diff options
Diffstat (limited to 'net')
44 files changed, 421 insertions, 298 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index 4f62f299da0c..0a9019da18f3 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1623,10 +1623,6 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, } p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count); - if (!count) { - p9_tag_remove(clnt, req); - return 0; - } if (non_zc) { int n = copy_to_iter(dataptr, count, to); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index e48f7ac8a854..3ddd66e4c29e 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -702,7 +702,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR(BATADV_DRIVER_AUTHOR); MODULE_DESCRIPTION(BATADV_DRIVER_DESC); -MODULE_SUPPORTED_DEVICE(BATADV_DRIVER_DEVICE); MODULE_VERSION(BATADV_SOURCE_VERSION); MODULE_ALIAS_RTNL_LINK("batadv"); MODULE_ALIAS_GENL_FAMILY(BATADV_NL_NAME); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0edc0b2baaa4..1bdcb33fb561 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2147,7 +2147,7 @@ out: out_err: cb->args[1] = idx; cb->args[0] = h; - cb->seq = net->dev_base_seq; + cb->seq = tgt_net->dev_base_seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); if (netnsid >= 0) put_net(tgt_net); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 545a472273a5..c421c8f80925 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3659,6 +3659,8 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, struct ts_state state; unsigned int ret; + BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb)); + config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 3589224c8da9..58b8fc82cd3c 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -118,6 +118,8 @@ config NET_DSA_TAG_OCELOT config NET_DSA_TAG_OCELOT_8021Q tristate "Tag driver for Ocelot family of switches, using VLAN" + depends on MSCC_OCELOT_SWITCH_LIB || \ + (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST) select NET_DSA_TAG_8021Q help Say Y or M if you want to enable support for tagging frames with a diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 2eeaa42f2e08..9d4b0e9b1aa1 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -230,8 +230,8 @@ int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr); void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; -static inline bool dsa_port_offloads_netdev(struct dsa_port *dp, - struct net_device *dev) +static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, + struct net_device *dev) { /* Switchdev offloading can be configured on: */ @@ -241,12 +241,6 @@ static inline bool dsa_port_offloads_netdev(struct dsa_port *dp, */ return true; - if (dp->bridge_dev == dev) - /* DSA ports connected to a bridge, and event was emitted - * for the bridge. - */ - return true; - if (dp->lag_dev == dev) /* DSA ports connected to a bridge via a LAG */ return true; @@ -254,14 +248,23 @@ static inline bool dsa_port_offloads_netdev(struct dsa_port *dp, return false; } +static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, + struct net_device *bridge_dev) +{ + /* DSA ports connected to a bridge, and event was emitted + * for the bridge. + */ + return dp->bridge_dev == bridge_dev; +} + /* Returns true if any port of this tree offloads the given net_device */ -static inline bool dsa_tree_offloads_netdev(struct dsa_switch_tree *dst, - struct net_device *dev) +static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, + struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_offloads_netdev(dp, dev)) + if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 491e3761b5f4..992fcab4b552 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -278,28 +278,43 @@ static int dsa_slave_port_attr_set(struct net_device *dev, struct dsa_port *dp = dsa_slave_to_port(dev); int ret; - if (!dsa_port_offloads_netdev(dp, attr->orig_dev)) - return -EOPNOTSUPP; - switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_set_state(dp, attr->u.stp_state); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: + if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, extack); break; default: @@ -341,9 +356,6 @@ static int dsa_slave_vlan_add(struct net_device *dev, struct switchdev_obj_port_vlan vlan; int err; - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) - return -EOPNOTSUPP; - if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; @@ -391,27 +403,36 @@ static int dsa_slave_port_obj_add(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + return -EOPNOTSUPP; + /* DSA can directly translate this to a normal MDB add, * but on the CPU port. */ err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_slave_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mrp_add_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; @@ -431,9 +452,6 @@ static int dsa_slave_vlan_del(struct net_device *dev, struct switchdev_obj_port_vlan *vlan; int err; - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) - return -EOPNOTSUPP; - if (dsa_port_skip_vlan_configuration(dp)) return 0; @@ -459,27 +477,36 @@ static int dsa_slave_port_obj_del(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + return -EOPNOTSUPP; + /* DSA can directly translate this to a normal MDB add, * but on the CPU port. */ err = dsa_port_mdb_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_slave_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mrp_del_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; @@ -2298,7 +2325,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, * other ports bridged with the LAG should be able to * autonomously forward towards it. */ - if (dsa_tree_offloads_netdev(dp->ds->dst, dev)) + if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev)) return NOTIFY_DONE; } diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 38dcdded74c0..59748487664f 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -13,6 +13,7 @@ #define MTK_HDR_LEN 4 #define MTK_HDR_XMIT_UNTAGGED 0 #define MTK_HDR_XMIT_TAGGED_TPID_8100 1 +#define MTK_HDR_XMIT_TAGGED_TPID_88A8 2 #define MTK_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) #define MTK_HDR_XMIT_DP_BIT_MASK GENMASK(5, 0) #define MTK_HDR_XMIT_SA_DIS BIT(6) @@ -21,8 +22,8 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); + u8 xmit_tpid; u8 *mtk_tag; - bool is_vlan_skb = true; unsigned char *dest = eth_hdr(skb)->h_dest; bool is_multicast_skb = is_multicast_ether_addr(dest) && !is_broadcast_ether_addr(dest); @@ -33,10 +34,17 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, * the both special and VLAN tag at the same time and then look up VLAN * table with VID. */ - if (!skb_vlan_tagged(skb)) { + switch (skb->protocol) { + case htons(ETH_P_8021Q): + xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_8100; + break; + case htons(ETH_P_8021AD): + xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_88A8; + break; + default: + xmit_tpid = MTK_HDR_XMIT_UNTAGGED; skb_push(skb, MTK_HDR_LEN); memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN); - is_vlan_skb = false; } mtk_tag = skb->data + 2 * ETH_ALEN; @@ -44,8 +52,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, /* Mark tag attribute on special tag insertion to notify hardware * whether that's a combined special tag with 802.1Q header. */ - mtk_tag[0] = is_vlan_skb ? MTK_HDR_XMIT_TAGGED_TPID_8100 : - MTK_HDR_XMIT_UNTAGGED; + mtk_tag[0] = xmit_tpid; mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; /* Disable SA learning for multicast frames */ @@ -53,7 +60,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS; /* Tag control information is kept for 802.1Q */ - if (!is_vlan_skb) { + if (xmit_tpid == MTK_HDR_XMIT_UNTAGGED) { mtk_tag[2] = 0; mtk_tag[3] = 0; } diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index c17d39b4a1a0..e9176475bac8 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -35,14 +35,12 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); + __be16 *p; u8 *tag; - u16 *p; u16 out; /* Pad out to at least 60 bytes */ - if (unlikely(eth_skb_pad(skb))) - return NULL; - if (skb_cow_head(skb, RTL4_A_HDR_LEN) < 0) + if (unlikely(__skb_put_padto(skb, ETH_ZLEN, false))) return NULL; netdev_dbg(dev, "add realtek tag to package to port %d\n", @@ -53,13 +51,13 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, tag = skb->data + 2 * ETH_ALEN; /* Set Ethertype */ - p = (u16 *)tag; + p = (__be16 *)tag; *p = htons(RTL4_A_ETHERTYPE); out = (RTL4_A_PROTOCOL_RTL8366RB << 12) | (2 << 8); - /* The lower bits is the port numer */ + /* The lower bits is the port number */ out |= (u8)dp->index; - p = (u16 *)(tag + 2); + p = (__be16 *)(tag + 2); *p = htons(out); return skb; diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 25a9e566ef5c..6a070dc8e4b0 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -116,10 +116,9 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) struct ethtool_channels channels = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; - const struct nlattr *err_attr; + u32 err_attr, max_rx_in_use = 0; const struct ethtool_ops *ops; struct net_device *dev; - u32 max_rx_in_use = 0; int ret; ret = ethnl_parse_header_dev_get(&req_info, @@ -157,34 +156,35 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) /* ensure new channel counts are within limits */ if (channels.rx_count > channels.max_rx) - err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (channels.tx_count > channels.max_tx) - err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else if (channels.other_count > channels.max_other) - err_attr = tb[ETHTOOL_A_CHANNELS_OTHER_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_OTHER_COUNT; else if (channels.combined_count > channels.max_combined) - err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; else - err_attr = NULL; + err_attr = 0; if (err_attr) { ret = -EINVAL; - NL_SET_ERR_MSG_ATTR(info->extack, err_attr, + NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], "requested channel count exceeds maximum"); goto out_ops; } /* ensure there is at least one RX and one TX channel */ if (!channels.combined_count && !channels.rx_count) - err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (!channels.combined_count && !channels.tx_count) - err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else - err_attr = NULL; + err_attr = 0; if (err_attr) { if (mod_combined) - err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; ret = -EINVAL; - NL_SET_ERR_MSG_ATTR(info->extack, err_attr, "requested channel counts would result in no RX or TX channel being configured"); + NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], + "requested channel counts would result in no RX or TX channel being configured"); goto out_ops; } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 471d33a0d095..bfaf327e9d12 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -519,16 +519,10 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!refcount_dec_and_test(&doi_def->refcount)) { - spin_unlock(&cipso_v4_doi_list_lock); - ret_val = -EBUSY; - goto doi_remove_return; - } list_del_rcu(&doi_def->list); spin_unlock(&cipso_v4_doi_list_lock); - cipso_v4_cache_invalidate(); - call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu); + cipso_v4_doi_putdef(doi_def); ret_val = 0; doi_remove_return: @@ -585,9 +579,6 @@ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def) if (!refcount_dec_and_test(&doi_def->refcount)) return; - spin_lock(&cipso_v4_doi_list_lock); - list_del_rcu(&doi_def->list); - spin_unlock(&cipso_v4_doi_list_lock); cipso_v4_cache_invalidate(); call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu); @@ -1162,7 +1153,7 @@ static void cipso_v4_gentag_hdr(const struct cipso_v4_doi *doi_def, { buf[0] = IPOPT_CIPSO; buf[1] = CIPSO_V4_HDR_LEN + len; - *(__be32 *)&buf[2] = htonl(doi_def->doi); + put_unaligned_be32(doi_def->doi, &buf[2]); } /** diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index ff327a62c9ce..da21dfce24d7 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(inet_peer_base_init); #define PEER_MAX_GC 32 /* Exported for sysctl_net_ipv4. */ -int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries more +int inet_peer_threshold __read_mostly; /* start to throw entries more * aggressively at this stage */ int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */ @@ -73,20 +73,13 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min /* Called from ip_output.c:ip_init */ void __init inet_initpeers(void) { - struct sysinfo si; + u64 nr_entries; - /* Use the straight interface to information about memory. */ - si_meminfo(&si); - /* The values below were suggested by Alexey Kuznetsov - * <kuznet@ms2.inr.ac.ru>. I don't have any opinion about the values - * myself. --SAW - */ - if (si.totalram <= (32768*1024)/PAGE_SIZE) - inet_peer_threshold >>= 1; /* max pool size about 1MB on IA32 */ - if (si.totalram <= (16384*1024)/PAGE_SIZE) - inet_peer_threshold >>= 1; /* about 512KB */ - if (si.totalram <= (8192*1024)/PAGE_SIZE) - inet_peer_threshold >>= 2; /* about 128KB */ + /* 1% of physical memory */ + nr_entries = div64_ul((u64)totalram_pages() << PAGE_SHIFT, + 100 * L1_CACHE_ALIGN(sizeof(struct inet_peer))); + + inet_peer_threshold = clamp_val(nr_entries, 4096, 65536 + 128); peer_cachep = kmem_cache_create("inet_peer_cache", sizeof(struct inet_peer), diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 76a420c76f16..f6cc26de5ed3 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -502,8 +502,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, if (!skb_is_gso(skb) && (inner_iph->frag_off & htons(IP_DF)) && mtu < pkt_size) { - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -E2BIG; } } @@ -527,7 +526,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && mtu < pkt_size) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -E2BIG; } } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index abc171e79d3e..eb207089ece0 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -238,13 +238,13 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); } else { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } dst_release(dst); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index f1c6cbdb9e43..743777bce179 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1399,7 +1399,7 @@ out: /* rtnl */ /* remove all nexthops tied to a device being deleted */ -static void nexthop_flush_dev(struct net_device *dev) +static void nexthop_flush_dev(struct net_device *dev, unsigned long event) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); @@ -1411,6 +1411,10 @@ static void nexthop_flush_dev(struct net_device *dev) if (nhi->fib_nhc.nhc_dev != dev) continue; + if (nhi->reject_nh && + (event == NETDEV_DOWN || event == NETDEV_CHANGE)) + continue; + remove_nexthop(net, nhi->nh_parent, NULL); } } @@ -2189,11 +2193,11 @@ static int nh_netdev_event(struct notifier_block *this, switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: - nexthop_flush_dev(dev); + nexthop_flush_dev(dev, event); break; case NETDEV_CHANGE: if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) - nexthop_flush_dev(dev); + nexthop_flush_dev(dev, event); break; case NETDEV_CHANGEMTU: info_ext = ptr; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a3422e42784e..de7cc8445ac0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3469,16 +3469,23 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_QUEUE_SEQ: - if (sk->sk_state != TCP_CLOSE) + if (sk->sk_state != TCP_CLOSE) { err = -EPERM; - else if (tp->repair_queue == TCP_SEND_QUEUE) - WRITE_ONCE(tp->write_seq, val); - else if (tp->repair_queue == TCP_RECV_QUEUE) { - WRITE_ONCE(tp->rcv_nxt, val); - WRITE_ONCE(tp->copied_seq, val); - } - else + } else if (tp->repair_queue == TCP_SEND_QUEUE) { + if (!tcp_rtx_queue_empty(sk)) + err = -EPERM; + else + WRITE_ONCE(tp->write_seq, val); + } else if (tp->repair_queue == TCP_RECV_QUEUE) { + if (tp->rcv_nxt != tp->copied_seq) { + err = -EPERM; + } else { + WRITE_ONCE(tp->rcv_nxt, val); + WRITE_ONCE(tp->copied_seq, val); + } + } else { err = -EINVAL; + } break; case TCP_REPAIR_OPTIONS: @@ -4143,7 +4150,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - if (len < offsetofend(struct tcp_zerocopy_receive, length)) + if (len < 0 || + len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; if (unlikely(len > sizeof(zc))) { err = check_zeroed_user(optval + sizeof(zc), diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index b76c48efd37e..c5b4b586570f 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -526,7 +526,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, } if (!sk || NAPI_GRO_CB(skb)->encap_mark || - (skb->ip_summed != CHECKSUM_PARTIAL && + (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid) || !udp_sk(sk)->gro_receive) diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 51184a70ac7e..1578ed9e97d8 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -83,6 +83,9 @@ struct calipso_map_cache_entry { static struct calipso_map_cache_bkt *calipso_cache; +static void calipso_cache_invalidate(void); +static void calipso_doi_putdef(struct calipso_doi *doi_def); + /* Label Mapping Cache Functions */ @@ -444,15 +447,10 @@ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!refcount_dec_and_test(&doi_def->refcount)) { - spin_unlock(&calipso_doi_list_lock); - ret_val = -EBUSY; - goto doi_remove_return; - } list_del_rcu(&doi_def->list); spin_unlock(&calipso_doi_list_lock); - call_rcu(&doi_def->rcu, calipso_doi_free_rcu); + calipso_doi_putdef(doi_def); ret_val = 0; doi_remove_return: @@ -508,10 +506,8 @@ static void calipso_doi_putdef(struct calipso_doi *doi_def) if (!refcount_dec_and_test(&doi_def->refcount)) return; - spin_lock(&calipso_doi_list_lock); - list_del_rcu(&doi_def->list); - spin_unlock(&calipso_doi_list_lock); + calipso_cache_invalidate(); call_rcu(&doi_def->rcu, calipso_doi_free_rcu); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c3bc89b6b1a1..1baf43aacb2e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -678,8 +678,8 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { - icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2); + icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); return -1; } *encap_limit = tel->encap_limit - 1; @@ -805,8 +805,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); return -1; } @@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) &mtu, skb->protocol); if (err != 0) { if (err == -EMSGSIZE) - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -1; } @@ -1063,10 +1063,10 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) { if (skb->protocol == htons(ETH_P_IP)) - icmp_send(skb, ICMP_DEST_UNREACH, - ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); else - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } goto tx_err; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a7950baa05e5..3fa0eca5a06f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1332,8 +1332,8 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, tel = (void *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { - icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2); + icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); return -1; } encap_limit = tel->encap_limit - 1; @@ -1385,11 +1385,11 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, if (err == -EMSGSIZE) switch (protocol) { case IPPROTO_IPIP: - icmp_send(skb, ICMP_DEST_UNREACH, - ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); break; case IPPROTO_IPV6: - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); break; default: break; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 0225fd694192..f10e7a72ea62 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -521,10 +521,10 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); } err = -EMSGSIZE; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 93636867aee2..63ccd9f2dccc 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -987,7 +987,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 7be5103ff2a8..203890e378cb 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -649,9 +649,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { - pr_warn_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", - tunnel->name, tunnel->tunnel_id, - session->session_id); + pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", + tunnel->name, tunnel->tunnel_id, + session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } @@ -702,8 +702,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { - pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -718,8 +718,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { - pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -809,9 +809,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - pr_warn_ratelimited("%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); - goto error; + pr_debug_ratelimited("%s: recv short packet (len=%d)\n", + tunnel->name, skb->len); + goto invalid; } /* Point to L2TP header */ @@ -824,9 +824,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Check protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; if (version != tunnel->version) { - pr_warn_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); - goto error; + pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", + tunnel->name, version, tunnel->version); + goto invalid; } /* Get length of L2TP packet */ @@ -834,7 +834,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* If type is control packet, it is handled by userspace. */ if (hdrflags & L2TP_HDRFLAG_T) - goto error; + goto pass; /* Skip flags */ ptr += 2; @@ -863,21 +863,24 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ - pr_warn_ratelimited("%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); - goto error; + pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n", + tunnel->name, tunnel_id, session_id); + goto pass; } if (tunnel->version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) - goto error; + goto invalid; l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); return 0; -error: +invalid: + atomic_long_inc(&tunnel->stats.rx_invalid); + +pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index cb21d906343e..98ea98eb9567 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -39,6 +39,7 @@ struct l2tp_stats { atomic_long_t rx_oos_packets; atomic_long_t rx_errors; atomic_long_t rx_cookie_discards; + atomic_long_t rx_invalid; }; struct l2tp_tunnel; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 83956c9ee1fc..96eb91be9238 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -428,6 +428,9 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla L2TP_ATTR_STATS_PAD) || nla_put_u64_64bit(skb, L2TP_ATTR_RX_ERRORS, atomic_long_read(&tunnel->stats.rx_errors), + L2TP_ATTR_STATS_PAD) || + nla_put_u64_64bit(skb, L2TP_ATTR_RX_INVALID, + atomic_long_read(&tunnel->stats.rx_invalid), L2TP_ATTR_STATS_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); @@ -771,6 +774,9 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl L2TP_ATTR_STATS_PAD) || nla_put_u64_64bit(skb, L2TP_ATTR_RX_ERRORS, atomic_long_read(&session->stats.rx_errors), + L2TP_ATTR_STATS_PAD) || + nla_put_u64_64bit(skb, L2TP_ATTR_RX_INVALID, + atomic_long_read(&session->stats.rx_invalid), L2TP_ATTR_STATS_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index b1690149b6fa..1482259de9b5 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -14,6 +14,7 @@ #include <linux/netdev_features.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <net/mpls.h> static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -27,6 +28,8 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, skb_reset_network_header(skb); mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); + if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN)) + goto out; if (unlikely(!pskb_may_pull(skb, mpls_hlen))) goto out; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c5d5e68940ea..76958570ae7f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1061,6 +1061,12 @@ out: } } +static void __mptcp_clean_una_wakeup(struct sock *sk) +{ + __mptcp_clean_una(sk); + mptcp_write_space(sk); +} + static void mptcp_enter_memory_pressure(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1189,6 +1195,7 @@ static bool mptcp_tx_cache_refill(struct sock *sk, int size, */ while (skbs->qlen > 1) { skb = __skb_dequeue_tail(skbs); + *total_ts -= skb->truesize; __kfree_skb(skb); } return skbs->qlen > 0; @@ -1444,7 +1451,7 @@ static void mptcp_push_release(struct sock *sk, struct sock *ssk, release_sock(ssk); } -static void mptcp_push_pending(struct sock *sk, unsigned int flags) +static void __mptcp_push_pending(struct sock *sk, unsigned int flags) { struct sock *prev_ssk = NULL, *ssk = NULL; struct mptcp_sock *msk = mptcp_sk(sk); @@ -1696,14 +1703,14 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) wait_for_memory: mptcp_set_nospace(sk); - mptcp_push_pending(sk, msg->msg_flags); + __mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) goto out; } if (copied) - mptcp_push_pending(sk, msg->msg_flags); + __mptcp_push_pending(sk, msg->msg_flags); out: release_sock(sk); @@ -2115,6 +2122,14 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) return backup; } +static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) +{ + if (msk->subflow) { + iput(SOCK_INODE(msk->subflow)); + msk->subflow = NULL; + } +} + /* subflow sockets can be either outgoing (connect) or incoming * (accept). * @@ -2126,6 +2141,8 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { + struct mptcp_sock *msk = mptcp_sk(sk); + list_del(&subflow->node); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); @@ -2154,6 +2171,18 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, release_sock(ssk); sock_put(ssk); + + if (ssk == msk->last_snd) + msk->last_snd = NULL; + + if (ssk == msk->ack_hint) + msk->ack_hint = NULL; + + if (ssk == msk->first) + msk->first = NULL; + + if (msk->subflow && ssk == msk->subflow->sk) + mptcp_dispose_initial_subflow(msk); } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, @@ -2238,14 +2267,58 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) mptcp_close_wake_up(sk); } -static void mptcp_worker(struct work_struct *work) +static void __mptcp_retrans(struct sock *sk) { - struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); - struct sock *ssk, *sk = &msk->sk.icsk_inet.sk; + struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = {}; struct mptcp_data_frag *dfrag; size_t copied = 0; - int state, ret; + struct sock *ssk; + int ret; + + __mptcp_clean_una_wakeup(sk); + dfrag = mptcp_rtx_head(sk); + if (!dfrag) + return; + + ssk = mptcp_subflow_get_retrans(msk); + if (!ssk) + goto reset_timer; + + lock_sock(ssk); + + /* limit retransmission to the bytes already sent on some subflows */ + info.sent = 0; + info.limit = dfrag->already_sent; + while (info.sent < dfrag->already_sent) { + if (!mptcp_alloc_tx_skb(sk, ssk)) + break; + + ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); + if (ret <= 0) + break; + + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS); + copied += ret; + info.sent += ret; + } + if (copied) + tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, + info.size_goal); + + mptcp_set_timeout(sk, ssk); + release_sock(ssk); + +reset_timer: + if (!mptcp_timer_pending(sk)) + mptcp_reset_timer(sk); +} + +static void mptcp_worker(struct work_struct *work) +{ + struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); + struct sock *sk = &msk->sk.icsk_inet.sk; + int state; lock_sock(sk); state = sk->sk_state; @@ -2280,45 +2353,8 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) __mptcp_close_subflow(msk); - if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) - goto unlock; - - __mptcp_clean_una(sk); - dfrag = mptcp_rtx_head(sk); - if (!dfrag) - goto unlock; - - ssk = mptcp_subflow_get_retrans(msk); - if (!ssk) - goto reset_unlock; - - lock_sock(ssk); - - /* limit retransmission to the bytes already sent on some subflows */ - info.sent = 0; - info.limit = dfrag->already_sent; - while (info.sent < dfrag->already_sent) { - if (!mptcp_alloc_tx_skb(sk, ssk)) - break; - - ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); - if (ret <= 0) - break; - - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS); - copied += ret; - info.sent += ret; - } - if (copied) - tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, - info.size_goal); - - mptcp_set_timeout(sk, ssk); - release_sock(ssk); - -reset_unlock: - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) + __mptcp_retrans(sk); unlock: release_sock(sk); @@ -2523,12 +2559,6 @@ static void __mptcp_destroy_sock(struct sock *sk) might_sleep(); - /* dispose the ancillatory tcp socket, if any */ - if (msk->subflow) { - iput(SOCK_INODE(msk->subflow)); - msk->subflow = NULL; - } - /* be sure to always acquire the join list lock, to sync vs * mptcp_finish_join(). */ @@ -2553,6 +2583,7 @@ static void __mptcp_destroy_sock(struct sock *sk) sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); + mptcp_dispose_initial_subflow(msk); sock_put(sk); } @@ -2934,13 +2965,14 @@ static void mptcp_release_cb(struct sock *sk) { unsigned long flags, nflags; - /* push_pending may touch wmem_reserved, do it before the later - * cleanup - */ - if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags)) - __mptcp_clean_una(sk); - if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) { - /* mptcp_push_pending() acquires the subflow socket lock + for (;;) { + flags = 0; + if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) + flags |= MPTCP_PUSH_PENDING; + if (!flags) + break; + + /* the following actions acquire the subflow socket lock * * 1) can't be invoked in atomic scope * 2) must avoid ABBA deadlock with msk socket spinlock: the RX @@ -2949,13 +2981,21 @@ static void mptcp_release_cb(struct sock *sk) */ spin_unlock_bh(&sk->sk_lock.slock); - mptcp_push_pending(sk, 0); + if (flags & MPTCP_PUSH_PENDING) + __mptcp_push_pending(sk, 0); + + cond_resched(); spin_lock_bh(&sk->sk_lock.slock); } + + if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags)) + __mptcp_clean_una_wakeup(sk); if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags)) __mptcp_error_report(sk); - /* clear any wmem reservation and errors */ + /* push_pending may touch wmem_reserved, ensure we do the cleanup + * later + */ __mptcp_update_wmem(sk); __mptcp_update_rmem(sk); @@ -3285,6 +3325,9 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, /* PM/worker can now acquire the first subflow socket * lock without racing with listener queue cleanup, * we can notify it, if needed. + * + * Even if remote has reset the initial subflow by now + * the refcnt is still at least one. */ subflow = mptcp_subflow_ctx(msk->first); list_add(&subflow->node, &msk->conn_list); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 91827d949766..e21a5bc36cf0 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -52,14 +52,15 @@ #define TCPOLEN_MPTCP_DSS_MAP64 14 #define TCPOLEN_MPTCP_DSS_CHECKSUM 2 #define TCPOLEN_MPTCP_ADD_ADDR 16 -#define TCPOLEN_MPTCP_ADD_ADDR_PORT 20 +#define TCPOLEN_MPTCP_ADD_ADDR_PORT 18 #define TCPOLEN_MPTCP_ADD_ADDR_BASE 8 -#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT 12 +#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT 10 #define TCPOLEN_MPTCP_ADD_ADDR6 28 -#define TCPOLEN_MPTCP_ADD_ADDR6_PORT 32 +#define TCPOLEN_MPTCP_ADD_ADDR6_PORT 30 #define TCPOLEN_MPTCP_ADD_ADDR6_BASE 20 -#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 24 -#define TCPOLEN_MPTCP_PORT_LEN 4 +#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 22 +#define TCPOLEN_MPTCP_PORT_LEN 2 +#define TCPOLEN_MPTCP_PORT_ALIGN 2 #define TCPOLEN_MPTCP_RM_ADDR_BASE 4 #define TCPOLEN_MPTCP_PRIO 3 #define TCPOLEN_MPTCP_PRIO_ALIGN 4 @@ -701,8 +702,9 @@ static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port) len = TCPOLEN_MPTCP_ADD_ADDR6_BASE; if (!echo) len += MPTCPOPT_THMAC_LEN; + /* account for 2 trailing 'nop' options */ if (port) - len += TCPOLEN_MPTCP_PORT_LEN; + len += TCPOLEN_MPTCP_PORT_LEN + TCPOLEN_MPTCP_PORT_ALIGN; return len; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e1fbcab257e6..3d47d670e665 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -687,11 +687,6 @@ create_child: /* move the msk reference ownership to the subflow */ subflow_req->msk = NULL; ctx->conn = (struct sock *)owner; - if (!mptcp_finish_join(child)) - goto dispose_child; - - SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); - tcp_rsk(req)->drop_req = true; if (subflow_use_different_sport(owner, sk)) { pr_debug("ack inet_sport=%d %d", @@ -699,10 +694,16 @@ create_child: ntohs(inet_sk((struct sock *)owner)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(owner, sk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); - goto out; + goto dispose_child; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX); } + + if (!mptcp_finish_join(child)) + goto dispose_child; + + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); + tcp_rsk(req)->drop_req = true; } } @@ -1297,6 +1298,7 @@ failed_unlink: spin_lock_bh(&msk->join_list_lock); list_del(&subflow->node); spin_unlock_bh(&msk->join_list_lock); + sock_put(mptcp_subflow_tcp_sock(subflow)); failed: subflow->disposable = 1; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 118f415928ae..b055187235f8 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -219,7 +219,7 @@ nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) return NULL; pr_info("nf_conntrack: default automatic helper assignment " "has been turned off for security reasons and CT-based " - " firewall rule not found. Use the iptables CT target " + "firewall rule not found. Use the iptables CT target " "to attach helpers instead.\n"); net->ct.auto_assign_helper_warned = 1; return NULL; @@ -228,7 +228,6 @@ nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) return __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); } - int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, gfp_t flags) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1d7e1c595546..ec23330687a5 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -982,8 +982,10 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "invalid packet ignored in " - "state %s ", tcp_conntrack_names[old_state]); + nf_ct_l4proto_log_invalid(skb, ct, + "packet (index %d) in dir %d ignored, state %s", + index, dir, + tcp_conntrack_names[old_state]); return NF_ACCEPT; case TCP_CONNTRACK_MAX: /* Special case for SYN proxy: when the SYN to the server or diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index e87b6bd6b3cd..4731d21fc3ad 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -646,8 +646,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, } static unsigned int -nf_nat_ipv4_in(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) +nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; @@ -660,6 +660,23 @@ nf_nat_ipv4_in(void *priv, struct sk_buff *skb, } static unsigned int +nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + __be32 saddr = ip_hdr(skb)->saddr; + struct sock *sk = skb->sk; + unsigned int ret; + + ret = nf_nat_ipv4_fn(priv, skb, state); + + if (ret == NF_ACCEPT && sk && saddr != ip_hdr(skb)->saddr && + !inet_sk_transparent(sk)) + skb_orphan(skb); /* TCP edemux obtained wrong socket */ + + return ret; +} + +static unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -736,7 +753,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, static const struct nf_hook_ops nf_nat_ipv4_ops[] = { /* Before packet filtering, change destination */ { - .hook = nf_nat_ipv4_in, + .hook = nf_nat_ipv4_pre_routing, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, @@ -757,7 +774,7 @@ static const struct nf_hook_ops nf_nat_ipv4_ops[] = { }, /* After packet filtering, change source */ { - .hook = nf_nat_ipv4_fn, + .hook = nf_nat_ipv4_local_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c1eb5cdb3033..224c8e537cb3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -916,6 +916,12 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags == ctx->table->flags) return 0; + if ((nft_table_has_owner(ctx->table) && + !(flags & NFT_TABLE_F_OWNER)) || + (!nft_table_has_owner(ctx->table) && + flags & NFT_TABLE_F_OWNER)) + return -EOPNOTSUPP; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) @@ -9022,8 +9028,12 @@ static void __nft_release_hooks(struct net *net) { struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) + list_for_each_entry(table, &net->nft.tables, list) { + if (nft_table_has_owner(table)) + continue; + __nft_release_hook(net, table); + } } static void __nft_release_table(struct net *net, struct nft_table *table) @@ -9073,13 +9083,12 @@ static void __nft_release_table(struct net *net, struct nft_table *table) nf_tables_table_destroy(&ctx); } -static void __nft_release_tables(struct net *net, u32 nlpid) +static void __nft_release_tables(struct net *net) { struct nft_table *table, *nt; list_for_each_entry_safe(table, nt, &net->nft.tables, list) { - if (nft_table_has_owner(table) && - nlpid != table->nlpid) + if (nft_table_has_owner(table)) continue; __nft_release_table(net, table); @@ -9145,7 +9154,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); - __nft_release_tables(net, 0); + __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); WARN_ON_ONCE(!list_empty(&net->nft.module_list)); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index acce622582e3..bce6ca203d46 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -330,6 +330,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) const struct xt_match *m; int have_rev = 0; + mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision > *bestp) @@ -338,6 +339,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) have_rev = 1; } } + mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return match_revfn(NFPROTO_UNSPEC, name, revision, bestp); @@ -350,6 +352,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) const struct xt_target *t; int have_rev = 0; + mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision > *bestp) @@ -358,6 +361,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) have_rev = 1; } } + mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return target_revfn(NFPROTO_UNSPEC, name, revision, bestp); @@ -371,12 +375,10 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target, { int have_rev, best = -1; - mutex_lock(&xt[af].mutex); if (target == 1) have_rev = target_revfn(af, name, revision, &best); else have_rev = match_revfn(af, name, revision, &best); - mutex_unlock(&xt[af].mutex); /* Nothing at all? Return 0 to try loading module. */ if (best == -1) { diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 726dda95934c..4f50a64315cf 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -575,6 +575,7 @@ list_start: break; } + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); genlmsg_end(ans_skb, data); @@ -583,12 +584,14 @@ list_start: list_retry: /* XXX - this limit is a guesstimate */ if (nlsze_mult < 4) { + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); kfree_skb(ans_skb); nlsze_mult *= 2; goto list_start; } list_failure_lock: + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); list_failure: kfree_skb(ans_skb); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index b34358282f37..edb6ac17ceca 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -439,7 +439,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (len == 0 || len & 3) return -EINVAL; - skb = netdev_alloc_skb(NULL, len); + skb = __netdev_alloc_skb(NULL, len, GFP_ATOMIC | __GFP_NOWARN); if (!skb) return -ENOMEM; @@ -958,8 +958,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) plen = (len + 3) & ~3; skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE, msg->msg_flags & MSG_DONTWAIT, &rc); - if (!skb) + if (!skb) { + rc = -ENOMEM; goto out_node; + } skb_reserve(skb, QRTR_HDR_MAX_SIZE); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e2e4353db8a7..f87d07736a14 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -2168,7 +2168,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, - int *t_p, int s_t) + int *t_p, int s_t, bool recur) { struct Qdisc *q; int b; @@ -2179,7 +2179,7 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0) return -1; - if (!qdisc_dev(root)) + if (!qdisc_dev(root) || !recur) return 0; if (tcm->tcm_parent) { @@ -2214,13 +2214,13 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; t = 0; - if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, - &t, s_t) < 0) + &t, s_t, false) < 0) goto done; done: diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index a9c6af5795d8..5ba456727f63 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -75,7 +75,7 @@ int sctp_tsnmap_check(const struct sctp_tsnmap *map, __u32 tsn) return 1; /* Verify that we can hold this TSN and that it will not - * overlfow our map + * overflow our map */ if (!TSN_lt(tsn, map->base_tsn + SCTP_TSN_MAP_SIZE)) return -1; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index bd4678db9d76..6dff64374bfe 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1825,11 +1825,14 @@ static int svcauth_gss_release(struct svc_rqst *rqstp) { struct gss_svc_data *gsd = (struct gss_svc_data *)rqstp->rq_auth_data; - struct rpc_gss_wire_cred *gc = &gsd->clcred; + struct rpc_gss_wire_cred *gc; struct xdr_buf *resbuf = &rqstp->rq_res; int stat = -EINVAL; struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); + if (!gsd) + goto out; + gc = &gsd->clcred; if (gc->gc_proc != RPC_GSS_PROC_DATA) goto out; /* Release can be called twice, but we only wrap once. */ @@ -1870,10 +1873,10 @@ out_err: if (rqstp->rq_cred.cr_group_info) put_group_info(rqstp->rq_cred.cr_group_info); rqstp->rq_cred.cr_group_info = NULL; - if (gsd->rsci) + if (gsd && gsd->rsci) { cache_put(&gsd->rsci->h, sn->rsc_cache); - gsd->rsci = NULL; - + gsd->rsci = NULL; + } return stat; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index cf702a5f7fe5..39ed0e0afe6d 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -963,8 +963,11 @@ void rpc_execute(struct rpc_task *task) rpc_set_active(task); rpc_make_runnable(rpciod_workqueue, task); - if (!is_async) + if (!is_async) { + unsigned int pflags = memalloc_nofs_save(); __rpc_execute(task); + memalloc_nofs_restore(pflags); + } } static void rpc_async_schedule(struct work_struct *work) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 61fb8a18552c..d76dc9d95d16 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1413,7 +1413,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) sendit: if (svc_authorise(rqstp)) - goto close; + goto close_xprt; return 1; /* Caller can now send it */ release_dropit: @@ -1425,6 +1425,8 @@ release_dropit: return 0; close: + svc_authorise(rqstp); +close_xprt: if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) svc_close_xprt(rqstp->rq_xprt); dprintk("svc: svc_process close\n"); @@ -1433,7 +1435,7 @@ release_dropit: err_short_len: svc_printk(rqstp, "short len %zd, dropping request\n", argv->iov_len); - goto close; + goto close_xprt; err_bad_rpc: serv->sv_stats->rpcbadfmt++; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index dcc50ae54550..3cdd71a8df1e 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1060,7 +1060,7 @@ static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, st struct svc_xprt *xprt; int ret = 0; - spin_lock(&serv->sv_lock); + spin_lock_bh(&serv->sv_lock); list_for_each_entry(xprt, xprt_list, xpt_list) { if (xprt->xpt_net != net) continue; @@ -1068,7 +1068,7 @@ static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, st set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); } - spin_unlock(&serv->sv_lock); + spin_unlock_bh(&serv->sv_lock); return ret; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 4a1edbb4028e..9150df35fb6f 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -252,9 +252,9 @@ xprt_setup_rdma_bc(struct xprt_create *args) xprt->timeout = &xprt_rdma_bc_timeout; xprt_set_bound(xprt); xprt_set_connected(xprt); - xprt->bind_timeout = RPCRDMA_BIND_TO; - xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO; - xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO; + xprt->bind_timeout = 0; + xprt->reestablish_timeout = 0; + xprt->idle_timeout = 0; xprt->prot = XPRT_TRANSPORT_BC_RDMA; xprt->ops = &xprt_rdma_bc_procs; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 6d28f23ceb35..7d34290e2ff8 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -266,46 +266,33 @@ void svc_rdma_release_rqst(struct svc_rqst *rqstp) svc_rdma_recv_ctxt_put(rdma, ctxt); } -static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma, - unsigned int wanted, bool temp) +static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma, + struct svc_rdma_recv_ctxt *ctxt) { - const struct ib_recv_wr *bad_wr = NULL; - struct svc_rdma_recv_ctxt *ctxt; - struct ib_recv_wr *recv_chain; int ret; - recv_chain = NULL; - while (wanted--) { - ctxt = svc_rdma_recv_ctxt_get(rdma); - if (!ctxt) - break; - - trace_svcrdma_post_recv(ctxt); - ctxt->rc_temp = temp; - ctxt->rc_recv_wr.next = recv_chain; - recv_chain = &ctxt->rc_recv_wr; - rdma->sc_pending_recvs++; - } - if (!recv_chain) - return false; - - ret = ib_post_recv(rdma->sc_qp, recv_chain, &bad_wr); + trace_svcrdma_post_recv(ctxt); + ret = ib_post_recv(rdma->sc_qp, &ctxt->rc_recv_wr, NULL); if (ret) goto err_post; - return true; + return 0; err_post: - while (bad_wr) { - ctxt = container_of(bad_wr, struct svc_rdma_recv_ctxt, - rc_recv_wr); - bad_wr = bad_wr->next; - svc_rdma_recv_ctxt_put(rdma, ctxt); - } - trace_svcrdma_rq_post_err(rdma, ret); - /* Since we're destroying the xprt, no need to reset - * sc_pending_recvs. */ - return false; + svc_rdma_recv_ctxt_put(rdma, ctxt); + return ret; +} + +static int svc_rdma_post_recv(struct svcxprt_rdma *rdma) +{ + struct svc_rdma_recv_ctxt *ctxt; + + if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags)) + return 0; + ctxt = svc_rdma_recv_ctxt_get(rdma); + if (!ctxt) + return -ENOMEM; + return __svc_rdma_post_recv(rdma, ctxt); } /** @@ -316,7 +303,20 @@ err_post: */ bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma) { - return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests, true); + struct svc_rdma_recv_ctxt *ctxt; + unsigned int i; + int ret; + + for (i = 0; i < rdma->sc_max_requests; i++) { + ctxt = svc_rdma_recv_ctxt_get(rdma); + if (!ctxt) + return false; + ctxt->rc_temp = true; + ret = __svc_rdma_post_recv(rdma, ctxt); + if (ret) + return false; + } + return true; } /** @@ -324,6 +324,8 @@ bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma) * @cq: Completion Queue context * @wc: Work Completion object * + * NB: The svc_xprt/svcxprt_rdma is pinned whenever it's possible that + * the Receive completion handler could be running. */ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) { @@ -331,8 +333,6 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_recv_ctxt *ctxt; - rdma->sc_pending_recvs--; - /* WARNING: Only wc->wr_cqe and wc->status are reliable */ ctxt = container_of(cqe, struct svc_rdma_recv_ctxt, rc_cqe); @@ -340,6 +340,9 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS) goto flushed; + if (svc_rdma_post_recv(rdma)) + goto post_err; + /* All wc fields are now known to be valid */ ctxt->rc_byte_len = wc->byte_len; @@ -350,18 +353,11 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) spin_unlock(&rdma->sc_rq_dto_lock); if (!test_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags)) svc_xprt_enqueue(&rdma->sc_xprt); - - if (!test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags) && - rdma->sc_pending_recvs < rdma->sc_max_requests) - if (!svc_rdma_refresh_recvs(rdma, RPCRDMA_MAX_RECV_BATCH, - false)) - goto post_err; - return; flushed: - svc_rdma_recv_ctxt_put(rdma, ctxt); post_err: + svc_rdma_recv_ctxt_put(rdma, ctxt); set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); svc_xprt_enqueue(&rdma->sc_xprt); } |