diff options
Diffstat (limited to 'net')
42 files changed, 382 insertions, 231 deletions
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index e1133bc634b5..8a3ce79b1307 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1549,9 +1549,41 @@ batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, return found; } +/** + * batadv_tt_global_sync_flags - update TT sync flags + * @tt_global: the TT global entry to update sync flags in + * + * Updates the sync flag bits in the tt_global flag attribute with a logical + * OR of all sync flags from any of its TT orig entries. + */ +static void +batadv_tt_global_sync_flags(struct batadv_tt_global_entry *tt_global) +{ + struct batadv_tt_orig_list_entry *orig_entry; + const struct hlist_head *head; + u16 flags = BATADV_NO_FLAGS; + + rcu_read_lock(); + head = &tt_global->orig_list; + hlist_for_each_entry_rcu(orig_entry, head, list) + flags |= orig_entry->flags; + rcu_read_unlock(); + + flags |= tt_global->common.flags & (~BATADV_TT_SYNC_MASK); + tt_global->common.flags = flags; +} + +/** + * batadv_tt_global_orig_entry_add - add or update a TT orig entry + * @tt_global: the TT global entry to add an orig entry in + * @orig_node: the originator to add an orig entry for + * @ttvn: translation table version number of this changeset + * @flags: TT sync flags + */ static void batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, - struct batadv_orig_node *orig_node, int ttvn) + struct batadv_orig_node *orig_node, int ttvn, + u8 flags) { struct batadv_tt_orig_list_entry *orig_entry; @@ -1561,7 +1593,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, * was added during a "temporary client detection" */ orig_entry->ttvn = ttvn; - goto out; + orig_entry->flags = flags; + goto sync_flags; } orig_entry = kmem_cache_zalloc(batadv_tt_orig_cache, GFP_ATOMIC); @@ -1573,6 +1606,7 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, batadv_tt_global_size_inc(orig_node, tt_global->common.vid); orig_entry->orig_node = orig_node; orig_entry->ttvn = ttvn; + orig_entry->flags = flags; kref_init(&orig_entry->refcount); spin_lock_bh(&tt_global->list_lock); @@ -1582,6 +1616,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, spin_unlock_bh(&tt_global->list_lock); atomic_inc(&tt_global->orig_list_count); +sync_flags: + batadv_tt_global_sync_flags(tt_global); out: if (orig_entry) batadv_tt_orig_list_entry_put(orig_entry); @@ -1703,10 +1739,10 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } /* the change can carry possible "attribute" flags like the - * TT_CLIENT_WIFI, therefore they have to be copied in the + * TT_CLIENT_TEMP, therefore they have to be copied in the * client entry */ - common->flags |= flags; + common->flags |= flags & (~BATADV_TT_SYNC_MASK); /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a @@ -1723,7 +1759,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } add_orig_entry: /* add the new orig_entry (if needed) or update it */ - batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn); + batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn, + flags & BATADV_TT_SYNC_MASK); batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new global tt entry: %pM (vid: %d, via %pM)\n", @@ -1946,6 +1983,7 @@ batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_tt_orig_list_entry *orig, bool best) { + u16 flags = (common->flags & (~BATADV_TT_SYNC_MASK)) | orig->flags; void *hdr; struct batadv_orig_node_vlan *vlan; u8 last_ttvn; @@ -1975,7 +2013,7 @@ batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, nla_put_u8(msg, BATADV_ATTR_TT_LAST_TTVN, last_ttvn) || nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || - nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, common->flags)) + nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, flags)) goto nla_put_failure; if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) @@ -2589,6 +2627,7 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; + struct batadv_tt_orig_list_entry *tt_orig; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; struct hlist_head *head; @@ -2627,8 +2666,9 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, /* find out if this global entry is announced by this * originator */ - if (!batadv_tt_global_entry_has_orig(tt_global, - orig_node)) + tt_orig = batadv_tt_global_orig_entry_find(tt_global, + orig_node); + if (!tt_orig) continue; /* use network order to read the VID: this ensures that @@ -2640,10 +2680,12 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, /* compute the CRC on flags that have to be kept in sync * among nodes */ - flags = tt_common->flags & BATADV_TT_SYNC_MASK; + flags = tt_orig->flags; crc_tmp = crc32c(crc_tmp, &flags, sizeof(flags)); crc ^= crc32c(crc_tmp, tt_common->addr, ETH_ALEN); + + batadv_tt_orig_list_entry_put(tt_orig); } rcu_read_unlock(); } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ea43a6449247..a62795868794 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1260,6 +1260,7 @@ struct batadv_tt_global_entry { * struct batadv_tt_orig_list_entry - orig node announcing a non-mesh client * @orig_node: pointer to orig node announcing this non-mesh client * @ttvn: translation table version number which added the non-mesh client + * @flags: per orig entry TT sync flags * @list: list node for batadv_tt_global_entry::orig_list * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner @@ -1267,6 +1268,7 @@ struct batadv_tt_global_entry { struct batadv_tt_orig_list_entry { struct batadv_orig_node *orig_node; u8 ttvn; + u8 flags; struct hlist_node list; struct kref refcount; struct rcu_head rcu; diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 746b145bfd11..417df675c71b 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -306,7 +306,7 @@ static __u32 *get_choose_arg_weights(const struct crush_bucket_straw2 *bucket, const struct crush_choose_arg *arg, int position) { - if (!arg || !arg->weight_set || arg->weight_set_size == 0) + if (!arg || !arg->weight_set) return bucket->item_weights; if (position >= arg->weight_set_size) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b7cc615d42ef..a67298c7e0cd 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1287,10 +1287,10 @@ static void prepare_write_message(struct ceph_connection *con) if (m->needs_out_seq) { m->hdr.seq = cpu_to_le64(++con->out_seq); m->needs_out_seq = false; - } - if (con->ops->reencode_message) - con->ops->reencode_message(m); + if (con->ops->reencode_message) + con->ops->reencode_message(m); + } dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n", m, con->out_seq, le16_to_cpu(m->hdr.type), diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 901bb8221366..dcfbdd74dfd1 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1337,6 +1337,8 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, bool legacy_change; bool split = false; bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE); + bool recovery_deletes = ceph_osdmap_flag(osdc, + CEPH_OSDMAP_RECOVERY_DELETES); enum calc_target_result ct_res; int ret; @@ -1399,6 +1401,8 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, pi->pg_num, t->sort_bitwise, sort_bitwise, + t->recovery_deletes, + recovery_deletes, &last_pgid)) force_resend = true; @@ -1421,6 +1425,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, t->pg_num = pi->pg_num; t->pg_num_mask = pi->pg_num_mask; t->sort_bitwise = sort_bitwise; + t->recovery_deletes = recovery_deletes; t->osd = acting.primary; } @@ -1918,10 +1923,12 @@ static void encode_request_partial(struct ceph_osd_request *req, } ceph_encode_32(&p, req->r_attempts); /* retry_attempt */ - BUG_ON(p != end - 8); /* space for features */ + BUG_ON(p > end - 8); /* space for features */ msg->hdr.version = cpu_to_le16(8); /* MOSDOp v8 */ /* front_len is finalized in encode_request_finish() */ + msg->front.iov_len = p - msg->front.iov_base; + msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); msg->hdr.data_len = cpu_to_le32(data_len); /* * The header "data_off" is a hint to the receiver allowing it @@ -1937,11 +1944,12 @@ static void encode_request_partial(struct ceph_osd_request *req, static void encode_request_finish(struct ceph_msg *msg) { void *p = msg->front.iov_base; + void *const partial_end = p + msg->front.iov_len; void *const end = p + msg->front_alloc_len; if (CEPH_HAVE_FEATURE(msg->con->peer_features, RESEND_ON_SPLIT)) { /* luminous OSD -- encode features and be done */ - p = end - 8; + p = partial_end; ceph_encode_64(&p, msg->con->peer_features); } else { struct { @@ -1984,7 +1992,7 @@ static void encode_request_finish(struct ceph_msg *msg) oid_len = p - oid; tail = p; - tail_len = (end - p) - 8; + tail_len = partial_end - p; p = msg->front.iov_base; ceph_encode_copy(&p, &head.client_inc, sizeof(head.client_inc)); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 64ae9f89773a..f358d0bfa76b 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -295,6 +295,10 @@ static int decode_choose_args(void **p, void *end, struct crush_map *c) ret = decode_choose_arg(p, end, arg); if (ret) goto fail; + + if (arg->ids_size && + arg->ids_size != c->buckets[bucket_index]->size) + goto e_inval; } insert_choose_arg_map(&c->choose_args, arg_map); @@ -2078,6 +2082,8 @@ bool ceph_is_new_interval(const struct ceph_osds *old_acting, u32 new_pg_num, bool old_sort_bitwise, bool new_sort_bitwise, + bool old_recovery_deletes, + bool new_recovery_deletes, const struct ceph_pg *pgid) { return !osds_equal(old_acting, new_acting) || @@ -2085,7 +2091,8 @@ bool ceph_is_new_interval(const struct ceph_osds *old_acting, old_size != new_size || old_min_size != new_min_size || ceph_pg_is_split(pgid, old_pg_num, new_pg_num) || - old_sort_bitwise != new_sort_bitwise; + old_sort_bitwise != new_sort_bitwise || + old_recovery_deletes != new_recovery_deletes; } static int calc_pg_rank(int osd, const struct ceph_osds *acting) @@ -2301,10 +2308,17 @@ static u32 raw_pg_to_pps(struct ceph_pg_pool_info *pi, } } +/* + * Magic value used for a "default" fallback choose_args, used if the + * crush_choose_arg_map passed to do_crush() does not exist. If this + * also doesn't exist, fall back to canonical weights. + */ +#define CEPH_DEFAULT_CHOOSE_ARGS -1 + static int do_crush(struct ceph_osdmap *map, int ruleno, int x, int *result, int result_max, const __u32 *weight, int weight_max, - u64 choose_args_index) + s64 choose_args_index) { struct crush_choose_arg_map *arg_map; int r; @@ -2313,6 +2327,9 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x, arg_map = lookup_choose_arg_map(&map->crush->choose_args, choose_args_index); + if (!arg_map) + arg_map = lookup_choose_arg_map(&map->crush->choose_args, + CEPH_DEFAULT_CHOOSE_ARGS); mutex_lock(&map->crush_workspace_mutex); r = crush_do_rule(map->crush, ruleno, x, result, result_max, @@ -2423,40 +2440,23 @@ static void apply_upmap(struct ceph_osdmap *osdmap, for (i = 0; i < pg->pg_upmap.len; i++) raw->osds[i] = pg->pg_upmap.osds[i]; raw->size = pg->pg_upmap.len; - return; + /* check and apply pg_upmap_items, if any */ } pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid); if (pg) { - /* - * Note: this approach does not allow a bidirectional swap, - * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1]. - */ - for (i = 0; i < pg->pg_upmap_items.len; i++) { - int from = pg->pg_upmap_items.from_to[i][0]; - int to = pg->pg_upmap_items.from_to[i][1]; - int pos = -1; - bool exists = false; - - /* make sure replacement doesn't already appear */ - for (j = 0; j < raw->size; j++) { - int osd = raw->osds[j]; - - if (osd == to) { - exists = true; + for (i = 0; i < raw->size; i++) { + for (j = 0; j < pg->pg_upmap_items.len; j++) { + int from = pg->pg_upmap_items.from_to[j][0]; + int to = pg->pg_upmap_items.from_to[j][1]; + + if (from == raw->osds[i]) { + if (!(to != CRUSH_ITEM_NONE && + to < osdmap->max_osd && + osdmap->osd_weight[to] == 0)) + raw->osds[i] = to; break; } - /* ignore mapping if target is marked out */ - if (osd == from && pos < 0 && - !(to != CRUSH_ITEM_NONE && - to < osdmap->max_osd && - osdmap->osd_weight[to] == 0)) { - pos = j; - } - } - if (!exists && pos >= 0) { - raw->osds[pos] = to; - return; } } } diff --git a/net/core/dev.c b/net/core/dev.c index 8515f8fe0460..ce15a06d5558 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2739,7 +2739,7 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) return skb->ip_summed != CHECKSUM_PARTIAL && - skb->ip_summed != CHECKSUM_NONE; + skb->ip_summed != CHECKSUM_UNNECESSARY; return skb->ip_summed == CHECKSUM_NONE; } diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 06b147d7d9e2..709a4e6fb447 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -263,6 +263,8 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return dev_set_mtu(dev, ifr->ifr_mtu); case SIOCSIFHWADDR: + if (dev->addr_len > sizeof(struct sockaddr)) + return -EINVAL; return dev_set_mac_address(dev, &ifr->ifr_hwaddr); case SIOCSIFHWBROADCAST: diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 8357f164c660..912731bed7b7 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -666,7 +666,7 @@ int netpoll_setup(struct netpoll *np) int err; rtnl_lock(); - if (np->dev_name) { + if (np->dev_name[0]) { struct net *net = current->nsproxy->net_ns; ndev = __dev_get_by_name(net, np->dev_name); } diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 1704948e6a12..f227f002c73d 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -1471,9 +1471,12 @@ int dccp_feat_init(struct sock *sk) * singleton values (which always leads to failure). * These settings can still (later) be overridden via sockopts. */ - if (ccid_get_builtin_ccids(&tx.val, &tx.len) || - ccid_get_builtin_ccids(&rx.val, &rx.len)) + if (ccid_get_builtin_ccids(&tx.val, &tx.len)) return -ENOBUFS; + if (ccid_get_builtin_ccids(&rx.val, &rx.len)) { + kfree(tx.val); + return -ENOBUFS; + } if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) || !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len)) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index f85d901f4e3f..1b202f16531f 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -631,6 +631,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); + reqsk_put(req); return 0; drop_and_free: diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index c376af5bfdfb..1b58eac8aad3 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -380,6 +380,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); + reqsk_put(req); return 0; drop_and_free: diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 56e46090526b..c442051d5a55 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -509,21 +509,22 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, dst->cpu_dp->netdev = ethernet_dev; } + /* Initialize cpu_port_mask now for drv->setup() + * to have access to a correct value, just like what + * net/dsa/dsa.c::dsa_switch_setup_one does. + */ + ds->cpu_port_mask |= BIT(index); + tag_protocol = ds->ops->get_tag_protocol(ds); dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); if (IS_ERR(dst->tag_ops)) { dev_warn(ds->dev, "No tagger for this switch\n"); + ds->cpu_port_mask &= ~BIT(index); return PTR_ERR(dst->tag_ops); } dst->rcv = dst->tag_ops->rcv; - /* Initialize cpu_port_mask now for drv->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - ds->cpu_port_mask |= BIT(index); - return 0; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 76c2077c3f5b..2e548eca3489 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1731,6 +1731,13 @@ static __net_init int inet_init_net(struct net *net) net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif + /* Some igmp sysctl, whose values are always used */ + net->ipv4.sysctl_igmp_max_memberships = 20; + net->ipv4.sysctl_igmp_max_msf = 10; + /* IGMP reports for link-local multicast groups are enabled by default */ + net->ipv4.sysctl_igmp_llm_reports = 1; + net->ipv4.sysctl_igmp_qrv = 2; + return 0; } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c4c6e1969ed0..2ae8f54cb321 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1523,9 +1523,17 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) int taglen; for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) { - if (optptr[0] == IPOPT_CIPSO) + switch (optptr[0]) { + case IPOPT_CIPSO: return optptr; - taglen = optptr[1]; + case IPOPT_END: + return NULL; + case IPOPT_NOOP: + taglen = 1; + break; + default: + taglen = optptr[1]; + } optlen -= taglen; optptr += taglen; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 222100103808..b8d18171cca3 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1452,7 +1452,7 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh, return call_fib_notifiers(dev_net(fib_nh->nh_dev), event_type, &info.info); case FIB_EVENT_NH_DEL: - if ((IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && + if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && fib_nh->nh_flags & RTNH_F_LINKDOWN) || (fib_nh->nh_flags & RTNH_F_DEAD)) return call_fib_notifiers(dev_net(fib_nh->nh_dev), diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 8e0257d01200..1540db65241a 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -450,6 +450,7 @@ out_unlock: out: NAPI_GRO_CB(skb)->flush |= flush; skb_gro_remcsum_cleanup(skb, &grc); + skb->remcsum_offload = 0; return pp; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 28f14afd0dd3..498706b072fb 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2974,12 +2974,6 @@ static int __net_init igmp_net_init(struct net *net) goto out_sock; } - /* Sysctl initialization */ - net->ipv4.sysctl_igmp_max_memberships = 20; - net->ipv4.sysctl_igmp_max_msf = 10; - /* IGMP reports for link-local multicast groups are enabled by default */ - net->ipv4.sysctl_igmp_llm_reports = 1; - net->ipv4.sysctl_igmp_qrv = 2; return 0; out_sock: diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 50c74cd890bc..e153c40c2436 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -965,11 +965,12 @@ static int __ip_append_data(struct sock *sk, csummode = CHECKSUM_PARTIAL; cork->length += length; - if ((((length + (skb ? skb->len : fragheaderlen)) > mtu) || - (skb && skb_is_gso(skb))) && + if ((skb && skb_is_gso(skb)) || + (((length + (skb ? skb->len : fragheaderlen)) > mtu) && + (skb_queue_len(queue) <= 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && - (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { + (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx)) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); @@ -1288,6 +1289,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, return -EINVAL; if ((size + skb->len > mtu) && + (skb_queue_len(&sk->sk_write_queue) == 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { if (skb->ip_summed != CHECKSUM_PARTIAL) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2920e0cb09f8..53de1424c13c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -107,6 +107,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ +#define FLAG_SET_XMIT_TIMER 0x1000 /* Set TLP or RTO timer */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ #define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */ @@ -2520,8 +2521,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) return; /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || - (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { + if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH && + (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) { tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_jiffies32; } @@ -3004,10 +3005,7 @@ void tcp_rearm_rto(struct sock *sk) /* Offset the time elapsed after installing regular RTO */ if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { - struct sk_buff *skb = tcp_write_queue_head(sk); - u64 rto_time_stamp = skb->skb_mstamp + - jiffies_to_usecs(rto); - s64 delta_us = rto_time_stamp - tp->tcp_mstamp; + s64 delta_us = tcp_rto_delta_us(sk); /* delta_us may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ @@ -3019,6 +3017,13 @@ void tcp_rearm_rto(struct sock *sk) } } +/* Try to schedule a loss probe; if that doesn't work, then schedule an RTO. */ +static void tcp_set_xmit_timer(struct sock *sk) +{ + if (!tcp_schedule_loss_probe(sk)) + tcp_rearm_rto(sk); +} + /* If we get here, the whole TSO packet has not been acked. */ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) { @@ -3180,7 +3185,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, ca_rtt_us, sack->rate); if (flag & FLAG_ACKED) { - tcp_rearm_rto(sk); + flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */ if (unlikely(icsk->icsk_mtup.probe_size && !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) { tcp_mtup_probe_success(sk); @@ -3208,7 +3213,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. */ - tcp_rearm_rto(sk); + flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */ } if (icsk->icsk_ca_ops->pkts_acked) { @@ -3580,9 +3585,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; - if (icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) - tcp_rearm_rto(sk); - if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; icsk->icsk_retransmits = 0; @@ -3647,18 +3649,20 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked, &sack_state); + if (tp->tlp_high_seq) + tcp_process_tlp_ack(sk, ack, flag); + /* If needed, reset TLP/RTO timer; RACK may later override this. */ + if (flag & FLAG_SET_XMIT_TIMER) + tcp_set_xmit_timer(sk); + if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); } - if (tp->tlp_high_seq) - tcp_process_tlp_ack(sk, ack, flag); if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) sk_dst_confirm(sk); - if (icsk->icsk_pending == ICSK_TIME_RETRANS) - tcp_schedule_loss_probe(sk); delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ lost = tp->lost - lost; /* freshly marked lost */ tcp_rate_gen(sk, delivered, lost, sack_state.rate); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4e985dea1dd2..b7661a68d498 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2202,9 +2202,10 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { const u32 now = tcp_jiffies32; + enum tcp_chrono old = tp->chrono_type; - if (tp->chrono_type > TCP_CHRONO_UNSPEC) - tp->chrono_stat[tp->chrono_type - 1] += now - tp->chrono_start; + if (old > TCP_CHRONO_UNSPEC) + tp->chrono_stat[old - 1] += now - tp->chrono_start; tp->chrono_start = now; tp->chrono_type = new; } @@ -2376,24 +2377,15 @@ bool tcp_schedule_loss_probe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, tlp_time_stamp, rto_time_stamp; u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3); + u32 timeout, rto_delta_us; - /* No consecutive loss probes. */ - if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) { - tcp_rearm_rto(sk); - return false; - } /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ if (tp->fastopen_rsk) return false; - /* TLP is only scheduled when next timer event is RTO. */ - if (icsk->icsk_pending != ICSK_TIME_RETRANS) - return false; - /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ @@ -2416,14 +2408,10 @@ bool tcp_schedule_loss_probe(struct sock *sk) (rtt + (rtt >> 1) + TCP_DELACK_MAX)); timeout = max_t(u32, timeout, msecs_to_jiffies(10)); - /* If RTO is shorter, just schedule TLP in its place. */ - tlp_time_stamp = tcp_jiffies32 + timeout; - rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout; - if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) { - s32 delta = rto_time_stamp - tcp_jiffies32; - if (delta > 0) - timeout = delta; - } + /* If the RTO formula yields an earlier time, then use that time. */ + rto_delta_us = tcp_rto_delta_us(sk); /* How far in future is RTO? */ + if (rto_delta_us > 0) + timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); @@ -3448,6 +3436,10 @@ int tcp_connect(struct sock *sk) int err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB); + + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) + return -EHOSTUNREACH; /* Routing failure or similar. */ + tcp_connect_init(sk); if (unlikely(tp->repair)) { diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c0feeeef962a..e906014890b6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -652,7 +652,8 @@ static void tcp_keepalive_timer (unsigned long data) goto death; } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) + if (!sock_flag(sk, SOCK_KEEPOPEN) || + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT))) goto out; elapsed = keepalive_time_when(tp); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b057653ceca9..a7c804f73990 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -802,7 +802,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); - else if (sk->sk_no_check_tx) { /* UDP csum disabled */ + else if (sk->sk_no_check_tx && !skb_is_gso(skb)) { /* UDP csum off */ skb->ip_summed = CHECKSUM_NONE; goto send; @@ -1163,34 +1163,32 @@ out: return ret; } -#if BITS_PER_LONG == 64 +#define UDP_SKB_IS_STATELESS 0x80000000 + static void udp_set_dev_scratch(struct sk_buff *skb) { - struct udp_dev_scratch *scratch; + struct udp_dev_scratch *scratch = udp_skb_scratch(skb); BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long)); - scratch = (struct udp_dev_scratch *)&skb->dev_scratch; - scratch->truesize = skb->truesize; + scratch->_tsize_state = skb->truesize; +#if BITS_PER_LONG == 64 scratch->len = skb->len; scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); +#endif + if (likely(!skb->_skb_refdst)) + scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } static int udp_skb_truesize(struct sk_buff *skb) { - return ((struct udp_dev_scratch *)&skb->dev_scratch)->truesize; -} -#else -static void udp_set_dev_scratch(struct sk_buff *skb) -{ - skb->dev_scratch = skb->truesize; + return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS; } -static int udp_skb_truesize(struct sk_buff *skb) +static bool udp_skb_has_head_state(struct sk_buff *skb) { - return skb->dev_scratch; + return !(udp_skb_scratch(skb)->_tsize_state & UDP_SKB_IS_STATELESS); } -#endif /* fully reclaim rmem/fwd memory allocated for skb */ static void udp_rmem_release(struct sock *sk, int size, int partial, @@ -1388,10 +1386,10 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) unlock_sock_fast(sk, slow); } - /* we cleared the head states previously only if the skb lacks any IP - * options, see __udp_queue_rcv_skb(). + /* In the more common cases we cleared the head states previously, + * see __udp_queue_rcv_skb(). */ - if (unlikely(IPCB(skb)->opt.optlen > 0)) + if (unlikely(udp_skb_has_head_state(skb))) skb_release_head_state(skb); consume_stateless_skb(skb); } @@ -1784,11 +1782,11 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id_once(sk, skb); } - /* At recvmsg() time we need skb->dst to process IP options-related - * cmsg, elsewhere can we clear all pending head states while they are - * hot in the cache + /* At recvmsg() time we may access skb->dst or skb->sp depending on + * the IP options and the cmsg flags, elsewhere can we clear all + * pending head states while they are hot in the cache */ - if (likely(IPCB(skb)->opt.optlen == 0)) + if (likely(IPCB(skb)->opt.optlen == 0 && !skb_sec_path(skb))) skb_release_head_state(skb); rc = __udp_enqueue_schedule_skb(sk, skb); @@ -1930,7 +1928,7 @@ drop: /* For TCP sockets, sk_rx_dst is protected by socket lock * For UDP, we use xchg() to guard against concurrent changes. */ -static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) +void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old; @@ -1939,6 +1937,7 @@ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) dst_release(old); } } +EXPORT_SYMBOL(udp_sk_rx_dst_set); /* * Multicasts and broadcasts go to each listener. diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 781250151d40..0932c85b42af 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -235,7 +235,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (uh->check == 0) uh->check = CSUM_MANGLED_0; - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 4996d734f1d2..3cec529c6113 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -756,6 +756,7 @@ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) goto drop; + IP6CB(skb)->flags |= IP6SKB_JUMBOGRAM; return true; drop: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1422d6c08377..2dfe50d8d609 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -673,8 +673,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, *prevhdr = NEXTHDR_FRAGMENT; tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } @@ -789,8 +787,6 @@ slow_path: frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) + hroom + troom, GFP_ATOMIC); if (!frag) { - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } @@ -1385,11 +1381,12 @@ emsgsize: */ cork->length += length; - if ((((length + (skb ? skb->len : headersize)) > mtu) || - (skb && skb_is_gso(skb))) && + if ((skb && skb_is_gso(skb)) || + (((length + (skb ? skb->len : headersize)) > mtu) && + (skb_queue_len(queue) <= 1) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && - (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { + (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk))) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, transhdrlen, mtu, flags, fl6); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4d30c96a819d..a640fbcba15d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2351,6 +2351,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; + nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; if (ip6_ins_rt(nrt)) @@ -2461,6 +2462,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), + .fc_protocol = RTPROT_RA, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, @@ -2513,6 +2515,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), + .fc_protocol = RTPROT_RA, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = dev_net(dev), @@ -3424,14 +3427,6 @@ static int rt6_fill_node(struct net *net, rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->rt6i_protocol; - if (rt->rt6i_flags & RTF_DYNAMIC) - rtm->rtm_protocol = RTPROT_REDIRECT; - else if (rt->rt6i_flags & RTF_ADDRCONF) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO)) - rtm->rtm_protocol = RTPROT_RA; - else - rtm->rtm_protocol = RTPROT_KERNEL; - } if (rt->rt6i_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4a3e65626e8b..578142b7ca3e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -291,11 +291,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, struct udp_table *udptable) { const struct ipv6hdr *iph = ipv6_hdr(skb); - struct sock *sk; - sk = skb_steal_sock(skb); - if (unlikely(sk)) - return sk; return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), udptable, skb); @@ -332,6 +328,15 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be EXPORT_SYMBOL_GPL(udp6_lib_lookup); #endif +/* do not use the scratch area len for jumbogram: their length execeeds the + * scratch area space; note that the IP6CB flags is still in the first + * cacheline, so checking for jumbograms is cheap + */ +static int udp6_skb_len(struct sk_buff *skb) +{ + return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb); +} + /* * This should be easy, if there is something there we * return it, otherwise we block. @@ -362,7 +367,7 @@ try_again: if (!skb) return err; - ulen = udp_skb_len(skb); + ulen = udp6_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; @@ -804,6 +809,24 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp6_csum_init(skb, uh, proto)) goto csum_error; + /* Check if the socket is already available, e.g. due to early demux */ + sk = skb_steal_sock(skb); + if (sk) { + struct dst_entry *dst = skb_dst(skb); + int ret; + + if (unlikely(sk->sk_rx_dst != dst)) + udp_sk_rx_dst_set(sk, dst); + + ret = udpv6_queue_rcv_skb(sk, skb); + sock_put(sk); + + /* a return value > 0 means to resubmit the input */ + if (ret > 0) + return ret; + return 0; + } + /* * Multicast receive code */ @@ -812,11 +835,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, saddr, daddr, udptable, proto); /* Unicast */ - - /* - * check socket cache ... must talk to Alan about his plans - * for sock caches... i'll skip this for now. - */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { int ret; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index a2267f80febb..e7d378c032cb 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -72,7 +72,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (uh->check == 0) uh->check = CSUM_MANGLED_0; - skb->ip_summed = CHECKSUM_NONE; + skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e3c4c6c3fef7..03859e386b47 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1310,8 +1310,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, nla_for_each_nested(a, attr, rem) { int type = nla_type(a); - int maxlen = ovs_ct_attr_lens[type].maxlen; - int minlen = ovs_ct_attr_lens[type].minlen; + int maxlen; + int minlen; if (type > OVS_CT_ATTR_MAX) { OVS_NLERR(log, @@ -1319,6 +1319,9 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, type, OVS_CT_ATTR_MAX); return -EINVAL; } + + maxlen = ovs_ct_attr_lens[type].maxlen; + minlen = ovs_ct_attr_lens[type].minlen; if (nla_len(a) < minlen || nla_len(a) > maxlen) { OVS_NLERR(log, "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)", diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 008bb34ee324..008a45ca3112 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3700,14 +3700,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; - po->tp_reserve = val; - return 0; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_reserve = val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_LOSS: { @@ -4329,7 +4334,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, register_prot_hook(sk); } spin_unlock(&po->bind_lock); - if (closing && (po->tp_version > TPACKET_V2)) { + if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index e10624aa6959..9722bf839d9d 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -1015,8 +1015,10 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, if (rds_ib_ring_empty(&ic->i_recv_ring)) rds_ib_stats_inc(s_ib_rx_ring_empty); - if (rds_ib_ring_low(&ic->i_recv_ring)) + if (rds_ib_ring_low(&ic->i_recv_ring)) { rds_ib_recv_refill(conn, 0, GFP_NOWAIT); + rds_ib_stats_inc(s_ib_rx_refill_from_cq); + } } int rds_ib_recv_path(struct rds_conn_path *cp) @@ -1029,6 +1031,7 @@ int rds_ib_recv_path(struct rds_conn_path *cp) if (rds_conn_up(conn)) { rds_ib_attempt_ack(ic); rds_ib_recv_refill(conn, 0, GFP_KERNEL); + rds_ib_stats_inc(s_ib_rx_refill_from_thread); } return ret; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 36f0ced9e60c..d516ba8178b8 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -36,8 +36,8 @@ static struct tc_action_ops act_ipt_ops; static unsigned int xt_net_id; static struct tc_action_ops act_xt_ops; -static int ipt_init_target(struct xt_entry_target *t, char *table, - unsigned int hook) +static int ipt_init_target(struct net *net, struct xt_entry_target *t, + char *table, unsigned int hook) { struct xt_tgchk_param par; struct xt_target *target; @@ -49,8 +49,9 @@ static int ipt_init_target(struct xt_entry_target *t, char *table, return PTR_ERR(target); t->u.kernel.target = target; + memset(&par, 0, sizeof(par)); + par.net = net; par.table = table; - par.entryinfo = NULL; par.target = target; par.targinfo = t->data; par.hook_mask = hook; @@ -91,10 +92,11 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; -static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, +static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, id); struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; struct xt_entry_target *td, *t; @@ -159,7 +161,7 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, if (unlikely(!t)) goto err2; - err = ipt_init_target(t, tname, hook); + err = ipt_init_target(net, t, tname, hook); if (err < 0) goto err3; @@ -193,18 +195,16 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind) { - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return __tcf_ipt_init(tn, nla, est, a, &act_ipt_ops, ovr, bind); + return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, + bind); } static int tcf_xt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind) { - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return __tcf_ipt_init(tn, nla, est, a, &act_xt_ops, ovr, bind); + return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, + bind); } static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/socket.c b/net/socket.c index bf2122691fba..ad22df1ffbd1 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1916,7 +1916,7 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; - kmsg->msg_control = msg.msg_control; + kmsg->msg_control = (void __force *)msg.msg_control; kmsg->msg_controllen = msg.msg_controllen; kmsg->msg_flags = msg.msg_flags; @@ -1935,7 +1935,8 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, if (msg.msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(msg.msg_name, kmsg->msg_namelen, + err = move_addr_to_kernel(msg.msg_name, + kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index ac701c28f44f..c2c68a15b59d 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -171,10 +171,10 @@ int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs) /* * Add the temporary list to the backchannel preallocation list */ - spin_lock_bh(&xprt->bc_pa_lock); + spin_lock(&xprt->bc_pa_lock); list_splice(&tmp_list, &xprt->bc_pa_list); xprt_inc_alloc_count(xprt, min_reqs); - spin_unlock_bh(&xprt->bc_pa_lock); + spin_unlock(&xprt->bc_pa_lock); dprintk("RPC: setup backchannel transport done\n"); return 0; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 2e49d1f892b7..69a9e5953744 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1903,6 +1903,14 @@ call_connect_status(struct rpc_task *task) task->tk_status = 0; switch (status) { case -ECONNREFUSED: + /* A positive refusal suggests a rebind is needed. */ + if (RPC_IS_SOFTCONN(task)) + break; + if (clnt->cl_autobind) { + rpc_force_rebind(clnt); + task->tk_action = call_bind; + return; + } case -ECONNRESET: case -ECONNABORTED: case -ENETUNREACH: diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 2b720fa35c4f..272063ca81e8 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1001,7 +1001,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) if (!bc_xprt) return -EAGAIN; - spin_lock_bh(&bc_xprt->transport_lock); + spin_lock(&bc_xprt->recv_lock); req = xprt_lookup_rqst(bc_xprt, xid); if (!req) goto unlock_notfound; @@ -1019,7 +1019,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) memcpy(dst->iov_base, src->iov_base, src->iov_len); xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len); rqstp->rq_arg.len = 0; - spin_unlock_bh(&bc_xprt->transport_lock); + spin_unlock(&bc_xprt->recv_lock); return 0; unlock_notfound: printk(KERN_NOTICE @@ -1028,7 +1028,7 @@ unlock_notfound: __func__, ntohl(calldir), bc_xprt, ntohl(xid)); unlock_eagain: - spin_unlock_bh(&bc_xprt->transport_lock); + spin_unlock(&bc_xprt->recv_lock); return -EAGAIN; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 4654a9934269..2af189c5ac3e 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -844,6 +844,48 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) } EXPORT_SYMBOL_GPL(xprt_lookup_rqst); +/** + * xprt_pin_rqst - Pin a request on the transport receive list + * @req: Request to pin + * + * Caller must ensure this is atomic with the call to xprt_lookup_rqst() + * so should be holding the xprt transport lock. + */ +void xprt_pin_rqst(struct rpc_rqst *req) +{ + set_bit(RPC_TASK_MSG_RECV, &req->rq_task->tk_runstate); +} + +/** + * xprt_unpin_rqst - Unpin a request on the transport receive list + * @req: Request to pin + * + * Caller should be holding the xprt transport lock. + */ +void xprt_unpin_rqst(struct rpc_rqst *req) +{ + struct rpc_task *task = req->rq_task; + + clear_bit(RPC_TASK_MSG_RECV, &task->tk_runstate); + if (test_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate)) + wake_up_bit(&task->tk_runstate, RPC_TASK_MSG_RECV); +} + +static void xprt_wait_on_pinned_rqst(struct rpc_rqst *req) +__must_hold(&req->rq_xprt->recv_lock) +{ + struct rpc_task *task = req->rq_task; + + if (task && test_bit(RPC_TASK_MSG_RECV, &task->tk_runstate)) { + spin_unlock(&req->rq_xprt->recv_lock); + set_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate); + wait_on_bit(&task->tk_runstate, RPC_TASK_MSG_RECV, + TASK_UNINTERRUPTIBLE); + clear_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate); + spin_lock(&req->rq_xprt->recv_lock); + } +} + static void xprt_update_rtt(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; @@ -966,13 +1008,13 @@ void xprt_transmit(struct rpc_task *task) /* * Add to the list only if we're expecting a reply */ - spin_lock_bh(&xprt->transport_lock); /* Update the softirq receive buffer */ memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(req->rq_private_buf)); /* Add request to the receive list */ + spin_lock(&xprt->recv_lock); list_add_tail(&req->rq_list, &xprt->recv); - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->recv_lock); xprt_reset_majortimeo(req); /* Turn off autodisconnect */ del_singleshot_timer_sync(&xprt->timer); @@ -1287,12 +1329,16 @@ void xprt_release(struct rpc_task *task) task->tk_ops->rpc_count_stats(task, task->tk_calldata); else if (task->tk_client) rpc_count_iostats(task, task->tk_client->cl_metrics); + spin_lock(&xprt->recv_lock); + if (!list_empty(&req->rq_list)) { + list_del(&req->rq_list); + xprt_wait_on_pinned_rqst(req); + } + spin_unlock(&xprt->recv_lock); spin_lock_bh(&xprt->transport_lock); xprt->ops->release_xprt(xprt, task); if (xprt->ops->release_request) xprt->ops->release_request(task); - if (!list_empty(&req->rq_list)) - list_del(&req->rq_list); xprt->last_used = jiffies; xprt_schedule_autodisconnect(xprt); spin_unlock_bh(&xprt->transport_lock); @@ -1318,6 +1364,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) spin_lock_init(&xprt->transport_lock); spin_lock_init(&xprt->reserve_lock); + spin_lock_init(&xprt->recv_lock); INIT_LIST_HEAD(&xprt->free); INIT_LIST_HEAD(&xprt->recv); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 84584caaa7e9..7fec4039cd15 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1292,7 +1292,7 @@ rpcrdma_reply_handler(struct work_struct *work) * RPC completion while holding the transport lock to ensure * the rep, rqst, and rq_task pointers remain stable. */ - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->recv_lock); rqst = xprt_lookup_rqst(xprt, xid); if (!rqst) goto out_norqst; @@ -1323,7 +1323,7 @@ out: xprt_release_rqst_cong(rqst->rq_task); xprt_complete_rqst(rqst->rq_task, status); - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->recv_lock); dprintk("RPC: %s: xprt_complete_rqst(0x%p, 0x%p, %d)\n", __func__, xprt, rqst, status); return; @@ -1354,12 +1354,12 @@ out_badheader: status = -EIO; goto out; -/* The req was still available, but by the time the transport_lock +/* The req was still available, but by the time the recv_lock * was acquired, the rqst and task had been released. Thus the RPC * has already been terminated. */ out_norqst: - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->recv_lock); rpcrdma_buffer_put(req); dprintk("RPC: %s: race, no rqst left for req %p\n", __func__, req); diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index ca41e28d2b36..ec37ad83b068 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -52,7 +52,7 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, if (src->iov_len < 24) goto out_shortreply; - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->recv_lock); req = xprt_lookup_rqst(xprt, xid); if (!req) goto out_notfound; @@ -69,17 +69,20 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, else if (credits > r_xprt->rx_buf.rb_bc_max_requests) credits = r_xprt->rx_buf.rb_bc_max_requests; + spin_lock_bh(&xprt->transport_lock); cwnd = xprt->cwnd; xprt->cwnd = credits << RPC_CWNDSHIFT; if (xprt->cwnd > cwnd) xprt_release_rqst_cong(req->rq_task); + spin_unlock_bh(&xprt->transport_lock); + ret = 0; xprt_complete_rqst(req->rq_task, rcvbuf->len); rcvbuf->len = 0; out_unlock: - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->recv_lock); out: return ret; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 5cf17001f0e2..9b5de31aa429 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -969,10 +969,12 @@ static void xs_local_data_read_skb(struct rpc_xprt *xprt, return; /* Look up and lock the request corresponding to the given XID */ - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->recv_lock); rovr = xprt_lookup_rqst(xprt, *xp); if (!rovr) goto out_unlock; + xprt_pin_rqst(rovr); + spin_unlock(&xprt->recv_lock); task = rovr->rq_task; copied = rovr->rq_private_buf.buflen; @@ -981,13 +983,16 @@ static void xs_local_data_read_skb(struct rpc_xprt *xprt, if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) { dprintk("RPC: sk_buff copy failed\n"); - goto out_unlock; + spin_lock(&xprt->recv_lock); + goto out_unpin; } + spin_lock(&xprt->recv_lock); xprt_complete_rqst(task, copied); - +out_unpin: + xprt_unpin_rqst(rovr); out_unlock: - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->recv_lock); } static void xs_local_data_receive(struct sock_xprt *transport) @@ -1050,10 +1055,12 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt, return; /* Look up and lock the request corresponding to the given XID */ - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->recv_lock); rovr = xprt_lookup_rqst(xprt, *xp); if (!rovr) goto out_unlock; + xprt_pin_rqst(rovr); + spin_unlock(&xprt->recv_lock); task = rovr->rq_task; if ((copied = rovr->rq_private_buf.buflen) > repsize) @@ -1062,16 +1069,21 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt, /* Suck it into the iovec, verify checksum if not done by hw. */ if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb)) { __UDPX_INC_STATS(sk, UDP_MIB_INERRORS); - goto out_unlock; + spin_lock(&xprt->recv_lock); + goto out_unpin; } __UDPX_INC_STATS(sk, UDP_MIB_INDATAGRAMS); + spin_lock_bh(&xprt->transport_lock); xprt_adjust_cwnd(xprt, task, copied); + spin_unlock_bh(&xprt->transport_lock); + spin_lock(&xprt->recv_lock); xprt_complete_rqst(task, copied); - +out_unpin: + xprt_unpin_rqst(rovr); out_unlock: - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->recv_lock); } static void xs_udp_data_receive(struct sock_xprt *transport) @@ -1277,25 +1289,12 @@ static inline void xs_tcp_read_common(struct rpc_xprt *xprt, } len = desc->count; - if (len > transport->tcp_reclen - transport->tcp_offset) { - struct xdr_skb_reader my_desc; - - len = transport->tcp_reclen - transport->tcp_offset; - memcpy(&my_desc, desc, sizeof(my_desc)); - my_desc.count = len; - r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied, - &my_desc, xdr_skb_read_bits); - desc->count -= r; - desc->offset += r; - } else - r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied, + if (len > transport->tcp_reclen - transport->tcp_offset) + desc->count = transport->tcp_reclen - transport->tcp_offset; + r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied, desc, xdr_skb_read_bits); - if (r > 0) { - transport->tcp_copied += r; - transport->tcp_offset += r; - } - if (r != len) { + if (desc->count) { /* Error when copying to the receive buffer, * usually because we weren't able to allocate * additional buffer pages. All we can do now @@ -1315,6 +1314,10 @@ static inline void xs_tcp_read_common(struct rpc_xprt *xprt, return; } + transport->tcp_copied += r; + transport->tcp_offset += r; + desc->count = len - r; + dprintk("RPC: XID %08x read %zd bytes\n", ntohl(transport->tcp_xid), r); dprintk("RPC: xprt = %p, tcp_copied = %lu, tcp_offset = %u, " @@ -1343,21 +1346,24 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, dprintk("RPC: read reply XID %08x\n", ntohl(transport->tcp_xid)); /* Find and lock the request corresponding to this xid */ - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->recv_lock); req = xprt_lookup_rqst(xprt, transport->tcp_xid); if (!req) { dprintk("RPC: XID %08x request not found!\n", ntohl(transport->tcp_xid)); - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->recv_lock); return -1; } + xprt_pin_rqst(req); + spin_unlock(&xprt->recv_lock); xs_tcp_read_common(xprt, desc, req); + spin_lock(&xprt->recv_lock); if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) xprt_complete_rqst(req->rq_task, transport->tcp_copied); - - spin_unlock_bh(&xprt->transport_lock); + xprt_unpin_rqst(req); + spin_unlock(&xprt->recv_lock); return 0; } @@ -1376,11 +1382,9 @@ static int xs_tcp_read_callback(struct rpc_xprt *xprt, container_of(xprt, struct sock_xprt, xprt); struct rpc_rqst *req; - /* Look up and lock the request corresponding to the given XID */ - spin_lock_bh(&xprt->transport_lock); + /* Look up the request corresponding to the given XID */ req = xprt_lookup_bc_request(xprt, transport->tcp_xid); if (req == NULL) { - spin_unlock_bh(&xprt->transport_lock); printk(KERN_WARNING "Callback slot table overflowed\n"); xprt_force_disconnect(xprt); return -1; @@ -1391,7 +1395,6 @@ static int xs_tcp_read_callback(struct rpc_xprt *xprt, if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) xprt_complete_bc_request(req, transport->tcp_copied); - spin_unlock_bh(&xprt->transport_lock); return 0; } @@ -1516,6 +1519,7 @@ static void xs_tcp_data_receive(struct sock_xprt *transport) .arg.data = xprt, }; unsigned long total = 0; + int loop; int read = 0; mutex_lock(&transport->recv_mutex); @@ -1524,20 +1528,20 @@ static void xs_tcp_data_receive(struct sock_xprt *transport) goto out; /* We use rd_desc to pass struct xprt to xs_tcp_data_recv */ - for (;;) { + for (loop = 0; loop < 64; loop++) { lock_sock(sk); read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv); if (read <= 0) { clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); release_sock(sk); - if (!test_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) - break; - } else { - release_sock(sk); - total += read; + break; } + release_sock(sk); + total += read; rd_desc.count = 65536; } + if (test_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) + queue_work(xprtiod_workqueue, &transport->recv_worker); out: mutex_unlock(&transport->recv_mutex); trace_xs_tcp_data_ready(xprt, read, total); diff --git a/net/tipc/node.c b/net/tipc/node.c index aeef8011ac7d..9b4dcb6a16b5 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1455,10 +1455,8 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, /* Initiate synch mode if applicable */ if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) { syncpt = iseqno + exp_pkts - 1; - if (!tipc_link_is_up(l)) { - tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + if (!tipc_link_is_up(l)) __tipc_node_link_up(n, bearer_id, xmitq); - } if (n->state == SELF_UP_PEER_UP) { n->sync_point = syncpt; tipc_link_fsm_evt(l, LINK_SYNCH_BEGIN_EVT); |