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_saddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_saddr.s6_addr); seq_printf(seq, - " saddr: %s min_saddr: %s max_saddr: %s\n", b1, - b2, b3); - - fmt_ip6(b1, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_daddr.s6_addr); - seq_printf(seq, - " daddr: %s min_daddr: %s max_daddr: %s\n", b1, - b2, b3); - + " saddr: %pI6c min_saddr: %pI6c max_saddr: %pI6c\n" + " daddr: %pI6c min_daddr: %pI6c max_daddr: %pI6c\n", + &pkt_dev->in6_saddr, + &pkt_dev->min_in6_saddr, &pkt_dev->max_in6_saddr, + &pkt_dev->in6_daddr, + &pkt_dev->min_in6_daddr, &pkt_dev->max_in6_daddr); } else { seq_printf(seq, " dst_min: %s dst_max: %s\n", @@ -706,10 +698,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->cur_src_mac_offset); if (pkt_dev->flags & F_IPV6) { - char b1[128], b2[128]; - fmt_ip6(b1, pkt_dev->cur_in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->cur_in6_saddr.s6_addr); - seq_printf(seq, " cur_saddr: %s cur_daddr: %s\n", b2, b1); + seq_printf(seq, " cur_saddr: %pI6c cur_daddr: %pI6c\n", + &pkt_dev->cur_in6_saddr, + &pkt_dev->cur_in6_daddr); } else seq_printf(seq, " cur_saddr: 0x%x cur_daddr: 0x%x\n", pkt_dev->cur_saddr, pkt_dev->cur_daddr); @@ -1309,7 +1300,7 @@ static ssize_t pktgen_if_write(struct file *file, buf[len] = 0; scan_ip6(buf, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_daddr.s6_addr); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr); ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr); @@ -1332,7 +1323,7 @@ static ssize_t pktgen_if_write(struct file *file, buf[len] = 0; scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr); ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->min_in6_daddr); @@ -1355,7 +1346,7 @@ static ssize_t pktgen_if_write(struct file *file, buf[len] = 0; scan_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_daddr); if (debug) printk(KERN_DEBUG "pktgen: dst6_max set to: %s\n", buf); @@ -1376,7 +1367,7 @@ static ssize_t pktgen_if_write(struct file *file, buf[len] = 0; scan_ip6(buf, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_saddr.s6_addr); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr); ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr); @@ -1430,11 +1421,6 @@ static ssize_t pktgen_if_write(struct file *file, return count; } if (!strcmp(name, "dst_mac")) { - char *v = valstr; - unsigned char old_dmac[ETH_ALEN]; - unsigned char *m = pkt_dev->dst_mac; - memcpy(old_dmac, pkt_dev->dst_mac, ETH_ALEN); - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); if (len < 0) return len; @@ -1442,35 +1428,16 @@ static ssize_t pktgen_if_write(struct file *file, memset(valstr, 0, sizeof(valstr)); if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; - i += len; - - for (*m = 0; *v && m < pkt_dev->dst_mac + 6; v++) { - int value; - - value = hex_to_bin(*v); - if (value >= 0) - *m = *m * 16 + value; - - if (*v == ':') { - m++; - *m = 0; - } - } + if (!mac_pton(valstr, pkt_dev->dst_mac)) + return -EINVAL; /* Set up Dest MAC */ - if (compare_ether_addr(old_dmac, pkt_dev->dst_mac)) - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); + memcpy(&pkt_dev->hh[0], pkt_dev->dst_mac, ETH_ALEN); - sprintf(pg_result, "OK: dstmac"); + sprintf(pg_result, "OK: dstmac %pM", pkt_dev->dst_mac); return count; } if (!strcmp(name, "src_mac")) { - char *v = valstr; - unsigned char old_smac[ETH_ALEN]; - unsigned char *m = pkt_dev->src_mac; - - memcpy(old_smac, pkt_dev->src_mac, ETH_ALEN); - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); if (len < 0) return len; @@ -1478,26 +1445,13 @@ static ssize_t pktgen_if_write(struct file *file, memset(valstr, 0, sizeof(valstr)); if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; - i += len; - - for (*m = 0; *v && m < pkt_dev->src_mac + 6; v++) { - int value; - - value = hex_to_bin(*v); - if (value >= 0) - *m = *m * 16 + value; - - if (*v == ':') { - m++; - *m = 0; - } - } + if (!mac_pton(valstr, pkt_dev->src_mac)) + return -EINVAL; /* Set up Src MAC */ - if (compare_ether_addr(old_smac, pkt_dev->src_mac)) - memcpy(&(pkt_dev->hh[6]), pkt_dev->src_mac, ETH_ALEN); + memcpy(&pkt_dev->hh[6], pkt_dev->src_mac, ETH_ALEN); - sprintf(pg_result, "OK: srcmac"); + sprintf(pg_result, "OK: srcmac %pM", pkt_dev->src_mac); return count; } @@ -2514,7 +2468,6 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) { struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; int err = 0; - struct iphdr *iph; if (!x) return 0; @@ -2524,7 +2477,6 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) return 0; spin_lock(&x->lock); - iph = ip_hdr(skb); err = x->outer_mode->output(x, skb); if (err) @@ -2624,6 +2576,7 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, } else { int frags = pkt_dev->nfrags; int i, len; + int frag_len; if (frags > MAX_SKB_FRAGS) @@ -2635,6 +2588,8 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, } i = 0; + frag_len = (datalen/frags) < PAGE_SIZE ? + (datalen/frags) : PAGE_SIZE; while (datalen > 0) { if (unlikely(!pkt_dev->page)) { int node = numa_node_id(); @@ -2648,38 +2603,18 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, skb_shinfo(skb)->frags[i].page = pkt_dev->page; get_page(pkt_dev->page); skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + /*last fragment, fill rest of data*/ + if (i == (frags - 1)) + skb_shinfo(skb)->frags[i].size = + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + else + skb_shinfo(skb)->frags[i].size = frag_len; datalen -= skb_shinfo(skb)->frags[i].size; skb->len += skb_shinfo(skb)->frags[i].size; skb->data_len += skb_shinfo(skb)->frags[i].size; i++; skb_shinfo(skb)->nr_frags = i; } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; - - skb_shinfo(skb)->frags[i - 1].size -= rem; - - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } } /* Stamp the time, and sequence number, @@ -2917,79 +2852,6 @@ static unsigned int scan_ip6(const char *s, char ip[16]) return len; } -static char tohex(char hexdigit) -{ - return hexdigit > 9 ? hexdigit + 'a' - 10 : hexdigit + '0'; -} - -static int fmt_xlong(char *s, unsigned int i) -{ - char *bak = s; - *s = tohex((i >> 12) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex((i >> 8) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex((i >> 4) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex(i & 0xf); - return s - bak + 1; -} - -static unsigned int fmt_ip6(char *s, const char ip[16]) -{ - unsigned int len; - unsigned int i; - unsigned int temp; - unsigned int compressing; - int j; - - len = 0; - compressing = 0; - for (j = 0; j < 16; j += 2) { - -#ifdef V4MAPPEDPREFIX - if (j == 12 && !memcmp(ip, V4mappedprefix, 12)) { - inet_ntoa_r(*(struct in_addr *)(ip + 12), s); - temp = strlen(s); - return len + temp; - } -#endif - temp = ((unsigned long)(unsigned char)ip[j] << 8) + - (unsigned long)(unsigned char)ip[j + 1]; - if (temp == 0) { - if (!compressing) { - compressing = 1; - if (j == 0) { - *s++ = ':'; - ++len; - } - } - } else { - if (compressing) { - compressing = 0; - *s++ = ':'; - ++len; - } - i = fmt_xlong(s, temp); - len += i; - s += i; - if (j < 14) { - *s++ = ':'; - ++len; - } - } - } - if (compressing) { - *s++ = ':'; - ++len; - } - *s = 0; - return len; -} - static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct pktgen_dev *pkt_dev) { @@ -3682,13 +3544,12 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) return -ENOMEM; strcpy(pkt_dev->odevname, ifname); - pkt_dev->flows = vmalloc_node(MAX_CFLOWS * sizeof(struct flow_state), + pkt_dev->flows = vzalloc_node(MAX_CFLOWS * sizeof(struct flow_state), node); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; } - memset(pkt_dev->flows, 0, MAX_CFLOWS * sizeof(struct flow_state)); pkt_dev->removal_mark = 0; pkt_dev->min_pkt_size = ETH_ZLEN; @@ -3846,6 +3707,7 @@ static int __init pg_init(void) { int cpu; struct proc_dir_entry *pe; + int ret = 0; pr_info("%s", version); @@ -3856,11 +3718,10 @@ static int __init pg_init(void) pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops); if (pe == NULL) { pr_err("ERROR: cannot create %s procfs entry\n", PGCTRL); - proc_net_remove(&init_net, PG_PROC_DIR); - return -EINVAL; + ret = -EINVAL; + goto remove_dir; } - /* Register us to receive netdevice events */ register_netdevice_notifier(&pktgen_notifier_block); for_each_online_cpu(cpu) { @@ -3874,13 +3735,18 @@ static int __init pg_init(void) if (list_empty(&pktgen_threads)) { pr_err("ERROR: Initialization failed for all threads\n"); - unregister_netdevice_notifier(&pktgen_notifier_block); - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(&init_net, PG_PROC_DIR); - return -ENODEV; + ret = -ENODEV; + goto unregister; } return 0; + + unregister: + unregister_netdevice_notifier(&pktgen_notifier_block); + remove_proc_entry(PGCTRL, pg_proc_dir); + remove_dir: + proc_net_remove(&init_net, PG_PROC_DIR); + return ret; } static void __exit pg_cleanup(void) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 49f7ea5b4c75..2d56cb9b0b94 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -196,7 +196,7 @@ EXPORT_SYMBOL_GPL(__rtnl_register); * as failure of this function is very unlikely, it can only happen due * to lack of memory when allocating the chain to store all message * handlers for a protocol. Meant for use in init functions where lack - * of memory implies no sense in continueing. + * of memory implies no sense in continuing. */ void rtnl_register(int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit) @@ -850,6 +850,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct nlattr *attr, *af_spec; struct rtnl_af_ops *af_ops; + ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -1007,10 +1008,11 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) s_h = cb->args[0]; s_idx = cb->args[1]; + rcu_read_lock(); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { if (idx < s_idx) goto cont; if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, @@ -1023,6 +1025,7 @@ cont: } } out: + rcu_read_unlock(); cb->args[1] = idx; cb->args[0] = h; @@ -1440,7 +1443,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, errout: if (err < 0 && modified && net_ratelimit()) printk(KERN_WARNING "A link change request failed with " - "some changes comitted already. Interface %s may " + "some changes committed already. Interface %s may " "have been left with an inconsistent configuration, " "please check.\n", dev->name); @@ -1499,6 +1502,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; int err; + LIST_HEAD(list_kill); err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1522,7 +1526,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (!ops) return -EOPNOTSUPP; - ops->dellink(dev, NULL); + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + list_del(&list_kill); return 0; } @@ -1570,12 +1576,6 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, dev->rtnl_link_state = RTNL_LINK_INITIALIZING; dev->real_num_tx_queues = real_num_queues; - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto err_free; - } - if (tb[IFLA_MTU]) dev->mtu = nla_get_u32(tb[IFLA_MTU]); if (tb[IFLA_ADDRESS]) @@ -1595,8 +1595,6 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, return dev; -err_free: - free_netdev(dev); err: return ERR_PTR(err); } @@ -1963,6 +1961,8 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_GOING_DOWN: case NETDEV_UNREGISTER: case NETDEV_UNREGISTER_BATCH: + case NETDEV_RELEASE: + case NETDEV_JOIN: break; default: rtmsg_ifinfo(RTM_NEWLINK, dev, 0); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 801dd08908f9..46cbd28f40f9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -57,6 +57,7 @@ #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/errqueue.h> +#include <linux/prefetch.h> #include <net/protocol.h> #include <net/dst.h> @@ -2267,7 +2268,7 @@ EXPORT_SYMBOL(skb_prepare_seq_read); * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * - * Note 1: The size of each block of data returned can be arbitary, + * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy seqeuental * reads of potentially non linear data. * @@ -2993,6 +2994,9 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb->destructor = sock_rmem_free; atomic_add(skb->truesize, &sk->sk_rmem_alloc); + /* before exiting rcu section, make sure dst is refcounted */ + skb_dst_force(skb); + skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk, skb->len); diff --git a/net/core/sock.c b/net/core/sock.c index 7dfed792434d..6e819780c232 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -215,7 +215,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; -/* Maximal space eaten by iovec or ancilliary data plus some space */ +/* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); @@ -1175,7 +1175,7 @@ static void __sk_free(struct sock *sk) void sk_free(struct sock *sk) { /* - * We substract one from sk_wmem_alloc and can know if + * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ @@ -1185,10 +1185,10 @@ void sk_free(struct sock *sk) EXPORT_SYMBOL(sk_free); /* - * Last sock_put should drop referrence to sk->sk_net. It has already - * been dropped in sk_change_net. Taking referrence to stopping namespace + * Last sock_put should drop reference to sk->sk_net. It has already + * been dropped in sk_change_net. Taking reference to stopping namespace * is not an option. - * Take referrence to a socket to remove it from hash _alive_ and after that + * Take reference to a socket to remove it from hash _alive_ and after that * destroy it in the context of init_net. */ void sk_release_kernel(struct sock *sk) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 385b6095fdc4..77a65f031488 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -17,6 +17,7 @@ #include <net/ip.h> #include <net/sock.h> +#include <net/net_ratelimit.h> #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(ctl_table *table, int write, @@ -122,6 +123,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_BPF_JIT + { + .procname = "bpf_jit_enable", + .data = &bpf_jit_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif { .procname = "netdev_tstamp_prequeue", .data = &netdev_tstamp_prequeue, diff --git a/net/core/utils.c b/net/core/utils.c index 5fea0ab21902..386e263f6066 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -27,6 +27,7 @@ #include <linux/ratelimit.h> #include <net/sock.h> +#include <net/net_ratelimit.h> #include <asm/byteorder.h> #include <asm/system.h> @@ -296,3 +297,27 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, csum_unfold(*sum))); } EXPORT_SYMBOL(inet_proto_csum_replace4); + +int mac_pton(const char *s, u8 *mac) +{ + int i; + + /* XX:XX:XX:XX:XX:XX */ + if (strlen(s) < 3 * ETH_ALEN - 1) + return 0; + + /* Don't dirty result unless string is valid MAC. */ + for (i = 0; i < ETH_ALEN; i++) { + if (!strchr("0123456789abcdefABCDEF", s[i * 3])) + return 0; + if (!strchr("0123456789abcdefABCDEF", s[i * 3 + 1])) + return 0; + if (i != ETH_ALEN - 1 && s[i * 3 + 2] != ':') + return 0; + } + for (i = 0; i < ETH_ALEN; i++) { + mac[i] = (hex_to_bin(s[i * 3]) << 4) | hex_to_bin(s[i * 3 + 1]); + } + return 1; +} +EXPORT_SYMBOL(mac_pton); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ae451c6d83ba..8c36adfd1919 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -40,13 +40,15 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { + const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; __be16 orig_sport, orig_dport; - struct rtable *rt; __be32 daddr, nexthop; + struct flowi4 *fl4; + struct rtable *rt; int err; + struct ip_options_rcu *inet_opt; dp->dccps_role = DCCP_ROLE_CLIENT; @@ -57,15 +59,19 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; - if (inet->opt != NULL && inet->opt->srr) { + + inet_opt = rcu_dereference_protected(inet->inet_opt, + sock_owned_by_user(sk)); + if (inet_opt != NULL && inet_opt->opt.srr) { if (daddr == 0) return -EINVAL; - nexthop = inet->opt->faddr; + nexthop = inet_opt->opt.faddr; } orig_sport = inet->inet_sport; orig_dport = usin->sin_port; - rt = ip_route_connect(nexthop, inet->inet_saddr, + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_DCCP, orig_sport, orig_dport, sk, true); @@ -77,19 +83,19 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -ENETUNREACH; } - if (inet->opt == NULL || !inet->opt->srr) - daddr = rt->rt_dst; + if (inet_opt == NULL || !inet_opt->opt.srr) + daddr = fl4->daddr; if (inet->inet_saddr == 0) - inet->inet_saddr = rt->rt_src; + inet->inet_saddr = fl4->saddr; inet->inet_rcv_saddr = inet->inet_saddr; inet->inet_dport = usin->sin_port; inet->inet_daddr = daddr; inet_csk(sk)->icsk_ext_hdr_len = 0; - if (inet->opt != NULL) - inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen; + if (inet_opt) + inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; /* * Socket identity is still unknown (sport may be zero). * However we set state to DCCP_REQUESTING and not releasing socket @@ -101,8 +107,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err != 0) goto failure; - rt = ip_route_newports(rt, IPPROTO_DCCP, - orig_sport, orig_dport, + rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { rt = NULL; @@ -391,32 +396,30 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, if (sk_acceptq_is_full(sk)) goto exit_overflow; - if (dst == NULL && (dst = inet_csk_route_req(sk, req)) == NULL) - goto exit; - newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) goto exit_nonewsk; - sk_setup_caps(newsk, dst); - newinet = inet_sk(newsk); ireq = inet_rsk(req); newinet->inet_daddr = ireq->rmt_addr; newinet->inet_rcv_saddr = ireq->loc_addr; newinet->inet_saddr = ireq->loc_addr; - newinet->opt = ireq->opt; + newinet->inet_opt = ireq->opt; ireq->opt = NULL; newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->inet_id = jiffies; + if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) + goto put_and_exit; + + sk_setup_caps(newsk, dst); + dccp_sync_mss(newsk, dst_mtu(dst)); - if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); - goto exit; - } + if (__inet_inherit_port(sk, newsk) < 0) + goto put_and_exit; __inet_hash_nolisten(newsk, NULL); return newsk; @@ -428,6 +431,9 @@ exit_nonewsk: exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; +put_and_exit: + sock_put(newsk); + goto exit; } EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock); @@ -491,8 +497,9 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, int err = -1; struct sk_buff *skb; struct dst_entry *dst; + struct flowi4 fl4; - dst = inet_csk_route_req(sk, req); + dst = inet_csk_route_req(sk, &fl4, req); if (dst == NULL) goto out; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index de1b7e37ad5b..8dc4348774a5 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -54,8 +54,8 @@ static void dccp_v6_hash(struct sock *sk) /* add pseudo-header to DCCP checksum stored in skb->csum */ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, - struct in6_addr *saddr, - struct in6_addr *daddr) + const struct in6_addr *saddr, + const struct in6_addr *daddr) { return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum); } @@ -87,7 +87,7 @@ static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; + const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct ipv6_pinfo *np; @@ -296,7 +296,7 @@ static void dccp_v6_reqsk_destructor(struct request_sock *req) static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) { - struct ipv6hdr *rxip6h; + const struct ipv6hdr *rxip6h; struct sk_buff *skb; struct flowi6 fl6; struct net *net = dev_net(skb_dst(rxskb)->dev); @@ -573,7 +573,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, First: no IPv4 options. */ - newinet->opt = NULL; + newinet->inet_opt = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; diff --git a/net/dccp/options.c b/net/dccp/options.c index f06ffcfc8d71..4b2ab657ac8e 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -123,6 +123,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R: if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */ break; + if (len == 0) + goto out_invalid_option; rc = dccp_feat_parse_options(sk, dreq, mandatory, opt, *value, value + 1, len - 1); if (rc) diff --git a/net/dccp/output.c b/net/dccp/output.c index 784d30210543..fab108e51e5a 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -43,7 +43,7 @@ static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb) static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) { if (likely(skb != NULL)) { - const struct inet_sock *inet = inet_sk(sk); + struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct dccp_sock *dp = dccp_sk(sk); struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); @@ -136,14 +136,14 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) DCCP_INC_STATS(DCCP_MIB_OUTSEGS); - err = icsk->icsk_af_ops->queue_xmit(skb); + err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl); return net_xmit_eval(err); } return -ENOBUFS; } /** - * dccp_determine_ccmps - Find out about CCID-specfic packet-size limits + * dccp_determine_ccmps - Find out about CCID-specific packet-size limits * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.), * since the RX CCID is restricted to feedback packets (Acks), which are small * in comparison with the data traffic. A value of 0 means "no current CCMPS". diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 0dcaa903e00e..cf26ac74a188 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -332,14 +332,9 @@ static struct dn_ifaddr *dn_dev_alloc_ifa(void) return ifa; } -static void dn_dev_free_ifa_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct dn_ifaddr, rcu)); -} - static void dn_dev_free_ifa(struct dn_ifaddr *ifa) { - call_rcu(&ifa->rcu, dn_dev_free_ifa_rcu); + kfree_rcu(ifa, rcu); } static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr __rcu **ifap, int destroy) @@ -752,7 +747,8 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) skip_naddr = cb->args[1]; idx = 0; - for_each_netdev(&init_net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { if (idx < skip_ndevs) goto cont; else if (idx > skip_ndevs) { @@ -761,11 +757,11 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) skip_naddr = 0; } - if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) + if ((dn_db = rcu_dereference(dev->dn_ptr)) == NULL) goto cont; - for (ifa = rtnl_dereference(dn_db->ifa_list), dn_idx = 0; ifa; - ifa = rtnl_dereference(ifa->ifa_next), dn_idx++) { + for (ifa = rcu_dereference(dn_db->ifa_list), dn_idx = 0; ifa; + ifa = rcu_dereference(ifa->ifa_next), dn_idx++) { if (dn_idx < skip_naddr) continue; @@ -778,6 +774,7 @@ cont: idx++; } done: + rcu_read_unlock(); cb->args[0] = idx; cb->args[1] = dn_idx; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 9f09d4fc2880..74544bc6fdec 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1125,13 +1125,11 @@ make_route: if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - rt = dst_alloc(&dn_dst_ops, 0); + rt = dst_alloc(&dn_dst_ops, dev_out, 1, 0, DST_HOST); if (rt == NULL) goto e_nobufs; - atomic_set(&rt->dst.__refcnt, 1); - rt->dst.flags = DST_HOST; - + memset(&rt->fld, 0, sizeof(rt->fld)); rt->fld.saddr = oldflp->saddr; rt->fld.daddr = oldflp->daddr; rt->fld.flowidn_oif = oldflp->flowidn_oif; @@ -1146,8 +1144,6 @@ make_route: rt->rt_dst_map = fld.daddr; rt->rt_src_map = fld.saddr; - rt->dst.dev = dev_out; - dev_hold(dev_out); rt->dst.neighbour = neigh; neigh = NULL; @@ -1399,10 +1395,11 @@ static int dn_route_input_slow(struct sk_buff *skb) } make_route: - rt = dst_alloc(&dn_dst_ops, 0); + rt = dst_alloc(&dn_dst_ops, out_dev, 0, 0, DST_HOST); if (rt == NULL) goto e_nobufs; + memset(&rt->fld, 0, sizeof(rt->fld)); rt->rt_saddr = fld.saddr; rt->rt_daddr = fld.daddr; rt->rt_gateway = fld.daddr; @@ -1419,9 +1416,7 @@ make_route: rt->fld.flowidn_iif = in_dev->ifindex; rt->fld.flowidn_mark = fld.flowidn_mark; - rt->dst.flags = DST_HOST; rt->dst.neighbour = neigh; - rt->dst.dev = out_dev; rt->dst.lastuse = jiffies; rt->dst.output = dn_rt_bug; switch(res.type) { @@ -1440,8 +1435,6 @@ make_route: rt->dst.input = dst_discard; } rt->rt_flags = flags; - if (rt->dst.dev) - dev_hold(rt->dst.dev); err = dn_rt_set_next_hop(rt, &res); if (err) diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 99d8d3a40998..bd0a52dd1d40 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -123,11 +123,11 @@ static inline void dn_rebuild_zone(struct dn_zone *dz, struct dn_fib_node **old_ht, int old_divisor) { - int i; struct dn_fib_node *f, **fp, *next; + int i; for(i = 0; i < old_divisor; i++) { - for(f = old_ht[i]; f; f = f->fn_next) { + for(f = old_ht[i]; f; f = next) { next = f->fn_next; for(fp = dn_chain_p(f->fn_key, dz); *fp && dn_key_leq((*fp)->fn_key, f->fn_key); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 87bb5f4de0e8..c53ded2a98df 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -41,12 +41,12 @@ config NET_DSA_MV88E6XXX_NEED_PPU default n config NET_DSA_MV88E6131 - bool "Marvell 88E6095/6095F/6131 ethernet switch chip support" + bool "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support" select NET_DSA_MV88E6XXX select NET_DSA_MV88E6XXX_NEED_PPU select NET_DSA_TAG_DSA ---help--- - This enables support for the Marvell 88E6095/6095F/6131 + This enables support for the Marvell 88E6085/6095/6095F/6131 ethernet switch chips. config NET_DSA_MV88E6123_61_65 diff --git a/net/dsa/mv88e6131.c b/net/dsa/mv88e6131.c index bb2b41bc854e..45f7411e90ba 100644 --- a/net/dsa/mv88e6131.c +++ b/net/dsa/mv88e6131.c @@ -14,6 +14,13 @@ #include "dsa_priv.h" #include "mv88e6xxx.h" +/* + * Switch product IDs + */ +#define ID_6085 0x04a0 +#define ID_6095 0x0950 +#define ID_6131 0x1060 + static char *mv88e6131_probe(struct mii_bus *bus, int sw_addr) { int ret; @@ -21,9 +28,11 @@ static char *mv88e6131_probe(struct mii_bus *bus, int sw_addr) ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), 0x03); if (ret >= 0) { ret &= 0xfff0; - if (ret == 0x0950) + if (ret == ID_6085) + return "Marvell 88E6085"; + if (ret == ID_6095) return "Marvell 88E6095/88E6095F"; - if (ret == 0x1060) + if (ret == ID_6131) return "Marvell 88E6131"; } @@ -124,7 +133,7 @@ static int mv88e6131_setup_global(struct dsa_switch *ds) * Ignore removed tag data on doubly tagged packets, disable * flow control messages, force flow control priority to the * highest, and send all special multicast frames to the CPU - * port at the higest priority. + * port at the highest priority. */ REG_WRITE(REG_GLOBAL2, 0x05, 0x00ff); @@ -164,6 +173,7 @@ static int mv88e6131_setup_global(struct dsa_switch *ds) static int mv88e6131_setup_port(struct dsa_switch *ds, int p) { + struct mv88e6xxx_priv_state *ps = (void *)(ds + 1); int addr = REG_PORT(p); u16 val; @@ -171,10 +181,13 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p) * MAC Forcing register: don't force link, speed, duplex * or flow control state to any particular values on physical * ports, but force the CPU port and all DSA ports to 1000 Mb/s - * full duplex. + * (100 Mb/s on 6085) full duplex. */ if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p)) - REG_WRITE(addr, 0x01, 0x003e); + if (ps->id == ID_6085) + REG_WRITE(addr, 0x01, 0x003d); /* 100 Mb/s */ + else + REG_WRITE(addr, 0x01, 0x003e); /* 1000 Mb/s */ else REG_WRITE(addr, 0x01, 0x0003); @@ -194,8 +207,15 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p) * mode, but do not enable forwarding of unknown unicasts. */ val = 0x0433; - if (p == dsa_upstream_port(ds)) + if (p == dsa_upstream_port(ds)) { val |= 0x0104; + /* + * On 6085, unknown multicast forward is controlled + * here rather than in Port Control 2 register. + */ + if (ps->id == ID_6085) + val |= 0x0008; + } if (ds->dsa_port_mask & (1 << p)) val |= 0x0100; REG_WRITE(addr, 0x04, val); @@ -238,10 +258,19 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p) * If this is the upstream port for this switch, enable * forwarding of unknown multicast addresses. */ - val = 0x0080 | dsa_upstream_port(ds); - if (p == dsa_upstream_port(ds)) - val |= 0x0040; - REG_WRITE(addr, 0x08, val); + if (ps->id == ID_6085) + /* + * on 6085, bits 3:0 are reserved, bit 6 control ARP + * mirroring, and multicast forward is handled in + * Port Control register. + */ + REG_WRITE(addr, 0x08, 0x0080); + else { + val = 0x0080 | dsa_upstream_port(ds); + if (p == dsa_upstream_port(ds)) + val |= 0x0040; + REG_WRITE(addr, 0x08, val); + } /* * Rate Control: disable ingress rate limiting. @@ -286,6 +315,8 @@ static int mv88e6131_setup(struct dsa_switch *ds) mv88e6xxx_ppu_state_init(ds); mutex_init(&ps->stats_mutex); + ps->id = REG_READ(REG_PORT(0), 0x03) & 0xfff0; + ret = mv88e6131_switch_reset(ds); if (ret < 0) return ret; diff --git a/net/dsa/mv88e6xxx.h b/net/dsa/mv88e6xxx.h index eb0e0aaa9f1b..61156ca26a0d 100644 --- a/net/dsa/mv88e6xxx.h +++ b/net/dsa/mv88e6xxx.h @@ -39,6 +39,8 @@ struct mv88e6xxx_priv_state { * Hold this mutex over snapshot + dump sequences. */ struct mutex stats_mutex; + + int id; /* switch product id */ }; struct mv88e6xxx_hw_stat { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 64ca2a6fa0d4..0a47b6c37038 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -288,7 +288,6 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_drvinfo = dsa_slave_get_drvinfo, .nway_reset = dsa_slave_nway_reset, .get_link = dsa_slave_get_link, - .set_sg = ethtool_op_set_sg, .get_strings = dsa_slave_get_strings, .get_ethtool_stats = dsa_slave_get_ethtool_stats, .get_sset_count = dsa_slave_get_sset_count, diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index 116d3fd3d669..a1d9f3787dd5 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -935,7 +935,6 @@ static void aun_data_available(struct sock *sk, int slen) struct sk_buff *skb; unsigned char *data; struct aunhdr *ah; - struct iphdr *ip; size_t len; while ((skb = skb_recv_datagram(sk, 0, 1, &err)) == NULL) { @@ -949,7 +948,6 @@ static void aun_data_available(struct sock *sk, int slen) data = skb_transport_header(skb) + sizeof(struct udphdr); ah = (struct aunhdr *)data; len = skb->len - sizeof(struct udphdr); - ip = ip_hdr(skb); switch (ah->code) { @@ -962,12 +960,6 @@ static void aun_data_available(struct sock *sk, int slen) case 4: aun_tx_ack(ah->handle, ECTYPE_TRANSMIT_NOT_LISTENING); break; -#if 0 - /* This isn't quite right yet. */ - case 5: - aun_send_response(ip->saddr, ah->handle, 6, ah->cb); - break; -#endif default: printk(KERN_DEBUG "unknown AUN packet (type %d)\n", data[0]); } diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index ce2d33582859..5761185f884e 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -1,5 +1,3 @@ obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o af_802154-y := af_ieee802154.o raw.o dgram.o - -ccflags-y += -Wall -DDEBUG diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 0dc772d0d125..f2dc69cffb57 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -11,7 +11,7 @@ obj-y := route.o inetpeer.o protocol.o \ datagram.o raw.o udp.o udplite.o \ arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o \ - inet_fragment.o + inet_fragment.o ping.o obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o obj-$(CONFIG_PROC_FS) += proc.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 807d83c02ef6..cc1463156cd0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -105,6 +105,7 @@ #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> +#include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/raw.h> @@ -153,7 +154,7 @@ void inet_sock_destruct(struct sock *sk) WARN_ON(sk->sk_wmem_queued); WARN_ON(sk->sk_forward_alloc); - kfree(inet->opt); + kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); sk_refcnt_debug_dec(sk); } @@ -1008,6 +1009,14 @@ static struct inet_protosw inetsw_array[] = .flags = INET_PROTOSW_PERMANENT, }, + { + .type = SOCK_DGRAM, + .protocol = IPPROTO_ICMP, + .prot = &ping_prot, + .ops = &inet_dgram_ops, + .no_check = UDP_CSUM_DEFAULT, + .flags = INET_PROTOSW_REUSE, + }, { .type = SOCK_RAW, @@ -1103,14 +1112,19 @@ static int inet_sk_reselect_saddr(struct sock *sk) struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; + struct flowi4 *fl4; struct rtable *rt; __be32 new_saddr; + struct ip_options_rcu *inet_opt; - if (inet->opt && inet->opt->srr) - daddr = inet->opt->faddr; + inet_opt = rcu_dereference_protected(inet->inet_opt, + sock_owned_by_user(sk)); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; /* Query new route. */ - rt = ip_route_connect(daddr, 0, RT_CONN_FLAGS(sk), + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_connect(fl4, daddr, 0, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, sk->sk_protocol, inet->inet_sport, inet->inet_dport, sk, false); if (IS_ERR(rt)) @@ -1118,7 +1132,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) sk_setup_caps(sk, &rt->dst); - new_saddr = rt->rt_src; + new_saddr = fl4->saddr; if (new_saddr == old_saddr) return 0; @@ -1147,6 +1161,8 @@ int inet_sk_rebuild_header(struct sock *sk) struct inet_sock *inet = inet_sk(sk); struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0); __be32 daddr; + struct ip_options_rcu *inet_opt; + struct flowi4 *fl4; int err; /* Route is OK, nothing to do. */ @@ -1154,10 +1170,14 @@ int inet_sk_rebuild_header(struct sock *sk) return 0; /* Reroute. */ + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); daddr = inet->inet_daddr; - if (inet->opt && inet->opt->srr) - daddr = inet->opt->faddr; - rt = ip_route_output_ports(sock_net(sk), sk, daddr, inet->inet_saddr, + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + rcu_read_unlock(); + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); @@ -1186,7 +1206,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); static int inet_gso_send_check(struct sk_buff *skb) { - struct iphdr *iph; + const struct iphdr *iph; const struct net_protocol *ops; int proto; int ihl; @@ -1293,7 +1313,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, const struct net_protocol *ops; struct sk_buff **pp = NULL; struct sk_buff *p; - struct iphdr *iph; + const struct iphdr *iph; unsigned int hlen; unsigned int off; unsigned int id; @@ -1516,6 +1536,7 @@ static const struct net_protocol udp_protocol = { static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, + .err_handler = ping_err, .no_policy = 1, .netns_ok = 1, }; @@ -1631,6 +1652,10 @@ static int __init inet_init(void) if (rc) goto out_unregister_udp_proto; + rc = proto_register(&ping_prot, 1); + if (rc) + goto out_unregister_raw_proto; + /* * Tell SOCKET that we are alive... */ @@ -1686,6 +1711,8 @@ static int __init inet_init(void) /* Add UDP-Lite (RFC 3828) */ udplite4_register(); + ping_init(); + /* * Set the ICMP layer up */ @@ -1716,6 +1743,8 @@ static int __init inet_init(void) rc = 0; out: return rc; +out_unregister_raw_proto: + proto_unregister(&raw_prot); out_unregister_udp_proto: proto_unregister(&udp_prot); out_unregister_tcp_proto: @@ -1740,11 +1769,15 @@ static int __init ipv4_proc_init(void) goto out_tcp; if (udp4_proc_init()) goto out_udp; + if (ping_proc_init()) + goto out_ping; if (ip_misc_proc_init()) goto out_misc; out: return rc; out_misc: + ping_proc_exit(); +out_ping: udp4_proc_exit(); out_udp: tcp4_proc_exit(); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 4286fd3cc0e2..c1f4154552fc 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -73,7 +73,7 @@ static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, * into IP header for icv calculation. Options are already checked * for validity, so paranoia is not required. */ -static int ip_clear_mutable_options(struct iphdr *iph, __be32 *daddr) +static int ip_clear_mutable_options(const struct iphdr *iph, __be32 *daddr) { unsigned char * optptr = (unsigned char*)(iph+1); int l = iph->ihl*4 - sizeof(struct iphdr); @@ -396,7 +396,7 @@ out: static void ah4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); - struct iphdr *iph = (struct iphdr *)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; @@ -404,7 +404,8 @@ static void ah4_err(struct sk_buff *skb, u32 info) icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return; - x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + ah->spi, IPPROTO_AH, AF_INET); if (!x) return; printk(KERN_DEBUG "pmtu discovery on SA AH/%08x/%08x\n", diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 094e150c6260..2b3c23c287cd 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -112,7 +112,7 @@ int cipso_v4_rbm_strictvalid = 1; /* The maximum number of category ranges permitted in the ranged category tag * (tag #5). You may note that the IETF draft states that the maximum number * of category ranges is 7, but if the low end of the last category range is - * zero then it is possibile to fit 8 category ranges because the zero should + * zero then it is possible to fit 8 category ranges because the zero should * be omitted. */ #define CIPSO_V4_TAG_RNG_CAT_MAX 8 @@ -438,7 +438,7 @@ cache_add_failure: * * Description: * Search the DOI definition list for a DOI definition with a DOI value that - * matches @doi. The caller is responsibile for calling rcu_read_[un]lock(). + * matches @doi. The caller is responsible for calling rcu_read_[un]lock(). * Returns a pointer to the DOI definition on success and NULL on failure. */ static struct cipso_v4_doi *cipso_v4_doi_search(u32 doi) @@ -1293,7 +1293,7 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def, return ret_val; /* This will send packets using the "optimized" format when - * possibile as specified in section 3.4.2.6 of the + * possible as specified in section 3.4.2.6 of the * CIPSO draft. */ if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10) tag_len = 14; @@ -1752,7 +1752,7 @@ validate_return: } /** - * cipso_v4_error - Send the correct reponse for a bad packet + * cipso_v4_error - Send the correct response for a bad packet * @skb: the packet * @error: the error code * @gateway: CIPSO gateway flag @@ -1857,6 +1857,11 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, return CIPSO_V4_HDR_LEN + ret_val; } +static void opt_kfree_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_options_rcu, rcu)); +} + /** * cipso_v4_sock_setattr - Add a CIPSO option to a socket * @sk: the socket @@ -1879,7 +1884,7 @@ int cipso_v4_sock_setattr(struct sock *sk, unsigned char *buf = NULL; u32 buf_len; u32 opt_len; - struct ip_options *opt = NULL; + struct ip_options_rcu *old, *opt = NULL; struct inet_sock *sk_inet; struct inet_connection_sock *sk_conn; @@ -1915,22 +1920,25 @@ int cipso_v4_sock_setattr(struct sock *sk, ret_val = -ENOMEM; goto socket_setattr_failure; } - memcpy(opt->__data, buf, buf_len); - opt->optlen = opt_len; - opt->cipso = sizeof(struct iphdr); + memcpy(opt->opt.__data, buf, buf_len); + opt->opt.optlen = opt_len; + opt->opt.cipso = sizeof(struct iphdr); kfree(buf); buf = NULL; sk_inet = inet_sk(sk); + + old = rcu_dereference_protected(sk_inet->inet_opt, sock_owned_by_user(sk)); if (sk_inet->is_icsk) { sk_conn = inet_csk(sk); - if (sk_inet->opt) - sk_conn->icsk_ext_hdr_len -= sk_inet->opt->optlen; - sk_conn->icsk_ext_hdr_len += opt->optlen; + if (old) + sk_conn->icsk_ext_hdr_len -= old->opt.optlen; + sk_conn->icsk_ext_hdr_len += opt->opt.optlen; sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie); } - opt = xchg(&sk_inet->opt, opt); - kfree(opt); + rcu_assign_pointer(sk_inet->inet_opt, opt); + if (old) + call_rcu(&old->rcu, opt_kfree_rcu); return 0; @@ -1960,7 +1968,7 @@ int cipso_v4_req_setattr(struct request_sock *req, unsigned char *buf = NULL; u32 buf_len; u32 opt_len; - struct ip_options *opt = NULL; + struct ip_options_rcu *opt = NULL; struct inet_request_sock *req_inet; /* We allocate the maximum CIPSO option size here so we are probably @@ -1988,15 +1996,16 @@ int cipso_v4_req_setattr(struct request_sock *req, ret_val = -ENOMEM; goto req_setattr_failure; } - memcpy(opt->__data, buf, buf_len); - opt->optlen = opt_len; - opt->cipso = sizeof(struct iphdr); + memcpy(opt->opt.__data, buf, buf_len); + opt->opt.optlen = opt_len; + opt->opt.cipso = sizeof(struct iphdr); kfree(buf); buf = NULL; req_inet = inet_rsk(req); opt = xchg(&req_inet->opt, opt); - kfree(opt); + if (opt) + call_rcu(&opt->rcu, opt_kfree_rcu); return 0; @@ -2016,34 +2025,34 @@ req_setattr_failure: * values on failure. * */ -static int cipso_v4_delopt(struct ip_options **opt_ptr) +static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) { int hdr_delta = 0; - struct ip_options *opt = *opt_ptr; + struct ip_options_rcu *opt = *opt_ptr; - if (opt->srr || opt->rr || opt->ts || opt->router_alert) { + if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) { u8 cipso_len; u8 cipso_off; unsigned char *cipso_ptr; int iter; int optlen_new; - cipso_off = opt->cipso - sizeof(struct iphdr); - cipso_ptr = &opt->__data[cipso_off]; + cipso_off = opt->opt.cipso - sizeof(struct iphdr); + cipso_ptr = &opt->opt.__data[cipso_off]; cipso_len = cipso_ptr[1]; - if (opt->srr > opt->cipso) - opt->srr -= cipso_len; - if (opt->rr > opt->cipso) - opt->rr -= cipso_len; - if (opt->ts > opt->cipso) - opt->ts -= cipso_len; - if (opt->router_alert > opt->cipso) - opt->router_alert -= cipso_len; - opt->cipso = 0; + if (opt->opt.srr > opt->opt.cipso) + opt->opt.srr -= cipso_len; + if (opt->opt.rr > opt->opt.cipso) + opt->opt.rr -= cipso_len; + if (opt->opt.ts > opt->opt.cipso) + opt->opt.ts -= cipso_len; + if (opt->opt.router_alert > opt->opt.cipso) + opt->opt.router_alert -= cipso_len; + opt->opt.cipso = 0; memmove(cipso_ptr, cipso_ptr + cipso_len, - opt->optlen - cipso_off - cipso_len); + opt->opt.optlen - cipso_off - cipso_len); /* determining the new total option length is tricky because of * the padding necessary, the only thing i can think to do at @@ -2052,21 +2061,21 @@ static int cipso_v4_delopt(struct ip_options **opt_ptr) * from there we can determine the new total option length */ iter = 0; optlen_new = 0; - while (iter < opt->optlen) - if (opt->__data[iter] != IPOPT_NOP) { - iter += opt->__data[iter + 1]; + while (iter < opt->opt.optlen) + if (opt->opt.__data[iter] != IPOPT_NOP) { + iter += opt->opt.__data[iter + 1]; optlen_new = iter; } else iter++; - hdr_delta = opt->optlen; - opt->optlen = (optlen_new + 3) & ~3; - hdr_delta -= opt->optlen; + hdr_delta = opt->opt.optlen; + opt->opt.optlen = (optlen_new + 3) & ~3; + hdr_delta -= opt->opt.optlen; } else { /* only the cipso option was present on the socket so we can * remove the entire option struct */ *opt_ptr = NULL; - hdr_delta = opt->optlen; - kfree(opt); + hdr_delta = opt->opt.optlen; + call_rcu(&opt->rcu, opt_kfree_rcu); } return hdr_delta; @@ -2083,15 +2092,15 @@ static int cipso_v4_delopt(struct ip_options **opt_ptr) void cipso_v4_sock_delattr(struct sock *sk) { int hdr_delta; - struct ip_options *opt; + struct ip_options_rcu *opt; struct inet_sock *sk_inet; sk_inet = inet_sk(sk); - opt = sk_inet->opt; - if (opt == NULL || opt->cipso == 0) + opt = rcu_dereference_protected(sk_inet->inet_opt, 1); + if (opt == NULL || opt->opt.cipso == 0) return; - hdr_delta = cipso_v4_delopt(&sk_inet->opt); + hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt); if (sk_inet->is_icsk && hdr_delta > 0) { struct inet_connection_sock *sk_conn = inet_csk(sk); sk_conn->icsk_ext_hdr_len -= hdr_delta; @@ -2109,12 +2118,12 @@ void cipso_v4_sock_delattr(struct sock *sk) */ void cipso_v4_req_delattr(struct request_sock *req) { - struct ip_options *opt; + struct ip_options_rcu *opt; struct inet_request_sock *req_inet; req_inet = inet_rsk(req); opt = req_inet->opt; - if (opt == NULL || opt->cipso == 0) + if (opt == NULL || opt->opt.cipso == 0) return; cipso_v4_delopt(&req_inet->opt); @@ -2184,14 +2193,18 @@ getattr_return: */ int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { - struct ip_options *opt; + struct ip_options_rcu *opt; + int res = -ENOMSG; - opt = inet_sk(sk)->opt; - if (opt == NULL || opt->cipso == 0) - return -ENOMSG; - - return cipso_v4_getattr(opt->__data + opt->cipso - sizeof(struct iphdr), - secattr); + rcu_read_lock(); + opt = rcu_dereference(inet_sk(sk)->inet_opt); + if (opt && opt->opt.cipso) + res = cipso_v4_getattr(opt->opt.__data + + opt->opt.cipso - + sizeof(struct iphdr), + secattr); + rcu_read_unlock(); + return res; } /** diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 85bd24ca4f6d..424fafbc8cb0 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -24,6 +24,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *usin = (struct sockaddr_in *) uaddr; + struct flowi4 *fl4; struct rtable *rt; __be32 saddr; int oif; @@ -38,6 +39,8 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_dst_reset(sk); + lock_sock(sk); + oif = sk->sk_bound_dev_if; saddr = inet->inet_saddr; if (ipv4_is_multicast(usin->sin_addr.s_addr)) { @@ -46,7 +49,8 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (!saddr) saddr = inet->mc_addr; } - rt = ip_route_connect(usin->sin_addr.s_addr, saddr, + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, RT_CONN_FLAGS(sk), oif, sk->sk_protocol, inet->inet_sport, usin->sin_port, sk, true); @@ -54,26 +58,30 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) err = PTR_ERR(rt); if (err == -ENETUNREACH) IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); - return err; + goto out; } if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) { ip_rt_put(rt); - return -EACCES; + err = -EACCES; + goto out; } if (!inet->inet_saddr) - inet->inet_saddr = rt->rt_src; /* Update source address */ + inet->inet_saddr = fl4->saddr; /* Update source address */ if (!inet->inet_rcv_saddr) { - inet->inet_rcv_saddr = rt->rt_src; + inet->inet_rcv_saddr = fl4->saddr; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } - inet->inet_daddr = rt->rt_dst; + inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; inet->inet_id = jiffies; sk_dst_set(sk, &rt->dst); - return 0; + err = 0; +out: + release_sock(sk); + return err; } EXPORT_SYMBOL(ip4_datagram_connect); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5345b0bee6df..0d4a184af16f 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1369,7 +1369,7 @@ errout: static size_t inet_get_link_af_size(const struct net_device *dev) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (!in_dev) return 0; @@ -1379,7 +1379,7 @@ static size_t inet_get_link_af_size(const struct net_device *dev) static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; int i; @@ -1680,7 +1680,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) return; cnf->sysctl = NULL; - unregister_sysctl_table(t->sysctl_header); + unregister_net_sysctl_table(t->sysctl_header); kfree(t->dev_name); kfree(t); } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 03f994bcf7de..a5b413416da3 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -276,7 +276,7 @@ error: static int esp_input_done2(struct sk_buff *skb, int err) { - struct iphdr *iph; + const struct iphdr *iph; struct xfrm_state *x = xfrm_input_state(skb); struct esp_data *esp = x->data; struct crypto_aead *aead = esp->aead; @@ -484,7 +484,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) static void esp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); - struct iphdr *iph = (struct iphdr *)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; @@ -492,7 +492,8 @@ static void esp4_err(struct sk_buff *skb, u32 info) icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return; - x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + esph->spi, IPPROTO_ESP, AF_INET); if (!x) return; NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n", diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 451088330bbb..22524716fe70 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -44,6 +44,7 @@ #include <net/arp.h> #include <net/ip_fib.h> #include <net/rtnetlink.h> +#include <net/xfrm.h> #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -188,9 +189,9 @@ EXPORT_SYMBOL(inet_dev_addr_type); * - 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) +int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, + int oif, struct net_device *dev, __be32 *spec_dst, + u32 *itag) { struct in_device *in_dev; struct flowi4 fl4; @@ -202,7 +203,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, fl4.flowi4_oif = 0; fl4.flowi4_iif = oif; - fl4.flowi4_mark = mark; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; @@ -212,10 +212,12 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, in_dev = __in_dev_get_rcu(dev); if (in_dev) { no_addr = in_dev->ifa_list == NULL; - rpf = IN_DEV_RPFILTER(in_dev); + + /* Ignore rp_filter for packets protected by IPsec. */ + rpf = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(in_dev); + accept_local = IN_DEV_ACCEPT_LOCAL(in_dev); - if (mark && !IN_DEV_SRC_VMARK(in_dev)) - fl4.flowi4_mark = 0; + fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; } if (in_dev == NULL) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 641a5a2a9f9c..33e2c35b74b7 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -141,18 +141,8 @@ const struct fib_prop fib_props[RTN_MAX + 1] = { }, }; - /* 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); - - if (fi->fib_metrics != (u32 *) dst_default_metrics) - kfree(fi->fib_metrics); - kfree(fi); -} - void free_fib_info(struct fib_info *fi) { if (fi->fib_dead == 0) { @@ -166,7 +156,7 @@ void free_fib_info(struct fib_info *fi) } endfor_nexthops(fi); fib_info_cnt--; release_net(fi->fib_net); - call_rcu(&fi->rcu, free_fib_info_rcu); + kfree_rcu(fi, rcu); } void fib_release_info(struct fib_info *fi) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b92c86f6e9b3..58c25ea5a5c1 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -12,7 +12,7 @@ * * Hans Liss <hans.liss@its.uu.se> Uppsala Universitet * - * This work is based on the LPC-trie which is originally descibed in: + * This work is based on the LPC-trie which is originally described in: * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. @@ -72,6 +72,7 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/prefetch.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> @@ -126,7 +127,7 @@ struct tnode { struct work_struct work; struct tnode *tnode_free; }; - struct rt_trie_node *child[0]; + struct rt_trie_node __rcu *child[0]; }; #ifdef CONFIG_IP_FIB_TRIE_STATS @@ -151,7 +152,7 @@ struct trie_stat { }; struct trie { - struct rt_trie_node *trie; + struct rt_trie_node __rcu *trie; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats stats; #endif @@ -177,16 +178,29 @@ static const int sync_pages = 128; static struct kmem_cache *fn_alias_kmem __read_mostly; static struct kmem_cache *trie_leaf_kmem __read_mostly; -static inline struct tnode *node_parent(struct rt_trie_node *node) +/* + * caller must hold RTNL + */ +static inline struct tnode *node_parent(const struct rt_trie_node *node) { - return (struct tnode *)(node->parent & ~NODE_TYPE_MASK); + unsigned long parent; + + parent = rcu_dereference_index_check(node->parent, lockdep_rtnl_is_held()); + + return (struct tnode *)(parent & ~NODE_TYPE_MASK); } -static inline struct tnode *node_parent_rcu(struct rt_trie_node *node) +/* + * caller must hold RCU read lock or RTNL + */ +static inline struct tnode *node_parent_rcu(const struct rt_trie_node *node) { - struct tnode *ret = node_parent(node); + unsigned long parent; - return rcu_dereference_rtnl(ret); + parent = rcu_dereference_index_check(node->parent, rcu_read_lock_held() || + lockdep_rtnl_is_held()); + + return (struct tnode *)(parent & ~NODE_TYPE_MASK); } /* Same as rcu_assign_pointer @@ -198,18 +212,24 @@ static inline void node_set_parent(struct rt_trie_node *node, struct tnode *ptr) node->parent = (unsigned long)ptr | NODE_TYPE(node); } -static inline struct rt_trie_node *tnode_get_child(struct tnode *tn, unsigned int i) +/* + * caller must hold RTNL + */ +static inline struct rt_trie_node *tnode_get_child(const struct tnode *tn, unsigned int i) { BUG_ON(i >= 1U << tn->bits); - return tn->child[i]; + return rtnl_dereference(tn->child[i]); } -static inline struct rt_trie_node *tnode_get_child_rcu(struct tnode *tn, unsigned int i) +/* + * caller must hold RCU read lock or RTNL + */ +static inline struct rt_trie_node *tnode_get_child_rcu(const struct tnode *tn, unsigned int i) { - struct rt_trie_node *ret = tnode_get_child(tn, i); + BUG_ON(i >= 1U << tn->bits); - return rcu_dereference_rtnl(ret); + return rcu_dereference_rtnl(tn->child[i]); } static inline int tnode_child_length(const struct tnode *tn) @@ -350,14 +370,9 @@ static inline void free_leaf(struct leaf *l) call_rcu_bh(&l->rcu, __leaf_free_rcu); } -static void __leaf_info_free_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct leaf_info, rcu)); -} - static inline void free_leaf_info(struct leaf_info *leaf) { - call_rcu(&leaf->rcu, __leaf_info_free_rcu); + kfree_rcu(leaf, rcu); } static struct tnode *tnode_alloc(size_t size) @@ -487,7 +502,7 @@ static inline void put_child(struct trie *t, struct tnode *tn, int i, static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull) { - struct rt_trie_node *chi = tn->child[i]; + struct rt_trie_node *chi = rtnl_dereference(tn->child[i]); int isfull; BUG_ON(i >= 1<<tn->bits); @@ -665,7 +680,7 @@ one_child: for (i = 0; i < tnode_child_length(tn); i++) { struct rt_trie_node *n; - n = tn->child[i]; + n = rtnl_dereference(tn->child[i]); if (!n) continue; @@ -679,6 +694,20 @@ one_child: return (struct rt_trie_node *) tn; } + +static void tnode_clean_free(struct tnode *tn) +{ + int i; + struct tnode *tofree; + + for (i = 0; i < tnode_child_length(tn); i++) { + tofree = (struct tnode *)rtnl_dereference(tn->child[i]); + if (tofree) + tnode_free(tofree); + } + tnode_free(tn); +} + static struct tnode *inflate(struct trie *t, struct tnode *tn) { struct tnode *oldtnode = tn; @@ -755,8 +784,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) inode = (struct tnode *) node; if (inode->bits == 1) { - put_child(t, tn, 2*i, inode->child[0]); - put_child(t, tn, 2*i+1, inode->child[1]); + put_child(t, tn, 2*i, rtnl_dereference(inode->child[0])); + put_child(t, tn, 2*i+1, rtnl_dereference(inode->child[1])); tnode_free_safe(inode); continue; @@ -797,8 +826,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) size = tnode_child_length(left); for (j = 0; j < size; j++) { - put_child(t, left, j, inode->child[j]); - put_child(t, right, j, inode->child[j + size]); + put_child(t, left, j, rtnl_dereference(inode->child[j])); + put_child(t, right, j, rtnl_dereference(inode->child[j + size])); } put_child(t, tn, 2*i, resize(t, left)); put_child(t, tn, 2*i+1, resize(t, right)); @@ -808,18 +837,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) tnode_free_safe(oldtnode); return tn; nomem: - { - int size = tnode_child_length(tn); - int j; - - for (j = 0; j < size; j++) - if (tn->child[j]) - tnode_free((struct tnode *)tn->child[j]); - - tnode_free(tn); - - return ERR_PTR(-ENOMEM); - } + tnode_clean_free(tn); + return ERR_PTR(-ENOMEM); } static struct tnode *halve(struct trie *t, struct tnode *tn) @@ -890,18 +909,8 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) tnode_free_safe(oldtnode); return tn; nomem: - { - int size = tnode_child_length(tn); - int j; - - for (j = 0; j < size; j++) - if (tn->child[j]) - tnode_free((struct tnode *)tn->child[j]); - - tnode_free(tn); - - return ERR_PTR(-ENOMEM); - } + tnode_clean_free(tn); + return ERR_PTR(-ENOMEM); } /* readside must use rcu_read_lock currently dump routines @@ -1033,7 +1042,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) t_key cindex; pos = 0; - n = t->trie; + n = rtnl_dereference(t->trie); /* If we point to NULL, stop. Either the tree is empty and we should * just put a new leaf in if, or we have reached an empty child slot, @@ -1319,6 +1328,9 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) } } + if (!plen) + tb->tb_num_default++; + list_add_tail_rcu(&new_fa->fa_list, (fa ? &fa->fa_list : fa_head)); @@ -1684,6 +1696,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) list_del_rcu(&fa->fa_list); + if (!plen) + tb->tb_num_default--; + if (list_empty(fa_head)) { hlist_del_rcu(&li->hlist); free_leaf_info(li); @@ -1756,7 +1771,7 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c) continue; if (IS_LEAF(c)) { - prefetch(p->child[idx]); + prefetch(rcu_dereference_rtnl(p->child[idx])); return (struct leaf *) c; } @@ -1974,13 +1989,11 @@ struct fib_table *fib_trie_table(u32 id) tb->tb_id = id; tb->tb_default = -1; + tb->tb_num_default = 0; t = (struct trie *) tb->tb_data; memset(t, 0, sizeof(*t)); - if (id == RT_TABLE_LOCAL) - pr_info("IPv4 FIB: Using LC-trie version %s\n", VERSION); - return tb; } @@ -2272,7 +2285,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* walk rest of this hash chain */ h = tb->tb_id & (FIB_TABLE_HASHSZ - 1); - while ( (tb_node = rcu_dereference(tb->tb_hlist.next)) ) { + while ((tb_node = rcu_dereference(hlist_next_rcu(&tb->tb_hlist)))) { tb = hlist_entry(tb_node, struct fib_table, tb_hlist); n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index a91dc1611081..5395e45dcce6 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -83,6 +83,7 @@ #include <net/tcp.h> #include <net/udp.h> #include <net/raw.h> +#include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> @@ -108,8 +109,7 @@ struct icmp_bxm { __be32 times[3]; } data; int head_len; - struct ip_options replyopts; - unsigned char optbuf[40]; + struct ip_options_data replyopts; }; /* An array of errno for error messages from dest unreach. */ @@ -234,7 +234,7 @@ static inline void icmp_xmit_unlock(struct sock *sk) */ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, - int type, int code) + struct flowi4 *fl4, int type, int code) { struct dst_entry *dst = &rt->dst; bool rc = true; @@ -253,7 +253,7 @@ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, /* Limit if icmp type is enabled in ratemask. */ if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) { if (!rt->peer) - rt_bind_peer(rt, 1); + rt_bind_peer(rt, fl4->daddr, 1); rc = inet_peer_xrlim_allow(rt->peer, net->ipv4.sysctl_icmp_ratelimit); } @@ -291,13 +291,14 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, } static void icmp_push_reply(struct icmp_bxm *icmp_param, + struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rt) { struct sock *sk; struct sk_buff *skb; sk = icmp_sk(dev_net((*rt)->dst.dev)); - if (ip_append_data(sk, icmp_glue_bits, icmp_param, + if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, ipc, rt, MSG_DONTWAIT) < 0) { @@ -316,7 +317,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, icmp_param->head_len, csum); icmph->checksum = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; - ip_push_pending_frames(sk); + ip_push_pending_frames(sk, fl4); } } @@ -329,11 +330,12 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) struct ipcm_cookie ipc; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->dst.dev); + struct flowi4 fl4; struct sock *sk; struct inet_sock *inet; __be32 daddr; - if (ip_options_echo(&icmp_param->replyopts, skb)) + if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb)) return; sk = icmp_xmit_lock(net); @@ -344,65 +346,60 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) icmp_param->data.icmph.checksum = 0; inet->tos = ip_hdr(skb)->tos; - daddr = ipc.addr = rt->rt_src; + daddr = ipc.addr = ip_hdr(skb)->saddr; ipc.opt = NULL; ipc.tx_flags = 0; - if (icmp_param->replyopts.optlen) { - ipc.opt = &icmp_param->replyopts; - if (ipc.opt->srr) - daddr = icmp_param->replyopts.faddr; + if (icmp_param->replyopts.opt.opt.optlen) { + ipc.opt = &icmp_param->replyopts.opt; + if (ipc.opt->opt.srr) + daddr = icmp_param->replyopts.opt.opt.faddr; } - { - struct flowi4 fl4 = { - .daddr = daddr, - .saddr = rt->rt_spec_dst, - .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), - .flowi4_proto = IPPROTO_ICMP, - }; - security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - goto out_unlock; - } - if (icmpv4_xrlim_allow(net, rt, icmp_param->data.icmph.type, + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = daddr; + fl4.saddr = rt->rt_spec_dst; + fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); + fl4.flowi4_proto = IPPROTO_ICMP; + security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + goto out_unlock; + if (icmpv4_xrlim_allow(net, rt, &fl4, icmp_param->data.icmph.type, icmp_param->data.icmph.code)) - icmp_push_reply(icmp_param, &ipc, &rt); + icmp_push_reply(icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); } -static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in, - struct iphdr *iph, +static struct rtable *icmp_route_lookup(struct net *net, + struct flowi4 *fl4, + struct sk_buff *skb_in, + const struct iphdr *iph, __be32 saddr, u8 tos, int type, int code, struct icmp_bxm *param) { - struct flowi4 fl4 = { - .daddr = (param->replyopts.srr ? - param->replyopts.faddr : iph->saddr), - .saddr = saddr, - .flowi4_tos = RT_TOS(tos), - .flowi4_proto = IPPROTO_ICMP, - .fl4_icmp_type = type, - .fl4_icmp_code = code, - }; struct rtable *rt, *rt2; int err; - security_skb_classify_flow(skb_in, flowi4_to_flowi(&fl4)); - rt = __ip_route_output_key(net, &fl4); + memset(fl4, 0, sizeof(*fl4)); + fl4->daddr = (param->replyopts.opt.opt.srr ? + param->replyopts.opt.opt.faddr : iph->saddr); + fl4->saddr = saddr; + fl4->flowi4_tos = RT_TOS(tos); + fl4->flowi4_proto = IPPROTO_ICMP; + fl4->fl4_icmp_type = type; + fl4->fl4_icmp_code = code; + security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); + rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) return rt; /* No need to clone since we're just using its address. */ rt2 = rt; - if (!fl4.saddr) - fl4.saddr = rt->rt_src; - rt = (struct rtable *) xfrm_lookup(net, &rt->dst, - flowi4_to_flowi(&fl4), NULL, 0); + flowi4_to_flowi(fl4), NULL, 0); if (!IS_ERR(rt)) { if (rt != rt2) return rt; @@ -411,19 +408,19 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in, } else return rt; - err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(&fl4), AF_INET); + err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(fl4), AF_INET); if (err) goto relookup_failed; - if (inet_addr_type(net, fl4.saddr) == RTN_LOCAL) { - rt2 = __ip_route_output_key(net, &fl4); + if (inet_addr_type(net, fl4->saddr) == RTN_LOCAL) { + rt2 = __ip_route_output_key(net, fl4); if (IS_ERR(rt2)) err = PTR_ERR(rt2); } else { struct flowi4 fl4_2 = {}; unsigned long orefdst; - fl4_2.daddr = fl4.saddr; + fl4_2.daddr = fl4->saddr; rt2 = ip_route_output_key(net, &fl4_2); if (IS_ERR(rt2)) { err = PTR_ERR(rt2); @@ -431,7 +428,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in, } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ - err = ip_route_input(skb_in, fl4.daddr, fl4.saddr, + err = ip_route_input(skb_in, fl4->daddr, fl4->saddr, RT_TOS(tos), rt2->dst.dev); dst_release(&rt2->dst); @@ -443,7 +440,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in, goto relookup_failed; rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst, - flowi4_to_flowi(&fl4), NULL, + flowi4_to_flowi(fl4), NULL, XFRM_LOOKUP_ICMP); if (!IS_ERR(rt2)) { dst_release(&rt->dst); @@ -482,6 +479,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) struct icmp_bxm icmp_param; struct rtable *rt = skb_rtable(skb_in); struct ipcm_cookie ipc; + struct flowi4 fl4; __be32 saddr; u8 tos; struct net *net; @@ -581,7 +579,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) IPTOS_PREC_INTERNETCONTROL) : iph->tos; - if (ip_options_echo(&icmp_param.replyopts, skb_in)) + if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in)) goto out_unlock; @@ -597,15 +595,15 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; ipc.addr = iph->saddr; - ipc.opt = &icmp_param.replyopts; + ipc.opt = &icmp_param.replyopts.opt; ipc.tx_flags = 0; - rt = icmp_route_lookup(net, skb_in, iph, saddr, tos, + rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, type, code, &icmp_param); if (IS_ERR(rt)) goto out_unlock; - if (!icmpv4_xrlim_allow(net, rt, type, code)) + if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code)) goto ende; /* RFC says return as much as we can without exceeding 576 bytes. */ @@ -613,7 +611,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) room = dst_mtu(&rt->dst); if (room > 576) room = 576; - room -= sizeof(struct iphdr) + icmp_param.replyopts.optlen; + room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); icmp_param.data_len = skb_in->len - icmp_param.offset; @@ -621,7 +619,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); - icmp_push_reply(&icmp_param, &ipc, &rt); + icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); out_unlock: @@ -637,7 +635,7 @@ EXPORT_SYMBOL(icmp_send); static void icmp_unreach(struct sk_buff *skb) { - struct iphdr *iph; + const struct iphdr *iph; struct icmphdr *icmph; int hash, protocol; const struct net_protocol *ipprot; @@ -656,7 +654,7 @@ static void icmp_unreach(struct sk_buff *skb) goto out_err; icmph = icmp_hdr(skb); - iph = (struct iphdr *)skb->data; + iph = (const struct iphdr *)skb->data; if (iph->ihl < 5) /* Mangled header, drop. */ goto out_err; @@ -704,7 +702,7 @@ static void icmp_unreach(struct sk_buff *skb) */ /* - * Check the other end isnt violating RFC 1122. Some routers send + * Check the other end isn't violating RFC 1122. Some routers send * bogus responses to broadcast frames. If you see this message * first check your netmask matches at both ends, if it does then * get the other vendor to fix their kit. @@ -729,7 +727,7 @@ static void icmp_unreach(struct sk_buff *skb) if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) goto out; - iph = (struct iphdr *)skb->data; + iph = (const struct iphdr *)skb->data; protocol = iph->protocol; /* @@ -758,7 +756,7 @@ out_err: static void icmp_redirect(struct sk_buff *skb) { - struct iphdr *iph; + const struct iphdr *iph; if (skb->len < sizeof(struct iphdr)) goto out_err; @@ -769,7 +767,7 @@ static void icmp_redirect(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; - iph = (struct iphdr *)skb->data; + iph = (const struct iphdr *)skb->data; switch (icmp_hdr(skb)->code & 7) { case ICMP_REDIR_NET: @@ -784,6 +782,15 @@ static void icmp_redirect(struct sk_buff *skb) iph->saddr, skb->dev); break; } + + /* Ping wants to see redirects. + * Let's pretend they are errors of sorts... */ + if (iph->protocol == IPPROTO_ICMP && + iph->ihl >= 5 && + pskb_may_pull(skb, (iph->ihl<<2)+8)) { + ping_err(skb, icmp_hdr(skb)->un.gateway); + } + out: return; out_err: @@ -933,12 +940,12 @@ static void icmp_address_reply(struct sk_buff *skb) BUG_ON(mp == NULL); for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { if (*mp == ifa->ifa_mask && - inet_ifa_match(rt->rt_src, ifa)) + inet_ifa_match(ip_hdr(skb)->saddr, ifa)) break; } if (!ifa && net_ratelimit()) { printk(KERN_INFO "Wrong address mask %pI4 from %s/%pI4\n", - mp, dev->name, &rt->rt_src); + mp, dev->name, &ip_hdr(skb)->saddr); } } } @@ -1044,7 +1051,7 @@ error: */ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = { [ICMP_ECHOREPLY] = { - .handler = icmp_discard, + .handler = ping_rcv, }, [1] = { .handler = icmp_discard, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 1fd3d9ce8398..f1d27f6c9351 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -149,17 +149,11 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); - -static void ip_mc_list_reclaim(struct rcu_head *head) -{ - kfree(container_of(head, struct ip_mc_list, rcu)); -} - static void ip_ma_put(struct ip_mc_list *im) { if (atomic_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); - call_rcu(&im->rcu, ip_mc_list_reclaim); + kfree_rcu(im, rcu); } } @@ -309,6 +303,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) struct iphdr *pip; struct igmpv3_report *pig; struct net *net = dev_net(dev); + struct flowi4 fl4; while (1) { skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), @@ -321,18 +316,13 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) } igmp_skb_size(skb) = size; - rt = ip_route_output_ports(net, NULL, IGMPV3_ALL_MCR, 0, + rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) { kfree_skb(skb); return NULL; } - if (rt->rt_src == 0) { - kfree_skb(skb); - ip_rt_put(rt); - return NULL; - } skb_dst_set(skb, &rt->dst); skb->dev = dev; @@ -348,8 +338,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->tos = 0xc0; pip->frag_off = htons(IP_DF); pip->ttl = 1; - pip->daddr = rt->rt_dst; - pip->saddr = rt->rt_src; + pip->daddr = fl4.daddr; + pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(pip, &rt->dst, NULL); @@ -655,6 +645,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, struct net_device *dev = in_dev->dev; struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; + struct flowi4 fl4; __be32 dst; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) @@ -664,17 +655,12 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, else dst = group; - rt = ip_route_output_ports(net, NULL, dst, 0, + rt = ip_route_output_ports(net, &fl4, NULL, dst, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) return -1; - if (rt->rt_src == 0) { - ip_rt_put(rt); - return -1; - } - skb = alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); if (skb == NULL) { ip_rt_put(rt); @@ -695,7 +681,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->daddr = dst; - iph->saddr = rt->rt_src; + iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(iph, &rt->dst, NULL); ((u8*)&iph[1])[0] = IPOPT_RA; @@ -1169,20 +1155,18 @@ static void igmp_group_dropped(struct ip_mc_list *im) if (!in_dev->dead) { if (IGMP_V1_SEEN(in_dev)) - goto done; + return; if (IGMP_V2_SEEN(in_dev)) { if (reporter) igmp_send_report(in_dev, im, IGMP_HOST_LEAVE_MESSAGE); - goto done; + return; } /* IGMPv3 */ igmpv3_add_delrec(in_dev, im); igmp_ifc_event(in_dev); } -done: #endif - ip_mc_clear_src(im); } static void igmp_group_added(struct ip_mc_list *im) @@ -1319,6 +1303,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) *ip = i->next_rcu; in_dev->mc_count--; igmp_group_dropped(i); + ip_mc_clear_src(i); if (!in_dev->dead) ip_rt_multicast_event(in_dev); @@ -1428,7 +1413,8 @@ void ip_mc_destroy_dev(struct in_device *in_dev) in_dev->mc_list = i->next_rcu; in_dev->mc_count--; - igmp_group_dropped(i); + /* We've dropped the groups in ip_mc_down already */ + ip_mc_clear_src(i); ip_ma_put(i); } } @@ -1836,12 +1822,6 @@ done: } EXPORT_SYMBOL(ip_mc_join_group); -static void ip_sf_socklist_reclaim(struct rcu_head *rp) -{ - kfree(container_of(rp, struct ip_sf_socklist, rcu)); - /* sk_omem_alloc should have been decreased by the caller*/ -} - static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { @@ -1858,18 +1838,10 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, rcu_assign_pointer(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psf->sl_max), &sk->sk_omem_alloc); - call_rcu(&psf->rcu, ip_sf_socklist_reclaim); + kfree_rcu(psf, rcu); return err; } - -static void ip_mc_socklist_reclaim(struct rcu_head *rp) -{ - kfree(container_of(rp, struct ip_mc_socklist, rcu)); - /* sk_omem_alloc should have been decreased by the caller*/ -} - - /* * Ask a socket to leave a group. */ @@ -1909,7 +1881,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_unlock(); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); - call_rcu(&iml->rcu, ip_mc_socklist_reclaim); + kfree_rcu(iml, rcu); return 0; } if (!in_dev) @@ -2026,7 +1998,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); - call_rcu(&psl->rcu, ip_sf_socklist_reclaim); + kfree_rcu(psl, rcu); } rcu_assign_pointer(pmc->sflist, newpsl); psl = newpsl; @@ -2127,7 +2099,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); - call_rcu(&psl->rcu, ip_sf_socklist_reclaim); + kfree_rcu(psl, rcu); } else (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); @@ -2324,7 +2296,7 @@ void ip_mc_drop_socket(struct sock *sk) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); - call_rcu(&iml->rcu, ip_mc_socklist_reclaim); + kfree_rcu(iml, rcu); } rtnl_unlock(); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6c0b7f4a3d7d..61fac4cabc78 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -73,7 +73,7 @@ int inet_csk_bind_conflict(const struct sock *sk, !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { if (!reuse || !sk2->sk_reuse || - ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) { + sk2->sk_state == TCP_LISTEN) { const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || sk2_rcv_saddr == sk_rcv_saddr(sk)) @@ -122,8 +122,7 @@ again: (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; - if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 && - !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { + if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) { spin_unlock(&head->lock); snum = smallest_rover; goto have_snum; @@ -351,30 +350,24 @@ void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len) EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); struct dst_entry *inet_csk_route_req(struct sock *sk, + struct flowi4 *fl4, const struct request_sock *req) { struct rtable *rt; const struct inet_request_sock *ireq = inet_rsk(req); - struct ip_options *opt = inet_rsk(req)->opt; - struct flowi4 fl4 = { - .flowi4_oif = sk->sk_bound_dev_if, - .flowi4_mark = sk->sk_mark, - .daddr = ((opt && opt->srr) ? - opt->faddr : ireq->rmt_addr), - .saddr = ireq->loc_addr, - .flowi4_tos = RT_CONN_FLAGS(sk), - .flowi4_proto = sk->sk_protocol, - .flowi4_flags = inet_sk_flowi_flags(sk), - .fl4_sport = inet_sk(sk)->inet_sport, - .fl4_dport = ireq->rmt_port, - }; + struct ip_options_rcu *opt = inet_rsk(req)->opt; struct net *net = sock_net(sk); - security_req_classify_flow(req, flowi4_to_flowi(&fl4)); - rt = ip_route_output_flow(net, &fl4, sk); + flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, + sk->sk_protocol, inet_sk_flowi_flags(sk), + (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr, + ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport); + security_req_classify_flow(req, flowi4_to_flowi(fl4)); + rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) + if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway) goto route_err; return &rt->dst; @@ -386,6 +379,39 @@ no_route: } EXPORT_SYMBOL_GPL(inet_csk_route_req); +struct dst_entry *inet_csk_route_child_sock(struct sock *sk, + struct sock *newsk, + const struct request_sock *req) +{ + const struct inet_request_sock *ireq = inet_rsk(req); + struct inet_sock *newinet = inet_sk(newsk); + struct ip_options_rcu *opt = ireq->opt; + struct net *net = sock_net(sk); + struct flowi4 *fl4; + struct rtable *rt; + + fl4 = &newinet->cork.fl.u.ip4; + flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, + sk->sk_protocol, inet_sk_flowi_flags(sk), + (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr, + ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport); + security_req_classify_flow(req, flowi4_to_flowi(fl4)); + rt = ip_route_output_flow(net, fl4, sk); + if (IS_ERR(rt)) + goto no_route; + if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway) + goto route_err; + return &rt->dst; + +route_err: + ip_rt_put(rt); +no_route: + IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + return NULL; +} +EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); + static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport, const u32 rnd, const u32 synq_hsize) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 2ada17129fce..6ffe94ca5bc9 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -124,7 +124,7 @@ static int inet_csk_diag_fill(struct sock *sk, #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, &np->rcv_saddr); diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 47038cb6c138..85a0f75dae64 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -51,8 +51,8 @@ MODULE_DESCRIPTION("Large Receive Offload (ipv4 / tcp)"); * Basic tcp checks whether packet is suitable for LRO */ -static int lro_tcp_ip_check(struct iphdr *iph, struct tcphdr *tcph, - int len, struct net_lro_desc *lro_desc) +static int lro_tcp_ip_check(const struct iphdr *iph, const struct tcphdr *tcph, + int len, const struct net_lro_desc *lro_desc) { /* check ip header: don't aggregate padded frames */ if (ntohs(iph->tot_len) != len) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index dd1b20eca1a2..ce616d92cc54 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -154,11 +154,9 @@ void __init inet_initpeers(void) /* Called with or without local BH being disabled. */ static void unlink_from_unused(struct inet_peer *p) { - if (!list_empty(&p->unused)) { - spin_lock_bh(&unused_peers.lock); - list_del_init(&p->unused); - spin_unlock_bh(&unused_peers.lock); - } + spin_lock_bh(&unused_peers.lock); + list_del_init(&p->unused); + spin_unlock_bh(&unused_peers.lock); } static int addr_compare(const struct inetpeer_addr *a, @@ -205,6 +203,20 @@ static int addr_compare(const struct inetpeer_addr *a, u; \ }) +static bool atomic_add_unless_return(atomic_t *ptr, int a, int u, int *newv) +{ + int cur, old = atomic_read(ptr); + + while (old != u) { + *newv = old + a; + cur = atomic_cmpxchg(ptr, old, *newv); + if (cur == old) + return true; + old = cur; + } + return false; +} + /* * Called with rcu_read_lock() * Because we hold no lock against a writer, its quite possible we fall @@ -213,7 +225,8 @@ static int addr_compare(const struct inetpeer_addr *a, * We exit from this function if number of links exceeds PEER_MAXDEPTH */ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, - struct inet_peer_base *base) + struct inet_peer_base *base, + int *newrefcnt) { struct inet_peer *u = rcu_dereference(base->root); int count = 0; @@ -226,7 +239,7 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, * distinction between an unused entry (refcnt=0) and * a freed one. */ - if (unlikely(!atomic_add_unless(&u->refcnt, 1, -1))) + if (!atomic_add_unless_return(&u->refcnt, 1, -1, newrefcnt)) u = NULL; return u; } @@ -354,7 +367,8 @@ static void inetpeer_free_rcu(struct rcu_head *head) } /* May be called with local BH enabled. */ -static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base) +static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base, + struct inet_peer __rcu **stack[PEER_MAXDEPTH]) { int do_free; @@ -368,7 +382,6 @@ static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base) * We use refcnt=-1 to alert lockless readers this entry is deleted. */ if (atomic_cmpxchg(&p->refcnt, 1, -1) == 1) { - struct inet_peer __rcu **stack[PEER_MAXDEPTH]; struct inet_peer __rcu ***stackptr, ***delp; if (lookup(&p->daddr, stack, base) != p) BUG(); @@ -422,7 +435,7 @@ static struct inet_peer_base *peer_to_base(struct inet_peer *p) } /* May be called with local BH enabled. */ -static int cleanup_once(unsigned long ttl) +static int cleanup_once(unsigned long ttl, struct inet_peer __rcu **stack[PEER_MAXDEPTH]) { struct inet_peer *p = NULL; @@ -454,7 +467,7 @@ static int cleanup_once(unsigned long ttl) * happen because of entry limits in route cache. */ return -1; - unlink_from_pool(p, peer_to_base(p)); + unlink_from_pool(p, peer_to_base(p), stack); return 0; } @@ -465,22 +478,23 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) struct inet_peer_base *base = family_to_base(daddr->family); struct inet_peer *p; unsigned int sequence; - int invalidated; + int invalidated, newrefcnt = 0; /* Look up for the address quickly, lockless. * Because of a concurrent writer, we might not find an existing entry. */ rcu_read_lock(); sequence = read_seqbegin(&base->lock); - p = lookup_rcu(daddr, base); + p = lookup_rcu(daddr, base, &newrefcnt); invalidated = read_seqretry(&base->lock, sequence); rcu_read_unlock(); if (p) { - /* The existing node has been found. +found: /* The existing node has been found. * Remove the entry from unused list if it was there. */ - unlink_from_unused(p); + if (newrefcnt == 1) + unlink_from_unused(p); return p; } @@ -494,11 +508,9 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) write_seqlock_bh(&base->lock); p = lookup(daddr, stack, base); if (p != peer_avl_empty) { - atomic_inc(&p->refcnt); + newrefcnt = atomic_inc_return(&p->refcnt); write_sequnlock_bh(&base->lock); - /* Remove the entry from unused list if it was there. */ - unlink_from_unused(p); - return p; + goto found; } p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL; if (p) { @@ -524,7 +536,7 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) if (base->total >= inet_peer_threshold) /* Remove one less-recently-used entry. */ - cleanup_once(0); + cleanup_once(0, stack); return p; } @@ -540,6 +552,7 @@ static void peer_check_expire(unsigned long dummy) { unsigned long now = jiffies; int ttl, total; + struct inet_peer __rcu **stack[PEER_MAXDEPTH]; total = compute_total(); if (total >= inet_peer_threshold) @@ -548,7 +561,7 @@ static void peer_check_expire(unsigned long dummy) ttl = inet_peer_maxttl - (inet_peer_maxttl - inet_peer_minttl) / HZ * total / inet_peer_threshold * HZ; - while (!cleanup_once(ttl)) { + while (!cleanup_once(ttl, stack)) { if (jiffies != now) break; } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 99461f09320f..3b34d1c86270 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway) + if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index a1151b8adf3c..0ad6035f6366 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -77,22 +77,40 @@ struct ipq { struct inet_peer *peer; }; -#define IPFRAG_ECN_CLEAR 0x01 /* one frag had INET_ECN_NOT_ECT */ -#define IPFRAG_ECN_SET_CE 0x04 /* one frag had INET_ECN_CE */ +/* RFC 3168 support : + * We want to check ECN values of all fragments, do detect invalid combinations. + * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value. + */ +#define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */ +#define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */ +#define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */ +#define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */ static inline u8 ip4_frag_ecn(u8 tos) { - tos = (tos & INET_ECN_MASK) + 1; - /* - * After the last operation we have (in binary): - * INET_ECN_NOT_ECT => 001 - * INET_ECN_ECT_1 => 010 - * INET_ECN_ECT_0 => 011 - * INET_ECN_CE => 100 - */ - return (tos & 2) ? 0 : tos; + return 1 << (tos & INET_ECN_MASK); } +/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements + * Value : 0xff if frame should be dropped. + * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field + */ +static const u8 ip4_frag_ecn_table[16] = { + /* at least one fragment had CE, and others ECT_0 or ECT_1 */ + [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE, + [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE, + [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE, + + /* invalid combinations : drop frame */ + [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff, + [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff, + [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff, + [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, + [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff, + [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff, + [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, +}; + static struct inet_frags ip4_frags; int ip_frag_nqueues(struct net *net) @@ -223,31 +241,30 @@ static void ip_expire(unsigned long arg) if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) { struct sk_buff *head = qp->q.fragments; + const struct iphdr *iph; + int err; rcu_read_lock(); head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out_rcu_unlock; + /* skb dst is stale, drop it, and perform route lookup again */ + skb_dst_drop(head); + iph = ip_hdr(head); + err = ip_route_input_noref(head, iph->daddr, iph->saddr, + iph->tos, head->dev); + if (err) + goto out_rcu_unlock; + /* - * Only search router table for the head fragment, - * when defraging timeout at PRE_ROUTING HOOK. + * Only an end host needs to send an ICMP + * "Fragment Reassembly Timeout" message, per RFC792. */ - if (qp->user == IP_DEFRAG_CONNTRACK_IN && !skb_dst(head)) { - const struct iphdr *iph = ip_hdr(head); - int err = ip_route_input(head, iph->daddr, iph->saddr, - iph->tos, head->dev); - if (unlikely(err)) - goto out_rcu_unlock; - - /* - * Only an end host needs to send an ICMP - * "Fragment Reassembly Timeout" message, per RFC792. - */ - if (skb_rtable(head)->rt_type != RTN_LOCAL) - goto out_rcu_unlock; + if (qp->user == IP_DEFRAG_CONNTRACK_IN && + skb_rtable(head)->rt_type != RTN_LOCAL) + goto out_rcu_unlock; - } /* Send an ICMP "Fragment Reassembly Timeout" message. */ icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); @@ -525,9 +542,15 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, int len; int ihlen; int err; + u8 ecn; ipq_kill(qp); + ecn = ip4_frag_ecn_table[qp->ecn]; + if (unlikely(ecn == 0xff)) { + err = -EINVAL; + goto out_fail; + } /* Make the one we just received the head. */ if (prev) { head = prev->next; @@ -606,17 +629,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, iph = ip_hdr(head); iph->frag_off = 0; iph->tot_len = htons(len); - /* RFC3168 5.3 Fragmentation support - * If one fragment had INET_ECN_NOT_ECT, - * reassembled frame also has INET_ECN_NOT_ECT - * Elif one fragment had INET_ECN_CE - * reassembled frame also has INET_ECN_CE - */ - if (qp->ecn & IPFRAG_ECN_CLEAR) - iph->tos &= ~INET_ECN_MASK; - else if (qp->ecn & IPFRAG_ECN_SET_CE) - iph->tos |= INET_ECN_CE; - + iph->tos |= ecn; IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS); qp->q.fragments = NULL; qp->q.fragments_tail = NULL; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index da5941f18c3c..8871067560db 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -413,11 +413,6 @@ static struct ip_tunnel *ipgre_tunnel_locate(struct net *net, dev_net_set(dev, net); - if (strchr(name, '%')) { - if (dev_alloc_name(dev, name) < 0) - goto failed_free; - } - nt = netdev_priv(dev); nt->parms = *parms; dev->rtnl_link_ops = &ipgre_link_ops; @@ -462,7 +457,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) by themself??? */ - struct iphdr *iph = (struct iphdr *)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; __be16 *p = (__be16*)(skb->data+(iph->ihl<<2)); int grehlen = (iph->ihl<<2) + 4; const int type = icmp_hdr(skb)->type; @@ -534,7 +529,7 @@ out: rcu_read_unlock(); } -static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) +static inline void ipgre_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb) { if (INET_ECN_is_ce(iph->tos)) { if (skb->protocol == htons(ETH_P_IP)) { @@ -546,19 +541,19 @@ static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) } static inline u8 -ipgre_ecn_encapsulate(u8 tos, struct iphdr *old_iph, struct sk_buff *skb) +ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb) { u8 inner = 0; if (skb->protocol == htons(ETH_P_IP)) inner = old_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) - inner = ipv6_get_dsfield((struct ipv6hdr *)old_iph); + inner = ipv6_get_dsfield((const struct ipv6hdr *)old_iph); return INET_ECN_encapsulate(tos, inner); } static int ipgre_rcv(struct sk_buff *skb) { - struct iphdr *iph; + const struct iphdr *iph; u8 *h; __be16 flags; __sum16 csum = 0; @@ -697,8 +692,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev { struct ip_tunnel *tunnel = netdev_priv(dev); struct pcpu_tstats *tstats; - struct iphdr *old_iph = ip_hdr(skb); - struct iphdr *tiph; + const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *tiph; + struct flowi4 fl4; u8 tos; __be16 df; struct rtable *rt; /* Route to the other host */ @@ -714,7 +710,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (dev->header_ops && dev->type == ARPHRD_IPGRE) { gre_hlen = 0; - tiph = (struct iphdr *)skb->data; + tiph = (const struct iphdr *)skb->data; } else { gre_hlen = tunnel->hlen; tiph = &tunnel->parms.iph; @@ -735,14 +731,14 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { - struct in6_addr *addr6; + const struct in6_addr *addr6; int addr_type; struct neighbour *neigh = skb_dst(skb)->neighbour; if (neigh == NULL) goto tx_error; - addr6 = (struct in6_addr *)&neigh->primary_key; + addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { @@ -766,10 +762,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb->protocol == htons(ETH_P_IP)) tos = old_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) - tos = ipv6_get_dsfield((struct ipv6hdr *)old_iph); + tos = ipv6_get_dsfield((const struct ipv6hdr *)old_iph); } - rt = ip_route_output_gre(dev_net(dev), dst, tiph->saddr, + rt = ip_route_output_gre(dev_net(dev), &fl4, dst, tiph->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); if (IS_ERR(rt)) { @@ -873,15 +869,15 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->frag_off = df; iph->protocol = IPPROTO_GRE; iph->tos = ipgre_ecn_encapsulate(tos, old_iph, skb); - iph->daddr = rt->rt_dst; - iph->saddr = rt->rt_src; + iph->daddr = fl4.daddr; + iph->saddr = fl4.saddr; if ((iph->ttl = tiph->ttl) == 0) { if (skb->protocol == htons(ETH_P_IP)) iph->ttl = old_iph->ttl; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) - iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit; + iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit; #endif else iph->ttl = ip4_dst_hoplimit(&rt->dst); @@ -927,7 +923,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; struct ip_tunnel *tunnel; - struct iphdr *iph; + const struct iphdr *iph; int hlen = LL_MAX_HEADER; int mtu = ETH_DATA_LEN; int addend = sizeof(struct iphdr) + 4; @@ -938,12 +934,14 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) /* Guess output device to choose reasonable mtu and needed_headroom */ if (iph->daddr) { - struct rtable *rt = ip_route_output_gre(dev_net(dev), - iph->daddr, iph->saddr, - tunnel->parms.o_key, - RT_TOS(iph->tos), - tunnel->parms.link); - + struct flowi4 fl4; + struct rtable *rt; + + rt = ip_route_output_gre(dev_net(dev), &fl4, + iph->daddr, iph->saddr, + tunnel->parms.o_key, + RT_TOS(iph->tos), + tunnel->parms.link); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); @@ -1180,7 +1178,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr) { - struct iphdr *iph = (struct iphdr *) skb_mac_header(skb); + const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } @@ -1196,13 +1194,15 @@ static int ipgre_open(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { - struct rtable *rt = ip_route_output_gre(dev_net(dev), - t->parms.iph.daddr, - t->parms.iph.saddr, - t->parms.o_key, - RT_TOS(t->parms.iph.tos), - t->parms.link); - + struct flowi4 fl4; + struct rtable *rt; + + rt = ip_route_output_gre(dev_net(dev), &fl4, + t->parms.iph.daddr, + t->parms.iph.saddr, + t->parms.o_key, + RT_TOS(t->parms.iph.tos), + t->parms.link); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index d7b2b0987a3b..c8f48efc5fd3 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -268,7 +268,7 @@ int ip_local_deliver(struct sk_buff *skb) static inline int ip_rcv_options(struct sk_buff *skb) { struct ip_options *opt; - struct iphdr *iph; + const struct iphdr *iph; struct net_device *dev = skb->dev; /* It looks as overkill, because not all @@ -374,7 +374,7 @@ drop: */ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct iphdr *iph; + const struct iphdr *iph; u32 len; /* When the interface is in promisc. mode, drop all the crap diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 28a736f3442f..c3118e1cd3bb 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -36,8 +36,8 @@ * saddr is address of outgoing interface. */ -void ip_options_build(struct sk_buff * skb, struct ip_options * opt, - __be32 daddr, struct rtable *rt, int is_frag) +void ip_options_build(struct sk_buff *skb, struct ip_options *opt, + __be32 daddr, struct rtable *rt, int is_frag) { unsigned char *iph = skb_network_header(skb); @@ -50,9 +50,9 @@ void ip_options_build(struct sk_buff * skb, struct ip_options * opt, if (!is_frag) { if (opt->rr_needaddr) - ip_rt_get_source(iph+opt->rr+iph[opt->rr+2]-5, rt); + ip_rt_get_source(iph+opt->rr+iph[opt->rr+2]-5, skb, rt); if (opt->ts_needaddr) - ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, rt); + ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, skb, rt); if (opt->ts_needtime) { struct timespec tv; __be32 midtime; @@ -83,9 +83,9 @@ void ip_options_build(struct sk_buff * skb, struct ip_options * opt, * NOTE: dopt cannot point to skb. */ -int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) +int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) { - struct ip_options *sopt; + const struct ip_options *sopt; unsigned char *sptr, *dptr; int soffset, doffset; int optlen; @@ -95,10 +95,8 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) sopt = &(IPCB(skb)->opt); - if (sopt->optlen == 0) { - dopt->optlen = 0; + if (sopt->optlen == 0) return 0; - } sptr = skb_network_header(skb); dptr = dopt->__data; @@ -157,7 +155,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) dopt->optlen += optlen; } if (sopt->srr) { - unsigned char * start = sptr+sopt->srr; + unsigned char *start = sptr+sopt->srr; __be32 faddr; optlen = start[1]; @@ -329,7 +327,7 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 2; goto error; } - if (skb) { + if (rt) { memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); opt->is_changed = 1; } @@ -371,7 +369,7 @@ int ip_options_compile(struct net *net, goto error; } opt->ts = optptr - iph; - if (skb) { + if (rt) { memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); timeptr = (__be32*)&optptr[optptr[2]+3]; } @@ -499,19 +497,19 @@ void ip_options_undo(struct ip_options * opt) } } -static struct ip_options *ip_options_get_alloc(const int optlen) +static struct ip_options_rcu *ip_options_get_alloc(const int optlen) { - return kzalloc(sizeof(struct ip_options) + ((optlen + 3) & ~3), + return kzalloc(sizeof(struct ip_options_rcu) + ((optlen + 3) & ~3), GFP_KERNEL); } -static int ip_options_get_finish(struct net *net, struct ip_options **optp, - struct ip_options *opt, int optlen) +static int ip_options_get_finish(struct net *net, struct ip_options_rcu **optp, + struct ip_options_rcu *opt, int optlen) { while (optlen & 3) - opt->__data[optlen++] = IPOPT_END; - opt->optlen = optlen; - if (optlen && ip_options_compile(net, opt, NULL)) { + opt->opt.__data[optlen++] = IPOPT_END; + opt->opt.optlen = optlen; + if (optlen && ip_options_compile(net, &opt->opt, NULL)) { kfree(opt); return -EINVAL; } @@ -520,29 +518,29 @@ static int ip_options_get_finish(struct net *net, struct ip_options **optp, return 0; } -int ip_options_get_from_user(struct net *net, struct ip_options **optp, +int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp, unsigned char __user *data, int optlen) { - struct ip_options *opt = ip_options_get_alloc(optlen); + struct ip_options_rcu *opt = ip_options_get_alloc(optlen); if (!opt) return -ENOMEM; - if (optlen && copy_from_user(opt->__data, data, optlen)) { + if (optlen && copy_from_user(opt->opt.__data, data, optlen)) { kfree(opt); return -EFAULT; } return ip_options_get_finish(net, optp, opt, optlen); } -int ip_options_get(struct net *net, struct ip_options **optp, +int ip_options_get(struct net *net, struct ip_options_rcu **optp, unsigned char *data, int optlen) { - struct ip_options *opt = ip_options_get_alloc(optlen); + struct ip_options_rcu *opt = ip_options_get_alloc(optlen); if (!opt) return -ENOMEM; if (optlen) - memcpy(opt->__data, data, optlen); + memcpy(opt->opt.__data, data, optlen); return ip_options_get_finish(net, optp, opt, optlen); } @@ -555,7 +553,7 @@ void ip_forward_options(struct sk_buff *skb) if (opt->rr_needaddr) { optptr = (unsigned char *)raw + opt->rr; - ip_rt_get_source(&optptr[optptr[2]-5], rt); + ip_rt_get_source(&optptr[optptr[2]-5], skb, rt); opt->is_changed = 1; } if (opt->srr_is_hit) { @@ -569,19 +567,18 @@ void ip_forward_options(struct sk_buff *skb) ) { if (srrptr + 3 > srrspace) break; - if (memcmp(&rt->rt_dst, &optptr[srrptr-1], 4) == 0) + if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; - ip_rt_get_source(&optptr[srrptr-1], rt); - ip_hdr(skb)->daddr = rt->rt_dst; + ip_rt_get_source(&optptr[srrptr-1], skb, rt); optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); if (opt->ts_needaddr) { optptr = raw + opt->ts; - ip_rt_get_source(&optptr[optptr[2]-9], rt); + ip_rt_get_source(&optptr[optptr[2]-9], skb, rt); opt->is_changed = 1; } } @@ -603,7 +600,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) unsigned long orefdst; int err; - if (!opt->srr) + if (!rt) return 0; if (skb->pkt_type != PACKET_HOST) @@ -637,7 +634,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) if (rt2->rt_type != RTN_LOCAL) break; /* Superfast 8) loopback forward */ - memcpy(&iph->daddr, &optptr[srrptr-1], 4); + iph->daddr = nexthop; opt->is_changed = 1; } if (srrptr <= srrspace) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 67f241b97649..98af3697c718 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -140,14 +140,14 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) * */ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, - __be32 saddr, __be32 daddr, struct ip_options *opt) + __be32 saddr, __be32 daddr, struct ip_options_rcu *opt) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); struct iphdr *iph; /* Build the IP header. */ - skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0)); + skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; @@ -158,14 +158,14 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, else iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); - iph->daddr = rt->rt_dst; - iph->saddr = rt->rt_src; + iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); + iph->saddr = saddr; iph->protocol = sk->sk_protocol; ip_select_ident(iph, &rt->dst, sk); - if (opt && opt->optlen) { - iph->ihl += opt->optlen>>2; - ip_options_build(skb, opt, daddr, rt, 0); + if (opt && opt->opt.optlen) { + iph->ihl += opt->opt.optlen>>2; + ip_options_build(skb, &opt->opt, daddr, rt, 0); } skb->priority = sk->sk_priority; @@ -312,11 +312,12 @@ int ip_output(struct sk_buff *skb) !(IPCB(skb)->flags & IPSKB_REROUTED)); } -int ip_queue_xmit(struct sk_buff *skb) +int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); - struct ip_options *opt = inet->opt; + struct ip_options_rcu *inet_opt; + struct flowi4 *fl4; struct rtable *rt; struct iphdr *iph; int res; @@ -325,6 +326,8 @@ int ip_queue_xmit(struct sk_buff *skb) * f.e. by something like SCTP. */ rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + fl4 = &fl->u.ip4; rt = skb_rtable(skb); if (rt != NULL) goto packet_routed; @@ -336,14 +339,14 @@ int ip_queue_xmit(struct sk_buff *skb) /* Use correct destination address if we have options. */ daddr = inet->inet_daddr; - if(opt && opt->srr) - daddr = opt->faddr; + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ - rt = ip_route_output_ports(sock_net(sk), sk, + rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, @@ -357,11 +360,11 @@ int ip_queue_xmit(struct sk_buff *skb) skb_dst_set_noref(skb, &rt->dst); packet_routed: - if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) + if (inet_opt && inet_opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ - skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0)); + skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff)); @@ -371,13 +374,13 @@ packet_routed: iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; - iph->saddr = rt->rt_src; - iph->daddr = rt->rt_dst; + iph->saddr = fl4->saddr; + iph->daddr = fl4->daddr; /* Transport layer set skb->h.foo itself. */ - if (opt && opt->optlen) { - iph->ihl += opt->optlen >> 2; - ip_options_build(skb, opt, inet->inet_daddr, rt, 0); + if (inet_opt && inet_opt->opt.optlen) { + iph->ihl += inet_opt->opt.optlen >> 2; + ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } ip_select_ident_more(iph, &rt->dst, sk, @@ -603,7 +606,7 @@ slow_path: /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) len = mtu; - /* IF: we are not sending upto and including the packet end + /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < left) { len &= ~7; @@ -773,7 +776,9 @@ static inline int ip_ufo_append_data(struct sock *sk, (length - transhdrlen)); } -static int __ip_append_data(struct sock *sk, struct sk_buff_head *queue, +static int __ip_append_data(struct sock *sk, + struct flowi4 *fl4, + struct sk_buff_head *queue, struct inet_cork *cork, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), @@ -805,7 +810,7 @@ static int __ip_append_data(struct sock *sk, struct sk_buff_head *queue, maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; if (cork->length + length > 0xFFFF - fragheaderlen) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, + ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu-exthdrlen); return -EMSGSIZE; } @@ -1033,7 +1038,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ipcm_cookie *ipc, struct rtable **rtp) { struct inet_sock *inet = inet_sk(sk); - struct ip_options *opt; + struct ip_options_rcu *opt; struct rtable *rt; /* @@ -1047,7 +1052,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, if (unlikely(cork->opt == NULL)) return -ENOBUFS; } - memcpy(cork->opt, opt, sizeof(struct ip_options) + opt->optlen); + memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } @@ -1080,7 +1085,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, * * LATER: length must be adjusted by pad at tail, when it is required. */ -int ip_append_data(struct sock *sk, +int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, @@ -1094,24 +1099,25 @@ int ip_append_data(struct sock *sk, return 0; if (skb_queue_empty(&sk->sk_write_queue)) { - err = ip_setup_cork(sk, &inet->cork, ipc, rtp); + err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp); if (err) return err; } else { transhdrlen = 0; } - return __ip_append_data(sk, &sk->sk_write_queue, &inet->cork, getfrag, + return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, getfrag, from, length, transhdrlen, flags); } -ssize_t ip_append_page(struct sock *sk, struct page *page, +ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, int offset, size_t size, int flags) { struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; struct rtable *rt; struct ip_options *opt = NULL; + struct inet_cork *cork; int hh_len; int mtu; int len; @@ -1127,28 +1133,29 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, if (skb_queue_empty(&sk->sk_write_queue)) return -EINVAL; - rt = (struct rtable *)inet->cork.dst; - if (inet->cork.flags & IPCORK_OPT) - opt = inet->cork.opt; + cork = &inet->cork.base; + rt = (struct rtable *)cork->dst; + if (cork->flags & IPCORK_OPT) + opt = cork->opt; if (!(rt->dst.dev->features&NETIF_F_SG)) return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); - mtu = inet->cork.fragsize; + mtu = cork->fragsize; fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - if (inet->cork.length + size > 0xFFFF - fragheaderlen) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, mtu); + if (cork->length + size > 0xFFFF - fragheaderlen) { + ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu); return -EMSGSIZE; } if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) return -EINVAL; - inet->cork.length += size; + cork->length += size; if ((size + skb->len > mtu) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { @@ -1243,7 +1250,7 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, return 0; error: - inet->cork.length -= size; + cork->length -= size; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); return err; } @@ -1262,6 +1269,7 @@ static void ip_cork_release(struct inet_cork *cork) * and push them out. */ struct sk_buff *__ip_make_skb(struct sock *sk, + struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork) { @@ -1319,17 +1327,18 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph = (struct iphdr *)skb->data; iph->version = 4; iph->ihl = 5; - if (opt) { - iph->ihl += opt->optlen>>2; - ip_options_build(skb, opt, cork->addr, rt, 0); - } iph->tos = inet->tos; iph->frag_off = df; ip_select_ident(iph, &rt->dst, sk); iph->ttl = ttl; iph->protocol = sk->sk_protocol; - iph->saddr = rt->rt_src; - iph->daddr = rt->rt_dst; + iph->saddr = fl4->saddr; + iph->daddr = fl4->daddr; + + if (opt) { + iph->ihl += opt->optlen>>2; + ip_options_build(skb, opt, cork->addr, rt, 0); + } skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -1365,11 +1374,11 @@ int ip_send_skb(struct sk_buff *skb) return err; } -int ip_push_pending_frames(struct sock *sk) +int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4) { struct sk_buff *skb; - skb = ip_finish_skb(sk); + skb = ip_finish_skb(sk, fl4); if (!skb) return 0; @@ -1394,17 +1403,18 @@ static void __ip_flush_pending_frames(struct sock *sk, void ip_flush_pending_frames(struct sock *sk) { - __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork); + __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } struct sk_buff *ip_make_skb(struct sock *sk, + struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, unsigned int flags) { - struct inet_cork cork = {}; + struct inet_cork cork; struct sk_buff_head queue; int err; @@ -1413,18 +1423,21 @@ struct sk_buff *ip_make_skb(struct sock *sk, __skb_queue_head_init(&queue); + cork.flags = 0; + cork.addr = 0; + cork.opt = NULL; err = ip_setup_cork(sk, &cork, ipc, rtp); if (err) return ERR_PTR(err); - err = __ip_append_data(sk, &queue, &cork, getfrag, + err = __ip_append_data(sk, fl4, &queue, &cork, getfrag, from, length, transhdrlen, flags); if (err) { __ip_flush_pending_frames(sk, &queue, &cork); return ERR_PTR(err); } - return __ip_make_skb(sk, &queue, &cork); + return __ip_make_skb(sk, fl4, &queue, &cork); } /* @@ -1447,48 +1460,39 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, * Should run single threaded per socket because it uses the sock * structure to pass arguments. */ -void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg, - unsigned int len) +void ip_send_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, + struct ip_reply_arg *arg, unsigned int len) { struct inet_sock *inet = inet_sk(sk); - struct { - struct ip_options opt; - char data[40]; - } replyopts; + struct ip_options_data replyopts; struct ipcm_cookie ipc; - __be32 daddr; + struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); - if (ip_options_echo(&replyopts.opt, skb)) + if (ip_options_echo(&replyopts.opt.opt, skb)) return; - daddr = ipc.addr = rt->rt_src; + ipc.addr = daddr; ipc.opt = NULL; ipc.tx_flags = 0; - if (replyopts.opt.optlen) { + if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; - if (ipc.opt->srr) - daddr = replyopts.opt.faddr; + if (replyopts.opt.opt.srr) + daddr = replyopts.opt.opt.faddr; } - { - struct flowi4 fl4 = { - .flowi4_oif = arg->bound_dev_if, - .daddr = daddr, - .saddr = rt->rt_spec_dst, - .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), - .fl4_sport = tcp_hdr(skb)->dest, - .fl4_dport = tcp_hdr(skb)->source, - .flowi4_proto = sk->sk_protocol, - .flowi4_flags = ip_reply_arg_flowi_flags(arg), - }; - security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); - rt = ip_route_output_key(sock_net(sk), &fl4); - if (IS_ERR(rt)) - return; - } + flowi4_init_output(&fl4, arg->bound_dev_if, 0, + RT_TOS(ip_hdr(skb)->tos), + RT_SCOPE_UNIVERSE, sk->sk_protocol, + ip_reply_arg_flowi_flags(arg), + daddr, rt->rt_spec_dst, + tcp_hdr(skb)->source, tcp_hdr(skb)->dest); + security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); + rt = ip_route_output_key(sock_net(sk), &fl4); + if (IS_ERR(rt)) + return; /* And let IP do all the hard work. @@ -1501,7 +1505,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - ip_append_data(sk, ip_reply_glue_bits, arg->iov->iov_base, len, 0, + ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { if (arg->csumoffset >= 0) @@ -1509,7 +1513,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar arg->csumoffset) = csum_fold(csum_add(skb->csum, arg->csum)); skb->ip_summed = CHECKSUM_NONE; - ip_push_pending_frames(sk); + ip_push_pending_frames(sk, &fl4); } bh_unlock_sock(sk); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 3948c86e59ca..ab0c9efd1efa 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -131,7 +131,7 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); __be16 *ports = (__be16 *)skb_transport_header(skb); if (skb_transport_offset(skb) + 4 > skb->len) @@ -451,6 +451,11 @@ out: } +static void opt_kfree_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_options_rcu, rcu)); +} + /* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket. @@ -497,13 +502,16 @@ static int do_ip_setsockopt(struct sock *sk, int level, switch (optname) { case IP_OPTIONS: { - struct ip_options *opt = NULL; + struct ip_options_rcu *old, *opt = NULL; + if (optlen > 40) goto e_inval; err = ip_options_get_from_user(sock_net(sk), &opt, optval, optlen); if (err) break; + old = rcu_dereference_protected(inet->inet_opt, + sock_owned_by_user(sk)); if (inet->is_icsk) { struct inet_connection_sock *icsk = inet_csk(sk); #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) @@ -512,17 +520,18 @@ static int do_ip_setsockopt(struct sock *sk, int level, (TCPF_LISTEN | TCPF_CLOSE)) && inet->inet_daddr != LOOPBACK4_IPV6)) { #endif - if (inet->opt) - icsk->icsk_ext_hdr_len -= inet->opt->optlen; + if (old) + icsk->icsk_ext_hdr_len -= old->opt.optlen; if (opt) - icsk->icsk_ext_hdr_len += opt->optlen; + icsk->icsk_ext_hdr_len += opt->opt.optlen; icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) } #endif } - opt = xchg(&inet->opt, opt); - kfree(opt); + rcu_assign_pointer(inet->inet_opt, opt); + if (old) + call_rcu(&old->rcu, opt_kfree_rcu); break; } case IP_PKTINFO: @@ -1081,12 +1090,16 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_OPTIONS: { unsigned char optbuf[sizeof(struct ip_options)+40]; - struct ip_options * opt = (struct ip_options *)optbuf; + struct ip_options *opt = (struct ip_options *)optbuf; + struct ip_options_rcu *inet_opt; + + inet_opt = rcu_dereference_protected(inet->inet_opt, + sock_owned_by_user(sk)); opt->optlen = 0; - if (inet->opt) - memcpy(optbuf, inet->opt, - sizeof(struct ip_options)+ - inet->opt->optlen); + if (inet_opt) + memcpy(optbuf, &inet_opt->opt, + sizeof(struct ip_options) + + inet_opt->opt.optlen); release_sock(sk); if (opt->optlen == 0) diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 629067571f02..c857f6f49b03 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -27,7 +27,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); __be32 spi; - struct iphdr *iph = (struct iphdr *)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; @@ -36,7 +36,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) return; spi = htonl(ntohs(ipch->cpi)); - x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) return; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 2b097752426b..ab7e5542c1cf 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -87,8 +87,8 @@ #endif /* Define the friendly delay before and after opening net devices */ -#define CONF_PRE_OPEN 500 /* Before opening: 1/2 second */ -#define CONF_POST_OPEN 1 /* After opening: 1 second */ +#define CONF_POST_OPEN 10 /* After opening: 10 msecs */ +#define CONF_CARRIER_TIMEOUT 120000 /* Wait for carrier timeout */ /* Define the timeout for waiting for a DHCP/BOOTP/RARP reply */ #define CONF_OPEN_RETRIES 2 /* (Re)open devices twice */ @@ -188,14 +188,14 @@ struct ic_device { static struct ic_device *ic_first_dev __initdata = NULL;/* List of open device */ static struct net_device *ic_dev __initdata = NULL; /* Selected device */ -static bool __init ic_device_match(struct net_device *dev) +static bool __init ic_is_init_dev(struct net_device *dev) { - if (user_dev_name[0] ? !strcmp(dev->name, user_dev_name) : + if (dev->flags & IFF_LOOPBACK) + return false; + return user_dev_name[0] ? !strcmp(dev->name, user_dev_name) : (!(dev->flags & IFF_LOOPBACK) && (dev->flags & (IFF_POINTOPOINT|IFF_BROADCAST)) && - strncmp(dev->name, "dummy", 5))) - return true; - return false; + strncmp(dev->name, "dummy", 5)); } static int __init ic_open_devs(void) @@ -203,6 +203,7 @@ static int __init ic_open_devs(void) struct ic_device *d, **last; struct net_device *dev; unsigned short oflags; + unsigned long start; last = &ic_first_dev; rtnl_lock(); @@ -216,9 +217,7 @@ static int __init ic_open_devs(void) } for_each_netdev(&init_net, dev) { - if (dev->flags & IFF_LOOPBACK) - continue; - if (ic_device_match(dev)) { + if (ic_is_init_dev(dev)) { int able = 0; if (dev->mtu >= 364) able |= IC_BOOTP; @@ -252,6 +251,17 @@ static int __init ic_open_devs(void) dev->name, able, d->xid)); } } + + /* wait for a carrier on at least one device */ + start = jiffies; + while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) { + for_each_netdev(&init_net, dev) + if (ic_is_init_dev(dev) && netif_carrier_ok(dev)) + goto have_carrier; + + msleep(1); + } +have_carrier: rtnl_unlock(); *last = NULL; @@ -1324,14 +1334,13 @@ static int __init wait_for_devices(void) { int i; - msleep(CONF_PRE_OPEN); for (i = 0; i < DEVICE_WAIT_MAX; i++) { struct net_device *dev; int found = 0; rtnl_lock(); for_each_netdev(&init_net, dev) { - if (ic_device_match(dev)) { + if (ic_is_init_dev(dev)) { found = 1; break; } @@ -1378,7 +1387,7 @@ static int __init ip_auto_config(void) return err; /* Give drivers a chance to settle */ - ssleep(CONF_POST_OPEN); + msleep(CONF_POST_OPEN); /* * If the config information is insufficient (e.g., our IP address or @@ -1444,7 +1453,7 @@ static int __init ip_auto_config(void) root_server_addr = addr; /* - * Use defaults whereever applicable. + * Use defaults wherever applicable. */ if (ic_defaults() < 0) return -1; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index bfc17c5914e7..378b20b7ca6e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -276,11 +276,6 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, dev_net_set(dev, net); - if (strchr(name, '%')) { - if (dev_alloc_name(dev, name) < 0) - goto failed_free; - } - nt = netdev_priv(dev); nt->parms = *parms; @@ -319,7 +314,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. */ - struct iphdr *iph = (struct iphdr *)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; @@ -433,15 +428,16 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct pcpu_tstats *tstats; - struct iphdr *tiph = &tunnel->parms.iph; + const 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 iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph = ip_hdr(skb); struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; + struct flowi4 fl4; int mtu; if (skb->protocol != htons(ETH_P_IP)) @@ -460,7 +456,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_error_icmp; } - rt = ip_route_output_ports(dev_net(dev), NULL, + rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, dst, tiph->saddr, 0, 0, IPPROTO_IPIP, RT_TOS(tos), @@ -549,8 +545,8 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) iph->frag_off = df; iph->protocol = IPPROTO_IPIP; iph->tos = INET_ECN_encapsulate(tos, old_iph->tos); - iph->daddr = rt->rt_dst; - iph->saddr = rt->rt_src; + iph->daddr = fl4.daddr; + iph->saddr = fl4.saddr; if ((iph->ttl = tiph->ttl) == 0) iph->ttl = old_iph->ttl; @@ -572,19 +568,21 @@ static void ipip_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; struct ip_tunnel *tunnel; - struct iphdr *iph; + const struct iphdr *iph; tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; if (iph->daddr) { - struct rtable *rt = ip_route_output_ports(dev_net(dev), NULL, - iph->daddr, iph->saddr, - 0, 0, - IPPROTO_IPIP, - RT_TOS(iph->tos), - tunnel->parms.link); - + struct rtable *rt; + struct flowi4 fl4; + + rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, + iph->daddr, iph->saddr, + 0, 0, + IPPROTO_IPIP, + RT_TOS(iph->tos), + tunnel->parms.link); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 1f62eaeb6de4..30a7763c400e 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1549,7 +1549,7 @@ static struct notifier_block ip_mr_notifier = { static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct iphdr *iph; - struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph = ip_hdr(skb); skb_push(skb, sizeof(struct iphdr)); skb->transport_header = skb->network_header; @@ -1595,6 +1595,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *dev; struct rtable *rt; + struct flowi4 fl4; int encap = 0; if (vif->dev == NULL) @@ -1612,7 +1613,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, #endif if (vif->flags & VIFF_TUNNEL) { - rt = ip_route_output_ports(net, NULL, + rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, 0, 0, IPPROTO_IPIP, @@ -1621,7 +1622,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, goto out_free; encap = sizeof(struct iphdr); } else { - rt = ip_route_output_ports(net, NULL, iph->daddr, 0, + rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0, 0, 0, IPPROTO_IPIP, RT_TOS(iph->tos), vif->link); @@ -1788,12 +1789,14 @@ dont_forward: return 0; } -static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct rtable *rt) +static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) { + struct rtable *rt = skb_rtable(skb); + struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { - .daddr = rt->rt_key_dst, - .saddr = rt->rt_key_src, - .flowi4_tos = rt->rt_tos, + .daddr = iph->daddr, + .saddr = iph->saddr, + .flowi4_tos = iph->tos, .flowi4_oif = rt->rt_oif, .flowi4_iif = rt->rt_iif, .flowi4_mark = rt->rt_mark, @@ -1825,7 +1828,7 @@ int ip_mr_input(struct sk_buff *skb) if (IPCB(skb)->flags & IPSKB_FORWARDED) goto dont_forward; - mrt = ipmr_rt_fib_lookup(net, skb_rtable(skb)); + mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) { kfree_skb(skb); return PTR_ERR(mrt); @@ -1957,7 +1960,7 @@ int pim_rcv_v1(struct sk_buff *skb) pim = igmp_hdr(skb); - mrt = ipmr_rt_fib_lookup(net, skb_rtable(skb)); + mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) goto drop; if (!mrt->mroute_do_pim || @@ -1989,7 +1992,7 @@ static int pim_rcv(struct sk_buff *skb) csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; - mrt = ipmr_rt_fib_lookup(net, skb_rtable(skb)); + mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) goto drop; if (__pim_rcv(mrt, skb, sizeof(*pim))) { @@ -2038,20 +2041,20 @@ rtattr_failure: return -EMSGSIZE; } -int ipmr_get_route(struct net *net, - struct sk_buff *skb, struct rtmsg *rtm, int nowait) +int ipmr_get_route(struct net *net, struct sk_buff *skb, + __be32 saddr, __be32 daddr, + struct rtmsg *rtm, int nowait) { - int err; - struct mr_table *mrt; struct mfc_cache *cache; - struct rtable *rt = skb_rtable(skb); + struct mr_table *mrt; + int err; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); if (mrt == NULL) return -ENOENT; rcu_read_lock(); - cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst); + cache = ipmr_cache_find(mrt, saddr, daddr); if (cache == NULL) { struct sk_buff *skb2; @@ -2084,8 +2087,8 @@ int ipmr_get_route(struct net *net, skb_reset_network_header(skb2); iph = ip_hdr(skb2); iph->ihl = sizeof(struct iphdr) >> 2; - iph->saddr = rt->rt_src; - iph->daddr = rt->rt_dst; + iph->saddr = saddr; + iph->daddr = daddr; iph->version = 0; err = ipmr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f3c0b549b8e1..4614babdc45f 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -221,9 +221,10 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, return csum; } -static int nf_ip_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict __always_unused) { - struct rtable *rt = ip_route_output_key(&init_net, &fl->u.ip4); + struct rtable *rt = ip_route_output_key(net, &fl->u.ip4); if (IS_ERR(rt)) return PTR_ERR(rt); *dst = &rt->dst; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 4b5d457c2d76..fd7a3f68917f 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -76,7 +76,7 @@ static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, } /* - * Unfortunatly, _b and _mask are not aligned to an int (or long int) + * Unfortunately, _b and _mask are not aligned to an int (or long int) * Some arches dont care, unrolling the loop is a win on them. * For other arches, we only have a 16bit alignement. */ @@ -260,6 +260,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, void *table_base; const struct xt_table_info *private; struct xt_action_param acpar; + unsigned int addend; if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) return NF_DROP; @@ -267,7 +268,8 @@ unsigned int arpt_do_table(struct sk_buff *skb, indev = in ? in->name : nulldevname; outdev = out ? out->name : nulldevname; - xt_info_rdlock_bh(); + local_bh_disable(); + addend = xt_write_recseq_begin(); private = table->private; table_base = private->entries[smp_processor_id()]; @@ -338,7 +340,8 @@ unsigned int arpt_do_table(struct sk_buff *skb, /* Verdict */ break; } while (!acpar.hotdrop); - xt_info_rdunlock_bh(); + xt_write_recseq_end(addend); + local_bh_enable(); if (acpar.hotdrop) return NF_DROP; @@ -712,7 +715,7 @@ static void get_counters(const struct xt_table_info *t, unsigned int i; for_each_possible_cpu(cpu) { - seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries[cpu], t->size) { @@ -720,10 +723,10 @@ static void get_counters(const struct xt_table_info *t, unsigned int start; do { - start = read_seqbegin(lock); + start = read_seqcount_begin(s); bcnt = iter->counters.bcnt; pcnt = iter->counters.pcnt; - } while (read_seqretry(lock, start)); + } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; @@ -1115,6 +1118,7 @@ static int do_add_counters(struct net *net, const void __user *user, int ret = 0; void *loc_cpu_entry; struct arpt_entry *iter; + unsigned int addend; #ifdef CONFIG_COMPAT struct compat_xt_counters_info compat_tmp; @@ -1171,12 +1175,12 @@ static int do_add_counters(struct net *net, const void __user *user, /* Choose the copy that is on our node */ curcpu = smp_processor_id(); loc_cpu_entry = private->entries[curcpu]; - xt_info_wrlock(curcpu); + addend = xt_write_recseq_begin(); xt_entry_foreach(iter, loc_cpu_entry, private->size) { ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt); ++i; } - xt_info_wrunlock(curcpu); + xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); @@ -1874,7 +1878,7 @@ static int __init arp_tables_init(void) if (ret < 0) goto err1; - /* Noone else will be downing sem now, so we won't sleep */ + /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); if (ret < 0) goto err2; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index ffcea0d1678e..764743843503 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -68,15 +68,6 @@ void *ipt_alloc_initial_table(const struct xt_table *info) } EXPORT_SYMBOL_GPL(ipt_alloc_initial_table); -/* - We keep a set of rules for each CPU, so we can avoid write-locking - them in the softirq when updating the counters and therefore - only need to read-lock in the softirq; doing a write_lock_bh() in user - context stops packets coming through and allows user context to read - the counters or update the rules. - - Hence the start of any table is given by get_table() below. */ - /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool @@ -311,6 +302,7 @@ ipt_do_table(struct sk_buff *skb, unsigned int *stackptr, origptr, cpu; const struct xt_table_info *private; struct xt_action_param acpar; + unsigned int addend; /* Initialization */ ip = ip_hdr(skb); @@ -331,7 +323,8 @@ ipt_do_table(struct sk_buff *skb, acpar.hooknum = hook; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - xt_info_rdlock_bh(); + local_bh_disable(); + addend = xt_write_recseq_begin(); private = table->private; cpu = smp_processor_id(); table_base = private->entries[cpu]; @@ -430,7 +423,9 @@ ipt_do_table(struct sk_buff *skb, pr_debug("Exiting %s; resetting sp from %u to %u\n", __func__, *stackptr, origptr); *stackptr = origptr; - xt_info_rdunlock_bh(); + xt_write_recseq_end(addend); + local_bh_enable(); + #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; #else @@ -886,7 +881,7 @@ get_counters(const struct xt_table_info *t, unsigned int i; for_each_possible_cpu(cpu) { - seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries[cpu], t->size) { @@ -894,10 +889,10 @@ get_counters(const struct xt_table_info *t, unsigned int start; do { - start = read_seqbegin(lock); + start = read_seqcount_begin(s); bcnt = iter->counters.bcnt; pcnt = iter->counters.pcnt; - } while (read_seqretry(lock, start)); + } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; /* macro does multi eval of i */ @@ -1312,6 +1307,7 @@ do_add_counters(struct net *net, const void __user *user, int ret = 0; void *loc_cpu_entry; struct ipt_entry *iter; + unsigned int addend; #ifdef CONFIG_COMPAT struct compat_xt_counters_info compat_tmp; @@ -1368,12 +1364,12 @@ do_add_counters(struct net *net, const void __user *user, /* Choose the copy that is on our node */ curcpu = smp_processor_id(); loc_cpu_entry = private->entries[curcpu]; - xt_info_wrlock(curcpu); + addend = xt_write_recseq_begin(); xt_entry_foreach(iter, loc_cpu_entry, private->size) { ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt); ++i; } - xt_info_wrunlock(curcpu); + xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); @@ -2233,7 +2229,7 @@ static int __init ip_tables_init(void) if (ret < 0) goto err1; - /* Noone else will be downing sem now, so we won't sleep */ + /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); if (ret < 0) goto err2; diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 21bcf471b25a..9c71b2755ce3 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -521,7 +521,7 @@ int nf_nat_protocol_register(const struct nf_nat_protocol *proto) } EXPORT_SYMBOL(nf_nat_protocol_register); -/* Noone stores the protocol anywhere; simply delete it. */ +/* No one stores the protocol anywhere; simply delete it. */ void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto) { spin_lock_bh(&nf_nat_lock); @@ -532,7 +532,7 @@ void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto) } EXPORT_SYMBOL(nf_nat_protocol_unregister); -/* Noone using conntrack by the time this called. */ +/* No one using conntrack by the time this called. */ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) { struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 31427fb57aa8..99cfa28b6d38 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -153,7 +153,7 @@ void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); -static void nf_nat_csum(struct sk_buff *skb, struct iphdr *iph, void *data, +static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data, int datalen, __sum16 *check, int oldlen) { struct rtable *rt = skb_rtable(skb); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c new file mode 100644 index 000000000000..9aaa67165f42 --- /dev/null +++ b/net/ipv4/ping.c @@ -0,0 +1,932 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * "Ping" sockets + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Based on ipv4/udp.c code. + * + * Authors: Vasiliy Kulikov / Openwall (for Linux 2.6), + * Pavel Kankovsky (for Linux 2.4.32) + * + * Pavel gave all rights to bugs to Vasiliy, + * none of the bugs are Pavel's now. + * + */ + +#include <asm/system.h> +#include <linux/uaccess.h> +#include <linux/types.h> +#include <linux/fcntl.h> +#include <linux/socket.h> +#include <linux/sockios.h> +#include <linux/in.h> +#include <linux/errno.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/inet.h> +#include <linux/netdevice.h> +#include <net/snmp.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/icmp.h> +#include <net/protocol.h> +#include <linux/skbuff.h> +#include <linux/proc_fs.h> +#include <net/sock.h> +#include <net/ping.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/route.h> +#include <net/inet_common.h> +#include <net/checksum.h> + + +static struct ping_table ping_table; + +static u16 ping_port_rover; + +static inline int ping_hashfn(struct net *net, unsigned num, unsigned mask) +{ + int res = (num + net_hash_mix(net)) & mask; + pr_debug("hash(%d) = %d\n", num, res); + return res; +} + +static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table, + struct net *net, unsigned num) +{ + return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)]; +} + +static int ping_v4_get_port(struct sock *sk, unsigned short ident) +{ + struct hlist_nulls_node *node; + struct hlist_nulls_head *hlist; + struct inet_sock *isk, *isk2; + struct sock *sk2 = NULL; + + isk = inet_sk(sk); + write_lock_bh(&ping_table.lock); + if (ident == 0) { + u32 i; + u16 result = ping_port_rover + 1; + + for (i = 0; i < (1L << 16); i++, result++) { + if (!result) + result++; /* avoid zero */ + hlist = ping_hashslot(&ping_table, sock_net(sk), + result); + ping_portaddr_for_each_entry(sk2, node, hlist) { + isk2 = inet_sk(sk2); + + if (isk2->inet_num == result) + goto next_port; + } + + /* found */ + ping_port_rover = ident = result; + break; +next_port: + ; + } + if (i >= (1L << 16)) + goto fail; + } else { + hlist = ping_hashslot(&ping_table, sock_net(sk), ident); + ping_portaddr_for_each_entry(sk2, node, hlist) { + isk2 = inet_sk(sk2); + + if ((isk2->inet_num == ident) && + (sk2 != sk) && + (!sk2->sk_reuse || !sk->sk_reuse)) + goto fail; + } + } + + pr_debug("found port/ident = %d\n", ident); + isk->inet_num = ident; + if (sk_unhashed(sk)) { + pr_debug("was not hashed\n"); + sock_hold(sk); + hlist_nulls_add_head(&sk->sk_nulls_node, hlist); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + } + write_unlock_bh(&ping_table.lock); + return 0; + +fail: + write_unlock_bh(&ping_table.lock); + return 1; +} + +static void ping_v4_hash(struct sock *sk) +{ + pr_debug("ping_v4_hash(sk->port=%u)\n", inet_sk(sk)->inet_num); + BUG(); /* "Please do not press this button again." */ +} + +static void ping_v4_unhash(struct sock *sk) +{ + struct inet_sock *isk = inet_sk(sk); + pr_debug("ping_v4_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); + if (sk_hashed(sk)) { + write_lock_bh(&ping_table.lock); + hlist_nulls_del(&sk->sk_nulls_node); + sock_put(sk); + isk->inet_num = isk->inet_sport = 0; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + write_unlock_bh(&ping_table.lock); + } +} + +static struct sock *ping_v4_lookup(struct net *net, u32 saddr, u32 daddr, + u16 ident, int dif) +{ + struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident); + struct sock *sk = NULL; + struct inet_sock *isk; + struct hlist_nulls_node *hnode; + + pr_debug("try to find: num = %d, daddr = %ld, dif = %d\n", + (int)ident, (unsigned long)daddr, dif); + read_lock_bh(&ping_table.lock); + + ping_portaddr_for_each_entry(sk, hnode, hslot) { + isk = inet_sk(sk); + + pr_debug("found: %p: num = %d, daddr = %ld, dif = %d\n", sk, + (int)isk->inet_num, (unsigned long)isk->inet_rcv_saddr, + sk->sk_bound_dev_if); + + pr_debug("iterate\n"); + if (isk->inet_num != ident) + continue; + if (isk->inet_rcv_saddr && isk->inet_rcv_saddr != daddr) + continue; + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) + continue; + + sock_hold(sk); + goto exit; + } + + sk = NULL; +exit: + read_unlock_bh(&ping_table.lock); + + return sk; +} + +static void inet_get_ping_group_range_net(struct net *net, gid_t *low, + gid_t *high) +{ + gid_t *data = net->ipv4.sysctl_ping_group_range; + unsigned seq; + do { + seq = read_seqbegin(&sysctl_local_ports.lock); + + *low = data[0]; + *high = data[1]; + } while (read_seqretry(&sysctl_local_ports.lock, seq)); +} + + +static int ping_init_sock(struct sock *sk) +{ + struct net *net = sock_net(sk); + gid_t group = current_egid(); + gid_t range[2]; + struct group_info *group_info = get_current_groups(); + int i, j, count = group_info->ngroups; + + inet_get_ping_group_range_net(net, range, range+1); + if (range[0] <= group && group <= range[1]) + return 0; + + for (i = 0; i < group_info->nblocks; i++) { + int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); + + for (j = 0; j < cp_count; j++) { + group = group_info->blocks[i][j]; + if (range[0] <= group && group <= range[1]) + return 0; + } + + count -= cp_count; + } + + return -EACCES; +} + +static void ping_close(struct sock *sk, long timeout) +{ + pr_debug("ping_close(sk=%p,sk->num=%u)\n", + inet_sk(sk), inet_sk(sk)->inet_num); + pr_debug("isk->refcnt = %d\n", sk->sk_refcnt.counter); + + sk_common_release(sk); +} + +/* + * We need our own bind because there are no privileged id's == local ports. + * Moreover, we don't allow binding to multi- and broadcast addresses. + */ + +static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +{ + struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; + struct inet_sock *isk = inet_sk(sk); + unsigned short snum; + int chk_addr_ret; + int err; + + if (addr_len < sizeof(struct sockaddr_in)) + return -EINVAL; + + pr_debug("ping_v4_bind(sk=%p,sa_addr=%08x,sa_port=%d)\n", + sk, addr->sin_addr.s_addr, ntohs(addr->sin_port)); + + chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); + if (addr->sin_addr.s_addr == INADDR_ANY) + chk_addr_ret = RTN_LOCAL; + + if ((sysctl_ip_nonlocal_bind == 0 && + isk->freebind == 0 && isk->transparent == 0 && + chk_addr_ret != RTN_LOCAL) || + chk_addr_ret == RTN_MULTICAST || + chk_addr_ret == RTN_BROADCAST) + return -EADDRNOTAVAIL; + + lock_sock(sk); + + err = -EINVAL; + if (isk->inet_num != 0) + goto out; + + err = -EADDRINUSE; + isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr; + snum = ntohs(addr->sin_port); + if (ping_v4_get_port(sk, snum) != 0) { + isk->inet_saddr = isk->inet_rcv_saddr = 0; + goto out; + } + + pr_debug("after bind(): num = %d, daddr = %ld, dif = %d\n", + (int)isk->inet_num, + (unsigned long) isk->inet_rcv_saddr, + (int)sk->sk_bound_dev_if); + + err = 0; + if (isk->inet_rcv_saddr) + sk->sk_userlocks |= SOCK_BINDADDR_LOCK; + if (snum) + sk->sk_userlocks |= SOCK_BINDPORT_LOCK; + isk->inet_sport = htons(isk->inet_num); + isk->inet_daddr = 0; + isk->inet_dport = 0; + sk_dst_reset(sk); +out: + release_sock(sk); + pr_debug("ping_v4_bind -> %d\n", err); + return err; +} + +/* + * Is this a supported type of ICMP message? + */ + +static inline int ping_supported(int type, int code) +{ + if (type == ICMP_ECHO && code == 0) + return 1; + return 0; +} + +/* + * This routine is called by the ICMP module when it gets some + * sort of error condition. + */ + +static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +void ping_err(struct sk_buff *skb, u32 info) +{ + struct iphdr *iph = (struct iphdr *)skb->data; + struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); + struct inet_sock *inet_sock; + int type = icmph->type; + int code = icmph->code; + struct net *net = dev_net(skb->dev); + struct sock *sk; + int harderr; + int err; + + /* We assume the packet has already been checked by icmp_unreach */ + + if (!ping_supported(icmph->type, icmph->code)) + return; + + pr_debug("ping_err(type=%04x,code=%04x,id=%04x,seq=%04x)\n", type, + code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); + + sk = ping_v4_lookup(net, iph->daddr, iph->saddr, + ntohs(icmph->un.echo.id), skb->dev->ifindex); + if (sk == NULL) { + ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); + pr_debug("no socket, dropping\n"); + return; /* No socket for error */ + } + pr_debug("err on socket %p\n", sk); + + err = 0; + harderr = 0; + inet_sock = inet_sk(sk); + + switch (type) { + default: + case ICMP_TIME_EXCEEDED: + err = EHOSTUNREACH; + break; + case ICMP_SOURCE_QUENCH: + /* This is not a real error but ping wants to see it. + * Report it with some fake errno. */ + err = EREMOTEIO; + break; + case ICMP_PARAMETERPROB: + err = EPROTO; + harderr = 1; + break; + case ICMP_DEST_UNREACH: + if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ + if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) { + err = EMSGSIZE; + harderr = 1; + break; + } + goto out; + } + err = EHOSTUNREACH; + if (code <= NR_ICMP_UNREACH) { + harderr = icmp_err_convert[code].fatal; + err = icmp_err_convert[code].errno; + } + break; + case ICMP_REDIRECT: + /* See ICMP_SOURCE_QUENCH */ + err = EREMOTEIO; + break; + } + + /* + * RFC1122: OK. Passes ICMP errors back to application, as per + * 4.1.3.3. + */ + if (!inet_sock->recverr) { + if (!harderr || sk->sk_state != TCP_ESTABLISHED) + goto out; + } else { + ip_icmp_error(sk, skb, err, 0 /* no remote port */, + info, (u8 *)icmph); + } + sk->sk_err = err; + sk->sk_error_report(sk); +out: + sock_put(sk); +} + +/* + * Copy and checksum an ICMP Echo packet from user space into a buffer. + */ + +struct pingfakehdr { + struct icmphdr icmph; + struct iovec *iov; + u32 wcheck; +}; + +static int ping_getfrag(void *from, char * to, + int offset, int fraglen, int odd, struct sk_buff *skb) +{ + struct pingfakehdr *pfh = (struct pingfakehdr *)from; + + if (offset == 0) { + if (fraglen < sizeof(struct icmphdr)) + BUG(); + if (csum_partial_copy_fromiovecend(to + sizeof(struct icmphdr), + pfh->iov, 0, fraglen - sizeof(struct icmphdr), + &pfh->wcheck)) + return -EFAULT; + + return 0; + } + if (offset < sizeof(struct icmphdr)) + BUG(); + if (csum_partial_copy_fromiovecend + (to, pfh->iov, offset - sizeof(struct icmphdr), + fraglen, &pfh->wcheck)) + return -EFAULT; + return 0; +} + +static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, + struct flowi4 *fl4) +{ + struct sk_buff *skb = skb_peek(&sk->sk_write_queue); + + pfh->wcheck = csum_partial((char *)&pfh->icmph, + sizeof(struct icmphdr), pfh->wcheck); + pfh->icmph.checksum = csum_fold(pfh->wcheck); + memcpy(icmp_hdr(skb), &pfh->icmph, sizeof(struct icmphdr)); + skb->ip_summed = CHECKSUM_NONE; + return ip_push_pending_frames(sk, fl4); +} + +static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len) +{ + struct net *net = sock_net(sk); + struct flowi4 fl4; + struct inet_sock *inet = inet_sk(sk); + struct ipcm_cookie ipc; + struct icmphdr user_icmph; + struct pingfakehdr pfh; + struct rtable *rt = NULL; + struct ip_options_data opt_copy; + int free = 0; + u32 saddr, daddr, faddr; + u8 tos; + int err; + + pr_debug("ping_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); + + + if (len > 0xFFFF) + return -EMSGSIZE; + + /* + * Check the flags. + */ + + /* Mirror BSD error message compatibility */ + if (msg->msg_flags & MSG_OOB) + return -EOPNOTSUPP; + + /* + * Fetch the ICMP header provided by the userland. + * iovec is modified! + */ + + if (memcpy_fromiovec((u8 *)&user_icmph, msg->msg_iov, + sizeof(struct icmphdr))) + return -EFAULT; + if (!ping_supported(user_icmph.type, user_icmph.code)) + return -EINVAL; + + /* + * Get and verify the address. + */ + + if (msg->msg_name) { + struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name; + if (msg->msg_namelen < sizeof(*usin)) + return -EINVAL; + if (usin->sin_family != AF_INET) + return -EINVAL; + daddr = usin->sin_addr.s_addr; + /* no remote port */ + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + daddr = inet->inet_daddr; + /* no remote port */ + } + + ipc.addr = inet->inet_saddr; + ipc.opt = NULL; + ipc.oif = sk->sk_bound_dev_if; + ipc.tx_flags = 0; + err = sock_tx_timestamp(sk, &ipc.tx_flags); + if (err) + return err; + + if (msg->msg_controllen) { + err = ip_cmsg_send(sock_net(sk), msg, &ipc); + if (err) + return err; + if (ipc.opt) + free = 1; + } + if (!ipc.opt) { + struct ip_options_rcu *inet_opt; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + memcpy(&opt_copy, inet_opt, + sizeof(*inet_opt) + inet_opt->opt.optlen); + ipc.opt = &opt_copy.opt; + } + rcu_read_unlock(); + } + + saddr = ipc.addr; + ipc.addr = faddr = daddr; + + if (ipc.opt && ipc.opt->opt.srr) { + if (!daddr) + return -EINVAL; + faddr = ipc.opt->opt.faddr; + } + tos = RT_TOS(inet->tos); + if (sock_flag(sk, SOCK_LOCALROUTE) || + (msg->msg_flags & MSG_DONTROUTE) || + (ipc.opt && ipc.opt->opt.is_strictroute)) { + tos |= RTO_ONLINK; + } + + if (ipv4_is_multicast(daddr)) { + if (!ipc.oif) + ipc.oif = inet->mc_index; + if (!saddr) + saddr = inet->mc_addr; + } + + flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, + RT_SCOPE_UNIVERSE, sk->sk_protocol, + inet_sk_flowi_flags(sk), faddr, saddr, 0, 0); + + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); + rt = ip_route_output_flow(net, &fl4, sk); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + rt = NULL; + if (err == -ENETUNREACH) + IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + goto out; + } + + err = -EACCES; + if ((rt->rt_flags & RTCF_BROADCAST) && + !sock_flag(sk, SOCK_BROADCAST)) + goto out; + + if (msg->msg_flags & MSG_CONFIRM) + goto do_confirm; +back_from_confirm: + + if (!ipc.addr) + ipc.addr = fl4.daddr; + + lock_sock(sk); + + pfh.icmph.type = user_icmph.type; /* already checked */ + pfh.icmph.code = user_icmph.code; /* ditto */ + pfh.icmph.checksum = 0; + pfh.icmph.un.echo.id = inet->inet_sport; + pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence; + pfh.iov = msg->msg_iov; + pfh.wcheck = 0; + + err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len, + 0, &ipc, &rt, msg->msg_flags); + if (err) + ip_flush_pending_frames(sk); + else + err = ping_push_pending_frames(sk, &pfh, &fl4); + release_sock(sk); + +out: + ip_rt_put(rt); + if (free) + kfree(ipc.opt); + if (!err) { + icmp_out_count(sock_net(sk), user_icmph.type); + return len; + } + return err; + +do_confirm: + dst_confirm(&rt->dst); + if (!(msg->msg_flags & MSG_PROBE) || len) + goto back_from_confirm; + err = 0; + goto out; +} + +static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len, int noblock, int flags, int *addr_len) +{ + struct inet_sock *isk = inet_sk(sk); + struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + struct sk_buff *skb; + int copied, err; + + pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); + + if (flags & MSG_OOB) + goto out; + + if (addr_len) + *addr_len = sizeof(*sin); + + if (flags & MSG_ERRQUEUE) + return ip_recv_error(sk, msg, len); + + skb = skb_recv_datagram(sk, flags, noblock, &err); + if (!skb) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + + /* Don't bother checking the checksum */ + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto done; + + sock_recv_timestamp(msg, sk, skb); + + /* Copy the address. */ + if (sin) { + sin->sin_family = AF_INET; + sin->sin_port = 0 /* skb->h.uh->source */; + sin->sin_addr.s_addr = ip_hdr(skb)->saddr; + memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + } + if (isk->cmsg_flags) + ip_cmsg_recv(msg, skb); + err = copied; + +done: + skb_free_datagram(sk, skb); +out: + pr_debug("ping_recvmsg -> %d\n", err); + return err; +} + +static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", + inet_sk(sk), inet_sk(sk)->inet_num, skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { + ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_INERRORS); + kfree_skb(skb); + pr_debug("ping_queue_rcv_skb -> failed\n"); + return -1; + } + return 0; +} + + +/* + * All we need to do is get the socket. + */ + +void ping_rcv(struct sk_buff *skb) +{ + struct sock *sk; + struct net *net = dev_net(skb->dev); + struct iphdr *iph = ip_hdr(skb); + struct icmphdr *icmph = icmp_hdr(skb); + u32 saddr = iph->saddr; + u32 daddr = iph->daddr; + + /* We assume the packet has already been checked by icmp_rcv */ + + pr_debug("ping_rcv(skb=%p,id=%04x,seq=%04x)\n", + skb, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); + + /* Push ICMP header back */ + skb_push(skb, skb->data - (u8 *)icmph); + + sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id), + skb->dev->ifindex); + if (sk != NULL) { + pr_debug("rcv on socket %p\n", sk); + ping_queue_rcv_skb(sk, skb_get(skb)); + sock_put(sk); + return; + } + pr_debug("no socket, dropping\n"); + + /* We're called from icmp_rcv(). kfree_skb() is done there. */ +} + +struct proto ping_prot = { + .name = "PING", + .owner = THIS_MODULE, + .init = ping_init_sock, + .close = ping_close, + .connect = ip4_datagram_connect, + .disconnect = udp_disconnect, + .setsockopt = ip_setsockopt, + .getsockopt = ip_getsockopt, + .sendmsg = ping_sendmsg, + .recvmsg = ping_recvmsg, + .bind = ping_bind, + .backlog_rcv = ping_queue_rcv_skb, + .hash = ping_v4_hash, + .unhash = ping_v4_unhash, + .get_port = ping_v4_get_port, + .obj_size = sizeof(struct inet_sock), +}; +EXPORT_SYMBOL(ping_prot); + +#ifdef CONFIG_PROC_FS + +static struct sock *ping_get_first(struct seq_file *seq, int start) +{ + struct sock *sk; + struct ping_iter_state *state = seq->private; + struct net *net = seq_file_net(seq); + + for (state->bucket = start; state->bucket < PING_HTABLE_SIZE; + ++state->bucket) { + struct hlist_nulls_node *node; + struct hlist_nulls_head *hslot; + + hslot = &ping_table.hash[state->bucket]; + + if (hlist_nulls_empty(hslot)) + continue; + + sk_nulls_for_each(sk, node, hslot) { + if (net_eq(sock_net(sk), net)) + goto found; + } + } + sk = NULL; +found: + return sk; +} + +static struct sock *ping_get_next(struct seq_file *seq, struct sock *sk) +{ + struct ping_iter_state *state = seq->private; + struct net *net = seq_file_net(seq); + + do { + sk = sk_nulls_next(sk); + } while (sk && (!net_eq(sock_net(sk), net))); + + if (!sk) + return ping_get_first(seq, state->bucket + 1); + return sk; +} + +static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) +{ + struct sock *sk = ping_get_first(seq, 0); + + if (sk) + while (pos && (sk = ping_get_next(seq, sk)) != NULL) + --pos; + return pos ? NULL : sk; +} + +static void *ping_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct ping_iter_state *state = seq->private; + state->bucket = 0; + + read_lock_bh(&ping_table.lock); + + return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; +} + +static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct sock *sk; + + if (v == SEQ_START_TOKEN) + sk = ping_get_idx(seq, 0); + else + sk = ping_get_next(seq, v); + + ++*pos; + return sk; +} + +static void ping_seq_stop(struct seq_file *seq, void *v) +{ + read_unlock_bh(&ping_table.lock); +} + +static void ping_format_sock(struct sock *sp, struct seq_file *f, + int bucket, int *len) +{ + struct inet_sock *inet = inet_sk(sp); + __be32 dest = inet->inet_daddr; + __be32 src = inet->inet_rcv_saddr; + __u16 destp = ntohs(inet->inet_dport); + __u16 srcp = ntohs(inet->inet_sport); + + seq_printf(f, "%5d: %08X:%04X %08X:%04X" + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d%n", + bucket, src, srcp, dest, destp, sp->sk_state, + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), + 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), + atomic_read(&sp->sk_refcnt), sp, + atomic_read(&sp->sk_drops), len); +} + +static int ping_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_printf(seq, "%-127s\n", + " sl local_address rem_address st tx_queue " + "rx_queue tr tm->when retrnsmt uid timeout " + "inode ref pointer drops"); + else { + struct ping_iter_state *state = seq->private; + int len; + + ping_format_sock(v, seq, state->bucket, &len); + seq_printf(seq, "%*s\n", 127 - len, ""); + } + return 0; +} + +static const struct seq_operations ping_seq_ops = { + .show = ping_seq_show, + .start = ping_seq_start, + .next = ping_seq_next, + .stop = ping_seq_stop, +}; + +static int ping_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ping_seq_ops, + sizeof(struct ping_iter_state)); +} + +static const struct file_operations ping_seq_fops = { + .open = ping_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static int ping_proc_register(struct net *net) +{ + struct proc_dir_entry *p; + int rc = 0; + + p = proc_net_fops_create(net, "icmp", S_IRUGO, &ping_seq_fops); + if (!p) + rc = -ENOMEM; + return rc; +} + +static void ping_proc_unregister(struct net *net) +{ + proc_net_remove(net, "icmp"); +} + + +static int __net_init ping_proc_init_net(struct net *net) +{ + return ping_proc_register(net); +} + +static void __net_exit ping_proc_exit_net(struct net *net) +{ + ping_proc_unregister(net); +} + +static struct pernet_operations ping_net_ops = { + .init = ping_proc_init_net, + .exit = ping_proc_exit_net, +}; + +int __init ping_proc_init(void) +{ + return register_pernet_subsys(&ping_net_ops); +} + +void ping_proc_exit(void) +{ + unregister_pernet_subsys(&ping_net_ops); +} + +#endif + +void __init ping_init(void) +{ + int i; + + for (i = 0; i < PING_HTABLE_SIZE; i++) + INIT_HLIST_NULLS_HEAD(&ping_table.hash[i], i); + rwlock_init(&ping_table.lock); +} diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 2d3c72e5bbbf..c9893d43242e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -154,7 +154,7 @@ static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb) * RFC 1122: SHOULD pass TOS value up to the transport layer. * -> It does. And not only TOS, but all IP header. */ -static int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash) +static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) { struct sock *sk; struct hlist_head *head; @@ -247,7 +247,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) } if (inet->recverr) { - struct iphdr *iph = (struct iphdr *)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; u8 *payload = skb->data + (iph->ihl << 2); if (inet->hdrincl) @@ -265,7 +265,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) { int hash; struct sock *raw_sk; - struct iphdr *iph; + const struct iphdr *iph; struct net *net; hash = protocol & (RAW_HTABLE_SIZE - 1); @@ -273,7 +273,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) read_lock(&raw_v4_hashinfo.lock); raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]); if (raw_sk != NULL) { - iph = (struct iphdr *)skb->data; + iph = (const struct iphdr *)skb->data; net = dev_net(skb->dev); while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol, @@ -281,7 +281,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) skb->dev->ifindex)) != NULL) { raw_err(raw_sk, skb, info); raw_sk = sk_next(raw_sk); - iph = (struct iphdr *)skb->data; + iph = (const struct iphdr *)skb->data; } } read_unlock(&raw_v4_hashinfo.lock); @@ -314,9 +314,10 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) return 0; } -static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, - struct rtable **rtp, - unsigned int flags) +static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, + void *from, size_t length, + struct rtable **rtp, + unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); @@ -327,7 +328,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, struct rtable *rt = *rtp; if (length > rt->dst.dev->mtu) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, + ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, rt->dst.dev->mtu); return -EMSGSIZE; } @@ -372,7 +373,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, if (iphlen >= sizeof(*iph)) { if (!iph->saddr) - iph->saddr = rt->rt_src; + iph->saddr = fl4->saddr; iph->check = 0; iph->tot_len = htons(length); if (!iph->id) @@ -455,11 +456,13 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct inet_sock *inet = inet_sk(sk); struct ipcm_cookie ipc; struct rtable *rt = NULL; + struct flowi4 fl4; int free = 0; __be32 daddr; __be32 saddr; u8 tos; int err; + struct ip_options_data opt_copy; err = -EMSGSIZE; if (len > 0xFFFF) @@ -520,8 +523,18 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, saddr = ipc.addr; ipc.addr = daddr; - if (!ipc.opt) - ipc.opt = inet->opt; + if (!ipc.opt) { + struct ip_options_rcu *inet_opt; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + memcpy(&opt_copy, inet_opt, + sizeof(*inet_opt) + inet_opt->opt.optlen); + ipc.opt = &opt_copy.opt; + } + rcu_read_unlock(); + } if (ipc.opt) { err = -EINVAL; @@ -530,10 +543,10 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, */ if (inet->hdrincl) goto done; - if (ipc.opt->srr) { + if (ipc.opt->opt.srr) { if (!daddr) goto done; - daddr = ipc.opt->faddr; + daddr = ipc.opt->opt.faddr; } } tos = RT_CONN_FLAGS(sk); @@ -547,31 +560,23 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, saddr = inet->mc_addr; } - { - struct flowi4 fl4 = { - .flowi4_oif = ipc.oif, - .flowi4_mark = sk->sk_mark, - .daddr = daddr, - .saddr = saddr, - .flowi4_tos = tos, - .flowi4_proto = (inet->hdrincl ? - IPPROTO_RAW : - sk->sk_protocol), - .flowi4_flags = FLOWI_FLAG_CAN_SLEEP, - }; - if (!inet->hdrincl) { - err = raw_probe_proto_opt(&fl4, msg); - if (err) - goto done; - } + flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, + RT_SCOPE_UNIVERSE, + inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + FLOWI_FLAG_CAN_SLEEP, daddr, saddr, 0, 0); - security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); - rt = ip_route_output_flow(sock_net(sk), &fl4, sk); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - rt = NULL; + if (!inet->hdrincl) { + err = raw_probe_proto_opt(&fl4, msg); + if (err) goto done; - } + } + + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + rt = NULL; + goto done; } err = -EACCES; @@ -583,19 +588,20 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, back_from_confirm: if (inet->hdrincl) - err = raw_send_hdrinc(sk, msg->msg_iov, len, - &rt, msg->msg_flags); + err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len, + &rt, msg->msg_flags); else { if (!ipc.addr) - ipc.addr = rt->rt_dst; + ipc.addr = fl4.daddr; lock_sock(sk); - err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0, - &ipc, &rt, msg->msg_flags); + err = ip_append_data(sk, &fl4, ip_generic_getfrag, + msg->msg_iov, len, 0, + &ipc, &rt, msg->msg_flags); if (err) ip_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) { - err = ip_push_pending_frames(sk); + err = ip_push_pending_frames(sk, &fl4); if (err == -ENOBUFS && !inet->recverr) err = 0; } @@ -622,7 +628,7 @@ do_confirm: static void raw_close(struct sock *sk, long timeout) { /* - * Raw sockets may have direct kernel refereneces. Kill them. + * Raw sockets may have direct kernel references. Kill them. */ ip_ra_control(sk, 0, NULL); @@ -973,7 +979,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) srcp = inet->inet_num; seq_printf(seq, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", i, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4b0c81180804..52b0b956508b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -156,7 +156,7 @@ static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) u32 *p = NULL; if (!rt->peer) - rt_bind_peer(rt, 1); + rt_bind_peer(rt, rt->rt_dst, 1); peer = rt->peer; if (peer) { @@ -424,7 +424,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) dst_metric(&r->dst, RTAX_WINDOW), (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) + dst_metric(&r->dst, RTAX_RTTVAR)), - r->rt_tos, + r->rt_key_tos, r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1, r->dst.hh ? (r->dst.hh->hh_output == dev_queue_xmit) : 0, @@ -724,7 +724,7 @@ static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) return (((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) | ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | (rt1->rt_mark ^ rt2->rt_mark) | - (rt1->rt_tos ^ rt2->rt_tos) | + (rt1->rt_key_tos ^ rt2->rt_key_tos) | (rt1->rt_oif ^ rt2->rt_oif) | (rt1->rt_iif ^ rt2->rt_iif)) == 0; } @@ -821,7 +821,7 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) } /* - * Pertubation of rt_genid by a small quantity [1..256] + * Perturbation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() * many times (2^24) without giving recent rt_genid. * Jenkins hash is strong enough that litle changes of rt_genid are OK. @@ -968,10 +968,6 @@ static int rt_garbage_collect(struct dst_ops *ops) break; expire >>= 1; -#if RT_CACHE_DEBUG >= 2 - printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire, - dst_entries_get_fast(&ipv4_dst_ops), goal, i); -#endif if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size) goto out; @@ -992,10 +988,6 @@ work_done: 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, - dst_entries_get_fast(&ipv4_dst_ops), goal, rover); -#endif out: return 0; } @@ -1179,19 +1171,9 @@ restart: rt->dst.rt_next = rt_hash_table[hash].chain; -#if RT_CACHE_DEBUG >= 2 - if (rt->dst.rt_next) { - struct rtable *trt; - printk(KERN_DEBUG "rt_cache @%02x: %pI4", - hash, &rt->rt_dst); - for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next) - printk(" . %pI4", &trt->rt_dst); - printk("\n"); - } -#endif /* * Since lookup is lockfree, we must make sure - * previous writes to rt are comitted to memory + * previous writes to rt are committed to memory * before making rt visible to other CPUS. */ rcu_assign_pointer(rt_hash_table[hash].chain, rt); @@ -1211,11 +1193,11 @@ static u32 rt_peer_genid(void) return atomic_read(&__rt_peer_genid); } -void rt_bind_peer(struct rtable *rt, int create) +void rt_bind_peer(struct rtable *rt, __be32 daddr, int create) { struct inet_peer *peer; - peer = inet_getpeer_v4(rt->rt_dst, create); + peer = inet_getpeer_v4(daddr, create); if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL) inet_putpeer(peer); @@ -1249,7 +1231,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) if (rt) { if (rt->peer == NULL) - rt_bind_peer(rt, 1); + rt_bind_peer(rt, rt->rt_dst, 1); /* If peer is attached to destination, it is never detached, so that we need not to grab a lock to dereference it. @@ -1347,10 +1329,6 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) unsigned hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, rt->rt_oif, rt_genid(dev_net(dst->dev))); -#if RT_CACHE_DEBUG >= 1 - printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped\n", - &rt->rt_dst, rt->rt_tos); -#endif rt_del(hash, rt); ret = NULL; } else if (rt->peer && @@ -1399,7 +1377,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) rcu_read_unlock(); if (!rt->peer) - rt_bind_peer(rt, 1); + rt_bind_peer(rt, rt->rt_dst, 1); peer = rt->peer; if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); @@ -1435,7 +1413,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) peer->rate_tokens == ip_rt_redirect_number && net_ratelimit()) printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n", - &rt->rt_src, rt->rt_iif, + &ip_hdr(skb)->saddr, rt->rt_iif, &rt->rt_dst, &rt->rt_gateway); #endif } @@ -1467,7 +1445,7 @@ static int ip_error(struct sk_buff *skb) } if (!rt->peer) - rt_bind_peer(rt, 1); + rt_bind_peer(rt, rt->rt_dst, 1); peer = rt->peer; send = true; @@ -1507,7 +1485,7 @@ static inline unsigned short guess_mtu(unsigned short old_mtu) return 68; } -unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, +unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph, unsigned short new_mtu, struct net_device *dev) { @@ -1574,7 +1552,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) dst_confirm(dst); if (!rt->peer) - rt_bind_peer(rt, 1); + rt_bind_peer(rt, rt->rt_dst, 1); peer = rt->peer; if (peer) { if (mtu < ip_rt_min_pmtu) @@ -1631,7 +1609,7 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) struct inet_peer *peer; if (!rt->peer) - rt_bind_peer(rt, 0); + rt_bind_peer(rt, rt->rt_dst, 0); peer = rt->peer; if (peer && peer->pmtu_expires) @@ -1687,6 +1665,7 @@ static int ip_rt_bug(struct sk_buff *skb) &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, skb->dev ? skb->dev->name : "?"); kfree_skb(skb); + WARN_ON(1); return 0; } @@ -1699,22 +1678,26 @@ static int ip_rt_bug(struct sk_buff *skb) in IP options! */ -void ip_rt_get_source(u8 *addr, struct rtable *rt) +void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) { __be32 src; - struct fib_result res; if (rt_is_output_route(rt)) - src = rt->rt_src; + src = ip_hdr(skb)->saddr; else { - struct flowi4 fl4 = { - .daddr = rt->rt_key_dst, - .saddr = rt->rt_key_src, - .flowi4_tos = rt->rt_tos, - .flowi4_oif = rt->rt_oif, - .flowi4_iif = rt->rt_iif, - .flowi4_mark = rt->rt_mark, - }; + struct fib_result res; + struct flowi4 fl4; + struct iphdr *iph; + + iph = ip_hdr(skb); + + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = iph->daddr; + fl4.saddr = iph->saddr; + fl4.flowi4_tos = iph->tos; + fl4.flowi4_oif = rt->dst.dev->ifindex; + fl4.flowi4_iif = skb->dev->ifindex; + fl4.flowi4_mark = skb->mark; rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0) @@ -1767,7 +1750,7 @@ static unsigned int ipv4_default_mtu(const struct dst_entry *dst) return mtu; } -static void rt_init_metrics(struct rtable *rt, const struct flowi4 *oldflp4, +static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, struct fib_info *fi) { struct inet_peer *peer; @@ -1776,7 +1759,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *oldflp4, /* If a peer entry exists for this destination, we must hook * it up in order to get at cached metrics. */ - if (oldflp4 && (oldflp4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS)) + if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS)) create = 1; rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create); @@ -1803,7 +1786,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *oldflp4, } } -static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4, +static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4, const struct fib_result *res, struct fib_info *fi, u16 type, u32 itag) { @@ -1813,7 +1796,7 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4, if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = FIB_RES_GW(*res); - rt_init_metrics(rt, oldflp4, fi); + rt_init_metrics(rt, fl4, fi); #ifdef CONFIG_IP_ROUTE_CLASSID dst->tclassid = FIB_RES_NH(*res).nh_tclassid; #endif @@ -1830,20 +1813,15 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4, #endif set_class_tag(rt, itag); #endif - rt->rt_type = type; } -static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm) +static struct rtable *rt_dst_alloc(struct net_device *dev, + bool nopolicy, bool noxfrm) { - struct rtable *rt = dst_alloc(&ipv4_dst_ops, 1); - if (rt) { - rt->dst.obsolete = -1; - - rt->dst.flags = DST_HOST | - (nopolicy ? DST_NOPOLICY : 0) | - (noxfrm ? DST_NOXFRM : 0); - } - return rt; + return dst_alloc(&ipv4_dst_ops, dev, 1, -1, + DST_HOST | + (nopolicy ? DST_NOPOLICY : 0) | + (noxfrm ? DST_NOXFRM : 0)); } /* called in rcu_read_lock() section */ @@ -1871,35 +1849,38 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto e_inval; spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); } else { - err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst, - &itag, 0); + err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst, + &itag); if (err < 0) goto e_err; } - rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false); + rth = rt_dst_alloc(init_net.loopback_dev, + IN_DEV_CONF_GET(in_dev, NOPOLICY), false); if (!rth) goto e_nobufs; +#ifdef CONFIG_IP_ROUTE_CLASSID + rth->dst.tclassid = itag; +#endif rth->dst.output = ip_rt_bug; rth->rt_key_dst = daddr; - rth->rt_dst = daddr; - rth->rt_tos = tos; - rth->rt_mark = skb->mark; rth->rt_key_src = saddr; + rth->rt_genid = rt_genid(dev_net(dev)); + rth->rt_flags = RTCF_MULTICAST; + rth->rt_type = RTN_MULTICAST; + rth->rt_key_tos = tos; + rth->rt_dst = daddr; rth->rt_src = saddr; -#ifdef CONFIG_IP_ROUTE_CLASSID - rth->dst.tclassid = itag; -#endif + rth->rt_route_iif = dev->ifindex; rth->rt_iif = dev->ifindex; - rth->dst.dev = init_net.loopback_dev; - dev_hold(rth->dst.dev); rth->rt_oif = 0; + rth->rt_mark = skb->mark; rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; - rth->rt_genid = rt_genid(dev_net(dev)); - rth->rt_flags = RTCF_MULTICAST; - rth->rt_type = RTN_MULTICAST; + rth->rt_peer_genid = 0; + rth->peer = NULL; + rth->fi = NULL; if (our) { rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; @@ -1980,8 +1961,8 @@ static int __mkroute_input(struct sk_buff *skb, } - err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(*res), - in_dev->dev, &spec_dst, &itag, skb->mark); + err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res), + in_dev->dev, &spec_dst, &itag); if (err < 0) { ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); @@ -2012,7 +1993,8 @@ static int __mkroute_input(struct sk_buff *skb, } } - rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), + rth = rt_dst_alloc(out_dev->dev, + IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; @@ -2020,26 +2002,28 @@ static int __mkroute_input(struct sk_buff *skb, } rth->rt_key_dst = daddr; - rth->rt_dst = daddr; - rth->rt_tos = tos; - rth->rt_mark = skb->mark; rth->rt_key_src = saddr; + rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); + rth->rt_flags = flags; + rth->rt_type = res->type; + rth->rt_key_tos = tos; + rth->rt_dst = daddr; rth->rt_src = saddr; - rth->rt_gateway = daddr; + rth->rt_route_iif = in_dev->dev->ifindex; rth->rt_iif = in_dev->dev->ifindex; - rth->dst.dev = (out_dev)->dev; - dev_hold(rth->dst.dev); rth->rt_oif = 0; + rth->rt_mark = skb->mark; + rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; + rth->rt_peer_genid = 0; + rth->peer = NULL; + rth->fi = NULL; rth->dst.input = ip_forward; rth->dst.output = ip_output; - rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag); - rth->rt_flags = flags; - *result = rth; err = 0; cleanup: @@ -2148,9 +2132,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto brd_input; if (res.type == RTN_LOCAL) { - err = fib_validate_source(saddr, daddr, tos, + err = fib_validate_source(skb, saddr, daddr, tos, net->loopback_dev->ifindex, - dev, &spec_dst, &itag, skb->mark); + dev, &spec_dst, &itag); if (err < 0) goto martian_source_keep_err; if (err) @@ -2174,8 +2158,8 @@ brd_input: if (ipv4_is_zeronet(saddr)) spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); else { - err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst, - &itag, skb->mark); + err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst, + &itag); if (err < 0) goto martian_source_keep_err; if (err) @@ -2186,35 +2170,42 @@ brd_input: RT_CACHE_STAT_INC(in_brd); local_input: - rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false); + rth = rt_dst_alloc(net->loopback_dev, + IN_DEV_CONF_GET(in_dev, NOPOLICY), false); if (!rth) goto e_nobufs; + rth->dst.input= ip_local_deliver; rth->dst.output= ip_rt_bug; - rth->rt_genid = rt_genid(net); +#ifdef CONFIG_IP_ROUTE_CLASSID + rth->dst.tclassid = itag; +#endif rth->rt_key_dst = daddr; - rth->rt_dst = daddr; - rth->rt_tos = tos; - rth->rt_mark = skb->mark; rth->rt_key_src = saddr; + rth->rt_genid = rt_genid(net); + rth->rt_flags = flags|RTCF_LOCAL; + rth->rt_type = res.type; + rth->rt_key_tos = tos; + rth->rt_dst = daddr; rth->rt_src = saddr; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif + rth->rt_route_iif = dev->ifindex; rth->rt_iif = dev->ifindex; - rth->dst.dev = net->loopback_dev; - dev_hold(rth->dst.dev); + rth->rt_oif = 0; + rth->rt_mark = skb->mark; rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; - rth->dst.input= ip_local_deliver; - rth->rt_flags = flags|RTCF_LOCAL; + rth->rt_peer_genid = 0; + rth->peer = NULL; + rth->fi = NULL; if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } - rth->rt_type = res.type; hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net)); rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif); err = 0; @@ -2285,7 +2276,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, ((__force u32)rth->rt_key_src ^ (__force u32)saddr) | (rth->rt_iif ^ iif) | rth->rt_oif | - (rth->rt_tos ^ tos)) == 0 && + (rth->rt_key_tos ^ tos)) == 0 && rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { @@ -2346,12 +2337,12 @@ EXPORT_SYMBOL(ip_route_input_common); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, - const struct flowi4 *oldflp4, - struct net_device *dev_out, + __be32 orig_daddr, __be32 orig_saddr, + int orig_oif, struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; - u32 tos = RT_FL_TOS(oldflp4); + u32 tos = RT_FL_TOS(fl4); struct in_device *in_dev; u16 type = res->type; struct rtable *rth; @@ -2378,8 +2369,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, fi = NULL; } else if (type == RTN_MULTICAST) { flags |= RTCF_MULTICAST | RTCF_LOCAL; - if (!ip_check_mc_rcu(in_dev, oldflp4->daddr, oldflp4->saddr, - oldflp4->flowi4_proto)) + if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, + fl4->flowi4_proto)) flags &= ~RTCF_LOCAL; /* If multicast route do not exist use * default one, but do not gateway in this case. @@ -2389,28 +2380,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res, fi = NULL; } - rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), + rth = rt_dst_alloc(dev_out, + IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(in_dev, NOXFRM)); if (!rth) return ERR_PTR(-ENOBUFS); - rth->rt_key_dst = oldflp4->daddr; - rth->rt_tos = tos; - rth->rt_key_src = oldflp4->saddr; - rth->rt_oif = oldflp4->flowi4_oif; - rth->rt_mark = oldflp4->flowi4_mark; + rth->dst.output = ip_output; + + rth->rt_key_dst = orig_daddr; + rth->rt_key_src = orig_saddr; + rth->rt_genid = rt_genid(dev_net(dev_out)); + rth->rt_flags = flags; + rth->rt_type = type; + rth->rt_key_tos = tos; rth->rt_dst = fl4->daddr; rth->rt_src = fl4->saddr; - rth->rt_iif = 0; - /* get references to the devices that are to be hold by the routing - cache entry */ - rth->dst.dev = dev_out; - dev_hold(dev_out); + rth->rt_route_iif = 0; + rth->rt_iif = orig_oif ? : dev_out->ifindex; + rth->rt_oif = orig_oif; + rth->rt_mark = fl4->flowi4_mark; rth->rt_gateway = fl4->daddr; rth->rt_spec_dst= fl4->saddr; - - rth->dst.output=ip_output; - rth->rt_genid = rt_genid(dev_net(dev_out)); + rth->rt_peer_genid = 0; + rth->peer = NULL; + rth->fi = NULL; RT_CACHE_STAT_INC(out_slow_tot); @@ -2428,7 +2422,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, #ifdef CONFIG_IP_MROUTE if (type == RTN_MULTICAST) { if (IN_DEV_MFORWARD(in_dev) && - !ipv4_is_local_multicast(oldflp4->daddr)) { + !ipv4_is_local_multicast(fl4->daddr)) { rth->dst.input = ip_mr_input; rth->dst.output = ip_mc_output; } @@ -2436,9 +2430,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, #endif } - rt_set_nexthop(rth, oldflp4, res, fi, type, 0); + rt_set_nexthop(rth, fl4, res, fi, type, 0); - rth->rt_flags = flags; return rth; } @@ -2447,36 +2440,37 @@ static struct rtable *__mkroute_output(const struct fib_result *res, * called with rcu_read_lock(); */ -static struct rtable *ip_route_output_slow(struct net *net, - const struct flowi4 *oldflp4) +static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) { - u32 tos = RT_FL_TOS(oldflp4); - struct flowi4 fl4; - struct fib_result res; - unsigned int flags = 0; struct net_device *dev_out = NULL; + u32 tos = RT_FL_TOS(fl4); + unsigned int flags = 0; + struct fib_result res; struct rtable *rth; + __be32 orig_daddr; + __be32 orig_saddr; + int orig_oif; res.fi = NULL; #ifdef CONFIG_IP_MULTIPLE_TABLES res.r = NULL; #endif - fl4.flowi4_oif = oldflp4->flowi4_oif; - fl4.flowi4_iif = net->loopback_dev->ifindex; - fl4.flowi4_mark = oldflp4->flowi4_mark; - fl4.daddr = oldflp4->daddr; - fl4.saddr = oldflp4->saddr; - fl4.flowi4_tos = tos & IPTOS_RT_MASK; - fl4.flowi4_scope = ((tos & RTO_ONLINK) ? - RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); + orig_daddr = fl4->daddr; + orig_saddr = fl4->saddr; + orig_oif = fl4->flowi4_oif; + + fl4->flowi4_iif = net->loopback_dev->ifindex; + fl4->flowi4_tos = tos & IPTOS_RT_MASK; + fl4->flowi4_scope = ((tos & RTO_ONLINK) ? + RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); rcu_read_lock(); - if (oldflp4->saddr) { + if (fl4->saddr) { rth = ERR_PTR(-EINVAL); - if (ipv4_is_multicast(oldflp4->saddr) || - ipv4_is_lbcast(oldflp4->saddr) || - ipv4_is_zeronet(oldflp4->saddr)) + if (ipv4_is_multicast(fl4->saddr) || + ipv4_is_lbcast(fl4->saddr) || + ipv4_is_zeronet(fl4->saddr)) goto out; /* I removed check for oif == dev_out->oif here. @@ -2487,11 +2481,11 @@ static struct rtable *ip_route_output_slow(struct net *net, of another iface. --ANK */ - if (oldflp4->flowi4_oif == 0 && - (ipv4_is_multicast(oldflp4->daddr) || - ipv4_is_lbcast(oldflp4->daddr))) { + if (fl4->flowi4_oif == 0 && + (ipv4_is_multicast(fl4->daddr) || + ipv4_is_lbcast(fl4->daddr))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ - dev_out = __ip_dev_find(net, oldflp4->saddr, false); + dev_out = __ip_dev_find(net, fl4->saddr, false); if (dev_out == NULL) goto out; @@ -2510,20 +2504,20 @@ static struct rtable *ip_route_output_slow(struct net *net, Luckily, this hack is good workaround. */ - fl4.flowi4_oif = dev_out->ifindex; + fl4->flowi4_oif = dev_out->ifindex; goto make_route; } - if (!(oldflp4->flowi4_flags & FLOWI_FLAG_ANYSRC)) { + if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ - if (!__ip_dev_find(net, oldflp4->saddr, false)) + if (!__ip_dev_find(net, fl4->saddr, false)) goto out; } } - if (oldflp4->flowi4_oif) { - dev_out = dev_get_by_index_rcu(net, oldflp4->flowi4_oif); + if (fl4->flowi4_oif) { + dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif); rth = ERR_PTR(-ENODEV); if (dev_out == NULL) goto out; @@ -2533,37 +2527,37 @@ static struct rtable *ip_route_output_slow(struct net *net, rth = ERR_PTR(-ENETUNREACH); goto out; } - if (ipv4_is_local_multicast(oldflp4->daddr) || - ipv4_is_lbcast(oldflp4->daddr)) { - if (!fl4.saddr) - fl4.saddr = inet_select_addr(dev_out, 0, - RT_SCOPE_LINK); + if (ipv4_is_local_multicast(fl4->daddr) || + ipv4_is_lbcast(fl4->daddr)) { + if (!fl4->saddr) + fl4->saddr = inet_select_addr(dev_out, 0, + RT_SCOPE_LINK); goto make_route; } - if (!fl4.saddr) { - if (ipv4_is_multicast(oldflp4->daddr)) - fl4.saddr = inet_select_addr(dev_out, 0, - fl4.flowi4_scope); - else if (!oldflp4->daddr) - fl4.saddr = inet_select_addr(dev_out, 0, - RT_SCOPE_HOST); + if (fl4->saddr) { + if (ipv4_is_multicast(fl4->daddr)) + fl4->saddr = inet_select_addr(dev_out, 0, + fl4->flowi4_scope); + else if (!fl4->daddr) + fl4->saddr = inet_select_addr(dev_out, 0, + RT_SCOPE_HOST); } } - if (!fl4.daddr) { - fl4.daddr = fl4.saddr; - if (!fl4.daddr) - fl4.daddr = fl4.saddr = htonl(INADDR_LOOPBACK); + if (!fl4->daddr) { + fl4->daddr = fl4->saddr; + if (!fl4->daddr) + fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; - fl4.flowi4_oif = net->loopback_dev->ifindex; + fl4->flowi4_oif = net->loopback_dev->ifindex; res.type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } - if (fib_lookup(net, &fl4, &res)) { + if (fib_lookup(net, fl4, &res)) { res.fi = NULL; - if (oldflp4->flowi4_oif) { + if (fl4->flowi4_oif) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. @@ -2582,9 +2576,9 @@ static struct rtable *ip_route_output_slow(struct net *net, likely IPv6, but we do not. */ - if (fl4.saddr == 0) - fl4.saddr = inet_select_addr(dev_out, 0, - RT_SCOPE_LINK); + if (fl4->saddr == 0) + fl4->saddr = inet_select_addr(dev_out, 0, + RT_SCOPE_LINK); res.type = RTN_UNICAST; goto make_route; } @@ -2593,42 +2587,45 @@ static struct rtable *ip_route_output_slow(struct net *net, } if (res.type == RTN_LOCAL) { - if (!fl4.saddr) { + if (!fl4->saddr) { if (res.fi->fib_prefsrc) - fl4.saddr = res.fi->fib_prefsrc; + fl4->saddr = res.fi->fib_prefsrc; else - fl4.saddr = fl4.daddr; + fl4->saddr = fl4->daddr; } dev_out = net->loopback_dev; - fl4.flowi4_oif = dev_out->ifindex; + fl4->flowi4_oif = dev_out->ifindex; res.fi = NULL; flags |= RTCF_LOCAL; goto make_route; } #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res.fi->fib_nhs > 1 && fl4.flowi4_oif == 0) + if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0) fib_select_multipath(&res); else #endif - if (!res.prefixlen && res.type == RTN_UNICAST && !fl4.flowi4_oif) + if (!res.prefixlen && + res.table->tb_num_default > 1 && + res.type == RTN_UNICAST && !fl4->flowi4_oif) fib_select_default(&res); - if (!fl4.saddr) - fl4.saddr = FIB_RES_PREFSRC(net, res); + if (!fl4->saddr) + fl4->saddr = FIB_RES_PREFSRC(net, res); dev_out = FIB_RES_DEV(res); - fl4.flowi4_oif = dev_out->ifindex; + fl4->flowi4_oif = dev_out->ifindex; make_route: - rth = __mkroute_output(&res, &fl4, oldflp4, dev_out, flags); + rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif, + dev_out, flags); if (!IS_ERR(rth)) { unsigned int hash; - hash = rt_hash(oldflp4->daddr, oldflp4->saddr, oldflp4->flowi4_oif, + hash = rt_hash(orig_daddr, orig_saddr, orig_oif, rt_genid(dev_net(dev_out))); - rth = rt_intern_hash(hash, rth, NULL, oldflp4->flowi4_oif); + rth = rt_intern_hash(hash, rth, NULL, orig_oif); } out: @@ -2636,7 +2633,7 @@ out: return rth; } -struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *flp4) +struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4) { struct rtable *rth; unsigned int hash; @@ -2654,13 +2651,17 @@ struct rtable *__ip_route_output_key(struct net *net, const struct flowi4 *flp4) rt_is_output_route(rth) && rth->rt_oif == flp4->flowi4_oif && rth->rt_mark == flp4->flowi4_mark && - !((rth->rt_tos ^ flp4->flowi4_tos) & + !((rth->rt_key_tos ^ flp4->flowi4_tos) & (IPTOS_RT_MASK | RTO_ONLINK)) && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { dst_use(&rth->dst, jiffies); RT_CACHE_STAT_INC(out_hit); rcu_read_unlock_bh(); + if (!flp4->saddr) + flp4->saddr = rth->rt_src; + if (!flp4->daddr) + flp4->daddr = rth->rt_dst; return rth; } RT_CACHE_STAT_INC(out_hlist_search); @@ -2686,6 +2687,12 @@ static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst, + unsigned long old) +{ + return NULL; +} + static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), @@ -2694,11 +2701,12 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .default_mtu = ipv4_blackhole_default_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, + .cow_metrics = ipv4_rt_blackhole_cow_metrics, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, 1); + struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, 0, 0); struct rtable *ort = (struct rtable *) dst_orig; if (rt) { @@ -2715,7 +2723,8 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_key_dst = ort->rt_key_dst; rt->rt_key_src = ort->rt_key_src; - rt->rt_tos = ort->rt_tos; + rt->rt_key_tos = ort->rt_key_tos; + rt->rt_route_iif = ort->rt_route_iif; rt->rt_iif = ort->rt_iif; rt->rt_oif = ort->rt_oif; rt->rt_mark = ort->rt_mark; @@ -2725,7 +2734,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_type = ort->rt_type; rt->rt_dst = ort->rt_dst; rt->rt_src = ort->rt_src; - rt->rt_iif = ort->rt_iif; rt->rt_gateway = ort->rt_gateway; rt->rt_spec_dst = ort->rt_spec_dst; rt->peer = ort->peer; @@ -2751,15 +2759,10 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, if (IS_ERR(rt)) return rt; - if (flp4->flowi4_proto) { - if (!flp4->saddr) - flp4->saddr = rt->rt_src; - if (!flp4->daddr) - flp4->daddr = rt->rt_dst; + if (flp4->flowi4_proto) rt = (struct rtable *) xfrm_lookup(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0); - } return rt; } @@ -2783,7 +2786,7 @@ static int rt_fill_info(struct net *net, r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; - r->rtm_tos = rt->rt_tos; + r->rtm_tos = rt->rt_key_tos; r->rtm_table = RT_TABLE_MAIN; NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; @@ -2837,7 +2840,9 @@ static int rt_fill_info(struct net *net, if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { - int err = ipmr_get_route(net, skb, r, nowait); + int err = ipmr_get_route(net, skb, + rt->rt_src, rt->rt_dst, + r, nowait); if (err <= 0) { if (!nowait) { if (err == 0) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 8b44c6d2a79b..26461492a847 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -321,10 +321,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * the ACK carries the same options again (see RFC1122 4.2.3.8) */ if (opt && opt->optlen) { - int opt_size = sizeof(struct ip_options) + opt->optlen; + int opt_size = sizeof(struct ip_options_rcu) + opt->optlen; ireq->opt = kmalloc(opt_size, GFP_ATOMIC); - if (ireq->opt != NULL && ip_options_echo(ireq->opt, skb)) { + if (ireq->opt != NULL && ip_options_echo(&ireq->opt->opt, skb)) { kfree(ireq->opt); ireq->opt = NULL; } @@ -345,17 +345,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * no easy way to do this. */ { - struct flowi4 fl4 = { - .flowi4_mark = sk->sk_mark, - .daddr = ((opt && opt->srr) ? - opt->faddr : ireq->rmt_addr), - .saddr = ireq->loc_addr, - .flowi4_tos = RT_CONN_FLAGS(sk), - .flowi4_proto = IPPROTO_TCP, - .flowi4_flags = inet_sk_flowi_flags(sk), - .fl4_sport = th->dest, - .fl4_dport = th->source, - }; + struct flowi4 fl4; + + flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), + RT_SCOPE_UNIVERSE, IPPROTO_TCP, + inet_sk_flowi_flags(sk), + (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, + ireq->loc_addr, th->source, th->dest); security_req_classify_flow(req, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(sock_net(sk), &fl4); if (IS_ERR(rt)) { diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1a456652086b..57d0752e239a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -13,6 +13,7 @@ #include <linux/seqlock.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/nsproxy.h> #include <net/snmp.h> #include <net/icmp.h> #include <net/ip.h> @@ -21,6 +22,7 @@ #include <net/udp.h> #include <net/cipso_ipv4.h> #include <net/inet_frag.h> +#include <net/ping.h> static int zero; static int tcp_retr1_max = 255; @@ -30,6 +32,8 @@ static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; static int ip_ttl_min = 1; static int ip_ttl_max = 255; +static int ip_ping_group_range_min[] = { 0, 0 }; +static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; /* Update system visible IP port range */ static void set_local_port_range(int range[2]) @@ -68,6 +72,53 @@ static int ipv4_local_port_range(ctl_table *table, int write, return ret; } + +void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high) +{ + gid_t *data = table->data; + unsigned seq; + do { + seq = read_seqbegin(&sysctl_local_ports.lock); + + *low = data[0]; + *high = data[1]; + } while (read_seqretry(&sysctl_local_ports.lock, seq)); +} + +/* Update system visible IP port range */ +static void set_ping_group_range(struct ctl_table *table, int range[2]) +{ + gid_t *data = table->data; + write_seqlock(&sysctl_local_ports.lock); + data[0] = range[0]; + data[1] = range[1]; + write_sequnlock(&sysctl_local_ports.lock); +} + +/* Validate changes from /proc interface. */ +static int ipv4_ping_group_range(ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret; + gid_t range[2]; + ctl_table tmp = { + .data = &range, + .maxlen = sizeof(range), + .mode = table->mode, + .extra1 = &ip_ping_group_range_min, + .extra2 = &ip_ping_group_range_max, + }; + + inet_get_ping_group_range_table(table, range, range + 1); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + + if (write && ret == 0) + set_ping_group_range(table, range); + + return ret; +} + static int proc_tcp_congestion_control(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -311,7 +362,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_do_large_bitmap, }, -#ifdef CONFIG_IP_MULTICAST { .procname = "igmp_max_memberships", .data = &sysctl_igmp_max_memberships, @@ -319,8 +369,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - -#endif { .procname = "igmp_max_msf", .data = &sysctl_igmp_max_msf, @@ -680,6 +728,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ping_group_range", + .data = &init_net.ipv4.sysctl_ping_group_range, + .maxlen = sizeof(init_net.ipv4.sysctl_ping_group_range), + .mode = 0644, + .proc_handler = ipv4_ping_group_range, + }, { } }; @@ -714,8 +769,18 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) &net->ipv4.sysctl_icmp_ratemask; table[6].data = &net->ipv4.sysctl_rt_cache_rebuild_count; + table[7].data = + &net->ipv4.sysctl_ping_group_range; + } + /* + * Sane defaults - nobody may create ping sockets. + * Boot scripts should set this to distro-specific group. + */ + net->ipv4.sysctl_ping_group_range[0] = 1; + net->ipv4.sysctl_ping_group_range[1] = 0; + net->ipv4.sysctl_rt_cache_rebuild_count = 4; net->ipv4.ipv4_hdr = register_net_sysctl_table(net, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b22d45010545..054a59d21eb0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -999,7 +999,8 @@ new_segment: /* We have some space in skb head. Superb! */ if (copy > skb_tailroom(skb)) copy = skb_tailroom(skb); - if ((err = skb_add_data(skb, from, copy)) != 0) + err = skb_add_data_nocache(sk, skb, from, copy); + if (err) goto do_fault; } else { int merge = 0; @@ -1042,8 +1043,8 @@ new_segment: /* Time to copy data. We are close to * the end! */ - err = skb_copy_to_page(sk, from, skb, page, - off, copy); + err = skb_copy_to_page_nocache(sk, from, skb, + page, off, copy); if (err) { /* If this page was new, give it to the * socket so it does not get leaked. diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 34340c9c95fa..f376b05cca81 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -93,6 +93,7 @@ struct bictcp { u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ #define ACK_RATIO_SHIFT 4 +#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT) u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ u8 sample_cnt; /* number of samples to decide curr_rtt */ u8 found; /* the exit point is found? */ @@ -398,8 +399,12 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) u32 delay; if (icsk->icsk_ca_state == TCP_CA_Open) { - cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT; - ca->delayed_ack += cnt; + u32 ratio = ca->delayed_ack; + + ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; + ratio += cnt; + + ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT); } /* Some calls are for duplicates without timetamps */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f7e6c2c2d2bb..a7d6671e33b8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -146,13 +146,15 @@ EXPORT_SYMBOL_GPL(tcp_twsk_unique); /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { + struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; __be16 orig_sport, orig_dport; - struct rtable *rt; __be32 daddr, nexthop; + struct flowi4 *fl4; + struct rtable *rt; int err; + struct ip_options_rcu *inet_opt; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; @@ -161,15 +163,18 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; - if (inet->opt && inet->opt->srr) { + inet_opt = rcu_dereference_protected(inet->inet_opt, + sock_owned_by_user(sk)); + if (inet_opt && inet_opt->opt.srr) { if (!daddr) return -EINVAL; - nexthop = inet->opt->faddr; + nexthop = inet_opt->opt.faddr; } orig_sport = inet->inet_sport; orig_dport = usin->sin_port; - rt = ip_route_connect(nexthop, inet->inet_saddr, + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, orig_sport, orig_dport, sk, true); @@ -185,11 +190,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -ENETUNREACH; } - if (!inet->opt || !inet->opt->srr) - daddr = rt->rt_dst; + if (!inet_opt || !inet_opt->opt.srr) + daddr = fl4->daddr; if (!inet->inet_saddr) - inet->inet_saddr = rt->rt_src; + inet->inet_saddr = fl4->saddr; inet->inet_rcv_saddr = inet->inet_saddr; if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { @@ -200,8 +205,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (tcp_death_row.sysctl_tw_recycle && - !tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) { - struct inet_peer *peer = rt_get_peer(rt); + !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr) { + struct inet_peer *peer = rt_get_peer(rt, fl4->daddr); /* * VJ's idea. We save last timestamp seen from * the destination in peer table, when entering state @@ -221,8 +226,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr = daddr; inet_csk(sk)->icsk_ext_hdr_len = 0; - if (inet->opt) - inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen; + if (inet_opt) + inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; @@ -236,8 +241,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - rt = ip_route_newports(rt, IPPROTO_TCP, - orig_sport, orig_dport, + rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); @@ -279,7 +283,7 @@ EXPORT_SYMBOL(tcp_v4_connect); /* * This routine does path mtu discovery as defined in RFC1191. */ -static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) +static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); @@ -341,7 +345,7 @@ static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu) void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) { - struct iphdr *iph = (struct iphdr *)icmp_skb->data; + const struct iphdr *iph = (const struct iphdr *)icmp_skb->data; struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2)); struct inet_connection_sock *icsk; struct tcp_sock *tp; @@ -647,7 +651,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; net = dev_net(skb_dst(skb)->dev); - ip_send_reply(net->ipv4.tcp_sock, skb, + ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -722,7 +726,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; - ip_send_reply(net->ipv4.tcp_sock, skb, + ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -765,11 +769,12 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_values *rvp) { const struct inet_request_sock *ireq = inet_rsk(req); + struct flowi4 fl4; int err = -1; struct sk_buff * skb; /* First, grab a route. */ - if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) + if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; skb = tcp_make_synack(sk, dst, req, rvp); @@ -820,17 +825,18 @@ static void syn_flood_warning(const struct sk_buff *skb) /* * Save and compile IPv4 options into the request_sock if needed. */ -static struct ip_options *tcp_v4_save_options(struct sock *sk, - struct sk_buff *skb) +static struct ip_options_rcu *tcp_v4_save_options(struct sock *sk, + struct sk_buff *skb) { - struct ip_options *opt = &(IPCB(skb)->opt); - struct ip_options *dopt = NULL; + const struct ip_options *opt = &(IPCB(skb)->opt); + struct ip_options_rcu *dopt = NULL; if (opt && opt->optlen) { - int opt_size = optlength(opt); + int opt_size = sizeof(*dopt) + opt->optlen; + dopt = kmalloc(opt_size, GFP_ATOMIC); if (dopt) { - if (ip_options_echo(dopt, skb)) { + if (ip_options_echo(&dopt->opt, skb)) { kfree(dopt); dopt = NULL; } @@ -1333,6 +1339,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) req->cookie_ts = tmp_opt.tstamp_ok; } else if (!isn) { struct inet_peer *peer = NULL; + struct flowi4 fl4; /* VJ's idea. We save last timestamp seen * from the destination in peer table, when entering @@ -1345,9 +1352,9 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet_csk_route_req(sk, req)) != NULL && - (peer = rt_get_peer((struct rtable *)dst)) != NULL && - peer->daddr.addr.a4 == saddr) { + (dst = inet_csk_route_req(sk, &fl4, req)) != NULL && + fl4.daddr == saddr && + (peer = rt_get_peer((struct rtable *)dst, fl4.daddr)) != NULL) { inet_peer_refcheck(peer); if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && (s32)(peer->tcp_ts - req->ts_recent) > @@ -1411,19 +1418,16 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; #endif + struct ip_options_rcu *inet_opt; if (sk_acceptq_is_full(sk)) goto exit_overflow; - if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) - goto exit; - newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; - sk_setup_caps(newsk, dst); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); @@ -1431,15 +1435,21 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->inet_daddr = ireq->rmt_addr; newinet->inet_rcv_saddr = ireq->loc_addr; newinet->inet_saddr = ireq->loc_addr; - newinet->opt = ireq->opt; + inet_opt = ireq->opt; + rcu_assign_pointer(newinet->inet_opt, inet_opt); ireq->opt = NULL; newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newinet->opt) - inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen; + if (inet_opt) + inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; + if (!dst && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) + goto put_and_exit; + + sk_setup_caps(newsk, dst); + tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); @@ -1467,10 +1477,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } #endif - if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); - goto exit; - } + if (__inet_inherit_port(sk, newsk) < 0) + goto put_and_exit; __inet_hash_nolisten(newsk, NULL); return newsk; @@ -1482,6 +1490,9 @@ exit_nonewsk: exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; +put_and_exit: + sock_put(newsk); + goto exit; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); @@ -1764,12 +1775,13 @@ struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it) struct inet_sock *inet = inet_sk(sk); struct inet_peer *peer; - if (!rt || rt->rt_dst != inet->inet_daddr) { + if (!rt || + inet->cork.fl.u.ip4.daddr != inet->inet_daddr) { peer = inet_getpeer_v4(inet->inet_daddr, 1); *release_it = true; } else { if (!rt->peer) - rt_bind_peer(rt, 1); + rt_bind_peer(rt, inet->inet_daddr, 1); peer = rt->peer; *release_it = false; } @@ -2359,7 +2371,7 @@ static void get_openreq4(struct sock *sk, struct request_sock *req, int ttd = req->expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %pK%n", i, ireq->loc_addr, ntohs(inet_sk(sk)->inet_sport), @@ -2414,7 +2426,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " - "%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n", + "%08X %5d %8d %lu %d %pK %lu %lu %u %u %d%n", i, src, srcp, dest, destp, sk->sk_state, tp->write_seq - tp->snd_una, rx_queue, @@ -2449,7 +2461,7 @@ static void get_timewait4_sock(struct inet_timewait_sock *tw, srcp = ntohs(tw->tw_sport); seq_printf(f, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p%n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK%n", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw, len); @@ -2527,7 +2539,7 @@ void tcp4_proc_exit(void) struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - struct iphdr *iph = skb_gro_network_header(skb); + const struct iphdr *iph = skb_gro_network_header(skb); switch (skb->ip_summed) { case CHECKSUM_COMPLETE: @@ -2548,7 +2560,7 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) int tcp4_gro_complete(struct sk_buff *skb) { - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb), diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 656d431c99ad..72f7218b03f5 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -12,7 +12,7 @@ * within cong_avoid. * o Error correcting in remote HZ, therefore remote HZ will be keeped * on checking and updating. - * o Handling calculation of One-Way-Delay (OWD) within rtt_sample, sicne + * o Handling calculation of One-Way-Delay (OWD) within rtt_sample, since * OWD have a similar meaning as RTT. Also correct the buggy formular. * o Handle reaction for Early Congestion Indication (ECI) within * pkts_acked, as mentioned within pseudo code. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8b0d0167e44a..882e0b0964d0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -73,7 +73,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; - /* Don't override Nagle indefinately with F-RTO */ + /* Don't override Nagle indefinitely with F-RTO */ if (tp->frto_counter == 2) tp->frto_counter = 3; @@ -899,7 +899,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); - err = icsk->icsk_af_ops->queue_xmit(skb); + err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl); if (likely(err <= 0)) return err; diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index dc7f43179c9a..05c3b6f0e8e1 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -20,7 +20,7 @@ #define TCP_YEAH_DELTA 3 //log minimum fraction of cwnd to be removed on loss #define TCP_YEAH_EPSILON 1 //log maximum fraction to be removed on early decongestion #define TCP_YEAH_PHY 8 //lin maximum delta from base -#define TCP_YEAH_RHO 16 //lin minumum number of consecutive rtt to consider competition on loss +#define TCP_YEAH_RHO 16 //lin minimum number of consecutive rtt to consider competition on loss #define TCP_YEAH_ZETA 50 //lin minimum number of state switchs to reset reno_count #define TCP_SCALABLE_AI_CNT 100U diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 588f47af5faf..abca870d8ff6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -189,7 +189,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, * @sk: socket struct in question * @snum: port number to look up * @saddr_comp: AF-dependent comparison of bound local IP addresses - * @hash2_nulladdr: AF-dependant hash value in secondary hash chains, + * @hash2_nulladdr: AF-dependent hash value in secondary hash chains, * with NULL address */ int udp_lib_get_port(struct sock *sk, unsigned short snum, @@ -578,7 +578,7 @@ found: void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) { struct inet_sock *inet; - struct iphdr *iph = (struct iphdr *)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2)); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; @@ -706,12 +706,11 @@ static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) } } -static int udp_send_skb(struct sk_buff *skb, __be32 daddr, __be32 dport) +static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct udphdr *uh; - struct rtable *rt = (struct rtable *)skb_dst(skb); int err = 0; int is_udplite = IS_UDPLITE(sk); int offset = skb_transport_offset(skb); @@ -723,7 +722,7 @@ static int udp_send_skb(struct sk_buff *skb, __be32 daddr, __be32 dport) */ uh = udp_hdr(skb); uh->source = inet->inet_sport; - uh->dest = dport; + uh->dest = fl4->fl4_dport; uh->len = htons(len); uh->check = 0; @@ -737,14 +736,14 @@ static int udp_send_skb(struct sk_buff *skb, __be32 daddr, __be32 dport) } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ - udp4_hwcsum(skb, rt->rt_src, daddr); + udp4_hwcsum(skb, fl4->saddr, fl4->daddr); goto send; } else csum = udp_csum(skb); /* add protocol-dependent pseudo-header */ - uh->check = csum_tcpudp_magic(rt->rt_src, daddr, len, + uh->check = csum_tcpudp_magic(fl4->saddr, fl4->daddr, len, sk->sk_protocol, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; @@ -774,11 +773,11 @@ static int udp_push_pending_frames(struct sock *sk) struct sk_buff *skb; int err = 0; - skb = ip_finish_skb(sk); + skb = ip_finish_skb(sk, fl4); if (!skb) goto out; - err = udp_send_skb(skb, fl4->daddr, fl4->fl4_dport); + err = udp_send_skb(skb, fl4); out: up->len = 0; @@ -791,6 +790,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); + struct flowi4 fl4_stack; struct flowi4 *fl4; int ulen = len; struct ipcm_cookie ipc; @@ -804,6 +804,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; + struct ip_options_data opt_copy; if (len > 0xFFFF) return -EMSGSIZE; @@ -820,6 +821,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; + fl4 = &inet->cork.fl.u.ip4; if (up->pending) { /* * There are pending frames. @@ -877,22 +879,32 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, free = 1; connected = 0; } - if (!ipc.opt) - ipc.opt = inet->opt; + if (!ipc.opt) { + struct ip_options_rcu *inet_opt; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + memcpy(&opt_copy, inet_opt, + sizeof(*inet_opt) + inet_opt->opt.optlen); + ipc.opt = &opt_copy.opt; + } + rcu_read_unlock(); + } saddr = ipc.addr; ipc.addr = faddr = daddr; - if (ipc.opt && ipc.opt->srr) { + if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) return -EINVAL; - faddr = ipc.opt->faddr; + faddr = ipc.opt->opt.faddr; connected = 0; } tos = RT_TOS(inet->tos); if (sock_flag(sk, SOCK_LOCALROUTE) || (msg->msg_flags & MSG_DONTROUTE) || - (ipc.opt && ipc.opt->is_strictroute)) { + (ipc.opt && ipc.opt->opt.is_strictroute)) { tos |= RTO_ONLINK; connected = 0; } @@ -909,22 +921,16 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, rt = (struct rtable *)sk_dst_check(sk, 0); if (rt == NULL) { - struct flowi4 fl4 = { - .flowi4_oif = ipc.oif, - .flowi4_mark = sk->sk_mark, - .daddr = faddr, - .saddr = saddr, - .flowi4_tos = tos, - .flowi4_proto = sk->sk_protocol, - .flowi4_flags = (inet_sk_flowi_flags(sk) | - FLOWI_FLAG_CAN_SLEEP), - .fl4_sport = inet->inet_sport, - .fl4_dport = dport, - }; struct net *net = sock_net(sk); - security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); - rt = ip_route_output_flow(net, &fl4, sk); + fl4 = &fl4_stack; + flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, + RT_SCOPE_UNIVERSE, sk->sk_protocol, + inet_sk_flowi_flags(sk)|FLOWI_FLAG_CAN_SLEEP, + faddr, saddr, dport, inet->inet_sport); + + security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); + rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -945,18 +951,18 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto do_confirm; back_from_confirm: - saddr = rt->rt_src; + saddr = fl4->saddr; if (!ipc.addr) - daddr = ipc.addr = rt->rt_dst; + daddr = ipc.addr = fl4->daddr; /* Lockless fast path for the non-corking case. */ if (!corkreq) { - skb = ip_make_skb(sk, getfrag, msg->msg_iov, ulen, + skb = ip_make_skb(sk, fl4, getfrag, msg->msg_iov, ulen, sizeof(struct udphdr), &ipc, &rt, msg->msg_flags); err = PTR_ERR(skb); if (skb && !IS_ERR(skb)) - err = udp_send_skb(skb, daddr, dport); + err = udp_send_skb(skb, fl4); goto out; } @@ -982,9 +988,9 @@ back_from_confirm: do_append_data: up->len += ulen; - err = ip_append_data(sk, getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), &ipc, &rt, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); + err = ip_append_data(sk, fl4, getfrag, msg->msg_iov, ulen, + sizeof(struct udphdr), &ipc, &rt, + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_flush_pending_frames(sk); else if (!corkreq) @@ -1024,6 +1030,7 @@ EXPORT_SYMBOL(udp_sendmsg); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); int ret; @@ -1048,7 +1055,8 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, return -EINVAL; } - ret = ip_append_page(sk, page, offset, size, flags); + ret = ip_append_page(sk, &inet->cork.fl.u.ip4, + page, offset, size, flags); if (ret == -EOPNOTSUPP) { release_sock(sk); return sock_no_sendpage(sk->sk_socket, page, offset, @@ -2082,7 +2090,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, __u16 srcp = ntohs(inet->inet_sport); seq_printf(f, "%5d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d%n", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 571aa96a175c..2d51840e53a1 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -69,7 +69,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm4_prepare_output); -static int xfrm4_output_finish(struct sk_buff *skb) +int xfrm4_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER if (!skb_dst(skb)->xfrm) { @@ -86,7 +86,11 @@ static int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, - NULL, skb_dst(skb)->dev, xfrm4_output_finish, + NULL, dst->dev, + x->outer_mode->afinfo->output_finish, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 13e0e7f659ff..981e43eaf704 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -18,38 +18,46 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo; -static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, - const xfrm_address_t *saddr, - const xfrm_address_t *daddr) +static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, + int tos, + const xfrm_address_t *saddr, + const xfrm_address_t *daddr) { - struct flowi4 fl4 = { - .daddr = daddr->a4, - .flowi4_tos = tos, - }; struct rtable *rt; + memset(fl4, 0, sizeof(*fl4)); + fl4->daddr = daddr->a4; + fl4->flowi4_tos = tos; if (saddr) - fl4.saddr = saddr->a4; + fl4->saddr = saddr->a4; - rt = __ip_route_output_key(net, &fl4); + rt = __ip_route_output_key(net, fl4); if (!IS_ERR(rt)) return &rt->dst; return ERR_CAST(rt); } +static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, + const xfrm_address_t *saddr, + const xfrm_address_t *daddr) +{ + struct flowi4 fl4; + + return __xfrm4_dst_lookup(net, &fl4, tos, saddr, daddr); +} + static int xfrm4_get_saddr(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; - struct rtable *rt; + struct flowi4 fl4; - dst = xfrm4_dst_lookup(net, 0, NULL, daddr); + dst = __xfrm4_dst_lookup(net, &fl4, 0, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; - rt = (struct rtable *)dst; - saddr->a4 = rt->rt_src; + saddr->a4 = fl4.saddr; dst_release(dst); return 0; } @@ -73,7 +81,8 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, rt->rt_key_dst = fl4->daddr; rt->rt_key_src = fl4->saddr; - rt->rt_tos = fl4->flowi4_tos; + rt->rt_key_tos = fl4->flowi4_tos; + rt->rt_route_iif = fl4->flowi4_iif; rt->rt_iif = fl4->flowi4_iif; rt->rt_oif = fl4->flowi4_oif; rt->rt_mark = fl4->flowi4_mark; @@ -101,7 +110,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, static void _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) { - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); u8 *xprth = skb_network_header(skb) + iph->ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 1717c64628d1..d9ac0a0058b5 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -55,7 +55,7 @@ xfrm4_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, int xfrm4_extract_header(struct sk_buff *skb) { - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph); XFRM_MODE_SKB_CB(skb)->id = iph->id; @@ -78,6 +78,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .init_tempsel = __xfrm4_init_tempsel, .init_temprop = xfrm4_init_temprop, .output = xfrm4_output, + .output_finish = xfrm4_output_finish, .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, .transport_finish = xfrm4_transport_finish, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3daaf3c7703c..498b927f68be 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -289,19 +289,19 @@ static int snmp6_alloc_dev(struct inet6_dev *idev) sizeof(struct ipstats_mib), __alignof__(struct ipstats_mib)) < 0) goto err_ip; - if (snmp_mib_init((void __percpu **)idev->stats.icmpv6, - sizeof(struct icmpv6_mib), - __alignof__(struct icmpv6_mib)) < 0) + idev->stats.icmpv6dev = kzalloc(sizeof(struct icmpv6_mib_device), + GFP_KERNEL); + if (!idev->stats.icmpv6dev) goto err_icmp; - if (snmp_mib_init((void __percpu **)idev->stats.icmpv6msg, - sizeof(struct icmpv6msg_mib), - __alignof__(struct icmpv6msg_mib)) < 0) + idev->stats.icmpv6msgdev = kzalloc(sizeof(struct icmpv6msg_mib_device), + GFP_KERNEL); + if (!idev->stats.icmpv6msgdev) goto err_icmpmsg; return 0; err_icmpmsg: - snmp_mib_free((void __percpu **)idev->stats.icmpv6); + kfree(idev->stats.icmpv6dev); err_icmp: snmp_mib_free((void __percpu **)idev->stats.ipv6); err_ip: @@ -310,19 +310,13 @@ err_ip: static void snmp6_free_dev(struct inet6_dev *idev) { - snmp_mib_free((void __percpu **)idev->stats.icmpv6msg); - snmp_mib_free((void __percpu **)idev->stats.icmpv6); + kfree(idev->stats.icmpv6msgdev); + kfree(idev->stats.icmpv6dev); snmp_mib_free((void __percpu **)idev->stats.ipv6); } /* Nobody refers to this device, we may destroy it. */ -static void in6_dev_finish_destroy_rcu(struct rcu_head *head) -{ - struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu); - kfree(idev); -} - void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; @@ -339,7 +333,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) return; } snmp6_free_dev(idev); - call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu); + kfree_rcu(idev, rcu); } EXPORT_SYMBOL(in6_dev_finish_destroy); @@ -535,12 +529,6 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) } #endif -static void inet6_ifa_finish_destroy_rcu(struct rcu_head *head) -{ - struct inet6_ifaddr *ifp = container_of(head, struct inet6_ifaddr, rcu); - kfree(ifp); -} - /* Nobody refers to this ifaddr, destroy it */ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) { @@ -561,7 +549,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) } dst_release(&ifp->rt->dst); - call_rcu(&ifp->rcu, inet6_ifa_finish_destroy_rcu); + kfree_rcu(ifp, rcu); } static void @@ -825,6 +813,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) dst_release(&rt->dst); } + /* clean up prefsrc entries */ + rt6_remove_prefsrc(ifp); out: in6_ifa_put(ifp); } @@ -1084,7 +1074,7 @@ static int ipv6_get_saddr_eval(struct net *net, case IPV6_SADDR_RULE_PRIVACY: { /* Rule 7: Prefer public address - * Note: prefer temprary address if use_tempaddr >= 2 + * Note: prefer temporary address if use_tempaddr >= 2 */ int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ? !!(dst->prefs & IPV6_PREFER_SRC_TMP) : @@ -1281,7 +1271,7 @@ static int ipv6_count_addresses(struct inet6_dev *idev) return cnt; } -int ipv6_chk_addr(struct net *net, struct in6_addr *addr, +int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { struct inet6_ifaddr *ifp; @@ -1324,7 +1314,7 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, return false; } -int ipv6_chk_prefix(struct in6_addr *addr, struct net_device *dev) +int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; @@ -1455,7 +1445,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) /* Join to solicited addr multicast group. */ -void addrconf_join_solict(struct net_device *dev, struct in6_addr *addr) +void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; @@ -1466,7 +1456,7 @@ void addrconf_join_solict(struct net_device *dev, struct in6_addr *addr) ipv6_dev_mc_inc(dev, &maddr); } -void addrconf_leave_solict(struct inet6_dev *idev, struct in6_addr *addr) +void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; @@ -1968,7 +1958,7 @@ ok: * to the stored lifetime since we'll * be updating the timestamp below, * else we'll set it back to the - * minumum. + * minimum. */ if (prefered_lft != ifp->prefered_lft) { valid_lft = stored_lft; @@ -2111,7 +2101,7 @@ err_exit: /* * Manual configuration of address on an interface */ -static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, +static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx, unsigned int plen, __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft) { @@ -2185,7 +2175,7 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, return PTR_ERR(ifp); } -static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx, +static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *pfx, unsigned int plen) { struct inet6_ifaddr *ifp; @@ -2348,7 +2338,7 @@ static void init_loopback(struct net_device *dev) add_addr(idev, &in6addr_loopback, 128, IFA_HOST); } -static void addrconf_add_linklocal(struct inet6_dev *idev, struct in6_addr *addr) +static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) { struct inet6_ifaddr * ifp; u32 addr_flags = IFA_F_PERMANENT; @@ -3119,7 +3109,7 @@ void if6_proc_exit(void) #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) /* Check if address is a home address configured on any interface. */ -int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) +int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { int ret = 0; struct inet6_ifaddr *ifp = NULL; @@ -3836,7 +3826,7 @@ static inline size_t inet6_if_nlmsg_size(void) + nla_total_size(inet6_ifla6_size()); /* IFLA_PROTINFO */ } -static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib, +static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib, int items, int bytes) { int i; @@ -3846,7 +3836,7 @@ static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib, /* Use put_unaligned() because stats may not be aligned for u64. */ put_unaligned(items, &stats[0]); for (i = 1; i < items; i++) - put_unaligned(snmp_fold_field(mib, i), &stats[i]); + put_unaligned(atomic_long_read(&mib[i]), &stats[i]); memset(&stats[items], 0, pad); } @@ -3875,7 +3865,7 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp)); break; case IFLA_INET6_ICMP6STATS: - __snmp6_fill_stats(stats, (void __percpu **)idev->stats.icmpv6, ICMP6_MIB_MAX, bytes); + __snmp6_fill_statsdev(stats, idev->stats.icmpv6dev->mibs, ICMP6_MIB_MAX, bytes); break; } } @@ -4537,7 +4527,7 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) t = p->sysctl; p->sysctl = NULL; - unregister_sysctl_table(t->sysctl_header); + unregister_net_sysctl_table(t->sysctl_header); kfree(t->dev_name); kfree(t); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 4b13d5d8890e..b7919f901fbf 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -740,7 +740,7 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) static int ipv6_gso_send_check(struct sk_buff *skb) { - struct ipv6hdr *ipv6h; + const struct ipv6hdr *ipv6h; const struct inet6_protocol *ops; int err = -EINVAL; @@ -1113,7 +1113,7 @@ static int __init inet6_init(void) /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance - * in a host availiable by both INET and INET6 APIs and + * in a host available by both INET and INET6 APIs and * able to communicate via both network protocols. */ diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 0e5e943446f0..674255f5e6b7 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -44,7 +44,7 @@ #include <net/checksum.h> -static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr); +static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); /* Big ac list lock for all the sockets */ static DEFINE_RWLOCK(ipv6_sk_ac_lock); @@ -54,7 +54,7 @@ static DEFINE_RWLOCK(ipv6_sk_ac_lock); * socket join an anycast group */ -int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr) +int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; @@ -145,7 +145,7 @@ error: /* * socket leave an anycast group */ -int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr) +int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev; @@ -252,7 +252,7 @@ static void aca_put(struct ifacaddr6 *ac) /* * device anycast group inc (add if not found) */ -int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) +int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) { struct ifacaddr6 *aca; struct inet6_dev *idev; @@ -324,7 +324,7 @@ out: /* * device anycast group decrement */ -int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) +int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; @@ -358,7 +358,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) } /* called with rcu_read_lock() */ -static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr) +static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev = __in6_dev_get(dev); @@ -371,7 +371,7 @@ static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr) * check if the interface has this anycast address * called with rcu_read_lock() */ -static int ipv6_chk_acast_dev(struct net_device *dev, struct in6_addr *addr) +static int ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; struct ifacaddr6 *aca; @@ -392,7 +392,7 @@ static int ipv6_chk_acast_dev(struct net_device *dev, struct in6_addr *addr) * check if given interface (or any, if dev==0) has this anycast address */ int ipv6_chk_acast_addr(struct net *net, struct net_device *dev, - struct in6_addr *addr) + const struct in6_addr *addr) { int found = 0; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 5aa8ec88f194..1ac7938dd9ec 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -371,7 +371,7 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); asg = esp_req_sg(aead, req); - sg = asg + 1; + sg = asg + sglists; skb->ip_summed = CHECKSUM_NONE; @@ -430,7 +430,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); - struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; @@ -438,7 +438,8 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, type != ICMPV6_PKT_TOOBIG) return; - x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n", diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 83cb4f9add81..11900417b1cc 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -372,7 +372,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; struct ipv6_pinfo *np; - struct in6_addr *saddr = NULL; + const struct in6_addr *saddr = NULL; struct dst_entry *dst; struct icmp6hdr tmp_hdr; struct flowi6 fl6; @@ -521,7 +521,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct sock *sk; struct inet6_dev *idev; struct ipv6_pinfo *np; - struct in6_addr *saddr = NULL; + const struct in6_addr *saddr = NULL; struct icmp6hdr *icmph = icmp6_hdr(skb); struct icmp6hdr tmp_hdr; struct flowi6 fl6; @@ -645,8 +645,8 @@ static int icmpv6_rcv(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); - struct in6_addr *saddr, *daddr; - struct ipv6hdr *orig_hdr; + const struct in6_addr *saddr, *daddr; + const struct ipv6hdr *orig_hdr; struct icmp6hdr *hdr; u8 type; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 166054650466..8a58e8cf6646 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -44,7 +44,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && (!sk->sk_reuse || !sk2->sk_reuse || - ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) && + sk2->sk_state == TCP_LISTEN) && ipv6_rcv_saddr_equal(sk, sk2)) break; } @@ -203,7 +203,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) return dst; } -int inet6_csk_xmit(struct sk_buff *skb) +int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7548905e79e1..4076a0b14b20 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -134,9 +134,9 @@ static __inline__ u32 fib6_new_sernum(void) # define BITOP_BE32_SWIZZLE 0 #endif -static __inline__ __be32 addr_bit_set(void *token, int fn_bit) +static __inline__ __be32 addr_bit_set(const void *token, int fn_bit) { - __be32 *addr = token; + const __be32 *addr = token; /* * Here, * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) @@ -394,10 +394,11 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) arg.net = net; w->args = &arg; + rcu_read_lock(); for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry(tb, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) { if (e < s_e) goto next; res = fib6_dump_table(tb, skb, cb); @@ -408,6 +409,7 @@ next: } } out: + rcu_read_unlock(); cb->args[1] = e; cb->args[0] = h; @@ -822,7 +824,7 @@ st_failure: struct lookup_args { int offset; /* key offset on rt6_info */ - struct in6_addr *addr; /* search key */ + const struct in6_addr *addr; /* search key */ }; static struct fib6_node * fib6_lookup_1(struct fib6_node *root, @@ -881,8 +883,8 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, return NULL; } -struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr, - struct in6_addr *saddr) +struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { @@ -916,7 +918,7 @@ struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr, static struct fib6_node * fib6_locate_1(struct fib6_node *root, - struct in6_addr *addr, + const struct in6_addr *addr, int plen, int offset) { struct fib6_node *fn; @@ -946,8 +948,8 @@ static struct fib6_node * fib6_locate_1(struct fib6_node *root, } struct fib6_node * fib6_locate(struct fib6_node *root, - struct in6_addr *daddr, int dst_len, - struct in6_addr *saddr, int src_len) + const struct in6_addr *daddr, int dst_len, + const struct in6_addr *saddr, int src_len) { struct fib6_node *fn; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index a83e9209cecc..027c7ff6f1e5 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -57,7 +57,7 @@ inline int ip6_rcv_finish( struct sk_buff *skb) int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; u32 pkt_len; struct inet6_dev *idev; struct net *net = dev_net(skb->dev); @@ -186,7 +186,7 @@ resubmit: int ret; if (ipprot->flags & INET6_PROTO_FINAL) { - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; /* Free reference early: we don't need it any more, and it may hold ip_conntrack module loaded @@ -242,7 +242,7 @@ int ip6_input(struct sk_buff *skb) int ip6_mc_input(struct sk_buff *skb) { - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; int deliver; IP6_UPD_PO_STATS_BH(dev_net(skb_dst(skb)->dev), diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 18208876aa8a..9d4b165837d6 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -779,7 +779,7 @@ slow_path: /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) len = mtu; - /* IF: we are not sending upto and including the packet end + /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < left) { len &= ~7; @@ -869,9 +869,9 @@ fail: return err; } -static inline int ip6_rt_check(struct rt6key *rt_key, - struct in6_addr *fl_addr, - struct in6_addr *addr_cache) +static inline int ip6_rt_check(const struct rt6key *rt_key, + const struct in6_addr *fl_addr, + const 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)); @@ -879,7 +879,7 @@ static inline int ip6_rt_check(struct rt6key *rt_key, static struct dst_entry *ip6_sk_dst_check(struct sock *sk, struct dst_entry *dst, - struct flowi6 *fl6) + const struct flowi6 *fl6) { struct ipv6_pinfo *np = inet6_sk(sk); struct rt6_info *rt = (struct rt6_info *)dst; @@ -930,10 +930,10 @@ static int ip6_dst_lookup_tail(struct sock *sk, goto out_err_release; if (ipv6_addr_any(&fl6->saddr)) { - err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev, - &fl6->daddr, - sk ? inet6_sk(sk)->srcprefs : 0, - &fl6->saddr); + struct rt6_info *rt = (struct rt6_info *) *dst; + err = ip6_route_get_saddr(net, rt, &fl6->daddr, + sk ? inet6_sk(sk)->srcprefs : 0, + &fl6->saddr); if (err) goto out_err_release; } @@ -1150,6 +1150,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); + struct inet_cork *cork; struct sk_buff *skb; unsigned int maxfraglen, fragheaderlen; int exthdrlen; @@ -1163,6 +1164,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (flags&MSG_PROBE) return 0; + cork = &inet->cork.base; if (skb_queue_empty(&sk->sk_write_queue)) { /* * setup for corking @@ -1202,7 +1204,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, /* need source address above miyazawa*/ } dst_hold(&rt->dst); - inet->cork.dst = &rt->dst; + cork->dst = &rt->dst; inet->cork.fl.u.ip6 = *fl6; np->cork.hop_limit = hlimit; np->cork.tclass = tclass; @@ -1212,10 +1214,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (np->frag_size) mtu = np->frag_size; } - inet->cork.fragsize = mtu; + cork->fragsize = mtu; if (dst_allfrag(rt->dst.path)) - inet->cork.flags |= IPCORK_ALLFRAG; - inet->cork.length = 0; + cork->flags |= IPCORK_ALLFRAG; + cork->length = 0; sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) - @@ -1223,12 +1225,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, length += exthdrlen; transhdrlen += exthdrlen; } else { - rt = (struct rt6_info *)inet->cork.dst; + rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; opt = np->cork.opt; transhdrlen = 0; exthdrlen = 0; - mtu = inet->cork.fragsize; + mtu = cork->fragsize; } hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1238,7 +1240,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) { - if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) { + if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) { ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen); return -EMSGSIZE; } @@ -1267,7 +1269,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * --yoshfuji */ - inet->cork.length += length; + cork->length += length; if (length > mtu) { int proto = sk->sk_protocol; if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ @@ -1292,7 +1294,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, while (length > 0) { /* Check if the remaining data fits into current packet. */ - copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; + copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; @@ -1317,7 +1319,7 @@ alloc_new_skb: * we know we need more fragment(s). */ datalen = length + fraggap; - if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) + if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; @@ -1481,7 +1483,7 @@ alloc_new_skb: } return 0; error: - inet->cork.length -= length; + cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; } @@ -1497,10 +1499,10 @@ static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np) np->cork.opt = NULL; } - if (inet->cork.dst) { - dst_release(inet->cork.dst); - inet->cork.dst = NULL; - inet->cork.flags &= ~IPCORK_ALLFRAG; + if (inet->cork.base.dst) { + dst_release(inet->cork.base.dst); + inet->cork.base.dst = NULL; + inet->cork.base.flags &= ~IPCORK_ALLFRAG; } memset(&inet->cork.fl, 0, sizeof(inet->cork.fl)); } @@ -1515,7 +1517,7 @@ int ip6_push_pending_frames(struct sock *sk) struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = np->cork.opt; - struct rt6_info *rt = (struct rt6_info *)inet->cork.dst; + struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst; struct flowi6 *fl6 = &inet->cork.fl.u.ip6; unsigned char proto = fl6->flowi6_proto; int err = 0; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index c1b1bd312df2..36c2842a86b2 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -162,7 +162,7 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) static struct ip6_tnl * -ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) +ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { unsigned int h0 = HASH(remote); unsigned int h1 = HASH(local); @@ -194,10 +194,10 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) **/ static struct ip6_tnl __rcu ** -ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p) +ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct ip6_tnl_parm *p) { - struct in6_addr *remote = &p->raddr; - struct in6_addr *local = &p->laddr; + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; unsigned h = 0; int prio = 0; @@ -280,11 +280,6 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) dev_net_set(dev, net); - if (strchr(name, '%')) { - if (dev_alloc_name(dev, name) < 0) - goto failed_free; - } - t = netdev_priv(dev); t->parms = *p; err = ip6_tnl_dev_init(dev); @@ -321,8 +316,8 @@ failed: static struct ip6_tnl *ip6_tnl_locate(struct net *net, struct ip6_tnl_parm *p, int create) { - struct in6_addr *remote = &p->raddr; - struct in6_addr *local = &p->laddr; + const struct in6_addr *remote = &p->raddr; + const 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); @@ -374,7 +369,7 @@ ip6_tnl_dev_uninit(struct net_device *dev) static __u16 parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw) { - struct ipv6hdr *ipv6h = (struct ipv6hdr *) raw; + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw; __u8 nexthdr = ipv6h->nexthdr; __u16 off = sizeof (*ipv6h); @@ -435,7 +430,7 @@ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) { - struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data; + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) skb->data; struct ip6_tnl *t; int rel_msg = 0; u8 rel_type = ICMPV6_DEST_UNREACH; @@ -535,8 +530,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u32 rel_info = ntohl(info); int err; struct sk_buff *skb2; - struct iphdr *eiph; + const struct iphdr *eiph; struct rtable *rt; + struct flowi4 fl4; err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); @@ -577,7 +573,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, eiph = ip_hdr(skb2); /* Try to guess incoming interface */ - rt = ip_route_output_ports(dev_net(skb->dev), NULL, + rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, 0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); @@ -590,7 +586,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); rt = NULL; - rt = ip_route_output_ports(dev_net(skb->dev), NULL, + rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, @@ -669,8 +665,8 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } -static void ip4ip6_dscp_ecn_decapsulate(struct ip6_tnl *t, - struct ipv6hdr *ipv6h, +static void ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, struct sk_buff *skb) { __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; @@ -682,8 +678,8 @@ static void ip4ip6_dscp_ecn_decapsulate(struct ip6_tnl *t, IP_ECN_set_ce(ip_hdr(skb)); } -static void ip6ip6_dscp_ecn_decapsulate(struct ip6_tnl *t, - struct ipv6hdr *ipv6h, +static void ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, struct sk_buff *skb) { if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) @@ -726,12 +722,12 @@ static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, __u8 ipproto, - void (*dscp_ecn_decapsulate)(struct ip6_tnl *t, - struct ipv6hdr *ipv6h, + void (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, struct sk_buff *skb)) { struct ip6_tnl *t; - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); rcu_read_lock(); @@ -828,7 +824,7 @@ static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) **/ static inline int -ip6_tnl_addr_conflict(struct ip6_tnl *t, struct ipv6hdr *hdr) +ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } @@ -1005,7 +1001,7 @@ static inline int ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); int encap_limit = -1; struct flowi6 fl6; __u8 dsfield; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 29e48593bf22..82a809901f8e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -989,8 +989,8 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, } static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, - struct in6_addr *origin, - struct in6_addr *mcastgrp) + const struct in6_addr *origin, + const struct in6_addr *mcastgrp) { int line = MFC6_HASH(mcastgrp, origin); struct mfc6_cache *c; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 85cccd6ed0b7..bba658d9a03c 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -55,7 +55,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, { struct net *net = dev_net(skb->dev); __be32 spi; - struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; struct ip_comp_hdr *ipcomph = (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; @@ -64,7 +64,8 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; spi = htonl(ntohs(ipcomph->cpi)); - x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, IPPROTO_COMP, AF_INET6); if (!x) return; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 76b893771e6e..3e6ebcdb4779 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -92,16 +92,16 @@ static void mld_gq_timer_expire(unsigned long data); static void mld_ifc_timer_expire(unsigned long data); static void mld_ifc_event(struct inet6_dev *idev); static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc); -static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *addr); +static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *addr); static void mld_clear_delrec(struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); static void sf_markstate(struct ifmcaddr6 *pmc); static void ip6_mc_clear_src(struct ifmcaddr6 *pmc); -static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca, - int sfmode, int sfcount, struct in6_addr *psfsrc, +static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, + int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); -static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca, - int sfmode, int sfcount, struct in6_addr *psfsrc, +static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, + int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); @@ -201,10 +201,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } -static void ipv6_mc_socklist_reclaim(struct rcu_head *head) -{ - kfree(container_of(head, struct ipv6_mc_socklist, rcu)); -} /* * socket leave on multicast group */ @@ -239,7 +235,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); - call_rcu(&mc_lst->rcu, ipv6_mc_socklist_reclaim); + kfree_rcu(mc_lst, rcu); return 0; } } @@ -250,7 +246,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) /* called with rcu_read_lock() */ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, - struct in6_addr *group, + const struct in6_addr *group, int ifindex) { struct net_device *dev = NULL; @@ -307,7 +303,7 @@ void ipv6_sock_mc_close(struct sock *sk) rcu_read_unlock(); atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); - call_rcu(&mc_lst->rcu, ipv6_mc_socklist_reclaim); + kfree_rcu(mc_lst, rcu); spin_lock(&ipv6_sk_mc_lock); } @@ -451,7 +447,7 @@ done: int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) { - struct in6_addr *group; + const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); @@ -542,7 +538,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen) { int err, i, count, copycount; - struct in6_addr *group; + const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); @@ -752,7 +748,7 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) spin_unlock_bh(&idev->mc_lock); } -static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca) +static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca) { struct ifmcaddr6 *pmc, *pmc_prev; struct ip6_sf_list *psf, *psf_next; @@ -1052,7 +1048,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) /* mark EXCLUDE-mode sources */ static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, - struct in6_addr *srcs) + const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; @@ -1080,7 +1076,7 @@ static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, } static int mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, - struct in6_addr *srcs) + const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; @@ -1115,7 +1111,7 @@ int igmp6_event_query(struct sk_buff *skb) { struct mld2_query *mlh2 = NULL; struct ifmcaddr6 *ma; - struct in6_addr *group; + const struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; struct mld_msg *mld; @@ -1821,7 +1817,7 @@ err_out: } static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, - struct in6_addr *psfsrc) + const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; int rv = 0; @@ -1857,8 +1853,8 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, return rv; } -static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca, - int sfmode, int sfcount, struct in6_addr *psfsrc, +static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, + int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; @@ -1918,7 +1914,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca, * Add multicast single-source filter to the interface list */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, - struct in6_addr *psfsrc, int delta) + const struct in6_addr *psfsrc, int delta) { struct ip6_sf_list *psf, *psf_prev; @@ -2021,8 +2017,8 @@ static int sf_setstate(struct ifmcaddr6 *pmc) /* * Add multicast source filter list to the interface list */ -static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca, - int sfmode, int sfcount, struct in6_addr *psfsrc, +static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, + int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 9b210482fb05..43242e6e6103 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -126,7 +126,7 @@ static struct mip6_report_rate_limiter mip6_report_rl = { static int mip6_destopt_input(struct xfrm_state *x, struct sk_buff *skb) { - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); struct ipv6_destopt_hdr *destopt = (struct ipv6_destopt_hdr *)skb->data; int err = destopt->nexthdr; @@ -181,8 +181,8 @@ static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb) } static inline int mip6_report_rl_allow(struct timeval *stamp, - struct in6_addr *dst, - struct in6_addr *src, int iif) + const struct in6_addr *dst, + const struct in6_addr *src, int iif) { int allow = 0; @@ -349,7 +349,7 @@ static const struct xfrm_type mip6_destopt_type = static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb) { - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); struct rt2_hdr *rt2 = (struct rt2_hdr *)skb->data; int err = rt2->rt_hdr.nexthdr; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 92f952d093db..7596f071d308 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -324,7 +324,7 @@ static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, return lladdr + prepad; } -int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir) +int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: @@ -611,6 +611,29 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, inc_opt ? ND_OPT_TARGET_LL_ADDR : 0); } +static void ndisc_send_unsol_na(struct net_device *dev) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + struct in6_addr mcaddr; + + idev = in6_dev_get(dev); + if (!idev) + return; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + addrconf_addr_solict_mult(&ifa->addr, &mcaddr); + ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr, + /*router=*/ !!idev->cnf.forwarding, + /*solicited=*/ false, /*override=*/ true, + /*inc_opt=*/ true); + } + read_unlock_bh(&idev->lock); + + in6_dev_put(idev); +} + void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr) @@ -725,8 +748,8 @@ static int pndisc_is_router(const void *pkey, static void ndisc_recv_ns(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); - struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; - struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; + const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb->tail - (skb->transport_header + offsetof(struct nd_msg, opt)); @@ -901,8 +924,8 @@ out: static void ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); - struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; - struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; + const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb->tail - (skb->transport_header + offsetof(struct nd_msg, opt)); @@ -945,9 +968,10 @@ static void ndisc_recv_na(struct sk_buff *skb) } ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { - if (ifp->flags & IFA_F_TENTATIVE) { - addrconf_dad_failure(ifp); - return; + if (skb->pkt_type != PACKET_LOOPBACK + && (ifp->flags & IFA_F_TENTATIVE)) { + addrconf_dad_failure(ifp); + return; } /* What should we make now? The advertisement is invalid, but ndisc specs say nothing @@ -1014,7 +1038,7 @@ static void ndisc_recv_rs(struct sk_buff *skb) unsigned long ndoptlen = skb->len - sizeof(*rs_msg); struct neighbour *neigh; struct inet6_dev *idev; - struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; struct ndisc_options ndopts; u8 *lladdr = NULL; @@ -1411,8 +1435,8 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) { struct inet6_dev *in6_dev; struct icmp6hdr *icmph; - struct in6_addr *dest; - struct in6_addr *target; /* new first hop to destination */ + const struct in6_addr *dest; + const struct in6_addr *target; /* new first hop to destination */ struct neighbour *neigh; int on_link = 0; struct ndisc_options ndopts; @@ -1445,7 +1469,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) } icmph = icmp6_hdr(skb); - target = (struct in6_addr *) (icmph + 1); + target = (const struct in6_addr *) (icmph + 1); dest = target + 1; if (ipv6_addr_is_multicast(dest)) { @@ -1722,6 +1746,9 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, neigh_ifdown(&nd_tbl, dev); fib6_run_gc(~0UL, net); break; + case NETDEV_NOTIFY_PEERS: + ndisc_send_unsol_na(dev); + break; default: break; } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 39aaca2b4fd2..30fcee465448 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -13,7 +13,7 @@ int ip6_route_me_harder(struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, @@ -67,7 +67,7 @@ static void nf_ip6_saveroute(const struct sk_buff *skb, struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->hook == NF_INET_LOCAL_OUT) { - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); rt_info->daddr = iph->daddr; rt_info->saddr = iph->saddr; @@ -81,7 +81,7 @@ static int nf_ip6_reroute(struct sk_buff *skb, struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->hook == NF_INET_LOCAL_OUT) { - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || skb->mark != rt_info->mark) @@ -90,16 +90,25 @@ static int nf_ip6_reroute(struct sk_buff *skb, return 0; } -static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict) { - *dst = ip6_route_output(&init_net, NULL, &fl->u.ip6); + static const struct ipv6_pinfo fake_pinfo; + static const struct inet_sock fake_sk = { + /* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */ + .sk.sk_bound_dev_if = 1, + .pinet6 = (struct ipv6_pinfo *) &fake_pinfo, + }; + const void *sk = strict ? &fake_sk : NULL; + + *dst = ip6_route_output(net, sk, &fl->u.ip6); return (*dst)->error; } __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol) { - struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); __sum16 csum = 0; switch (skb->ip_summed) { @@ -133,7 +142,7 @@ static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, unsigned int len, u_int8_t protocol) { - struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); __wsum hsum; __sum16 csum = 0; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 0b2af9b85cec..94874b0bdcdc 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -340,6 +340,7 @@ ip6t_do_table(struct sk_buff *skb, unsigned int *stackptr, origptr, cpu; const struct xt_table_info *private; struct xt_action_param acpar; + unsigned int addend; /* Initialization */ indev = in ? in->name : nulldevname; @@ -358,7 +359,8 @@ ip6t_do_table(struct sk_buff *skb, IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - xt_info_rdlock_bh(); + local_bh_disable(); + addend = xt_write_recseq_begin(); private = table->private; cpu = smp_processor_id(); table_base = private->entries[cpu]; @@ -442,7 +444,9 @@ ip6t_do_table(struct sk_buff *skb, } while (!acpar.hotdrop); *stackptr = origptr; - xt_info_rdunlock_bh(); + + xt_write_recseq_end(addend); + local_bh_enable(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -899,7 +903,7 @@ get_counters(const struct xt_table_info *t, unsigned int i; for_each_possible_cpu(cpu) { - seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries[cpu], t->size) { @@ -907,10 +911,10 @@ get_counters(const struct xt_table_info *t, unsigned int start; do { - start = read_seqbegin(lock); + start = read_seqcount_begin(s); bcnt = iter->counters.bcnt; pcnt = iter->counters.pcnt; - } while (read_seqretry(lock, start)); + } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; @@ -1325,6 +1329,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, int ret = 0; const void *loc_cpu_entry; struct ip6t_entry *iter; + unsigned int addend; #ifdef CONFIG_COMPAT struct compat_xt_counters_info compat_tmp; @@ -1381,13 +1386,13 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, i = 0; /* Choose the copy that is on our node */ curcpu = smp_processor_id(); - xt_info_wrlock(curcpu); + addend = xt_write_recseq_begin(); loc_cpu_entry = private->entries[curcpu]; xt_entry_foreach(iter, loc_cpu_entry, private->size) { ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt); ++i; } - xt_info_wrunlock(curcpu); + xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); @@ -1578,7 +1583,6 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; - struct xt_target *target; struct ip6t_entry *de; unsigned int origsize; int ret, h; @@ -1600,7 +1604,6 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, } de->target_offset = e->target_offset - (origsize - *size); t = compat_ip6t_get_target(e); - target = t->u.kernel.target; xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); @@ -2248,7 +2251,7 @@ static int __init ip6_tables_init(void) if (ret < 0) goto err1; - /* Noone else will be downing sem now, so we won't sleep */ + /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); if (ret < 0) goto err2; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 28e74488a329..a5a4c5dd5396 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -45,6 +45,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) int tcphoff, needs_ack; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); struct ipv6hdr *ip6h; +#define DEFAULT_TOS_VALUE 0x0U + const __u8 tclass = DEFAULT_TOS_VALUE; struct dst_entry *dst = NULL; u8 proto; struct flowi6 fl6; @@ -124,7 +126,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) skb_put(nskb, sizeof(struct ipv6hdr)); skb_reset_network_header(nskb); ip6h = ipv6_hdr(nskb); - ip6h->version = 6; + *(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20)); ip6h->hop_limit = ip6_dst_hoplimit(dst); ip6h->nexthdr = IPPROTO_TCP; ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 679a0a3b7b3c..00d19173db7e 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -64,7 +64,8 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || skb->mark != mark || - ipv6_hdr(skb)->hop_limit != hop_limit)) + ipv6_hdr(skb)->hop_limit != hop_limit || + flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP; return ret; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index 97c5b21b9674..cdd6d045e42e 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -71,7 +71,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (reasm == NULL) return NF_STOLEN; - /* error occured or not fragmented */ + /* error occurred or not fragmented */ if (reasm == skb) return NF_ACCEPT; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 24b3558b8e67..18ff5df7ec02 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -141,7 +141,11 @@ static const struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_SENTINEL }; -static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib) +/* can be called either with percpu mib (pcpumib != NULL), + * or shared one (smib != NULL) + */ +static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpumib, + atomic_long_t *smib) { char name[32]; int i; @@ -158,14 +162,14 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib) snprintf(name, sizeof(name), "Icmp6%s%s", i & 0x100 ? "Out" : "In", p); seq_printf(seq, "%-32s\t%lu\n", name, - snmp_fold_field(mib, i)); + pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i)); } /* print by number (nonzero only) - ICMPMsgStat format */ for (i = 0; i < ICMP6MSG_MIB_MAX; i++) { unsigned long val; - val = snmp_fold_field(mib, i); + val = pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i); if (!val) continue; snprintf(name, sizeof(name), "Icmp6%sType%u", @@ -174,14 +178,22 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib) } } -static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **mib, +/* can be called either with percpu mib (pcpumib != NULL), + * or shared one (smib != NULL) + */ +static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **pcpumib, + atomic_long_t *smib, const struct snmp_mib *itemlist) { int i; + unsigned long val; - for (i = 0; itemlist[i].name; i++) - seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, - snmp_fold_field(mib, itemlist[i].entry)); + for (i = 0; itemlist[i].name; i++) { + val = pcpumib ? + snmp_fold_field(pcpumib, itemlist[i].entry) : + atomic_long_read(smib + itemlist[i].entry); + seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, val); + } } static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu **mib, @@ -201,13 +213,13 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) snmp6_seq_show_item64(seq, (void __percpu **)net->mib.ipv6_statistics, snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp)); snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics, - snmp6_icmp6_list); + NULL, snmp6_icmp6_list); snmp6_seq_show_icmpv6msg(seq, - (void __percpu **)net->mib.icmpv6msg_statistics); + (void __percpu **)net->mib.icmpv6msg_statistics, NULL); snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6, - snmp6_udp6_list); + NULL, snmp6_udp6_list); snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6, - snmp6_udplite6_list); + NULL, snmp6_udplite6_list); return 0; } @@ -229,11 +241,11 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v) struct inet6_dev *idev = (struct inet6_dev *)seq->private; seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex); - snmp6_seq_show_item(seq, (void __percpu **)idev->stats.ipv6, + snmp6_seq_show_item(seq, (void __percpu **)idev->stats.ipv6, NULL, snmp6_ipstats_list); - snmp6_seq_show_item(seq, (void __percpu **)idev->stats.icmpv6, + snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs, snmp6_icmp6_list); - snmp6_seq_show_icmpv6msg(seq, (void __percpu **)idev->stats.icmpv6msg); + snmp6_seq_show_icmpv6msg(seq, NULL, idev->stats.icmpv6msgdev->mibs); return 0; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 4a1c3b46c56b..cc7313b8f7ea 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -67,8 +67,8 @@ static struct raw_hashinfo raw_v6_hashinfo = { }; static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, - unsigned short num, struct in6_addr *loc_addr, - struct in6_addr *rmt_addr, int dif) + unsigned short num, const struct in6_addr *loc_addr, + const struct in6_addr *rmt_addr, int dif) { struct hlist_node *node; int is_multicast = ipv6_addr_is_multicast(loc_addr); @@ -154,8 +154,8 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister); */ static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { - struct in6_addr *saddr; - struct in6_addr *daddr; + const struct in6_addr *saddr; + const struct in6_addr *daddr; struct sock *sk; int delivered = 0; __u8 hash; @@ -348,7 +348,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, { struct sock *sk; int hash; - struct in6_addr *saddr, *daddr; + const struct in6_addr *saddr, *daddr; struct net *net; hash = nexthdr & (RAW_HTABLE_SIZE - 1); @@ -357,7 +357,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (sk != NULL) { /* Note: ipv6_hdr(skb) != skb->data */ - struct ipv6hdr *ip6h = (struct ipv6hdr *)skb->data; + const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; saddr = &ip6h->saddr; daddr = &ip6h->daddr; net = dev_net(skb->dev); @@ -542,8 +542,8 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, goto out; offset = rp->offset; - total_len = inet_sk(sk)->cork.length - (skb_network_header(skb) - - skb->data); + total_len = inet_sk(sk)->cork.base.length - (skb_network_header(skb) - + skb->data); if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); @@ -1231,7 +1231,7 @@ struct proto rawv6_prot = { static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) { struct ipv6_pinfo *np = inet6_sk(sp); - struct in6_addr *dest, *src; + const struct in6_addr *dest, *src; __u16 destp, srcp; dest = &np->daddr; @@ -1240,7 +1240,7 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) srcp = inet_sk(sp)->inet_num; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 07beeb06f752..7b954e2539d0 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -224,7 +224,7 @@ out: } static __inline__ struct frag_queue * -fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst) +fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6_addr *dst) { struct inet_frag_queue *q; struct ip6_create_arg arg; @@ -535,7 +535,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) { struct frag_hdr *fhdr; struct frag_queue *fq; - struct ipv6hdr *hdr = ipv6_hdr(skb); + const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 843406f14d7b..de2b1decd786 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -89,12 +89,12 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, - struct in6_addr *prefix, int prefixlen, - struct in6_addr *gwaddr, int ifindex, + const struct in6_addr *prefix, int prefixlen, + const struct in6_addr *gwaddr, int ifindex, unsigned pref); static struct rt6_info *rt6_get_route_info(struct net *net, - struct in6_addr *prefix, int prefixlen, - struct in6_addr *gwaddr, int ifindex); + const struct in6_addr *prefix, int prefixlen, + const struct in6_addr *gwaddr, int ifindex); #endif static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) @@ -153,6 +153,12 @@ static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, + unsigned long old) +{ + return NULL; +} + static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -161,6 +167,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .default_mtu = ip6_blackhole_default_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, + .cow_metrics = ip6_rt_blackhole_cow_metrics, }; static const u32 ip6_template_metrics[RTAX_MAX] = { @@ -220,9 +227,14 @@ static struct rt6_info ip6_blk_hole_entry_template = { #endif /* allocate dst with ip6_dst_ops */ -static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops) +static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops, + struct net_device *dev) { - return (struct rt6_info *)dst_alloc(ops, 0); + struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, 0); + + memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry)); + + return rt; } static void ip6_dst_destroy(struct dst_entry *dst) @@ -283,7 +295,7 @@ static __inline__ int rt6_check_expired(const struct rt6_info *rt) time_after(jiffies, rt->rt6i_expires); } -static inline int rt6_need_strict(struct in6_addr *daddr) +static inline int rt6_need_strict(const struct in6_addr *daddr) { return ipv6_addr_type(daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); @@ -295,7 +307,7 @@ static inline int rt6_need_strict(struct in6_addr *daddr) static inline struct rt6_info *rt6_device_match(struct net *net, struct rt6_info *rt, - struct in6_addr *saddr, + const struct in6_addr *saddr, int oif, int flags) { @@ -507,7 +519,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) #ifdef CONFIG_IPV6_ROUTE_INFO int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, - struct in6_addr *gwaddr) + const struct in6_addr *gwaddr) { struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; @@ -670,8 +682,8 @@ int ip6_ins_rt(struct rt6_info *rt) return __ip6_ins_rt(rt, &info); } -static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr, - struct in6_addr *saddr) +static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct rt6_info *rt; @@ -739,7 +751,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad return rt; } -static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *daddr) +static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, const struct in6_addr *daddr) { struct rt6_info *rt = ip6_rt_copy(ort); if (rt) { @@ -830,7 +842,7 @@ static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table * void ip6_route_input(struct sk_buff *skb) { - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR; struct flowi6 fl6 = { @@ -874,11 +886,13 @@ EXPORT_SYMBOL(ip6_route_output); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rt6_info *rt = dst_alloc(&ip6_dst_blackhole_ops, 1); - struct rt6_info *ort = (struct rt6_info *) dst_orig; + struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig; struct dst_entry *new = NULL; + rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0); if (rt) { + memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry)); + new = &rt->dst; new->__use = 1; @@ -886,9 +900,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->output = dst_discard; dst_copy_metrics(new, &ort->dst); - new->dev = ort->dst.dev; - if (new->dev) - dev_hold(new->dev); rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); @@ -1031,13 +1042,12 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (unlikely(idev == NULL)) return NULL; - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev); if (unlikely(rt == NULL)) { in6_dev_put(idev); goto out; } - dev_hold(dev); if (neigh) neigh_hold(neigh); else { @@ -1046,7 +1056,6 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, neigh = NULL; } - rt->rt6i_dev = dev; rt->rt6i_idev = idev; rt->rt6i_nexthop = neigh; atomic_set(&rt->dst.__refcnt, 1); @@ -1205,7 +1214,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL); if (rt == NULL) { err = -ENOMEM; @@ -1272,7 +1281,7 @@ int ip6_route_add(struct fib6_config *cfg) } if (cfg->fc_flags & RTF_GATEWAY) { - struct in6_addr *gw_addr; + const struct in6_addr *gw_addr; int gwa_type; gw_addr = &cfg->fc_gateway; @@ -1325,6 +1334,16 @@ int ip6_route_add(struct fib6_config *cfg) if (dev == NULL) goto out; + if (!ipv6_addr_any(&cfg->fc_prefsrc)) { + if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { + err = -EINVAL; + goto out; + } + ipv6_addr_copy(&rt->rt6i_prefsrc.addr, &cfg->fc_prefsrc); + rt->rt6i_prefsrc.plen = 128; + } else + rt->rt6i_prefsrc.plen = 0; + if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev); if (IS_ERR(rt->rt6i_nexthop)) { @@ -1502,9 +1521,9 @@ out: return rt; }; -static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, - struct in6_addr *src, - struct in6_addr *gateway, +static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest, + const struct in6_addr *src, + const struct in6_addr *gateway, struct net_device *dev) { int flags = RT6_LOOKUP_F_HAS_SADDR; @@ -1526,8 +1545,8 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, flags, __ip6_route_redirect); } -void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, - struct in6_addr *saddr, +void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, + const struct in6_addr *saddr, struct neighbour *neigh, u8 *lladdr, int on_link) { struct rt6_info *rt, *nrt = NULL; @@ -1601,7 +1620,7 @@ out: * i.e. Path MTU discovery */ -static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr, +static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr, struct net *net, u32 pmtu, int ifindex) { struct rt6_info *rt, *nrt; @@ -1686,7 +1705,7 @@ out: dst_release(&rt->dst); } -void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, +void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr, struct net_device *dev, u32 pmtu) { struct net *net = dev_net(dev); @@ -1714,7 +1733,8 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) { struct net *net = dev_net(ort->rt6i_dev); - struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); + struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, + ort->dst.dev); if (rt) { rt->dst.input = ort->dst.input; @@ -1722,9 +1742,6 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) dst_copy_metrics(&rt->dst, &ort->dst); rt->dst.error = ort->dst.error; - rt->dst.dev = ort->dst.dev; - if (rt->dst.dev) - dev_hold(rt->dst.dev); rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); @@ -1739,6 +1756,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif + memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key)); rt->rt6i_table = ort->rt6i_table; } return rt; @@ -1746,8 +1764,8 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_get_route_info(struct net *net, - struct in6_addr *prefix, int prefixlen, - struct in6_addr *gwaddr, int ifindex) + const struct in6_addr *prefix, int prefixlen, + const struct in6_addr *gwaddr, int ifindex) { struct fib6_node *fn; struct rt6_info *rt = NULL; @@ -1778,8 +1796,8 @@ out: } static struct rt6_info *rt6_add_route_info(struct net *net, - struct in6_addr *prefix, int prefixlen, - struct in6_addr *gwaddr, int ifindex, + const struct in6_addr *prefix, int prefixlen, + const struct in6_addr *gwaddr, int ifindex, unsigned pref) { struct fib6_config cfg = { @@ -1807,7 +1825,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, } #endif -struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev) +struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev) { struct rt6_info *rt; struct fib6_table *table; @@ -1829,7 +1847,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d return rt; } -struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr, +struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { @@ -1994,7 +2012,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, int anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); + struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, + net->loopback_dev); struct neighbour *neigh; if (rt == NULL) { @@ -2004,15 +2023,12 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, return ERR_PTR(-ENOMEM); } - dev_hold(net->loopback_dev); in6_dev_hold(idev); rt->dst.flags = DST_HOST; rt->dst.input = ip6_input; rt->dst.output = ip6_output; - rt->rt6i_dev = net->loopback_dev; rt->rt6i_idev = idev; - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1); rt->dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; @@ -2037,6 +2053,55 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, return rt; } +int ip6_route_get_saddr(struct net *net, + struct rt6_info *rt, + const struct in6_addr *daddr, + unsigned int prefs, + struct in6_addr *saddr) +{ + struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt); + int err = 0; + if (rt->rt6i_prefsrc.plen) + ipv6_addr_copy(saddr, &rt->rt6i_prefsrc.addr); + else + err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, + daddr, prefs, saddr); + return err; +} + +/* remove deleted ip from prefsrc entries */ +struct arg_dev_net_ip { + struct net_device *dev; + struct net *net; + struct in6_addr *addr; +}; + +static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) +{ + struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev; + struct net *net = ((struct arg_dev_net_ip *)arg)->net; + struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; + + if (((void *)rt->rt6i_dev == dev || dev == NULL) && + rt != net->ipv6.ip6_null_entry && + ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { + /* remove prefsrc entry */ + rt->rt6i_prefsrc.plen = 0; + } + return 0; +} + +void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) +{ + struct net *net = dev_net(ifp->idev->dev); + struct arg_dev_net_ip adni = { + .dev = ifp->idev->dev, + .net = net, + .addr = &ifp->addr, + }; + fib6_clean_all(net, fib6_remove_prefsrc, 0, &adni); +} + struct arg_dev_net { struct net_device *dev; struct net *net; @@ -2183,6 +2248,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } + if (tb[RTA_PREFSRC]) + nla_memcpy(&cfg->fc_prefsrc, tb[RTA_PREFSRC], 16); + if (tb[RTA_OIF]) cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); @@ -2325,13 +2393,17 @@ static int rt6_fill_node(struct net *net, #endif NLA_PUT_U32(skb, RTA_IIF, iif); } else if (dst) { - struct inet6_dev *idev = ip6_dst_idev(&rt->dst); struct in6_addr saddr_buf; - if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, - dst, 0, &saddr_buf) == 0) + if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0) NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } + if (rt->rt6i_prefsrc.plen) { + struct in6_addr saddr_buf; + ipv6_addr_copy(&saddr_buf, &rt->rt6i_prefsrc.addr); + NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); + } + if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 43b33373adb2..1cca5761aea9 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -250,11 +250,6 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, dev_net_set(dev, net); - if (strchr(name, '%')) { - if (dev_alloc_name(dev, name) < 0) - goto failed_free; - } - nt = netdev_priv(dev); nt->parms = *parms; @@ -401,11 +396,6 @@ out: return err; } -static void prl_entry_destroy_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct ip_tunnel_prl_entry, rcu_head)); -} - static void prl_list_destroy_rcu(struct rcu_head *head) { struct ip_tunnel_prl_entry *p, *n; @@ -433,7 +423,7 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) p = &x->next) { if (x->addr == a->addr) { *p = x->next; - call_rcu(&x->rcu_head, prl_entry_destroy_rcu); + kfree_rcu(x, rcu_head); t->prl_count--; goto out; } @@ -452,7 +442,7 @@ out: } static int -isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t) +isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t) { struct ip_tunnel_prl_entry *p; int ok = 1; @@ -465,7 +455,8 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t) else skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT; } else { - struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr; + const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr; + if (ipv6_addr_is_isatap(addr6) && (addr6->s6_addr32[3] == iph->saddr) && ipv6_chk_prefix(addr6, t->dev)) @@ -499,7 +490,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. */ - struct iphdr *iph = (struct iphdr*)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; @@ -557,7 +548,7 @@ out: return err; } -static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) +static inline void ipip6_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb) { if (INET_ECN_is_ce(iph->tos)) IP6_ECN_set_ce(ipv6_hdr(skb)); @@ -565,7 +556,7 @@ static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) static int ipip6_rcv(struct sk_buff *skb) { - struct iphdr *iph; + const struct iphdr *iph; struct ip_tunnel *tunnel; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) @@ -621,7 +612,7 @@ out: * comes from 6rd / 6to4 (RFC 3056) addr space. */ static inline -__be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel) +__be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel) { __be32 dst = 0; @@ -664,8 +655,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, { struct ip_tunnel *tunnel = netdev_priv(dev); struct pcpu_tstats *tstats; - struct iphdr *tiph = &tunnel->parms.iph; - struct ipv6hdr *iph6 = ipv6_hdr(skb); + const struct iphdr *tiph = &tunnel->parms.iph; + const 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 */ @@ -673,8 +664,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; + struct flowi4 fl4; int mtu; - struct in6_addr *addr6; + const struct in6_addr *addr6; int addr_type; if (skb->protocol != htons(ETH_P_IPV6)) @@ -693,7 +685,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } - addr6 = (struct in6_addr*)&neigh->primary_key; + addr6 = (const struct in6_addr*)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if ((addr_type & IPV6_ADDR_UNICAST) && @@ -718,7 +710,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } - addr6 = (struct in6_addr*)&neigh->primary_key; + addr6 = (const struct in6_addr*)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { @@ -732,7 +724,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, dst = addr6->s6_addr32[3]; } - rt = ip_route_output_ports(dev_net(dev), NULL, + rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, dst, tiph->saddr, 0, 0, IPPROTO_IPV6, RT_TOS(tos), @@ -826,8 +818,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, iph->frag_off = df; iph->protocol = IPPROTO_IPV6; iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); - iph->daddr = rt->rt_dst; - iph->saddr = rt->rt_src; + iph->daddr = fl4.daddr; + iph->saddr = fl4.saddr; if ((iph->ttl = tiph->ttl) == 0) iph->ttl = iph6->hop_limit; @@ -849,13 +841,14 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; struct ip_tunnel *tunnel; - struct iphdr *iph; + const struct iphdr *iph; + struct flowi4 fl4; tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; if (iph->daddr) { - struct rtable *rt = ip_route_output_ports(dev_net(dev), NULL, + struct rtable *rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, iph->daddr, iph->saddr, 0, 0, IPPROTO_IPV6, diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 352c26081f5d..8b9644a8b697 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -66,7 +66,7 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch); -static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr, +static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, u32 count, int c) { __u32 *tmp = __get_cpu_var(ipv6_cookie_scratch); @@ -86,7 +86,8 @@ static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr, return tmp[17]; } -static __u32 secure_tcp_syn_cookie(struct in6_addr *saddr, struct in6_addr *daddr, +static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, + const struct in6_addr *daddr, __be16 sport, __be16 dport, __u32 sseq, __u32 count, __u32 data) { @@ -96,8 +97,8 @@ static __u32 secure_tcp_syn_cookie(struct in6_addr *saddr, struct in6_addr *dadd & COOKIEMASK)); } -static __u32 check_tcp_syn_cookie(__u32 cookie, struct in6_addr *saddr, - struct in6_addr *daddr, __be16 sport, +static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, + const struct in6_addr *daddr, __be16 sport, __be16 dport, __u32 sseq, __u32 count, __u32 maxdiff) { @@ -116,7 +117,7 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, struct in6_addr *saddr, __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) { - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); int mssind; const __u16 mss = *mssp; @@ -138,7 +139,7 @@ __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) static inline int cookie_check(struct sk_buff *skb, __u32 cookie) { - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); __u32 seq = ntohl(th->seq) - 1; __u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2b0c186862c8..d1fd28711ba5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -76,8 +76,8 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static void __tcp_v6_send_check(struct sk_buff *skb, - struct in6_addr *saddr, - struct in6_addr *daddr); + const struct in6_addr *saddr, + const struct in6_addr *daddr); static const struct inet_connection_sock_af_ops ipv6_mapped; static const struct inet_connection_sock_af_ops ipv6_specific; @@ -86,7 +86,7 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #else static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, - struct in6_addr *addr) + const struct in6_addr *addr) { return NULL; } @@ -106,8 +106,8 @@ static void tcp_v6_hash(struct sock *sk) } static __inline__ __sum16 tcp_v6_check(int len, - struct in6_addr *saddr, - struct in6_addr *daddr, + const struct in6_addr *saddr, + const struct in6_addr *daddr, __wsum base) { return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); @@ -331,7 +331,7 @@ failure: static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; + const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct ipv6_pinfo *np; struct sock *sk; @@ -503,6 +503,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); if (IS_ERR(dst)) { err = PTR_ERR(dst); + dst = NULL; goto done; } skb = tcp_make_synack(sk, dst, req, rvp); @@ -550,7 +551,7 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req) #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, - struct in6_addr *addr) + const struct in6_addr *addr) { struct tcp_sock *tp = tcp_sk(sk); int i; @@ -579,7 +580,7 @@ static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr); } -static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, +static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer, char *newkey, u8 newkeylen) { /* Add key to the list */ @@ -644,7 +645,7 @@ static int tcp_v6_md5_add_func(struct sock *sk, struct sock *addr_sk, newkey, newkeylen); } -static int tcp_v6_md5_do_del(struct sock *sk, struct in6_addr *peer) +static int tcp_v6_md5_do_del(struct sock *sk, const struct in6_addr *peer) { struct tcp_sock *tp = tcp_sk(sk); int i; @@ -752,8 +753,8 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, } static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, - struct in6_addr *daddr, - struct in6_addr *saddr, int nbytes) + const struct in6_addr *daddr, + const struct in6_addr *saddr, int nbytes) { struct tcp6_pseudohdr *bp; struct scatterlist sg; @@ -770,7 +771,7 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, } static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, - struct in6_addr *daddr, struct in6_addr *saddr, + const struct in6_addr *daddr, struct in6_addr *saddr, struct tcphdr *th) { struct tcp_md5sig_pool *hp; @@ -806,7 +807,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, struct sock *sk, struct request_sock *req, struct sk_buff *skb) { - struct in6_addr *saddr, *daddr; + const struct in6_addr *saddr, *daddr; struct tcp_md5sig_pool *hp; struct hash_desc *desc; struct tcphdr *th = tcp_hdr(skb); @@ -818,7 +819,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, saddr = &inet6_rsk(req)->loc_addr; daddr = &inet6_rsk(req)->rmt_addr; } else { - struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; daddr = &ip6h->daddr; } @@ -856,7 +857,7 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) { __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; - struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); int genhash; u8 newhash[16]; @@ -914,7 +915,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { #endif static void __tcp_v6_send_check(struct sk_buff *skb, - struct in6_addr *saddr, struct in6_addr *daddr) + const struct in6_addr *saddr, const struct in6_addr *daddr) { struct tcphdr *th = tcp_hdr(skb); @@ -938,7 +939,7 @@ static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) static int tcp_v6_gso_send_check(struct sk_buff *skb) { - struct ipv6hdr *ipv6h; + const struct ipv6hdr *ipv6h; struct tcphdr *th; if (!pskb_may_pull(skb, sizeof(*th))) @@ -956,7 +957,7 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb) static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - struct ipv6hdr *iph = skb_gro_network_header(skb); + const struct ipv6hdr *iph = skb_gro_network_header(skb); switch (skb->ip_summed) { case CHECKSUM_COMPLETE: @@ -977,7 +978,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, static int tcp6_gro_complete(struct sk_buff *skb) { - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), @@ -1468,7 +1469,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, First: no IPv4 options. */ - newinet->opt = NULL; + newinet->inet_opt = NULL; newnp->ipv6_fl_list = NULL; /* Clone RX bits */ @@ -1621,6 +1622,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, GFP_ATOMIC); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + sock_rps_save_rxhash(sk, skb->rxhash); if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; if (opt_skb) @@ -1648,7 +1650,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) __kfree_skb(opt_skb); return 0; } - } + } else + sock_rps_save_rxhash(sk, skb->rxhash); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) goto reset; @@ -1699,7 +1702,7 @@ ipv6_pktoptions: static int tcp_v6_rcv(struct sk_buff *skb) { struct tcphdr *th; - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; struct sock *sk; int ret; struct net *net = dev_net(skb->dev); @@ -2025,15 +2028,15 @@ static void get_openreq6(struct seq_file *seq, struct sock *sk, struct request_sock *req, int i, int uid) { int ttd = req->expires - jiffies; - struct in6_addr *src = &inet6_rsk(req)->loc_addr; - struct in6_addr *dest = &inet6_rsk(req)->rmt_addr; + const struct in6_addr *src = &inet6_rsk(req)->loc_addr; + const struct in6_addr *dest = &inet6_rsk(req)->rmt_addr; if (ttd < 0) ttd = 0; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], @@ -2054,7 +2057,7 @@ static void get_openreq6(struct seq_file *seq, static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) { - struct in6_addr *dest, *src; + const struct in6_addr *dest, *src; __u16 destp, srcp; int timer_active; unsigned long timer_expires; @@ -2084,7 +2087,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %lu %lu %u %u %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, @@ -2111,7 +2114,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { - struct in6_addr *dest, *src; + const struct in6_addr *dest, *src; __u16 destp, srcp; struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); int ttd = tw->tw_ttd - jiffies; @@ -2126,7 +2129,7 @@ static void get_timewait6_sock(struct seq_file *seq, seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d7037c006e13..41f8c9c08dba 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -311,7 +311,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, struct udp_table *udptable) { struct sock *sk; - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); if (unlikely(sk = skb_steal_sock(skb))) return sk; @@ -463,9 +463,9 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct udp_table *udptable) { struct ipv6_pinfo *np; - struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; - struct in6_addr *saddr = &hdr->saddr; - struct in6_addr *daddr = &hdr->daddr; + const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; + const struct in6_addr *saddr = &hdr->saddr; + const struct in6_addr *daddr = &hdr->daddr; struct udphdr *uh = (struct udphdr*)(skb->data+offset); struct sock *sk; int err; @@ -505,6 +505,9 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) int rc; int is_udplite = IS_UDPLITE(sk); + if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) + sock_rps_save_rxhash(sk, skb->rxhash); + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; @@ -550,8 +553,8 @@ drop_no_sk_drops_inc: } static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, - __be16 loc_port, struct in6_addr *loc_addr, - __be16 rmt_port, struct in6_addr *rmt_addr, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, int dif) { struct hlist_nulls_node *node; @@ -630,7 +633,7 @@ drop: * so we don't need to lock the hashes. */ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, - struct in6_addr *saddr, struct in6_addr *daddr, + const struct in6_addr *saddr, const struct in6_addr *daddr, struct udp_table *udptable) { struct sock *sk, *stack[256 / sizeof(struct sock *)]; @@ -713,7 +716,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct net *net = dev_net(skb->dev); struct sock *sk; struct udphdr *uh; - struct in6_addr *saddr, *daddr; + const struct in6_addr *saddr, *daddr; u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) @@ -1275,7 +1278,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, static int udp6_ufo_send_check(struct sk_buff *skb) { - struct ipv6hdr *ipv6h; + const struct ipv6hdr *ipv6h; struct udphdr *uh; if (!pskb_may_pull(skb, sizeof(*uh))) @@ -1325,14 +1328,14 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features) /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ - offset = skb->csum_start - skb_headroom(skb); + offset = skb_checksum_start_offset(skb); csum = skb_checksum(skb, offset, skb->len- offset, 0); offset += skb->csum_offset; *(__sum16 *)(skb->data + offset) = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; /* Check if there is enough headroom to insert fragment header. */ - if ((skb_headroom(skb) < frag_hdr_sz) && + if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) goto out; @@ -1379,7 +1382,7 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket { struct inet_sock *inet = inet_sk(sp); struct ipv6_pinfo *np = inet6_sk(sp); - struct in6_addr *dest, *src; + const struct in6_addr *dest, *src; __u16 destp, srcp; dest = &np->daddr; @@ -1388,7 +1391,7 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket srcp = ntohs(inet->inet_sport); seq_printf(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", bucket, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index bbd48b101bae..3437d7d4eed6 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -41,10 +41,8 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *top_iph; struct ip_beet_phdr *ph; - struct iphdr *iphv4; int optlen, hdr_len; - iphv4 = ip_hdr(skb); hdr_len = 0; optlen = XFRM_MODE_SKB_CB(skb)->optlen; if (unlikely(optlen)) diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 645cb968d450..4d6edff0498f 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -20,7 +20,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) { - struct ipv6hdr *outer_iph = ipv6_hdr(skb); + const struct ipv6hdr *outer_iph = ipv6_hdr(skb); struct ipv6hdr *inner_iph = ipipv6_hdr(skb); if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) @@ -55,8 +55,8 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) dsfield &= ~INET_ECN_MASK; ipv6_change_dsfield(top_iph, 0, dsfield); top_iph->hop_limit = ip6_dst_hoplimit(dst->child); - ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); - ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); + ipv6_addr_copy(&top_iph->saddr, (const struct in6_addr *)&x->props.saddr); + ipv6_addr_copy(&top_iph->daddr, (const struct in6_addr *)&x->id.daddr); return 0; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8e688b3de9ab..49a91c5f5623 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -79,7 +79,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm6_prepare_output); -static int xfrm6_output_finish(struct sk_buff *skb) +int xfrm6_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; @@ -97,9 +97,9 @@ static int __xfrm6_output(struct sk_buff *skb) if ((x && x->props.mode == XFRM_MODE_TUNNEL) && ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { - return ip6_fragment(skb, xfrm6_output_finish); + return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); } - return xfrm6_output_finish(skb); + return x->outer_mode->afinfo->output_finish(skb); } int xfrm6_output(struct sk_buff *skb) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 05e34c8ec913..d879f7efbd10 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -124,7 +124,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) struct flowi6 *fl6 = &fl->u.ip6; int onlyproto = 0; u16 offset = skb_network_header_len(skb); - struct ipv6hdr *hdr = ipv6_hdr(skb); + const struct ipv6hdr *hdr = ipv6_hdr(skb); struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u8 nexthdr = nh[IP6CB(skb)->nhoff]; diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index afe941e9415c..248f0b2a7ee9 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -178,6 +178,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, + .output_finish = xfrm6_output_finish, .extract_input = xfrm6_extract_input, .extract_output = xfrm6_extract_output, .transport_finish = xfrm6_transport_finish, diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 2969cad408de..4fe1db12d2a3 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -68,7 +68,7 @@ static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock); static struct kmem_cache *xfrm6_tunnel_spi_kmem __read_mostly; -static inline unsigned xfrm6_tunnel_spi_hash_byaddr(xfrm_address_t *addr) +static inline unsigned xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *addr) { unsigned h; @@ -85,7 +85,7 @@ static inline unsigned xfrm6_tunnel_spi_hash_byspi(u32 spi) return spi % XFRM6_TUNNEL_SPI_BYSPI_HSIZE; } -static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr) +static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; @@ -101,7 +101,7 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, xfrm_ return NULL; } -__be32 xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr) +__be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; @@ -237,11 +237,11 @@ static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_tunnel_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); - struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph = ipv6_hdr(skb); __be32 spi; - spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&iph->saddr); - return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi) > 0 ? : 0; + spi = xfrm6_tunnel_spi_lookup(net, (const xfrm_address_t *)&iph->saddr); + return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi); } static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index c9890e25cd4c..cc616974a447 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1297,8 +1297,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock, /* Note : socket.c set MSG_EOR on SEQPACKET sockets */ if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_EOR | MSG_CMSG_COMPAT | MSG_NOSIGNAL)) { - err = -EINVAL; - goto out; + return -EINVAL; } lock_sock(sk); diff --git a/net/irda/ircomm/ircomm_core.c b/net/irda/ircomm/ircomm_core.c index e97082017f4f..52079f19bbbe 100644 --- a/net/irda/ircomm/ircomm_core.c +++ b/net/irda/ircomm/ircomm_core.c @@ -244,14 +244,8 @@ EXPORT_SYMBOL(ircomm_connect_request); void ircomm_connect_indication(struct ircomm_cb *self, struct sk_buff *skb, struct ircomm_info *info) { - int clen = 0; - IRDA_DEBUG(2, "%s()\n", __func__ ); - /* Check if the packet contains data on the control channel */ - if (skb->len > 0) - clen = skb->data[0]; - /* * If there are any data hiding in the control channel, we must * deliver it first. The side effect is that the control channel diff --git a/net/irda/ircomm/ircomm_lmp.c b/net/irda/ircomm/ircomm_lmp.c index 08fb54dc8c41..3b8095c771d4 100644 --- a/net/irda/ircomm/ircomm_lmp.c +++ b/net/irda/ircomm/ircomm_lmp.c @@ -75,7 +75,6 @@ static int ircomm_lmp_connect_response(struct ircomm_cb *self, struct sk_buff *userdata) { struct sk_buff *tx_skb; - int ret; IRDA_DEBUG(0, "%s()\n", __func__ ); @@ -100,9 +99,7 @@ static int ircomm_lmp_connect_response(struct ircomm_cb *self, tx_skb = userdata; } - ret = irlmp_connect_response(self->lsap, tx_skb); - - return 0; + return irlmp_connect_response(self->lsap, tx_skb); } static int ircomm_lmp_disconnect_request(struct ircomm_cb *self, diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index a39cca8331df..b3cc8b3989a9 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -38,6 +38,7 @@ #include <linux/seq_file.h> #include <linux/termios.h> #include <linux/tty.h> +#include <linux/tty_flip.h> #include <linux/interrupt.h> #include <linux/device.h> /* for MODULE_ALIAS_CHARDEV_MAJOR */ @@ -1132,7 +1133,6 @@ static int ircomm_tty_data_indication(void *instance, void *sap, struct sk_buff *skb) { struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) instance; - struct tty_ldisc *ld; IRDA_DEBUG(2, "%s()\n", __func__ ); @@ -1161,15 +1161,11 @@ static int ircomm_tty_data_indication(void *instance, void *sap, } /* - * Just give it over to the line discipline. There is no need to - * involve the flip buffers, since we are not running in an interrupt - * handler + * Use flip buffer functions since the code may be called from interrupt + * context */ - - ld = tty_ldisc_ref(self->tty); - if (ld) - ld->ops->receive_buf(self->tty, skb->data, NULL, skb->len); - tty_ldisc_deref(ld); + tty_insert_flip_string(self->tty, skb->data, skb->len); + tty_flip_buffer_push(self->tty); /* No need to kfree_skb - see ircomm_ttp_data_indication() */ diff --git a/net/irda/irlan/irlan_filter.c b/net/irda/irlan/irlan_filter.c index 9ff7823abec7..7977be7caf0f 100644 --- a/net/irda/irlan/irlan_filter.c +++ b/net/irda/irlan/irlan_filter.c @@ -143,12 +143,8 @@ void irlan_filter_request(struct irlan_cb *self, struct sk_buff *skb) */ void irlan_check_command_param(struct irlan_cb *self, char *param, char *value) { - __u8 *bytes; - IRDA_DEBUG(4, "%s()\n", __func__ ); - bytes = value; - IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); diff --git a/net/irda/irlan/irlan_provider.c b/net/irda/irlan/irlan_provider.c index 5cf5e6c872bb..b8af74ab8b68 100644 --- a/net/irda/irlan/irlan_provider.c +++ b/net/irda/irlan/irlan_provider.c @@ -128,7 +128,6 @@ static void irlan_provider_connect_indication(void *instance, void *sap, { struct irlan_cb *self; struct tsap_cb *tsap; - __u32 saddr, daddr; IRDA_DEBUG(0, "%s()\n", __func__ ); @@ -141,8 +140,6 @@ static void irlan_provider_connect_indication(void *instance, void *sap, IRDA_ASSERT(tsap == self->provider.tsap_ctrl,return;); IRDA_ASSERT(self->provider.state == IRLAN_IDLE, return;); - daddr = irttp_get_daddr(tsap); - saddr = irttp_get_saddr(tsap); self->provider.max_sdu_size = max_sdu_size; self->provider.max_header_size = max_header_size; diff --git a/net/irda/irlap.c b/net/irda/irlap.c index 783c5f367d29..005b424494a0 100644 --- a/net/irda/irlap.c +++ b/net/irda/irlap.c @@ -165,7 +165,7 @@ struct irlap_cb *irlap_open(struct net_device *dev, struct qos_info *qos, irlap_apply_default_connection_parameters(self); - self->N3 = 3; /* # connections attemts to try before giving up */ + self->N3 = 3; /* # connections attempts to try before giving up */ self->state = LAP_NDM; diff --git a/net/irda/irlap_event.c b/net/irda/irlap_event.c index d434c8880745..ccd214f9d196 100644 --- a/net/irda/irlap_event.c +++ b/net/irda/irlap_event.c @@ -708,7 +708,7 @@ static int irlap_state_reply(struct irlap_cb *self, IRLAP_EVENT event, self->frame_sent = TRUE; } - /* Readjust our timer to accomodate devices + /* Readjust our timer to accommodate devices * doing faster or slower discovery than us... * Jean II */ irlap_start_query_timer(self, info->S, info->s); @@ -931,7 +931,7 @@ static int irlap_state_setup(struct irlap_cb *self, IRLAP_EVENT event, irlap_send_rr_frame(self, CMD_FRAME); /* The timer is set to half the normal timer to quickly - * detect a failure to negociate the new connection + * detect a failure to negotiate the new connection * parameters. IrLAP 6.11.3.2, note 3. * Note that currently we don't process this failure * properly, as we should do a quick disconnect. @@ -1052,7 +1052,7 @@ static int irlap_state_xmit_p(struct irlap_cb *self, IRLAP_EVENT event, return -EPROTO; } - /* Substract space used by this skb */ + /* Subtract space used by this skb */ self->bytes_left -= skb->len; #else /* CONFIG_IRDA_DYNAMIC_WINDOW */ /* Window has been adjusted for the max packet @@ -1808,7 +1808,7 @@ static int irlap_state_xmit_s(struct irlap_cb *self, IRLAP_EVENT event, return -EPROTO; /* Try again later */ } - /* Substract space used by this skb */ + /* Subtract space used by this skb */ self->bytes_left -= skb->len; #else /* CONFIG_IRDA_DYNAMIC_WINDOW */ /* Window has been adjusted for the max packet @@ -2227,8 +2227,6 @@ static int irlap_state_nrm_s(struct irlap_cb *self, IRLAP_EVENT event, static int irlap_state_sclose(struct irlap_cb *self, IRLAP_EVENT event, struct sk_buff *skb, struct irlap_info *info) { - int ret = 0; - IRDA_DEBUG(1, "%s()\n", __func__); IRDA_ASSERT(self != NULL, return -ENODEV;); @@ -2289,7 +2287,6 @@ static int irlap_state_sclose(struct irlap_cb *self, IRLAP_EVENT event, IRDA_DEBUG(1, "%s(), Unknown event %d, (%s)\n", __func__, event, irlap_event[event]); - ret = -EINVAL; break; } diff --git a/net/irda/irlap_frame.c b/net/irda/irlap_frame.c index 688222cbf55b..8c004161a843 100644 --- a/net/irda/irlap_frame.c +++ b/net/irda/irlap_frame.c @@ -848,7 +848,7 @@ void irlap_send_data_primary_poll(struct irlap_cb *self, struct sk_buff *skb) * though IrLAP is currently sending the *last* frame of the * tx-window, the driver most likely has only just started * sending the *first* frame of the same tx-window. - * I.e. we are always at the very begining of or Tx window. + * I.e. we are always at the very beginning of or Tx window. * Now, we are supposed to set the final timer from the end * of our tx-window to let the other peer reply. So, we need * to add extra time to compensate for the fact that we diff --git a/net/irda/irlmp_event.c b/net/irda/irlmp_event.c index c1fb5db81042..9505a7d06f1a 100644 --- a/net/irda/irlmp_event.c +++ b/net/irda/irlmp_event.c @@ -498,7 +498,7 @@ static int irlmp_state_disconnected(struct lsap_cb *self, IRLMP_EVENT event, switch (event) { #ifdef CONFIG_IRDA_ULTRA case LM_UDATA_INDICATION: - /* This is most bizzare. Those packets are aka unreliable + /* This is most bizarre. Those packets are aka unreliable * connected, aka IrLPT or SOCK_DGRAM/IRDAPROTO_UNITDATA. * Why do we pass them as Ultra ??? Jean II */ irlmp_connless_data_indication(self, skb); diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index 0d82ff5aeff1..979ecb2435a7 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -73,7 +73,7 @@ * Infinite thanks to those brave souls for providing the infrastructure * upon which IrNET is built. * - * Thanks to all my collegues in HP for helping me. In particular, + * Thanks to all my colleagues in HP for helping me. In particular, * thanks to Salil Pradhan and Bill Serra for W2k testing... * Thanks to Luiz Magalhaes for irnetd and much testing... * diff --git a/net/irda/irproc.c b/net/irda/irproc.c index 318766e5dbdf..b9ac598e2116 100644 --- a/net/irda/irproc.c +++ b/net/irda/irproc.c @@ -65,15 +65,14 @@ static const struct irda_entry irda_dirs[] = { void __init irda_proc_register(void) { int i; - struct proc_dir_entry *d; proc_irda = proc_mkdir("irda", init_net.proc_net); if (proc_irda == NULL) return; for (i = 0; i < ARRAY_SIZE(irda_dirs); i++) - d = proc_create(irda_dirs[i].name, 0, proc_irda, - irda_dirs[i].fops); + (void) proc_create(irda_dirs[i].name, 0, proc_irda, + irda_dirs[i].fops); } /* diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c index 849aaf0dabb5..9715e6e5900b 100644 --- a/net/irda/irqueue.c +++ b/net/irda/irqueue.c @@ -40,7 +40,7 @@ * o the hash function for ints is pathetic (but could be changed) * o locking is sometime suspicious (especially during enumeration) * o most users have only a few elements (== overhead) - * o most users never use seach, so don't benefit from hashing + * o most users never use search, so don't benefit from hashing * Problem already fixed : * o not 64 bit compliant (most users do hashv = (int) self) * o hashbin_remove() is broken => use hashbin_remove_this() diff --git a/net/irda/irttp.c b/net/irda/irttp.c index f6054f9ccbe3..9d9af4606970 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -1193,7 +1193,7 @@ EXPORT_SYMBOL(irttp_connect_request); /* * Function irttp_connect_confirm (handle, qos, skb) * - * Sevice user confirms TSAP connection with peer. + * Service user confirms TSAP connection with peer. * */ static void irttp_connect_confirm(void *instance, void *sap, diff --git a/net/irda/qos.c b/net/irda/qos.c index 2b00974e5bae..1b51bcf42394 100644 --- a/net/irda/qos.c +++ b/net/irda/qos.c @@ -39,16 +39,16 @@ #include <net/irda/irlap_frame.h> /* - * Maximum values of the baud rate we negociate with the other end. + * Maximum values of the baud rate we negotiate with the other end. * Most often, you don't have to change that, because Linux-IrDA will * use the maximum offered by the link layer, which usually works fine. * In some very rare cases, you may want to limit it to lower speeds... */ int sysctl_max_baud_rate = 16000000; /* - * Maximum value of the lap disconnect timer we negociate with the other end. + * Maximum value of the lap disconnect timer we negotiate with the other end. * Most often, the value below represent the best compromise, but some user - * may want to keep the LAP alive longuer or shorter in case of link failure. + * may want to keep the LAP alive longer or shorter in case of link failure. * Remember that the threshold time (early warning) is fixed to 3s... */ int sysctl_max_noreply_time = 12; @@ -411,7 +411,7 @@ static void irlap_adjust_qos_settings(struct qos_info *qos) * Fix tx data size according to user limits - Jean II */ if (qos->data_size.value > sysctl_max_tx_data_size) - /* Allow non discrete adjustement to avoid loosing capacity */ + /* Allow non discrete adjustement to avoid losing capacity */ qos->data_size.value = sysctl_max_tx_data_size; /* * Override Tx window if user request it. - Jean II diff --git a/net/irda/timer.c b/net/irda/timer.c index 0335ba0cc593..f418cb2ad49c 100644 --- a/net/irda/timer.c +++ b/net/irda/timer.c @@ -59,7 +59,7 @@ void irlap_start_query_timer(struct irlap_cb *self, int S, int s) * slot time, plus add some extra time to properly receive the last * discovery packet (which is longer due to extra discovery info), * to avoid messing with for incomming connections requests and - * to accomodate devices that perform discovery slower than us. + * to accommodate devices that perform discovery slower than us. * Jean II */ timeout = ((sysctl_slot_timeout * HZ / 1000) * (S - s) + XIDEXTRA_TIMEOUT + SMALLBUSY_TIMEOUT); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 9637e45744fa..e2013e434d03 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -190,7 +190,6 @@ static int afiucv_pm_freeze(struct device *dev) */ static int afiucv_pm_restore_thaw(struct device *dev) { - struct iucv_sock *iucv; struct sock *sk; struct hlist_node *node; @@ -199,7 +198,6 @@ static int afiucv_pm_restore_thaw(struct device *dev) #endif read_lock(&iucv_sk_list.lock); sk_for_each(sk, node, &iucv_sk_list.head) { - iucv = iucv_sk(sk); switch (sk->sk_state) { case IUCV_CONNECTED: sk->sk_err = EPIPE; @@ -250,7 +248,7 @@ static struct device *af_iucv_dev; * PRMDATA[0..6] socket data (max 7 bytes); * PRMDATA[7] socket data length value (len is 0xff - PRMDATA[7]) * - * The socket data length is computed by substracting the socket data length + * The socket data length is computed by subtracting the socket data length * value from 0xFF. * If the socket data len is greater 7, then PRMDATA can be used for special * notifications (see iucv_sock_shutdown); and further, @@ -381,7 +379,6 @@ static void iucv_sock_close(struct sock *sk) { unsigned char user_data[16]; struct iucv_sock *iucv = iucv_sk(sk); - int err; unsigned long timeo; iucv_sock_clear_timer(sk); @@ -394,8 +391,6 @@ static void iucv_sock_close(struct sock *sk) case IUCV_CONNECTED: case IUCV_DISCONN: - err = 0; - sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); @@ -404,7 +399,7 @@ static void iucv_sock_close(struct sock *sk) timeo = sk->sk_lingertime; else timeo = IUCV_DISCONN_TIMEOUT; - err = iucv_sock_wait(sk, + iucv_sock_wait(sk, iucv_sock_in_state(sk, IUCV_CLOSED, 0), timeo); } @@ -417,7 +412,7 @@ static void iucv_sock_close(struct sock *sk) low_nmcpy(user_data, iucv->src_name); high_nmcpy(user_data, iucv->dst_name); ASCEBC(user_data, sizeof(user_data)); - err = iucv_path_sever(iucv->path, user_data); + iucv_path_sever(iucv->path, user_data); iucv_path_free(iucv->path); iucv->path = NULL; } diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 1ee5dab3cfae..a15c01524959 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -128,8 +128,8 @@ struct iucv_irq_list { }; static struct iucv_irq_data *iucv_irq_data[NR_CPUS]; -static cpumask_t iucv_buffer_cpumask = CPU_MASK_NONE; -static cpumask_t iucv_irq_cpumask = CPU_MASK_NONE; +static cpumask_t iucv_buffer_cpumask = { CPU_BITS_NONE }; +static cpumask_t iucv_irq_cpumask = { CPU_BITS_NONE }; /* * Queue of interrupt buffers lock for delivery via the tasklet @@ -406,7 +406,7 @@ static void iucv_allow_cpu(void *data) parm->set_mask.ipmask = 0xf8; iucv_call_b2f0(IUCV_SETCONTROLMASK, parm); /* Set indication that iucv interrupts are allowed for this cpu. */ - cpu_set(cpu, iucv_irq_cpumask); + cpumask_set_cpu(cpu, &iucv_irq_cpumask); } /** @@ -426,7 +426,7 @@ static void iucv_block_cpu(void *data) iucv_call_b2f0(IUCV_SETMASK, parm); /* Clear indication that iucv interrupts are allowed for this cpu. */ - cpu_clear(cpu, iucv_irq_cpumask); + cpumask_clear_cpu(cpu, &iucv_irq_cpumask); } /** @@ -451,7 +451,7 @@ static void iucv_block_cpu_almost(void *data) iucv_call_b2f0(IUCV_SETCONTROLMASK, parm); /* Clear indication that iucv interrupts are allowed for this cpu. */ - cpu_clear(cpu, iucv_irq_cpumask); + cpumask_clear_cpu(cpu, &iucv_irq_cpumask); } /** @@ -466,7 +466,7 @@ static void iucv_declare_cpu(void *data) union iucv_param *parm; int rc; - if (cpu_isset(cpu, iucv_buffer_cpumask)) + if (cpumask_test_cpu(cpu, &iucv_buffer_cpumask)) return; /* Declare interrupt buffer. */ @@ -499,9 +499,9 @@ static void iucv_declare_cpu(void *data) } /* Set indication that an iucv buffer exists for this cpu. */ - cpu_set(cpu, iucv_buffer_cpumask); + cpumask_set_cpu(cpu, &iucv_buffer_cpumask); - if (iucv_nonsmp_handler == 0 || cpus_empty(iucv_irq_cpumask)) + if (iucv_nonsmp_handler == 0 || cpumask_empty(&iucv_irq_cpumask)) /* Enable iucv interrupts on this cpu. */ iucv_allow_cpu(NULL); else @@ -520,7 +520,7 @@ static void iucv_retrieve_cpu(void *data) int cpu = smp_processor_id(); union iucv_param *parm; - if (!cpu_isset(cpu, iucv_buffer_cpumask)) + if (!cpumask_test_cpu(cpu, &iucv_buffer_cpumask)) return; /* Block iucv interrupts. */ @@ -531,7 +531,7 @@ static void iucv_retrieve_cpu(void *data) iucv_call_b2f0(IUCV_RETRIEVE_BUFFER, parm); /* Clear indication that an iucv buffer exists for this cpu. */ - cpu_clear(cpu, iucv_buffer_cpumask); + cpumask_clear_cpu(cpu, &iucv_buffer_cpumask); } /** @@ -546,8 +546,8 @@ static void iucv_setmask_mp(void) get_online_cpus(); for_each_online_cpu(cpu) /* Enable all cpus with a declared buffer. */ - if (cpu_isset(cpu, iucv_buffer_cpumask) && - !cpu_isset(cpu, iucv_irq_cpumask)) + if (cpumask_test_cpu(cpu, &iucv_buffer_cpumask) && + !cpumask_test_cpu(cpu, &iucv_irq_cpumask)) smp_call_function_single(cpu, iucv_allow_cpu, NULL, 1); put_online_cpus(); @@ -564,9 +564,9 @@ static void iucv_setmask_up(void) int cpu; /* Disable all cpu but the first in cpu_irq_cpumask. */ - cpumask = iucv_irq_cpumask; - cpu_clear(first_cpu(iucv_irq_cpumask), cpumask); - for_each_cpu_mask_nr(cpu, cpumask) + cpumask_copy(&cpumask, &iucv_irq_cpumask); + cpumask_clear_cpu(cpumask_first(&iucv_irq_cpumask), &cpumask); + for_each_cpu(cpu, &cpumask) smp_call_function_single(cpu, iucv_block_cpu, NULL, 1); } @@ -593,7 +593,7 @@ static int iucv_enable(void) rc = -EIO; for_each_online_cpu(cpu) smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1); - if (cpus_empty(iucv_buffer_cpumask)) + if (cpumask_empty(&iucv_buffer_cpumask)) /* No cpu could declare an iucv buffer. */ goto out; put_online_cpus(); @@ -675,15 +675,16 @@ static int __cpuinit iucv_cpu_notify(struct notifier_block *self, case CPU_DOWN_PREPARE_FROZEN: if (!iucv_path_table) break; - cpumask = iucv_buffer_cpumask; - cpu_clear(cpu, cpumask); - if (cpus_empty(cpumask)) + cpumask_copy(&cpumask, &iucv_buffer_cpumask); + cpumask_clear_cpu(cpu, &cpumask); + if (cpumask_empty(&cpumask)) /* Can't offline last IUCV enabled cpu. */ return notifier_from_errno(-EINVAL); smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 1); - if (cpus_empty(iucv_irq_cpumask)) - smp_call_function_single(first_cpu(iucv_buffer_cpumask), - iucv_allow_cpu, NULL, 1); + if (cpumask_empty(&iucv_irq_cpumask)) + smp_call_function_single( + cpumask_first(&iucv_buffer_cpumask), + iucv_allow_cpu, NULL, 1); break; } return NOTIFY_OK; @@ -735,7 +736,7 @@ static void iucv_cleanup_queue(void) struct iucv_irq_list *p, *n; /* - * When a path is severed, the pathid can be reused immediatly + * When a path is severed, the pathid can be reused immediately * on a iucv connect or a connection pending interrupt. Remove * all entries from the task queue that refer to a stale pathid * (iucv_path_table[ix] == NULL). Only then do the iucv connect @@ -807,7 +808,7 @@ void iucv_unregister(struct iucv_handler *handler, int smp) spin_lock_bh(&iucv_table_lock); /* Remove handler from the iucv_handler_list. */ list_del_init(&handler->list); - /* Sever all pathids still refering to the handler. */ + /* Sever all pathids still referring to the handler. */ list_for_each_entry_safe(p, n, &handler->paths, list) { iucv_sever_pathid(p->pathid, NULL); iucv_path_table[p->pathid] = NULL; @@ -828,14 +829,14 @@ EXPORT_SYMBOL(iucv_unregister); static int iucv_reboot_event(struct notifier_block *this, unsigned long event, void *ptr) { - int i, rc; + int i; get_online_cpus(); on_each_cpu(iucv_block_cpu, NULL, 1); preempt_disable(); for (i = 0; i < iucv_max_pathid; i++) { if (iucv_path_table[i]) - rc = iucv_sever_pathid(i, NULL); + iucv_sever_pathid(i, NULL); } preempt_enable(); put_online_cpus(); @@ -866,7 +867,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, int rc; local_bh_disable(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -915,7 +916,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, spin_lock_bh(&iucv_table_lock); iucv_cleanup_queue(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -975,7 +976,7 @@ int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]) int rc; local_bh_disable(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1007,7 +1008,7 @@ int iucv_path_resume(struct iucv_path *path, u8 userdata[16]) int rc; local_bh_disable(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1036,7 +1037,7 @@ int iucv_path_sever(struct iucv_path *path, u8 userdata[16]) int rc; preempt_disable(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1070,7 +1071,7 @@ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg, int rc; local_bh_disable(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1162,7 +1163,7 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, if (msg->flags & IUCV_IPRMDATA) return iucv_message_receive_iprmdata(path, msg, flags, buffer, size, residual); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1235,7 +1236,7 @@ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg) int rc; local_bh_disable(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1274,7 +1275,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, int rc; local_bh_disable(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1324,7 +1325,7 @@ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, union iucv_param *parm; int rc; - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1411,7 +1412,7 @@ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, int rc; local_bh_disable(); - if (cpus_empty(iucv_buffer_cpumask)) { + if (cpumask_empty(&iucv_buffer_cpumask)) { rc = -EIO; goto out; } @@ -1888,7 +1889,7 @@ static int iucv_pm_freeze(struct device *dev) printk(KERN_WARNING "iucv_pm_freeze\n"); #endif if (iucv_pm_state != IUCV_PM_FREEZING) { - for_each_cpu_mask_nr(cpu, iucv_irq_cpumask) + for_each_cpu(cpu, &iucv_irq_cpumask) smp_call_function_single(cpu, iucv_block_cpu_almost, NULL, 1); cancel_work_sync(&iucv_work); @@ -1928,7 +1929,7 @@ static int iucv_pm_thaw(struct device *dev) if (rc) goto out; } - if (cpus_empty(iucv_irq_cpumask)) { + if (cpumask_empty(&iucv_irq_cpumask)) { if (iucv_nonsmp_handler) /* enable interrupts on one cpu */ iucv_allow_cpu(NULL); @@ -1961,7 +1962,7 @@ static int iucv_pm_restore(struct device *dev) pr_warning("Suspending Linux did not completely close all IUCV " "connections\n"); iucv_pm_state = IUCV_PM_RESTORING; - if (cpus_empty(iucv_irq_cpumask)) { + if (cpumask_empty(&iucv_irq_cpumask)) { rc = iucv_query_maxconn(); rc = iucv_enable(); if (rc) diff --git a/net/key/af_key.c b/net/key/af_key.c index 7db86ffcf070..8f92cf8116ea 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -712,7 +712,7 @@ static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port sin6->sin6_family = AF_INET6; sin6->sin6_port = port; sin6->sin6_flowinfo = 0; - ipv6_addr_copy(&sin6->sin6_addr, (struct in6_addr *)xaddr->a6); + ipv6_addr_copy(&sin6->sin6_addr, (const struct in6_addr *)xaddr->a6); sin6->sin6_scope_id = 0; return 128; } @@ -3656,7 +3656,7 @@ static int pfkey_seq_show(struct seq_file *f, void *v) if (v == SEQ_START_TOKEN) seq_printf(f ,"sk RefCnt Rmem Wmem User Inode\n"); else - seq_printf(f ,"%p %-6d %-6u %-6u %-6u %-6lu\n", + seq_printf(f, "%pK %-6d %-6u %-6u %-6u %-6lu\n", s, atomic_read(&s->sk_refcnt), sk_rmem_alloc_get(s), diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index c64ce0a0bb03..ed8a2335442f 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -954,7 +954,7 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) } static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, - size_t data_len) + struct flowi *fl, size_t data_len) { struct l2tp_tunnel *tunnel = session->tunnel; unsigned int len = skb->len; @@ -987,7 +987,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->local_df = 1; - error = ip_queue_xmit(skb); + error = ip_queue_xmit(skb, fl); /* Update stats */ if (error >= 0) { @@ -1028,6 +1028,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len int data_len = skb->len; struct l2tp_tunnel *tunnel = session->tunnel; struct sock *sk = tunnel->sock; + struct flowi *fl; struct udphdr *uh; struct inet_sock *inet; __wsum csum; @@ -1060,14 +1061,21 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len IPSKB_REROUTED); nf_reset(skb); + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + dev_kfree_skb(skb); + goto out_unlock; + } + /* Get routing info from the tunnel socket */ skb_dst_drop(skb); skb_dst_set(skb, dst_clone(__sk_dst_get(sk))); + inet = inet_sk(sk); + fl = &inet->cork.fl; switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* Setup UDP header */ - inet = inet_sk(sk); __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); @@ -1105,7 +1113,9 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len l2tp_skb_set_owner_w(skb, sk); - l2tp_xmit_core(session, skb, data_len); + l2tp_xmit_core(session, skb, fl, data_len); +out_unlock: + bh_unlock_sock(sk); abort: return 0; @@ -1425,16 +1435,15 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Add tunnel to our list */ INIT_LIST_HEAD(&tunnel->list); - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - synchronize_rcu(); atomic_inc(&l2tp_tunnel_count); /* Bump the reference count. The tunnel context is deleted - * only when this drops to zero. + * only when this drops to zero. Must be done before list insertion */ l2tp_tunnel_inc_refcount(tunnel); + spin_lock_bh(&pn->l2tp_tunnel_list_lock); + list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); + spin_unlock_bh(&pn->l2tp_tunnel_list_lock); err = 0; err: @@ -1626,7 +1635,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn hlist_add_head_rcu(&session->global_hlist, l2tp_session_id_hash_2(pn, session_id)); spin_unlock_bh(&pn->l2tp_session_hlist_lock); - synchronize_rcu(); } /* Ignore management session in session count value */ diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index fce9bd3bd3fe..b6466e71f5e1 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -296,12 +296,12 @@ out_in_use: static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - int rc; - struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr; + struct inet_sock *inet = inet_sk(sk); + struct flowi4 *fl4; struct rtable *rt; __be32 saddr; - int oif; + int oif, rc; rc = -EINVAL; if (addr_len < sizeof(*lsa)) @@ -311,6 +311,8 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len if (lsa->l2tp_family != AF_INET) goto out; + lock_sock(sk); + sk_dst_reset(sk); oif = sk->sk_bound_dev_if; @@ -320,7 +322,8 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) goto out; - rt = ip_route_connect(lsa->l2tp_addr.s_addr, saddr, + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_connect(fl4, lsa->l2tp_addr.s_addr, saddr, RT_CONN_FLAGS(sk), oif, IPPROTO_L2TP, 0, 0, sk, true); @@ -340,10 +343,10 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; if (!inet->inet_saddr) - inet->inet_saddr = rt->rt_src; + inet->inet_saddr = fl4->saddr; if (!inet->inet_rcv_saddr) - inet->inet_rcv_saddr = rt->rt_src; - inet->inet_daddr = rt->rt_dst; + inet->inet_rcv_saddr = fl4->saddr; + inet->inet_daddr = fl4->daddr; sk->sk_state = TCP_ESTABLISHED; inet->inet_id = jiffies; @@ -356,6 +359,7 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len rc = 0; out: + release_sock(sk); return rc; } @@ -416,23 +420,28 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m int rc; struct l2tp_ip_sock *lsa = l2tp_ip_sk(sk); struct inet_sock *inet = inet_sk(sk); - struct ip_options *opt = inet->opt; struct rtable *rt = NULL; + struct flowi4 *fl4; int connected = 0; __be32 daddr; + lock_sock(sk); + + rc = -ENOTCONN; if (sock_flag(sk, SOCK_DEAD)) - return -ENOTCONN; + goto out; /* Get and verify the address. */ if (msg->msg_name) { struct sockaddr_l2tpip *lip = (struct sockaddr_l2tpip *) msg->msg_name; + rc = -EINVAL; if (msg->msg_namelen < sizeof(*lip)) - return -EINVAL; + goto out; if (lip->l2tp_family != AF_INET) { + rc = -EAFNOSUPPORT; if (lip->l2tp_family != AF_UNSPEC) - return -EAFNOSUPPORT; + goto out; } daddr = lip->l2tp_addr.s_addr; @@ -467,19 +476,27 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m goto error; } + fl4 = &inet->cork.fl.u.ip4; if (connected) rt = (struct rtable *) __sk_dst_check(sk, 0); if (rt == NULL) { + struct ip_options_rcu *inet_opt; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + /* Use correct destination address if we have options. */ - if (opt && opt->srr) - daddr = opt->faddr; + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + + rcu_read_unlock(); /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ - rt = ip_route_output_ports(sock_net(sk), sk, + rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), @@ -491,7 +508,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m skb_dst_set(skb, dst_clone(&rt->dst)); /* Queue the packet to IP for output */ - rc = ip_queue_xmit(skb); + rc = ip_queue_xmit(skb, &inet->cork.fl); error: /* Update stats */ @@ -503,12 +520,15 @@ error: lsa->tx_errors++; } +out: + release_sock(sk); return rc; no_route: IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); - return -EHOSTUNREACH; + rc = -EHOSTUNREACH; + goto out; } static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, @@ -667,7 +687,7 @@ MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); -/* Use the value of SOCK_DGRAM (2) directory, because __stringify does't like +/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like * enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 4c1e540732d7..93a41a09458b 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -795,11 +795,12 @@ int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops goto out; l2tp_nl_cmd_ops[pw_type] = ops; + ret = 0; out: genl_unlock(); err: - return 0; + return ret; } EXPORT_SYMBOL_GPL(l2tp_nl_register_ops); diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index 058f1e9a9128..903242111317 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -121,8 +121,7 @@ static inline int llc_fixup_skb(struct sk_buff *skb) s32 data_size = ntohs(pdulen) - llc_len; if (data_size < 0 || - ((skb_tail_pointer(skb) - - (u8 *)pdu) - llc_len) < data_size) + !pskb_may_pull(skb, data_size)) return 0; if (unlikely(pskb_trim_rcsum(skb, data_size))) return 0; diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index cd5125f77cc5..c8be8eff70da 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -144,14 +144,6 @@ void ieee80211_assign_tid_tx(struct sta_info *sta, int tid, rcu_assign_pointer(sta->ampdu_mlme.tid_tx[tid], tid_tx); } -static void kfree_tid_tx(struct rcu_head *rcu_head) -{ - struct tid_ampdu_tx *tid_tx = - container_of(rcu_head, struct tid_ampdu_tx, rcu_head); - - kfree(tid_tx); -} - int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_back_parties initiator, bool tx) @@ -174,7 +166,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, /* not even started yet! */ ieee80211_assign_tid_tx(sta, tid, NULL); spin_unlock_bh(&sta->lock); - call_rcu(&tid_tx->rcu_head, kfree_tid_tx); + kfree_rcu(tid_tx, rcu_head); return 0; } @@ -333,7 +325,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) spin_unlock_bh(&sta->lock); ieee80211_wake_queue_agg(local, tid); - call_rcu(&tid_tx->rcu_head, kfree_tid_tx); + kfree_rcu(tid_tx, rcu_head); return; } @@ -718,7 +710,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) ieee80211_agg_splice_finish(local, tid); - call_rcu(&tid_tx->rcu_head, kfree_tid_tx); + kfree_rcu(tid_tx, rcu_head); unlock_sta: spin_unlock_bh(&sta->lock); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ed755889645d..2025af52b195 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -97,7 +97,7 @@ struct ieee80211_bss { size_t supp_rates_len; /* - * During assocation, we save an ERP value from a probe response so + * During association, we save an ERP value from a probe response so * that we can feed ERP info to the driver when handling the * association completes. these fields probably won't be up-to-date * otherwise, you probably don't want to use them. diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index dee30aea9ab3..49d4f869e0bc 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1145,10 +1145,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, + IEEE80211_ENCRYPT_HEADROOM; ndev->needed_tailroom = IEEE80211_ENCRYPT_TAILROOM; - ret = dev_alloc_name(ndev, ndev->name); - if (ret < 0) - goto fail; - ieee80211_assign_perm_addr(local, ndev, type); memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN); SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy)); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 51f6fe86d890..0d2faacc3e87 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -722,7 +722,7 @@ void mesh_path_discard_frame(struct sk_buff *skb, * * @mpath: mesh path whose queue has to be freed * - * Locking: the function must me called withing a rcu_read_lock region + * Locking: the function must me called within a rcu_read_lock region */ void mesh_path_flush_pending(struct mesh_path *mpath) { diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 3d09c58938e2..333b5118be6d 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -259,7 +259,7 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) } } - /* try to sample up to half of the availble rates during each interval */ + /* try to sample up to half of the available rates during each interval */ mi->sample_count *= 4; cur_prob = 0; diff --git a/net/mac80211/rc80211_pid.h b/net/mac80211/rc80211_pid.h index 6510f8ee738e..19111c7bf454 100644 --- a/net/mac80211/rc80211_pid.h +++ b/net/mac80211/rc80211_pid.h @@ -77,7 +77,7 @@ union rc_pid_event_data { }; struct rc_pid_event { - /* The time when the event occured */ + /* The time when the event occurred */ unsigned long timestamp; /* Event ID number */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 78c72a41d864..7fa8c6be7bf0 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -382,7 +382,7 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) * specs were sane enough this time around to require padding each A-MSDU * subframe to a length that is a multiple of four. * - * Padding like Atheros hardware adds which is inbetween the 802.11 header and + * Padding like Atheros hardware adds which is between the 802.11 header and * the payload is not supported, the driver is required to move the 802.11 * header to be directly in front of the payload in that case. */ diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4a15f9603562..b83870bf60fa 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -47,9 +47,9 @@ * Station entries are added by mac80211 when you establish a link with a * peer. This means different things for the different type of interfaces * we support. For a regular station this mean we add the AP sta when we - * receive an assocation response from the AP. For IBSS this occurs when + * receive an association response from the AP. For IBSS this occurs when * get to know about a peer on the same IBSS. For WDS we add the sta for - * the peer imediately upon device open. When using AP mode we add stations + * the peer immediately upon device open. When using AP mode we add stations * for each respective station upon request from userspace through nl80211. * * In order to remove a STA info structure, various sta_info_destroy_*() diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 6eeaaa2bbafe..64e0f7587e6d 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -237,6 +237,10 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) &local->dynamic_ps_disable_work); } + /* Don't restart the timer if we're not disassociated */ + if (!ifmgd->associated) + return TX_CONTINUE; + mod_timer(&local->dynamic_ps_timer, jiffies + msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout)); diff --git a/net/mac80211/work.c b/net/mac80211/work.c index a94b312dbfac..d2e7f0e86677 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -65,17 +65,9 @@ static void run_again(struct ieee80211_local *local, mod_timer(&local->work_timer, timeout); } -static void work_free_rcu(struct rcu_head *head) -{ - struct ieee80211_work *wk = - container_of(head, struct ieee80211_work, rcu_head); - - kfree(wk); -} - void free_work(struct ieee80211_work *wk) { - call_rcu(&wk->rcu_head, work_free_rcu); + kfree_rcu(wk, rcu_head); } static int ieee80211_compatible_rates(const u8 *supp_rates, int supp_rates_len, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c3f988aa1152..32bff6d86cb2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -652,7 +652,6 @@ comment "Xtables matches" config NETFILTER_XT_MATCH_ADDRTYPE tristate '"addrtype" address type match support' depends on NETFILTER_ADVANCED - depends on (IPV6 || IPV6=n) ---help--- This option allows you to match what routing thinks of an address, eg. UNICAST, LOCAL, BROADCAST, ... diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index bca96990218d..ba2d16607f48 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -293,7 +293,7 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], for (; !before(ip_to, ip); ip += map->hosts) { id = ip_to_id(map, ip); - ret = adtfn(set, &id, timeout);; + ret = adtfn(set, &id, timeout); if (ret && !ip_set_eexist(ret, flags)) return ret; @@ -338,8 +338,7 @@ bitmap_ip_head(struct ip_set *set, struct sk_buff *skb) NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); if (map->netmask != 32) NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, map->netmask); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->memsize)); if (with_timeout(map->timeout)) diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 5e790172deff..a274300b6a56 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -343,6 +343,10 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, ipset_adtfn adtfn = set->variant->adt[adt]; struct ipmac data; + /* MAC can be src only */ + if (!(flags & IPSET_DIM_TWO_SRC)) + return 0; + data.id = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC)); if (data.id < map->first_ip || data.id > map->last_ip) return -IPSET_ERR_BITMAP_RANGE; @@ -434,8 +438,7 @@ bitmap_ipmac_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, htonl(map->first_ip)); NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + (map->last_ip - map->first_ip + 1) * map->dsize)); diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 165f09b1a9cb..6b38eb8f6ed8 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -320,8 +320,7 @@ bitmap_port_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; NLA_PUT_NET16(skb, IPSET_ATTR_PORT, htons(map->first_port)); NLA_PUT_NET16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->memsize)); if (with_timeout(map->timeout)) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index d6b48230a540..8041befc6555 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -26,6 +26,7 @@ static LIST_HEAD(ip_set_type_list); /* all registered set types */ static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */ +static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */ static struct ip_set **ip_set_list; /* all individual sets */ static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */ @@ -301,13 +302,18 @@ EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6); static inline void __ip_set_get(ip_set_id_t index) { - atomic_inc(&ip_set_list[index]->ref); + write_lock_bh(&ip_set_ref_lock); + ip_set_list[index]->ref++; + write_unlock_bh(&ip_set_ref_lock); } static inline void __ip_set_put(ip_set_id_t index) { - atomic_dec(&ip_set_list[index]->ref); + write_lock_bh(&ip_set_ref_lock); + BUG_ON(ip_set_list[index]->ref == 0); + ip_set_list[index]->ref--; + write_unlock_bh(&ip_set_ref_lock); } /* @@ -324,7 +330,7 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret = 0; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -356,7 +362,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -378,7 +384,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, struct ip_set *set = ip_set_list[index]; int ret = 0; - BUG_ON(set == NULL || atomic_read(&set->ref) == 0); + BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); if (dim < set->type->dimension || @@ -397,7 +403,6 @@ EXPORT_SYMBOL_GPL(ip_set_del); * Find set by name, reference it once. The reference makes sure the * thing pointed to, does not go away under our feet. * - * The nfnl mutex must already be activated. */ ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set) @@ -423,15 +428,12 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname); * reference count by 1. The caller shall not assume the index * to be valid, after calling this function. * - * The nfnl mutex must already be activated. */ void ip_set_put_byindex(ip_set_id_t index) { - if (ip_set_list[index] != NULL) { - BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0); + if (ip_set_list[index] != NULL) __ip_set_put(index); - } } EXPORT_SYMBOL_GPL(ip_set_put_byindex); @@ -441,7 +443,6 @@ EXPORT_SYMBOL_GPL(ip_set_put_byindex); * can't be destroyed. The set cannot be renamed due to * the referencing either. * - * The nfnl mutex must already be activated. */ const char * ip_set_name_byindex(ip_set_id_t index) @@ -449,7 +450,7 @@ ip_set_name_byindex(ip_set_id_t index) const struct ip_set *set = ip_set_list[index]; BUG_ON(set == NULL); - BUG_ON(atomic_read(&set->ref) == 0); + BUG_ON(set->ref == 0); /* Referenced, so it's safe */ return set->name; @@ -515,10 +516,7 @@ void ip_set_nfnl_put(ip_set_id_t index) { nfnl_lock(); - if (ip_set_list[index] != NULL) { - BUG_ON(atomic_read(&ip_set_list[index]->ref) == 0); - __ip_set_put(index); - } + ip_set_put_byindex(index); nfnl_unlock(); } EXPORT_SYMBOL_GPL(ip_set_nfnl_put); @@ -526,7 +524,7 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_put); /* * Communication protocol with userspace over netlink. * - * We already locked by nfnl_lock. + * The commands are serialized by the nfnl mutex. */ static inline bool @@ -657,7 +655,6 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, return -ENOMEM; rwlock_init(&set->lock); strlcpy(set->name, name, IPSET_MAXNAMELEN); - atomic_set(&set->ref, 0); set->family = family; /* @@ -690,8 +687,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, /* * Here, we have a valid, constructed set and we are protected - * by nfnl_lock. Find the first free index in ip_set_list and - * check clashing. + * by the nfnl mutex. Find the first free index in ip_set_list + * and check clashing. */ if ((ret = find_free_id(set->name, &index, &clash)) != 0) { /* If this is the same set and requested, ignore error */ @@ -751,31 +748,51 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, const struct nlattr * const attr[]) { ip_set_id_t i; + int ret = 0; if (unlikely(protocol_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* References are protected by the nfnl mutex */ + /* Commands are serialized and references are + * protected by the ip_set_ref_lock. + * External systems (i.e. xt_set) must call + * ip_set_put|get_nfnl_* functions, that way we + * can safely check references here. + * + * list:set timer can only decrement the reference + * counter, so if it's already zero, we can proceed + * without holding the lock. + */ + read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < ip_set_max; i++) { - if (ip_set_list[i] != NULL && - (atomic_read(&ip_set_list[i]->ref))) - return -IPSET_ERR_BUSY; + if (ip_set_list[i] != NULL && ip_set_list[i]->ref) { + ret = IPSET_ERR_BUSY; + goto out; + } } + read_unlock_bh(&ip_set_ref_lock); for (i = 0; i < ip_set_max; i++) { if (ip_set_list[i] != NULL) ip_set_destroy_set(i); } } else { i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); - if (i == IPSET_INVALID_ID) - return -ENOENT; - else if (atomic_read(&ip_set_list[i]->ref)) - return -IPSET_ERR_BUSY; + if (i == IPSET_INVALID_ID) { + ret = -ENOENT; + goto out; + } else if (ip_set_list[i]->ref) { + ret = -IPSET_ERR_BUSY; + goto out; + } + read_unlock_bh(&ip_set_ref_lock); ip_set_destroy_set(i); } return 0; +out: + read_unlock_bh(&ip_set_ref_lock); + return ret; } /* Flush sets */ @@ -798,7 +815,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb, ip_set_id_t i; if (unlikely(protocol_failed(attr))) - return -EPROTO; + return -IPSET_ERR_PROTOCOL; if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < ip_set_max; i++) @@ -834,6 +851,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set; const char *name2; ip_set_id_t i; + int ret = 0; if (unlikely(protocol_failed(attr) || attr[IPSET_ATTR_SETNAME] == NULL || @@ -843,25 +861,33 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, set = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); if (set == NULL) return -ENOENT; - if (atomic_read(&set->ref) != 0) - return -IPSET_ERR_REFERENCED; + + read_lock_bh(&ip_set_ref_lock); + if (set->ref != 0) { + ret = -IPSET_ERR_REFERENCED; + goto out; + } name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); for (i = 0; i < ip_set_max; i++) { if (ip_set_list[i] != NULL && - STREQ(ip_set_list[i]->name, name2)) - return -IPSET_ERR_EXIST_SETNAME2; + STREQ(ip_set_list[i]->name, name2)) { + ret = -IPSET_ERR_EXIST_SETNAME2; + goto out; + } } strncpy(set->name, name2, IPSET_MAXNAMELEN); - return 0; +out: + read_unlock_bh(&ip_set_ref_lock); + return ret; } /* Swap two sets so that name/index points to the other. * References and set names are also swapped. * - * We are protected by the nfnl mutex and references are - * manipulated only by holding the mutex. The kernel interfaces + * The commands are serialized by the nfnl mutex and references are + * protected by the ip_set_ref_lock. The kernel interfaces * do not hold the mutex but the pointer settings are atomic * so the ip_set_list always contains valid pointers to the sets. */ @@ -874,7 +900,6 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, struct ip_set *from, *to; ip_set_id_t from_id, to_id; char from_name[IPSET_MAXNAMELEN]; - u32 from_ref; if (unlikely(protocol_failed(attr) || attr[IPSET_ATTR_SETNAME] == NULL || @@ -893,23 +918,21 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, to = ip_set_list[to_id]; /* Features must not change. - * Not an artifical restriction anymore, as we must prevent + * Not an artificial restriction anymore, as we must prevent * possible loops created by swapping in setlist type of sets. */ if (!(from->type->features == to->type->features && from->type->family == to->type->family)) return -IPSET_ERR_TYPE_MISMATCH; - /* No magic here: ref munging protected by the nfnl_lock */ strncpy(from_name, from->name, IPSET_MAXNAMELEN); - from_ref = atomic_read(&from->ref); - strncpy(from->name, to->name, IPSET_MAXNAMELEN); - atomic_set(&from->ref, atomic_read(&to->ref)); strncpy(to->name, from_name, IPSET_MAXNAMELEN); - atomic_set(&to->ref, from_ref); + write_lock_bh(&ip_set_ref_lock); + swap(from->ref, to->ref); ip_set_list[from_id] = to; ip_set_list[to_id] = from; + write_unlock_bh(&ip_set_ref_lock); return 0; } @@ -926,7 +949,7 @@ ip_set_dump_done(struct netlink_callback *cb) { if (cb->args[2]) { pr_debug("release set %s\n", ip_set_list[cb->args[1]]->name); - __ip_set_put((ip_set_id_t) cb->args[1]); + ip_set_put_byindex((ip_set_id_t) cb->args[1]); } return 0; } @@ -999,8 +1022,9 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) if (cb->args[1] >= ip_set_max) goto out; - pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]); max = cb->args[0] == DUMP_ONE ? cb->args[1] + 1 : ip_set_max; +dump_last: + pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]); for (; cb->args[1] < max; cb->args[1]++) { index = (ip_set_id_t) cb->args[1]; set = ip_set_list[index]; @@ -1015,8 +1039,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) * so that lists (unions of sets) are dumped last. */ if (cb->args[0] != DUMP_ONE && - !((cb->args[0] == DUMP_ALL) ^ - (set->type->features & IPSET_DUMP_LAST))) + ((cb->args[0] == DUMP_ALL) == + !!(set->type->features & IPSET_DUMP_LAST))) continue; pr_debug("List set: %s\n", set->name); if (!cb->args[2]) { @@ -1060,6 +1084,12 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) goto release_refcount; } } + /* If we dump all sets, continue with dumping last ones */ + if (cb->args[0] == DUMP_ALL) { + cb->args[0] = DUMP_LAST; + cb->args[1] = 0; + goto dump_last; + } goto out; nla_put_failure: @@ -1068,13 +1098,8 @@ release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[2]) { pr_debug("release set %s\n", ip_set_list[index]->name); - __ip_set_put(index); + ip_set_put_byindex(index); } - - /* If we dump all sets, continue with dumping last ones */ - if (cb->args[0] == DUMP_ALL && cb->args[1] >= max && !cb->args[2]) - cb->args[0] = DUMP_LAST; - out: if (nlh) { nlmsg_end(skb, nlh); diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 8d5227212686..757143b2240a 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -11,6 +11,7 @@ #include <linux/skbuff.h> #include <linux/icmp.h> #include <linux/icmpv6.h> +#include <linux/sctp.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/ip.h> #include <net/ipv6.h> @@ -35,7 +36,20 @@ get_port(const struct sk_buff *skb, int protocol, unsigned int protooff, *port = src ? th->source : th->dest; break; } - case IPPROTO_UDP: { + case IPPROTO_SCTP: { + sctp_sctphdr_t _sh; + const sctp_sctphdr_t *sh; + + sh = skb_header_pointer(skb, protooff, sizeof(_sh), &_sh); + if (sh == NULL) + /* No choice either */ + return false; + + *port = src ? sh->source : sh->dest; + break; + } + case IPPROTO_UDP: + case IPPROTO_UDPLITE: { struct udphdr _udph; const struct udphdr *uh; diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index b9214145d357..14281b6b8074 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -491,7 +491,7 @@ static struct ip_set_type hash_ipport_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, .family = AF_UNSPEC, - .revision = 0, + .revision = 1, .create = hash_ipport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 4642872df6e1..401c8a2531db 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -509,7 +509,7 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, .family = AF_UNSPEC, - .revision = 0, + .revision = 1, .create = hash_ipportip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 2cb84a54b7ad..4743e5402522 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -574,7 +574,7 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, .family = AF_UNSPEC, - .revision = 0, + .revision = 1, .create = hash_ipportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 8598676f2a05..d2a40362dd3a 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -526,7 +526,7 @@ static struct ip_set_type hash_netport_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, .family = AF_UNSPEC, - .revision = 0, + .revision = 1, .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index a47c32982f06..e9159e99fc4b 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -43,14 +43,19 @@ struct list_set { static inline struct set_elem * list_set_elem(const struct list_set *map, u32 id) { - return (struct set_elem *)((char *)map->members + id * map->dsize); + return (struct set_elem *)((void *)map->members + id * map->dsize); +} + +static inline struct set_telem * +list_set_telem(const struct list_set *map, u32 id) +{ + return (struct set_telem *)((void *)map->members + id * map->dsize); } static inline bool list_set_timeout(const struct list_set *map, u32 id) { - const struct set_telem *elem = - (const struct set_telem *) list_set_elem(map, id); + const struct set_telem *elem = list_set_telem(map, id); return ip_set_timeout_test(elem->timeout); } @@ -58,19 +63,11 @@ list_set_timeout(const struct list_set *map, u32 id) static inline bool list_set_expired(const struct list_set *map, u32 id) { - const struct set_telem *elem = - (const struct set_telem *) list_set_elem(map, id); + const struct set_telem *elem = list_set_telem(map, id); return ip_set_timeout_expired(elem->timeout); } -static inline int -list_set_exist(const struct set_telem *elem) -{ - return elem->id != IPSET_INVALID_ID && - !ip_set_timeout_expired(elem->timeout); -} - /* Set list without and with timeout */ static int @@ -146,11 +143,11 @@ list_elem_tadd(struct list_set *map, u32 i, ip_set_id_t id, struct set_telem *e; for (; i < map->size; i++) { - e = (struct set_telem *)list_set_elem(map, i); + e = list_set_telem(map, i); swap(e->id, id); + swap(e->timeout, timeout); if (e->id == IPSET_INVALID_ID) break; - swap(e->timeout, timeout); } } @@ -164,7 +161,7 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, /* Last element replaced: e.g. add new,before,last */ ip_set_put_byindex(e->id); if (with_timeout(map->timeout)) - list_elem_tadd(map, i, id, timeout); + list_elem_tadd(map, i, id, ip_set_timeout_set(timeout)); else list_elem_add(map, i, id); @@ -172,11 +169,11 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, } static int -list_set_del(struct list_set *map, ip_set_id_t id, u32 i) +list_set_del(struct list_set *map, u32 i) { struct set_elem *a = list_set_elem(map, i), *b; - ip_set_put_byindex(id); + ip_set_put_byindex(a->id); for (; i < map->size - 1; i++) { b = list_set_elem(map, i + 1); @@ -308,11 +305,11 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], (before == 0 || (before > 0 && next_id_eq(map, i, refid)))) - ret = list_set_del(map, id, i); + ret = list_set_del(map, i); else if (before < 0 && elem->id == refid && next_id_eq(map, i, id)) - ret = list_set_del(map, id, i + 1); + ret = list_set_del(map, i + 1); } break; default: @@ -369,8 +366,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) NLA_PUT_NET32(skb, IPSET_ATTR_SIZE, htonl(map->size)); if (with_timeout(map->timeout)) NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout)); - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + map->size * map->dsize)); ipset_nest_end(skb, nested); @@ -461,16 +457,13 @@ list_set_gc(unsigned long ul_set) struct set_telem *e; u32 i; - /* We run parallel with other readers (test element) - * but adding/deleting new entries is locked out */ - read_lock_bh(&set->lock); - for (i = map->size - 1; i >= 0; i--) { - e = (struct set_telem *) list_set_elem(map, i); - if (e->id != IPSET_INVALID_ID && - list_set_expired(map, i)) - list_set_del(map, e->id, i); + write_lock_bh(&set->lock); + for (i = 0; i < map->size; i++) { + e = list_set_telem(map, i); + if (e->id != IPSET_INVALID_ID && list_set_expired(map, i)) + list_set_del(map, i); } - read_unlock_bh(&set->lock); + write_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; add_timer(&map->gc); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 2dc6de13ac18..059af3120be7 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -572,11 +572,11 @@ static const struct file_operations ip_vs_app_fops = { .open = ip_vs_app_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; #endif -static int __net_init __ip_vs_app_init(struct net *net) +int __net_init __ip_vs_app_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -585,26 +585,17 @@ static int __net_init __ip_vs_app_init(struct net *net) return 0; } -static void __net_exit __ip_vs_app_cleanup(struct net *net) +void __net_exit __ip_vs_app_cleanup(struct net *net) { proc_net_remove(net, "ip_vs_app"); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_app_init, - .exit = __ip_vs_app_cleanup, -}; - int __init ip_vs_app_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_app_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index f289306cbf12..bf28ac2fc99b 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -595,7 +595,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) atomic_inc(&dest->inactconns); } else { /* It is a persistent connection/template, so increase - the peristent connection counter */ + the persistent connection counter */ atomic_inc(&dest->persistconns); } @@ -657,7 +657,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) } } else { /* It is a persistent connection/template, so decrease - the peristent connection counter */ + the persistent connection counter */ atomic_dec(&dest->persistconns); } @@ -1046,7 +1046,7 @@ static const struct file_operations ip_vs_conn_fops = { .open = ip_vs_conn_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; static const char *ip_vs_origin_name(unsigned flags) @@ -1114,7 +1114,7 @@ static const struct file_operations ip_vs_conn_sync_fops = { .open = ip_vs_conn_sync_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; #endif @@ -1258,22 +1258,17 @@ int __net_init __ip_vs_conn_init(struct net *net) return 0; } -static void __net_exit __ip_vs_conn_cleanup(struct net *net) +void __net_exit __ip_vs_conn_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); proc_net_remove(net, "ip_vs_conn"); proc_net_remove(net, "ip_vs_conn_sync"); } -static struct pernet_operations ipvs_conn_ops = { - .init = __ip_vs_conn_init, - .exit = __ip_vs_conn_cleanup, -}; int __init ip_vs_conn_init(void) { int idx; - int retc; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1309,17 +1304,14 @@ int __init ip_vs_conn_init(void) rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - retc = register_pernet_subsys(&ipvs_conn_ops); - /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); - return retc; + return 0; } void ip_vs_conn_cleanup(void) { - unregister_pernet_subsys(&ipvs_conn_ops); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); vfree(ip_vs_conn_tab); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 07accf6b2401..bfa808f4da13 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1113,6 +1113,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) return NF_ACCEPT; net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1343,6 +1346,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) return NF_ACCEPT; /* The packet looks wrong, ignore */ net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->protocol); if (!pd) return NF_ACCEPT; @@ -1378,15 +1382,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol) offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit(skb, cp, pp, offset); - /* LOCALNODE from FORWARD hook is not supported */ - if (verdict == NF_ACCEPT && hooknum == NF_INET_FORWARD && - skb_rtable(skb)->rt_flags & RTCF_LOCAL) { - IP_VS_DBG(1, "%s(): " - "local delivery to %pI4 but in FORWARD\n", - __func__, &skb_rtable(skb)->rt_dst); - verdict = NF_DROP; - } + verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum); out: __ip_vs_conn_put(cp); @@ -1408,7 +1404,6 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, verdict; - struct rt6_info *rt; *related = 1; @@ -1470,23 +1465,12 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) if (!cp) return NF_ACCEPT; - verdict = NF_DROP; - /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->nexthdr || IPPROTO_UDP == cih->nexthdr || IPPROTO_SCTP == cih->nexthdr) offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset); - /* LOCALNODE from FORWARD hook is not supported */ - if (verdict == NF_ACCEPT && hooknum == NF_INET_FORWARD && - (rt = (struct rt6_info *) skb_dst(skb)) && - rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK) { - IP_VS_DBG(1, "%s(): " - "local delivery to %pI6 but in FORWARD\n", - __func__, &rt->rt6i_dst); - verdict = NF_DROP; - } + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum); __ip_vs_conn_put(cp); @@ -1529,6 +1513,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); /* Bad... Do not break raw sockets */ @@ -1562,7 +1551,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } - net = skb_net(skb); /* Protocol supported? */ pd = ip_vs_proto_data_get(net, iph.protocol); if (unlikely(!pd)) @@ -1588,7 +1576,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - net = skb_net(skb); ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { @@ -1743,10 +1730,16 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp(skb, &r, hooknum); } @@ -1757,10 +1750,16 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp_v6(skb, &r, hooknum); } #endif @@ -1884,19 +1883,70 @@ static int __net_init __ip_vs_init(struct net *net) pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } + /* Hold the beast until a service is registerd */ + ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; + + if (__ip_vs_estimator_init(net) < 0) + goto estimator_fail; + + if (__ip_vs_control_init(net) < 0) + goto control_fail; + + if (__ip_vs_protocol_init(net) < 0) + goto protocol_fail; + + if (__ip_vs_app_init(net) < 0) + goto app_fail; + + if (__ip_vs_conn_init(net) < 0) + goto conn_fail; + + if (__ip_vs_sync_init(net) < 0) + goto sync_fail; + printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", sizeof(struct netns_ipvs), ipvs->gen); return 0; +/* + * Error handling + */ + +sync_fail: + __ip_vs_conn_cleanup(net); +conn_fail: + __ip_vs_app_cleanup(net); +app_fail: + __ip_vs_protocol_cleanup(net); +protocol_fail: + __ip_vs_control_cleanup(net); +control_fail: + __ip_vs_estimator_cleanup(net); +estimator_fail: + return -ENOMEM; } static void __net_exit __ip_vs_cleanup(struct net *net) { - IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen); + __ip_vs_service_cleanup(net); /* ip_vs_flush() with locks */ + __ip_vs_conn_cleanup(net); + __ip_vs_app_cleanup(net); + __ip_vs_protocol_cleanup(net); + __ip_vs_control_cleanup(net); + __ip_vs_estimator_cleanup(net); + IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); +} + +static void __net_exit __ip_vs_dev_cleanup(struct net *net) +{ + EnterFunction(2); + net_ipvs(net)->enable = 0; /* Disable packet reception */ + __ip_vs_sync_cleanup(net); + LeaveFunction(2); } static struct pernet_operations ipvs_core_ops = { @@ -1906,6 +1956,10 @@ static struct pernet_operations ipvs_core_ops = { .size = sizeof(struct netns_ipvs), }; +static struct pernet_operations ipvs_core_dev_ops = { + .exit = __ip_vs_dev_cleanup, +}; + /* * Initialize IP Virtual Server */ @@ -1913,10 +1967,6 @@ static int __init ip_vs_init(void) { int ret; - ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ - if (ret < 0) - return ret; - ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { @@ -1944,15 +1994,28 @@ static int __init ip_vs_init(void) goto cleanup_conn; } + ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ + if (ret < 0) + goto cleanup_sync; + + ret = register_pernet_device(&ipvs_core_dev_ops); + if (ret < 0) + goto cleanup_sub; + ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { pr_err("can't register hooks.\n"); - goto cleanup_sync; + goto cleanup_dev; } pr_info("ipvs loaded.\n"); + return ret; +cleanup_dev: + unregister_pernet_device(&ipvs_core_dev_ops); +cleanup_sub: + unregister_pernet_subsys(&ipvs_core_ops); cleanup_sync: ip_vs_sync_cleanup(); cleanup_conn: @@ -1964,20 +2027,20 @@ cleanup_sync: ip_vs_control_cleanup(); cleanup_estimator: ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ return ret; } static void __exit ip_vs_cleanup(void) { nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + unregister_pernet_device(&ipvs_core_dev_ops); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 33733c8872e7..699c79a55657 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -69,6 +69,11 @@ int ip_vs_get_debug_level(void) } #endif + +/* Protos */ +static void __ip_vs_del_service(struct ip_vs_service *svc); + + #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ static int __ip_vs_addr_is_local_v6(struct net *net, @@ -1214,6 +1219,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, write_unlock_bh(&__ip_vs_svc_lock); *svc_p = svc; + /* Now there is a service - full throttle */ + ipvs->enable = 1; return 0; @@ -1472,6 +1479,84 @@ static int ip_vs_flush(struct net *net) return 0; } +/* + * Delete service by {netns} in the service table. + * Called by __ip_vs_cleanup() + */ +void __ip_vs_service_cleanup(struct net *net) +{ + EnterFunction(2); + /* Check for "full" addressed entries */ + mutex_lock(&__ip_vs_mutex); + ip_vs_flush(net); + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); +} +/* + * Release dst hold by dst_cache + */ +static inline void +__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev) +{ + spin_lock_bh(&dest->dst_lock); + if (dest->dst_cache && dest->dst_cache->dev == dev) { + IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n", + dev->name, + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), + atomic_read(&dest->refcnt)); + ip_vs_dst_reset(dest); + } + spin_unlock_bh(&dest->dst_lock); + +} +/* + * Netdev event receiver + * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to + * a device that is "unregister" it must be released. + */ +static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct net *net = dev_net(dev); + struct ip_vs_service *svc; + struct ip_vs_dest *dest; + unsigned int idx; + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); + EnterFunction(2); + mutex_lock(&__ip_vs_mutex); + for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + } + + list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + + } + } + + list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + __ip_vs_dev_reset(dest, dev); + } + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); + return NOTIFY_DONE; +} /* * Zero counters in a service or all services @@ -1981,12 +2066,9 @@ static const struct file_operations ip_vs_info_fops = { .open = ip_vs_info_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; -#endif - -#ifdef CONFIG_PROC_FS static int ip_vs_stats_show(struct seq_file *seq, void *v) { struct net *net = seq_file_single_net(seq); @@ -2024,7 +2106,7 @@ static const struct file_operations ip_vs_stats_fops = { .open = ip_vs_stats_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) @@ -2093,7 +2175,7 @@ static const struct file_operations ip_vs_stats_percpu_fops = { .open = ip_vs_stats_percpu_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; #endif @@ -3120,7 +3202,7 @@ nla_put_failure: static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb_net(skb); + struct net *net = skb_sknet(skb); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); @@ -3588,6 +3670,10 @@ void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { } #endif +static struct notifier_block ip_vs_dst_notifier = { + .notifier_call = ip_vs_dst_event, +}; + int __net_init __ip_vs_control_init(struct net *net) { int idx; @@ -3626,7 +3712,7 @@ err: return -ENOMEM; } -static void __net_exit __ip_vs_control_cleanup(struct net *net) +void __net_exit __ip_vs_control_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3639,11 +3725,6 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net) free_percpu(ipvs->tot_stats.cpustats); } -static struct pernet_operations ipvs_control_ops = { - .init = __ip_vs_control_init, - .exit = __ip_vs_control_cleanup, -}; - int __init ip_vs_control_init(void) { int idx; @@ -3657,33 +3738,32 @@ int __init ip_vs_control_init(void) INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); } - ret = register_pernet_subsys(&ipvs_control_ops); - if (ret) { - pr_err("cannot register namespace.\n"); - goto err; - } - smp_wmb(); /* Do we really need it now ? */ ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); - goto err_net; + goto err_sock; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); - nf_unregister_sockopt(&ip_vs_sockopts); - goto err_net; + goto err_genl; } + ret = register_netdevice_notifier(&ip_vs_dst_notifier); + if (ret < 0) + goto err_notf; + LeaveFunction(2); return 0; -err_net: - unregister_pernet_subsys(&ipvs_control_ops); -err: +err_notf: + ip_vs_genl_unregister(); +err_genl: + nf_unregister_sockopt(&ip_vs_sockopts); +err_sock: return ret; } @@ -3691,7 +3771,6 @@ err: void ip_vs_control_cleanup(void) { EnterFunction(2); - unregister_pernet_subsys(&ipvs_control_ops); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 8c8766ca56ad..508cce98777c 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -192,7 +192,7 @@ void ip_vs_read_estimator(struct ip_vs_stats_user *dst, dst->outbps = (e->outbps + 0xF) >> 5; } -static int __net_init __ip_vs_estimator_init(struct net *net) +int __net_init __ip_vs_estimator_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -203,24 +203,16 @@ static int __net_init __ip_vs_estimator_init(struct net *net) return 0; } -static void __net_exit __ip_vs_estimator_exit(struct net *net) +void __net_exit __ip_vs_estimator_cleanup(struct net *net) { del_timer_sync(&net_ipvs(net)->est_timer); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_estimator_init, - .exit = __ip_vs_estimator_exit, -}; int __init ip_vs_estimator_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_estimator_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 6b5dd6ddaae9..af63553fa332 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -411,25 +411,35 @@ static struct ip_vs_app ip_vs_ftp = { static int __net_init __ip_vs_ftp_init(struct net *net) { int i, ret; - struct ip_vs_app *app = &ip_vs_ftp; + struct ip_vs_app *app; + struct netns_ipvs *ipvs = net_ipvs(net); + + app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL); + if (!app) + return -ENOMEM; + INIT_LIST_HEAD(&app->a_list); + INIT_LIST_HEAD(&app->incs_list); + ipvs->ftp_app = app; ret = register_ip_vs_app(net, app); if (ret) - return ret; + goto err_exit; for (i=0; i<IP_VS_APP_MAX_PORTS; i++) { if (!ports[i]) continue; ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]); if (ret) - break; + goto err_unreg; pr_info("%s: loaded support on port[%d] = %d\n", app->name, i, ports[i]); } + return 0; - if (ret) - unregister_ip_vs_app(net, app); - +err_unreg: + unregister_ip_vs_app(net, app); +err_exit: + kfree(ipvs->ftp_app); return ret; } /* @@ -437,9 +447,10 @@ static int __net_init __ip_vs_ftp_init(struct net *net) */ static void __ip_vs_ftp_exit(struct net *net) { - struct ip_vs_app *app = &ip_vs_ftp; + struct netns_ipvs *ipvs = net_ipvs(net); - unregister_ip_vs_app(net, app); + unregister_ip_vs_app(net, ipvs->ftp_app); + kfree(ipvs->ftp_app); } static struct pernet_operations ip_vs_ftp_ops = { diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index f276df9896b3..87e40ea77a95 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -131,7 +131,7 @@ static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) { list_del(&en->list); /* - * We don't kfree dest because it is refered either by its service + * We don't kfree dest because it is referred either by its service * or the trash dest list. */ atomic_dec(&en->dest->refcnt); diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index cb1c9913d38b..90f618ab6dda 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -152,7 +152,7 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) write_lock(&set->lock); list_for_each_entry_safe(e, ep, &set->list, list) { /* - * We don't kfree dest because it is refered either + * We don't kfree dest because it is referred either * by its service or by the trash dest list. */ atomic_dec(&e->dest->refcnt); diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 17484a4416ef..eb86028536fc 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -316,7 +316,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -static int __net_init __ip_vs_protocol_init(struct net *net) +int __net_init __ip_vs_protocol_init(struct net *net) { #ifdef CONFIG_IP_VS_PROTO_TCP register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); @@ -336,7 +336,7 @@ static int __net_init __ip_vs_protocol_init(struct net *net) return 0; } -static void __net_exit __ip_vs_protocol_cleanup(struct net *net) +void __net_exit __ip_vs_protocol_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; @@ -349,11 +349,6 @@ static void __net_exit __ip_vs_protocol_cleanup(struct net *net) } } -static struct pernet_operations ipvs_proto_ops = { - .init = __ip_vs_protocol_init, - .exit = __ip_vs_protocol_cleanup, -}; - int __init ip_vs_protocol_init(void) { char protocols[64]; @@ -382,7 +377,6 @@ int __init ip_vs_protocol_init(void) REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); - return register_pernet_subsys(&ipvs_proto_ops); return 0; } @@ -393,7 +387,6 @@ void ip_vs_protocol_cleanup(void) struct ip_vs_protocol *pp; int i; - unregister_pernet_subsys(&ipvs_proto_ops); /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index b027ccc49f43..d12ed53ec95f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -566,7 +566,7 @@ static struct ipvs_sctp_nextstate * SHUTDOWN sent from the client, waitinf for SHUT ACK from the server */ /* - * We recieved the data chuck, keep the state unchanged. I assume + * We received the data chuck, keep the state unchanged. I assume * that still data chuncks can be received by both the peers in * SHUDOWN state */ @@ -633,7 +633,7 @@ static struct ipvs_sctp_nextstate * SHUTDOWN sent from the server, waitinf for SHUTDOWN ACK from client */ /* - * We recieved the data chuck, keep the state unchanged. I assume + * We received the data chuck, keep the state unchanged. I assume * that still data chuncks can be received by both the peers in * SHUDOWN state */ @@ -701,7 +701,7 @@ static struct ipvs_sctp_nextstate * SHUTDOWN ACK from the client, awaiting for SHUTDOWN COM from server */ /* - * We recieved the data chuck, keep the state unchanged. I assume + * We received the data chuck, keep the state unchanged. I assume * that still data chuncks can be received by both the peers in * SHUDOWN state */ @@ -771,7 +771,7 @@ static struct ipvs_sctp_nextstate * SHUTDOWN ACK from the server, awaiting for SHUTDOWN COM from client */ /* - * We recieved the data chuck, keep the state unchanged. I assume + * We received the data chuck, keep the state unchanged. I assume * that still data chuncks can be received by both the peers in * SHUDOWN state */ diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 3e7961e85e9c..e292e5bddc70 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1303,13 +1303,18 @@ static struct socket *make_send_sock(struct net *net) struct socket *sock; int result; - /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + /* First create a socket move it to right name space later */ + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); @@ -1334,8 +1339,8 @@ static struct socket *make_send_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1350,12 +1355,17 @@ static struct socket *make_receive_sock(struct net *net) int result; /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = 1; @@ -1377,8 +1387,8 @@ static struct socket *make_receive_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1473,7 +1483,7 @@ static int sync_thread_master(void *data) ip_vs_sync_buff_release(sb); /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo); return 0; @@ -1513,7 +1523,7 @@ static int sync_thread_backup(void *data) } /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo->buf); kfree(tinfo); @@ -1601,7 +1611,7 @@ outtinfo: outbuf: kfree(buf); outsocket: - sock_release(sock); + sk_release_kernel(sock->sk); out: return result; } @@ -1610,6 +1620,7 @@ out: int stop_sync_thread(struct net *net, int state) { struct netns_ipvs *ipvs = net_ipvs(net); + int retc = -EINVAL; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); @@ -1629,7 +1640,7 @@ int stop_sync_thread(struct net *net, int state) spin_lock_bh(&ipvs->sync_lock); ipvs->sync_state &= ~IP_VS_STATE_MASTER; spin_unlock_bh(&ipvs->sync_lock); - kthread_stop(ipvs->master_thread); + retc = kthread_stop(ipvs->master_thread); ipvs->master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { if (!ipvs->backup_thread) @@ -1639,22 +1650,20 @@ int stop_sync_thread(struct net *net, int state) task_pid_nr(ipvs->backup_thread)); ipvs->sync_state &= ~IP_VS_STATE_BACKUP; - kthread_stop(ipvs->backup_thread); + retc = kthread_stop(ipvs->backup_thread); ipvs->backup_thread = NULL; - } else { - return -EINVAL; } /* decrease the module use count */ ip_vs_use_count_dec(); - return 0; + return retc; } /* * Initialize data struct for each netns */ -static int __net_init __ip_vs_sync_init(struct net *net) +int __net_init __ip_vs_sync_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1668,24 +1677,24 @@ static int __net_init __ip_vs_sync_init(struct net *net) return 0; } -static void __ip_vs_sync_cleanup(struct net *net) +void __ip_vs_sync_cleanup(struct net *net) { - stop_sync_thread(net, IP_VS_STATE_MASTER); - stop_sync_thread(net, IP_VS_STATE_BACKUP); -} + int retc; -static struct pernet_operations ipvs_sync_ops = { - .init = __ip_vs_sync_init, - .exit = __ip_vs_sync_cleanup, -}; + retc = stop_sync_thread(net, IP_VS_STATE_MASTER); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Master Daemon\n"); + retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Backup Daemon\n"); +} int __init ip_vs_sync_init(void) { - return register_pernet_subsys(&ipvs_sync_ops); + return 0; } void ip_vs_sync_cleanup(void) { - unregister_pernet_subsys(&ipvs_sync_ops); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 6132b213eddc..ee319a4338b0 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -87,7 +87,7 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos) /* Get route to destination or remote server */ static struct rtable * __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, - __be32 daddr, u32 rtos, int rt_mode) + __be32 daddr, u32 rtos, int rt_mode, __be32 *ret_saddr) { struct net *net = dev_net(skb_dst(skb)->dev); struct rtable *rt; /* Route to the other host */ @@ -98,7 +98,12 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, spin_lock(&dest->dst_lock); if (!(rt = (struct rtable *) __ip_vs_dst_check(dest, rtos))) { - rt = ip_route_output(net, dest->addr.ip, 0, rtos, 0); + struct flowi4 fl4; + + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = dest->addr.ip; + fl4.flowi4_tos = rtos; + rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { spin_unlock(&dest->dst_lock); IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", @@ -106,18 +111,30 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, return NULL; } __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0); - IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n", - &dest->addr.ip, + dest->dst_saddr.ip = fl4.saddr; + IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, " + "rtos=%X\n", + &dest->addr.ip, &dest->dst_saddr.ip, atomic_read(&rt->dst.__refcnt), rtos); } + daddr = dest->addr.ip; + if (ret_saddr) + *ret_saddr = dest->dst_saddr.ip; spin_unlock(&dest->dst_lock); } else { - rt = ip_route_output(net, daddr, 0, rtos, 0); + struct flowi4 fl4; + + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = daddr; + fl4.flowi4_tos = rtos; + rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr); return NULL; } + if (ret_saddr) + *ret_saddr = fl4.saddr; } local = rt->rt_flags & RTCF_LOCAL; @@ -125,7 +142,7 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, rt_mode)) { IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n", (rt->rt_flags & RTCF_LOCAL) ? - "local":"non-local", &rt->rt_dst); + "local":"non-local", &daddr); ip_rt_put(rt); return NULL; } @@ -133,14 +150,14 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest, !((ort = skb_rtable(skb)) && ort->rt_flags & RTCF_LOCAL)) { IP_VS_DBG_RL("Redirect from non-local address %pI4 to local " "requires NAT method, dest: %pI4\n", - &ip_hdr(skb)->daddr, &rt->rt_dst); + &ip_hdr(skb)->daddr, &daddr); ip_rt_put(rt); return NULL; } if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) { IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 " "to non-local address, dest: %pI4\n", - &ip_hdr(skb)->saddr, &rt->rt_dst); + &ip_hdr(skb)->saddr, &daddr); ip_rt_put(rt); return NULL; } @@ -229,8 +246,6 @@ out_err: /* * Get route to destination or remote server - * rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest, - * &4=Allow redirect from remote daddr to local */ static struct rt6_info * __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, @@ -250,7 +265,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, u32 cookie; dst = __ip_vs_route_output_v6(net, &dest->addr.in6, - &dest->dst_saddr, + &dest->dst_saddr.in6, do_xfrm); if (!dst) { spin_unlock(&dest->dst_lock); @@ -260,11 +275,11 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", - &dest->addr.in6, &dest->dst_saddr, + &dest->addr.in6, &dest->dst_saddr.in6, atomic_read(&rt->dst.__refcnt)); } if (ret_saddr) - ipv6_addr_copy(ret_saddr, &dest->dst_saddr); + ipv6_addr_copy(ret_saddr, &dest->dst_saddr.in6); spin_unlock(&dest->dst_lock); } else { dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); @@ -274,13 +289,14 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, } local = __ip_vs_is_local_route6(rt); - if (!((local ? 1 : 2) & rt_mode)) { + if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) & + rt_mode)) { IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n", local ? "local":"non-local", daddr); dst_release(&rt->dst); return NULL; } - if (local && !(rt_mode & 4) && + if (local && !(rt_mode & IP_VS_RT_MODE_RDR) && !((ort = (struct rt6_info *) skb_dst(skb)) && __ip_vs_is_local_route6(ort))) { IP_VS_DBG_RL("Redirect from non-local address %pI6 to local " @@ -386,7 +402,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (!(rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr, RT_TOS(iph->tos), - IP_VS_RT_MODE_NON_LOCAL))) + IP_VS_RT_MODE_NON_LOCAL, NULL))) goto tx_error_icmp; /* MTU checking */ @@ -440,7 +456,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); - if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0, 2))) + if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0, + IP_VS_RT_MODE_NON_LOCAL))) goto tx_error_icmp; /* MTU checking */ @@ -517,7 +534,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, RT_TOS(iph->tos), IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | - IP_VS_RT_MODE_RDR))) + IP_VS_RT_MODE_RDR, NULL))) goto tx_error_icmp; local = rt->rt_flags & RTCF_LOCAL; /* @@ -539,7 +556,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #endif /* From world but DNAT to loopback address? */ - if (local && ipv4_is_loopback(rt->rt_dst) && + if (local && ipv4_is_loopback(cp->daddr.ip) && rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " "stopping DNAT to loopback address"); @@ -632,7 +649,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, - 0, 1|2|4))) + 0, (IP_VS_RT_MODE_LOCAL | + IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_RDR)))) goto tx_error_icmp; local = __ip_vs_is_local_route6(rt); /* @@ -748,6 +767,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rtable *rt; /* Route to the other host */ + __be32 saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ struct iphdr *old_iph = ip_hdr(skb); u8 tos = old_iph->tos; @@ -761,7 +781,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(tos), IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL))) + IP_VS_RT_MODE_NON_LOCAL, + &saddr))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); @@ -829,8 +850,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->frag_off = df; iph->protocol = IPPROTO_IPIP; iph->tos = tos; - iph->daddr = rt->rt_dst; - iph->saddr = rt->rt_src; + iph->daddr = cp->daddr.ip; + iph->saddr = saddr; iph->ttl = old_iph->ttl; ip_select_ident(iph, &rt->dst, NULL); @@ -875,7 +896,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, - &saddr, 1, 1|2))) + &saddr, 1, (IP_VS_RT_MODE_LOCAL | + IP_VS_RT_MODE_NON_LOCAL)))) goto tx_error_icmp; if (__ip_vs_is_local_route6(rt)) { dst_release(&rt->dst); @@ -992,7 +1014,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(iph->tos), IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL))) + IP_VS_RT_MODE_NON_LOCAL, NULL))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); @@ -1050,7 +1072,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, - 0, 1|2))) + 0, (IP_VS_RT_MODE_LOCAL | + IP_VS_RT_MODE_NON_LOCAL)))) goto tx_error_icmp; if (__ip_vs_is_local_route6(rt)) { dst_release(&rt->dst); @@ -1109,12 +1132,13 @@ tx_error: */ int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset) + struct ip_vs_protocol *pp, int offset, unsigned int hooknum) { struct rtable *rt; /* Route to the other host */ int mtu; int rc; int local; + int rt_mode; EnterFunction(10); @@ -1135,11 +1159,13 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, * mangle and send the packet here (only for VS/NAT) */ + /* LOCALNODE from FORWARD hook is not supported */ + rt_mode = (hooknum != NF_INET_FORWARD) ? + IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(ip_hdr(skb)->tos), - IP_VS_RT_MODE_LOCAL | - IP_VS_RT_MODE_NON_LOCAL | - IP_VS_RT_MODE_RDR))) + rt_mode, NULL))) goto tx_error_icmp; local = rt->rt_flags & RTCF_LOCAL; @@ -1162,7 +1188,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #endif /* From world but DNAT to loopback address? */ - if (local && ipv4_is_loopback(rt->rt_dst) && + if (local && ipv4_is_loopback(cp->daddr.ip) && rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI4\n", @@ -1227,12 +1253,13 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset) + struct ip_vs_protocol *pp, int offset, unsigned int hooknum) { struct rt6_info *rt; /* Route to the other host */ int mtu; int rc; int local; + int rt_mode; EnterFunction(10); @@ -1253,8 +1280,12 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, * mangle and send the packet here (only for VS/NAT) */ + /* LOCALNODE from FORWARD hook is not supported */ + rt_mode = (hooknum != NF_INET_FORWARD) ? + IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | + IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, - 0, 1|2|4))) + 0, rt_mode))) goto tx_error_icmp; local = __ip_vs_is_local_route6(rt); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 941286ca911d..2e1c11f78419 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -453,7 +453,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) REJECT will give spurious warnings here. */ /* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */ - /* No external references means noone else could have + /* No external references means no one else could have confirmed us. */ NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); pr_debug("Confirming conntrack %p\n", ct); @@ -901,7 +901,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, ret = l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, &protonum); if (ret <= 0) { - pr_debug("not prepared to track yet or error occured\n"); + pr_debug("not prepared to track yet or error occurred\n"); NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); ret = -ret; diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 80a23ed62bb0..05ecdc281a53 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -68,12 +68,6 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) return (void *)(*ext) + off; } -static void __nf_ct_ext_free_rcu(struct rcu_head *head) -{ - struct nf_ct_ext *ext = container_of(head, struct nf_ct_ext, rcu); - kfree(ext); -} - void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) { struct nf_ct_ext *old, *new; @@ -114,7 +108,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) (void *)old + old->offset[i]); rcu_read_unlock(); } - call_rcu(&old->rcu, __nf_ct_ext_free_rcu); + kfree_rcu(old, rcu); ct->ext = new; } diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index 867882313e49..bcd5ed6b7130 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -631,7 +631,7 @@ static int decode_seqof(bitstr_t *bs, const struct field_t *f, CHECK_BOUND(bs, 2); count = *bs->cur++; count <<= 8; - count = *bs->cur++; + count += *bs->cur++; break; case SEMI: BYTE_ALIGN(bs); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 533a183e6661..18b2ce5c8ced 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -731,10 +731,10 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); fl2.daddr = dst->ip; - if (!afinfo->route((struct dst_entry **)&rt1, - flowi4_to_flowi(&fl1))) { - if (!afinfo->route((struct dst_entry **)&rt2, - flowi4_to_flowi(&fl2))) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, + flowi4_to_flowi(&fl1), false)) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, + flowi4_to_flowi(&fl2), false)) { if (rt1->rt_gateway == rt2->rt_gateway && rt1->dst.dev == rt2->dst.dev) ret = 1; @@ -755,10 +755,10 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); ipv6_addr_copy(&fl2.daddr, &dst->in6); - if (!afinfo->route((struct dst_entry **)&rt1, - flowi6_to_flowi(&fl1))) { - if (!afinfo->route((struct dst_entry **)&rt2, - flowi6_to_flowi(&fl2))) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, + flowi6_to_flowi(&fl1), false)) { + if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, + flowi6_to_flowi(&fl2), false)) { if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, sizeof(rt1->rt6i_gateway)) && rt1->dst.dev == rt2->dst.dev) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 30bf8a167fc8..482e90c61850 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1334,6 +1334,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; + struct nf_conn_tstamp *tstamp; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) @@ -1451,6 +1452,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_to_ns(ktime_get_real()); add_timer(&ct->timeout); nf_conntrack_hash_insert(ct); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 9ae57c57c50e..2e664a69d7db 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -98,7 +98,7 @@ static const char * const dccp_state_names[] = { #define sIV CT_DCCP_INVALID /* - * DCCP state transistion table + * DCCP state transition table * * The assumption is the same as for TCP tracking: * diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 6f4ee70f460b..6772b1154654 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -107,9 +107,9 @@ static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = { /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA}, /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant have Stale cookie*/ +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't have Stale cookie*/ /* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant come in orig dir */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in orig dir */ /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL} }, { @@ -121,7 +121,7 @@ static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = { /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA}, /* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Cant come in reply dir */ +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in reply dir */ /* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA}, /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL} } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index bcf47eb518ef..cb5a28581782 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -707,7 +707,7 @@ static const char *ct_sdp_header_search(const char *dptr, const char *limit, } /* Locate a SDP header (optionally a substring within the header value), - * optionally stopping at the first occurence of the term header, parse + * optionally stopping at the first occurrence of the term header, parse * it and return the offset and length of the data we're interested in. */ int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr, @@ -1419,6 +1419,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, const char *dptr, *end; s16 diff, tdiff = 0; int ret = NF_ACCEPT; + bool term; typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust; if (ctinfo != IP_CT_ESTABLISHED && @@ -1453,14 +1454,21 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, if (dptr + matchoff == end) break; - if (end + strlen("\r\n\r\n") > dptr + datalen) - break; - if (end[0] != '\r' || end[1] != '\n' || - end[2] != '\r' || end[3] != '\n') + term = false; + for (; end + strlen("\r\n\r\n") <= dptr + datalen; end++) { + if (end[0] == '\r' && end[1] == '\n' && + end[2] == '\r' && end[3] == '\n') { + term = true; + break; + } + } + if (!term) break; end += strlen("\r\n\r\n") + clen; msglen = origlen = end - dptr; + if (msglen > datalen) + return NF_DROP; ret = process_sip_msg(skb, ct, dataoff, &dptr, &msglen); if (ret != NF_ACCEPT) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 0ae142825881..05e9feb101c3 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -245,7 +245,7 @@ static int ct_seq_show(struct seq_file *s, void *v) ret = 0; release: nf_ct_put(ct); - return 0; + return ret; } static const struct seq_operations ct_seq_ops = { diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 5ab22e2bbd7d..5b466cd1272f 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -134,7 +134,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_afinfo *afinfo; const struct nf_queue_handler *qh; - /* QUEUE == DROP if noone is waiting, to be safe. */ + /* QUEUE == DROP if no one is waiting, to be safe. */ rcu_read_lock(); qh = rcu_dereference(queue_handler[pf]); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 985e9b76c916..e0ee010935e7 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -381,7 +381,6 @@ __build_packet_message(struct nfulnl_instance *inst, struct nfulnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - __be32 tmp_uint; sk_buff_data_t old_tail = inst->skb->tail; nlh = NLMSG_PUT(inst->skb, 0, 0, @@ -428,7 +427,6 @@ __build_packet_message(struct nfulnl_instance *inst, } if (outdev) { - tmp_uint = htonl(outdev->ifindex); #ifndef CONFIG_BRIDGE_NETFILTER NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(outdev->ifindex)); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index a9adf4c6b299..b0869fe3633b 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -455,6 +455,7 @@ void xt_compat_flush_offsets(u_int8_t af) vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; + xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); @@ -473,8 +474,7 @@ int xt_compat_calc_jump(u_int8_t af, unsigned int offset) else return mid ? tmp[mid - 1].delta : 0; } - WARN_ON_ONCE(1); - return 0; + return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); @@ -762,8 +762,8 @@ void xt_compat_unlock(u_int8_t af) EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif -DEFINE_PER_CPU(struct xt_info_lock, xt_info_locks); -EXPORT_PER_CPU_SYMBOL_GPL(xt_info_locks); +DEFINE_PER_CPU(seqcount_t, xt_recseq); +EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); static int xt_jumpstack_alloc(struct xt_table_info *i) { @@ -1362,10 +1362,7 @@ static int __init xt_init(void) int rv; for_each_possible_cpu(i) { - struct xt_info_lock *lock = &per_cpu(xt_info_locks, i); - - seqlock_init(&lock->lock); - lock->readers = 0; + seqcount_init(&per_cpu(xt_recseq, i)); } xt = kmalloc(sizeof(struct xt_af) * NFPROTO_NUMPROTO, GFP_KERNEL); diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c index 0a229191e55b..ae8271652efa 100644 --- a/net/netfilter/xt_DSCP.c +++ b/net/netfilter/xt_DSCP.c @@ -99,7 +99,7 @@ tos_tg6(struct sk_buff *skb, const struct xt_action_param *par) u_int8_t orig, nv; orig = ipv6_get_dsfield(iph); - nv = (orig & info->tos_mask) ^ info->tos_value; + nv = (orig & ~info->tos_mask) ^ info->tos_value; if (orig != nv) { if (!skb_make_writable(skb, sizeof(struct iphdr))) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 6e6b46cb1db9..9e63b43faeed 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, rcu_read_lock(); ai = nf_get_afinfo(family); if (ai != NULL) - ai->route((struct dst_entry **)&rt, &fl); + ai->route(&init_net, (struct dst_entry **)&rt, &fl, false); rcu_read_unlock(); if (rt != NULL) { diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 2220b85e9519..b77d383cec78 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -32,11 +32,32 @@ MODULE_ALIAS("ipt_addrtype"); MODULE_ALIAS("ip6t_addrtype"); #if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) -static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt) +static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, + const struct in6_addr *addr) { + const struct nf_afinfo *afinfo; + struct flowi6 flow; + struct rt6_info *rt; u32 ret; + int route_err; - if (!rt) + memset(&flow, 0, sizeof(flow)); + ipv6_addr_copy(&flow.daddr, addr); + if (dev) + flow.flowi6_oif = dev->ifindex; + + rcu_read_lock(); + + afinfo = nf_get_afinfo(NFPROTO_IPV6); + if (afinfo != NULL) + route_err = afinfo->route(net, (struct dst_entry **)&rt, + flowi6_to_flowi(&flow), !!dev); + else + route_err = 1; + + rcu_read_unlock(); + + if (route_err) return XT_ADDRTYPE_UNREACHABLE; if (rt->rt6i_flags & RTF_REJECT) @@ -48,6 +69,9 @@ static u32 xt_addrtype_rt6_to_type(const struct rt6_info *rt) ret |= XT_ADDRTYPE_LOCAL; if (rt->rt6i_flags & RTF_ANYCAST) ret |= XT_ADDRTYPE_ANYCAST; + + + dst_release(&rt->dst); return ret; } @@ -65,18 +89,8 @@ static bool match_type6(struct net *net, const struct net_device *dev, return false; if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST | - XT_ADDRTYPE_UNREACHABLE) & mask) { - struct rt6_info *rt; - u32 type; - int ifindex = dev ? dev->ifindex : 0; - - rt = rt6_lookup(net, addr, NULL, ifindex, !!dev); - - type = xt_addrtype_rt6_to_type(rt); - - dst_release(&rt->dst); - return !!(mask & type); - } + XT_ADDRTYPE_UNREACHABLE) & mask) + return !!(mask & match_lookup_rt6(net, dev, addr)); return true; } diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 2c0086a4751e..61805d7b38aa 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -195,7 +195,7 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, return info->match_flags & XT_CONNTRACK_STATE; if ((info->match_flags & XT_CONNTRACK_DIRECTION) && (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) ^ - !!(info->invert_flags & XT_CONNTRACK_DIRECTION)) + !(info->invert_flags & XT_CONNTRACK_DIRECTION)) return false; if (info->match_flags & XT_CONNTRACK_ORIGSRC) @@ -272,11 +272,6 @@ static int conntrack_mt_check(const struct xt_mtchk_param *par) { int ret; - if (strcmp(par->table, "raw") == 0) { - pr_info("state is undetermined at the time of raw table\n"); - return -EINVAL; - } - ret = nf_ct_l3proto_try_module_get(par->family); if (ret < 0) pr_info("cannot load conntrack support for proto=%u\n", diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 4327e101c047..846f895cb656 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -62,13 +62,6 @@ static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = { [OSF_ATTR_FINGER] = { .len = sizeof(struct xt_osf_user_finger) }, }; -static void xt_osf_finger_free_rcu(struct rcu_head *rcu_head) -{ - struct xt_osf_finger *f = container_of(rcu_head, struct xt_osf_finger, rcu_head); - - kfree(f); -} - static int xt_osf_add_callback(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const osf_attrs[]) @@ -133,7 +126,7 @@ static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb, * We are protected by nfnl mutex. */ list_del_rcu(&sf->finger_entry); - call_rcu(&sf->rcu_head, xt_osf_finger_free_rcu); + kfree_rcu(sf, rcu_head); err = 0; break; @@ -414,7 +407,7 @@ static void __exit xt_osf_fini(void) list_for_each_entry_rcu(f, &xt_osf_fingers[i], finger_entry) { list_del_rcu(&f->finger_entry); - call_rcu(&f->rcu_head, xt_osf_finger_free_rcu); + kfree_rcu(f, rcu_head); } } rcu_read_unlock(); diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 061d48cec137..b3babaed7719 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -81,6 +81,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par) if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) { pr_warning("Protocol error: set match dimension " "is over the limit!\n"); + ip_set_nfnl_put(info->match_set.index); return -ERANGE; } @@ -135,6 +136,8 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) if (index == IPSET_INVALID_ID) { pr_warning("Cannot find del_set index %u as target\n", info->del_set.index); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); return -ENOENT; } } @@ -142,6 +145,10 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par) info->del_set.u.flags[IPSET_DIM_MAX-1] != 0) { pr_warning("Protocol error: SET target dimension " "is over the limit!\n"); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->del_set.index); return -ERANGE; } @@ -192,6 +199,7 @@ set_match_checkentry(const struct xt_mtchk_param *par) if (info->match_set.dim > IPSET_DIM_MAX) { pr_warning("Protocol error: set match dimension " "is over the limit!\n"); + ip_set_nfnl_put(info->match_set.index); return -ERANGE; } @@ -219,7 +227,7 @@ set_target(struct sk_buff *skb, const struct xt_action_param *par) if (info->del_set.index != IPSET_INVALID_ID) ip_set_del(info->del_set.index, skb, par->family, - info->add_set.dim, + info->del_set.dim, info->del_set.flags); return XT_CONTINUE; @@ -245,13 +253,19 @@ set_target_checkentry(const struct xt_tgchk_param *par) if (index == IPSET_INVALID_ID) { pr_warning("Cannot find del_set index %u as target\n", info->del_set.index); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); return -ENOENT; } } if (info->add_set.dim > IPSET_DIM_MAX || - info->del_set.flags > IPSET_DIM_MAX) { + info->del_set.dim > IPSET_DIM_MAX) { pr_warning("Protocol error: SET target dimension " "is over the limit!\n"); + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->add_set.index); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_nfnl_put(info->del_set.index); return -ERANGE; } diff --git a/net/netlabel/netlabel_addrlist.h b/net/netlabel/netlabel_addrlist.h index 1c1c093cf279..2b9644e19de0 100644 --- a/net/netlabel/netlabel_addrlist.h +++ b/net/netlabel/netlabel_addrlist.h @@ -96,12 +96,12 @@ static inline struct netlbl_af4list *__af4list_valid_rcu(struct list_head *s, #define netlbl_af4list_foreach(iter, head) \ for (iter = __af4list_valid((head)->next, head); \ - prefetch(iter->list.next), &iter->list != (head); \ + &iter->list != (head); \ iter = __af4list_valid(iter->list.next, head)) #define netlbl_af4list_foreach_rcu(iter, head) \ for (iter = __af4list_valid_rcu((head)->next, head); \ - prefetch(iter->list.next), &iter->list != (head); \ + &iter->list != (head); \ iter = __af4list_valid_rcu(iter->list.next, head)) #define netlbl_af4list_foreach_safe(iter, tmp, head) \ @@ -163,12 +163,12 @@ static inline struct netlbl_af6list *__af6list_valid_rcu(struct list_head *s, #define netlbl_af6list_foreach(iter, head) \ for (iter = __af6list_valid((head)->next, head); \ - prefetch(iter->list.next), &iter->list != (head); \ + &iter->list != (head); \ iter = __af6list_valid(iter->list.next, head)) #define netlbl_af6list_foreach_rcu(iter, head) \ for (iter = __af6list_valid_rcu((head)->next, head); \ - prefetch(iter->list.next), &iter->list != (head); \ + &iter->list != (head); \ iter = __af6list_valid_rcu(iter->list.next, head)) #define netlbl_af6list_foreach_safe(iter, tmp, head) \ diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 5f14c8462e30..bae5756b1626 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -422,7 +422,6 @@ static int netlbl_cipsov4_add(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; - const char *type_str = "(unknown)"; struct netlbl_audit audit_info; if (!info->attrs[NLBL_CIPSOV4_A_DOI] || @@ -432,15 +431,12 @@ static int netlbl_cipsov4_add(struct sk_buff *skb, struct genl_info *info) netlbl_netlink_auditinfo(skb, &audit_info); switch (nla_get_u32(info->attrs[NLBL_CIPSOV4_A_MTYPE])) { case CIPSO_V4_MAP_TRANS: - type_str = "trans"; ret_val = netlbl_cipsov4_add_std(info, &audit_info); break; case CIPSO_V4_MAP_PASS: - type_str = "pass"; ret_val = netlbl_cipsov4_add_pass(info, &audit_info); break; case CIPSO_V4_MAP_LOCAL: - type_str = "local"; ret_val = netlbl_cipsov4_add_local(info, &audit_info); break; } diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index d37b7f80fa37..de0d8e4cbfb6 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -109,7 +109,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry) * * Description: * This is the hashing function for the domain hash table, it returns the - * correct bucket number for the domain. The caller is responsibile for + * correct bucket number for the domain. The caller is responsible for * ensuring that the hash table is protected with either a RCU read lock or the * hash table lock. * @@ -134,7 +134,7 @@ static u32 netlbl_domhsh_hash(const char *key) * * Description: * Searches the domain hash table and returns a pointer to the hash table - * entry if found, otherwise NULL is returned. The caller is responsibile for + * entry if found, otherwise NULL is returned. The caller is responsible for * ensuring that the hash table is protected with either a RCU read lock or the * hash table lock. * @@ -165,7 +165,7 @@ static struct netlbl_dom_map *netlbl_domhsh_search(const char *domain) * Searches the domain hash table and returns a pointer to the hash table * entry if an exact match is found, if an exact match is not present in the * hash table then the default entry is returned if valid otherwise NULL is - * returned. The caller is responsibile ensuring that the hash table is + * returned. The caller is responsible ensuring that the hash table is * protected with either a RCU read lock or the hash table lock. * */ @@ -193,7 +193,7 @@ static struct netlbl_dom_map *netlbl_domhsh_search_def(const char *domain) * * Description: * Generate an audit record for adding a new NetLabel/LSM mapping entry with - * the given information. Caller is responsibile for holding the necessary + * the given information. Caller is responsible for holding the necessary * locks. * */ @@ -605,7 +605,7 @@ int netlbl_domhsh_remove_default(struct netlbl_audit *audit_info) * * Description: * Look through the domain hash table searching for an entry to match @domain, - * return a pointer to a copy of the entry or NULL. The caller is responsibile + * return a pointer to a copy of the entry or NULL. The caller is responsible * for ensuring that rcu_read_[un]lock() is called. * */ diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 998e85e895d0..4f251b19fbcc 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -259,7 +259,7 @@ add_failure: * * Description: * This function is a helper function used by the LISTALL and LISTDEF command - * handlers. The caller is responsibile for ensuring that the RCU read lock + * handlers. The caller is responsible for ensuring that the RCU read lock * is held. Returns zero on success, negative values on failure. * */ diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index e2b0a680dd56..9c38658fba8b 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -154,44 +154,6 @@ static const struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1 */ /** - * netlbl_unlhsh_free_addr4 - Frees an IPv4 address entry from the hash table - * @entry: the entry's RCU field - * - * Description: - * This function is designed to be used as a callback to the call_rcu() - * function so that memory allocated to a hash table address entry can be - * released safely. - * - */ -static void netlbl_unlhsh_free_addr4(struct rcu_head *entry) -{ - struct netlbl_unlhsh_addr4 *ptr; - - ptr = container_of(entry, struct netlbl_unlhsh_addr4, rcu); - kfree(ptr); -} - -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -/** - * netlbl_unlhsh_free_addr6 - Frees an IPv6 address entry from the hash table - * @entry: the entry's RCU field - * - * Description: - * This function is designed to be used as a callback to the call_rcu() - * function so that memory allocated to a hash table address entry can be - * released safely. - * - */ -static void netlbl_unlhsh_free_addr6(struct rcu_head *entry) -{ - struct netlbl_unlhsh_addr6 *ptr; - - ptr = container_of(entry, struct netlbl_unlhsh_addr6, rcu); - kfree(ptr); -} -#endif /* IPv6 */ - -/** * netlbl_unlhsh_free_iface - Frees an interface entry from the hash table * @entry: the entry's RCU field * @@ -568,7 +530,7 @@ static int netlbl_unlhsh_remove_addr4(struct net *net, if (entry == NULL) return -ENOENT; - call_rcu(&entry->rcu, netlbl_unlhsh_free_addr4); + kfree_rcu(entry, rcu); return 0; } @@ -629,7 +591,7 @@ static int netlbl_unlhsh_remove_addr6(struct net *net, if (entry == NULL) return -ENOENT; - call_rcu(&entry->rcu, netlbl_unlhsh_free_addr6); + kfree_rcu(entry, rcu); return 0; } #endif /* IPv6 */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c8f35b5d2ee9..6ef64adf7362 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1566,12 +1566,6 @@ netlink_kernel_release(struct sock *sk) } EXPORT_SYMBOL(netlink_kernel_release); - -static void listeners_free_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct listeners, rcu)); -} - int __netlink_change_ngroups(struct sock *sk, unsigned int groups) { struct listeners *new, *old; @@ -1588,7 +1582,7 @@ int __netlink_change_ngroups(struct sock *sk, unsigned int groups) memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); - call_rcu(&old->rcu, listeners_free_rcu); + kfree_rcu(old, rcu); } tbl->groups = groups; @@ -1991,7 +1985,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v) struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); - seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %-8d %-8d %-8lu\n", + seq_printf(seq, "%pK %-3d %-6d %08x %-8d %-8d %pK %-8d %-8d %-8lu\n", s, s->sk_protocol, nlk->pid, diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 06cb02796a0e..732152f718e0 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -591,7 +591,6 @@ static int nr_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return -EINVAL; } if ((dev = nr_dev_get(&addr->fsa_ax25.sax25_call)) == NULL) { - SOCK_DEBUG(sk, "NET/ROM: bind failed: invalid node callsign\n"); release_sock(sk); return -EADDRNOTAVAIL; } @@ -632,7 +631,7 @@ static int nr_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) sock_reset_flag(sk, SOCK_ZAPPED); dev_put(dev); release_sock(sk); - SOCK_DEBUG(sk, "NET/ROM: socket is bound\n"); + return 0; } @@ -1082,8 +1081,6 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, sax.sax25_call = nr->dest_addr; } - SOCK_DEBUG(sk, "NET/ROM: sendto: Addresses built.\n"); - /* Build a packet - the conventional user limit is 236 bytes. We can do ludicrously large NetROM frames but must not overflow */ if (len > 65536) { @@ -1091,7 +1088,6 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, goto out; } - SOCK_DEBUG(sk, "NET/ROM: sendto: building packet.\n"); size = len + NR_NETWORK_LEN + NR_TRANSPORT_LEN; if ((skb = sock_alloc_send_skb(sk, size, msg->msg_flags & MSG_DONTWAIT, &err)) == NULL) @@ -1105,7 +1101,6 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, */ asmptr = skb_push(skb, NR_TRANSPORT_LEN); - SOCK_DEBUG(sk, "Building NET/ROM Header.\n"); /* Build a NET/ROM Transport header */ @@ -1114,15 +1109,12 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, *asmptr++ = 0; /* To be filled in later */ *asmptr++ = 0; /* Ditto */ *asmptr++ = NR_INFO; - SOCK_DEBUG(sk, "Built header.\n"); /* * Put the data on the end */ skb_put(skb, len); - SOCK_DEBUG(sk, "NET/ROM: Appending user data\n"); - /* User data follows immediately after the NET/ROM transport header */ if (memcpy_fromiovec(skb_transport_header(skb), msg->msg_iov, len)) { kfree_skb(skb); @@ -1130,8 +1122,6 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, goto out; } - SOCK_DEBUG(sk, "NET/ROM: Transmitting buffer\n"); - if (sk->sk_state != TCP_ESTABLISHED) { kfree_skb(skb); err = -ENOTCONN; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b5362e96022b..925f715686a5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,7 +538,7 @@ static inline unsigned int run_filter(const struct sk_buff *skb, rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) - res = sk_run_filter(skb, filter->insns); + res = SK_RUN_FILTER(filter, skb); rcu_read_unlock(); return res; @@ -2706,7 +2706,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) const struct packet_sock *po = pkt_sk(s); seq_printf(seq, - "%p %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", + "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, atomic_read(&s->sk_refcnt), s->sk_type, diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 947038ddd04c..d2df8f33160b 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -162,14 +162,6 @@ int phonet_address_add(struct net_device *dev, u8 addr) return err; } -static void phonet_device_rcu_free(struct rcu_head *head) -{ - struct phonet_device *pnd; - - pnd = container_of(head, struct phonet_device, rcu); - kfree(pnd); -} - int phonet_address_del(struct net_device *dev, u8 addr) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); @@ -188,7 +180,7 @@ int phonet_address_del(struct net_device *dev, u8 addr) mutex_unlock(&pndevs->lock); if (pnd) - call_rcu(&pnd->rcu, phonet_device_rcu_free); + kfree_rcu(pnd, rcu); return err; } @@ -426,18 +418,14 @@ int phonet_route_del(struct net_device *dev, u8 daddr) return 0; } -struct net_device *phonet_route_get(struct net *net, u8 daddr) +struct net_device *phonet_route_get_rcu(struct net *net, u8 daddr) { struct phonet_net *pnn = phonet_pernet(net); struct phonet_routes *routes = &pnn->routes; struct net_device *dev; - ASSERT_RTNL(); /* no need to hold the device */ - daddr >>= 2; - rcu_read_lock(); dev = rcu_dereference(routes->table[daddr]); - rcu_read_unlock(); return dev; } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 58b3b1f991ed..438accb7a5a8 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -264,10 +264,11 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); u8 addr, addr_idx = 0, addr_start_idx = cb->args[0]; + rcu_read_lock(); for (addr = 0; addr < 64; addr++) { struct net_device *dev; - dev = phonet_route_get(net, addr << 2); + dev = phonet_route_get_rcu(net, addr << 2); if (!dev) continue; @@ -279,6 +280,7 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } out: + rcu_read_unlock(); cb->args[0] = addr_idx; cb->args[1] = 0; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index b1adafab377c..ab07711cf2f4 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -52,7 +52,7 @@ static int pn_socket_release(struct socket *sock) static struct { struct hlist_head hlist[PN_HASHSIZE]; - spinlock_t lock; + struct mutex lock; } pnsocks; void __init pn_sock_init(void) @@ -61,7 +61,7 @@ void __init pn_sock_init(void) for (i = 0; i < PN_HASHSIZE; i++) INIT_HLIST_HEAD(pnsocks.hlist + i); - spin_lock_init(&pnsocks.lock); + mutex_init(&pnsocks.lock); } static struct hlist_head *pn_hash_list(u16 obj) @@ -82,9 +82,8 @@ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) u8 res = spn->spn_resource; struct hlist_head *hlist = pn_hash_list(obj); - spin_lock_bh(&pnsocks.lock); - - sk_for_each(sknode, node, hlist) { + rcu_read_lock(); + sk_for_each_rcu(sknode, node, hlist) { struct pn_sock *pn = pn_sk(sknode); BUG_ON(!pn->sobject); /* unbound socket */ @@ -107,8 +106,7 @@ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) sock_hold(sknode); break; } - - spin_unlock_bh(&pnsocks.lock); + rcu_read_unlock(); return rval; } @@ -119,7 +117,7 @@ void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb) struct hlist_head *hlist = pnsocks.hlist; unsigned h; - spin_lock(&pnsocks.lock); + rcu_read_lock(); for (h = 0; h < PN_HASHSIZE; h++) { struct hlist_node *node; struct sock *sknode; @@ -140,25 +138,26 @@ void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb) } hlist++; } - spin_unlock(&pnsocks.lock); + rcu_read_unlock(); } void pn_sock_hash(struct sock *sk) { struct hlist_head *hlist = pn_hash_list(pn_sk(sk)->sobject); - spin_lock_bh(&pnsocks.lock); - sk_add_node(sk, hlist); - spin_unlock_bh(&pnsocks.lock); + mutex_lock(&pnsocks.lock); + sk_add_node_rcu(sk, hlist); + mutex_unlock(&pnsocks.lock); } EXPORT_SYMBOL(pn_sock_hash); void pn_sock_unhash(struct sock *sk) { - spin_lock_bh(&pnsocks.lock); - sk_del_node_init(sk); - spin_unlock_bh(&pnsocks.lock); + mutex_lock(&pnsocks.lock); + sk_del_node_init_rcu(sk); + mutex_unlock(&pnsocks.lock); pn_sock_unbind_all_res(sk); + synchronize_rcu(); } EXPORT_SYMBOL(pn_sock_unhash); @@ -548,7 +547,7 @@ static struct sock *pn_sock_get_idx(struct seq_file *seq, loff_t pos) unsigned h; for (h = 0; h < PN_HASHSIZE; h++) { - sk_for_each(sknode, node, hlist) { + sk_for_each_rcu(sknode, node, hlist) { if (!net_eq(net, sock_net(sknode))) continue; if (!pos) @@ -572,9 +571,9 @@ static struct sock *pn_sock_get_next(struct seq_file *seq, struct sock *sk) } static void *pn_sock_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(pnsocks.lock) + __acquires(rcu) { - spin_lock_bh(&pnsocks.lock); + rcu_read_lock(); return *pos ? pn_sock_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -591,9 +590,9 @@ static void *pn_sock_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void pn_sock_seq_stop(struct seq_file *seq, void *v) - __releases(pnsocks.lock) + __releases(rcu) { - spin_unlock_bh(&pnsocks.lock); + rcu_read_unlock(); } static int pn_sock_seq_show(struct seq_file *seq, void *v) @@ -608,7 +607,7 @@ static int pn_sock_seq_show(struct seq_file *seq, void *v) struct pn_sock *pn = pn_sk(sk); seq_printf(seq, "%2d %04X:%04X:%02X %02X %08X:%08X %5d %lu " - "%d %p %d%n", + "%d %pK %d%n", sk->sk_protocol, pn->sobject, pn->dobject, pn->resource, sk->sk_state, sk_wmem_alloc_get(sk), sk_rmem_alloc_get(sk), @@ -721,13 +720,11 @@ void pn_sock_unbind_all_res(struct sock *sk) } mutex_unlock(&resource_mutex); - if (match == 0) - return; - synchronize_rcu(); while (match > 0) { - sock_put(sk); + __sock_put(sk); match--; } + /* Caller is responsible for RCU sync before final sock_put() */ } #ifdef CONFIG_PROC_FS diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index c47a511f203d..7c4dce8fa5e6 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -355,7 +355,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) * * Conceptually, we have two counters: * - send credits: this tells us how many WRs we're allowed - * to submit without overruning the reciever's queue. For + * to submit without overruning the receiver's queue. For * each SEND WR we post, we decrement this by one. * * - posted credits: this tells us how many WRs we recently diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c index 712cf2d1f28e..3a60a15d1b4a 100644 --- a/net/rds/iw_cm.c +++ b/net/rds/iw_cm.c @@ -181,7 +181,7 @@ static int rds_iw_init_qp_attrs(struct ib_qp_init_attr *attr, unsigned int send_size, recv_size; int ret; - /* The offset of 1 is to accomodate the additional ACK WR. */ + /* The offset of 1 is to accommodate the additional ACK WR. */ send_size = min_t(unsigned int, rds_iwdev->max_wrs, rds_iw_sysctl_max_send_wr + 1); recv_size = min_t(unsigned int, rds_iwdev->max_wrs, rds_iw_sysctl_max_recv_wr + 1); rds_iw_ring_resize(send_ring, send_size - 1); diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index 59509e9a9e72..6deaa77495e3 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -122,7 +122,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd #else /* FIXME - needs to compare the local and remote * ipaddr/port tuple, but the ipaddr is the only - * available infomation in the rds_sock (as the rest are + * available information in the rds_sock (as the rest are * zero'ed. It doesn't appear to be properly populated * during connection setup... */ diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 6280ea020d4e..545d8ee3efb1 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -307,7 +307,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context) * * Conceptually, we have two counters: * - send credits: this tells us how many WRs we're allowed - * to submit without overruning the reciever's queue. For + * to submit without overruning the receiver's queue. For * each SEND WR we post, we decrement this by one. * * - posted credits: this tells us how many WRs we recently diff --git a/net/rds/send.c b/net/rds/send.c index 35b9c2e9caf1..d58ae5f9339e 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -116,7 +116,7 @@ static void release_in_xmit(struct rds_connection *conn) } /* - * We're making the concious trade-off here to only send one message + * We're making the conscious trade-off here to only send one message * down the connection at a time. * Pro: * - tx queueing is a simple fifo list diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index a80aef6e3d1f..f9ea925ad9cb 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -682,10 +682,8 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS) return -EINVAL; - if ((dev = rose_dev_get(&addr->srose_addr)) == NULL) { - SOCK_DEBUG(sk, "ROSE: bind failed: invalid address\n"); + if ((dev = rose_dev_get(&addr->srose_addr)) == NULL) return -EADDRNOTAVAIL; - } source = &addr->srose_call; @@ -716,7 +714,7 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) rose_insert_socket(sk); sock_reset_flag(sk, SOCK_ZAPPED); - SOCK_DEBUG(sk, "ROSE: socket is bound\n"); + return 0; } @@ -1109,10 +1107,7 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, srose.srose_digis[n] = rose->dest_digis[n]; } - SOCK_DEBUG(sk, "ROSE: sendto: Addresses built.\n"); - /* Build a packet */ - SOCK_DEBUG(sk, "ROSE: sendto: building packet.\n"); /* Sanity check the packet size */ if (len > 65535) return -EMSGSIZE; @@ -1127,7 +1122,6 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, /* * Put the data on the end */ - SOCK_DEBUG(sk, "ROSE: Appending user data\n"); skb_reset_transport_header(skb); skb_put(skb, len); @@ -1152,8 +1146,6 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, */ asmptr = skb_push(skb, ROSE_MIN_LEN); - SOCK_DEBUG(sk, "ROSE: Building Network Header.\n"); - /* Build a ROSE Network header */ asmptr[0] = ((rose->lci >> 8) & 0x0F) | ROSE_GFI; asmptr[1] = (rose->lci >> 0) & 0xFF; @@ -1162,10 +1154,6 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, if (qbit) asmptr[0] |= ROSE_Q_BIT; - SOCK_DEBUG(sk, "ROSE: Built header.\n"); - - SOCK_DEBUG(sk, "ROSE: Transmitting buffer\n"); - if (sk->sk_state != TCP_ESTABLISHED) { kfree_skb(skb); return -ENOTCONN; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 08dcd2f29cdc..479cae57d187 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -587,7 +587,7 @@ static int rose_clear_routes(void) /* * Check that the device given is a valid AX.25 interface that is "up". - * called whith RTNL + * called with RTNL */ static struct net_device *rose_ax25_dev_find(char *devname) { diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index b6ffe4e1b84a..f99cfce7ca97 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -375,7 +375,6 @@ protocol_error: */ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, u32 hard) { - struct rxrpc_skb_priv *sp; unsigned long _skb; int tail = call->acks_tail, old_tail; int win = CIRC_CNT(call->acks_head, tail, call->acks_winsz); @@ -387,7 +386,6 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, u32 hard) while (call->acks_hard < hard) { smp_read_barrier_depends(); _skb = call->acks_window[tail] & ~1; - sp = rxrpc_skb((struct sk_buff *) _skb); rxrpc_free_skb((struct sk_buff *) _skb); old_tail = tail; tail = (tail + 1) & (call->acks_winsz - 1); diff --git a/net/rxrpc/ar-connevent.c b/net/rxrpc/ar-connevent.c index 0505cdc4d6d4..e7ed43a54c41 100644 --- a/net/rxrpc/ar-connevent.c +++ b/net/rxrpc/ar-connevent.c @@ -259,7 +259,6 @@ void rxrpc_process_connection(struct work_struct *work) { struct rxrpc_connection *conn = container_of(work, struct rxrpc_connection, processor); - struct rxrpc_skb_priv *sp; struct sk_buff *skb; u32 abort_code = RX_PROTOCOL_ERROR; int ret; @@ -276,8 +275,6 @@ void rxrpc_process_connection(struct work_struct *work) /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { - sp = rxrpc_skb(skb); - ret = rxrpc_process_event(conn, skb, &abort_code); switch (ret) { case -EPROTO: diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c index d4d1ae26d293..5d6b572a6704 100644 --- a/net/rxrpc/ar-error.c +++ b/net/rxrpc/ar-error.c @@ -139,7 +139,7 @@ void rxrpc_UDP_error_handler(struct work_struct *work) struct rxrpc_transport *trans = container_of(work, struct rxrpc_transport, error_handler); struct sk_buff *skb; - int local, err; + int err; _enter(""); @@ -157,7 +157,6 @@ void rxrpc_UDP_error_handler(struct work_struct *work) switch (ee->ee_origin) { case SO_EE_ORIGIN_ICMP: - local = 0; switch (ee->ee_type) { case ICMP_DEST_UNREACH: switch (ee->ee_code) { @@ -207,7 +206,6 @@ void rxrpc_UDP_error_handler(struct work_struct *work) case SO_EE_ORIGIN_LOCAL: _proto("Rx Received local error { error=%d }", ee->ee_errno); - local = 1; break; case SO_EE_ORIGIN_NONE: @@ -215,7 +213,6 @@ void rxrpc_UDP_error_handler(struct work_struct *work) default: _proto("Rx Received error report { orig=%u }", ee->ee_origin); - local = 0; break; } diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c index 55b93dc60d0c..2754f098d436 100644 --- a/net/rxrpc/ar-peer.c +++ b/net/rxrpc/ar-peer.c @@ -36,10 +36,11 @@ static void rxrpc_destroy_peer(struct work_struct *work); static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) { struct rtable *rt; + struct flowi4 fl4; peer->if_mtu = 1500; - rt = ip_route_output_ports(&init_net, NULL, + rt = ip_route_output_ports(&init_net, &fl4, NULL, peer->srx.transport.sin.sin_addr.s_addr, 0, htons(7000), htons(7001), IPPROTO_UDP, 0, 0); @@ -156,6 +157,7 @@ struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *srx, gfp_t gfp) /* we can now add the new candidate to the list */ peer = candidate; candidate = NULL; + usage = atomic_read(&peer->usage); list_add_tail(&peer->link, &rxrpc_peers); write_unlock_bh(&rxrpc_peer_lock); @@ -170,7 +172,7 @@ success: &peer->srx.transport.sin.sin_addr, ntohs(peer->srx.transport.sin.sin_port)); - _leave(" = %p {u=%d}", peer, atomic_read(&peer->usage)); + _leave(" = %p {u=%d}", peer, usage); return peer; /* we found the peer in the list immediately */ diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c index 5e0226fe587e..92df566930b9 100644 --- a/net/rxrpc/ar-transport.c +++ b/net/rxrpc/ar-transport.c @@ -111,6 +111,7 @@ struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *local, /* we can now add the new candidate to the list */ trans = candidate; candidate = NULL; + usage = atomic_read(&trans->usage); rxrpc_get_local(trans->local); atomic_inc(&trans->peer->usage); @@ -125,7 +126,7 @@ success: trans->local->debug_id, trans->peer->debug_id); - _leave(" = %p {u=%d}", trans, atomic_read(&trans->usage)); + _leave(" = %p {u=%d}", trans, usage); return trans; /* we found the transport in the list immediately */ diff --git a/net/sched/Kconfig b/net/sched/Kconfig index a7a5583d4f68..2590e91b3289 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -239,6 +239,17 @@ config NET_SCH_CHOKE To compile this code as a module, choose M here: the module will be called sch_choke. +config NET_SCH_QFQ + tristate "Quick Fair Queueing scheduler (QFQ)" + help + Say Y here if you want to use the Quick Fair Queueing Scheduler (QFQ) + packet scheduling algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_qfq. + + If unsure, say N. + config NET_SCH_INGRESS tristate "Ingress Qdisc" depends on NET_CLS_ACT @@ -277,6 +288,7 @@ config NET_CLS_TCINDEX config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" + depends on INET select IP_ROUTE_CLASSID select NET_CLS ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 2e77b8dba22e..dc5889c0a15a 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o +obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 15873e14cb54..a606025814a1 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -26,11 +26,6 @@ #include <net/act_api.h> #include <net/netlink.h> -static void tcf_common_free_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct tcf_common, tcfc_rcu)); -} - void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) { unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); @@ -47,7 +42,7 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) * gen_estimator est_timer() might access p->tcfc_lock * or bstats, wait a RCU grace period before freeing p */ - call_rcu(&p->tcfc_rcu, tcf_common_free_rcu); + kfree_rcu(p, tcfc_rcu); return; } } @@ -999,7 +994,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) switch (n->nlmsg_type) { case RTM_NEWACTION: /* we are going to assume all other flags - * imply create only if it doesnt exist + * imply create only if it doesn't exist * Note that CREATE | EXCL implies that * but since we want avoid ambiguity (eg when flags * is zero) then just set this diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 50c7c06c019d..7affe9a92757 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -161,7 +161,7 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, } if (offset > 0 && offset > skb->len) { pr_info("tc filter pedit" - " offset %d cant exceed pkt length %d\n", + " offset %d can't exceed pkt length %d\n", offset, skb->len); goto bad; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 8a1630774fd6..b3b9b32f4e00 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -96,11 +96,6 @@ nla_put_failure: goto done; } -static void tcf_police_free_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct tcf_police, tcf_rcu)); -} - static void tcf_police_destroy(struct tcf_police *p) { unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK); @@ -121,7 +116,7 @@ static void tcf_police_destroy(struct tcf_police *p) * gen_estimator est_timer() might access p->tcf_lock * or bstats, wait a RCU grace period before freeing p */ - call_rcu(&p->tcf_rcu, tcf_police_free_rcu); + kfree_rcu(p, tcf_rcu); return; } } @@ -401,7 +396,6 @@ static void __exit police_cleanup_module(void) { tcf_unregister_action(&act_police_ops); - rcu_barrier(); /* Wait for completion of call_rcu()'s (tcf_police_free_rcu) */ } module_init(police_init_module); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index a4de67eca824..49130e8abff0 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -47,7 +47,7 @@ * on the meta type. Obviously, the length of the data must also * be provided for non-numeric types. * - * Additionaly, type dependant modifiers such as shift operators + * Additionally, type dependent modifiers such as shift operators * or mask may be applied to extend the functionaliy. As of now, * the variable length type supports shifting the byte string to * the right, eating up any number of octets and thus supporting diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 7490f3f2db8b..6b8627661c98 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1673,10 +1673,8 @@ int tc_classify(struct sk_buff *skb, struct tcf_proto *tp, { int err = 0; #ifdef CONFIG_NET_CLS_ACT - __be16 protocol; struct tcf_proto *otp = tp; reclassify: - protocol = skb->protocol; #endif err = tc_classify_compat(skb, tp, res); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index c84b65920d1b..b1721d71c27c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -815,9 +815,17 @@ static bool some_qdisc_is_busy(struct net_device *dev) return false; } +/** + * dev_deactivate_many - deactivate transmissions on several devices + * @head: list of devices to deactivate + * + * This function returns only when all outstanding transmissions + * have completed, unless all devices are in dismantle phase. + */ void dev_deactivate_many(struct list_head *head) { struct net_device *dev; + bool sync_needed = false; list_for_each_entry(dev, head, unreg_list) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, @@ -827,10 +835,15 @@ void dev_deactivate_many(struct list_head *head) &noop_qdisc); dev_watchdog_down(dev); + sync_needed |= !dev->dismantle; } - /* Wait for outstanding qdisc-less dev_queue_xmit calls. */ - synchronize_rcu(); + /* Wait for outstanding qdisc-less dev_queue_xmit calls. + * This is avoided if all devices are in dismantle phase : + * Caller will call synchronize_net() for us + */ + if (sync_needed) + synchronize_net(); /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, unreg_list) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index e1429a85091f..29b942ce9e82 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -183,7 +183,7 @@ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) * filters in qdisc and in inner nodes (if higher filter points to the inner * node). If we end up with classid MAJOR:0 we enqueue the skb into special * internal fifo (direct). These packets then go directly thru. If we still - * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessfull + * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessful * then finish and return direct queue. */ #define HTB_DIRECT ((struct htb_class *)-1L) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index edbbf7ad6623..69c35f6cd13f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -160,7 +160,7 @@ static bool loss_4state(struct netem_sched_data *q) u32 rnd = net_random(); /* - * Makes a comparision between rnd and the transition + * Makes a comparison between rnd and the transition * probabilities outgoing from the current state, then decides the * next state and if the next packet has to be transmitted or lost. * The four states correspond to: @@ -212,9 +212,9 @@ static bool loss_4state(struct netem_sched_data *q) * Generates losses according to the Gilbert-Elliot loss model or * its special cases (Gilbert or Simple Gilbert) * - * Makes a comparision between random number and the transition + * Makes a comparison between random number and the transition * probabilities outgoing from the current state, then decides the - * next state. A second random number is extracted and the comparision + * next state. A second random number is extracted and the comparison * with the loss probability of the current state decides if the next * packet will be transmitted or lost. */ diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c new file mode 100644 index 000000000000..103343408593 --- /dev/null +++ b/net/sched/sch_qfq.c @@ -0,0 +1,1137 @@ +/* + * net/sched/sch_qfq.c Quick Fair Queueing Scheduler. + * + * Copyright (c) 2009 Fabio Checconi, Luigi Rizzo, and Paolo Valente. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/errno.h> +#include <linux/netdevice.h> +#include <linux/pkt_sched.h> +#include <net/sch_generic.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> + + +/* Quick Fair Queueing + =================== + + Sources: + + Fabio Checconi, Luigi Rizzo, and Paolo Valente: "QFQ: Efficient + Packet Scheduling with Tight Bandwidth Distribution Guarantees." + + See also: + http://retis.sssup.it/~fabio/linux/qfq/ + */ + +/* + + Virtual time computations. + + S, F and V are all computed in fixed point arithmetic with + FRAC_BITS decimal bits. + + QFQ_MAX_INDEX is the maximum index allowed for a group. We need + one bit per index. + QFQ_MAX_WSHIFT is the maximum power of two supported as a weight. + + The layout of the bits is as below: + + [ MTU_SHIFT ][ FRAC_BITS ] + [ MAX_INDEX ][ MIN_SLOT_SHIFT ] + ^.__grp->index = 0 + *.__grp->slot_shift + + where MIN_SLOT_SHIFT is derived by difference from the others. + + The max group index corresponds to Lmax/w_min, where + Lmax=1<<MTU_SHIFT, w_min = 1 . + From this, and knowing how many groups (MAX_INDEX) we want, + we can derive the shift corresponding to each group. + + Because we often need to compute + F = S + len/w_i and V = V + len/wsum + instead of storing w_i store the value + inv_w = (1<<FRAC_BITS)/w_i + so we can do F = S + len * inv_w * wsum. + We use W_TOT in the formulas so we can easily move between + static and adaptive weight sum. + + The per-scheduler-instance data contain all the data structures + for the scheduler: bitmaps and bucket lists. + + */ + +/* + * Maximum number of consecutive slots occupied by backlogged classes + * inside a group. + */ +#define QFQ_MAX_SLOTS 32 + +/* + * Shifts used for class<->group mapping. We allow class weights that are + * in the range [1, 2^MAX_WSHIFT], and we try to map each class i to the + * group with the smallest index that can support the L_i / r_i configured + * for the class. + * + * grp->index is the index of the group; and grp->slot_shift + * is the shift for the corresponding (scaled) sigma_i. + */ +#define QFQ_MAX_INDEX 19 +#define QFQ_MAX_WSHIFT 16 + +#define QFQ_MAX_WEIGHT (1<<QFQ_MAX_WSHIFT) +#define QFQ_MAX_WSUM (2*QFQ_MAX_WEIGHT) + +#define FRAC_BITS 30 /* fixed point arithmetic */ +#define ONE_FP (1UL << FRAC_BITS) +#define IWSUM (ONE_FP/QFQ_MAX_WSUM) + +#define QFQ_MTU_SHIFT 11 +#define QFQ_MIN_SLOT_SHIFT (FRAC_BITS + QFQ_MTU_SHIFT - QFQ_MAX_INDEX) + +/* + * Possible group states. These values are used as indexes for the bitmaps + * array of struct qfq_queue. + */ +enum qfq_state { ER, IR, EB, IB, QFQ_MAX_STATE }; + +struct qfq_group; + +struct qfq_class { + struct Qdisc_class_common common; + + unsigned int refcnt; + unsigned int filter_cnt; + + struct gnet_stats_basic_packed bstats; + struct gnet_stats_queue qstats; + struct gnet_stats_rate_est rate_est; + struct Qdisc *qdisc; + + struct hlist_node next; /* Link for the slot list. */ + u64 S, F; /* flow timestamps (exact) */ + + /* group we belong to. In principle we would need the index, + * which is log_2(lmax/weight), but we never reference it + * directly, only the group. + */ + struct qfq_group *grp; + + /* these are copied from the flowset. */ + u32 inv_w; /* ONE_FP/weight */ + u32 lmax; /* Max packet size for this flow. */ +}; + +struct qfq_group { + u64 S, F; /* group timestamps (approx). */ + unsigned int slot_shift; /* Slot shift. */ + unsigned int index; /* Group index. */ + unsigned int front; /* Index of the front slot. */ + unsigned long full_slots; /* non-empty slots */ + + /* Array of RR lists of active classes. */ + struct hlist_head slots[QFQ_MAX_SLOTS]; +}; + +struct qfq_sched { + struct tcf_proto *filter_list; + struct Qdisc_class_hash clhash; + + u64 V; /* Precise virtual time. */ + u32 wsum; /* weight sum */ + + unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */ + struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */ +}; + +static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct Qdisc_class_common *clc; + + clc = qdisc_class_find(&q->clhash, classid); + if (clc == NULL) + return NULL; + return container_of(clc, struct qfq_class, common); +} + +static void qfq_purge_queue(struct qfq_class *cl) +{ + unsigned int len = cl->qdisc->q.qlen; + + qdisc_reset(cl->qdisc); + qdisc_tree_decrease_qlen(cl->qdisc, len); +} + +static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { + [TCA_QFQ_WEIGHT] = { .type = NLA_U32 }, + [TCA_QFQ_LMAX] = { .type = NLA_U32 }, +}; + +/* + * Calculate a flow index, given its weight and maximum packet length. + * index = log_2(maxlen/weight) but we need to apply the scaling. + * This is used only once at flow creation. + */ +static int qfq_calc_index(u32 inv_w, unsigned int maxlen) +{ + u64 slot_size = (u64)maxlen * inv_w; + unsigned long size_map; + int index = 0; + + size_map = slot_size >> QFQ_MIN_SLOT_SHIFT; + if (!size_map) + goto out; + + index = __fls(size_map) + 1; /* basically a log_2 */ + index -= !(slot_size - (1ULL << (index + QFQ_MIN_SLOT_SHIFT - 1))); + + if (index < 0) + index = 0; +out: + pr_debug("qfq calc_index: W = %lu, L = %u, I = %d\n", + (unsigned long) ONE_FP/inv_w, maxlen, index); + + return index; +} + +static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, + struct nlattr **tca, unsigned long *arg) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_class *cl = (struct qfq_class *)*arg; + struct nlattr *tb[TCA_QFQ_MAX + 1]; + u32 weight, lmax, inv_w; + int i, err; + + if (tca[TCA_OPTIONS] == NULL) { + pr_notice("qfq: no options\n"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], qfq_policy); + if (err < 0) + return err; + + if (tb[TCA_QFQ_WEIGHT]) { + weight = nla_get_u32(tb[TCA_QFQ_WEIGHT]); + if (!weight || weight > (1UL << QFQ_MAX_WSHIFT)) { + pr_notice("qfq: invalid weight %u\n", weight); + return -EINVAL; + } + } else + weight = 1; + + inv_w = ONE_FP / weight; + weight = ONE_FP / inv_w; + if (q->wsum + weight > QFQ_MAX_WSUM) { + pr_notice("qfq: total weight out of range (%u + %u)\n", + weight, q->wsum); + return -EINVAL; + } + + if (tb[TCA_QFQ_LMAX]) { + lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); + if (!lmax || lmax > (1UL << QFQ_MTU_SHIFT)) { + pr_notice("qfq: invalid max length %u\n", lmax); + return -EINVAL; + } + } else + lmax = 1UL << QFQ_MTU_SHIFT; + + if (cl != NULL) { + if (tca[TCA_RATE]) { + err = gen_replace_estimator(&cl->bstats, &cl->rate_est, + qdisc_root_sleeping_lock(sch), + tca[TCA_RATE]); + if (err) + return err; + } + + sch_tree_lock(sch); + if (tb[TCA_QFQ_WEIGHT]) { + q->wsum = weight - ONE_FP / cl->inv_w; + cl->inv_w = inv_w; + } + sch_tree_unlock(sch); + + return 0; + } + + cl = kzalloc(sizeof(struct qfq_class), GFP_KERNEL); + if (cl == NULL) + return -ENOBUFS; + + cl->refcnt = 1; + cl->common.classid = classid; + cl->lmax = lmax; + cl->inv_w = inv_w; + i = qfq_calc_index(cl->inv_w, cl->lmax); + + cl->grp = &q->groups[i]; + q->wsum += weight; + + cl->qdisc = qdisc_create_dflt(sch->dev_queue, + &pfifo_qdisc_ops, classid); + if (cl->qdisc == NULL) + cl->qdisc = &noop_qdisc; + + if (tca[TCA_RATE]) { + err = gen_new_estimator(&cl->bstats, &cl->rate_est, + qdisc_root_sleeping_lock(sch), + tca[TCA_RATE]); + if (err) { + qdisc_destroy(cl->qdisc); + kfree(cl); + return err; + } + } + + sch_tree_lock(sch); + qdisc_class_hash_insert(&q->clhash, &cl->common); + sch_tree_unlock(sch); + + qdisc_class_hash_grow(sch, &q->clhash); + + *arg = (unsigned long)cl; + return 0; +} + +static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) +{ + struct qfq_sched *q = qdisc_priv(sch); + + if (cl->inv_w) { + q->wsum -= ONE_FP / cl->inv_w; + cl->inv_w = 0; + } + + gen_kill_estimator(&cl->bstats, &cl->rate_est); + qdisc_destroy(cl->qdisc); + kfree(cl); +} + +static int qfq_delete_class(struct Qdisc *sch, unsigned long arg) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_class *cl = (struct qfq_class *)arg; + + if (cl->filter_cnt > 0) + return -EBUSY; + + sch_tree_lock(sch); + + qfq_purge_queue(cl); + qdisc_class_hash_remove(&q->clhash, &cl->common); + + BUG_ON(--cl->refcnt == 0); + /* + * This shouldn't happen: we "hold" one cops->get() when called + * from tc_ctl_tclass; the destroy method is done from cops->put(). + */ + + sch_tree_unlock(sch); + return 0; +} + +static unsigned long qfq_get_class(struct Qdisc *sch, u32 classid) +{ + struct qfq_class *cl = qfq_find_class(sch, classid); + + if (cl != NULL) + cl->refcnt++; + + return (unsigned long)cl; +} + +static void qfq_put_class(struct Qdisc *sch, unsigned long arg) +{ + struct qfq_class *cl = (struct qfq_class *)arg; + + if (--cl->refcnt == 0) + qfq_destroy_class(sch, cl); +} + +static struct tcf_proto **qfq_tcf_chain(struct Qdisc *sch, unsigned long cl) +{ + struct qfq_sched *q = qdisc_priv(sch); + + if (cl) + return NULL; + + return &q->filter_list; +} + +static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + struct qfq_class *cl = qfq_find_class(sch, classid); + + if (cl != NULL) + cl->filter_cnt++; + + return (unsigned long)cl; +} + +static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg) +{ + struct qfq_class *cl = (struct qfq_class *)arg; + + cl->filter_cnt--; +} + +static int qfq_graft_class(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old) +{ + struct qfq_class *cl = (struct qfq_class *)arg; + + if (new == NULL) { + new = qdisc_create_dflt(sch->dev_queue, + &pfifo_qdisc_ops, cl->common.classid); + if (new == NULL) + new = &noop_qdisc; + } + + sch_tree_lock(sch); + qfq_purge_queue(cl); + *old = cl->qdisc; + cl->qdisc = new; + sch_tree_unlock(sch); + return 0; +} + +static struct Qdisc *qfq_class_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct qfq_class *cl = (struct qfq_class *)arg; + + return cl->qdisc; +} + +static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct qfq_class *cl = (struct qfq_class *)arg; + struct nlattr *nest; + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle = cl->common.classid; + tcm->tcm_info = cl->qdisc->handle; + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (nest == NULL) + goto nla_put_failure; + NLA_PUT_U32(skb, TCA_QFQ_WEIGHT, ONE_FP/cl->inv_w); + NLA_PUT_U32(skb, TCA_QFQ_LMAX, cl->lmax); + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, + struct gnet_dump *d) +{ + struct qfq_class *cl = (struct qfq_class *)arg; + struct tc_qfq_stats xstats; + + memset(&xstats, 0, sizeof(xstats)); + cl->qdisc->qstats.qlen = cl->qdisc->q.qlen; + + xstats.weight = ONE_FP/cl->inv_w; + xstats.lmax = cl->lmax; + + if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || + gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || + gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0) + return -1; + + return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); +} + +static void qfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_class *cl; + struct hlist_node *n; + unsigned int i; + + if (arg->stop) + return; + + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + if (arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, (unsigned long)cl, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } + } +} + +static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_class *cl; + struct tcf_result res; + int result; + + if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) { + pr_debug("qfq_classify: found %d\n", skb->priority); + cl = qfq_find_class(sch, skb->priority); + if (cl != NULL) + return cl; + } + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + result = tc_classify(skb, q->filter_list, &res); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_QUEUED: + case TC_ACT_STOLEN: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + case TC_ACT_SHOT: + return NULL; + } +#endif + cl = (struct qfq_class *)res.class; + if (cl == NULL) + cl = qfq_find_class(sch, res.classid); + return cl; + } + + return NULL; +} + +/* Generic comparison function, handling wraparound. */ +static inline int qfq_gt(u64 a, u64 b) +{ + return (s64)(a - b) > 0; +} + +/* Round a precise timestamp to its slotted value. */ +static inline u64 qfq_round_down(u64 ts, unsigned int shift) +{ + return ts & ~((1ULL << shift) - 1); +} + +/* return the pointer to the group with lowest index in the bitmap */ +static inline struct qfq_group *qfq_ffs(struct qfq_sched *q, + unsigned long bitmap) +{ + int index = __ffs(bitmap); + return &q->groups[index]; +} +/* Calculate a mask to mimic what would be ffs_from(). */ +static inline unsigned long mask_from(unsigned long bitmap, int from) +{ + return bitmap & ~((1UL << from) - 1); +} + +/* + * The state computation relies on ER=0, IR=1, EB=2, IB=3 + * First compute eligibility comparing grp->S, q->V, + * then check if someone is blocking us and possibly add EB + */ +static int qfq_calc_state(struct qfq_sched *q, const struct qfq_group *grp) +{ + /* if S > V we are not eligible */ + unsigned int state = qfq_gt(grp->S, q->V); + unsigned long mask = mask_from(q->bitmaps[ER], grp->index); + struct qfq_group *next; + + if (mask) { + next = qfq_ffs(q, mask); + if (qfq_gt(grp->F, next->F)) + state |= EB; + } + + return state; +} + + +/* + * In principle + * q->bitmaps[dst] |= q->bitmaps[src] & mask; + * q->bitmaps[src] &= ~mask; + * but we should make sure that src != dst + */ +static inline void qfq_move_groups(struct qfq_sched *q, unsigned long mask, + int src, int dst) +{ + q->bitmaps[dst] |= q->bitmaps[src] & mask; + q->bitmaps[src] &= ~mask; +} + +static void qfq_unblock_groups(struct qfq_sched *q, int index, u64 old_F) +{ + unsigned long mask = mask_from(q->bitmaps[ER], index + 1); + struct qfq_group *next; + + if (mask) { + next = qfq_ffs(q, mask); + if (!qfq_gt(next->F, old_F)) + return; + } + + mask = (1UL << index) - 1; + qfq_move_groups(q, mask, EB, ER); + qfq_move_groups(q, mask, IB, IR); +} + +/* + * perhaps + * + old_V ^= q->V; + old_V >>= QFQ_MIN_SLOT_SHIFT; + if (old_V) { + ... + } + * + */ +static void qfq_make_eligible(struct qfq_sched *q, u64 old_V) +{ + unsigned long vslot = q->V >> QFQ_MIN_SLOT_SHIFT; + unsigned long old_vslot = old_V >> QFQ_MIN_SLOT_SHIFT; + + if (vslot != old_vslot) { + unsigned long mask = (1UL << fls(vslot ^ old_vslot)) - 1; + qfq_move_groups(q, mask, IR, ER); + qfq_move_groups(q, mask, IB, EB); + } +} + + +/* + * XXX we should make sure that slot becomes less than 32. + * This is guaranteed by the input values. + * roundedS is always cl->S rounded on grp->slot_shift bits. + */ +static void qfq_slot_insert(struct qfq_group *grp, struct qfq_class *cl, + u64 roundedS) +{ + u64 slot = (roundedS - grp->S) >> grp->slot_shift; + unsigned int i = (grp->front + slot) % QFQ_MAX_SLOTS; + + hlist_add_head(&cl->next, &grp->slots[i]); + __set_bit(slot, &grp->full_slots); +} + +/* Maybe introduce hlist_first_entry?? */ +static struct qfq_class *qfq_slot_head(struct qfq_group *grp) +{ + return hlist_entry(grp->slots[grp->front].first, + struct qfq_class, next); +} + +/* + * remove the entry from the slot + */ +static void qfq_front_slot_remove(struct qfq_group *grp) +{ + struct qfq_class *cl = qfq_slot_head(grp); + + BUG_ON(!cl); + hlist_del(&cl->next); + if (hlist_empty(&grp->slots[grp->front])) + __clear_bit(0, &grp->full_slots); +} + +/* + * Returns the first full queue in a group. As a side effect, + * adjust the bucket list so the first non-empty bucket is at + * position 0 in full_slots. + */ +static struct qfq_class *qfq_slot_scan(struct qfq_group *grp) +{ + unsigned int i; + + pr_debug("qfq slot_scan: grp %u full %#lx\n", + grp->index, grp->full_slots); + + if (grp->full_slots == 0) + return NULL; + + i = __ffs(grp->full_slots); /* zero based */ + if (i > 0) { + grp->front = (grp->front + i) % QFQ_MAX_SLOTS; + grp->full_slots >>= i; + } + + return qfq_slot_head(grp); +} + +/* + * adjust the bucket list. When the start time of a group decreases, + * we move the index down (modulo QFQ_MAX_SLOTS) so we don't need to + * move the objects. The mask of occupied slots must be shifted + * because we use ffs() to find the first non-empty slot. + * This covers decreases in the group's start time, but what about + * increases of the start time ? + * Here too we should make sure that i is less than 32 + */ +static void qfq_slot_rotate(struct qfq_group *grp, u64 roundedS) +{ + unsigned int i = (grp->S - roundedS) >> grp->slot_shift; + + grp->full_slots <<= i; + grp->front = (grp->front - i) % QFQ_MAX_SLOTS; +} + +static void qfq_update_eligible(struct qfq_sched *q, u64 old_V) +{ + struct qfq_group *grp; + unsigned long ineligible; + + ineligible = q->bitmaps[IR] | q->bitmaps[IB]; + if (ineligible) { + if (!q->bitmaps[ER]) { + grp = qfq_ffs(q, ineligible); + if (qfq_gt(grp->S, q->V)) + q->V = grp->S; + } + qfq_make_eligible(q, old_V); + } +} + +/* What is length of next packet in queue (0 if queue is empty) */ +static unsigned int qdisc_peek_len(struct Qdisc *sch) +{ + struct sk_buff *skb; + + skb = sch->ops->peek(sch); + return skb ? qdisc_pkt_len(skb) : 0; +} + +/* + * Updates the class, returns true if also the group needs to be updated. + */ +static bool qfq_update_class(struct qfq_group *grp, struct qfq_class *cl) +{ + unsigned int len = qdisc_peek_len(cl->qdisc); + + cl->S = cl->F; + if (!len) + qfq_front_slot_remove(grp); /* queue is empty */ + else { + u64 roundedS; + + cl->F = cl->S + (u64)len * cl->inv_w; + roundedS = qfq_round_down(cl->S, grp->slot_shift); + if (roundedS == grp->S) + return false; + + qfq_front_slot_remove(grp); + qfq_slot_insert(grp, cl, roundedS); + } + + return true; +} + +static struct sk_buff *qfq_dequeue(struct Qdisc *sch) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_group *grp; + struct qfq_class *cl; + struct sk_buff *skb; + unsigned int len; + u64 old_V; + + if (!q->bitmaps[ER]) + return NULL; + + grp = qfq_ffs(q, q->bitmaps[ER]); + + cl = qfq_slot_head(grp); + skb = qdisc_dequeue_peeked(cl->qdisc); + if (!skb) { + WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n"); + return NULL; + } + + sch->q.qlen--; + qdisc_bstats_update(sch, skb); + + old_V = q->V; + len = qdisc_pkt_len(skb); + q->V += (u64)len * IWSUM; + pr_debug("qfq dequeue: len %u F %lld now %lld\n", + len, (unsigned long long) cl->F, (unsigned long long) q->V); + + if (qfq_update_class(grp, cl)) { + u64 old_F = grp->F; + + cl = qfq_slot_scan(grp); + if (!cl) + __clear_bit(grp->index, &q->bitmaps[ER]); + else { + u64 roundedS = qfq_round_down(cl->S, grp->slot_shift); + unsigned int s; + + if (grp->S == roundedS) + goto skip_unblock; + grp->S = roundedS; + grp->F = roundedS + (2ULL << grp->slot_shift); + __clear_bit(grp->index, &q->bitmaps[ER]); + s = qfq_calc_state(q, grp); + __set_bit(grp->index, &q->bitmaps[s]); + } + + qfq_unblock_groups(q, grp->index, old_F); + } + +skip_unblock: + qfq_update_eligible(q, old_V); + + return skb; +} + +/* + * Assign a reasonable start time for a new flow k in group i. + * Admissible values for \hat(F) are multiples of \sigma_i + * no greater than V+\sigma_i . Larger values mean that + * we had a wraparound so we consider the timestamp to be stale. + * + * If F is not stale and F >= V then we set S = F. + * Otherwise we should assign S = V, but this may violate + * the ordering in ER. So, if we have groups in ER, set S to + * the F_j of the first group j which would be blocking us. + * We are guaranteed not to move S backward because + * otherwise our group i would still be blocked. + */ +static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl) +{ + unsigned long mask; + uint32_t limit, roundedF; + int slot_shift = cl->grp->slot_shift; + + roundedF = qfq_round_down(cl->F, slot_shift); + limit = qfq_round_down(q->V, slot_shift) + (1UL << slot_shift); + + if (!qfq_gt(cl->F, q->V) || qfq_gt(roundedF, limit)) { + /* timestamp was stale */ + mask = mask_from(q->bitmaps[ER], cl->grp->index); + if (mask) { + struct qfq_group *next = qfq_ffs(q, mask); + if (qfq_gt(roundedF, next->F)) { + cl->S = next->F; + return; + } + } + cl->S = q->V; + } else /* timestamp is not stale */ + cl->S = cl->F; +} + +static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_group *grp; + struct qfq_class *cl; + int err; + u64 roundedS; + int s; + + cl = qfq_classify(skb, sch, &err); + if (cl == NULL) { + if (err & __NET_XMIT_BYPASS) + sch->qstats.drops++; + kfree_skb(skb); + return err; + } + pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid); + + err = qdisc_enqueue(skb, cl->qdisc); + if (unlikely(err != NET_XMIT_SUCCESS)) { + pr_debug("qfq_enqueue: enqueue failed %d\n", err); + if (net_xmit_drop_count(err)) { + cl->qstats.drops++; + sch->qstats.drops++; + } + return err; + } + + bstats_update(&cl->bstats, skb); + ++sch->q.qlen; + + /* If the new skb is not the head of queue, then done here. */ + if (cl->qdisc->q.qlen != 1) + return err; + + /* If reach this point, queue q was idle */ + grp = cl->grp; + qfq_update_start(q, cl); + + /* compute new finish time and rounded start. */ + cl->F = cl->S + (u64)qdisc_pkt_len(skb) * cl->inv_w; + roundedS = qfq_round_down(cl->S, grp->slot_shift); + + /* + * insert cl in the correct bucket. + * If cl->S >= grp->S we don't need to adjust the + * bucket list and simply go to the insertion phase. + * Otherwise grp->S is decreasing, we must make room + * in the bucket list, and also recompute the group state. + * Finally, if there were no flows in this group and nobody + * was in ER make sure to adjust V. + */ + if (grp->full_slots) { + if (!qfq_gt(grp->S, cl->S)) + goto skip_update; + + /* create a slot for this cl->S */ + qfq_slot_rotate(grp, roundedS); + /* group was surely ineligible, remove */ + __clear_bit(grp->index, &q->bitmaps[IR]); + __clear_bit(grp->index, &q->bitmaps[IB]); + } else if (!q->bitmaps[ER] && qfq_gt(roundedS, q->V)) + q->V = roundedS; + + grp->S = roundedS; + grp->F = roundedS + (2ULL << grp->slot_shift); + s = qfq_calc_state(q, grp); + __set_bit(grp->index, &q->bitmaps[s]); + + pr_debug("qfq enqueue: new state %d %#lx S %lld F %lld V %lld\n", + s, q->bitmaps[s], + (unsigned long long) cl->S, + (unsigned long long) cl->F, + (unsigned long long) q->V); + +skip_update: + qfq_slot_insert(grp, cl, roundedS); + + return err; +} + + +static void qfq_slot_remove(struct qfq_sched *q, struct qfq_group *grp, + struct qfq_class *cl) +{ + unsigned int i, offset; + u64 roundedS; + + roundedS = qfq_round_down(cl->S, grp->slot_shift); + offset = (roundedS - grp->S) >> grp->slot_shift; + i = (grp->front + offset) % QFQ_MAX_SLOTS; + + hlist_del(&cl->next); + if (hlist_empty(&grp->slots[i])) + __clear_bit(offset, &grp->full_slots); +} + +/* + * called to forcibly destroy a queue. + * If the queue is not in the front bucket, or if it has + * other queues in the front bucket, we can simply remove + * the queue with no other side effects. + * Otherwise we must propagate the event up. + */ +static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) +{ + struct qfq_group *grp = cl->grp; + unsigned long mask; + u64 roundedS; + int s; + + cl->F = cl->S; + qfq_slot_remove(q, grp, cl); + + if (!grp->full_slots) { + __clear_bit(grp->index, &q->bitmaps[IR]); + __clear_bit(grp->index, &q->bitmaps[EB]); + __clear_bit(grp->index, &q->bitmaps[IB]); + + if (test_bit(grp->index, &q->bitmaps[ER]) && + !(q->bitmaps[ER] & ~((1UL << grp->index) - 1))) { + mask = q->bitmaps[ER] & ((1UL << grp->index) - 1); + if (mask) + mask = ~((1UL << __fls(mask)) - 1); + else + mask = ~0UL; + qfq_move_groups(q, mask, EB, ER); + qfq_move_groups(q, mask, IB, IR); + } + __clear_bit(grp->index, &q->bitmaps[ER]); + } else if (hlist_empty(&grp->slots[grp->front])) { + cl = qfq_slot_scan(grp); + roundedS = qfq_round_down(cl->S, grp->slot_shift); + if (grp->S != roundedS) { + __clear_bit(grp->index, &q->bitmaps[ER]); + __clear_bit(grp->index, &q->bitmaps[IR]); + __clear_bit(grp->index, &q->bitmaps[EB]); + __clear_bit(grp->index, &q->bitmaps[IB]); + grp->S = roundedS; + grp->F = roundedS + (2ULL << grp->slot_shift); + s = qfq_calc_state(q, grp); + __set_bit(grp->index, &q->bitmaps[s]); + } + } + + qfq_update_eligible(q, q->V); +} + +static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_class *cl = (struct qfq_class *)arg; + + if (cl->qdisc->q.qlen == 0) + qfq_deactivate_class(q, cl); +} + +static unsigned int qfq_drop(struct Qdisc *sch) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_group *grp; + unsigned int i, j, len; + + for (i = 0; i <= QFQ_MAX_INDEX; i++) { + grp = &q->groups[i]; + for (j = 0; j < QFQ_MAX_SLOTS; j++) { + struct qfq_class *cl; + struct hlist_node *n; + + hlist_for_each_entry(cl, n, &grp->slots[j], next) { + + if (!cl->qdisc->ops->drop) + continue; + + len = cl->qdisc->ops->drop(cl->qdisc); + if (len > 0) { + sch->q.qlen--; + if (!cl->qdisc->q.qlen) + qfq_deactivate_class(q, cl); + + return len; + } + } + } + } + + return 0; +} + +static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_group *grp; + int i, j, err; + + err = qdisc_class_hash_init(&q->clhash); + if (err < 0) + return err; + + for (i = 0; i <= QFQ_MAX_INDEX; i++) { + grp = &q->groups[i]; + grp->index = i; + grp->slot_shift = QFQ_MTU_SHIFT + FRAC_BITS + - (QFQ_MAX_INDEX - i); + for (j = 0; j < QFQ_MAX_SLOTS; j++) + INIT_HLIST_HEAD(&grp->slots[j]); + } + + return 0; +} + +static void qfq_reset_qdisc(struct Qdisc *sch) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_group *grp; + struct qfq_class *cl; + struct hlist_node *n, *tmp; + unsigned int i, j; + + for (i = 0; i <= QFQ_MAX_INDEX; i++) { + grp = &q->groups[i]; + for (j = 0; j < QFQ_MAX_SLOTS; j++) { + hlist_for_each_entry_safe(cl, n, tmp, + &grp->slots[j], next) { + qfq_deactivate_class(q, cl); + } + } + } + + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) + qdisc_reset(cl->qdisc); + } + sch->q.qlen = 0; +} + +static void qfq_destroy_qdisc(struct Qdisc *sch) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_class *cl; + struct hlist_node *n, *next; + unsigned int i; + + tcf_destroy_chain(&q->filter_list); + + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + common.hnode) { + qfq_destroy_class(sch, cl); + } + } + qdisc_class_hash_destroy(&q->clhash); +} + +static const struct Qdisc_class_ops qfq_class_ops = { + .change = qfq_change_class, + .delete = qfq_delete_class, + .get = qfq_get_class, + .put = qfq_put_class, + .tcf_chain = qfq_tcf_chain, + .bind_tcf = qfq_bind_tcf, + .unbind_tcf = qfq_unbind_tcf, + .graft = qfq_graft_class, + .leaf = qfq_class_leaf, + .qlen_notify = qfq_qlen_notify, + .dump = qfq_dump_class, + .dump_stats = qfq_dump_class_stats, + .walk = qfq_walk, +}; + +static struct Qdisc_ops qfq_qdisc_ops __read_mostly = { + .cl_ops = &qfq_class_ops, + .id = "qfq", + .priv_size = sizeof(struct qfq_sched), + .enqueue = qfq_enqueue, + .dequeue = qfq_dequeue, + .peek = qdisc_peek_dequeued, + .drop = qfq_drop, + .init = qfq_init_qdisc, + .reset = qfq_reset_qdisc, + .destroy = qfq_destroy_qdisc, + .owner = THIS_MODULE, +}; + +static int __init qfq_init(void) +{ + return register_qdisc(&qfq_qdisc_ops); +} + +static void __exit qfq_exit(void) +{ + unregister_qdisc(&qfq_qdisc_ops); +} + +module_init(qfq_init); +module_exit(qfq_exit); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index c2e628dfaacc..b6ea6afa55b0 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -169,7 +169,7 @@ static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) } case htons(ETH_P_IPV6): { - struct ipv6hdr *iph; + const struct ipv6hdr *iph; int poff; if (!pskb_network_may_pull(skb, sizeof(*iph))) @@ -361,7 +361,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct sfq_sched_data *q = qdisc_priv(sch); unsigned int hash; - sfq_index x; + sfq_index x, qlen; struct sfq_slot *slot; int uninitialized_var(ret); @@ -405,20 +405,12 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (++sch->q.qlen <= q->limit) return NET_XMIT_SUCCESS; + qlen = slot->qlen; sfq_drop(sch); - return NET_XMIT_CN; -} - -static struct sk_buff * -sfq_peek(struct Qdisc *sch) -{ - struct sfq_sched_data *q = qdisc_priv(sch); - - /* No active slots */ - if (q->tail == NULL) - return NULL; - - return q->slots[q->tail->next].skblist_next; + /* Return Congestion Notification only if we dropped a packet + * from this flow. + */ + return (qlen != slot->qlen) ? NET_XMIT_CN : NET_XMIT_SUCCESS; } static struct sk_buff * @@ -702,7 +694,7 @@ static struct Qdisc_ops sfq_qdisc_ops __read_mostly = { .priv_size = sizeof(struct sfq_sched_data), .enqueue = sfq_enqueue, .dequeue = sfq_dequeue, - .peek = sfq_peek, + .peek = qdisc_peek_dequeued, .drop = sfq_drop, .init = sfq_init, .reset = sfq_reset, diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 6b04287913cd..525f97c467e9 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -64,6 +64,7 @@ /* Forward declarations for internal functions. */ static void sctp_assoc_bh_rcv(struct work_struct *work); static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc); +static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc); /* Keep track of the new idr low so that we don't re-use association id * numbers too fast. It is protected by they idr spin lock is in the @@ -446,6 +447,9 @@ void sctp_association_free(struct sctp_association *asoc) /* Free any cached ASCONF_ACK chunk. */ sctp_assoc_free_asconf_acks(asoc); + /* Free the ASCONF queue. */ + sctp_assoc_free_asconf_queue(asoc); + /* Free any cached ASCONF chunk. */ if (asoc->addip_last_asconf) sctp_chunk_free(asoc->addip_last_asconf); @@ -569,6 +573,8 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, sctp_assoc_set_primary(asoc, transport); if (asoc->peer.active_path == peer) asoc->peer.active_path = transport; + if (asoc->peer.retran_path == peer) + asoc->peer.retran_path = transport; if (asoc->peer.last_data_from == peer) asoc->peer.last_data_from = transport; @@ -1323,6 +1329,8 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) if (t) asoc->peer.retran_path = t; + else + t = asoc->peer.retran_path; SCTP_DEBUG_PRINTK_IPADDR("sctp_assoc_update_retran_path:association" " %p addr: ", @@ -1574,6 +1582,18 @@ retry: return error; } +/* Free the ASCONF queue */ +static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc) +{ + struct sctp_chunk *asconf; + struct sctp_chunk *tmp; + + list_for_each_entry_safe(asconf, tmp, &asoc->addip_chunk_list, list) { + list_del_init(&asconf->list); + sctp_chunk_free(asconf); + } +} + /* Free asconf_ack cache */ static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc) { @@ -1593,7 +1613,7 @@ void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc) struct sctp_chunk *ack; struct sctp_chunk *tmp; - /* We can remove all the entries from the queue upto + /* We can remove all the entries from the queue up to * the "Peer-Sequence-Number". */ list_for_each_entry_safe(ack, tmp, &asoc->asconf_ack_list, diff --git a/net/sctp/auth.c b/net/sctp/auth.c index ddbbf7c81fa1..865e68fef21c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -113,7 +113,7 @@ struct sctp_shared_key *sctp_auth_shkey_create(__u16 key_id, gfp_t gfp) return new; } -/* Free the shared key stucture */ +/* Free the shared key structure */ static void sctp_auth_shkey_free(struct sctp_shared_key *sh_key) { BUG_ON(!list_empty(&sh_key->key_list)); @@ -122,7 +122,7 @@ static void sctp_auth_shkey_free(struct sctp_shared_key *sh_key) kfree(sh_key); } -/* Destory the entire key list. This is done during the +/* Destroy the entire key list. This is done during the * associon and endpoint free process. */ void sctp_auth_destroy_keys(struct list_head *keys) @@ -324,7 +324,7 @@ static struct sctp_auth_bytes *sctp_auth_asoc_create_secret( if (!peer_key_vector || !local_key_vector) goto out; - /* Figure out the order in wich the key_vectors will be + /* Figure out the order in which the key_vectors will be * added to the endpoint shared key. * SCTP-AUTH, Section 6.1: * This is performed by selecting the numerically smaller key diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index faf71d179e46..83e3011c19ca 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -140,14 +140,12 @@ void sctp_bind_addr_init(struct sctp_bind_addr *bp, __u16 port) /* Dispose of the address list. */ static void sctp_bind_addr_clean(struct sctp_bind_addr *bp) { - struct sctp_sockaddr_entry *addr; - struct list_head *pos, *temp; + struct sctp_sockaddr_entry *addr, *temp; /* Empty the bind address list. */ - list_for_each_safe(pos, temp, &bp->address_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); - list_del(pos); - kfree(addr); + list_for_each_entry_safe(addr, temp, &bp->address_list, list) { + list_del_rcu(&addr->list); + kfree_rcu(addr, rcu); SCTP_DBG_OBJCNT_DEC(addr); } } @@ -219,7 +217,7 @@ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) } if (found) { - call_rcu(&addr->rcu, sctp_local_addr_free); + kfree_rcu(addr, rcu); SCTP_DBG_OBJCNT_DEC(addr); return 0; } diff --git a/net/sctp/debug.c b/net/sctp/debug.c index bf24fa697de2..ec997cfe0a7e 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -98,7 +98,6 @@ const char *sctp_cname(const sctp_subtype_t cid) /* These are printable forms of the states. */ const char *const sctp_state_tbl[SCTP_STATE_NUM_STATES] = { - "STATE_EMPTY", "STATE_CLOSED", "STATE_COOKIE_WAIT", "STATE_COOKIE_ECHOED", diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index e10acc01c75f..c8cc24e282c3 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -325,6 +325,7 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( struct sctp_transport **transport) { struct sctp_association *asoc = NULL; + struct sctp_association *tmp; struct sctp_transport *t = NULL; struct sctp_hashbucket *head; struct sctp_ep_common *epb; @@ -333,25 +334,32 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( int rport; *transport = NULL; + + /* If the local port is not set, there can't be any associations + * on this endpoint. + */ + if (!ep->base.bind_addr.port) + goto out; + rport = ntohs(paddr->v4.sin_port); hash = sctp_assoc_hashfn(ep->base.bind_addr.port, rport); head = &sctp_assoc_hashtable[hash]; read_lock(&head->lock); sctp_for_each_hentry(epb, node, &head->chain) { - asoc = sctp_assoc(epb); - if (asoc->ep != ep || rport != asoc->peer.port) - goto next; + tmp = sctp_assoc(epb); + if (tmp->ep != ep || rport != tmp->peer.port) + continue; - t = sctp_assoc_lookup_paddr(asoc, paddr); + t = sctp_assoc_lookup_paddr(tmp, paddr); if (t) { + asoc = tmp; *transport = t; break; } -next: - asoc = NULL; } read_unlock(&head->lock); +out: return asoc; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 826661be73e7..741ed1648838 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -565,7 +565,7 @@ void sctp_err_finish(struct sock *sk, struct sctp_association *asoc) */ void sctp_v4_err(struct sk_buff *skb, __u32 info) { - struct iphdr *iph = (struct iphdr *)skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; const int ihlen = iph->ihl * 4; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; @@ -661,7 +661,6 @@ static int sctp_rcv_ootb(struct sk_buff *skb) { sctp_chunkhdr_t *ch; __u8 *ch_end; - sctp_errhdr_t *err; ch = (sctp_chunkhdr_t *) skb->data; @@ -697,20 +696,6 @@ static int sctp_rcv_ootb(struct sk_buff *skb) if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data) goto discard; - /* RFC 8.4, 7) If the packet contains a "Stale cookie" ERROR - * or a COOKIE ACK the SCTP Packet should be silently - * discarded. - */ - if (SCTP_CID_COOKIE_ACK == ch->type) - goto discard; - - if (SCTP_CID_ERROR == ch->type) { - sctp_walk_errors(err, ch) { - if (SCTP_ERROR_STALE_COOKIE == err->cause) - goto discard; - } - } - ch = (sctp_chunkhdr_t *) ch_end; } while (ch_end < skb_tail_pointer(skb)); @@ -1017,7 +1002,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( /* Skip over the ADDIP header and find the Address parameter */ param = (union sctp_addr_param *)(asconf + 1); - af = sctp_get_af_specific(param_type2af(param->v4.param_hdr.type)); + af = sctp_get_af_specific(param_type2af(param->p.type)); if (unlikely(!af)) return NULL; @@ -1034,7 +1019,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( * association. * * This means that any chunks that can help us identify the association need -* to be looked at to find this assocation. +* to be looked at to find this association. */ static struct sctp_association *__sctp_rcv_walk_lookup(struct sk_buff *skb, const union sctp_addr *laddr, diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 865ce7ba4e14..0bb0d7cb9f10 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -80,6 +80,13 @@ #include <asm/uaccess.h> +static inline int sctp_v6_addr_match_len(union sctp_addr *s1, + union sctp_addr *s2); +static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, + __be16 port); +static int sctp_v6_cmp_addr(const union sctp_addr *addr1, + const union sctp_addr *addr2); + /* Event handler for inet6 address addition/deletion events. * The sctp_local_addr_list needs to be protocted by a spin lock since * multiple notifiers (say IPv4 and IPv6) may be running at the same @@ -123,7 +130,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, } spin_unlock_bh(&sctp_local_addr_lock); if (found) - call_rcu(&addr->rcu, sctp_local_addr_free); + kfree_rcu(addr, rcu); break; } @@ -240,37 +247,107 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) /* Returns the dst cache entry for the given source and destination ip * addresses. */ -static struct dst_entry *sctp_v6_get_dst(struct sctp_association *asoc, - union sctp_addr *daddr, - union sctp_addr *saddr) +static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, + struct flowi *fl, struct sock *sk) { - struct dst_entry *dst; - struct flowi6 fl6; + struct sctp_association *asoc = t->asoc; + struct dst_entry *dst = NULL; + struct flowi6 *fl6 = &fl->u.ip6; + struct sctp_bind_addr *bp; + struct sctp_sockaddr_entry *laddr; + union sctp_addr *baddr = NULL; + union sctp_addr *daddr = &t->ipaddr; + union sctp_addr dst_saddr; + __u8 matchlen = 0; + __u8 bmatchlen; + sctp_scope_t scope; - memset(&fl6, 0, sizeof(fl6)); - ipv6_addr_copy(&fl6.daddr, &daddr->v6.sin6_addr); + memset(fl6, 0, sizeof(struct flowi6)); + ipv6_addr_copy(&fl6->daddr, &daddr->v6.sin6_addr); + fl6->fl6_dport = daddr->v6.sin6_port; + fl6->flowi6_proto = IPPROTO_SCTP; if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) - fl6.flowi6_oif = daddr->v6.sin6_scope_id; + fl6->flowi6_oif = daddr->v6.sin6_scope_id; + SCTP_DEBUG_PRINTK("%s: DST=%pI6 ", __func__, &fl6->daddr); - SCTP_DEBUG_PRINTK("%s: DST=%pI6 ", __func__, &fl6.daddr); + if (asoc) + fl6->fl6_sport = htons(asoc->base.bind_addr.port); if (saddr) { - ipv6_addr_copy(&fl6.saddr, &saddr->v6.sin6_addr); - SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6.saddr); + ipv6_addr_copy(&fl6->saddr, &saddr->v6.sin6_addr); + fl6->fl6_sport = saddr->v6.sin6_port; + SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6->saddr); + } + + dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); + if (!asoc || saddr) + goto out; + + bp = &asoc->base.bind_addr; + scope = sctp_scope(daddr); + /* ip6_dst_lookup has filled in the fl6->saddr for us. Check + * to see if we can use it. + */ + if (!IS_ERR(dst)) { + /* Walk through the bind address list and look for a bind + * address that matches the source address of the returned dst. + */ + sctp_v6_to_addr(&dst_saddr, &fl6->saddr, htons(bp->port)); + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { + if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC)) + continue; + + /* Do not compare against v4 addrs */ + if ((laddr->a.sa.sa_family == AF_INET6) && + (sctp_v6_cmp_addr(&dst_saddr, &laddr->a))) { + rcu_read_unlock(); + goto out; + } + } + rcu_read_unlock(); + /* None of the bound addresses match the source address of the + * dst. So release it. + */ + dst_release(dst); + dst = NULL; } - dst = ip6_route_output(&init_net, NULL, &fl6); - if (!dst->error) { + /* Walk through the bind address list and try to get the + * best source address for a given destination. + */ + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { + if (!laddr->valid && laddr->state != SCTP_ADDR_SRC) + continue; + if ((laddr->a.sa.sa_family == AF_INET6) && + (scope <= sctp_scope(&laddr->a))) { + bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); + if (!baddr || (matchlen < bmatchlen)) { + baddr = &laddr->a; + matchlen = bmatchlen; + } + } + } + rcu_read_unlock(); + if (baddr) { + ipv6_addr_copy(&fl6->saddr, &baddr->v6.sin6_addr); + fl6->fl6_sport = baddr->v6.sin6_port; + dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); + } + +out: + if (!IS_ERR(dst)) { struct rt6_info *rt; rt = (struct rt6_info *)dst; + t->dst = dst; SCTP_DEBUG_PRINTK("rt6_dst:%pI6 rt6_src:%pI6\n", - &rt->rt6i_dst.addr, &rt->rt6i_src.addr); - return dst; + &rt->rt6i_dst.addr, &fl6->saddr); + } else { + t->dst = NULL; + SCTP_DEBUG_PRINTK("NO ROUTE\n"); } - SCTP_DEBUG_PRINTK("NO ROUTE\n"); - dst_release(dst); - return NULL; } /* Returns the number of consecutive initial bits that match in the 2 ipv6 @@ -286,64 +363,18 @@ static inline int sctp_v6_addr_match_len(union sctp_addr *s1, * and asoc's bind address list. */ static void sctp_v6_get_saddr(struct sctp_sock *sk, - struct sctp_association *asoc, - struct dst_entry *dst, - union sctp_addr *daddr, - union sctp_addr *saddr) + struct sctp_transport *t, + struct flowi *fl) { - struct sctp_bind_addr *bp; - struct sctp_sockaddr_entry *laddr; - sctp_scope_t scope; - union sctp_addr *baddr = NULL; - __u8 matchlen = 0; - __u8 bmatchlen; + struct flowi6 *fl6 = &fl->u.ip6; + union sctp_addr *saddr = &t->saddr; - SCTP_DEBUG_PRINTK("%s: asoc:%p dst:%p daddr:%pI6 ", - __func__, asoc, dst, &daddr->v6.sin6_addr); - - if (!asoc) { - ipv6_dev_get_saddr(sock_net(sctp_opt2sk(sk)), - dst ? ip6_dst_idev(dst)->dev : NULL, - &daddr->v6.sin6_addr, - inet6_sk(&sk->inet.sk)->srcprefs, - &saddr->v6.sin6_addr); - SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: %pI6\n", - &saddr->v6.sin6_addr); - return; - } - - scope = sctp_scope(daddr); - - bp = &asoc->base.bind_addr; + SCTP_DEBUG_PRINTK("%s: asoc:%p dst:%p\n", __func__, t->asoc, t->dst); - /* Go through the bind address list and find the best source address - * that matches the scope of the destination address. - */ - rcu_read_lock(); - list_for_each_entry_rcu(laddr, &bp->address_list, list) { - if (!laddr->valid) - continue; - if ((laddr->state == SCTP_ADDR_SRC) && - (laddr->a.sa.sa_family == AF_INET6) && - (scope <= sctp_scope(&laddr->a))) { - bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); - if (!baddr || (matchlen < bmatchlen)) { - baddr = &laddr->a; - matchlen = bmatchlen; - } - } - } - - if (baddr) { - memcpy(saddr, baddr, sizeof(union sctp_addr)); - SCTP_DEBUG_PRINTK("saddr: %pI6\n", &saddr->v6.sin6_addr); - } else { - pr_err("%s: asoc:%p Could not find a valid source " - "address for the dest:%pI6\n", - __func__, asoc, &daddr->v6.sin6_addr); + if (t->dst) { + saddr->v6.sin6_family = AF_INET6; + ipv6_addr_copy(&saddr->v6.sin6_addr, &fl6->saddr); } - - rcu_read_unlock(); } /* Make a copy of all potential local addresses. */ @@ -465,14 +496,13 @@ static int sctp_v6_to_addr_param(const union sctp_addr *addr, return length; } -/* Initialize a sctp_addr from a dst_entry. */ -static void sctp_v6_dst_saddr(union sctp_addr *addr, struct dst_entry *dst, +/* Initialize a sctp_addr from struct in6_addr. */ +static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, __be16 port) { - struct rt6_info *rt = (struct rt6_info *)dst; addr->sa.sa_family = AF_INET6; addr->v6.sin6_port = port; - ipv6_addr_copy(&addr->v6.sin6_addr, &rt->rt6i_src.addr); + ipv6_addr_copy(&addr->v6.sin6_addr, saddr); } /* Compare addresses exactly. @@ -531,7 +561,7 @@ static int sctp_v6_is_any(const union sctp_addr *addr) static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) { int type; - struct in6_addr *in6 = (struct in6_addr *)&addr->v6.sin6_addr; + const struct in6_addr *in6 = (const struct in6_addr *)&addr->v6.sin6_addr; type = ipv6_addr_type(in6); if (IPV6_ADDR_ANY == type) @@ -959,7 +989,6 @@ static struct sctp_af sctp_af_inet6 = { .to_sk_daddr = sctp_v6_to_sk_daddr, .from_addr_param = sctp_v6_from_addr_param, .to_addr_param = sctp_v6_to_addr_param, - .dst_saddr = sctp_v6_dst_saddr, .cmp_addr = sctp_v6_cmp_addr, .scope = sctp_v6_scope, .addr_valid = sctp_v6_addr_valid, diff --git a/net/sctp/output.c b/net/sctp/output.c index 60600d337a3a..b4f3cf06d8da 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -510,7 +510,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) sh->checksum = sctp_end_cksum(crc32); } else { if (dst->dev->features & NETIF_F_SCTP_CSUM) { - /* no need to seed psuedo checksum for SCTP */ + /* no need to seed pseudo checksum for SCTP */ nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (skb_transport_header(nskb) - nskb->head); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 26dc005113a0..1c88c8911dc5 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -131,7 +131,8 @@ static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary, static inline int sctp_cacc_skip_3_1_f(struct sctp_transport *transport, int count_of_newacks) { - if (count_of_newacks < 2 && !transport->cacc.cacc_saw_newack) + if (count_of_newacks < 2 && + (transport && !transport->cacc.cacc_saw_newack)) return 1; return 0; } @@ -177,13 +178,13 @@ static inline int sctp_cacc_skip_3_2(struct sctp_transport *primary, __u32 tsn) * 3) If the missing report count for TSN t is to be * incremented according to [RFC2960] and * [SCTP_STEWART-2002], and CHANGEOVER_ACTIVE is set, - * then the sender MUST futher execute steps 3.1 and + * then the sender MUST further execute steps 3.1 and * 3.2 to determine if the missing report count for * TSN t SHOULD NOT be incremented. * * 3.3) If 3.1 and 3.2 do not dictate that the missing * report count for t should not be incremented, then - * the sender SOULD increment missing report count for + * the sender SHOULD increment missing report count for * t (according to [RFC2960] and [SCTP_STEWART_2002]). */ static inline int sctp_cacc_skip(struct sctp_transport *primary, @@ -319,7 +320,6 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk) * chunk. */ switch (q->asoc->state) { - case SCTP_STATE_EMPTY: case SCTP_STATE_CLOSED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_SENT: @@ -577,6 +577,13 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, * try to send as much as possible. */ list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) { + /* If the chunk is abandoned, move it to abandoned list. */ + if (sctp_chunk_abandoned(chunk)) { + list_del_init(&chunk->transmitted_list); + sctp_insert_list(&q->abandoned, + &chunk->transmitted_list); + continue; + } /* Make sure that Gap Acked TSNs are not retransmitted. A * simple approach is just to move such TSNs out of the @@ -618,9 +625,12 @@ redo: /* If we are retransmitting, we should only * send a single packet. + * Otherwise, try appending this chunk again. */ if (rtx_timeout || fast_rtx) done = 1; + else + goto redo; /* Bundle next chunk in the next round. */ break; @@ -843,7 +853,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) case SCTP_CID_ECN_CWR: case SCTP_CID_ASCONF_ACK: one_packet = 1; - /* Fall throught */ + /* Fall through */ case SCTP_CID_SACK: case SCTP_CID_HEARTBEAT: @@ -1683,8 +1693,9 @@ static void sctp_mark_missing(struct sctp_outq *q, /* SFR-CACC may require us to skip marking * this chunk as missing. */ - if (!transport || !sctp_cacc_skip(primary, transport, - count_of_newacks, tsn)) { + if (!transport || !sctp_cacc_skip(primary, + chunk->transport, + count_of_newacks, tsn)) { chunk->tsn_missing_report++; SCTP_DEBUG_PRINTK( diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 61aacfbbaa92..05a6ce214714 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -212,7 +212,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) sctp_for_each_hentry(epb, node, &head->chain) { ep = sctp_ep(epb); sk = epb->sk; - seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, + seq_printf(seq, "%8pK %8pK %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, sctp_sk(sk)->type, sk->sk_state, hash, epb->bind_addr.port, sock_i_uid(sk), sock_i_ino(sk)); @@ -316,7 +316,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) assoc = sctp_assoc(epb); sk = epb->sk; seq_printf(seq, - "%8p %8p %-3d %-3d %-2d %-4d " + "%8pK %8pK %-3d %-3d %-2d %-4d " "%4d %8d %8d %7d %5lu %-5d %5d ", assoc, sk, sctp_sk(sk)->type, sk->sk_state, assoc->state, hash, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d5bf91d04f63..67380a29e2e9 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -230,13 +230,6 @@ static void sctp_free_local_addr_list(void) } } -void sctp_local_addr_free(struct rcu_head *head) -{ - struct sctp_sockaddr_entry *e = container_of(head, - struct sctp_sockaddr_entry, rcu); - kfree(e); -} - /* Copy the local addresses which are valid for 'scope' into 'bp'. */ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope, gfp_t gfp, int copy_flags) @@ -339,13 +332,12 @@ static int sctp_v4_to_addr_param(const union sctp_addr *addr, } /* Initialize a sctp_addr from a dst_entry. */ -static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct dst_entry *dst, +static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, __be16 port) { - struct rtable *rt = (struct rtable *)dst; saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; - saddr->v4.sin_addr.s_addr = rt->rt_src; + saddr->v4.sin_addr.s_addr = fl4->saddr; } /* Compare two addresses exactly. */ @@ -463,35 +455,36 @@ static sctp_scope_t sctp_v4_scope(union sctp_addr *addr) * addresses. If an association is passed, trys to get a dst entry with a * source address that matches an address in the bind address list. */ -static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, - union sctp_addr *daddr, - union sctp_addr *saddr) +static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, + struct flowi *fl, struct sock *sk) { + struct sctp_association *asoc = t->asoc; struct rtable *rt; - struct flowi4 fl4; + struct flowi4 *fl4 = &fl->u.ip4; struct sctp_bind_addr *bp; struct sctp_sockaddr_entry *laddr; struct dst_entry *dst = NULL; + union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; - memset(&fl4, 0x0, sizeof(struct flowi4)); - fl4.daddr = daddr->v4.sin_addr.s_addr; - fl4.fl4_dport = daddr->v4.sin_port; - fl4.flowi4_proto = IPPROTO_SCTP; + memset(fl4, 0x0, sizeof(struct flowi4)); + fl4->daddr = daddr->v4.sin_addr.s_addr; + fl4->fl4_dport = daddr->v4.sin_port; + fl4->flowi4_proto = IPPROTO_SCTP; if (asoc) { - fl4.flowi4_tos = RT_CONN_FLAGS(asoc->base.sk); - fl4.flowi4_oif = asoc->base.sk->sk_bound_dev_if; - fl4.fl4_sport = htons(asoc->base.bind_addr.port); + fl4->flowi4_tos = RT_CONN_FLAGS(asoc->base.sk); + fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if; + fl4->fl4_sport = htons(asoc->base.bind_addr.port); } if (saddr) { - fl4.saddr = saddr->v4.sin_addr.s_addr; - fl4.fl4_sport = saddr->v4.sin_port; + fl4->saddr = saddr->v4.sin_addr.s_addr; + fl4->fl4_sport = saddr->v4.sin_port; } SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ", - __func__, &fl4.daddr, &fl4.saddr); + __func__, &fl4->daddr, &fl4->saddr); - rt = ip_route_output_key(&init_net, &fl4); + rt = ip_route_output_key(&init_net, fl4); if (!IS_ERR(rt)) dst = &rt->dst; @@ -507,7 +500,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, /* Walk through the bind address list and look for a bind * address that matches the source address of the returned dst. */ - sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port)); + sctp_v4_dst_saddr(&dst_saddr, fl4, htons(bp->port)); rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC)) @@ -533,9 +526,9 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, continue; if ((laddr->state == SCTP_ADDR_SRC) && (AF_INET == laddr->a.sa.sa_family)) { - fl4.saddr = laddr->a.v4.sin_addr.s_addr; - fl4.fl4_sport = laddr->a.v4.sin_port; - rt = ip_route_output_key(&init_net, &fl4); + fl4->saddr = laddr->a.v4.sin_addr.s_addr; + fl4->fl4_sport = laddr->a.v4.sin_port; + rt = ip_route_output_key(&init_net, fl4); if (!IS_ERR(rt)) { dst = &rt->dst; goto out_unlock; @@ -546,33 +539,27 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, out_unlock: rcu_read_unlock(); out: + t->dst = dst; if (dst) SCTP_DEBUG_PRINTK("rt_dst:%pI4, rt_src:%pI4\n", - &rt->rt_dst, &rt->rt_src); + &fl4->daddr, &fl4->saddr); else SCTP_DEBUG_PRINTK("NO ROUTE\n"); - - return dst; } /* For v4, the source address is cached in the route entry(dst). So no need * to cache it separately and hence this is an empty routine. */ static void sctp_v4_get_saddr(struct sctp_sock *sk, - struct sctp_association *asoc, - struct dst_entry *dst, - union sctp_addr *daddr, - union sctp_addr *saddr) + struct sctp_transport *t, + struct flowi *fl) { - struct rtable *rt = (struct rtable *)dst; - - if (!asoc) - return; + union sctp_addr *saddr = &t->saddr; + struct rtable *rt = (struct rtable *)t->dst; if (rt) { saddr->v4.sin_family = AF_INET; - saddr->v4.sin_port = htons(asoc->base.bind_addr.port); - saddr->v4.sin_addr.s_addr = rt->rt_src; + saddr->v4.sin_addr.s_addr = fl->u.ip4.saddr; } } @@ -681,7 +668,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, } spin_unlock_bh(&sctp_local_addr_lock); if (found) - call_rcu(&addr->rcu, sctp_local_addr_free); + kfree_rcu(addr, rcu); break; } @@ -854,14 +841,14 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, skb->len, - &skb_rtable(skb)->rt_src, - &skb_rtable(skb)->rt_dst); + &transport->fl.u.ip4.saddr, + &transport->fl.u.ip4.daddr); inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO : IP_PMTUDISC_DONT; SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS); - return ip_queue_xmit(skb); + return ip_queue_xmit(skb, &transport->fl); } static struct sctp_af sctp_af_inet; @@ -950,7 +937,6 @@ static struct sctp_af sctp_af_inet = { .to_sk_daddr = sctp_v4_to_sk_daddr, .from_addr_param = sctp_v4_from_addr_param, .to_addr_param = sctp_v4_to_addr_param, - .dst_saddr = sctp_v4_dst_saddr, .cmp_addr = sctp_v4_cmp_addr, .addr_valid = sctp_v4_addr_valid, .inaddr_any = sctp_v4_inaddr_any, diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index b3434cc7d0cf..58eb27fed4b4 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1075,20 +1075,28 @@ nodata: /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, - const struct sctp_transport *transport, - const void *payload, const size_t paylen) + const struct sctp_transport *transport) { - struct sctp_chunk *retval = sctp_make_chunk(asoc, SCTP_CID_HEARTBEAT, - 0, paylen); + struct sctp_chunk *retval; + sctp_sender_hb_info_t hbinfo; + + retval = sctp_make_chunk(asoc, SCTP_CID_HEARTBEAT, 0, sizeof(hbinfo)); if (!retval) goto nodata; + hbinfo.param_hdr.type = SCTP_PARAM_HEARTBEAT_INFO; + hbinfo.param_hdr.length = htons(sizeof(sctp_sender_hb_info_t)); + hbinfo.daddr = transport->ipaddr; + hbinfo.sent_at = jiffies; + hbinfo.hb_nonce = transport->hb_nonce; + /* Cast away the 'const', as this is just telling the chunk * what transport it belongs to. */ retval->transport = (struct sctp_transport *) transport; - retval->subh.hbs_hdr = sctp_addto_chunk(retval, paylen, payload); + retval->subh.hbs_hdr = sctp_addto_chunk(retval, sizeof(hbinfo), + &hbinfo); nodata: return retval; @@ -2242,14 +2250,17 @@ int sctp_verify_init(const struct sctp_association *asoc, * Returns 0 on failure, else success. * FIXME: This is an association method. */ -int sctp_process_init(struct sctp_association *asoc, sctp_cid_t cid, +int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, const union sctp_addr *peer_addr, sctp_init_chunk_t *peer_init, gfp_t gfp) { union sctp_params param; struct sctp_transport *transport; struct list_head *pos, *temp; + struct sctp_af *af; + union sctp_addr addr; char *cookie; + int src_match = 0; /* We must include the address that the INIT packet came from. * This is the only address that matters for an INIT packet. @@ -2261,18 +2272,31 @@ int sctp_process_init(struct sctp_association *asoc, sctp_cid_t cid, * added as the primary transport. The source address seems to * be a a better choice than any of the embedded addresses. */ - if (peer_addr) { - if(!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) - goto nomem; - } + if(!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) + goto nomem; + + if (sctp_cmp_addr_exact(sctp_source(chunk), peer_addr)) + src_match = 1; /* Process the initialization parameters. */ sctp_walk_params(param, peer_init, init_hdr.params) { + if (!src_match && (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { + af = sctp_get_af_specific(param_type2af(param.p->type)); + af->from_addr_param(&addr, param.addr, + chunk->sctp_hdr->source, 0); + if (sctp_cmp_addr_exact(sctp_source(chunk), &addr)) + src_match = 1; + } if (!sctp_process_param(asoc, param, peer_addr, gfp)) goto clean_up; } + /* source address of chunk may not match any valid address */ + if (!src_match) + goto clean_up; + /* AUTH: After processing the parameters, make sure that we * have all the required info to potentially do authentications. */ @@ -2923,7 +2947,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, asconf_param->param_hdr.type != SCTP_PARAM_SET_PRIMARY) return SCTP_ERROR_UNKNOWN_PARAM; - switch (addr_param->v4.param_hdr.type) { + switch (addr_param->p.type) { case SCTP_PARAM_IPV6_ADDRESS: if (!asoc->peer.ipv6_address) return SCTP_ERROR_DNS_FAILED; @@ -2936,7 +2960,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, return SCTP_ERROR_DNS_FAILED; } - af = sctp_get_af_specific(param_type2af(addr_param->v4.param_hdr.type)); + af = sctp_get_af_specific(param_type2af(addr_param->p.type)); if (unlikely(!af)) return SCTP_ERROR_DNS_FAILED; @@ -3100,7 +3124,7 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, /* Skip the address parameter and store a pointer to the first * asconf parameter. */ - length = ntohs(addr_param->v4.param_hdr.length); + length = ntohs(addr_param->p.length); asconf_param = (sctp_addip_param_t *)((void *)addr_param + length); chunk_len -= length; @@ -3177,7 +3201,7 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, ((void *)asconf_param + sizeof(sctp_addip_param_t)); /* We have checked the packet before, so we do not check again. */ - af = sctp_get_af_specific(param_type2af(addr_param->v4.param_hdr.type)); + af = sctp_get_af_specific(param_type2af(addr_param->p.type)); af->from_addr_param(&addr, addr_param, htons(bp->port), 0); switch (asconf_param->param_hdr.type) { @@ -3193,11 +3217,8 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, local_bh_enable(); list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { - if (transport->state == SCTP_ACTIVE) - continue; dst_release(transport->dst); - sctp_transport_route(transport, NULL, - sctp_sk(asoc->base.sk)); + transport->dst = NULL; } break; case SCTP_PARAM_DEL_IP: @@ -3207,8 +3228,7 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { dst_release(transport->dst); - sctp_transport_route(transport, NULL, - sctp_sk(asoc->base.sk)); + transport->dst = NULL; } break; default: @@ -3304,7 +3324,7 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, /* Skip the address parameter in the last asconf sent and store a * pointer to the first asconf parameter. */ - length = ntohs(addr_param->v4.param_hdr.length); + length = ntohs(addr_param->p.length); asconf_param = (sctp_addip_param_t *)((void *)addr_param + length); asconf_len -= length; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b21b218d564f..d612ca1ca6c0 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -482,7 +482,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, * If the timer was a heartbeat, we only increment error counts * when we already have an outstanding HEARTBEAT that has not * been acknowledged. - * Additionaly, some tranport states inhibit error increments. + * Additionally, some tranport states inhibit error increments. */ if (!is_hb) { asoc->overall_error_count++; @@ -595,8 +595,7 @@ static int sctp_cmd_process_init(sctp_cmd_seq_t *commands, * fail during INIT processing (due to malloc problems), * just return the error and stop processing the stack. */ - if (!sctp_process_init(asoc, chunk->chunk_hdr->type, - sctp_source(chunk), peer_init, gfp)) + if (!sctp_process_init(asoc, chunk, sctp_source(chunk), peer_init, gfp)) error = -ENOMEM; else error = 0; @@ -1415,12 +1414,6 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, SCTP_RTXR_T3_RTX); break; - case SCTP_CMD_TRANSMIT: - /* Kick start transmission. */ - error = sctp_outq_uncork(&asoc->outqueue); - local_cork = 0; - break; - case SCTP_CMD_ECN_CE: /* Do delayed CE processing. */ sctp_do_ecn_ce_work(asoc, cmd->obj.u32); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 4b4eb7c96bbd..7f4a4f8368ee 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -393,8 +393,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, goto nomem_init; /* The call, sctp_process_init(), can fail on memory allocation. */ - if (!sctp_process_init(new_asoc, chunk->chunk_hdr->type, - sctp_source(chunk), + if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), (sctp_init_chunk_t *)chunk->chunk_hdr, GFP_ATOMIC)) goto nomem_init; @@ -551,7 +550,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(const struct sctp_endpoint *ep, * * This means that if we only want to abort associations * in an authenticated way (i.e AUTH+ABORT), then we - * can't destroy this association just becuase the packet + * can't destroy this association just because the packet * was malformed. */ if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) @@ -725,7 +724,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep, */ peer_init = &chunk->subh.cookie_hdr->c.peer_init[0]; - if (!sctp_process_init(new_asoc, chunk->chunk_hdr->type, + if (!sctp_process_init(new_asoc, chunk, &chunk->subh.cookie_hdr->c.peer_addr, peer_init, GFP_ATOMIC)) goto nomem_init; @@ -942,18 +941,9 @@ static sctp_disposition_t sctp_sf_heartbeat(const struct sctp_endpoint *ep, { struct sctp_transport *transport = (struct sctp_transport *) arg; struct sctp_chunk *reply; - sctp_sender_hb_info_t hbinfo; - size_t paylen = 0; - - hbinfo.param_hdr.type = SCTP_PARAM_HEARTBEAT_INFO; - hbinfo.param_hdr.length = htons(sizeof(sctp_sender_hb_info_t)); - hbinfo.daddr = transport->ipaddr; - hbinfo.sent_at = jiffies; - hbinfo.hb_nonce = transport->hb_nonce; /* Send a heartbeat to our peer. */ - paylen = sizeof(sctp_sender_hb_info_t); - reply = sctp_make_heartbeat(asoc, transport, &hbinfo, paylen); + reply = sctp_make_heartbeat(asoc, transport); if (!reply) return SCTP_DISPOSITION_NOMEM; @@ -1464,8 +1454,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( * Verification Tag and Peers Verification tag into a reserved * place (local tie-tag and per tie-tag) within the state cookie. */ - if (!sctp_process_init(new_asoc, chunk->chunk_hdr->type, - sctp_source(chunk), + if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), (sctp_init_chunk_t *)chunk->chunk_hdr, GFP_ATOMIC)) goto nomem; @@ -1546,7 +1535,7 @@ cleanup: } /* - * Handle simultanous INIT. + * Handle simultaneous INIT. * This means we started an INIT and then we got an INIT request from * our peer. * @@ -1694,8 +1683,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep, */ peer_init = &chunk->subh.cookie_hdr->c.peer_init[0]; - if (!sctp_process_init(new_asoc, chunk->chunk_hdr->type, - sctp_source(chunk), peer_init, + if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), peer_init, GFP_ATOMIC)) goto nomem; @@ -1780,8 +1768,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_b(const struct sctp_endpoint *ep, * side effects--it is safe to run them here. */ peer_init = &chunk->subh.cookie_hdr->c.peer_init[0]; - if (!sctp_process_init(new_asoc, chunk->chunk_hdr->type, - sctp_source(chunk), peer_init, + if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), peer_init, GFP_ATOMIC)) goto nomem; @@ -2079,7 +2066,7 @@ sctp_disposition_t sctp_sf_shutdown_pending_abort( * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. - * Becasue the length is "invalid", we can't really discard just + * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ @@ -2120,7 +2107,7 @@ sctp_disposition_t sctp_sf_shutdown_sent_abort(const struct sctp_endpoint *ep, * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. - * Becasue the length is "invalid", we can't really discard just + * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ @@ -2381,7 +2368,7 @@ sctp_disposition_t sctp_sf_do_9_1_abort(const struct sctp_endpoint *ep, * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. - * Becasue the length is "invalid", we can't really discard just + * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ @@ -2412,8 +2399,15 @@ static sctp_disposition_t __sctp_sf_do_9_1_abort(const struct sctp_endpoint *ep, /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); - if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) + if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { + + sctp_errhdr_t *err; + sctp_walk_errors(err, chunk->chunk_hdr); + if ((void *)err != (void *)chunk->chunk_end) + return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + error = ((sctp_errhdr_t *)chunk->skb->data)->cause; + } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ @@ -2448,7 +2442,7 @@ sctp_disposition_t sctp_sf_cookie_wait_abort(const struct sctp_endpoint *ep, * RFC 2960, Section 3.3.7 * If an endpoint receives an ABORT with a format error or for an * association that doesn't exist, it MUST silently discard it. - * Becasue the length is "invalid", we can't really discard just + * Because the length is "invalid", we can't really discard just * as we do not know its true length. So, to be safe, discard the * packet. */ @@ -3204,6 +3198,7 @@ sctp_disposition_t sctp_sf_operr_notify(const struct sctp_endpoint *ep, sctp_cmd_seq_t *commands) { struct sctp_chunk *chunk = arg; + sctp_errhdr_t *err; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); @@ -3212,6 +3207,10 @@ sctp_disposition_t sctp_sf_operr_notify(const struct sctp_endpoint *ep, if (!sctp_chunk_length_valid(chunk, sizeof(sctp_operr_chunk_t))) return sctp_sf_violation_chunklen(ep, asoc, type, arg, commands); + sctp_walk_errors(err, chunk->chunk_hdr); + if ((void *)err != (void *)chunk->chunk_end) + return sctp_sf_violation_paramlen(ep, asoc, type, arg, + (void *)err, commands); sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_OPERR, SCTP_CHUNK(chunk)); @@ -3320,8 +3319,10 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, struct sctp_chunk *chunk = arg; struct sk_buff *skb = chunk->skb; sctp_chunkhdr_t *ch; + sctp_errhdr_t *err; __u8 *ch_end; int ootb_shut_ack = 0; + int ootb_cookie_ack = 0; SCTP_INC_STATS(SCTP_MIB_OUTOFBLUES); @@ -3346,6 +3347,23 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, if (SCTP_CID_ABORT == ch->type) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + /* RFC 8.4, 7) If the packet contains a "Stale cookie" ERROR + * or a COOKIE ACK the SCTP Packet should be silently + * discarded. + */ + + if (SCTP_CID_COOKIE_ACK == ch->type) + ootb_cookie_ack = 1; + + if (SCTP_CID_ERROR == ch->type) { + sctp_walk_errors(err, ch) { + if (SCTP_ERROR_STALE_COOKIE == err->cause) { + ootb_cookie_ack = 1; + break; + } + } + } + /* Report violation if chunk len overflows */ ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); if (ch_end > skb_tail_pointer(skb)) @@ -3357,6 +3375,8 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, if (ootb_shut_ack) return sctp_sf_shut_8_4_5(ep, asoc, type, arg, commands); + else if (ootb_cookie_ack) + return sctp_sf_pdiscard(ep, asoc, type, arg, commands); else return sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands); } @@ -3855,7 +3875,7 @@ gen_shutdown: } /* - * SCTP-AUTH Section 6.3 Receving authenticated chukns + * SCTP-AUTH Section 6.3 Receiving authenticated chukns * * The receiver MUST use the HMAC algorithm indicated in the HMAC * Identifier field. If this algorithm was not specified by the @@ -4231,7 +4251,7 @@ static sctp_disposition_t sctp_sf_abort_violation( * * This means that if we only want to abort associations * in an authenticated way (i.e AUTH+ABORT), then we - * can't destroy this association just becuase the packet + * can't destroy this association just because the packet * was malformed. */ if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) @@ -4343,8 +4363,9 @@ static sctp_disposition_t sctp_sf_violation_chunklen( /* * Handle a protocol violation when the parameter length is invalid. - * "Invalid" length is identified as smaller than the minimal length a - * given parameter can be. + * If the length is smaller than the minimum length of a given parameter, + * or accumulated length in multi parameters exceeds the end of the chunk, + * the length is considered as invalid. */ static sctp_disposition_t sctp_sf_violation_paramlen( const struct sctp_endpoint *ep, @@ -4402,9 +4423,9 @@ static sctp_disposition_t sctp_sf_violation_ctsn( } /* Handle protocol violation of an invalid chunk bundling. For example, - * when we have an association and we recieve bundled INIT-ACK, or + * when we have an association and we receive bundled INIT-ACK, or * SHUDOWN-COMPLETE, our peer is clearly violationg the "MUST NOT bundle" - * statement from the specs. Additinally, there might be an attacker + * statement from the specs. Additionally, there might be an attacker * on the path and we may not want to continue this communication. */ static sctp_disposition_t sctp_sf_violation_chunk( @@ -5056,6 +5077,30 @@ sctp_disposition_t sctp_sf_ignore_primitive( ***************************************************************************/ /* + * When the SCTP stack has no more user data to send or retransmit, this + * notification is given to the user. Also, at the time when a user app + * subscribes to this event, if there is no data to be sent or + * retransmit, the stack will immediately send up this notification. + */ +sctp_disposition_t sctp_sf_do_no_pending_tsn( + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const sctp_subtype_t type, + void *arg, + sctp_cmd_seq_t *commands) +{ + struct sctp_ulpevent *event; + + event = sctp_ulpevent_make_sender_dry_event(asoc, GFP_ATOMIC); + if (!event) + return SCTP_DISPOSITION_NOMEM; + + sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(event)); + + return SCTP_DISPOSITION_CONSUME; +} + +/* * Start the shutdown negotiation. * * From Section 9.2: diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 546d4387fb3c..0338dc6fdc9d 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -107,8 +107,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, #define TYPE_SCTP_FUNC(func) {.fn = func, .name = #func} #define TYPE_SCTP_DATA { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -128,8 +126,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_DATA */ #define TYPE_SCTP_INIT { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1B_init), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -149,8 +145,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_INIT */ #define TYPE_SCTP_INIT_ACK { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_3_initack), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -170,8 +164,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_INIT_ACK */ #define TYPE_SCTP_SACK { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -191,8 +183,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_SACK */ #define TYPE_SCTP_HEARTBEAT { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -213,8 +203,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_HEARTBEAT */ #define TYPE_SCTP_HEARTBEAT_ACK { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -234,8 +222,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_HEARTBEAT_ACK */ #define TYPE_SCTP_ABORT { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_pdiscard), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -255,8 +241,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_ABORT */ #define TYPE_SCTP_SHUTDOWN { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -276,8 +260,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_SHUTDOWN */ #define TYPE_SCTP_SHUTDOWN_ACK { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -297,8 +279,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_SHUTDOWN_ACK */ #define TYPE_SCTP_ERROR { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -318,8 +298,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_ERROR */ #define TYPE_SCTP_COOKIE_ECHO { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1D_ce), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -339,8 +317,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_COOKIE_ECHO */ #define TYPE_SCTP_COOKIE_ACK { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -360,8 +336,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_COOKIE_ACK */ #define TYPE_SCTP_ECN_ECNE { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -381,8 +355,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_ECN_ECNE */ #define TYPE_SCTP_ECN_CWR { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -402,8 +374,6 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, } /* TYPE_SCTP_ECN_CWR */ #define TYPE_SCTP_SHUTDOWN_COMPLETE { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -446,8 +416,6 @@ static const sctp_sm_table_entry_t chunk_event_table[SCTP_NUM_BASE_CHUNK_TYPES][ }; /* state_fn_t chunk_event_table[][] */ #define TYPE_SCTP_ASCONF { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -467,8 +435,6 @@ static const sctp_sm_table_entry_t chunk_event_table[SCTP_NUM_BASE_CHUNK_TYPES][ } /* TYPE_SCTP_ASCONF */ #define TYPE_SCTP_ASCONF_ACK { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -496,8 +462,6 @@ static const sctp_sm_table_entry_t addip_chunk_event_table[SCTP_NUM_ADDIP_CHUNK_ }; /*state_fn_t addip_chunk_event_table[][] */ #define TYPE_SCTP_FWD_TSN { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -524,8 +488,6 @@ static const sctp_sm_table_entry_t prsctp_chunk_event_table[SCTP_NUM_PRSCTP_CHUN }; /*state_fn_t prsctp_chunk_event_table[][] */ #define TYPE_SCTP_AUTH { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -553,8 +515,6 @@ static const sctp_sm_table_entry_t auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TY static const sctp_sm_table_entry_t chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { - /* SCTP_STATE_EMPTY */ - TYPE_SCTP_FUNC(sctp_sf_ootb), /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_ootb), /* SCTP_STATE_COOKIE_WAIT */ @@ -575,8 +535,6 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { #define TYPE_SCTP_PRIMITIVE_ASSOCIATE { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asoc), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -596,8 +554,6 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { } /* TYPE_SCTP_PRIMITIVE_ASSOCIATE */ #define TYPE_SCTP_PRIMITIVE_SHUTDOWN { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -617,8 +573,6 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { } /* TYPE_SCTP_PRIMITIVE_SHUTDOWN */ #define TYPE_SCTP_PRIMITIVE_ABORT { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -638,8 +592,6 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { } /* TYPE_SCTP_PRIMITIVE_ABORT */ #define TYPE_SCTP_PRIMITIVE_SEND { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -659,8 +611,6 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { } /* TYPE_SCTP_PRIMITIVE_SEND */ #define TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -680,8 +630,6 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { } /* TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT */ #define TYPE_SCTP_PRIMITIVE_ASCONF { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -713,8 +661,6 @@ static const sctp_sm_table_entry_t primitive_event_table[SCTP_NUM_PRIMITIVE_TYPE }; #define TYPE_SCTP_OTHER_NO_PENDING_TSN { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -722,7 +668,7 @@ static const sctp_sm_table_entry_t primitive_event_table[SCTP_NUM_PRIMITIVE_TYPE /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_ESTABLISHED */ \ - TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ + TYPE_SCTP_FUNC(sctp_sf_do_no_pending_tsn), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_start_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ @@ -734,8 +680,6 @@ static const sctp_sm_table_entry_t primitive_event_table[SCTP_NUM_PRIMITIVE_TYPE } #define TYPE_SCTP_OTHER_ICMP_PROTO_UNREACH { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -760,8 +704,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ }; #define TYPE_SCTP_EVENT_TIMEOUT_NONE { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -781,8 +723,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -802,8 +742,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_T1_INIT { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -823,8 +761,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_T2_SHUTDOWN { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -844,8 +780,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_T3_RTX { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -865,8 +799,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_T4_RTO { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -886,8 +818,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -907,8 +837,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -928,8 +856,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_SACK { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ @@ -949,8 +875,6 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ } #define TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE { \ - /* SCTP_STATE_EMPTY */ \ - TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3951a10605bc..6766913a53e6 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -658,11 +658,15 @@ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt) goto err_bindx_rem; } - if (sa_addr->v4.sin_port != htons(bp->port)) { + if (sa_addr->v4.sin_port && + sa_addr->v4.sin_port != htons(bp->port)) { retval = -EINVAL; goto err_bindx_rem; } + if (!sa_addr->v4.sin_port) + sa_addr->v4.sin_port = htons(bp->port); + /* FIXME - There is probably a need to check if sk->sk_saddr and * sk->sk_rcv_addr are currently set to one of the addresses to * be removed. This is something which needs to be looked into @@ -1193,7 +1197,7 @@ out_free: * an endpoint that is multi-homed. Much like sctp_bindx() this call * allows a caller to specify multiple addresses at which a peer can be * reached. The way the SCTP stack uses the list of addresses to set up - * the association is implementation dependant. This function only + * the association is implementation dependent. This function only * specifies that the stack will try to make use of all the addresses in * the list when needed. * @@ -1492,7 +1496,7 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, struct sctp_chunk *chunk; union sctp_addr to; struct sockaddr *msg_name = NULL; - struct sctp_sndrcvinfo default_sinfo = { 0 }; + struct sctp_sndrcvinfo default_sinfo; struct sctp_sndrcvinfo *sinfo; struct sctp_initmsg *sinit; sctp_assoc_t associd = 0; @@ -1756,6 +1760,7 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, /* If the user didn't specify SNDRCVINFO, make up one with * some defaults. */ + memset(&default_sinfo, 0, sizeof(default_sinfo)); default_sinfo.sinfo_stream = asoc->default_stream; default_sinfo.sinfo_flags = asoc->default_flags; default_sinfo.sinfo_ppid = asoc->default_ppid; @@ -1786,12 +1791,10 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, goto out_free; } - if (sinfo) { - /* Check for invalid stream. */ - if (sinfo->sinfo_stream >= asoc->c.sinit_num_ostreams) { - err = -EINVAL; - goto out_free; - } + /* Check for invalid stream. */ + if (sinfo->sinfo_stream >= asoc->c.sinit_num_ostreams) { + err = -EINVAL; + goto out_free; } timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); @@ -2283,7 +2286,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, trans->param_flags = (trans->param_flags & ~SPP_PMTUD) | pmtud_change; if (update) { - sctp_transport_pmtu(trans); + sctp_transport_pmtu(trans, sctp_opt2sk(sp)); sctp_assoc_sync_pmtu(asoc); } } else if (asoc) { @@ -3215,14 +3218,9 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, if (optlen < sizeof(struct sctp_hmacalgo)) return -EINVAL; - hmacs = kmalloc(optlen, GFP_KERNEL); - if (!hmacs) - return -ENOMEM; - - if (copy_from_user(hmacs, optval, optlen)) { - err = -EFAULT; - goto out; - } + hmacs= memdup_user(optval, optlen); + if (IS_ERR(hmacs)) + return PTR_ERR(hmacs); idents = hmacs->shmac_num_idents; if (idents == 0 || idents > SCTP_AUTH_NUM_HMACS || @@ -3257,14 +3255,9 @@ static int sctp_setsockopt_auth_key(struct sock *sk, if (optlen <= sizeof(struct sctp_authkey)) return -EINVAL; - authkey = kmalloc(optlen, GFP_KERNEL); - if (!authkey) - return -ENOMEM; - - if (copy_from_user(authkey, optval, optlen)) { - ret = -EFAULT; - goto out; - } + authkey= memdup_user(optval, optlen); + if (IS_ERR(authkey)) + return PTR_ERR(authkey); if (authkey->sca_keylength > optlen - sizeof(struct sctp_authkey)) { ret = -EINVAL; @@ -5283,6 +5276,55 @@ static int sctp_getsockopt_assoc_number(struct sock *sk, int len, return 0; } +/* + * 8.2.6. Get the Current Identifiers of Associations + * (SCTP_GET_ASSOC_ID_LIST) + * + * This option gets the current list of SCTP association identifiers of + * the SCTP associations handled by a one-to-many style socket. + */ +static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, + char __user *optval, int __user *optlen) +{ + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_association *asoc; + struct sctp_assoc_ids *ids; + u32 num = 0; + + if (sctp_style(sk, TCP)) + return -EOPNOTSUPP; + + if (len < sizeof(struct sctp_assoc_ids)) + return -EINVAL; + + list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { + num++; + } + + if (len < sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num) + return -EINVAL; + + len = sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num; + + ids = kmalloc(len, GFP_KERNEL); + if (unlikely(!ids)) + return -ENOMEM; + + ids->gaids_number_of_ids = num; + num = 0; + list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { + ids->gaids_assoc_id[num++] = asoc->assoc_id; + } + + if (put_user(len, optlen) || copy_to_user(optval, ids, len)) { + kfree(ids); + return -EFAULT; + } + + kfree(ids); + return 0; +} + SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -5415,6 +5457,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_GET_ASSOC_NUMBER: retval = sctp_getsockopt_assoc_number(sk, len, optval, optlen); break; + case SCTP_GET_ASSOC_ID_LIST: + retval = sctp_getsockopt_assoc_ids(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index d3ae493d234a..394c57ca2f54 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -211,15 +211,17 @@ void sctp_transport_set_owner(struct sctp_transport *transport, } /* Initialize the pmtu of a transport. */ -void sctp_transport_pmtu(struct sctp_transport *transport) +void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) { - struct dst_entry *dst; - - dst = transport->af_specific->get_dst(NULL, &transport->ipaddr, NULL); + /* If we don't have a fresh route, look one up */ + if (!transport->dst || transport->dst->obsolete > 1) { + dst_release(transport->dst); + transport->af_specific->get_dst(transport, &transport->saddr, + &transport->fl, sk); + } - if (dst) { - transport->pathmtu = dst_mtu(dst); - dst_release(dst); + if (transport->dst) { + transport->pathmtu = dst_mtu(transport->dst); } else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } @@ -270,22 +272,19 @@ void sctp_transport_route(struct sctp_transport *transport, { struct sctp_association *asoc = transport->asoc; struct sctp_af *af = transport->af_specific; - union sctp_addr *daddr = &transport->ipaddr; - struct dst_entry *dst; - dst = af->get_dst(asoc, daddr, saddr); + af->get_dst(transport, saddr, &transport->fl, sctp_opt2sk(opt)); if (saddr) memcpy(&transport->saddr, saddr, sizeof(union sctp_addr)); else - af->get_saddr(opt, asoc, dst, daddr, &transport->saddr); + af->get_saddr(opt, transport, &transport->fl); - transport->dst = dst; if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) { return; } - if (dst) { - transport->pathmtu = dst_mtu(dst); + if (transport->dst) { + transport->pathmtu = dst_mtu(transport->dst); /* Initialize sk->sk_rcv_saddr, if the transport is the * association's active path for getsockname(). diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index aa72e89c3ee1..e70e5fc87890 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -554,7 +554,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_send_failed( memcpy(&ssf->ssf_info, &chunk->sinfo, sizeof(struct sctp_sndrcvinfo)); /* Per TSVWG discussion with Randy. Allow the application to - * ressemble a fragmented message. + * reassemble a fragmented message. */ ssf->ssf_info.sinfo_flags = chunk->chunk_hdr->flags; @@ -843,7 +843,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_authkey( ak = (struct sctp_authkey_event *) skb_put(skb, sizeof(struct sctp_authkey_event)); - ak->auth_type = SCTP_AUTHENTICATION_INDICATION; + ak->auth_type = SCTP_AUTHENTICATION_EVENT; ak->auth_flags = 0; ak->auth_length = sizeof(struct sctp_authkey_event); @@ -862,6 +862,34 @@ fail: return NULL; } +/* + * Socket Extensions for SCTP + * 6.3.10. SCTP_SENDER_DRY_EVENT + */ +struct sctp_ulpevent *sctp_ulpevent_make_sender_dry_event( + const struct sctp_association *asoc, gfp_t gfp) +{ + struct sctp_ulpevent *event; + struct sctp_sender_dry_event *sdry; + struct sk_buff *skb; + + event = sctp_ulpevent_new(sizeof(struct sctp_sender_dry_event), + MSG_NOTIFICATION, gfp); + if (!event) + return NULL; + + skb = sctp_event2skb(event); + sdry = (struct sctp_sender_dry_event *) + skb_put(skb, sizeof(struct sctp_sender_dry_event)); + + sdry->sender_dry_type = SCTP_SENDER_DRY_EVENT; + sdry->sender_dry_flags = 0; + sdry->sender_dry_length = sizeof(struct sctp_sender_dry_event); + sctp_ulpevent_set_owner(event, asoc); + sdry->sender_dry_assoc_id = sctp_assoc2id(asoc); + + return event; +} /* Return the notification type, assuming this is a notification * event. diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 17678189d054..f2d1de7f2ffb 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -240,7 +240,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) } else { /* * If fragment interleave is enabled, we - * can queue this to the recieve queue instead + * can queue this to the receive queue instead * of the lobby. */ if (sctp_sk(sk)->frag_interleave) diff --git a/net/socket.c b/net/socket.c index 5212447c86e7..02dc82db3d23 100644 --- a/net/socket.c +++ b/net/socket.c @@ -263,15 +263,6 @@ static struct inode *sock_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } - - -static void wq_free_rcu(struct rcu_head *head) -{ - struct socket_wq *wq = container_of(head, struct socket_wq, rcu); - - kfree(wq); -} - static void sock_destroy_inode(struct inode *inode) { struct socket_alloc *ei; @@ -279,7 +270,7 @@ static void sock_destroy_inode(struct inode *inode) ei = container_of(inode, struct socket_alloc, vfs_inode); wq = rcu_dereference_protected(ei->socket.wq, 1); - call_rcu(&wq->rcu, wq_free_rcu); + kfree_rcu(wq, rcu); kmem_cache_free(sock_inode_cachep, ei); } @@ -551,11 +542,10 @@ int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags) } EXPORT_SYMBOL(sock_tx_timestamp); -static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size) +static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size) { struct sock_iocb *si = kiocb_to_siocb(iocb); - int err; sock_update_classid(sock->sk); @@ -564,13 +554,17 @@ static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, si->msg = msg; si->size = size; - err = security_socket_sendmsg(sock, msg, size); - if (err) - return err; - return sock->ops->sendmsg(iocb, sock, msg, size); } +static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size) +{ + int err = security_socket_sendmsg(sock, msg, size); + + return err ?: __sock_sendmsg_nosec(iocb, sock, msg, size); +} + int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct kiocb iocb; @@ -586,6 +580,20 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } EXPORT_SYMBOL(sock_sendmsg); +int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg, size_t size) +{ + struct kiocb iocb; + struct sock_iocb siocb; + int ret; + + init_sync_kiocb(&iocb, NULL); + iocb.private = &siocb; + ret = __sock_sendmsg_nosec(&iocb, sock, msg, size); + if (-EIOCBQUEUED == ret) + ret = wait_on_sync_kiocb(&iocb); + return ret; +} + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { @@ -1863,57 +1871,47 @@ SYSCALL_DEFINE2(shutdown, int, fd, int, how) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) -/* - * BSD sendmsg interface - */ - -SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) +static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, + struct msghdr *msg_sys, unsigned flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; - struct socket *sock; struct sockaddr_storage address; struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; unsigned char ctl[sizeof(struct cmsghdr) + 20] __attribute__ ((aligned(sizeof(__kernel_size_t)))); /* 20 is size of ipv6_pktinfo */ unsigned char *ctl_buf = ctl; - struct msghdr msg_sys; int err, ctl_len, iov_size, total_len; - int fput_needed; err = -EFAULT; if (MSG_CMSG_COMPAT & flags) { - if (get_compat_msghdr(&msg_sys, msg_compat)) + if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr))) + } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) return -EFAULT; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - goto out; - /* do not move before msg_sys is valid */ err = -EMSGSIZE; - if (msg_sys.msg_iovlen > UIO_MAXIOV) - goto out_put; + if (msg_sys->msg_iovlen > UIO_MAXIOV) + goto out; /* Check whether to allocate the iovec area */ err = -ENOMEM; - iov_size = msg_sys.msg_iovlen * sizeof(struct iovec); - if (msg_sys.msg_iovlen > UIO_FASTIOV) { + iov_size = msg_sys->msg_iovlen * sizeof(struct iovec); + if (msg_sys->msg_iovlen > UIO_FASTIOV) { iov = sock_kmalloc(sock->sk, iov_size, GFP_KERNEL); if (!iov) - goto out_put; + goto out; } /* This will also move the address data into kernel space */ if (MSG_CMSG_COMPAT & flags) { - err = verify_compat_iovec(&msg_sys, iov, + err = verify_compat_iovec(msg_sys, iov, (struct sockaddr *)&address, VERIFY_READ); } else - err = verify_iovec(&msg_sys, iov, + err = verify_iovec(msg_sys, iov, (struct sockaddr *)&address, VERIFY_READ); if (err < 0) @@ -1922,17 +1920,17 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) err = -ENOBUFS; - if (msg_sys.msg_controllen > INT_MAX) + if (msg_sys->msg_controllen > INT_MAX) goto out_freeiov; - ctl_len = msg_sys.msg_controllen; + ctl_len = msg_sys->msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { err = - cmsghdr_from_user_compat_to_kern(&msg_sys, sock->sk, ctl, + cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl, sizeof(ctl)); if (err) goto out_freeiov; - ctl_buf = msg_sys.msg_control; - ctl_len = msg_sys.msg_controllen; + ctl_buf = msg_sys->msg_control; + ctl_len = msg_sys->msg_controllen; } else if (ctl_len) { if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); @@ -1941,21 +1939,22 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) } err = -EFAULT; /* - * Careful! Before this, msg_sys.msg_control contains a user pointer. + * Careful! Before this, msg_sys->msg_control contains a user pointer. * Afterwards, it will be a kernel pointer. Thus the compiler-assisted * checking falls down on this. */ if (copy_from_user(ctl_buf, - (void __user __force *)msg_sys.msg_control, + (void __user __force *)msg_sys->msg_control, ctl_len)) goto out_freectl; - msg_sys.msg_control = ctl_buf; + msg_sys->msg_control = ctl_buf; } - msg_sys.msg_flags = flags; + msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) - msg_sys.msg_flags |= MSG_DONTWAIT; - err = sock_sendmsg(sock, &msg_sys, total_len); + msg_sys->msg_flags |= MSG_DONTWAIT; + err = (nosec ? sock_sendmsg_nosec : sock_sendmsg)(sock, msg_sys, + total_len); out_freectl: if (ctl_buf != ctl) @@ -1963,12 +1962,114 @@ out_freectl: out_freeiov: if (iov != iovstack) sock_kfree_s(sock->sk, iov, iov_size); -out_put: +out: + return err; +} + +/* + * BSD sendmsg interface + */ + +SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) +{ + int fput_needed, err; + struct msghdr msg_sys; + struct socket *sock = sockfd_lookup_light(fd, &err, &fput_needed); + + if (!sock) + goto out; + + err = __sys_sendmsg(sock, msg, &msg_sys, flags, 0); + fput_light(sock->file, fput_needed); out: return err; } +/* + * Linux sendmmsg interface + */ + +int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, + unsigned int flags) +{ + int fput_needed, err, datagrams; + struct socket *sock; + struct mmsghdr __user *entry; + struct compat_mmsghdr __user *compat_entry; + struct msghdr msg_sys; + + datagrams = 0; + + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (!sock) + return err; + + err = sock_error(sock->sk); + if (err) + goto out_put; + + entry = mmsg; + compat_entry = (struct compat_mmsghdr __user *)mmsg; + + while (datagrams < vlen) { + /* + * No need to ask LSM for more than the first datagram. + */ + if (MSG_CMSG_COMPAT & flags) { + err = __sys_sendmsg(sock, (struct msghdr __user *)compat_entry, + &msg_sys, flags, datagrams); + if (err < 0) + break; + err = __put_user(err, &compat_entry->msg_len); + ++compat_entry; + } else { + err = __sys_sendmsg(sock, (struct msghdr __user *)entry, + &msg_sys, flags, datagrams); + if (err < 0) + break; + err = put_user(err, &entry->msg_len); + ++entry; + } + + if (err) + break; + ++datagrams; + } + +out_put: + fput_light(sock->file, fput_needed); + + if (err == 0) + return datagrams; + + if (datagrams != 0) { + /* + * We may send less entries than requested (vlen) if the + * sock is non blocking... + */ + if (err != -EAGAIN) { + /* + * ... or if sendmsg returns an error after we + * send some datagrams, where we record the + * error to return on the next call or if the + * app asks about it using getsockopt(SO_ERROR). + */ + sock->sk->sk_err = -err; + } + + return datagrams; + } + + return err; +} + +SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, + unsigned int, vlen, unsigned int, flags) +{ + return __sys_sendmmsg(fd, mmsg, vlen, flags); +} + static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg, struct msghdr *msg_sys, unsigned flags, int nosec) { @@ -2122,14 +2223,16 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, */ if (MSG_CMSG_COMPAT & flags) { err = __sys_recvmsg(sock, (struct msghdr __user *)compat_entry, - &msg_sys, flags, datagrams); + &msg_sys, flags & ~MSG_WAITFORONE, + datagrams); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = __sys_recvmsg(sock, (struct msghdr __user *)entry, - &msg_sys, flags, datagrams); + &msg_sys, flags & ~MSG_WAITFORONE, + datagrams); if (err < 0) break; err = put_user(err, &entry->msg_len); @@ -2214,11 +2317,11 @@ SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, #ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) -static const unsigned char nargs[20] = { +static const unsigned char nargs[21] = { AL(0), AL(3), AL(3), AL(3), AL(2), AL(3), AL(3), AL(3), AL(4), AL(4), AL(4), AL(6), AL(6), AL(2), AL(5), AL(5), AL(3), AL(3), - AL(4), AL(5) + AL(4), AL(5), AL(4) }; #undef AL @@ -2238,7 +2341,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) int err; unsigned int len; - if (call < 1 || call > SYS_RECVMMSG) + if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; len = nargs[call]; @@ -2313,6 +2416,9 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) case SYS_SENDMSG: err = sys_sendmsg(a0, (struct msghdr __user *)a1, a[2]); break; + case SYS_SENDMMSG: + err = sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3]); + break; case SYS_RECVMSG: err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); break; @@ -2643,13 +2749,13 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) return -EFAULT; if (convert_in) { - /* We expect there to be holes between fs.m_u and + /* We expect there to be holes between fs.m_ext and * fs.ring_cookie and at the end of fs, but nowhere else. */ - BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_u) + - sizeof(compat_rxnfc->fs.m_u) != - offsetof(struct ethtool_rxnfc, fs.m_u) + - sizeof(rxnfc->fs.m_u)); + BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + + sizeof(compat_rxnfc->fs.m_ext) != + offsetof(struct ethtool_rxnfc, fs.m_ext) + + sizeof(rxnfc->fs.m_ext)); BUILD_BUG_ON( offsetof(struct compat_ethtool_rxnfc, fs.location) - offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != @@ -2657,7 +2763,7 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) offsetof(struct ethtool_rxnfc, fs.ring_cookie)); if (copy_in_user(rxnfc, compat_rxnfc, - (void *)(&rxnfc->fs.m_u + 1) - + (void *)(&rxnfc->fs.m_ext + 1) - (void *)rxnfc) || copy_in_user(&rxnfc->fs.ring_cookie, &compat_rxnfc->fs.ring_cookie, @@ -2674,7 +2780,7 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) if (convert_out) { if (copy_in_user(compat_rxnfc, rxnfc, - (const void *)(&rxnfc->fs.m_u + 1) - + (const void *)(&rxnfc->fs.m_ext + 1) - (const void *)rxnfc) || copy_in_user(&compat_rxnfc->fs.ring_cookie, &rxnfc->fs.ring_cookie, @@ -2986,7 +3092,7 @@ out: /* Since old style bridge ioctl's endup using SIOCDEVPRIVATE * for some operations; this forces use of the newer bridge-utils that - * use compatiable ioctls + * use compatible ioctls */ static int old_bridge_ioctl(compat_ulong_t __user *argp) { diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 8873fd8ddacd..b2198e65d8bb 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -18,14 +18,13 @@ config SUNRPC_XPRT_RDMA If unsure, say N. config RPCSEC_GSS_KRB5 - tristate + tristate "Secure RPC: Kerberos V mechanism" depends on SUNRPC && CRYPTO - prompt "Secure RPC: Kerberos V mechanism" if !(NFS_V4 || NFSD_V4) + depends on CRYPTO_MD5 && CRYPTO_DES && CRYPTO_CBC && CRYPTO_CTS + depends on CRYPTO_ECB && CRYPTO_HMAC && CRYPTO_SHA1 && CRYPTO_AES + depends on CRYPTO_ARC4 default y select SUNRPC_GSS - select CRYPTO_MD5 - select CRYPTO_DES - select CRYPTO_CBC help Choose Y here to enable Secure RPC using the Kerberos version 5 GSS-API mechanism (RFC 1964). diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index 1419d0cdbbac..4195233c4914 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -151,7 +151,7 @@ static size_t rpc_pton4(const char *buf, const size_t buflen, return 0; sin->sin_family = AF_INET; - return sizeof(struct sockaddr_in);; + return sizeof(struct sockaddr_in); } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index f3914d0c5079..339ba64cce1e 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -520,7 +520,7 @@ gss_refresh_upcall(struct rpc_task *task) warn_gssd(); task->tk_timeout = 15*HZ; rpc_sleep_on(&pipe_version_rpc_waitqueue, task, NULL); - return 0; + return -EAGAIN; } if (IS_ERR(gss_msg)) { err = PTR_ERR(gss_msg); @@ -563,10 +563,12 @@ retry: if (PTR_ERR(gss_msg) == -EAGAIN) { err = wait_event_interruptible_timeout(pipe_version_waitqueue, pipe_version >= 0, 15*HZ); + if (pipe_version < 0) { + warn_gssd(); + err = -EACCES; + } if (err) goto out; - if (pipe_version < 0) - warn_gssd(); goto retry; } if (IS_ERR(gss_msg)) { diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 9022f0a6503e..0a9a2ec2e469 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -427,7 +427,7 @@ static int context_derive_keys_rc4(struct krb5_ctx *ctx) { struct crypto_hash *hmac; - static const char sigkeyconstant[] = "signaturekey"; + char sigkeyconstant[] = "signaturekey"; int slen = strlen(sigkeyconstant) + 1; /* include null terminator */ struct hash_desc desc; struct scatterlist sg[1]; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index bcdae78fdfc6..8d0f7d3c71c8 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1101,7 +1101,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) /* credential is: * version(==1), proc(0,1,2,3), seq, service (1,2,3), handle - * at least 5 u32s, and is preceeded by length, so that makes 6. + * at least 5 u32s, and is preceded by length, so that makes 6. */ if (argv->iov_len < 5 * 4) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index e7a96e478f63..8d83f9d48713 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1508,7 +1508,10 @@ call_timeout(struct rpc_task *task) if (clnt->cl_chatty) printk(KERN_NOTICE "%s: server %s not responding, timed out\n", clnt->cl_protname, clnt->cl_server); - rpc_exit(task, -EIO); + if (task->tk_flags & RPC_TASK_TIMEOUT) + rpc_exit(task, -ETIMEDOUT); + else + rpc_exit(task, -EIO); return; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 9494c3767356..ce5eb68a9664 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -906,6 +906,7 @@ void xprt_transmit(struct rpc_task *task) } dprintk("RPC: %5u xmit complete\n", task->tk_pid); + task->tk_flags |= RPC_TASK_SENT; spin_lock_bh(&xprt->transport_lock); xprt->ops->set_retrans_timeout(task); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 1a10dcd999ea..6c014dd3a20b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -333,7 +333,7 @@ static void rq_cq_reap(struct svcxprt_rdma *xprt) } /* - * Processs a completion context + * Process a completion context */ static void process_context(struct svcxprt_rdma *xprt, struct svc_rdma_op_ctxt *ctxt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 1e336a06d3e6..bf005d3c65ef 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -504,7 +504,7 @@ static int xs_nospace(struct rpc_task *task) * EAGAIN: The socket was blocked, please call again later to * complete the request * ENOTCONN: Caller needs to invoke connect logic then call again - * other: Some other error occured, the request was not sent + * other: Some other error occurred, the request was not sent */ static int xs_udp_send_request(struct rpc_task *task) { @@ -590,7 +590,7 @@ static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf) * EAGAIN: The socket was blocked, please call again later to * complete the request * ENOTCONN: Caller needs to invoke connect logic then call again - * other: Some other error occured, the request was not sent + * other: Some other error occurred, the request was not sent * * XXX: In the case of soft timeouts, should we eventually give up * if sendmsg is not able to make progress? diff --git a/net/tipc/addr.h b/net/tipc/addr.h index 8971aba99aea..e4f35afe3207 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -37,14 +37,17 @@ #ifndef _TIPC_ADDR_H #define _TIPC_ADDR_H +#define TIPC_ZONE_MASK 0xff000000u +#define TIPC_CLUSTER_MASK 0xfffff000u + static inline u32 tipc_zone_mask(u32 addr) { - return addr & 0xff000000u; + return addr & TIPC_ZONE_MASK; } static inline u32 tipc_cluster_mask(u32 addr) { - return addr & 0xfffff000u; + return addr & TIPC_CLUSTER_MASK; } static inline int in_own_cluster(u32 addr) diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 7dc1dc7151ea..fa68d1e9ff4b 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -44,13 +44,6 @@ #define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */ -/* - * Loss rate for incoming broadcast frames; used to test retransmission code. - * Set to N to cause every N'th frame to be discarded; 0 => don't discard any. - */ - -#define TIPC_BCAST_LOSS_RATE 0 - /** * struct bcbearer_pair - a pair of bearers used by broadcast link * @primary: pointer to primary bearer @@ -414,9 +407,7 @@ int tipc_bclink_send_msg(struct sk_buff *buf) spin_lock_bh(&bc_lock); res = tipc_link_send_buf(bcl, buf); - if (unlikely(res == -ELINKCONG)) - buf_discard(buf); - else + if (likely(res > 0)) bclink_set_last_sent(); bcl->stats.queue_sz_counts++; @@ -434,9 +425,6 @@ int tipc_bclink_send_msg(struct sk_buff *buf) void tipc_bclink_recv_pkt(struct sk_buff *buf) { -#if (TIPC_BCAST_LOSS_RATE) - static int rx_count; -#endif struct tipc_msg *msg = buf_msg(buf); struct tipc_node *node = tipc_node_find(msg_prevnode(msg)); u32 next_in; @@ -470,14 +458,6 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) return; } -#if (TIPC_BCAST_LOSS_RATE) - if (++rx_count == TIPC_BCAST_LOSS_RATE) { - rx_count = 0; - buf_discard(buf); - return; - } -#endif - tipc_node_lock(node); receive: deferred = node->bclink.deferred_head; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 411719feb803..85209eadfae6 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -46,6 +46,8 @@ static u32 media_count; struct tipc_bearer tipc_bearers[MAX_BEARERS]; +static void bearer_disable(struct tipc_bearer *b_ptr); + /** * media_name_valid - validate media name * @@ -342,15 +344,15 @@ struct sk_buff *tipc_bearer_get_names(void) void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest) { tipc_nmap_add(&b_ptr->nodes, dest); - tipc_disc_update_link_req(b_ptr->link_req); tipc_bcbearer_sort(); + tipc_disc_add_dest(b_ptr->link_req); } void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest) { tipc_nmap_remove(&b_ptr->nodes, dest); - tipc_disc_update_link_req(b_ptr->link_req); tipc_bcbearer_sort(); + tipc_disc_remove_dest(b_ptr->link_req); } /* @@ -493,8 +495,15 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) warn("Bearer <%s> rejected, illegal name\n", name); return -EINVAL; } - if (!tipc_addr_domain_valid(disc_domain) || - !tipc_in_scope(disc_domain, tipc_own_addr)) { + if (tipc_addr_domain_valid(disc_domain) && + (disc_domain != tipc_own_addr)) { + if (tipc_in_scope(disc_domain, tipc_own_addr)) { + disc_domain = tipc_own_addr & TIPC_CLUSTER_MASK; + res = 0; /* accept any node in own cluster */ + } else if (in_own_cluster(disc_domain)) + res = 0; /* accept specified node in own cluster */ + } + if (res) { warn("Bearer <%s> rejected, illegal discovery domain\n", name); return -EINVAL; } @@ -511,7 +520,7 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) if (!m_ptr) { warn("Bearer <%s> rejected, media <%s> not registered\n", name, b_name.media_name); - goto failed; + goto exit; } if (priority == TIPC_MEDIA_LINK_PRI) @@ -527,14 +536,14 @@ restart: } if (!strcmp(name, tipc_bearers[i].name)) { warn("Bearer <%s> rejected, already enabled\n", name); - goto failed; + goto exit; } if ((tipc_bearers[i].priority == priority) && (++with_this_prio > 2)) { if (priority-- == 0) { warn("Bearer <%s> rejected, duplicate priority\n", name); - goto failed; + goto exit; } warn("Bearer <%s> priority adjustment required %u->%u\n", name, priority + 1, priority); @@ -544,7 +553,7 @@ restart: if (bearer_id >= MAX_BEARERS) { warn("Bearer <%s> rejected, bearer limit reached (%u)\n", name, MAX_BEARERS); - goto failed; + goto exit; } b_ptr = &tipc_bearers[bearer_id]; @@ -552,7 +561,7 @@ restart: res = m_ptr->enable_bearer(b_ptr); if (res) { warn("Bearer <%s> rejected, enable failure (%d)\n", name, -res); - goto failed; + goto exit; } b_ptr->identity = bearer_id; @@ -562,14 +571,18 @@ restart: b_ptr->priority = priority; INIT_LIST_HEAD(&b_ptr->cong_links); INIT_LIST_HEAD(&b_ptr->links); - b_ptr->link_req = tipc_disc_init_link_req(b_ptr, &m_ptr->bcast_addr, - disc_domain); spin_lock_init(&b_ptr->lock); - write_unlock_bh(&tipc_net_lock); + + res = tipc_disc_create(b_ptr, &m_ptr->bcast_addr, disc_domain); + if (res) { + bearer_disable(b_ptr); + warn("Bearer <%s> rejected, discovery object creation failed\n", + name); + goto exit; + } info("Enabled bearer <%s>, discovery domain %s, priority %u\n", name, tipc_addr_string_fill(addr_string, disc_domain), priority); - return 0; -failed: +exit: write_unlock_bh(&tipc_net_lock); return res; } @@ -620,14 +633,14 @@ static void bearer_disable(struct tipc_bearer *b_ptr) struct link *temp_l_ptr; info("Disabling bearer <%s>\n", b_ptr->name); - tipc_disc_stop_link_req(b_ptr->link_req); spin_lock_bh(&b_ptr->lock); - b_ptr->link_req = NULL; b_ptr->blocked = 1; b_ptr->media->disable_bearer(b_ptr); list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { tipc_link_delete(l_ptr); } + if (b_ptr->link_req) + tipc_disc_delete(b_ptr->link_req); spin_unlock_bh(&b_ptr->lock); memset(b_ptr, 0, sizeof(struct tipc_bearer)); } diff --git a/net/tipc/core.c b/net/tipc/core.c index c9a73e7763f6..943b6af84265 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -179,8 +179,7 @@ static int __init tipc_init(void) if (tipc_log_resize(CONFIG_TIPC_LOG) != 0) warn("Unable to create log buffer\n"); - info("Activated (version " TIPC_MOD_VER - " compiled " __DATE__ " " __TIME__ ")\n"); + info("Activated (version " TIPC_MOD_VER ")\n"); tipc_own_addr = 0; tipc_remote_management = 1; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 491eff56b9da..0987933155b9 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -39,19 +39,17 @@ #include "discover.h" #define TIPC_LINK_REQ_INIT 125 /* min delay during bearer start up */ -#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 */ - -/* - * TODO: Most of the inter-cluster setup stuff should be - * rewritten, and be made conformant with specification. - */ +#define TIPC_LINK_REQ_FAST 1000 /* max delay if bearer has no links */ +#define TIPC_LINK_REQ_SLOW 60000 /* max delay if bearer has links */ +#define TIPC_LINK_REQ_INACTIVE 0xffffffff /* indicates no timer in use */ /** * struct link_req - information about an ongoing link setup request * @bearer: bearer issuing requests * @dest: destination address for request messages + * @domain: network domain to which links can be established + * @num_nodes: number of nodes currently discovered (i.e. with an active link) * @buf: request message to be (repeatedly) sent * @timer: timer governing period between requests * @timer_intv: current interval between requests (in ms) @@ -59,6 +57,8 @@ struct link_req { struct tipc_bearer *bearer; struct tipc_media_addr dest; + u32 domain; + int num_nodes; struct sk_buff *buf; struct timer_list timer; unsigned int timer_intv; @@ -147,7 +147,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) } if (!tipc_in_scope(dest, tipc_own_addr)) return; - if (!in_own_cluster(orig)) + if (!tipc_in_scope(b_ptr->link_req->domain, orig)) return; /* Locate structure corresponding to requesting node */ @@ -214,44 +214,54 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) } /** - * tipc_disc_stop_link_req - stop sending periodic link setup requests + * disc_update - update frequency of periodic link setup requests * @req: ptr to link request structure + * + * Reinitiates discovery process if discovery object has no associated nodes + * and is either not currently searching or is searching at a slow rate */ -void tipc_disc_stop_link_req(struct link_req *req) +static void disc_update(struct link_req *req) { - if (!req) - return; + if (!req->num_nodes) { + if ((req->timer_intv == TIPC_LINK_REQ_INACTIVE) || + (req->timer_intv > TIPC_LINK_REQ_FAST)) { + req->timer_intv = TIPC_LINK_REQ_INIT; + k_start_timer(&req->timer, req->timer_intv); + } + } +} - k_cancel_timer(&req->timer); - k_term_timer(&req->timer); - buf_discard(req->buf); - kfree(req); +/** + * tipc_disc_add_dest - increment set of discovered nodes + * @req: ptr to link request structure + */ + +void tipc_disc_add_dest(struct link_req *req) +{ + req->num_nodes++; } /** - * tipc_disc_update_link_req - update frequency of periodic link setup requests + * tipc_disc_remove_dest - decrement set of discovered nodes * @req: ptr to link request structure */ -void tipc_disc_update_link_req(struct link_req *req) +void tipc_disc_remove_dest(struct link_req *req) { - if (!req) - return; + req->num_nodes--; + disc_update(req); +} - if (req->timer_intv == TIPC_LINK_REQ_SLOW) { - if (!req->bearer->nodes.count) { - req->timer_intv = TIPC_LINK_REQ_FAST; - k_start_timer(&req->timer, req->timer_intv); - } - } else if (req->timer_intv == TIPC_LINK_REQ_FAST) { - if (req->bearer->nodes.count) { - req->timer_intv = TIPC_LINK_REQ_SLOW; - k_start_timer(&req->timer, req->timer_intv); - } - } else { - /* leave timer "as is" if haven't yet reached a "normal" rate */ - } +/** + * disc_send_msg - send link setup request message + * @req: ptr to link request structure + */ + +static void disc_send_msg(struct link_req *req) +{ + if (!req->bearer->blocked) + tipc_bearer_send(req->bearer, req->buf, &req->dest); } /** @@ -263,56 +273,86 @@ void tipc_disc_update_link_req(struct link_req *req) static void disc_timeout(struct link_req *req) { + int max_delay; + spin_lock_bh(&req->bearer->lock); - req->bearer->media->send_msg(req->buf, req->bearer, &req->dest); - - if ((req->timer_intv == TIPC_LINK_REQ_SLOW) || - (req->timer_intv == TIPC_LINK_REQ_FAST)) { - /* leave timer interval "as is" if already at a "normal" rate */ - } else { - req->timer_intv *= 2; - if (req->timer_intv > TIPC_LINK_REQ_FAST) - req->timer_intv = TIPC_LINK_REQ_FAST; - if ((req->timer_intv == TIPC_LINK_REQ_FAST) && - (req->bearer->nodes.count)) - req->timer_intv = TIPC_LINK_REQ_SLOW; + /* Stop searching if only desired node has been found */ + + if (tipc_node(req->domain) && req->num_nodes) { + req->timer_intv = TIPC_LINK_REQ_INACTIVE; + goto exit; } - k_start_timer(&req->timer, req->timer_intv); + /* + * Send discovery message, then update discovery timer + * + * Keep doubling time between requests until limit is reached; + * hold at fast polling rate if don't have any associated nodes, + * otherwise hold at slow polling rate + */ + + disc_send_msg(req); + + req->timer_intv *= 2; + if (req->num_nodes) + max_delay = TIPC_LINK_REQ_SLOW; + else + max_delay = TIPC_LINK_REQ_FAST; + if (req->timer_intv > max_delay) + req->timer_intv = max_delay; + + k_start_timer(&req->timer, req->timer_intv); +exit: spin_unlock_bh(&req->bearer->lock); } /** - * tipc_disc_init_link_req - start sending periodic link setup requests + * tipc_disc_create - create object to send periodic link setup requests * @b_ptr: ptr to bearer issuing requests * @dest: destination address for request messages - * @dest_domain: network domain of node(s) which should respond to message + * @dest_domain: network domain to which links can be established * - * Returns pointer to link request structure, or NULL if unable to create. + * Returns 0 if successful, otherwise -errno. */ -struct link_req *tipc_disc_init_link_req(struct tipc_bearer *b_ptr, - const struct tipc_media_addr *dest, - u32 dest_domain) +int tipc_disc_create(struct tipc_bearer *b_ptr, + struct tipc_media_addr *dest, u32 dest_domain) { struct link_req *req; req = kmalloc(sizeof(*req), GFP_ATOMIC); if (!req) - return NULL; + return -ENOMEM; req->buf = tipc_disc_init_msg(DSC_REQ_MSG, dest_domain, b_ptr); if (!req->buf) { kfree(req); - return NULL; + return -ENOMSG; } memcpy(&req->dest, dest, sizeof(*dest)); req->bearer = b_ptr; + req->domain = dest_domain; + req->num_nodes = 0; req->timer_intv = TIPC_LINK_REQ_INIT; k_init_timer(&req->timer, (Handler)disc_timeout, (unsigned long)req); k_start_timer(&req->timer, req->timer_intv); - return req; + b_ptr->link_req = req; + disc_send_msg(req); + return 0; +} + +/** + * tipc_disc_delete - destroy object sending periodic link setup requests + * @req: ptr to link request structure + */ + +void tipc_disc_delete(struct link_req *req) +{ + k_cancel_timer(&req->timer); + k_term_timer(&req->timer); + buf_discard(req->buf); + kfree(req); } diff --git a/net/tipc/discover.h b/net/tipc/discover.h index e48a167e47b2..a3af595b86cb 100644 --- a/net/tipc/discover.h +++ b/net/tipc/discover.h @@ -39,12 +39,11 @@ struct link_req; -struct link_req *tipc_disc_init_link_req(struct tipc_bearer *b_ptr, - const struct tipc_media_addr *dest, - u32 dest_domain); -void tipc_disc_update_link_req(struct link_req *req); -void tipc_disc_stop_link_req(struct link_req *req); - +int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest, + u32 dest_domain); +void tipc_disc_delete(struct link_req *req); +void tipc_disc_add_dest(struct link_req *req); +void tipc_disc_remove_dest(struct link_req *req); void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr); #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index 43639ff1cbec..5ed4b4f7452d 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -92,7 +92,8 @@ static int link_recv_changeover_msg(struct link **l_ptr, struct sk_buff **buf); static void link_set_supervision_props(struct link *l_ptr, u32 tolerance); static int link_send_sections_long(struct tipc_port *sender, struct iovec const *msg_sect, - u32 num_sect, u32 destnode); + u32 num_sect, unsigned int total_len, + u32 destnode); static void link_check_defragm_bufs(struct link *l_ptr); static void link_state_event(struct link *l_ptr, u32 event); static void link_reset_statistics(struct link *l_ptr); @@ -842,6 +843,25 @@ static void link_add_to_outqueue(struct link *l_ptr, l_ptr->stats.max_queue_sz = l_ptr->out_queue_size; } +static void link_add_chain_to_outqueue(struct link *l_ptr, + struct sk_buff *buf_chain, + u32 long_msgno) +{ + struct sk_buff *buf; + struct tipc_msg *msg; + + if (!l_ptr->next_out) + l_ptr->next_out = buf_chain; + while (buf_chain) { + buf = buf_chain; + buf_chain = buf_chain->next; + + msg = buf_msg(buf); + msg_set_long_msgno(msg, long_msgno); + link_add_to_outqueue(l_ptr, buf, msg); + } +} + /* * tipc_link_send_buf() is the 'full path' for messages, called from * inside TIPC when the 'fast path' in tipc_send_buf @@ -864,8 +884,9 @@ int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf) if (unlikely(queue_size >= queue_limit)) { if (imp <= TIPC_CRITICAL_IMPORTANCE) { - return link_schedule_port(l_ptr, msg_origport(msg), - size); + link_schedule_port(l_ptr, msg_origport(msg), size); + buf_discard(buf); + return -ELINKCONG; } buf_discard(buf); if (imp > CONN_MANAGER) { @@ -1042,6 +1063,7 @@ int tipc_send_buf_fast(struct sk_buff *buf, u32 destnode) int tipc_link_send_sections_fast(struct tipc_port *sender, struct iovec const *msg_sect, const u32 num_sect, + unsigned int total_len, u32 destaddr) { struct tipc_msg *hdr = &sender->phdr; @@ -1057,8 +1079,8 @@ again: * (Must not hold any locks while building message.) */ - res = tipc_msg_build(hdr, msg_sect, num_sect, sender->max_pkt, - !sender->user_port, &buf); + res = tipc_msg_build(hdr, msg_sect, num_sect, total_len, + sender->max_pkt, !sender->user_port, &buf); read_lock_bh(&tipc_net_lock); node = tipc_node_find(destaddr); @@ -1069,8 +1091,6 @@ again: if (likely(buf)) { res = link_send_buf_fast(l_ptr, buf, &sender->max_pkt); - if (unlikely(res < 0)) - buf_discard(buf); exit: tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); @@ -1105,7 +1125,8 @@ exit: goto again; return link_send_sections_long(sender, msg_sect, - num_sect, destaddr); + num_sect, total_len, + destaddr); } tipc_node_unlock(node); } @@ -1117,7 +1138,7 @@ exit: return tipc_reject_msg(buf, TIPC_ERR_NO_NODE); if (res >= 0) return tipc_port_reject_sections(sender, hdr, msg_sect, num_sect, - TIPC_ERR_NO_NODE); + total_len, TIPC_ERR_NO_NODE); return res; } @@ -1138,12 +1159,13 @@ exit: static int link_send_sections_long(struct tipc_port *sender, struct iovec const *msg_sect, u32 num_sect, + unsigned int total_len, u32 destaddr) { struct link *l_ptr; struct tipc_node *node; struct tipc_msg *hdr = &sender->phdr; - u32 dsz = msg_data_sz(hdr); + u32 dsz = total_len; u32 max_pkt, fragm_sz, rest; struct tipc_msg fragm_hdr; struct sk_buff *buf, *buf_chain, *prev; @@ -1169,7 +1191,6 @@ again: tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(hdr)); - msg_set_link_selector(&fragm_hdr, sender->ref); msg_set_size(&fragm_hdr, max_pkt); msg_set_fragm_no(&fragm_hdr, 1); @@ -1271,28 +1292,15 @@ reject: buf_discard(buf_chain); } return tipc_port_reject_sections(sender, hdr, msg_sect, num_sect, - TIPC_ERR_NO_NODE); + total_len, TIPC_ERR_NO_NODE); } - /* Append whole chain to send queue: */ + /* Append chain of fragments to send queue & send them */ - buf = buf_chain; - l_ptr->long_msg_seq_no = mod(l_ptr->long_msg_seq_no + 1); - if (!l_ptr->next_out) - l_ptr->next_out = buf_chain; + l_ptr->long_msg_seq_no++; + link_add_chain_to_outqueue(l_ptr, buf_chain, l_ptr->long_msg_seq_no); + l_ptr->stats.sent_fragments += fragm_no; l_ptr->stats.sent_fragmented++; - while (buf) { - struct sk_buff *next = buf->next; - struct tipc_msg *msg = buf_msg(buf); - - l_ptr->stats.sent_fragments++; - msg_set_long_msgno(msg, l_ptr->long_msg_seq_no); - link_add_to_outqueue(l_ptr, buf, msg); - buf = next; - } - - /* Send it, if possible: */ - tipc_link_push_queue(l_ptr); tipc_node_unlock(node); return dsz; @@ -2407,6 +2415,8 @@ void tipc_link_recv_bundle(struct sk_buff *buf) */ static int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) { + struct sk_buff *buf_chain = NULL; + struct sk_buff *buf_chain_tail = (struct sk_buff *)&buf_chain; struct tipc_msg *inmsg = buf_msg(buf); struct tipc_msg fragm_hdr; u32 insize = msg_size(inmsg); @@ -2415,7 +2425,7 @@ static int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) u32 rest = insize; u32 pack_sz = l_ptr->max_pkt; u32 fragm_sz = pack_sz - INT_H_SIZE; - u32 fragm_no = 1; + u32 fragm_no = 0; u32 destaddr; if (msg_short(inmsg)) @@ -2427,10 +2437,6 @@ static int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, destaddr); - msg_set_link_selector(&fragm_hdr, msg_link_selector(inmsg)); - msg_set_long_msgno(&fragm_hdr, mod(l_ptr->long_msg_seq_no++)); - msg_set_fragm_no(&fragm_hdr, fragm_no); - l_ptr->stats.sent_fragmented++; /* Chop up message: */ @@ -2443,27 +2449,37 @@ static int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) } fragm = tipc_buf_acquire(fragm_sz + INT_H_SIZE); if (fragm == NULL) { - warn("Link unable to fragment message\n"); - dsz = -ENOMEM; - goto exit; + buf_discard(buf); + while (buf_chain) { + buf = buf_chain; + buf_chain = buf_chain->next; + buf_discard(buf); + } + return -ENOMEM; } msg_set_size(&fragm_hdr, fragm_sz + INT_H_SIZE); + fragm_no++; + msg_set_fragm_no(&fragm_hdr, fragm_no); skb_copy_to_linear_data(fragm, &fragm_hdr, INT_H_SIZE); skb_copy_to_linear_data_offset(fragm, INT_H_SIZE, crs, fragm_sz); - /* Send queued messages first, if any: */ + buf_chain_tail->next = fragm; + buf_chain_tail = fragm; - l_ptr->stats.sent_fragments++; - tipc_link_send_buf(l_ptr, fragm); - if (!tipc_link_is_up(l_ptr)) - return dsz; - msg_set_fragm_no(&fragm_hdr, ++fragm_no); rest -= fragm_sz; crs += fragm_sz; msg_set_type(&fragm_hdr, FRAGMENT); } -exit: buf_discard(buf); + + /* Append chain of fragments to send queue & send them */ + + l_ptr->long_msg_seq_no++; + link_add_chain_to_outqueue(l_ptr, buf_chain, l_ptr->long_msg_seq_no); + l_ptr->stats.sent_fragments += fragm_no; + l_ptr->stats.sent_fragmented++; + tipc_link_push_queue(l_ptr); + return dsz; } @@ -2471,7 +2487,7 @@ exit: * A pending message being re-assembled must store certain values * to handle subsequent fragments correctly. The following functions * help storing these values in unused, available fields in the - * pending message. This makes dynamic memory allocation unecessary. + * pending message. This makes dynamic memory allocation unnecessary. */ static void set_long_msg_seqno(struct sk_buff *buf, u32 seqno) diff --git a/net/tipc/link.h b/net/tipc/link.h index e6a30dbe1aaa..74fbecab1ea0 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -228,6 +228,7 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector); int tipc_link_send_sections_fast(struct tipc_port *sender, struct iovec const *msg_sect, const u32 num_sect, + unsigned int total_len, u32 destnode); void tipc_link_recv_bundle(struct sk_buff *buf); int tipc_link_recv_fragment(struct sk_buff **pending, diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 6d92d17e7fb5..03e57bf92c73 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -68,20 +68,6 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, } /** - * tipc_msg_calc_data_size - determine total data size for message - */ - -int tipc_msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect) -{ - int dsz = 0; - int i; - - for (i = 0; i < num_sect; i++) - dsz += msg_sect[i].iov_len; - return dsz; -} - -/** * tipc_msg_build - create message using specified header and data * * Note: Caller must not hold any locks in case copy_from_user() is interrupted! @@ -89,18 +75,13 @@ int tipc_msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect) * Returns message data size or errno */ -int tipc_msg_build(struct tipc_msg *hdr, - struct iovec const *msg_sect, u32 num_sect, +int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, + u32 num_sect, unsigned int total_len, int max_size, int usrmem, struct sk_buff **buf) { int dsz, sz, hsz, pos, res, cnt; - dsz = tipc_msg_calc_data_size(msg_sect, num_sect); - if (unlikely(dsz > TIPC_MAX_USER_MSG_SIZE)) { - *buf = NULL; - return -EINVAL; - } - + dsz = total_len; pos = hsz = msg_hdr_sz(hdr); sz = hsz + dsz; msg_set_size(hdr, sz); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index de02339fc175..8452454731fa 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -39,41 +39,24 @@ #include "bearer.h" +/* + * Constants and routines used to read and write TIPC payload message headers + * + * Note: Some items are also used with TIPC internal message headers + */ + #define TIPC_VERSION 2 /* - * TIPC user data message header format, version 2: - * - * - * 1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0 - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w0:|vers | user |hdr sz |n|d|s|-| message size | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w1:|mstyp| error |rer cnt|lsc|opt p| broadcast ack no | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w2:| link level ack no | broadcast/link level seq no | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w3:| previous node | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w4:| originating port | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w5:| destination port | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w6:| originating node | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w7:| destination node | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w8:| name type / transport sequence number | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w9:| name instance/multicast lower bound | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * wA:| multicast upper bound | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * / / - * \ options \ - * / / - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * + * Payload message users are defined in TIPC's public API: + * - TIPC_LOW_IMPORTANCE + * - TIPC_MEDIUM_IMPORTANCE + * - TIPC_HIGH_IMPORTANCE + * - TIPC_CRITICAL_IMPORTANCE + */ + +/* + * Payload message types */ #define TIPC_CONN_MSG 0 @@ -81,6 +64,9 @@ #define TIPC_NAMED_MSG 2 #define TIPC_DIRECT_MSG 3 +/* + * Message header sizes + */ #define SHORT_H_SIZE 24 /* Connected, in-cluster messages */ #define DIR_MSG_H_SIZE 32 /* Directly addressed messages */ @@ -473,40 +459,11 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) /* - TIPC internal message header format, version 2 - - 1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0 - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w0:|vers |msg usr|hdr sz |n|resrv| packet size | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w1:|m typ| sequence gap | broadcast ack no | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w2:| link level ack no/bc_gap_from | seq no / bcast_gap_to | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w3:| previous node | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w4:| next sent broadcast/fragm no | next sent pkt/ fragm msg no | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w5:| session no |rsv=0|r|berid|link prio|netpl|p| - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w6:| originating node | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w7:| destination node | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w8:| transport sequence number | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w9:| msg count / bcast tag | link tolerance | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - \ \ - / User Specific Data / - \ \ - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - - NB: CONN_MANAGER use data message format. LINK_CONFIG has own format. -*/ + * Constants and routines used to read and write TIPC internal message headers + */ /* - * Internal users + * Internal message users */ #define BCAST_PROTOCOL 5 @@ -520,7 +477,7 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) #define LINK_CONFIG 13 /* - * Connection management protocol messages + * Connection management protocol message types */ #define CONN_PROBE 0 @@ -528,12 +485,41 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) #define CONN_ACK 2 /* - * Name distributor messages + * Name distributor message types */ #define PUBLICATION 0 #define WITHDRAWAL 1 +/* + * Segmentation message types + */ + +#define FIRST_FRAGMENT 0 +#define FRAGMENT 1 +#define LAST_FRAGMENT 2 + +/* + * Link management protocol message types + */ + +#define STATE_MSG 0 +#define RESET_MSG 1 +#define ACTIVATE_MSG 2 + +/* + * Changeover tunnel message types + */ +#define DUPLICATE_MSG 0 +#define ORIGINAL_MSG 1 + +/* + * Config protocol message types + */ + +#define DSC_REQ_MSG 0 +#define DSC_RESP_MSG 1 + /* * Word 1 @@ -761,50 +747,11 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } -/* - * Segmentation message types - */ - -#define FIRST_FRAGMENT 0 -#define FRAGMENT 1 -#define LAST_FRAGMENT 2 - -/* - * Link management protocol message types - */ - -#define STATE_MSG 0 -#define RESET_MSG 1 -#define ACTIVATE_MSG 2 - -/* - * Changeover tunnel message types - */ -#define DUPLICATE_MSG 0 -#define ORIGINAL_MSG 1 - -/* - * Routing table message types - */ -#define EXT_ROUTING_TABLE 0 -#define LOCAL_ROUTING_TABLE 1 /* obsoleted */ -#define SLAVE_ROUTING_TABLE 2 -#define ROUTE_ADDITION 3 -#define ROUTE_REMOVAL 4 - -/* - * Config protocol message types - */ - -#define DSC_REQ_MSG 0 -#define DSC_RESP_MSG 1 - u32 tipc_msg_tot_importance(struct tipc_msg *m); void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); -int tipc_msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect); -int tipc_msg_build(struct tipc_msg *hdr, - struct iovec const *msg_sect, u32 num_sect, +int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, + u32 num_sect, unsigned int total_len, int max_size, int usrmem, struct sk_buff **buf); static inline void msg_set_media_addr(struct tipc_msg *m, struct tipc_media_addr *a) diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index c9fa6dfcf287..80025a1b3bfd 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -160,7 +160,7 @@ void tipc_named_withdraw(struct publication *publ) buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0); if (!buf) { - warn("Withdrawl distribution failure\n"); + warn("Withdrawal distribution failure\n"); return; } diff --git a/net/tipc/port.c b/net/tipc/port.c index 6ff78f9c7d65..c68dc956a423 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -74,7 +74,8 @@ static u32 port_peerport(struct tipc_port *p_ptr) */ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, - u32 num_sect, struct iovec const *msg_sect) + u32 num_sect, struct iovec const *msg_sect, + unsigned int total_len) { struct tipc_msg *hdr; struct sk_buff *buf; @@ -91,11 +92,14 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, hdr = &oport->phdr; msg_set_type(hdr, TIPC_MCAST_MSG); + msg_set_lookup_scope(hdr, TIPC_CLUSTER_SCOPE); + msg_set_destport(hdr, 0); + msg_set_destnode(hdr, 0); msg_set_nametype(hdr, seq->type); msg_set_namelower(hdr, seq->lower); msg_set_nameupper(hdr, seq->upper); msg_set_hdr_sz(hdr, MCAST_H_SIZE); - res = tipc_msg_build(hdr, msg_sect, num_sect, MAX_MSG_SIZE, + res = tipc_msg_build(hdr, msg_sect, num_sect, total_len, MAX_MSG_SIZE, !oport->user_port, &buf); if (unlikely(!buf)) return res; @@ -161,6 +165,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct port_list *dp) /* Deliver a copy of message to each destination port */ if (dp->count != 0) { + msg_set_destnode(msg, tipc_own_addr); if (dp->count == 1) { msg_set_destport(msg, dp->ports[0]); tipc_port_recv_msg(buf); @@ -414,12 +419,12 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, - int err) + unsigned int total_len, int err) { struct sk_buff *buf; int res; - res = tipc_msg_build(hdr, msg_sect, num_sect, MAX_MSG_SIZE, + res = tipc_msg_build(hdr, msg_sect, num_sect, total_len, MAX_MSG_SIZE, !p_ptr->user_port, &buf); if (!buf) return res; @@ -1065,6 +1070,7 @@ int tipc_connect2port(u32 ref, struct tipc_portid const *peer) msg_set_orignode(msg, tipc_own_addr); msg_set_origport(msg, p_ptr->ref); msg_set_type(msg, TIPC_CONN_MSG); + msg_set_lookup_scope(msg, 0); msg_set_hdr_sz(msg, SHORT_H_SIZE); p_ptr->probing_interval = PROBING_INTERVAL; @@ -1158,12 +1164,13 @@ int tipc_shutdown(u32 ref) */ static int tipc_port_recv_sections(struct tipc_port *sender, unsigned int num_sect, - struct iovec const *msg_sect) + struct iovec const *msg_sect, + unsigned int total_len) { struct sk_buff *buf; int res; - res = tipc_msg_build(&sender->phdr, msg_sect, num_sect, + res = tipc_msg_build(&sender->phdr, msg_sect, num_sect, total_len, MAX_MSG_SIZE, !sender->user_port, &buf); if (likely(buf)) tipc_port_recv_msg(buf); @@ -1174,7 +1181,8 @@ static int tipc_port_recv_sections(struct tipc_port *sender, unsigned int num_se * tipc_send - send message sections on connection */ -int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) +int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect, + unsigned int total_len) { struct tipc_port *p_ptr; u32 destnode; @@ -1189,9 +1197,10 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) destnode = port_peernode(p_ptr); if (likely(destnode != tipc_own_addr)) res = tipc_link_send_sections_fast(p_ptr, msg_sect, num_sect, - destnode); + total_len, destnode); else - res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect); + res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect, + total_len); if (likely(res != -ELINKCONG)) { p_ptr->congested = 0; @@ -1202,8 +1211,7 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) } if (port_unreliable(p_ptr)) { p_ptr->congested = 0; - /* Just calculate msg length and return */ - return tipc_msg_calc_data_size(msg_sect, num_sect); + return total_len; } return -ELINKCONG; } @@ -1213,7 +1221,8 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) */ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, - unsigned int num_sect, struct iovec const *msg_sect) + unsigned int num_sect, struct iovec const *msg_sect, + unsigned int total_len) { struct tipc_port *p_ptr; struct tipc_msg *msg; @@ -1240,23 +1249,23 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, if (likely(destport)) { if (likely(destnode == tipc_own_addr)) res = tipc_port_recv_sections(p_ptr, num_sect, - msg_sect); + msg_sect, total_len); else res = tipc_link_send_sections_fast(p_ptr, msg_sect, - num_sect, destnode); + num_sect, total_len, + destnode); if (likely(res != -ELINKCONG)) { if (res > 0) p_ptr->sent++; return res; } if (port_unreliable(p_ptr)) { - /* Just calculate msg length and return */ - return tipc_msg_calc_data_size(msg_sect, num_sect); + return total_len; } return -ELINKCONG; } return tipc_port_reject_sections(p_ptr, msg, msg_sect, num_sect, - TIPC_ERR_NO_NAME); + total_len, TIPC_ERR_NO_NAME); } /** @@ -1264,7 +1273,8 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, */ int tipc_send2port(u32 ref, struct tipc_portid const *dest, - unsigned int num_sect, struct iovec const *msg_sect) + unsigned int num_sect, struct iovec const *msg_sect, + unsigned int total_len) { struct tipc_port *p_ptr; struct tipc_msg *msg; @@ -1276,6 +1286,7 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, msg = &p_ptr->phdr; msg_set_type(msg, TIPC_DIRECT_MSG); + msg_set_lookup_scope(msg, 0); msg_set_orignode(msg, tipc_own_addr); msg_set_origport(msg, ref); msg_set_destnode(msg, dest->node); @@ -1283,18 +1294,18 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, msg_set_hdr_sz(msg, DIR_MSG_H_SIZE); if (dest->node == tipc_own_addr) - res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect); + res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect, + total_len); else res = tipc_link_send_sections_fast(p_ptr, msg_sect, num_sect, - dest->node); + total_len, dest->node); if (likely(res != -ELINKCONG)) { if (res > 0) p_ptr->sent++; return res; } if (port_unreliable(p_ptr)) { - /* Just calculate msg length and return */ - return tipc_msg_calc_data_size(msg_sect, num_sect); + return total_len; } return -ELINKCONG; } diff --git a/net/tipc/port.h b/net/tipc/port.h index 87b9424ae0ec..b9aa34195aec 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -205,23 +205,27 @@ int tipc_disconnect_port(struct tipc_port *tp_ptr); /* * TIPC messaging routines */ -int tipc_send(u32 portref, unsigned int num_sect, struct iovec const *msg_sect); +int tipc_send(u32 portref, unsigned int num_sect, struct iovec const *msg_sect, + unsigned int total_len); int tipc_send2name(u32 portref, struct tipc_name const *name, u32 domain, - unsigned int num_sect, struct iovec const *msg_sect); + unsigned int num_sect, struct iovec const *msg_sect, + unsigned int total_len); int tipc_send2port(u32 portref, struct tipc_portid const *dest, - unsigned int num_sect, struct iovec const *msg_sect); + unsigned int num_sect, struct iovec const *msg_sect, + unsigned int total_len); int tipc_send_buf2port(u32 portref, struct tipc_portid const *dest, struct sk_buff *buf, unsigned int dsz); int tipc_multicast(u32 portref, struct tipc_name_seq const *seq, - unsigned int section_count, struct iovec const *msg); + unsigned int section_count, struct iovec const *msg, + unsigned int total_len); int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, - int err); + unsigned int total_len, int err); struct sk_buff *tipc_port_get_ports(void); void tipc_port_recv_proto_msg(struct sk_buff *buf); void tipc_port_recv_mcast(struct sk_buff *buf, struct port_list *dp); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 29d94d53198d..338837396642 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -535,6 +535,9 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, if (unlikely((m->msg_namelen < sizeof(*dest)) || (dest->family != AF_TIPC))) return -EINVAL; + if ((total_len > TIPC_MAX_USER_MSG_SIZE) || + (m->msg_iovlen > (unsigned)INT_MAX)) + return -EMSGSIZE; if (iocb) lock_sock(sk); @@ -573,12 +576,14 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, &dest->addr.name.name, dest->addr.name.domain, m->msg_iovlen, - m->msg_iov); + m->msg_iov, + total_len); } else if (dest->addrtype == TIPC_ADDR_ID) { res = tipc_send2port(tport->ref, &dest->addr.id, m->msg_iovlen, - m->msg_iov); + m->msg_iov, + total_len); } else if (dest->addrtype == TIPC_ADDR_MCAST) { if (needs_conn) { res = -EOPNOTSUPP; @@ -590,7 +595,8 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, res = tipc_multicast(tport->ref, &dest->addr.nameseq, m->msg_iovlen, - m->msg_iov); + m->msg_iov, + total_len); } if (likely(res != -ELINKCONG)) { if (needs_conn && (res >= 0)) @@ -640,6 +646,10 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, if (unlikely(dest)) return send_msg(iocb, sock, m, total_len); + if ((total_len > TIPC_MAX_USER_MSG_SIZE) || + (m->msg_iovlen > (unsigned)INT_MAX)) + return -EMSGSIZE; + if (iocb) lock_sock(sk); @@ -652,7 +662,8 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, break; } - res = tipc_send(tport->ref, m->msg_iovlen, m->msg_iov); + res = tipc_send(tport->ref, m->msg_iovlen, m->msg_iov, + total_len); if (likely(res != -ELINKCONG)) break; if (m->msg_flags & MSG_DONTWAIT) { @@ -723,6 +734,12 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, goto exit; } + if ((total_len > (unsigned)INT_MAX) || + (m->msg_iovlen > (unsigned)INT_MAX)) { + res = -EMSGSIZE; + goto exit; + } + /* * Send each iovec entry using one or more messages * @@ -753,7 +770,7 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, bytes_to_send = curr_left; my_iov.iov_base = curr_start; my_iov.iov_len = bytes_to_send; - res = send_packet(NULL, sock, &my_msg, 0); + res = send_packet(NULL, sock, &my_msg, bytes_to_send); if (res < 0) { if (bytes_sent) res = bytes_sent; diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index aae9eae13404..6cf726863485 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -109,7 +109,7 @@ static void subscr_send_event(struct subscription *sub, sub->evt.found_upper = htohl(found_upper, sub->swap); sub->evt.port.ref = htohl(port_ref, sub->swap); sub->evt.port.node = htohl(node, sub->swap); - tipc_send(sub->server_ref, 1, &msg_sect); + tipc_send(sub->server_ref, 1, &msg_sect, msg_sect.iov_len); } /** @@ -521,7 +521,7 @@ static void subscr_named_msg_event(void *usr_handle, /* Send an ACK- to complete connection handshaking */ - tipc_send(server_port_ref, 0, NULL); + tipc_send(server_port_ref, 0, NULL, 0); /* Handle optional subscription request */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1663e1a2efdd..0722a25a3a33 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -207,7 +207,7 @@ static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned *hashp) /* * This may look like an off by one error but it is a bit more * subtle. 108 is the longest valid AF_UNIX path for a binding. - * sun_path[108] doesnt as such exist. However in kernel space + * sun_path[108] doesn't as such exist. However in kernel space * we are guaranteed that it is a valid memory location in our * kernel address buffer. */ @@ -524,6 +524,8 @@ static int unix_dgram_connect(struct socket *, struct sockaddr *, int, int); static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t); +static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, + struct msghdr *, size_t, int); static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, @@ -583,7 +585,7 @@ static const struct proto_ops unix_seqpacket_ops = { .setsockopt = sock_no_setsockopt, .getsockopt = sock_no_getsockopt, .sendmsg = unix_seqpacket_sendmsg, - .recvmsg = unix_dgram_recvmsg, + .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; @@ -1699,6 +1701,18 @@ static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock, return unix_dgram_sendmsg(kiocb, sock, msg, len); } +static int unix_seqpacket_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t size, + int flags) +{ + struct sock *sk = sock->sk; + + if (sk->sk_state != TCP_ESTABLISHED) + return -ENOTCONN; + + return unix_dgram_recvmsg(iocb, sock, msg, size, flags); +} + static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { struct unix_sock *u = unix_sk(sk); @@ -2240,7 +2254,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) struct unix_sock *u = unix_sk(s); unix_state_lock(s); - seq_printf(seq, "%p: %08X %08X %08X %04X %02X %5lu", + seq_printf(seq, "%pK: %08X %08X %08X %04X %02X %5lu", s, atomic_read(&s->sk_refcnt), 0, diff --git a/net/wanrouter/wanproc.c b/net/wanrouter/wanproc.c index 11f25c7a7a05..f346395314ba 100644 --- a/net/wanrouter/wanproc.c +++ b/net/wanrouter/wanproc.c @@ -51,7 +51,7 @@ /* * Structures for interfacing with the /proc filesystem. - * Router creates its own directory /proc/net/router with the folowing + * Router creates its own directory /proc/net/router with the following * entries: * config device configuration * status global device statistics diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 798cb4cd0702..1ad0f39fe091 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -810,7 +810,7 @@ static void handle_channel(struct wiphy *wiphy, if (r) { /* * We will disable all channels that do not match our - * recieved regulatory rule unless the hint is coming + * received regulatory rule unless the hint is coming * from a Country IE and the Country IE had no information * about a band. The IEEE 802.11 spec allows for an AP * to send only a subset of the regulatory rules allowed, @@ -839,7 +839,7 @@ static void handle_channel(struct wiphy *wiphy, request_wiphy && request_wiphy == wiphy && request_wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY) { /* - * This gaurantees the driver's requested regulatory domain + * This guarantees the driver's requested regulatory domain * will always be used as a base for further regulatory * settings */ diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 406207515b5e..f77e4e75f914 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -31,7 +31,7 @@ * x25_parse_facilities - Parse facilities from skb into the facilities structs * * @skb: sk_buff to parse - * @facilities: Regular facilites, updated as facilities are found + * @facilities: Regular facilities, updated as facilities are found * @dte_facs: ITU DTE facilities, updated as DTE facilities are found * @vc_fac_mask: mask is updated with all facilities found * diff --git a/net/x25/x25_forward.c b/net/x25/x25_forward.c index 25a810793968..c541b622ae16 100644 --- a/net/x25/x25_forward.c +++ b/net/x25/x25_forward.c @@ -31,7 +31,7 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, goto out_no_route; if ((neigh_new = x25_get_neigh(rt->dev)) == NULL) { - /* This shouldnt happen, if it occurs somehow + /* This shouldn't happen, if it occurs somehow * do something sensible */ goto out_put_route; @@ -45,7 +45,7 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, } /* Remote end sending a call request on an already - * established LCI? It shouldnt happen, just in case.. + * established LCI? It shouldn't happen, just in case.. */ read_lock_bh(&x25_forward_list_lock); list_for_each(entry, &x25_forward_list) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 15792d8b6272..9bec2e8a838c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1348,7 +1348,8 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) default: BUG(); } - xdst = dst_alloc(dst_ops, 0); + xdst = dst_alloc(dst_ops, NULL, 0, 0, 0); + memset(&xdst->u.rt6.rt6i_table, 0, sizeof(*xdst) - sizeof(struct dst_entry)); xfrm_policy_put_afinfo(afinfo); if (likely(xdst)) @@ -1406,6 +1407,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; + struct xfrm_mode *inner_mode; struct dst_entry *dst_prev = NULL; struct dst_entry *dst0 = NULL; int i = 0; @@ -1436,6 +1438,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, goto put_states; } + if (xfrm[i]->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(xfrm[i], + xfrm_af2proto(family)); + if (!inner_mode) { + err = -EAFNOSUPPORT; + dst_release(dst); + goto put_states; + } + } else + inner_mode = xfrm[i]->inner_mode; + if (!dst_prev) dst0 = dst1; else { @@ -1464,7 +1477,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst1->lastuse = now; dst1->input = dst_discard; - dst1->output = xfrm[i]->outer_mode->afinfo->output; + dst1->output = inner_mode->afinfo->output; dst1->next = dst_prev; dst_prev = dst1; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index f218385950ca..47f1b8638df9 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -532,9 +532,12 @@ int xfrm_init_replay(struct xfrm_state *x) if (replay_esn) { if (replay_esn->replay_window > - replay_esn->bmp_len * sizeof(__u32)) + replay_esn->bmp_len * sizeof(__u32) * 8) return -EINVAL; + if ((x->props.flags & XFRM_STATE_ESN) && replay_esn->replay_window == 0) + return -EINVAL; + if ((x->props.flags & XFRM_STATE_ESN) && x->replay_esn) x->repl = &xfrm_replay_esn; else diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index dd78536d40de..d70f85eb7864 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1036,15 +1036,15 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m, case AF_INET6: ipv6_addr_copy((struct in6_addr *)x->sel.daddr.a6, - (struct in6_addr *)daddr); + (const struct in6_addr *)daddr); ipv6_addr_copy((struct in6_addr *)x->sel.saddr.a6, - (struct in6_addr *)saddr); + (const struct in6_addr *)saddr); x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; ipv6_addr_copy((struct in6_addr *)x->props.saddr.a6, - (struct in6_addr *)saddr); + (const struct in6_addr *)saddr); ipv6_addr_copy((struct in6_addr *)x->id.daddr.a6, - (struct in6_addr *)daddr); + (const struct in6_addr *)daddr); break; } @@ -2092,8 +2092,8 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x, static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, struct audit_buffer *audit_buf) { - struct iphdr *iph4; - struct ipv6hdr *iph6; + const struct iphdr *iph4; + const struct ipv6hdr *iph6; switch (family) { case AF_INET: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 3d15d3e1b2c4..c658cb3bc7c3 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -124,6 +124,9 @@ static inline int verify_replay(struct xfrm_usersa_info *p, { struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; + if ((p->flags & XFRM_STATE_ESN) && !rt) + return -EINVAL; + if (!rt) return 0; @@ -894,7 +897,7 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net, u32 *f; nlh = nlmsg_put(skb, pid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0); - if (nlh == NULL) /* shouldnt really happen ... */ + if (nlh == NULL) /* shouldn't really happen ... */ return -EMSGSIZE; f = nlmsg_data(nlh); @@ -954,7 +957,7 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net, u32 *f; nlh = nlmsg_put(skb, pid, seq, XFRM_MSG_NEWSADINFO, sizeof(u32), 0); - if (nlh == NULL) /* shouldnt really happen ... */ + if (nlh == NULL) /* shouldn't really happen ... */ return -EMSGSIZE; f = nlmsg_data(nlh); @@ -1361,7 +1364,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (!xp) return err; - /* shouldnt excl be based on nlh flags?? + /* shouldn't excl be based on nlh flags?? * Aha! this is anti-netlink really i.e more pfkey derived * in netlink excl is a flag and you wouldnt need * a type XFRM_MSG_UPDPOLICY - JHS */ |