diff options
author | Scott Wood <scottwood@freescale.com> | 2014-05-14 18:19:12 (GMT) |
---|---|---|
committer | Scott Wood <scottwood@freescale.com> | 2014-05-14 18:37:18 (GMT) |
commit | 86ba38e6f5f2fbfe9b49e153ea89593b26482019 (patch) | |
tree | f99d2906b0eafca507f37289e68052fc105cc2dc /net | |
parent | 07c8b57b111585a617b2b456497fc9b33c00743c (diff) | |
download | linux-fsl-qoriq-86ba38e6f5f2fbfe9b49e153ea89593b26482019.tar.xz |
Reset to 3.12.19
Diffstat (limited to 'net')
53 files changed, 361 insertions, 303 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 61fc573..856499f 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -307,9 +307,11 @@ static void vlan_sync_address(struct net_device *dev, static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { + struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); + vlandev->gso_max_size = dev->gso_max_size; - if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) + if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index edf44d0..d1537dc 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -557,6 +557,9 @@ static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; + if (saddr == NULL) + saddr = dev->dev_addr; + return dev_hard_header(skb, real_dev, type, daddr, saddr, len); } @@ -608,7 +611,8 @@ static int vlan_dev_init(struct net_device *dev) #endif dev->needed_headroom = real_dev->needed_headroom; - if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) { + if (vlan_hw_offload_capable(real_dev->features, + vlan_dev_priv(dev)->vlan_proto)) { dev->header_ops = &vlan_passthru_header_ops; dev->hard_header_len = real_dev->hard_header_len; } else { diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 8db3e89..a3af2b7 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3565,7 +3565,13 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); - if (ltk->type & HCI_SMP_STK) { + /* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a + * temporary key used to encrypt a connection following + * pairing. It is used during the Encrypted Session Setup to + * distribute the keys. Later, security can be re-established + * using a distributed LTK. + */ + if (ltk->type == HCI_SMP_STK_SLAVE) { list_del(<k->list); kfree(ltk); } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 1b148a3..162d6c7 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1129,9 +1129,10 @@ static void br_multicast_query_received(struct net_bridge *br, struct net_bridge_port *port, struct bridge_mcast_querier *querier, int saddr, + bool is_general_query, unsigned long max_delay) { - if (saddr) + if (saddr && is_general_query) br_multicast_update_querier_timer(br, querier, max_delay); else if (timer_pending(&querier->timer)) return; @@ -1183,8 +1184,16 @@ static int br_ip4_multicast_query(struct net_bridge *br, IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; } + /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer + * all-systems destination addresses (224.0.0.1) for general queries + */ + if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) { + err = -EINVAL; + goto out; + } + br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr, - max_delay); + !group, max_delay); if (!group) goto out; @@ -1230,6 +1239,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, unsigned long max_delay; unsigned long now = jiffies; const struct in6_addr *group = NULL; + bool is_general_query; int err = 0; u16 vid = 0; @@ -1238,6 +1248,12 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; + /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ + if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) { + err = -EINVAL; + goto out; + } + if (skb->len == sizeof(*mld)) { if (!pskb_may_pull(skb, sizeof(*mld))) { err = -EINVAL; @@ -1259,8 +1275,19 @@ static int br_ip6_multicast_query(struct net_bridge *br, max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); } + is_general_query = group && ipv6_addr_any(group); + + /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer + * all-nodes destination address (ff02::1) for general queries + */ + if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) { + err = -EINVAL; + goto out; + } + br_multicast_query_received(br, port, &br->ip6_querier, - !ipv6_addr_any(&ip6h->saddr), max_delay); + !ipv6_addr_any(&ip6h->saddr), + is_general_query, max_delay); if (!group) goto out; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 4a5df7b..464303f 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3126,7 +3126,6 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, INIT_LIST_HEAD(&m->data); /* front */ - m->front_max = front_len; if (front_len) { if (front_len > PAGE_CACHE_SIZE) { m->front.iov_base = __vmalloc(front_len, flags, @@ -3143,7 +3142,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, } else { m->front.iov_base = NULL; } - m->front.iov_len = front_len; + m->front_alloc_len = m->front.iov_len = front_len; dout("ceph_msg_new %p front %d\n", m, front_len); return m; @@ -3301,8 +3300,8 @@ EXPORT_SYMBOL(ceph_msg_last_put); void ceph_msg_dump(struct ceph_msg *msg) { - pr_debug("msg_dump %p (front_max %d length %zd)\n", msg, - msg->front_max, msg->data_length); + pr_debug("msg_dump %p (front_alloc_len %d length %zd)\n", msg, + msg->front_alloc_len, msg->data_length); print_hex_dump(KERN_DEBUG, "header: ", DUMP_PREFIX_OFFSET, 16, 1, &msg->hdr, sizeof(msg->hdr), true); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 1fe25cd..2ac9ef3 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -152,7 +152,7 @@ static int __open_session(struct ceph_mon_client *monc) /* initiatiate authentication handshake */ ret = ceph_auth_build_hello(monc->auth, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); __send_prepared_auth_request(monc, ret); } else { dout("open_session mon%d already open\n", monc->cur_mon); @@ -196,7 +196,7 @@ static void __send_subscribe(struct ceph_mon_client *monc) int num; p = msg->front.iov_base; - end = p + msg->front_max; + end = p + msg->front_alloc_len; num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap; ceph_encode_32(&p, num); @@ -897,7 +897,7 @@ static void handle_auth_reply(struct ceph_mon_client *monc, ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base, msg->front.iov_len, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); if (ret < 0) { monc->client->auth_err = ret; wake_up_all(&monc->client->auth_wq); @@ -939,7 +939,7 @@ static int __validate_auth(struct ceph_mon_client *monc) return 0; ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); if (ret <= 0) return ret; /* either an error, or no need to authenticate */ __send_prepared_auth_request(monc, ret); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 2b4b32a..e6b2db6 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1232,6 +1232,22 @@ void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, EXPORT_SYMBOL(ceph_osdc_set_request_linger); /* + * Returns whether a request should be blocked from being sent + * based on the current osdmap and osd_client settings. + * + * Caller should hold map_sem for read. + */ +static bool __req_should_be_paused(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD); + bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL); + return (req->r_flags & CEPH_OSD_FLAG_READ && pauserd) || + (req->r_flags & CEPH_OSD_FLAG_WRITE && pausewr); +} + +/* * Pick an osd (the first 'up' osd in the pg), allocate the osd struct * (as needed), and set the request r_osd appropriately. If there is * no up osd, set r_osd to NULL. Move the request to the appropriate list @@ -1248,6 +1264,7 @@ static int __map_request(struct ceph_osd_client *osdc, int acting[CEPH_PG_MAX_SIZE]; int o = -1, num = 0; int err; + bool was_paused; dout("map_request %p tid %lld\n", req, req->r_tid); err = ceph_calc_ceph_pg(&pgid, req->r_oid, osdc->osdmap, @@ -1264,12 +1281,18 @@ static int __map_request(struct ceph_osd_client *osdc, num = err; } + was_paused = req->r_paused; + req->r_paused = __req_should_be_paused(osdc, req); + if (was_paused && !req->r_paused) + force_resend = 1; + if ((!force_resend && req->r_osd && req->r_osd->o_osd == o && req->r_sent >= req->r_osd->o_incarnation && req->r_num_pg_osds == num && memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) || - (req->r_osd == NULL && o == -1)) + (req->r_osd == NULL && o == -1) || + req->r_paused) return 0; /* no change */ dout("map_request tid %llu pgid %lld.%x osd%d (was osd%d)\n", @@ -1613,14 +1636,17 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) * * Caller should hold map_sem for read. */ -static void kick_requests(struct ceph_osd_client *osdc, int force_resend) +static void kick_requests(struct ceph_osd_client *osdc, bool force_resend, + bool force_resend_writes) { struct ceph_osd_request *req, *nreq; struct rb_node *p; int needmap = 0; int err; + bool force_resend_req; - dout("kick_requests %s\n", force_resend ? " (force resend)" : ""); + dout("kick_requests %s %s\n", force_resend ? " (force resend)" : "", + force_resend_writes ? " (force resend writes)" : ""); mutex_lock(&osdc->request_mutex); for (p = rb_first(&osdc->requests); p; ) { req = rb_entry(p, struct ceph_osd_request, r_node); @@ -1645,7 +1671,10 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) continue; } - err = __map_request(osdc, req, force_resend); + force_resend_req = force_resend || + (force_resend_writes && + req->r_flags & CEPH_OSD_FLAG_WRITE); + err = __map_request(osdc, req, force_resend_req); if (err < 0) continue; /* error */ if (req->r_osd == NULL) { @@ -1665,7 +1694,8 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) r_linger_item) { dout("linger req=%p req->r_osd=%p\n", req, req->r_osd); - err = __map_request(osdc, req, force_resend); + err = __map_request(osdc, req, + force_resend || force_resend_writes); dout("__map_request returned %d\n", err); if (err == 0) continue; /* no change and no osd was specified */ @@ -1707,6 +1737,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) struct ceph_osdmap *newmap = NULL, *oldmap; int err; struct ceph_fsid fsid; + bool was_full; dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0); p = msg->front.iov_base; @@ -1720,6 +1751,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) down_write(&osdc->map_sem); + was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL); + /* incremental maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d inc maps\n", nr_maps); @@ -1744,7 +1777,10 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) ceph_osdmap_destroy(osdc->osdmap); osdc->osdmap = newmap; } - kick_requests(osdc, 0); + was_full = was_full || + ceph_osdmap_flag(osdc->osdmap, + CEPH_OSDMAP_FULL); + kick_requests(osdc, 0, was_full); } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); @@ -1787,7 +1823,10 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) skipped_map = 1; ceph_osdmap_destroy(oldmap); } - kick_requests(osdc, skipped_map); + was_full = was_full || + ceph_osdmap_flag(osdc->osdmap, + CEPH_OSDMAP_FULL); + kick_requests(osdc, skipped_map, was_full); } p += maplen; nr_maps--; @@ -1804,7 +1843,9 @@ done: * we find out when we are no longer full and stop returning * ENOSPC. */ - if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) + if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) ceph_monc_request_next_osdmap(&osdc->client->monc); mutex_lock(&osdc->request_mutex); @@ -2454,7 +2495,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_msg *m; struct ceph_osd_request *req; - int front = le32_to_cpu(hdr->front_len); + int front_len = le32_to_cpu(hdr->front_len); int data_len = le32_to_cpu(hdr->data_len); u64 tid; @@ -2474,12 +2515,13 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, req->r_reply, req->r_reply->con); ceph_msg_revoke_incoming(req->r_reply); - if (front > req->r_reply->front.iov_len) { + if (front_len > req->r_reply->front_alloc_len) { pr_warning("get_reply front %d > preallocated %d (%u#%llu)\n", - front, (int)req->r_reply->front.iov_len, + front_len, req->r_reply->front_alloc_len, (unsigned int)con->peer_name.type, le64_to_cpu(con->peer_name.num)); - m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS, false); + m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS, + false); if (!m) goto out; ceph_msg_put(req->r_reply); diff --git a/net/core/dev.c b/net/core/dev.c index ab4df3d..b327975 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -175,7 +175,6 @@ static unsigned int napi_gen_id; static DEFINE_HASHTABLE(napi_hash, 8); static seqcount_t devnet_rename_seq; -static DEFINE_MUTEX(devnet_rename_mutex); static inline void dev_base_seq_inc(struct net *net) { @@ -197,14 +196,14 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) static inline void rps_lock(struct softnet_data *sd) { #ifdef CONFIG_RPS - raw_spin_lock(&sd->input_pkt_queue.raw_lock); + spin_lock(&sd->input_pkt_queue.lock); #endif } static inline void rps_unlock(struct softnet_data *sd) { #ifdef CONFIG_RPS - raw_spin_unlock(&sd->input_pkt_queue.raw_lock); + spin_unlock(&sd->input_pkt_queue.lock); #endif } @@ -827,8 +826,7 @@ retry: strcpy(name, dev->name); rcu_read_unlock(); if (read_seqcount_retry(&devnet_rename_seq, seq)) { - mutex_lock(&devnet_rename_mutex); - mutex_unlock(&devnet_rename_mutex); + cond_resched(); goto retry; } @@ -1094,28 +1092,30 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - mutex_lock(&devnet_rename_mutex); - __write_seqcount_begin(&devnet_rename_seq); + write_seqcount_begin(&devnet_rename_seq); - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) - goto outunlock; + if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { + write_seqcount_end(&devnet_rename_seq); + return 0; + } memcpy(oldname, dev->name, IFNAMSIZ); err = dev_get_valid_name(net, dev, newname); - if (err < 0) - goto outunlock; + if (err < 0) { + write_seqcount_end(&devnet_rename_seq); + return err; + } rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); - err = ret; - goto outunlock; + write_seqcount_end(&devnet_rename_seq); + return ret; } - __write_seqcount_end(&devnet_rename_seq); - mutex_unlock(&devnet_rename_mutex); + write_seqcount_end(&devnet_rename_seq); write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); @@ -1134,8 +1134,7 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - mutex_lock(&devnet_rename_mutex); - __write_seqcount_begin(&devnet_rename_seq); + write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; } else { @@ -1145,11 +1144,6 @@ rollback: } return err; - -outunlock: - __write_seqcount_end(&devnet_rename_seq); - mutex_unlock(&devnet_rename_mutex); - return err; } /** @@ -2138,7 +2132,6 @@ static inline void __netif_reschedule(struct Qdisc *q) sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); - preempt_check_resched_rt(); } void __netif_schedule(struct Qdisc *q) @@ -2160,7 +2153,6 @@ void dev_kfree_skb_irq(struct sk_buff *skb) sd->completion_queue = skb; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); - preempt_check_resched_rt(); } } EXPORT_SYMBOL(dev_kfree_skb_irq); @@ -3212,7 +3204,6 @@ enqueue: rps_unlock(sd); local_irq_restore(flags); - preempt_check_resched_rt(); atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); @@ -3250,7 +3241,7 @@ int netif_rx(struct sk_buff *skb) struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - migrate_disable(); + preempt_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -3260,13 +3251,13 @@ int netif_rx(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - migrate_enable(); + preempt_enable(); } else #endif { unsigned int qtail; - ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); - put_cpu_light(); + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); + put_cpu(); } return ret; } @@ -3276,44 +3267,16 @@ int netif_rx_ni(struct sk_buff *skb) { int err; - local_bh_disable(); + preempt_disable(); err = netif_rx(skb); - local_bh_enable(); + if (local_softirq_pending()) + do_softirq(); + preempt_enable(); return err; } EXPORT_SYMBOL(netif_rx_ni); -#ifdef CONFIG_PREEMPT_RT_FULL -/* - * RT runs ksoftirqd as a real time thread and the root_lock is a - * "sleeping spinlock". If the trylock fails then we can go into an - * infinite loop when ksoftirqd preempted the task which actually - * holds the lock, because we requeue q and raise NET_TX softirq - * causing ksoftirqd to loop forever. - * - * It's safe to use spin_lock on RT here as softirqs run in thread - * context and cannot deadlock against the thread which is holding - * root_lock. - * - * On !RT the trylock might fail, but there we bail out from the - * softirq loop after 10 attempts which we can't do on RT. And the - * task holding root_lock cannot be preempted, so the only downside of - * that trylock is that we need 10 loops to decide that we should have - * given up in the first one :) - */ -static inline int take_root_lock(spinlock_t *lock) -{ - spin_lock(lock); - return 1; -} -#else -static inline int take_root_lock(spinlock_t *lock) -{ - return spin_trylock(lock); -} -#endif - static void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = &__get_cpu_var(softnet_data); @@ -3352,7 +3315,7 @@ static void net_tx_action(struct softirq_action *h) head = head->next_sched; root_lock = qdisc_lock(q); - if (take_root_lock(root_lock)) { + if (spin_trylock(root_lock)) { smp_mb__before_clear_bit(); clear_bit(__QDISC_STATE_SCHED, &q->state); @@ -3743,7 +3706,7 @@ static void flush_backlog(void *arg) skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev == dev) { __skb_unlink(skb, &sd->input_pkt_queue); - __skb_queue_tail(&sd->tofree_queue, skb); + kfree_skb(skb); input_queue_head_incr(sd); } } @@ -3752,13 +3715,10 @@ static void flush_backlog(void *arg) skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev == dev) { __skb_unlink(skb, &sd->process_queue); - __skb_queue_tail(&sd->tofree_queue, skb); + kfree_skb(skb); input_queue_head_incr(sd); } } - - if (!skb_queue_empty(&sd->tofree_queue)) - raise_softirq_irqoff(NET_RX_SOFTIRQ); } static int napi_gro_complete(struct sk_buff *skb) @@ -4115,7 +4075,6 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) } else #endif local_irq_enable(); - preempt_check_resched_rt(); } static int process_backlog(struct napi_struct *napi, int quota) @@ -4188,7 +4147,6 @@ void __napi_schedule(struct napi_struct *n) local_irq_save(flags); ____napi_schedule(&__get_cpu_var(softnet_data), n); local_irq_restore(flags); - preempt_check_resched_rt(); } EXPORT_SYMBOL(__napi_schedule); @@ -4318,17 +4276,10 @@ static void net_rx_action(struct softirq_action *h) struct softnet_data *sd = &__get_cpu_var(softnet_data); unsigned long time_limit = jiffies + 2; int budget = netdev_budget; - struct sk_buff *skb; void *have; local_irq_disable(); - while ((skb = __skb_dequeue(&sd->tofree_queue))) { - local_irq_enable(); - kfree_skb(skb); - local_irq_disable(); - } - while (!list_empty(&sd->poll_list)) { struct napi_struct *n; int work, weight; @@ -6447,7 +6398,6 @@ static int dev_cpu_callback(struct notifier_block *nfb, raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); - preempt_check_resched_rt(); /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { @@ -6458,9 +6408,6 @@ static int dev_cpu_callback(struct notifier_block *nfb, netif_rx(skb); input_queue_head_incr(oldsd); } - while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { - kfree_skb(skb); - } return NOTIFY_OK; } @@ -6772,9 +6719,8 @@ static int __init net_dev_init(void) struct softnet_data *sd = &per_cpu(softnet_data, i); memset(sd, 0, sizeof(*sd)); - skb_queue_head_init_raw(&sd->input_pkt_queue); - skb_queue_head_init_raw(&sd->process_queue); - skb_queue_head_init_raw(&sd->tofree_queue); + skb_queue_head_init(&sd->input_pkt_queue); + skb_queue_head_init(&sd->process_queue); sd->completion_queue = NULL; INIT_LIST_HEAD(&sd->poll_list); sd->output_queue = NULL; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 462cdc9..9b40f23 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -740,7 +740,7 @@ static bool pkt_is_ns(struct sk_buff *skb) struct nd_msg *msg; struct ipv6hdr *hdr; - if (skb->protocol != htons(ETH_P_ARP)) + if (skb->protocol != htons(ETH_P_IPV6)) return false; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) return false; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2a0e21d..37b492e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2014,12 +2014,13 @@ EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, u8 *addr, u32 pid, u32 seq, - int type, unsigned int flags) + int type, unsigned int flags, + int nlflags) { struct nlmsghdr *nlh; struct ndmsg *ndm; - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags); if (!nlh) return -EMSGSIZE; @@ -2057,7 +2058,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type) if (!skb) goto errout; - err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF); + err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0); if (err < 0) { kfree_skb(skb); goto errout; @@ -2282,7 +2283,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, portid, seq, - RTM_NEWNEIGH, NTF_SELF); + RTM_NEWNEIGH, NTF_SELF, + NLM_F_MULTI); if (err < 0) return err; skip: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index da24627..21571dc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -62,7 +62,6 @@ #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> -#include <linux/locallock.h> #include <net/protocol.h> #include <net/dst.h> @@ -335,7 +334,6 @@ struct netdev_alloc_cache { unsigned int pagecnt_bias; }; static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); -static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { @@ -344,7 +342,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) int order; unsigned long flags; - local_lock_irqsave(netdev_alloc_lock, flags); + local_irq_save(flags); nc = &__get_cpu_var(netdev_alloc_cache); if (unlikely(!nc->frag.page)) { refill: @@ -378,7 +376,7 @@ recycle: nc->frag.offset += fragsz; nc->pagecnt_bias--; end: - local_unlock_irqrestore(netdev_alloc_lock, flags); + local_irq_restore(flags); return data; } diff --git a/net/core/sock.c b/net/core/sock.c index e57770c..ec228a3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2339,11 +2339,12 @@ void lock_sock_nested(struct sock *sk, int subclass) if (sk->sk_lock.owned) __lock_sock(sk); sk->sk_lock.owned = 1; - spin_unlock_bh(&sk->sk_lock.slock); + spin_unlock(&sk->sk_lock.slock); /* * The sk_lock has mutex_lock() semantics here: */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); + local_bh_enable(); } EXPORT_SYMBOL(lock_sock_nested); @@ -2358,10 +2359,13 @@ void release_sock(struct sock *sk) if (sk->sk_backlog.tail) __release_sock(sk); + /* Warning : release_cb() might need to release sk ownership, + * ie call sock_release_ownership(sk) before us. + */ if (sk->sk_prot->release_cb) sk->sk_prot->release_cb(sk); - sk->sk_lock.owned = 0; + sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 736c9fc3..0c0c1f0 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -211,6 +211,14 @@ static int gre_cisco_rcv(struct sk_buff *skb) int i; bool csum_err = false; +#ifdef CONFIG_NET_IPGRE_BROADCAST + if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { + /* Looped back packet, drop it! */ + if (rt_is_output_route(skb_rtable(skb))) + goto drop; + } +#endif + if (parse_gre_header(skb, &tpi, &csum_err) < 0) goto drop; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1f0c7e0..5f7d11a 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -69,7 +69,6 @@ #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/fcntl.h> -#include <linux/sysrq.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> @@ -777,30 +776,6 @@ static void icmp_redirect(struct sk_buff *skb) } /* - * 32bit and 64bit have different timestamp length, so we check for - * the cookie at offset 20 and verify it is repeated at offset 50 - */ -#define CO_POS0 20 -#define CO_POS1 50 -#define CO_SIZE sizeof(int) -#define ICMP_SYSRQ_SIZE 57 - -/* - * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie - * pattern and if it matches send the next byte as a trigger to sysrq. - */ -static void icmp_check_sysrq(struct net *net, struct sk_buff *skb) -{ - int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq); - char *p = skb->data; - - if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) && - !memcmp(&cookie, p + CO_POS1, CO_SIZE) && - p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE]) - handle_sysrq(p[CO_POS0 + CO_SIZE]); -} - -/* * Handle ICMP_ECHO ("ping") requests. * * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo @@ -827,11 +802,6 @@ static void icmp_echo(struct sk_buff *skb) icmp_param.data_len = skb->len; icmp_param.head_len = sizeof(struct icmphdr); icmp_reply(&icmp_param, skb); - - if (skb->len == ICMP_SYSRQ_SIZE && - net->ipv4.sysctl_icmp_echo_sysrq) { - icmp_check_sysrq(net, skb); - } } } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c5313a9..12b80fb 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -211,7 +211,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) } work = frag_mem_limit(nf) - nf->low_thresh; - while (work > 0) { + while (work > 0 || force) { spin_lock(&nf->lru_lock); if (list_empty(&nf->lru_list)) { @@ -281,9 +281,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); + inet_frag_lru_add(nf, qp); spin_unlock(&hb->chain_lock); read_unlock(&f->lock); - inet_frag_lru_add(nf, qp); + return qp; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8bb3b4a..3982eab 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -79,7 +79,6 @@ #include <linux/mroute.h> #include <linux/netlink.h> #include <linux/tcp.h> -#include <linux/locallock.h> int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; EXPORT_SYMBOL(sysctl_ip_default_ttl); @@ -1469,9 +1468,6 @@ static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = { .uc_ttl = -1, }; -/* serialize concurrent calls on the same CPU to ip_send_unicast_reply */ -static DEFINE_LOCAL_IRQ_LOCK(unicast_lock); - void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len) @@ -1509,7 +1505,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, if (IS_ERR(rt)) return; - inet = &get_locked_var(unicast_lock, unicast_sock); + inet = &get_cpu_var(unicast_sock); inet->tos = arg->tos; sk = &inet->sk; @@ -1533,7 +1529,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, ip_push_pending_frames(sk, &fl4); } - put_locked_var(unicast_lock, unicast_sock); + put_cpu_var(unicast_sock); ip_rt_put(rt); } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 995a0bb..3bedb26 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -411,9 +411,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { - /* Looped back packet, drop it! */ - if (rt_is_output_route(skb_rtable(skb))) - goto drop; tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index ba22cc3..c31e3ad 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -109,6 +109,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) secpath_reset(skb); if (!skb->l4_rxhash) skb->rxhash = 0; + skb_dst_drop(skb); skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); skb->pkt_type = PACKET_HOST; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 1672409..6fbf339 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2253,13 +2253,14 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc_cache *c, int cmd) + u32 portid, u32 seq, struct mfc_cache *c, int cmd, + int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; - nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2327,7 +2328,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, if (skb == NULL) goto errout; - err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; @@ -2366,7 +2367,8 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) goto done; next_entry: e++; @@ -2380,7 +2382,8 @@ next_entry: if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) { + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { spin_unlock_bh(&mfc_unres_lock); goto done; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index c482f7c..c211607 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -249,26 +249,33 @@ int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); kgid_t group = current_egid(); - struct group_info *group_info = get_current_groups(); - int i, j, count = group_info->ngroups; + struct group_info *group_info; + int i, j, count; kgid_t low, high; + int ret = 0; inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; + group_info = get_current_groups(); + count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); for (j = 0; j < cp_count; j++) { kgid_t gid = group_info->blocks[i][j]; if (gid_lte(low, gid) && gid_lte(gid, high)) - return 0; + goto out_release_group; } count -= cp_count; } - return -EACCES; + ret = -EACCES; + +out_release_group: + put_group_info(group_info); + return ret; } EXPORT_SYMBOL_GPL(ping_init_sock); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 99461ed..540279f 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -812,13 +812,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .procname = "icmp_echo_sysrq", - .data = &init_net.ipv4.sysctl_icmp_echo_sysrq, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "icmp_ignore_bogus_error_responses", .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e088932..826fc6f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -765,6 +765,17 @@ void tcp_release_cb(struct sock *sk) if (flags & (1UL << TCP_TSQ_DEFERRED)) tcp_tsq_handler(sk); + /* Here begins the tricky part : + * We are called from release_sock() with : + * 1) BH disabled + * 2) sk_lock.slock spinlock held + * 3) socket owned by us (sk->sk_lock.owned == 1) + * + * But following code is meant to be called from BH handlers, + * so we should keep BH disabled, but early release socket ownership + */ + sock_release_ownership(sk); + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { tcp_write_timer_handler(sk); __sock_put(sk); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cd3fb30..5dac9fd 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1079,8 +1079,11 @@ retry: * Lifetime is greater than REGEN_ADVANCE time units. In particular, * an implementation must not create a temporary address with a zero * Preferred Lifetime. + * Use age calculation as in addrconf_verify to avoid unnecessary + * temporary addresses being generated. */ - if (tmp_prefered_lft <= regen_advance) { + age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + if (tmp_prefered_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c index cf77f3a..447a7fb 100644 --- a/net/ipv6/exthdrs_offload.c +++ b/net/ipv6/exthdrs_offload.c @@ -25,11 +25,11 @@ int __init ipv6_exthdrs_offload_init(void) int ret; ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING); - if (!ret) + if (ret) goto out; ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS); - if (!ret) + if (ret) goto out_rt; out: diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index eef8d94..e2c9ff8 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -516,7 +516,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) np->tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 68fd491..516e136 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1088,21 +1088,19 @@ static void ip6_append_data_mtu(unsigned int *mtu, unsigned int fragheaderlen, struct sk_buff *skb, struct rt6_info *rt, - bool pmtuprobe) + unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (skb == NULL) { /* first fragment, reserve header_len */ - *mtu = *mtu - rt->dst.header_len; + *mtu = orig_mtu - rt->dst.header_len; } else { /* * this fragment is not first, the headers * space is regarded as data space. */ - *mtu = min(*mtu, pmtuprobe ? - rt->dst.dev->mtu : - dst_mtu(rt->dst.path)); + *mtu = orig_mtu; } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); @@ -1119,7 +1117,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_cork *cork; struct sk_buff *skb, *skb_prev = NULL; - unsigned int maxfraglen, fragheaderlen, mtu; + unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; int exthdrlen; int dst_exthdrlen; int hh_len; @@ -1201,6 +1199,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, dst_exthdrlen = 0; mtu = cork->fragsize; } + orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1280,8 +1279,7 @@ alloc_new_skb: if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, - np->pmtudisc == - IPV6_PMTUDISC_PROBE); + orig_mtu); skb_prev = skb; @@ -1537,8 +1535,8 @@ int ip6_push_pending_frames(struct sock *sk) if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } err = ip6_local_out(skb); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0eb4038..8737400 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2349,13 +2349,14 @@ int ip6mr_get_route(struct net *net, } static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc6_cache *c, int cmd) + u32 portid, u32 seq, struct mfc6_cache *c, int cmd, + int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; - nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2423,7 +2424,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, if (skb == NULL) goto errout; - err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; @@ -2462,7 +2463,8 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) goto done; next_entry: e++; @@ -2476,7 +2478,8 @@ next_entry: if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) { + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { spin_unlock_bh(&mfc_unres_lock); goto done; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d18f9f9..d81abd5 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1620,11 +1620,12 @@ static void mld_sendpack(struct sk_buff *skb) dst_output); out: if (!err) { - ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); - } else - IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS); + ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); + } else { + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + } rcu_read_unlock(); return; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 7856e96..6acab0b 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -182,8 +182,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev, - ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, + ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0accb13..77f81be 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1500,7 +1500,7 @@ int ip6_route_add(struct fib6_config *cfg) if (!table) goto out; - rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table); + rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table); if (!rt) { err = -ENOMEM; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 62fba17..1e5bd0d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3298,7 +3298,7 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) struct ieee80211_supported_band *sband; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - WARN_ON_ONCE_NONRT(softirq_count() == 0); + WARN_ON_ONCE(softirq_count() == 0); if (WARN_ON(status->band >= IEEE80211_NUM_BANDS)) goto drop; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 6bd22aa..593b16e 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -21,17 +21,11 @@ #include <linux/proc_fs.h> #include <linux/mutex.h> #include <linux/slab.h> -#include <linux/locallock.h> #include <net/net_namespace.h> #include <net/sock.h> #include "nf_internals.h" -#ifdef CONFIG_PREEMPT_RT_BASE -DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); -EXPORT_PER_CPU_SYMBOL(xt_write_lock); -#endif - static DEFINE_MUTEX(afinfo_mutex); const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 4c8e5c0..d585626 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -871,11 +871,11 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, cp->protocol = p->protocol; ip_vs_addr_set(p->af, &cp->caddr, p->caddr); cp->cport = p->cport; - ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr); - cp->vport = p->vport; - /* proto should only be IPPROTO_IP if d_addr is a fwmark */ + /* proto should only be IPPROTO_IP if p->vaddr is a fwmark */ ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, - &cp->daddr, daddr); + &cp->vaddr, p->vaddr); + cp->vport = p->vport; + ip_vs_addr_set(p->af, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; cp->fwmark = fwmark; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index a99b6c3..59359be 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -428,7 +428,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const char *msg; u_int8_t state; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); BUG_ON(dh == NULL); state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; @@ -486,7 +486,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, u_int8_t type, old_state, new_state; enum ct_dccp_roles role; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); BUG_ON(dh == NULL); type = dh->dccph_type; @@ -577,7 +577,7 @@ static int dccp_error(struct net *net, struct nf_conn *tmpl, unsigned int cscov; const char *msg; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); if (dh == NULL) { msg = "nf_ct_dccp: short packet "; goto out_invalid; diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index c323567..5c2dab2 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -65,8 +65,7 @@ void ovs_dp_notify_wq(struct work_struct *work) continue; netdev_vport = netdev_vport_priv(vport); - if (netdev_vport->dev->reg_state == NETREG_UNREGISTERED || - netdev_vport->dev->reg_state == NETREG_UNREGISTERING) + if (!(netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH)) dp_detach_port_notify(vport); } } @@ -88,6 +87,10 @@ static int dp_device_event(struct notifier_block *unused, unsigned long event, return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { + /* upper_dev_unlink and decrement promisc immediately */ + ovs_netdev_detach_dev(vport); + + /* schedule vport destroy, dev_put and genl notification */ ovs_net = net_generic(dev_net(dev), ovs_net_id); queue_work(system_wq, &ovs_net->dp_notify_work); } diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 09d93c1..d21f77d 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -150,15 +150,25 @@ static void free_port_rcu(struct rcu_head *rcu) ovs_vport_free(vport_from_priv(netdev_vport)); } -static void netdev_destroy(struct vport *vport) +void ovs_netdev_detach_dev(struct vport *vport) { struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - rtnl_lock(); + ASSERT_RTNL(); netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; netdev_rx_handler_unregister(netdev_vport->dev); - netdev_upper_dev_unlink(netdev_vport->dev, get_dpdev(vport->dp)); + netdev_upper_dev_unlink(netdev_vport->dev, + netdev_master_upper_dev_get(netdev_vport->dev)); dev_set_promiscuity(netdev_vport->dev, -1); +} + +static void netdev_destroy(struct vport *vport) +{ + struct netdev_vport *netdev_vport = netdev_vport_priv(vport); + + rtnl_lock(); + if (netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH) + ovs_netdev_detach_dev(vport); rtnl_unlock(); call_rcu(&netdev_vport->rcu, free_port_rcu); diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index dd298b5..8df01c11 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -39,5 +39,6 @@ netdev_vport_priv(const struct vport *vport) } const char *ovs_netdev_get_name(const struct vport *); +void ovs_netdev_detach_dev(struct vport *); #endif /* vport_netdev.h */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d1705d0..88cfbc1 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -63,7 +63,6 @@ #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> -#include <linux/delay.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -631,7 +630,7 @@ static void prb_retire_rx_blk_timer_expired(unsigned long data) if (BLOCK_NUM_PKTS(pbd)) { while (atomic_read(&pkc->blk_fill_in_prog)) { /* Waiting for skb_copy_bits to finish... */ - cpu_chill(); + cpu_relax(); } } @@ -882,7 +881,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, if (!(status & TP_STATUS_BLK_TMO)) { while (atomic_read(&pkc->blk_fill_in_prog)) { /* Waiting for skb_copy_bits to finish... */ - cpu_chill(); + cpu_relax(); } } prb_close_block(pkc, pbd, po, status); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 5a44c6e..e8fdb17 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -34,7 +34,6 @@ #include <linux/slab.h> #include <linux/rculist.h> #include <linux/llist.h> -#include <linux/delay.h> #include "rds.h" #include "ib.h" @@ -287,7 +286,7 @@ static inline void wait_clean_list_grace(void) for_each_online_cpu(cpu) { flag = &per_cpu(clean_list_grace, cpu); while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) - cpu_chill(); + cpu_relax(); } } diff --git a/net/rds/iw.c b/net/rds/iw.c index 7826d46..5899356 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr) ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); /* due to this, we will claim to support IB devices unless we check node_type. */ - if (ret || cm_id->device->node_type != RDMA_NODE_RNIC) + if (ret || !cm_id->device || + cm_id->device->node_type != RDMA_NODE_RNIC) ret = -EADDRNOTAVAIL; rdsdebug("addr %pI4 ret %d node type %d\n", diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 2e55f81..52229f9 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -577,9 +577,11 @@ static void fq_rehash(struct fq_sched_data *q, q->stat_gc_flows += fcnt; } -static int fq_resize(struct fq_sched_data *q, u32 log) +static int fq_resize(struct Qdisc *sch, u32 log) { + struct fq_sched_data *q = qdisc_priv(sch); struct rb_root *array; + void *old_fq_root; u32 idx; if (q->fq_root && log == q->fq_trees_log) @@ -592,13 +594,19 @@ static int fq_resize(struct fq_sched_data *q, u32 log) for (idx = 0; idx < (1U << log); idx++) array[idx] = RB_ROOT; - if (q->fq_root) { - fq_rehash(q, q->fq_root, q->fq_trees_log, array, log); - kfree(q->fq_root); - } + sch_tree_lock(sch); + + old_fq_root = q->fq_root; + if (old_fq_root) + fq_rehash(q, old_fq_root, q->fq_trees_log, array, log); + q->fq_root = array; q->fq_trees_log = log; + sch_tree_unlock(sch); + + kfree(old_fq_root); + return 0; } @@ -674,9 +682,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->flow_refill_delay = usecs_to_jiffies(usecs_delay); } - if (!err) - err = fq_resize(q, fq_log); - + if (!err) { + sch_tree_unlock(sch); + err = fq_resize(sch, fq_log); + sch_tree_lock(sch); + } while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); @@ -722,7 +732,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) if (opt) err = fq_change(sch, opt); else - err = fq_resize(q, q->fq_trees_log); + err = fq_resize(sch, q->fq_trees_log); return err; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 1dcebc9..a74e278 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -850,7 +850,7 @@ void dev_deactivate_many(struct list_head *head) /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, unreg_list) while (some_qdisc_is_busy(dev)) - msleep(1); + yield(); } void dev_deactivate(struct net_device *dev) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index d244a23..26be077 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1433,8 +1433,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk) BUG_ON(!list_empty(&chunk->list)); list_del_init(&chunk->transmitted_list); - /* Free the chunk skb data and the SCTP_chunk stub itself. */ - dev_kfree_skb(chunk->skb); + consume_skb(chunk->skb); + consume_skb(chunk->auth_chunk); SCTP_DBG_OBJCNT_DEC(chunk); kmem_cache_free(sctp_chunk_cachep, chunk); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 56ebe71..0a5f050 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -761,7 +761,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, /* Make sure that we and the peer are AUTH capable */ if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { - kfree_skb(chunk->auth_chunk); sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } @@ -776,10 +775,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, auth.transport = chunk->transport; ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - - /* We can now safely free the auth_chunk clone */ - kfree_skb(chunk->auth_chunk); - if (ret != SCTP_IERROR_NO_ERROR) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); diff --git a/net/socket.c b/net/socket.c index e83c416..dc57dae 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1972,6 +1972,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, { if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) return -EFAULT; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); return 0; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index a7f9821..bb035f8 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1508,7 +1508,7 @@ out: static int gss_refresh_null(struct rpc_task *task) { - return -EACCES; + return 0; } static __be32 * diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 890a299..e860d4f 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -64,7 +64,6 @@ static void xprt_free_allocation(struct rpc_rqst *req) free_page((unsigned long)xbufp->head[0].iov_base); xbufp = &req->rq_snd_buf; free_page((unsigned long)xbufp->head[0].iov_base); - list_del(&req->rq_bc_pa_list); kfree(req); } @@ -168,8 +167,10 @@ out_free: /* * Memory allocation failed, free the temporary list */ - list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) + list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) { + list_del(&req->rq_bc_pa_list); xprt_free_allocation(req); + } dprintk("RPC: setup backchannel transport failed\n"); return -ENOMEM; @@ -198,6 +199,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs) xprt_dec_alloc_count(xprt, max_reqs); list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) { dprintk("RPC: req=%p\n", req); + list_del(&req->rq_bc_pa_list); xprt_free_allocation(req); if (--max_reqs == 0) break; diff --git a/net/tipc/config.c b/net/tipc/config.c index c301a9a..5afe633 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -376,7 +376,6 @@ static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr, struct tipc_cfg_msg_hdr *req_hdr; struct tipc_cfg_msg_hdr *rep_hdr; struct sk_buff *rep_buf; - int ret; /* Validate configuration message header (ignore invalid message) */ req_hdr = (struct tipc_cfg_msg_hdr *)buf; @@ -398,12 +397,8 @@ static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr, memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr)); rep_hdr->tcm_len = htonl(rep_buf->len); rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST); - - ret = tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data, - rep_buf->len); - if (ret < 0) - pr_err("Sending cfg reply message failed, no memory\n"); - + tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data, + rep_buf->len); kfree_skb(rep_buf); } } diff --git a/net/tipc/handler.c b/net/tipc/handler.c index b36f0fc..79b991e 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -57,7 +57,6 @@ unsigned int tipc_k_signal(Handler routine, unsigned long argument) struct queue_item *item; if (!handler_enabled) { - pr_err("Signal request ignored by handler\n"); return -ENOPROTOOPT; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 09dcd54..299e45af 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -942,20 +942,51 @@ int tipc_nametbl_init(void) return 0; } +/** + * tipc_purge_publications - remove all publications for a given type + * + * tipc_nametbl_lock must be held when calling this function + */ +static void tipc_purge_publications(struct name_seq *seq) +{ + struct publication *publ, *safe; + struct sub_seq *sseq; + struct name_info *info; + + if (!seq->sseqs) { + nameseq_delete_empty(seq); + return; + } + sseq = seq->sseqs; + info = sseq->info; + list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) { + tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node, + publ->ref, publ->key); + } +} + void tipc_nametbl_stop(void) { u32 i; + struct name_seq *seq; + struct hlist_head *seq_head; + struct hlist_node *safe; if (!table.types) return; - /* Verify name table is empty, then release it */ + /* Verify name table is empty and purge any lingering + * publications, then release the name table + */ write_lock_bh(&tipc_nametbl_lock); for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { if (hlist_empty(&table.types[i])) continue; - pr_err("nametbl_stop(): orphaned hash chain detected\n"); - break; + seq_head = &table.types[i]; + hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) { + tipc_purge_publications(seq); + } + continue; } kfree(table.types); table.types = NULL; diff --git a/net/tipc/server.c b/net/tipc/server.c index fd3fa57..bd2336a 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -87,7 +87,6 @@ static void tipc_clean_outqueues(struct tipc_conn *con); static void tipc_conn_kref_release(struct kref *kref) { struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); - struct tipc_server *s = con->server; if (con->sock) { tipc_sock_release_local(con->sock); @@ -95,10 +94,6 @@ static void tipc_conn_kref_release(struct kref *kref) } tipc_clean_outqueues(con); - - if (con->conid) - s->tipc_conn_shutdown(con->conid, con->usr_data); - kfree(con); } @@ -181,6 +176,9 @@ static void tipc_close_conn(struct tipc_conn *con) struct tipc_server *s = con->server; if (test_and_clear_bit(CF_CONNECTED, &con->flags)) { + if (con->conid) + s->tipc_conn_shutdown(con->conid, con->usr_data); + spin_lock_bh(&s->idr_lock); idr_remove(&s->conn_idr, con->conid); s->idr_in_use--; @@ -429,10 +427,12 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid, list_add_tail(&e->list, &con->outqueue); spin_unlock_bh(&con->outqueue_lock); - if (test_bit(CF_CONNECTED, &con->flags)) + if (test_bit(CF_CONNECTED, &con->flags)) { if (!queue_work(s->send_wq, &con->swork)) conn_put(con); - + } else { + conn_put(con); + } return 0; } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index d38bb45..c2a37aa 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -96,20 +96,16 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower, { struct tipc_subscriber *subscriber = sub->subscriber; struct kvec msg_sect; - int ret; msg_sect.iov_base = (void *)&sub->evt; msg_sect.iov_len = sizeof(struct tipc_event); - sub->evt.event = htohl(event, sub->swap); sub->evt.found_lower = htohl(found_lower, sub->swap); sub->evt.found_upper = htohl(found_upper, sub->swap); sub->evt.port.ref = htohl(port_ref, sub->swap); sub->evt.port.node = htohl(node, sub->swap); - ret = tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, - msg_sect.iov_base, msg_sect.iov_len); - if (ret < 0) - pr_err("Sending subscription event failed, no memory\n"); + tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base, + msg_sect.iov_len); } /** @@ -153,14 +149,6 @@ static void subscr_timeout(struct tipc_subscription *sub) /* The spin lock per subscriber is used to protect its members */ spin_lock_bh(&subscriber->lock); - /* Validate if the connection related to the subscriber is - * closed (in case subscriber is terminating) - */ - if (subscriber->conid == 0) { - spin_unlock_bh(&subscriber->lock); - return; - } - /* Validate timeout (in case subscription is being cancelled) */ if (sub->timeout == TIPC_WAIT_FOREVER) { spin_unlock_bh(&subscriber->lock); @@ -215,9 +203,6 @@ static void subscr_release(struct tipc_subscriber *subscriber) spin_lock_bh(&subscriber->lock); - /* Invalidate subscriber reference */ - subscriber->conid = 0; - /* Destroy any existing subscriptions for subscriber */ list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, subscription_list) { @@ -278,9 +263,9 @@ static void subscr_cancel(struct tipc_subscr *s, * * Called with subscriber lock held. */ -static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, - struct tipc_subscriber *subscriber) -{ +static int subscr_subscribe(struct tipc_subscr *s, + struct tipc_subscriber *subscriber, + struct tipc_subscription **sub_p) { struct tipc_subscription *sub; int swap; @@ -291,23 +276,21 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) { s->filter &= ~htohl(TIPC_SUB_CANCEL, swap); subscr_cancel(s, subscriber); - return NULL; + return 0; } /* Refuse subscription if global limit exceeded */ if (atomic_read(&subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) { pr_warn("Subscription rejected, limit reached (%u)\n", TIPC_MAX_SUBSCRIPTIONS); - subscr_terminate(subscriber); - return NULL; + return -EINVAL; } /* Allocate subscription object */ sub = kmalloc(sizeof(*sub), GFP_ATOMIC); if (!sub) { pr_warn("Subscription rejected, no memory\n"); - subscr_terminate(subscriber); - return NULL; + return -ENOMEM; } /* Initialize subscription object */ @@ -321,8 +304,7 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, (sub->seq.lower > sub->seq.upper)) { pr_warn("Subscription rejected, illegal request\n"); kfree(sub); - subscr_terminate(subscriber); - return NULL; + return -EINVAL; } INIT_LIST_HEAD(&sub->nameseq_list); list_add(&sub->subscription_list, &subscriber->subscription_list); @@ -335,8 +317,8 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s, (Handler)subscr_timeout, (unsigned long)sub); k_start_timer(&sub->timer, sub->timeout); } - - return sub; + *sub_p = sub; + return 0; } /* Handle one termination request for the subscriber */ @@ -350,10 +332,14 @@ static void subscr_conn_msg_event(int conid, struct sockaddr_tipc *addr, void *usr_data, void *buf, size_t len) { struct tipc_subscriber *subscriber = usr_data; - struct tipc_subscription *sub; + struct tipc_subscription *sub = NULL; spin_lock_bh(&subscriber->lock); - sub = subscr_subscribe((struct tipc_subscr *)buf, subscriber); + if (subscr_subscribe((struct tipc_subscr *)buf, subscriber, &sub) < 0) { + spin_unlock_bh(&subscriber->lock); + subscr_terminate(subscriber); + return; + } if (sub) tipc_nametbl_subscribe(sub); spin_unlock_bh(&subscriber->lock); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index d7c1ac6..c3975bc 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1785,8 +1785,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; err = mutex_lock_interruptible(&u->readlock); - if (err) { - err = sock_intr_errno(sock_rcvtimeo(sk, noblock)); + if (unlikely(err)) { + /* recvmsg() in non blocking mode is supposed to return -EAGAIN + * sk_rcvtimeo is not honored by mutex_lock_interruptible() + */ + err = noblock ? -EAGAIN : -ERESTARTSYS; goto out; } @@ -1911,6 +1914,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = msg->msg_name; int copied = 0; + int noblock = flags & MSG_DONTWAIT; int check_creds = 0; int target; int err = 0; @@ -1926,7 +1930,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; target = sock_rcvlowat(sk, flags&MSG_WAITALL, size); - timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT); + timeo = sock_rcvtimeo(sk, noblock); /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg @@ -1938,8 +1942,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, } err = mutex_lock_interruptible(&u->readlock); - if (err) { - err = sock_intr_errno(timeo); + if (unlikely(err)) { + /* recvmsg() in non blocking mode is supposed to return -EAGAIN + * sk_rcvtimeo is not honored by mutex_lock_interruptible() + */ + err = noblock ? -EAGAIN : -ERESTARTSYS; goto out; } |