diff options
Diffstat (limited to 'net')
95 files changed, 1567 insertions, 788 deletions
diff --git a/net/802/mrp.c b/net/802/mrp.c index 1eb05d80b07b..3ed616215870 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -24,6 +24,11 @@ static unsigned int mrp_join_time __read_mostly = 200; module_param(mrp_join_time, uint, 0644); MODULE_PARM_DESC(mrp_join_time, "Join time in ms (default 200ms)"); + +static unsigned int mrp_periodic_time __read_mostly = 1000; +module_param(mrp_periodic_time, uint, 0644); +MODULE_PARM_DESC(mrp_periodic_time, "Periodic time in ms (default 1s)"); + MODULE_LICENSE("GPL"); static const u8 @@ -595,6 +600,24 @@ static void mrp_join_timer(unsigned long data) mrp_join_timer_arm(app); } +static void mrp_periodic_timer_arm(struct mrp_applicant *app) +{ + mod_timer(&app->periodic_timer, + jiffies + msecs_to_jiffies(mrp_periodic_time)); +} + +static void mrp_periodic_timer(unsigned long data) +{ + struct mrp_applicant *app = (struct mrp_applicant *)data; + + spin_lock(&app->lock); + mrp_mad_event(app, MRP_EVENT_PERIODIC); + mrp_pdu_queue(app); + spin_unlock(&app->lock); + + mrp_periodic_timer_arm(app); +} + static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) { __be16 endmark; @@ -845,6 +868,9 @@ int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); setup_timer(&app->join_timer, mrp_join_timer, (unsigned long)app); mrp_join_timer_arm(app); + setup_timer(&app->periodic_timer, mrp_periodic_timer, + (unsigned long)app); + mrp_periodic_timer_arm(app); return 0; err3: @@ -870,6 +896,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) * all pending messages before the applicant is gone. */ del_timer_sync(&app->join_timer); + del_timer_sync(&app->periodic_timer); spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); diff --git a/net/9p/client.c b/net/9p/client.c index ba93bdab2701..ee8fd6bd4035 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -987,6 +987,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) { int err; struct p9_client *clnt; + char *client_id; err = 0; clnt = kmalloc(sizeof(struct p9_client), GFP_KERNEL); @@ -995,6 +996,10 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) clnt->trans_mod = NULL; clnt->trans = NULL; + + client_id = utsname()->nodename; + memcpy(clnt->name, client_id, strlen(client_id) + 1); + spin_lock_init(&clnt->lock); INIT_LIST_HEAD(&clnt->fidlist); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index e1c26b101830..990afab2be1b 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -577,6 +577,10 @@ static int p9_virtio_probe(struct virtio_device *vdev) mutex_lock(&virtio_9p_lock); list_add_tail(&chan->chan_list, &virtio_chan_list); mutex_unlock(&virtio_9p_lock); + + /* Let udev rules use the new mount_tag attribute. */ + kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE); + return 0; out_free_tag: @@ -654,6 +658,7 @@ static void p9_virtio_remove(struct virtio_device *vdev) list_del(&chan->chan_list); mutex_unlock(&virtio_9p_lock); sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); + kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE); kfree(chan->tag); kfree(chan->vc_wq); kfree(chan); diff --git a/net/Kconfig b/net/Kconfig index ee0213667272..b50dacc072f0 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -228,7 +228,7 @@ config RPS config RFS_ACCEL boolean - depends on RPS && GENERIC_HARDIRQS + depends on RPS select CPU_RMAP default y diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 4493913f0d5c..813db4e64602 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -168,6 +168,7 @@ static int batadv_interface_tx(struct sk_buff *skb, case ETH_P_8021Q: vhdr = (struct vlan_ethhdr *)skb->data; vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + vid |= BATADV_VLAN_HAS_TAG; if (vhdr->h_vlan_encapsulated_proto != ethertype) break; @@ -331,6 +332,7 @@ void batadv_interface_rx(struct net_device *soft_iface, case ETH_P_8021Q: vhdr = (struct vlan_ethhdr *)skb->data; vid = ntohs(vhdr->h_vlan_TCI) & VLAN_VID_MASK; + vid |= BATADV_VLAN_HAS_TAG; if (vhdr->h_vlan_encapsulated_proto != ethertype) break; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 634debab4d54..fb7356fcfe51 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1146,7 +1146,11 @@ int hci_dev_open(__u16 dev) goto done; } - if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) { + /* Check for rfkill but allow the HCI setup stage to proceed + * (which in itself doesn't cause any RF activity). + */ + if (test_bit(HCI_RFKILLED, &hdev->dev_flags) && + !test_bit(HCI_SETUP, &hdev->dev_flags)) { ret = -ERFKILL; goto done; } @@ -1566,10 +1570,13 @@ static int hci_rfkill_set_block(void *data, bool blocked) BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); - if (!blocked) - return 0; - - hci_dev_do_close(hdev); + if (blocked) { + set_bit(HCI_RFKILLED, &hdev->dev_flags); + if (!test_bit(HCI_SETUP, &hdev->dev_flags)) + hci_dev_do_close(hdev); + } else { + clear_bit(HCI_RFKILLED, &hdev->dev_flags); + } return 0; } @@ -1591,9 +1598,13 @@ static void hci_power_on(struct work_struct *work) return; } - if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + if (test_bit(HCI_RFKILLED, &hdev->dev_flags)) { + clear_bit(HCI_AUTO_OFF, &hdev->dev_flags); + hci_dev_do_close(hdev); + } else if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { queue_delayed_work(hdev->req_workqueue, &hdev->power_off, HCI_AUTO_OFF_TIMEOUT); + } if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) mgmt_index_added(hdev); @@ -2209,6 +2220,9 @@ int hci_register_dev(struct hci_dev *hdev) } } + if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) + set_bit(HCI_RFKILLED, &hdev->dev_flags); + set_bit(HCI_SETUP, &hdev->dev_flags); if (hdev->dev_type != HCI_AMP) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 94aab73f89d4..8db3e89fae35 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3557,7 +3557,11 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) cp.handle = cpu_to_le16(conn->handle); if (ltk->authenticated) - conn->sec_level = BT_SECURITY_HIGH; + conn->pending_sec_level = BT_SECURITY_HIGH; + else + conn->pending_sec_level = BT_SECURITY_MEDIUM; + + conn->enc_key_size = ltk->enc_size; hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b3bb7bca8e60..63fa11109a1c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3755,6 +3755,13 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, sk = chan->sk; + /* For certain devices (ex: HID mouse), support for authentication, + * pairing and bonding is optional. For such devices, inorder to avoid + * the ACL alive for too long after L2CAP disconnection, reset the ACL + * disc_timeout back to HCI_DISCONN_TIMEOUT during L2CAP connect. + */ + conn->hcon->disc_timeout = HCI_DISCONN_TIMEOUT; + bacpy(&bt_sk(sk)->src, conn->src); bacpy(&bt_sk(sk)->dst, conn->dst); chan->psm = psm; diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 6d126faf145f..84fcf9fff3ea 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -569,7 +569,6 @@ static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb) static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) { struct rfcomm_dev *dev = dlc->owner; - struct tty_struct *tty; if (!dev) return; @@ -581,38 +580,8 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) DPM_ORDER_DEV_AFTER_PARENT); wake_up_interruptible(&dev->port.open_wait); - } else if (dlc->state == BT_CLOSED) { - tty = tty_port_tty_get(&dev->port); - if (!tty) { - if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) { - /* Drop DLC lock here to avoid deadlock - * 1. rfcomm_dev_get will take rfcomm_dev_lock - * but in rfcomm_dev_add there's lock order: - * rfcomm_dev_lock -> dlc lock - * 2. tty_port_put will deadlock if it's - * the last reference - * - * FIXME: when we release the lock anything - * could happen to dev, even its destruction - */ - rfcomm_dlc_unlock(dlc); - if (rfcomm_dev_get(dev->id) == NULL) { - rfcomm_dlc_lock(dlc); - return; - } - - if (!test_and_set_bit(RFCOMM_TTY_RELEASED, - &dev->flags)) - tty_port_put(&dev->port); - - tty_port_put(&dev->port); - rfcomm_dlc_lock(dlc); - } - } else { - tty_hangup(tty); - tty_kref_put(tty); - } - } + } else if (dlc->state == BT_CLOSED) + tty_port_tty_hangup(&dev->port, false); } static void rfcomm_dev_modem_status(struct rfcomm_dlc *dlc, u8 v24_sig) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index b9259efa636e..e74ddc1c29a8 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -207,7 +207,7 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask) { int err = 0; - struct net_bridge_port *port = br_port_get_rcu(dev); + struct net_bridge_port *port = br_port_get_rtnl(dev); /* not a bridge port and */ if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN)) @@ -451,7 +451,7 @@ static size_t br_get_link_af_size(const struct net_device *dev) struct net_port_vlans *pv; if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rcu(dev)); + pv = nbp_get_vlan_info(br_port_get_rtnl(dev)); else if (dev->priv_flags & IFF_EBRIDGE) pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); else diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 598cb0b333c6..efb57d911569 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -202,13 +202,10 @@ struct net_bridge_port static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev) { - struct net_bridge_port *port = - rcu_dereference_rtnl(dev->rx_handler_data); - - return br_port_exists(dev) ? port : NULL; + return rcu_dereference(dev->rx_handler_data); } -static inline struct net_bridge_port *br_port_get_rtnl(struct net_device *dev) +static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device *dev) { return br_port_exists(dev) ? rtnl_dereference(dev->rx_handler_data) : NULL; @@ -746,6 +743,7 @@ 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 void __br_set_forward_delay(struct net_bridge *br, unsigned long t); 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); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 1c0a50f13229..3c86f0538cbb 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -209,7 +209,7 @@ static void br_record_config_information(struct net_bridge_port *p, p->designated_age = jiffies - bpdu->message_age; mod_timer(&p->message_age_timer, jiffies - + (p->br->max_age - bpdu->message_age)); + + (bpdu->max_age - bpdu->message_age)); } /* called under bridge lock */ @@ -544,18 +544,27 @@ int br_set_max_age(struct net_bridge *br, unsigned long val) } +void __br_set_forward_delay(struct net_bridge *br, unsigned long t) +{ + br->bridge_forward_delay = t; + if (br_is_root_bridge(br)) + br->forward_delay = br->bridge_forward_delay; +} + int br_set_forward_delay(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); + int err = -ERANGE; + spin_lock_bh(&br->lock); if (br->stp_enabled != BR_NO_STP && (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY)) - return -ERANGE; + goto unlock; - spin_lock_bh(&br->lock); - br->bridge_forward_delay = t; - if (br_is_root_bridge(br)) - br->forward_delay = br->bridge_forward_delay; + __br_set_forward_delay(br, t); + err = 0; + +unlock: spin_unlock_bh(&br->lock); - return 0; + return err; } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index d45e760141bb..108084a04671 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -129,6 +129,14 @@ static void br_stp_start(struct net_bridge *br) char *envp[] = { NULL }; r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + + spin_lock_bh(&br->lock); + + if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY) + __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY); + else if (br->bridge_forward_delay < BR_MAX_FORWARD_DELAY) + __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); + if (r == 0) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); @@ -137,10 +145,10 @@ static void br_stp_start(struct net_bridge *br) br_debug(br, "using kernel STP\n"); /* To start timers on any ports left in blocking */ - spin_lock_bh(&br->lock); br_port_state_selection(br); - spin_unlock_bh(&br->lock); } + + spin_unlock_bh(&br->lock); } static void br_stp_stop(struct net_bridge *br) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3be308e14302..4a5df7b1cc9f 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -290,7 +290,7 @@ int ceph_msgr_init(void) if (ceph_msgr_slab_init()) return -ENOMEM; - ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0); + ceph_msgr_wq = alloc_workqueue("ceph-msgr", 0, 0); if (ceph_msgr_wq) return 0; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index dd47889adc4a..2b4b32aaa893 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -503,7 +503,9 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req, struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, opcode); size_t payload_len = 0; - BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE); + BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && + opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_ZERO && + opcode != CEPH_OSD_OP_TRUNCATE); op->extent.offset = offset; op->extent.length = length; @@ -631,6 +633,9 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_WRITE: + case CEPH_OSD_OP_ZERO: + case CEPH_OSD_OP_DELETE: + case CEPH_OSD_OP_TRUNCATE: if (src->op == CEPH_OSD_OP_WRITE) request_data_len = src->extent.length; dst->extent.offset = cpu_to_le64(src->extent.offset); @@ -715,7 +720,9 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, u64 object_base; int r; - BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE); + BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && + opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_ZERO && + opcode != CEPH_OSD_OP_TRUNCATE); req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool, GFP_NOFS); @@ -1488,14 +1495,14 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, dout("handle_reply %p tid %llu req %p result %d\n", msg, tid, req, result); - ceph_decode_need(&p, end, 4, bad); + ceph_decode_need(&p, end, 4, bad_put); numops = ceph_decode_32(&p); if (numops > CEPH_OSD_MAX_OP) goto bad_put; if (numops != req->r_num_ops) goto bad_put; payload_len = 0; - ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad); + ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad_put); for (i = 0; i < numops; i++) { struct ceph_osd_op *op = p; int len; @@ -1513,7 +1520,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, goto bad_put; } - ceph_decode_need(&p, end, 4 + numops * 4, bad); + ceph_decode_need(&p, end, 4 + numops * 4, bad_put); retry_attempt = ceph_decode_32(&p); for (i = 0; i < numops; i++) req->r_reply_op_result[i] = ceph_decode_32(&p); @@ -1786,6 +1793,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) nr_maps--; } + if (!osdc->osdmap) + goto bad; done: downgrade_write(&osdc->map_sem); ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch); @@ -2129,6 +2138,8 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, dout("osdc_start_request failed map, " " will retry %lld\n", req->r_tid); rc = 0; + } else { + __unregister_request(osdc, req); } goto out_unlock; } @@ -2205,6 +2216,17 @@ void ceph_osdc_sync(struct ceph_osd_client *osdc) EXPORT_SYMBOL(ceph_osdc_sync); /* + * Call all pending notify callbacks - for use after a watch is + * unregistered, to make sure no more callbacks for it will be invoked + */ +extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc) +{ + flush_workqueue(osdc->notify_wq); +} +EXPORT_SYMBOL(ceph_osdc_flush_notifies); + + +/* * init, shutdown */ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) @@ -2253,12 +2275,10 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) if (err < 0) goto out_msgpool; + err = -ENOMEM; osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify"); - if (IS_ERR(osdc->notify_wq)) { - err = PTR_ERR(osdc->notify_wq); - osdc->notify_wq = NULL; + if (!osdc->notify_wq) goto out_msgpool; - } return 0; out_msgpool: diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 603ddd92db19..dbd9a4792427 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1129,7 +1129,7 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, /* pg_temp? */ pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num, - pool->pgp_num_mask); + pool->pg_num_mask); pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); if (pg) { *num = pg->len; diff --git a/net/core/dev.c b/net/core/dev.c index 5c713f2239cc..65f829cfd928 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5247,10 +5247,12 @@ static int dev_new_index(struct net *net) /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); +static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); + dev_net(dev)->dev_unreg_count++; } static void rollback_registered_many(struct list_head *head) @@ -5918,6 +5920,12 @@ void netdev_run_todo(void) if (dev->destructor) dev->destructor(dev); + /* Report a network device has been unregistered */ + rtnl_lock(); + dev_net(dev)->dev_unreg_count--; + __rtnl_unlock(); + wake_up(&netdev_unregistering_wq); + /* Free network device */ kobject_put(&dev->dev.kobj); } @@ -6603,6 +6611,34 @@ static void __net_exit default_device_exit(struct net *net) rtnl_unlock(); } +static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) +{ + /* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace in net_list. + */ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network @@ -6614,7 +6650,18 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) struct net *net; LIST_HEAD(dev_kill_list); - rtnl_lock(); + /* To prevent network device cleanup code from dereferencing + * loopback devices or network devices that have been freed + * wait here for all pending unregistrations to complete, + * before unregistring the loopback device and allowing the + * network namespace be freed. + * + * The netdev todo list containing all network devices + * unregistrations that happen in default_device_exit_batch + * will run in the rtnl_unlock() at the end of + * default_device_exit_batch. + */ + rtnl_lock_unregistering(net_list); list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0ff42f029ace..8d7d0dd72db2 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -154,8 +154,8 @@ ipv6: if (poff >= 0) { __be32 *ports, _ports; - nhoff += poff; - ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports); + ports = skb_header_pointer(skb, nhoff + poff, + sizeof(_ports), &_ports); if (ports) flow->ports = *ports; } @@ -352,7 +352,7 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) if (queue_index != new_index && sk && rcu_access_pointer(sk->sk_dst_cache)) - sk_tx_queue_set(sk, queue_index); + sk_tx_queue_set(sk, new_index); queue_index = new_index; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 3f40ea9de814..d954b56b4e47 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1196,6 +1196,13 @@ static void remove_queue_kobjects(struct net_device *net) #endif } +static bool net_current_may_mount(void) +{ + struct net *net = current->nsproxy->net_ns; + + return ns_capable(net->user_ns, CAP_SYS_ADMIN); +} + static void *net_grab_current_ns(void) { struct net *ns = current->nsproxy->net_ns; @@ -1218,6 +1225,7 @@ static const void *net_netlink_ns(struct sock *sk) struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, + .current_may_mount = net_current_may_mount, .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index f97652036754..81d3a9a08453 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -651,7 +651,7 @@ static int netns_install(struct nsproxy *nsproxy, void *ns) struct net *net = ns; if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || - !nsown_capable(CAP_SYS_ADMIN)) + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return -EPERM; put_net(nsproxy->net_ns); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2c637e9a0b27..fc75c9e461b8 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -550,7 +550,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo return; proto = ntohs(eth_hdr(skb)->h_proto); - if (proto == ETH_P_IP) { + if (proto == ETH_P_ARP) { struct arphdr *arp; unsigned char *arp_ptr; /* No arp on this interface */ @@ -1284,15 +1284,14 @@ EXPORT_SYMBOL_GPL(__netpoll_free_async); void netpoll_cleanup(struct netpoll *np) { - if (!np->dev) - return; - rtnl_lock(); + if (!np->dev) + goto out; __netpoll_cleanup(np); - rtnl_unlock(); - dev_put(np->dev); np->dev = NULL; +out: + rtnl_unlock(); } EXPORT_SYMBOL(netpoll_cleanup); diff --git a/net/core/scm.c b/net/core/scm.c index b4da80b1cc07..b442e7e25e60 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -56,9 +56,9 @@ static __inline__ int scm_check_creds(struct ucred *creds) if ((creds->pid == task_tgid_vnr(current) || ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) && ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || - uid_eq(uid, cred->suid)) || nsown_capable(CAP_SETUID)) && + uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) && ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || - gid_eq(gid, cred->sgid)) || nsown_capable(CAP_SETGID))) { + gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) { return 0; } return -EPERM; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 6a2f13cee86a..3f1ec1586ae1 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -10,11 +10,24 @@ #include <net/secure_seq.h> -static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; +#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) -void net_secret_init(void) +static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; + +static void net_secret_init(void) { - get_random_bytes(net_secret, sizeof(net_secret)); + u32 tmp; + int i; + + if (likely(net_secret[0])) + return; + + for (i = NET_SECRET_SIZE; i > 0;) { + do { + get_random_bytes(&tmp, sizeof(tmp)); + } while (!tmp); + cmpxchg(&net_secret[--i], 0, tmp); + } } #ifdef CONFIG_INET @@ -42,6 +55,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, u32 hash[MD5_DIGEST_WORDS]; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + (__force u32)daddr[i]; @@ -63,6 +77,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, u32 hash[MD5_DIGEST_WORDS]; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + (__force u32) daddr[i]; @@ -82,6 +97,7 @@ __u32 secure_ip_id(__be32 daddr) { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force __u32) daddr; hash[1] = net_secret[13]; hash[2] = net_secret[14]; @@ -96,6 +112,7 @@ __u32 secure_ipv6_id(const __be32 daddr[4]) { __u32 hash[4]; + net_secret_init(); memcpy(hash, daddr, 16); md5_transform(hash, net_secret); @@ -107,6 +124,7 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = ((__force u16)sport << 16) + (__force u16)dport; @@ -121,6 +139,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = (__force u32)dport ^ net_secret[14]; @@ -140,6 +159,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, u32 hash[MD5_DIGEST_WORDS]; u64 seq; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = ((__force u16)sport << 16) + (__force u16)dport; @@ -164,6 +184,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, u64 seq; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + daddr[i]; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c61f9c02fdb..6cf9f7782ad4 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -135,6 +135,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (dst) dst->ops->redirect(dst, sk, skb); + goto out; } if (type == ICMPV6_PKT_TOOBIG) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 7a1874b7b8fd..cfeb85cff4f0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -263,10 +263,8 @@ void build_ehash_secret(void) get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) { + if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); - net_secret_init(); - } } EXPORT_SYMBOL(build_ehash_secret); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d6c0e64ec97f..7defdc9ba167 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(pip, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -736,7 +736,7 @@ static void igmp_gq_timer_expire(unsigned long data) in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); - __in_dev_put(in_dev); + in_dev_put(in_dev); } static void igmp_ifc_timer_expire(unsigned long data) @@ -749,7 +749,7 @@ static void igmp_ifc_timer_expire(unsigned long data) igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } - __in_dev_put(in_dev); + in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 000e3d239d64..33d5537881ed 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -32,8 +32,8 @@ * At the moment of writing this notes identifier of IP packets is generated * to be unpredictable using this code only for packets subjected * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size uses a constant ID and do not use this code (see - * ip_select_ident() in include/net/ip.h). + * PMTU in size when local fragmentation is disabled use a constant ID and do + * not use this code (see ip_select_ident() in include/net/ip.h). * * Route cache entries hold references to our nodes. * New cache entries get references via lookup by destination IP address in diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9ee17e3d11c3..a04d872c54f9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, 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); + ip_select_ident(skb, &rt->dst, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -386,7 +386,7 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(iph, &rt->dst, sk, + ip_select_ident_more(skb, &rt->dst, sk, (skb_shinfo(skb)->gso_segs ?: 1) - 1); skb->priority = sk->sk_priority; @@ -1316,7 +1316,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, else ttl = ip_select_ttl(inet, &rt->dst); - iph = (struct iphdr *)skb->data; + iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = inet->tos; @@ -1324,7 +1324,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, &rt->dst, sk); if (opt) { iph->ihl += opt->optlen>>2; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index ac9fabe0300f..63a6d6d6b875 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -623,6 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_count = 0; } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) @@ -641,18 +642,17 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len; - if (max_headroom > dev->needed_headroom) { + if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; - if (skb_cow_head(skb, dev->needed_headroom)) { - dev->stats.tx_dropped++; - dev_kfree_skb(skb); - return; - } + + if (skb_cow_head(skb, dev->needed_headroom)) { + dev->stats.tx_dropped++; + dev_kfree_skb(skb); + return; } err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol, - ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df, - !net_eq(tunnel->net, dev_net(dev))); + tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return; @@ -853,8 +853,10 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - if (!IS_ERR(itn->fb_tunnel_dev)) + if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); + } rtnl_unlock(); return PTR_RET(itn->fb_tunnel_dev); @@ -884,8 +886,6 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head, if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); } - if (itn->fb_tunnel_dev) - unregister_netdevice_queue(itn->fb_tunnel_dev, head); } void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index d6c856b17fd4..c31e3ad98ef2 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -61,7 +61,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, memset(IPCB(skb), 0, sizeof(*IPCB(skb))); /* Push down and install the IP header. */ - __skb_push(skb, sizeof(struct iphdr)); + skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9ae54b09254f..62212c772a4b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1658,7 +1658,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(iph, skb_dst(skb), NULL); + ip_select_ident(skb, skb_dst(skb), NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 67e17dcda65e..b6346bf2fde3 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -267,7 +267,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) if (th == NULL) return NF_DROP; - synproxy_parse_options(skb, par->thoff, th, &opts); + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ @@ -350,7 +351,8 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum, /* fall through */ case TCP_CONNTRACK_SYN_SENT: - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { @@ -373,7 +375,9 @@ static unsigned int ipv4_synproxy_hook(unsigned int hooknum, if (!th->syn || !th->ack) break; - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->tsoff = opts.tsval - synproxy->its; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a86c7ae71881..193db03540ad 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -218,8 +218,10 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_sk_update_pmtu(skb, sk, info); - else if (type == ICMP_REDIRECT) + else if (type == ICMP_REDIRECT) { ipv4_sk_redirect(skb, sk); + return; + } /* Report error on raw socket, if: 1. User requested ip_recverr. @@ -387,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1969e16d936d..25a89eaa669d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3162,16 +3162,14 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) /* If reordering is high then always grow cwnd whenever data is * delivered regardless of its ordering. Otherwise stay conservative - * and only grow cwnd on in-order delivery in Open state, and retain - * cwnd in Disordered state (RFC5681). A stretched ACK with + * and only grow cwnd on in-order delivery (RFC5681). A stretched ACK w/ * new SACK or ECE mark may first advance cwnd here and later reduce * cwnd in tcp_fastretrans_alert() based on more states. */ if (tcp_sk(sk)->reordering > sysctl_tcp_reordering) return flag & FLAG_FORWARD_PROGRESS; - return inet_csk(sk)->icsk_ca_state == TCP_CA_Open && - flag & FLAG_DATA_ACKED; + return flag & FLAG_DATA_ACKED; } /* Check that window update is acceptable. @@ -4141,6 +4139,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { __skb_queue_after(&tp->out_of_order_queue, skb1, skb); } else { + tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); skb = NULL; } @@ -4216,8 +4215,10 @@ add_sack: if (tcp_is_sack(tp)) tcp_sack_new_ofo_skb(sk, seq, end_seq); end: - if (skb) + if (skb) { + tcp_grow_window(sk, skb); skb_set_owner_r(skb, sk); + } } static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen, diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 8a57d79b0b16..559d4ae6ebf4 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -87,8 +87,8 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) if (!cg_proto) return -EINVAL; - if (val > RESOURCE_MAX) - val = RESOURCE_MAX; + if (val > RES_COUNTER_MAX) + val = RES_COUNTER_MAX; tcp = tcp_from_cgproto(cg_proto); @@ -101,9 +101,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT, net->ipv4.sysctl_tcp_mem[i]); - if (val == RESOURCE_MAX) + if (val == RES_COUNTER_MAX) clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); - else if (val != RESOURCE_MAX) { + else if (val != RES_COUNTER_MAX) { /* * The active bit needs to be written after the static_key * update. This is what guarantees that the socket activation @@ -187,7 +187,7 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) switch (cft->private) { case RES_LIMIT: - val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX); + val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX); break; case RES_USAGE: val = tcp_read_usage(memcg); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4a22f3e715df..52f3c6b971d2 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -502,7 +502,9 @@ reset: * ACKs, wait for troubles. */ if (crtt > tp->srtt) { - inet_csk(sk)->icsk_rto = crtt + max(crtt >> 2, tcp_rto_min(sk)); + /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ + crtt >>= 3; + inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from * 3WHS. This is most likely due to retransmission, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7c83cb8bf137..e6bb8256e59f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -895,8 +895,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_orphan(skb); skb->sk = sk; - skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? - tcp_wfree : sock_wfree; + skb->destructor = tcp_wfree; atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ @@ -1840,7 +1839,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; - tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1869,13 +1867,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } - /* TSQ : sk_wmem_alloc accounts skb truesize, - * including skb overhead. But thats OK. + /* TCP Small Queues : + * Control number of packets in qdisc/devices to two packets / or ~1 ms. + * This allows for : + * - better RTT estimation and ACK scheduling + * - faster recovery + * - high rates */ - if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + limit = max(skb->truesize, sk->sk_pacing_rate >> 10); + + if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); break; } + limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 74d2c95db57f..0ca44df51ee9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -658,7 +658,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) break; case ICMP_REDIRECT: ipv4_sk_redirect(skb, sk); - break; + goto out; } /* diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index eb1dd4d643f2..b5663c37f089 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -117,7 +117,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(top_iph, dst->child, NULL); + ip_select_ident(skb, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d6ff12617f36..cd3fb301da38 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1499,6 +1499,33 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, return false; } +/* Compares an address/prefix_len with addresses on device @dev. + * If one is found it returns true. + */ +bool ipv6_chk_custom_prefix(const struct in6_addr *addr, + const unsigned int prefix_len, struct net_device *dev) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + bool ret = false; + + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); + if (ret) + break; + } + read_unlock_bh(&idev->lock); + } + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(ipv6_chk_custom_prefix); + int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { struct inet6_dev *idev; @@ -2193,43 +2220,21 @@ ok: else stored_lft = 0; if (!update_lft && !create && stored_lft) { - if (valid_lft > MIN_VALID_LIFETIME || - valid_lft > stored_lft) - update_lft = 1; - else if (stored_lft <= MIN_VALID_LIFETIME) { - /* valid_lft <= stored_lft is always true */ - /* - * RFC 4862 Section 5.5.3e: - * "Note that the preferred lifetime of - * the corresponding address is always - * reset to the Preferred Lifetime in - * the received Prefix Information - * option, regardless of whether the - * valid lifetime is also reset or - * ignored." - * - * So if the preferred lifetime in - * this advertisement is different - * than what we have stored, but the - * valid lifetime is invalid, just - * reset prefered_lft. - * - * We must set the valid lifetime - * to the stored lifetime since we'll - * be updating the timestamp below, - * else we'll set it back to the - * minimum. - */ - if (prefered_lft != ifp->prefered_lft) { - valid_lft = stored_lft; - update_lft = 1; - } - } else { - valid_lft = MIN_VALID_LIFETIME; - if (valid_lft < prefered_lft) - prefered_lft = valid_lft; - update_lft = 1; - } + const u32 minimum_lft = min( + stored_lft, (u32)MIN_VALID_LIFETIME); + valid_lft = max(valid_lft, minimum_lft); + + /* RFC4862 Section 5.5.3e: + * "Note that the preferred lifetime of the + * corresponding address is always reset to + * the Preferred Lifetime in the received + * Prefix Information option, regardless of + * whether the valid lifetime is also reset or + * ignored." + * + * So we should always update prefered_lft here. + */ + update_lft = 1; } if (update_lft) { diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 136fe55c1a47..7c96100b021e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -915,6 +915,9 @@ static int __init inet6_init(void) err = ip6_route_init(); if (err) goto ip6_route_fail; + err = ndisc_late_init(); + if (err) + goto ndisc_late_fail; err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; @@ -981,6 +984,8 @@ ipv6_exthdrs_fail: addrconf_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: + ndisc_late_cleanup(); +ndisc_late_fail: ip6_route_cleanup(); ip6_route_fail: #ifdef CONFIG_PROC_FS @@ -1043,6 +1048,7 @@ static void __exit inet6_exit(void) ipv6_exthdrs_exit(); addrconf_cleanup(); ip6_flowlabel_cleanup(); + ndisc_late_cleanup(); ip6_route_cleanup(); #ifdef CONFIG_PROC_FS diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 07a7d65a7cb6..8d67900aa003 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -162,12 +162,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) off += optlen; len -= optlen; } - /* This case will not be caught by above check since its padding - * length is smaller than 7: - * 1 byte NH + 1 byte Length + 6 bytes Padding - */ - if ((padlen == 6) && ((off - skb_network_header_len(skb)) == 8)) - goto bad; if (len == 0) return true; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index a6c58ce43d34..e27591635f92 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -138,8 +138,8 @@ static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg return false; suppress_route: - ip6_rt_put(rt); - return true; + ip6_rt_put(rt); + return true; } static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 73db48eba1c4..5bec666aba61 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -825,9 +825,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, replace_required); - if (IS_ERR(fn)) { err = PTR_ERR(fn); + fn = NULL; goto out; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 6b26e9feafb9..7bb5446b9d73 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -618,7 +618,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, struct ip6_tnl *tunnel = netdev_priv(dev); struct net_device *tdev; /* Device to other host */ struct ipv6hdr *ipv6h; /* Our new IP header */ - unsigned int max_headroom; /* The extra header space needed */ + unsigned int max_headroom = 0; /* The extra header space needed */ int gre_hlen; struct ipv6_tel_txoption opt; int mtu; @@ -693,7 +693,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); - max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; + max_headroom += LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3a692d529163..a54c45ce4a48 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1015,6 +1015,8 @@ static inline int ip6_ufo_append_data(struct sock *sk, * udp datagram */ if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) { + struct frag_hdr fhdr; + skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); @@ -1036,12 +1038,6 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - } - - err = skb_append_datato_frags(sk,skb, getfrag, from, - (length - transhdrlen)); - if (!err) { - struct frag_hdr fhdr; /* Specify the length of each IPv6 datagram fragment. * It has to be a multiple of 8. @@ -1052,15 +1048,10 @@ static inline int ip6_ufo_append_data(struct sock *sk, ipv6_select_ident(&fhdr, rt); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); - - return 0; } - /* There is not enough support do UPD LSO, - * so follow normal path - */ - kfree_skb(skb); - return err; + return skb_append_datato_frags(sk, skb, getfrag, from, + (length - transhdrlen)); } static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, @@ -1227,27 +1218,27 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * --yoshfuji */ - cork->length += length; - if (length > mtu) { - int proto = sk->sk_protocol; - if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ - ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); - return -EMSGSIZE; - } - - if (proto == IPPROTO_UDP && - (rt->dst.dev->features & NETIF_F_UFO)) { + if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_RAW)) { + ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); + return -EMSGSIZE; + } - err = ip6_ufo_append_data(sk, getfrag, from, length, - hh_len, fragheaderlen, - transhdrlen, mtu, flags, rt); - if (err) - goto error; - return 0; - } + skb = skb_peek_tail(&sk->sk_write_queue); + cork->length += length; + if (((length > mtu) || + (skb && skb_is_gso(skb))) && + (sk->sk_protocol == IPPROTO_UDP) && + (rt->dst.dev->features & NETIF_F_UFO)) { + err = ip6_ufo_append_data(sk, getfrag, from, length, + hh_len, fragheaderlen, + transhdrlen, mtu, flags, rt); + if (err) + goto error; + return 0; } - if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) + if (!skb) goto alloc_new_skb; while (length > 0) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 61355f7f4da5..a791552e0422 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1656,9 +1656,9 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), - &parm->raddr) || - nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), &parm->laddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || @@ -1731,8 +1731,6 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) } } - t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, &list); unregister_netdevice_many(&list); } @@ -1752,6 +1750,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 096cd67b737c..d18f9f903db6 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2034,7 +2034,7 @@ static void mld_dad_timer_expire(unsigned long data) if (idev->mc_dad_count) mld_dad_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, @@ -2379,7 +2379,7 @@ static void mld_gq_timer_expire(unsigned long data) idev->mc_gq_running = 0; mld_send_report(idev, NULL); - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_timer_expire(unsigned long data) @@ -2392,7 +2392,7 @@ static void mld_ifc_timer_expire(unsigned long data) if (idev->mc_ifc_count) mld_ifc_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_event(struct inet6_dev *idev) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 12179457b2cd..f8a55ff1971b 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1727,24 +1727,28 @@ int __init ndisc_init(void) if (err) goto out_unregister_pernet; #endif - err = register_netdevice_notifier(&ndisc_netdev_notifier); - if (err) - goto out_unregister_sysctl; out: return err; -out_unregister_sysctl: #ifdef CONFIG_SYSCTL - neigh_sysctl_unregister(&nd_tbl.parms); out_unregister_pernet: -#endif unregister_pernet_subsys(&ndisc_net_ops); goto out; +#endif } -void ndisc_cleanup(void) +int __init ndisc_late_init(void) +{ + return register_netdevice_notifier(&ndisc_netdev_notifier); +} + +void ndisc_late_cleanup(void) { unregister_netdevice_notifier(&ndisc_netdev_notifier); +} + +void ndisc_cleanup(void) +{ #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 19cfea8dbcaa..2748b042da72 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -282,7 +282,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) if (th == NULL) return NF_DROP; - synproxy_parse_options(skb, par->thoff, th, &opts); + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ @@ -372,7 +373,8 @@ static unsigned int ipv6_synproxy_hook(unsigned int hooknum, /* fall through */ case TCP_CONNTRACK_SYN_SENT: - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { @@ -395,7 +397,9 @@ static unsigned int ipv6_synproxy_hook(unsigned int hooknum, if (!th->syn || !th->ack) break; - synproxy_parse_options(skb, thoff, th, &opts); + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->tsoff = opts.tsval - synproxy->its; diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c index 61aaf70f376e..2205e8eeeacf 100644 --- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -69,8 +69,8 @@ icmpv6_manip_pkt(struct sk_buff *skb, hdr = (struct icmp6hdr *)(skb->data + hdroff); l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); - if (hdr->icmp6_code == ICMPV6_ECHO_REQUEST || - hdr->icmp6_code == ICMPV6_ECHO_REPLY) { + if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || + hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, tuple->src.u.icmp.id, 0); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 58916bbb1728..a4ed2416399e 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -335,8 +335,10 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } - if (type == NDISC_REDIRECT) + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + return; + } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 7ee5cb96db34..19269453a8ea 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -566,6 +566,70 @@ static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, return false; } +/* Checks if an address matches an address on the tunnel interface. + * Used to detect the NAT of proto 41 packets and let them pass spoofing test. + * Long story: + * This function is called after we considered the packet as spoofed + * in is_spoofed_6rd. + * We may have a router that is doing NAT for proto 41 packets + * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb + * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd + * function will return true, dropping the packet. + * But, we can still check if is spoofed against the IP + * addresses associated with the interface. + */ +static bool only_dnatted(const struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + int prefix_len; + +#ifdef CONFIG_IPV6_SIT_6RD + prefix_len = tunnel->ip6rd.prefixlen + 32 + - tunnel->ip6rd.relay_prefixlen; +#else + prefix_len = 48; +#endif + return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); +} + +/* Returns true if a packet is spoofed */ +static bool packet_is_spoofed(struct sk_buff *skb, + const struct iphdr *iph, + struct ip_tunnel *tunnel) +{ + const struct ipv6hdr *ipv6h; + + if (tunnel->dev->priv_flags & IFF_ISATAP) { + if (!isatap_chksrc(skb, iph, tunnel)) + return true; + + return false; + } + + if (tunnel->dev->flags & IFF_POINTOPOINT) + return false; + + ipv6h = ipv6_hdr(skb); + + if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { + net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; + } + + if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) + return false; + + if (only_dnatted(tunnel, &ipv6h->daddr)) + return false; + + net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; +} + static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); @@ -586,19 +650,9 @@ static int ipip6_rcv(struct sk_buff *skb) IPCB(skb)->flags = 0; skb->protocol = htons(ETH_P_IPV6); - if (tunnel->dev->priv_flags & IFF_ISATAP) { - if (!isatap_chksrc(skb, iph, tunnel)) { - tunnel->dev->stats.rx_errors++; - goto out; - } - } else if (!(tunnel->dev->flags&IFF_POINTOPOINT)) { - if (is_spoofed_6rd(tunnel, iph->saddr, - &ipv6_hdr(skb)->saddr) || - is_spoofed_6rd(tunnel, iph->daddr, - &ipv6_hdr(skb)->daddr)) { - tunnel->dev->stats.rx_errors++; - goto out; - } + if (packet_is_spoofed(skb, iph, tunnel)) { + tunnel->dev->stats.rx_errors++; + goto out; } __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); @@ -748,7 +802,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -777,7 +831,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -1612,6 +1666,7 @@ static int __net_init sit_init_net(struct net *net) goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); + sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ @@ -1646,7 +1701,6 @@ static void __net_exit sit_exit_net(struct net *net) rtnl_lock(); sit_destroy_tunnels(sitn, &list); - unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f4058150262b..72b7eaaf3ca0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -525,8 +525,10 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == ICMPV6_PKT_TOOBIG) ip6_sk_update_pmtu(skb, sk, info); - if (type == NDISC_REDIRECT) + if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); + goto out; + } np = inet6_sk(sk); diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c index 54563ad8aeb1..355cc3b6fa4d 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -154,6 +154,7 @@ static void lapb_t1timer_expiry(unsigned long param) } else { lapb->n2count++; lapb_requeue_frames(lapb); + lapb_kick(lapb); } break; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index f77139007983..f2e30fb31e78 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1052,7 +1052,7 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, * 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)) + from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; strncpy(from_name, from->name, IPSET_MAXNAMELEN); @@ -1489,8 +1489,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb, if (ret == -EAGAIN) ret = 1; - return (ret < 0 && ret != -ENOTEMPTY) ? ret : - ret > 0 ? 0 : -IPSET_ERR_EXIST; + return ret > 0 ? 0 : -IPSET_ERR_EXIST; } /* Get headed data of a set */ diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 6fdf88ae2353..dac156f819ac 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -116,12 +116,12 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src, { int protoff; u8 nexthdr; - __be16 frag_off; + __be16 frag_off = 0; nexthdr = ipv6_hdr(skb)->nexthdr; protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); - if (protoff < 0) + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) return false; return get_port(skb, nexthdr, protoff, src, port, proto); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 57beb1762b2d..707bc520d629 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -325,18 +325,22 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length) static void mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length) { - u8 i, j; - - for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++) - ; - h->nets[i].nets--; - - if (h->nets[i].nets != 0) - return; - - for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) { - h->nets[j].cidr = h->nets[j + 1].cidr; - h->nets[j].nets = h->nets[j + 1].nets; + u8 i, j, net_end = nets_length - 1; + + for (i = 0; i < nets_length; i++) { + if (h->nets[i].cidr != cidr) + continue; + if (h->nets[i].nets > 1 || i == net_end || + h->nets[i + 1].nets == 0) { + h->nets[i].nets--; + return; + } + for (j = i; j < net_end && h->nets[j].nets; j++) { + h->nets[j].cidr = h->nets[j + 1].cidr; + h->nets[j].nets = h->nets[j + 1].nets; + } + h->nets[j].nets = 0; + return; } } #endif diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index c6a525373be4..f15f3e28b9c3 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -260,7 +260,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip = htonl(ip); e.ip2 = htonl(ip2_from & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -544,7 +544,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index da740ceb56ae..223e9f546d0f 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -199,7 +199,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret: ip_set_eexist(ret, flags) ? 0 : ret; } @@ -396,7 +396,7 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 84ae6f6ce624..7d798d5d5cd3 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -368,7 +368,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -634,7 +634,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 9a0869853be5..09d6690bee6f 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -244,7 +244,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -489,7 +489,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f69e83ff836..74fd00c27210 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -116,6 +116,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; + struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); s->ustats.inpkts++; @@ -123,11 +124,14 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(dest->svc->stats.cpustats); + rcu_read_lock(); + svc = rcu_dereference(dest->svc); + s = this_cpu_ptr(svc->stats.cpustats); s->ustats.inpkts++; u64_stats_update_begin(&s->syncp); s->ustats.inbytes += skb->len; u64_stats_update_end(&s->syncp); + rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.inpkts++; @@ -146,6 +150,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; + struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); s->ustats.outpkts++; @@ -153,11 +158,14 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(dest->svc->stats.cpustats); + rcu_read_lock(); + svc = rcu_dereference(dest->svc); + s = this_cpu_ptr(svc->stats.cpustats); s->ustats.outpkts++; u64_stats_update_begin(&s->syncp); s->ustats.outbytes += skb->len; u64_stats_update_end(&s->syncp); + rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); s->ustats.outpkts++; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c8148e487386..a3df9bddc4f7 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -460,7 +460,7 @@ static inline void __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc) { atomic_inc(&svc->refcnt); - dest->svc = svc; + rcu_assign_pointer(dest->svc, svc); } static void ip_vs_service_free(struct ip_vs_service *svc) @@ -470,18 +470,25 @@ static void ip_vs_service_free(struct ip_vs_service *svc) kfree(svc); } -static void -__ip_vs_unbind_svc(struct ip_vs_dest *dest) +static void ip_vs_service_rcu_free(struct rcu_head *head) { - struct ip_vs_service *svc = dest->svc; + struct ip_vs_service *svc; + + svc = container_of(head, struct ip_vs_service, rcu_head); + ip_vs_service_free(svc); +} - dest->svc = NULL; +static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay) +{ if (atomic_dec_and_test(&svc->refcnt)) { IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port)); - ip_vs_service_free(svc); + if (do_delay) + call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); + else + ip_vs_service_free(svc); } } @@ -667,11 +674,6 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); - /* We can not reuse dest while in grace period - * because conns still can use dest->svc - */ - if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state)) - continue; if (dest->af == svc->af && ip_vs_addr_equal(svc->af, &dest->addr, daddr) && dest->port == dport && @@ -697,8 +699,10 @@ out: static void ip_vs_dest_free(struct ip_vs_dest *dest) { + struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1); + __ip_vs_dst_cache_reset(dest); - __ip_vs_unbind_svc(dest); + __ip_vs_svc_put(svc, false); free_percpu(dest->stats.cpustats); kfree(dest); } @@ -771,6 +775,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct ip_vs_service *old_svc; struct ip_vs_scheduler *sched; int conn_flags; @@ -792,13 +797,14 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, atomic_set(&dest->conn_flags, conn_flags); /* bind the service */ - if (!dest->svc) { + old_svc = rcu_dereference_protected(dest->svc, 1); + if (!old_svc) { __ip_vs_bind_svc(dest, svc); } else { - if (dest->svc != svc) { - __ip_vs_unbind_svc(dest); + if (old_svc != svc) { ip_vs_zero_stats(&dest->stats); __ip_vs_bind_svc(dest, svc); + __ip_vs_svc_put(old_svc, true); } } @@ -998,16 +1004,6 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return 0; } -static void ip_vs_dest_wait_readers(struct rcu_head *head) -{ - struct ip_vs_dest *dest = container_of(head, struct ip_vs_dest, - rcu_head); - - /* End of grace period after unlinking */ - clear_bit(IP_VS_DEST_STATE_REMOVING, &dest->state); -} - - /* * Delete a destination (must be already unlinked from the service) */ @@ -1023,20 +1019,16 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest, */ ip_vs_rs_unhash(dest); - if (!cleanup) { - set_bit(IP_VS_DEST_STATE_REMOVING, &dest->state); - call_rcu(&dest->rcu_head, ip_vs_dest_wait_readers); - } - spin_lock_bh(&ipvs->dest_trash_lock); IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); if (list_empty(&ipvs->dest_trash) && !cleanup) mod_timer(&ipvs->dest_trash_timer, - jiffies + IP_VS_DEST_TRASH_PERIOD); + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); /* dest lives in trash without reference */ list_add(&dest->t_list, &ipvs->dest_trash); + dest->idle_start = 0; spin_unlock_bh(&ipvs->dest_trash_lock); ip_vs_dest_put(dest); } @@ -1108,24 +1100,30 @@ static void ip_vs_dest_trash_expire(unsigned long data) struct net *net = (struct net *) data; struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_dest *dest, *next; + unsigned long now = jiffies; spin_lock(&ipvs->dest_trash_lock); list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) { - /* Skip if dest is in grace period */ - if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state)) - continue; if (atomic_read(&dest->refcnt) > 0) continue; + if (dest->idle_start) { + if (time_before(now, dest->idle_start + + IP_VS_DEST_TRASH_PERIOD)) + continue; + } else { + dest->idle_start = max(1UL, now); + continue; + } IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n", dest->vfwmark, - IP_VS_DBG_ADDR(dest->svc->af, &dest->addr), + IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); list_del(&dest->t_list); ip_vs_dest_free(dest); } if (!list_empty(&ipvs->dest_trash)) mod_timer(&ipvs->dest_trash_timer, - jiffies + IP_VS_DEST_TRASH_PERIOD); + jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1)); spin_unlock(&ipvs->dest_trash_lock); } @@ -1320,14 +1318,6 @@ out: return ret; } -static void ip_vs_service_rcu_free(struct rcu_head *head) -{ - struct ip_vs_service *svc; - - svc = container_of(head, struct ip_vs_service, rcu_head); - ip_vs_service_free(svc); -} - /* * Delete a service from the service list * - The service must be unlinked, unlocked and not referenced! @@ -1376,13 +1366,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) /* * Free the service if nobody refers to it */ - if (atomic_dec_and_test(&svc->refcnt)) { - IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", - svc->fwmark, - IP_VS_DBG_ADDR(svc->af, &svc->addr), - ntohs(svc->port)); - call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); - } + __ip_vs_svc_put(svc, true); /* decrease the module use count */ ip_vs_use_count_dec(); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 6bee6d0c73a5..1425e9a924c4 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -59,12 +59,13 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, struct ip_vs_cpu_stats __percpu *stats) { int i; + bool add = false; for_each_possible_cpu(i) { struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i); unsigned int start; __u64 inbytes, outbytes; - if (i) { + if (add) { sum->conns += s->ustats.conns; sum->inpkts += s->ustats.inpkts; sum->outpkts += s->ustats.outpkts; @@ -76,6 +77,7 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, sum->inbytes += inbytes; sum->outbytes += outbytes; } else { + add = true; sum->conns = s->ustats.conns; sum->inpkts = s->ustats.inpkts; sum->outpkts = s->ustats.outpkts; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 1383b0eadc0e..eff13c94498e 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -93,7 +93,7 @@ struct ip_vs_lblc_entry { struct hlist_node list; int af; /* address family */ union nf_inet_addr addr; /* destination IP address */ - struct ip_vs_dest __rcu *dest; /* real server (cache) */ + struct ip_vs_dest *dest; /* real server (cache) */ unsigned long lastuse; /* last used time */ struct rcu_head rcu_head; }; @@ -130,20 +130,21 @@ static struct ctl_table vs_vars_table[] = { }; #endif -static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) +static void ip_vs_lblc_rcu_free(struct rcu_head *head) { - struct ip_vs_dest *dest; + struct ip_vs_lblc_entry *en = container_of(head, + struct ip_vs_lblc_entry, + rcu_head); - hlist_del_rcu(&en->list); - /* - * We don't kfree dest because it is referred either by its service - * or the trash dest list. - */ - dest = rcu_dereference_protected(en->dest, 1); - ip_vs_dest_put(dest); - kfree_rcu(en, rcu_head); + ip_vs_dest_put(en->dest); + kfree(en); } +static inline void ip_vs_lblc_del(struct ip_vs_lblc_entry *en) +{ + hlist_del_rcu(&en->list); + call_rcu(&en->rcu_head, ip_vs_lblc_rcu_free); +} /* * Returns hash value for IPVS LBLC entry @@ -203,30 +204,23 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr, struct ip_vs_lblc_entry *en; en = ip_vs_lblc_get(dest->af, tbl, daddr); - if (!en) { - en = kmalloc(sizeof(*en), GFP_ATOMIC); - if (!en) - return NULL; - - en->af = dest->af; - ip_vs_addr_copy(dest->af, &en->addr, daddr); - en->lastuse = jiffies; + if (en) { + if (en->dest == dest) + return en; + ip_vs_lblc_del(en); + } + en = kmalloc(sizeof(*en), GFP_ATOMIC); + if (!en) + return NULL; - ip_vs_dest_hold(dest); - RCU_INIT_POINTER(en->dest, dest); + en->af = dest->af; + ip_vs_addr_copy(dest->af, &en->addr, daddr); + en->lastuse = jiffies; - ip_vs_lblc_hash(tbl, en); - } else { - struct ip_vs_dest *old_dest; + ip_vs_dest_hold(dest); + en->dest = dest; - old_dest = rcu_dereference_protected(en->dest, 1); - if (old_dest != dest) { - ip_vs_dest_put(old_dest); - ip_vs_dest_hold(dest); - /* No ordering constraints for refcnt */ - RCU_INIT_POINTER(en->dest, dest); - } - } + ip_vs_lblc_hash(tbl, en); return en; } @@ -246,7 +240,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc) tbl->dead = 1; for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) { - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); } } @@ -281,7 +275,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) sysctl_lblc_expiration(svc))) continue; - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); } spin_unlock(&svc->sched_lock); @@ -335,7 +329,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) if (time_before(now, en->lastuse + ENTRY_TIMEOUT)) continue; - ip_vs_lblc_free(en); + ip_vs_lblc_del(en); atomic_dec(&tbl->entries); goal--; } @@ -443,8 +437,8 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } @@ -511,7 +505,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, * free up entries from the trash at any time. */ - dest = rcu_dereference(en->dest); + dest = en->dest; if ((dest->flags & IP_VS_DEST_F_AVAILABLE) && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc)) goto out; @@ -631,7 +625,7 @@ static void __exit ip_vs_lblc_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler); unregister_pernet_subsys(&ip_vs_lblc_ops); - synchronize_rcu(); + rcu_barrier(); } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 5199448697f6..0b8550089a2e 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -89,7 +89,7 @@ */ struct ip_vs_dest_set_elem { struct list_head list; /* list link */ - struct ip_vs_dest __rcu *dest; /* destination server */ + struct ip_vs_dest *dest; /* destination server */ struct rcu_head rcu_head; }; @@ -107,11 +107,7 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, if (check) { list_for_each_entry(e, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - if (d == dest) - /* already existed */ + if (e->dest == dest) return; } } @@ -121,7 +117,7 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, return; ip_vs_dest_hold(dest); - RCU_INIT_POINTER(e->dest, dest); + e->dest = dest; list_add_rcu(&e->list, &set->list); atomic_inc(&set->size); @@ -129,22 +125,27 @@ static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, set->lastmod = jiffies; } +static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head) +{ + struct ip_vs_dest_set_elem *e; + + e = container_of(head, struct ip_vs_dest_set_elem, rcu_head); + ip_vs_dest_put(e->dest); + kfree(e); +} + static void ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) { struct ip_vs_dest_set_elem *e; list_for_each_entry(e, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - if (d == dest) { + if (e->dest == dest) { /* HIT */ atomic_dec(&set->size); set->lastmod = jiffies; - ip_vs_dest_put(dest); list_del_rcu(&e->list); - kfree_rcu(e, rcu_head); + call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); break; } } @@ -155,16 +156,8 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) struct ip_vs_dest_set_elem *e, *ep; list_for_each_entry_safe(e, ep, &set->list, list) { - struct ip_vs_dest *d; - - d = rcu_dereference_protected(e->dest, 1); - /* - * We don't kfree dest because it is referred either - * by its service or by the trash dest list. - */ - ip_vs_dest_put(d); list_del_rcu(&e->list); - kfree_rcu(e, rcu_head); + call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); } } @@ -175,12 +168,9 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) struct ip_vs_dest *dest, *least; int loh, doh; - if (set == NULL) - return NULL; - /* select the first destination server, whose weight > 0 */ list_for_each_entry_rcu(e, &set->list, list) { - least = rcu_dereference(e->dest); + least = e->dest; if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; @@ -195,13 +185,13 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) /* find the destination with the weighted least load */ nextstage: list_for_each_entry_continue_rcu(e, &set->list, list) { - dest = rcu_dereference(e->dest); + dest = e->dest; if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); - if ((loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) + if (((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { least = dest; loh = doh; @@ -232,7 +222,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) /* select the first destination server, whose weight > 0 */ list_for_each_entry(e, &set->list, list) { - most = rcu_dereference_protected(e->dest, 1); + most = e->dest; if (atomic_read(&most->weight) > 0) { moh = ip_vs_dest_conn_overhead(most); goto nextstage; @@ -243,11 +233,11 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) /* find the destination with the weighted most load */ nextstage: list_for_each_entry_continue(e, &set->list, list) { - dest = rcu_dereference_protected(e->dest, 1); + dest = e->dest; doh = ip_vs_dest_conn_overhead(dest); /* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */ - if ((moh * atomic_read(&dest->weight) < - doh * atomic_read(&most->weight)) + if (((__s64)moh * atomic_read(&dest->weight) < + (__s64)doh * atomic_read(&most->weight)) && (atomic_read(&dest->weight) > 0)) { most = dest; moh = doh; @@ -611,8 +601,8 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } @@ -819,7 +809,7 @@ static void __exit ip_vs_lblcr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler); unregister_pernet_subsys(&ip_vs_lblcr_ops); - synchronize_rcu(); + rcu_barrier(); } diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index d8d9860934fe..961a6de9bb29 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -40,7 +40,7 @@ #include <net/ip_vs.h> -static inline unsigned int +static inline int ip_vs_nq_dest_overhead(struct ip_vs_dest *dest) { /* @@ -59,7 +59,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least = NULL; - unsigned int loh = 0, doh; + int loh = 0, doh; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -92,8 +92,8 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, } if (!least || - (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight))) { + ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight))) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index a5284cc3d882..e446b9fa7424 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -44,7 +44,7 @@ #include <net/ip_vs.h> -static inline unsigned int +static inline int ip_vs_sed_dest_overhead(struct ip_vs_dest *dest) { /* @@ -63,7 +63,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; - unsigned int loh, doh; + int loh, doh; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -99,8 +99,8 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_sed_dest_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index 6dc1fa128840..b5b4650d50a9 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -35,7 +35,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *least; - unsigned int loh, doh; + int loh, doh; IP_VS_DBG(6, "ip_vs_wlc_schedule(): Scheduling...\n"); @@ -71,8 +71,8 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); - if (loh * atomic_read(&dest->weight) > - doh * atomic_read(&least->weight)) { + if ((__s64)loh * atomic_read(&dest->weight) > + (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b75ff6429a04..c47444e4cf8c 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 6fd967c6278c..cdf4567ba9b3 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -24,7 +24,7 @@ int synproxy_net_id; EXPORT_SYMBOL_GPL(synproxy_net_id); -void +bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts) { @@ -32,7 +32,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, u8 buf[40], *ptr; ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); - BUG_ON(ptr == NULL); + if (ptr == NULL) + return false; opts->options = 0; while (length > 0) { @@ -41,16 +42,16 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, switch (opcode) { case TCPOPT_EOL: - return; + return true; case TCPOPT_NOP: length--; continue; default: opsize = *ptr++; if (opsize < 2) - return; + return true; if (opsize > length) - return; + return true; switch (opcode) { case TCPOPT_MSS: @@ -84,6 +85,7 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length -= opsize; } } + return true; } EXPORT_SYMBOL_GPL(synproxy_parse_options); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 95a98c8c1da6..ae2e5c11d01a 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -1009,7 +1009,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, verdict = NF_DROP; if (ct) - nfqnl_ct_seq_adjust(skb, ct, ctinfo, diff); + nfqnl_ct_seq_adjust(entry->skb, ct, ctinfo, diff); } if (nfqa[NFQA_MARK]) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index a17dda1bbee0..8df7f64c6db3 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -168,16 +168,43 @@ int netlink_remove_tap(struct netlink_tap *nt) } EXPORT_SYMBOL_GPL(netlink_remove_tap); +static bool netlink_filter_tap(const struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + bool pass = false; + + /* We take the more conservative approach and + * whitelist socket protocols that may pass. + */ + switch (sk->sk_protocol) { + case NETLINK_ROUTE: + case NETLINK_USERSOCK: + case NETLINK_SOCK_DIAG: + case NETLINK_NFLOG: + case NETLINK_XFRM: + case NETLINK_FIB_LOOKUP: + case NETLINK_NETFILTER: + case NETLINK_GENERIC: + pass = true; + break; + } + + return pass; +} + static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *nskb; + struct sock *sk = skb->sk; int ret = -ENOMEM; dev_hold(dev); nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; + nskb->protocol = htons((u16) sk->sk_protocol); + ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); @@ -192,6 +219,9 @@ static void __netlink_deliver_tap(struct sk_buff *skb) int ret; struct netlink_tap *tmp; + if (!netlink_filter_tap(skb)) + return; + list_for_each_entry_rcu(tmp, &netlink_tap_all, list) { ret = __netlink_deliver_tap_skb(skb, tmp->dev); if (unlikely(ret)) diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index fb36f8565161..410db90db73d 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -1178,6 +1178,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, if (type > OVS_KEY_ATTR_MAX) { OVS_NLERR("Unknown key attribute (type=%d, max=%d).\n", type, OVS_KEY_ATTR_MAX); + return -EINVAL; } if (attrs & (1 << type)) { diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 32ad015ee8ce..a2fef8b10b96 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -285,7 +285,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) /* remove one skb from head of flow queue */ -static struct sk_buff *fq_dequeue_head(struct fq_flow *flow) +static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) { struct sk_buff *skb = flow->head; @@ -293,6 +293,8 @@ static struct sk_buff *fq_dequeue_head(struct fq_flow *flow) flow->head = skb->next; skb->next = NULL; flow->qlen--; + sch->qstats.backlog -= qdisc_pkt_len(skb); + sch->q.qlen--; } return skb; } @@ -418,8 +420,9 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; + u32 rate; - skb = fq_dequeue_head(&q->internal); + skb = fq_dequeue_head(sch, &q->internal); if (skb) goto out; fq_check_throttled(q, now); @@ -449,7 +452,7 @@ begin: goto begin; } - skb = fq_dequeue_head(f); + skb = fq_dequeue_head(sch, f); if (!skb) { head->first = f->next; /* force a pass through old_flows to prevent starvation */ @@ -466,43 +469,74 @@ begin: f->time_next_packet = now; f->credit -= qdisc_pkt_len(skb); - if (f->credit <= 0 && - q->rate_enable && - skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) { - u32 rate = skb->sk->sk_pacing_rate ?: q->flow_default_rate; + if (f->credit > 0 || !q->rate_enable) + goto out; - rate = min(rate, q->flow_max_rate); - if (rate) { - u64 len = (u64)qdisc_pkt_len(skb) * NSEC_PER_SEC; - - do_div(len, rate); - /* Since socket rate can change later, - * clamp the delay to 125 ms. - * TODO: maybe segment the too big skb, as in commit - * e43ac79a4bc ("sch_tbf: segment too big GSO packets") - */ - if (unlikely(len > 125 * NSEC_PER_MSEC)) { - len = 125 * NSEC_PER_MSEC; - q->stat_pkts_too_long++; - } + if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) { + rate = skb->sk->sk_pacing_rate ?: q->flow_default_rate; - f->time_next_packet = now + len; + rate = min(rate, q->flow_max_rate); + } else { + rate = q->flow_max_rate; + if (rate == ~0U) + goto out; + } + if (rate) { + u32 plen = max(qdisc_pkt_len(skb), q->quantum); + u64 len = (u64)plen * NSEC_PER_SEC; + + do_div(len, rate); + /* Since socket rate can change later, + * clamp the delay to 125 ms. + * TODO: maybe segment the too big skb, as in commit + * e43ac79a4bc ("sch_tbf: segment too big GSO packets") + */ + if (unlikely(len > 125 * NSEC_PER_MSEC)) { + len = 125 * NSEC_PER_MSEC; + q->stat_pkts_too_long++; } + + f->time_next_packet = now + len; } out: - sch->qstats.backlog -= qdisc_pkt_len(skb); qdisc_bstats_update(sch, skb); - sch->q.qlen--; qdisc_unthrottled(sch); return skb; } static void fq_reset(struct Qdisc *sch) { + struct fq_sched_data *q = qdisc_priv(sch); + struct rb_root *root; struct sk_buff *skb; + struct rb_node *p; + struct fq_flow *f; + unsigned int idx; - while ((skb = fq_dequeue(sch)) != NULL) + while ((skb = fq_dequeue_head(sch, &q->internal)) != NULL) kfree_skb(skb); + + if (!q->fq_root) + return; + + for (idx = 0; idx < (1U << q->fq_trees_log); idx++) { + root = &q->fq_root[idx]; + while ((p = rb_first(root)) != NULL) { + f = container_of(p, struct fq_flow, fq_node); + rb_erase(p, root); + + while ((skb = fq_dequeue_head(sch, f)) != NULL) + kfree_skb(skb); + + kmem_cache_free(fq_flow_cachep, f); + } + } + q->new_flows.first = NULL; + q->old_flows.first = NULL; + q->delayed = RB_ROOT; + q->flows = 0; + q->inactive_flows = 0; + q->throttled_flows = 0; } static void fq_rehash(struct fq_sched_data *q, @@ -645,6 +679,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); + if (!skb) + break; kfree_skb(skb); drop_count++; } @@ -657,21 +693,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) static void fq_destroy(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); - struct rb_root *root; - struct rb_node *p; - unsigned int idx; - if (q->fq_root) { - for (idx = 0; idx < (1U << q->fq_trees_log); idx++) { - root = &q->fq_root[idx]; - while ((p = rb_first(root)) != NULL) { - rb_erase(p, root); - kmem_cache_free(fq_flow_cachep, - container_of(p, struct fq_flow, fq_node)); - } - } - kfree(q->fq_root); - } + fq_reset(sch); + kfree(q->fq_root); qdisc_watchdog_cancel(&q->watchdog); } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c2178b15ca6e..863846cc5513 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1495,7 +1495,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, psched_ratecfg_precompute(&cl->ceil, &hopt->ceil); cl->buffer = PSCHED_TICKS2NS(hopt->buffer); - cl->cbuffer = PSCHED_TICKS2NS(hopt->buffer); + cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer); sch_tree_unlock(sch); diff --git a/net/sctp/input.c b/net/sctp/input.c index 5f2068679f83..98b69bbecdd9 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -634,8 +634,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) break; case ICMP_REDIRECT: sctp_icmp_redirect(sk, transport, skb); - err = 0; - break; + /* Fall through to out_unlock. */ default: goto out_unlock; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index da613ceae28c..e7b2d4fe2b6a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -183,7 +183,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, break; case NDISC_REDIRECT: sctp_icmp_redirect(sk, transport, skb); - break; + goto out_unlock; default: break; } @@ -204,44 +204,23 @@ out: in6_dev_put(idev); } -/* Based on tcp_v6_xmit() in tcp_ipv6.c. */ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) { struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi6 fl6; - - memset(&fl6, 0, sizeof(fl6)); - - fl6.flowi6_proto = sk->sk_protocol; - - /* Fill in the dest address from the route entry passed with the skb - * and the source address from the transport. - */ - fl6.daddr = transport->ipaddr.v6.sin6_addr; - fl6.saddr = transport->saddr.v6.sin6_addr; - - fl6.flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl6.flowlabel); - if (ipv6_addr_type(&fl6.saddr) & IPV6_ADDR_LINKLOCAL) - fl6.flowi6_oif = transport->saddr.v6.sin6_scope_id; - else - fl6.flowi6_oif = sk->sk_bound_dev_if; - - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; - fl6.daddr = *rt0->addr; - } + struct flowi6 *fl6 = &transport->fl.u.ip6; pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb, - skb->len, &fl6.saddr, &fl6.daddr); + skb->len, &fl6->saddr, &fl6->daddr); - SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); + IP6_ECN_flow_xmit(sk, fl6->flowlabel); if (!(transport->param_flags & SPP_PMTUD_ENABLE)) skb->local_df = 1; - return ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); + + return ip6_xmit(sk, skb, fl6, np->opt, np->tclass); } /* Returns the dst cache entry for the given source and destination ip @@ -254,10 +233,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct dst_entry *dst = NULL; struct flowi6 *fl6 = &fl->u.ip6; struct sctp_bind_addr *bp; + struct ipv6_pinfo *np = inet6_sk(sk); struct sctp_sockaddr_entry *laddr; union sctp_addr *baddr = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; + struct in6_addr *final_p, final; __u8 matchlen = 0; __u8 bmatchlen; sctp_scope_t scope; @@ -281,7 +262,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, pr_debug("src=%pI6 - ", &fl6->saddr); } - dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); + final_p = fl6_update_dst(fl6, np->opt, &final); + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); if (!asoc || saddr) goto out; @@ -333,10 +315,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } } rcu_read_unlock(); + if (baddr) { fl6->saddr = baddr->v6.sin6_addr; fl6->fl6_sport = baddr->v6.sin6_port; - dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); + final_p = fl6_update_dst(fl6, np->opt, &final); + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); } out: diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d5d5882a2891..911b71b26b0e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -806,6 +806,9 @@ static int sctp_send_asconf_del_ip(struct sock *sk, goto skip_mkasconf; } + if (laddr == NULL) + return -EINVAL; + /* We do not need RCU protection throughout this loop * because this is done under a socket lock from the * setsockopt call. @@ -6176,7 +6179,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Is there any exceptional events? */ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR | - sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0; + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) diff --git a/net/socket.c b/net/socket.c index b2d7c629eeb9..ebed4b68f768 100644 --- a/net/socket.c +++ b/net/socket.c @@ -854,11 +854,6 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(kernel_recvmsg); -static void sock_aio_dtor(struct kiocb *iocb) -{ - kfree(iocb->private); -} - static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more) { @@ -889,12 +884,8 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, struct sock_iocb *siocb) { - if (!is_sync_kiocb(iocb)) { - siocb = kmalloc(sizeof(*siocb), GFP_KERNEL); - if (!siocb) - return NULL; - iocb->ki_dtor = sock_aio_dtor; - } + if (!is_sync_kiocb(iocb)) + BUG(); siocb->kiocb = iocb; iocb->private = siocb; @@ -931,7 +922,7 @@ static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, if (pos != 0) return -ESPIPE; - if (iocb->ki_left == 0) /* Match SYS5 behaviour */ + if (iocb->ki_nbytes == 0) /* Match SYS5 behaviour */ return 0; @@ -3072,12 +3063,12 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd, uifmap32 = &uifr32->ifr_ifru.ifru_map; err = copy_from_user(&ifr, uifr32, sizeof(ifr.ifr_name)); - err |= __get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); - err |= __get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); - err |= __get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); - err |= __get_user(ifr.ifr_map.irq, &uifmap32->irq); - err |= __get_user(ifr.ifr_map.dma, &uifmap32->dma); - err |= __get_user(ifr.ifr_map.port, &uifmap32->port); + err |= get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); + err |= get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); + err |= get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); + err |= get_user(ifr.ifr_map.irq, &uifmap32->irq); + err |= get_user(ifr.ifr_map.dma, &uifmap32->dma); + err |= get_user(ifr.ifr_map.port, &uifmap32->port); if (err) return -EFAULT; @@ -3088,12 +3079,12 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd, if (cmd == SIOCGIFMAP && !err) { err = copy_to_user(uifr32, &ifr, sizeof(ifr.ifr_name)); - err |= __put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); - err |= __put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); - err |= __put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); - err |= __put_user(ifr.ifr_map.irq, &uifmap32->irq); - err |= __put_user(ifr.ifr_map.dma, &uifmap32->dma); - err |= __put_user(ifr.ifr_map.port, &uifmap32->port); + err |= put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); + err |= put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); + err |= put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); + err |= put_user(ifr.ifr_map.irq, &uifmap32->irq); + err |= put_user(ifr.ifr_map.dma, &uifmap32->dma); + err |= put_user(ifr.ifr_map.port, &uifmap32->port); if (err) err = -EFAULT; } @@ -3167,25 +3158,25 @@ static int routing_ioctl(struct net *net, struct socket *sock, struct in6_rtmsg32 __user *ur6 = argp; ret = copy_from_user(&r6.rtmsg_dst, &(ur6->rtmsg_dst), 3 * sizeof(struct in6_addr)); - ret |= __get_user(r6.rtmsg_type, &(ur6->rtmsg_type)); - ret |= __get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len)); - ret |= __get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len)); - ret |= __get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric)); - ret |= __get_user(r6.rtmsg_info, &(ur6->rtmsg_info)); - ret |= __get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags)); - ret |= __get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex)); + ret |= get_user(r6.rtmsg_type, &(ur6->rtmsg_type)); + ret |= get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len)); + ret |= get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len)); + ret |= get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric)); + ret |= get_user(r6.rtmsg_info, &(ur6->rtmsg_info)); + ret |= get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags)); + ret |= get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex)); r = (void *) &r6; } else { /* ipv4 */ struct rtentry32 __user *ur4 = argp; ret = copy_from_user(&r4.rt_dst, &(ur4->rt_dst), 3 * sizeof(struct sockaddr)); - ret |= __get_user(r4.rt_flags, &(ur4->rt_flags)); - ret |= __get_user(r4.rt_metric, &(ur4->rt_metric)); - ret |= __get_user(r4.rt_mtu, &(ur4->rt_mtu)); - ret |= __get_user(r4.rt_window, &(ur4->rt_window)); - ret |= __get_user(r4.rt_irtt, &(ur4->rt_irtt)); - ret |= __get_user(rtdev, &(ur4->rt_dev)); + ret |= get_user(r4.rt_flags, &(ur4->rt_flags)); + ret |= get_user(r4.rt_metric, &(ur4->rt_metric)); + ret |= get_user(r4.rt_mtu, &(ur4->rt_mtu)); + ret |= get_user(r4.rt_window, &(ur4->rt_window)); + ret |= get_user(r4.rt_irtt, &(ur4->rt_irtt)); + ret |= get_user(rtdev, &(ur4->rt_dev)); if (rtdev) { ret |= copy_from_user(devname, compat_ptr(rtdev), 15); r4.rt_dev = (char __user __force *)devname; diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index ed2fdd210c0b..5285ead196c0 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -250,11 +250,11 @@ rpcauth_list_flavors(rpc_authflavor_t *array, int size) EXPORT_SYMBOL_GPL(rpcauth_list_flavors); struct rpc_auth * -rpcauth_create(rpc_authflavor_t pseudoflavor, struct rpc_clnt *clnt) +rpcauth_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { struct rpc_auth *auth; const struct rpc_authops *ops; - u32 flavor = pseudoflavor_to_flavor(pseudoflavor); + u32 flavor = pseudoflavor_to_flavor(args->pseudoflavor); auth = ERR_PTR(-EINVAL); if (flavor >= RPC_AUTH_MAXFLAVOR) @@ -269,7 +269,7 @@ rpcauth_create(rpc_authflavor_t pseudoflavor, struct rpc_clnt *clnt) goto out; } spin_unlock(&rpc_authflavor_lock); - auth = ops->create(clnt, pseudoflavor); + auth = ops->create(args, clnt); module_put(ops->owner); if (IS_ERR(auth)) return auth; @@ -343,6 +343,27 @@ out_nocache: EXPORT_SYMBOL_GPL(rpcauth_init_credcache); /* + * Setup a credential key lifetime timeout notification + */ +int +rpcauth_key_timeout_notify(struct rpc_auth *auth, struct rpc_cred *cred) +{ + if (!cred->cr_auth->au_ops->key_timeout) + return 0; + return cred->cr_auth->au_ops->key_timeout(auth, cred); +} +EXPORT_SYMBOL_GPL(rpcauth_key_timeout_notify); + +bool +rpcauth_cred_key_to_expire(struct rpc_cred *cred) +{ + if (!cred->cr_ops->crkey_to_expire) + return false; + return cred->cr_ops->crkey_to_expire(cred); +} +EXPORT_SYMBOL_GPL(rpcauth_cred_key_to_expire); + +/* * Destroy a list of credentials */ static inline @@ -413,12 +434,13 @@ EXPORT_SYMBOL_GPL(rpcauth_destroy_credcache); /* * Remove stale credentials. Avoid sleeping inside the loop. */ -static int +static long rpcauth_prune_expired(struct list_head *free, int nr_to_scan) { spinlock_t *cache_lock; struct rpc_cred *cred, *next; unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM; + long freed = 0; list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) { @@ -430,10 +452,11 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan) */ if (time_in_range(cred->cr_expire, expired, jiffies) && test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) - return 0; + break; list_del_init(&cred->cr_lru); number_cred_unused--; + freed++; if (atomic_read(&cred->cr_count) != 0) continue; @@ -446,29 +469,39 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan) } spin_unlock(cache_lock); } - return (number_cred_unused / 100) * sysctl_vfs_cache_pressure; + return freed; } /* * Run memory cache shrinker. */ -static int -rpcauth_cache_shrinker(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long +rpcauth_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) + { LIST_HEAD(free); - int res; - int nr_to_scan = sc->nr_to_scan; - gfp_t gfp_mask = sc->gfp_mask; + unsigned long freed; - if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) - return (nr_to_scan == 0) ? 0 : -1; + if ((sc->gfp_mask & GFP_KERNEL) != GFP_KERNEL) + return SHRINK_STOP; + + /* nothing left, don't come back */ if (list_empty(&cred_unused)) - return 0; + return SHRINK_STOP; + spin_lock(&rpc_credcache_lock); - res = rpcauth_prune_expired(&free, nr_to_scan); + freed = rpcauth_prune_expired(&free, sc->nr_to_scan); spin_unlock(&rpc_credcache_lock); rpcauth_destroy_credlist(&free); - return res; + + return freed; +} + +static unsigned long +rpcauth_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) + +{ + return (number_cred_unused / 100) * sysctl_vfs_cache_pressure; } /* @@ -784,7 +817,8 @@ rpcauth_uptodatecred(struct rpc_task *task) } static struct shrinker rpc_cred_shrinker = { - .shrink = rpcauth_cache_shrinker, + .count_objects = rpcauth_cache_shrink_count, + .scan_objects = rpcauth_cache_shrink_scan, .seeks = DEFAULT_SEEKS, }; diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index b6badafc6494..ed04869b2d4f 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -89,6 +89,7 @@ generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) gcred->acred.uid = acred->uid; gcred->acred.gid = acred->gid; gcred->acred.group_info = acred->group_info; + gcred->acred.ac_flags = 0; if (gcred->acred.group_info != NULL) get_group_info(gcred->acred.group_info); gcred->acred.machine_cred = acred->machine_cred; @@ -182,11 +183,78 @@ void rpc_destroy_generic_auth(void) rpcauth_destroy_credcache(&generic_auth); } +/* + * Test the the current time (now) against the underlying credential key expiry + * minus a timeout and setup notification. + * + * The normal case: + * If 'now' is before the key expiry minus RPC_KEY_EXPIRE_TIMEO, set + * the RPC_CRED_NOTIFY_TIMEOUT flag to setup the underlying credential + * rpc_credops crmatch routine to notify this generic cred when it's key + * expiration is within RPC_KEY_EXPIRE_TIMEO, and return 0. + * + * The error case: + * If the underlying cred lookup fails, return -EACCES. + * + * The 'almost' error case: + * If 'now' is within key expiry minus RPC_KEY_EXPIRE_TIMEO, but not within + * key expiry minus RPC_KEY_EXPIRE_FAIL, set the RPC_CRED_EXPIRE_SOON bit + * on the acred ac_flags and return 0. + */ +static int +generic_key_timeout(struct rpc_auth *auth, struct rpc_cred *cred) +{ + struct auth_cred *acred = &container_of(cred, struct generic_cred, + gc_base)->acred; + struct rpc_cred *tcred; + int ret = 0; + + + /* Fast track for non crkey_timeout (no key) underlying credentials */ + if (test_bit(RPC_CRED_NO_CRKEY_TIMEOUT, &acred->ac_flags)) + return 0; + + /* Fast track for the normal case */ + if (test_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags)) + return 0; + + /* lookup_cred either returns a valid referenced rpc_cred, or PTR_ERR */ + tcred = auth->au_ops->lookup_cred(auth, acred, 0); + if (IS_ERR(tcred)) + return -EACCES; + + if (!tcred->cr_ops->crkey_timeout) { + set_bit(RPC_CRED_NO_CRKEY_TIMEOUT, &acred->ac_flags); + ret = 0; + goto out_put; + } + + /* Test for the almost error case */ + ret = tcred->cr_ops->crkey_timeout(tcred); + if (ret != 0) { + set_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); + ret = 0; + } else { + /* In case underlying cred key has been reset */ + if (test_and_clear_bit(RPC_CRED_KEY_EXPIRE_SOON, + &acred->ac_flags)) + dprintk("RPC: UID %d Credential key reset\n", + from_kuid(&init_user_ns, tcred->cr_uid)); + /* set up fasttrack for the normal case */ + set_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags); + } + +out_put: + put_rpccred(tcred); + return ret; +} + static const struct rpc_authops generic_auth_ops = { .owner = THIS_MODULE, .au_name = "Generic", .lookup_cred = generic_lookup_cred, .crcreate = generic_create_cred, + .key_timeout = generic_key_timeout, }; static struct rpc_auth generic_auth = { @@ -194,9 +262,23 @@ static struct rpc_auth generic_auth = { .au_count = ATOMIC_INIT(0), }; +static bool generic_key_to_expire(struct rpc_cred *cred) +{ + struct auth_cred *acred = &container_of(cred, struct generic_cred, + gc_base)->acred; + bool ret; + + get_rpccred(cred); + ret = test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); + put_rpccred(cred); + + return ret; +} + static const struct rpc_credops generic_credops = { .cr_name = "Generic cred", .crdestroy = generic_destroy_cred, .crbind = generic_bind_cred, .crmatch = generic_match, + .crkey_to_expire = generic_key_to_expire, }; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index fc2f78d6a9b4..084656671d6e 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -51,6 +51,7 @@ #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/gss_api.h> #include <asm/uaccess.h> +#include <linux/hashtable.h> #include "../netns.h" @@ -62,6 +63,9 @@ static const struct rpc_credops gss_nullops; #define GSS_RETRY_EXPIRED 5 static unsigned int gss_expired_cred_retry_delay = GSS_RETRY_EXPIRED; +#define GSS_KEY_EXPIRE_TIMEO 240 +static unsigned int gss_key_expire_timeo = GSS_KEY_EXPIRE_TIMEO; + #ifdef RPC_DEBUG # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -71,19 +75,33 @@ static unsigned int gss_expired_cred_retry_delay = GSS_RETRY_EXPIRED; * using integrity (two 4-byte integers): */ #define GSS_VERF_SLACK 100 +static DEFINE_HASHTABLE(gss_auth_hash_table, 4); +static DEFINE_SPINLOCK(gss_auth_hash_lock); + +struct gss_pipe { + struct rpc_pipe_dir_object pdo; + struct rpc_pipe *pipe; + struct rpc_clnt *clnt; + const char *name; + struct kref kref; +}; + struct gss_auth { struct kref kref; + struct hlist_node hash; struct rpc_auth rpc_auth; struct gss_api_mech *mech; enum rpc_gss_svc service; struct rpc_clnt *client; + struct net *net; /* * There are two upcall pipes; dentry[1], named "gssd", is used * for the new text-based upcall; dentry[0] is named after the * mechanism (for example, "krb5") and exists for * backwards-compatibility with older gssd's. */ - struct rpc_pipe *pipe[2]; + struct gss_pipe *gss_pipe[2]; + const char *target_name; }; /* pipe_version >= 0 if and only if someone has a pipe open. */ @@ -294,7 +312,7 @@ static void put_pipe_version(struct net *net) static void gss_release_msg(struct gss_upcall_msg *gss_msg) { - struct net *net = rpc_net_ns(gss_msg->auth->client); + struct net *net = gss_msg->auth->net; if (!atomic_dec_and_test(&gss_msg->count)) return; put_pipe_version(net); @@ -406,8 +424,8 @@ static void gss_encode_v0_msg(struct gss_upcall_msg *gss_msg) } static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, - struct rpc_clnt *clnt, - const char *service_name) + const char *service_name, + const char *target_name) { struct gss_api_mech *mech = gss_msg->auth->mech; char *p = gss_msg->databuf; @@ -417,8 +435,8 @@ static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, mech->gm_name, from_kuid(&init_user_ns, gss_msg->uid)); p += gss_msg->msg.len; - if (clnt->cl_principal) { - len = sprintf(p, "target=%s ", clnt->cl_principal); + if (target_name) { + len = sprintf(p, "target=%s ", target_name); p += len; gss_msg->msg.len += len; } @@ -439,21 +457,8 @@ static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, BUG_ON(gss_msg->msg.len > UPCALL_BUF_LEN); } -static void gss_encode_msg(struct gss_upcall_msg *gss_msg, - struct rpc_clnt *clnt, - const char *service_name) -{ - struct net *net = rpc_net_ns(clnt); - struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); - - if (sn->pipe_version == 0) - gss_encode_v0_msg(gss_msg); - else /* pipe_version == 1 */ - gss_encode_v1_msg(gss_msg, clnt, service_name); -} - static struct gss_upcall_msg * -gss_alloc_msg(struct gss_auth *gss_auth, struct rpc_clnt *clnt, +gss_alloc_msg(struct gss_auth *gss_auth, kuid_t uid, const char *service_name) { struct gss_upcall_msg *gss_msg; @@ -462,31 +467,36 @@ gss_alloc_msg(struct gss_auth *gss_auth, struct rpc_clnt *clnt, gss_msg = kzalloc(sizeof(*gss_msg), GFP_NOFS); if (gss_msg == NULL) return ERR_PTR(-ENOMEM); - vers = get_pipe_version(rpc_net_ns(clnt)); + vers = get_pipe_version(gss_auth->net); if (vers < 0) { kfree(gss_msg); return ERR_PTR(vers); } - gss_msg->pipe = gss_auth->pipe[vers]; + gss_msg->pipe = gss_auth->gss_pipe[vers]->pipe; INIT_LIST_HEAD(&gss_msg->list); rpc_init_wait_queue(&gss_msg->rpc_waitqueue, "RPCSEC_GSS upcall waitq"); init_waitqueue_head(&gss_msg->waitqueue); atomic_set(&gss_msg->count, 1); gss_msg->uid = uid; gss_msg->auth = gss_auth; - gss_encode_msg(gss_msg, clnt, service_name); + switch (vers) { + case 0: + gss_encode_v0_msg(gss_msg); + default: + gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); + }; return gss_msg; } static struct gss_upcall_msg * -gss_setup_upcall(struct rpc_clnt *clnt, struct gss_auth *gss_auth, struct rpc_cred *cred) +gss_setup_upcall(struct gss_auth *gss_auth, struct rpc_cred *cred) { struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base); struct gss_upcall_msg *gss_new, *gss_msg; kuid_t uid = cred->cr_uid; - gss_new = gss_alloc_msg(gss_auth, clnt, uid, gss_cred->gc_principal); + gss_new = gss_alloc_msg(gss_auth, uid, gss_cred->gc_principal); if (IS_ERR(gss_new)) return gss_new; gss_msg = gss_add_msg(gss_new); @@ -527,7 +537,7 @@ gss_refresh_upcall(struct rpc_task *task) dprintk("RPC: %5u %s for uid %u\n", task->tk_pid, __func__, from_kuid(&init_user_ns, cred->cr_uid)); - gss_msg = gss_setup_upcall(task->tk_client, gss_auth, cred); + gss_msg = gss_setup_upcall(gss_auth, cred); if (PTR_ERR(gss_msg) == -EAGAIN) { /* XXX: warning on the first, under the assumption we * shouldn't normally hit this case on a refresh. */ @@ -566,7 +576,7 @@ out: static inline int gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred) { - struct net *net = rpc_net_ns(gss_auth->client); + struct net *net = gss_auth->net; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_pipe *pipe; struct rpc_cred *cred = &gss_cred->gc_base; @@ -583,7 +593,7 @@ retry: timeout = 15 * HZ; if (!sn->gssd_running) timeout = HZ >> 2; - gss_msg = gss_setup_upcall(gss_auth->client, gss_auth, cred); + gss_msg = gss_setup_upcall(gss_auth, cred); if (PTR_ERR(gss_msg) == -EAGAIN) { err = wait_event_interruptible_timeout(pipe_version_waitqueue, sn->pipe_version >= 0, timeout); @@ -797,83 +807,153 @@ gss_pipe_destroy_msg(struct rpc_pipe_msg *msg) } } -static void gss_pipes_dentries_destroy(struct rpc_auth *auth) +static void gss_pipe_dentry_destroy(struct dentry *dir, + struct rpc_pipe_dir_object *pdo) { - struct gss_auth *gss_auth; + struct gss_pipe *gss_pipe = pdo->pdo_data; + struct rpc_pipe *pipe = gss_pipe->pipe; - gss_auth = container_of(auth, struct gss_auth, rpc_auth); - if (gss_auth->pipe[0]->dentry) - rpc_unlink(gss_auth->pipe[0]->dentry); - if (gss_auth->pipe[1]->dentry) - rpc_unlink(gss_auth->pipe[1]->dentry); + if (pipe->dentry != NULL) { + rpc_unlink(pipe->dentry); + pipe->dentry = NULL; + } } -static int gss_pipes_dentries_create(struct rpc_auth *auth) +static int gss_pipe_dentry_create(struct dentry *dir, + struct rpc_pipe_dir_object *pdo) { - int err; - struct gss_auth *gss_auth; - struct rpc_clnt *clnt; + struct gss_pipe *p = pdo->pdo_data; + struct dentry *dentry; - gss_auth = container_of(auth, struct gss_auth, rpc_auth); - clnt = gss_auth->client; - - gss_auth->pipe[1]->dentry = rpc_mkpipe_dentry(clnt->cl_dentry, - "gssd", - clnt, gss_auth->pipe[1]); - if (IS_ERR(gss_auth->pipe[1]->dentry)) - return PTR_ERR(gss_auth->pipe[1]->dentry); - gss_auth->pipe[0]->dentry = rpc_mkpipe_dentry(clnt->cl_dentry, - gss_auth->mech->gm_name, - clnt, gss_auth->pipe[0]); - if (IS_ERR(gss_auth->pipe[0]->dentry)) { - err = PTR_ERR(gss_auth->pipe[0]->dentry); - goto err_unlink_pipe_1; - } + dentry = rpc_mkpipe_dentry(dir, p->name, p->clnt, p->pipe); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + p->pipe->dentry = dentry; return 0; +} -err_unlink_pipe_1: - rpc_unlink(gss_auth->pipe[1]->dentry); - return err; +static const struct rpc_pipe_dir_object_ops gss_pipe_dir_object_ops = { + .create = gss_pipe_dentry_create, + .destroy = gss_pipe_dentry_destroy, +}; + +static struct gss_pipe *gss_pipe_alloc(struct rpc_clnt *clnt, + const char *name, + const struct rpc_pipe_ops *upcall_ops) +{ + struct gss_pipe *p; + int err = -ENOMEM; + + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (p == NULL) + goto err; + p->pipe = rpc_mkpipe_data(upcall_ops, RPC_PIPE_WAIT_FOR_OPEN); + if (IS_ERR(p->pipe)) { + err = PTR_ERR(p->pipe); + goto err_free_gss_pipe; + } + p->name = name; + p->clnt = clnt; + kref_init(&p->kref); + rpc_init_pipe_dir_object(&p->pdo, + &gss_pipe_dir_object_ops, + p); + return p; +err_free_gss_pipe: + kfree(p); +err: + return ERR_PTR(err); +} + +struct gss_alloc_pdo { + struct rpc_clnt *clnt; + const char *name; + const struct rpc_pipe_ops *upcall_ops; +}; + +static int gss_pipe_match_pdo(struct rpc_pipe_dir_object *pdo, void *data) +{ + struct gss_pipe *gss_pipe; + struct gss_alloc_pdo *args = data; + + if (pdo->pdo_ops != &gss_pipe_dir_object_ops) + return 0; + gss_pipe = container_of(pdo, struct gss_pipe, pdo); + if (strcmp(gss_pipe->name, args->name) != 0) + return 0; + if (!kref_get_unless_zero(&gss_pipe->kref)) + return 0; + return 1; +} + +static struct rpc_pipe_dir_object *gss_pipe_alloc_pdo(void *data) +{ + struct gss_pipe *gss_pipe; + struct gss_alloc_pdo *args = data; + + gss_pipe = gss_pipe_alloc(args->clnt, args->name, args->upcall_ops); + if (!IS_ERR(gss_pipe)) + return &gss_pipe->pdo; + return NULL; } -static void gss_pipes_dentries_destroy_net(struct rpc_clnt *clnt, - struct rpc_auth *auth) +static struct gss_pipe *gss_pipe_get(struct rpc_clnt *clnt, + const char *name, + const struct rpc_pipe_ops *upcall_ops) { struct net *net = rpc_net_ns(clnt); - struct super_block *sb; + struct rpc_pipe_dir_object *pdo; + struct gss_alloc_pdo args = { + .clnt = clnt, + .name = name, + .upcall_ops = upcall_ops, + }; - sb = rpc_get_sb_net(net); - if (sb) { - if (clnt->cl_dentry) - gss_pipes_dentries_destroy(auth); - rpc_put_sb_net(net); - } + pdo = rpc_find_or_alloc_pipe_dir_object(net, + &clnt->cl_pipedir_objects, + gss_pipe_match_pdo, + gss_pipe_alloc_pdo, + &args); + if (pdo != NULL) + return container_of(pdo, struct gss_pipe, pdo); + return ERR_PTR(-ENOMEM); } -static int gss_pipes_dentries_create_net(struct rpc_clnt *clnt, - struct rpc_auth *auth) +static void __gss_pipe_free(struct gss_pipe *p) { + struct rpc_clnt *clnt = p->clnt; struct net *net = rpc_net_ns(clnt); - struct super_block *sb; - int err = 0; - sb = rpc_get_sb_net(net); - if (sb) { - if (clnt->cl_dentry) - err = gss_pipes_dentries_create(auth); - rpc_put_sb_net(net); - } - return err; + rpc_remove_pipe_dir_object(net, + &clnt->cl_pipedir_objects, + &p->pdo); + rpc_destroy_pipe_data(p->pipe); + kfree(p); +} + +static void __gss_pipe_release(struct kref *kref) +{ + struct gss_pipe *p = container_of(kref, struct gss_pipe, kref); + + __gss_pipe_free(p); +} + +static void gss_pipe_free(struct gss_pipe *p) +{ + if (p != NULL) + kref_put(&p->kref, __gss_pipe_release); } /* * NOTE: we have the opportunity to use different * parameters based on the input flavor (which must be a pseudoflavor) */ -static struct rpc_auth * -gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) +static struct gss_auth * +gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { + rpc_authflavor_t flavor = args->pseudoflavor; struct gss_auth *gss_auth; + struct gss_pipe *gss_pipe; struct rpc_auth * auth; int err = -ENOMEM; /* XXX? */ @@ -883,12 +963,20 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) return ERR_PTR(err); if (!(gss_auth = kmalloc(sizeof(*gss_auth), GFP_KERNEL))) goto out_dec; + INIT_HLIST_NODE(&gss_auth->hash); + gss_auth->target_name = NULL; + if (args->target_name) { + gss_auth->target_name = kstrdup(args->target_name, GFP_KERNEL); + if (gss_auth->target_name == NULL) + goto err_free; + } gss_auth->client = clnt; + gss_auth->net = get_net(rpc_net_ns(clnt)); err = -EINVAL; gss_auth->mech = gss_mech_get_by_pseudoflavor(flavor); if (!gss_auth->mech) { dprintk("RPC: Pseudoflavor %d not found!\n", flavor); - goto err_free; + goto err_put_net; } gss_auth->service = gss_pseudoflavor_to_service(gss_auth->mech, flavor); if (gss_auth->service == 0) @@ -901,42 +989,41 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) atomic_set(&auth->au_count, 1); kref_init(&gss_auth->kref); + err = rpcauth_init_credcache(auth); + if (err) + goto err_put_mech; /* * Note: if we created the old pipe first, then someone who * examined the directory at the right moment might conclude * that we supported only the old pipe. So we instead create * the new pipe first. */ - gss_auth->pipe[1] = rpc_mkpipe_data(&gss_upcall_ops_v1, - RPC_PIPE_WAIT_FOR_OPEN); - if (IS_ERR(gss_auth->pipe[1])) { - err = PTR_ERR(gss_auth->pipe[1]); - goto err_put_mech; + gss_pipe = gss_pipe_get(clnt, "gssd", &gss_upcall_ops_v1); + if (IS_ERR(gss_pipe)) { + err = PTR_ERR(gss_pipe); + goto err_destroy_credcache; } + gss_auth->gss_pipe[1] = gss_pipe; - gss_auth->pipe[0] = rpc_mkpipe_data(&gss_upcall_ops_v0, - RPC_PIPE_WAIT_FOR_OPEN); - if (IS_ERR(gss_auth->pipe[0])) { - err = PTR_ERR(gss_auth->pipe[0]); + gss_pipe = gss_pipe_get(clnt, gss_auth->mech->gm_name, + &gss_upcall_ops_v0); + if (IS_ERR(gss_pipe)) { + err = PTR_ERR(gss_pipe); goto err_destroy_pipe_1; } - err = gss_pipes_dentries_create_net(clnt, auth); - if (err) - goto err_destroy_pipe_0; - err = rpcauth_init_credcache(auth); - if (err) - goto err_unlink_pipes; + gss_auth->gss_pipe[0] = gss_pipe; - return auth; -err_unlink_pipes: - gss_pipes_dentries_destroy_net(clnt, auth); -err_destroy_pipe_0: - rpc_destroy_pipe_data(gss_auth->pipe[0]); + return gss_auth; err_destroy_pipe_1: - rpc_destroy_pipe_data(gss_auth->pipe[1]); + gss_pipe_free(gss_auth->gss_pipe[1]); +err_destroy_credcache: + rpcauth_destroy_credcache(auth); err_put_mech: gss_mech_put(gss_auth->mech); +err_put_net: + put_net(gss_auth->net); err_free: + kfree(gss_auth->target_name); kfree(gss_auth); out_dec: module_put(THIS_MODULE); @@ -946,10 +1033,11 @@ out_dec: static void gss_free(struct gss_auth *gss_auth) { - gss_pipes_dentries_destroy_net(gss_auth->client, &gss_auth->rpc_auth); - rpc_destroy_pipe_data(gss_auth->pipe[0]); - rpc_destroy_pipe_data(gss_auth->pipe[1]); + gss_pipe_free(gss_auth->gss_pipe[0]); + gss_pipe_free(gss_auth->gss_pipe[1]); gss_mech_put(gss_auth->mech); + put_net(gss_auth->net); + kfree(gss_auth->target_name); kfree(gss_auth); module_put(THIS_MODULE); @@ -966,18 +1054,113 @@ gss_free_callback(struct kref *kref) static void gss_destroy(struct rpc_auth *auth) { - struct gss_auth *gss_auth; + struct gss_auth *gss_auth = container_of(auth, + struct gss_auth, rpc_auth); dprintk("RPC: destroying GSS authenticator %p flavor %d\n", auth, auth->au_flavor); + if (hash_hashed(&gss_auth->hash)) { + spin_lock(&gss_auth_hash_lock); + hash_del(&gss_auth->hash); + spin_unlock(&gss_auth_hash_lock); + } + + gss_pipe_free(gss_auth->gss_pipe[0]); + gss_auth->gss_pipe[0] = NULL; + gss_pipe_free(gss_auth->gss_pipe[1]); + gss_auth->gss_pipe[1] = NULL; rpcauth_destroy_credcache(auth); - gss_auth = container_of(auth, struct gss_auth, rpc_auth); kref_put(&gss_auth->kref, gss_free_callback); } /* + * Auths may be shared between rpc clients that were cloned from a + * common client with the same xprt, if they also share the flavor and + * target_name. + * + * The auth is looked up from the oldest parent sharing the same + * cl_xprt, and the auth itself references only that common parent + * (which is guaranteed to last as long as any of its descendants). + */ +static struct gss_auth * +gss_auth_find_or_add_hashed(struct rpc_auth_create_args *args, + struct rpc_clnt *clnt, + struct gss_auth *new) +{ + struct gss_auth *gss_auth; + unsigned long hashval = (unsigned long)clnt; + + spin_lock(&gss_auth_hash_lock); + hash_for_each_possible(gss_auth_hash_table, + gss_auth, + hash, + hashval) { + if (gss_auth->client != clnt) + continue; + if (gss_auth->rpc_auth.au_flavor != args->pseudoflavor) + continue; + if (gss_auth->target_name != args->target_name) { + if (gss_auth->target_name == NULL) + continue; + if (args->target_name == NULL) + continue; + if (strcmp(gss_auth->target_name, args->target_name)) + continue; + } + if (!atomic_inc_not_zero(&gss_auth->rpc_auth.au_count)) + continue; + goto out; + } + if (new) + hash_add(gss_auth_hash_table, &new->hash, hashval); + gss_auth = new; +out: + spin_unlock(&gss_auth_hash_lock); + return gss_auth; +} + +static struct gss_auth * +gss_create_hashed(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +{ + struct gss_auth *gss_auth; + struct gss_auth *new; + + gss_auth = gss_auth_find_or_add_hashed(args, clnt, NULL); + if (gss_auth != NULL) + goto out; + new = gss_create_new(args, clnt); + if (IS_ERR(new)) + return new; + gss_auth = gss_auth_find_or_add_hashed(args, clnt, new); + if (gss_auth != new) + gss_destroy(&new->rpc_auth); +out: + return gss_auth; +} + +static struct rpc_auth * +gss_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +{ + struct gss_auth *gss_auth; + struct rpc_xprt *xprt = rcu_access_pointer(clnt->cl_xprt); + + while (clnt != clnt->cl_parent) { + struct rpc_clnt *parent = clnt->cl_parent; + /* Find the original parent for this transport */ + if (rcu_access_pointer(parent->cl_xprt) != xprt) + break; + clnt = parent; + } + + gss_auth = gss_create_hashed(args, clnt); + if (IS_ERR(gss_auth)) + return ERR_CAST(gss_auth); + return &gss_auth->rpc_auth; +} + +/* * gss_destroying_context will cause the RPCSEC_GSS to send a NULL RPC call * to the server with the GSS control procedure field set to * RPC_GSS_PROC_DESTROY. This should normally cause the server to release @@ -1126,10 +1309,32 @@ gss_cred_init(struct rpc_auth *auth, struct rpc_cred *cred) return err; } +/* + * Returns -EACCES if GSS context is NULL or will expire within the + * timeout (miliseconds) + */ +static int +gss_key_timeout(struct rpc_cred *rc) +{ + struct gss_cred *gss_cred = container_of(rc, struct gss_cred, gc_base); + unsigned long now = jiffies; + unsigned long expire; + + if (gss_cred->gc_ctx == NULL) + return -EACCES; + + expire = gss_cred->gc_ctx->gc_expiry - (gss_key_expire_timeo * HZ); + + if (time_after(now, expire)) + return -EACCES; + return 0; +} + static int gss_match(struct auth_cred *acred, struct rpc_cred *rc, int flags) { struct gss_cred *gss_cred = container_of(rc, struct gss_cred, gc_base); + int ret; if (test_bit(RPCAUTH_CRED_NEW, &rc->cr_flags)) goto out; @@ -1142,11 +1347,26 @@ out: if (acred->principal != NULL) { if (gss_cred->gc_principal == NULL) return 0; - return strcmp(acred->principal, gss_cred->gc_principal) == 0; + ret = strcmp(acred->principal, gss_cred->gc_principal) == 0; + goto check_expire; } if (gss_cred->gc_principal != NULL) return 0; - return uid_eq(rc->cr_uid, acred->uid); + ret = uid_eq(rc->cr_uid, acred->uid); + +check_expire: + if (ret == 0) + return ret; + + /* Notify acred users of GSS context expiration timeout */ + if (test_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags) && + (gss_key_timeout(rc) != 0)) { + /* test will now be done from generic cred */ + test_and_clear_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags); + /* tell NFS layer that key will expire soon */ + set_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); + } + return ret; } /* @@ -1292,6 +1512,7 @@ gss_validate(struct rpc_task *task, __be32 *p) struct xdr_netobj mic; u32 flav,len; u32 maj_stat; + __be32 *ret = ERR_PTR(-EIO); dprintk("RPC: %5u %s\n", task->tk_pid, __func__); @@ -1307,6 +1528,7 @@ gss_validate(struct rpc_task *task, __be32 *p) mic.data = (u8 *)p; mic.len = len; + ret = ERR_PTR(-EACCES); maj_stat = gss_verify_mic(ctx->gc_gss_ctx, &verf_buf, &mic); if (maj_stat == GSS_S_CONTEXT_EXPIRED) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); @@ -1324,8 +1546,9 @@ gss_validate(struct rpc_task *task, __be32 *p) return p + XDR_QUADLEN(len); out_bad: gss_put_ctx(ctx); - dprintk("RPC: %5u %s failed.\n", task->tk_pid, __func__); - return NULL; + dprintk("RPC: %5u %s failed ret %ld.\n", task->tk_pid, __func__, + PTR_ERR(ret)); + return ret; } static void gss_wrap_req_encode(kxdreproc_t encode, struct rpc_rqst *rqstp, @@ -1657,8 +1880,6 @@ static const struct rpc_authops authgss_ops = { .destroy = gss_destroy, .lookup_cred = gss_lookup_cred, .crcreate = gss_create_cred, - .pipes_create = gss_pipes_dentries_create, - .pipes_destroy = gss_pipes_dentries_destroy, .list_pseudoflavors = gss_mech_list_pseudoflavors, .info2flavor = gss_mech_info2flavor, .flavor2info = gss_mech_flavor2info, @@ -1675,6 +1896,7 @@ static const struct rpc_credops gss_credops = { .crvalidate = gss_validate, .crwrap_req = gss_wrap_req, .crunwrap_resp = gss_unwrap_resp, + .crkey_timeout = gss_key_timeout, }; static const struct rpc_credops gss_nullops = { @@ -1762,5 +1984,12 @@ module_param_named(expired_cred_retry_delay, MODULE_PARM_DESC(expired_cred_retry_delay, "Timeout (in seconds) until " "the RPC engine retries an expired credential"); +module_param_named(key_expire_timeo, + gss_key_expire_timeo, + uint, 0644); +MODULE_PARM_DESC(key_expire_timeo, "Time (in seconds) at the end of a " + "credential keys lifetime where the NFS layer cleans up " + "prior to key expiration"); + module_init(init_rpcsec_gss) module_exit(exit_rpcsec_gss) diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index af7ffd447fee..f1eb0d16666c 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -213,6 +213,26 @@ static int gssp_call(struct net *net, struct rpc_message *msg) return status; } +static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg) +{ + int i; + + for (i = 0; i < arg->npages && arg->pages[i]; i++) + __free_page(arg->pages[i]); +} + +static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg) +{ + arg->npages = DIV_ROUND_UP(NGROUPS_MAX * 4, PAGE_SIZE); + arg->pages = kzalloc(arg->npages * sizeof(struct page *), GFP_KERNEL); + /* + * XXX: actual pages are allocated by xdr layer in + * xdr_partial_copy_from_skb. + */ + if (!arg->pages) + return -ENOMEM; + return 0; +} /* * Public functions @@ -261,10 +281,16 @@ int gssp_accept_sec_context_upcall(struct net *net, arg.context_handle = &ctxh; res.output_token->len = GSSX_max_output_token_sz; + ret = gssp_alloc_receive_pages(&arg); + if (ret) + return ret; + /* use nfs/ for targ_name ? */ ret = gssp_call(net, &msg); + gssp_free_receive_pages(&arg); + /* we need to fetch all data even in case of error so * that we can free special strctures is they have been allocated */ data->major_status = res.status.major_status; diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 3c85d1c8a028..f0f78c5f1c7d 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -166,14 +166,15 @@ static int dummy_dec_opt_array(struct xdr_stream *xdr, return 0; } -static int get_s32(void **p, void *max, s32 *res) +static int get_host_u32(struct xdr_stream *xdr, u32 *res) { - void *base = *p; - void *next = (void *)((char *)base + sizeof(s32)); - if (unlikely(next > max || next < base)) + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (!p) return -EINVAL; - memcpy(res, base, sizeof(s32)); - *p = next; + /* Contents of linux creds are all host-endian: */ + memcpy(res, p, sizeof(u32)); return 0; } @@ -182,9 +183,9 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, { u32 length; __be32 *p; - void *q, *end; - s32 tmp; - int N, i, err; + u32 tmp; + u32 N; + int i, err; p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) @@ -192,33 +193,28 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, length = be32_to_cpup(p); - /* FIXME: we do not want to use the scratch buffer for this one - * may need to use functions that allows us to access an io vector - * directly */ - p = xdr_inline_decode(xdr, length); - if (unlikely(p == NULL)) + if (length > (3 + NGROUPS_MAX) * sizeof(u32)) return -ENOSPC; - q = p; - end = q + length; - /* uid */ - err = get_s32(&q, end, &tmp); + err = get_host_u32(xdr, &tmp); if (err) return err; creds->cr_uid = make_kuid(&init_user_ns, tmp); /* gid */ - err = get_s32(&q, end, &tmp); + err = get_host_u32(xdr, &tmp); if (err) return err; creds->cr_gid = make_kgid(&init_user_ns, tmp); /* number of additional gid's */ - err = get_s32(&q, end, &tmp); + err = get_host_u32(xdr, &tmp); if (err) return err; N = tmp; + if ((3 + N) * sizeof(u32) != length) + return -EINVAL; creds->cr_group_info = groups_alloc(N); if (creds->cr_group_info == NULL) return -ENOMEM; @@ -226,7 +222,7 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, /* gid's */ for (i = 0; i < N; i++) { kgid_t kgid; - err = get_s32(&q, end, &tmp); + err = get_host_u32(xdr, &tmp); if (err) goto out_free_groups; err = -EINVAL; @@ -784,6 +780,9 @@ void gssx_enc_accept_sec_context(struct rpc_rqst *req, /* arg->options */ err = dummy_enc_opt_array(xdr, &arg->options); + xdr_inline_pages(&req->rq_rcv_buf, + PAGE_SIZE/2 /* pretty arbitrary */, + arg->pages, 0 /* page base */, arg->npages * PAGE_SIZE); done: if (err) dprintk("RPC: gssx_enc_accept_sec_context: %d\n", err); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 1c98b27d870c..685a688f3d8a 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -147,6 +147,8 @@ struct gssx_arg_accept_sec_context { struct gssx_cb *input_cb; u32 ret_deleg_cred; struct gssx_option_array options; + struct page **pages; + unsigned int npages; }; struct gssx_res_accept_sec_context { @@ -240,7 +242,8 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, 2 * GSSX_max_princ_sz + \ 8 + 8 + 4 + 4 + 4) #define GSSX_max_output_token_sz 1024 -#define GSSX_max_creds_sz (4 + 4 + 4 + NGROUPS_MAX * 4) +/* grouplist not included; we allocate separate pages for that: */ +#define GSSX_max_creds_sz (4 + 4 + 4 /* + NGROUPS_MAX*4 */) #define GSSX_RES_accept_sec_context_sz (GSSX_default_status_sz + \ GSSX_default_ctx_sz + \ GSSX_max_output_token_sz + \ diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index a5c36c01707b..f0ebe07978a2 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -18,7 +18,7 @@ static struct rpc_auth null_auth; static struct rpc_cred null_cred; static struct rpc_auth * -nul_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) +nul_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { atomic_inc(&null_auth.au_count); return &null_auth; @@ -88,13 +88,13 @@ nul_validate(struct rpc_task *task, __be32 *p) flavor = ntohl(*p++); if (flavor != RPC_AUTH_NULL) { printk("RPC: bad verf flavor: %u\n", flavor); - return NULL; + return ERR_PTR(-EIO); } size = ntohl(*p++); if (size != 0) { printk("RPC: bad verf size: %u\n", size); - return NULL; + return ERR_PTR(-EIO); } return p; diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index dc37021fc3e5..d5d692366294 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -33,7 +33,7 @@ static struct rpc_auth unix_auth; static const struct rpc_credops unix_credops; static struct rpc_auth * -unx_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) +unx_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { dprintk("RPC: creating UNIX authenticator for client %p\n", clnt); @@ -192,13 +192,13 @@ unx_validate(struct rpc_task *task, __be32 *p) flavor != RPC_AUTH_UNIX && flavor != RPC_AUTH_SHORT) { printk("RPC: bad verf flavor: %u\n", flavor); - return NULL; + return ERR_PTR(-EIO); } size = ntohl(*p++); if (size > RPC_MAX_AUTH_SIZE) { printk("RPC: giant verf size: %u\n", size); - return NULL; + return ERR_PTR(-EIO); } task->tk_rqstp->rq_cred->cr_auth->au_rslack = (size >> 2) + 2; p += (size >> 2); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index ecbc4e3d83ad..77479606a971 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -102,12 +102,7 @@ static void rpc_unregister_client(struct rpc_clnt *clnt) static void __rpc_clnt_remove_pipedir(struct rpc_clnt *clnt) { - if (clnt->cl_dentry) { - if (clnt->cl_auth && clnt->cl_auth->au_ops->pipes_destroy) - clnt->cl_auth->au_ops->pipes_destroy(clnt->cl_auth); - rpc_remove_client_dir(clnt->cl_dentry); - } - clnt->cl_dentry = NULL; + rpc_remove_client_dir(clnt); } static void rpc_clnt_remove_pipedir(struct rpc_clnt *clnt) @@ -123,10 +118,10 @@ static void rpc_clnt_remove_pipedir(struct rpc_clnt *clnt) } static struct dentry *rpc_setup_pipedir_sb(struct super_block *sb, - struct rpc_clnt *clnt, - const char *dir_name) + struct rpc_clnt *clnt) { static uint32_t clntid; + const char *dir_name = clnt->cl_program->pipe_dir_name; char name[15]; struct dentry *dir, *dentry; @@ -153,28 +148,35 @@ static struct dentry *rpc_setup_pipedir_sb(struct super_block *sb, } static int -rpc_setup_pipedir(struct rpc_clnt *clnt, const char *dir_name, - struct super_block *pipefs_sb) +rpc_setup_pipedir(struct super_block *pipefs_sb, struct rpc_clnt *clnt) { struct dentry *dentry; - clnt->cl_dentry = NULL; - if (dir_name == NULL) - return 0; - dentry = rpc_setup_pipedir_sb(pipefs_sb, clnt, dir_name); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); - clnt->cl_dentry = dentry; + if (clnt->cl_program->pipe_dir_name != NULL) { + dentry = rpc_setup_pipedir_sb(pipefs_sb, clnt); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + } return 0; } -static inline int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event) +static int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event) { - if (((event == RPC_PIPEFS_MOUNT) && clnt->cl_dentry) || - ((event == RPC_PIPEFS_UMOUNT) && !clnt->cl_dentry)) - return 1; - if ((event == RPC_PIPEFS_MOUNT) && atomic_read(&clnt->cl_count) == 0) + if (clnt->cl_program->pipe_dir_name == NULL) return 1; + + switch (event) { + case RPC_PIPEFS_MOUNT: + if (clnt->cl_pipedir_objects.pdh_dentry != NULL) + return 1; + if (atomic_read(&clnt->cl_count) == 0) + return 1; + break; + case RPC_PIPEFS_UMOUNT: + if (clnt->cl_pipedir_objects.pdh_dentry == NULL) + return 1; + break; + } return 0; } @@ -186,18 +188,11 @@ static int __rpc_clnt_handle_event(struct rpc_clnt *clnt, unsigned long event, switch (event) { case RPC_PIPEFS_MOUNT: - dentry = rpc_setup_pipedir_sb(sb, clnt, - clnt->cl_program->pipe_dir_name); + dentry = rpc_setup_pipedir_sb(sb, clnt); if (!dentry) return -ENOENT; if (IS_ERR(dentry)) return PTR_ERR(dentry); - clnt->cl_dentry = dentry; - if (clnt->cl_auth->au_ops->pipes_create) { - err = clnt->cl_auth->au_ops->pipes_create(clnt->cl_auth); - if (err) - __rpc_clnt_remove_pipedir(clnt); - } break; case RPC_PIPEFS_UMOUNT: __rpc_clnt_remove_pipedir(clnt); @@ -230,8 +225,6 @@ static struct rpc_clnt *rpc_get_client_for_event(struct net *net, int event) spin_lock(&sn->rpc_client_lock); list_for_each_entry(clnt, &sn->all_clients, cl_clients) { - if (clnt->cl_program->pipe_dir_name == NULL) - continue; if (rpc_clnt_skip_event(clnt, event)) continue; spin_unlock(&sn->rpc_client_lock); @@ -282,7 +275,10 @@ static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) static int rpc_client_register(const struct rpc_create_args *args, struct rpc_clnt *clnt) { - const struct rpc_program *program = args->program; + struct rpc_auth_create_args auth_args = { + .pseudoflavor = args->authflavor, + .target_name = args->client_name, + }; struct rpc_auth *auth; struct net *net = rpc_net_ns(clnt); struct super_block *pipefs_sb; @@ -290,7 +286,7 @@ static int rpc_client_register(const struct rpc_create_args *args, pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { - err = rpc_setup_pipedir(clnt, program->pipe_dir_name, pipefs_sb); + err = rpc_setup_pipedir(pipefs_sb, clnt); if (err) goto out; } @@ -299,7 +295,7 @@ static int rpc_client_register(const struct rpc_create_args *args, if (pipefs_sb) rpc_put_sb_net(net); - auth = rpcauth_create(args->authflavor, clnt); + auth = rpcauth_create(&auth_args, clnt); if (IS_ERR(auth)) { dprintk("RPC: Couldn't create auth handle (flavor %u)\n", args->authflavor); @@ -317,7 +313,27 @@ out: return err; } -static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, struct rpc_xprt *xprt) +static DEFINE_IDA(rpc_clids); + +static int rpc_alloc_clid(struct rpc_clnt *clnt) +{ + int clid; + + clid = ida_simple_get(&rpc_clids, 0, 0, GFP_KERNEL); + if (clid < 0) + return clid; + clnt->cl_clid = clid; + return 0; +} + +static void rpc_free_clid(struct rpc_clnt *clnt) +{ + ida_simple_remove(&rpc_clids, clnt->cl_clid); +} + +static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, + struct rpc_xprt *xprt, + struct rpc_clnt *parent) { const struct rpc_program *program = args->program; const struct rpc_version *version; @@ -343,16 +359,20 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru clnt = kzalloc(sizeof(*clnt), GFP_KERNEL); if (!clnt) goto out_err; - clnt->cl_parent = clnt; + clnt->cl_parent = parent ? : clnt; + + err = rpc_alloc_clid(clnt); + if (err) + goto out_no_clid; rcu_assign_pointer(clnt->cl_xprt, xprt); clnt->cl_procinfo = version->procs; clnt->cl_maxproc = version->nrprocs; - clnt->cl_protname = program->name; clnt->cl_prog = args->prognumber ? : program->number; clnt->cl_vers = version->number; clnt->cl_stats = program->stats; clnt->cl_metrics = rpc_alloc_iostats(clnt); + rpc_init_pipe_dir_head(&clnt->cl_pipedir_objects); err = -ENOMEM; if (clnt->cl_metrics == NULL) goto out_no_stats; @@ -372,12 +392,6 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru clnt->cl_rtt = &clnt->cl_rtt_default; rpc_init_rtt(&clnt->cl_rtt_default, clnt->cl_timeout->to_initval); - clnt->cl_principal = NULL; - if (args->client_name) { - clnt->cl_principal = kstrdup(args->client_name, GFP_KERNEL); - if (!clnt->cl_principal) - goto out_no_principal; - } atomic_set(&clnt->cl_count, 1); @@ -387,13 +401,15 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru err = rpc_client_register(args, clnt); if (err) goto out_no_path; + if (parent) + atomic_inc(&parent->cl_count); return clnt; out_no_path: - kfree(clnt->cl_principal); -out_no_principal: rpc_free_iostats(clnt->cl_metrics); out_no_stats: + rpc_free_clid(clnt); +out_no_clid: kfree(clnt); out_err: rpciod_down(); @@ -479,7 +495,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT) xprt->resvport = 0; - clnt = rpc_new_client(args, xprt); + clnt = rpc_new_client(args, xprt, NULL); if (IS_ERR(clnt)) return clnt; @@ -526,15 +542,12 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, goto out_err; args->servername = xprt->servername; - new = rpc_new_client(args, xprt); + new = rpc_new_client(args, xprt, clnt); if (IS_ERR(new)) { err = PTR_ERR(new); goto out_err; } - atomic_inc(&clnt->cl_count); - new->cl_parent = clnt; - /* Turn off autobind on clones */ new->cl_autobind = 0; new->cl_softrtry = clnt->cl_softrtry; @@ -561,7 +574,6 @@ struct rpc_clnt *rpc_clone_client(struct rpc_clnt *clnt) .prognumber = clnt->cl_prog, .version = clnt->cl_vers, .authflavor = clnt->cl_auth->au_flavor, - .client_name = clnt->cl_principal, }; return __rpc_clone_client(&args, clnt); } @@ -583,7 +595,6 @@ rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor) .prognumber = clnt->cl_prog, .version = clnt->cl_vers, .authflavor = flavor, - .client_name = clnt->cl_principal, }; return __rpc_clone_client(&args, clnt); } @@ -629,7 +640,7 @@ void rpc_shutdown_client(struct rpc_clnt *clnt) might_sleep(); dprintk_rcu("RPC: shutting down %s client for %s\n", - clnt->cl_protname, + clnt->cl_program->name, rcu_dereference(clnt->cl_xprt)->servername); while (!list_empty(&clnt->cl_tasks)) { @@ -649,17 +660,17 @@ static void rpc_free_client(struct rpc_clnt *clnt) { dprintk_rcu("RPC: destroying %s client for %s\n", - clnt->cl_protname, + clnt->cl_program->name, rcu_dereference(clnt->cl_xprt)->servername); if (clnt->cl_parent != clnt) rpc_release_client(clnt->cl_parent); rpc_clnt_remove_pipedir(clnt); rpc_unregister_client(clnt); rpc_free_iostats(clnt->cl_metrics); - kfree(clnt->cl_principal); clnt->cl_metrics = NULL; xprt_put(rcu_dereference_raw(clnt->cl_xprt)); rpciod_down(); + rpc_free_clid(clnt); kfree(clnt); } @@ -720,7 +731,6 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old, .prognumber = program->number, .version = vers, .authflavor = old->cl_auth->au_flavor, - .client_name = old->cl_principal, }; struct rpc_clnt *clnt; int err; @@ -1299,7 +1309,7 @@ call_start(struct rpc_task *task) struct rpc_clnt *clnt = task->tk_client; dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid, - clnt->cl_protname, clnt->cl_vers, + clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), (RPC_IS_ASYNC(task) ? "async" : "sync")); @@ -1423,9 +1433,9 @@ call_refreshresult(struct rpc_task *task) return; case -ETIMEDOUT: rpc_delay(task, 3*HZ); - case -EKEYEXPIRED: case -EAGAIN: status = -EACCES; + case -EKEYEXPIRED: if (!task->tk_cred_retry) break; task->tk_cred_retry--; @@ -1912,7 +1922,7 @@ call_status(struct rpc_task *task) default: if (clnt->cl_chatty) printk("%s: RPC call returned error %d\n", - clnt->cl_protname, -status); + clnt->cl_program->name, -status); rpc_exit(task, status); } } @@ -1943,7 +1953,7 @@ call_timeout(struct rpc_task *task) if (clnt->cl_chatty) { rcu_read_lock(); printk(KERN_NOTICE "%s: server %s not responding, timed out\n", - clnt->cl_protname, + clnt->cl_program->name, rcu_dereference(clnt->cl_xprt)->servername); rcu_read_unlock(); } @@ -1959,7 +1969,7 @@ call_timeout(struct rpc_task *task) if (clnt->cl_chatty) { rcu_read_lock(); printk(KERN_NOTICE "%s: server %s not responding, still trying\n", - clnt->cl_protname, + clnt->cl_program->name, rcu_dereference(clnt->cl_xprt)->servername); rcu_read_unlock(); } @@ -1994,7 +2004,7 @@ call_decode(struct rpc_task *task) if (clnt->cl_chatty) { rcu_read_lock(); printk(KERN_NOTICE "%s: server %s OK\n", - clnt->cl_protname, + clnt->cl_program->name, rcu_dereference(clnt->cl_xprt)->servername); rcu_read_unlock(); } @@ -2019,7 +2029,7 @@ call_decode(struct rpc_task *task) goto out_retry; } dprintk("RPC: %s: too small RPC reply size (%d bytes)\n", - clnt->cl_protname, task->tk_status); + clnt->cl_program->name, task->tk_status); task->tk_action = call_timeout; goto out_retry; } @@ -2091,7 +2101,8 @@ rpc_verify_header(struct rpc_task *task) dprintk("RPC: %5u %s: XDR representation not a multiple of" " 4 bytes: 0x%x\n", task->tk_pid, __func__, task->tk_rqstp->rq_rcv_buf.len); - goto out_eio; + error = -EIO; + goto out_err; } if ((len -= 3) < 0) goto out_overflow; @@ -2100,6 +2111,7 @@ rpc_verify_header(struct rpc_task *task) if ((n = ntohl(*p++)) != RPC_REPLY) { dprintk("RPC: %5u %s: not an RPC reply: %x\n", task->tk_pid, __func__, n); + error = -EIO; goto out_garbage; } @@ -2118,7 +2130,8 @@ rpc_verify_header(struct rpc_task *task) dprintk("RPC: %5u %s: RPC call rejected, " "unknown error: %x\n", task->tk_pid, __func__, n); - goto out_eio; + error = -EIO; + goto out_err; } if (--len < 0) goto out_overflow; @@ -2163,9 +2176,11 @@ rpc_verify_header(struct rpc_task *task) task->tk_pid, __func__, n); goto out_err; } - if (!(p = rpcauth_checkverf(task, p))) { - dprintk("RPC: %5u %s: auth check failed\n", - task->tk_pid, __func__); + p = rpcauth_checkverf(task, p); + if (IS_ERR(p)) { + error = PTR_ERR(p); + dprintk("RPC: %5u %s: auth check failed with %d\n", + task->tk_pid, __func__, error); goto out_garbage; /* bad verifier, retry */ } len = p - (__be32 *)iov->iov_base - 1; @@ -2218,8 +2233,6 @@ out_garbage: out_retry: return ERR_PTR(-EAGAIN); } -out_eio: - error = -EIO; out_err: rpc_exit(task, error); dprintk("RPC: %5u %s: call failed with error %d\n", task->tk_pid, @@ -2291,7 +2304,7 @@ static void rpc_show_task(const struct rpc_clnt *clnt, printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%ps q:%s\n", task->tk_pid, task->tk_flags, task->tk_status, clnt, task->tk_rqstp, task->tk_timeout, task->tk_ops, - clnt->cl_protname, clnt->cl_vers, rpc_proc_name(task), + clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), task->tk_action, rpc_waitq); } diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 406859cc68aa..f94567b45bb3 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -409,7 +409,7 @@ rpc_show_info(struct seq_file *m, void *v) rcu_read_lock(); seq_printf(m, "RPC server: %s\n", rcu_dereference(clnt->cl_xprt)->servername); - seq_printf(m, "service: %s (%d) version %d\n", clnt->cl_protname, + seq_printf(m, "service: %s (%d) version %d\n", clnt->cl_program->name, clnt->cl_prog, clnt->cl_vers); seq_printf(m, "address: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); seq_printf(m, "protocol: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PROTO)); @@ -480,23 +480,6 @@ static const struct dentry_operations rpc_dentry_operations = { .d_delete = rpc_delete_dentry, }; -/* - * Lookup the data. This is trivial - if the dentry didn't already - * exist, we know it is negative. - */ -static struct dentry * -rpc_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) -{ - if (dentry->d_name.len > NAME_MAX) - return ERR_PTR(-ENAMETOOLONG); - d_add(dentry, NULL); - return NULL; -} - -static const struct inode_operations rpc_dir_inode_operations = { - .lookup = rpc_lookup, -}; - static struct inode * rpc_get_inode(struct super_block *sb, umode_t mode) { @@ -509,7 +492,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode) switch (mode & S_IFMT) { case S_IFDIR: inode->i_fop = &simple_dir_operations; - inode->i_op = &rpc_dir_inode_operations; + inode->i_op = &simple_dir_inode_operations; inc_nlink(inode); default: break; @@ -901,6 +884,159 @@ rpc_unlink(struct dentry *dentry) } EXPORT_SYMBOL_GPL(rpc_unlink); +/** + * rpc_init_pipe_dir_head - initialise a struct rpc_pipe_dir_head + * @pdh: pointer to struct rpc_pipe_dir_head + */ +void rpc_init_pipe_dir_head(struct rpc_pipe_dir_head *pdh) +{ + INIT_LIST_HEAD(&pdh->pdh_entries); + pdh->pdh_dentry = NULL; +} +EXPORT_SYMBOL_GPL(rpc_init_pipe_dir_head); + +/** + * rpc_init_pipe_dir_object - initialise a struct rpc_pipe_dir_object + * @pdo: pointer to struct rpc_pipe_dir_object + * @pdo_ops: pointer to const struct rpc_pipe_dir_object_ops + * @pdo_data: pointer to caller-defined data + */ +void rpc_init_pipe_dir_object(struct rpc_pipe_dir_object *pdo, + const struct rpc_pipe_dir_object_ops *pdo_ops, + void *pdo_data) +{ + INIT_LIST_HEAD(&pdo->pdo_head); + pdo->pdo_ops = pdo_ops; + pdo->pdo_data = pdo_data; +} +EXPORT_SYMBOL_GPL(rpc_init_pipe_dir_object); + +static int +rpc_add_pipe_dir_object_locked(struct net *net, + struct rpc_pipe_dir_head *pdh, + struct rpc_pipe_dir_object *pdo) +{ + int ret = 0; + + if (pdh->pdh_dentry) + ret = pdo->pdo_ops->create(pdh->pdh_dentry, pdo); + if (ret == 0) + list_add_tail(&pdo->pdo_head, &pdh->pdh_entries); + return ret; +} + +static void +rpc_remove_pipe_dir_object_locked(struct net *net, + struct rpc_pipe_dir_head *pdh, + struct rpc_pipe_dir_object *pdo) +{ + if (pdh->pdh_dentry) + pdo->pdo_ops->destroy(pdh->pdh_dentry, pdo); + list_del_init(&pdo->pdo_head); +} + +/** + * rpc_add_pipe_dir_object - associate a rpc_pipe_dir_object to a directory + * @net: pointer to struct net + * @pdh: pointer to struct rpc_pipe_dir_head + * @pdo: pointer to struct rpc_pipe_dir_object + * + */ +int +rpc_add_pipe_dir_object(struct net *net, + struct rpc_pipe_dir_head *pdh, + struct rpc_pipe_dir_object *pdo) +{ + int ret = 0; + + if (list_empty(&pdo->pdo_head)) { + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + + mutex_lock(&sn->pipefs_sb_lock); + ret = rpc_add_pipe_dir_object_locked(net, pdh, pdo); + mutex_unlock(&sn->pipefs_sb_lock); + } + return ret; +} +EXPORT_SYMBOL_GPL(rpc_add_pipe_dir_object); + +/** + * rpc_remove_pipe_dir_object - remove a rpc_pipe_dir_object from a directory + * @net: pointer to struct net + * @pdh: pointer to struct rpc_pipe_dir_head + * @pdo: pointer to struct rpc_pipe_dir_object + * + */ +void +rpc_remove_pipe_dir_object(struct net *net, + struct rpc_pipe_dir_head *pdh, + struct rpc_pipe_dir_object *pdo) +{ + if (!list_empty(&pdo->pdo_head)) { + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + + mutex_lock(&sn->pipefs_sb_lock); + rpc_remove_pipe_dir_object_locked(net, pdh, pdo); + mutex_unlock(&sn->pipefs_sb_lock); + } +} +EXPORT_SYMBOL_GPL(rpc_remove_pipe_dir_object); + +/** + * rpc_find_or_alloc_pipe_dir_object + * @net: pointer to struct net + * @pdh: pointer to struct rpc_pipe_dir_head + * @match: match struct rpc_pipe_dir_object to data + * @alloc: allocate a new struct rpc_pipe_dir_object + * @data: user defined data for match() and alloc() + * + */ +struct rpc_pipe_dir_object * +rpc_find_or_alloc_pipe_dir_object(struct net *net, + struct rpc_pipe_dir_head *pdh, + int (*match)(struct rpc_pipe_dir_object *, void *), + struct rpc_pipe_dir_object *(*alloc)(void *), + void *data) +{ + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + struct rpc_pipe_dir_object *pdo; + + mutex_lock(&sn->pipefs_sb_lock); + list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) { + if (!match(pdo, data)) + continue; + goto out; + } + pdo = alloc(data); + if (!pdo) + goto out; + rpc_add_pipe_dir_object_locked(net, pdh, pdo); +out: + mutex_unlock(&sn->pipefs_sb_lock); + return pdo; +} +EXPORT_SYMBOL_GPL(rpc_find_or_alloc_pipe_dir_object); + +static void +rpc_create_pipe_dir_objects(struct rpc_pipe_dir_head *pdh) +{ + struct rpc_pipe_dir_object *pdo; + struct dentry *dir = pdh->pdh_dentry; + + list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) + pdo->pdo_ops->create(dir, pdo); +} + +static void +rpc_destroy_pipe_dir_objects(struct rpc_pipe_dir_head *pdh) +{ + struct rpc_pipe_dir_object *pdo; + struct dentry *dir = pdh->pdh_dentry; + + list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) + pdo->pdo_ops->destroy(dir, pdo); +} + enum { RPCAUTH_info, RPCAUTH_EOF @@ -941,16 +1077,29 @@ struct dentry *rpc_create_client_dir(struct dentry *dentry, const char *name, struct rpc_clnt *rpc_client) { - return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, NULL, + struct dentry *ret; + + ret = rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, NULL, rpc_clntdir_populate, rpc_client); + if (!IS_ERR(ret)) { + rpc_client->cl_pipedir_objects.pdh_dentry = ret; + rpc_create_pipe_dir_objects(&rpc_client->cl_pipedir_objects); + } + return ret; } /** * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() - * @dentry: dentry for the pipe + * @rpc_client: rpc_client for the pipe */ -int rpc_remove_client_dir(struct dentry *dentry) +int rpc_remove_client_dir(struct rpc_clnt *rpc_client) { + struct dentry *dentry = rpc_client->cl_pipedir_objects.pdh_dentry; + + if (dentry == NULL) + return 0; + rpc_destroy_pipe_dir_objects(&rpc_client->cl_pipedir_objects); + rpc_client->cl_pipedir_objects.pdh_dentry = NULL; return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate); } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 93a7a4e94d80..ff3cc4bf4b24 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -258,7 +258,7 @@ static int rpc_wait_bit_killable(void *word) return 0; } -#ifdef RPC_DEBUG +#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS) static void rpc_task_set_debuginfo(struct rpc_task *task) { static atomic_t rpc_pid; diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 21b75cb08c03..54530490944e 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -188,7 +188,7 @@ void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) seq_printf(seq, "\tRPC iostats version: %s ", RPC_IOSTATS_VERS); seq_printf(seq, "p/v: %u/%u (%s)\n", - clnt->cl_prog, clnt->cl_vers, clnt->cl_protname); + clnt->cl_prog, clnt->cl_vers, clnt->cl_program->name); rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index d6656d7768f4..ee03d35677d9 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -47,6 +47,8 @@ #include <net/udp.h> #include <net/tcp.h> +#include <trace/events/sunrpc.h> + #include "sunrpc.h" static void xs_close(struct rpc_xprt *xprt); @@ -665,8 +667,10 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct socket *sock = transport->sock; - if (sock != NULL) + if (sock != NULL) { kernel_sock_shutdown(sock, SHUT_WR); + trace_rpc_socket_shutdown(xprt, sock); + } } /** @@ -811,6 +815,7 @@ static void xs_reset_transport(struct sock_xprt *transport) sk->sk_no_check = 0; + trace_rpc_socket_close(&transport->xprt, sock); sock_release(sock); } @@ -1492,6 +1497,7 @@ static void xs_tcp_state_change(struct sock *sk) sock_flag(sk, SOCK_ZAPPED), sk->sk_shutdown); + trace_rpc_socket_state_change(xprt, sk->sk_socket); switch (sk->sk_state) { case TCP_ESTABLISHED: spin_lock(&xprt->transport_lock); @@ -1896,6 +1902,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) xprt, xprt->address_strings[RPC_DISPLAY_ADDR]); status = xs_local_finish_connecting(xprt, sock); + trace_rpc_socket_connect(xprt, sock, status); switch (status) { case 0: dprintk("RPC: xprt %p connected to %s\n", @@ -2039,6 +2046,7 @@ static void xs_udp_setup_socket(struct work_struct *work) xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); + trace_rpc_socket_connect(xprt, sock, 0); status = 0; out: xprt_clear_connecting(xprt); @@ -2064,6 +2072,8 @@ static void xs_abort_connection(struct sock_xprt *transport) memset(&any, 0, sizeof(any)); any.sa_family = AF_UNSPEC; result = kernel_connect(transport->sock, &any, sizeof(any), 0); + trace_rpc_socket_reset_connection(&transport->xprt, + transport->sock, result); if (!result) xs_sock_reset_connection_flags(&transport->xprt); dprintk("RPC: AF_UNSPEC connect return code %d\n", result); @@ -2194,6 +2204,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) xprt->address_strings[RPC_DISPLAY_PORT]); status = xs_tcp_finish_connecting(xprt, sock); + trace_rpc_socket_connect(xprt, sock, status); dprintk("RPC: %p connect status %d connected %d sock state %d\n", xprt, -status, xprt_connected(xprt), sock->sk->sk_state); diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 9bc6db04be3e..e7000be321b0 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -47,12 +47,12 @@ static int net_ctl_permissions(struct ctl_table_header *head, /* Allow network administrator to have same access as root. */ if (ns_capable(net->user_ns, CAP_NET_ADMIN) || - uid_eq(root_uid, current_uid())) { + uid_eq(root_uid, current_euid())) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } /* Allow netns root group to have the same access as the root group */ - if (gid_eq(root_gid, current_gid())) { + if (in_egroup_p(root_gid)) { int mode = (table->mode >> 3) & 7; return (mode << 3) | mode; } |